diff options
Diffstat (limited to 'net')
42 files changed, 470 insertions, 175 deletions
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 9a47ef8b95c4..1f1f5b0873b2 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -391,6 +391,7 @@ out: /** * batadv_frag_create() - create a fragment from skb + * @net_dev: outgoing device for fragment * @skb: skb to create fragment from * @frag_head: header to use in new fragment * @fragment_size: size of new fragment @@ -401,22 +402,25 @@ out: * * Return: the new fragment, NULL on error. */ -static struct sk_buff *batadv_frag_create(struct sk_buff *skb, +static struct sk_buff *batadv_frag_create(struct net_device *net_dev, + struct sk_buff *skb, struct batadv_frag_packet *frag_head, unsigned int fragment_size) { + unsigned int ll_reserved = LL_RESERVED_SPACE(net_dev); + unsigned int tailroom = net_dev->needed_tailroom; struct sk_buff *skb_fragment; unsigned int header_size = sizeof(*frag_head); unsigned int mtu = fragment_size + header_size; - skb_fragment = netdev_alloc_skb(NULL, mtu + ETH_HLEN); + skb_fragment = dev_alloc_skb(ll_reserved + mtu + tailroom); if (!skb_fragment) goto err; skb_fragment->priority = skb->priority; /* Eat the last mtu-bytes of the skb */ - skb_reserve(skb_fragment, header_size + ETH_HLEN); + skb_reserve(skb_fragment, ll_reserved + header_size); skb_split(skb, skb_fragment, skb->len - fragment_size); /* Add the header */ @@ -439,11 +443,12 @@ int batadv_frag_send_packet(struct sk_buff *skb, struct batadv_orig_node *orig_node, struct batadv_neigh_node *neigh_node) { + struct net_device *net_dev = neigh_node->if_incoming->net_dev; struct batadv_priv *bat_priv; struct batadv_hard_iface *primary_if = NULL; struct batadv_frag_packet frag_header; struct sk_buff *skb_fragment; - unsigned int mtu = neigh_node->if_incoming->net_dev->mtu; + unsigned int mtu = net_dev->mtu; unsigned int header_size = sizeof(frag_header); unsigned int max_fragment_size, num_fragments; int ret; @@ -503,7 +508,7 @@ int batadv_frag_send_packet(struct sk_buff *skb, goto put_primary_if; } - skb_fragment = batadv_frag_create(skb, &frag_header, + skb_fragment = batadv_frag_create(net_dev, skb, &frag_header, max_fragment_size); if (!skb_fragment) { ret = -ENOMEM; @@ -522,13 +527,14 @@ int batadv_frag_send_packet(struct sk_buff *skb, frag_header.no++; } - /* Make room for the fragment header. */ - if (batadv_skb_head_push(skb, header_size) < 0 || - pskb_expand_head(skb, header_size + ETH_HLEN, 0, GFP_ATOMIC) < 0) { - ret = -ENOMEM; + /* make sure that there is at least enough head for the fragmentation + * and ethernet headers + */ + ret = skb_cow_head(skb, ETH_HLEN + header_size); + if (ret < 0) goto put_primary_if; - } + skb_push(skb, header_size); memcpy(skb->data, &frag_header, header_size); /* Send the last fragment */ diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index dad99641df2a..33904595fc56 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -554,6 +554,9 @@ static void batadv_hardif_recalc_extra_skbroom(struct net_device *soft_iface) needed_headroom = lower_headroom + (lower_header_len - ETH_HLEN); needed_headroom += batadv_max_header_len(); + /* fragmentation headers don't strip the unicast/... header */ + needed_headroom += sizeof(struct batadv_frag_packet); + soft_iface->needed_headroom = needed_headroom; soft_iface->needed_tailroom = lower_tailroom; } diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index a67b2b091447..c0ca5fbe5b08 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -180,6 +180,7 @@ static const struct file_operations batadv_log_fops = { .read = batadv_log_read, .poll = batadv_log_poll, .llseek = no_llseek, + .owner = THIS_MODULE, }; /** diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 04c3f9a82650..8edfb98ae1d5 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -735,6 +735,11 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff mtu_reserved = nf_bridge_mtu_reduction(skb); mtu = skb->dev->mtu; + if (nf_bridge->pkt_otherhost) { + skb->pkt_type = PACKET_OTHERHOST; + nf_bridge->pkt_otherhost = false; + } + if (nf_bridge->frag_max_size && nf_bridge->frag_max_size < mtu) mtu = nf_bridge->frag_max_size; @@ -835,8 +840,6 @@ static unsigned int br_nf_post_routing(void *priv, else return NF_ACCEPT; - /* We assume any code from br_dev_queue_push_xmit onwards doesn't care - * about the value of skb->pkt_type. */ if (skb->pkt_type == PACKET_OTHERHOST) { skb->pkt_type = PACKET_HOST; nf_bridge->pkt_otherhost = true; diff --git a/net/can/af_can.c b/net/can/af_can.c index 5d124c155904..4c343b43067f 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -541,10 +541,13 @@ void can_rx_unregister(struct net *net, struct net_device *dev, canid_t can_id, /* Check for bugs in CAN protocol implementations using af_can.c: * 'rcv' will be NULL if no matching list item was found for removal. + * As this case may potentially happen when closing a socket while + * the notifier for removing the CAN netdev is running we just print + * a warning here. */ if (!rcv) { - WARN(1, "BUG: receive list entry not found for dev %s, id %03X, mask %03X\n", - DNAME(dev), can_id, mask); + pr_warn("can: receive list entry not found for dev %s, id %03X, mask %03X\n", + DNAME(dev), can_id, mask); goto out; } diff --git a/net/core/dev.c b/net/core/dev.c index 82dc6b48e45f..8588ade790cb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4180,7 +4180,7 @@ int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev) } EXPORT_SYMBOL(dev_queue_xmit_accel); -int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) +int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { struct net_device *dev = skb->dev; struct sk_buff *orig_skb = skb; @@ -4210,17 +4210,13 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) dev_xmit_recursion_dec(); local_bh_enable(); - - if (!dev_xmit_complete(ret)) - kfree_skb(skb); - return ret; drop: atomic_long_inc(&dev->tx_dropped); kfree_skb_list(skb); return NET_XMIT_DROP; } -EXPORT_SYMBOL(dev_direct_xmit); +EXPORT_SYMBOL(__dev_direct_xmit); /************************************************************************* * Receiver routines diff --git a/net/core/devlink.c b/net/core/devlink.c index 4b0211590aac..8c5ddffd707d 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -517,7 +517,7 @@ devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_l return test_bit(limit, &devlink->ops->reload_limits); } -static int devlink_reload_stat_put(struct sk_buff *msg, enum devlink_reload_action action, +static int devlink_reload_stat_put(struct sk_buff *msg, enum devlink_reload_limit limit, u32 value) { struct nlattr *reload_stats_entry; @@ -526,8 +526,7 @@ static int devlink_reload_stat_put(struct sk_buff *msg, enum devlink_reload_acti if (!reload_stats_entry) return -EMSGSIZE; - if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, action) || - nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value)) goto nla_put_failure; nla_nest_end(msg, reload_stats_entry); @@ -540,7 +539,7 @@ nla_put_failure: static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote) { - struct nlattr *reload_stats_attr; + struct nlattr *reload_stats_attr, *act_info, *act_stats; int i, j, stat_idx; u32 value; @@ -552,17 +551,29 @@ static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink if (!reload_stats_attr) return -EMSGSIZE; - for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) { - /* Remote stats are shown even if not locally supported. Stats - * of actions with unspecified limit are shown though drivers - * don't need to register unspecified limit. - */ - if (!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC && - !devlink_reload_limit_is_supported(devlink, j)) + for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { + if ((!is_remote && + !devlink_reload_action_is_supported(devlink, i)) || + i == DEVLINK_RELOAD_ACTION_UNSPEC) continue; - for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { - if ((!is_remote && !devlink_reload_action_is_supported(devlink, i)) || - i == DEVLINK_RELOAD_ACTION_UNSPEC || + act_info = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_INFO); + if (!act_info) + goto nla_put_failure; + + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, i)) + goto action_info_nest_cancel; + act_stats = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_STATS); + if (!act_stats) + goto action_info_nest_cancel; + + for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) { + /* Remote stats are shown even if not locally supported. + * Stats of actions with unspecified limit are shown + * though drivers don't need to register unspecified + * limit. + */ + if ((!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC && + !devlink_reload_limit_is_supported(devlink, j)) || devlink_reload_combination_is_invalid(i, j)) continue; @@ -571,13 +582,19 @@ static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink value = devlink->stats.reload_stats[stat_idx]; else value = devlink->stats.remote_reload_stats[stat_idx]; - if (devlink_reload_stat_put(msg, i, j, value)) - goto nla_put_failure; + if (devlink_reload_stat_put(msg, j, value)) + goto action_stats_nest_cancel; } + nla_nest_end(msg, act_stats); + nla_nest_end(msg, act_info); } nla_nest_end(msg, reload_stats_attr); return 0; +action_stats_nest_cancel: + nla_nest_cancel(msg, act_stats); +action_info_nest_cancel: + nla_nest_cancel(msg, act_info); nla_put_failure: nla_nest_cancel(msg, reload_stats_attr); return -EMSGSIZE; @@ -755,6 +772,8 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) goto nla_put_failure; + /* Hold rtnl lock while accessing port's netdev attributes. */ + rtnl_lock(); spin_lock_bh(&devlink_port->type_lock); if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) goto nla_put_failure_type_locked; @@ -763,9 +782,10 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, devlink_port->desired_type)) goto nla_put_failure_type_locked; if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) { + struct net *net = devlink_net(devlink_port->devlink); struct net_device *netdev = devlink_port->type_dev; - if (netdev && + if (netdev && net_eq(net, dev_net(netdev)) && (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX, netdev->ifindex) || nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME, @@ -781,6 +801,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, goto nla_put_failure_type_locked; } spin_unlock_bh(&devlink_port->type_lock); + rtnl_unlock(); if (devlink_nl_port_attrs_put(msg, devlink_port)) goto nla_put_failure; if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack)) @@ -791,6 +812,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, nla_put_failure_type_locked: spin_unlock_bh(&devlink_port->type_lock); + rtnl_unlock(); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index e095fb871d91..6eb2e5ec2c50 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -99,9 +99,14 @@ void gro_cells_destroy(struct gro_cells *gcells) struct gro_cell *cell = per_cpu_ptr(gcells->cells, i); napi_disable(&cell->napi); - netif_napi_del(&cell->napi); + __netif_napi_del(&cell->napi); __skb_queue_purge(&cell->napi_skbs); } + /* This barrier is needed because netpoll could access dev->napi_list + * under rcu protection. + */ + synchronize_net(); + free_percpu(gcells->cells); gcells->cells = NULL; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1ba8f0163744..e578544b2cc7 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4549,7 +4549,7 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk) if (skb && (skb_next = skb_peek(q))) { icmp_next = is_icmp_err_skb(skb_next); if (icmp_next) - sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_origin; + sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_errno; } spin_unlock_irqrestore(&q->lock, flags); @@ -5786,6 +5786,9 @@ int skb_mpls_dec_ttl(struct sk_buff *skb) if (unlikely(!eth_p_mpls(skb->protocol))) return -EINVAL; + if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN)) + return -ENOMEM; + lse = be32_to_cpu(mpls_hdr(skb)->label_stack_entry); ttl = (lse & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT; if (!--ttl) diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index bb3d70664dde..b0b6e6a4784e 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -427,7 +427,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); if (*own_req) ireq->ireq_opt = NULL; else diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index ef4ab28cfde0..78ee1b5acf1f 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -533,7 +533,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, dccp_done(newsk); goto out; } - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); /* Clone pktoptions received with SYN, if we own the req */ if (*own_req && ireq->pktopts) { newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 4148f5f78f31..f60869acbef0 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -787,7 +787,7 @@ static void reqsk_queue_hash_req(struct request_sock *req, timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); mod_timer(&req->rsk_timer, jiffies + timeout); - inet_ehash_insert(req_to_sk(req), NULL); + inet_ehash_insert(req_to_sk(req), NULL, NULL); /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. */ diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 8cbe74313f38..45fb450b4522 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -20,6 +20,9 @@ #include <net/addrconf.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/inet6_hashtables.h> +#endif #include <net/secure_seq.h> #include <net/ip.h> #include <net/tcp.h> @@ -508,10 +511,52 @@ static u32 inet_sk_port_offset(const struct sock *sk) inet->inet_dport); } -/* insert a socket into ehash, and eventually remove another one - * (The another one can be a SYN_RECV or TIMEWAIT +/* Searches for an exsiting socket in the ehash bucket list. + * Returns true if found, false otherwise. */ -bool inet_ehash_insert(struct sock *sk, struct sock *osk) +static bool inet_ehash_lookup_by_sk(struct sock *sk, + struct hlist_nulls_head *list) +{ + const __portpair ports = INET_COMBINED_PORTS(sk->sk_dport, sk->sk_num); + const int sdif = sk->sk_bound_dev_if; + const int dif = sk->sk_bound_dev_if; + const struct hlist_nulls_node *node; + struct net *net = sock_net(sk); + struct sock *esk; + + INET_ADDR_COOKIE(acookie, sk->sk_daddr, sk->sk_rcv_saddr); + + sk_nulls_for_each_rcu(esk, node, list) { + if (esk->sk_hash != sk->sk_hash) + continue; + if (sk->sk_family == AF_INET) { + if (unlikely(INET_MATCH(esk, net, acookie, + sk->sk_daddr, + sk->sk_rcv_saddr, + ports, dif, sdif))) { + return true; + } + } +#if IS_ENABLED(CONFIG_IPV6) + else if (sk->sk_family == AF_INET6) { + if (unlikely(INET6_MATCH(esk, net, + &sk->sk_v6_daddr, + &sk->sk_v6_rcv_saddr, + ports, dif, sdif))) { + return true; + } + } +#endif + } + return false; +} + +/* Insert a socket into ehash, and eventually remove another one + * (The another one can be a SYN_RECV or TIMEWAIT) + * If an existing socket already exists, socket sk is not inserted, + * and sets found_dup_sk parameter to true. + */ +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; @@ -530,16 +575,23 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk) if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); ret = sk_nulls_del_node_init_rcu(osk); + } else if (found_dup_sk) { + *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); + if (*found_dup_sk) + ret = false; } + if (ret) __sk_nulls_add_node_rcu(sk, list); + spin_unlock(lock); + return ret; } -bool inet_ehash_nolisten(struct sock *sk, struct sock *osk) +bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk) { - bool ok = inet_ehash_insert(sk, osk); + bool ok = inet_ehash_insert(sk, osk, found_dup_sk); if (ok) { sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); @@ -583,7 +635,7 @@ int __inet_hash(struct sock *sk, struct sock *osk) int err = 0; if (sk->sk_state != TCP_LISTEN) { - inet_ehash_nolisten(sk, osk); + inet_ehash_nolisten(sk, osk, NULL); return 0; } WARN_ON(!sk_unhashed(sk)); @@ -679,7 +731,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, tb = inet_csk(sk)->icsk_bind_hash; spin_lock_bh(&head->lock); if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) { - inet_ehash_nolisten(sk, NULL); + inet_ehash_nolisten(sk, NULL, NULL); spin_unlock_bh(&head->lock); return 0; } @@ -758,7 +810,7 @@ ok: inet_bind_hash(sk, tb, port); if (sk_unhashed(sk)) { inet_sk(sk)->inet_sport = htons(port); - inet_ehash_nolisten(sk, (struct sock *)tw); + inet_ehash_nolisten(sk, (struct sock *)tw, NULL); } if (tw) inet_twsk_bind_unhash(tw, hinfo); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index dc2a399cd9f4..9f43abeac3a8 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3222,7 +3222,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.daddr = dst; fl4.saddr = src; - fl4.flowi4_tos = rtm->rtm_tos; + fl4.flowi4_tos = rtm->rtm_tos & IPTOS_RT_MASK; fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; @@ -3246,8 +3246,9 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.flowi4_iif = iif; /* for rt_fill_info */ skb->dev = dev; skb->mark = mark; - err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos, - dev, &res); + err = ip_route_input_rcu(skb, dst, src, + rtm->rtm_tos & IPTOS_RT_MASK, dev, + &res); rt = skb_rtable(skb); if (err == 0 && rt->dst.error) diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index db47ac24d057..563d016e7478 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -198,6 +198,11 @@ static void tcp_reinit_congestion_control(struct sock *sk, icsk->icsk_ca_setsockopt = 1; memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); + if (ca->flags & TCP_CONG_NEEDS_ECN) + INET_ECN_xmit(sk); + else + INET_ECN_dontxmit(sk); + if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) tcp_init_congestion_control(sk); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7352c097ae48..8391aa29e7a4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -980,17 +980,22 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); - tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? - tcp_rsk(req)->syn_tos : inet_sk(sk)->tos; - if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); + tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? + tcp_rsk(req)->syn_tos & ~INET_ECN_MASK : + inet_sk(sk)->tos; + + if (!INET_ECN_is_capable(tos) && + tcp_bpf_ca_needs_ecn((struct sock *)req)) + tos |= INET_ECN_ECT_0; + rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, rcu_dereference(ireq->ireq_opt), - tos & ~INET_ECN_MASK); + tos); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -1498,6 +1503,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, bool *own_req) { struct inet_request_sock *ireq; + bool found_dup_sk = false; struct inet_sock *newinet; struct tcp_sock *newtp; struct sock *newsk; @@ -1575,12 +1581,22 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), + &found_dup_sk); if (likely(*own_req)) { tcp_move_syn(newtp, req); ireq->ireq_opt = NULL; } else { - newinet->inet_opt = NULL; + if (!req_unhash && found_dup_sk) { + /* This code path should only be executed in the + * syncookie case only + */ + bh_unlock_sock(newsk); + sock_put(newsk); + newsk = NULL; + } else { + newinet->inet_opt = NULL; + } } return newsk; diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 642fc6ac13d2..8a22486cf270 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -306,7 +306,9 @@ static int ip6addrlbl_del(struct net *net, /* add default label */ static int __net_init ip6addrlbl_net_init(struct net *net) { - int err = 0; + struct ip6addrlbl_entry *p = NULL; + struct hlist_node *n; + int err; int i; ADDRLABEL(KERN_DEBUG "%s\n", __func__); @@ -315,14 +317,20 @@ static int __net_init ip6addrlbl_net_init(struct net *net) INIT_HLIST_HEAD(&net->ipv6.ip6addrlbl_table.head); for (i = 0; i < ARRAY_SIZE(ip6addrlbl_init_table); i++) { - int ret = ip6addrlbl_add(net, - ip6addrlbl_init_table[i].prefix, - ip6addrlbl_init_table[i].prefixlen, - 0, - ip6addrlbl_init_table[i].label, 0); - /* XXX: should we free all rules when we catch an error? */ - if (ret && (!err || err != -ENOMEM)) - err = ret; + err = ip6addrlbl_add(net, + ip6addrlbl_init_table[i].prefix, + ip6addrlbl_init_table[i].prefixlen, + 0, + ip6addrlbl_init_table[i].label, 0); + if (err) + goto err_ip6addrlbl_add; + } + return 0; + +err_ip6addrlbl_add: + hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { + hlist_del_rcu(&p->list); + kfree_rcu(p, rcu); } return err; } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 931b186d2e48..cf6e1380b527 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1133,8 +1133,13 @@ static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu, return; if (rt->dst.dev) { - dev->needed_headroom = rt->dst.dev->hard_header_len + - t_hlen; + unsigned short dst_len = rt->dst.dev->hard_header_len + + t_hlen; + + if (t->dev->header_ops) + dev->hard_header_len = dst_len; + else + dev->needed_headroom = dst_len; if (set_mtu) { dev->mtu = rt->dst.dev->mtu - t_hlen; @@ -1159,7 +1164,12 @@ static int ip6gre_calc_hlen(struct ip6_tnl *tunnel) tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; t_hlen = tunnel->hlen + sizeof(struct ipv6hdr); - tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen; + + if (tunnel->dev->header_ops) + tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen; + else + tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen; + return t_hlen; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 8db59f4e5f13..992cbf3eb9e3 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -527,15 +527,20 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, if (np->repflow && ireq->pktopts) fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); + tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? + tcp_rsk(req)->syn_tos & ~INET_ECN_MASK : + np->tclass; + + if (!INET_ECN_is_capable(tclass) && + tcp_bpf_ca_needs_ecn((struct sock *)req)) + tclass |= INET_ECN_ECT_0; + rcu_read_lock(); opt = ireq->ipv6_opt; - tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? - tcp_rsk(req)->syn_tos : np->tclass; if (!opt) opt = rcu_dereference(np->opt); err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, - tclass & ~INET_ECN_MASK, - sk->sk_priority); + tclass, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -1193,6 +1198,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * const struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct ipv6_txoptions *opt; struct inet_sock *newinet; + bool found_dup_sk = false; struct tcp_sock *newtp; struct sock *newsk; #ifdef CONFIG_TCP_MD5SIG @@ -1368,7 +1374,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * tcp_done(newsk); goto out; } - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), + &found_dup_sk); if (*own_req) { tcp_move_syn(newtp, req); @@ -1383,6 +1390,15 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * skb_set_owner_r(newnp->pktoptions, newsk); } } + } else { + if (!req_unhash && found_dup_sk) { + /* This code path should only be executed in the + * syncookie case only + */ + bh_unlock_sock(newsk); + sock_put(newsk); + newsk = NULL; + } } return newsk; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 047238f01ba6..db7d888914fa 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1645,7 +1645,7 @@ static int iucv_callback_connreq(struct iucv_path *path, } /* Create the new socket */ - nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0); + nsk = iucv_sock_alloc(NULL, sk->sk_protocol, GFP_ATOMIC, 0); if (!nsk) { err = pr_iucv->path_sever(path, user_data); iucv_path_free(path); @@ -1851,7 +1851,7 @@ static int afiucv_hs_callback_syn(struct sock *sk, struct sk_buff *skb) goto out; } - nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0); + nsk = iucv_sock_alloc(NULL, sk->sk_protocol, GFP_ATOMIC, 0); bh_lock_sock(sk); if ((sk->sk_state != IUCV_LISTEN) || sk_acceptq_is_full(sk) || diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index ac4a1fe3550b..953906e40742 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -543,9 +543,8 @@ create_msk: fallback = true; } else if (subflow_req->mp_join) { mptcp_get_options(skb, &mp_opt); - if (!mp_opt.mp_join || - !mptcp_can_accept_new_subflow(subflow_req->msk) || - !subflow_hmac_valid(req, &mp_opt)) { + if (!mp_opt.mp_join || !subflow_hmac_valid(req, &mp_opt) || + !mptcp_can_accept_new_subflow(subflow_req->msk)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); fallback = true; } diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 7cff6e5e7445..2b19189a930f 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -271,8 +271,7 @@ flag_nested(const struct nlattr *nla) static const struct nla_policy ipaddr_policy[IPSET_ATTR_IPADDR_MAX + 1] = { [IPSET_ATTR_IPADDR_IPV4] = { .type = NLA_U32 }, - [IPSET_ATTR_IPADDR_IPV6] = { .type = NLA_BINARY, - .len = sizeof(struct in6_addr) }, + [IPSET_ATTR_IPADDR_IPV6] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), }; int diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index e279ded4e306..d45dbcba8b49 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -4167,12 +4167,18 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) spin_lock_init(&ipvs->tot_stats.lock); - proc_create_net("ip_vs", 0, ipvs->net->proc_net, &ip_vs_info_seq_ops, - sizeof(struct ip_vs_iter)); - proc_create_net_single("ip_vs_stats", 0, ipvs->net->proc_net, - ip_vs_stats_show, NULL); - proc_create_net_single("ip_vs_stats_percpu", 0, ipvs->net->proc_net, - ip_vs_stats_percpu_show, NULL); +#ifdef CONFIG_PROC_FS + if (!proc_create_net("ip_vs", 0, ipvs->net->proc_net, + &ip_vs_info_seq_ops, sizeof(struct ip_vs_iter))) + goto err_vs; + if (!proc_create_net_single("ip_vs_stats", 0, ipvs->net->proc_net, + ip_vs_stats_show, NULL)) + goto err_stats; + if (!proc_create_net_single("ip_vs_stats_percpu", 0, + ipvs->net->proc_net, + ip_vs_stats_percpu_show, NULL)) + goto err_percpu; +#endif if (ip_vs_control_net_init_sysctl(ipvs)) goto err; @@ -4180,6 +4186,17 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) return 0; err: +#ifdef CONFIG_PROC_FS + remove_proc_entry("ip_vs_stats_percpu", ipvs->net->proc_net); + +err_percpu: + remove_proc_entry("ip_vs_stats", ipvs->net->proc_net); + +err_stats: + remove_proc_entry("ip_vs", ipvs->net->proc_net); + +err_vs: +#endif free_percpu(ipvs->tot_stats.cpustats); return -ENOMEM; } @@ -4188,9 +4205,11 @@ void __net_exit ip_vs_control_net_cleanup(struct netns_ipvs *ipvs) { ip_vs_trash_cleanup(ipvs); ip_vs_control_net_cleanup_sysctl(ipvs); +#ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_stats_percpu", ipvs->net->proc_net); remove_proc_entry("ip_vs_stats", ipvs->net->proc_net); remove_proc_entry("ip_vs", ipvs->net->proc_net); +#endif free_percpu(ipvs->tot_stats.cpustats); } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0f58e98542be..23abf1578594 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -619,7 +619,8 @@ static int nft_request_module(struct net *net, const char *fmt, ...) static void lockdep_nfnl_nft_mutex_not_held(void) { #ifdef CONFIG_PROVE_LOCKING - WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); + if (debug_locks) + WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); #endif } diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 9f625724a20f..9ae14270c543 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -28,6 +28,23 @@ static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions) return flow; } +void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, + enum flow_dissector_key_id addr_type) +{ + struct nft_flow_match *match = &flow->match; + struct nft_flow_key *mask = &match->mask; + struct nft_flow_key *key = &match->key; + + if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) + return; + + key->control.addr_type = addr_type; + mask->control.addr_type = 0xffff; + match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL); + match->dissector.offset[FLOW_DISSECTOR_KEY_CONTROL] = + offsetof(struct nft_flow_key, control); +} + struct nft_flow_rule *nft_flow_rule_create(struct net *net, const struct nft_rule *rule) { diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index bc079d68a536..00e563a72d3d 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -123,11 +123,11 @@ static int __nft_cmp_offload(struct nft_offload_ctx *ctx, u8 *mask = (u8 *)&flow->match.mask; u8 *key = (u8 *)&flow->match.key; - if (priv->op != NFT_CMP_EQ || reg->len != priv->len) + if (priv->op != NFT_CMP_EQ || priv->len > reg->len) return -EOPNOTSUPP; - memcpy(key + reg->offset, &priv->data, priv->len); - memcpy(mask + reg->offset, ®->mask, priv->len); + memcpy(key + reg->offset, &priv->data, reg->len); + memcpy(mask + reg->offset, ®->mask, reg->len); flow->match.dissector.used_keys |= BIT(reg->key); flow->match.dissector.offset[reg->key] = reg->base_offset; @@ -137,7 +137,7 @@ static int __nft_cmp_offload(struct nft_offload_ctx *ctx, nft_reg_load16(priv->data.data) != ARPHRD_ETHER) return -EOPNOTSUPP; - nft_offload_update_dependency(ctx, &priv->data, priv->len); + nft_offload_update_dependency(ctx, &priv->data, reg->len); return 0; } diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index b37bd02448d8..bf4b3ad5314c 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -724,22 +724,22 @@ static int nft_meta_get_offload(struct nft_offload_ctx *ctx, switch (priv->key) { case NFT_META_PROTOCOL: - NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, n_proto, - sizeof(__u16), reg); + NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_BASIC, basic, n_proto, + sizeof(__u16), reg); nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK); break; case NFT_META_L4PROTO: - NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto, - sizeof(__u8), reg); + NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto, + sizeof(__u8), reg); nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_TRANSPORT); break; case NFT_META_IIF: - NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_META, meta, - ingress_ifindex, sizeof(__u32), reg); + NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_META, meta, + ingress_ifindex, sizeof(__u32), reg); break; case NFT_META_IIFTYPE: - NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_META, meta, - ingress_iftype, sizeof(__u16), reg); + NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_META, meta, + ingress_iftype, sizeof(__u16), reg); break; default: return -EOPNOTSUPP; diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index dcd3c7b8a367..47d4e0e21651 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -165,6 +165,34 @@ nla_put_failure: return -1; } +static bool nft_payload_offload_mask(struct nft_offload_reg *reg, + u32 priv_len, u32 field_len) +{ + unsigned int remainder, delta, k; + struct nft_data mask = {}; + __be32 remainder_mask; + + if (priv_len == field_len) { + memset(®->mask, 0xff, priv_len); + return true; + } else if (priv_len > field_len) { + return false; + } + + memset(&mask, 0xff, field_len); + remainder = priv_len % sizeof(u32); + if (remainder) { + k = priv_len / sizeof(u32); + delta = field_len - priv_len; + remainder_mask = htonl(~((1 << (delta * BITS_PER_BYTE)) - 1)); + mask.data[k] = (__force u32)remainder_mask; + } + + memcpy(®->mask, &mask, field_len); + + return true; +} + static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow, const struct nft_payload *priv) @@ -173,21 +201,21 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct ethhdr, h_source): - if (priv->len != ETH_ALEN) + if (!nft_payload_offload_mask(reg, priv->len, ETH_ALEN)) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs, src, ETH_ALEN, reg); break; case offsetof(struct ethhdr, h_dest): - if (priv->len != ETH_ALEN) + if (!nft_payload_offload_mask(reg, priv->len, ETH_ALEN)) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs, dst, ETH_ALEN, reg); break; case offsetof(struct ethhdr, h_proto): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, @@ -195,14 +223,14 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK); break; case offsetof(struct vlan_ethhdr, h_vlan_TCI): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_VLAN, vlan, vlan_tci, sizeof(__be16), reg); break; case offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_VLAN, vlan, @@ -210,7 +238,7 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK); break; case offsetof(struct vlan_ethhdr, h_vlan_TCI) + sizeof(struct vlan_hdr): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_CVLAN, vlan, @@ -218,7 +246,7 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, break; case offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto) + sizeof(struct vlan_hdr): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_CVLAN, vlan, @@ -239,21 +267,25 @@ static int nft_payload_offload_ip(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct iphdr, saddr): - if (priv->len != sizeof(struct in_addr)) + if (!nft_payload_offload_mask(reg, priv->len, + sizeof(struct in_addr))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, src, sizeof(struct in_addr), reg); + nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV4_ADDRS); break; case offsetof(struct iphdr, daddr): - if (priv->len != sizeof(struct in_addr)) + if (!nft_payload_offload_mask(reg, priv->len, + sizeof(struct in_addr))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, dst, sizeof(struct in_addr), reg); + nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV4_ADDRS); break; case offsetof(struct iphdr, protocol): - if (priv->len != sizeof(__u8)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__u8))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto, @@ -275,21 +307,25 @@ static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct ipv6hdr, saddr): - if (priv->len != sizeof(struct in6_addr)) + if (!nft_payload_offload_mask(reg, priv->len, + sizeof(struct in6_addr))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, src, sizeof(struct in6_addr), reg); + nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV6_ADDRS); break; case offsetof(struct ipv6hdr, daddr): - if (priv->len != sizeof(struct in6_addr)) + if (!nft_payload_offload_mask(reg, priv->len, + sizeof(struct in6_addr))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, dst, sizeof(struct in6_addr), reg); + nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV6_ADDRS); break; case offsetof(struct ipv6hdr, nexthdr): - if (priv->len != sizeof(__u8)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__u8))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto, @@ -331,14 +367,14 @@ static int nft_payload_offload_tcp(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct tcphdr, source): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src, sizeof(__be16), reg); break; case offsetof(struct tcphdr, dest): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst, @@ -359,14 +395,14 @@ static int nft_payload_offload_udp(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct udphdr, source): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src, sizeof(__be16), reg); break; case offsetof(struct udphdr, dest): - if (priv->len != sizeof(__be16)) + if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16))) return -EOPNOTSUPP; NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst, diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index b87bfc82f44f..c3a664871cb5 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -199,6 +199,9 @@ static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key, __be32 lse; int err; + if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN)) + return -ENOMEM; + stack = mpls_hdr(skb); lse = OVS_MASKED(stack->label_stack_entry, *mpls_lse, *mask); err = skb_mpls_update_lse(skb, lse); @@ -958,14 +961,13 @@ static int dec_ttl_exception_handler(struct datapath *dp, struct sk_buff *skb, { /* The first action is always 'OVS_DEC_TTL_ATTR_ARG'. */ struct nlattr *dec_ttl_arg = nla_data(attr); - int rem = nla_len(attr); if (nla_len(dec_ttl_arg)) { - struct nlattr *actions = nla_next(dec_ttl_arg, &rem); + struct nlattr *actions = nla_data(dec_ttl_arg); if (actions) - return clone_execute(dp, skb, key, 0, actions, rem, - last, false); + return clone_execute(dp, skb, key, 0, nla_data(actions), + nla_len(actions), last, false); } consume_skb(skb); return 0; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 9d3e50c4d29f..ec0689ddc635 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2503,28 +2503,42 @@ static int validate_and_copy_dec_ttl(struct net *net, __be16 eth_type, __be16 vlan_tci, u32 mpls_label_count, bool log) { - int start, err; - u32 nested = true; + const struct nlattr *attrs[OVS_DEC_TTL_ATTR_MAX + 1]; + int start, action_start, err, rem; + const struct nlattr *a, *actions; + + memset(attrs, 0, sizeof(attrs)); + nla_for_each_nested(a, attr, rem) { + int type = nla_type(a); - if (!nla_len(attr)) - return ovs_nla_add_action(sfa, OVS_ACTION_ATTR_DEC_TTL, - NULL, 0, log); + /* Ignore unknown attributes to be future proof. */ + if (type > OVS_DEC_TTL_ATTR_MAX) + continue; + + if (!type || attrs[type]) + return -EINVAL; + + attrs[type] = a; + } + + actions = attrs[OVS_DEC_TTL_ATTR_ACTION]; + if (rem || !actions || (nla_len(actions) && nla_len(actions) < NLA_HDRLEN)) + return -EINVAL; start = add_nested_action_start(sfa, OVS_ACTION_ATTR_DEC_TTL, log); if (start < 0) return start; - err = ovs_nla_add_action(sfa, OVS_DEC_TTL_ATTR_ACTION, &nested, - sizeof(nested), log); - - if (err) - return err; + action_start = add_nested_action_start(sfa, OVS_DEC_TTL_ATTR_ACTION, log); + if (action_start < 0) + return start; - err = __ovs_nla_copy_actions(net, attr, key, sfa, eth_type, + err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type, vlan_tci, mpls_label_count, log); if (err) return err; + add_nested_action_end(*sfa, action_start); add_nested_action_end(*sfa, start); return 0; } @@ -3487,20 +3501,42 @@ out: static int dec_ttl_action_to_attr(const struct nlattr *attr, struct sk_buff *skb) { - int err = 0, rem = nla_len(attr); - struct nlattr *start; + struct nlattr *start, *action_start; + const struct nlattr *a; + int err = 0, rem; start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_DEC_TTL); - if (!start) return -EMSGSIZE; - err = ovs_nla_put_actions(nla_data(attr), rem, skb); - if (err) - nla_nest_cancel(skb, start); - else - nla_nest_end(skb, start); + nla_for_each_attr(a, nla_data(attr), nla_len(attr), rem) { + switch (nla_type(a)) { + case OVS_DEC_TTL_ATTR_ACTION: + + action_start = nla_nest_start_noflag(skb, OVS_DEC_TTL_ATTR_ACTION); + if (!action_start) { + err = -EMSGSIZE; + goto out; + } + + err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb); + if (err) + goto out; + + nla_nest_end(skb, action_start); + break; + default: + /* Ignore all other option to be future compatible */ + break; + } + } + + nla_nest_end(skb, start); + return 0; + +out: + nla_nest_cancel(skb, start); return err; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index cefbd50c1090..7a18ffff8551 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -93,8 +93,8 @@ /* Assumptions: - - If the device has no dev->header_ops, there is no LL header visible - above the device. In this case, its hard_header_len should be 0. + - If the device has no dev->header_ops->create, there is no LL header + visible above the device. In this case, its hard_header_len should be 0. The device may prepend its own header internally. In this case, its needed_headroom should be set to the space needed for it to add its internal header. @@ -108,26 +108,26 @@ On receive: ----------- -Incoming, dev->header_ops != NULL +Incoming, dev_has_header(dev) == true mac_header -> ll header data -> data -Outgoing, dev->header_ops != NULL +Outgoing, dev_has_header(dev) == true mac_header -> ll header data -> ll header -Incoming, dev->header_ops == NULL +Incoming, dev_has_header(dev) == false mac_header -> data However drivers often make it point to the ll header. This is incorrect because the ll header should be invisible to us. data -> data -Outgoing, dev->header_ops == NULL +Outgoing, dev_has_header(dev) == false mac_header -> data. ll header is invisible to us. data -> data Resume - If dev->header_ops == NULL we are unable to restore the ll header, + If dev_has_header(dev) == false we are unable to restore the ll header, because it is invisible to us. @@ -2069,7 +2069,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, skb->dev = dev; - if (dev->header_ops) { + if (dev_has_header(dev)) { /* The device has an explicit notion of ll header, * exported to higher levels. * @@ -2198,7 +2198,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; - if (dev->header_ops) { + if (dev_has_header(dev)) { if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 7b094275ea8b..11c45c8c6c16 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -96,10 +96,19 @@ static void rose_loopback_timer(struct timer_list *unused) } if (frametype == ROSE_CALL_REQUEST) { - if ((dev = rose_dev_get(dest)) != NULL) { - if (rose_rx_call_request(skb, dev, rose_loopback_neigh, lci_o) == 0) - kfree_skb(skb); - } else { + if (!rose_loopback_neigh->dev) { + kfree_skb(skb); + continue; + } + + dev = rose_dev_get(dest); + if (!dev) { + kfree_skb(skb); + continue; + } + + if (rose_rx_call_request(skb, dev, rose_loopback_neigh, lci_o) == 0) { + dev_put(dev); kfree_skb(skb); } } else { diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index 5c7456e5b5cf..d1486ea496a2 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -105,6 +105,9 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, goto drop; break; case TCA_MPLS_ACT_MODIFY: + if (!pskb_may_pull(skb, + skb_network_offset(skb) + MPLS_HLEN)) + goto drop; new_lse = tcf_mpls_get_lse(mpls_hdr(skb), p, false); if (skb_mpls_update_lse(skb, new_lse)) goto drop; diff --git a/net/tipc/node.c b/net/tipc/node.c index d269ebe382e1..c95d037fde51 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -2182,6 +2182,8 @@ void tipc_node_apply_property(struct net *net, struct tipc_bearer *b, else if (prop == TIPC_NLA_PROP_MTU) tipc_link_set_mtu(e->link, b->mtu); } + /* Update MTU for node link entry */ + e->mtu = tipc_link_mss(e->link); tipc_node_write_unlock(n); tipc_bearer_xmit(net, bearer_id, &xmitq, &e->maddr, NULL); } diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 54d3e161d198..a3ab2d3d4e4e 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -1262,6 +1262,8 @@ void tls_device_offload_cleanup_rx(struct sock *sk) if (tls_ctx->tx_conf != TLS_HW) { dev_put(netdev); tls_ctx->netdev = NULL; + } else { + set_bit(TLS_RX_DEV_CLOSED, &tls_ctx->flags); } out: up_read(&device_offload_lock); @@ -1291,7 +1293,8 @@ static int tls_device_down(struct net_device *netdev) if (ctx->tx_conf == TLS_HW) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_TX); - if (ctx->rx_conf == TLS_HW) + if (ctx->rx_conf == TLS_HW && + !test_bit(TLS_RX_DEV_CLOSED, &ctx->flags)) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_RX); WRITE_ONCE(ctx->netdev, NULL); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 2fe9e2cf8659..845c628ac1b2 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1295,6 +1295,12 @@ static struct sk_buff *tls_wait_data(struct sock *sk, struct sk_psock *psock, return NULL; } + if (!skb_queue_empty(&sk->sk_receive_queue)) { + __strp_unpause(&ctx->strp); + if (ctx->recv_pkt) + return ctx->recv_pkt; + } + if (sk->sk_shutdown & RCV_SHUTDOWN) return NULL; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 0edda1edf988..5956939eebb7 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -841,8 +841,10 @@ void virtio_transport_release(struct vsock_sock *vsk) virtio_transport_free_pkt(pkt); } - if (remove_sock) + if (remove_sock) { + sock_set_flag(sk, SOCK_DONE); vsock_remove_sock(vsk); + } } EXPORT_SYMBOL_GPL(virtio_transport_release); @@ -1132,8 +1134,8 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, lock_sock(sk); - /* Check if sk has been released before lock_sock */ - if (sk->sk_shutdown == SHUTDOWN_MASK) { + /* Check if sk has been closed before lock_sock */ + if (sock_flag(sk, SOCK_DONE)) { (void)virtio_transport_reset_no_sock(t, pkt); release_sock(sk); sock_put(sk); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index a10487e7574c..e65a50192432 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -681,7 +681,8 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) int len, i, rc = 0; if (addr_len != sizeof(struct sockaddr_x25) || - addr->sx25_family != AF_X25) { + addr->sx25_family != AF_X25 || + strnlen(addr->sx25_addr.x25_addr, X25_ADDR_LEN) == X25_ADDR_LEN) { rc = -EINVAL; goto out; } @@ -775,7 +776,8 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr, rc = -EINVAL; if (addr_len != sizeof(struct sockaddr_x25) || - addr->sx25_family != AF_X25) + addr->sx25_family != AF_X25 || + strnlen(addr->sx25_addr.x25_addr, X25_ADDR_LEN) == X25_ADDR_LEN) goto out; rc = -ENETUNREACH; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 56d052bc65cb..56a28a686988 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -66,18 +66,31 @@ static void xdp_umem_release(struct xdp_umem *umem) kfree(umem); } +static void xdp_umem_release_deferred(struct work_struct *work) +{ + struct xdp_umem *umem = container_of(work, struct xdp_umem, work); + + xdp_umem_release(umem); +} + void xdp_get_umem(struct xdp_umem *umem) { refcount_inc(&umem->users); } -void xdp_put_umem(struct xdp_umem *umem) +void xdp_put_umem(struct xdp_umem *umem, bool defer_cleanup) { if (!umem) return; - if (refcount_dec_and_test(&umem->users)) - xdp_umem_release(umem); + if (refcount_dec_and_test(&umem->users)) { + if (defer_cleanup) { + INIT_WORK(&umem->work, xdp_umem_release_deferred); + schedule_work(&umem->work); + } else { + xdp_umem_release(umem); + } + } } static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address) diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h index 181fdda2f2a8..aa9fe2780410 100644 --- a/net/xdp/xdp_umem.h +++ b/net/xdp/xdp_umem.h @@ -9,7 +9,7 @@ #include <net/xdp_sock_drv.h> void xdp_get_umem(struct xdp_umem *umem); -void xdp_put_umem(struct xdp_umem *umem); +void xdp_put_umem(struct xdp_umem *umem, bool defer_cleanup); struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr); #endif /* XDP_UMEM_H_ */ diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index cfbec3989a76..b7b039bd9d03 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -411,11 +411,7 @@ static int xsk_generic_xmit(struct sock *sk) skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr; skb->destructor = xsk_destruct_skb; - /* Hinder dev_direct_xmit from freeing the packet and - * therefore completing it in the destructor - */ - refcount_inc(&skb->users); - err = dev_direct_xmit(skb, xs->queue_id); + err = __dev_direct_xmit(skb, xs->queue_id); if (err == NETDEV_TX_BUSY) { /* Tell user-space to retry the send */ skb->destructor = sock_wfree; @@ -429,12 +425,10 @@ static int xsk_generic_xmit(struct sock *sk) /* Ignore NET_XMIT_CN as packet might have been sent */ if (err == NET_XMIT_DROP) { /* SKB completed but not sent */ - kfree_skb(skb); err = -EBUSY; goto out; } - consume_skb(skb); sent_frame = true; } @@ -1147,7 +1141,7 @@ static void xsk_destruct(struct sock *sk) return; if (!xp_put_pool(xs->pool)) - xdp_put_umem(xs->umem); + xdp_put_umem(xs->umem, !xs->pool); sk_refcnt_debug_dec(sk); } diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 8a3bf4e1318e..9287eddec52c 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -185,8 +185,10 @@ err_unreg_xsk: err_unreg_pool: if (!force_zc) err = 0; /* fallback to copy mode */ - if (err) + if (err) { xsk_clear_pool_at_qid(netdev, queue_id); + dev_put(netdev); + } return err; } @@ -242,7 +244,7 @@ static void xp_release_deferred(struct work_struct *work) pool->cq = NULL; } - xdp_put_umem(pool->umem); + xdp_put_umem(pool->umem, false); xp_destroy(pool); } |