diff options
Diffstat (limited to 'net')
51 files changed, 390 insertions, 425 deletions
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 9c891d0412a2..ae3a47f9d1d5 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -57,7 +57,7 @@ static const struct proto_ops ax25_proto_ops; static void ax25_free_sock(struct sock *sk) { - ax25_cb_put(ax25_sk(sk)); + ax25_cb_put(sk_to_ax25(sk)); } /* @@ -306,7 +306,7 @@ void ax25_destroy_socket(ax25_cb *ax25) while ((skb = skb_dequeue(&ax25->sk->sk_receive_queue)) != NULL) { if (skb->sk != ax25->sk) { /* A pending connection */ - ax25_cb *sax25 = ax25_sk(skb->sk); + ax25_cb *sax25 = sk_to_ax25(skb->sk); /* Queue the unaccepted socket for death */ sock_orphan(skb->sk); @@ -551,7 +551,7 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname, return -EFAULT; lock_sock(sk); - ax25 = ax25_sk(sk); + ax25 = sk_to_ax25(sk); switch (optname) { case AX25_WINDOW: @@ -697,7 +697,7 @@ static int ax25_getsockopt(struct socket *sock, int level, int optname, length = min_t(unsigned int, maxlen, sizeof(int)); lock_sock(sk); - ax25 = ax25_sk(sk); + ax25 = sk_to_ax25(sk); switch (optname) { case AX25_WINDOW: @@ -796,7 +796,7 @@ out: static struct proto ax25_proto = { .name = "AX25", .owner = THIS_MODULE, - .obj_size = sizeof(struct sock), + .obj_size = sizeof(struct ax25_sock), }; static int ax25_create(struct net *net, struct socket *sock, int protocol, @@ -858,7 +858,7 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol, if (sk == NULL) return -ENOMEM; - ax25 = sk->sk_protinfo = ax25_create_cb(); + ax25 = ax25_sk(sk)->cb = ax25_create_cb(); if (!ax25) { sk_free(sk); return -ENOMEM; @@ -910,7 +910,7 @@ struct sock *ax25_make_new(struct sock *osk, struct ax25_dev *ax25_dev) sk->sk_state = TCP_ESTABLISHED; sock_copy_flags(sk, osk); - oax25 = ax25_sk(osk); + oax25 = sk_to_ax25(osk); ax25->modulus = oax25->modulus; ax25->backoff = oax25->backoff; @@ -938,7 +938,7 @@ struct sock *ax25_make_new(struct sock *osk, struct ax25_dev *ax25_dev) } } - sk->sk_protinfo = ax25; + ax25_sk(sk)->cb = ax25; sk->sk_destruct = ax25_free_sock; ax25->sk = sk; @@ -956,7 +956,7 @@ static int ax25_release(struct socket *sock) sock_hold(sk); sock_orphan(sk); lock_sock(sk); - ax25 = ax25_sk(sk); + ax25 = sk_to_ax25(sk); if (sk->sk_type == SOCK_SEQPACKET) { switch (ax25->state) { @@ -1066,7 +1066,7 @@ static int ax25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) lock_sock(sk); - ax25 = ax25_sk(sk); + ax25 = sk_to_ax25(sk); if (!sock_flag(sk, SOCK_ZAPPED)) { err = -EINVAL; goto out; @@ -1113,7 +1113,7 @@ static int __must_check ax25_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; - ax25_cb *ax25 = ax25_sk(sk), *ax25t; + ax25_cb *ax25 = sk_to_ax25(sk), *ax25t; struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)uaddr; ax25_digi *digi = NULL; int ct = 0, err = 0; @@ -1394,7 +1394,7 @@ static int ax25_getname(struct socket *sock, struct sockaddr *uaddr, memset(fsa, 0, sizeof(*fsa)); lock_sock(sk); - ax25 = ax25_sk(sk); + ax25 = sk_to_ax25(sk); if (peer != 0) { if (sk->sk_state != TCP_ESTABLISHED) { @@ -1446,7 +1446,7 @@ static int ax25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) return -EINVAL; lock_sock(sk); - ax25 = ax25_sk(sk); + ax25 = sk_to_ax25(sk); if (sock_flag(sk, SOCK_ZAPPED)) { err = -EADDRNOTAVAIL; @@ -1621,7 +1621,7 @@ static int ax25_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, if (skb == NULL) goto out; - if (!ax25_sk(sk)->pidincl) + if (!sk_to_ax25(sk)->pidincl) skb_pull(skb, 1); /* Remove PID */ skb_reset_transport_header(skb); @@ -1762,7 +1762,7 @@ static int ax25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case SIOCAX25GETINFO: case SIOCAX25GETINFOOLD: { - ax25_cb *ax25 = ax25_sk(sk); + ax25_cb *ax25 = sk_to_ax25(sk); struct ax25_info_struct ax25_info; ax25_info.t1 = ax25->t1 / HZ; diff --git a/net/ax25/ax25_in.c b/net/ax25/ax25_in.c index 29a3687237aa..bb5a0e4e98d9 100644 --- a/net/ax25/ax25_in.c +++ b/net/ax25/ax25_in.c @@ -353,7 +353,7 @@ static int ax25_rcv(struct sk_buff *skb, struct net_device *dev, return 0; } - ax25 = ax25_sk(make); + ax25 = sk_to_ax25(make); skb_set_owner_r(skb, make); skb_queue_head(&sk->sk_receive_queue, skb); diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 9070dfd6b4ad..f1a117f8cad2 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -915,6 +915,7 @@ static int hidp_session_new(struct hidp_session **out, const bdaddr_t *bdaddr, session->conn = l2cap_conn_get(conn); session->user.probe = hidp_session_probe; session->user.remove = hidp_session_remove; + INIT_LIST_HEAD(&session->user.list); session->ctrl_sock = ctrl_sock; session->intr_sock = intr_sock; skb_queue_head_init(&session->ctrl_transmit); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 51594fb7b9e7..45fffa413642 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1634,7 +1634,7 @@ void l2cap_unregister_user(struct l2cap_conn *conn, struct l2cap_user *user) if (list_empty(&user->list)) goto out_unlock; - list_del(&user->list); + list_del_init(&user->list); user->remove(conn, user); out_unlock: @@ -1648,7 +1648,7 @@ static void l2cap_unregister_all_users(struct l2cap_conn *conn) while (!list_empty(&conn->users)) { user = list_first_entry(&conn->users, struct l2cap_user, list); - list_del(&user->list); + list_del_init(&user->list); user->remove(conn, user); } } diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index e97572b5d2cc..0ff6e1bbca91 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -42,6 +42,7 @@ int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb) } else { skb_push(skb, ETH_HLEN); br_drop_fake_rtable(skb); + skb_sender_cpu_clear(skb); dev_queue_xmit(skb); } diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index e29ad70b3000..c11cf2611db0 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -323,6 +323,7 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; struct net_bridge_mdb_htable *mdb; + unsigned long now = jiffies; int err; mdb = mlock_dereference(br->mdb, br); @@ -347,6 +348,8 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, if (unlikely(!p)) return -ENOMEM; rcu_assign_pointer(*pp, p); + if (state == MDB_TEMPORARY) + mod_timer(&p->timer, now + br->multicast_membership_interval); br_mdb_notify(br->dev, port, group, RTM_NEWMDB); return 0; @@ -371,6 +374,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, if (!p || p->br != br || p->state == BR_STATE_DISABLED) return -EINVAL; + memset(&ip, 0, sizeof(ip)); ip.proto = entry->addr.proto; if (ip.proto == htons(ETH_P_IP)) ip.u.ip4 = entry->addr.u.ip4; @@ -417,20 +421,14 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) if (!netif_running(br->dev) || br->multicast_disabled) return -EINVAL; + memset(&ip, 0, sizeof(ip)); ip.proto = entry->addr.proto; - if (ip.proto == htons(ETH_P_IP)) { - if (timer_pending(&br->ip4_other_query.timer)) - return -EBUSY; - + if (ip.proto == htons(ETH_P_IP)) ip.u.ip4 = entry->addr.u.ip4; #if IS_ENABLED(CONFIG_IPV6) - } else { - if (timer_pending(&br->ip6_other_query.timer)) - return -EBUSY; - + else ip.u.ip6 = entry->addr.u.ip6; #endif - } spin_lock_bh(&br->multicast_lock); mdb = mlock_dereference(br->mdb, br); diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index d89f4fac0bc5..c8b9bcfe997e 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -111,7 +111,7 @@ static inline __be16 pppoe_proto(const struct sk_buff *skb) /* largest possible L2 header, see br_nf_dev_queue_xmit() */ #define NF_BRIDGE_MAX_MAC_HEADER_LENGTH (PPPOE_SES_HLEN + ETH_HLEN) -#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) struct brnf_frag_data { char mac[NF_BRIDGE_MAX_MAC_HEADER_LENGTH]; u8 encap_size; @@ -694,6 +694,7 @@ static int br_nf_push_frag_xmit(struct sock *sk, struct sk_buff *skb) } #endif +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) static int br_nf_ip_fragment(struct sock *sk, struct sk_buff *skb, int (*output)(struct sock *, struct sk_buff *)) { @@ -712,6 +713,7 @@ static int br_nf_ip_fragment(struct sock *sk, struct sk_buff *skb, return ip_do_fragment(sk, skb, output); } +#endif static unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb) { @@ -742,7 +744,7 @@ static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) struct brnf_frag_data *data; if (br_validate_ipv4(skb)) - return NF_DROP; + goto drop; IPCB(skb)->frag_max_size = nf_bridge->frag_max_size; @@ -767,7 +769,7 @@ static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) struct brnf_frag_data *data; if (br_validate_ipv6(skb)) - return NF_DROP; + goto drop; IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size; @@ -782,12 +784,16 @@ static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) if (v6ops) return v6ops->fragment(sk, skb, br_nf_push_frag_xmit); - else - return -EMSGSIZE; + + kfree_skb(skb); + return -EMSGSIZE; } #endif nf_bridge_info_free(skb); return br_dev_queue_push_xmit(sk, skb); + drop: + kfree_skb(skb); + return 0; } /* PF_BRIDGE/POST_ROUTING ********************************************/ diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 6d12d2675c80..13b7d1e3d185 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -104,7 +104,7 @@ int br_validate_ipv6(struct sk_buff *skb) { const struct ipv6hdr *hdr; struct net_device *dev = skb->dev; - struct inet6_dev *idev = in6_dev_get(skb->dev); + struct inet6_dev *idev = __in6_dev_get(skb->dev); u32 pkt_len; u8 ip6h_len = sizeof(struct ipv6hdr); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 6b67ed3831de..364bdc98bd9b 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -457,6 +457,8 @@ static int br_afspec(struct net_bridge *br, if (nla_len(attr) != sizeof(struct bridge_vlan_info)) return -EINVAL; vinfo = nla_data(attr); + if (!vinfo->vid || vinfo->vid >= VLAN_VID_MASK) + return -EINVAL; if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { if (vinfo_start) return -EINVAL; diff --git a/net/core/dev.c b/net/core/dev.c index 6778a9999d52..a8e4dd430285 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -677,10 +677,6 @@ int dev_get_iflink(const struct net_device *dev) if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink) return dev->netdev_ops->ndo_get_iflink(dev); - /* If dev->rtnl_link_ops is set, it's a virtual interface. */ - if (dev->rtnl_link_ops) - return 0; - return dev->ifindex; } EXPORT_SYMBOL(dev_get_iflink); @@ -3452,6 +3448,8 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, local_irq_save(flags); rps_lock(sd); + if (!netif_running(skb->dev)) + goto drop; qlen = skb_queue_len(&sd->input_pkt_queue); if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) { if (qlen) { @@ -3473,6 +3471,7 @@ enqueue: goto enqueue; } +drop: sd->dropped++; rps_unlock(sd); @@ -3775,8 +3774,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc) pt_prev = NULL; - rcu_read_lock(); - another_round: skb->skb_iif = skb->dev->ifindex; @@ -3786,7 +3783,7 @@ another_round: skb->protocol == cpu_to_be16(ETH_P_8021AD)) { skb = skb_vlan_untag(skb); if (unlikely(!skb)) - goto unlock; + goto out; } #ifdef CONFIG_NET_CLS_ACT @@ -3816,10 +3813,10 @@ skip_taps: if (static_key_false(&ingress_needed)) { skb = handle_ing(skb, &pt_prev, &ret, orig_dev); if (!skb) - goto unlock; + goto out; if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0) - goto unlock; + goto out; } #endif #ifdef CONFIG_NET_CLS_ACT @@ -3837,7 +3834,7 @@ ncls: if (vlan_do_receive(&skb)) goto another_round; else if (unlikely(!skb)) - goto unlock; + goto out; } rx_handler = rcu_dereference(skb->dev->rx_handler); @@ -3849,7 +3846,7 @@ ncls: switch (rx_handler(&skb)) { case RX_HANDLER_CONSUMED: ret = NET_RX_SUCCESS; - goto unlock; + goto out; case RX_HANDLER_ANOTHER: goto another_round; case RX_HANDLER_EXACT: @@ -3903,8 +3900,7 @@ drop: ret = NET_RX_DROP; } -unlock: - rcu_read_unlock(); +out: return ret; } @@ -3935,29 +3931,30 @@ static int __netif_receive_skb(struct sk_buff *skb) static int netif_receive_skb_internal(struct sk_buff *skb) { + int ret; + net_timestamp_check(netdev_tstamp_prequeue, skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; + rcu_read_lock(); + #ifdef CONFIG_RPS if (static_key_false(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; - int cpu, ret; - - rcu_read_lock(); - - cpu = get_rps_cpu(skb->dev, skb, &rflow); + int cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu >= 0) { ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); return ret; } - rcu_read_unlock(); } #endif - return __netif_receive_skb(skb); + ret = __netif_receive_skb(skb); + rcu_read_unlock(); + return ret; } /** @@ -4502,8 +4499,10 @@ static int process_backlog(struct napi_struct *napi, int quota) struct sk_buff *skb; while ((skb = __skb_dequeue(&sd->process_queue))) { + rcu_read_lock(); local_irq_enable(); __netif_receive_skb(skb); + rcu_read_unlock(); local_irq_disable(); input_queue_head_incr(sd); if (++work >= quota) { @@ -6139,6 +6138,7 @@ static void rollback_registered_many(struct list_head *head) unlist_netdevice(dev); dev->reg_state = NETREG_UNREGISTERING; + on_each_cpu(flush_backlog, dev, 1); } synchronize_net(); @@ -6409,7 +6409,8 @@ static int netif_alloc_netdev_queues(struct net_device *dev) struct netdev_queue *tx; size_t sz = count * sizeof(*tx); - BUG_ON(count < 1 || count > 0xffff); + if (count < 1 || count > 0xffff) + return -EINVAL; tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); if (!tx) { @@ -6773,8 +6774,6 @@ void netdev_run_todo(void) dev->reg_state = NETREG_UNREGISTERED; - on_each_cpu(flush_backlog, dev, 1); - netdev_wait_allrefs(dev); /* paranoia */ diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 476e5dda59e1..2a834c6179b9 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -129,7 +129,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_ports *key_ports; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_keyid *key_keyid; - u8 ip_proto; + u8 ip_proto = 0; if (!data) { data = skb->data; diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 9dfb88a933e7..92d886f4adcb 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -66,7 +66,7 @@ NOTES. - * avbps is scaled by 2^5, avpps is scaled by 2^10. + * avbps and avpps are scaled by 2^5. * both values are reported as 32 bit unsigned values. bps can overflow for fast links : max speed being 34360Mbit/sec * Minimal interval is HZ/4=250msec (it is the greatest common divisor @@ -85,10 +85,10 @@ struct gen_estimator struct gnet_stats_rate_est64 *rate_est; spinlock_t *stats_lock; int ewma_log; + u32 last_packets; + unsigned long avpps; u64 last_bytes; u64 avbps; - u32 last_packets; - u32 avpps; struct rcu_head e_rcu; struct rb_node node; struct gnet_stats_basic_cpu __percpu *cpu_bstats; @@ -118,8 +118,8 @@ static void est_timer(unsigned long arg) rcu_read_lock(); list_for_each_entry_rcu(e, &elist[idx].list, list) { struct gnet_stats_basic_packed b = {0}; + unsigned long rate; u64 brate; - u32 rate; spin_lock(e->stats_lock); read_lock(&est_lock); @@ -133,10 +133,11 @@ static void est_timer(unsigned long arg) e->avbps += (brate >> e->ewma_log) - (e->avbps >> e->ewma_log); e->rate_est->bps = (e->avbps+0xF)>>5; - rate = (b.packets - e->last_packets)<<(12 - idx); + rate = b.packets - e->last_packets; + rate <<= (7 - idx); e->last_packets = b.packets; e->avpps += (rate >> e->ewma_log) - (e->avpps >> e->ewma_log); - e->rate_est->pps = (e->avpps+0x1FF)>>10; + e->rate_est->pps = (e->avpps + 0xF) >> 5; skip: read_unlock(&est_lock); spin_unlock(e->stats_lock); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 05badbb58865..1ebdf1c0d118 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3571,13 +3571,6 @@ static int pktgen_thread_worker(void *arg) pr_debug("%s removing thread\n", t->tsk->comm); pktgen_rem_thread(t); - /* Wait for kthread_stop */ - while (!kthread_should_stop()) { - set_current_state(TASK_INTERRUPTIBLE); - schedule(); - } - __set_current_state(TASK_RUNNING); - return 0; } @@ -3769,6 +3762,7 @@ static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn) } t->net = pn; + get_task_struct(p); wake_up_process(p); wait_for_completion(&t->start_done); @@ -3891,6 +3885,7 @@ static void __net_exit pg_net_exit(struct net *net) t = list_entry(q, struct pktgen_thread, th_list); list_del(&t->th_list); kthread_stop(t->tsk); + put_task_struct(t->tsk); kfree(t); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 01ced4a889e0..9e433d58d265 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1328,10 +1328,6 @@ static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { [IFLA_INFO_SLAVE_DATA] = { .type = NLA_NESTED }, }; -static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = { - [IFLA_VF_INFO] = { .type = NLA_NESTED }, -}; - static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { [IFLA_VF_MAC] = { .len = sizeof(struct ifla_vf_mac) }, [IFLA_VF_VLAN] = { .len = sizeof(struct ifla_vf_vlan) }, @@ -1488,96 +1484,98 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) return 0; } -static int do_setvfinfo(struct net_device *dev, struct nlattr *attr) +static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) { - int rem, err = -EINVAL; - struct nlattr *vf; const struct net_device_ops *ops = dev->netdev_ops; + int err = -EINVAL; - nla_for_each_nested(vf, attr, rem) { - switch (nla_type(vf)) { - case IFLA_VF_MAC: { - struct ifla_vf_mac *ivm; - ivm = nla_data(vf); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_mac) - err = ops->ndo_set_vf_mac(dev, ivm->vf, - ivm->mac); - break; - } - case IFLA_VF_VLAN: { - struct ifla_vf_vlan *ivv; - ivv = nla_data(vf); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_vlan) - err = ops->ndo_set_vf_vlan(dev, ivv->vf, - ivv->vlan, - ivv->qos); - break; - } - case IFLA_VF_TX_RATE: { - struct ifla_vf_tx_rate *ivt; - struct ifla_vf_info ivf; - ivt = nla_data(vf); - err = -EOPNOTSUPP; - if (ops->ndo_get_vf_config) - err = ops->ndo_get_vf_config(dev, ivt->vf, - &ivf); - if (err) - break; - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_rate) - err = ops->ndo_set_vf_rate(dev, ivt->vf, - ivf.min_tx_rate, - ivt->rate); - break; - } - case IFLA_VF_RATE: { - struct ifla_vf_rate *ivt; - ivt = nla_data(vf); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_rate) - err = ops->ndo_set_vf_rate(dev, ivt->vf, - ivt->min_tx_rate, - ivt->max_tx_rate); - break; - } - case IFLA_VF_SPOOFCHK: { - struct ifla_vf_spoofchk *ivs; - ivs = nla_data(vf); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_spoofchk) - err = ops->ndo_set_vf_spoofchk(dev, ivs->vf, - ivs->setting); - break; - } - case IFLA_VF_LINK_STATE: { - struct ifla_vf_link_state *ivl; - ivl = nla_data(vf); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_link_state) - err = ops->ndo_set_vf_link_state(dev, ivl->vf, - ivl->link_state); - break; - } - case IFLA_VF_RSS_QUERY_EN: { - struct ifla_vf_rss_query_en *ivrssq_en; + if (tb[IFLA_VF_MAC]) { + struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]); - ivrssq_en = nla_data(vf); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_rss_query_en) - err = ops->ndo_set_vf_rss_query_en(dev, - ivrssq_en->vf, - ivrssq_en->setting); - break; - } - default: - err = -EINVAL; - break; - } - if (err) - break; + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_mac) + err = ops->ndo_set_vf_mac(dev, ivm->vf, + ivm->mac); + if (err < 0) + return err; + } + + if (tb[IFLA_VF_VLAN]) { + struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]); + + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_vlan) + err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan, + ivv->qos); + if (err < 0) + return err; + } + + if (tb[IFLA_VF_TX_RATE]) { + struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]); + struct ifla_vf_info ivf; + + err = -EOPNOTSUPP; + if (ops->ndo_get_vf_config) + err = ops->ndo_get_vf_config(dev, ivt->vf, &ivf); + if (err < 0) + return err; + + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_rate) + err = ops->ndo_set_vf_rate(dev, ivt->vf, + ivf.min_tx_rate, + ivt->rate); + if (err < 0) + return err; + } + + if (tb[IFLA_VF_RATE]) { + struct ifla_vf_rate *ivt = nla_data(tb[IFLA_VF_RATE]); + + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_rate) + err = ops->ndo_set_vf_rate(dev, ivt->vf, + ivt->min_tx_rate, + ivt->max_tx_rate); + if (err < 0) + return err; } + + if (tb[IFLA_VF_SPOOFCHK]) { + struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]); + + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_spoofchk) + err = ops->ndo_set_vf_spoofchk(dev, ivs->vf, + ivs->setting); + if (err < 0) + return err; + } + + if (tb[IFLA_VF_LINK_STATE]) { + struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]); + + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_link_state) + err = ops->ndo_set_vf_link_state(dev, ivl->vf, + ivl->link_state); + if (err < 0) + return err; + } + + if (tb[IFLA_VF_RSS_QUERY_EN]) { + struct ifla_vf_rss_query_en *ivrssq_en; + + err = -EOPNOTSUPP; + ivrssq_en = nla_data(tb[IFLA_VF_RSS_QUERY_EN]); + if (ops->ndo_set_vf_rss_query_en) + err = ops->ndo_set_vf_rss_query_en(dev, ivrssq_en->vf, + ivrssq_en->setting); + if (err < 0) + return err; + } + return err; } @@ -1773,14 +1771,21 @@ static int do_setlink(const struct sk_buff *skb, } if (tb[IFLA_VFINFO_LIST]) { + struct nlattr *vfinfo[IFLA_VF_MAX + 1]; struct nlattr *attr; int rem; + nla_for_each_nested(attr, tb[IFLA_VFINFO_LIST], rem) { - if (nla_type(attr) != IFLA_VF_INFO) { + if (nla_type(attr) != IFLA_VF_INFO || + nla_len(attr) < NLA_HDRLEN) { err = -EINVAL; goto errout; } - err = do_setvfinfo(dev, attr); + err = nla_parse_nested(vfinfo, IFLA_VF_MAX, attr, + ifla_vf_policy); + if (err < 0) + goto errout; + err = do_setvfinfo(dev, vfinfo); if (err < 0) goto errout; status |= DO_SETLINK_NOTIFY; diff --git a/net/core/sock.c b/net/core/sock.c index 1e1fe9a68d83..08f16db46070 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1454,7 +1454,7 @@ void sk_destruct(struct sock *sk) static void __sk_free(struct sock *sk) { - if (unlikely(sock_diag_has_destroy_listeners(sk))) + if (unlikely(sock_diag_has_destroy_listeners(sk) && sk->sk_net_refcnt)) sock_diag_broadcast_destroy(sk); else sk_destruct(sk); @@ -2269,7 +2269,6 @@ static void sock_def_write_space(struct sock *sk) static void sock_def_destruct(struct sock *sk) { - kfree(sk->sk_protinfo); } void sk_send_sigurg(struct sock *sk) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 04ffad311704..0917123790ea 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -112,7 +112,7 @@ static int dsa_slave_open(struct net_device *dev) clear_promisc: if (dev->flags & IFF_PROMISC) - dev_set_promiscuity(master, 0); + dev_set_promiscuity(master, -1); clear_allmulti: if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(master, -1); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 7498716e8f54..e813196c91c7 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1740,6 +1740,8 @@ static int inet_netconf_msgsize_devconf(int type) size += nla_total_size(4); if (type == -1 || type == NETCONFA_PROXY_NEIGH) size += nla_total_size(4); + if (type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) + size += nla_total_size(4); return size; } @@ -1780,6 +1782,10 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, nla_put_s32(skb, NETCONFA_PROXY_NEIGH, IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0) goto nla_put_failure; + if ((type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) && + nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, + IPV4_DEVCONF(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0) + goto nla_put_failure; nlmsg_end(skb, nlh); return 0; @@ -1819,6 +1825,7 @@ static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = { [NETCONFA_FORWARDING] = { .len = sizeof(int) }, [NETCONFA_RP_FILTER] = { .len = sizeof(int) }, [NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) }, + [NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) }, }; static int inet_netconf_get_devconf(struct sk_buff *in_skb, @@ -2048,6 +2055,12 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write, inet_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH, ifindex, cnf); } + if (i == IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN - 1 && + new_value != old_value) { + ifindex = devinet_conf_ifindex(net, cnf); + inet_netconf_notify_devconf(net, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, + ifindex, cnf); + } } return ret; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 3bfccd83551c..c7358ea4ae93 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1045,7 +1045,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif)) goto nla_put_failure; if (fi->fib_nh->nh_flags & RTNH_F_LINKDOWN) { - in_dev = __in_dev_get_rcu(fi->fib_nh->nh_dev); + in_dev = __in_dev_get_rtnl(fi->fib_nh->nh_dev); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) rtm->rtm_flags |= RTNH_F_DEAD; @@ -1074,7 +1074,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, rtnh->rtnh_flags = nh->nh_flags & 0xFF; if (nh->nh_flags & RTNH_F_LINKDOWN) { - in_dev = __in_dev_get_rcu(nh->nh_dev); + in_dev = __in_dev_get_rtnl(nh->nh_dev); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) rtnh->rtnh_flags |= RTNH_F_DEAD; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 9bc26677058e..c3b1f3a0f4cf 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -152,8 +152,8 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, inet6_sk(sk)->tclass) < 0) goto errout; - if (ipv6_only_sock(sk) && - nla_put_u8(skb, INET_DIAG_SKV6ONLY, 1)) + if (((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) && + nla_put_u8(skb, INET_DIAG_SKV6ONLY, ipv6_only_sock(sk))) goto errout; } #endif diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 4c2c3ba4ba65..626d9e56a6bd 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -586,7 +586,8 @@ int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t, EXPORT_SYMBOL(ip_tunnel_encap); static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, - struct rtable *rt, __be16 df) + struct rtable *rt, __be16 df, + const struct iphdr *inner_iph) { struct ip_tunnel *tunnel = netdev_priv(dev); int pkt_size = skb->len - tunnel->hlen - dev->hard_header_len; @@ -603,7 +604,8 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, if (skb->protocol == htons(ETH_P_IP)) { if (!skb_is_gso(skb) && - (df & htons(IP_DF)) && mtu < pkt_size) { + (inner_iph->frag_off & htons(IP_DF)) && + mtu < pkt_size) { memset(IPCB(skb), 0, sizeof(*IPCB(skb))); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); return -E2BIG; @@ -737,7 +739,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } - if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) { + if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph)) { ip_rt_put(rt); goto tx_error; } diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 65de0684e22a..61eafc9b4545 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -197,11 +197,4 @@ static int __init ipv4_netfilter_init(void) { return nf_register_afinfo(&nf_ip_afinfo); } - -static void __exit ipv4_netfilter_fini(void) -{ - nf_unregister_afinfo(&nf_ip_afinfo); -} - -module_init(ipv4_netfilter_init); -module_exit(ipv4_netfilter_fini); +subsys_initcall(ipv4_netfilter_init); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 95c9b6eece25..92305a1a021a 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -254,9 +254,10 @@ unsigned int arpt_do_table(struct sk_buff *skb, static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); unsigned int verdict = NF_DROP; const struct arphdr *arp; - struct arpt_entry *e, *back; + struct arpt_entry *e, **jumpstack; const char *indev, *outdev; const void *table_base; + unsigned int cpu, stackidx = 0; const struct xt_table_info *private; struct xt_action_param acpar; unsigned int addend; @@ -270,15 +271,16 @@ unsigned int arpt_do_table(struct sk_buff *skb, local_bh_disable(); 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; + jumpstack = (struct arpt_entry **)private->jumpstack[cpu]; e = get_entry(table_base, private->hook_entry[hook]); - back = get_entry(table_base, private->underflow[hook]); acpar.in = state->in; acpar.out = state->out; @@ -312,18 +314,23 @@ unsigned int arpt_do_table(struct sk_buff *skb, verdict = (unsigned int)(-v) - 1; break; } - e = back; - back = get_entry(table_base, back->comefrom); + if (stackidx == 0) { + e = get_entry(table_base, + private->underflow[hook]); + } else { + e = jumpstack[--stackidx]; + e = arpt_next_entry(e); + } continue; } if (table_base + v != arpt_next_entry(e)) { - /* Save old back ptr in next entry */ - struct arpt_entry *next = arpt_next_entry(e); - next->comefrom = (void *)back - table_base; - /* set back pointer to next entry */ - back = next; + if (stackidx >= private->stacksize) { + verdict = NF_DROP; + break; + } + jumpstack[stackidx++] = e; } e = get_entry(table_base, v); diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index f2e464eba5ef..57990c929cd8 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -331,10 +331,10 @@ int ip6_mc_input(struct sk_buff *skb) if (offset < 0) goto out; - if (!ipv6_is_mld(skb, nexthdr, offset)) - goto out; + if (ipv6_is_mld(skb, nexthdr, offset)) + deliver = true; - deliver = true; + goto out; } /* unknown RA - process it normally */ } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 1a1122a6bbf5..6090969937f8 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -369,10 +369,7 @@ static void ip6_dst_destroy(struct dst_entry *dst) struct inet6_dev *idev; dst_destroy_metrics_generic(dst); - - if (rt->rt6i_pcpu) - free_percpu(rt->rt6i_pcpu); - + free_percpu(rt->rt6i_pcpu); rt6_uncached_list_del(rt); idev = rt->rt6i_idev; diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 36ba7c4f0283..fda33f961d83 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -103,7 +103,7 @@ ieee80211_rate_control_ops_get(const char *name) const struct rate_control_ops *ops; const char *alg_name; - kparam_block_sysfs_write(ieee80211_default_rc_algo); + kernel_param_lock(THIS_MODULE); if (!name) alg_name = ieee80211_default_rc_algo; else @@ -117,7 +117,7 @@ ieee80211_rate_control_ops_get(const char *name) /* try built-in one if specific alg requested but not found */ if (!ops && strlen(CONFIG_MAC80211_RC_DEFAULT)) ops = ieee80211_try_rate_control_ops_get(CONFIG_MAC80211_RC_DEFAULT); - kparam_unblock_sysfs_write(ieee80211_default_rc_algo); + kernel_param_unlock(THIS_MODULE); return ops; } diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index cd60d397fe05..8a8b2abc35ff 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -213,7 +213,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) if (verdict == NF_ACCEPT) { next_hook: - verdict = nf_iterate(&nf_hooks[entry->state.pf][entry->state.hook], + verdict = nf_iterate(entry->state.hook_list, skb, &entry->state, &elem); } diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 8b117c90ecd7..0c0e8ecf02ab 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -269,6 +269,12 @@ static void nfnl_err_deliver(struct list_head *err_list, struct sk_buff *skb) } } +enum { + NFNL_BATCH_FAILURE = (1 << 0), + NFNL_BATCH_DONE = (1 << 1), + NFNL_BATCH_REPLAY = (1 << 2), +}; + static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, u_int16_t subsys_id) { @@ -276,13 +282,15 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); const struct nfnetlink_subsystem *ss; const struct nfnl_callback *nc; - bool success = true, done = false; static LIST_HEAD(err_list); + u32 status; int err; if (subsys_id >= NFNL_SUBSYS_COUNT) return netlink_ack(skb, nlh, -EINVAL); replay: + status = 0; + skb = netlink_skb_clone(oskb, GFP_KERNEL); if (!skb) return netlink_ack(oskb, nlh, -ENOMEM); @@ -336,10 +344,10 @@ replay: if (type == NFNL_MSG_BATCH_BEGIN) { /* Malformed: Batch begin twice */ nfnl_err_reset(&err_list); - success = false; + status |= NFNL_BATCH_FAILURE; goto done; } else if (type == NFNL_MSG_BATCH_END) { - done = true; + status |= NFNL_BATCH_DONE; goto done; } else if (type < NLMSG_MIN_TYPE) { err = -EINVAL; @@ -382,11 +390,8 @@ replay: * original skb. */ if (err == -EAGAIN) { - nfnl_err_reset(&err_list); - ss->abort(oskb); - nfnl_unlock(subsys_id); - kfree_skb(skb); - goto replay; + status |= NFNL_BATCH_REPLAY; + goto next; } } ack: @@ -402,7 +407,7 @@ ack: */ nfnl_err_reset(&err_list); netlink_ack(skb, nlmsg_hdr(oskb), -ENOMEM); - success = false; + status |= NFNL_BATCH_FAILURE; goto done; } /* We don't stop processing the batch on errors, thus, @@ -410,19 +415,26 @@ ack: * triggers. */ if (err) - success = false; + status |= NFNL_BATCH_FAILURE; } - +next: msglen = NLMSG_ALIGN(nlh->nlmsg_len); if (msglen > skb->len) msglen = skb->len; skb_pull(skb, msglen); } done: - if (success && done) + if (status & NFNL_BATCH_REPLAY) { + ss->abort(oskb); + nfnl_err_reset(&err_list); + nfnl_unlock(subsys_id); + kfree_skb(skb); + goto replay; + } else if (status == NFNL_BATCH_DONE) { ss->commit(oskb); - else + } else { ss->abort(oskb); + } nfnl_err_deliver(&err_list, oskb); nfnl_unlock(subsys_id); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index dea925388a5b..9a0ae7172f92 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -158,7 +158,7 @@ static int __netlink_remove_tap(struct netlink_tap *nt) out: spin_unlock(&netlink_tap_lock); - if (found && nt->module) + if (found) module_put(nt->module); return found ? 0 : -ENODEV; diff --git a/net/rds/transport.c b/net/rds/transport.c index 8b4a6cd2c3a7..83498e1c75b8 100644 --- a/net/rds/transport.c +++ b/net/rds/transport.c @@ -73,7 +73,7 @@ EXPORT_SYMBOL_GPL(rds_trans_unregister); void rds_trans_put(struct rds_transport *trans) { - if (trans && trans->t_owner) + if (trans) module_put(trans->t_owner); } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index b92d3f49c23e..9d37ccd95062 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -216,8 +216,8 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_IPV6_DST_MASK] = { .len = sizeof(struct in6_addr) }, [TCA_FLOWER_KEY_TCP_SRC] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_TCP_DST] = { .type = NLA_U16 }, - [TCA_FLOWER_KEY_TCP_SRC] = { .type = NLA_U16 }, - [TCA_FLOWER_KEY_TCP_DST] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_UDP_SRC] = { .type = NLA_U16 }, + [TCA_FLOWER_KEY_UDP_DST] = { .type = NLA_U16 }, }; static void fl_set_key_val(struct nlattr **tb, diff --git a/net/sctp/output.c b/net/sctp/output.c index fc5e45b8a832..abe7c2db2412 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -599,7 +599,9 @@ out: return err; no_route: kfree_skb(nskb); - IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES); + + if (asoc) + IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES); /* FIXME: Returning the 'err' will effect all the associations * associated with a socket, although only one of the paths of the diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 5f6c4e61325b..1425ec2bbd5a 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2121,12 +2121,6 @@ static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (sp->subscribe.sctp_data_io_event) sctp_ulpevent_read_sndrcvinfo(event, msg); -#if 0 - /* FIXME: we should be calling IP/IPv6 layers. */ - if (sk->sk_protinfo.af_inet.cmsg_flags) - ip_cmsg_recv(msg, skb); -#endif - err = copied; /* If skb's length exceeds the user's buffer, update the skb and diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 9068e72aa73c..04ce2c0b660e 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -48,28 +48,16 @@ config SUNRPC_DEBUG If unsure, say Y. -config SUNRPC_XPRT_RDMA_CLIENT - tristate "RPC over RDMA Client Support" +config SUNRPC_XPRT_RDMA + tristate "RPC-over-RDMA transport" depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS default SUNRPC && INFINIBAND help - This option allows the NFS client to support an RDMA-enabled - transport. + This option allows the NFS client and server to use RDMA + transports (InfiniBand, iWARP, or RoCE). - To compile RPC client RDMA transport support as a module, - choose M here: the module will be called xprtrdma. + To compile this support as a module, choose M. The module + will be called rpcrdma.ko. - If unsure, say N. - -config SUNRPC_XPRT_RDMA_SERVER - tristate "RPC over RDMA Server Support" - depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS - default SUNRPC && INFINIBAND - help - This option allows the NFS server to support an RDMA-enabled - transport. - - To compile RPC server RDMA transport support as a module, - choose M here: the module will be called svcrdma. - - If unsure, say N. + If unsure, or you know there is no RDMA capability on your + hardware platform, say N. diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile index 15e6f6c23c5d..936ad0a15371 100644 --- a/net/sunrpc/Makefile +++ b/net/sunrpc/Makefile @@ -5,8 +5,7 @@ obj-$(CONFIG_SUNRPC) += sunrpc.o obj-$(CONFIG_SUNRPC_GSS) += auth_gss/ - -obj-y += xprtrdma/ +obj-$(CONFIG_SUNRPC_XPRT_RDMA) += xprtrdma/ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \ auth.o auth_null.o auth_unix.o auth_generic.o \ diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 47f38be4155f..02f53674dc39 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -72,7 +72,7 @@ static int param_get_hashtbl_sz(char *buffer, const struct kernel_param *kp) #define param_check_hashtbl_sz(name, p) __param_check(name, p, unsigned int); -static struct kernel_param_ops param_ops_hashtbl_sz = { +static const struct kernel_param_ops param_ops_hashtbl_sz = { .set = param_set_hashtbl_sz, .get = param_get_hashtbl_sz, }; diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index b5408e8a37f2..fee3c15a4b52 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -881,9 +881,7 @@ krb5_rc4_setup_seq_key(struct krb5_ctx *kctx, struct crypto_blkcipher *cipher, if (err) goto out_err; - sg_init_table(sg, 1); - sg_set_buf(sg, &zeroconstant, 4); - + sg_init_one(sg, &zeroconstant, 4); err = crypto_hash_digest(&desc, sg, 4, Kseq); if (err) goto out_err; @@ -951,9 +949,7 @@ krb5_rc4_setup_enc_key(struct krb5_ctx *kctx, struct crypto_blkcipher *cipher, if (err) goto out_err; - sg_init_table(sg, 1); - sg_set_buf(sg, zeroconstant, 4); - + sg_init_one(sg, zeroconstant, 4); err = crypto_hash_digest(&desc, sg, 4, Kcrypt); if (err) goto out_err; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 78974e4d9ad2..852ae606b02a 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1290,7 +1290,6 @@ err_bad: svc_putnl(resv, ntohl(rpc_stat)); goto sendit; } -EXPORT_SYMBOL_GPL(svc_process); /* * Process the RPC request. @@ -1338,6 +1337,7 @@ out_drop: svc_drop(rqstp); return 0; } +EXPORT_SYMBOL_GPL(svc_process); #if defined(CONFIG_SUNRPC_BACKCHANNEL) /* diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile index 579f72bbcf4b..48913de240bd 100644 --- a/net/sunrpc/xprtrdma/Makefile +++ b/net/sunrpc/xprtrdma/Makefile @@ -1,9 +1,7 @@ -obj-$(CONFIG_SUNRPC_XPRT_RDMA_CLIENT) += xprtrdma.o +obj-$(CONFIG_SUNRPC_XPRT_RDMA) += rpcrdma.o -xprtrdma-y := transport.o rpc_rdma.o verbs.o \ - fmr_ops.o frwr_ops.o physical_ops.o - -obj-$(CONFIG_SUNRPC_XPRT_RDMA_SERVER) += svcrdma.o - -svcrdma-y := svc_rdma.o svc_rdma_transport.o \ - svc_rdma_marshal.o svc_rdma_sendto.o svc_rdma_recvfrom.o +rpcrdma-y := transport.o rpc_rdma.o verbs.o \ + fmr_ops.o frwr_ops.o physical_ops.o \ + svc_rdma.o svc_rdma_transport.o \ + svc_rdma_marshal.o svc_rdma_sendto.o svc_rdma_recvfrom.o \ + module.o diff --git a/net/sunrpc/xprtrdma/module.c b/net/sunrpc/xprtrdma/module.c new file mode 100644 index 000000000000..560712bd9fa2 --- /dev/null +++ b/net/sunrpc/xprtrdma/module.c @@ -0,0 +1,46 @@ +/* + * Copyright (c) 2015 Oracle. All rights reserved. + */ + +/* rpcrdma.ko module initialization + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/sunrpc/svc_rdma.h> +#include "xprt_rdma.h" + +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) +# define RPCDBG_FACILITY RPCDBG_TRANS +#endif + +MODULE_AUTHOR("Open Grid Computing and Network Appliance, Inc."); +MODULE_DESCRIPTION("RPC/RDMA Transport"); +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_ALIAS("svcrdma"); +MODULE_ALIAS("xprtrdma"); + +static void __exit rpc_rdma_cleanup(void) +{ + xprt_rdma_cleanup(); + svc_rdma_cleanup(); +} + +static int __init rpc_rdma_init(void) +{ + int rc; + + rc = svc_rdma_init(); + if (rc) + goto out; + + rc = xprt_rdma_init(); + if (rc) + svc_rdma_cleanup(); + +out: + return rc; +} + +module_init(rpc_rdma_init); +module_exit(rpc_rdma_cleanup); diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index c1b6270262c2..2cd252f023a5 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -38,8 +38,7 @@ * * Author: Tom Tucker <tom@opengridcomputing.com> */ -#include <linux/module.h> -#include <linux/init.h> + #include <linux/slab.h> #include <linux/fs.h> #include <linux/sysctl.h> @@ -295,8 +294,3 @@ int svc_rdma_init(void) destroy_workqueue(svc_rdma_wq); return -ENOMEM; } -MODULE_AUTHOR("Tom Tucker <tom@opengridcomputing.com>"); -MODULE_DESCRIPTION("SVC RDMA Transport"); -MODULE_LICENSE("Dual BSD/GPL"); -module_init(svc_rdma_init); -module_exit(svc_rdma_cleanup); diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c index b681855cf970..e2fca7617242 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c +++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c @@ -50,12 +50,12 @@ /* * Decodes a read chunk list. The expected format is as follows: * descrim : xdr_one - * position : u32 offset into XDR stream - * handle : u32 RKEY + * position : __be32 offset into XDR stream + * handle : __be32 RKEY * . . . * end-of-list: xdr_zero */ -static u32 *decode_read_list(u32 *va, u32 *vaend) +static __be32 *decode_read_list(__be32 *va, __be32 *vaend) { struct rpcrdma_read_chunk *ch = (struct rpcrdma_read_chunk *)va; @@ -67,20 +67,20 @@ static u32 *decode_read_list(u32 *va, u32 *vaend) } ch++; } - return (u32 *)&ch->rc_position; + return &ch->rc_position; } /* * Decodes a write chunk list. The expected format is as follows: * descrim : xdr_one * nchunks : <count> - * handle : u32 RKEY ---+ - * length : u32 <len of segment> | + * handle : __be32 RKEY ---+ + * length : __be32 <len of segment> | * offset : remove va + <count> * . . . | * ---+ */ -static u32 *decode_write_list(u32 *va, u32 *vaend) +static __be32 *decode_write_list(__be32 *va, __be32 *vaend) { unsigned long start, end; int nchunks; @@ -90,14 +90,14 @@ static u32 *decode_write_list(u32 *va, u32 *vaend) /* Check for not write-array */ if (ary->wc_discrim == xdr_zero) - return (u32 *)&ary->wc_nchunks; + return &ary->wc_nchunks; if ((unsigned long)ary + sizeof(struct rpcrdma_write_array) > (unsigned long)vaend) { dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend); return NULL; } - nchunks = ntohl(ary->wc_nchunks); + nchunks = be32_to_cpu(ary->wc_nchunks); start = (unsigned long)&ary->wc_array[0]; end = (unsigned long)vaend; @@ -112,10 +112,10 @@ static u32 *decode_write_list(u32 *va, u32 *vaend) * rs_length is the 2nd 4B field in wc_target and taking its * address skips the list terminator */ - return (u32 *)&ary->wc_array[nchunks].wc_target.rs_length; + return &ary->wc_array[nchunks].wc_target.rs_length; } -static u32 *decode_reply_array(u32 *va, u32 *vaend) +static __be32 *decode_reply_array(__be32 *va, __be32 *vaend) { unsigned long start, end; int nchunks; @@ -124,14 +124,14 @@ static u32 *decode_reply_array(u32 *va, u32 *vaend) /* Check for no reply-array */ if (ary->wc_discrim == xdr_zero) - return (u32 *)&ary->wc_nchunks; + return &ary->wc_nchunks; if ((unsigned long)ary + sizeof(struct rpcrdma_write_array) > (unsigned long)vaend) { dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend); return NULL; } - nchunks = ntohl(ary->wc_nchunks); + nchunks = be32_to_cpu(ary->wc_nchunks); start = (unsigned long)&ary->wc_array[0]; end = (unsigned long)vaend; @@ -142,15 +142,14 @@ static u32 *decode_reply_array(u32 *va, u32 *vaend) ary, nchunks, vaend); return NULL; } - return (u32 *)&ary->wc_array[nchunks]; + return (__be32 *)&ary->wc_array[nchunks]; } int svc_rdma_xdr_decode_req(struct rpcrdma_msg **rdma_req, struct svc_rqst *rqstp) { struct rpcrdma_msg *rmsgp = NULL; - u32 *va; - u32 *vaend; + __be32 *va, *vaend; u32 hdr_len; rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base; @@ -162,22 +161,17 @@ int svc_rdma_xdr_decode_req(struct rpcrdma_msg **rdma_req, return -EINVAL; } - /* Decode the header */ - rmsgp->rm_xid = ntohl(rmsgp->rm_xid); - rmsgp->rm_vers = ntohl(rmsgp->rm_vers); - rmsgp->rm_credit = ntohl(rmsgp->rm_credit); - rmsgp->rm_type = ntohl(rmsgp->rm_type); - - if (rmsgp->rm_vers != RPCRDMA_VERSION) + if (rmsgp->rm_vers != rpcrdma_version) return -ENOSYS; /* Pull in the extra for the padded case and bump our pointer */ - if (rmsgp->rm_type == RDMA_MSGP) { + if (rmsgp->rm_type == rdma_msgp) { int hdrlen; + rmsgp->rm_body.rm_padded.rm_align = - ntohl(rmsgp->rm_body.rm_padded.rm_align); + be32_to_cpu(rmsgp->rm_body.rm_padded.rm_align); rmsgp->rm_body.rm_padded.rm_thresh = - ntohl(rmsgp->rm_body.rm_padded.rm_thresh); + be32_to_cpu(rmsgp->rm_body.rm_padded.rm_thresh); va = &rmsgp->rm_body.rm_padded.rm_pempty[4]; rqstp->rq_arg.head[0].iov_base = va; @@ -192,7 +186,7 @@ int svc_rdma_xdr_decode_req(struct rpcrdma_msg **rdma_req, * chunk list and a reply chunk list. */ va = &rmsgp->rm_body.rm_chunks[0]; - vaend = (u32 *)((unsigned long)rmsgp + rqstp->rq_arg.len); + vaend = (__be32 *)((unsigned long)rmsgp + rqstp->rq_arg.len); va = decode_read_list(va, vaend); if (!va) return -EINVAL; @@ -211,76 +205,20 @@ int svc_rdma_xdr_decode_req(struct rpcrdma_msg **rdma_req, return hdr_len; } -int svc_rdma_xdr_decode_deferred_req(struct svc_rqst *rqstp) -{ - struct rpcrdma_msg *rmsgp = NULL; - struct rpcrdma_read_chunk *ch; - struct rpcrdma_write_array *ary; - u32 *va; - u32 hdrlen; - - dprintk("svcrdma: processing deferred RDMA header on rqstp=%p\n", - rqstp); - rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base; - - /* Pull in the extra for the padded case and bump our pointer */ - if (rmsgp->rm_type == RDMA_MSGP) { - va = &rmsgp->rm_body.rm_padded.rm_pempty[4]; - rqstp->rq_arg.head[0].iov_base = va; - hdrlen = (u32)((unsigned long)va - (unsigned long)rmsgp); - rqstp->rq_arg.head[0].iov_len -= hdrlen; - return hdrlen; - } - - /* - * Skip all chunks to find RPC msg. These were previously processed - */ - va = &rmsgp->rm_body.rm_chunks[0]; - - /* Skip read-list */ - for (ch = (struct rpcrdma_read_chunk *)va; - ch->rc_discrim != xdr_zero; ch++); - va = (u32 *)&ch->rc_position; - - /* Skip write-list */ - ary = (struct rpcrdma_write_array *)va; - if (ary->wc_discrim == xdr_zero) - va = (u32 *)&ary->wc_nchunks; - else - /* - * rs_length is the 2nd 4B field in wc_target and taking its - * address skips the list terminator - */ - va = (u32 *)&ary->wc_array[ary->wc_nchunks].wc_target.rs_length; - - /* Skip reply-array */ - ary = (struct rpcrdma_write_array *)va; - if (ary->wc_discrim == xdr_zero) - va = (u32 *)&ary->wc_nchunks; - else - va = (u32 *)&ary->wc_array[ary->wc_nchunks]; - - rqstp->rq_arg.head[0].iov_base = va; - hdrlen = (unsigned long)va - (unsigned long)rmsgp; - rqstp->rq_arg.head[0].iov_len -= hdrlen; - - return hdrlen; -} - int svc_rdma_xdr_encode_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, - enum rpcrdma_errcode err, u32 *va) + enum rpcrdma_errcode err, __be32 *va) { - u32 *startp = va; + __be32 *startp = va; - *va++ = htonl(rmsgp->rm_xid); - *va++ = htonl(rmsgp->rm_vers); - *va++ = htonl(xprt->sc_max_requests); - *va++ = htonl(RDMA_ERROR); - *va++ = htonl(err); + *va++ = rmsgp->rm_xid; + *va++ = rmsgp->rm_vers; + *va++ = cpu_to_be32(xprt->sc_max_requests); + *va++ = rdma_error; + *va++ = cpu_to_be32(err); if (err == ERR_VERS) { - *va++ = htonl(RPCRDMA_VERSION); - *va++ = htonl(RPCRDMA_VERSION); + *va++ = rpcrdma_version; + *va++ = rpcrdma_version; } return (int)((unsigned long)va - (unsigned long)startp); @@ -297,7 +235,7 @@ int svc_rdma_xdr_get_reply_hdr_len(struct rpcrdma_msg *rmsgp) &rmsgp->rm_body.rm_chunks[1]; if (wr_ary->wc_discrim) wr_ary = (struct rpcrdma_write_array *) - &wr_ary->wc_array[ntohl(wr_ary->wc_nchunks)]. + &wr_ary->wc_array[be32_to_cpu(wr_ary->wc_nchunks)]. wc_target.rs_length; else wr_ary = (struct rpcrdma_write_array *) @@ -306,7 +244,7 @@ int svc_rdma_xdr_get_reply_hdr_len(struct rpcrdma_msg *rmsgp) /* skip reply array */ if (wr_ary->wc_discrim) wr_ary = (struct rpcrdma_write_array *) - &wr_ary->wc_array[ntohl(wr_ary->wc_nchunks)]; + &wr_ary->wc_array[be32_to_cpu(wr_ary->wc_nchunks)]; else wr_ary = (struct rpcrdma_write_array *) &wr_ary->wc_nchunks; @@ -325,7 +263,7 @@ void svc_rdma_xdr_encode_write_list(struct rpcrdma_msg *rmsgp, int chunks) ary = (struct rpcrdma_write_array *) &rmsgp->rm_body.rm_chunks[1]; ary->wc_discrim = xdr_one; - ary->wc_nchunks = htonl(chunks); + ary->wc_nchunks = cpu_to_be32(chunks); /* write-list terminator */ ary->wc_array[chunks].wc_target.rs_handle = xdr_zero; @@ -338,7 +276,7 @@ void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *ary, int chunks) { ary->wc_discrim = xdr_one; - ary->wc_nchunks = htonl(chunks); + ary->wc_nchunks = cpu_to_be32(chunks); } void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *ary, @@ -350,7 +288,7 @@ void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *ary, struct rpcrdma_segment *seg = &ary->wc_array[chunk_no].wc_target; seg->rs_handle = rs_handle; seg->rs_offset = rs_offset; - seg->rs_length = htonl(write_len); + seg->rs_length = cpu_to_be32(write_len); } void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *xprt, @@ -358,10 +296,10 @@ void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rdma_resp, enum rpcrdma_proc rdma_type) { - rdma_resp->rm_xid = htonl(rdma_argp->rm_xid); - rdma_resp->rm_vers = htonl(rdma_argp->rm_vers); - rdma_resp->rm_credit = htonl(xprt->sc_max_requests); - rdma_resp->rm_type = htonl(rdma_type); + rdma_resp->rm_xid = rdma_argp->rm_xid; + rdma_resp->rm_vers = rdma_argp->rm_vers; + rdma_resp->rm_credit = cpu_to_be32(xprt->sc_max_requests); + rdma_resp->rm_type = cpu_to_be32(rdma_type); /* Encode <nul> chunks lists */ rdma_resp->rm_body.rm_chunks[0] = xdr_zero; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 86b44164172b..2e1348bde325 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -85,7 +85,7 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, /* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */ rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base; - if (be32_to_cpu(rmsgp->rm_type) == RDMA_NOMSG) + if (rmsgp->rm_type == rdma_nomsg) rqstp->rq_arg.pages = &rqstp->rq_pages[0]; else rqstp->rq_arg.pages = &rqstp->rq_pages[1]; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 7de33d1af9b6..d25cd430f9ff 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -240,6 +240,7 @@ static int send_write_chunks(struct svcxprt_rdma *xprt, u32 xdr_off; int chunk_off; int chunk_no; + int nchunks; struct rpcrdma_write_array *arg_ary; struct rpcrdma_write_array *res_ary; int ret; @@ -251,14 +252,15 @@ static int send_write_chunks(struct svcxprt_rdma *xprt, &rdma_resp->rm_body.rm_chunks[1]; /* Write chunks start at the pagelist */ + nchunks = be32_to_cpu(arg_ary->wc_nchunks); for (xdr_off = rqstp->rq_res.head[0].iov_len, chunk_no = 0; - xfer_len && chunk_no < arg_ary->wc_nchunks; + xfer_len && chunk_no < nchunks; chunk_no++) { struct rpcrdma_segment *arg_ch; u64 rs_offset; arg_ch = &arg_ary->wc_array[chunk_no].wc_target; - write_len = min(xfer_len, ntohl(arg_ch->rs_length)); + write_len = min(xfer_len, be32_to_cpu(arg_ch->rs_length)); /* Prepare the response chunk given the length actually * written */ @@ -270,7 +272,7 @@ static int send_write_chunks(struct svcxprt_rdma *xprt, chunk_off = 0; while (write_len) { ret = send_write(xprt, rqstp, - ntohl(arg_ch->rs_handle), + be32_to_cpu(arg_ch->rs_handle), rs_offset + chunk_off, xdr_off, write_len, @@ -318,13 +320,13 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt, &rdma_resp->rm_body.rm_chunks[2]; /* xdr offset starts at RPC message */ - nchunks = ntohl(arg_ary->wc_nchunks); + nchunks = be32_to_cpu(arg_ary->wc_nchunks); for (xdr_off = 0, chunk_no = 0; xfer_len && chunk_no < nchunks; chunk_no++) { u64 rs_offset; ch = &arg_ary->wc_array[chunk_no].wc_target; - write_len = min(xfer_len, htonl(ch->rs_length)); + write_len = min(xfer_len, be32_to_cpu(ch->rs_length)); /* Prepare the reply chunk given the length actually * written */ @@ -335,7 +337,7 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt, chunk_off = 0; while (write_len) { ret = send_write(xprt, rqstp, - ntohl(ch->rs_handle), + be32_to_cpu(ch->rs_handle), rs_offset + chunk_off, xdr_off, write_len, @@ -515,7 +517,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) inline_bytes = rqstp->rq_res.len; /* Create the RDMA response header */ - res_page = svc_rdma_get_page(); + res_page = alloc_page(GFP_KERNEL | __GFP_NOFAIL); rdma_resp = page_address(res_page); reply_ary = svc_rdma_get_reply_array(rdma_argp); if (reply_ary) diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index f4cfa764d76f..6b36279e4288 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -91,7 +91,7 @@ struct svc_xprt_class svc_rdma_class = { .xcl_name = "rdma", .xcl_owner = THIS_MODULE, .xcl_ops = &svc_rdma_ops, - .xcl_max_payload = RPCSVC_MAXPAYLOAD_RDMA, + .xcl_max_payload = RPCRDMA_MAXPAYLOAD, .xcl_ident = XPRT_TRANSPORT_RDMA, }; @@ -99,12 +99,8 @@ struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt) { struct svc_rdma_op_ctxt *ctxt; - while (1) { - ctxt = kmem_cache_alloc(svc_rdma_ctxt_cachep, GFP_KERNEL); - if (ctxt) - break; - schedule_timeout_uninterruptible(msecs_to_jiffies(500)); - } + ctxt = kmem_cache_alloc(svc_rdma_ctxt_cachep, + GFP_KERNEL | __GFP_NOFAIL); ctxt->xprt = xprt; INIT_LIST_HEAD(&ctxt->dto_q); ctxt->count = 0; @@ -156,12 +152,8 @@ void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages) struct svc_rdma_req_map *svc_rdma_get_req_map(void) { struct svc_rdma_req_map *map; - while (1) { - map = kmem_cache_alloc(svc_rdma_map_cachep, GFP_KERNEL); - if (map) - break; - schedule_timeout_uninterruptible(msecs_to_jiffies(500)); - } + map = kmem_cache_alloc(svc_rdma_map_cachep, + GFP_KERNEL | __GFP_NOFAIL); map->count = 0; return map; } @@ -493,18 +485,6 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, return cma_xprt; } -struct page *svc_rdma_get_page(void) -{ - struct page *page; - - while ((page = alloc_page(GFP_KERNEL)) == NULL) { - /* If we can't get memory, wait a bit and try again */ - printk(KERN_INFO "svcrdma: out of memory...retrying in 1s\n"); - schedule_timeout_uninterruptible(msecs_to_jiffies(1000)); - } - return page; -} - int svc_rdma_post_recv(struct svcxprt_rdma *xprt) { struct ib_recv_wr recv_wr, *bad_recv_wr; @@ -523,7 +503,7 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt) pr_err("svcrdma: Too many sges (%d)\n", sge_no); goto err_put_ctxt; } - page = svc_rdma_get_page(); + page = alloc_page(GFP_KERNEL | __GFP_NOFAIL); ctxt->pages[sge_no] = page; pa = ib_dma_map_page(xprt->sc_cm_id->device, page, 0, PAGE_SIZE, @@ -1318,11 +1298,11 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, struct ib_send_wr err_wr; struct page *p; struct svc_rdma_op_ctxt *ctxt; - u32 *va; + __be32 *va; int length; int ret; - p = svc_rdma_get_page(); + p = alloc_page(GFP_KERNEL | __GFP_NOFAIL); va = page_address(p); /* XDR encode error */ diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 54f23b1be986..436da2caec95 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -48,7 +48,6 @@ */ #include <linux/module.h> -#include <linux/init.h> #include <linux/slab.h> #include <linux/seq_file.h> #include <linux/sunrpc/addr.h> @@ -59,11 +58,6 @@ # define RPCDBG_FACILITY RPCDBG_TRANS #endif -MODULE_LICENSE("Dual BSD/GPL"); - -MODULE_DESCRIPTION("RPC/RDMA Transport for Linux kernel NFS"); -MODULE_AUTHOR("Network Appliance, Inc."); - /* * tunables */ @@ -711,7 +705,7 @@ static struct xprt_class xprt_rdma = { .setup = xprt_setup_rdma, }; -static void __exit xprt_rdma_cleanup(void) +void xprt_rdma_cleanup(void) { int rc; @@ -728,7 +722,7 @@ static void __exit xprt_rdma_cleanup(void) __func__, rc); } -static int __init xprt_rdma_init(void) +int xprt_rdma_init(void) { int rc; @@ -753,6 +747,3 @@ static int __init xprt_rdma_init(void) #endif return 0; } - -module_init(xprt_rdma_init); -module_exit(xprt_rdma_cleanup); diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 78e0b8beaa36..58163b88738c 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -480,6 +480,11 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *); */ int rpcrdma_marshal_req(struct rpc_rqst *); +/* RPC/RDMA module init - xprtrdma/transport.c + */ +int xprt_rdma_init(void); +void xprt_rdma_cleanup(void); + /* Temporary NFS request map cache. Created in svc_rdma.c */ extern struct kmem_cache *svc_rdma_map_cachep; /* WR context cache. Created in svc_rdma.c */ @@ -487,10 +492,4 @@ extern struct kmem_cache *svc_rdma_ctxt_cachep; /* Workqueue created in svc_rdma.c */ extern struct workqueue_struct *svc_rdma_wq; -#if RPCSVC_MAXPAYLOAD < (RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT) -#define RPCSVC_MAXPAYLOAD_RDMA RPCSVC_MAXPAYLOAD -#else -#define RPCSVC_MAXPAYLOAD_RDMA (RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT) -#endif - #endif /* _LINUX_SUNRPC_XPRT_RDMA_H */ diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 66891e32c5e3..b0517287075b 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2982,7 +2982,7 @@ static int param_set_portnr(const char *val, const struct kernel_param *kp) RPC_MAX_RESVPORT); } -static struct kernel_param_ops param_ops_portnr = { +static const struct kernel_param_ops param_ops_portnr = { .set = param_set_portnr, .get = param_get_uint, }; @@ -3001,7 +3001,7 @@ static int param_set_slot_table_size(const char *val, RPC_MAX_SLOT_TABLE); } -static struct kernel_param_ops param_ops_slot_table_size = { +static const struct kernel_param_ops param_ops_slot_table_size = { .set = param_set_slot_table_size, .get = param_get_uint, }; @@ -3017,7 +3017,7 @@ static int param_set_max_slot_table_size(const char *val, RPC_MAX_SLOT_TABLE_LIMIT); } -static struct kernel_param_ops param_ops_max_slot_table_size = { +static const struct kernel_param_ops param_ops_max_slot_table_size = { .set = param_set_max_slot_table_size, .get = param_get_uint, }; diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 4906ca3c0f3a..a816382fc8af 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -108,6 +108,11 @@ void tipc_bclink_remove_node(struct net *net, u32 addr) tipc_bclink_lock(net); tipc_nmap_remove(&tn->bclink->bcast_nodes, addr); + + /* Last node? => reset backlog queue */ + if (!tn->bclink->bcast_nodes.count) + tipc_link_purge_backlog(&tn->bclink->link); + tipc_bclink_unlock(net); } diff --git a/net/tipc/link.c b/net/tipc/link.c index ca8b8e0f49b5..eaa9fe54b4ae 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -404,7 +404,7 @@ void tipc_link_reset_fragments(struct tipc_link *l_ptr) l_ptr->reasm_buf = NULL; } -static void tipc_link_purge_backlog(struct tipc_link *l) +void tipc_link_purge_backlog(struct tipc_link *l) { __skb_queue_purge(&l->backlogq); l->backlog[TIPC_LOW_IMPORTANCE].len = 0; diff --git a/net/tipc/link.h b/net/tipc/link.h index 0c02c973e985..ae0a0ea572f2 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -218,6 +218,7 @@ void tipc_link_reset_fragments(struct tipc_link *l_ptr); int tipc_link_is_up(struct tipc_link *l_ptr); int tipc_link_is_active(struct tipc_link *l_ptr); void tipc_link_purge_queues(struct tipc_link *l_ptr); +void tipc_link_purge_backlog(struct tipc_link *l); void tipc_link_reset_all(struct tipc_node *node); void tipc_link_reset(struct tipc_link *l_ptr); int tipc_link_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest, diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 46b6ed534ef2..3a7567f690f3 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2007,6 +2007,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags) res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 1); if (res) goto exit; + security_sk_clone(sock->sk, new_sock->sk); new_sk = new_sock->sk; new_tsock = tipc_sk(new_sk); |