diff options
Diffstat (limited to 'net')
78 files changed, 860 insertions, 532 deletions
diff --git a/net/atm/lec.c b/net/atm/lec.c index a107375c0629..fb93c6e1c329 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -1260,24 +1260,28 @@ static void lec_arp_clear_vccs(struct lec_arp_table *entry) struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); struct net_device *dev = (struct net_device *)vcc->proto_data; - vcc->pop = vpriv->old_pop; - if (vpriv->xoff) - netif_wake_queue(dev); - kfree(vpriv); - vcc->user_back = NULL; - vcc->push = entry->old_push; - vcc_release_async(vcc, -EPIPE); + if (vpriv) { + vcc->pop = vpriv->old_pop; + if (vpriv->xoff) + netif_wake_queue(dev); + kfree(vpriv); + vcc->user_back = NULL; + vcc->push = entry->old_push; + vcc_release_async(vcc, -EPIPE); + } entry->vcc = NULL; } if (entry->recv_vcc) { struct atm_vcc *vcc = entry->recv_vcc; struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); - kfree(vpriv); - vcc->user_back = NULL; + if (vpriv) { + kfree(vpriv); + vcc->user_back = NULL; - entry->recv_vcc->push = entry->old_recv_push; - vcc_release_async(entry->recv_vcc, -EPIPE); + entry->recv_vcc->push = entry->old_recv_push; + vcc_release_async(entry->recv_vcc, -EPIPE); + } entry->recv_vcc = NULL; } } diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 2ce4e5bf9292..fdc2abe96d77 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -111,7 +111,15 @@ static bool batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh, /* unsupported WiFi driver version */ goto default_throughput; - real_netdev = batadv_get_real_netdev(hard_iface->net_dev); + /* only use rtnl_trylock because the elp worker will be cancelled while + * the rntl_lock is held. the cancel_delayed_work_sync() would otherwise + * wait forever when the elp work_item was started and it is then also + * trying to rtnl_lock + */ + if (!rtnl_trylock()) + return false; + real_netdev = __batadv_get_real_netdev(hard_iface->net_dev); + rtnl_unlock(); if (!real_netdev) goto default_throughput; diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 7b7640f3ffe2..d6732c34aeaf 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -204,7 +204,7 @@ static bool batadv_is_valid_iface(const struct net_device *net_dev) } /** - * batadv_get_real_netdevice() - check if the given netdev struct is a virtual + * __batadv_get_real_netdev() - check if the given netdev struct is a virtual * interface on top of another 'real' interface * @netdev: the device to check * @@ -214,7 +214,7 @@ static bool batadv_is_valid_iface(const struct net_device *net_dev) * Return: the 'real' net device or the original net device and NULL in case * of an error. */ -static struct net_device *batadv_get_real_netdevice(struct net_device *netdev) +struct net_device *__batadv_get_real_netdev(struct net_device *netdev) { struct batadv_hard_iface *hard_iface = NULL; struct net_device *real_netdev = NULL; @@ -267,7 +267,7 @@ struct net_device *batadv_get_real_netdev(struct net_device *net_device) struct net_device *real_netdev; rtnl_lock(); - real_netdev = batadv_get_real_netdevice(net_device); + real_netdev = __batadv_get_real_netdev(net_device); rtnl_unlock(); return real_netdev; @@ -336,7 +336,7 @@ static u32 batadv_wifi_flags_evaluate(struct net_device *net_device) if (batadv_is_cfg80211_netdev(net_device)) wifi_flags |= BATADV_HARDIF_WIFI_CFG80211_DIRECT; - real_netdev = batadv_get_real_netdevice(net_device); + real_netdev = __batadv_get_real_netdev(net_device); if (!real_netdev) return wifi_flags; diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 9db8a310961e..9ba8fb2bdceb 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -67,6 +67,7 @@ enum batadv_hard_if_bcast { extern struct notifier_block batadv_hard_if_notifier; +struct net_device *__batadv_get_real_netdev(struct net_device *net_device); struct net_device *batadv_get_real_netdev(struct net_device *net_device); bool batadv_is_cfg80211_hardif(struct batadv_hard_iface *hard_iface); bool batadv_is_wifi_hardif(struct batadv_hard_iface *hard_iface); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index ee01122f466f..f7502e62dd35 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -74,7 +74,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) eth_hdr(skb)->h_proto == htons(ETH_P_RARP)) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) { br_do_proxy_suppress_arp(skb, br, vid, NULL); - } else if (IS_ENABLED(CONFIG_IPV6) && + } else if (ipv6_mod_enabled() && skb->protocol == htons(ETH_P_IPV6) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) && pskb_may_pull(skb, sizeof(struct ipv6hdr) + diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 1405f1061a54..2cbae0f9ae1f 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -170,7 +170,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb (skb->protocol == htons(ETH_P_ARP) || skb->protocol == htons(ETH_P_RARP))) { br_do_proxy_suppress_arp(skb, br, vid, p); - } else if (IS_ENABLED(CONFIG_IPV6) && + } else if (ipv6_mod_enabled() && skb->protocol == htons(ETH_P_IPV6) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) && pskb_may_pull(skb, sizeof(struct ipv6hdr) + diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index b9b2981c4841..9b55d38ea9ed 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1345,6 +1345,16 @@ br_multicast_ctx_options_equal(const struct net_bridge_mcast *brmctx1, } static inline bool +br_multicast_port_ctx_options_equal(const struct net_bridge_mcast_port *pmctx1, + const struct net_bridge_mcast_port *pmctx2) +{ + return br_multicast_ngroups_get(pmctx1) == + br_multicast_ngroups_get(pmctx2) && + br_multicast_ngroups_get_max(pmctx1) == + br_multicast_ngroups_get_max(pmctx2); +} + +static inline bool br_multicast_ctx_matches_vlan_snooping(const struct net_bridge_mcast *brmctx) { bool vlan_snooping_enabled; diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c index 8fa89b04ee94..5514e1fc8d1f 100644 --- a/net/bridge/br_vlan_options.c +++ b/net/bridge/br_vlan_options.c @@ -43,9 +43,29 @@ bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr, u8 range_mc_rtr = br_vlan_multicast_router(range_end); u8 curr_mc_rtr = br_vlan_multicast_router(v_curr); - return v_curr->state == range_end->state && - __vlan_tun_can_enter_range(v_curr, range_end) && - curr_mc_rtr == range_mc_rtr; + if (v_curr->state != range_end->state) + return false; + + if (!__vlan_tun_can_enter_range(v_curr, range_end)) + return false; + + if (curr_mc_rtr != range_mc_rtr) + return false; + + /* Check user-visible priv_flags that affect output */ + if ((v_curr->priv_flags ^ range_end->priv_flags) & + (BR_VLFLAG_NEIGH_SUPPRESS_ENABLED | BR_VLFLAG_MCAST_ENABLED)) + return false; + +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + if (!br_vlan_is_master(v_curr) && + !br_multicast_port_ctx_vlan_disabled(&v_curr->port_mcast_ctx) && + !br_multicast_port_ctx_options_equal(&v_curr->port_mcast_ctx, + &range_end->port_mcast_ctx)) + return false; +#endif + + return true; } bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v, diff --git a/net/can/bcm.c b/net/can/bcm.c index b7324e9c955b..fd9fa072881e 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1176,6 +1176,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, if (!op) return -ENOMEM; + spin_lock_init(&op->bcm_tx_lock); op->can_id = msg_head->can_id; op->nframes = msg_head->nframes; op->cfsiz = CFSIZ(msg_head->flags); diff --git a/net/ceph/auth.c b/net/ceph/auth.c index 343c841784ce..901b93530b21 100644 --- a/net/ceph/auth.c +++ b/net/ceph/auth.c @@ -205,9 +205,9 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac, s32 result; u64 global_id; void *payload, *payload_end; - int payload_len; + u32 payload_len; char *result_msg; - int result_msg_len; + u32 result_msg_len; int ret = -EINVAL; mutex_lock(&ac->mutex); @@ -217,10 +217,12 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac, result = ceph_decode_32(&p); global_id = ceph_decode_64(&p); payload_len = ceph_decode_32(&p); + ceph_decode_need(&p, end, payload_len, bad); payload = p; p += payload_len; ceph_decode_need(&p, end, sizeof(u32), bad); result_msg_len = ceph_decode_32(&p); + ceph_decode_need(&p, end, result_msg_len, bad); result_msg = p; p += result_msg_len; if (p != end) diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index 5ec3272cd2dd..50f65820f623 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -392,7 +392,7 @@ static int head_onwire_len(int ctrl_len, bool secure) int head_len; int rem_len; - BUG_ON(ctrl_len < 0 || ctrl_len > CEPH_MSG_MAX_CONTROL_LEN); + BUG_ON(ctrl_len < 1 || ctrl_len > CEPH_MSG_MAX_CONTROL_LEN); if (secure) { head_len = CEPH_PREAMBLE_SECURE_LEN; @@ -401,9 +401,7 @@ static int head_onwire_len(int ctrl_len, bool secure) head_len += padded_len(rem_len) + CEPH_GCM_TAG_LEN; } } else { - head_len = CEPH_PREAMBLE_PLAIN_LEN; - if (ctrl_len) - head_len += ctrl_len + CEPH_CRC_LEN; + head_len = CEPH_PREAMBLE_PLAIN_LEN + ctrl_len + CEPH_CRC_LEN; } return head_len; } @@ -528,11 +526,16 @@ static int decode_preamble(void *p, struct ceph_frame_desc *desc) desc->fd_aligns[i] = ceph_decode_16(&p); } - if (desc->fd_lens[0] < 0 || + /* + * This would fire for FRAME_TAG_WAIT (it has one empty + * segment), but we should never get it as client. + */ + if (desc->fd_lens[0] < 1 || desc->fd_lens[0] > CEPH_MSG_MAX_CONTROL_LEN) { pr_err("bad control segment length %d\n", desc->fd_lens[0]); return -EINVAL; } + if (desc->fd_lens[1] < 0 || desc->fd_lens[1] > CEPH_MSG_MAX_FRONT_LEN) { pr_err("bad front segment length %d\n", desc->fd_lens[1]); @@ -549,10 +552,6 @@ static int decode_preamble(void *p, struct ceph_frame_desc *desc) return -EINVAL; } - /* - * This would fire for FRAME_TAG_WAIT (it has one empty - * segment), but we should never get it as client. - */ if (!desc->fd_lens[desc->fd_seg_cnt - 1]) { pr_err("last segment empty, segment count %d\n", desc->fd_seg_cnt); @@ -2833,12 +2832,15 @@ static int process_message_header(struct ceph_connection *con, void *p, void *end) { struct ceph_frame_desc *desc = &con->v2.in_desc; - struct ceph_msg_header2 *hdr2 = p; + struct ceph_msg_header2 *hdr2; struct ceph_msg_header hdr; int skip; int ret; u64 seq; + ceph_decode_need(&p, end, sizeof(*hdr2), bad); + hdr2 = p; + /* verify seq# */ seq = le64_to_cpu(hdr2->seq); if ((s64)seq - (s64)con->in_seq < 1) { @@ -2869,6 +2871,10 @@ static int process_message_header(struct ceph_connection *con, WARN_ON(!con->in_msg); WARN_ON(con->in_msg->con != con); return 1; + +bad: + pr_err("failed to decode message header\n"); + return -EINVAL; } static int process_message(struct ceph_connection *con) @@ -2898,6 +2904,11 @@ static int __handle_control(struct ceph_connection *con, void *p) if (con->v2.in_desc.fd_tag != FRAME_TAG_MESSAGE) return process_control(con, p, end); + if (con->state != CEPH_CON_S_OPEN) { + con->error_msg = "protocol error, unexpected message"; + return -EINVAL; + } + ret = process_message_header(con, p, end); if (ret < 0) return ret; diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 5136b3766c44..d5080530ce0c 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -72,8 +72,8 @@ static struct ceph_monmap *ceph_monmap_decode(void **p, void *end, bool msgr2) struct ceph_monmap *monmap = NULL; struct ceph_fsid fsid; u32 struct_len; - int blob_len; - int num_mon; + u32 blob_len; + u32 num_mon; u8 struct_v; u32 epoch; int ret; @@ -112,7 +112,7 @@ static struct ceph_monmap *ceph_monmap_decode(void **p, void *end, bool msgr2) } ceph_decode_32_safe(p, end, num_mon, e_inval); - dout("%s fsid %pU epoch %u num_mon %d\n", __func__, &fsid, epoch, + dout("%s fsid %pU epoch %u num_mon %u\n", __func__, &fsid, epoch, num_mon); if (num_mon > CEPH_MAX_MON) goto e_inval; diff --git a/net/core/dev.c b/net/core/dev.c index c1a9f7fdcffa..14a83f2035b9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3987,7 +3987,7 @@ static struct sk_buff *validate_xmit_unreadable_skb(struct sk_buff *skb, if (shinfo->nr_frags > 0) { niov = netmem_to_net_iov(skb_frag_netmem(&shinfo->frags[0])); if (net_is_devmem_iov(niov) && - net_devmem_iov_binding(niov)->dev != dev) + READ_ONCE(net_devmem_iov_binding(niov)->dev) != dev) goto out_free; } @@ -4818,10 +4818,7 @@ 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 */ - /* 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 (!netif_tx_owned(txq, cpu)) { bool is_list = false; if (dev_xmit_recursion()) @@ -7794,11 +7791,12 @@ static int napi_thread_wait(struct napi_struct *napi) return -1; } -static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll) +static void napi_threaded_poll_loop(struct napi_struct *napi, + unsigned long *busy_poll_last_qs) { + unsigned long last_qs = busy_poll_last_qs ? *busy_poll_last_qs : jiffies; struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct softnet_data *sd; - unsigned long last_qs = jiffies; for (;;) { bool repoll = false; @@ -7827,12 +7825,12 @@ static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll) /* When busy poll is enabled, the old packets are not flushed in * napi_complete_done. So flush them here. */ - if (busy_poll) + if (busy_poll_last_qs) gro_flush_normal(&napi->gro, HZ >= 1000); local_bh_enable(); /* Call cond_resched here to avoid watchdog warnings. */ - if (repoll || busy_poll) { + if (repoll || busy_poll_last_qs) { rcu_softirq_qs_periodic(last_qs); cond_resched(); } @@ -7840,11 +7838,15 @@ static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll) if (!repoll) break; } + + if (busy_poll_last_qs) + *busy_poll_last_qs = last_qs; } static int napi_threaded_poll(void *data) { struct napi_struct *napi = data; + unsigned long last_qs = jiffies; bool want_busy_poll; bool in_busy_poll; unsigned long val; @@ -7862,7 +7864,7 @@ static int napi_threaded_poll(void *data) assign_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state, want_busy_poll); - napi_threaded_poll_loop(napi, want_busy_poll); + napi_threaded_poll_loop(napi, want_busy_poll ? &last_qs : NULL); } return 0; @@ -13175,7 +13177,7 @@ static void run_backlog_napi(unsigned int cpu) { struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); - napi_threaded_poll_loop(&sd->backlog, false); + napi_threaded_poll_loop(&sd->backlog, NULL); } static void backlog_napi_setup(unsigned int cpu) diff --git a/net/core/dev.h b/net/core/dev.h index 98793a738f43..781619e76b3e 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -366,41 +366,6 @@ static inline void napi_assert_will_not_race(const struct napi_struct *napi) void kick_defer_list_purge(unsigned int cpu); -#define XMIT_RECURSION_LIMIT 8 - -#ifndef CONFIG_PREEMPT_RT -static inline bool dev_xmit_recursion(void) -{ - return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > - XMIT_RECURSION_LIMIT); -} - -static inline void dev_xmit_recursion_inc(void) -{ - __this_cpu_inc(softnet_data.xmit.recursion); -} - -static inline void dev_xmit_recursion_dec(void) -{ - __this_cpu_dec(softnet_data.xmit.recursion); -} -#else -static inline bool dev_xmit_recursion(void) -{ - return unlikely(current->net_xmit.recursion > XMIT_RECURSION_LIMIT); -} - -static inline void dev_xmit_recursion_inc(void) -{ - current->net_xmit.recursion++; -} - -static inline void dev_xmit_recursion_dec(void) -{ - current->net_xmit.recursion--; -} -#endif - int dev_set_hwtstamp_phylib(struct net_device *dev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack); diff --git a/net/core/devmem.c b/net/core/devmem.c index 8c9aad776bf4..69d79aee07ef 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -396,7 +396,8 @@ struct net_devmem_dmabuf_binding *net_devmem_get_binding(struct sock *sk, * net_device. */ dst_dev = dst_dev_rcu(dst); - if (unlikely(!dst_dev) || unlikely(dst_dev != binding->dev)) { + if (unlikely(!dst_dev) || + unlikely(dst_dev != READ_ONCE(binding->dev))) { err = -ENODEV; goto out_unlock; } @@ -513,7 +514,8 @@ static void mp_dmabuf_devmem_uninstall(void *mp_priv, xa_erase(&binding->bound_rxqs, xa_idx); if (xa_empty(&binding->bound_rxqs)) { mutex_lock(&binding->lock); - binding->dev = NULL; + ASSERT_EXCLUSIVE_WRITER(binding->dev); + WRITE_ONCE(binding->dev, NULL); mutex_unlock(&binding->lock); } break; diff --git a/net/core/filter.c b/net/core/filter.c index 0d5d5a17acb2..78b548158fb0 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2228,6 +2228,9 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb, return -ENOMEM; } + if (unlikely(!ipv6_mod_enabled())) + goto out_drop; + rcu_read_lock(); if (!nh) { dst = skb_dst(skb); @@ -2335,6 +2338,10 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb, neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); } else if (nh->nh_family == AF_INET6) { + if (unlikely(!ipv6_mod_enabled())) { + rcu_read_unlock(); + goto out_drop; + } neigh = ip_neigh_gw6(dev, &nh->ipv6_nh); is_v6gw = true; } else if (nh->nh_family == AF_INET) { @@ -4150,12 +4157,14 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset) struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags - 1]; struct xdp_rxq_info *rxq = xdp->rxq; - unsigned int tailroom; + int tailroom; if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz) return -EOPNOTSUPP; - tailroom = rxq->frag_size - skb_frag_size(frag) - skb_frag_off(frag); + tailroom = rxq->frag_size - skb_frag_size(frag) - + skb_frag_off(frag) % rxq->frag_size; + WARN_ON_ONCE(tailroom < 0); if (unlikely(offset > tailroom)) return -EINVAL; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index a95cfe77f7f0..c56a4e7bf790 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -820,7 +820,8 @@ int pneigh_create(struct neigh_table *tbl, struct net *net, update: WRITE_ONCE(n->flags, flags); n->permanent = permanent; - WRITE_ONCE(n->protocol, protocol); + if (protocol) + WRITE_ONCE(n->protocol, protocol); out: mutex_unlock(&tbl->phash_lock); return err; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index a8558a52884f..cd74beffd209 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -132,7 +132,7 @@ static int netif_local_xmit_active(struct net_device *dev) for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - if (READ_ONCE(txq->xmit_lock_owner) == smp_processor_id()) + if (netif_tx_owned(txq, smp_processor_id())) return 1; } diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index c82a95beceff..ee5060d8eec0 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -245,7 +245,7 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, goto err_cancel; if (pool->user.detach_time && nla_put_uint(rsp, NETDEV_A_PAGE_POOL_DETACH_TIME, - pool->user.detach_time)) + ktime_divns(pool->user.detach_time, NSEC_PER_SEC))) goto err_cancel; if (pool->mp_ops && pool->mp_ops->nl_fill(pool->mp_priv, rsp, NULL)) @@ -337,7 +337,7 @@ err_unlock: void page_pool_detached(struct page_pool *pool) { mutex_lock(&page_pools_lock); - pool->user.detach_time = ktime_get_boottime_seconds(); + pool->user.detach_time = ktime_get_boottime(); netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF); mutex_unlock(&page_pools_lock); } diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 9a3965680451..6a6f2cda5aae 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -20,7 +20,6 @@ #include <net/tcp.h> static siphash_aligned_key_t net_secret; -static siphash_aligned_key_t ts_secret; #define EPHEMERAL_PORT_SHUFFLE_PERIOD (10 * HZ) @@ -28,11 +27,6 @@ static __always_inline void net_secret_init(void) { net_get_random_once(&net_secret, sizeof(net_secret)); } - -static __always_inline void ts_secret_init(void) -{ - net_get_random_once(&ts_secret, sizeof(ts_secret)); -} #endif #ifdef CONFIG_INET @@ -53,28 +47,9 @@ static u32 seq_scale(u32 seq) #endif #if IS_ENABLED(CONFIG_IPV6) -u32 secure_tcpv6_ts_off(const struct net *net, - const __be32 *saddr, const __be32 *daddr) -{ - const struct { - struct in6_addr saddr; - struct in6_addr daddr; - } __aligned(SIPHASH_ALIGNMENT) combined = { - .saddr = *(struct in6_addr *)saddr, - .daddr = *(struct in6_addr *)daddr, - }; - - if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) - return 0; - - ts_secret_init(); - return siphash(&combined, offsetofend(typeof(combined), daddr), - &ts_secret); -} -EXPORT_IPV6_MOD(secure_tcpv6_ts_off); - -u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, - __be16 sport, __be16 dport) +union tcp_seq_and_ts_off +secure_tcpv6_seq_and_ts_off(const struct net *net, const __be32 *saddr, + const __be32 *daddr, __be16 sport, __be16 dport) { const struct { struct in6_addr saddr; @@ -87,14 +62,20 @@ u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, .sport = sport, .dport = dport }; - u32 hash; + union tcp_seq_and_ts_off st; net_secret_init(); - hash = siphash(&combined, offsetofend(typeof(combined), dport), - &net_secret); - return seq_scale(hash); + + st.hash64 = siphash(&combined, offsetofend(typeof(combined), dport), + &net_secret); + + if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) + st.ts_off = 0; + + st.seq = seq_scale(st.seq); + return st; } -EXPORT_SYMBOL(secure_tcpv6_seq); +EXPORT_SYMBOL(secure_tcpv6_seq_and_ts_off); u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport) @@ -118,33 +99,30 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #ifdef CONFIG_INET -u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr) -{ - if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) - return 0; - - ts_secret_init(); - return siphash_2u32((__force u32)saddr, (__force u32)daddr, - &ts_secret); -} - /* secure_tcp_seq_and_tsoff(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d), * but fortunately, `sport' cannot be 0 in any circumstances. If this changes, * it would be easy enough to have the former function use siphash_4u32, passing * the arguments as separate u32. */ -u32 secure_tcp_seq(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport) +union tcp_seq_and_ts_off +secure_tcp_seq_and_ts_off(const struct net *net, __be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) { - u32 hash; + u32 ports = (__force u32)sport << 16 | (__force u32)dport; + union tcp_seq_and_ts_off st; net_secret_init(); - hash = siphash_3u32((__force u32)saddr, (__force u32)daddr, - (__force u32)sport << 16 | (__force u32)dport, - &net_secret); - return seq_scale(hash); + + st.hash64 = siphash_3u32((__force u32)saddr, (__force u32)daddr, + ports, &net_secret); + + if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) + st.ts_off = 0; + + st.seq = seq_scale(st.seq); + return st; } -EXPORT_SYMBOL_GPL(secure_tcp_seq); +EXPORT_SYMBOL_GPL(secure_tcp_seq_and_ts_off); u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 2e26174c9919..3261793abe83 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1205,8 +1205,8 @@ void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) return; psock->saved_data_ready = sk->sk_data_ready; - sk->sk_data_ready = sk_psock_strp_data_ready; - sk->sk_write_space = sk_psock_write_space; + WRITE_ONCE(sk->sk_data_ready, sk_psock_strp_data_ready); + WRITE_ONCE(sk->sk_write_space, sk_psock_write_space); } void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) @@ -1216,8 +1216,8 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) if (!psock->saved_data_ready) return; - sk->sk_data_ready = psock->saved_data_ready; - psock->saved_data_ready = NULL; + WRITE_ONCE(sk->sk_data_ready, psock->saved_data_ready); + WRITE_ONCE(psock->saved_data_ready, NULL); strp_stop(&psock->strp); } @@ -1296,8 +1296,8 @@ void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock) return; psock->saved_data_ready = sk->sk_data_ready; - sk->sk_data_ready = sk_psock_verdict_data_ready; - sk->sk_write_space = sk_psock_write_space; + WRITE_ONCE(sk->sk_data_ready, sk_psock_verdict_data_ready); + WRITE_ONCE(sk->sk_write_space, sk_psock_write_space); } void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock) @@ -1308,6 +1308,6 @@ void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock) if (!psock->saved_data_ready) return; - sk->sk_data_ready = psock->saved_data_ready; + WRITE_ONCE(sk->sk_data_ready, psock->saved_data_ready); psock->saved_data_ready = NULL; } diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index b71c22475c51..df922f9f5289 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -748,6 +748,7 @@ config TCP_SIGPOOL config TCP_AO bool "TCP: Authentication Option (RFC5925)" select CRYPTO + select CRYPTO_LIB_UTILS select TCP_SIGPOOL depends on 64BIT && IPV6 != m # seq-number extension needs WRITE_ONCE(u64) help @@ -761,6 +762,7 @@ config TCP_AO config TCP_MD5SIG bool "TCP: MD5 Signature Option support (RFC2385)" select CRYPTO_LIB_MD5 + select CRYPTO_LIB_UTILS help RFC2385 specifies a method of giving MD5 protection to TCP sessions. Its main (only?) use is to protect BGP sessions between core routers diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 8036e76aa1e4..c7731e300a44 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -124,6 +124,12 @@ #include <trace/events/sock.h> +/* Keep the definition of IPv6 disable here for now, to avoid annoying linker + * issues in case IPv6=m + */ +int disable_ipv6_mod; +EXPORT_SYMBOL(disable_ipv6_mod); + /* The inetsw table contains everything that inet_create needs to * build a new socket. */ diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index fca980772c81..9bfccc283fa6 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -200,7 +200,7 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2, void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, struct inet_bind2_bucket *tb2, unsigned short port) { - inet_sk(sk)->inet_num = port; + WRITE_ONCE(inet_sk(sk)->inet_num, port); inet_csk(sk)->icsk_bind_hash = tb; inet_csk(sk)->icsk_bind2_hash = tb2; sk_add_bind_node(sk, &tb2->owners); @@ -224,7 +224,7 @@ static void __inet_put_port(struct sock *sk) spin_lock(&head->lock); tb = inet_csk(sk)->icsk_bind_hash; inet_csk(sk)->icsk_bind_hash = NULL; - inet_sk(sk)->inet_num = 0; + WRITE_ONCE(inet_sk(sk)->inet_num, 0); sk->sk_userlocks &= ~SOCK_CONNECT_BIND; spin_lock(&head2->lock); @@ -352,7 +352,7 @@ static inline int compute_score(struct sock *sk, const struct net *net, { int score = -1; - if (net_eq(sock_net(sk), net) && sk->sk_num == hnum && + if (net_eq(sock_net(sk), net) && READ_ONCE(sk->sk_num) == hnum && !ipv6_only_sock(sk)) { if (sk->sk_rcv_saddr != daddr) return -1; @@ -1206,7 +1206,7 @@ error: sk->sk_hash = 0; inet_sk(sk)->inet_sport = 0; - inet_sk(sk)->inet_num = 0; + WRITE_ONCE(inet_sk(sk)->inet_num, 0); if (tw) inet_twsk_bind_unhash(tw, hinfo); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 2e61ac137128..5683c328990f 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -58,6 +58,19 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, struct iphdr *iph; int err; + if (unlikely(dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT)) { + if (dev) { + net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", + dev->name); + DEV_STATS_INC(dev, tx_errors); + } + ip_rt_put(rt); + kfree_skb(skb); + return; + } + + dev_xmit_recursion_inc(); + skb_scrub_packet(skb, xnet); skb_clear_hash_if_not_l4(skb); @@ -88,6 +101,8 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, pkt_len = 0; iptunnel_xmit_stats(dev, pkt_len); } + + dev_xmit_recursion_dec(); } EXPORT_SYMBOL_GPL(iptunnel_xmit); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 1aa2b05ee8de..c942f1282236 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -2002,7 +2002,8 @@ static void nh_hthr_group_rebalance(struct nh_group *nhg) } static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, - struct nl_info *nlinfo) + struct nl_info *nlinfo, + struct list_head *deferred_free) { struct nh_grp_entry *nhges, *new_nhges; struct nexthop *nhp = nhge->nh_parent; @@ -2062,8 +2063,8 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, rcu_assign_pointer(nhp->nh_grp, newg); list_del(&nhge->nh_list); - free_percpu(nhge->stats); nexthop_put(nhge->nh); + list_add(&nhge->nh_list, deferred_free); /* Removal of a NH from a resilient group is notified through * bucket notifications. @@ -2083,6 +2084,7 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, struct nl_info *nlinfo) { struct nh_grp_entry *nhge, *tmp; + LIST_HEAD(deferred_free); /* If there is nothing to do, let's avoid the costly call to * synchronize_net() @@ -2091,10 +2093,16 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, return; list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) - remove_nh_grp_entry(net, nhge, nlinfo); + remove_nh_grp_entry(net, nhge, nlinfo, &deferred_free); /* make sure all see the newly published array before releasing rtnl */ synchronize_net(); + + /* Now safe to free percpu stats — all RCU readers have finished */ + list_for_each_entry_safe(nhge, tmp, &deferred_free, nh_list) { + list_del(&nhge->nh_list); + free_percpu(nhge->stats); + } } static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 061751aabc8e..fc3affd9c801 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -378,9 +378,14 @@ static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk, tcp_parse_options(net, skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { - tsoff = secure_tcp_ts_off(net, - ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr); + union tcp_seq_and_ts_off st; + + st = secure_tcp_seq_and_ts_off(net, + ip_hdr(skb)->daddr, + ip_hdr(skb)->saddr, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); + tsoff = st.ts_off; tcp_opt.rcv_tsecr -= tsoff; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 643763bc2142..5654cc9c8a0b 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -486,7 +486,8 @@ static void proc_fib_multipath_hash_set_seed(struct net *net, u32 user_seed) proc_fib_multipath_hash_rand_seed), }; - WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed, new); + WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.user_seed, new.user_seed); + WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.mp_seed, new.mp_seed); } static int proc_fib_multipath_hash_seed(const struct ctl_table *table, int write, @@ -500,7 +501,7 @@ static int proc_fib_multipath_hash_seed(const struct ctl_table *table, int write int ret; mphs = &net->ipv4.sysctl_fib_multipath_hash_seed; - user_seed = mphs->user_seed; + user_seed = READ_ONCE(mphs->user_seed); tmp = *table; tmp.data = &user_seed; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f84d9a45cc9d..202a4e57a218 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -244,6 +244,7 @@ #define pr_fmt(fmt) "TCP: " fmt #include <crypto/md5.h> +#include <crypto/utils.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> @@ -1446,7 +1447,7 @@ out_err: err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { - sk->sk_write_space(sk); + READ_ONCE(sk->sk_write_space)(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } if (binding) @@ -4181,7 +4182,7 @@ ao_parse: break; case TCP_NOTSENT_LOWAT: WRITE_ONCE(tp->notsent_lowat, val); - sk->sk_write_space(sk); + READ_ONCE(sk->sk_write_space)(sk); break; case TCP_INQ: if (val > 1 || val < 0) @@ -4970,7 +4971,7 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, tcp_v4_md5_hash_skb(newhash, key, NULL, skb); else tp->af_specific->calc_md5_hash(newhash, key, NULL, skb); - if (memcmp(hash_location, newhash, 16) != 0) { + if (crypto_memneq(hash_location, newhash, 16)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); trace_tcp_hash_md5_mismatch(sk, skb); return SKB_DROP_REASON_TCP_MD5FAILURE; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 4980caddb0fc..a97cdf3e6af4 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -10,6 +10,7 @@ #define pr_fmt(fmt) "TCP: " fmt #include <crypto/hash.h> +#include <crypto/utils.h> #include <linux/inetdevice.h> #include <linux/tcp.h> @@ -922,7 +923,7 @@ tcp_ao_verify_hash(const struct sock *sk, const struct sk_buff *skb, /* XXX: make it per-AF callback? */ tcp_ao_hash_skb(family, hash_buf, key, sk, skb, traffic_key, (phash - (u8 *)th), sne); - if (memcmp(phash, hash_buf, maclen)) { + if (crypto_memneq(phash, hash_buf, maclen)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); atomic64_inc(&info->counters.pkt_bad); atomic64_inc(&key->pkt_bad); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index c449a044895e..813d2e498c93 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -725,7 +725,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) WRITE_ONCE(sk->sk_prot->unhash, psock->saved_unhash); tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space); } else { - sk->sk_write_space = psock->saved_write_space; + WRITE_ONCE(sk->sk_write_space, psock->saved_write_space); /* Pairs with lockless read in sk_clone_lock() */ sock_replace_proto(sk, psock->sk_proto); } diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index d83efd91f461..7935702e394b 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -509,7 +509,7 @@ next_chunk: if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) goto next_normal; - if (r->id.idiag_sport != htons(sk->sk_num) && + if (r->id.idiag_sport != htons(READ_ONCE(sk->sk_num)) && r->id.idiag_sport) goto next_normal; if (r->id.idiag_dport != sk->sk_dport && diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 41c57efd125c..cba89733d121 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5374,25 +5374,11 @@ static void tcp_ofo_queue(struct sock *sk) static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb); static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb); -/* Check if this incoming skb can be added to socket receive queues - * while satisfying sk->sk_rcvbuf limit. - * - * In theory we should use skb->truesize, but this can cause problems - * when applications use too small SO_RCVBUF values. - * When LRO / hw gro is used, the socket might have a high tp->scaling_ratio, - * allowing RWIN to be close to available space. - * Whenever the receive queue gets full, we can receive a small packet - * filling RWIN, but with a high skb->truesize, because most NIC use 4K page - * plus sk_buff metadata even when receiving less than 1500 bytes of payload. - * - * Note that we use skb->len to decide to accept or drop this packet, - * but sk->sk_rmem_alloc is the sum of all skb->truesize. - */ static bool tcp_can_ingest(const struct sock *sk, const struct sk_buff *skb) { unsigned int rmem = atomic_read(&sk->sk_rmem_alloc); - return rmem + skb->len <= sk->sk_rcvbuf; + return rmem <= sk->sk_rcvbuf; } static int tcp_try_rmem_schedule(struct sock *sk, const struct sk_buff *skb, @@ -5425,7 +5411,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP); - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); tcp_drop_reason(sk, skb, SKB_DROP_REASON_PROTO_MEM); return; } @@ -5635,7 +5621,7 @@ err: void tcp_data_ready(struct sock *sk) { if (tcp_epollin_ready(sk, sk->sk_rcvlowat) || sock_flag(sk, SOCK_DONE)) - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); } static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) @@ -5691,7 +5677,7 @@ queue_and_out: inet_csk(sk)->icsk_ack.pending |= (ICSK_ACK_NOMEM | ICSK_ACK_NOW); inet_csk_schedule_ack(sk); - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); if (skb_queue_len(&sk->sk_receive_queue) && skb->len) { reason = SKB_DROP_REASON_PROTO_MEM; @@ -6114,7 +6100,9 @@ static void tcp_new_space(struct sock *sk) tp->snd_cwnd_stamp = tcp_jiffies32; } - INDIRECT_CALL_1(sk->sk_write_space, sk_stream_write_space, sk); + INDIRECT_CALL_1(READ_ONCE(sk->sk_write_space), + sk_stream_write_space, + sk); } /* Caller made space either from: @@ -6325,7 +6313,7 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t BUG(); WRITE_ONCE(tp->urg_data, TCP_URG_VALID | tmp); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); } } } @@ -7658,6 +7646,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct sock *fastopen_sk = NULL; + union tcp_seq_and_ts_off st; struct request_sock *req; bool want_cookie = false; struct dst_entry *dst; @@ -7727,9 +7716,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (!dst) goto drop_and_free; + if (tmp_opt.tstamp_ok || (!want_cookie && !isn)) + st = af_ops->init_seq_and_ts_off(net, skb); + if (tmp_opt.tstamp_ok) { tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst); - tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb); + tcp_rsk(req)->ts_off = st.ts_off; } if (!want_cookie && !isn) { int max_syn_backlog = READ_ONCE(net->ipv4.sysctl_max_syn_backlog); @@ -7751,7 +7743,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop_and_release; } - isn = af_ops->init_seq(skb); + isn = st.seq; } tcp_ecn_create_request(req, skb, sk, dst); @@ -7792,7 +7784,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, sock_put(fastopen_sk); goto drop_and_free; } - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); bh_unlock_sock(fastopen_sk); sock_put(fastopen_sk); } else { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d53d39be291a..c7b2463c2e25 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -88,6 +88,7 @@ #include <linux/skbuff_ref.h> #include <crypto/md5.h> +#include <crypto/utils.h> #include <trace/events/tcp.h> @@ -104,17 +105,14 @@ static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = { static DEFINE_MUTEX(tcp_exit_batch_mutex); -static u32 tcp_v4_init_seq(const struct sk_buff *skb) +static union tcp_seq_and_ts_off +tcp_v4_init_seq_and_ts_off(const struct net *net, const struct sk_buff *skb) { - return secure_tcp_seq(ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr, - tcp_hdr(skb)->dest, - tcp_hdr(skb)->source); -} - -static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb) -{ - return secure_tcp_ts_off(net, ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); + return secure_tcp_seq_and_ts_off(net, + ip_hdr(skb)->daddr, + ip_hdr(skb)->saddr, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); } int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) @@ -326,15 +324,16 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len rt = NULL; if (likely(!tp->repair)) { + union tcp_seq_and_ts_off st; + + st = secure_tcp_seq_and_ts_off(net, + inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, + usin->sin_port); if (!tp->write_seq) - WRITE_ONCE(tp->write_seq, - secure_tcp_seq(inet->inet_saddr, - inet->inet_daddr, - inet->inet_sport, - usin->sin_port)); - WRITE_ONCE(tp->tsoffset, - secure_tcp_ts_off(net, inet->inet_saddr, - inet->inet_daddr)); + WRITE_ONCE(tp->write_seq, st.seq); + WRITE_ONCE(tp->tsoffset, st.ts_off); } atomic_set(&inet->inet_id, get_random_u16()); @@ -839,7 +838,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, goto out; tcp_v4_md5_hash_skb(newhash, key, NULL, skb); - if (memcmp(md5_hash_location, newhash, 16) != 0) + if (crypto_memneq(md5_hash_location, newhash, 16)) goto out; } @@ -1676,8 +1675,7 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .cookie_init_seq = cookie_v4_init_sequence, #endif .route_req = tcp_v4_route_req, - .init_seq = tcp_v4_init_seq, - .init_ts_off = tcp_v4_init_ts_off, + .init_seq_and_ts_off = tcp_v4_init_seq_and_ts_off, .send_synack = tcp_v4_send_synack, }; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index d9c5a43bd281..dafb63b923d0 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -1004,7 +1004,7 @@ enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child, reason = tcp_rcv_state_process(child, skb); /* Wakeup parent, send SIGIO */ if (state == TCP_SYN_RECV && child->sk_state != state) - parent->sk_data_ready(parent); + READ_ONCE(parent->sk_data_ready)(parent); } else { /* Alas, it is possible again, because we do lookup * in main socket hash table and lock on listening diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 6c6b68a66dcd..b60fad393e18 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1787,7 +1787,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) * using prepare_to_wait_exclusive(). */ while (nb) { - INDIRECT_CALL_1(sk->sk_data_ready, + INDIRECT_CALL_1(READ_ONCE(sk->sk_data_ready), sock_def_readable, sk); nb--; } @@ -2287,7 +2287,6 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4) udp_sk(sk)->udp_port_hash); hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); nhslot2 = udp_hashslot2(udptable, newhash); - udp_sk(sk)->udp_portaddr_hash = newhash; if (hslot2 != nhslot2 || rcu_access_pointer(sk->sk_reuseport_cb)) { @@ -2321,19 +2320,25 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4) if (udp_hashed4(sk)) { spin_lock_bh(&hslot->lock); - udp_rehash4(udptable, sk, newhash4); - if (hslot2 != nhslot2) { - spin_lock(&hslot2->lock); - udp_hash4_dec(hslot2); - spin_unlock(&hslot2->lock); - - spin_lock(&nhslot2->lock); - udp_hash4_inc(nhslot2); - spin_unlock(&nhslot2->lock); + if (inet_rcv_saddr_any(sk)) { + udp_unhash4(udptable, sk); + } else { + udp_rehash4(udptable, sk, newhash4); + if (hslot2 != nhslot2) { + spin_lock(&hslot2->lock); + udp_hash4_dec(hslot2); + spin_unlock(&hslot2->lock); + + spin_lock(&nhslot2->lock); + udp_hash4_inc(nhslot2); + spin_unlock(&nhslot2->lock); + } } spin_unlock_bh(&hslot->lock); } + + udp_sk(sk)->udp_portaddr_hash = newhash; } } EXPORT_IPV6_MOD(udp_lib_rehash); diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index 91233e37cd97..779a3a03762f 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -158,7 +158,7 @@ int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6; if (restore) { - sk->sk_write_space = psock->saved_write_space; + WRITE_ONCE(sk->sk_write_space, psock->saved_write_space); sock_replace_proto(sk, psock->sk_proto); return 0; } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 23cc9b4cb2f1..4cbd45b68088 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -86,8 +86,6 @@ struct ipv6_params ipv6_defaults = { .autoconf = 1, }; -static int disable_ipv6_mod; - module_param_named(disable, disable_ipv6_mod, int, 0444); MODULE_PARM_DESC(disable, "Disable IPv6 module such that it is non-functional"); @@ -97,12 +95,6 @@ MODULE_PARM_DESC(disable_ipv6, "Disable IPv6 on all interfaces"); module_param_named(autoconf, ipv6_defaults.autoconf, int, 0444); MODULE_PARM_DESC(autoconf, "Enable IPv6 address autoconfiguration on all interfaces"); -bool ipv6_mod_enabled(void) -{ - return disable_ipv6_mod == 0; -} -EXPORT_SYMBOL_GPL(ipv6_mod_enabled); - static struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) { const int offset = sk->sk_prot->ipv6_pinfo_offset; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 5e1da088d8e1..182d38e6d6d8 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -95,7 +95,8 @@ static inline int compute_score(struct sock *sk, const struct net *net, { int score = -1; - if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum && + if (net_eq(sock_net(sk), net) && + READ_ONCE(inet_sk(sk)->inet_num) == hnum && sk->sk_family == PF_INET6) { if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return -1; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 85df25c36409..08cd86f49bf9 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1063,7 +1063,8 @@ static struct net_device *ip6_rt_get_dev_rcu(const struct fib6_result *res) */ if (netif_is_l3_slave(dev) && !rt6_need_strict(&res->f6i->fib6_dst.addr)) - dev = l3mdev_master_dev_rcu(dev); + dev = l3mdev_master_dev_rcu(dev) ? : + dev_net(dev)->loopback_dev; else if (!netif_is_l3_master(dev)) dev = dev_net(dev)->loopback_dev; /* last case is netif_is_l3_master(dev) is true in which @@ -3582,7 +3583,6 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, netdevice_tracker *dev_tracker = &fib6_nh->fib_nh_dev_tracker; struct net_device *dev = NULL; struct inet6_dev *idev = NULL; - int addr_type; int err; fib6_nh->fib_nh_family = AF_INET6; @@ -3624,11 +3624,10 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, fib6_nh->fib_nh_weight = 1; - /* We cannot add true routes via loopback here, - * they would result in kernel looping; promote them to reject routes + /* Reset the nexthop device to the loopback device in case of reject + * routes. */ - addr_type = ipv6_addr_type(&cfg->fc_dst); - if (fib6_is_reject(cfg->fc_flags, dev, addr_type)) { + if (cfg->fc_flags & RTF_REJECT) { /* hold loopback dev/idev if we haven't done so. */ if (dev != net->loopback_dev) { if (dev) { diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 7e007f013ec8..4f6f0d751d6c 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -151,9 +151,14 @@ static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk, tcp_parse_options(net, skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { - tsoff = secure_tcpv6_ts_off(net, - ipv6_hdr(skb)->daddr.s6_addr32, - ipv6_hdr(skb)->saddr.s6_addr32); + union tcp_seq_and_ts_off st; + + st = secure_tcpv6_seq_and_ts_off(net, + ipv6_hdr(skb)->daddr.s6_addr32, + ipv6_hdr(skb)->saddr.s6_addr32, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); + tsoff = st.ts_off; tcp_opt.rcv_tsecr -= tsoff; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index e46a0efae012..bb09d5ccf599 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -68,6 +68,7 @@ #include <linux/seq_file.h> #include <crypto/md5.h> +#include <crypto/utils.h> #include <trace/events/tcp.h> @@ -104,18 +105,14 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) } } -static u32 tcp_v6_init_seq(const struct sk_buff *skb) +static union tcp_seq_and_ts_off +tcp_v6_init_seq_and_ts_off(const struct net *net, const struct sk_buff *skb) { - return secure_tcpv6_seq(ipv6_hdr(skb)->daddr.s6_addr32, - ipv6_hdr(skb)->saddr.s6_addr32, - tcp_hdr(skb)->dest, - tcp_hdr(skb)->source); -} - -static u32 tcp_v6_init_ts_off(const struct net *net, const struct sk_buff *skb) -{ - return secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32, - ipv6_hdr(skb)->saddr.s6_addr32); + return secure_tcpv6_seq_and_ts_off(net, + ipv6_hdr(skb)->daddr.s6_addr32, + ipv6_hdr(skb)->saddr.s6_addr32, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); } static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, @@ -319,14 +316,16 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr_unsized *uaddr, sk_set_txhash(sk); if (likely(!tp->repair)) { + union tcp_seq_and_ts_off st; + + st = secure_tcpv6_seq_and_ts_off(net, + np->saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, + inet->inet_sport, + inet->inet_dport); if (!tp->write_seq) - WRITE_ONCE(tp->write_seq, - secure_tcpv6_seq(np->saddr.s6_addr32, - sk->sk_v6_daddr.s6_addr32, - inet->inet_sport, - inet->inet_dport)); - tp->tsoffset = secure_tcpv6_ts_off(net, np->saddr.s6_addr32, - sk->sk_v6_daddr.s6_addr32); + WRITE_ONCE(tp->write_seq, st.seq); + tp->tsoffset = st.ts_off; } if (tcp_fastopen_defer_connect(sk, &err)) @@ -816,8 +815,7 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .cookie_init_seq = cookie_v6_init_sequence, #endif .route_req = tcp_v6_route_req, - .init_seq = tcp_v6_init_seq, - .init_ts_off = tcp_v6_init_ts_off, + .init_seq_and_ts_off = tcp_v6_init_seq_and_ts_off, .send_synack = tcp_v6_send_synack, }; @@ -1048,7 +1046,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb, key.type = TCP_KEY_MD5; tcp_v6_md5_hash_skb(newhash, key.md5_key, NULL, skb); - if (memcmp(md5_hash_location, newhash, 16) != 0) + if (crypto_memneq(md5_hash_location, newhash, 16)) goto out; } #endif diff --git a/net/mac80211/eht.c b/net/mac80211/eht.c index 75096b2195d2..078e1e23d8d1 100644 --- a/net/mac80211/eht.c +++ b/net/mac80211/eht.c @@ -154,6 +154,7 @@ void ieee80211_rx_eml_op_mode_notif(struct ieee80211_sub_if_data *sdata, u8 *ptr = mgmt->u.action.u.eml_omn.variable; struct ieee80211_eml_params eml_params = { .link_id = status->link_id, + .control = control, }; struct sta_info *sta; int opt_len = 0; diff --git a/net/mctp/route.c b/net/mctp/route.c index 0381377ab760..59ad60b88563 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -359,6 +359,7 @@ static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev) { struct mctp_sk_key *key; struct mctp_flow *flow; + unsigned long flags; flow = skb_ext_find(skb, SKB_EXT_MCTP); if (!flow) @@ -366,12 +367,14 @@ static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev) key = flow->key; - if (key->dev) { + spin_lock_irqsave(&key->lock, flags); + + if (!key->dev) + mctp_dev_set_key(dev, key); + else WARN_ON(key->dev != dev); - return; - } - mctp_dev_set_key(dev, key); + spin_unlock_irqrestore(&key->lock, flags); } #else static void mctp_skb_set_flow(struct sk_buff *skb, struct mctp_sk_key *key) {} diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 7298836469b3..57a456690406 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -212,9 +212,24 @@ void mptcp_pm_send_ack(struct mptcp_sock *msk, spin_lock_bh(&msk->pm.lock); } -void mptcp_pm_addr_send_ack(struct mptcp_sock *msk) +static bool subflow_in_rm_list(const struct mptcp_subflow_context *subflow, + const struct mptcp_rm_list *rm_list) +{ + u8 i, id = subflow_get_local_id(subflow); + + for (i = 0; i < rm_list->nr; i++) { + if (rm_list->ids[i] == id) + return true; + } + + return false; +} + +static void +mptcp_pm_addr_send_ack_avoid_list(struct mptcp_sock *msk, + const struct mptcp_rm_list *rm_list) { - struct mptcp_subflow_context *subflow, *alt = NULL; + struct mptcp_subflow_context *subflow, *stale = NULL, *same_id = NULL; msk_owned_by_me(msk); lockdep_assert_held(&msk->pm.lock); @@ -224,19 +239,35 @@ void mptcp_pm_addr_send_ack(struct mptcp_sock *msk) return; mptcp_for_each_subflow(msk, subflow) { - if (__mptcp_subflow_active(subflow)) { - if (!subflow->stale) { - mptcp_pm_send_ack(msk, subflow, false, false); - return; - } + if (!__mptcp_subflow_active(subflow)) + continue; - if (!alt) - alt = subflow; + if (unlikely(subflow->stale)) { + if (!stale) + stale = subflow; + } else if (unlikely(rm_list && + subflow_in_rm_list(subflow, rm_list))) { + if (!same_id) + same_id = subflow; + } else { + goto send_ack; } } - if (alt) - mptcp_pm_send_ack(msk, alt, false, false); + if (same_id) + subflow = same_id; + else if (stale) + subflow = stale; + else + return; + +send_ack: + mptcp_pm_send_ack(msk, subflow, false, false); +} + +void mptcp_pm_addr_send_ack(struct mptcp_sock *msk) +{ + mptcp_pm_addr_send_ack_avoid_list(msk, NULL); } int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk, @@ -470,7 +501,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_ msk->pm.rm_list_tx = *rm_list; rm_addr |= BIT(MPTCP_RM_ADDR_SIGNAL); WRITE_ONCE(msk->pm.addr_signal, rm_addr); - mptcp_pm_addr_send_ack(msk); + mptcp_pm_addr_send_ack_avoid_list(msk, rm_list); return 0; } diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index b5316a6c7d1b..b2b9df43960e 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -418,6 +418,15 @@ subflow: } exit: + /* If an endpoint has both the signal and subflow flags, but it is not + * possible to create subflows -- the 'while' loop body above never + * executed -- then still mark the endp as used, which is somehow the + * case. This avoids issues later when removing the endpoint and calling + * __mark_subflow_endp_available(), which expects the increment here. + */ + if (signal_and_subflow && local.addr.id != msk->mpc_endpoint_id) + msk->pm.local_addr_used++; + mptcp_pm_nl_check_work_pending(msk); } diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c index 62fb1031763d..040a31557201 100644 --- a/net/ncsi/ncsi-aen.c +++ b/net/ncsi/ncsi-aen.c @@ -224,7 +224,8 @@ int ncsi_aen_handler(struct ncsi_dev_priv *ndp, struct sk_buff *skb) if (!nah) { netdev_warn(ndp->ndev.dev, "Invalid AEN (0x%x) received\n", h->type); - return -ENOENT; + ret = -ENOENT; + goto out; } ret = ncsi_validate_aen_pkt(h, nah->payload); diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 271ec6c3929e..fbd84bc8026a 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -1176,8 +1176,10 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev, /* Find the NCSI device */ nd = ncsi_find_dev(orig_dev); ndp = nd ? TO_NCSI_DEV_PRIV(nd) : NULL; - if (!ndp) - return -ENODEV; + if (!ndp) { + ret = -ENODEV; + goto err_free_skb; + } /* Check if it is AEN packet */ hdr = (struct ncsi_pkt_hdr *)skb_network_header(skb); @@ -1199,7 +1201,8 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev, if (!nrh) { netdev_err(nd->dev, "Received unrecognized packet (0x%x)\n", hdr->type); - return -ENOENT; + ret = -ENOENT; + goto err_free_skb; } /* Associate with the request */ @@ -1207,7 +1210,8 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev, nr = &ndp->requests[hdr->id]; if (!nr->used) { spin_unlock_irqrestore(&ndp->lock, flags); - return -ENODEV; + ret = -ENODEV; + goto err_free_skb; } nr->rsp = skb; @@ -1261,4 +1265,8 @@ out_netlink: out: ncsi_free_request(nr); return ret; + +err_free_skb: + kfree_skb(skb); + return ret; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fd7f7e4e2a43..dacec5f8a11c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -829,10 +829,14 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, nft_set_elem_change_active(ctx->net, set, ext); nft_setelem_data_deactivate(ctx->net, set, catchall->elem); - break; } } +/* Use NFT_ITER_UPDATE iterator even if this may be called from the preparation + * phase, the set clone might already exist from a previous command, or it might + * be a set that is going away and does not require a clone. The netns and + * netlink release paths also need to work on the live set. + */ static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter iter = { @@ -5868,7 +5872,6 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx, nft_clear(ctx->net, ext); nft_setelem_data_activate(ctx->net, set, catchall->elem); - break; } } @@ -7170,6 +7173,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, struct nft_data_desc desc; enum nft_registers dreg; struct nft_trans *trans; + bool set_full = false; u64 expiration; u64 timeout; int err, i; @@ -7461,10 +7465,18 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) goto err_elem_free; + if (!(flags & NFT_SET_ELEM_CATCHALL)) { + unsigned int max = nft_set_maxsize(set), nelems; + + nelems = atomic_inc_return(&set->nelems); + if (nelems > max) + set_full = true; + } + trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set); if (trans == NULL) { err = -ENOMEM; - goto err_elem_free; + goto err_set_size; } ext->genmask = nft_genmask_cur(ctx->net); @@ -7516,7 +7528,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, ue->priv = elem_priv; nft_trans_commit_list_add_elem(ctx->net, trans); - goto err_elem_free; + goto err_set_size; } } } @@ -7534,23 +7546,16 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, goto err_element_clash; } - if (!(flags & NFT_SET_ELEM_CATCHALL)) { - unsigned int max = nft_set_maxsize(set); - - if (!atomic_add_unless(&set->nelems, 1, max)) { - err = -ENFILE; - goto err_set_full; - } - } - nft_trans_container_elem(trans)->elems[0].priv = elem.priv; nft_trans_commit_list_add_elem(ctx->net, trans); - return 0; -err_set_full: - nft_setelem_remove(ctx->net, set, elem.priv); + return set_full ? -ENFILE : 0; + err_element_clash: kfree(trans); +err_set_size: + if (!(flags & NFT_SET_ELEM_CATCHALL)) + atomic_dec(&set->nelems); err_elem_free: nf_tables_set_elem_destroy(ctx, set, elem.priv); err_parse_data: @@ -7901,9 +7906,12 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx, static int nft_set_flush(struct nft_ctx *ctx, struct nft_set *set, u8 genmask) { + /* The set backend might need to clone the set, do it now from the + * preparation phase, use NFT_ITER_UPDATE_CLONE iterator type. + */ struct nft_set_iter iter = { .genmask = genmask, - .type = NFT_ITER_UPDATE, + .type = NFT_ITER_UPDATE_CLONE, .fn = nft_setelem_flush, }; @@ -9678,7 +9686,7 @@ static int nft_flowtable_event(unsigned long event, struct net_device *dev, break; case NETDEV_REGISTER: /* NOP if not matching or already registered */ - if (!match || (changename && ops)) + if (!match || ops) continue; ops = kzalloc_obj(struct nf_hook_ops, @@ -10483,11 +10491,6 @@ static void nft_trans_gc_queue_work(struct nft_trans_gc *trans) schedule_work(&trans_gc_work); } -static int nft_trans_gc_space(struct nft_trans_gc *trans) -{ - return NFT_TRANS_GC_BATCHCOUNT - trans->count; -} - struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, unsigned int gc_seq, gfp_t gfp) { diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index d658b1478fa0..d545fa459455 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -601,10 +601,10 @@ restart: goto out; } } - } - if (cb->args[1]) { - cb->args[1] = 0; - goto restart; + if (cb->args[1]) { + cb->args[1] = 0; + goto restart; + } } out: rcu_read_unlock(); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 7f5248b5f1ee..47f7f62906e2 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1546,8 +1546,10 @@ static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info, if (entry->state.pf == PF_BRIDGE) { err = nfqa_parse_bridge(entry, nfqa); - if (err < 0) + if (err < 0) { + nfqnl_reinject(entry, NF_DROP); return err; + } } if (nfqa[NFQA_PAYLOAD]) { diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index b16185e9a6dd..041426e3bdbf 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -344,7 +344,7 @@ static int nft_netdev_event(unsigned long event, struct net_device *dev, break; case NETDEV_REGISTER: /* NOP if not matching or already registered */ - if (!match || (changename && ops)) + if (!match || ops) continue; ops = kmemdup(&basechain->ops, diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 739b992bde59..b0e571c8e3f3 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -374,6 +374,7 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, { switch (iter->type) { case NFT_ITER_UPDATE: + case NFT_ITER_UPDATE_CLONE: /* only relevant for netlink dumps which use READ type */ WARN_ON_ONCE(iter->skip != 0); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 7ef4b44471d3..7fd24e0cc428 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1640,6 +1640,7 @@ static void pipapo_drop(struct nft_pipapo_match *m, int i; nft_pipapo_for_each_field(f, i, m) { + bool last = i == m->field_count - 1; int g; for (g = 0; g < f->groups; g++) { @@ -1659,7 +1660,7 @@ static void pipapo_drop(struct nft_pipapo_match *m, } pipapo_unmap(f->mt, f->rules, rulemap[i].to, rulemap[i].n, - rulemap[i + 1].n, i == m->field_count - 1); + last ? 0 : rulemap[i + 1].n, last); if (pipapo_resize(f, f->rules, f->rules - rulemap[i].n)) { /* We can ignore this, a failure to shrink tables down * doesn't make tables invalid. @@ -1680,11 +1681,11 @@ static void nft_pipapo_gc_deactivate(struct net *net, struct nft_set *set, } /** - * pipapo_gc() - Drop expired entries from set, destroy start and end elements + * pipapo_gc_scan() - Drop expired entries from set and link them to gc list * @set: nftables API set representation * @m: Matching data */ -static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) +static void pipapo_gc_scan(struct nft_set *set, struct nft_pipapo_match *m) { struct nft_pipapo *priv = nft_set_priv(set); struct net *net = read_pnet(&set->net); @@ -1697,6 +1698,8 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) if (!gc) return; + list_add(&gc->list, &priv->gc_head); + while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; const struct nft_pipapo_field *f; @@ -1724,9 +1727,13 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) * NFT_SET_ELEM_DEAD_BIT. */ if (__nft_set_elem_expired(&e->ext, tstamp)) { - gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); - if (!gc) - return; + if (!nft_trans_gc_space(gc)) { + gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); + if (!gc) + return; + + list_add(&gc->list, &priv->gc_head); + } nft_pipapo_gc_deactivate(net, set, e); pipapo_drop(m, rulemap); @@ -1740,10 +1747,30 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) } } - gc = nft_trans_gc_catchall_sync(gc); + priv->last_gc = jiffies; +} + +/** + * pipapo_gc_queue() - Free expired elements + * @set: nftables API set representation + */ +static void pipapo_gc_queue(struct nft_set *set) +{ + struct nft_pipapo *priv = nft_set_priv(set); + struct nft_trans_gc *gc, *next; + + /* always do a catchall cycle: */ + gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); if (gc) { + gc = nft_trans_gc_catchall_sync(gc); + if (gc) + nft_trans_gc_queue_sync_done(gc); + } + + /* always purge queued gc elements. */ + list_for_each_entry_safe(gc, next, &priv->gc_head, list) { + list_del(&gc->list); nft_trans_gc_queue_sync_done(gc); - priv->last_gc = jiffies; } } @@ -1797,6 +1824,10 @@ static void pipapo_reclaim_match(struct rcu_head *rcu) * * We also need to create a new working copy for subsequent insertions and * deletions. + * + * After the live copy has been replaced by the clone, we can safely queue + * expired elements that have been collected by pipapo_gc_scan() for + * memory reclaim. */ static void nft_pipapo_commit(struct nft_set *set) { @@ -1807,7 +1838,7 @@ static void nft_pipapo_commit(struct nft_set *set) return; if (time_after_eq(jiffies, priv->last_gc + nft_set_gc_interval(set))) - pipapo_gc(set, priv->clone); + pipapo_gc_scan(set, priv->clone); old = rcu_replace_pointer(priv->match, priv->clone, nft_pipapo_transaction_mutex_held(set)); @@ -1815,6 +1846,8 @@ static void nft_pipapo_commit(struct nft_set *set) if (old) call_rcu(&old->rcu, pipapo_reclaim_match); + + pipapo_gc_queue(set); } static void nft_pipapo_abort(const struct nft_set *set) @@ -2144,13 +2177,20 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_pipapo_match *m; switch (iter->type) { - case NFT_ITER_UPDATE: + case NFT_ITER_UPDATE_CLONE: m = pipapo_maybe_clone(set); if (!m) { iter->err = -ENOMEM; return; } - + nft_pipapo_do_walk(ctx, set, m, iter); + break; + case NFT_ITER_UPDATE: + if (priv->clone) + m = priv->clone; + else + m = rcu_dereference_protected(priv->match, + nft_pipapo_transaction_mutex_held(set)); nft_pipapo_do_walk(ctx, set, m, iter); break; case NFT_ITER_READ: @@ -2272,6 +2312,7 @@ static int nft_pipapo_init(const struct nft_set *set, f->mt = NULL; } + INIT_LIST_HEAD(&priv->gc_head); rcu_assign_pointer(priv->match, m); return 0; @@ -2321,6 +2362,8 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m; + WARN_ON_ONCE(!list_empty(&priv->gc_head)); + m = rcu_dereference_protected(priv->match, true); if (priv->clone) { diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index eaab422aa56a..9aee9a9eaeb7 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -156,12 +156,14 @@ struct nft_pipapo_match { * @clone: Copy where pending insertions and deletions are kept * @width: Total bytes to be matched for one packet, including padding * @last_gc: Timestamp of last garbage collection run, jiffies + * @gc_head: list of nft_trans_gc to queue up for mem reclaim */ struct nft_pipapo { struct nft_pipapo_match __rcu *match; struct nft_pipapo_match *clone; int width; unsigned long last_gc; + struct list_head gc_head; }; struct nft_pipapo_elem; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 3f02e4478216..ee3d4f5b9ff7 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -861,13 +861,15 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, struct nft_rbtree *priv = nft_set_priv(set); switch (iter->type) { - case NFT_ITER_UPDATE: - lockdep_assert_held(&nft_pernet(ctx->net)->commit_mutex); - + case NFT_ITER_UPDATE_CLONE: if (nft_array_may_resize(set) < 0) { iter->err = -ENOMEM; break; } + fallthrough; + case NFT_ITER_UPDATE: + lockdep_assert_held(&nft_pernet(ctx->net)->commit_mutex); + nft_rbtree_do_walk(ctx, set, iter); break; case NFT_ITER_READ: diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 5d93e225d0f8..517106165ad2 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -318,6 +318,12 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par) info->timer = __idletimer_tg_find_by_label(info->label); if (info->timer) { + if (info->timer->timer_type & XT_IDLETIMER_ALARM) { + pr_debug("Adding/Replacing rule with same label and different timer type is not allowed\n"); + mutex_unlock(&list_mutex); + return -EINVAL; + } + info->timer->refcnt++; mod_timer(&info->timer->timer, secs_to_jiffies(info->timeout) + jiffies); diff --git a/net/netfilter/xt_dccp.c b/net/netfilter/xt_dccp.c index e5a13ecbe67a..037ab93e25d0 100644 --- a/net/netfilter/xt_dccp.c +++ b/net/netfilter/xt_dccp.c @@ -62,10 +62,10 @@ dccp_find_option(u_int8_t option, return true; } - if (op[i] < 2) + if (op[i] < 2 || i == optlen - 1) i++; else - i += op[i+1]?:1; + i += op[i + 1] ? : 1; } spin_unlock_bh(&dccp_buflock); diff --git a/net/netfilter/xt_tcpudp.c b/net/netfilter/xt_tcpudp.c index e8991130a3de..f76cf18f1a24 100644 --- a/net/netfilter/xt_tcpudp.c +++ b/net/netfilter/xt_tcpudp.c @@ -59,8 +59,10 @@ tcp_find_option(u_int8_t option, for (i = 0; i < optlen; ) { if (op[i] == option) return !invert; - if (op[i] < 2) i++; - else i += op[i+1]?:1; + if (op[i] < 2 || i == optlen - 1) + i++; + else + i += op[i + 1] ? : 1; } return invert; diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index 3670bb33732e..7cb1e6aaae90 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -707,8 +707,10 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target, int rc; data_exch = kzalloc_obj(*data_exch); - if (!data_exch) + if (!data_exch) { + kfree_skb(skb); return -ENOMEM; + } data_exch->cb = cb; data_exch->cb_context = cb_context; @@ -731,8 +733,10 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target, data_exch); exit: - if (rc) + if (rc) { + kfree_skb(skb); kfree(data_exch); + } return rc; } diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 6e9b76e2cc56..43d871525dbc 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -567,6 +567,10 @@ static int nci_close_device(struct nci_dev *ndev) flush_workqueue(ndev->cmd_wq); timer_delete_sync(&ndev->cmd_timer); timer_delete_sync(&ndev->data_timer); + if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags)) + nci_data_exchange_complete(ndev, NULL, + ndev->cur_conn_id, + -ENODEV); mutex_unlock(&ndev->req_lock); return 0; } @@ -598,6 +602,11 @@ static int nci_close_device(struct nci_dev *ndev) flush_workqueue(ndev->cmd_wq); timer_delete_sync(&ndev->cmd_timer); + timer_delete_sync(&ndev->data_timer); + + if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags)) + nci_data_exchange_complete(ndev, NULL, ndev->cur_conn_id, + -ENODEV); /* Clear flags except NCI_UNREG */ ndev->flags &= BIT(NCI_UNREG); @@ -1035,18 +1044,23 @@ static int nci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target, struct nci_conn_info *conn_info; conn_info = ndev->rf_conn_info; - if (!conn_info) + if (!conn_info) { + kfree_skb(skb); return -EPROTO; + } pr_debug("target_idx %d, len %d\n", target->idx, skb->len); if (!ndev->target_active_prot) { pr_err("unable to exchange data, no active target\n"); + kfree_skb(skb); return -EINVAL; } - if (test_and_set_bit(NCI_DATA_EXCHANGE, &ndev->flags)) + if (test_and_set_bit(NCI_DATA_EXCHANGE, &ndev->flags)) { + kfree_skb(skb); return -EBUSY; + } /* store cb and context to be used on receiving data */ conn_info->data_exchange_cb = cb; @@ -1482,10 +1496,20 @@ static bool nci_valid_size(struct sk_buff *skb) unsigned int hdr_size = NCI_CTRL_HDR_SIZE; if (skb->len < hdr_size || - !nci_plen(skb->data) || skb->len < hdr_size + nci_plen(skb->data)) { return false; } + + if (!nci_plen(skb->data)) { + /* Allow zero length in proprietary notifications (0x20 - 0x3F). */ + if (nci_opcode_oid(nci_opcode(skb->data)) >= 0x20 && + nci_mt(skb->data) == NCI_MT_NTF_PKT) + return true; + + /* Disallow zero length otherwise. */ + return false; + } + return true; } diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index 78f4131af3cf..5f98c73db5af 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -33,7 +33,8 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb, conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id); if (!conn_info) { kfree_skb(skb); - goto exit; + clear_bit(NCI_DATA_EXCHANGE, &ndev->flags); + return; } cb = conn_info->data_exchange_cb; @@ -45,6 +46,12 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb, timer_delete_sync(&ndev->data_timer); clear_bit(NCI_DATA_EXCHANGE_TO, &ndev->flags); + /* Mark the exchange as done before calling the callback. + * The callback (e.g. rawsock_data_exchange_complete) may + * want to immediately queue another data exchange. + */ + clear_bit(NCI_DATA_EXCHANGE, &ndev->flags); + if (cb) { /* forward skb to nfc core */ cb(cb_context, skb, err); @@ -54,9 +61,6 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb, /* no waiting callback, free skb */ kfree_skb(skb); } - -exit: - clear_bit(NCI_DATA_EXCHANGE, &ndev->flags); } /* ----------------- NCI TX Data ----------------- */ diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index b049022399ae..f7d7a599fade 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -67,6 +67,17 @@ static int rawsock_release(struct socket *sock) if (sock->type == SOCK_RAW) nfc_sock_unlink(&raw_sk_list, sk); + if (sk->sk_state == TCP_ESTABLISHED) { + /* Prevent rawsock_tx_work from starting new transmits and + * wait for any in-progress work to finish. This must happen + * before the socket is orphaned to avoid a race where + * rawsock_tx_work runs after the NCI device has been freed. + */ + sk->sk_shutdown |= SEND_SHUTDOWN; + cancel_work_sync(&nfc_rawsock(sk)->tx_work); + rawsock_write_queue_purge(sk); + } + sock_orphan(sk); sock_put(sk); diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 04f310255692..654e23d13e3d 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -490,18 +490,24 @@ bool rds_tcp_tune(struct socket *sock) struct rds_tcp_net *rtn; tcp_sock_set_nodelay(sock->sk); - lock_sock(sk); /* TCP timer functions might access net namespace even after * a process which created this net namespace terminated. */ if (!sk->sk_net_refcnt) { - if (!maybe_get_net(net)) { - release_sock(sk); + if (!maybe_get_net(net)) return false; - } + /* + * sk_net_refcnt_upgrade() must be called before lock_sock() + * because it does a GFP_KERNEL allocation, which can trigger + * fs_reclaim and create a circular lock dependency with the + * socket lock. The fields it modifies (sk_net_refcnt, + * ns_tracker) are not accessed by any concurrent code path + * at this point. + */ sk_net_refcnt_upgrade(sk); put_net(net); } + lock_sock(sk); rtn = net_generic(net, rds_tcp_netid); if (rtn->sndbuf_size > 0) { sk->sk_sndbuf = rtn->sndbuf_size; diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 0c2c68c4b07e..0f90272ac254 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -267,12 +267,13 @@ static int rxrpc_listen(struct socket *sock, int backlog) * Lookup or create a remote transport endpoint record for the specified * address. * - * Return: The peer record found with a reference, %NULL if no record is found - * or a negative error code if the address is invalid or unsupported. + * Return: The peer record found with a reference or a negative error code if + * the address is invalid or unsupported. */ struct rxrpc_peer *rxrpc_kernel_lookup_peer(struct socket *sock, struct sockaddr_rxrpc *srx, gfp_t gfp) { + struct rxrpc_peer *peer; struct rxrpc_sock *rx = rxrpc_sk(sock->sk); int ret; @@ -280,7 +281,8 @@ struct rxrpc_peer *rxrpc_kernel_lookup_peer(struct socket *sock, if (ret < 0) return ERR_PTR(ret); - return rxrpc_lookup_peer(rx->local, srx, gfp); + peer = rxrpc_lookup_peer(rx->local, srx, gfp); + return peer ?: ERR_PTR(-ENOMEM); } EXPORT_SYMBOL(rxrpc_kernel_lookup_peer); diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index bd51522c7953..7d5e50c921a0 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1360,6 +1360,12 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, return -EINVAL; } + if (bind && !(flags & TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT)) { + NL_SET_ERR_MSG_MOD(extack, + "Attaching ct to a non ingress/clsact qdisc is unsupported"); + return -EOPNOTSUPP; + } + err = nla_parse_nested(tb, TCA_CT_MAX, nla, ct_policy, extack); if (err < 0) return err; diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index 686eaed81b81..fdbfcaa3e2ab 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -32,9 +32,12 @@ static ktime_t gate_get_time(struct tcf_gate *gact) return KTIME_MAX; } -static void gate_get_start_time(struct tcf_gate *gact, ktime_t *start) +static void tcf_gate_params_free_rcu(struct rcu_head *head); + +static void gate_get_start_time(struct tcf_gate *gact, + const struct tcf_gate_params *param, + ktime_t *start) { - struct tcf_gate_params *param = &gact->param; ktime_t now, base, cycle; u64 n; @@ -69,12 +72,14 @@ static enum hrtimer_restart gate_timer_func(struct hrtimer *timer) { struct tcf_gate *gact = container_of(timer, struct tcf_gate, hitimer); - struct tcf_gate_params *p = &gact->param; struct tcfg_gate_entry *next; + struct tcf_gate_params *p; ktime_t close_time, now; spin_lock(&gact->tcf_lock); + p = rcu_dereference_protected(gact->param, + lockdep_is_held(&gact->tcf_lock)); next = gact->next_entry; /* cycle start, clear pending bit, clear total octets */ @@ -225,6 +230,35 @@ static void release_entry_list(struct list_head *entries) } } +static int tcf_gate_copy_entries(struct tcf_gate_params *dst, + const struct tcf_gate_params *src, + struct netlink_ext_ack *extack) +{ + struct tcfg_gate_entry *entry; + int i = 0; + + list_for_each_entry(entry, &src->entries, list) { + struct tcfg_gate_entry *new; + + new = kzalloc(sizeof(*new), GFP_ATOMIC); + if (!new) { + NL_SET_ERR_MSG(extack, "Not enough memory for entry"); + return -ENOMEM; + } + + new->index = entry->index; + new->gate_state = entry->gate_state; + new->interval = entry->interval; + new->ipv = entry->ipv; + new->maxoctets = entry->maxoctets; + list_add_tail(&new->list, &dst->entries); + i++; + } + + dst->num_entries = i; + return 0; +} + static int parse_gate_list(struct nlattr *list_attr, struct tcf_gate_params *sched, struct netlink_ext_ack *extack) @@ -270,24 +304,44 @@ release_list: return err; } -static void gate_setup_timer(struct tcf_gate *gact, u64 basetime, - enum tk_offsets tko, s32 clockid, - bool do_init) +static bool gate_timer_needs_cancel(u64 basetime, u64 old_basetime, + enum tk_offsets tko, + enum tk_offsets old_tko, + s32 clockid, s32 old_clockid) { - if (!do_init) { - if (basetime == gact->param.tcfg_basetime && - tko == gact->tk_offset && - clockid == gact->param.tcfg_clockid) - return; + return basetime != old_basetime || + clockid != old_clockid || + tko != old_tko; +} - spin_unlock_bh(&gact->tcf_lock); - hrtimer_cancel(&gact->hitimer); - spin_lock_bh(&gact->tcf_lock); +static int gate_clock_resolve(s32 clockid, enum tk_offsets *tko, + struct netlink_ext_ack *extack) +{ + switch (clockid) { + case CLOCK_REALTIME: + *tko = TK_OFFS_REAL; + return 0; + case CLOCK_MONOTONIC: + *tko = TK_OFFS_MAX; + return 0; + case CLOCK_BOOTTIME: + *tko = TK_OFFS_BOOT; + return 0; + case CLOCK_TAI: + *tko = TK_OFFS_TAI; + return 0; + default: + NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); + return -EINVAL; } - gact->param.tcfg_basetime = basetime; - gact->param.tcfg_clockid = clockid; - gact->tk_offset = tko; - hrtimer_setup(&gact->hitimer, gate_timer_func, clockid, HRTIMER_MODE_ABS_SOFT); +} + +static void gate_setup_timer(struct tcf_gate *gact, s32 clockid, + enum tk_offsets tko) +{ + WRITE_ONCE(gact->tk_offset, tko); + hrtimer_setup(&gact->hitimer, gate_timer_func, clockid, + HRTIMER_MODE_ABS_SOFT); } static int tcf_gate_init(struct net *net, struct nlattr *nla, @@ -296,15 +350,22 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_gate_ops.net_id); - enum tk_offsets tk_offset = TK_OFFS_TAI; + u64 cycletime = 0, basetime = 0, cycletime_ext = 0; + struct tcf_gate_params *p = NULL, *old_p = NULL; + enum tk_offsets old_tk_offset = TK_OFFS_TAI; + const struct tcf_gate_params *cur_p = NULL; bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_GATE_MAX + 1]; + enum tk_offsets tko = TK_OFFS_TAI; struct tcf_chain *goto_ch = NULL; - u64 cycletime = 0, basetime = 0; - struct tcf_gate_params *p; + s32 timer_clockid = CLOCK_TAI; + bool use_old_entries = false; + s32 old_clockid = CLOCK_TAI; + bool need_cancel = false; s32 clockid = CLOCK_TAI; struct tcf_gate *gact; struct tc_gate *parm; + u64 old_basetime = 0; int ret = 0, err; u32 gflags = 0; s32 prio = -1; @@ -321,26 +382,8 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (!tb[TCA_GATE_PARMS]) return -EINVAL; - if (tb[TCA_GATE_CLOCKID]) { + if (tb[TCA_GATE_CLOCKID]) clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]); - switch (clockid) { - case CLOCK_REALTIME: - tk_offset = TK_OFFS_REAL; - break; - case CLOCK_MONOTONIC: - tk_offset = TK_OFFS_MAX; - break; - case CLOCK_BOOTTIME: - tk_offset = TK_OFFS_BOOT; - break; - case CLOCK_TAI: - tk_offset = TK_OFFS_TAI; - break; - default: - NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); - return -EINVAL; - } - } parm = nla_data(tb[TCA_GATE_PARMS]); index = parm->index; @@ -366,6 +409,60 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, return -EEXIST; } + gact = to_gate(*a); + + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) { + err = -ENOMEM; + goto chain_put; + } + INIT_LIST_HEAD(&p->entries); + + use_old_entries = !tb[TCA_GATE_ENTRY_LIST]; + if (!use_old_entries) { + err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack); + if (err < 0) + goto err_free; + use_old_entries = !err; + } + + if (ret == ACT_P_CREATED && use_old_entries) { + NL_SET_ERR_MSG(extack, "The entry list is empty"); + err = -EINVAL; + goto err_free; + } + + if (ret != ACT_P_CREATED) { + rcu_read_lock(); + cur_p = rcu_dereference(gact->param); + + old_basetime = cur_p->tcfg_basetime; + old_clockid = cur_p->tcfg_clockid; + old_tk_offset = READ_ONCE(gact->tk_offset); + + basetime = old_basetime; + cycletime_ext = cur_p->tcfg_cycletime_ext; + prio = cur_p->tcfg_priority; + gflags = cur_p->tcfg_flags; + + if (!tb[TCA_GATE_CLOCKID]) + clockid = old_clockid; + + err = 0; + if (use_old_entries) { + err = tcf_gate_copy_entries(p, cur_p, extack); + if (!err && !tb[TCA_GATE_CYCLE_TIME]) + cycletime = cur_p->tcfg_cycletime; + } + rcu_read_unlock(); + if (err) + goto err_free; + } + if (tb[TCA_GATE_PRIORITY]) prio = nla_get_s32(tb[TCA_GATE_PRIORITY]); @@ -375,25 +472,26 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (tb[TCA_GATE_FLAGS]) gflags = nla_get_u32(tb[TCA_GATE_FLAGS]); - gact = to_gate(*a); - if (ret == ACT_P_CREATED) - INIT_LIST_HEAD(&gact->param.entries); + if (tb[TCA_GATE_CYCLE_TIME]) + cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]); - err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); - if (err < 0) - goto release_idr; + if (tb[TCA_GATE_CYCLE_TIME_EXT]) + cycletime_ext = nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]); - spin_lock_bh(&gact->tcf_lock); - p = &gact->param; + err = gate_clock_resolve(clockid, &tko, extack); + if (err) + goto err_free; + timer_clockid = clockid; - if (tb[TCA_GATE_CYCLE_TIME]) - cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]); + need_cancel = ret != ACT_P_CREATED && + gate_timer_needs_cancel(basetime, old_basetime, + tko, old_tk_offset, + timer_clockid, old_clockid); - if (tb[TCA_GATE_ENTRY_LIST]) { - err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack); - if (err < 0) - goto chain_put; - } + if (need_cancel) + hrtimer_cancel(&gact->hitimer); + + spin_lock_bh(&gact->tcf_lock); if (!cycletime) { struct tcfg_gate_entry *entry; @@ -402,22 +500,20 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, list_for_each_entry(entry, &p->entries, list) cycle = ktime_add_ns(cycle, entry->interval); cycletime = cycle; - if (!cycletime) { - err = -EINVAL; - goto chain_put; - } } p->tcfg_cycletime = cycletime; + p->tcfg_cycletime_ext = cycletime_ext; - if (tb[TCA_GATE_CYCLE_TIME_EXT]) - p->tcfg_cycletime_ext = - nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]); - - gate_setup_timer(gact, basetime, tk_offset, clockid, - ret == ACT_P_CREATED); + if (need_cancel || ret == ACT_P_CREATED) + gate_setup_timer(gact, timer_clockid, tko); p->tcfg_priority = prio; p->tcfg_flags = gflags; - gate_get_start_time(gact, &start); + p->tcfg_basetime = basetime; + p->tcfg_clockid = timer_clockid; + gate_get_start_time(gact, p, &start); + + old_p = rcu_replace_pointer(gact->param, p, + lockdep_is_held(&gact->tcf_lock)); gact->current_close_time = start; gact->current_gate_status = GATE_ACT_GATE_OPEN | GATE_ACT_PENDING; @@ -434,11 +530,15 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); + if (old_p) + call_rcu(&old_p->rcu, tcf_gate_params_free_rcu); + return ret; +err_free: + release_entry_list(&p->entries); + kfree(p); chain_put: - spin_unlock_bh(&gact->tcf_lock); - if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: @@ -446,21 +546,29 @@ release_idr: * without taking tcf_lock. */ if (ret == ACT_P_CREATED) - gate_setup_timer(gact, gact->param.tcfg_basetime, - gact->tk_offset, gact->param.tcfg_clockid, - true); + gate_setup_timer(gact, timer_clockid, tko); + tcf_idr_release(*a, bind); return err; } +static void tcf_gate_params_free_rcu(struct rcu_head *head) +{ + struct tcf_gate_params *p = container_of(head, struct tcf_gate_params, rcu); + + release_entry_list(&p->entries); + kfree(p); +} + static void tcf_gate_cleanup(struct tc_action *a) { struct tcf_gate *gact = to_gate(a); struct tcf_gate_params *p; - p = &gact->param; hrtimer_cancel(&gact->hitimer); - release_entry_list(&p->entries); + p = rcu_dereference_protected(gact->param, 1); + if (p) + call_rcu(&p->rcu, tcf_gate_params_free_rcu); } static int dumping_entry(struct sk_buff *skb, @@ -509,10 +617,9 @@ static int tcf_gate_dump(struct sk_buff *skb, struct tc_action *a, struct nlattr *entry_list; struct tcf_t t; - spin_lock_bh(&gact->tcf_lock); - opt.action = gact->tcf_action; - - p = &gact->param; + rcu_read_lock(); + opt.action = READ_ONCE(gact->tcf_action); + p = rcu_dereference(gact->param); if (nla_put(skb, TCA_GATE_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -552,12 +659,12 @@ static int tcf_gate_dump(struct sk_buff *skb, struct tc_action *a, tcf_tm_dump(&t, &gact->tcf_tm); if (nla_put_64bit(skb, TCA_GATE_TM, sizeof(t), &t, TCA_GATE_PAD)) goto nla_put_failure; - spin_unlock_bh(&gact->tcf_lock); + rcu_read_unlock(); return skb->len; nla_put_failure: - spin_unlock_bh(&gact->tcf_lock); + rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 79df81d12894..d5e8a91bb4eb 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -293,8 +293,8 @@ static int load_metaops_and_vet(u32 metaid, void *val, int len, bool rtnl_held) /* called when adding new meta information */ static int __add_metainfo(const struct tcf_meta_ops *ops, - struct tcf_ife_info *ife, u32 metaid, void *metaval, - int len, bool atomic, bool exists) + struct tcf_ife_params *p, u32 metaid, void *metaval, + int len, bool atomic) { struct tcf_meta_info *mi = NULL; int ret = 0; @@ -313,45 +313,40 @@ static int __add_metainfo(const struct tcf_meta_ops *ops, } } - if (exists) - spin_lock_bh(&ife->tcf_lock); - list_add_tail(&mi->metalist, &ife->metalist); - if (exists) - spin_unlock_bh(&ife->tcf_lock); + list_add_tail(&mi->metalist, &p->metalist); return ret; } static int add_metainfo_and_get_ops(const struct tcf_meta_ops *ops, - struct tcf_ife_info *ife, u32 metaid, - bool exists) + struct tcf_ife_params *p, u32 metaid) { int ret; if (!try_module_get(ops->owner)) return -ENOENT; - ret = __add_metainfo(ops, ife, metaid, NULL, 0, true, exists); + ret = __add_metainfo(ops, p, metaid, NULL, 0, true); if (ret) module_put(ops->owner); return ret; } -static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, - int len, bool exists) +static int add_metainfo(struct tcf_ife_params *p, u32 metaid, void *metaval, + int len) { const struct tcf_meta_ops *ops = find_ife_oplist(metaid); int ret; if (!ops) return -ENOENT; - ret = __add_metainfo(ops, ife, metaid, metaval, len, false, exists); + ret = __add_metainfo(ops, p, metaid, metaval, len, false); if (ret) /*put back what find_ife_oplist took */ module_put(ops->owner); return ret; } -static int use_all_metadata(struct tcf_ife_info *ife, bool exists) +static int use_all_metadata(struct tcf_ife_params *p) { struct tcf_meta_ops *o; int rc = 0; @@ -359,7 +354,7 @@ static int use_all_metadata(struct tcf_ife_info *ife, bool exists) read_lock(&ife_mod_lock); list_for_each_entry(o, &ifeoplist, list) { - rc = add_metainfo_and_get_ops(o, ife, o->metaid, exists); + rc = add_metainfo_and_get_ops(o, p, o->metaid); if (rc == 0) installed += 1; } @@ -371,7 +366,7 @@ static int use_all_metadata(struct tcf_ife_info *ife, bool exists) return -EINVAL; } -static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife) +static int dump_metalist(struct sk_buff *skb, struct tcf_ife_params *p) { struct tcf_meta_info *e; struct nlattr *nest; @@ -379,14 +374,14 @@ static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife) int total_encoded = 0; /*can only happen on decode */ - if (list_empty(&ife->metalist)) + if (list_empty(&p->metalist)) return 0; nest = nla_nest_start_noflag(skb, TCA_IFE_METALST); if (!nest) goto out_nlmsg_trim; - list_for_each_entry(e, &ife->metalist, metalist) { + list_for_each_entry(e, &p->metalist, metalist) { if (!e->ops->get(skb, e)) total_encoded += 1; } @@ -403,13 +398,11 @@ out_nlmsg_trim: return -1; } -/* under ife->tcf_lock */ -static void _tcf_ife_cleanup(struct tc_action *a) +static void __tcf_ife_cleanup(struct tcf_ife_params *p) { - struct tcf_ife_info *ife = to_ife(a); struct tcf_meta_info *e, *n; - list_for_each_entry_safe(e, n, &ife->metalist, metalist) { + list_for_each_entry_safe(e, n, &p->metalist, metalist) { list_del(&e->metalist); if (e->metaval) { if (e->ops->release) @@ -422,18 +415,23 @@ static void _tcf_ife_cleanup(struct tc_action *a) } } +static void tcf_ife_cleanup_params(struct rcu_head *head) +{ + struct tcf_ife_params *p = container_of(head, struct tcf_ife_params, + rcu); + + __tcf_ife_cleanup(p); + kfree(p); +} + static void tcf_ife_cleanup(struct tc_action *a) { struct tcf_ife_info *ife = to_ife(a); struct tcf_ife_params *p; - spin_lock_bh(&ife->tcf_lock); - _tcf_ife_cleanup(a); - spin_unlock_bh(&ife->tcf_lock); - p = rcu_dereference_protected(ife->params, 1); if (p) - kfree_rcu(p, rcu); + call_rcu(&p->rcu, tcf_ife_cleanup_params); } static int load_metalist(struct nlattr **tb, bool rtnl_held) @@ -455,8 +453,7 @@ static int load_metalist(struct nlattr **tb, bool rtnl_held) return 0; } -static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, - bool exists, bool rtnl_held) +static int populate_metalist(struct tcf_ife_params *p, struct nlattr **tb) { int len = 0; int rc = 0; @@ -468,7 +465,7 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, val = nla_data(tb[i]); len = nla_len(tb[i]); - rc = add_metainfo(ife, i, val, len, exists); + rc = add_metainfo(p, i, val, len); if (rc) return rc; } @@ -523,6 +520,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, p = kzalloc_obj(*p); if (!p) return -ENOMEM; + INIT_LIST_HEAD(&p->metalist); if (tb[TCA_IFE_METALST]) { err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, @@ -567,8 +565,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } ife = to_ife(*a); - if (ret == ACT_P_CREATED) - INIT_LIST_HEAD(&ife->metalist); err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) @@ -600,8 +596,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } if (tb[TCA_IFE_METALST]) { - err = populate_metalist(ife, tb2, exists, - !(flags & TCA_ACT_FLAGS_NO_RTNL)); + err = populate_metalist(p, tb2); if (err) goto metadata_parse_err; } else { @@ -610,7 +605,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, * as we can. You better have at least one else we are * going to bail out */ - err = use_all_metadata(ife, exists); + err = use_all_metadata(p); if (err) goto metadata_parse_err; } @@ -626,13 +621,14 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); if (p) - kfree_rcu(p, rcu); + call_rcu(&p->rcu, tcf_ife_cleanup_params); return ret; metadata_parse_err: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: + __tcf_ife_cleanup(p); kfree(p); tcf_idr_release(*a, bind); return err; @@ -679,7 +675,7 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, if (nla_put(skb, TCA_IFE_TYPE, 2, &p->eth_type)) goto nla_put_failure; - if (dump_metalist(skb, ife)) { + if (dump_metalist(skb, p)) { /*ignore failure to dump metalist */ pr_info("Failed to dump metalist\n"); } @@ -693,13 +689,13 @@ nla_put_failure: return -1; } -static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, +static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_params *p, u16 metaid, u16 mlen, void *mdata) { struct tcf_meta_info *e; /* XXX: use hash to speed up */ - list_for_each_entry(e, &ife->metalist, metalist) { + list_for_each_entry_rcu(e, &p->metalist, metalist) { if (metaid == e->metaid) { if (e->ops) { /* We check for decode presence already */ @@ -716,10 +712,13 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, { struct tcf_ife_info *ife = to_ife(a); int action = ife->tcf_action; + struct tcf_ife_params *p; u8 *ifehdr_end; u8 *tlv_data; u16 metalen; + p = rcu_dereference_bh(ife->params); + bstats_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); @@ -745,7 +744,7 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, return TC_ACT_SHOT; } - if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) { + if (find_decode_metaid(skb, p, mtype, dlen, curr_data)) { /* abuse overlimits to count when we receive metadata * but dont have an ops for it */ @@ -769,12 +768,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, /*XXX: check if we can do this at install time instead of current * send data path **/ -static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife) +static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_params *p) { - struct tcf_meta_info *e, *n; + struct tcf_meta_info *e; int tot_run_sz = 0, run_sz = 0; - list_for_each_entry_safe(e, n, &ife->metalist, metalist) { + list_for_each_entry_rcu(e, &p->metalist, metalist) { if (e->ops->check_presence) { run_sz = e->ops->check_presence(skb, e); tot_run_sz += run_sz; @@ -795,7 +794,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA where ORIGDATA = original ethernet header ... */ - u16 metalen = ife_get_sz(skb, ife); + u16 metalen = ife_get_sz(skb, p); int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN; unsigned int skboff = 0; int new_len = skb->len + hdrm; @@ -833,25 +832,21 @@ drop: if (!ife_meta) goto drop; - spin_lock(&ife->tcf_lock); - /* XXX: we dont have a clever way of telling encode to * not repeat some of the computations that are done by * ops->presence_check... */ - list_for_each_entry(e, &ife->metalist, metalist) { + list_for_each_entry_rcu(e, &p->metalist, metalist) { if (e->ops->encode) { err = e->ops->encode(skb, (void *)(ife_meta + skboff), e); } if (err < 0) { /* too corrupt to keep around if overwritten */ - spin_unlock(&ife->tcf_lock); goto drop; } skboff += err; } - spin_unlock(&ife->tcf_lock); oethh = (struct ethhdr *)skb->data; if (!is_zero_ether_addr(p->eth_src)) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 343309e9009b..4829c27446e3 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2228,6 +2228,11 @@ static bool is_qdisc_ingress(__u32 classid) return (TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_INGRESS)); } +static bool is_ingress_or_clsact(struct tcf_block *block, struct Qdisc *q) +{ + return tcf_block_shared(block) || (q && !!(q->flags & TCQ_F_INGRESS)); +} + static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { @@ -2420,6 +2425,8 @@ replay: flags |= TCA_ACT_FLAGS_NO_RTNL; if (is_qdisc_ingress(parent)) flags |= TCA_ACT_FLAGS_AT_INGRESS; + if (is_ingress_or_clsact(block, q)) + flags |= TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT; err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh, flags, extack); if (err == 0) { diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index a01f14b1c216..9efe23f8371b 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -391,8 +391,8 @@ static const u32 inv_sqrt_cache[REC_INV_SQRT_CACHE] = { 1239850263, 1191209601, 1147878294, 1108955788 }; -static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, - u64 target_ns, u64 rtt_est_ns); +static void cake_configure_rates(struct Qdisc *sch, u64 rate, bool rate_adjust); + /* http://en.wikipedia.org/wiki/Methods_of_computing_square_roots * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2) * @@ -2013,7 +2013,8 @@ static struct sk_buff *cake_dequeue(struct Qdisc *sch) u64 delay; u32 len; - if (q->config->is_shared && now - q->last_checked_active >= q->config->sync_time) { + if (q->config->is_shared && q->rate_ns && + now - q->last_checked_active >= q->config->sync_time) { struct net_device *dev = qdisc_dev(sch); struct cake_sched_data *other_priv; u64 new_rate = q->config->rate_bps; @@ -2039,12 +2040,9 @@ static struct sk_buff *cake_dequeue(struct Qdisc *sch) if (num_active_qs > 1) new_rate = div64_u64(q->config->rate_bps, num_active_qs); - /* mtu = 0 is used to only update the rate and not mess with cobalt params */ - cake_set_rate(b, new_rate, 0, 0, 0); + cake_configure_rates(sch, new_rate, true); q->last_checked_active = now; q->active_queues = num_active_qs; - q->rate_ns = b->tin_rate_ns; - q->rate_shft = b->tin_rate_shft; } begin: @@ -2361,12 +2359,10 @@ static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, b->cparams.p_dec = 1 << 20; /* 1/4096 */ } -static int cake_config_besteffort(struct Qdisc *sch) +static int cake_config_besteffort(struct Qdisc *sch, u64 rate, u32 mtu) { struct cake_sched_data *q = qdisc_priv(sch); struct cake_tin_data *b = &q->tins[0]; - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; q->tin_cnt = 1; @@ -2380,12 +2376,10 @@ static int cake_config_besteffort(struct Qdisc *sch) return 0; } -static int cake_config_precedence(struct Qdisc *sch) +static int cake_config_precedence(struct Qdisc *sch, u64 rate, u32 mtu) { /* convert high-level (user visible) parameters into internal format */ struct cake_sched_data *q = qdisc_priv(sch); - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; u32 quantum = 256; u32 i; @@ -2456,7 +2450,7 @@ static int cake_config_precedence(struct Qdisc *sch) * Total 12 traffic classes. */ -static int cake_config_diffserv8(struct Qdisc *sch) +static int cake_config_diffserv8(struct Qdisc *sch, u64 rate, u32 mtu) { /* Pruned list of traffic classes for typical applications: * @@ -2473,8 +2467,6 @@ static int cake_config_diffserv8(struct Qdisc *sch) */ struct cake_sched_data *q = qdisc_priv(sch); - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; u32 quantum = 256; u32 i; @@ -2504,7 +2496,7 @@ static int cake_config_diffserv8(struct Qdisc *sch) return 0; } -static int cake_config_diffserv4(struct Qdisc *sch) +static int cake_config_diffserv4(struct Qdisc *sch, u64 rate, u32 mtu) { /* Further pruned list of traffic classes for four-class system: * @@ -2517,8 +2509,6 @@ static int cake_config_diffserv4(struct Qdisc *sch) */ struct cake_sched_data *q = qdisc_priv(sch); - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; u32 quantum = 1024; q->tin_cnt = 4; @@ -2546,7 +2536,7 @@ static int cake_config_diffserv4(struct Qdisc *sch) return 0; } -static int cake_config_diffserv3(struct Qdisc *sch) +static int cake_config_diffserv3(struct Qdisc *sch, u64 rate, u32 mtu) { /* Simplified Diffserv structure with 3 tins. * Latency Sensitive (CS7, CS6, EF, VA, TOS4) @@ -2554,8 +2544,6 @@ static int cake_config_diffserv3(struct Qdisc *sch) * Low Priority (LE, CS1) */ struct cake_sched_data *q = qdisc_priv(sch); - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; u32 quantum = 1024; q->tin_cnt = 3; @@ -2580,32 +2568,33 @@ static int cake_config_diffserv3(struct Qdisc *sch) return 0; } -static void cake_reconfigure(struct Qdisc *sch) +static void cake_configure_rates(struct Qdisc *sch, u64 rate, bool rate_adjust) { + u32 mtu = likely(rate_adjust) ? 0 : psched_mtu(qdisc_dev(sch)); struct cake_sched_data *qd = qdisc_priv(sch); struct cake_sched_config *q = qd->config; int c, ft; switch (q->tin_mode) { case CAKE_DIFFSERV_BESTEFFORT: - ft = cake_config_besteffort(sch); + ft = cake_config_besteffort(sch, rate, mtu); break; case CAKE_DIFFSERV_PRECEDENCE: - ft = cake_config_precedence(sch); + ft = cake_config_precedence(sch, rate, mtu); break; case CAKE_DIFFSERV_DIFFSERV8: - ft = cake_config_diffserv8(sch); + ft = cake_config_diffserv8(sch, rate, mtu); break; case CAKE_DIFFSERV_DIFFSERV4: - ft = cake_config_diffserv4(sch); + ft = cake_config_diffserv4(sch, rate, mtu); break; case CAKE_DIFFSERV_DIFFSERV3: default: - ft = cake_config_diffserv3(sch); + ft = cake_config_diffserv3(sch, rate, mtu); break; } @@ -2616,6 +2605,14 @@ static void cake_reconfigure(struct Qdisc *sch) qd->rate_ns = qd->tins[ft].tin_rate_ns; qd->rate_shft = qd->tins[ft].tin_rate_shft; +} + +static void cake_reconfigure(struct Qdisc *sch) +{ + struct cake_sched_data *qd = qdisc_priv(sch); + struct cake_sched_config *q = qd->config; + + cake_configure_rates(sch, qd->config->rate_bps, false); if (q->buffer_config_limit) { qd->buffer_limit = q->buffer_config_limit; diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 306e046276d4..a4b07b661b77 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -115,12 +115,12 @@ static void ets_offload_change(struct Qdisc *sch) struct ets_sched *q = qdisc_priv(sch); struct tc_ets_qopt_offload qopt; unsigned int w_psum_prev = 0; - unsigned int q_psum = 0; - unsigned int q_sum = 0; unsigned int quantum; unsigned int w_psum; unsigned int weight; unsigned int i; + u64 q_psum = 0; + u64 q_sum = 0; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return; @@ -138,8 +138,12 @@ static void ets_offload_change(struct Qdisc *sch) for (i = 0; i < q->nbands; i++) { quantum = q->classes[i].quantum; - q_psum += quantum; - w_psum = quantum ? q_psum * 100 / q_sum : 0; + if (quantum) { + q_psum += quantum; + w_psum = div64_u64(q_psum * 100, q_sum); + } else { + w_psum = 0; + } weight = w_psum - w_psum_prev; w_psum_prev = w_psum; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 80235e85f844..05084c9af48e 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -827,6 +827,7 @@ static void fq_reset(struct Qdisc *sch) for (idx = 0; idx < FQ_BANDS; idx++) { q->band_flows[idx].new_flows.first = NULL; q->band_flows[idx].old_flows.first = NULL; + q->band_pkt_count[idx] = 0; } q->delayed = RB_ROOT; q->flows = 0; diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 6e4bdaa876ed..783300d8b019 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -315,6 +315,7 @@ restart: if (__netif_tx_trylock(slave_txq)) { unsigned int length = qdisc_pkt_len(skb); + skb->dev = slave; if (!netif_xmit_frozen_or_stopped(slave_txq) && netdev_start_xmit(skb, slave, slave_txq, false) == NETDEV_TX_OK) { diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index 005bfc766e22..3fd6629cb999 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -759,11 +759,7 @@ int net_shaper_nl_get_doit(struct sk_buff *skb, struct genl_info *info) if (ret) goto free_msg; - ret = genlmsg_reply(msg, info); - if (ret) - goto free_msg; - - return 0; + return genlmsg_reply(msg, info); free_msg: nlmsg_free(msg); @@ -1313,10 +1309,7 @@ int net_shaper_nl_cap_get_doit(struct sk_buff *skb, struct genl_info *info) if (ret) goto free_msg; - ret = genlmsg_reply(msg, info); - if (ret) - goto free_msg; - return 0; + return genlmsg_reply(msg, info); free_msg: nlmsg_free(msg); diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 15bbf953dfad..b51a162885bb 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1362,7 +1362,7 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed) needed += RPCRDMA_MAX_RECV_BATCH; if (atomic_inc_return(&ep->re_receiving) > 1) - goto out; + goto out_dec; /* fast path: all needed reps can be found on the free list */ wr = NULL; @@ -1385,7 +1385,7 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed) ++count; } if (!wr) - goto out; + goto out_dec; rc = ib_post_recv(ep->re_id->qp, wr, (const struct ib_recv_wr **)&bad_wr); @@ -1400,9 +1400,10 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed) --count; } } + +out_dec: if (atomic_dec_return(&ep->re_receiving) > 0) complete(&ep->re_done); - out: trace_xprtrdma_post_recvs(r_xprt, count); ep->re_receive_count += count; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 4c618c2b871d..9329919fb07f 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2233,6 +2233,8 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb, if (skb_queue_empty(&sk->sk_write_queue)) break; get_random_bytes(&delay, 2); + if (tsk->conn_timeout < 4) + tsk->conn_timeout = 4; delay %= (tsk->conn_timeout / 4); delay = msecs_to_jiffies(delay + 100); sk_reset_timer(sk, &sk->sk_timer, jiffies + delay); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3756a93dc63a..7eaa5b187fef 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1785,7 +1785,7 @@ restart: __skb_queue_tail(&other->sk_receive_queue, skb); spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); - other->sk_data_ready(other); + READ_ONCE(other->sk_data_ready)(other); sock_put(other); return 0; @@ -2278,7 +2278,7 @@ restart_locked: scm_stat_add(other, skb); skb_queue_tail(&other->sk_receive_queue, skb); unix_state_unlock(other); - other->sk_data_ready(other); + READ_ONCE(other->sk_data_ready)(other); sock_put(other); scm_destroy(&scm); return len; @@ -2351,7 +2351,7 @@ static int queue_oob(struct sock *sk, struct msghdr *msg, struct sock *other, sk_send_sigurg(other); unix_state_unlock(other); - other->sk_data_ready(other); + READ_ONCE(other->sk_data_ready)(other); return 0; out_unlock: @@ -2477,7 +2477,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); - other->sk_data_ready(other); + READ_ONCE(other->sk_data_ready)(other); sent += size; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 3b46bc635c43..6149f6a79897 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -167,26 +167,32 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) struct xdp_buff_xsk *pos, *tmp; struct list_head *xskb_list; u32 contd = 0; + u32 num_desc; int err; - if (frags) - contd = XDP_PKT_CONTD; + if (likely(!frags)) { + err = __xsk_rcv_zc(xs, xskb, len, contd); + if (err) + goto err; + return 0; + } - err = __xsk_rcv_zc(xs, xskb, len, contd); - if (err) + contd = XDP_PKT_CONTD; + num_desc = xdp_get_shared_info_from_buff(xdp)->nr_frags + 1; + if (xskq_prod_nb_free(xs->rx, num_desc) < num_desc) { + xs->rx_queue_full++; + err = -ENOBUFS; goto err; - if (likely(!frags)) - return 0; + } + __xsk_rcv_zc(xs, xskb, len, contd); xskb_list = &xskb->pool->xskb_list; list_for_each_entry_safe(pos, tmp, xskb_list, list_node) { if (list_is_singular(xskb_list)) contd = 0; len = pos->xdp.data_end - pos->xdp.data; - err = __xsk_rcv_zc(xs, pos, len, contd); - if (err) - goto err; - list_del(&pos->list_node); + __xsk_rcv_zc(xs, pos, len, contd); + list_del_init(&pos->list_node); } return 0; |