diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/inet_hashtables.c | 184 | ||||
-rw-r--r-- | net/ipv4/inet_timewait_sock.c | 27 | ||||
-rw-r--r-- | net/ipv4/ip_gre.c | 172 | ||||
-rw-r--r-- | net/ipv4/route.c | 2 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 3 | ||||
-rw-r--r-- | net/ipv4/tcp_fastopen.c | 30 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 31 | ||||
-rw-r--r-- | net/ipv4/tcp_metrics.c | 5 | ||||
-rw-r--r-- | net/ipv4/tcp_minisocks.c | 7 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 9 | ||||
-rw-r--r-- | net/ipv4/tcp_timer.c | 17 | ||||
-rw-r--r-- | net/ipv4/udp.c | 44 | ||||
-rw-r--r-- | net/ipv4/xfrm4_mode_tunnel.c | 2 |
13 files changed, 343 insertions, 190 deletions
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index e7d15fb0d94d..f6f58108b4c5 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -19,6 +19,7 @@ #include <linux/slab.h> #include <linux/wait.h> #include <linux/vmalloc.h> +#include <linux/bootmem.h> #include <net/addrconf.h> #include <net/inet_connection_sock.h> @@ -168,6 +169,60 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child) } EXPORT_SYMBOL_GPL(__inet_inherit_port); +static struct inet_listen_hashbucket * +inet_lhash2_bucket_sk(struct inet_hashinfo *h, struct sock *sk) +{ + u32 hash; + +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) + hash = ipv6_portaddr_hash(sock_net(sk), + &sk->sk_v6_rcv_saddr, + inet_sk(sk)->inet_num); + else +#endif + hash = ipv4_portaddr_hash(sock_net(sk), + inet_sk(sk)->inet_rcv_saddr, + inet_sk(sk)->inet_num); + return inet_lhash2_bucket(h, hash); +} + +static void inet_hash2(struct inet_hashinfo *h, struct sock *sk) +{ + struct inet_listen_hashbucket *ilb2; + + if (!h->lhash2) + return; + + ilb2 = inet_lhash2_bucket_sk(h, sk); + + spin_lock(&ilb2->lock); + if (sk->sk_reuseport && sk->sk_family == AF_INET6) + hlist_add_tail_rcu(&inet_csk(sk)->icsk_listen_portaddr_node, + &ilb2->head); + else + hlist_add_head_rcu(&inet_csk(sk)->icsk_listen_portaddr_node, + &ilb2->head); + ilb2->count++; + spin_unlock(&ilb2->lock); +} + +static void inet_unhash2(struct inet_hashinfo *h, struct sock *sk) +{ + struct inet_listen_hashbucket *ilb2; + + if (!h->lhash2 || + WARN_ON_ONCE(hlist_unhashed(&inet_csk(sk)->icsk_listen_portaddr_node))) + return; + + ilb2 = inet_lhash2_bucket_sk(h, sk); + + spin_lock(&ilb2->lock); + hlist_del_init_rcu(&inet_csk(sk)->icsk_listen_portaddr_node); + ilb2->count--; + spin_unlock(&ilb2->lock); +} + static inline int compute_score(struct sock *sk, struct net *net, const unsigned short hnum, const __be32 daddr, const int dif, const int sdif, bool exact_dif) @@ -207,6 +262,40 @@ static inline int compute_score(struct sock *sk, struct net *net, */ /* called with rcu_read_lock() : No refcount taken on the socket */ +static struct sock *inet_lhash2_lookup(struct net *net, + struct inet_listen_hashbucket *ilb2, + struct sk_buff *skb, int doff, + const __be32 saddr, __be16 sport, + const __be32 daddr, const unsigned short hnum, + const int dif, const int sdif) +{ + bool exact_dif = inet_exact_dif_match(net, skb); + struct inet_connection_sock *icsk; + struct sock *sk, *result = NULL; + int score, hiscore = 0; + u32 phash = 0; + + inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) { + sk = (struct sock *)icsk; + score = compute_score(sk, net, hnum, daddr, + dif, sdif, exact_dif); + if (score > hiscore) { + if (sk->sk_reuseport) { + phash = inet_ehashfn(net, daddr, hnum, + saddr, sport); + result = reuseport_select_sock(sk, phash, + skb, doff); + if (result) + return result; + } + result = sk; + hiscore = score; + } + } + + return result; +} + struct sock *__inet_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, @@ -216,32 +305,57 @@ struct sock *__inet_lookup_listener(struct net *net, { unsigned int hash = inet_lhashfn(net, hnum); struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash]; - int score, hiscore = 0, matches = 0, reuseport = 0; bool exact_dif = inet_exact_dif_match(net, skb); + struct inet_listen_hashbucket *ilb2; struct sock *sk, *result = NULL; + int score, hiscore = 0; + unsigned int hash2; u32 phash = 0; + if (ilb->count <= 10 || !hashinfo->lhash2) + goto port_lookup; + + /* Too many sk in the ilb bucket (which is hashed by port alone). + * Try lhash2 (which is hashed by port and addr) instead. + */ + + hash2 = ipv4_portaddr_hash(net, daddr, hnum); + ilb2 = inet_lhash2_bucket(hashinfo, hash2); + if (ilb2->count > ilb->count) + goto port_lookup; + + result = inet_lhash2_lookup(net, ilb2, skb, doff, + saddr, sport, daddr, hnum, + dif, sdif); + if (result) + return result; + + /* Lookup lhash2 with INADDR_ANY */ + + hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum); + ilb2 = inet_lhash2_bucket(hashinfo, hash2); + if (ilb2->count > ilb->count) + goto port_lookup; + + return inet_lhash2_lookup(net, ilb2, skb, doff, + saddr, sport, daddr, hnum, + dif, sdif); + +port_lookup: sk_for_each_rcu(sk, &ilb->head) { score = compute_score(sk, net, hnum, daddr, dif, sdif, exact_dif); if (score > hiscore) { - reuseport = sk->sk_reuseport; - if (reuseport) { + if (sk->sk_reuseport) { phash = inet_ehashfn(net, daddr, hnum, saddr, sport); result = reuseport_select_sock(sk, phash, skb, doff); if (result) return result; - matches = 1; } result = sk; hiscore = score; - } else if (score == hiscore && reuseport) { - matches++; - if (reciprocal_scale(phash, matches) == 0) - result = sk; - phash = next_pseudo_random32(phash); } } return result; @@ -483,6 +597,8 @@ int __inet_hash(struct sock *sk, struct sock *osk) hlist_add_tail_rcu(&sk->sk_node, &ilb->head); else hlist_add_head_rcu(&sk->sk_node, &ilb->head); + inet_hash2(hashinfo, sk); + ilb->count++; sock_set_flag(sk, SOCK_RCU_FREE); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); unlock: @@ -509,28 +625,35 @@ EXPORT_SYMBOL_GPL(inet_hash); void inet_unhash(struct sock *sk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; + struct inet_listen_hashbucket *ilb; spinlock_t *lock; bool listener = false; - int done; if (sk_unhashed(sk)) return; if (sk->sk_state == TCP_LISTEN) { - lock = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)].lock; + ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; + lock = &ilb->lock; listener = true; } else { lock = inet_ehash_lockp(hashinfo, sk->sk_hash); } spin_lock_bh(lock); + if (sk_unhashed(sk)) + goto unlock; + if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_detach_sock(sk); - if (listener) - done = __sk_del_node_init(sk); - else - done = __sk_nulls_del_node_init_rcu(sk); - if (done) - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + if (listener) { + inet_unhash2(hashinfo, sk); + __sk_del_node_init(sk); + ilb->count--; + } else { + __sk_nulls_del_node_init_rcu(sk); + } + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); +unlock: spin_unlock_bh(lock); } EXPORT_SYMBOL_GPL(inet_unhash); @@ -665,10 +788,37 @@ void inet_hashinfo_init(struct inet_hashinfo *h) for (i = 0; i < INET_LHTABLE_SIZE; i++) { spin_lock_init(&h->listening_hash[i].lock); INIT_HLIST_HEAD(&h->listening_hash[i].head); + h->listening_hash[i].count = 0; } + + h->lhash2 = NULL; } EXPORT_SYMBOL_GPL(inet_hashinfo_init); +void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, + unsigned long numentries, int scale, + unsigned long low_limit, + unsigned long high_limit) +{ + unsigned int i; + + h->lhash2 = alloc_large_system_hash(name, + sizeof(*h->lhash2), + numentries, + scale, + 0, + NULL, + &h->lhash2_mask, + low_limit, + high_limit); + + for (i = 0; i <= h->lhash2_mask; i++) { + spin_lock_init(&h->lhash2[i].lock); + INIT_HLIST_HEAD(&h->lhash2[i].head); + h->lhash2[i].count = 0; + } +} + int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo) { unsigned int locksz = sizeof(spinlock_t); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index b563e0c46bac..277ff69a312d 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -97,7 +97,7 @@ static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw, * Essentially we whip up a timewait bucket, copy the relevant info into it * from the SK, and mess with hash chains and list linkage. */ -void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, +void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, struct inet_hashinfo *hashinfo) { const struct inet_sock *inet = inet_sk(sk); @@ -119,18 +119,6 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, spin_lock(lock); - /* - * Step 2: Hash TW into tcp ehash chain. - * Notes : - * - tw_refcnt is set to 4 because : - * - We have one reference from bhash chain. - * - We have one reference from ehash chain. - * - We have one reference from timer. - * - One reference for ourself (our caller will release it). - * We can use atomic_set() because prior spin_lock()/spin_unlock() - * committed into memory all tw fields. - */ - refcount_set(&tw->tw_refcnt, 4); inet_twsk_add_node_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ @@ -138,8 +126,19 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); spin_unlock(lock); + + /* tw_refcnt is set to 3 because we have : + * - one reference for bhash chain. + * - one reference for ehash chain. + * - one reference for timer. + * We can use atomic_set() because prior spin_lock()/spin_unlock() + * committed into memory all tw fields. + * Also note that after this point, we lost our implicit reference + * so we are not allowed to use tw anymore. + */ + refcount_set(&tw->tw_refcnt, 3); } -EXPORT_SYMBOL_GPL(__inet_twsk_hashdance); +EXPORT_SYMBOL_GPL(inet_twsk_hashdance); static void tw_timer_handler(struct timer_list *t) { diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 9c1735632c8c..9a80d84fc182 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -114,7 +114,8 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static struct rtnl_link_ops ipgre_link_ops __read_mostly; static int ipgre_tunnel_init(struct net_device *dev); static void erspan_build_header(struct sk_buff *skb, - __be32 id, u32 index, bool truncate); + __be32 id, u32 index, + bool truncate, bool is_ipv4); static unsigned int ipgre_net_id __read_mostly; static unsigned int gre_tap_net_id __read_mostly; @@ -255,34 +256,41 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, { struct net *net = dev_net(skb->dev); struct metadata_dst *tun_dst = NULL; + struct erspan_base_hdr *ershdr; + struct erspan_metadata *pkt_md; struct ip_tunnel_net *itn; struct ip_tunnel *tunnel; - struct erspanhdr *ershdr; const struct iphdr *iph; - __be32 index; + int ver; int len; itn = net_generic(net, erspan_net_id); len = gre_hdr_len + sizeof(*ershdr); + /* Check based hdr len */ if (unlikely(!pskb_may_pull(skb, len))) return PACKET_REJECT; iph = ip_hdr(skb); - ershdr = (struct erspanhdr *)(skb->data + gre_hdr_len); + ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); + ver = (ntohs(ershdr->ver_vlan) & VER_MASK) >> VER_OFFSET; /* The original GRE header does not have key field, * Use ERSPAN 10-bit session ID as key. */ tpi->key = cpu_to_be32(ntohs(ershdr->session_id) & ID_MASK); - index = ershdr->md.index; + pkt_md = (struct erspan_metadata *)(ershdr + 1); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags | TUNNEL_KEY, iph->saddr, iph->daddr, tpi->key); if (tunnel) { + len = gre_hdr_len + erspan_hdr_len(ver); + if (unlikely(!pskb_may_pull(skb, len))) + return -ENOMEM; + if (__iptunnel_pull_header(skb, - gre_hdr_len + sizeof(*ershdr), + len, htons(ETH_P_TEB), false, false) < 0) goto drop; @@ -306,12 +314,27 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, if (!md) return PACKET_REJECT; - md->index = index; + memcpy(md, pkt_md, sizeof(*md)); + md->version = ver; + info = &tun_dst->u.tun_info; info->key.tun_flags |= TUNNEL_ERSPAN_OPT; info->options_len = sizeof(*md); } else { - tunnel->index = ntohl(index); + tunnel->erspan_ver = ver; + if (ver == 1) { + tunnel->index = ntohl(pkt_md->u.index); + } else { + u16 md2_flags; + u16 dir, hwid; + + md2_flags = ntohs(pkt_md->u.md2.flags); + dir = (md2_flags & DIR_MASK) >> DIR_OFFSET; + hwid = (md2_flags & HWID_MASK) >> HWID_OFFSET; + tunnel->dir = dir; + tunnel->hwid = hwid; + } + } skb_reset_mac_header(skb); @@ -405,7 +428,8 @@ static int gre_rcv(struct sk_buff *skb) if (hdr_len < 0) goto drop; - if (unlikely(tpi.proto == htons(ETH_P_ERSPAN))) { + if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) || + tpi.proto == htons(ETH_P_ERSPAN2))) { if (erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; } @@ -560,6 +584,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, bool truncate = false; struct flowi4 fl; int tunnel_hlen; + int version; __be16 df; tun_info = skb_tunnel_info(skb); @@ -568,9 +593,13 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, goto err_free_skb; key = &tun_info->key; + md = ip_tunnel_info_opts(tun_info); + if (!md) + goto err_free_rt; /* ERSPAN has fixed 8 byte GRE header */ - tunnel_hlen = 8 + sizeof(struct erspanhdr); + version = md->version; + tunnel_hlen = 8 + erspan_hdr_len(version); rt = prepare_fb_xmit(skb, dev, &fl, tunnel_hlen); if (!rt) @@ -584,12 +613,23 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, truncate = true; } - md = ip_tunnel_info_opts(tun_info); - if (!md) - goto err_free_rt; + if (version == 1) { + erspan_build_header(skb, tunnel_id_to_key32(key->tun_id), + ntohl(md->u.index), truncate, true); + } else if (version == 2) { + u16 md2_flags; + u8 direction; + u16 hwid; - erspan_build_header(skb, tunnel_id_to_key32(key->tun_id), - ntohl(md->index), truncate); + md2_flags = ntohs(md->u.md2.flags); + direction = (md2_flags & DIR_MASK) >> DIR_OFFSET; + hwid = (md2_flags & HWID_MASK) >> HWID_OFFSET; + + erspan_build_header_v2(skb, tunnel_id_to_key32(key->tun_id), + direction, hwid, truncate, true); + } else { + goto err_free_rt; + } gre_build_header(skb, 8, TUNNEL_SEQ, htons(ETH_P_ERSPAN), 0, htonl(tunnel->o_seqno++)); @@ -668,52 +708,6 @@ free_skb: return NETDEV_TX_OK; } -static inline u8 tos_to_cos(u8 tos) -{ - u8 dscp, cos; - - dscp = tos >> 2; - cos = dscp >> 3; - return cos; -} - -static void erspan_build_header(struct sk_buff *skb, - __be32 id, u32 index, bool truncate) -{ - struct iphdr *iphdr = ip_hdr(skb); - struct ethhdr *eth = eth_hdr(skb); - enum erspan_encap_type enc_type; - struct erspanhdr *ershdr; - struct qtag_prefix { - __be16 eth_type; - __be16 tci; - } *qp; - u16 vlan_tci = 0; - - enc_type = ERSPAN_ENCAP_NOVLAN; - - /* If mirrored packet has vlan tag, extract tci and - * perserve vlan header in the mirrored frame. - */ - if (eth->h_proto == htons(ETH_P_8021Q)) { - qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN); - vlan_tci = ntohs(qp->tci); - enc_type = ERSPAN_ENCAP_INFRAME; - } - - skb_push(skb, sizeof(*ershdr)); - ershdr = (struct erspanhdr *)skb->data; - memset(ershdr, 0, sizeof(*ershdr)); - - ershdr->ver_vlan = htons((vlan_tci & VLAN_MASK) | - (ERSPAN_VERSION << VER_OFFSET)); - ershdr->session_id = htons((u16)(ntohl(id) & ID_MASK) | - ((tos_to_cos(iphdr->tos) << COS_OFFSET) & COS_MASK) | - (enc_type << EN_OFFSET & EN_MASK) | - ((truncate << T_OFFSET) & T_MASK)); - ershdr->md.index = htonl(index & INDEX_MASK); -} - static netdev_tx_t erspan_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -737,7 +731,14 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, } /* Push ERSPAN header */ - erspan_build_header(skb, tunnel->parms.o_key, tunnel->index, truncate); + if (tunnel->erspan_ver == 1) + erspan_build_header(skb, tunnel->parms.o_key, tunnel->index, + truncate, true); + else + erspan_build_header_v2(skb, tunnel->parms.o_key, + tunnel->dir, tunnel->hwid, + truncate, true); + tunnel->parms.o_flags &= ~TUNNEL_KEY; __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_ERSPAN)); return NETDEV_TX_OK; @@ -1209,13 +1210,32 @@ static int ipgre_netlink_parms(struct net_device *dev, if (data[IFLA_GRE_FWMARK]) *fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]); - if (data[IFLA_GRE_ERSPAN_INDEX]) { - t->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); + if (data[IFLA_GRE_ERSPAN_VER]) { + t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); - if (t->index & ~INDEX_MASK) + if (t->erspan_ver != 1 && t->erspan_ver != 2) return -EINVAL; } + if (t->erspan_ver == 1) { + if (data[IFLA_GRE_ERSPAN_INDEX]) { + t->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); + if (t->index & ~INDEX_MASK) + return -EINVAL; + } + } else if (t->erspan_ver == 2) { + if (data[IFLA_GRE_ERSPAN_DIR]) { + t->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]); + if (t->dir & ~(DIR_MASK >> DIR_OFFSET)) + return -EINVAL; + } + if (data[IFLA_GRE_ERSPAN_HWID]) { + t->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]); + if (t->hwid & ~(HWID_MASK >> HWID_OFFSET)) + return -EINVAL; + } + } + return 0; } @@ -1282,7 +1302,7 @@ static int erspan_tunnel_init(struct net_device *dev) tunnel->tun_hlen = 8; tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen + - sizeof(struct erspanhdr); + erspan_hdr_len(tunnel->erspan_ver); t_hlen = tunnel->hlen + sizeof(struct iphdr); dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4; @@ -1412,6 +1432,12 @@ static size_t ipgre_get_size(const struct net_device *dev) nla_total_size(4) + /* IFLA_GRE_ERSPAN_INDEX */ nla_total_size(4) + + /* IFLA_GRE_ERSPAN_VER */ + nla_total_size(1) + + /* IFLA_GRE_ERSPAN_DIR */ + nla_total_size(1) + + /* IFLA_GRE_ERSPAN_HWID */ + nla_total_size(2) + 0; } @@ -1454,9 +1480,18 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; } - if (t->index) + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) + goto nla_put_failure; + + if (t->erspan_ver == 1) { if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) goto nla_put_failure; + } else if (t->erspan_ver == 2) { + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) + goto nla_put_failure; + } return 0; @@ -1492,6 +1527,9 @@ static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_IGNORE_DF] = { .type = NLA_U8 }, [IFLA_GRE_FWMARK] = { .type = NLA_U32 }, [IFLA_GRE_ERSPAN_INDEX] = { .type = NLA_U32 }, + [IFLA_GRE_ERSPAN_VER] = { .type = NLA_U8 }, + [IFLA_GRE_ERSPAN_DIR] = { .type = NLA_U8 }, + [IFLA_GRE_ERSPAN_HWID] = { .type = NLA_U16 }, }; static struct rtnl_link_ops ipgre_link_ops __read_mostly = { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 43b69af242e1..f0ed031f3594 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1106,7 +1106,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) new = true; } - __ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu); + __ip_rt_update_pmtu((struct rtable *) xfrm_dst_path(&rt->dst), &fl4, mtu); if (!dst_check(&rt->dst, 0)) { if (new) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f08eebe60446..c470fec9062f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3578,6 +3578,9 @@ void __init tcp_init(void) percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL); inet_hashinfo_init(&tcp_hashinfo); + inet_hashinfo2_init(&tcp_hashinfo, "tcp_listen_portaddr_hash", + thash_entries, 21, /* one slot per 2 MB*/ + 0, 64 * 1024); tcp_hashinfo.bind_bucket_cachep = kmem_cache_create("tcp_bind_bucket", sizeof(struct inet_bind_bucket), 0, diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 78c192ee03a4..018a48477355 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -379,18 +379,9 @@ fastopen: bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie) { - unsigned long last_syn_loss = 0; const struct dst_entry *dst; - int syn_loss = 0; - tcp_fastopen_cache_get(sk, mss, cookie, &syn_loss, &last_syn_loss); - - /* Recurring FO SYN losses: no cookie or data in SYN */ - if (syn_loss > 1 && - time_before(jiffies, last_syn_loss + (60*HZ << syn_loss))) { - cookie->len = -1; - return false; - } + tcp_fastopen_cache_get(sk, mss, cookie); /* Firewall blackhole issue check */ if (tcp_fastopen_active_should_disable(sk)) { @@ -448,6 +439,8 @@ EXPORT_SYMBOL(tcp_fastopen_defer_connect); * following circumstances: * 1. client side TFO socket receives out of order FIN * 2. client side TFO socket receives out of order RST + * 3. client side TFO socket has timed out three times consecutively during + * or after handshake * We disable active side TFO globally for 1hr at first. Then if it * happens again, we disable it for 2h, then 4h, 8h, ... * And we reset the timeout back to 1hr when we see a successful active @@ -524,3 +517,20 @@ void tcp_fastopen_active_disable_ofo_check(struct sock *sk) dst_release(dst); } } + +void tcp_fastopen_active_detect_blackhole(struct sock *sk, bool expired) +{ + u32 timeouts = inet_csk(sk)->icsk_retransmits; + struct tcp_sock *tp = tcp_sk(sk); + + /* Broken middle-boxes may black-hole Fast Open connection during or + * even after the handshake. Be extremely conservative and pause + * Fast Open globally after hitting the third consecutive timeout or + * exceeding the configured timeout limit. + */ + if ((tp->syn_fastopen || tp->syn_data || tp->syn_data_acked) && + (timeouts == 2 || (timeouts < 2 && expired))) { + tcp_fastopen_active_disable(sk); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); + } +} diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 45f750e85714..4d55c4b338ee 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -578,8 +578,8 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, void tcp_rcv_space_adjust(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + u32 copied; int time; - int copied; tcp_mstamp_refresh(tp); time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time); @@ -602,38 +602,31 @@ void tcp_rcv_space_adjust(struct sock *sk) if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { - int rcvwin, rcvmem, rcvbuf; + int rcvmem, rcvbuf; + u64 rcvwin, grow; /* minimal window to cope with packet losses, assuming * steady state. Add some cushion because of small variations. */ - rcvwin = (copied << 1) + 16 * tp->advmss; + rcvwin = ((u64)copied << 1) + 16 * tp->advmss; - /* If rate increased by 25%, - * assume slow start, rcvwin = 3 * copied - * If rate increased by 50%, - * assume sender can use 2x growth, rcvwin = 4 * copied - */ - if (copied >= - tp->rcvq_space.space + (tp->rcvq_space.space >> 2)) { - if (copied >= - tp->rcvq_space.space + (tp->rcvq_space.space >> 1)) - rcvwin <<= 1; - else - rcvwin += (rcvwin >> 1); - } + /* Accommodate for sender rate increase (eg. slow start) */ + grow = rcvwin * (copied - tp->rcvq_space.space); + do_div(grow, tp->rcvq_space.space); + rcvwin += (grow << 1); rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER); while (tcp_win_from_space(sk, rcvmem) < tp->advmss) rcvmem += 128; - rcvbuf = min(rcvwin / tp->advmss * rcvmem, - sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); + do_div(rcvwin, tp->advmss); + rcvbuf = min_t(u64, rcvwin * rcvmem, + sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); if (rcvbuf > sk->sk_rcvbuf) { sk->sk_rcvbuf = rcvbuf; /* Make the window clamp follow along. */ - tp->window_clamp = rcvwin; + tp->window_clamp = tcp_win_from_space(sk, rcvbuf); } } tp->rcvq_space.space = copied; diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 7097f92d16e5..759e6bc8327b 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -546,8 +546,7 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst) static DEFINE_SEQLOCK(fastopen_seqlock); void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, - struct tcp_fastopen_cookie *cookie, - int *syn_loss, unsigned long *last_syn_loss) + struct tcp_fastopen_cookie *cookie) { struct tcp_metrics_block *tm; @@ -564,8 +563,6 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, *cookie = tfom->cookie; if (cookie->len <= 0 && tfom->try_exp == 1) cookie->exp = true; - *syn_loss = tfom->syn_loss; - *last_syn_loss = *syn_loss ? tfom->last_syn_loss : 0; } while (read_seqretry(&fastopen_seqlock, seq)); } rcu_read_unlock(); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index b079b619b60c..a8384b0c11f8 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -316,9 +316,10 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) */ local_bh_disable(); inet_twsk_schedule(tw, timeo); - /* Linkage updates. */ - __inet_twsk_hashdance(tw, sk, &tcp_hashinfo); - inet_twsk_put(tw); + /* Linkage updates. + * Note that access to tw after this point is illegal. + */ + inet_twsk_hashdance(tw, sk, &tcp_hashinfo); local_bh_enable(); } else { /* Sorry, if we're out of memory, just CLOSE this diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index a4d214c7b506..04be9f833927 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2414,15 +2414,12 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans; /* Schedule a loss probe in 2*RTT for SACK capable connections - * in Open state, that are either limited by cwnd or application. + * not in loss recovery, that are either limited by cwnd or application. */ if ((early_retrans != 3 && early_retrans != 4) || !tp->packets_out || !tcp_is_sack(tp) || - icsk->icsk_ca_state != TCP_CA_Open) - return false; - - if ((tp->snd_cwnd > tcp_packets_in_flight(tp)) && - !tcp_write_queue_empty(sk)) + (icsk->icsk_ca_state != TCP_CA_Open && + icsk->icsk_ca_state != TCP_CA_CWR)) return false; /* Probe timeout is 2*rtt. Add minimum RTO to account diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 968fda198376..6db3124cdbda 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -183,11 +183,6 @@ static int tcp_write_timeout(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) { dst_negative_advice(sk); - if (tp->syn_fastopen || tp->syn_data) - tcp_fastopen_cache_set(sk, 0, NULL, true, 0); - if (tp->syn_data && icsk->icsk_retransmits == 1) - NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPFASTOPENACTIVEFAIL); } else if (!tp->syn_data && !tp->syn_fastopen) { sk_rethink_txhash(sk); } @@ -195,17 +190,6 @@ static int tcp_write_timeout(struct sock *sk) expired = icsk->icsk_retransmits >= retry_until; } else { if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0)) { - /* Some middle-boxes may black-hole Fast Open _after_ - * the handshake. Therefore we conservatively disable - * Fast Open on this path on recurring timeouts after - * successful Fast Open. - */ - if (tp->syn_data_acked) { - tcp_fastopen_cache_set(sk, 0, NULL, true, 0); - if (icsk->icsk_retransmits == net->ipv4.sysctl_tcp_retries1) - NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPFASTOPENACTIVEFAIL); - } /* Black hole detection */ tcp_mtu_probing(icsk, sk); @@ -228,6 +212,7 @@ static int tcp_write_timeout(struct sock *sk) expired = retransmits_timed_out(sk, retry_until, icsk->icsk_user_timeout); } + tcp_fastopen_active_detect_blackhole(sk, expired); if (expired) { /* Has it gone just too far? */ tcp_write_err(sk); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e4ff25c947c5..e9c0d1e1772e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -357,18 +357,12 @@ fail: } EXPORT_SYMBOL(udp_lib_get_port); -static u32 udp4_portaddr_hash(const struct net *net, __be32 saddr, - unsigned int port) -{ - return jhash_1word((__force u32)saddr, net_hash_mix(net)) ^ port; -} - int udp_v4_get_port(struct sock *sk, unsigned short snum) { unsigned int hash2_nulladdr = - udp4_portaddr_hash(sock_net(sk), htonl(INADDR_ANY), snum); + ipv4_portaddr_hash(sock_net(sk), htonl(INADDR_ANY), snum); unsigned int hash2_partial = - udp4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, 0); + ipv4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, 0); /* precompute partial secondary hash */ udp_sk(sk)->udp_portaddr_hash = hash2_partial; @@ -445,7 +439,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, struct sk_buff *skb) { struct sock *sk, *result; - int score, badness, matches = 0, reuseport = 0; + int score, badness; u32 hash = 0; result = NULL; @@ -454,23 +448,16 @@ static struct sock *udp4_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif, exact_dif); if (score > badness) { - reuseport = sk->sk_reuseport; - if (reuseport) { + if (sk->sk_reuseport) { hash = udp_ehashfn(net, daddr, hnum, saddr, sport); result = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); if (result) return result; - matches = 1; } badness = score; result = sk; - } else if (score == badness && reuseport) { - matches++; - if (reciprocal_scale(hash, matches) == 0) - result = sk; - hash = next_pseudo_random32(hash); } } return result; @@ -488,11 +475,11 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; bool exact_dif = udp_lib_exact_dif_match(net, skb); - int score, badness, matches = 0, reuseport = 0; + int score, badness; u32 hash = 0; if (hslot->count > 10) { - hash2 = udp4_portaddr_hash(net, daddr, hnum); + hash2 = ipv4_portaddr_hash(net, daddr, hnum); slot2 = hash2 & udptable->mask; hslot2 = &udptable->hash2[slot2]; if (hslot->count < hslot2->count) @@ -503,7 +490,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, exact_dif, hslot2, skb); if (!result) { unsigned int old_slot2 = slot2; - hash2 = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum); + hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum); slot2 = hash2 & udptable->mask; /* avoid searching the same slot again. */ if (unlikely(slot2 == old_slot2)) @@ -526,23 +513,16 @@ begin: score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif, exact_dif); if (score > badness) { - reuseport = sk->sk_reuseport; - if (reuseport) { + if (sk->sk_reuseport) { hash = udp_ehashfn(net, daddr, hnum, saddr, sport); result = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); if (result) return result; - matches = 1; } result = sk; badness = score; - } else if (score == badness && reuseport) { - matches++; - if (reciprocal_scale(hash, matches) == 0) - result = sk; - hash = next_pseudo_random32(hash); } } return result; @@ -1775,7 +1755,7 @@ EXPORT_SYMBOL(udp_lib_rehash); static void udp_v4_rehash(struct sock *sk) { - u16 new_hash = udp4_portaddr_hash(sock_net(sk), + u16 new_hash = ipv4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, inet_sk(sk)->inet_num); udp_lib_rehash(sk, new_hash); @@ -1966,9 +1946,9 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, struct sk_buff *nskb; if (use_hash2) { - hash2_any = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum) & + hash2_any = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum) & udptable->mask; - hash2 = udp4_portaddr_hash(net, daddr, hnum) & udptable->mask; + hash2 = ipv4_portaddr_hash(net, daddr, hnum) & udptable->mask; start_lookup: hslot = &udptable->hash2[hash2]; offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); @@ -2200,7 +2180,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net, int dif, int sdif) { unsigned short hnum = ntohs(loc_port); - unsigned int hash2 = udp4_portaddr_hash(net, loc_addr, hnum); + unsigned int hash2 = ipv4_portaddr_hash(net, loc_addr, hnum); unsigned int slot2 = hash2 & udp_table.mask; struct udp_hslot *hslot2 = &udp_table.hash2[slot2]; INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr); diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index e6265e2c274e..7d885a44dc9d 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -62,7 +62,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? 0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF)); - top_iph->ttl = ip4_dst_hoplimit(dst->child); + top_iph->ttl = ip4_dst_hoplimit(xfrm_dst_child(dst)); top_iph->saddr = x->props.saddr.a4; top_iph->daddr = x->id.daddr.a4; |