diff options
Diffstat (limited to 'net')
57 files changed, 584 insertions, 402 deletions
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 240ed70912d6..d78938e3e008 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -277,17 +277,23 @@ static u8 batadv_hop_penalty(u8 tq, const struct batadv_priv *bat_priv) * batadv_iv_ogm_aggr_packet() - checks if there is another OGM attached * @buff_pos: current position in the skb * @packet_len: total length of the skb - * @tvlv_len: tvlv length of the previously considered OGM + * @ogm_packet: potential OGM in buffer * * Return: true if there is enough space for another OGM, false otherwise. */ -static bool batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len, - __be16 tvlv_len) +static bool +batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len, + const struct batadv_ogm_packet *ogm_packet) { int next_buff_pos = 0; - next_buff_pos += buff_pos + BATADV_OGM_HLEN; - next_buff_pos += ntohs(tvlv_len); + /* check if there is enough space for the header */ + next_buff_pos += buff_pos + sizeof(*ogm_packet); + if (next_buff_pos > packet_len) + return false; + + /* check if there is enough space for the optional TVLV */ + next_buff_pos += ntohs(ogm_packet->tvlv_len); return (next_buff_pos <= packet_len) && (next_buff_pos <= BATADV_MAX_AGGREGATION_BYTES); @@ -315,7 +321,7 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet, /* adjust all flags and log packets */ while (batadv_iv_ogm_aggr_packet(buff_pos, forw_packet->packet_len, - batadv_ogm_packet->tvlv_len)) { + batadv_ogm_packet)) { /* we might have aggregated direct link packets with an * ordinary base packet */ @@ -1704,7 +1710,7 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb, /* unpack the aggregated packets and process them one by one */ while (batadv_iv_ogm_aggr_packet(ogm_offset, skb_headlen(skb), - ogm_packet->tvlv_len)) { + ogm_packet)) { batadv_iv_ogm_process(skb, ogm_offset, if_incoming); ogm_offset += BATADV_OGM_HLEN; diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index fad95ef64e01..bc06e3cdfa84 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -631,17 +631,23 @@ batadv_v_ogm_process_per_outif(struct batadv_priv *bat_priv, * batadv_v_ogm_aggr_packet() - checks if there is another OGM aggregated * @buff_pos: current position in the skb * @packet_len: total length of the skb - * @tvlv_len: tvlv length of the previously considered OGM + * @ogm2_packet: potential OGM2 in buffer * * Return: true if there is enough space for another OGM, false otherwise. */ -static bool batadv_v_ogm_aggr_packet(int buff_pos, int packet_len, - __be16 tvlv_len) +static bool +batadv_v_ogm_aggr_packet(int buff_pos, int packet_len, + const struct batadv_ogm2_packet *ogm2_packet) { int next_buff_pos = 0; - next_buff_pos += buff_pos + BATADV_OGM2_HLEN; - next_buff_pos += ntohs(tvlv_len); + /* check if there is enough space for the header */ + next_buff_pos += buff_pos + sizeof(*ogm2_packet); + if (next_buff_pos > packet_len) + return false; + + /* check if there is enough space for the optional TVLV */ + next_buff_pos += ntohs(ogm2_packet->tvlv_len); return (next_buff_pos <= packet_len) && (next_buff_pos <= BATADV_MAX_AGGREGATION_BYTES); @@ -818,7 +824,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb, ogm_packet = (struct batadv_ogm2_packet *)skb->data; while (batadv_v_ogm_aggr_packet(ogm_offset, skb_headlen(skb), - ogm_packet->tvlv_len)) { + ogm_packet)) { batadv_v_ogm_process(skb, ogm_offset, if_incoming); ogm_offset += BATADV_OGM2_HLEN; diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c index 1804e867f715..7c9e92b2f806 100644 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -53,7 +53,7 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr, goto err; br_vlan_get_proto(br_dev, &p_proto); - nft_reg_store16(dest, p_proto); + nft_reg_store16(dest, htons(p_proto)); return; } default: diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 2cf27da1baeb..849380a622ef 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -122,7 +122,7 @@ static void queue_process(struct work_struct *work) txq = netdev_get_tx_queue(dev, q_index); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (netif_xmit_frozen_or_stopped(txq) || - netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) { + !dev_xmit_complete(netpoll_start_xmit(skb, dev, txq))) { skb_queue_head(&npinfo->txq, skb); HARD_TX_UNLOCK(dev, txq); local_irq_restore(flags); @@ -335,7 +335,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, HARD_TX_UNLOCK(dev, txq); - if (status == NETDEV_TX_OK) + if (dev_xmit_complete(status)) break; } @@ -352,7 +352,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, } - if (status != NETDEV_TX_OK) { + if (!dev_xmit_complete(status)) { skb_queue_tail(&npinfo->txq, skb); schedule_delayed_work(&npinfo->tx_work,0); } diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 6ebbd799c4eb..67a1bc635a7b 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -28,6 +28,7 @@ * * RSV - VID[9]: * To be used for further expansion of SWITCH_ID or for other purposes. + * Must be transmitted as zero and ignored on receive. * * SWITCH_ID - VID[8:6]: * Index of switch within DSA tree. Must be between 0 and @@ -35,6 +36,7 @@ * * RSV - VID[5:4]: * To be used for further expansion of PORT or for other purposes. + * Must be transmitted as zero and ignored on receive. * * PORT - VID[3:0]: * Index of switch port. Must be between 0 and DSA_MAX_PORTS - 1. diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 77b485d60b9d..61082065b26a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -935,6 +935,22 @@ static int tcp_send_mss(struct sock *sk, int *size_goal, int flags) return mss_now; } +/* In some cases, both sendpage() and sendmsg() could have added + * an skb to the write queue, but failed adding payload on it. + * We need to remove it to consume less memory, but more + * importantly be able to generate EPOLLOUT for Edge Trigger epoll() + * users. + */ +static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb) +{ + if (skb && !skb->len) { + tcp_unlink_write_queue(skb, sk); + if (tcp_write_queue_empty(sk)) + tcp_chrono_stop(sk, TCP_CHRONO_BUSY); + sk_wmem_free_skb(sk, skb); + } +} + ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, size_t size, int flags) { @@ -1064,6 +1080,7 @@ out: return copied; do_error: + tcp_remove_empty_skb(sk, tcp_write_queue_tail(sk)); if (copied) goto out; out_err: @@ -1388,18 +1405,11 @@ out_nopush: sock_zerocopy_put(uarg); return copied + copied_syn; +do_error: + skb = tcp_write_queue_tail(sk); do_fault: - if (!skb->len) { - tcp_unlink_write_queue(skb, sk); - /* It is the one place in all of TCP, except connection - * reset, where we can be unlinking the send_head. - */ - if (tcp_write_queue_empty(sk)) - tcp_chrono_stop(sk, TCP_CHRONO_BUSY); - sk_wmem_free_skb(sk, skb); - } + tcp_remove_empty_skb(sk, skb); -do_error: if (copied + copied_syn) goto out; out_err: diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 979520e46e33..8a645f304e6c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2053,7 +2053,7 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) if (len <= skb->len) break; - if (unlikely(TCP_SKB_CB(skb)->eor)) + if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb)) return false; len -= skb->len; @@ -2170,6 +2170,7 @@ static int tcp_mtu_probe(struct sock *sk) * we need to propagate it to the new skb. */ TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor; + tcp_skb_collapse_tstamp(nskb, skb); tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); } else { diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 7f3f13c37916..eaa4c2cc2fbb 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -787,14 +787,15 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) if (pmc) { im->idev = pmc->idev; if (im->mca_sfmode == MCAST_INCLUDE) { - im->mca_tomb = pmc->mca_tomb; - im->mca_sources = pmc->mca_sources; + swap(im->mca_tomb, pmc->mca_tomb); + swap(im->mca_sources, pmc->mca_sources); for (psf = im->mca_sources; psf; psf = psf->sf_next) psf->sf_crcount = idev->mc_qrv; } else { im->mca_crcount = idev->mc_qrv; } in6_dev_put(pmc->idev); + ip6_mc_clear_src(pmc); kfree(pmc); } spin_unlock_bh(&im->mca_lock); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 3c1ab870fefe..768d14c9a716 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2447,11 +2447,13 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb, skb->protocol == cpu_to_be16(ETH_P_PREAUTH)) && sdata->control_port_over_nl80211)) { struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); - bool noencrypt = status->flag & RX_FLAG_DECRYPTED; + bool noencrypt = !(status->flag & RX_FLAG_DECRYPTED); cfg80211_rx_control_port(dev, skb, noencrypt); dev_kfree_skb(skb); } else { + memset(skb->cb, 0, sizeof(skb->cb)); + /* deliver to local stack */ if (rx->napi) napi_gro_receive(rx->napi, skb); @@ -2546,8 +2548,6 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) if (skb) { skb->protocol = eth_type_trans(skb, dev); - memset(skb->cb, 0, sizeof(skb->cb)); - ieee80211_deliver_skb_to_local_stack(skb, rx); } diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 0ecb3e289ef2..8d96738b7dfd 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -322,7 +322,7 @@ static int find_pattern(const char *data, size_t dlen, i++; } - pr_debug("Skipped up to `%c'!\n", skip); + pr_debug("Skipped up to 0x%hhx delimiter!\n", skip); *numoff = i; *numlen = getnum(data + i, dlen - i, cmd, term, numoff); diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index e0d392cb3075..0006503d2da9 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -1037,9 +1037,14 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) table[NF_SYSCTL_CT_COUNT].data = &net->ct.count; table[NF_SYSCTL_CT_CHECKSUM].data = &net->ct.sysctl_checksum; table[NF_SYSCTL_CT_LOG_INVALID].data = &net->ct.sysctl_log_invalid; + table[NF_SYSCTL_CT_ACCT].data = &net->ct.sysctl_acct; + table[NF_SYSCTL_CT_HELPER].data = &net->ct.sysctl_auto_assign_helper; #ifdef CONFIG_NF_CONNTRACK_EVENTS table[NF_SYSCTL_CT_EVENTS].data = &net->ct.sysctl_events; #endif +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + table[NF_SYSCTL_CT_TIMESTAMP].data = &net->ct.sysctl_tstamp; +#endif table[NF_SYSCTL_CT_PROTO_TIMEOUT_GENERIC].data = &nf_generic_pernet(net)->timeout; table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP].data = &nf_icmp_pernet(net)->timeout; table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6].data = &nf_icmpv6_pernet(net)->timeout; diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index d68c801dd614..b9e7dd6e60ce 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -228,7 +228,6 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, { skb_orphan(skb); skb_dst_set_noref(skb, dst); - skb->tstamp = 0; dst_output(state->net, state->sk, skb); return NF_STOLEN; } @@ -284,6 +283,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; iph = ip_hdr(skb); ip_decrease_ttl(iph); + skb->tstamp = 0; if (unlikely(dst_xfrm(&rt->dst))) { memset(skb->cb, 0, sizeof(struct inet_skb_parm)); @@ -512,6 +512,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; ip6h = ipv6_hdr(skb); ip6h->hop_limit--; + skb->tstamp = 0; if (unlikely(dst_xfrm(&rt->dst))) { memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index ead7c6022208..b92b22ce8abd 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -101,11 +101,9 @@ static int physdev_mt_check(const struct xt_mtchk_param *par) if (info->bitmask & (XT_PHYSDEV_OP_OUT | XT_PHYSDEV_OP_ISOUT) && (!(info->bitmask & XT_PHYSDEV_OP_BRIDGED) || info->invert & XT_PHYSDEV_OP_BRIDGED) && - par->hook_mask & ((1 << NF_INET_LOCAL_OUT) | - (1 << NF_INET_FORWARD) | (1 << NF_INET_POST_ROUTING))) { + par->hook_mask & (1 << NF_INET_LOCAL_OUT)) { pr_info_ratelimited("--physdev-out and --physdev-is-out only supported in the FORWARD and POSTROUTING chains with bridged traffic\n"); - if (par->hook_mask & (1 << NF_INET_LOCAL_OUT)) - return -EINVAL; + return -EINVAL; } if (!brnf_probed) { diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index d8da6477d6be..05249eb45082 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -525,6 +525,11 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, return -EPFNOSUPPORT; } + /* The key extracted from the fragment that completed this datagram + * likely didn't have an L4 header, so regenerate it. + */ + ovs_flow_key_update_l3l4(skb, key); + key->ip.frag = OVS_FRAG_TYPE_NONE; skb_clear_hash(skb); skb->ignore_df = 1; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index bc89e16e0505..9d81d2c7bf82 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -523,78 +523,15 @@ static int parse_nsh(struct sk_buff *skb, struct sw_flow_key *key) } /** - * key_extract - extracts a flow key from an Ethernet frame. + * key_extract_l3l4 - extracts L3/L4 header information. * @skb: sk_buff that contains the frame, with skb->data pointing to the - * Ethernet header + * L3 header * @key: output flow key * - * The caller must ensure that skb->len >= ETH_HLEN. - * - * Returns 0 if successful, otherwise a negative errno value. - * - * Initializes @skb header fields as follows: - * - * - skb->mac_header: the L2 header. - * - * - skb->network_header: just past the L2 header, or just past the - * VLAN header, to the first byte of the L2 payload. - * - * - skb->transport_header: If key->eth.type is ETH_P_IP or ETH_P_IPV6 - * on output, then just past the IP header, if one is present and - * of a correct length, otherwise the same as skb->network_header. - * For other key->eth.type values it is left untouched. - * - * - skb->protocol: the type of the data starting at skb->network_header. - * Equals to key->eth.type. */ -static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) +static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) { int error; - struct ethhdr *eth; - - /* Flags are always used as part of stats */ - key->tp.flags = 0; - - skb_reset_mac_header(skb); - - /* Link layer. */ - clear_vlan(key); - if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) { - if (unlikely(eth_type_vlan(skb->protocol))) - return -EINVAL; - - skb_reset_network_header(skb); - key->eth.type = skb->protocol; - } else { - eth = eth_hdr(skb); - ether_addr_copy(key->eth.src, eth->h_source); - ether_addr_copy(key->eth.dst, eth->h_dest); - - __skb_pull(skb, 2 * ETH_ALEN); - /* We are going to push all headers that we pull, so no need to - * update skb->csum here. - */ - - if (unlikely(parse_vlan(skb, key))) - return -ENOMEM; - - key->eth.type = parse_ethertype(skb); - if (unlikely(key->eth.type == htons(0))) - return -ENOMEM; - - /* Multiple tagged packets need to retain TPID to satisfy - * skb_vlan_pop(), which will later shift the ethertype into - * skb->protocol. - */ - if (key->eth.cvlan.tci & htons(VLAN_CFI_MASK)) - skb->protocol = key->eth.cvlan.tpid; - else - skb->protocol = key->eth.type; - - skb_reset_network_header(skb); - __skb_push(skb, skb->data - skb_mac_header(skb)); - } - skb_reset_mac_len(skb); /* Network layer. */ if (key->eth.type == htons(ETH_P_IP)) { @@ -623,6 +560,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) offset = nh->frag_off & htons(IP_OFFSET); if (offset) { key->ip.frag = OVS_FRAG_TYPE_LATER; + memset(&key->tp, 0, sizeof(key->tp)); return 0; } if (nh->frag_off & htons(IP_MF) || @@ -740,8 +678,10 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) return error; } - if (key->ip.frag == OVS_FRAG_TYPE_LATER) + if (key->ip.frag == OVS_FRAG_TYPE_LATER) { + memset(&key->tp, 0, sizeof(key->tp)); return 0; + } if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP) key->ip.frag = OVS_FRAG_TYPE_FIRST; @@ -788,6 +728,92 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) return 0; } +/** + * key_extract - extracts a flow key from an Ethernet frame. + * @skb: sk_buff that contains the frame, with skb->data pointing to the + * Ethernet header + * @key: output flow key + * + * The caller must ensure that skb->len >= ETH_HLEN. + * + * Returns 0 if successful, otherwise a negative errno value. + * + * Initializes @skb header fields as follows: + * + * - skb->mac_header: the L2 header. + * + * - skb->network_header: just past the L2 header, or just past the + * VLAN header, to the first byte of the L2 payload. + * + * - skb->transport_header: If key->eth.type is ETH_P_IP or ETH_P_IPV6 + * on output, then just past the IP header, if one is present and + * of a correct length, otherwise the same as skb->network_header. + * For other key->eth.type values it is left untouched. + * + * - skb->protocol: the type of the data starting at skb->network_header. + * Equals to key->eth.type. + */ +static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) +{ + struct ethhdr *eth; + + /* Flags are always used as part of stats */ + key->tp.flags = 0; + + skb_reset_mac_header(skb); + + /* Link layer. */ + clear_vlan(key); + if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) { + if (unlikely(eth_type_vlan(skb->protocol))) + return -EINVAL; + + skb_reset_network_header(skb); + key->eth.type = skb->protocol; + } else { + eth = eth_hdr(skb); + ether_addr_copy(key->eth.src, eth->h_source); + ether_addr_copy(key->eth.dst, eth->h_dest); + + __skb_pull(skb, 2 * ETH_ALEN); + /* We are going to push all headers that we pull, so no need to + * update skb->csum here. + */ + + if (unlikely(parse_vlan(skb, key))) + return -ENOMEM; + + key->eth.type = parse_ethertype(skb); + if (unlikely(key->eth.type == htons(0))) + return -ENOMEM; + + /* Multiple tagged packets need to retain TPID to satisfy + * skb_vlan_pop(), which will later shift the ethertype into + * skb->protocol. + */ + if (key->eth.cvlan.tci & htons(VLAN_CFI_MASK)) + skb->protocol = key->eth.cvlan.tpid; + else + skb->protocol = key->eth.type; + + skb_reset_network_header(skb); + __skb_push(skb, skb->data - skb_mac_header(skb)); + } + + skb_reset_mac_len(skb); + + /* Fill out L3/L4 key info, if any */ + return key_extract_l3l4(skb, key); +} + +/* In the case of conntrack fragment handling it expects L3 headers, + * add a helper. + */ +int ovs_flow_key_update_l3l4(struct sk_buff *skb, struct sw_flow_key *key) +{ + return key_extract_l3l4(skb, key); +} + int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key) { int res; diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index a5506e2d4b7a..b830d5ff7af4 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -270,6 +270,7 @@ void ovs_flow_stats_clear(struct sw_flow *); u64 ovs_flow_used_time(unsigned long flow_jiffies); int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key); +int ovs_flow_key_update_l3l4(struct sk_buff *skb, struct sw_flow_key *key); int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, struct sk_buff *skb, struct sw_flow_key *key); diff --git a/net/psample/psample.c b/net/psample/psample.c index 841f198ea1a8..66e4b61a350d 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -154,7 +154,7 @@ static void psample_group_destroy(struct psample_group *group) { psample_group_notify(group, PSAMPLE_CMD_DEL_GROUP); list_del(&group->list); - kfree(group); + kfree_rcu(group, rcu); } static struct psample_group * diff --git a/net/rds/recv.c b/net/rds/recv.c index 853de4876088..a42ba7fa06d5 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved. + * Copyright (c) 2006, 2019 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -811,6 +811,7 @@ void rds6_inc_info_copy(struct rds_incoming *inc, minfo6.seq = be64_to_cpu(inc->i_hdr.h_sequence); minfo6.len = be32_to_cpu(inc->i_hdr.h_len); + minfo6.tos = inc->i_conn->c_tos; if (flip) { minfo6.laddr = *daddr; @@ -824,6 +825,8 @@ void rds6_inc_info_copy(struct rds_incoming *inc, minfo6.fport = inc->i_hdr.h_dport; } + minfo6.flags = 0; + rds_info_copy(iter, &minfo6, sizeof(minfo6)); } #endif diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 0dbbfd1b6487..d72ddb67bb74 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -862,7 +862,6 @@ static void rxrpc_sock_destructor(struct sock *sk) static int rxrpc_release_sock(struct sock *sk) { struct rxrpc_sock *rx = rxrpc_sk(sk); - struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk)); _enter("%p{%d,%d}", sk, sk->sk_state, refcount_read(&sk->sk_refcnt)); @@ -898,8 +897,6 @@ static int rxrpc_release_sock(struct sock *sk) rxrpc_release_calls_on_socket(rx); flush_workqueue(rxrpc_workqueue); rxrpc_purge_queue(&sk->sk_receive_queue); - rxrpc_queue_work(&rxnet->service_conn_reaper); - rxrpc_queue_work(&rxnet->client_conn_reaper); rxrpc_unuse_local(rx->local); rx->local = NULL; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 145335611af6..8051dfdcf26d 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -185,11 +185,17 @@ struct rxrpc_host_header { * - max 48 bytes (struct sk_buff::cb) */ struct rxrpc_skb_priv { - union { - u8 nr_jumbo; /* Number of jumbo subpackets */ - }; + atomic_t nr_ring_pins; /* Number of rxtx ring pins */ + u8 nr_subpackets; /* Number of subpackets */ + u8 rx_flags; /* Received packet flags */ +#define RXRPC_SKB_INCL_LAST 0x01 /* - Includes last packet */ +#define RXRPC_SKB_TX_BUFFER 0x02 /* - Is transmit buffer */ union { int remain; /* amount of space remaining for next write */ + + /* List of requested ACKs on subpackets */ + unsigned long rx_req_ack[(RXRPC_MAX_NR_JUMBO + BITS_PER_LONG - 1) / + BITS_PER_LONG]; }; struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ @@ -613,8 +619,7 @@ struct rxrpc_call { #define RXRPC_TX_ANNO_LAST 0x04 #define RXRPC_TX_ANNO_RESENT 0x08 -#define RXRPC_RX_ANNO_JUMBO 0x3f /* Jumbo subpacket number + 1 if not zero */ -#define RXRPC_RX_ANNO_JLAST 0x40 /* Set if last element of a jumbo packet */ +#define RXRPC_RX_ANNO_SUBPACKET 0x3f /* Subpacket number in jumbogram */ #define RXRPC_RX_ANNO_VERIFIED 0x80 /* Set if verified and decrypted */ rxrpc_seq_t tx_hard_ack; /* Dead slot in buffer; the first transmitted but * not hard-ACK'd packet follows this. @@ -905,6 +910,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *); void rxrpc_put_client_conn(struct rxrpc_connection *); void rxrpc_discard_expired_client_conns(struct work_struct *); void rxrpc_destroy_all_client_connections(struct rxrpc_net *); +void rxrpc_clean_up_local_conns(struct rxrpc_local *); /* * conn_event.c @@ -1105,6 +1111,7 @@ void rxrpc_kernel_data_consumed(struct rxrpc_call *, struct sk_buff *); void rxrpc_packet_destructor(struct sk_buff *); void rxrpc_new_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_see_skb(struct sk_buff *, enum rxrpc_skb_trace); +void rxrpc_eaten_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_get_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_free_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_purge_queue(struct sk_buff_head *); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index c767679bfa5d..cedbbb3a7c2e 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -199,7 +199,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) continue; skb = call->rxtx_buffer[ix]; - rxrpc_see_skb(skb, rxrpc_skb_tx_seen); + rxrpc_see_skb(skb, rxrpc_skb_seen); if (anno_type == RXRPC_TX_ANNO_UNACK) { if (ktime_after(skb->tstamp, max_age)) { @@ -255,18 +255,18 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) continue; skb = call->rxtx_buffer[ix]; - rxrpc_get_skb(skb, rxrpc_skb_tx_got); + rxrpc_get_skb(skb, rxrpc_skb_got); spin_unlock_bh(&call->lock); if (rxrpc_send_data_packet(call, skb, true) < 0) { - rxrpc_free_skb(skb, rxrpc_skb_tx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); return; } if (rxrpc_is_client_call(call)) rxrpc_expose_client_call(call); - rxrpc_free_skb(skb, rxrpc_skb_tx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); spin_lock_bh(&call->lock); /* We need to clear the retransmit state, but there are two diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 217b12be9e08..014548c259ce 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -422,6 +422,19 @@ void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) } /* + * Clean up the RxTx skb ring. + */ +static void rxrpc_cleanup_ring(struct rxrpc_call *call) +{ + int i; + + for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) { + rxrpc_free_skb(call->rxtx_buffer[i], rxrpc_skb_cleaned); + call->rxtx_buffer[i] = NULL; + } +} + +/* * Detach a call from its owning socket. */ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) @@ -429,7 +442,6 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) const void *here = __builtin_return_address(0); struct rxrpc_connection *conn = call->conn; bool put = false; - int i; _enter("{%d,%d}", call->debug_id, atomic_read(&call->usage)); @@ -479,13 +491,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) if (conn) rxrpc_disconnect_call(call); - for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) { - rxrpc_free_skb(call->rxtx_buffer[i], - (call->tx_phase ? rxrpc_skb_tx_cleaned : - rxrpc_skb_rx_cleaned)); - call->rxtx_buffer[i] = NULL; - } - + rxrpc_cleanup_ring(call); _leave(""); } @@ -568,8 +574,6 @@ static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) */ void rxrpc_cleanup_call(struct rxrpc_call *call) { - int i; - _net("DESTROY CALL %d", call->debug_id); memset(&call->sock_node, 0xcd, sizeof(call->sock_node)); @@ -580,13 +584,8 @@ void rxrpc_cleanup_call(struct rxrpc_call *call) ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags)); ASSERTCMP(call->conn, ==, NULL); - /* Clean up the Rx/Tx buffer */ - for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) - rxrpc_free_skb(call->rxtx_buffer[i], - (call->tx_phase ? rxrpc_skb_tx_cleaned : - rxrpc_skb_rx_cleaned)); - - rxrpc_free_skb(call->tx_pending, rxrpc_skb_tx_cleaned); + rxrpc_cleanup_ring(call); + rxrpc_free_skb(call->tx_pending, rxrpc_skb_cleaned); call_rcu(&call->rcu, rxrpc_rcu_destroy_call); } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index aea82f909c60..3f1da1b49f69 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -1162,3 +1162,47 @@ void rxrpc_destroy_all_client_connections(struct rxrpc_net *rxnet) _leave(""); } + +/* + * Clean up the client connections on a local endpoint. + */ +void rxrpc_clean_up_local_conns(struct rxrpc_local *local) +{ + struct rxrpc_connection *conn, *tmp; + struct rxrpc_net *rxnet = local->rxnet; + unsigned int nr_active; + LIST_HEAD(graveyard); + + _enter(""); + + spin_lock(&rxnet->client_conn_cache_lock); + nr_active = rxnet->nr_active_client_conns; + + list_for_each_entry_safe(conn, tmp, &rxnet->idle_client_conns, + cache_link) { + if (conn->params.local == local) { + ASSERTCMP(conn->cache_state, ==, RXRPC_CONN_CLIENT_IDLE); + + trace_rxrpc_client(conn, -1, rxrpc_client_discard); + if (!test_and_clear_bit(RXRPC_CONN_EXPOSED, &conn->flags)) + BUG(); + conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE; + list_move(&conn->cache_link, &graveyard); + nr_active--; + } + } + + rxnet->nr_active_client_conns = nr_active; + spin_unlock(&rxnet->client_conn_cache_lock); + ASSERTCMP(nr_active, >=, 0); + + while (!list_empty(&graveyard)) { + conn = list_entry(graveyard.next, + struct rxrpc_connection, cache_link); + list_del_init(&conn->cache_link); + + rxrpc_put_connection(conn); + } + + _leave(" [culled]"); +} diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index df6624c140be..a1ceef4f5cd0 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -472,7 +472,7 @@ void rxrpc_process_connection(struct work_struct *work) /* go through the conn-level event packets, releasing the ref on this * connection that each one has when we've finished with it */ while ((skb = skb_dequeue(&conn->rx_queue))) { - rxrpc_see_skb(skb, rxrpc_skb_rx_seen); + rxrpc_see_skb(skb, rxrpc_skb_seen); ret = rxrpc_process_event(conn, skb, &abort_code); switch (ret) { case -EPROTO: @@ -484,7 +484,7 @@ void rxrpc_process_connection(struct work_struct *work) goto requeue_and_leave; case -ECONNABORTED: default: - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); break; } } @@ -501,6 +501,6 @@ requeue_and_leave: protocol_error: if (rxrpc_abort_connection(conn, ret, abort_code) < 0) goto requeue_and_leave; - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); goto out; } diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 434ef392212b..ed05b6922132 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -398,7 +398,7 @@ void rxrpc_service_connection_reaper(struct work_struct *work) if (conn->state == RXRPC_CONN_SERVICE_PREALLOC) continue; - if (rxnet->live) { + if (rxnet->live && !conn->params.local->dead) { idle_timestamp = READ_ONCE(conn->idle_timestamp); expire_at = idle_timestamp + rxrpc_connection_expiry * HZ; if (conn->params.local->service_closed) diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index dd47d465d1d3..d122c53c8697 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -233,7 +233,7 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, ix = call->tx_hard_ack & RXRPC_RXTX_BUFF_MASK; skb = call->rxtx_buffer[ix]; annotation = call->rxtx_annotations[ix]; - rxrpc_see_skb(skb, rxrpc_skb_tx_rotated); + rxrpc_see_skb(skb, rxrpc_skb_rotated); call->rxtx_buffer[ix] = NULL; call->rxtx_annotations[ix] = 0; skb->next = list; @@ -258,7 +258,7 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, skb = list; list = skb->next; skb_mark_not_on_list(skb); - rxrpc_free_skb(skb, rxrpc_skb_tx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); } return rot_last; @@ -347,7 +347,7 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) } /* - * Scan a jumbo packet to validate its structure and to work out how many + * Scan a data packet to validate its structure and to work out how many * subpackets it contains. * * A jumbo packet is a collection of consecutive packets glued together with @@ -358,16 +358,21 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) * the last are RXRPC_JUMBO_DATALEN in size. The last subpacket may be of any * size. */ -static bool rxrpc_validate_jumbo(struct sk_buff *skb) +static bool rxrpc_validate_data(struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned int offset = sizeof(struct rxrpc_wire_header); unsigned int len = skb->len; - int nr_jumbo = 1; u8 flags = sp->hdr.flags; - do { - nr_jumbo++; + for (;;) { + if (flags & RXRPC_REQUEST_ACK) + __set_bit(sp->nr_subpackets, sp->rx_req_ack); + sp->nr_subpackets++; + + if (!(flags & RXRPC_JUMBO_PACKET)) + break; + if (len - offset < RXRPC_JUMBO_SUBPKTLEN) goto protocol_error; if (flags & RXRPC_LAST_PACKET) @@ -376,9 +381,10 @@ static bool rxrpc_validate_jumbo(struct sk_buff *skb) if (skb_copy_bits(skb, offset, &flags, 1) < 0) goto protocol_error; offset += sizeof(struct rxrpc_jumbo_header); - } while (flags & RXRPC_JUMBO_PACKET); + } - sp->nr_jumbo = nr_jumbo; + if (flags & RXRPC_LAST_PACKET) + sp->rx_flags |= RXRPC_SKB_INCL_LAST; return true; protocol_error: @@ -399,10 +405,10 @@ protocol_error: * (that information is encoded in the ACK packet). */ static void rxrpc_input_dup_data(struct rxrpc_call *call, rxrpc_seq_t seq, - u8 annotation, bool *_jumbo_bad) + bool is_jumbo, bool *_jumbo_bad) { /* Discard normal packets that are duplicates. */ - if (annotation == 0) + if (is_jumbo) return; /* Skip jumbo subpackets that are duplicates. When we've had three or @@ -416,29 +422,30 @@ static void rxrpc_input_dup_data(struct rxrpc_call *call, rxrpc_seq_t seq, } /* - * Process a DATA packet, adding the packet to the Rx ring. + * Process a DATA packet, adding the packet to the Rx ring. The caller's + * packet ref must be passed on or discarded. */ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); enum rxrpc_call_state state; - unsigned int offset = sizeof(struct rxrpc_wire_header); - unsigned int ix; + unsigned int j; rxrpc_serial_t serial = sp->hdr.serial, ack_serial = 0; - rxrpc_seq_t seq = sp->hdr.seq, hard_ack; - bool immediate_ack = false, jumbo_bad = false, queued; - u16 len; - u8 ack = 0, flags, annotation = 0; + rxrpc_seq_t seq0 = sp->hdr.seq, hard_ack; + bool immediate_ack = false, jumbo_bad = false; + u8 ack = 0; _enter("{%u,%u},{%u,%u}", - call->rx_hard_ack, call->rx_top, skb->len, seq); + call->rx_hard_ack, call->rx_top, skb->len, seq0); - _proto("Rx DATA %%%u { #%u f=%02x }", - sp->hdr.serial, seq, sp->hdr.flags); + _proto("Rx DATA %%%u { #%u f=%02x n=%u }", + sp->hdr.serial, seq0, sp->hdr.flags, sp->nr_subpackets); state = READ_ONCE(call->state); - if (state >= RXRPC_CALL_COMPLETE) + if (state >= RXRPC_CALL_COMPLETE) { + rxrpc_free_skb(skb, rxrpc_skb_freed); return; + } if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST) { unsigned long timo = READ_ONCE(call->next_req_timo); @@ -463,137 +470,137 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) !rxrpc_receiving_reply(call)) goto unlock; - call->ackr_prev_seq = seq; - + call->ackr_prev_seq = seq0; hard_ack = READ_ONCE(call->rx_hard_ack); - if (after(seq, hard_ack + call->rx_winsize)) { - ack = RXRPC_ACK_EXCEEDS_WINDOW; - ack_serial = serial; - goto ack; - } - flags = sp->hdr.flags; - if (flags & RXRPC_JUMBO_PACKET) { + if (sp->nr_subpackets > 1) { if (call->nr_jumbo_bad > 3) { ack = RXRPC_ACK_NOSPACE; ack_serial = serial; goto ack; } - annotation = 1; } -next_subpacket: - queued = false; - ix = seq & RXRPC_RXTX_BUFF_MASK; - len = skb->len; - if (flags & RXRPC_JUMBO_PACKET) - len = RXRPC_JUMBO_DATALEN; - - if (flags & RXRPC_LAST_PACKET) { - if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - seq != call->rx_top) { - rxrpc_proto_abort("LSN", call, seq); - goto unlock; - } - } else { - if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - after_eq(seq, call->rx_top)) { - rxrpc_proto_abort("LSA", call, seq); - goto unlock; + for (j = 0; j < sp->nr_subpackets; j++) { + rxrpc_serial_t serial = sp->hdr.serial + j; + rxrpc_seq_t seq = seq0 + j; + unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK; + bool terminal = (j == sp->nr_subpackets - 1); + bool last = terminal && (sp->rx_flags & RXRPC_SKB_INCL_LAST); + u8 flags, annotation = j; + + _proto("Rx DATA+%u %%%u { #%x t=%u l=%u }", + j, serial, seq, terminal, last); + + if (last) { + if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && + seq != call->rx_top) { + rxrpc_proto_abort("LSN", call, seq); + goto unlock; + } + } else { + if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && + after_eq(seq, call->rx_top)) { + rxrpc_proto_abort("LSA", call, seq); + goto unlock; + } } - } - trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation); - if (before_eq(seq, hard_ack)) { - ack = RXRPC_ACK_DUPLICATE; - ack_serial = serial; - goto skip; - } + flags = 0; + if (last) + flags |= RXRPC_LAST_PACKET; + if (!terminal) + flags |= RXRPC_JUMBO_PACKET; + if (test_bit(j, sp->rx_req_ack)) + flags |= RXRPC_REQUEST_ACK; + trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation); - if (flags & RXRPC_REQUEST_ACK && !ack) { - ack = RXRPC_ACK_REQUESTED; - ack_serial = serial; - } - - if (call->rxtx_buffer[ix]) { - rxrpc_input_dup_data(call, seq, annotation, &jumbo_bad); - if (ack != RXRPC_ACK_DUPLICATE) { + if (before_eq(seq, hard_ack)) { ack = RXRPC_ACK_DUPLICATE; ack_serial = serial; + continue; } - immediate_ack = true; - goto skip; - } - /* Queue the packet. We use a couple of memory barriers here as need - * to make sure that rx_top is perceived to be set after the buffer - * pointer and that the buffer pointer is set after the annotation and - * the skb data. - * - * Barriers against rxrpc_recvmsg_data() and rxrpc_rotate_rx_window() - * and also rxrpc_fill_out_ack(). - */ - rxrpc_get_skb(skb, rxrpc_skb_rx_got); - call->rxtx_annotations[ix] = annotation; - smp_wmb(); - call->rxtx_buffer[ix] = skb; - if (after(seq, call->rx_top)) { - smp_store_release(&call->rx_top, seq); - } else if (before(seq, call->rx_top)) { - /* Send an immediate ACK if we fill in a hole */ - if (!ack) { - ack = RXRPC_ACK_DELAY; - ack_serial = serial; + if (call->rxtx_buffer[ix]) { + rxrpc_input_dup_data(call, seq, sp->nr_subpackets > 1, + &jumbo_bad); + if (ack != RXRPC_ACK_DUPLICATE) { + ack = RXRPC_ACK_DUPLICATE; + ack_serial = serial; + } + immediate_ack = true; + continue; } - immediate_ack = true; - } - if (flags & RXRPC_LAST_PACKET) { - set_bit(RXRPC_CALL_RX_LAST, &call->flags); - trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq); - } else { - trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq); - } - queued = true; - if (after_eq(seq, call->rx_expect_next)) { - if (after(seq, call->rx_expect_next)) { - _net("OOS %u > %u", seq, call->rx_expect_next); - ack = RXRPC_ACK_OUT_OF_SEQUENCE; - ack_serial = serial; - } - call->rx_expect_next = seq + 1; - } - -skip: - offset += len; - if (flags & RXRPC_JUMBO_PACKET) { - if (skb_copy_bits(skb, offset, &flags, 1) < 0) { - rxrpc_proto_abort("XJF", call, seq); - goto unlock; - } - offset += sizeof(struct rxrpc_jumbo_header); - seq++; - serial++; - annotation++; - if (flags & RXRPC_JUMBO_PACKET) - annotation |= RXRPC_RX_ANNO_JLAST; if (after(seq, hard_ack + call->rx_winsize)) { ack = RXRPC_ACK_EXCEEDS_WINDOW; ack_serial = serial; - if (!jumbo_bad) { - call->nr_jumbo_bad++; - jumbo_bad = true; + if (flags & RXRPC_JUMBO_PACKET) { + if (!jumbo_bad) { + call->nr_jumbo_bad++; + jumbo_bad = true; + } } + goto ack; } - _proto("Rx DATA Jumbo %%%u", serial); - goto next_subpacket; - } + if (flags & RXRPC_REQUEST_ACK && !ack) { + ack = RXRPC_ACK_REQUESTED; + ack_serial = serial; + } + + /* Queue the packet. We use a couple of memory barriers here as need + * to make sure that rx_top is perceived to be set after the buffer + * pointer and that the buffer pointer is set after the annotation and + * the skb data. + * + * Barriers against rxrpc_recvmsg_data() and rxrpc_rotate_rx_window() + * and also rxrpc_fill_out_ack(). + */ + if (!terminal) + rxrpc_get_skb(skb, rxrpc_skb_got); + call->rxtx_annotations[ix] = annotation; + smp_wmb(); + call->rxtx_buffer[ix] = skb; + if (after(seq, call->rx_top)) { + smp_store_release(&call->rx_top, seq); + } else if (before(seq, call->rx_top)) { + /* Send an immediate ACK if we fill in a hole */ + if (!ack) { + ack = RXRPC_ACK_DELAY; + ack_serial = serial; + } + immediate_ack = true; + } + + if (terminal) { + /* From this point on, we're not allowed to touch the + * packet any longer as its ref now belongs to the Rx + * ring. + */ + skb = NULL; + } - if (queued && flags & RXRPC_LAST_PACKET && !ack) { - ack = RXRPC_ACK_DELAY; - ack_serial = serial; + if (last) { + set_bit(RXRPC_CALL_RX_LAST, &call->flags); + if (!ack) { + ack = RXRPC_ACK_DELAY; + ack_serial = serial; + } + trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq); + } else { + trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq); + } + + if (after_eq(seq, call->rx_expect_next)) { + if (after(seq, call->rx_expect_next)) { + _net("OOS %u > %u", seq, call->rx_expect_next); + ack = RXRPC_ACK_OUT_OF_SEQUENCE; + ack_serial = serial; + } + call->rx_expect_next = seq + 1; + } } ack: @@ -606,13 +613,14 @@ ack: false, true, rxrpc_propose_ack_input_data); - if (sp->hdr.seq == READ_ONCE(call->rx_hard_ack) + 1) { + if (seq0 == READ_ONCE(call->rx_hard_ack) + 1) { trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); } unlock: spin_unlock(&call->input_lock); + rxrpc_free_skb(skb, rxrpc_skb_freed); _leave(" [queued]"); } @@ -1021,7 +1029,7 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_DATA: rxrpc_input_data(call, skb); - break; + goto no_free; case RXRPC_PACKET_TYPE_ACK: rxrpc_input_ack(call, skb); @@ -1048,6 +1056,8 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, break; } + rxrpc_free_skb(skb, rxrpc_skb_freed); +no_free: _leave(""); } @@ -1109,7 +1119,7 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, skb_queue_tail(&local->event_queue, skb); rxrpc_queue_local(local); } else { - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); } } @@ -1124,7 +1134,7 @@ static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) skb_queue_tail(&local->reject_queue, skb); rxrpc_queue_local(local); } else { - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); } } @@ -1188,7 +1198,7 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) if (skb->tstamp == 0) skb->tstamp = ktime_get_real(); - rxrpc_new_skb(skb, rxrpc_skb_rx_received); + rxrpc_new_skb(skb, rxrpc_skb_received); skb_pull(skb, sizeof(struct udphdr)); @@ -1205,7 +1215,7 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) static int lose; if ((lose++ & 7) == 7) { trace_rxrpc_rx_lose(sp); - rxrpc_free_skb(skb, rxrpc_skb_rx_lost); + rxrpc_free_skb(skb, rxrpc_skb_lost); return 0; } } @@ -1237,9 +1247,26 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) if (sp->hdr.callNumber == 0 || sp->hdr.seq == 0) goto bad_message; - if (sp->hdr.flags & RXRPC_JUMBO_PACKET && - !rxrpc_validate_jumbo(skb)) + if (!rxrpc_validate_data(skb)) goto bad_message; + + /* Unshare the packet so that it can be modified for in-place + * decryption. + */ + if (sp->hdr.securityIndex != 0) { + struct sk_buff *nskb = skb_unshare(skb, GFP_ATOMIC); + if (!nskb) { + rxrpc_eaten_skb(skb, rxrpc_skb_unshared_nomem); + goto out; + } + + if (nskb != skb) { + rxrpc_eaten_skb(skb, rxrpc_skb_received); + rxrpc_new_skb(skb, rxrpc_skb_unshared); + skb = nskb; + sp = rxrpc_skb(skb); + } + } break; case RXRPC_PACKET_TYPE_CHALLENGE: @@ -1373,11 +1400,14 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) mutex_unlock(&call->user_mutex); } + /* Process a call packet; this either discards or passes on the ref + * elsewhere. + */ rxrpc_input_call_packet(call, skb); - goto discard; + goto out; discard: - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); out: trace_rxrpc_rx_done(0, 0); return 0; diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index e93a78f7c05e..3ce6d628cd75 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -90,7 +90,7 @@ void rxrpc_process_local_events(struct rxrpc_local *local) if (skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - rxrpc_see_skb(skb, rxrpc_skb_rx_seen); + rxrpc_see_skb(skb, rxrpc_skb_seen); _debug("{%d},{%u}", local->debug_id, sp->hdr.type); switch (sp->hdr.type) { @@ -108,7 +108,7 @@ void rxrpc_process_local_events(struct rxrpc_local *local) break; } - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); } _leave(""); diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 72a6e12a9304..36587260cabd 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -426,11 +426,14 @@ static void rxrpc_local_destroyer(struct rxrpc_local *local) _enter("%d", local->debug_id); + local->dead = true; + mutex_lock(&rxnet->local_mutex); list_del_init(&local->link); mutex_unlock(&rxnet->local_mutex); - ASSERT(RB_EMPTY_ROOT(&local->client_conns)); + rxrpc_clean_up_local_conns(local); + rxrpc_service_connection_reaper(&rxnet->service_conn_reaper); ASSERT(!local->service); if (socket) { diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 369e516c4bdf..935bb60fff56 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -565,7 +565,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local) memset(&whdr, 0, sizeof(whdr)); while ((skb = skb_dequeue(&local->reject_queue))) { - rxrpc_see_skb(skb, rxrpc_skb_rx_seen); + rxrpc_see_skb(skb, rxrpc_skb_seen); sp = rxrpc_skb(skb); switch (skb->mark) { @@ -581,7 +581,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local) ioc = 2; break; default: - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); continue; } @@ -606,7 +606,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local) rxrpc_tx_point_reject); } - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); } _leave(""); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 7666ec72d37e..c97ebdc043e4 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -163,11 +163,11 @@ void rxrpc_error_report(struct sock *sk) _leave("UDP socket errqueue empty"); return; } - rxrpc_new_skb(skb, rxrpc_skb_rx_received); + rxrpc_new_skb(skb, rxrpc_skb_received); serr = SKB_EXT_ERR(skb); if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) { _leave("UDP empty message"); - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); return; } @@ -177,7 +177,7 @@ void rxrpc_error_report(struct sock *sk) peer = NULL; if (!peer) { rcu_read_unlock(); - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); _leave(" [no peer]"); return; } @@ -189,7 +189,7 @@ void rxrpc_error_report(struct sock *sk) serr->ee.ee_code == ICMP_FRAG_NEEDED)) { rxrpc_adjust_mtu(peer, serr); rcu_read_unlock(); - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); rxrpc_put_peer(peer); _leave(" [MTU update]"); return; @@ -197,7 +197,7 @@ void rxrpc_error_report(struct sock *sk) rxrpc_store_error(peer, serr); rcu_read_unlock(); - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); rxrpc_put_peer(peer); _leave(""); diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h index 99ce322d7caa..49bb972539aa 100644 --- a/net/rxrpc/protocol.h +++ b/net/rxrpc/protocol.h @@ -89,6 +89,15 @@ struct rxrpc_jumbo_header { #define RXRPC_JUMBO_DATALEN 1412 /* non-terminal jumbo packet data length */ #define RXRPC_JUMBO_SUBPKTLEN (RXRPC_JUMBO_DATALEN + sizeof(struct rxrpc_jumbo_header)) +/* + * The maximum number of subpackets that can possibly fit in a UDP packet is: + * + * ((max_IP - IP_hdr - UDP_hdr) / RXRPC_JUMBO_SUBPKTLEN) + 1 + * = ((65535 - 28 - 28) / 1416) + 1 + * = 46 non-terminal packets and 1 terminal packet. + */ +#define RXRPC_MAX_NR_JUMBO 47 + /*****************************************************************************/ /* * on-the-wire Rx ACK packet data payload diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 9a7e1bc9791d..3b0becb12041 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -177,7 +177,8 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) struct sk_buff *skb; rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top; - u8 flags; + bool last = false; + u8 subpacket; int ix; _enter("%d", call->debug_id); @@ -189,23 +190,25 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) hard_ack++; ix = hard_ack & RXRPC_RXTX_BUFF_MASK; skb = call->rxtx_buffer[ix]; - rxrpc_see_skb(skb, rxrpc_skb_rx_rotated); + rxrpc_see_skb(skb, rxrpc_skb_rotated); sp = rxrpc_skb(skb); - flags = sp->hdr.flags; - serial = sp->hdr.serial; - if (call->rxtx_annotations[ix] & RXRPC_RX_ANNO_JUMBO) - serial += (call->rxtx_annotations[ix] & RXRPC_RX_ANNO_JUMBO) - 1; + + subpacket = call->rxtx_annotations[ix] & RXRPC_RX_ANNO_SUBPACKET; + serial = sp->hdr.serial + subpacket; + + if (subpacket == sp->nr_subpackets - 1 && + sp->rx_flags & RXRPC_SKB_INCL_LAST) + last = true; call->rxtx_buffer[ix] = NULL; call->rxtx_annotations[ix] = 0; /* Barrier against rxrpc_input_data(). */ smp_store_release(&call->rx_hard_ack, hard_ack); - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); - _debug("%u,%u,%02x", hard_ack, top, flags); trace_rxrpc_receive(call, rxrpc_receive_rotate, serial, hard_ack); - if (flags & RXRPC_LAST_PACKET) { + if (last) { rxrpc_end_rx_phase(call, serial); } else { /* Check to see if there's an ACK that needs sending. */ @@ -233,18 +236,19 @@ static int rxrpc_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, struct rxrpc_skb_priv *sp = rxrpc_skb(skb); rxrpc_seq_t seq = sp->hdr.seq; u16 cksum = sp->hdr.cksum; + u8 subpacket = annotation & RXRPC_RX_ANNO_SUBPACKET; _enter(""); /* For all but the head jumbo subpacket, the security checksum is in a * jumbo header immediately prior to the data. */ - if ((annotation & RXRPC_RX_ANNO_JUMBO) > 1) { + if (subpacket > 0) { __be16 tmp; if (skb_copy_bits(skb, offset - 2, &tmp, 2) < 0) BUG(); cksum = ntohs(tmp); - seq += (annotation & RXRPC_RX_ANNO_JUMBO) - 1; + seq += subpacket; } return call->conn->security->verify_packet(call, skb, offset, len, @@ -265,19 +269,18 @@ static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb, u8 *_annotation, unsigned int *_offset, unsigned int *_len) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned int offset = sizeof(struct rxrpc_wire_header); unsigned int len; int ret; u8 annotation = *_annotation; + u8 subpacket = annotation & RXRPC_RX_ANNO_SUBPACKET; /* Locate the subpacket */ + offset += subpacket * RXRPC_JUMBO_SUBPKTLEN; len = skb->len - offset; - if ((annotation & RXRPC_RX_ANNO_JUMBO) > 0) { - offset += (((annotation & RXRPC_RX_ANNO_JUMBO) - 1) * - RXRPC_JUMBO_SUBPKTLEN); - len = (annotation & RXRPC_RX_ANNO_JLAST) ? - skb->len - offset : RXRPC_JUMBO_SUBPKTLEN; - } + if (subpacket < sp->nr_subpackets - 1) + len = RXRPC_JUMBO_DATALEN; if (!(annotation & RXRPC_RX_ANNO_VERIFIED)) { ret = rxrpc_verify_packet(call, skb, annotation, offset, len); @@ -303,6 +306,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, { struct rxrpc_skb_priv *sp; struct sk_buff *skb; + rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top, seq; size_t remain; bool last; @@ -336,12 +340,15 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, break; } smp_rmb(); - rxrpc_see_skb(skb, rxrpc_skb_rx_seen); + rxrpc_see_skb(skb, rxrpc_skb_seen); sp = rxrpc_skb(skb); - if (!(flags & MSG_PEEK)) + if (!(flags & MSG_PEEK)) { + serial = sp->hdr.serial; + serial += call->rxtx_annotations[ix] & RXRPC_RX_ANNO_SUBPACKET; trace_rxrpc_receive(call, rxrpc_receive_front, - sp->hdr.serial, seq); + serial, seq); + } if (msg) sock_recv_timestamp(msg, sock->sk, skb); diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index ae8cd8926456..c60c520fde7c 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -187,10 +187,8 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, struct rxrpc_skb_priv *sp; struct rxrpc_crypt iv; struct scatterlist sg[16]; - struct sk_buff *trailer; unsigned int len; u16 check; - int nsg; int err; sp = rxrpc_skb(skb); @@ -214,15 +212,14 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, crypto_skcipher_encrypt(req); /* we want to encrypt the skbuff in-place */ - nsg = skb_cow_data(skb, 0, &trailer); - err = -ENOMEM; - if (nsg < 0 || nsg > 16) + err = -EMSGSIZE; + if (skb_shinfo(skb)->nr_frags > 16) goto out; len = data_size + call->conn->size_align - 1; len &= ~(call->conn->size_align - 1); - sg_init_table(sg, nsg); + sg_init_table(sg, ARRAY_SIZE(sg)); err = skb_to_sgvec(skb, sg, 0, len); if (unlikely(err < 0)) goto out; @@ -319,11 +316,10 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, struct rxkad_level1_hdr sechdr; struct rxrpc_crypt iv; struct scatterlist sg[16]; - struct sk_buff *trailer; bool aborted; u32 data_size, buf; u16 check; - int nsg, ret; + int ret; _enter(""); @@ -336,11 +332,7 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, /* Decrypt the skbuff in-place. TODO: We really want to decrypt * directly into the target buffer. */ - nsg = skb_cow_data(skb, 0, &trailer); - if (nsg < 0 || nsg > 16) - goto nomem; - - sg_init_table(sg, nsg); + sg_init_table(sg, ARRAY_SIZE(sg)); ret = skb_to_sgvec(skb, sg, offset, 8); if (unlikely(ret < 0)) return ret; @@ -388,10 +380,6 @@ protocol_error: if (aborted) rxrpc_send_abort_packet(call); return -EPROTO; - -nomem: - _leave(" = -ENOMEM"); - return -ENOMEM; } /* @@ -406,7 +394,6 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, struct rxkad_level2_hdr sechdr; struct rxrpc_crypt iv; struct scatterlist _sg[4], *sg; - struct sk_buff *trailer; bool aborted; u32 data_size, buf; u16 check; @@ -423,12 +410,11 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, /* Decrypt the skbuff in-place. TODO: We really want to decrypt * directly into the target buffer. */ - nsg = skb_cow_data(skb, 0, &trailer); - if (nsg < 0) - goto nomem; - sg = _sg; - if (unlikely(nsg > 4)) { + nsg = skb_shinfo(skb)->nr_frags; + if (nsg <= 4) { + nsg = 4; + } else { sg = kmalloc_array(nsg, sizeof(*sg), GFP_NOIO); if (!sg) goto nomem; diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index bae14438f869..6a1547b270fe 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -176,7 +176,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, skb->tstamp = ktime_get_real(); ix = seq & RXRPC_RXTX_BUFF_MASK; - rxrpc_get_skb(skb, rxrpc_skb_tx_got); + rxrpc_get_skb(skb, rxrpc_skb_got); call->rxtx_annotations[ix] = annotation; smp_wmb(); call->rxtx_buffer[ix] = skb; @@ -248,7 +248,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, } out: - rxrpc_free_skb(skb, rxrpc_skb_tx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); _leave(" = %d", ret); return ret; } @@ -289,7 +289,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, skb = call->tx_pending; call->tx_pending = NULL; - rxrpc_see_skb(skb, rxrpc_skb_tx_seen); + rxrpc_see_skb(skb, rxrpc_skb_seen); copied = 0; do { @@ -336,7 +336,9 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, if (!skb) goto maybe_error; - rxrpc_new_skb(skb, rxrpc_skb_tx_new); + sp = rxrpc_skb(skb); + sp->rx_flags |= RXRPC_SKB_TX_BUFFER; + rxrpc_new_skb(skb, rxrpc_skb_new); _debug("ALLOC SEND %p", skb); @@ -346,7 +348,6 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, skb_reserve(skb, call->conn->security_size); skb->len += call->conn->security_size; - sp = rxrpc_skb(skb); sp->remain = chunk; if (sp->remain > skb_tailroom(skb)) sp->remain = skb_tailroom(skb); @@ -439,7 +440,7 @@ out: return ret; call_terminated: - rxrpc_free_skb(skb, rxrpc_skb_tx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); _leave(" = %d", call->error); return call->error; diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index 9ad5045b7c2f..0348d2bf6f7d 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -14,7 +14,8 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" -#define select_skb_count(op) (op >= rxrpc_skb_tx_cleaned ? &rxrpc_n_tx_skbs : &rxrpc_n_rx_skbs) +#define is_tx_skb(skb) (rxrpc_skb(skb)->rx_flags & RXRPC_SKB_TX_BUFFER) +#define select_skb_count(skb) (is_tx_skb(skb) ? &rxrpc_n_tx_skbs : &rxrpc_n_rx_skbs) /* * Note the allocation or reception of a socket buffer. @@ -22,8 +23,9 @@ void rxrpc_new_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); - int n = atomic_inc_return(select_skb_count(op)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); + int n = atomic_inc_return(select_skb_count(skb)); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, + rxrpc_skb(skb)->rx_flags, here); } /* @@ -33,8 +35,9 @@ void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); if (skb) { - int n = atomic_read(select_skb_count(op)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); + int n = atomic_read(select_skb_count(skb)); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, + rxrpc_skb(skb)->rx_flags, here); } } @@ -44,12 +47,23 @@ void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) void rxrpc_get_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); - int n = atomic_inc_return(select_skb_count(op)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); + int n = atomic_inc_return(select_skb_count(skb)); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, + rxrpc_skb(skb)->rx_flags, here); skb_get(skb); } /* + * Note the dropping of a ref on a socket buffer by the core. + */ +void rxrpc_eaten_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) +{ + const void *here = __builtin_return_address(0); + int n = atomic_inc_return(&rxrpc_n_rx_skbs); + trace_rxrpc_skb(skb, op, 0, n, 0, here); +} + +/* * Note the destruction of a socket buffer. */ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) @@ -58,8 +72,9 @@ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) if (skb) { int n; CHECK_SLAB_OKAY(&skb->users); - n = atomic_dec_return(select_skb_count(op)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); + n = atomic_dec_return(select_skb_count(skb)); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, + rxrpc_skb(skb)->rx_flags, here); kfree_skb(skb); } } @@ -72,9 +87,10 @@ void rxrpc_purge_queue(struct sk_buff_head *list) const void *here = __builtin_return_address(0); struct sk_buff *skb; while ((skb = skb_dequeue((list))) != NULL) { - int n = atomic_dec_return(select_skb_count(rxrpc_skb_rx_purged)); - trace_rxrpc_skb(skb, rxrpc_skb_rx_purged, - refcount_read(&skb->users), n, here); + int n = atomic_dec_return(select_skb_count(skb)); + trace_rxrpc_skb(skb, rxrpc_skb_purged, + refcount_read(&skb->users), n, + rxrpc_skb(skb)->rx_flags, here); kfree_skb(skb); } } diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index fd1f7e799e23..04b7bd4ec751 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -422,7 +422,7 @@ static __net_init int bpf_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, bpf_net_id); - return tc_action_net_init(tn, &act_bpf_ops); + return tc_action_net_init(net, tn, &act_bpf_ops); } static void __net_exit bpf_exit_net(struct list_head *net_list) diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 32ac04d77a45..2b43cacf82af 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -231,7 +231,7 @@ static __net_init int connmark_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, connmark_net_id); - return tc_action_net_init(tn, &act_connmark_ops); + return tc_action_net_init(net, tn, &act_connmark_ops); } static void __net_exit connmark_exit_net(struct list_head *net_list) diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 9b9288267a54..d3cfad88dc3a 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -714,7 +714,7 @@ static __net_init int csum_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, csum_net_id); - return tc_action_net_init(tn, &act_csum_ops); + return tc_action_net_init(net, tn, &act_csum_ops); } static void __net_exit csum_exit_net(struct list_head *net_list) diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 33a1a7406e87..cdd6f3818097 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -939,7 +939,7 @@ static __net_init int ct_init_net(struct net *net) tn->labels = true; } - return tc_action_net_init(&tn->tn, &act_ct_ops); + return tc_action_net_init(net, &tn->tn, &act_ct_ops); } static void __net_exit ct_exit_net(struct list_head *net_list) diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 06ef74b74911..0dbcfd1dca7b 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -376,7 +376,7 @@ static __net_init int ctinfo_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, ctinfo_net_id); - return tc_action_net_init(tn, &act_ctinfo_ops); + return tc_action_net_init(net, tn, &act_ctinfo_ops); } static void __net_exit ctinfo_exit_net(struct list_head *net_list) diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 8f0140c6ca58..324f1d1f6d47 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -278,7 +278,7 @@ static __net_init int gact_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, gact_net_id); - return tc_action_net_init(tn, &act_gact_ops); + return tc_action_net_init(net, tn, &act_gact_ops); } static void __net_exit gact_exit_net(struct list_head *net_list) diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 92ee853d43e6..3a31e241c647 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -890,7 +890,7 @@ static __net_init int ife_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, ife_net_id); - return tc_action_net_init(tn, &act_ife_ops); + return tc_action_net_init(net, tn, &act_ife_ops); } static void __net_exit ife_exit_net(struct list_head *net_list) diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index ce2c30a591d2..214a03d405cf 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -61,12 +61,13 @@ static int ipt_init_target(struct net *net, struct xt_entry_target *t, return 0; } -static void ipt_destroy_target(struct xt_entry_target *t) +static void ipt_destroy_target(struct xt_entry_target *t, struct net *net) { struct xt_tgdtor_param par = { .target = t->u.kernel.target, .targinfo = t->data, .family = NFPROTO_IPV4, + .net = net, }; if (par.target->destroy != NULL) par.target->destroy(&par); @@ -78,7 +79,7 @@ static void tcf_ipt_release(struct tc_action *a) struct tcf_ipt *ipt = to_ipt(a); if (ipt->tcfi_t) { - ipt_destroy_target(ipt->tcfi_t); + ipt_destroy_target(ipt->tcfi_t, a->idrinfo->net); kfree(ipt->tcfi_t); } kfree(ipt->tcfi_tname); @@ -180,7 +181,7 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, spin_lock_bh(&ipt->tcf_lock); if (ret != ACT_P_CREATED) { - ipt_destroy_target(ipt->tcfi_t); + ipt_destroy_target(ipt->tcfi_t, net); kfree(ipt->tcfi_tname); kfree(ipt->tcfi_t); } @@ -350,7 +351,7 @@ static __net_init int ipt_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, ipt_net_id); - return tc_action_net_init(tn, &act_ipt_ops); + return tc_action_net_init(net, tn, &act_ipt_ops); } static void __net_exit ipt_exit_net(struct list_head *net_list) @@ -399,7 +400,7 @@ static __net_init int xt_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, xt_net_id); - return tc_action_net_init(tn, &act_xt_ops); + return tc_action_net_init(net, tn, &act_xt_ops); } static void __net_exit xt_exit_net(struct list_head *net_list) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index be3f88dfc37e..9d1bf508075a 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -453,7 +453,7 @@ static __net_init int mirred_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, mirred_net_id); - return tc_action_net_init(tn, &act_mirred_ops); + return tc_action_net_init(net, tn, &act_mirred_ops); } static void __net_exit mirred_exit_net(struct list_head *net_list) diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index 0f299e3b618c..e168df0e008a 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -375,7 +375,7 @@ static __net_init int mpls_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, mpls_net_id); - return tc_action_net_init(tn, &act_mpls_ops); + return tc_action_net_init(net, tn, &act_mpls_ops); } static void __net_exit mpls_exit_net(struct list_head *net_list) diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 7b858c11b1b5..ea4c5359e7df 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -327,7 +327,7 @@ static __net_init int nat_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, nat_net_id); - return tc_action_net_init(tn, &act_nat_ops); + return tc_action_net_init(net, tn, &act_nat_ops); } static void __net_exit nat_exit_net(struct list_head *net_list) diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 17360c6faeaa..cdfaa79382a2 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -498,7 +498,7 @@ static __net_init int pedit_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, pedit_net_id); - return tc_action_net_init(tn, &act_pedit_ops); + return tc_action_net_init(net, tn, &act_pedit_ops); } static void __net_exit pedit_exit_net(struct list_head *net_list) diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 49cec3e64a4d..6315e0f8d26e 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -371,7 +371,7 @@ static __net_init int police_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, police_net_id); - return tc_action_net_init(tn, &act_police_ops); + return tc_action_net_init(net, tn, &act_police_ops); } static void __net_exit police_exit_net(struct list_head *net_list) diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 595308d60133..10229124a992 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -102,13 +102,17 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); s->rate = rate; s->psample_group_num = psample_group_num; - RCU_INIT_POINTER(s->psample_group, psample_group); + rcu_swap_protected(s->psample_group, psample_group, + lockdep_is_held(&s->tcf_lock)); if (tb[TCA_SAMPLE_TRUNC_SIZE]) { s->truncate = true; s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]); } spin_unlock_bh(&s->tcf_lock); + + if (psample_group) + psample_group_put(psample_group); if (goto_ch) tcf_chain_put_by_act(goto_ch); @@ -265,7 +269,7 @@ static __net_init int sample_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, sample_net_id); - return tc_action_net_init(tn, &act_sample_ops); + return tc_action_net_init(net, tn, &act_sample_ops); } static void __net_exit sample_exit_net(struct list_head *net_list) diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 33aefa25b545..6120e56117ca 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -232,7 +232,7 @@ static __net_init int simp_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, simp_net_id); - return tc_action_net_init(tn, &act_simp_ops); + return tc_action_net_init(net, tn, &act_simp_ops); } static void __net_exit simp_exit_net(struct list_head *net_list) diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 37dced00b63d..6a8d3337c577 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -336,7 +336,7 @@ static __net_init int skbedit_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); - return tc_action_net_init(tn, &act_skbedit_ops); + return tc_action_net_init(net, tn, &act_skbedit_ops); } static void __net_exit skbedit_exit_net(struct list_head *net_list) diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 7da3518e18ef..888437f97ba6 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -287,7 +287,7 @@ static __net_init int skbmod_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, skbmod_net_id); - return tc_action_net_init(tn, &act_skbmod_ops); + return tc_action_net_init(net, tn, &act_skbmod_ops); } static void __net_exit skbmod_exit_net(struct list_head *net_list) diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 6d0debdc9b97..2f83a79f76aa 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -600,7 +600,7 @@ static __net_init int tunnel_key_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); - return tc_action_net_init(tn, &act_tunnel_key_ops); + return tc_action_net_init(net, tn, &act_tunnel_key_ops); } static void __net_exit tunnel_key_exit_net(struct list_head *net_list) diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index a3c9eea1ee8a..287a30bf8930 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -334,7 +334,7 @@ static __net_init int vlan_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, vlan_net_id); - return tc_action_net_init(tn, &act_vlan_ops); + return tc_action_net_init(net, tn, &act_vlan_ops); } static void __net_exit vlan_exit_net(struct list_head *net_list) diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index 732e109c3055..810645b5c086 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -181,11 +181,6 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch) s64 credits; int len; - if (atomic64_read(&q->port_rate) == -1) { - WARN_ONCE(1, "cbs: dequeue() called with unknown port rate."); - return NULL; - } - if (q->credits < 0) { credits = timediff_to_credits(now - q->last, q->idleslope); @@ -303,11 +298,19 @@ static int cbs_enable_offload(struct net_device *dev, struct cbs_sched_data *q, static void cbs_set_port_rate(struct net_device *dev, struct cbs_sched_data *q) { struct ethtool_link_ksettings ecmd; + int speed = SPEED_10; int port_rate = -1; + int err; + + err = __ethtool_get_link_ksettings(dev, &ecmd); + if (err < 0) + goto skip; + + if (ecmd.base.speed != SPEED_UNKNOWN) + speed = ecmd.base.speed; - if (!__ethtool_get_link_ksettings(dev, &ecmd) && - ecmd.base.speed != SPEED_UNKNOWN) - port_rate = ecmd.base.speed * 1000 * BYTES_PER_KBIT; +skip: + port_rate = speed * 1000 * BYTES_PER_KBIT; atomic64_set(&q->port_rate, port_rate); netdev_dbg(dev, "cbs: set %s's port_rate to: %lld, linkspeed: %d\n", diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 11c03cf4aa74..137db1cbde85 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -624,8 +624,12 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, err = skb_array_produce(q, skb); - if (unlikely(err)) - return qdisc_drop_cpu(skb, qdisc, to_free); + if (unlikely(err)) { + if (qdisc_is_percpu_stats(qdisc)) + return qdisc_drop_cpu(skb, qdisc, to_free); + else + return qdisc_drop(skb, qdisc, to_free); + } qdisc_update_stats_at_enqueue(qdisc, pkt_len); return NET_XMIT_SUCCESS; @@ -688,11 +692,14 @@ static void pfifo_fast_reset(struct Qdisc *qdisc) kfree_skb(skb); } - for_each_possible_cpu(i) { - struct gnet_stats_queue *q = per_cpu_ptr(qdisc->cpu_qstats, i); + if (qdisc_is_percpu_stats(qdisc)) { + for_each_possible_cpu(i) { + struct gnet_stats_queue *q; - q->backlog = 0; - q->qlen = 0; + q = per_cpu_ptr(qdisc->cpu_qstats, i); + q->backlog = 0; + q->qlen = 0; + } } } diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index e25d414ae12f..8d8bc2ec5cd6 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -477,11 +477,6 @@ static struct sk_buff *taprio_dequeue(struct Qdisc *sch) u32 gate_mask; int i; - if (atomic64_read(&q->picos_per_byte) == -1) { - WARN_ONCE(1, "taprio: dequeue() called with unknown picos per byte."); - return NULL; - } - rcu_read_lock(); entry = rcu_dereference(q->current_entry); /* if there's no entry, it means that the schedule didn't @@ -958,12 +953,20 @@ static void taprio_set_picos_per_byte(struct net_device *dev, struct taprio_sched *q) { struct ethtool_link_ksettings ecmd; - int picos_per_byte = -1; + int speed = SPEED_10; + int picos_per_byte; + int err; - if (!__ethtool_get_link_ksettings(dev, &ecmd) && - ecmd.base.speed != SPEED_UNKNOWN) - picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8, - ecmd.base.speed * 1000 * 1000); + err = __ethtool_get_link_ksettings(dev, &ecmd); + if (err < 0) + goto skip; + + if (ecmd.base.speed != SPEED_UNKNOWN) + speed = ecmd.base.speed; + +skip: + picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8, + speed * 1000 * 1000); atomic64_set(&q->picos_per_byte, picos_per_byte); netdev_dbg(dev, "taprio: set %s's picos_per_byte to: %lld, linkspeed: %d\n", @@ -1249,6 +1252,10 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt, */ q->clockid = -1; + spin_lock(&taprio_list_lock); + list_add(&q->taprio_list, &taprio_list); + spin_unlock(&taprio_list_lock); + if (sch->parent != TC_H_ROOT) return -EOPNOTSUPP; @@ -1266,10 +1273,6 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt, if (!opt) return -EINVAL; - spin_lock(&taprio_list_lock); - list_add(&q->taprio_list, &taprio_list); - spin_unlock(&taprio_list_lock); - for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *dev_queue; struct Qdisc *qdisc; |