diff options
Diffstat (limited to 'net')
32 files changed, 197 insertions, 192 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 9c9e763bfe0e..522288177bbd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4140,7 +4140,8 @@ EXPORT_SYMBOL(netdev_max_backlog); int netdev_tstamp_prequeue __read_mostly = 1; int netdev_budget __read_mostly = 300; -unsigned int __read_mostly netdev_budget_usecs = 2000; +/* Must be at least 2 jiffes to guarantee 1 jiffy timeout */ +unsigned int __read_mostly netdev_budget_usecs = 2 * USEC_PER_SEC / HZ; int weight_p __read_mostly = 64; /* old backlog weight */ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ @@ -8666,8 +8667,8 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, const struct net_device_ops *ops = dev->netdev_ops; enum bpf_netdev_command query; u32 prog_id, expected_id = 0; - struct bpf_prog *prog = NULL; bpf_op_t bpf_op, bpf_chk; + struct bpf_prog *prog; bool offload; int err; @@ -8733,6 +8734,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, } else { if (!prog_id) return 0; + prog = NULL; } err = dev_xdp_install(dev, bpf_op, extack, flags, prog); diff --git a/net/core/filter.c b/net/core/filter.c index 7628b947dbc3..7d6ceaa54d21 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5925,7 +5925,7 @@ BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) return -EOPNOTSUPP; if (unlikely(dev_net(skb->dev) != sock_net(sk))) return -ENETUNREACH; - if (unlikely(sk->sk_reuseport)) + if (unlikely(sk_fullsock(sk) && sk->sk_reuseport)) return -ESOCKTNOSUPPORT; if (sk_is_refcounted(sk) && unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index cf0215734ceb..4773ad6ec111 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -80,7 +80,7 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, struct net_device *netdev = to_net_dev(dev); struct net *net = dev_net(netdev); unsigned long new; - int ret = -EINVAL; + int ret; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; diff --git a/net/core/sock.c b/net/core/sock.c index ce1d8dce9b7a..90509c37d291 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1872,7 +1872,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) * as not suitable for copying when cloning. */ if (sk_user_data_is_nocopy(newsk)) - RCU_INIT_POINTER(newsk->sk_user_data, NULL); + newsk->sk_user_data = NULL; newsk->sk_err = 0; newsk->sk_err_soft = 0; diff --git a/net/dsa/port.c b/net/dsa/port.c index 231b2d494f1c..a58fdd362574 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -670,11 +670,16 @@ int dsa_port_link_register_of(struct dsa_port *dp) { struct dsa_switch *ds = dp->ds; struct device_node *phy_np; + int port = dp->index; if (!ds->ops->adjust_link) { phy_np = of_parse_phandle(dp->dn, "phy-handle", 0); - if (of_phy_is_fixed_link(dp->dn) || phy_np) + if (of_phy_is_fixed_link(dp->dn) || phy_np) { + if (ds->ops->phylink_mac_link_down) + ds->ops->phylink_mac_link_down(ds, port, + MLO_AN_FIXED, PHY_INTERFACE_MODE_NA); return dsa_port_phylink_register(dp); + } return 0; } diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 5465a395da04..1decb25f6764 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -69,10 +69,16 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, else multicast_spec = nla_get_u8(data[IFLA_HSR_MULTICAST_SPEC]); - if (!data[IFLA_HSR_VERSION]) + if (!data[IFLA_HSR_VERSION]) { hsr_version = 0; - else + } else { hsr_version = nla_get_u8(data[IFLA_HSR_VERSION]); + if (hsr_version > 1) { + NL_SET_ERR_MSG_MOD(extack, + "Only versions 0..1 are supported"); + return -EINVAL; + } + } return hsr_dev_finalize(dev, link, multicast_spec, hsr_version, extack); } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 30fa42f5997d..c0dd561aa190 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -614,12 +614,15 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, return NULL; } -static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa) +static int ip_mc_autojoin_config(struct net *net, bool join, + const struct in_ifaddr *ifa) { +#if defined(CONFIG_IP_MULTICAST) struct ip_mreqn mreq = { .imr_multiaddr.s_addr = ifa->ifa_address, .imr_ifindex = ifa->ifa_dev->dev->ifindex, }; + struct sock *sk = net->ipv4.mc_autojoin_sk; int ret; ASSERT_RTNL(); @@ -632,6 +635,9 @@ static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa) release_sock(sk); return ret; +#else + return -EOPNOTSUPP; +#endif } static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -675,7 +681,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, continue; if (ipv4_is_multicast(ifa->ifa_address)) - ip_mc_config(net->ipv4.mc_autojoin_sk, false, ifa); + ip_mc_autojoin_config(net, false, ifa); __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid); return 0; } @@ -940,8 +946,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, */ set_ifa_lifetime(ifa, valid_lft, prefered_lft); if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) { - int ret = ip_mc_config(net->ipv4.mc_autojoin_sk, - true, ifa); + int ret = ip_mc_autojoin_config(net, true, ifa); if (ret < 0) { inet_free_ifa(ifa); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 2688f3e82165..fc5000370030 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -229,6 +229,25 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type, return res; } +static bool icmpv6_rt_has_prefsrc(struct sock *sk, u8 type, + struct flowi6 *fl6) +{ + struct net *net = sock_net(sk); + struct dst_entry *dst; + bool res = false; + + dst = ip6_route_output(net, sk, fl6); + if (!dst->error) { + struct rt6_info *rt = (struct rt6_info *)dst; + struct in6_addr prefsrc; + + rt6_get_prefsrc(rt, &prefsrc); + res = !ipv6_addr_any(&prefsrc); + } + dst_release(dst); + return res; +} + /* * an inline helper for the "simple" if statement below * checks if parameter problem report is caused by an @@ -527,7 +546,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, saddr = force_saddr; if (saddr) { fl6.saddr = *saddr; - } else { + } else if (!icmpv6_rt_has_prefsrc(sk, type, &fl6)) { /* select a more meaningful saddr from input if */ struct net_device *in_netdev; diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 75421a472d25..4c7e0a27fa9c 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -434,7 +434,7 @@ static struct genl_family seg6_genl_family __ro_after_init = { int __init seg6_init(void) { - int err = -ENOMEM; + int err; err = genl_register_family(&seg6_genl_family); if (err) diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index f5a9bdc4980c..ebb381c3f1b9 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -920,51 +920,51 @@ static const struct genl_ops l2tp_nl_ops[] = { .cmd = L2TP_CMD_TUNNEL_CREATE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_tunnel_create, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_TUNNEL_DELETE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_tunnel_delete, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_TUNNEL_MODIFY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_tunnel_modify, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_TUNNEL_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_tunnel_get, .dumpit = l2tp_nl_cmd_tunnel_dump, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_SESSION_CREATE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_session_create, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_SESSION_DELETE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_session_delete, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_SESSION_MODIFY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_session_modify, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_SESSION_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_session_get, .dumpit = l2tp_nl_cmd_session_dump, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, }; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 8345926193de..0e9ad60fb2b3 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1069,7 +1069,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->hw.wiphy->signal_type = CFG80211_SIGNAL_TYPE_UNSPEC; if (hw->max_signal <= 0) { result = -EINVAL; - goto fail_wiphy_register; + goto fail_workqueue; } } @@ -1135,7 +1135,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) result = ieee80211_init_cipher_suites(local); if (result < 0) - goto fail_wiphy_register; + goto fail_workqueue; if (!local->ops->remain_on_channel) local->hw.wiphy->max_remain_on_channel_duration = 5000; @@ -1161,10 +1161,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CSA_COUNTERS_NUM; - result = wiphy_register(local->hw.wiphy); - if (result < 0) - goto fail_wiphy_register; - /* * We use the number of queues for feature tests (QoS, HT) internally * so restrict them appropriately. @@ -1217,9 +1213,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) goto fail_flows; rtnl_lock(); - result = ieee80211_init_rate_ctrl_alg(local, hw->rate_control_algorithm); + rtnl_unlock(); if (result < 0) { wiphy_debug(local->hw.wiphy, "Failed to initialize rate control algorithm\n"); @@ -1273,6 +1269,12 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->sband_allocated |= BIT(band); } + result = wiphy_register(local->hw.wiphy); + if (result < 0) + goto fail_wiphy_register; + + rtnl_lock(); + /* add one default STA interface if supported */ if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION) && !ieee80211_hw_check(hw, NO_AUTO_VIF)) { @@ -1312,17 +1314,17 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) #if defined(CONFIG_INET) || defined(CONFIG_IPV6) fail_ifa: #endif + wiphy_unregister(local->hw.wiphy); + fail_wiphy_register: rtnl_lock(); rate_control_deinitialize(local); ieee80211_remove_interfaces(local); - fail_rate: rtnl_unlock(); + fail_rate: fail_flows: ieee80211_led_exit(local); destroy_workqueue(local->workqueue); fail_workqueue: - wiphy_unregister(local->hw.wiphy); - fail_wiphy_register: if (local->wiphy_ciphers_allocated) kfree(local->hw.wiphy->cipher_suites); kfree(local->int_scan_req); @@ -1372,8 +1374,8 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) skb_queue_purge(&local->skb_queue_unreliable); skb_queue_purge(&local->skb_queue_tdls_chsw); - destroy_workqueue(local->workqueue); wiphy_unregister(local->hw.wiphy); + destroy_workqueue(local->workqueue); ieee80211_led_exit(local); kfree(local->int_scan_req); } diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index d09b3c789314..36978a0e5000 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1257,15 +1257,15 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, sdata->u.mesh.mshcfg.rssi_threshold < rx_status->signal) mesh_neighbour_update(sdata, mgmt->sa, &elems, rx_status); + + if (ifmsh->csa_role != IEEE80211_MESH_CSA_ROLE_INIT && + !sdata->vif.csa_active) + ieee80211_mesh_process_chnswitch(sdata, &elems, true); } if (ifmsh->sync_ops) ifmsh->sync_ops->rx_bcn_presp(sdata, stype, mgmt, &elems, rx_status); - - if (ifmsh->csa_role != IEEE80211_MESH_CSA_ROLE_INIT && - !sdata->vif.csa_active) - ieee80211_mesh_process_chnswitch(sdata, &elems, true); } int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata) @@ -1373,6 +1373,9 @@ static void mesh_rx_csa_frame(struct ieee80211_sub_if_data *sdata, ieee802_11_parse_elems(pos, len - baselen, true, &elems, mgmt->bssid, NULL); + if (!mesh_matches_local(sdata, &elems)) + return; + ifmsh->chsw_ttl = elems.mesh_chansw_params_ie->mesh_ttl; if (!--ifmsh->chsw_ttl) fwd_csa = false; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 939a5045181a..9936e33ac351 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -97,12 +97,7 @@ static struct socket *__mptcp_tcp_fallback(struct mptcp_sock *msk) if (likely(!__mptcp_needs_tcp_fallback(msk))) return NULL; - if (msk->subflow) { - release_sock((struct sock *)msk); - return msk->subflow; - } - - return NULL; + return msk->subflow; } static bool __mptcp_can_create_subflow(const struct mptcp_sock *msk) @@ -734,9 +729,10 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto out; } +fallback: ssock = __mptcp_tcp_fallback(msk); if (unlikely(ssock)) { -fallback: + release_sock(sk); pr_debug("fallback passthrough"); ret = sock_sendmsg(ssock, msg); return ret >= 0 ? ret + copied : (copied ? copied : ret); @@ -769,8 +765,14 @@ fallback: if (ret < 0) break; if (ret == 0 && unlikely(__mptcp_needs_tcp_fallback(msk))) { + /* Can happen for passive sockets: + * 3WHS negotiated MPTCP, but first packet after is + * plain TCP (e.g. due to middlebox filtering unknown + * options). + * + * Fall back to TCP. + */ release_sock(ssk); - ssock = __mptcp_tcp_fallback(msk); goto fallback; } @@ -883,6 +885,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, ssock = __mptcp_tcp_fallback(msk); if (unlikely(ssock)) { fallback: + release_sock(sk); pr_debug("fallback-read subflow=%p", mptcp_subflow_ctx(ssock->sk)); copied = sock_recvmsg(ssock, msg, flags); @@ -1467,12 +1470,11 @@ static int mptcp_setsockopt(struct sock *sk, int level, int optname, */ lock_sock(sk); ssock = __mptcp_tcp_fallback(msk); + release_sock(sk); if (ssock) return tcp_setsockopt(ssock->sk, level, optname, optval, optlen); - release_sock(sk); - return -EOPNOTSUPP; } @@ -1492,12 +1494,11 @@ static int mptcp_getsockopt(struct sock *sk, int level, int optname, */ lock_sock(sk); ssock = __mptcp_tcp_fallback(msk); + release_sock(sk); if (ssock) return tcp_getsockopt(ssock->sk, level, optname, optval, option); - release_sock(sk); - return -EOPNOTSUPP; } diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 8dd17589217d..340cb955af25 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -86,7 +86,8 @@ find_set_type(const char *name, u8 family, u8 revision) { struct ip_set_type *type; - list_for_each_entry_rcu(type, &ip_set_type_list, list) + list_for_each_entry_rcu(type, &ip_set_type_list, list, + lockdep_is_held(&ip_set_type_mutex)) if (STRNCMP(type->name, name) && (type->family == family || type->family == NFPROTO_UNSPEC) && diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4471393da6d8..9780bd93b7e4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3542,6 +3542,7 @@ cont: continue; if (!strcmp(set->name, i->name)) { kfree(set->name); + set->name = NULL; return -ENFILE; } } @@ -3961,8 +3962,8 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (flags & ~(NFT_SET_ANONYMOUS | NFT_SET_CONSTANT | NFT_SET_INTERVAL | NFT_SET_TIMEOUT | NFT_SET_MAP | NFT_SET_EVAL | - NFT_SET_OBJECT)) - return -EINVAL; + NFT_SET_OBJECT | NFT_SET_CONCAT)) + return -EOPNOTSUPP; /* Only one of these operations is supported */ if ((flags & (NFT_SET_MAP | NFT_SET_OBJECT)) == (NFT_SET_MAP | NFT_SET_OBJECT)) @@ -4000,7 +4001,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE])); if (objtype == NFT_OBJECT_UNSPEC || objtype > NFT_OBJECT_MAX) - return -EINVAL; + return -EOPNOTSUPP; } else if (flags & NFT_SET_OBJECT) return -EINVAL; else diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 1e70359d633c..f1363b8aabba 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -29,7 +29,7 @@ void nft_lookup_eval(const struct nft_expr *expr, { const struct nft_lookup *priv = nft_expr_priv(expr); const struct nft_set *set = priv->set; - const struct nft_set_ext *ext; + const struct nft_set_ext *ext = NULL; bool found; found = set->ops->lookup(nft_net(pkt), set, ®s->data[priv->sreg], @@ -39,11 +39,13 @@ void nft_lookup_eval(const struct nft_expr *expr, return; } - if (set->flags & NFT_SET_MAP) - nft_data_copy(®s->data[priv->dreg], - nft_set_ext_data(ext), set->dlen); + if (ext) { + if (set->flags & NFT_SET_MAP) + nft_data_copy(®s->data[priv->dreg], + nft_set_ext_data(ext), set->dlen); - nft_set_elem_update_expr(ext, regs, pkt); + nft_set_elem_update_expr(ext, regs, pkt); + } } static const struct nla_policy nft_lookup_policy[NFTA_LOOKUP_MAX + 1] = { diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 32f0fc8be3a4..2a81ea421819 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -81,7 +81,6 @@ static bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set, u32 idx, off; nft_bitmap_location(set, key, &idx, &off); - *ext = NULL; return nft_bitmap_active(priv->bitmap, idx, off, genmask); } diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 3a5552e14f75..3ffef454d469 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -218,27 +218,26 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, /* Detect overlaps as we descend the tree. Set the flag in these cases: * - * a1. |__ _ _? >|__ _ _ (insert start after existing start) - * a2. _ _ __>| ?_ _ __| (insert end before existing end) - * a3. _ _ ___| ?_ _ _>| (insert end after existing end) - * a4. >|__ _ _ _ _ __| (insert start before existing end) + * a1. _ _ __>| ?_ _ __| (insert end before existing end) + * a2. _ _ ___| ?_ _ _>| (insert end after existing end) + * a3. _ _ ___? >|_ _ __| (insert start before existing end) * * and clear it later on, as we eventually reach the points indicated by * '?' above, in the cases described below. We'll always meet these * later, locally, due to tree ordering, and overlaps for the intervals * that are the closest together are always evaluated last. * - * b1. |__ _ _! >|__ _ _ (insert start after existing end) - * b2. _ _ __>| !_ _ __| (insert end before existing start) - * b3. !_____>| (insert end after existing start) + * b1. _ _ __>| !_ _ __| (insert end before existing start) + * b2. _ _ ___| !_ _ _>| (insert end after existing start) + * b3. _ _ ___! >|_ _ __| (insert start after existing end) * - * Case a4. resolves to b1.: + * Case a3. resolves to b3.: * - if the inserted start element is the leftmost, because the '0' * element in the tree serves as end element * - otherwise, if an existing end is found. Note that end elements are * always inserted after corresponding start elements. * - * For a new, rightmost pair of elements, we'll hit cases b1. and b3., + * For a new, rightmost pair of elements, we'll hit cases b3. and b2., * in that order. * * The flag is also cleared in two special cases: @@ -262,9 +261,9 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, p = &parent->rb_left; if (nft_rbtree_interval_start(new)) { - overlap = nft_rbtree_interval_start(rbe) && - nft_set_elem_active(&rbe->ext, - genmask); + if (nft_rbtree_interval_end(rbe) && + nft_set_elem_active(&rbe->ext, genmask)) + overlap = false; } else { overlap = nft_rbtree_interval_end(rbe) && nft_set_elem_active(&rbe->ext, diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 75bd0e5dd312..7b2f359bfce4 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -346,6 +346,9 @@ static int idletimer_tg_checkentry_v1(const struct xt_tgchk_param *par) pr_debug("checkentry targinfo%s\n", info->label); + if (info->send_nl_msg) + return -EOPNOTSUPP; + ret = idletimer_tg_helper((struct idletimer_tg_info *)info); if(ret < 0) { diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index e22092e4a783..7ed31b5e77e4 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -906,20 +906,21 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) node = NULL; if (addr->sq_node == QRTR_NODE_BCAST) { - enqueue_fn = qrtr_bcast_enqueue; - if (addr->sq_port != QRTR_PORT_CTRL) { + if (addr->sq_port != QRTR_PORT_CTRL && + qrtr_local_nid != QRTR_NODE_BCAST) { release_sock(sk); return -ENOTCONN; } + enqueue_fn = qrtr_bcast_enqueue; } else if (addr->sq_node == ipc->us.sq_node) { enqueue_fn = qrtr_local_enqueue; } else { - enqueue_fn = qrtr_node_enqueue; node = qrtr_node_lookup(addr->sq_node); if (!node) { release_sock(sk); return -ECONNRESET; } + enqueue_fn = qrtr_node_enqueue; } plen = (len + 3) & ~3; diff --git a/net/rds/message.c b/net/rds/message.c index 50f13f1d4ae0..071a261fdaab 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2006 Oracle. All rights reserved. + * Copyright (c) 2006, 2020 Oracle and/or its affiliates. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -162,12 +162,12 @@ static void rds_message_purge(struct rds_message *rm) if (rm->rdma.op_active) rds_rdma_free_op(&rm->rdma); if (rm->rdma.op_rdma_mr) - rds_mr_put(rm->rdma.op_rdma_mr); + kref_put(&rm->rdma.op_rdma_mr->r_kref, __rds_put_mr_final); if (rm->atomic.op_active) rds_atomic_free_op(&rm->atomic); if (rm->atomic.op_rdma_mr) - rds_mr_put(rm->atomic.op_rdma_mr); + kref_put(&rm->atomic.op_rdma_mr->r_kref, __rds_put_mr_final); } void rds_message_put(struct rds_message *rm) @@ -308,26 +308,20 @@ out: /* * RDS ops use this to grab SG entries from the rm's sg pool. */ -struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents, - int *ret) +struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents) { struct scatterlist *sg_first = (struct scatterlist *) &rm[1]; struct scatterlist *sg_ret; - if (WARN_ON(!ret)) - return NULL; - if (nents <= 0) { pr_warn("rds: alloc sgs failed! nents <= 0\n"); - *ret = -EINVAL; - return NULL; + return ERR_PTR(-EINVAL); } if (rm->m_used_sgs + nents > rm->m_total_sgs) { pr_warn("rds: alloc sgs failed! total %d used %d nents %d\n", rm->m_total_sgs, rm->m_used_sgs, nents); - *ret = -ENOMEM; - return NULL; + return ERR_PTR(-ENOMEM); } sg_ret = &sg_first[rm->m_used_sgs]; @@ -343,7 +337,6 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in unsigned int i; int num_sgs = DIV_ROUND_UP(total_len, PAGE_SIZE); int extra_bytes = num_sgs * sizeof(struct scatterlist); - int ret; rm = rds_message_alloc(extra_bytes, GFP_NOWAIT); if (!rm) @@ -352,10 +345,10 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in set_bit(RDS_MSG_PAGEVEC, &rm->m_flags); rm->m_inc.i_hdr.h_len = cpu_to_be32(total_len); rm->data.op_nents = DIV_ROUND_UP(total_len, PAGE_SIZE); - rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs, &ret); - if (!rm->data.op_sg) { + rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); + if (IS_ERR(rm->data.op_sg)) { rds_message_put(rm); - return ERR_PTR(ret); + return ERR_CAST(rm->data.op_sg); } for (i = 0; i < rm->data.op_nents; ++i) { diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 585e6b3b69ce..a7ae11846cd7 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007, 2017 Oracle and/or its affiliates. All rights reserved. + * Copyright (c) 2007, 2020 Oracle and/or its affiliates. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -84,7 +84,7 @@ static struct rds_mr *rds_mr_tree_walk(struct rb_root *root, u64 key, if (insert) { rb_link_node(&insert->r_rb_node, parent, p); rb_insert_color(&insert->r_rb_node, root); - refcount_inc(&insert->r_refcount); + kref_get(&insert->r_kref); } return NULL; } @@ -99,10 +99,7 @@ static void rds_destroy_mr(struct rds_mr *mr) unsigned long flags; rdsdebug("RDS: destroy mr key is %x refcnt %u\n", - mr->r_key, refcount_read(&mr->r_refcount)); - - if (test_and_set_bit(RDS_MR_DEAD, &mr->r_state)) - return; + mr->r_key, kref_read(&mr->r_kref)); spin_lock_irqsave(&rs->rs_rdma_lock, flags); if (!RB_EMPTY_NODE(&mr->r_rb_node)) @@ -115,8 +112,10 @@ static void rds_destroy_mr(struct rds_mr *mr) mr->r_trans->free_mr(trans_private, mr->r_invalidate); } -void __rds_put_mr_final(struct rds_mr *mr) +void __rds_put_mr_final(struct kref *kref) { + struct rds_mr *mr = container_of(kref, struct rds_mr, r_kref); + rds_destroy_mr(mr); kfree(mr); } @@ -140,8 +139,7 @@ void rds_rdma_drop_keys(struct rds_sock *rs) rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); RB_CLEAR_NODE(&mr->r_rb_node); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); - rds_destroy_mr(mr); - rds_mr_put(mr); + kref_put(&mr->r_kref, __rds_put_mr_final); spin_lock_irqsave(&rs->rs_rdma_lock, flags); } spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); @@ -242,7 +240,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, goto out; } - refcount_set(&mr->r_refcount, 1); + kref_init(&mr->r_kref); RB_CLEAR_NODE(&mr->r_rb_node); mr->r_trans = rs->rs_transport; mr->r_sock = rs; @@ -343,7 +341,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, rdsdebug("RDS: get_mr key is %x\n", mr->r_key); if (mr_ret) { - refcount_inc(&mr->r_refcount); + kref_get(&mr->r_kref); *mr_ret = mr; } @@ -351,7 +349,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, out: kfree(pages); if (mr) - rds_mr_put(mr); + kref_put(&mr->r_kref, __rds_put_mr_final); return ret; } @@ -434,13 +432,7 @@ int rds_free_mr(struct rds_sock *rs, char __user *optval, int optlen) if (!mr) return -EINVAL; - /* - * call rds_destroy_mr() ourselves so that we're sure it's done by the time - * we return. If we let rds_mr_put() do it it might not happen until - * someone else drops their ref. - */ - rds_destroy_mr(mr); - rds_mr_put(mr); + kref_put(&mr->r_kref, __rds_put_mr_final); return 0; } @@ -464,6 +456,14 @@ void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force) return; } + /* Get a reference so that the MR won't go away before calling + * sync_mr() below. + */ + kref_get(&mr->r_kref); + + /* If it is going to be freed, remove it from the tree now so + * that no other thread can find it and free it. + */ if (mr->r_use_once || force) { rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); RB_CLEAR_NODE(&mr->r_rb_node); @@ -477,12 +477,13 @@ void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force) if (mr->r_trans->sync_mr) mr->r_trans->sync_mr(mr->r_trans_private, DMA_FROM_DEVICE); + /* Release the reference held above. */ + kref_put(&mr->r_kref, __rds_put_mr_final); + /* If the MR was marked as invalidate, this will * trigger an async flush. */ - if (zot_me) { - rds_destroy_mr(mr); - rds_mr_put(mr); - } + if (zot_me) + kref_put(&mr->r_kref, __rds_put_mr_final); } void rds_rdma_free_op(struct rm_rdma_op *ro) @@ -490,7 +491,7 @@ void rds_rdma_free_op(struct rm_rdma_op *ro) unsigned int i; if (ro->op_odp_mr) { - rds_mr_put(ro->op_odp_mr); + kref_put(&ro->op_odp_mr->r_kref, __rds_put_mr_final); } else { for (i = 0; i < ro->op_nents; i++) { struct page *page = sg_page(&ro->op_sg[i]); @@ -664,9 +665,11 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, op->op_odp_mr = NULL; WARN_ON(!nr_pages); - op->op_sg = rds_message_alloc_sgs(rm, nr_pages, &ret); - if (!op->op_sg) + op->op_sg = rds_message_alloc_sgs(rm, nr_pages); + if (IS_ERR(op->op_sg)) { + ret = PTR_ERR(op->op_sg); goto out_pages; + } if (op->op_notify || op->op_recverr) { /* We allocate an uninitialized notifier here, because @@ -730,7 +733,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, goto out_pages; } RB_CLEAR_NODE(&local_odp_mr->r_rb_node); - refcount_set(&local_odp_mr->r_refcount, 1); + kref_init(&local_odp_mr->r_kref); local_odp_mr->r_trans = rs->rs_transport; local_odp_mr->r_sock = rs; local_odp_mr->r_trans_private = @@ -827,7 +830,7 @@ int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm, if (!mr) err = -EINVAL; /* invalid r_key */ else - refcount_inc(&mr->r_refcount); + kref_get(&mr->r_kref); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (mr) { @@ -905,9 +908,11 @@ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, rm->atomic.op_silent = !!(args->flags & RDS_RDMA_SILENT); rm->atomic.op_active = 1; rm->atomic.op_recverr = rs->rs_recverr; - rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1, &ret); - if (!rm->atomic.op_sg) + rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1); + if (IS_ERR(rm->atomic.op_sg)) { + ret = PTR_ERR(rm->atomic.op_sg); goto err; + } /* verify 8 byte-aligned */ if (args->local_addr & 0x7) { diff --git a/net/rds/rds.h b/net/rds/rds.h index e4a603523083..6019b0c004a9 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -291,7 +291,7 @@ struct rds_incoming { struct rds_mr { struct rb_node r_rb_node; - refcount_t r_refcount; + struct kref r_kref; u32 r_key; /* A copy of the creation flags */ @@ -299,19 +299,11 @@ struct rds_mr { unsigned int r_invalidate:1; unsigned int r_write:1; - /* This is for RDS_MR_DEAD. - * It would be nice & consistent to make this part of the above - * bit field here, but we need to use test_and_set_bit. - */ - unsigned long r_state; struct rds_sock *r_sock; /* back pointer to the socket that owns us */ struct rds_transport *r_trans; void *r_trans_private; }; -/* Flags for mr->r_state */ -#define RDS_MR_DEAD 0 - static inline rds_rdma_cookie_t rds_rdma_make_cookie(u32 r_key, u32 offset) { return r_key | (((u64) offset) << 32); @@ -852,8 +844,7 @@ rds_conn_connecting(struct rds_connection *conn) /* message.c */ struct rds_message *rds_message_alloc(unsigned int nents, gfp_t gfp); -struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents, - int *ret); +struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents); int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from, bool zcopy); struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned int total_len); @@ -946,12 +937,7 @@ void rds_atomic_send_complete(struct rds_message *rm, int wc_status); int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg); -void __rds_put_mr_final(struct rds_mr *mr); -static inline void rds_mr_put(struct rds_mr *mr) -{ - if (refcount_dec_and_test(&mr->r_refcount)) - __rds_put_mr_final(mr); -} +void __rds_put_mr_final(struct kref *kref); static inline bool rds_destroy_pending(struct rds_connection *conn) { diff --git a/net/rds/send.c b/net/rds/send.c index 82dcd8b84fe7..68e2bdb08fd0 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1274,9 +1274,11 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* Attach data to the rm */ if (payload_len) { - rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs, &ret); - if (!rm->data.op_sg) + rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); + if (IS_ERR(rm->data.op_sg)) { + ret = PTR_ERR(rm->data.op_sg); goto out; + } ret = rds_message_copy_from_user(rm, &msg->msg_iter, zcopy); if (ret) goto out; diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index a6c1349e965d..01135e54d95d 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -165,15 +165,6 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) goto error; } - /* we want to set the don't fragment bit */ - opt = IPV6_PMTUDISC_DO; - ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER, - (char *) &opt, sizeof(opt)); - if (ret < 0) { - _debug("setsockopt failed"); - goto error; - } - /* Fall through and set IPv4 options too otherwise we don't get * errors from IPv4 packets sent through the IPv6 socket. */ diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index bad3d2420344..90e263c6aa69 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -474,41 +474,21 @@ send_fragmentable: skb->tstamp = ktime_get_real(); switch (conn->params.local->srx.transport.family) { + case AF_INET6: case AF_INET: opt = IP_PMTUDISC_DONT; - ret = kernel_setsockopt(conn->params.local->socket, - SOL_IP, IP_MTU_DISCOVER, - (char *)&opt, sizeof(opt)); - if (ret == 0) { - ret = kernel_sendmsg(conn->params.local->socket, &msg, - iov, 2, len); - conn->params.peer->last_tx_at = ktime_get_seconds(); - - opt = IP_PMTUDISC_DO; - kernel_setsockopt(conn->params.local->socket, SOL_IP, - IP_MTU_DISCOVER, - (char *)&opt, sizeof(opt)); - } - break; - -#ifdef CONFIG_AF_RXRPC_IPV6 - case AF_INET6: - opt = IPV6_PMTUDISC_DONT; - ret = kernel_setsockopt(conn->params.local->socket, - SOL_IPV6, IPV6_MTU_DISCOVER, - (char *)&opt, sizeof(opt)); - if (ret == 0) { - ret = kernel_sendmsg(conn->params.local->socket, &msg, - iov, 2, len); - conn->params.peer->last_tx_at = ktime_get_seconds(); - - opt = IPV6_PMTUDISC_DO; - kernel_setsockopt(conn->params.local->socket, - SOL_IPV6, IPV6_MTU_DISCOVER, - (char *)&opt, sizeof(opt)); - } + kernel_setsockopt(conn->params.local->socket, + SOL_IP, IP_MTU_DISCOVER, + (char *)&opt, sizeof(opt)); + ret = kernel_sendmsg(conn->params.local->socket, &msg, + iov, 2, len); + conn->params.peer->last_tx_at = ktime_get_seconds(); + + opt = IP_PMTUDISC_DO; + kernel_setsockopt(conn->params.local->socket, + SOL_IP, IP_MTU_DISCOVER, + (char *)&opt, sizeof(opt)); break; -#endif default: BUG(); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index f6a3b969ead0..55bd1429678f 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1667,6 +1667,7 @@ int tcf_classify_ingress(struct sk_buff *skb, skb_ext_del(skb, TC_SKB_EXT); tp = rcu_dereference_bh(fchain->filter_chain); + last_executed_chain = fchain->index; } ret = __tcf_classify(skb, tp, orig_tp, res, compat_mode, diff --git a/net/tipc/link.c b/net/tipc/link.c index 467c53a1fb5c..d4675e922a8f 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1065,7 +1065,7 @@ static void tipc_link_update_cwin(struct tipc_link *l, int released, /* Enter fast recovery */ if (unlikely(retransmitted)) { l->ssthresh = max_t(u16, l->window / 2, 300); - l->window = l->ssthresh; + l->window = min_t(u16, l->ssthresh, l->window); return; } /* Enter slow start */ diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 156efce50dbd..0e989005bdc2 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -56,9 +56,9 @@ enum { TLS_NUM_PROTS, }; -static struct proto *saved_tcpv6_prot; +static const struct proto *saved_tcpv6_prot; static DEFINE_MUTEX(tcpv6_prot_mutex); -static struct proto *saved_tcpv4_prot; +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; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5fa402144cda..692bcd35f809 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -644,10 +644,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_HE_CAPABILITY] = { .type = NLA_BINARY, .len = NL80211_HE_MAX_CAPABILITY_LEN }, - [NL80211_ATTR_FTM_RESPONDER] = { - .type = NLA_NESTED, - .validation_data = nl80211_ftm_responder_policy, - }, + [NL80211_ATTR_FTM_RESPONDER] = + NLA_POLICY_NESTED(nl80211_ftm_responder_policy), [NL80211_ATTR_TIMEOUT] = NLA_POLICY_MIN(NLA_U32, 1), [NL80211_ATTR_PEER_MEASUREMENTS] = NLA_POLICY_NESTED(nl80211_pmsr_attr_policy), diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index fa7bb5e060d0..ed7a6060f73c 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -343,7 +343,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) u32 chunk_size = mr->chunk_size, headroom = mr->headroom; unsigned int chunks, chunks_per_page; u64 addr = mr->addr, size = mr->len; - int size_chk, err; + int err; if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) { /* Strictly speaking we could support this, if: @@ -382,8 +382,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) return -EINVAL; } - size_chk = chunk_size - headroom - XDP_PACKET_HEADROOM; - if (size_chk < 0) + if (headroom >= chunk_size - XDP_PACKET_HEADROOM) return -EINVAL; umem->address = (unsigned long)addr; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 356f90e4522b..c350108aa38d 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -131,8 +131,9 @@ static void __xsk_rcv_memcpy(struct xdp_umem *umem, u64 addr, void *from_buf, u64 page_start = addr & ~(PAGE_SIZE - 1); u64 first_len = PAGE_SIZE - (addr - page_start); - memcpy(to_buf, from_buf, first_len + metalen); - memcpy(next_pg_addr, from_buf + first_len, len - first_len); + memcpy(to_buf, from_buf, first_len); + memcpy(next_pg_addr, from_buf + first_len, + len + metalen - first_len); return; } |