diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/af_inet.c | 8 | ||||
-rw-r--r-- | net/ipv4/arp.c | 17 | ||||
-rw-r--r-- | net/ipv4/fib_frontend.c | 9 | ||||
-rw-r--r-- | net/ipv4/fib_trie.c | 48 | ||||
-rw-r--r-- | net/ipv4/igmp.c | 33 | ||||
-rw-r--r-- | net/ipv4/ip_gre.c | 4 | ||||
-rw-r--r-- | net/ipv4/ip_output.c | 11 | ||||
-rw-r--r-- | net/ipv4/ip_sockglue.c | 2 | ||||
-rw-r--r-- | net/ipv4/ip_tunnel.c | 8 | ||||
-rw-r--r-- | net/ipv4/ipconfig.c | 14 | ||||
-rw-r--r-- | net/ipv4/ipmr.c | 32 | ||||
-rw-r--r-- | net/ipv4/ipmr_base.c | 5 | ||||
-rw-r--r-- | net/ipv4/netfilter/ip_tables.c | 1 | ||||
-rw-r--r-- | net/ipv4/netfilter/ipt_rpfilter.c | 2 | ||||
-rw-r--r-- | net/ipv4/ping.c | 59 | ||||
-rw-r--r-- | net/ipv4/proc.c | 48 | ||||
-rw-r--r-- | net/ipv4/raw.c | 45 | ||||
-rw-r--r-- | net/ipv4/route.c | 141 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 38 | ||||
-rw-r--r-- | net/ipv4/tcp_bbr.c | 4 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 7 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 82 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 7 | ||||
-rw-r--r-- | net/ipv4/udp.c | 115 | ||||
-rw-r--r-- | net/ipv4/udplite.c | 21 |
25 files changed, 236 insertions, 525 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index eaed0367e669..8a59428e63ab 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -986,7 +986,7 @@ const struct proto_ops inet_stream_ops = { .socketpair = sock_no_socketpair, .accept = inet_accept, .getname = inet_getname, - .poll = tcp_poll, + .poll_mask = tcp_poll_mask, .ioctl = inet_ioctl, .listen = inet_listen, .shutdown = inet_shutdown, @@ -1018,7 +1018,7 @@ const struct proto_ops inet_dgram_ops = { .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = inet_getname, - .poll = udp_poll, + .poll_mask = udp_poll_mask, .ioctl = inet_ioctl, .listen = sock_no_listen, .shutdown = inet_shutdown, @@ -1039,7 +1039,7 @@ EXPORT_SYMBOL(inet_dgram_ops); /* * For SOCK_RAW sockets; should be the same as inet_dgram_ops but without - * udp_poll + * udp_poll_mask */ static const struct proto_ops inet_sockraw_ops = { .family = PF_INET, @@ -1050,7 +1050,7 @@ static const struct proto_ops inet_sockraw_ops = { .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = inet_getname, - .poll = datagram_poll, + .poll_mask = datagram_poll_mask, .ioctl = inet_ioctl, .listen = sock_no_listen, .shutdown = inet_shutdown, diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index bf6c2d4d4fdc..e90c89ef8c08 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1418,23 +1418,12 @@ static const struct seq_operations arp_seq_ops = { .show = arp_seq_show, }; -static int arp_seq_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &arp_seq_ops, - sizeof(struct neigh_seq_state)); -} - -static const struct file_operations arp_seq_fops = { - .open = arp_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; - +/* ------------------------------------------------------------------------ */ static int __net_init arp_net_init(struct net *net) { - if (!proc_create("arp", 0444, net->proc_net, &arp_seq_fops)) + if (!proc_create_net("arp", 0444, net->proc_net, &arp_seq_ops, + sizeof(struct neigh_seq_state))) return -ENOMEM; return 0; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index f05afaf3235c..e66172aaf241 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -326,10 +326,11 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, int rpf, struct in_device *idev, u32 *itag) { + struct net *net = dev_net(dev); + struct flow_keys flkeys; int ret, no_addr; struct fib_result res; struct flowi4 fl4; - struct net *net = dev_net(dev); bool dev_match; fl4.flowi4_oif = 0; @@ -347,6 +348,11 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, no_addr = idev->ifa_list == NULL; fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0; + if (!fib4_rules_early_flow_dissect(net, skb, &fl4, &flkeys)) { + fl4.flowi4_proto = 0; + fl4.fl4_sport = 0; + fl4.fl4_dport = 0; + } trace_fib_validate_source(dev, &fl4); @@ -643,6 +649,7 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { [RTA_ENCAP] = { .type = NLA_NESTED }, [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, + [RTA_TABLE] = { .type = NLA_U32 }, }; static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 3dcffd3ce98c..99c23a0cb8ca 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2348,18 +2348,6 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v) return 0; } -static int fib_triestat_seq_open(struct inode *inode, struct file *file) -{ - return single_open_net(inode, file, fib_triestat_seq_show); -} - -static const struct file_operations fib_triestat_fops = { - .open = fib_triestat_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release_net, -}; - static struct key_vector *fib_trie_get_idx(struct seq_file *seq, loff_t pos) { struct fib_trie_iter *iter = seq->private; @@ -2533,19 +2521,6 @@ static const struct seq_operations fib_trie_seq_ops = { .show = fib_trie_seq_show, }; -static int fib_trie_seq_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &fib_trie_seq_ops, - sizeof(struct fib_trie_iter)); -} - -static const struct file_operations fib_trie_fops = { - .open = fib_trie_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; - struct fib_route_iter { struct seq_net_private p; struct fib_table *main_tb; @@ -2726,29 +2701,18 @@ static const struct seq_operations fib_route_seq_ops = { .show = fib_route_seq_show, }; -static int fib_route_seq_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &fib_route_seq_ops, - sizeof(struct fib_route_iter)); -} - -static const struct file_operations fib_route_fops = { - .open = fib_route_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; - int __net_init fib_proc_init(struct net *net) { - if (!proc_create("fib_trie", 0444, net->proc_net, &fib_trie_fops)) + if (!proc_create_net("fib_trie", 0444, net->proc_net, &fib_trie_seq_ops, + sizeof(struct fib_trie_iter))) goto out1; - if (!proc_create("fib_triestat", 0444, net->proc_net, - &fib_triestat_fops)) + if (!proc_create_net_single("fib_triestat", 0444, net->proc_net, + fib_triestat_seq_show, NULL)) goto out2; - if (!proc_create("route", 0444, net->proc_net, &fib_route_fops)) + if (!proc_create_net("route", 0444, net->proc_net, &fib_route_seq_ops, + sizeof(struct fib_route_iter))) goto out3; return 0; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index b26a81a7de42..85b617b655bc 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2829,19 +2829,6 @@ static const struct seq_operations igmp_mc_seq_ops = { .show = igmp_mc_seq_show, }; -static int igmp_mc_seq_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &igmp_mc_seq_ops, - sizeof(struct igmp_mc_iter_state)); -} - -static const struct file_operations igmp_mc_seq_fops = { - .open = igmp_mc_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; - struct igmp_mcf_iter_state { struct seq_net_private p; struct net_device *dev; @@ -2975,29 +2962,17 @@ static const struct seq_operations igmp_mcf_seq_ops = { .show = igmp_mcf_seq_show, }; -static int igmp_mcf_seq_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &igmp_mcf_seq_ops, - sizeof(struct igmp_mcf_iter_state)); -} - -static const struct file_operations igmp_mcf_seq_fops = { - .open = igmp_mcf_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; - static int __net_init igmp_net_init(struct net *net) { struct proc_dir_entry *pde; int err; - pde = proc_create("igmp", 0444, net->proc_net, &igmp_mc_seq_fops); + pde = proc_create_net("igmp", 0444, net->proc_net, &igmp_mc_seq_ops, + sizeof(struct igmp_mc_iter_state)); if (!pde) goto out_igmp; - pde = proc_create("mcfilter", 0444, net->proc_net, - &igmp_mcf_seq_fops); + pde = proc_create_net("mcfilter", 0444, net->proc_net, + &igmp_mcf_seq_ops, sizeof(struct igmp_mcf_iter_state)); if (!pde) goto out_mcfilter; err = inet_ctl_sock_create(&net->ipv4.mc_autojoin_sk, AF_INET, diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 9c169bb2444d..f200b304f76c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -722,10 +722,12 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, erspan_build_header(skb, ntohl(tunnel->parms.o_key), tunnel->index, truncate, true); - else + else if (tunnel->erspan_ver == 2) erspan_build_header_v2(skb, ntohl(tunnel->parms.o_key), tunnel->dir, tunnel->hwid, truncate, true); + else + goto free_skb; tunnel->parms.o_flags &= ~TUNNEL_KEY; __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_ERSPAN)); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 4c11b810a447..d54abc097800 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1045,7 +1045,8 @@ alloc_new_skb: if (copy > length) copy = length; - if (!(rt->dst.dev->features&NETIF_F_SG)) { + if (!(rt->dst.dev->features&NETIF_F_SG) && + skb_tailroom(skb) >= copy) { unsigned int off; off = skb->len; @@ -1109,6 +1110,10 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, struct ip_options_rcu *opt; struct rtable *rt; + rt = *rtp; + if (unlikely(!rt)) + return -EFAULT; + /* * setup for corking. */ @@ -1124,9 +1129,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->flags |= IPCORK_OPT; cork->addr = ipc->addr; } - rt = *rtp; - if (unlikely(!rt)) - return -EFAULT; + /* * We steal reference to this route, caller should not release it */ diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 5ad2d8ed3a3f..57bbb060faaf 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -505,8 +505,6 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) int err; int copied; - WARN_ON_ONCE(sk->sk_family == AF_INET6); - err = -EAGAIN; skb = sock_dequeue_err_skb(sk); if (!skb) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 6b0e362cc99b..38d906baf1df 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -328,7 +328,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) if (tdev) { hlen = tdev->hard_header_len + tdev->needed_headroom; - mtu = tdev->mtu; + mtu = min(tdev->mtu, IP_MAX_MTU); } dev->needed_headroom = t_hlen + hlen; @@ -362,7 +362,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net, nt = netdev_priv(dev); t_hlen = nt->hlen + sizeof(struct iphdr); dev->min_mtu = ETH_MIN_MTU; - dev->max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen; + dev->max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen; ip_tunnel_add(itn, nt); return nt; @@ -930,7 +930,7 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); - int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen; + int max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen; if (new_mtu < ETH_MIN_MTU) return -EINVAL; @@ -1107,7 +1107,7 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], mtu = ip_tunnel_bind_dev(dev); if (tb[IFLA_MTU]) { - unsigned int max = 0xfff8 - dev->hard_header_len - nt->hlen; + unsigned int max = IP_MAX_MTU - dev->hard_header_len - nt->hlen; mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, (unsigned int)(max - sizeof(struct iphdr))); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 43f620feb1c4..bbcbcc113d19 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1282,18 +1282,6 @@ static int pnp_seq_show(struct seq_file *seq, void *v) &ic_servaddr); return 0; } - -static int pnp_seq_open(struct inode *indoe, struct file *file) -{ - return single_open(file, pnp_seq_show, NULL); -} - -static const struct file_operations pnp_seq_fops = { - .open = pnp_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; #endif /* CONFIG_PROC_FS */ /* @@ -1369,7 +1357,7 @@ static int __init ip_auto_config(void) unsigned int i; #ifdef CONFIG_PROC_FS - proc_create("pnp", 0444, init_net.proc_net, &pnp_seq_fops); + proc_create_single("pnp", 0444, init_net.proc_net, pnp_seq_show); #endif /* CONFIG_PROC_FS */ if (!ic_enable) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 2fb4de3f7f66..37c4f885ff7b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2828,19 +2828,6 @@ static const struct seq_operations ipmr_vif_seq_ops = { .show = ipmr_vif_seq_show, }; -static int ipmr_vif_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &ipmr_vif_seq_ops, - sizeof(struct mr_vif_iter)); -} - -static const struct file_operations ipmr_vif_fops = { - .open = ipmr_vif_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; - static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); @@ -2900,19 +2887,6 @@ static const struct seq_operations ipmr_mfc_seq_ops = { .stop = mr_mfc_seq_stop, .show = ipmr_mfc_seq_show, }; - -static int ipmr_mfc_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &ipmr_mfc_seq_ops, - sizeof(struct mr_mfc_iter)); -} - -static const struct file_operations ipmr_mfc_fops = { - .open = ipmr_mfc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; #endif #ifdef CONFIG_IP_PIMSM_V2 @@ -2977,9 +2951,11 @@ static int __net_init ipmr_net_init(struct net *net) #ifdef CONFIG_PROC_FS err = -ENOMEM; - if (!proc_create("ip_mr_vif", 0, net->proc_net, &ipmr_vif_fops)) + if (!proc_create_net("ip_mr_vif", 0, net->proc_net, &ipmr_vif_seq_ops, + sizeof(struct mr_vif_iter))) goto proc_vif_fail; - if (!proc_create("ip_mr_cache", 0, net->proc_net, &ipmr_mfc_fops)) + if (!proc_create_net("ip_mr_cache", 0, net->proc_net, &ipmr_mfc_seq_ops, + sizeof(struct mr_mfc_iter))) goto proc_cache_fail; #endif return 0; diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index 4fe97723b53f..30221701614c 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -43,7 +43,10 @@ mr_table_alloc(struct net *net, u32 id, write_pnet(&mrt->net, net); mrt->ops = *ops; - rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params); + if (rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params)) { + kfree(mrt); + return NULL; + } INIT_LIST_HEAD(&mrt->mfc_cache_list); INIT_LIST_HEAD(&mrt->mfc_unres_queue); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 44b308d93ec2..e85f35b89c49 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -34,6 +34,7 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("IPv4 packet filter"); +MODULE_ALIAS("ipt_icmp"); void *ipt_alloc_initial_table(const struct xt_table *info) { diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index fd01f13c896a..12843c9ef142 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -89,10 +89,10 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) return true ^ invert; } + memset(&flow, 0, sizeof(flow)); flow.flowi4_iif = LOOPBACK_IFINDEX; flow.daddr = iph->saddr; flow.saddr = rpfilter_get_saddr(iph->daddr); - flow.flowi4_oif = 0; flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; flow.flowi4_tos = RT_TOS(iph->tos); flow.flowi4_scope = RT_SCOPE_UNIVERSE; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 05e47d777009..2ed64bca54e3 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -775,8 +775,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc.addr = faddr = daddr; if (ipc.opt && ipc.opt->opt.srr) { - if (!daddr) - return -EINVAL; + if (!daddr) { + err = -EINVAL; + goto out_free; + } faddr = ipc.opt->opt.faddr; } tos = get_rttos(&ipc, inet); @@ -842,6 +844,7 @@ back_from_confirm: out: ip_rt_put(rt); +out_free: if (free) kfree(ipc.opt); if (!err) { @@ -1147,58 +1150,24 @@ static int ping_v4_seq_show(struct seq_file *seq, void *v) return 0; } -static int ping_seq_open(struct inode *inode, struct file *file) -{ - struct ping_seq_afinfo *afinfo = PDE_DATA(inode); - return seq_open_net(inode, file, &afinfo->seq_ops, - sizeof(struct ping_iter_state)); -} - -const struct file_operations ping_seq_fops = { - .open = ping_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; -EXPORT_SYMBOL_GPL(ping_seq_fops); - -static struct ping_seq_afinfo ping_v4_seq_afinfo = { - .name = "icmp", - .family = AF_INET, - .seq_fops = &ping_seq_fops, - .seq_ops = { - .start = ping_v4_seq_start, - .show = ping_v4_seq_show, - .next = ping_seq_next, - .stop = ping_seq_stop, - }, +static const struct seq_operations ping_v4_seq_ops = { + .start = ping_v4_seq_start, + .show = ping_v4_seq_show, + .next = ping_seq_next, + .stop = ping_seq_stop, }; -int ping_proc_register(struct net *net, struct ping_seq_afinfo *afinfo) +static int __net_init ping_v4_proc_init_net(struct net *net) { - struct proc_dir_entry *p; - p = proc_create_data(afinfo->name, 0444, net->proc_net, - afinfo->seq_fops, afinfo); - if (!p) + if (!proc_create_net("icmp", 0444, net->proc_net, &ping_v4_seq_ops, + sizeof(struct ping_iter_state))) return -ENOMEM; return 0; } -EXPORT_SYMBOL_GPL(ping_proc_register); - -void ping_proc_unregister(struct net *net, struct ping_seq_afinfo *afinfo) -{ - remove_proc_entry(afinfo->name, net->proc_net); -} -EXPORT_SYMBOL_GPL(ping_proc_unregister); - -static int __net_init ping_v4_proc_init_net(struct net *net) -{ - return ping_proc_register(net, &ping_v4_seq_afinfo); -} static void __net_exit ping_v4_proc_exit_net(struct net *net) { - ping_proc_unregister(net, &ping_v4_seq_afinfo); + remove_proc_entry("icmp", net->proc_net); } static struct pernet_operations ping_v4_net_ops = { diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index a058de677e94..573e43c8ed87 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -77,18 +77,6 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) return 0; } -static int sockstat_seq_open(struct inode *inode, struct file *file) -{ - return single_open_net(inode, file, sockstat_seq_show); -} - -static const struct file_operations sockstat_seq_fops = { - .open = sockstat_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release_net, -}; - /* snmp items */ static const struct snmp_mib snmp4_ipstats_list[] = { SNMP_MIB_ITEM("InReceives", IPSTATS_MIB_INPKTS), @@ -460,20 +448,6 @@ static int snmp_seq_show(struct seq_file *seq, void *v) return 0; } -static int snmp_seq_open(struct inode *inode, struct file *file) -{ - return single_open_net(inode, file, snmp_seq_show); -} - -static const struct file_operations snmp_seq_fops = { - .open = snmp_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release_net, -}; - - - /* * Output /proc/net/netstat */ @@ -507,26 +481,16 @@ static int netstat_seq_show(struct seq_file *seq, void *v) return 0; } -static int netstat_seq_open(struct inode *inode, struct file *file) -{ - return single_open_net(inode, file, netstat_seq_show); -} - -static const struct file_operations netstat_seq_fops = { - .open = netstat_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release_net, -}; - static __net_init int ip_proc_init_net(struct net *net) { - if (!proc_create("sockstat", 0444, net->proc_net, - &sockstat_seq_fops)) + if (!proc_create_net_single("sockstat", 0444, net->proc_net, + sockstat_seq_show, NULL)) goto out_sockstat; - if (!proc_create("netstat", 0444, net->proc_net, &netstat_seq_fops)) + if (!proc_create_net_single("netstat", 0444, net->proc_net, + netstat_seq_show, NULL)) goto out_netstat; - if (!proc_create("snmp", 0444, net->proc_net, &snmp_seq_fops)) + if (!proc_create_net_single("snmp", 0444, net->proc_net, snmp_seq_show, + NULL)) goto out_snmp; return 0; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 1b4d3355624a..abb3c9490c55 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -1003,11 +1003,12 @@ struct proto raw_prot = { static struct sock *raw_get_first(struct seq_file *seq) { struct sock *sk; + struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file)); struct raw_iter_state *state = raw_seq_private(seq); for (state->bucket = 0; state->bucket < RAW_HTABLE_SIZE; ++state->bucket) { - sk_for_each(sk, &state->h->ht[state->bucket]) + sk_for_each(sk, &h->ht[state->bucket]) if (sock_net(sk) == seq_file_net(seq)) goto found; } @@ -1018,6 +1019,7 @@ found: static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk) { + struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file)); struct raw_iter_state *state = raw_seq_private(seq); do { @@ -1027,7 +1029,7 @@ try_again: } while (sk && sock_net(sk) != seq_file_net(seq)); if (!sk && ++state->bucket < RAW_HTABLE_SIZE) { - sk = sk_head(&state->h->ht[state->bucket]); + sk = sk_head(&h->ht[state->bucket]); goto try_again; } return sk; @@ -1045,9 +1047,9 @@ static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos) void *raw_seq_start(struct seq_file *seq, loff_t *pos) { - struct raw_iter_state *state = raw_seq_private(seq); + struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file)); - read_lock(&state->h->lock); + read_lock(&h->lock); return *pos ? raw_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } EXPORT_SYMBOL_GPL(raw_seq_start); @@ -1067,9 +1069,9 @@ EXPORT_SYMBOL_GPL(raw_seq_next); void raw_seq_stop(struct seq_file *seq, void *v) { - struct raw_iter_state *state = raw_seq_private(seq); + struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file)); - read_unlock(&state->h->lock); + read_unlock(&h->lock); } EXPORT_SYMBOL_GPL(raw_seq_stop); @@ -1110,37 +1112,10 @@ static const struct seq_operations raw_seq_ops = { .show = raw_seq_show, }; -int raw_seq_open(struct inode *ino, struct file *file, - struct raw_hashinfo *h, const struct seq_operations *ops) -{ - int err; - struct raw_iter_state *i; - - err = seq_open_net(ino, file, ops, sizeof(struct raw_iter_state)); - if (err < 0) - return err; - - i = raw_seq_private((struct seq_file *)file->private_data); - i->h = h; - return 0; -} -EXPORT_SYMBOL_GPL(raw_seq_open); - -static int raw_v4_seq_open(struct inode *inode, struct file *file) -{ - return raw_seq_open(inode, file, &raw_v4_hashinfo, &raw_seq_ops); -} - -static const struct file_operations raw_seq_fops = { - .open = raw_v4_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; - static __net_init int raw_init_net(struct net *net) { - if (!proc_create("raw", 0444, net->proc_net, &raw_seq_fops)) + if (!proc_create_net_data("raw", 0444, net->proc_net, &raw_seq_ops, + sizeof(struct raw_iter_state), &raw_v4_hashinfo)) return -ENOMEM; return 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ccb25d80f679..75fb8864be67 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -360,18 +360,6 @@ static int rt_acct_proc_show(struct seq_file *m, void *v) kfree(dst); return 0; } - -static int rt_acct_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, rt_acct_proc_show, NULL); -} - -static const struct file_operations rt_acct_proc_fops = { - .open = rt_acct_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; #endif static int __net_init ip_rt_do_proc_init(struct net *net) @@ -389,7 +377,8 @@ static int __net_init ip_rt_do_proc_init(struct net *net) goto err2; #ifdef CONFIG_IP_ROUTE_CLASSID - pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops); + pde = proc_create_single("rt_acct", 0, net->proc_net, + rt_acct_proc_show); if (!pde) goto err3; #endif @@ -709,7 +698,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; fnhe->fnhe_mtu_locked = lock; - fnhe->fnhe_expires = expires; + fnhe->fnhe_expires = max(1UL, expires); /* Exception created; mark the cached routes for the nexthop * stale, so anyone caching it rechecks if this exception @@ -1297,6 +1286,36 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } +static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) +{ + struct fnhe_hash_bucket *hash; + struct fib_nh_exception *fnhe, __rcu **fnhe_p; + u32 hval = fnhe_hashfun(daddr); + + spin_lock_bh(&fnhe_lock); + + hash = rcu_dereference_protected(nh->nh_exceptions, + lockdep_is_held(&fnhe_lock)); + hash += hval; + + fnhe_p = &hash->chain; + fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); + while (fnhe) { + if (fnhe->fnhe_daddr == daddr) { + rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( + fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); + fnhe_flush_routes(fnhe); + kfree_rcu(fnhe, rcu); + break; + } + fnhe_p = &fnhe->fnhe_next; + fnhe = rcu_dereference_protected(fnhe->fnhe_next, + lockdep_is_held(&fnhe_lock)); + } + + spin_unlock_bh(&fnhe_lock); +} + static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) { struct fnhe_hash_bucket *hash = rcu_dereference(nh->nh_exceptions); @@ -1310,8 +1329,14 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) for (fnhe = rcu_dereference(hash[hval].chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { - if (fnhe->fnhe_daddr == daddr) + if (fnhe->fnhe_daddr == daddr) { + if (fnhe->fnhe_expires && + time_after(jiffies, fnhe->fnhe_expires)) { + ip_del_fnhe(nh, daddr); + break; + } return fnhe; + } } return NULL; } @@ -1339,6 +1364,7 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, fnhe->fnhe_gw = 0; fnhe->fnhe_pmtu = 0; fnhe->fnhe_expires = 0; + fnhe->fnhe_mtu_locked = false; fnhe_flush_routes(fnhe); orig = NULL; } @@ -1636,36 +1662,6 @@ static void ip_handle_martian_source(struct net_device *dev, #endif } -static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) -{ - struct fnhe_hash_bucket *hash; - struct fib_nh_exception *fnhe, __rcu **fnhe_p; - u32 hval = fnhe_hashfun(daddr); - - spin_lock_bh(&fnhe_lock); - - hash = rcu_dereference_protected(nh->nh_exceptions, - lockdep_is_held(&fnhe_lock)); - hash += hval; - - fnhe_p = &hash->chain; - fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); - while (fnhe) { - if (fnhe->fnhe_daddr == daddr) { - rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( - fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); - fnhe_flush_routes(fnhe); - kfree_rcu(fnhe, rcu); - break; - } - fnhe_p = &fnhe->fnhe_next; - fnhe = rcu_dereference_protected(fnhe->fnhe_next, - lockdep_is_held(&fnhe_lock)); - } - - spin_unlock_bh(&fnhe_lock); -} - /* called in rcu_read_lock() section */ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, @@ -1719,20 +1715,10 @@ static int __mkroute_input(struct sk_buff *skb, fnhe = find_exception(&FIB_RES_NH(*res), daddr); if (do_cache) { - if (fnhe) { + if (fnhe) rth = rcu_dereference(fnhe->fnhe_rth_input); - if (rth && rth->dst.expires && - time_after(jiffies, rth->dst.expires)) { - ip_del_fnhe(&FIB_RES_NH(*res), daddr); - fnhe = NULL; - } else { - goto rt_cache; - } - } - - rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); - -rt_cache: + else + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; @@ -1964,8 +1950,13 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.saddr = saddr; fl4.flowi4_uid = sock_net_uid(net, NULL); - if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) + if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) { flkeys = &_flkeys; + } else { + fl4.flowi4_proto = 0; + fl4.fl4_sport = 0; + fl4.fl4_dport = 0; + } err = fib_lookup(net, &fl4, res, 0); if (err != 0) { @@ -2216,39 +2207,31 @@ static struct rtable *__mkroute_output(const struct fib_result *res, * the loopback interface and the IP_PKTINFO ipi_ifindex will * be set to the loopback interface as well. */ - fi = NULL; + do_cache = false; } fnhe = NULL; do_cache &= fi != NULL; - if (do_cache) { + if (fi) { struct rtable __rcu **prth; struct fib_nh *nh = &FIB_RES_NH(*res); fnhe = find_exception(nh, fl4->daddr); + if (!do_cache) + goto add; if (fnhe) { prth = &fnhe->fnhe_rth_output; - rth = rcu_dereference(*prth); - if (rth && rth->dst.expires && - time_after(jiffies, rth->dst.expires)) { - ip_del_fnhe(nh, fl4->daddr); - fnhe = NULL; - } else { - goto rt_cache; + } else { + if (unlikely(fl4->flowi4_flags & + FLOWI_FLAG_KNOWN_NH && + !(nh->nh_gw && + nh->nh_scope == RT_SCOPE_LINK))) { + do_cache = false; + goto add; } + prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); } - - if (unlikely(fl4->flowi4_flags & - FLOWI_FLAG_KNOWN_NH && - !(nh->nh_gw && - nh->nh_scope == RT_SCOPE_LINK))) { - do_cache = false; - goto add; - } - prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); rth = rcu_dereference(*prth); - -rt_cache: if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst)) return rth; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bccc4c270087..dec47e6789e7 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -494,32 +494,21 @@ static inline bool tcp_stream_is_readable(const struct tcp_sock *tp, } /* - * Wait for a TCP event. - * - * Note that we don't need to lock the socket, as the upper poll layers - * take care of normal races (between the test and the event) and we don't - * go look at any of the socket buffers directly. + * Socket is not locked. We are protected from async events by poll logic and + * correct handling of state changes made by other threads is impossible in + * any case. */ -__poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) +__poll_t tcp_poll_mask(struct socket *sock, __poll_t events) { - __poll_t mask; struct sock *sk = sock->sk; const struct tcp_sock *tp = tcp_sk(sk); + __poll_t mask = 0; int state; - sock_poll_wait(file, sk_sleep(sk), wait); - state = inet_sk_state_load(sk); if (state == TCP_LISTEN) return inet_csk_listen_poll(sk); - /* Socket is not locked. We are protected from async events - * by poll logic and correct handling of state changes - * made by other threads is impossible in any case. - */ - - mask = 0; - /* * EPOLLHUP is certainly not done right. But poll() doesn't * have a notion of HUP in just one direction, and for a @@ -600,7 +589,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) return mask; } -EXPORT_SYMBOL(tcp_poll); +EXPORT_SYMBOL(tcp_poll_mask); int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) { @@ -697,7 +686,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, { return skb->len < size_goal && sock_net(sk)->ipv4.sysctl_tcp_autocorking && - skb != tcp_write_queue_head(sk) && + !tcp_rtx_queue_empty(sk) && refcount_read(&sk->sk_wmem_alloc) > skb->truesize; } @@ -1204,7 +1193,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) uarg->zerocopy = 0; } - if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) { + if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) && + !tp->repair) { err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); if (err == -EINPROGRESS && copied_syn > 0) goto out; @@ -2368,6 +2358,7 @@ void tcp_write_queue_purge(struct sock *sk) INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); sk_mem_reclaim(sk); tcp_clear_all_retrans_hints(tcp_sk(sk)); + tcp_sk(sk)->packets_out = 0; } int tcp_disconnect(struct sock *sk, int flags) @@ -2417,7 +2408,6 @@ int tcp_disconnect(struct sock *sk, int flags) icsk->icsk_backoff = 0; tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; - tp->packets_out = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_cnt = 0; tp->window_clamp = 0; @@ -2673,7 +2663,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_REPAIR_QUEUE: if (!tp->repair) err = -EPERM; - else if (val < TCP_QUEUES_NR) + else if ((unsigned int)val < TCP_QUEUES_NR) tp->repair_queue = val; else err = -EINVAL; @@ -2813,8 +2803,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: case TCP_MD5SIG_EXT: - /* Read the IP->Key mappings from userspace */ - err = tp->af_specific->md5_parse(sk, optname, optval, optlen); + if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) + err = tp->af_specific->md5_parse(sk, optname, optval, optlen); + else + err = -EINVAL; break; #endif case TCP_USER_TIMEOUT: diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 158d105e76da..58e2f479ffb4 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -806,7 +806,9 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) } } } - bbr->idle_restart = 0; + /* Restart after idle ends only once we process a new S/ACK for data */ + if (rs->delivered > 0) + bbr->idle_restart = 0; } static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 367def6ddeda..e51c644484dc 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3868,11 +3868,8 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th) int length = (th->doff << 2) - sizeof(*th); const u8 *ptr = (const u8 *)(th + 1); - /* If the TCP option is too short, we can short cut */ - if (length < TCPOLEN_MD5SIG) - return NULL; - - while (length > 0) { + /* If not enough data remaining, we can short cut */ + while (length >= TCPOLEN_MD5SIG) { int opcode = *ptr++; int opsize; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f70586b50838..2c970626b398 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1961,6 +1961,7 @@ EXPORT_SYMBOL(tcp_v4_destroy_sock); */ static void *listening_get_next(struct seq_file *seq, void *cur) { + struct tcp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file)); struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); struct inet_listen_hashbucket *ilb; @@ -1983,7 +1984,7 @@ get_sk: sk_for_each_from(sk) { if (!net_eq(sock_net(sk), net)) continue; - if (sk->sk_family == st->family) + if (sk->sk_family == afinfo->family) return sk; } spin_unlock(&ilb->lock); @@ -2020,6 +2021,7 @@ static inline bool empty_bucket(const struct tcp_iter_state *st) */ static void *established_get_first(struct seq_file *seq) { + struct tcp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file)); struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); void *rc = NULL; @@ -2036,7 +2038,7 @@ static void *established_get_first(struct seq_file *seq) spin_lock_bh(lock); sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) { - if (sk->sk_family != st->family || + if (sk->sk_family != afinfo->family || !net_eq(sock_net(sk), net)) { continue; } @@ -2051,6 +2053,7 @@ out: static void *established_get_next(struct seq_file *seq, void *cur) { + struct tcp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file)); struct sock *sk = cur; struct hlist_nulls_node *node; struct tcp_iter_state *st = seq->private; @@ -2062,7 +2065,8 @@ static void *established_get_next(struct seq_file *seq, void *cur) sk = sk_nulls_next(sk); sk_nulls_for_each_from(sk, node) { - if (sk->sk_family == st->family && net_eq(sock_net(sk), net)) + if (sk->sk_family == afinfo->family && + net_eq(sock_net(sk), net)) return sk; } @@ -2135,7 +2139,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq) return rc; } -static void *tcp_seq_start(struct seq_file *seq, loff_t *pos) +void *tcp_seq_start(struct seq_file *seq, loff_t *pos) { struct tcp_iter_state *st = seq->private; void *rc; @@ -2156,8 +2160,9 @@ out: st->last_pos = *pos; return rc; } +EXPORT_SYMBOL(tcp_seq_start); -static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) +void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct tcp_iter_state *st = seq->private; void *rc = NULL; @@ -2186,8 +2191,9 @@ out: st->last_pos = *pos; return rc; } +EXPORT_SYMBOL(tcp_seq_next); -static void tcp_seq_stop(struct seq_file *seq, void *v) +void tcp_seq_stop(struct seq_file *seq, void *v) { struct tcp_iter_state *st = seq->private; @@ -2202,47 +2208,7 @@ static void tcp_seq_stop(struct seq_file *seq, void *v) break; } } - -int tcp_seq_open(struct inode *inode, struct file *file) -{ - struct tcp_seq_afinfo *afinfo = PDE_DATA(inode); - struct tcp_iter_state *s; - int err; - - err = seq_open_net(inode, file, &afinfo->seq_ops, - sizeof(struct tcp_iter_state)); - if (err < 0) - return err; - - s = ((struct seq_file *)file->private_data)->private; - s->family = afinfo->family; - s->last_pos = 0; - return 0; -} -EXPORT_SYMBOL(tcp_seq_open); - -int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo) -{ - int rc = 0; - struct proc_dir_entry *p; - - afinfo->seq_ops.start = tcp_seq_start; - afinfo->seq_ops.next = tcp_seq_next; - afinfo->seq_ops.stop = tcp_seq_stop; - - p = proc_create_data(afinfo->name, 0444, net->proc_net, - afinfo->seq_fops, afinfo); - if (!p) - rc = -ENOMEM; - return rc; -} -EXPORT_SYMBOL(tcp_proc_register); - -void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo) -{ - remove_proc_entry(afinfo->name, net->proc_net); -} -EXPORT_SYMBOL(tcp_proc_unregister); +EXPORT_SYMBOL(tcp_seq_stop); static void get_openreq4(const struct request_sock *req, struct seq_file *f, int i) @@ -2377,30 +2343,28 @@ out: return 0; } -static const struct file_operations tcp_afinfo_seq_fops = { - .open = tcp_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net +static const struct seq_operations tcp4_seq_ops = { + .show = tcp4_seq_show, + .start = tcp_seq_start, + .next = tcp_seq_next, + .stop = tcp_seq_stop, }; static struct tcp_seq_afinfo tcp4_seq_afinfo = { - .name = "tcp", .family = AF_INET, - .seq_fops = &tcp_afinfo_seq_fops, - .seq_ops = { - .show = tcp4_seq_show, - }, }; static int __net_init tcp4_proc_init_net(struct net *net) { - return tcp_proc_register(net, &tcp4_seq_afinfo); + if (!proc_create_net_data("tcp", 0444, net->proc_net, &tcp4_seq_ops, + sizeof(struct tcp_iter_state), &tcp4_seq_afinfo)) + return -ENOMEM; + return 0; } static void __net_exit tcp4_proc_exit_net(struct net *net) { - tcp_proc_unregister(net, &tcp4_seq_afinfo); + remove_proc_entry("tcp", net->proc_net); } static struct pernet_operations tcp4_net_ops = { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 383cac0ff0ec..d07e34f8e309 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2833,8 +2833,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) return -EBUSY; if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { - if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) - BUG(); + if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) { + WARN_ON_ONCE(1); + return -EINVAL; + } if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq)) return -ENOMEM; } @@ -3342,6 +3344,7 @@ static void tcp_connect_init(struct sock *sk) sock_reset_flag(sk, SOCK_DONE); tp->snd_wnd = 0; tcp_init_wl(tp, 0); + tcp_write_queue_purge(sk); tp->snd_una = tp->write_seq; tp->snd_sml = tp->write_seq; tp->snd_up = tp->write_seq; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 24b5c59b1c53..675433eb53a8 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -401,9 +401,9 @@ static int compute_score(struct sock *sk, struct net *net, bool dev_match = (sk->sk_bound_dev_if == dif || sk->sk_bound_dev_if == sdif); - if (exact_dif && !dev_match) + if (!dev_match) return -1; - if (sk->sk_bound_dev_if && dev_match) + if (sk->sk_bound_dev_if) score += 4; } @@ -952,8 +952,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags); if (ipc.opt && ipc.opt->opt.srr) { - if (!daddr) - return -EINVAL; + if (!daddr) { + err = -EINVAL; + goto out_free; + } faddr = ipc.opt->opt.faddr; connected = 0; } @@ -1074,6 +1076,7 @@ do_append_data: out: ip_rt_put(rt); +out_free: if (free) kfree(ipc.opt); if (!err) @@ -2498,7 +2501,7 @@ int compat_udp_getsockopt(struct sock *sk, int level, int optname, * udp_poll - wait for a UDP event. * @file - file struct * @sock - socket - * @wait - poll table + * @events - events to wait for * * This is same as datagram poll, except for the special case of * blocking sockets. If application is using a blocking fd @@ -2507,23 +2510,23 @@ int compat_udp_getsockopt(struct sock *sk, int level, int optname, * but then block when reading it. Add special case code * to work around these arguably broken applications. */ -__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait) +__poll_t udp_poll_mask(struct socket *sock, __poll_t events) { - __poll_t mask = datagram_poll(file, sock, wait); + __poll_t mask = datagram_poll_mask(sock, events); struct sock *sk = sock->sk; if (!skb_queue_empty(&udp_sk(sk)->reader_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* Check for false positives due to checksum errors */ - if ((mask & EPOLLRDNORM) && !(file->f_flags & O_NONBLOCK) && + if ((mask & EPOLLRDNORM) && !(sock->file->f_flags & O_NONBLOCK) && !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1) mask &= ~(EPOLLIN | EPOLLRDNORM); return mask; } -EXPORT_SYMBOL(udp_poll); +EXPORT_SYMBOL(udp_poll_mask); int udp_abort(struct sock *sk, int err) { @@ -2579,12 +2582,13 @@ EXPORT_SYMBOL(udp_prot); static struct sock *udp_get_first(struct seq_file *seq, int start) { struct sock *sk; + struct udp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file)); struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); - for (state->bucket = start; state->bucket <= state->udp_table->mask; + for (state->bucket = start; state->bucket <= afinfo->udp_table->mask; ++state->bucket) { - struct udp_hslot *hslot = &state->udp_table->hash[state->bucket]; + struct udp_hslot *hslot = &afinfo->udp_table->hash[state->bucket]; if (hlist_empty(&hslot->head)) continue; @@ -2593,7 +2597,7 @@ static struct sock *udp_get_first(struct seq_file *seq, int start) sk_for_each(sk, &hslot->head) { if (!net_eq(sock_net(sk), net)) continue; - if (sk->sk_family == state->family) + if (sk->sk_family == afinfo->family) goto found; } spin_unlock_bh(&hslot->lock); @@ -2605,16 +2609,17 @@ found: static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) { + struct udp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file)); struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); do { sk = sk_next(sk); - } while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != state->family)); + } while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != afinfo->family)); if (!sk) { - if (state->bucket <= state->udp_table->mask) - spin_unlock_bh(&state->udp_table->hash[state->bucket].lock); + if (state->bucket <= afinfo->udp_table->mask) + spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock); return udp_get_first(seq, state->bucket + 1); } return sk; @@ -2630,15 +2635,16 @@ static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos) return pos ? NULL : sk; } -static void *udp_seq_start(struct seq_file *seq, loff_t *pos) +void *udp_seq_start(struct seq_file *seq, loff_t *pos) { struct udp_iter_state *state = seq->private; state->bucket = MAX_UDP_PORTS; return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } +EXPORT_SYMBOL(udp_seq_start); -static void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) +void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct sock *sk; @@ -2650,56 +2656,17 @@ static void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) ++*pos; return sk; } +EXPORT_SYMBOL(udp_seq_next); -static void udp_seq_stop(struct seq_file *seq, void *v) +void udp_seq_stop(struct seq_file *seq, void *v) { + struct udp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file)); struct udp_iter_state *state = seq->private; - if (state->bucket <= state->udp_table->mask) - spin_unlock_bh(&state->udp_table->hash[state->bucket].lock); + if (state->bucket <= afinfo->udp_table->mask) + spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock); } - -int udp_seq_open(struct inode *inode, struct file *file) -{ - struct udp_seq_afinfo *afinfo = PDE_DATA(inode); - struct udp_iter_state *s; - int err; - - err = seq_open_net(inode, file, &afinfo->seq_ops, - sizeof(struct udp_iter_state)); - if (err < 0) - return err; - - s = ((struct seq_file *)file->private_data)->private; - s->family = afinfo->family; - s->udp_table = afinfo->udp_table; - return err; -} -EXPORT_SYMBOL(udp_seq_open); - -/* ------------------------------------------------------------------------ */ -int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo) -{ - struct proc_dir_entry *p; - int rc = 0; - - afinfo->seq_ops.start = udp_seq_start; - afinfo->seq_ops.next = udp_seq_next; - afinfo->seq_ops.stop = udp_seq_stop; - - p = proc_create_data(afinfo->name, 0444, net->proc_net, - afinfo->seq_fops, afinfo); - if (!p) - rc = -ENOMEM; - return rc; -} -EXPORT_SYMBOL(udp_proc_register); - -void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo) -{ - remove_proc_entry(afinfo->name, net->proc_net); -} -EXPORT_SYMBOL(udp_proc_unregister); +EXPORT_SYMBOL(udp_seq_stop); /* ------------------------------------------------------------------------ */ static void udp4_format_sock(struct sock *sp, struct seq_file *f, @@ -2739,32 +2706,30 @@ int udp4_seq_show(struct seq_file *seq, void *v) return 0; } -static const struct file_operations udp_afinfo_seq_fops = { - .open = udp_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net +const struct seq_operations udp_seq_ops = { + .start = udp_seq_start, + .next = udp_seq_next, + .stop = udp_seq_stop, + .show = udp4_seq_show, }; +EXPORT_SYMBOL(udp_seq_ops); -/* ------------------------------------------------------------------------ */ static struct udp_seq_afinfo udp4_seq_afinfo = { - .name = "udp", .family = AF_INET, .udp_table = &udp_table, - .seq_fops = &udp_afinfo_seq_fops, - .seq_ops = { - .show = udp4_seq_show, - }, }; static int __net_init udp4_proc_init_net(struct net *net) { - return udp_proc_register(net, &udp4_seq_afinfo); + if (!proc_create_net_data("udp", 0444, net->proc_net, &udp_seq_ops, + sizeof(struct udp_iter_state), &udp4_seq_afinfo)) + return -ENOMEM; + return 0; } static void __net_exit udp4_proc_exit_net(struct net *net) { - udp_proc_unregister(net, &udp4_seq_afinfo); + remove_proc_entry("udp", net->proc_net); } static struct pernet_operations udp4_net_ops = { diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index f96614e9b9a5..8545457752fb 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -14,6 +14,7 @@ #define pr_fmt(fmt) "UDPLite: " fmt #include <linux/export.h> +#include <linux/proc_fs.h> #include "udp_impl.h" struct udp_table udplite_table __read_mostly; @@ -73,32 +74,22 @@ static struct inet_protosw udplite4_protosw = { }; #ifdef CONFIG_PROC_FS - -static const struct file_operations udplite_afinfo_seq_fops = { - .open = udp_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net -}; - static struct udp_seq_afinfo udplite4_seq_afinfo = { - .name = "udplite", .family = AF_INET, .udp_table = &udplite_table, - .seq_fops = &udplite_afinfo_seq_fops, - .seq_ops = { - .show = udp4_seq_show, - }, }; static int __net_init udplite4_proc_init_net(struct net *net) { - return udp_proc_register(net, &udplite4_seq_afinfo); + if (!proc_create_net_data("udplite", 0444, net->proc_net, &udp_seq_ops, + sizeof(struct udp_iter_state), &udplite4_seq_afinfo)) + return -ENOMEM; + return 0; } static void __net_exit udplite4_proc_exit_net(struct net *net) { - udp_proc_unregister(net, &udplite4_seq_afinfo); + remove_proc_entry("udplite", net->proc_net); } static struct pernet_operations udplite4_net_ops = { |