diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/af_inet.c | 2 | ||||
-rw-r--r-- | net/ipv4/ah4.c | 23 | ||||
-rw-r--r-- | net/ipv4/esp4.c | 58 | ||||
-rw-r--r-- | net/ipv4/inet_connection_sock.c | 22 | ||||
-rw-r--r-- | net/ipv4/inet_hashtables.c | 106 | ||||
-rw-r--r-- | net/ipv4/inet_timewait_sock.c | 4 | ||||
-rw-r--r-- | net/ipv4/ip_output.c | 2 | ||||
-rw-r--r-- | net/ipv4/ip_tunnel_core.c | 67 | ||||
-rw-r--r-- | net/ipv4/ipcomp.c | 10 | ||||
-rw-r--r-- | net/ipv4/ipip.c | 62 | ||||
-rw-r--r-- | net/ipv4/ipmr.c | 2 | ||||
-rw-r--r-- | net/ipv4/netfilter/ipt_rpfilter.c | 1 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_nat_h323.c | 60 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_socket_ipv4.c | 4 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_tproxy_ipv4.c | 16 | ||||
-rw-r--r-- | net/ipv4/netfilter/nft_fib_ipv4.c | 3 | ||||
-rw-r--r-- | net/ipv4/proc.c | 2 | ||||
-rw-r--r-- | net/ipv4/sysctl_net_ipv4.c | 47 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 39 | ||||
-rw-r--r-- | net/ipv4/tcp_diag.c | 18 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 25 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 143 | ||||
-rw-r--r-- | net/ipv4/tcp_minisocks.c | 28 | ||||
-rw-r--r-- | net/ipv4/tcp_offload.c | 17 | ||||
-rw-r--r-- | net/ipv4/udp.c | 48 | ||||
-rw-r--r-- | net/ipv4/udp_tunnel_core.c | 1 | ||||
-rw-r--r-- | net/ipv4/xfrm4_tunnel.c | 10 |
27 files changed, 493 insertions, 327 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index d3ab1ae32ef5..e2c219382345 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1250,7 +1250,7 @@ static int inet_sk_reselect_saddr(struct sock *sk) } prev_addr_hashbucket = - inet_bhashfn_portaddr(sk->sk_prot->h.hashinfo, sk, + inet_bhashfn_portaddr(tcp_or_dccp_get_hashinfo(sk), sk, sock_net(sk), inet->inet_num); inet->inet_saddr = inet->inet_rcv_saddr = new_saddr; diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index f8ad04470d3a..ee4e578c7f20 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -471,30 +471,38 @@ static int ah4_err(struct sk_buff *skb, u32 info) return 0; } -static int ah_init_state(struct xfrm_state *x) +static int ah_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) { struct ah_data *ahp = NULL; struct xfrm_algo_desc *aalg_desc; struct crypto_ahash *ahash; - if (!x->aalg) + if (!x->aalg) { + NL_SET_ERR_MSG(extack, "AH requires a state with an AUTH algorithm"); goto error; + } - if (x->encap) + if (x->encap) { + NL_SET_ERR_MSG(extack, "AH is not compatible with encapsulation"); goto error; + } ahp = kzalloc(sizeof(*ahp), GFP_KERNEL); if (!ahp) return -ENOMEM; ahash = crypto_alloc_ahash(x->aalg->alg_name, 0, 0); - if (IS_ERR(ahash)) + if (IS_ERR(ahash)) { + NL_SET_ERR_MSG(extack, "Kernel was unable to initialize cryptographic operations"); goto error; + } ahp->ahash = ahash; if (crypto_ahash_setkey(ahash, x->aalg->alg_key, - (x->aalg->alg_key_len + 7) / 8)) + (x->aalg->alg_key_len + 7) / 8)) { + NL_SET_ERR_MSG(extack, "Kernel was unable to initialize cryptographic operations"); goto error; + } /* * Lookup the algorithm description maintained by xfrm_algo, @@ -507,10 +515,7 @@ static int ah_init_state(struct xfrm_state *x) if (aalg_desc->uinfo.auth.icv_fullbits/8 != crypto_ahash_digestsize(ahash)) { - pr_info("%s: %s digestsize %u != %u\n", - __func__, x->aalg->alg_name, - crypto_ahash_digestsize(ahash), - aalg_desc->uinfo.auth.icv_fullbits / 8); + NL_SET_ERR_MSG(extack, "Kernel was unable to initialize cryptographic operations"); goto error; } diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 5c03eba787e5..52c8047efedb 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -134,6 +134,7 @@ static void esp_free_tcp_sk(struct rcu_head *head) static struct sock *esp_find_tcp_sk(struct xfrm_state *x) { struct xfrm_encap_tmpl *encap = x->encap; + struct net *net = xs_net(x); struct esp_tcp_sk *esk; __be16 sport, dport; struct sock *nsk; @@ -160,7 +161,7 @@ static struct sock *esp_find_tcp_sk(struct xfrm_state *x) } spin_unlock_bh(&x->lock); - sk = inet_lookup_established(xs_net(x), &tcp_hashinfo, x->id.daddr.a4, + sk = inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, x->id.daddr.a4, dport, x->props.saddr.a4, sport, 0); if (!sk) return ERR_PTR(-ENOENT); @@ -1007,16 +1008,17 @@ static void esp_destroy(struct xfrm_state *x) crypto_free_aead(aead); } -static int esp_init_aead(struct xfrm_state *x) +static int esp_init_aead(struct xfrm_state *x, struct netlink_ext_ack *extack) { char aead_name[CRYPTO_MAX_ALG_NAME]; struct crypto_aead *aead; int err; - err = -ENAMETOOLONG; if (snprintf(aead_name, CRYPTO_MAX_ALG_NAME, "%s(%s)", - x->geniv, x->aead->alg_name) >= CRYPTO_MAX_ALG_NAME) - goto error; + x->geniv, x->aead->alg_name) >= CRYPTO_MAX_ALG_NAME) { + NL_SET_ERR_MSG(extack, "Algorithm name is too long"); + return -ENAMETOOLONG; + } aead = crypto_alloc_aead(aead_name, 0, 0); err = PTR_ERR(aead); @@ -1034,11 +1036,15 @@ static int esp_init_aead(struct xfrm_state *x) if (err) goto error; + return 0; + error: + NL_SET_ERR_MSG(extack, "Kernel was unable to initialize cryptographic operations"); return err; } -static int esp_init_authenc(struct xfrm_state *x) +static int esp_init_authenc(struct xfrm_state *x, + struct netlink_ext_ack *extack) { struct crypto_aead *aead; struct crypto_authenc_key_param *param; @@ -1049,10 +1055,6 @@ static int esp_init_authenc(struct xfrm_state *x) unsigned int keylen; int err; - err = -EINVAL; - if (!x->ealg) - goto error; - err = -ENAMETOOLONG; if ((x->props.flags & XFRM_STATE_ESN)) { @@ -1061,22 +1063,28 @@ static int esp_init_authenc(struct xfrm_state *x) x->geniv ?: "", x->geniv ? "(" : "", x->aalg ? x->aalg->alg_name : "digest_null", x->ealg->alg_name, - x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME) + x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME) { + NL_SET_ERR_MSG(extack, "Algorithm name is too long"); goto error; + } } else { if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME, "%s%sauthenc(%s,%s)%s", x->geniv ?: "", x->geniv ? "(" : "", x->aalg ? x->aalg->alg_name : "digest_null", x->ealg->alg_name, - x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME) + x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME) { + NL_SET_ERR_MSG(extack, "Algorithm name is too long"); goto error; + } } aead = crypto_alloc_aead(authenc_name, 0, 0); err = PTR_ERR(aead); - if (IS_ERR(aead)) + if (IS_ERR(aead)) { + NL_SET_ERR_MSG(extack, "Kernel was unable to initialize cryptographic operations"); goto error; + } x->data = aead; @@ -1106,17 +1114,16 @@ static int esp_init_authenc(struct xfrm_state *x) err = -EINVAL; if (aalg_desc->uinfo.auth.icv_fullbits / 8 != crypto_aead_authsize(aead)) { - pr_info("ESP: %s digestsize %u != %u\n", - x->aalg->alg_name, - crypto_aead_authsize(aead), - aalg_desc->uinfo.auth.icv_fullbits / 8); + NL_SET_ERR_MSG(extack, "Kernel was unable to initialize cryptographic operations"); goto free_key; } err = crypto_aead_setauthsize( aead, x->aalg->alg_trunc_len / 8); - if (err) + if (err) { + NL_SET_ERR_MSG(extack, "Kernel was unable to initialize cryptographic operations"); goto free_key; + } } param->enckeylen = cpu_to_be32((x->ealg->alg_key_len + 7) / 8); @@ -1131,7 +1138,7 @@ error: return err; } -static int esp_init_state(struct xfrm_state *x) +static int esp_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) { struct crypto_aead *aead; u32 align; @@ -1139,10 +1146,14 @@ static int esp_init_state(struct xfrm_state *x) x->data = NULL; - if (x->aead) - err = esp_init_aead(x); - else - err = esp_init_authenc(x); + if (x->aead) { + err = esp_init_aead(x, extack); + } else if (x->ealg) { + err = esp_init_authenc(x, extack); + } else { + NL_SET_ERR_MSG(extack, "ESP: AEAD or CRYPT must be provided"); + err = -EINVAL; + } if (err) goto error; @@ -1160,6 +1171,7 @@ static int esp_init_state(struct xfrm_state *x) switch (encap->encap_type) { default: + NL_SET_ERR_MSG(extack, "Unsupported encapsulation type for ESP"); err = -EINVAL; goto error; case UDP_ENCAP_ESPINUDP: diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index f0038043b661..ebca860e113f 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -285,16 +285,14 @@ inet_csk_find_open_port(const struct sock *sk, struct inet_bind_bucket **tb_ret, struct inet_bind2_bucket **tb2_ret, struct inet_bind_hashbucket **head2_ret, int *port_ret) { - struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo; - int port = 0; + struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); + int i, low, high, attempt_half, port, l3mdev; struct inet_bind_hashbucket *head, *head2; struct net *net = sock_net(sk); - bool relax = false; - int i, low, high, attempt_half; struct inet_bind2_bucket *tb2; struct inet_bind_bucket *tb; u32 remaining, offset; - int l3mdev; + bool relax = false; l3mdev = inet_sk_bound_l3mdev(sk); ports_exhausted: @@ -469,17 +467,16 @@ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, */ int inet_csk_get_port(struct sock *sk, unsigned short snum) { + struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; - struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo; - int ret = 1, port = snum; - struct net *net = sock_net(sk); bool found_port = false, check_bind_conflict = true; bool bhash_created = false, bhash2_created = false; struct inet_bind_hashbucket *head, *head2; struct inet_bind2_bucket *tb2 = NULL; struct inet_bind_bucket *tb = NULL; bool head2_lock_acquired = false; - int l3mdev; + int ret = 1, port = snum, l3mdev; + struct net *net = sock_net(sk); l3mdev = inet_sk_bound_l3mdev(sk); @@ -909,14 +906,15 @@ static void reqsk_migrate_reset(struct request_sock *req) /* return true if req was found in the ehash table */ static bool reqsk_queue_unlink(struct request_sock *req) { - struct inet_hashinfo *hashinfo = req_to_sk(req)->sk_prot->h.hashinfo; + struct sock *sk = req_to_sk(req); bool found = false; - if (sk_hashed(req_to_sk(req))) { + if (sk_hashed(sk)) { + struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk); spinlock_t *lock = inet_ehash_lockp(hashinfo, req->rsk_hash); spin_lock(lock); - found = __sk_nulls_del_node_init_rcu(req_to_sk(req)); + found = __sk_nulls_del_node_init_rcu(sk); spin_unlock(lock); } if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer)) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 60d77e234a68..dc1c5629cd0d 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -109,6 +109,7 @@ static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb, tb->l3mdev = l3mdev; tb->port = port; #if IS_ENABLED(CONFIG_IPV6) + tb->family = sk->sk_family; if (sk->sk_family == AF_INET6) tb->v6_rcv_saddr = sk->sk_v6_rcv_saddr; else @@ -146,6 +147,9 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2, const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family != tb2->family) + return false; + if (sk->sk_family == AF_INET6) return ipv6_addr_equal(&tb2->v6_rcv_saddr, &sk->sk_v6_rcv_saddr); @@ -168,14 +172,15 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, */ static void __inet_put_port(struct sock *sk) { - struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; - const int bhash = inet_bhashfn(sock_net(sk), inet_sk(sk)->inet_num, - hashinfo->bhash_size); - struct inet_bind_hashbucket *head = &hashinfo->bhash[bhash]; - struct inet_bind_hashbucket *head2 = - inet_bhashfn_portaddr(hashinfo, sk, sock_net(sk), - inet_sk(sk)->inet_num); + struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk); + struct inet_bind_hashbucket *head, *head2; + struct net *net = sock_net(sk); struct inet_bind_bucket *tb; + int bhash; + + bhash = inet_bhashfn(net, inet_sk(sk)->inet_num, hashinfo->bhash_size); + head = &hashinfo->bhash[bhash]; + head2 = inet_bhashfn_portaddr(hashinfo, sk, net, inet_sk(sk)->inet_num); spin_lock(&head->lock); tb = inet_csk(sk)->icsk_bind_hash; @@ -207,19 +212,19 @@ EXPORT_SYMBOL(inet_put_port); int __inet_inherit_port(const struct sock *sk, struct sock *child) { - struct inet_hashinfo *table = sk->sk_prot->h.hashinfo; + struct inet_hashinfo *table = tcp_or_dccp_get_hashinfo(sk); unsigned short port = inet_sk(child)->inet_num; - const int bhash = inet_bhashfn(sock_net(sk), port, - table->bhash_size); - struct inet_bind_hashbucket *head = &table->bhash[bhash]; - struct inet_bind_hashbucket *head2 = - inet_bhashfn_portaddr(table, child, sock_net(sk), port); + struct inet_bind_hashbucket *head, *head2; bool created_inet_bind_bucket = false; - bool update_fastreuse = false; struct net *net = sock_net(sk); + bool update_fastreuse = false; struct inet_bind2_bucket *tb2; struct inet_bind_bucket *tb; - int l3mdev; + int bhash, l3mdev; + + bhash = inet_bhashfn(net, port, table->bhash_size); + head = &table->bhash[bhash]; + head2 = inet_bhashfn_portaddr(table, child, net, port); spin_lock(&head->lock); spin_lock(&head2->lock); @@ -385,7 +390,7 @@ static inline struct sock *inet_lookup_run_bpf(struct net *net, struct sock *sk, *reuse_sk; bool no_reuseport; - if (hashinfo != &tcp_hashinfo) + if (hashinfo != net->ipv4.tcp_death_row.hashinfo) return NULL; /* only TCP is supported */ no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP, saddr, sport, @@ -628,9 +633,9 @@ static bool inet_ehash_lookup_by_sk(struct sock *sk, */ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) { - struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; - struct hlist_nulls_head *list; + struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk); struct inet_ehash_bucket *head; + struct hlist_nulls_head *list; spinlock_t *lock; bool ret = true; @@ -700,7 +705,7 @@ static int inet_reuseport_add_sock(struct sock *sk, int __inet_hash(struct sock *sk, struct sock *osk) { - struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; + struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk); struct inet_listen_hashbucket *ilb2; int err = 0; @@ -746,7 +751,7 @@ EXPORT_SYMBOL_GPL(inet_hash); void inet_unhash(struct sock *sk) { - struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; + struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk); if (sk_unhashed(sk)) return; @@ -790,6 +795,9 @@ static bool inet_bind2_bucket_match(const struct inet_bind2_bucket *tb, int l3mdev, const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family != tb->family) + return false; + if (sk->sk_family == AF_INET6) return net_eq(ib2_net(tb), net) && tb->port == port && tb->l3mdev == l3mdev && @@ -806,6 +814,9 @@ bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const #if IS_ENABLED(CONFIG_IPV6) struct in6_addr addr_any = {}; + if (sk->sk_family != tb->family) + return false; + if (sk->sk_family == AF_INET6) return net_eq(ib2_net(tb), net) && tb->port == port && tb->l3mdev == l3mdev && @@ -833,7 +844,7 @@ inet_bind2_bucket_find(const struct inet_bind_hashbucket *head, const struct net struct inet_bind_hashbucket * inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, int port) { - struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo; + struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); u32 hash; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr addr_any = {}; @@ -849,7 +860,7 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk) { - struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo; + struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); struct inet_bind2_bucket *tb2, *new_tb2; int l3mdev = inet_sk_bound_l3mdev(sk); struct inet_bind_hashbucket *head2; @@ -947,8 +958,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, if (likely(remaining > 1)) remaining &= ~1U; - net_get_random_once(table_perturb, - INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb)); + get_random_slow_once(table_perturb, + INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb)); index = port_offset & (INET_TABLE_PERTURB_SIZE - 1); offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32); @@ -1144,3 +1155,50 @@ int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo) return 0; } EXPORT_SYMBOL_GPL(inet_ehash_locks_alloc); + +struct inet_hashinfo *inet_pernet_hashinfo_alloc(struct inet_hashinfo *hashinfo, + unsigned int ehash_entries) +{ + struct inet_hashinfo *new_hashinfo; + int i; + + new_hashinfo = kmemdup(hashinfo, sizeof(*hashinfo), GFP_KERNEL); + if (!new_hashinfo) + goto err; + + new_hashinfo->ehash = vmalloc_huge(ehash_entries * sizeof(struct inet_ehash_bucket), + GFP_KERNEL_ACCOUNT); + if (!new_hashinfo->ehash) + goto free_hashinfo; + + new_hashinfo->ehash_mask = ehash_entries - 1; + + if (inet_ehash_locks_alloc(new_hashinfo)) + goto free_ehash; + + for (i = 0; i < ehash_entries; i++) + INIT_HLIST_NULLS_HEAD(&new_hashinfo->ehash[i].chain, i); + + new_hashinfo->pernet = true; + + return new_hashinfo; + +free_ehash: + vfree(new_hashinfo->ehash); +free_hashinfo: + kfree(new_hashinfo); +err: + return NULL; +} +EXPORT_SYMBOL_GPL(inet_pernet_hashinfo_alloc); + +void inet_pernet_hashinfo_free(struct inet_hashinfo *hashinfo) +{ + if (!hashinfo->pernet) + return; + + inet_ehash_locks_free(hashinfo); + vfree(hashinfo->ehash); + kfree(hashinfo); +} +EXPORT_SYMBOL_GPL(inet_pernet_hashinfo_free); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 47ccc343c9fb..71d3bb0abf6c 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -59,9 +59,7 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw) inet_twsk_bind_unhash(tw, hashinfo); spin_unlock(&bhead->lock); - if (refcount_dec_and_test(&tw->tw_dr->tw_refcount)) - kfree(tw->tw_dr); - + refcount_dec(&tw->tw_dr->tw_refcount); inet_twsk_put(tw); } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8201cd423ff9..1ae83ad629b2 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1043,7 +1043,7 @@ static int __ip_append_data(struct sock *sk, paged = true; zc = true; } else { - uarg->zerocopy = 0; + uarg_to_msgzc(uarg)->zerocopy = 0; skb_zcopy_set(skb, uarg, &extra_uref); } } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index cc1caab4a654..92c02c886fe7 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -1079,3 +1079,70 @@ EXPORT_SYMBOL(ip_tunnel_parse_protocol); const struct header_ops ip_tunnel_header_ops = { .parse_protocol = ip_tunnel_parse_protocol }; EXPORT_SYMBOL(ip_tunnel_header_ops); + +/* This function returns true when ENCAP attributes are present in the nl msg */ +bool ip_tunnel_netlink_encap_parms(struct nlattr *data[], + struct ip_tunnel_encap *encap) +{ + bool ret = false; + + memset(encap, 0, sizeof(*encap)); + + if (!data) + return ret; + + if (data[IFLA_IPTUN_ENCAP_TYPE]) { + ret = true; + encap->type = nla_get_u16(data[IFLA_IPTUN_ENCAP_TYPE]); + } + + if (data[IFLA_IPTUN_ENCAP_FLAGS]) { + ret = true; + encap->flags = nla_get_u16(data[IFLA_IPTUN_ENCAP_FLAGS]); + } + + if (data[IFLA_IPTUN_ENCAP_SPORT]) { + ret = true; + encap->sport = nla_get_be16(data[IFLA_IPTUN_ENCAP_SPORT]); + } + + if (data[IFLA_IPTUN_ENCAP_DPORT]) { + ret = true; + encap->dport = nla_get_be16(data[IFLA_IPTUN_ENCAP_DPORT]); + } + + return ret; +} +EXPORT_SYMBOL_GPL(ip_tunnel_netlink_encap_parms); + +void ip_tunnel_netlink_parms(struct nlattr *data[], + struct ip_tunnel_parm *parms) +{ + if (data[IFLA_IPTUN_LINK]) + parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); + + if (data[IFLA_IPTUN_LOCAL]) + parms->iph.saddr = nla_get_be32(data[IFLA_IPTUN_LOCAL]); + + if (data[IFLA_IPTUN_REMOTE]) + parms->iph.daddr = nla_get_be32(data[IFLA_IPTUN_REMOTE]); + + if (data[IFLA_IPTUN_TTL]) { + parms->iph.ttl = nla_get_u8(data[IFLA_IPTUN_TTL]); + if (parms->iph.ttl) + parms->iph.frag_off = htons(IP_DF); + } + + if (data[IFLA_IPTUN_TOS]) + parms->iph.tos = nla_get_u8(data[IFLA_IPTUN_TOS]); + + if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC])) + parms->iph.frag_off = htons(IP_DF); + + if (data[IFLA_IPTUN_FLAGS]) + parms->i_flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); + + if (data[IFLA_IPTUN_PROTO]) + parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]); +} +EXPORT_SYMBOL_GPL(ip_tunnel_netlink_parms); diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index 366094c1ce6c..5a4fb2539b08 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -117,7 +117,8 @@ out: return err; } -static int ipcomp4_init_state(struct xfrm_state *x) +static int ipcomp4_init_state(struct xfrm_state *x, + struct netlink_ext_ack *extack) { int err = -EINVAL; @@ -129,17 +130,20 @@ static int ipcomp4_init_state(struct xfrm_state *x) x->props.header_len += sizeof(struct iphdr); break; default: + NL_SET_ERR_MSG(extack, "Unsupported XFRM mode for IPcomp"); goto out; } - err = ipcomp_init_state(x); + err = ipcomp_init_state(x, extack); if (err) goto out; if (x->props.mode == XFRM_MODE_TUNNEL) { err = ipcomp_tunnel_attach(x); - if (err) + if (err) { + NL_SET_ERR_MSG(extack, "Kernel error: failed to initialize the associated state"); goto out; + } } err = 0; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 123ea63a04cb..180f9daf5bec 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -417,29 +417,7 @@ static void ipip_netlink_parms(struct nlattr *data[], if (!data) return; - if (data[IFLA_IPTUN_LINK]) - parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); - - if (data[IFLA_IPTUN_LOCAL]) - parms->iph.saddr = nla_get_in_addr(data[IFLA_IPTUN_LOCAL]); - - if (data[IFLA_IPTUN_REMOTE]) - parms->iph.daddr = nla_get_in_addr(data[IFLA_IPTUN_REMOTE]); - - if (data[IFLA_IPTUN_TTL]) { - parms->iph.ttl = nla_get_u8(data[IFLA_IPTUN_TTL]); - if (parms->iph.ttl) - parms->iph.frag_off = htons(IP_DF); - } - - if (data[IFLA_IPTUN_TOS]) - parms->iph.tos = nla_get_u8(data[IFLA_IPTUN_TOS]); - - if (data[IFLA_IPTUN_PROTO]) - parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]); - - if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC])) - parms->iph.frag_off = htons(IP_DF); + ip_tunnel_netlink_parms(data, parms); if (data[IFLA_IPTUN_COLLECT_METADATA]) *collect_md = true; @@ -448,40 +426,6 @@ static void ipip_netlink_parms(struct nlattr *data[], *fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]); } -/* This function returns true when ENCAP attributes are present in the nl msg */ -static bool ipip_netlink_encap_parms(struct nlattr *data[], - struct ip_tunnel_encap *ipencap) -{ - bool ret = false; - - memset(ipencap, 0, sizeof(*ipencap)); - - if (!data) - return ret; - - if (data[IFLA_IPTUN_ENCAP_TYPE]) { - ret = true; - ipencap->type = nla_get_u16(data[IFLA_IPTUN_ENCAP_TYPE]); - } - - if (data[IFLA_IPTUN_ENCAP_FLAGS]) { - ret = true; - ipencap->flags = nla_get_u16(data[IFLA_IPTUN_ENCAP_FLAGS]); - } - - if (data[IFLA_IPTUN_ENCAP_SPORT]) { - ret = true; - ipencap->sport = nla_get_be16(data[IFLA_IPTUN_ENCAP_SPORT]); - } - - if (data[IFLA_IPTUN_ENCAP_DPORT]) { - ret = true; - ipencap->dport = nla_get_be16(data[IFLA_IPTUN_ENCAP_DPORT]); - } - - return ret; -} - static int ipip_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) @@ -491,7 +435,7 @@ static int ipip_newlink(struct net *src_net, struct net_device *dev, struct ip_tunnel_encap ipencap; __u32 fwmark = 0; - if (ipip_netlink_encap_parms(data, &ipencap)) { + if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) @@ -512,7 +456,7 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], bool collect_md; __u32 fwmark = t->fwmark; - if (ipip_netlink_encap_parms(data, &ipencap)) { + if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 95eefbe2e142..e04544ac4b45 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1004,7 +1004,9 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else { + rcu_read_lock(); ip_mr_forward(net, mrt, skb->dev, skb, c, 0); + rcu_read_unlock(); } } } diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index 8cd3224d913e..8183bbcabb4a 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -33,7 +33,6 @@ static bool rpfilter_lookup_reverse(struct net *net, struct flowi4 *fl4, const struct net_device *dev, u8 flags) { struct fib_result res; - int ret __maybe_unused; if (fib_lookup(net, fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE)) return false; diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index a334f0dcc2d0..faee20af4856 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -291,20 +291,7 @@ static int nat_t120(struct sk_buff *skb, struct nf_conn *ct, exp->expectfn = nf_nat_follow_master; exp->dir = !dir; - /* Try to get same port: if not, try to change it. */ - for (; nated_port != 0; nated_port++) { - int ret; - - exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp, 0); - if (ret == 0) - break; - else if (ret != -EBUSY) { - nated_port = 0; - break; - } - } - + nated_port = nf_nat_exp_find_port(exp, nated_port); if (nated_port == 0) { /* No port available */ net_notice_ratelimited("nf_nat_h323: out of TCP ports\n"); return 0; @@ -347,20 +334,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, if (info->sig_port[dir] == port) nated_port = ntohs(info->sig_port[!dir]); - /* Try to get same port: if not, try to change it. */ - for (; nated_port != 0; nated_port++) { - int ret; - - exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp, 0); - if (ret == 0) - break; - else if (ret != -EBUSY) { - nated_port = 0; - break; - } - } - + nated_port = nf_nat_exp_find_port(exp, nated_port); if (nated_port == 0) { /* No port available */ net_notice_ratelimited("nf_nat_q931: out of TCP ports\n"); return 0; @@ -439,20 +413,7 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, if (info->sig_port[dir] == port) nated_port = ntohs(info->sig_port[!dir]); - /* Try to get same port: if not, try to change it. */ - for (; nated_port != 0; nated_port++) { - int ret; - - exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp, 0); - if (ret == 0) - break; - else if (ret != -EBUSY) { - nated_port = 0; - break; - } - } - + nated_port = nf_nat_exp_find_port(exp, nated_port); if (nated_port == 0) { /* No port available */ net_notice_ratelimited("nf_nat_ras: out of TCP ports\n"); return 0; @@ -532,20 +493,7 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, exp->expectfn = ip_nat_callforwarding_expect; exp->dir = !dir; - /* Try to get same port: if not, try to change it. */ - for (nated_port = ntohs(port); nated_port != 0; nated_port++) { - int ret; - - exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp, 0); - if (ret == 0) - break; - else if (ret != -EBUSY) { - nated_port = 0; - break; - } - } - + nated_port = nf_nat_exp_find_port(exp, ntohs(port)); if (nated_port == 0) { /* No port available */ net_notice_ratelimited("nf_nat_q931: out of TCP ports\n"); return 0; diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c index 2d42e4c35a20..a1350fc25838 100644 --- a/net/ipv4/netfilter/nf_socket_ipv4.c +++ b/net/ipv4/netfilter/nf_socket_ipv4.c @@ -71,8 +71,8 @@ nf_socket_get_sock_v4(struct net *net, struct sk_buff *skb, const int doff, { switch (protocol) { case IPPROTO_TCP: - return inet_lookup(net, &tcp_hashinfo, skb, doff, - saddr, sport, daddr, dport, + return inet_lookup(net, net->ipv4.tcp_death_row.hashinfo, + skb, doff, saddr, sport, daddr, dport, in->ifindex); case IPPROTO_UDP: return udp4_lib_lookup(net, saddr, sport, daddr, dport, diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c index b2bae0b0e42a..b22b2c745c76 100644 --- a/net/ipv4/netfilter/nf_tproxy_ipv4.c +++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c @@ -79,6 +79,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, const struct net_device *in, const enum nf_tproxy_lookup_t lookup_type) { + struct inet_hashinfo *hinfo = net->ipv4.tcp_death_row.hashinfo; struct sock *sk; switch (protocol) { @@ -92,12 +93,10 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, switch (lookup_type) { case NF_TPROXY_LOOKUP_LISTENER: - sk = inet_lookup_listener(net, &tcp_hashinfo, skb, - ip_hdrlen(skb) + - __tcp_hdrlen(hp), - saddr, sport, - daddr, dport, - in->ifindex, 0); + sk = inet_lookup_listener(net, hinfo, skb, + ip_hdrlen(skb) + __tcp_hdrlen(hp), + saddr, sport, daddr, dport, + in->ifindex, 0); if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; @@ -108,9 +107,8 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, */ break; case NF_TPROXY_LOOKUP_ESTABLISHED: - sk = inet_lookup_established(net, &tcp_hashinfo, - saddr, sport, daddr, dport, - in->ifindex); + sk = inet_lookup_established(net, hinfo, saddr, sport, + daddr, dport, in->ifindex); break; default: BUG(); diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index b75cac69bd7e..7ade04ff972d 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -83,6 +83,9 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, else oif = NULL; + if (priv->flags & NFTA_FIB_F_IIF) + fl4.flowi4_oif = l3mdev_master_ifindex_rcu(oif); + if (nft_hook(pkt) == NF_INET_PRE_ROUTING && nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { nft_fib_store_result(dest, priv, nft_in(pkt)); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 0088a4c64d77..5386f460bd20 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -59,7 +59,7 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) socket_seq_show(seq); seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n", sock_prot_inuse_get(net, &tcp_prot), orphans, - refcount_read(&net->ipv4.tcp_death_row->tw_refcount) - 1, + refcount_read(&net->ipv4.tcp_death_row.tw_refcount) - 1, sockets, proto_memory_allocated(&tcp_prot)); seq_printf(seq, "UDP: inuse %d mem %ld\n", sock_prot_inuse_get(net, &udp_prot), diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 5490c285668b..9b8a6db7a66b 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -39,6 +39,7 @@ static u32 u32_max_div_HZ = UINT_MAX / HZ; static int one_day_secs = 24 * 3600; static u32 fib_multipath_hash_fields_all_mask __maybe_unused = FIB_MULTIPATH_HASH_FIELD_ALL_MASK; +static unsigned int tcp_child_ehash_entries_max = 16 * 1024 * 1024; /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; @@ -382,6 +383,29 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl, return ret; } +static int proc_tcp_ehash_entries(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct net *net = container_of(table->data, struct net, + ipv4.sysctl_tcp_child_ehash_entries); + struct inet_hashinfo *hinfo = net->ipv4.tcp_death_row.hashinfo; + int tcp_ehash_entries; + struct ctl_table tbl; + + tcp_ehash_entries = hinfo->ehash_mask + 1; + + /* A negative number indicates that the child netns + * shares the global ehash. + */ + if (!net_eq(net, &init_net) && !hinfo->pernet) + tcp_ehash_entries *= -1; + + tbl.data = &tcp_ehash_entries; + tbl.maxlen = sizeof(int); + + return proc_dointvec(&tbl, write, buffer, lenp, ppos); +} + #ifdef CONFIG_IP_ROUTE_MULTIPATH static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write, void *buffer, size_t *lenp, @@ -530,10 +554,9 @@ static struct ctl_table ipv4_table[] = { }; static struct ctl_table ipv4_net_table[] = { - /* tcp_max_tw_buckets must be first in this table. */ { .procname = "tcp_max_tw_buckets", -/* .data = &init_net.ipv4.tcp_death_row.sysctl_max_tw_buckets, */ + .data = &init_net.ipv4.tcp_death_row.sysctl_max_tw_buckets, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec @@ -1322,6 +1345,21 @@ static struct ctl_table ipv4_net_table[] = { .extra2 = SYSCTL_ONE, }, { + .procname = "tcp_ehash_entries", + .data = &init_net.ipv4.sysctl_tcp_child_ehash_entries, + .mode = 0444, + .proc_handler = proc_tcp_ehash_entries, + }, + { + .procname = "tcp_child_ehash_entries", + .data = &init_net.ipv4.sysctl_tcp_child_ehash_entries, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &tcp_child_ehash_entries_max, + }, + { .procname = "udp_rmem_min", .data = &init_net.ipv4.sysctl_udp_rmem_min, .maxlen = sizeof(init_net.ipv4.sysctl_udp_rmem_min), @@ -1361,8 +1399,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) if (!table) goto err_alloc; - /* skip first entry (sysctl_max_tw_buckets) */ - for (i = 1; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) { + for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) { if (table[i].data) { /* Update the variables to point into * the current struct net @@ -1377,8 +1414,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) } } - table[0].data = &net->ipv4.tcp_death_row->sysctl_max_tw_buckets; - net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); if (!net->ipv4.ipv4_hdr) goto err_reg; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 52b8879e7d20..648b5c54bb32 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1015,7 +1015,7 @@ new_segment: skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else { get_page(page); - skb_fill_page_desc(skb, i, page, offset, copy); + skb_fill_page_desc_noacc(skb, i, page, offset, copy); } if (!(flags & MSG_NO_SHARED_FRAGS)) @@ -1162,9 +1162,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp) } } -static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, - int *copied, size_t size, - struct ubuf_info *uarg) +int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, + size_t size, struct ubuf_info *uarg) { struct tcp_sock *tp = tcp_sk(sk); struct inet_sock *inet = inet_sk(sk); @@ -1239,7 +1238,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) } zc = sk->sk_route_caps & NETIF_F_SG; if (!zc) - uarg->zerocopy = 0; + uarg_to_msgzc(uarg)->zerocopy = 0; } } @@ -1761,19 +1760,28 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; - skb = tcp_recv_skb(sk, seq, &offset); - if (!skb) - return 0; + while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { + u8 tcp_flags; + int used; - __skb_unlink(skb, &sk->sk_receive_queue); - WARN_ON(!skb_set_owner_sk_safe(skb, sk)); - copied = recv_actor(sk, skb); - if (copied >= 0) { - seq += copied; - if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) + __skb_unlink(skb, &sk->sk_receive_queue); + WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); + tcp_flags = TCP_SKB_CB(skb)->tcp_flags; + used = recv_actor(sk, skb); + consume_skb(skb); + if (used < 0) { + if (!copied) + copied = used; + break; + } + seq += used; + copied += used; + + if (tcp_flags & TCPHDR_FIN) { ++seq; + break; + } } - consume_skb(skb); WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); @@ -4790,6 +4798,7 @@ void __init tcp_init(void) INIT_HLIST_HEAD(&tcp_hashinfo.bhash2[i].chain); } + tcp_hashinfo.pernet = false; cnt = tcp_hashinfo.ehash_mask + 1; sysctl_tcp_max_orphans = cnt / 2; diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 75a1c985f49a..01b50fa79189 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -181,13 +181,21 @@ static size_t tcp_diag_get_aux_size(struct sock *sk, bool net_admin) static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { - inet_diag_dump_icsk(&tcp_hashinfo, skb, cb, r); + struct inet_hashinfo *hinfo; + + hinfo = sock_net(cb->skb->sk)->ipv4.tcp_death_row.hashinfo; + + inet_diag_dump_icsk(hinfo, skb, cb, r); } static int tcp_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { - return inet_diag_dump_one_icsk(&tcp_hashinfo, cb, req); + struct inet_hashinfo *hinfo; + + hinfo = sock_net(cb->skb->sk)->ipv4.tcp_death_row.hashinfo; + + return inet_diag_dump_one_icsk(hinfo, cb, req); } #ifdef CONFIG_INET_DIAG_DESTROY @@ -195,9 +203,13 @@ static int tcp_diag_destroy(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req) { struct net *net = sock_net(in_skb->sk); - struct sock *sk = inet_diag_find_one_icsk(net, &tcp_hashinfo, req); + struct inet_hashinfo *hinfo; + struct sock *sk; int err; + hinfo = net->ipv4.tcp_death_row.hashinfo; + sk = inet_diag_find_one_icsk(net, hinfo, req); + if (IS_ERR(sk)) return PTR_ERR(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b85a9f755da4..bc2ea12221f9 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2513,6 +2513,21 @@ static inline bool tcp_may_undo(const struct tcp_sock *tp) return tp->undo_marker && (!tp->undo_retrans || tcp_packet_delayed(tp)); } +static bool tcp_is_non_sack_preventing_reopen(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) { + /* Hold old state until something *above* high_seq + * is ACKed. For Reno it is MUST to prevent false + * fast retransmits (RFC2582). SACK TCP is safe. */ + if (!tcp_any_retrans_done(sk)) + tp->retrans_stamp = 0; + return true; + } + return false; +} + /* People celebrate: "We love our President!" */ static bool tcp_try_undo_recovery(struct sock *sk) { @@ -2535,14 +2550,8 @@ static bool tcp_try_undo_recovery(struct sock *sk) } else if (tp->rack.reo_wnd_persist) { tp->rack.reo_wnd_persist--; } - if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) { - /* Hold old state until something *above* high_seq - * is ACKed. For Reno it is MUST to prevent false - * fast retransmits (RFC2582). SACK TCP is safe. */ - if (!tcp_any_retrans_done(sk)) - tp->retrans_stamp = 0; + if (tcp_is_non_sack_preventing_reopen(sk)) return true; - } tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; return false; @@ -2578,6 +2587,8 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSPURIOUSRTOS); inet_csk(sk)->icsk_retransmits = 0; + if (tcp_is_non_sack_preventing_reopen(sk)) + return true; if (frto_undo || tcp_is_sack(tp)) { tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 01b31f5c7aba..6376ad915765 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -201,15 +201,16 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; + struct inet_timewait_death_row *tcp_death_row; __be32 daddr, nexthop, prev_sk_rcv_saddr; struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); + struct ip_options_rcu *inet_opt; + struct net *net = sock_net(sk); __be16 orig_sport, orig_dport; struct flowi4 *fl4; struct rtable *rt; int err; - struct ip_options_rcu *inet_opt; - struct inet_timewait_death_row *tcp_death_row = sock_net(sk)->ipv4.tcp_death_row; if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; @@ -235,7 +236,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (IS_ERR(rt)) { err = PTR_ERR(rt); if (err == -ENETUNREACH) - IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return err; } @@ -247,11 +248,12 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (!inet_opt || !inet_opt->opt.srr) daddr = fl4->daddr; + tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; + if (!inet->inet_saddr) { if (inet_csk(sk)->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(&tcp_hashinfo, - sk, sock_net(sk), - inet->inet_num); + prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo, + sk, net, inet->inet_num); prev_sk_rcv_saddr = sk->sk_rcv_saddr; } inet->inet_saddr = fl4->saddr; @@ -317,8 +319,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, usin->sin_port)); - tp->tsoffset = secure_tcp_ts_off(sock_net(sk), - inet->inet_saddr, + tp->tsoffset = secure_tcp_ts_off(net, inet->inet_saddr, inet->inet_daddr); } @@ -494,9 +495,9 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) int err; struct net *net = dev_net(skb->dev); - sk = __inet_lookup_established(net, &tcp_hashinfo, iph->daddr, - th->dest, iph->saddr, ntohs(th->source), - inet_iif(skb), 0); + sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, + iph->daddr, th->dest, iph->saddr, + ntohs(th->source), inet_iif(skb), 0); if (!sk) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return -ENOENT; @@ -759,8 +760,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) * Incoming packet is checked with md5 hash with finding key, * no RST generated if md5 hash doesn't match. */ - sk1 = __inet_lookup_listener(net, &tcp_hashinfo, NULL, 0, - ip_hdr(skb)->saddr, + sk1 = __inet_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo, + NULL, 0, ip_hdr(skb)->saddr, th->source, ip_hdr(skb)->daddr, ntohs(th->source), dif, sdif); /* don't send rst if it can't find key */ @@ -1728,6 +1729,7 @@ EXPORT_SYMBOL(tcp_v4_do_rcv); int tcp_v4_early_demux(struct sk_buff *skb) { + struct net *net = dev_net(skb->dev); const struct iphdr *iph; const struct tcphdr *th; struct sock *sk; @@ -1744,7 +1746,7 @@ int tcp_v4_early_demux(struct sk_buff *skb) if (th->doff < sizeof(struct tcphdr) / 4) return 0; - sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo, + sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, iph->saddr, th->source, iph->daddr, ntohs(th->dest), skb->skb_iif, inet_sdif(skb)); @@ -1970,7 +1972,8 @@ int tcp_v4_rcv(struct sk_buff *skb) th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); lookup: - sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source, + sk = __inet_lookup_skb(net->ipv4.tcp_death_row.hashinfo, + skb, __tcp_hdrlen(th), th->source, th->dest, sdif, &refcounted); if (!sk) goto no_tcp_socket; @@ -2152,9 +2155,9 @@ do_time_wait: } switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) { case TCP_TW_SYN: { - struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev), - &tcp_hashinfo, skb, - __tcp_hdrlen(th), + struct sock *sk2 = inet_lookup_listener(net, + net->ipv4.tcp_death_row.hashinfo, + skb, __tcp_hdrlen(th), iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb), @@ -2304,15 +2307,16 @@ static bool seq_sk_match(struct seq_file *seq, const struct sock *sk) */ static void *listening_get_first(struct seq_file *seq) { + struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct tcp_iter_state *st = seq->private; st->offset = 0; - for (; st->bucket <= tcp_hashinfo.lhash2_mask; st->bucket++) { + for (; st->bucket <= hinfo->lhash2_mask; st->bucket++) { struct inet_listen_hashbucket *ilb2; struct hlist_nulls_node *node; struct sock *sk; - ilb2 = &tcp_hashinfo.lhash2[st->bucket]; + ilb2 = &hinfo->lhash2[st->bucket]; if (hlist_nulls_empty(&ilb2->nulls_head)) continue; @@ -2337,6 +2341,7 @@ static void *listening_get_next(struct seq_file *seq, void *cur) struct tcp_iter_state *st = seq->private; struct inet_listen_hashbucket *ilb2; struct hlist_nulls_node *node; + struct inet_hashinfo *hinfo; struct sock *sk = cur; ++st->num; @@ -2348,7 +2353,8 @@ static void *listening_get_next(struct seq_file *seq, void *cur) return sk; } - ilb2 = &tcp_hashinfo.lhash2[st->bucket]; + hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; + ilb2 = &hinfo->lhash2[st->bucket]; spin_unlock(&ilb2->lock); ++st->bucket; return listening_get_first(seq); @@ -2370,9 +2376,10 @@ static void *listening_get_idx(struct seq_file *seq, loff_t *pos) return rc; } -static inline bool empty_bucket(const struct tcp_iter_state *st) +static inline bool empty_bucket(struct inet_hashinfo *hinfo, + const struct tcp_iter_state *st) { - return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain); + return hlist_nulls_empty(&hinfo->ehash[st->bucket].chain); } /* @@ -2381,20 +2388,21 @@ static inline bool empty_bucket(const struct tcp_iter_state *st) */ static void *established_get_first(struct seq_file *seq) { + struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct tcp_iter_state *st = seq->private; st->offset = 0; - for (; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) { + for (; st->bucket <= hinfo->ehash_mask; ++st->bucket) { struct sock *sk; struct hlist_nulls_node *node; - spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket); + spinlock_t *lock = inet_ehash_lockp(hinfo, st->bucket); /* Lockless fast path for the common case of empty buckets */ - if (empty_bucket(st)) + if (empty_bucket(hinfo, st)) continue; spin_lock_bh(lock); - sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) { + sk_nulls_for_each(sk, node, &hinfo->ehash[st->bucket].chain) { if (seq_sk_match(seq, sk)) return sk; } @@ -2406,9 +2414,10 @@ static void *established_get_first(struct seq_file *seq) static void *established_get_next(struct seq_file *seq, void *cur) { - struct sock *sk = cur; - struct hlist_nulls_node *node; + struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct tcp_iter_state *st = seq->private; + struct hlist_nulls_node *node; + struct sock *sk = cur; ++st->num; ++st->offset; @@ -2420,7 +2429,7 @@ static void *established_get_next(struct seq_file *seq, void *cur) return sk; } - spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); + spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket)); ++st->bucket; return established_get_first(seq); } @@ -2458,6 +2467,7 @@ static void *tcp_get_idx(struct seq_file *seq, loff_t pos) static void *tcp_seek_last_pos(struct seq_file *seq) { + struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct tcp_iter_state *st = seq->private; int bucket = st->bucket; int offset = st->offset; @@ -2466,7 +2476,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq) switch (st->state) { case TCP_SEQ_STATE_LISTENING: - if (st->bucket > tcp_hashinfo.lhash2_mask) + if (st->bucket > hinfo->lhash2_mask) break; st->state = TCP_SEQ_STATE_LISTENING; rc = listening_get_first(seq); @@ -2478,7 +2488,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq) st->state = TCP_SEQ_STATE_ESTABLISHED; fallthrough; case TCP_SEQ_STATE_ESTABLISHED: - if (st->bucket > tcp_hashinfo.ehash_mask) + if (st->bucket > hinfo->ehash_mask) break; rc = established_get_first(seq); while (offset-- && rc && bucket == st->bucket) @@ -2546,16 +2556,17 @@ EXPORT_SYMBOL(tcp_seq_next); void tcp_seq_stop(struct seq_file *seq, void *v) { + struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct tcp_iter_state *st = seq->private; switch (st->state) { case TCP_SEQ_STATE_LISTENING: if (v != SEQ_START_TOKEN) - spin_unlock(&tcp_hashinfo.lhash2[st->bucket].lock); + spin_unlock(&hinfo->lhash2[st->bucket].lock); break; case TCP_SEQ_STATE_ESTABLISHED: if (v) - spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); + spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket)); break; } } @@ -2750,6 +2761,7 @@ static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter, static unsigned int bpf_iter_tcp_listening_batch(struct seq_file *seq, struct sock *start_sk) { + struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct bpf_tcp_iter_state *iter = seq->private; struct tcp_iter_state *st = &iter->state; struct hlist_nulls_node *node; @@ -2769,7 +2781,7 @@ static unsigned int bpf_iter_tcp_listening_batch(struct seq_file *seq, expected++; } } - spin_unlock(&tcp_hashinfo.lhash2[st->bucket].lock); + spin_unlock(&hinfo->lhash2[st->bucket].lock); return expected; } @@ -2777,6 +2789,7 @@ static unsigned int bpf_iter_tcp_listening_batch(struct seq_file *seq, static unsigned int bpf_iter_tcp_established_batch(struct seq_file *seq, struct sock *start_sk) { + struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct bpf_tcp_iter_state *iter = seq->private; struct tcp_iter_state *st = &iter->state; struct hlist_nulls_node *node; @@ -2796,13 +2809,14 @@ static unsigned int bpf_iter_tcp_established_batch(struct seq_file *seq, expected++; } } - spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); + spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket)); return expected; } static struct sock *bpf_iter_tcp_batch(struct seq_file *seq) { + struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct bpf_tcp_iter_state *iter = seq->private; struct tcp_iter_state *st = &iter->state; unsigned int expected; @@ -2818,7 +2832,7 @@ static struct sock *bpf_iter_tcp_batch(struct seq_file *seq) st->offset = 0; st->bucket++; if (st->state == TCP_SEQ_STATE_LISTENING && - st->bucket > tcp_hashinfo.lhash2_mask) { + st->bucket > hinfo->lhash2_mask) { st->state = TCP_SEQ_STATE_ESTABLISHED; st->bucket = 0; } @@ -3083,7 +3097,7 @@ struct proto tcp_prot = { .slab_flags = SLAB_TYPESAFE_BY_RCU, .twsk_prot = &tcp_timewait_sock_ops, .rsk_prot = &tcp_request_sock_ops, - .h.hashinfo = &tcp_hashinfo, + .h.hashinfo = NULL, .no_autobind = true, .diag_destroy = tcp_abort, }; @@ -3091,19 +3105,43 @@ EXPORT_SYMBOL(tcp_prot); static void __net_exit tcp_sk_exit(struct net *net) { - struct inet_timewait_death_row *tcp_death_row = net->ipv4.tcp_death_row; - if (net->ipv4.tcp_congestion_control) bpf_module_put(net->ipv4.tcp_congestion_control, net->ipv4.tcp_congestion_control->owner); - if (refcount_dec_and_test(&tcp_death_row->tw_refcount)) - kfree(tcp_death_row); } -static int __net_init tcp_sk_init(struct net *net) +static void __net_init tcp_set_hashinfo(struct net *net) { - int cnt; + struct inet_hashinfo *hinfo; + unsigned int ehash_entries; + struct net *old_net; + if (net_eq(net, &init_net)) + goto fallback; + + old_net = current->nsproxy->net_ns; + ehash_entries = READ_ONCE(old_net->ipv4.sysctl_tcp_child_ehash_entries); + if (!ehash_entries) + goto fallback; + + ehash_entries = roundup_pow_of_two(ehash_entries); + hinfo = inet_pernet_hashinfo_alloc(&tcp_hashinfo, ehash_entries); + if (!hinfo) { + pr_warn("Failed to allocate TCP ehash (entries: %u) " + "for a netns, fallback to the global one\n", + ehash_entries); +fallback: + hinfo = &tcp_hashinfo; + ehash_entries = tcp_hashinfo.ehash_mask + 1; + } + + net->ipv4.tcp_death_row.hashinfo = hinfo; + net->ipv4.tcp_death_row.sysctl_max_tw_buckets = ehash_entries / 2; + net->ipv4.sysctl_max_syn_backlog = max(128U, ehash_entries / 128); +} + +static int __net_init tcp_sk_init(struct net *net) +{ net->ipv4.sysctl_tcp_ecn = 2; net->ipv4.sysctl_tcp_ecn_fallback = 1; @@ -3129,15 +3167,9 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_tw_reuse = 2; net->ipv4.sysctl_tcp_no_ssthresh_metrics_save = 1; - net->ipv4.tcp_death_row = kzalloc(sizeof(struct inet_timewait_death_row), GFP_KERNEL); - if (!net->ipv4.tcp_death_row) - return -ENOMEM; - refcount_set(&net->ipv4.tcp_death_row->tw_refcount, 1); - cnt = tcp_hashinfo.ehash_mask + 1; - net->ipv4.tcp_death_row->sysctl_max_tw_buckets = cnt / 2; - net->ipv4.tcp_death_row->hashinfo = &tcp_hashinfo; + refcount_set(&net->ipv4.tcp_death_row.tw_refcount, 1); + tcp_set_hashinfo(net); - net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 128); net->ipv4.sysctl_tcp_sack = 1; net->ipv4.sysctl_tcp_window_scaling = 1; net->ipv4.sysctl_tcp_timestamps = 1; @@ -3199,10 +3231,13 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; - inet_twsk_purge(&tcp_hashinfo, AF_INET); + tcp_twsk_purge(net_exit_list, AF_INET); - list_for_each_entry(net, net_exit_list, exit_list) + list_for_each_entry(net, net_exit_list, exit_list) { + inet_pernet_hashinfo_free(net->ipv4.tcp_death_row.hashinfo); + WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount)); tcp_fastopen_ctx_destroy(net); + } } static struct pernet_operations __net_initdata tcp_sk_ops = { diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ddcdc2bc4c04..79f30f026d89 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -247,10 +247,10 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) { const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); + struct net *net = sock_net(sk); struct inet_timewait_sock *tw; - struct inet_timewait_death_row *tcp_death_row = sock_net(sk)->ipv4.tcp_death_row; - tw = inet_twsk_alloc(sk, tcp_death_row, state); + tw = inet_twsk_alloc(sk, &net->ipv4.tcp_death_row, state); if (tw) { struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); @@ -319,14 +319,14 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) /* Linkage updates. * Note that access to tw after this point is illegal. */ - inet_twsk_hashdance(tw, sk, &tcp_hashinfo); + inet_twsk_hashdance(tw, sk, net->ipv4.tcp_death_row.hashinfo); local_bh_enable(); } else { /* Sorry, if we're out of memory, just CLOSE this * socket up. We've got bigger problems than * non-graceful socket closings. */ - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEWAITOVERFLOW); + NET_INC_STATS(net, LINUX_MIB_TCPTIMEWAITOVERFLOW); } tcp_update_metrics(sk); @@ -347,6 +347,26 @@ void tcp_twsk_destructor(struct sock *sk) } EXPORT_SYMBOL_GPL(tcp_twsk_destructor); +void tcp_twsk_purge(struct list_head *net_exit_list, int family) +{ + bool purged_once = false; + struct net *net; + + list_for_each_entry(net, net_exit_list, exit_list) { + /* The last refcount is decremented in tcp_sk_exit_batch() */ + if (refcount_read(&net->ipv4.tcp_death_row.tw_refcount) == 1) + continue; + + if (net->ipv4.tcp_death_row.hashinfo->pernet) { + inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo, family); + } else if (!purged_once) { + inet_twsk_purge(&tcp_hashinfo, family); + purged_once = true; + } + } +} +EXPORT_SYMBOL_GPL(tcp_twsk_purge); + /* Warning : This function is called without sk_listener being locked. * Be sure to read socket fields once, as their value could change under us. */ diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index a844a0d38482..45dda7889387 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -255,7 +255,15 @@ found: mss = skb_shinfo(p)->gso_size; - flush |= (len - 1) >= mss; + /* If skb is a GRO packet, make sure its gso_size matches prior packet mss. + * If it is a single frame, do not aggregate it if its length + * is bigger than our mss. + */ + if (unlikely(skb_is_gso(skb))) + flush |= (mss != skb_shinfo(skb)->gso_size); + else + flush |= (len - 1) >= mss; + flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq); #ifdef CONFIG_TLS_DEVICE flush |= p->decrypted ^ skb->decrypted; @@ -269,7 +277,12 @@ found: tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH); out_check_final: - flush = len < mss; + /* Force a flush if last segment is smaller than mss. */ + if (unlikely(skb_is_gso(skb))) + flush = len != NAPI_GRO_CB(skb)->count * skb_shinfo(skb)->gso_size; + else + flush = len < mss; + flush |= (__force int)(flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST | TCP_FLAG_SYN | TCP_FLAG_FIN)); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 34eda973bbf1..d63118ce5900 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -783,6 +783,8 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) */ if (tunnel) { /* ...not for tunnels though: we don't have a sending socket */ + if (udp_sk(sk)->encap_err_rcv) + udp_sk(sk)->encap_err_rcv(sk, skb, iph->ihl << 2); goto out; } if (!inet->recverr) { @@ -1799,41 +1801,29 @@ EXPORT_SYMBOL(__skb_recv_udp); int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { - int copied = 0; - - while (1) { - struct sk_buff *skb; - int err, used; - - skb = skb_recv_udp(sk, MSG_DONTWAIT, &err); - if (!skb) - return err; + struct sk_buff *skb; + int err, copied; - if (udp_lib_checksum_complete(skb)) { - __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, - IS_UDPLITE(sk)); - __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, - IS_UDPLITE(sk)); - atomic_inc(&sk->sk_drops); - kfree_skb(skb); - continue; - } +try_again: + skb = skb_recv_udp(sk, MSG_DONTWAIT, &err); + if (!skb) + return err; - WARN_ON(!skb_set_owner_sk_safe(skb, sk)); - used = recv_actor(sk, skb); - if (used <= 0) { - if (!copied) - copied = used; - kfree_skb(skb); - break; - } else if (used <= skb->len) { - copied += used; - } + if (udp_lib_checksum_complete(skb)) { + int is_udplite = IS_UDPLITE(sk); + struct net *net = sock_net(sk); + __UDP_INC_STATS(net, UDP_MIB_CSUMERRORS, is_udplite); + __UDP_INC_STATS(net, UDP_MIB_INERRORS, is_udplite); + atomic_inc(&sk->sk_drops); kfree_skb(skb); - break; + goto try_again; } + WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); + copied = recv_actor(sk, skb); + kfree_skb(skb); + return copied; } EXPORT_SYMBOL(udp_read_skb); diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index 8efaf8c3fe2a..8242c8947340 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -72,6 +72,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, udp_sk(sk)->encap_type = cfg->encap_type; udp_sk(sk)->encap_rcv = cfg->encap_rcv; + udp_sk(sk)->encap_err_rcv = cfg->encap_err_rcv; udp_sk(sk)->encap_err_lookup = cfg->encap_err_lookup; udp_sk(sk)->encap_destroy = cfg->encap_destroy; udp_sk(sk)->gro_receive = cfg->gro_receive; diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c index 9d4f418f1bf8..8489fa106583 100644 --- a/net/ipv4/xfrm4_tunnel.c +++ b/net/ipv4/xfrm4_tunnel.c @@ -22,13 +22,17 @@ static int ipip_xfrm_rcv(struct xfrm_state *x, struct sk_buff *skb) return ip_hdr(skb)->protocol; } -static int ipip_init_state(struct xfrm_state *x) +static int ipip_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) { - if (x->props.mode != XFRM_MODE_TUNNEL) + if (x->props.mode != XFRM_MODE_TUNNEL) { + NL_SET_ERR_MSG(extack, "IPv4 tunnel can only be used with tunnel mode"); return -EINVAL; + } - if (x->encap) + if (x->encap) { + NL_SET_ERR_MSG(extack, "IPv4 tunnel is not compatible with encapsulation"); return -EINVAL; + } x->props.header_len = sizeof(struct iphdr); |