diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/Kconfig | 13 | ||||
-rw-r--r-- | net/ipv4/af_inet.c | 3 | ||||
-rw-r--r-- | net/ipv4/fib_frontend.c | 9 | ||||
-rw-r--r-- | net/ipv4/fou.c | 3 | ||||
-rw-r--r-- | net/ipv4/inet_diag.c | 65 | ||||
-rw-r--r-- | net/ipv4/ip_output.c | 2 | ||||
-rw-r--r-- | net/ipv4/netfilter/Kconfig | 1 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_nat_l3proto_ipv4.c | 3 | ||||
-rw-r--r-- | net/ipv4/syncookies.c | 4 | ||||
-rw-r--r-- | net/ipv4/sysctl_net_ipv4.c | 11 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 36 | ||||
-rw-r--r-- | net/ipv4/tcp_diag.c | 19 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 2 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 7 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 23 | ||||
-rw-r--r-- | net/ipv4/udp.c | 3 | ||||
-rw-r--r-- | net/ipv4/udp_offload.c | 5 |
17 files changed, 161 insertions, 48 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 416dfa004cfb..c22920525e5d 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -436,6 +436,19 @@ config INET_UDP_DIAG Support for UDP socket monitoring interface used by the ss tool. If unsure, say Y. +config INET_DIAG_DESTROY + bool "INET: allow privileged process to administratively close sockets" + depends on INET_DIAG + default n + ---help--- + Provides a SOCK_DESTROY operation that allows privileged processes + (e.g., a connection manager or a network administration tool such as + ss) to close sockets opened by other processes. Closing a socket in + this way interrupts any blocking read/write/connect operations on + the socket and causes future socket calls to behave as if the socket + had been disconnected. + If unsure, say N. + menuconfig TCP_CONG_ADVANCED bool "TCP: advanced congestion control" ---help--- diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 11c4ca13ec3b..5c5db6636704 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -257,6 +257,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol, int try_loading_module = 0; int err; + if (protocol < 0 || protocol >= IPPROTO_MAX) + return -EINVAL; + sock->state = SS_UNCONNECTED; /* Look for the requested type/protocol pair. */ diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index cc8f3e506cde..473447593060 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1155,6 +1155,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info; struct in_device *in_dev; struct net *net = dev_net(dev); unsigned int flags; @@ -1193,6 +1194,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo case NETDEV_CHANGEMTU: rt_cache_flush(net); break; + case NETDEV_CHANGEUPPER: + info = ptr; + /* flush all routes if dev is linked to or unlinked from + * an L3 master device (e.g., VRF) + */ + if (info->upper_dev && netif_is_l3_master(info->upper_dev)) + fib_disable_ip(dev, NETDEV_DOWN, true); + break; } return NOTIFY_DONE; } diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index e0fcbbbcfe54..bd903fe0f750 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -24,6 +24,7 @@ struct fou { u16 type; struct udp_offload udp_offloads; struct list_head list; + struct rcu_head rcu; }; #define FOU_F_REMCSUM_NOPARTIAL BIT(0) @@ -417,7 +418,7 @@ static void fou_release(struct fou *fou) list_del(&fou->list); udp_tunnel_sock_release(sock); - kfree(fou); + kfree_rcu(fou, rcu); } static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index ab9f8a66615d..8bb8e7ad8548 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -350,17 +350,12 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, nlmsg_flags, unlh); } -int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, - struct sk_buff *in_skb, - const struct nlmsghdr *nlh, - const struct inet_diag_req_v2 *req) +struct sock *inet_diag_find_one_icsk(struct net *net, + struct inet_hashinfo *hashinfo, + const struct inet_diag_req_v2 *req) { - struct net *net = sock_net(in_skb->sk); - struct sk_buff *rep; struct sock *sk; - int err; - err = -EINVAL; if (req->sdiag_family == AF_INET) sk = inet_lookup(net, hashinfo, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_src[0], @@ -375,15 +370,33 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, req->id.idiag_if); #endif else - goto out_nosk; + return ERR_PTR(-EINVAL); - err = -ENOENT; if (!sk) - goto out_nosk; + return ERR_PTR(-ENOENT); - err = sock_diag_check_cookie(sk, req->id.idiag_cookie); - if (err) - goto out; + if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) { + sock_gen_put(sk); + return ERR_PTR(-ENOENT); + } + + return sk; +} +EXPORT_SYMBOL_GPL(inet_diag_find_one_icsk); + +int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, + struct sk_buff *in_skb, + const struct nlmsghdr *nlh, + const struct inet_diag_req_v2 *req) +{ + struct net *net = sock_net(in_skb->sk); + struct sk_buff *rep; + struct sock *sk; + int err; + + sk = inet_diag_find_one_icsk(net, hashinfo, req); + if (IS_ERR(sk)) + return PTR_ERR(sk); rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL); if (!rep) { @@ -409,12 +422,11 @@ out: if (sk) sock_gen_put(sk); -out_nosk: return err; } EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk); -static int inet_diag_get_exact(struct sk_buff *in_skb, +static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb, const struct nlmsghdr *nlh, const struct inet_diag_req_v2 *req) { @@ -424,8 +436,12 @@ static int inet_diag_get_exact(struct sk_buff *in_skb, handler = inet_diag_lock_handler(req->sdiag_protocol); if (IS_ERR(handler)) err = PTR_ERR(handler); - else + else if (cmd == SOCK_DIAG_BY_FAMILY) err = handler->dump_one(in_skb, nlh, req); + else if (cmd == SOCK_DESTROY && handler->destroy) + err = handler->destroy(in_skb, req); + else + err = -EOPNOTSUPP; inet_diag_unlock_handler(handler); return err; @@ -938,7 +954,7 @@ static int inet_diag_get_exact_compat(struct sk_buff *in_skb, req.idiag_states = rc->idiag_states; req.id = rc->id; - return inet_diag_get_exact(in_skb, nlh, &req); + return inet_diag_cmd_exact(SOCK_DIAG_BY_FAMILY, in_skb, nlh, &req); } static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) @@ -972,7 +988,7 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) return inet_diag_get_exact_compat(skb, nlh); } -static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) +static int inet_diag_handler_cmd(struct sk_buff *skb, struct nlmsghdr *h) { int hdrlen = sizeof(struct inet_diag_req_v2); struct net *net = sock_net(skb->sk); @@ -980,7 +996,8 @@ static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) if (nlmsg_len(h) < hdrlen) return -EINVAL; - if (h->nlmsg_flags & NLM_F_DUMP) { + if (h->nlmsg_type == SOCK_DIAG_BY_FAMILY && + h->nlmsg_flags & NLM_F_DUMP) { if (nlmsg_attrlen(h, hdrlen)) { struct nlattr *attr; @@ -999,7 +1016,7 @@ static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) } } - return inet_diag_get_exact(skb, h, nlmsg_data(h)); + return inet_diag_cmd_exact(h->nlmsg_type, skb, h, nlmsg_data(h)); } static @@ -1050,14 +1067,16 @@ int inet_diag_handler_get_info(struct sk_buff *skb, struct sock *sk) static const struct sock_diag_handler inet_diag_handler = { .family = AF_INET, - .dump = inet_diag_handler_dump, + .dump = inet_diag_handler_cmd, .get_info = inet_diag_handler_get_info, + .destroy = inet_diag_handler_cmd, }; static const struct sock_diag_handler inet6_diag_handler = { .family = AF_INET6, - .dump = inet_diag_handler_dump, + .dump = inet_diag_handler_cmd, .get_info = inet_diag_handler_get_info, + .destroy = inet_diag_handler_cmd, }; int inet_diag_register(const struct inet_diag_handler *h) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index e0b94cd843d7..568e2bc0d93d 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -911,7 +911,7 @@ static int __ip_append_data(struct sock *sk, */ if (transhdrlen && length + fragheaderlen <= mtu && - rt->dst.dev->features & NETIF_F_V4_CSUM && + rt->dst.dev->features & (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM) && !(flags & MSG_MORE) && !exthdrlen) csummode = CHECKSUM_PARTIAL; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index a35584176535..c187c60e3e0c 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -60,6 +60,7 @@ config NFT_REJECT_IPV4 config NFT_DUP_IPV4 tristate "IPv4 nf_tables packet duplication support" + depends on !NF_CONNTRACK || NF_CONNTRACK select NF_DUP_IPV4 help This module enables IPv4 packet duplication support for nf_tables. diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index 5075b7ecd26d..61c7cc22ea68 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -132,7 +132,8 @@ static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_PARTIAL) { if (!(rt->rt_flags & RTCF_LOCAL) && - (!skb->dev || skb->dev->features & NETIF_F_V4_CSUM)) { + (!skb->dev || skb->dev->features & + (NETIF_F_IP_CSUM | NETIF_F_HW_CSUM))) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 4cbe9f0a4281..643a86c49020 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -351,7 +351,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) treq->snt_synack.v64 = 0; treq->tfo_listener = false; - ireq->ir_iif = sk->sk_bound_dev_if; + ireq->ir_iif = inet_request_bound_dev_if(sk, skb); /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) @@ -371,7 +371,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) * hasn't changed since we received the original syn, but I see * no easy way to do this. */ - flowi4_init_output(&fl4, sk->sk_bound_dev_if, ireq->ir_mark, + flowi4_init_output(&fl4, ireq->ir_iif, ireq->ir_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP, inet_sk_flowi_flags(sk), opt->srr ? opt->faddr : ireq->ir_rmt_addr, diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index a0bd7a55193e..41ff1f87dfd7 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -915,6 +915,17 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#ifdef CONFIG_NET_L3_MASTER_DEV + { + .procname = "tcp_l3mdev_accept", + .data = &init_net.ipv4.sysctl_tcp_l3mdev_accept, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, +#endif { .procname = "tcp_mtu_probing", .data = &init_net.ipv4.sysctl_tcp_mtu_probing, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c82cca18c90f..2c0e340518d2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1018,7 +1018,7 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset, ssize_t res; if (!(sk->sk_route_caps & NETIF_F_SG) || - !(sk->sk_route_caps & NETIF_F_ALL_CSUM)) + !sk_check_csum_caps(sk)) return sock_no_sendpage(sk->sk_socket, page, offset, size, flags); @@ -1175,7 +1175,7 @@ new_segment: /* * Check whether we can use HW checksum. */ - if (sk->sk_route_caps & NETIF_F_ALL_CSUM) + if (sk_check_csum_caps(sk)) skb->ip_summed = CHECKSUM_PARTIAL; skb_entail(sk, skb); @@ -3080,6 +3080,38 @@ void tcp_done(struct sock *sk) } EXPORT_SYMBOL_GPL(tcp_done); +int tcp_abort(struct sock *sk, int err) +{ + if (!sk_fullsock(sk)) { + sock_gen_put(sk); + return -EOPNOTSUPP; + } + + /* Don't race with userspace socket closes such as tcp_close. */ + lock_sock(sk); + + /* Don't race with BH socket closes such as inet_csk_listen_stop. */ + local_bh_disable(); + bh_lock_sock(sk); + + if (!sock_flag(sk, SOCK_DEAD)) { + sk->sk_err = err; + /* This barrier is coupled with smp_rmb() in tcp_poll() */ + smp_wmb(); + sk->sk_error_report(sk); + if (tcp_need_reset(sk->sk_state)) + tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_done(sk); + } + + bh_unlock_sock(sk); + local_bh_enable(); + release_sock(sk); + sock_put(sk); + return 0; +} +EXPORT_SYMBOL_GPL(tcp_abort); + extern struct tcp_congestion_ops tcp_reno; static __initdata unsigned long thash_entries; diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index b31604086edd..4d610934fb39 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -10,6 +10,8 @@ */ #include <linux/module.h> +#include <linux/net.h> +#include <linux/sock_diag.h> #include <linux/inet_diag.h> #include <linux/tcp.h> @@ -46,12 +48,29 @@ static int tcp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, return inet_diag_dump_one_icsk(&tcp_hashinfo, in_skb, nlh, req); } +#ifdef CONFIG_INET_DIAG_DESTROY +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); + + if (IS_ERR(sk)) + return PTR_ERR(sk); + + return sock_diag_destroy(sk, ECONNABORTED); +} +#endif + static const struct inet_diag_handler tcp_diag_handler = { .dump = tcp_diag_dump, .dump_one = tcp_diag_dump_one, .idiag_get_info = tcp_diag_get_info, .idiag_type = IPPROTO_TCP, .idiag_info_size = sizeof(struct tcp_info), +#ifdef CONFIG_INET_DIAG_DESTROY + .destroy = tcp_diag_destroy, +#endif }; static int __init tcp_diag_init(void) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2d656eef7f8e..7b1fddc47019 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6204,7 +6204,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_openreq_init(req, &tmp_opt, skb, sk); /* Note: tcp_v6_init_req() might override ir_iif for link locals */ - inet_rsk(req)->ir_iif = sk->sk_bound_dev_if; + inet_rsk(req)->ir_iif = inet_request_bound_dev_if(sk, skb); af_ops->init_req(req, sk, skb); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index db003438aaf5..46e92fbd26a8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1276,6 +1276,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, ireq = inet_rsk(req); sk_daddr_set(newsk, ireq->ir_rmt_addr); sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); + newsk->sk_bound_dev_if = ireq->ir_iif; newinet->inet_saddr = ireq->ir_loc_addr; inet_opt = ireq->opt; rcu_assign_pointer(newinet->inet_opt, inet_opt); @@ -1493,7 +1494,7 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb) if (likely(sk->sk_rx_dst)) skb_dst_drop(skb); else - skb_dst_force(skb); + skb_dst_force_safe(skb); __skb_queue_tail(&tp->ucopy.prequeue, skb); tp->ucopy.memory += skb->truesize; @@ -1721,8 +1722,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - if (dst) { - dst_hold(dst); + if (dst && dst_hold_safe(dst)) { sk->sk_rx_dst = dst; inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; } @@ -2342,6 +2342,7 @@ struct proto tcp_prot = { .destroy_cgroup = tcp_destroy_cgroup, .proto_cgroup = tcp_proto_cgroup, #endif + .diag_destroy = tcp_abort, }; EXPORT_SYMBOL(tcp_prot); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index a800cee88035..412a920fe0ec 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3150,7 +3150,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_request *fo = tp->fastopen_req; - int syn_loss = 0, space, err = 0, copied; + int syn_loss = 0, space, err = 0; unsigned long last_syn_loss = 0; struct sk_buff *syn_data; @@ -3188,17 +3188,18 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) goto fallback; syn_data->ip_summed = CHECKSUM_PARTIAL; memcpy(syn_data->cb, syn->cb, sizeof(syn->cb)); - copied = copy_from_iter(skb_put(syn_data, space), space, - &fo->data->msg_iter); - if (unlikely(!copied)) { - kfree_skb(syn_data); - goto fallback; - } - if (copied != space) { - skb_trim(syn_data, copied); - space = copied; + if (space) { + int copied = copy_from_iter(skb_put(syn_data, space), space, + &fo->data->msg_iter); + if (unlikely(!copied)) { + kfree_skb(syn_data); + goto fallback; + } + if (copied != space) { + skb_trim(syn_data, copied); + space = copied; + } } - /* No more data pending in inet_wait_for_connect() */ if (space == fo->size) fo->data = NULL; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 0c7b0e61b917..8841e984f8bf 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -772,7 +772,8 @@ void udp_set_csum(bool nocheck, struct sk_buff *skb, else if (skb_is_gso(skb)) uh->check = ~udp_v4_check(len, saddr, daddr, 0); else if (skb_dst(skb) && skb_dst(skb)->dev && - (skb_dst(skb)->dev->features & NETIF_F_V4_CSUM)) { + (skb_dst(skb)->dev->features & + (NETIF_F_IP_CSUM | NETIF_F_HW_CSUM))) { BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index f9386160cbee..130042660181 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -60,8 +60,9 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, /* Try to offload checksum if possible */ offload_csum = !!(need_csum && - (skb->dev->features & - (is_ipv6 ? NETIF_F_V6_CSUM : NETIF_F_V4_CSUM))); + ((skb->dev->features & NETIF_F_HW_CSUM) || + (skb->dev->features & (is_ipv6 ? + NETIF_F_IPV6_CSUM : NETIF_F_IP_CSUM)))); /* segment inner packet. */ enc_features = skb->dev->hw_enc_features & features; |