diff options
Diffstat (limited to 'net')
57 files changed, 458 insertions, 232 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index a3a0a5e994f5..abaa5d96ded2 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -184,9 +184,6 @@ int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) if (err) goto out_unregister_netdev; - /* Account for reference in struct vlan_dev_priv */ - dev_hold(real_dev); - vlan_stacked_transfer_operstate(real_dev, dev, vlan); linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */ diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index ab6dee28536d..a54535cbcf4c 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -615,6 +615,9 @@ static int vlan_dev_init(struct net_device *dev) if (!vlan->vlan_pcpu_stats) return -ENOMEM; + /* Get vlan's reference to real_dev */ + dev_hold(real_dev); + return 0; } diff --git a/net/core/dev.c b/net/core/dev.c index 15ac064b5562..2a352e668d10 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4210,7 +4210,10 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ - if (txq->xmit_lock_owner != cpu) { + /* Other cpus might concurrently change txq->xmit_lock_owner + * to -1 or to their cpu id, but not to our id. + */ + if (READ_ONCE(txq->xmit_lock_owner) != cpu) { if (dev_xmit_recursion()) goto recursion_alert; diff --git a/net/core/devlink.c b/net/core/devlink.c index 5ad72dbfcd07..c06c9ba6e8c5 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4110,14 +4110,6 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) return err; } - if (info->attrs[DEVLINK_ATTR_NETNS_PID] || - info->attrs[DEVLINK_ATTR_NETNS_FD] || - info->attrs[DEVLINK_ATTR_NETNS_ID]) { - dest_net = devlink_netns_get(skb, info); - if (IS_ERR(dest_net)) - return PTR_ERR(dest_net); - } - if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION]) action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]); else @@ -4160,6 +4152,14 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } } + if (info->attrs[DEVLINK_ATTR_NETNS_PID] || + info->attrs[DEVLINK_ATTR_NETNS_FD] || + info->attrs[DEVLINK_ATTR_NETNS_ID]) { + dest_net = devlink_netns_get(skb, info); + if (IS_ERR(dest_net)) + return PTR_ERR(dest_net); + } + err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack); if (dest_net) diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c index be74ab4551c2..0ccfd5fa5cb9 100644 --- a/net/core/dst_cache.c +++ b/net/core/dst_cache.c @@ -162,3 +162,22 @@ void dst_cache_destroy(struct dst_cache *dst_cache) free_percpu(dst_cache->cache); } EXPORT_SYMBOL_GPL(dst_cache_destroy); + +void dst_cache_reset_now(struct dst_cache *dst_cache) +{ + int i; + + if (!dst_cache->cache) + return; + + dst_cache->reset_ts = jiffies; + for_each_possible_cpu(i) { + struct dst_cache_pcpu *idst = per_cpu_ptr(dst_cache->cache, i); + struct dst_entry *dst = idst->dst; + + idst->cookie = 0; + idst->dst = NULL; + dst_release(dst); + } +} +EXPORT_SYMBOL_GPL(dst_cache_reset_now); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 79df7cd9dbc1..1bb567a3b329 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -323,7 +323,7 @@ jumped: if (!err && ops->suppress && INDIRECT_CALL_MT(ops->suppress, fib6_rule_suppress, fib4_rule_suppress, - rule, arg)) + rule, flags, arg)) continue; if (err != -EAGAIN) { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 47931c8be04b..dda12fbd177b 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -763,11 +763,10 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, ASSERT_RTNL(); - n = kmalloc(sizeof(*n) + key_len, GFP_KERNEL); + n = kzalloc(sizeof(*n) + key_len, GFP_KERNEL); if (!n) goto out; - n->protocol = 0; write_pnet(&n->net, net); memcpy(n->key, pkey, key_len); n->dev = dev; @@ -1779,6 +1778,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl) { neigh_tables[index] = NULL; /* It is not clean... Fix it to unload IPv6 module safely */ + cancel_delayed_work_sync(&tbl->managed_work); cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); pneigh_queue_purge(&tbl->proxy_queue); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 1ae52ac943f6..8eb671c827f9 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1124,6 +1124,8 @@ void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) { + psock_set_prog(&psock->progs.stream_parser, NULL); + if (!psock->saved_data_ready) return; @@ -1212,6 +1214,9 @@ void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock) void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock) { + psock_set_prog(&psock->progs.stream_verdict, NULL); + psock_set_prog(&psock->progs.skb_verdict, NULL); + if (!psock->saved_data_ready) return; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index f39ef79ced67..4ca4b11f4e5f 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -167,8 +167,11 @@ static void sock_map_del_link(struct sock *sk, write_lock_bh(&sk->sk_callback_lock); if (strp_stop) sk_psock_stop_strp(sk, psock); - else + if (verdict_stop) sk_psock_stop_verdict(sk, psock); + + if (psock->psock_update_sk_prot) + psock->psock_update_sk_prot(sk, psock, false); write_unlock_bh(&sk->sk_callback_lock); } } @@ -282,6 +285,12 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk) if (msg_parser) psock_set_prog(&psock->progs.msg_parser, msg_parser); + if (stream_parser) + psock_set_prog(&psock->progs.stream_parser, stream_parser); + if (stream_verdict) + psock_set_prog(&psock->progs.stream_verdict, stream_verdict); + if (skb_verdict) + psock_set_prog(&psock->progs.skb_verdict, skb_verdict); ret = sock_map_init_proto(sk, psock); if (ret < 0) @@ -292,14 +301,10 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk) ret = sk_psock_init_strp(sk, psock); if (ret) goto out_unlock_drop; - psock_set_prog(&psock->progs.stream_verdict, stream_verdict); - psock_set_prog(&psock->progs.stream_parser, stream_parser); sk_psock_start_strp(sk, psock); } else if (!stream_parser && stream_verdict && !psock->saved_data_ready) { - psock_set_prog(&psock->progs.stream_verdict, stream_verdict); sk_psock_start_verdict(sk,psock); } else if (!stream_verdict && skb_verdict && !psock->saved_data_ready) { - psock_set_prog(&psock->progs.skb_verdict, skb_verdict); sk_psock_start_verdict(sk, psock); } write_unlock_bh(&sk->sk_callback_lock); diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 65e9bc1058b5..20bcf86970ff 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1719,7 +1719,7 @@ static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev, struct ethtool_coalesce coalesce; int ret; - if (!dev->ethtool_ops->set_coalesce && !dev->ethtool_ops->get_coalesce) + if (!dev->ethtool_ops->set_coalesce || !dev->ethtool_ops->get_coalesce) return -EOPNOTSUPP; ret = dev->ethtool_ops->get_coalesce(dev, &coalesce, &kernel_coalesce, diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 38b44c0291b1..96f4180aabd2 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -40,7 +40,8 @@ int ethnl_ops_begin(struct net_device *dev) if (dev->dev.parent) pm_runtime_get_sync(dev->dev.parent); - if (!netif_device_present(dev)) { + if (!netif_device_present(dev) || + dev->reg_state == NETREG_UNREGISTERING) { ret = -ENODEV; goto err; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 9fe13e4f5d08..4d61ddd8a0ec 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1582,7 +1582,7 @@ static int __net_init fib_net_init(struct net *net) int error; #ifdef CONFIG_IP_ROUTE_CLASSID - net->ipv4.fib_num_tclassid_users = 0; + atomic_set(&net->ipv4.fib_num_tclassid_users, 0); #endif error = ip_fib_net_init(net); if (error < 0) diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index ce54a30c2ef1..d279cb8ac158 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -141,6 +141,7 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_action(struct fib_rule *rule, } INDIRECT_CALLABLE_SCOPE bool fib4_rule_suppress(struct fib_rule *rule, + int flags, struct fib_lookup_arg *arg) { struct fib_result *result = (struct fib_result *) arg->result; @@ -263,7 +264,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, if (tb[FRA_FLOW]) { rule4->tclassid = nla_get_u32(tb[FRA_FLOW]); if (rule4->tclassid) - net->ipv4.fib_num_tclassid_users++; + atomic_inc(&net->ipv4.fib_num_tclassid_users); } #endif @@ -295,7 +296,7 @@ static int fib4_rule_delete(struct fib_rule *rule) #ifdef CONFIG_IP_ROUTE_CLASSID if (((struct fib4_rule *)rule)->tclassid) - net->ipv4.fib_num_tclassid_users--; + atomic_dec(&net->ipv4.fib_num_tclassid_users); #endif net->ipv4.fib_has_custom_rules = true; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 3364cb9c67e0..fde7797b5806 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -220,7 +220,7 @@ void fib_nh_release(struct net *net, struct fib_nh *fib_nh) { #ifdef CONFIG_IP_ROUTE_CLASSID if (fib_nh->nh_tclassid) - net->ipv4.fib_num_tclassid_users--; + atomic_dec(&net->ipv4.fib_num_tclassid_users); #endif fib_nh_common_release(&fib_nh->nh_common); } @@ -632,7 +632,7 @@ int fib_nh_init(struct net *net, struct fib_nh *nh, #ifdef CONFIG_IP_ROUTE_CLASSID nh->nh_tclassid = cfg->fc_flow; if (nh->nh_tclassid) - net->ipv4.fib_num_tclassid_users++; + atomic_inc(&net->ipv4.fib_num_tclassid_users); #endif #ifdef CONFIG_IP_ROUTE_MULTIPATH nh->fib_nh_weight = nh_weight; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index f7fea3a7c5e6..62a67fdc344c 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -721,7 +721,7 @@ static struct request_sock *inet_reqsk_clone(struct request_sock *req, sk_node_init(&nreq_sk->sk_node); nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping; -#ifdef CONFIG_XPS +#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING nreq_sk->sk_rx_queue_mapping = req_sk->sk_rx_queue_mapping; #endif nreq_sk->sk_incoming_cpu = req_sk->sk_incoming_cpu; diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 9e8100728d46..5dbd4b5505eb 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -1899,15 +1899,36 @@ static void remove_nexthop(struct net *net, struct nexthop *nh, /* if any FIB entries reference this nexthop, any dst entries * need to be regenerated */ -static void nh_rt_cache_flush(struct net *net, struct nexthop *nh) +static void nh_rt_cache_flush(struct net *net, struct nexthop *nh, + struct nexthop *replaced_nh) { struct fib6_info *f6i; + struct nh_group *nhg; + int i; if (!list_empty(&nh->fi_list)) rt_cache_flush(net); list_for_each_entry(f6i, &nh->f6i_list, nh_list) ipv6_stub->fib6_update_sernum(net, f6i); + + /* if an IPv6 group was replaced, we have to release all old + * dsts to make sure all refcounts are released + */ + if (!replaced_nh->is_group) + return; + + /* new dsts must use only the new nexthop group */ + synchronize_net(); + + nhg = rtnl_dereference(replaced_nh->nh_grp); + for (i = 0; i < nhg->num_nh; i++) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + struct nh_info *nhi = rtnl_dereference(nhge->nh->nh_info); + + if (nhi->family == AF_INET6) + ipv6_stub->fib6_nh_release_dsts(&nhi->fib6_nh); + } } static int replace_nexthop_grp(struct net *net, struct nexthop *old, @@ -2247,7 +2268,7 @@ static int replace_nexthop(struct net *net, struct nexthop *old, err = replace_nexthop_single(net, old, new, extack); if (!err) { - nh_rt_cache_flush(net, old); + nh_rt_cache_flush(net, old, new); __remove_nexthop(net, new, NULL); nexthop_put(new); @@ -2544,11 +2565,15 @@ static int nh_create_ipv6(struct net *net, struct nexthop *nh, /* sets nh_dev if successful */ err = ipv6_stub->fib6_nh_init(net, fib6_nh, &fib6_cfg, GFP_KERNEL, extack); - if (err) + if (err) { + /* IPv6 is not enabled, don't call fib6_nh_release */ + if (err == -EAFNOSUPPORT) + goto out; ipv6_stub->fib6_nh_release(fib6_nh); - else + } else { nh->nh_flags = fib6_nh->fib_nh_flags; - + } +out: return err; } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 5e9d9c51164c..e07837e23b3f 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -330,8 +330,6 @@ static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) return; if (tcp_in_slow_start(tp)) { - if (hystart && after(ack, ca->end_seq)) - bictcp_hystart_reset(sk); acked = tcp_slow_start(tp, acked); if (!acked) return; @@ -391,6 +389,9 @@ static void hystart_update(struct sock *sk, u32 delay) struct bictcp *ca = inet_csk_ca(sk); u32 threshold; + if (after(tp->snd_una, ca->end_seq)) + bictcp_hystart_reset(sk); + if (hystart_detect & HYSTART_ACK_TRAIN) { u32 now = bictcp_clock_us(sk); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index cf913a66df17..7c2d3ac2363a 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -829,8 +829,8 @@ int tcp_child_process(struct sock *parent, struct sock *child, int ret = 0; int state = child->sk_state; - /* record NAPI ID of child */ - sk_mark_napi_id(child, skb); + /* record sk_napi_id and sk_rx_queue_mapping of child. */ + sk_mark_napi_id_set(child, skb); tcp_segs_in(tcp_sk(child), skb); if (!sock_owned_by_user(child)) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8bcecdd6aeda..23b05e28490b 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -916,7 +916,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, kfree_skb(skb); return -EINVAL; } - if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) { + if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) { kfree_skb(skb); return -EINVAL; } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 0c4da163535a..dab4a047590b 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1026,6 +1026,7 @@ static const struct ipv6_stub ipv6_stub_impl = { .ip6_mtu_from_fib6 = ip6_mtu_from_fib6, .fib6_nh_init = fib6_nh_init, .fib6_nh_release = fib6_nh_release, + .fib6_nh_release_dsts = fib6_nh_release_dsts, .fib6_update_sernum = fib6_update_sernum_stub, .fib6_rt_update = fib6_rt_update, .ip6_del_rt = ip6_del_rt, diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 40f3e4f9f33a..dcedfe29d9d9 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -267,6 +267,7 @@ INDIRECT_CALLABLE_SCOPE int fib6_rule_action(struct fib_rule *rule, } INDIRECT_CALLABLE_SCOPE bool fib6_rule_suppress(struct fib_rule *rule, + int flags, struct fib_lookup_arg *arg) { struct fib6_result *res = arg->result; @@ -294,8 +295,7 @@ INDIRECT_CALLABLE_SCOPE bool fib6_rule_suppress(struct fib_rule *rule, return false; suppress_route: - if (!(arg->flags & FIB_LOOKUP_NOREF)) - ip6_rt_put(rt); + ip6_rt_put_flags(rt, flags); return true; } diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 1b9827ff8ccf..1cbd49d5788d 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -248,9 +248,9 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, * memcmp() alone below is sufficient, right? */ if ((first_word & htonl(0xF00FFFFF)) || - !ipv6_addr_equal(&iph->saddr, &iph2->saddr) || - !ipv6_addr_equal(&iph->daddr, &iph2->daddr) || - *(u16 *)&iph->nexthdr != *(u16 *)&iph2->nexthdr) { + !ipv6_addr_equal(&iph->saddr, &iph2->saddr) || + !ipv6_addr_equal(&iph->daddr, &iph2->daddr) || + *(u16 *)&iph->nexthdr != *(u16 *)&iph2->nexthdr) { not_same_flow: NAPI_GRO_CB(p)->same_flow = 0; continue; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 2f044a49afa8..ff4e83e2a506 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -174,7 +174,7 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { - IPCB(skb)->flags |= IPSKB_REROUTED; + IP6CB(skb)->flags |= IP6SKB_REROUTED; return dst_output(net, sk, skb); } #endif diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 3ae25b8ffbd6..42d60c76d30a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3680,6 +3680,25 @@ void fib6_nh_release(struct fib6_nh *fib6_nh) fib_nh_common_release(&fib6_nh->nh_common); } +void fib6_nh_release_dsts(struct fib6_nh *fib6_nh) +{ + int cpu; + + if (!fib6_nh->rt6i_pcpu) + return; + + for_each_possible_cpu(cpu) { + struct rt6_info *pcpu_rt, **ppcpu_rt; + + ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); + pcpu_rt = xchg(ppcpu_rt, NULL); + if (pcpu_rt) { + dst_dev_put(&pcpu_rt->dst); + dst_release(&pcpu_rt->dst); + } + } +} + static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 3adc5d9211ad..d64855010948 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -161,6 +161,14 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + + /* the control block has been erased, so we have to set the + * iif once again. + * We read the receiving interface index directly from the + * skb->skb_iif as it is done in the IPv4 receiving path (i.e.: + * ip_rcv_core(...)). + */ + IP6CB(skb)->iif = skb->skb_iif; } hdr->nexthdr = NEXTHDR_ROUTING; diff --git a/net/mctp/route.c b/net/mctp/route.c index 46c44823edb7..cdf09c2a7007 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -952,7 +952,7 @@ static int mctp_route_add(struct mctp_dev *mdev, mctp_eid_t daddr_start, } static int mctp_route_remove(struct mctp_dev *mdev, mctp_eid_t daddr_start, - unsigned int daddr_extent) + unsigned int daddr_extent, unsigned char type) { struct net *net = dev_net(mdev->dev); struct mctp_route *rt, *tmp; @@ -969,7 +969,8 @@ static int mctp_route_remove(struct mctp_dev *mdev, mctp_eid_t daddr_start, list_for_each_entry_safe(rt, tmp, &net->mctp.routes, list) { if (rt->dev == mdev && - rt->min == daddr_start && rt->max == daddr_end) { + rt->min == daddr_start && rt->max == daddr_end && + rt->type == type) { list_del_rcu(&rt->list); /* TODO: immediate RTM_DELROUTE */ mctp_route_release(rt); @@ -987,7 +988,7 @@ int mctp_route_add_local(struct mctp_dev *mdev, mctp_eid_t addr) int mctp_route_remove_local(struct mctp_dev *mdev, mctp_eid_t addr) { - return mctp_route_remove(mdev, addr, 0); + return mctp_route_remove(mdev, addr, 0, RTN_LOCAL); } /* removes all entries for a given device */ @@ -1195,7 +1196,7 @@ static int mctp_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, if (rtm->rtm_type != RTN_UNICAST) return -EINVAL; - rc = mctp_route_remove(mdev, daddr_start, rtm->rtm_dst_len); + rc = mctp_route_remove(mdev, daddr_start, rtm->rtm_dst_len, RTN_UNICAST); return rc; } diff --git a/net/mctp/test/utils.c b/net/mctp/test/utils.c index cc6b8803aa9d..7b7918702592 100644 --- a/net/mctp/test/utils.c +++ b/net/mctp/test/utils.c @@ -12,7 +12,7 @@ static netdev_tx_t mctp_test_dev_tx(struct sk_buff *skb, struct net_device *ndev) { - kfree(skb); + kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index ffeb2df8be7a..0c7bde1c14a6 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -409,7 +409,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, goto err; /* Find the output device */ - out_dev = rcu_dereference(nh->nh_dev); + out_dev = nh->nh_dev; if (!mpls_output_possible(out_dev)) goto tx_err; @@ -698,7 +698,7 @@ static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt, (dev->addr_len != nh->nh_via_alen)) goto errout; - RCU_INIT_POINTER(nh->nh_dev, dev); + nh->nh_dev = dev; if (!(dev->flags & IFF_UP)) { nh->nh_flags |= RTNH_F_DEAD; @@ -1491,26 +1491,53 @@ static void mpls_dev_destroy_rcu(struct rcu_head *head) kfree(mdev); } -static void mpls_ifdown(struct net_device *dev, int event) +static int mpls_ifdown(struct net_device *dev, int event) { struct mpls_route __rcu **platform_label; struct net *net = dev_net(dev); - u8 alive, deleted; unsigned index; platform_label = rtnl_dereference(net->mpls.platform_label); for (index = 0; index < net->mpls.platform_labels; index++) { struct mpls_route *rt = rtnl_dereference(platform_label[index]); + bool nh_del = false; + u8 alive = 0; if (!rt) continue; - alive = 0; - deleted = 0; + if (event == NETDEV_UNREGISTER) { + u8 deleted = 0; + + for_nexthops(rt) { + if (!nh->nh_dev || nh->nh_dev == dev) + deleted++; + if (nh->nh_dev == dev) + nh_del = true; + } endfor_nexthops(rt); + + /* if there are no more nexthops, delete the route */ + if (deleted == rt->rt_nhn) { + mpls_route_update(net, index, NULL, NULL); + continue; + } + + if (nh_del) { + size_t size = sizeof(*rt) + rt->rt_nhn * + rt->rt_nh_size; + struct mpls_route *orig = rt; + + rt = kmalloc(size, GFP_KERNEL); + if (!rt) + return -ENOMEM; + memcpy(rt, orig, size); + } + } + change_nexthops(rt) { unsigned int nh_flags = nh->nh_flags; - if (rtnl_dereference(nh->nh_dev) != dev) + if (nh->nh_dev != dev) goto next; switch (event) { @@ -1523,23 +1550,22 @@ static void mpls_ifdown(struct net_device *dev, int event) break; } if (event == NETDEV_UNREGISTER) - RCU_INIT_POINTER(nh->nh_dev, NULL); + nh->nh_dev = NULL; if (nh->nh_flags != nh_flags) WRITE_ONCE(nh->nh_flags, nh_flags); next: if (!(nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))) alive++; - if (!rtnl_dereference(nh->nh_dev)) - deleted++; } endfor_nexthops(rt); WRITE_ONCE(rt->rt_nhn_alive, alive); - /* if there are no more nexthops, delete the route */ - if (event == NETDEV_UNREGISTER && deleted == rt->rt_nhn) - mpls_route_update(net, index, NULL, NULL); + if (nh_del) + mpls_route_update(net, index, rt, NULL); } + + return 0; } static void mpls_ifup(struct net_device *dev, unsigned int flags) @@ -1559,14 +1585,12 @@ static void mpls_ifup(struct net_device *dev, unsigned int flags) alive = 0; change_nexthops(rt) { unsigned int nh_flags = nh->nh_flags; - struct net_device *nh_dev = - rtnl_dereference(nh->nh_dev); if (!(nh_flags & flags)) { alive++; continue; } - if (nh_dev != dev) + if (nh->nh_dev != dev) continue; alive++; nh_flags &= ~flags; @@ -1597,8 +1621,12 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, return NOTIFY_OK; switch (event) { + int err; + case NETDEV_DOWN: - mpls_ifdown(dev, event); + err = mpls_ifdown(dev, event); + if (err) + return notifier_from_errno(err); break; case NETDEV_UP: flags = dev_get_flags(dev); @@ -1609,13 +1637,18 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, break; case NETDEV_CHANGE: flags = dev_get_flags(dev); - if (flags & (IFF_RUNNING | IFF_LOWER_UP)) + if (flags & (IFF_RUNNING | IFF_LOWER_UP)) { mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); - else - mpls_ifdown(dev, event); + } else { + err = mpls_ifdown(dev, event); + if (err) + return notifier_from_errno(err); + } break; case NETDEV_UNREGISTER: - mpls_ifdown(dev, event); + err = mpls_ifdown(dev, event); + if (err) + return notifier_from_errno(err); mdev = mpls_dev_get(dev); if (mdev) { mpls_dev_sysctl_unregister(dev, mdev); @@ -1626,8 +1659,6 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, case NETDEV_CHANGENAME: mdev = mpls_dev_get(dev); if (mdev) { - int err; - mpls_dev_sysctl_unregister(dev, mdev); err = mpls_dev_sysctl_register(dev, mdev); if (err) @@ -1994,7 +2025,7 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), nh->nh_via_alen)) goto nla_put_failure; - dev = rtnl_dereference(nh->nh_dev); + dev = nh->nh_dev; if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex)) goto nla_put_failure; if (nh->nh_flags & RTNH_F_LINKDOWN) @@ -2012,7 +2043,7 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, goto nla_put_failure; for_nexthops(rt) { - dev = rtnl_dereference(nh->nh_dev); + dev = nh->nh_dev; if (!dev) continue; @@ -2123,18 +2154,14 @@ static int mpls_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, static bool mpls_rt_uses_dev(struct mpls_route *rt, const struct net_device *dev) { - struct net_device *nh_dev; - if (rt->rt_nhn == 1) { struct mpls_nh *nh = rt->rt_nh; - nh_dev = rtnl_dereference(nh->nh_dev); - if (dev == nh_dev) + if (nh->nh_dev == dev) return true; } else { for_nexthops(rt) { - nh_dev = rtnl_dereference(nh->nh_dev); - if (nh_dev == dev) + if (nh->nh_dev == dev) return true; } endfor_nexthops(rt); } @@ -2222,7 +2249,7 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt) size_t nhsize = 0; for_nexthops(rt) { - if (!rtnl_dereference(nh->nh_dev)) + if (!nh->nh_dev) continue; nhsize += nla_total_size(sizeof(struct rtnexthop)); /* RTA_VIA */ @@ -2468,7 +2495,7 @@ static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), nh->nh_via_alen)) goto nla_put_failure; - dev = rtnl_dereference(nh->nh_dev); + dev = nh->nh_dev; if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex)) goto nla_put_failure; @@ -2507,7 +2534,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) rt0 = mpls_rt_alloc(1, lo->addr_len, 0); if (IS_ERR(rt0)) goto nort0; - RCU_INIT_POINTER(rt0->rt_nh->nh_dev, lo); + rt0->rt_nh->nh_dev = lo; rt0->rt_protocol = RTPROT_KERNEL; rt0->rt_payload_type = MPT_IPV4; rt0->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; @@ -2521,7 +2548,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) rt2 = mpls_rt_alloc(1, lo->addr_len, 0); if (IS_ERR(rt2)) goto nort2; - RCU_INIT_POINTER(rt2->rt_nh->nh_dev, lo); + rt2->rt_nh->nh_dev = lo; rt2->rt_protocol = RTPROT_KERNEL; rt2->rt_payload_type = MPT_IPV6; rt2->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; diff --git a/net/mpls/internal.h b/net/mpls/internal.h index 838cdfc10e47..893df00b77b6 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -87,7 +87,7 @@ enum mpls_payload_type { }; struct mpls_nh { /* next hop label forwarding entry */ - struct net_device __rcu *nh_dev; + struct net_device *nh_dev; /* nh_flags is accessed under RCU in the packet path; it is * modified handling netdev events with rtnl lock held diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 7c3420afb1a0..fe98e4f475ba 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -422,28 +422,6 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, return false; } -/* MP_JOIN client subflow must wait for 4th ack before sending any data: - * TCP can't schedule delack timer before the subflow is fully established. - * MPTCP uses the delack timer to do 3rd ack retransmissions - */ -static void schedule_3rdack_retransmission(struct sock *sk) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_sock *tp = tcp_sk(sk); - unsigned long timeout; - - /* reschedule with a timeout above RTT, as we must look only for drop */ - if (tp->srtt_us) - timeout = tp->srtt_us << 1; - else - timeout = TCP_TIMEOUT_INIT; - - WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER); - icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; - icsk->icsk_ack.timeout = timeout; - sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout); -} - static void clear_3rdack_retransmission(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -526,7 +504,15 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, *size = TCPOLEN_MPTCP_MPJ_ACK; pr_debug("subflow=%p", subflow); - schedule_3rdack_retransmission(sk); + /* we can use the full delegate action helper only from BH context + * If we are in process context - sk is flushing the backlog at + * socket lock release time - just set the appropriate flag, will + * be handled by the release callback + */ + if (sock_owned_by_user(sk)) + set_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status); + else + mptcp_subflow_delegate(subflow, MPTCP_DELEGATE_ACK); return true; } return false; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b7e32e316738..c82a76d2d0bf 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1596,7 +1596,8 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk) if (!xmit_ssk) goto out; if (xmit_ssk != ssk) { - mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk)); + mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk), + MPTCP_DELEGATE_SEND); goto out; } @@ -2943,7 +2944,7 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk) if (xmit_ssk == ssk) __mptcp_subflow_push_pending(sk, ssk); else if (xmit_ssk) - mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk)); + mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk), MPTCP_DELEGATE_SEND); } else { set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags); } @@ -2993,18 +2994,50 @@ static void mptcp_release_cb(struct sock *sk) __mptcp_update_rmem(sk); } +/* MP_JOIN client subflow must wait for 4th ack before sending any data: + * TCP can't schedule delack timer before the subflow is fully established. + * MPTCP uses the delack timer to do 3rd ack retransmissions + */ +static void schedule_3rdack_retransmission(struct sock *ssk) +{ + struct inet_connection_sock *icsk = inet_csk(ssk); + struct tcp_sock *tp = tcp_sk(ssk); + unsigned long timeout; + + if (mptcp_subflow_ctx(ssk)->fully_established) + return; + + /* reschedule with a timeout above RTT, as we must look only for drop */ + if (tp->srtt_us) + timeout = usecs_to_jiffies(tp->srtt_us >> (3 - 1)); + else + timeout = TCP_TIMEOUT_INIT; + timeout += jiffies; + + WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER); + icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; + icsk->icsk_ack.timeout = timeout; + sk_reset_timer(ssk, &icsk->icsk_delack_timer, timeout); +} + void mptcp_subflow_process_delegated(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = subflow->conn; - mptcp_data_lock(sk); - if (!sock_owned_by_user(sk)) - __mptcp_subflow_push_pending(sk, ssk); - else - set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags); - mptcp_data_unlock(sk); - mptcp_subflow_delegated_done(subflow); + if (test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) { + mptcp_data_lock(sk); + if (!sock_owned_by_user(sk)) + __mptcp_subflow_push_pending(sk, ssk); + else + set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags); + mptcp_data_unlock(sk); + mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_SEND); + } + if (test_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status)) { + schedule_3rdack_retransmission(ssk); + mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_ACK); + } } static int mptcp_hash(struct sock *sk) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 67a61ac48b20..d87cc040352e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -387,6 +387,7 @@ struct mptcp_delegated_action { DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); #define MPTCP_DELEGATE_SEND 0 +#define MPTCP_DELEGATE_ACK 1 /* MPTCP subflow context */ struct mptcp_subflow_context { @@ -492,23 +493,23 @@ static inline void mptcp_add_pending_subflow(struct mptcp_sock *msk, void mptcp_subflow_process_delegated(struct sock *ssk); -static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow) +static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow, int action) { struct mptcp_delegated_action *delegated; bool schedule; + /* the caller held the subflow bh socket lock */ + lockdep_assert_in_softirq(); + /* The implied barrier pairs with mptcp_subflow_delegated_done(), and * ensures the below list check sees list updates done prior to status * bit changes */ - if (!test_and_set_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) { + if (!test_and_set_bit(action, &subflow->delegated_status)) { /* still on delegated list from previous scheduling */ if (!list_empty(&subflow->delegated_node)) return; - /* the caller held the subflow bh socket lock */ - lockdep_assert_in_softirq(); - delegated = this_cpu_ptr(&mptcp_delegated_actions); schedule = list_empty(&delegated->head); list_add_tail(&subflow->delegated_node, &delegated->head); @@ -533,16 +534,16 @@ mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated) static inline bool mptcp_subflow_has_delegated_action(const struct mptcp_subflow_context *subflow) { - return test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status); + return !!READ_ONCE(subflow->delegated_status); } -static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow) +static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow, int action) { /* pairs with mptcp_subflow_delegate, ensures delegate_node is updated before * touching the status bit */ smp_wmb(); - clear_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status); + clear_bit(action, &subflow->delegated_status); } int mptcp_is_enabled(const struct net *net); diff --git a/net/ncsi/ncsi-cmd.c b/net/ncsi/ncsi-cmd.c index ba9ae482141b..dda8b76b7798 100644 --- a/net/ncsi/ncsi-cmd.c +++ b/net/ncsi/ncsi-cmd.c @@ -18,6 +18,8 @@ #include "internal.h" #include "ncsi-pkt.h" +static const int padding_bytes = 26; + u32 ncsi_calculate_checksum(unsigned char *data, int len) { u32 checksum = 0; @@ -213,12 +215,17 @@ static int ncsi_cmd_handler_oem(struct sk_buff *skb, { struct ncsi_cmd_oem_pkt *cmd; unsigned int len; + int payload; + /* NC-SI spec DSP_0222_1.2.0, section 8.2.2.2 + * requires payload to be padded with 0 to + * 32-bit boundary before the checksum field. + * Ensure the padding bytes are accounted for in + * skb allocation + */ + payload = ALIGN(nca->payload, 4); len = sizeof(struct ncsi_cmd_pkt_hdr) + 4; - if (nca->payload < 26) - len += 26; - else - len += nca->payload; + len += max(payload, padding_bytes); cmd = skb_put_zero(skb, len); memcpy(&cmd->mfr_id, nca->data, nca->payload); @@ -272,6 +279,7 @@ static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca) struct net_device *dev = nd->dev; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; + int payload; int len = hlen + tlen; struct sk_buff *skb; struct ncsi_request *nr; @@ -281,14 +289,14 @@ static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca) return NULL; /* NCSI command packet has 16-bytes header, payload, 4 bytes checksum. + * Payload needs padding so that the checksum field following payload is + * aligned to 32-bit boundary. * The packet needs padding if its payload is less than 26 bytes to * meet 64 bytes minimal ethernet frame length. */ len += sizeof(struct ncsi_cmd_pkt_hdr) + 4; - if (nca->payload < 26) - len += 26; - else - len += nca->payload; + payload = ALIGN(nca->payload, 4); + len += max(payload, padding_bytes); /* Allocate skb */ skb = alloc_skb(len, GFP_ATOMIC); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index e93c937a8bf0..51ad557a525b 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1919,7 +1919,6 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; int ret, pkts; - int conn_reuse_mode; struct sock *sk; int af = state->pf; @@ -1997,15 +1996,16 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, af, skb, &iph); - conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); - if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) { + if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) { + int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); bool old_ct = false, resched = false; if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && unlikely(!atomic_read(&cp->dest->weight))) { resched = true; old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); - } else if (is_new_conn_expected(cp, conn_reuse_mode)) { + } else if (conn_reuse_mode && + is_new_conn_expected(cp, conn_reuse_mode)) { old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!atomic_read(&cp->n_control)) { resched = true; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 770a63103c7a..4712a90a1820 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -684,7 +684,7 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report) tstamp = nf_conn_tstamp_find(ct); if (tstamp) { - s32 timeout = ct->timeout - nfct_time_stamp; + s32 timeout = READ_ONCE(ct->timeout) - nfct_time_stamp; tstamp->stop = ktime_get_real_ns(); if (timeout < 0) @@ -1036,7 +1036,7 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx) } /* We want the clashing entry to go away real soon: 1 second timeout. */ - loser_ct->timeout = nfct_time_stamp + HZ; + WRITE_ONCE(loser_ct->timeout, nfct_time_stamp + HZ); /* IPS_NAT_CLASH removes the entry automatically on the first * reply. Also prevents UDP tracker from moving the entry to @@ -1560,7 +1560,7 @@ __nf_conntrack_alloc(struct net *net, /* save hash for reusing when confirming */ *(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash; ct->status = 0; - ct->timeout = 0; + WRITE_ONCE(ct->timeout, 0); write_pnet(&ct->ct_net, net); memset(&ct->__nfct_init_offset, 0, offsetof(struct nf_conn, proto) - diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index f1e5443fe7c7..81d03acf68d4 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1011,11 +1011,9 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) CTA_TUPLE_REPLY, filter->family, &filter->zone, - filter->orig_flags); - if (err < 0) { - err = -EINVAL; + filter->reply_flags); + if (err < 0) goto err_filter; - } } return filter; @@ -2000,7 +1998,7 @@ static int ctnetlink_change_timeout(struct nf_conn *ct, if (timeout > INT_MAX) timeout = INT_MAX; - ct->timeout = nfct_time_stamp + (u32)timeout; + WRITE_ONCE(ct->timeout, nfct_time_stamp + (u32)timeout); if (test_bit(IPS_DYING_BIT, &ct->status)) return -ETIME; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 87a7388b6c89..ed37bb9b4e58 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -201,8 +201,8 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) if (timeout < 0) timeout = 0; - if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout) - ct->timeout = nfct_time_stamp + timeout; + if (nf_flow_timeout_delta(READ_ONCE(ct->timeout)) > (__s32)timeout) + WRITE_ONCE(ct->timeout, nfct_time_stamp + timeout); } static void flow_offload_fixup_ct_state(struct nf_conn *ct) diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index d6bf1b2cd541..b561e0a44a45 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -65,11 +65,11 @@ static void nf_flow_rule_lwt_match(struct nf_flow_match *match, sizeof(struct in6_addr)); if (memcmp(&key->enc_ipv6.src, &in6addr_any, sizeof(struct in6_addr))) - memset(&key->enc_ipv6.src, 0xff, + memset(&mask->enc_ipv6.src, 0xff, sizeof(struct in6_addr)); if (memcmp(&key->enc_ipv6.dst, &in6addr_any, sizeof(struct in6_addr))) - memset(&key->enc_ipv6.dst, 0xff, + memset(&mask->enc_ipv6.dst, 0xff, sizeof(struct in6_addr)); enc_keys |= BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS); key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 4acc4b8e9fe5..5837e8efc9c2 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -387,7 +387,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct net_device *indev; struct net_device *outdev; struct nf_conn *ct = NULL; - enum ip_conntrack_info ctinfo; + enum ip_conntrack_info ctinfo = 0; struct nfnl_ct_hook *nfnl_ct; bool csum_verify; char *secdata = NULL; diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index af4ee874a067..dbe1f2e7dd9e 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -236,7 +236,7 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, &tcphdr_len); if (!tcph) - return; + goto err; opt = (u8 *)tcph; for (i = sizeof(*tcph); i < tcphdr_len - 1; i += optl) { @@ -251,16 +251,16 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, continue; if (i + optl > tcphdr_len || priv->len + priv->offset > optl) - return; + goto err; if (skb_ensure_writable(pkt->skb, nft_thoff(pkt) + i + priv->len)) - return; + goto err; tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, &tcphdr_len); if (!tcph) - return; + goto err; offset = i + priv->offset; @@ -303,6 +303,9 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, return; } + return; +err: + regs->verdict.code = NFT_BREAK; } static void nft_exthdr_sctp_eval(const struct nft_expr *expr, diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index cbfe4e4a4ad7..bd689938a2e0 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -22,7 +22,6 @@ #include <linux/icmpv6.h> #include <linux/ip.h> #include <linux/ipv6.h> -#include <linux/ip.h> #include <net/sctp/checksum.h> static bool nft_payload_rebuild_vlan_hdr(const struct sk_buff *skb, int mac_off, diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index e517663e0cd1..6f4116e72958 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -886,7 +886,7 @@ static int nft_pipapo_avx2_lookup_8b_6(unsigned long *map, unsigned long *fill, NFT_PIPAPO_AVX2_BUCKET_LOAD8(4, lt, 4, pkt[4], bsize); NFT_PIPAPO_AVX2_AND(5, 0, 1); - NFT_PIPAPO_AVX2_BUCKET_LOAD8(6, lt, 6, pkt[5], bsize); + NFT_PIPAPO_AVX2_BUCKET_LOAD8(6, lt, 5, pkt[5], bsize); NFT_PIPAPO_AVX2_AND(7, 2, 3); /* Stall */ diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 2f7cf5ecebf4..0f8bb0bf558f 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -85,9 +85,9 @@ static ssize_t idletimer_tg_show(struct device *dev, mutex_unlock(&list_mutex); if (time_after(expires, jiffies) || ktimespec.tv_sec > 0) - return snprintf(buf, PAGE_SIZE, "%ld\n", time_diff); + return sysfs_emit(buf, "%ld\n", time_diff); - return snprintf(buf, PAGE_SIZE, "0\n"); + return sysfs_emit(buf, "0\n"); } static void idletimer_tg_work(struct work_struct *work) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 4c575324a985..9eba2e648385 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1852,6 +1852,11 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; + if (len == 0) { + pr_warn_once("Zero length message leads to an empty skb\n"); + return -ENODATA; + } + err = scm_send(sock, msg, &scm, true); if (err < 0) return err; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 334f63c9529e..f184b0db79d4 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -636,8 +636,10 @@ static int nfc_genl_dump_devices_done(struct netlink_callback *cb) { struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0]; - nfc_device_iter_exit(iter); - kfree(iter); + if (iter) { + nfc_device_iter_exit(iter); + kfree(iter); + } return 0; } @@ -1392,8 +1394,10 @@ static int nfc_genl_dump_ses_done(struct netlink_callback *cb) { struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0]; - nfc_device_iter_exit(iter); - kfree(iter); + if (iter) { + nfc_device_iter_exit(iter); + kfree(iter); + } return 0; } diff --git a/net/rds/tcp.c b/net/rds/tcp.c index abf19c0e3ba0..5327d130c4b5 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -500,7 +500,7 @@ void rds_tcp_tune(struct socket *sock) sk->sk_userlocks |= SOCK_SNDBUF_LOCK; } if (rtn->rcvbuf_size > 0) { - sk->sk_sndbuf = rtn->rcvbuf_size; + sk->sk_rcvbuf = rtn->rcvbuf_size; sk->sk_userlocks |= SOCK_RCVBUF_LOCK; } release_sock(sk); diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index dbea0bfee48e..8120138dac01 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -135,16 +135,20 @@ struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle) return bundle; } +static void rxrpc_free_bundle(struct rxrpc_bundle *bundle) +{ + rxrpc_put_peer(bundle->params.peer); + kfree(bundle); +} + void rxrpc_put_bundle(struct rxrpc_bundle *bundle) { unsigned int d = bundle->debug_id; unsigned int u = atomic_dec_return(&bundle->usage); _debug("PUT B=%x %u", d, u); - if (u == 0) { - rxrpc_put_peer(bundle->params.peer); - kfree(bundle); - } + if (u == 0) + rxrpc_free_bundle(bundle); } /* @@ -328,7 +332,7 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c return candidate; found_bundle_free: - kfree(candidate); + rxrpc_free_bundle(candidate); found_bundle: rxrpc_get_bundle(bundle); spin_unlock(&local->client_bundles_lock); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 68396d052052..0298fe2ad6d3 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -299,6 +299,12 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx, return peer; } +static void rxrpc_free_peer(struct rxrpc_peer *peer) +{ + rxrpc_put_local(peer->local); + kfree_rcu(peer, rcu); +} + /* * Set up a new incoming peer. There shouldn't be any other matching peers * since we've already done a search in the list from the non-reentrant context @@ -365,7 +371,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, spin_unlock_bh(&rxnet->peer_hash_lock); if (peer) - kfree(candidate); + rxrpc_free_peer(candidate); else peer = candidate; } @@ -420,8 +426,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) list_del_init(&peer->keepalive_link); spin_unlock_bh(&rxnet->peer_hash_lock); - rxrpc_put_local(peer->local); - kfree_rcu(peer, rcu); + rxrpc_free_peer(peer); } /* @@ -457,8 +462,7 @@ void rxrpc_put_peer_locked(struct rxrpc_peer *peer) if (n == 0) { hash_del_rcu(&peer->hash_link); list_del_init(&peer->keepalive_link); - rxrpc_put_local(peer->local); - kfree_rcu(peer, rcu); + rxrpc_free_peer(peer); } } diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 0eae9ff5edf6..e007fc75ef2f 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -665,12 +665,14 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, q->classes[i].deficit = quanta[i]; } } + for (i = q->nbands; i < oldbands; i++) { + qdisc_tree_flush_backlog(q->classes[i].qdisc); + if (i >= q->nstrict) + list_del(&q->classes[i].alist); + } q->nstrict = nstrict; memcpy(q->prio2band, priomap, sizeof(priomap)); - for (i = q->nbands; i < oldbands; i++) - qdisc_tree_flush_backlog(q->classes[i].qdisc); - for (i = 0; i < q->nbands; i++) q->classes[i].quantum = quanta[i]; diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 830f3559f727..d6aba6edd16e 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -531,6 +531,7 @@ static void fq_pie_destroy(struct Qdisc *sch) struct fq_pie_sched_data *q = qdisc_priv(sch); tcf_block_put(q->block); + q->p_params.tupdate = 0; del_timer_sync(&q->adapt_timer); kvfree(q->flows); } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index b61c802e3bf3..230072f9ec48 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -585,7 +585,7 @@ static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code) * to clcsocket->wq during the fallback. */ spin_lock_irqsave(&smc_wait->lock, flags); - spin_lock(&clc_wait->lock); + spin_lock_nested(&clc_wait->lock, SINGLE_DEPTH_NESTING); list_splice_init(&smc_wait->head, &clc_wait->head); spin_unlock(&clc_wait->lock); spin_unlock_irqrestore(&smc_wait->lock, flags); @@ -2134,8 +2134,10 @@ static int smc_listen(struct socket *sock, int backlog) smc->clcsock->sk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); rc = kernel_listen(smc->clcsock, backlog); - if (rc) + if (rc) { + smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; goto out; + } sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; sk->sk_state = SMC_LISTEN; @@ -2368,8 +2370,10 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, static int smc_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; + bool do_shutdown = true; struct smc_sock *smc; int rc = -EINVAL; + int old_state; int rc1 = 0; smc = smc_sk(sk); @@ -2396,7 +2400,11 @@ static int smc_shutdown(struct socket *sock, int how) } switch (how) { case SHUT_RDWR: /* shutdown in both directions */ + old_state = sk->sk_state; rc = smc_close_active(smc); + if (old_state == SMC_ACTIVE && + sk->sk_state == SMC_PEERCLOSEWAIT1) + do_shutdown = false; break; case SHUT_WR: rc = smc_close_shutdown_write(smc); @@ -2406,7 +2414,7 @@ static int smc_shutdown(struct socket *sock, int how) /* nothing more to do because peer is not involved */ break; } - if (smc->clcsock) + if (do_shutdown && smc->clcsock) rc1 = kernel_sock_shutdown(smc->clcsock, how); /* map sock_shutdown_cmd constants to sk_shutdown value range */ sk->sk_shutdown |= how + 1; diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 0f9ffba07d26..292e4d904ab6 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -195,6 +195,7 @@ int smc_close_active(struct smc_sock *smc) int old_state; long timeout; int rc = 0; + int rc1 = 0; timeout = current->flags & PF_EXITING ? 0 : sock_flag(sk, SOCK_LINGER) ? @@ -228,6 +229,15 @@ again: /* send close request */ rc = smc_close_final(conn); sk->sk_state = SMC_PEERCLOSEWAIT1; + + /* actively shutdown clcsock before peer close it, + * prevent peer from entering TIME_WAIT state. + */ + if (smc->clcsock && smc->clcsock->sk) { + rc1 = kernel_sock_shutdown(smc->clcsock, + SHUT_RDWR); + rc = rc ? rc : rc1; + } } else { /* peer event has changed the state */ goto again; @@ -354,9 +364,9 @@ static void smc_close_passive_work(struct work_struct *work) if (rxflags->peer_conn_abort) { /* peer has not received all data */ smc_close_passive_abort_received(smc); - release_sock(&smc->sk); + release_sock(sk); cancel_delayed_work_sync(&conn->tx_work); - lock_sock(&smc->sk); + lock_sock(sk); goto wakeup; } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 25ebd30feecd..387d28b2f8dd 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -625,18 +625,17 @@ int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb) void smc_lgr_cleanup_early(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; - struct list_head *lgr_list; spinlock_t *lgr_lock; if (!lgr) return; smc_conn_free(conn); - lgr_list = smc_lgr_list_head(lgr, &lgr_lock); + smc_lgr_list_head(lgr, &lgr_lock); spin_lock_bh(lgr_lock); /* do not use this link group for new connections */ - if (!list_empty(lgr_list)) - list_del_init(lgr_list); + if (!list_empty(&lgr->list)) + list_del_init(&lgr->list); spin_unlock_bh(lgr_lock); __smc_lgr_terminate(lgr, true); } @@ -1672,14 +1671,26 @@ static void smc_link_down_work(struct work_struct *work) mutex_unlock(&lgr->llc_conf_mutex); } -/* Determine vlan of internal TCP socket. - * @vlan_id: address to store the determined vlan id into - */ +static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev, + struct netdev_nested_priv *priv) +{ + unsigned short *vlan_id = (unsigned short *)priv->data; + + if (is_vlan_dev(lower_dev)) { + *vlan_id = vlan_dev_vlan_id(lower_dev); + return 1; + } + + return 0; +} + +/* Determine vlan of internal TCP socket. */ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(clcsock->sk); + struct netdev_nested_priv priv; struct net_device *ndev; - int i, nest_lvl, rc = 0; + int rc = 0; ini->vlan_id = 0; if (!dst) { @@ -1697,20 +1708,9 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini) goto out_rel; } + priv.data = (void *)&ini->vlan_id; rtnl_lock(); - nest_lvl = ndev->lower_level; - for (i = 0; i < nest_lvl; i++) { - struct list_head *lower = &ndev->adj_list.lower; - - if (list_empty(lower)) - break; - lower = lower->next; - ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower); - if (is_vlan_dev(ndev)) { - ini->vlan_id = vlan_dev_vlan_id(ndev); - break; - } - } + netdev_walk_all_lower_dev(ndev, smc_vlan_by_tcpsk_walk, &priv); rtnl_unlock(); out_rel: diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ae48c9c84ee1..d8ee06a9650a 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1720,15 +1720,15 @@ static void xs_local_set_port(struct rpc_xprt *xprt, unsigned short port) } #ifdef CONFIG_DEBUG_LOCK_ALLOC -static struct lock_class_key xs_key[2]; -static struct lock_class_key xs_slock_key[2]; +static struct lock_class_key xs_key[3]; +static struct lock_class_key xs_slock_key[3]; static inline void xs_reclassify_socketu(struct socket *sock) { struct sock *sk = sock->sk; sock_lock_init_class_and_name(sk, "slock-AF_LOCAL-RPC", - &xs_slock_key[1], "sk_lock-AF_LOCAL-RPC", &xs_key[1]); + &xs_slock_key[0], "sk_lock-AF_LOCAL-RPC", &xs_key[0]); } static inline void xs_reclassify_socket4(struct socket *sock) @@ -1736,7 +1736,7 @@ static inline void xs_reclassify_socket4(struct socket *sock) struct sock *sk = sock->sk; sock_lock_init_class_and_name(sk, "slock-AF_INET-RPC", - &xs_slock_key[0], "sk_lock-AF_INET-RPC", &xs_key[0]); + &xs_slock_key[1], "sk_lock-AF_INET-RPC", &xs_key[1]); } static inline void xs_reclassify_socket6(struct socket *sock) @@ -1744,7 +1744,7 @@ static inline void xs_reclassify_socket6(struct socket *sock) struct sock *sk = sock->sk; sock_lock_init_class_and_name(sk, "slock-AF_INET6-RPC", - &xs_slock_key[1], "sk_lock-AF_INET6-RPC", &xs_key[1]); + &xs_slock_key[2], "sk_lock-AF_INET6-RPC", &xs_key[2]); } static inline void xs_reclassify_socket(int family, struct socket *sock) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index acfba9f1ba72..6bc2879ba637 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -61,7 +61,7 @@ static DEFINE_MUTEX(tcpv6_prot_mutex); static const struct proto *saved_tcpv4_prot; static DEFINE_MUTEX(tcpv4_prot_mutex); static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; -static struct proto_ops tls_sw_proto_ops; +static struct proto_ops tls_proto_ops[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], const struct proto *base); @@ -71,6 +71,8 @@ void update_sk_prot(struct sock *sk, struct tls_context *ctx) WRITE_ONCE(sk->sk_prot, &tls_prots[ip_ver][ctx->tx_conf][ctx->rx_conf]); + WRITE_ONCE(sk->sk_socket->ops, + &tls_proto_ops[ip_ver][ctx->tx_conf][ctx->rx_conf]); } int wait_on_pending_writer(struct sock *sk, long *timeo) @@ -669,8 +671,6 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, if (tx) { ctx->sk_write_space = sk->sk_write_space; sk->sk_write_space = tls_write_space; - } else { - sk->sk_socket->ops = &tls_sw_proto_ops; } goto out; @@ -728,6 +728,39 @@ struct tls_context *tls_ctx_create(struct sock *sk) return ctx; } +static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG], + const struct proto_ops *base) +{ + ops[TLS_BASE][TLS_BASE] = *base; + + ops[TLS_SW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; + ops[TLS_SW ][TLS_BASE].sendpage_locked = tls_sw_sendpage_locked; + + ops[TLS_BASE][TLS_SW ] = ops[TLS_BASE][TLS_BASE]; + ops[TLS_BASE][TLS_SW ].splice_read = tls_sw_splice_read; + + ops[TLS_SW ][TLS_SW ] = ops[TLS_SW ][TLS_BASE]; + ops[TLS_SW ][TLS_SW ].splice_read = tls_sw_splice_read; + +#ifdef CONFIG_TLS_DEVICE + ops[TLS_HW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; + ops[TLS_HW ][TLS_BASE].sendpage_locked = NULL; + + ops[TLS_HW ][TLS_SW ] = ops[TLS_BASE][TLS_SW ]; + ops[TLS_HW ][TLS_SW ].sendpage_locked = NULL; + + ops[TLS_BASE][TLS_HW ] = ops[TLS_BASE][TLS_SW ]; + + ops[TLS_SW ][TLS_HW ] = ops[TLS_SW ][TLS_SW ]; + + ops[TLS_HW ][TLS_HW ] = ops[TLS_HW ][TLS_SW ]; + ops[TLS_HW ][TLS_HW ].sendpage_locked = NULL; +#endif +#ifdef CONFIG_TLS_TOE + ops[TLS_HW_RECORD][TLS_HW_RECORD] = *base; +#endif +} + static void tls_build_proto(struct sock *sk) { int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; @@ -739,6 +772,8 @@ static void tls_build_proto(struct sock *sk) mutex_lock(&tcpv6_prot_mutex); if (likely(prot != saved_tcpv6_prot)) { build_protos(tls_prots[TLSV6], prot); + build_proto_ops(tls_proto_ops[TLSV6], + sk->sk_socket->ops); smp_store_release(&saved_tcpv6_prot, prot); } mutex_unlock(&tcpv6_prot_mutex); @@ -749,6 +784,8 @@ static void tls_build_proto(struct sock *sk) mutex_lock(&tcpv4_prot_mutex); if (likely(prot != saved_tcpv4_prot)) { build_protos(tls_prots[TLSV4], prot); + build_proto_ops(tls_proto_ops[TLSV4], + sk->sk_socket->ops); smp_store_release(&saved_tcpv4_prot, prot); } mutex_unlock(&tcpv4_prot_mutex); @@ -959,10 +996,6 @@ static int __init tls_register(void) if (err) return err; - tls_sw_proto_ops = inet_stream_ops; - tls_sw_proto_ops.splice_read = tls_sw_splice_read; - tls_sw_proto_ops.sendpage_locked = tls_sw_sendpage_locked; - tls_device_init(); tcp_register_ulp(&tcp_tls_ulp_ops); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index d81564078557..dfe623a4e72f 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -521,7 +521,7 @@ static int tls_do_encryption(struct sock *sk, memcpy(&rec->iv_data[iv_offset], tls_ctx->tx.iv, prot->iv_size + prot->salt_size); - xor_iv_with_seq(prot, rec->iv_data, tls_ctx->tx.rec_seq); + xor_iv_with_seq(prot, rec->iv_data + iv_offset, tls_ctx->tx.rec_seq); sge->offset += prot->prepend_size; sge->length -= prot->prepend_size; @@ -1499,7 +1499,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, else memcpy(iv + iv_offset, tls_ctx->rx.iv, prot->salt_size); - xor_iv_with_seq(prot, iv, tls_ctx->rx.rec_seq); + xor_iv_with_seq(prot, iv + iv_offset, tls_ctx->rx.rec_seq); /* Prepare AAD */ tls_make_aad(aad, rxm->full_len - prot->overhead_size + @@ -2005,6 +2005,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, struct sock *sk = sock->sk; struct sk_buff *skb; ssize_t copied = 0; + bool from_queue; int err = 0; long timeo; int chunk; @@ -2014,25 +2015,28 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, timeo = sock_rcvtimeo(sk, flags & SPLICE_F_NONBLOCK); - skb = tls_wait_data(sk, NULL, flags & SPLICE_F_NONBLOCK, timeo, &err); - if (!skb) - goto splice_read_end; - - if (!ctx->decrypted) { - err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false); - - /* splice does not support reading control messages */ - if (ctx->control != TLS_RECORD_TYPE_DATA) { - err = -EINVAL; + from_queue = !skb_queue_empty(&ctx->rx_list); + if (from_queue) { + skb = __skb_dequeue(&ctx->rx_list); + } else { + skb = tls_wait_data(sk, NULL, flags & SPLICE_F_NONBLOCK, timeo, + &err); + if (!skb) goto splice_read_end; - } + err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false); if (err < 0) { tls_err_abort(sk, -EBADMSG); goto splice_read_end; } - ctx->decrypted = 1; } + + /* splice does not support reading control messages */ + if (ctx->control != TLS_RECORD_TYPE_DATA) { + err = -EINVAL; + goto splice_read_end; + } + rxm = strp_msg(skb); chunk = min_t(unsigned int, rxm->full_len, len); @@ -2040,7 +2044,17 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, if (copied < 0) goto splice_read_end; - tls_sw_advance_skb(sk, skb, copied); + if (!from_queue) { + ctx->recv_pkt = NULL; + __strp_unpause(&ctx->strp); + } + if (chunk < rxm->full_len) { + __skb_queue_head(&ctx->rx_list, skb); + rxm->offset += len; + rxm->full_len -= len; + } else { + consume_skb(skb); + } splice_read_end: release_sock(sk); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 78e08e82c08c..b0bfc78e421c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2882,9 +2882,6 @@ static int unix_shutdown(struct socket *sock, int mode) unix_state_lock(sk); sk->sk_shutdown |= mode; - if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) && - mode == SHUTDOWN_MASK) - sk->sk_state = TCP_CLOSE; other = unix_peer(sk); if (other) sock_hold(other); |