diff options
Diffstat (limited to 'net')
31 files changed, 396 insertions, 183 deletions
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index ca04163635da..e6b7fecb3af1 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -64,7 +64,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) br_flood_deliver(br, skb, false); goto out; } - if (br_multicast_rcv(br, NULL, skb)) { + if (br_multicast_rcv(br, NULL, skb, vid)) { kfree_skb(skb); goto out; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index a2fd37ec35f7..7e73c32e205d 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -80,7 +80,7 @@ int br_handle_frame_finish(struct sk_buff *skb) br_fdb_update(br, p, eth_hdr(skb)->h_source, vid); if (!is_broadcast_ether_addr(dest) && is_multicast_ether_addr(dest) && - br_multicast_rcv(br, p, skb)) + br_multicast_rcv(br, p, skb, vid)) goto drop; if (p->state == BR_STATE_LEARNING) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 8b0b610ca2c9..686284ff3d6a 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -947,7 +947,8 @@ void br_multicast_disable_port(struct net_bridge_port *port) static int br_ip4_multicast_igmp3_report(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, + u16 vid) { struct igmpv3_report *ih; struct igmpv3_grec *grec; @@ -957,12 +958,10 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, int type; int err = 0; __be32 group; - u16 vid = 0; if (!pskb_may_pull(skb, sizeof(*ih))) return -EINVAL; - br_vlan_get_tag(skb, &vid); ih = igmpv3_report_hdr(skb); num = ntohs(ih->ngrec); len = sizeof(*ih); @@ -1005,7 +1004,8 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, #if IS_ENABLED(CONFIG_IPV6) static int br_ip6_multicast_mld2_report(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, + u16 vid) { struct icmp6hdr *icmp6h; struct mld2_grec *grec; @@ -1013,12 +1013,10 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, int len; int num; int err = 0; - u16 vid = 0; if (!pskb_may_pull(skb, sizeof(*icmp6h))) return -EINVAL; - br_vlan_get_tag(skb, &vid); icmp6h = icmp6_hdr(skb); num = ntohs(icmp6h->icmp6_dataun.un_data16[1]); len = sizeof(*icmp6h); @@ -1141,7 +1139,8 @@ static void br_multicast_query_received(struct net_bridge *br, static int br_ip4_multicast_query(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, + u16 vid) { const struct iphdr *iph = ip_hdr(skb); struct igmphdr *ih = igmp_hdr(skb); @@ -1153,7 +1152,6 @@ static int br_ip4_multicast_query(struct net_bridge *br, unsigned long now = jiffies; __be32 group; int err = 0; - u16 vid = 0; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || @@ -1189,7 +1187,6 @@ static int br_ip4_multicast_query(struct net_bridge *br, if (!group) goto out; - br_vlan_get_tag(skb, &vid); mp = br_mdb_ip4_get(mlock_dereference(br->mdb, br), group, vid); if (!mp) goto out; @@ -1219,7 +1216,8 @@ out: #if IS_ENABLED(CONFIG_IPV6) static int br_ip6_multicast_query(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, + u16 vid) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct mld_msg *mld; @@ -1231,7 +1229,6 @@ static int br_ip6_multicast_query(struct net_bridge *br, unsigned long now = jiffies; const struct in6_addr *group = NULL; int err = 0; - u16 vid = 0; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || @@ -1265,7 +1262,6 @@ static int br_ip6_multicast_query(struct net_bridge *br, if (!group) goto out; - br_vlan_get_tag(skb, &vid); mp = br_mdb_ip6_get(mlock_dereference(br->mdb, br), group, vid); if (!mp) goto out; @@ -1439,7 +1435,8 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br, static int br_multicast_ipv4_rcv(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, + u16 vid) { struct sk_buff *skb2 = skb; const struct iphdr *iph; @@ -1447,7 +1444,6 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, unsigned int len; unsigned int offset; int err; - u16 vid = 0; /* We treat OOM as packet loss for now. */ if (!pskb_may_pull(skb, sizeof(*iph))) @@ -1508,7 +1504,6 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, err = 0; - br_vlan_get_tag(skb2, &vid); BR_INPUT_SKB_CB(skb)->igmp = 1; ih = igmp_hdr(skb2); @@ -1519,10 +1514,10 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, err = br_ip4_multicast_add_group(br, port, ih->group, vid); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: - err = br_ip4_multicast_igmp3_report(br, port, skb2); + err = br_ip4_multicast_igmp3_report(br, port, skb2, vid); break; case IGMP_HOST_MEMBERSHIP_QUERY: - err = br_ip4_multicast_query(br, port, skb2); + err = br_ip4_multicast_query(br, port, skb2, vid); break; case IGMP_HOST_LEAVE_MESSAGE: br_ip4_multicast_leave_group(br, port, ih->group, vid); @@ -1540,7 +1535,8 @@ err_out: #if IS_ENABLED(CONFIG_IPV6) static int br_multicast_ipv6_rcv(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, + u16 vid) { struct sk_buff *skb2; const struct ipv6hdr *ip6h; @@ -1550,7 +1546,6 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, unsigned int len; int offset; int err; - u16 vid = 0; if (!pskb_may_pull(skb, sizeof(*ip6h))) return -EINVAL; @@ -1640,7 +1635,6 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, err = 0; - br_vlan_get_tag(skb, &vid); BR_INPUT_SKB_CB(skb)->igmp = 1; switch (icmp6_type) { @@ -1657,10 +1651,10 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, break; } case ICMPV6_MLD2_REPORT: - err = br_ip6_multicast_mld2_report(br, port, skb2); + err = br_ip6_multicast_mld2_report(br, port, skb2, vid); break; case ICMPV6_MGM_QUERY: - err = br_ip6_multicast_query(br, port, skb2); + err = br_ip6_multicast_query(br, port, skb2, vid); break; case ICMPV6_MGM_REDUCTION: { @@ -1681,7 +1675,7 @@ out: #endif int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, u16 vid) { BR_INPUT_SKB_CB(skb)->igmp = 0; BR_INPUT_SKB_CB(skb)->mrouters_only = 0; @@ -1691,10 +1685,10 @@ int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, switch (skb->protocol) { case htons(ETH_P_IP): - return br_multicast_ipv4_rcv(br, port, skb); + return br_multicast_ipv4_rcv(br, port, skb, vid); #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): - return br_multicast_ipv6_rcv(br, port, skb); + return br_multicast_ipv6_rcv(br, port, skb, vid); #endif } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index e14c33b42f75..2e8244efb262 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -451,7 +451,8 @@ extern int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __us extern unsigned int br_mdb_rehash_seq; extern int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb); + struct sk_buff *skb, + u16 vid); extern struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, struct sk_buff *skb, u16 vid); extern void br_multicast_add_port(struct net_bridge_port *port); @@ -522,7 +523,8 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br, #else static inline int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, + u16 vid) { return 0; } diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index 518093802d1d..7c470c371e14 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -181,6 +181,7 @@ static void ebt_ulog_packet(struct net *net, unsigned int hooknr, ub->qlen++; pm = nlmsg_data(nlh); + memset(pm, 0, sizeof(*pm)); /* Fill in the ulog data */ pm->version = EBT_ULOG_VERSION; @@ -193,8 +194,6 @@ static void ebt_ulog_packet(struct net *net, unsigned int hooknr, pm->hook = hooknr; if (uloginfo->prefix != NULL) strcpy(pm->prefix, uloginfo->prefix); - else - *(pm->prefix) = '\0'; if (in) { strcpy(pm->physindev, in->name); @@ -204,16 +203,14 @@ static void ebt_ulog_packet(struct net *net, unsigned int hooknr, strcpy(pm->indev, br_port_get_rcu(in)->br->dev->name); else strcpy(pm->indev, in->name); - } else - pm->indev[0] = pm->physindev[0] = '\0'; + } if (out) { /* If out exists, then out is a bridge port */ strcpy(pm->physoutdev, out->name); /* rcu_read_lock()ed by nf_hook_slow */ strcpy(pm->outdev, br_port_get_rcu(out)->br->dev->name); - } else - pm->outdev[0] = pm->physoutdev[0] = '\0'; + } if (skb_copy_bits(skb, -ETH_HLEN, pm->data, copy_len) < 0) BUG(); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 8d7d0dd72db2..143b6fdb9647 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -40,7 +40,7 @@ again: struct iphdr _iph; ip: iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); - if (!iph) + if (!iph || iph->ihl < 5) return false; if (ip_is_fragment(iph)) diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index d954b56b4e47..325dee863e46 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1344,17 +1344,19 @@ int netdev_register_kobject(struct net_device *net) return error; } -int netdev_class_create_file(struct class_attribute *class_attr) +int netdev_class_create_file_ns(struct class_attribute *class_attr, + const void *ns) { - return class_create_file(&net_class, class_attr); + return class_create_file_ns(&net_class, class_attr, ns); } -EXPORT_SYMBOL(netdev_class_create_file); +EXPORT_SYMBOL(netdev_class_create_file_ns); -void netdev_class_remove_file(struct class_attribute *class_attr) +void netdev_class_remove_file_ns(struct class_attribute *class_attr, + const void *ns) { - class_remove_file(&net_class, class_attr); + class_remove_file_ns(&net_class, class_attr, ns); } -EXPORT_SYMBOL(netdev_class_remove_file); +EXPORT_SYMBOL(netdev_class_remove_file_ns); int netdev_kobject_init(void) { diff --git a/net/core/netpoll.c b/net/core/netpoll.c index fc75c9e461b8..8f971990677c 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -636,8 +636,9 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo netpoll_send_skb(np, send_skb); - /* If there are several rx_hooks for the same address, - we're fine by sending a single reply */ + /* If there are several rx_skb_hooks for the same + * address we're fine by sending a single reply + */ break; } spin_unlock_irqrestore(&npinfo->rx_lock, flags); @@ -719,8 +720,9 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo netpoll_send_skb(np, send_skb); - /* If there are several rx_hooks for the same address, - we're fine by sending a single reply */ + /* If there are several rx_skb_hooks for the same + * address, we're fine by sending a single reply + */ break; } spin_unlock_irqrestore(&npinfo->rx_lock, flags); @@ -756,11 +758,12 @@ static bool pkt_is_ns(struct sk_buff *skb) int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) { - int proto, len, ulen; - int hits = 0; + int proto, len, ulen, data_len; + int hits = 0, offset; const struct iphdr *iph; struct udphdr *uh; struct netpoll *np, *tmp; + uint16_t source; if (list_empty(&npinfo->rx_np)) goto out; @@ -820,7 +823,10 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) len -= iph->ihl*4; uh = (struct udphdr *)(((char *)iph) + iph->ihl*4); + offset = (unsigned char *)(uh + 1) - skb->data; ulen = ntohs(uh->len); + data_len = skb->len - offset; + source = ntohs(uh->source); if (ulen != len) goto out; @@ -834,9 +840,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) if (np->local_port && np->local_port != ntohs(uh->dest)) continue; - np->rx_hook(np, ntohs(uh->source), - (char *)(uh+1), - ulen - sizeof(struct udphdr)); + np->rx_skb_hook(np, source, skb, offset, data_len); hits++; } } else { @@ -859,7 +863,10 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; uh = udp_hdr(skb); + offset = (unsigned char *)(uh + 1) - skb->data; ulen = ntohs(uh->len); + data_len = skb->len - offset; + source = ntohs(uh->source); if (ulen != skb->len) goto out; if (udp6_csum_init(skb, uh, IPPROTO_UDP)) @@ -872,9 +879,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) if (np->local_port && np->local_port != ntohs(uh->dest)) continue; - np->rx_hook(np, ntohs(uh->source), - (char *)(uh+1), - ulen - sizeof(struct udphdr)); + np->rx_skb_hook(np, source, skb, offset, data_len); hits++; } #endif @@ -1062,7 +1067,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) npinfo->netpoll = np; - if (np->rx_hook) { + if (np->rx_skb_hook) { spin_lock_irqsave(&npinfo->rx_lock, flags); npinfo->rx_flags |= NETPOLL_RX_ENABLED; list_add_tail(&np->rx, &npinfo->rx_np); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 85a4f21aac1a..59da7cde0724 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -271,6 +271,11 @@ unsigned int arpt_do_table(struct sk_buff *skb, local_bh_disable(); addend = xt_write_recseq_begin(); private = table->private; + /* + * Ensure we load private-> members after we've fetched the base + * pointer. + */ + smp_read_barrier_depends(); table_base = private->entries[smp_processor_id()]; e = get_entry(table_base, private->hook_entry[hook]); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index d23118d95ff9..718dfbd30cbe 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -327,6 +327,11 @@ ipt_do_table(struct sk_buff *skb, addend = xt_write_recseq_begin(); private = table->private; cpu = smp_processor_id(); + /* + * Ensure we load private-> members after we've fetched the base + * pointer. + */ + smp_read_barrier_depends(); table_base = private->entries[cpu]; jumpstack = (struct ipt_entry **)private->jumpstack[cpu]; stackptr = per_cpu_ptr(private->stackptr, cpu); diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index cbc22158af49..9cb993cd224b 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -220,6 +220,7 @@ static void ipt_ulog_packet(struct net *net, ub->qlen++; pm = nlmsg_data(nlh); + memset(pm, 0, sizeof(*pm)); /* We might not have a timestamp, get one */ if (skb->tstamp.tv64 == 0) @@ -238,8 +239,6 @@ static void ipt_ulog_packet(struct net *net, } else if (loginfo->prefix[0] != '\0') strncpy(pm->prefix, loginfo->prefix, sizeof(pm->prefix)); - else - *(pm->prefix) = '\0'; if (in && in->hard_header_len > 0 && skb->mac_header != skb->network_header && @@ -251,13 +250,9 @@ static void ipt_ulog_packet(struct net *net, if (in) strncpy(pm->indev_name, in->name, sizeof(pm->indev_name)); - else - pm->indev_name[0] = '\0'; if (out) strncpy(pm->outdev_name, out->name, sizeof(pm->outdev_name)); - else - pm->outdev_name[0] = '\0'; /* copy_len <= skb->len, so can't fail. */ if (skb_copy_bits(skb, 0, pm->payload, copy_len) < 0) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a16b01b537ba..068c8fb0d158 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2856,7 +2856,8 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, * left edge of the send window. * See draft-ietf-tcplw-high-performance-00, section 3.3. */ - if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) + if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && + flag & FLAG_ACKED) seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr; if (seq_rtt < 0) @@ -2871,14 +2872,19 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, } /* Compute time elapsed between (last) SYNACK and the ACK completing 3WHS. */ -static void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req) +static void tcp_synack_rtt_meas(struct sock *sk, const u32 synack_stamp) { struct tcp_sock *tp = tcp_sk(sk); s32 seq_rtt = -1; - if (tp->lsndtime && !tp->total_retrans) - seq_rtt = tcp_time_stamp - tp->lsndtime; - tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1); + if (synack_stamp && !tp->total_retrans) + seq_rtt = tcp_time_stamp - synack_stamp; + + /* If the ACK acks both the SYNACK and the (Fast Open'd) data packets + * sent in SYN_RECV, SYNACK RTT is the smooth RTT computed in tcp_ack() + */ + if (!tp->srtt) + tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1); } static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) @@ -2981,6 +2987,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, s32 seq_rtt = -1; s32 ca_seq_rtt = -1; ktime_t last_ackt = net_invalid_timestamp(); + bool rtt_update; while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); @@ -3057,14 +3064,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) flag |= FLAG_SACK_RENEGING; - if (tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt) || - (flag & FLAG_ACKED)) - tcp_rearm_rto(sk); + rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt); if (flag & FLAG_ACKED) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; + tcp_rearm_rto(sk); if (unlikely(icsk->icsk_mtup.probe_size && !after(tp->mtu_probe.probe_seq_end, tp->snd_una))) { tcp_mtup_probe_success(sk); @@ -3103,6 +3109,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, ca_ops->pkts_acked(sk, pkts_acked, rtt_us); } + } else if (skb && rtt_update && sack_rtt >= 0 && + sack_rtt > (s32)(now - TCP_SKB_CB(skb)->when)) { + /* Do not re-arm RTO if the sack RTT is measured from data sent + * after when the head was last (re)transmitted. Otherwise the + * timeout may continue to extend in loss recovery. + */ + tcp_rearm_rto(sk); } #if FASTRETRANS_DEBUG > 0 @@ -5587,6 +5600,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, struct request_sock *req; int queued = 0; bool acceptable; + u32 synack_stamp; tp->rx_opt.saw_tstamp = 0; @@ -5669,9 +5683,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, * so release it. */ if (req) { + synack_stamp = tcp_rsk(req)->snt_synack; tp->total_retrans = req->num_retrans; reqsk_fastopen_remove(sk, req, false); } else { + synack_stamp = tp->lsndtime; /* Make sure socket is routed, for correct metrics. */ icsk->icsk_af_ops->rebuild_header(sk); tcp_init_congestion_control(sk); @@ -5694,7 +5710,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, tp->snd_una = TCP_SKB_CB(skb)->ack_seq; tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale; tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); - tcp_synack_rtt_meas(sk, req); + tcp_synack_rtt_meas(sk, synack_stamp); if (tp->rx_opt.tstamp_ok) tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 3a7525e6c086..533c58a5cfb7 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -18,6 +18,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); + unsigned int sum_truesize = 0; struct tcphdr *th; unsigned int thlen; unsigned int seq; @@ -102,13 +103,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, if (copy_destructor) { skb->destructor = gso_skb->destructor; skb->sk = gso_skb->sk; - /* {tcp|sock}_wfree() use exact truesize accounting : - * sum(skb->truesize) MUST be exactly be gso_skb->truesize - * So we account mss bytes of 'true size' for each segment. - * The last segment will contain the remaining. - */ - skb->truesize = mss; - gso_skb->truesize -= mss; + sum_truesize += skb->truesize; } skb = skb->next; th = tcp_hdr(skb); @@ -125,7 +120,9 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, if (copy_destructor) { swap(gso_skb->sk, skb->sk); swap(gso_skb->destructor, skb->destructor); - swap(gso_skb->truesize, skb->truesize); + sum_truesize += skb->truesize; + atomic_add(sum_truesize - gso_skb->truesize, + &skb->sk->sk_wmem_alloc); } delta = htonl(oldlen + (skb_tail_pointer(skb) - diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index ccde54248c8c..e1a63930a967 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -104,10 +104,14 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) const struct iphdr *iph = ip_hdr(skb); u8 *xprth = skb_network_header(skb) + iph->ihl * 4; struct flowi4 *fl4 = &fl->u.ip4; + int oif = 0; + + if (skb_dst(skb)) + oif = skb_dst(skb)->dev->ifindex; memset(fl4, 0, sizeof(struct flowi4)); fl4->flowi4_mark = skb->mark; - fl4->flowi4_oif = skb_dst(skb)->dev->ifindex; + fl4->flowi4_oif = reverse ? skb->skb_iif : oif; if (!ip_is_fragment(iph)) { switch (iph->protocol) { @@ -236,7 +240,7 @@ static struct dst_ops xfrm4_dst_ops = { .destroy = xfrm4_dst_destroy, .ifdown = xfrm4_dst_ifdown, .local_out = __ip_local_out, - .gc_thresh = 1024, + .gc_thresh = 32768, }; static struct xfrm_policy_afinfo xfrm4_policy_afinfo = { diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 44400c216dc6..710238f58aa9 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -349,6 +349,11 @@ ip6t_do_table(struct sk_buff *skb, local_bh_disable(); addend = xt_write_recseq_begin(); private = table->private; + /* + * Ensure we load private-> members after we've fetched the base + * pointer. + */ + smp_read_barrier_depends(); cpu = smp_processor_id(); table_base = private->entries[cpu]; jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f54e3a101098..04e17b3309fb 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1087,10 +1087,13 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) if (rt->rt6i_genid != rt_genid_ipv6(dev_net(rt->dst.dev))) return NULL; - if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) - return dst; + if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie)) + return NULL; - return NULL; + if (rt6_check_expired(rt)) + return NULL; + + return dst; } static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 08ed2772b7aa..5f8e128c512d 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -135,10 +135,14 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) struct ipv6_opt_hdr *exthdr; const unsigned char *nh = skb_network_header(skb); u8 nexthdr = nh[IP6CB(skb)->nhoff]; + int oif = 0; + + if (skb_dst(skb)) + oif = skb_dst(skb)->dev->ifindex; memset(fl6, 0, sizeof(struct flowi6)); fl6->flowi6_mark = skb->mark; - fl6->flowi6_oif = skb_dst(skb)->dev->ifindex; + fl6->flowi6_oif = reverse ? skb->skb_iif : oif; fl6->daddr = reverse ? hdr->saddr : hdr->daddr; fl6->saddr = reverse ? hdr->daddr : hdr->saddr; @@ -285,7 +289,7 @@ static struct dst_ops xfrm6_dst_ops = { .destroy = xfrm6_dst_destroy, .ifdown = xfrm6_dst_ifdown, .local_out = __ip6_local_out, - .gc_thresh = 1024, + .gc_thresh = 32768, }; static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 8b03028cca69..227aa11e8409 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -845,8 +845,13 @@ xt_replace_table(struct xt_table *table, return NULL; } - table->private = newinfo; newinfo->initial_entries = private->initial_entries; + /* + * Ensure contents of newinfo are visible before assigning to + * private. + */ + smp_wmb(); + table->private = newinfo; /* * Even though table entries have now been swapped, other CPU's diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c index 1e2fae32f81b..ed00fef58996 100644 --- a/net/netfilter/xt_NFQUEUE.c +++ b/net/netfilter/xt_NFQUEUE.c @@ -147,6 +147,7 @@ nfqueue_tg_v3(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_NFQ_info_v3 *info = par->targinfo; u32 queue = info->queuenum; + int ret; if (info->queues_total > 1) { if (info->flags & NFQ_FLAG_CPU_FANOUT) { @@ -157,7 +158,11 @@ nfqueue_tg_v3(struct sk_buff *skb, const struct xt_action_param *par) queue = nfqueue_hash(skb, par); } - return NF_QUEUE_NR(queue); + ret = NF_QUEUE_NR(queue); + if (info->flags & NFQ_FLAG_BYPASS) + ret |= NF_VERDICT_FLAG_QUEUE_BYPASS; + + return ret; } static struct xt_target nfqueue_tg_reg[] __read_mostly = { diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c index c3235675f359..5c2dab276109 100644 --- a/net/openvswitch/dp_notify.c +++ b/net/openvswitch/dp_notify.c @@ -65,8 +65,7 @@ void ovs_dp_notify_wq(struct work_struct *work) continue; netdev_vport = netdev_vport_priv(vport); - if (netdev_vport->dev->reg_state == NETREG_UNREGISTERED || - netdev_vport->dev->reg_state == NETREG_UNREGISTERING) + if (!(netdev_vport->dev->priv_flags & IFF_OVS_DATAPATH)) dp_detach_port_notify(vport); } } @@ -88,6 +87,10 @@ static int dp_device_event(struct notifier_block *unused, unsigned long event, return NOTIFY_DONE; if (event == NETDEV_UNREGISTER) { + /* upper_dev_unlink and decrement promisc immediately */ + ovs_netdev_detach_dev(vport); + + /* schedule vport destroy, dev_put and genl notification */ ovs_net = net_generic(dev_net(dev), ovs_net_id); queue_work(system_wq, &ovs_net->dp_notify_work); } diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 09d93c13cfd6..d21f77d875ba 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -150,15 +150,25 @@ static void free_port_rcu(struct rcu_head *rcu) ovs_vport_free(vport_from_priv(netdev_vport)); } -static void netdev_destroy(struct vport *vport) +void ovs_netdev_detach_dev(struct vport *vport) { struct netdev_vport *netdev_vport = netdev_vport_priv(vport); - rtnl_lock(); + ASSERT_RTNL(); netdev_vport->dev->priv_flags &= ~IFF_OVS_DATAPATH; netdev_rx_handler_unregister(netdev_vport->dev); - netdev_upper_dev_unlink(netdev_vport->dev, get_dpdev(vport->dp)); + netdev_upper_dev_unlink(netdev_vport->dev, + netdev_master_upper_dev_get(netdev_vport->dev)); dev_set_promiscuity(netdev_vport->dev, -1); +} + +static void netdev_destroy(struct vport *vport) +{ + struct netdev_vport *netdev_vport = netdev_vport_priv(vport); + + rtnl_lock(); + if (netdev_vport->dev->priv_flags & IFF_OVS_DATAPATH) + ovs_netdev_detach_dev(vport); rtnl_unlock(); call_rcu(&netdev_vport->rcu, free_port_rcu); diff --git a/net/openvswitch/vport-netdev.h b/net/openvswitch/vport-netdev.h index dd298b5c5cdb..8df01c1127e5 100644 --- a/net/openvswitch/vport-netdev.h +++ b/net/openvswitch/vport-netdev.h @@ -39,5 +39,6 @@ netdev_vport_priv(const struct vport *vport) } const char *ovs_netdev_get_name(const struct vport *); +void ovs_netdev_detach_dev(struct vport *); #endif /* vport_netdev.h */ diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index a9dfdda9ed1d..fdc041c57853 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -255,6 +255,7 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) f->socket_hash != sk->sk_hash)) { f->credit = q->initial_quantum; f->socket_hash = sk->sk_hash; + f->time_next_packet = 0ULL; } return f; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e7b2d4fe2b6a..96a55910262c 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -279,7 +279,9 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, sctp_v6_to_addr(&dst_saddr, &fl6->saddr, htons(bp->port)); rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { - if (!laddr->valid || (laddr->state != SCTP_ADDR_SRC)) + if (!laddr->valid || laddr->state == SCTP_ADDR_DEL || + (laddr->state != SCTP_ADDR_SRC && + !asoc->src_out_of_asoc_ok)) continue; /* Do not compare against v4 addrs */ diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 666c66842799..1a6eef39ab2f 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -860,7 +860,6 @@ static void sctp_cmd_delete_tcb(sctp_cmd_seq_t *cmds, (!asoc->temp) && (sk->sk_shutdown != SHUTDOWN_MASK)) return; - BUG_ON(asoc->peer.primary_path == NULL); sctp_unhash_established(asoc); sctp_association_free(asoc); } diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 084656671d6e..97912b40c254 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -420,41 +420,53 @@ static void gss_encode_v0_msg(struct gss_upcall_msg *gss_msg) memcpy(gss_msg->databuf, &uid, sizeof(uid)); gss_msg->msg.data = gss_msg->databuf; gss_msg->msg.len = sizeof(uid); - BUG_ON(sizeof(uid) > UPCALL_BUF_LEN); + + BUILD_BUG_ON(sizeof(uid) > sizeof(gss_msg->databuf)); } -static void gss_encode_v1_msg(struct gss_upcall_msg *gss_msg, +static int gss_encode_v1_msg(struct gss_upcall_msg *gss_msg, const char *service_name, const char *target_name) { struct gss_api_mech *mech = gss_msg->auth->mech; char *p = gss_msg->databuf; - int len = 0; - - gss_msg->msg.len = sprintf(gss_msg->databuf, "mech=%s uid=%d ", - mech->gm_name, - from_kuid(&init_user_ns, gss_msg->uid)); - p += gss_msg->msg.len; + size_t buflen = sizeof(gss_msg->databuf); + int len; + + len = scnprintf(p, buflen, "mech=%s uid=%d ", mech->gm_name, + from_kuid(&init_user_ns, gss_msg->uid)); + buflen -= len; + p += len; + gss_msg->msg.len = len; if (target_name) { - len = sprintf(p, "target=%s ", target_name); + len = scnprintf(p, buflen, "target=%s ", target_name); + buflen -= len; p += len; gss_msg->msg.len += len; } if (service_name != NULL) { - len = sprintf(p, "service=%s ", service_name); + len = scnprintf(p, buflen, "service=%s ", service_name); + buflen -= len; p += len; gss_msg->msg.len += len; } if (mech->gm_upcall_enctypes) { - len = sprintf(p, "enctypes=%s ", mech->gm_upcall_enctypes); + len = scnprintf(p, buflen, "enctypes=%s ", + mech->gm_upcall_enctypes); + buflen -= len; p += len; gss_msg->msg.len += len; } - len = sprintf(p, "\n"); + len = scnprintf(p, buflen, "\n"); + if (len == 0) + goto out_overflow; gss_msg->msg.len += len; gss_msg->msg.data = gss_msg->databuf; - BUG_ON(gss_msg->msg.len > UPCALL_BUF_LEN); + return 0; +out_overflow: + WARN_ON_ONCE(1); + return -ENOMEM; } static struct gss_upcall_msg * @@ -463,15 +475,15 @@ gss_alloc_msg(struct gss_auth *gss_auth, { struct gss_upcall_msg *gss_msg; int vers; + int err = -ENOMEM; gss_msg = kzalloc(sizeof(*gss_msg), GFP_NOFS); if (gss_msg == NULL) - return ERR_PTR(-ENOMEM); + goto err; vers = get_pipe_version(gss_auth->net); - if (vers < 0) { - kfree(gss_msg); - return ERR_PTR(vers); - } + err = vers; + if (err < 0) + goto err_free_msg; gss_msg->pipe = gss_auth->gss_pipe[vers]->pipe; INIT_LIST_HEAD(&gss_msg->list); rpc_init_wait_queue(&gss_msg->rpc_waitqueue, "RPCSEC_GSS upcall waitq"); @@ -482,10 +494,17 @@ gss_alloc_msg(struct gss_auth *gss_auth, switch (vers) { case 0: gss_encode_v0_msg(gss_msg); + break; default: - gss_encode_v1_msg(gss_msg, service_name, gss_auth->target_name); + err = gss_encode_v1_msg(gss_msg, service_name, gss_auth->target_name); + if (err) + goto err_free_msg; }; return gss_msg; +err_free_msg: + kfree(gss_msg); +err: + return ERR_PTR(err); } static struct gss_upcall_msg * diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 77479606a971..dab09dac8fc7 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -25,12 +25,12 @@ #include <linux/namei.h> #include <linux/mount.h> #include <linux/slab.h> +#include <linux/rcupdate.h> #include <linux/utsname.h> #include <linux/workqueue.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/un.h> -#include <linux/rcupdate.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/addr.h> @@ -264,6 +264,26 @@ void rpc_clients_notifier_unregister(void) return rpc_pipefs_notifier_unregister(&rpc_clients_block); } +static struct rpc_xprt *rpc_clnt_set_transport(struct rpc_clnt *clnt, + struct rpc_xprt *xprt, + const struct rpc_timeout *timeout) +{ + struct rpc_xprt *old; + + spin_lock(&clnt->cl_lock); + old = rcu_dereference_protected(clnt->cl_xprt, + lockdep_is_held(&clnt->cl_lock)); + + if (!xprt_bound(xprt)) + clnt->cl_autobind = 1; + + clnt->cl_timeout = timeout; + rcu_assign_pointer(clnt->cl_xprt, xprt); + spin_unlock(&clnt->cl_lock); + + return old; +} + static void rpc_clnt_set_nodename(struct rpc_clnt *clnt, const char *nodename) { clnt->cl_nodelen = strlen(nodename); @@ -272,12 +292,13 @@ static void rpc_clnt_set_nodename(struct rpc_clnt *clnt, const char *nodename) memcpy(clnt->cl_nodename, nodename, clnt->cl_nodelen); } -static int rpc_client_register(const struct rpc_create_args *args, - struct rpc_clnt *clnt) +static int rpc_client_register(struct rpc_clnt *clnt, + rpc_authflavor_t pseudoflavor, + const char *client_name) { struct rpc_auth_create_args auth_args = { - .pseudoflavor = args->authflavor, - .target_name = args->client_name, + .pseudoflavor = pseudoflavor, + .target_name = client_name, }; struct rpc_auth *auth; struct net *net = rpc_net_ns(clnt); @@ -298,7 +319,7 @@ static int rpc_client_register(const struct rpc_create_args *args, auth = rpcauth_create(&auth_args, clnt); if (IS_ERR(auth)) { dprintk("RPC: Couldn't create auth handle (flavor %u)\n", - args->authflavor); + pseudoflavor); err = PTR_ERR(auth); goto err_auth; } @@ -337,7 +358,8 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, { const struct rpc_program *program = args->program; const struct rpc_version *version; - struct rpc_clnt *clnt = NULL; + struct rpc_clnt *clnt = NULL; + const struct rpc_timeout *timeout; int err; /* sanity check the name before trying to print it */ @@ -365,7 +387,6 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, if (err) goto out_no_clid; - rcu_assign_pointer(clnt->cl_xprt, xprt); clnt->cl_procinfo = version->procs; clnt->cl_maxproc = version->nrprocs; clnt->cl_prog = args->prognumber ? : program->number; @@ -380,16 +401,15 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, INIT_LIST_HEAD(&clnt->cl_tasks); spin_lock_init(&clnt->cl_lock); - if (!xprt_bound(xprt)) - clnt->cl_autobind = 1; - - clnt->cl_timeout = xprt->timeout; + timeout = xprt->timeout; if (args->timeout != NULL) { memcpy(&clnt->cl_timeout_default, args->timeout, sizeof(clnt->cl_timeout_default)); - clnt->cl_timeout = &clnt->cl_timeout_default; + timeout = &clnt->cl_timeout_default; } + rpc_clnt_set_transport(clnt, xprt, timeout); + clnt->cl_rtt = &clnt->cl_rtt_default; rpc_init_rtt(&clnt->cl_rtt_default, clnt->cl_timeout->to_initval); @@ -398,7 +418,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, /* save the nodename */ rpc_clnt_set_nodename(clnt, utsname()->nodename); - err = rpc_client_register(args, clnt); + err = rpc_client_register(clnt, args->authflavor, args->client_name); if (err) goto out_no_path; if (parent) @@ -600,6 +620,80 @@ rpc_clone_client_set_auth(struct rpc_clnt *clnt, rpc_authflavor_t flavor) } EXPORT_SYMBOL_GPL(rpc_clone_client_set_auth); +/** + * rpc_switch_client_transport: switch the RPC transport on the fly + * @clnt: pointer to a struct rpc_clnt + * @args: pointer to the new transport arguments + * @timeout: pointer to the new timeout parameters + * + * This function allows the caller to switch the RPC transport for the + * rpc_clnt structure 'clnt' to allow it to connect to a mirrored NFS + * server, for instance. It assumes that the caller has ensured that + * there are no active RPC tasks by using some form of locking. + * + * Returns zero if "clnt" is now using the new xprt. Otherwise a + * negative errno is returned, and "clnt" continues to use the old + * xprt. + */ +int rpc_switch_client_transport(struct rpc_clnt *clnt, + struct xprt_create *args, + const struct rpc_timeout *timeout) +{ + const struct rpc_timeout *old_timeo; + rpc_authflavor_t pseudoflavor; + struct rpc_xprt *xprt, *old; + struct rpc_clnt *parent; + int err; + + xprt = xprt_create_transport(args); + if (IS_ERR(xprt)) { + dprintk("RPC: failed to create new xprt for clnt %p\n", + clnt); + return PTR_ERR(xprt); + } + + pseudoflavor = clnt->cl_auth->au_flavor; + + old_timeo = clnt->cl_timeout; + old = rpc_clnt_set_transport(clnt, xprt, timeout); + + rpc_unregister_client(clnt); + __rpc_clnt_remove_pipedir(clnt); + + /* + * A new transport was created. "clnt" therefore + * becomes the root of a new cl_parent tree. clnt's + * children, if it has any, still point to the old xprt. + */ + parent = clnt->cl_parent; + clnt->cl_parent = clnt; + + /* + * The old rpc_auth cache cannot be re-used. GSS + * contexts in particular are between a single + * client and server. + */ + err = rpc_client_register(clnt, pseudoflavor, NULL); + if (err) + goto out_revert; + + synchronize_rcu(); + if (parent != clnt) + rpc_release_client(parent); + xprt_put(old); + dprintk("RPC: replaced xprt for clnt %p\n", clnt); + return 0; + +out_revert: + rpc_clnt_set_transport(clnt, old, old_timeo); + clnt->cl_parent = parent; + rpc_client_register(clnt, pseudoflavor, NULL); + xprt_put(xprt); + dprintk("RPC: failed to switch xprt for clnt %p\n", clnt); + return err; +} +EXPORT_SYMBOL_GPL(rpc_switch_client_transport); + /* * Kill all tasks for the given client. * XXX: kill their descendants as well? @@ -772,6 +866,8 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt) atomic_inc(&clnt->cl_count); if (clnt->cl_softrtry) task->tk_flags |= RPC_TASK_SOFT; + if (clnt->cl_noretranstimeo) + task->tk_flags |= RPC_TASK_NO_RETRANS_TIMEOUT; if (sk_memalloc_socks()) { struct rpc_xprt *xprt; @@ -1690,6 +1786,7 @@ call_connect_status(struct rpc_task *task) dprint_status(task); trace_rpc_connect_status(task, status); + task->tk_status = 0; switch (status) { /* if soft mounted, test if we've timed out */ case -ETIMEDOUT: @@ -1698,12 +1795,14 @@ call_connect_status(struct rpc_task *task) case -ECONNREFUSED: case -ECONNRESET: case -ENETUNREACH: + /* retry with existing socket, after a delay */ + rpc_delay(task, 3*HZ); if (RPC_IS_SOFTCONN(task)) break; - /* retry with existing socket, after a delay */ - case 0: case -EAGAIN: - task->tk_status = 0; + task->tk_action = call_bind; + return; + case 0: clnt->cl_stats->netreconn++; task->tk_action = call_transmit; return; @@ -1717,13 +1816,14 @@ call_connect_status(struct rpc_task *task) static void call_transmit(struct rpc_task *task) { + int is_retrans = RPC_WAS_SENT(task); + dprint_status(task); task->tk_action = call_status; if (task->tk_status < 0) return; - task->tk_status = xprt_prepare_transmit(task); - if (task->tk_status != 0) + if (!xprt_prepare_transmit(task)) return; task->tk_action = call_transmit_status; /* Encode here so that rpcsec_gss can use correct sequence number. */ @@ -1742,6 +1842,8 @@ call_transmit(struct rpc_task *task) xprt_transmit(task); if (task->tk_status < 0) return; + if (is_retrans) + task->tk_client->cl_stats->rpcretrans++; /* * On success, ensure that we call xprt_end_transmit() before sleeping * in order to allow access to the socket to other RPC requests. @@ -1811,8 +1913,7 @@ call_bc_transmit(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; - task->tk_status = xprt_prepare_transmit(task); - if (task->tk_status == -EAGAIN) { + if (!xprt_prepare_transmit(task)) { /* * Could not reserve the transport. Try again after the * transport is released. @@ -1900,7 +2001,8 @@ call_status(struct rpc_task *task) rpc_delay(task, 3*HZ); case -ETIMEDOUT: task->tk_action = call_timeout; - if (task->tk_client->cl_discrtry) + if (!(task->tk_flags & RPC_TASK_NO_RETRANS_TIMEOUT) + && task->tk_client->cl_discrtry) xprt_conditional_disconnect(req->rq_xprt, req->rq_connect_cookie); break; @@ -1982,7 +2084,6 @@ call_timeout(struct rpc_task *task) rpcauth_invalcred(task); retry: - clnt->cl_stats->rpcretrans++; task->tk_action = call_bind; task->tk_status = 0; } @@ -2025,7 +2126,6 @@ call_decode(struct rpc_task *task) if (req->rq_rcv_buf.len < 12) { if (!RPC_IS_SOFT(task)) { task->tk_action = call_bind; - clnt->cl_stats->rpcretrans++; goto out_retry; } dprintk("RPC: %s: too small RPC reply size (%d bytes)\n", diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 095363eee764..04199bc8416f 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -205,10 +205,8 @@ int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task) goto out_sleep; } xprt->snd_task = task; - if (req != NULL) { - req->rq_bytes_sent = 0; + if (req != NULL) req->rq_ntrans++; - } return 1; @@ -263,7 +261,6 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task) } if (__xprt_get_cong(xprt, task)) { xprt->snd_task = task; - req->rq_bytes_sent = 0; req->rq_ntrans++; return 1; } @@ -300,10 +297,8 @@ static bool __xprt_lock_write_func(struct rpc_task *task, void *data) req = task->tk_rqstp; xprt->snd_task = task; - if (req) { - req->rq_bytes_sent = 0; + if (req) req->rq_ntrans++; - } return true; } @@ -329,7 +324,6 @@ static bool __xprt_lock_write_cong_func(struct rpc_task *task, void *data) } if (__xprt_get_cong(xprt, task)) { xprt->snd_task = task; - req->rq_bytes_sent = 0; req->rq_ntrans++; return true; } @@ -358,6 +352,11 @@ out_unlock: void xprt_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task) { if (xprt->snd_task == task) { + if (task != NULL) { + struct rpc_rqst *req = task->tk_rqstp; + if (req != NULL) + req->rq_bytes_sent = 0; + } xprt_clear_locked(xprt); __xprt_lock_write_next(xprt); } @@ -375,6 +374,11 @@ EXPORT_SYMBOL_GPL(xprt_release_xprt); void xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task) { if (xprt->snd_task == task) { + if (task != NULL) { + struct rpc_rqst *req = task->tk_rqstp; + if (req != NULL) + req->rq_bytes_sent = 0; + } xprt_clear_locked(xprt); __xprt_lock_write_next_cong(xprt); } @@ -854,24 +858,36 @@ static inline int xprt_has_timer(struct rpc_xprt *xprt) * @task: RPC task about to send a request * */ -int xprt_prepare_transmit(struct rpc_task *task) +bool xprt_prepare_transmit(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; - int err = 0; + bool ret = false; dprintk("RPC: %5u xprt_prepare_transmit\n", task->tk_pid); spin_lock_bh(&xprt->transport_lock); - if (req->rq_reply_bytes_recvd && !req->rq_bytes_sent) { - err = req->rq_reply_bytes_recvd; + if (!req->rq_bytes_sent) { + if (req->rq_reply_bytes_recvd) { + task->tk_status = req->rq_reply_bytes_recvd; + goto out_unlock; + } + if ((task->tk_flags & RPC_TASK_NO_RETRANS_TIMEOUT) + && xprt_connected(xprt) + && req->rq_connect_cookie == xprt->connect_cookie) { + xprt->ops->set_retrans_timeout(task); + rpc_sleep_on(&xprt->pending, task, xprt_timer); + goto out_unlock; + } + } + if (!xprt->ops->reserve_xprt(xprt, task)) { + task->tk_status = -EAGAIN; goto out_unlock; } - if (!xprt->ops->reserve_xprt(xprt, task)) - err = -EAGAIN; + ret = true; out_unlock: spin_unlock_bh(&xprt->transport_lock); - return err; + return ret; } void xprt_end_transmit(struct rpc_task *task) @@ -912,7 +928,6 @@ void xprt_transmit(struct rpc_task *task) } else if (!req->rq_bytes_sent) return; - req->rq_connect_cookie = xprt->connect_cookie; req->rq_xtime = ktime_get(); status = xprt->ops->send_request(task); if (status != 0) { @@ -938,12 +953,14 @@ void xprt_transmit(struct rpc_task *task) /* Don't race with disconnect */ if (!xprt_connected(xprt)) task->tk_status = -ENOTCONN; - else if (!req->rq_reply_bytes_recvd && rpc_reply_expected(task)) { + else { /* * Sleep on the pending queue since * we're expecting a reply. */ - rpc_sleep_on(&xprt->pending, task, xprt_timer); + if (!req->rq_reply_bytes_recvd && rpc_reply_expected(task)) + rpc_sleep_on(&xprt->pending, task, xprt_timer); + req->rq_connect_cookie = xprt->connect_cookie; } spin_unlock_bh(&xprt->transport_lock); } @@ -1087,11 +1104,9 @@ struct rpc_xprt *xprt_alloc(struct net *net, size_t size, for (i = 0; i < num_prealloc; i++) { req = kzalloc(sizeof(struct rpc_rqst), GFP_KERNEL); if (!req) - break; + goto out_free; list_add(&req->rq_list, &xprt->free); } - if (i < num_prealloc) - goto out_free; if (max_alloc > num_prealloc) xprt->max_reqs = max_alloc; else @@ -1186,6 +1201,12 @@ static void xprt_request_init(struct rpc_task *task, struct rpc_xprt *xprt) req->rq_xprt = xprt; req->rq_buffer = NULL; req->rq_xid = xprt_alloc_xid(xprt); + req->rq_connect_cookie = xprt->connect_cookie - 1; + req->rq_bytes_sent = 0; + req->rq_snd_buf.len = 0; + req->rq_snd_buf.buflen = 0; + req->rq_rcv_buf.len = 0; + req->rq_rcv_buf.buflen = 0; req->rq_release_snd_buf = NULL; xprt_reset_majortimeo(req); dprintk("RPC: %5u reserved req %p xid %08x\n", task->tk_pid, diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ee03d35677d9..17c88928b7db 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -835,6 +835,8 @@ static void xs_close(struct rpc_xprt *xprt) dprintk("RPC: xs_close xprt %p\n", xprt); + cancel_delayed_work_sync(&transport->connect_worker); + xs_reset_transport(transport); xprt->reestablish_timeout = 0; @@ -854,14 +856,6 @@ static void xs_tcp_close(struct rpc_xprt *xprt) xs_tcp_shutdown(xprt); } -static void xs_local_destroy(struct rpc_xprt *xprt) -{ - xs_close(xprt); - xs_free_peer_addresses(xprt); - xprt_free(xprt); - module_put(THIS_MODULE); -} - /** * xs_destroy - prepare to shutdown a transport * @xprt: doomed transport @@ -869,13 +863,12 @@ static void xs_local_destroy(struct rpc_xprt *xprt) */ static void xs_destroy(struct rpc_xprt *xprt) { - struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); - dprintk("RPC: xs_destroy xprt %p\n", xprt); - cancel_delayed_work_sync(&transport->connect_worker); - - xs_local_destroy(xprt); + xs_close(xprt); + xs_free_peer_addresses(xprt); + xprt_free(xprt); + module_put(THIS_MODULE); } static inline struct rpc_xprt *xprt_from_sock(struct sock *sk) @@ -1511,6 +1504,7 @@ static void xs_tcp_state_change(struct sock *sk) transport->tcp_copied = 0; transport->tcp_flags = TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID; + xprt->connect_cookie++; xprt_wake_pending_tasks(xprt, -EAGAIN); } @@ -1816,6 +1810,10 @@ static inline void xs_reclassify_socket(int family, struct socket *sock) } #endif +static void xs_dummy_setup_socket(struct work_struct *work) +{ +} + static struct socket *xs_create_sock(struct rpc_xprt *xprt, struct sock_xprt *transport, int family, int type, int protocol) { @@ -2112,6 +2110,19 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) if (!transport->inet) { struct sock *sk = sock->sk; + unsigned int keepidle = xprt->timeout->to_initval / HZ; + unsigned int keepcnt = xprt->timeout->to_retries + 1; + unsigned int opt_on = 1; + + /* TCP Keepalive options */ + kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE, + (char *)&opt_on, sizeof(opt_on)); + kernel_setsockopt(sock, SOL_TCP, TCP_KEEPIDLE, + (char *)&keepidle, sizeof(keepidle)); + kernel_setsockopt(sock, SOL_TCP, TCP_KEEPINTVL, + (char *)&keepidle, sizeof(keepidle)); + kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT, + (char *)&keepcnt, sizeof(keepcnt)); write_lock_bh(&sk->sk_callback_lock); @@ -2151,7 +2162,6 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) case 0: case -EINPROGRESS: /* SYN_SENT! */ - xprt->connect_cookie++; if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; } @@ -2498,7 +2508,7 @@ static struct rpc_xprt_ops xs_local_ops = { .send_request = xs_local_send_request, .set_retrans_timeout = xprt_set_retrans_timeout_def, .close = xs_close, - .destroy = xs_local_destroy, + .destroy = xs_destroy, .print_stats = xs_local_print_stats, }; @@ -2655,6 +2665,9 @@ static struct rpc_xprt *xs_setup_local(struct xprt_create *args) xprt->ops = &xs_local_ops; xprt->timeout = &xs_local_default_timeout; + INIT_DELAYED_WORK(&transport->connect_worker, + xs_dummy_setup_socket); + switch (sun->sun_family) { case AF_LOCAL: if (sun->sun_path[0] != '/') { @@ -2859,8 +2872,8 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) if (args->bc_xprt->xpt_bc_xprt) { /* * This server connection already has a backchannel - * export; we can't create a new one, as we wouldn't be - * able to match replies based on xid any more. So, + * transport; we can't create a new one, as we wouldn't + * be able to match replies based on xid any more. So, * reuse the already-existing one: */ return args->bc_xprt->xpt_bc_xprt; diff --git a/net/x25/Kconfig b/net/x25/Kconfig index c959312c45e3..e2fa133f9fba 100644 --- a/net/x25/Kconfig +++ b/net/x25/Kconfig @@ -16,8 +16,8 @@ config X25 if you want that) and the lower level data link layer protocol LAPB (say Y to "LAPB Data Link Driver" below if you want that). - You can read more about X.25 at <http://www.sangoma.com/x25.htm> and - <http://www.cisco.com/univercd/cc/td/doc/product/software/ios11/cbook/cx25.htm>. + You can read more about X.25 at <http://www.sangoma.com/tutorials/x25/> and + <http://docwiki.cisco.com/wiki/X.25>. Information about X.25 for Linux is contained in the files <file:Documentation/networking/x25.txt> and <file:Documentation/networking/x25-iface.txt>. diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index 2906d520eea7..3be02b680268 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -141,14 +141,14 @@ static int ipcomp_compress(struct xfrm_state *x, struct sk_buff *skb) const int plen = skb->len; int dlen = IPCOMP_SCRATCH_SIZE; u8 *start = skb->data; - const int cpu = get_cpu(); - u8 *scratch = *per_cpu_ptr(ipcomp_scratches, cpu); - struct crypto_comp *tfm = *per_cpu_ptr(ipcd->tfms, cpu); + struct crypto_comp *tfm; + u8 *scratch; int err; local_bh_disable(); + scratch = *this_cpu_ptr(ipcomp_scratches); + tfm = *this_cpu_ptr(ipcd->tfms); err = crypto_comp_compress(tfm, start, plen, scratch, &dlen); - local_bh_enable(); if (err) goto out; @@ -158,13 +158,13 @@ static int ipcomp_compress(struct xfrm_state *x, struct sk_buff *skb) } memcpy(start + sizeof(struct ip_comp_hdr), scratch, dlen); - put_cpu(); + local_bh_enable(); pskb_trim(skb, dlen + sizeof(struct ip_comp_hdr)); return 0; out: - put_cpu(); + local_bh_enable(); return err; } |