diff options
| author | Trond Myklebust <trond.myklebust@primarydata.com> | 2016-03-16 23:24:36 +0300 |
|---|---|---|
| committer | Trond Myklebust <trond.myklebust@primarydata.com> | 2016-03-16 23:25:09 +0300 |
| commit | 1425075e7272faaa3629a1e2df679c0ba4cf55d3 (patch) | |
| tree | 6d79a735f8a02d6dc9e27b915f6244fe1ab6b7ff /net | |
| parent | 849dc3244c916545790bfb9055625a3719061c92 (diff) | |
| parent | 2fa8f88d8892507ecff0126fbc67906740491d31 (diff) | |
| download | linux-1425075e7272faaa3629a1e2df679c0ba4cf55d3.tar.xz | |
Merge tag 'nfs-rdma-4.6-1' of git://git.linux-nfs.org/projects/anna/nfs-rdma
NFS: NFSoRDMA Client Side Changes
These patches include several bugfixes and cleanups for the NFSoRDMA client.
This includes bugfixes for NFS v4.1, proper RDMA_ERROR handling, and fixes
from the recent workqueue swicchover. These patches also switch xprtrdma to
use the new CQ API
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
* tag 'nfs-rdma-4.6-1' of git://git.linux-nfs.org/projects/anna/nfs-rdma: (787 commits)
xprtrdma: Use new CQ API for RPC-over-RDMA client send CQs
xprtrdma: Use an anonymous union in struct rpcrdma_mw
xprtrdma: Use new CQ API for RPC-over-RDMA client receive CQs
xprtrdma: Serialize credit accounting again
xprtrdma: Properly handle RDMA_ERROR replies
rpcrdma: Add RPCRDMA_HDRLEN_ERR
xprtrdma: Do not wait if ib_post_send() fails
xprtrdma: Segment head and tail XDR buffers on page boundaries
xprtrdma: Clean up dprintk format string containing a newline
xprtrdma: Clean up physical_op_map()
xprtrdma: Clean up unused RPCRDMA_INLINE_PAD_THRESH macro
Diffstat (limited to 'net')
58 files changed, 708 insertions, 410 deletions
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index d5871ac493eb..f066781be3c8 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1625,7 +1625,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) rt = atrtr_find(&at_hint); } - err = ENETUNREACH; + err = -ENETUNREACH; if (!rt) goto out; diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index e6c8382c79ba..ccf70bed0d0c 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -527,11 +527,12 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, * gets dereferenced. */ spin_lock_bh(&bat_priv->gw.list_lock); - hlist_del_init_rcu(&gw_node->list); + if (!hlist_unhashed(&gw_node->list)) { + hlist_del_init_rcu(&gw_node->list); + batadv_gw_node_free_ref(gw_node); + } spin_unlock_bh(&bat_priv->gw.list_lock); - batadv_gw_node_free_ref(gw_node); - curr_gw = batadv_gw_get_selected_gw_node(bat_priv); if (gw_node == curr_gw) batadv_gw_reselect(bat_priv); diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 01acccc4d218..57f7107169f5 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -76,6 +76,28 @@ out: } /** + * batadv_mutual_parents - check if two devices are each others parent + * @dev1: 1st net_device + * @dev2: 2nd net_device + * + * veth devices come in pairs and each is the parent of the other! + * + * Return: true if the devices are each others parent, otherwise false + */ +static bool batadv_mutual_parents(const struct net_device *dev1, + const struct net_device *dev2) +{ + int dev1_parent_iflink = dev_get_iflink(dev1); + int dev2_parent_iflink = dev_get_iflink(dev2); + + if (!dev1_parent_iflink || !dev2_parent_iflink) + return false; + + return (dev1_parent_iflink == dev2->ifindex) && + (dev2_parent_iflink == dev1->ifindex); +} + +/** * batadv_is_on_batman_iface - check if a device is a batman iface descendant * @net_dev: the device to check * @@ -108,6 +130,9 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) if (WARN(!parent_dev, "Cannot find parent device")) return false; + if (batadv_mutual_parents(net_dev, parent_dev)) + return false; + ret = batadv_is_on_batman_iface(parent_dev); return ret; diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index cdfc85fa2743..0e80fd1461ab 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -303,9 +303,11 @@ static void batadv_tt_global_size_mod(struct batadv_orig_node *orig_node, if (atomic_add_return(v, &vlan->tt.num_entries) == 0) { spin_lock_bh(&orig_node->vlan_list_lock); - hlist_del_init_rcu(&vlan->list); + if (!hlist_unhashed(&vlan->list)) { + hlist_del_init_rcu(&vlan->list); + batadv_orig_node_vlan_free_ref(vlan); + } spin_unlock_bh(&orig_node->vlan_list_lock); - batadv_orig_node_vlan_free_ref(vlan); } batadv_orig_node_vlan_free_ref(vlan); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 47bcef754796..883c821a9e78 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -4112,8 +4112,10 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, break; } - *req_complete = bt_cb(skb)->hci.req_complete; - *req_complete_skb = bt_cb(skb)->hci.req_complete_skb; + if (bt_cb(skb)->hci.req_flags & HCI_REQ_SKB) + *req_complete_skb = bt_cb(skb)->hci.req_complete_skb; + else + *req_complete = bt_cb(skb)->hci.req_complete; kfree_skb(skb); } spin_unlock_irqrestore(&hdev->cmd_q.lock, flags); diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 30e105f57f0d..74c278e00225 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -425,8 +425,8 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, mp = br_mdb_ip_get(mdb, group); if (!mp) { mp = br_multicast_new_group(br, port, group); - err = PTR_ERR(mp); - if (IS_ERR(mp)) + err = PTR_ERR_OR_ZERO(mp); + if (err) return err; } diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c index 61d7617d9249..b82440e1fcb4 100644 --- a/net/caif/cfrfml.c +++ b/net/caif/cfrfml.c @@ -159,7 +159,7 @@ static int cfrfml_receive(struct cflayer *layr, struct cfpkt *pkt) tmppkt = NULL; /* Verify that length is correct */ - err = EPROTO; + err = -EPROTO; if (rfml->pdu_size != cfpkt_getlen(pkt) - RFM_HEAD_SIZE + 1) goto out; } diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 9cfedf565f5b..9382619a405b 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1197,6 +1197,13 @@ static bool ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, return new_piece; } +static size_t sizeof_footer(struct ceph_connection *con) +{ + return (con->peer_features & CEPH_FEATURE_MSG_AUTH) ? + sizeof(struct ceph_msg_footer) : + sizeof(struct ceph_msg_footer_old); +} + static void prepare_message_data(struct ceph_msg *msg, u32 data_len) { BUG_ON(!msg); @@ -2335,9 +2342,9 @@ static int read_partial_message(struct ceph_connection *con) ceph_pr_addr(&con->peer_addr.in_addr), seq, con->in_seq + 1); con->in_base_pos = -front_len - middle_len - data_len - - sizeof(m->footer); + sizeof_footer(con); con->in_tag = CEPH_MSGR_TAG_READY; - return 0; + return 1; } else if ((s64)seq - (s64)con->in_seq > 1) { pr_err("read_partial_message bad seq %lld expected %lld\n", seq, con->in_seq + 1); @@ -2360,10 +2367,10 @@ static int read_partial_message(struct ceph_connection *con) /* skip this message */ dout("alloc_msg said skip message\n"); con->in_base_pos = -front_len - middle_len - data_len - - sizeof(m->footer); + sizeof_footer(con); con->in_tag = CEPH_MSGR_TAG_READY; con->in_seq++; - return 0; + return 1; } BUG_ON(!con->in_msg); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 3534e12683d3..5bc053778fed 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -2853,8 +2853,8 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, mutex_lock(&osdc->request_mutex); req = __lookup_request(osdc, tid); if (!req) { - pr_warn("%s osd%d tid %llu unknown, skipping\n", - __func__, osd->o_osd, tid); + dout("%s osd%d tid %llu unknown, skipping\n", __func__, + osd->o_osd, tid); m = NULL; *skip = 1; goto out; diff --git a/net/core/dev.c b/net/core/dev.c index 8cba3d852f25..0ef061b2badc 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5379,12 +5379,12 @@ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; - lower = list_entry((*iter)->next, struct netdev_adjacent, list); + lower = list_entry(*iter, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; - *iter = &lower->list; + *iter = lower->list.next; return lower->dev; } @@ -7422,8 +7422,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); - if (!dev->tx_queue_len) + if (!dev->tx_queue_len) { dev->priv_flags |= IFF_NO_QUEUE; + dev->tx_queue_len = 1; + } dev->num_tx_queues = txqs; dev->real_num_tx_queues = txqs; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index d79699c9d1b9..12e700332010 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -208,7 +208,6 @@ ip: case htons(ETH_P_IPV6): { const struct ipv6hdr *iph; struct ipv6hdr _iph; - __be32 flow_label; ipv6: iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph); @@ -230,8 +229,12 @@ ipv6: key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } - flow_label = ip6_flowlabel(iph); - if (flow_label) { + if ((dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_FLOW_LABEL) || + (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL)) && + ip6_flowlabel(iph)) { + __be32 flow_label = ip6_flowlabel(iph); + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { key_tags = skb_flow_dissector_target(flow_dissector, @@ -396,6 +399,13 @@ ip_proto_again: goto out_bad; proto = eth->h_proto; nhoff += sizeof(*eth); + + /* Cap headers that we access via pointers at the + * end of the Ethernet header as our maximum alignment + * at that point is only 2 bytes. + */ + if (NET_IP_ALIGN) + hlen = nhoff; } key_control->flags |= FLOW_DIS_ENCAPSULATION; diff --git a/net/core/scm.c b/net/core/scm.c index 14596fb37172..2696aefdc148 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -87,6 +87,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) *fplp = fpl; fpl->count = 0; fpl->max = SCM_MAX_FD; + fpl->user = NULL; } fpp = &fpl->fp[fpl->count]; @@ -107,6 +108,10 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) *fpp++ = file; fpl->count++; } + + if (!fpl->user) + fpl->user = get_uid(current_user()); + return num; } @@ -119,6 +124,7 @@ void __scm_destroy(struct scm_cookie *scm) scm->fp = NULL; for (i=fpl->count-1; i>=0; i--) fput(fpl->fp[i]); + free_uid(fpl->user); kfree(fpl); } } @@ -336,6 +342,7 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) for (i = 0; i < fpl->count; i++) get_file(fpl->fp[i]); new_fpl->max = new_fpl->count; + new_fpl->user = get_uid(fpl->user); } return new_fpl; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b2df375ec9c2..5bf88f58bee7 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -79,6 +79,8 @@ struct kmem_cache *skbuff_head_cache __read_mostly; static struct kmem_cache *skbuff_fclone_cache __read_mostly; +int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; +EXPORT_SYMBOL(sysctl_max_skb_frags); /** * skb_panic - private function for out-of-line support diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 95b6139d710c..a6beb7b6ae55 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -26,6 +26,7 @@ static int zero = 0; static int one = 1; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; +static int max_skb_frags = MAX_SKB_FRAGS; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -392,6 +393,15 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "max_skb_frags", + .data = &sysctl_max_skb_frags, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &max_skb_frags, + }, { } }; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 5684e14932bd..902d606324a0 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -824,26 +824,26 @@ lookup: if (sk->sk_state == DCCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; - if (likely(sk->sk_state == DCCP_LISTEN)) { - nsk = dccp_check_req(sk, skb, req); - } else { + if (unlikely(sk->sk_state != DCCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = dccp_check_req(sk, skb, req); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); } else if (dccp_child_process(sk, nsk, skb)) { dccp_v4_ctl_send_reset(sk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 9c6d0508e63a..b8608b71a66d 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -691,26 +691,26 @@ lookup: if (sk->sk_state == DCCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; - if (likely(sk->sk_state == DCCP_LISTEN)) { - nsk = dccp_check_req(sk, skb, req); - } else { + if (unlikely(sk->sk_state != DCCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = dccp_check_req(sk, skb, req); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); } else if (dccp_child_process(sk, nsk, skb)) { dccp_v6_ctl_send_reset(sk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 40b9ca72aae3..ab24521beb4d 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1194,7 +1194,6 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, if (ret) { netdev_err(master, "error %d registering interface %s\n", ret, slave_dev->name); - phy_disconnect(p->phy); ds->ports[port] = NULL; free_netdev(slave_dev); return ret; @@ -1205,6 +1204,7 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, ret = dsa_slave_phy_setup(p, slave_dev); if (ret) { netdev_err(master, "error %d setting up slave phy\n", ret); + unregister_netdev(slave_dev); free_netdev(slave_dev); return ret; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index cebd9d31e65a..f6303b17546b 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1847,7 +1847,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, if (err < 0) goto errout; - err = EINVAL; + err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 46b9c887bede..64148914803a 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -789,14 +789,16 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, reqsk_put(req); } -void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, - struct sock *child) +struct sock *inet_csk_reqsk_queue_add(struct sock *sk, + struct request_sock *req, + struct sock *child) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; spin_lock(&queue->rskq_lock); if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_child_forget(sk, req, child); + child = NULL; } else { req->sk = child; req->dl_next = NULL; @@ -808,6 +810,7 @@ void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, sk_acceptq_added(sk); } spin_unlock(&queue->rskq_lock); + return child; } EXPORT_SYMBOL(inet_csk_reqsk_queue_add); @@ -817,11 +820,8 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, if (own_req) { inet_csk_reqsk_queue_drop(sk, req); reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); - inet_csk_reqsk_queue_add(sk, req, child); - /* Warning: caller must not call reqsk_put(req); - * child stole last reference on it. - */ - return child; + if (inet_csk_reqsk_queue_add(sk, req, child)) + return child; } /* Too bad, another child took ownership of the request, undo. */ bh_unlock_sock(child); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 7c51c4e1661f..41ba68de46d8 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1054,8 +1054,9 @@ static const struct net_device_ops gre_tap_netdev_ops = { static void ipgre_tap_setup(struct net_device *dev) { ether_setup(dev); - dev->netdev_ops = &gre_tap_netdev_ops; - dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + dev->netdev_ops = &gre_tap_netdev_ops; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, gre_tap_net_id); } @@ -1240,6 +1241,14 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, err = ipgre_newlink(net, dev, tb, NULL); if (err < 0) goto out; + + /* openvswitch users expect packet sizes to be unrestricted, + * so set the largest MTU we can. + */ + err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false); + if (err) + goto out; + return dev; out: free_netdev(dev); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 5f73a7c03e27..a50124260f5a 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -249,6 +249,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc, switch (cmsg->cmsg_type) { case IP_RETOPTS: err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr)); + + /* Our caller is responsible for freeing ipc->opt */ err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg), err < 40 ? err : 40); if (err) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index c7bd72e9b544..89e8861e05fc 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -943,17 +943,31 @@ done: } EXPORT_SYMBOL_GPL(ip_tunnel_ioctl); -int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu) +int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); + int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen; - if (new_mtu < 68 || - new_mtu > 0xFFF8 - dev->hard_header_len - t_hlen) + if (new_mtu < 68) return -EINVAL; + + if (new_mtu > max_mtu) { + if (strict) + return -EINVAL; + + new_mtu = max_mtu; + } + dev->mtu = new_mtu; return 0; } +EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu); + +int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu) +{ + return __ip_tunnel_change_mtu(dev, new_mtu, true); +} EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu); static void ip_tunnel_dev_free(struct net_device *dev) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index c117b21b937d..d3a27165f9cc 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -746,8 +746,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); return err; + } if (ipc.opt) free = 1; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index bc35f1842512..7113bae4e6a0 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -547,8 +547,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(net, msg, &ipc, false); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); goto out; + } if (ipc.opt) free = 1; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 85f184e429c6..02c62299d717 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -129,6 +129,7 @@ static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; +static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; /* * Interface to generic destination cache. */ @@ -755,7 +756,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, new_gw, - 0, 0); + 0, jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; @@ -1556,6 +1557,36 @@ static void ip_handle_martian_source(struct net_device *dev, #endif } +static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) +{ + struct fnhe_hash_bucket *hash; + struct fib_nh_exception *fnhe, __rcu **fnhe_p; + u32 hval = fnhe_hashfun(daddr); + + spin_lock_bh(&fnhe_lock); + + hash = rcu_dereference_protected(nh->nh_exceptions, + lockdep_is_held(&fnhe_lock)); + hash += hval; + + fnhe_p = &hash->chain; + fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); + while (fnhe) { + if (fnhe->fnhe_daddr == daddr) { + rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( + fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); + fnhe_flush_routes(fnhe); + kfree_rcu(fnhe, rcu); + break; + } + fnhe_p = &fnhe->fnhe_next; + fnhe = rcu_dereference_protected(fnhe->fnhe_next, + lockdep_is_held(&fnhe_lock)); + } + + spin_unlock_bh(&fnhe_lock); +} + /* called in rcu_read_lock() section */ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, @@ -1609,11 +1640,20 @@ static int __mkroute_input(struct sk_buff *skb, fnhe = find_exception(&FIB_RES_NH(*res), daddr); if (do_cache) { - if (fnhe) + if (fnhe) { rth = rcu_dereference(fnhe->fnhe_rth_input); - else - rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); + if (rth && rth->dst.expires && + time_after(jiffies, rth->dst.expires)) { + ip_del_fnhe(&FIB_RES_NH(*res), daddr); + fnhe = NULL; + } else { + goto rt_cache; + } + } + + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); +rt_cache: if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; @@ -2014,19 +2054,29 @@ static struct rtable *__mkroute_output(const struct fib_result *res, struct fib_nh *nh = &FIB_RES_NH(*res); fnhe = find_exception(nh, fl4->daddr); - if (fnhe) + if (fnhe) { prth = &fnhe->fnhe_rth_output; - else { - if (unlikely(fl4->flowi4_flags & - FLOWI_FLAG_KNOWN_NH && - !(nh->nh_gw && - nh->nh_scope == RT_SCOPE_LINK))) { - do_cache = false; - goto add; + rth = rcu_dereference(*prth); + if (rth && rth->dst.expires && + time_after(jiffies, rth->dst.expires)) { + ip_del_fnhe(nh, fl4->daddr); + fnhe = NULL; + } else { + goto rt_cache; } - prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); } + + if (unlikely(fl4->flowi4_flags & + FLOWI_FLAG_KNOWN_NH && + !(nh->nh_gw && + nh->nh_scope == RT_SCOPE_LINK))) { + do_cache = false; + goto add; + } + prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); rth = rcu_dereference(*prth); + +rt_cache: if (rt_cache_valid(rth)) { dst_hold(&rth->dst); return rth; @@ -2569,7 +2619,6 @@ void ip_rt_multicast_event(struct in_device *in_dev) } #ifdef CONFIG_SYSCTL -static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 19746b3fcbbe..483ffdf5aa4d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -940,7 +940,7 @@ new_segment: i = skb_shinfo(skb)->nr_frags; can_coalesce = skb_can_coalesce(skb, i, page, offset); - if (!can_coalesce && i >= MAX_SKB_FRAGS) { + if (!can_coalesce && i >= sysctl_max_skb_frags) { tcp_mark_push(tp, skb); goto new_segment; } @@ -1213,7 +1213,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i == MAX_SKB_FRAGS || !sg) { + if (i == sysctl_max_skb_frags || !sg) { tcp_mark_push(tp, skb); goto new_segment; } @@ -2950,7 +2950,7 @@ static void __tcp_alloc_md5sig_pool(void) struct crypto_hash *hash; hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR_OR_NULL(hash)) + if (IS_ERR(hash)) return; per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm = hash; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 1c2a73406261..3b2c8e90a475 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2896,7 +2896,10 @@ static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us) { const u32 now = tcp_time_stamp, wlen = sysctl_tcp_min_rtt_wlen * HZ; struct rtt_meas *m = tcp_sk(sk)->rtt_min; - struct rtt_meas rttm = { .rtt = (rtt_us ? : 1), .ts = now }; + struct rtt_meas rttm = { + .rtt = likely(rtt_us) ? rtt_us : jiffies_to_usecs(1), + .ts = now, + }; u32 elapsed; /* Check if the new measurement updates the 1st, 2nd, or 3rd choices */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a4d523709ab3..487ac67059e2 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -311,7 +311,7 @@ static void do_redirect(struct sk_buff *skb, struct sock *sk) /* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */ -void tcp_req_err(struct sock *sk, u32 seq) +void tcp_req_err(struct sock *sk, u32 seq, bool abort) { struct request_sock *req = inet_reqsk(sk); struct net *net = sock_net(sk); @@ -323,7 +323,7 @@ void tcp_req_err(struct sock *sk, u32 seq) if (seq != tcp_rsk(req)->snt_isn) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - } else { + } else if (abort) { /* * Still in SYN_RECV, just remove it silently. * There is no good way to pass the error to the newly @@ -383,7 +383,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) } seq = ntohl(th->seq); if (sk->sk_state == TCP_NEW_SYN_RECV) - return tcp_req_err(sk, seq); + return tcp_req_err(sk, seq, + type == ICMP_PARAMETERPROB || + type == ICMP_TIME_EXCEEDED || + (type == ICMP_DEST_UNREACH && + (code == ICMP_NET_UNREACH || + code == ICMP_HOST_UNREACH))); bh_lock_sock(sk); /* If too many ICMPs get dropped on busy @@ -1592,28 +1597,30 @@ process: if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; - if (tcp_v4_inbound_md5_hash(sk, skb)) - goto discard_and_relse; - if (likely(sk->sk_state == TCP_LISTEN)) { - nsk = tcp_check_req(sk, skb, req, false); - } else { + if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) { + reqsk_put(req); + goto discard_it; + } + if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = tcp_check_req(sk, skb, req, false); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); } else if (tcp_child_process(sk, nsk, skb)) { tcp_v4_send_reset(nsk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index be0b21852b13..95d2f198017e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1048,8 +1048,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sock_net(sk), msg, &ipc, sk->sk_family == AF_INET6); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); return err; + } if (ipc.opt) free = 1; connected = 0; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 38eeddedfc21..bdd7eac4307a 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -583,7 +583,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, if (err < 0) goto errout; - err = EINVAL; + err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; @@ -3538,6 +3538,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net_device *dev = idev->dev; + bool notify = false; addrconf_join_solict(dev, &ifp->addr); @@ -3583,7 +3584,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) /* Because optimistic nodes can use this address, * notify listeners. If DAD fails, RTM_DELADDR is sent. */ - ipv6_ifa_notify(RTM_NEWADDR, ifp); + notify = true; } } @@ -3591,6 +3592,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) out: spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); + if (notify) + ipv6_ifa_notify(RTM_NEWADDR, ifp); } static void addrconf_dad_start(struct inet6_ifaddr *ifp) diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 1f9ebe3cbb4a..dc2db4f7b182 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -540,12 +540,13 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) } spin_lock_bh(&ip6_sk_fl_lock); for (sflp = &np->ipv6_fl_list; - (sfl = rcu_dereference(*sflp)) != NULL; + (sfl = rcu_dereference_protected(*sflp, + lockdep_is_held(&ip6_sk_fl_lock))) != NULL; sflp = &sfl->next) { if (sfl->fl->label == freq.flr_label) { if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK)) np->flow_label &= ~IPV6_FLOWLABEL_MASK; - *sflp = rcu_dereference(sfl->next); + *sflp = sfl->next; spin_unlock_bh(&ip6_sk_fl_lock); fl_release(sfl->fl); kfree_rcu(sfl, rcu); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index f37f18b6b40c..a69aad1e29d1 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1512,6 +1512,7 @@ static void ip6gre_tap_setup(struct net_device *dev) dev->destructor = ip6gre_dev_free; dev->features |= NETIF_F_NETNS_LOCAL; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; } static int ip6gre_newlink(struct net *src_net, struct net_device *dev, diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c index 31ba7ca19757..051b6a6bfff6 100644 --- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c @@ -21,6 +21,10 @@ #include <net/ipv6.h> #include <net/netfilter/ipv6/nf_nat_masquerade.h> +#define MAX_WORK_COUNT 16 + +static atomic_t v6_worker_count; + unsigned int nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, const struct net_device *out) @@ -78,14 +82,78 @@ static struct notifier_block masq_dev_notifier = { .notifier_call = masq_device_event, }; +struct masq_dev_work { + struct work_struct work; + struct net *net; + int ifindex; +}; + +static void iterate_cleanup_work(struct work_struct *work) +{ + struct masq_dev_work *w; + long index; + + w = container_of(work, struct masq_dev_work, work); + + index = w->ifindex; + nf_ct_iterate_cleanup(w->net, device_cmp, (void *)index, 0, 0); + + put_net(w->net); + kfree(w); + atomic_dec(&v6_worker_count); + module_put(THIS_MODULE); +} + +/* ipv6 inet notifier is an atomic notifier, i.e. we cannot + * schedule. + * + * Unfortunately, nf_ct_iterate_cleanup can run for a long + * time if there are lots of conntracks and the system + * handles high softirq load, so it frequently calls cond_resched + * while iterating the conntrack table. + * + * So we defer nf_ct_iterate_cleanup walk to the system workqueue. + * + * As we can have 'a lot' of inet_events (depending on amount + * of ipv6 addresses being deleted), we also need to add an upper + * limit to the number of queued work items. + */ static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { struct inet6_ifaddr *ifa = ptr; - struct netdev_notifier_info info; + const struct net_device *dev; + struct masq_dev_work *w; + struct net *net; + + if (event != NETDEV_DOWN || + atomic_read(&v6_worker_count) >= MAX_WORK_COUNT) + return NOTIFY_DONE; + + dev = ifa->idev->dev; + net = maybe_get_net(dev_net(dev)); + if (!net) + return NOTIFY_DONE; - netdev_notifier_info_init(&info, ifa->idev->dev); - return masq_device_event(this, event, &info); + if (!try_module_get(THIS_MODULE)) + goto err_module; + + w = kmalloc(sizeof(*w), GFP_ATOMIC); + if (w) { + atomic_inc(&v6_worker_count); + + INIT_WORK(&w->work, iterate_cleanup_work); + w->ifindex = dev->ifindex; + w->net = net; + schedule_work(&w->work); + + return NOTIFY_DONE; + } + + module_put(THIS_MODULE); + err_module: + put_net(net); + return NOTIFY_DONE; } static struct notifier_block masq_inet_notifier = { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 006396e31cb0..5c8c84273028 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -327,6 +327,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct tcp_sock *tp; __u32 seq, snd_una; struct sock *sk; + bool fatal; int err; sk = __inet6_lookup_established(net, &tcp_hashinfo, @@ -345,8 +346,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return; } seq = ntohl(th->seq); + fatal = icmpv6_err_convert(type, code, &err); if (sk->sk_state == TCP_NEW_SYN_RECV) - return tcp_req_err(sk, seq); + return tcp_req_err(sk, seq, fatal); bh_lock_sock(sk); if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) @@ -400,7 +402,6 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, goto out; } - icmpv6_err_convert(type, code, &err); /* Might be for an request_sock */ switch (sk->sk_state) { @@ -1386,7 +1387,7 @@ process: if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; tcp_v6_fill_cb(skb, hdr, th); @@ -1394,24 +1395,24 @@ process: reqsk_put(req); goto discard_it; } - if (likely(sk->sk_state == TCP_LISTEN)) { - nsk = tcp_check_req(sk, skb, req, false); - } else { + if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = tcp_check_req(sk, skb, req, false); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); tcp_v6_restore_cb(skb); } else if (tcp_child_process(sk, nsk, skb)) { tcp_v6_send_reset(nsk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index f93c5be612a7..2caaa84ce92d 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -124,8 +124,13 @@ static int l2tp_tunnel_notify(struct genl_family *family, ret = l2tp_nl_tunnel_send(msg, info->snd_portid, info->snd_seq, NLM_F_ACK, tunnel, cmd); - if (ret >= 0) - return genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + if (ret >= 0) { + ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + /* We don't care if no one is listening */ + if (ret == -ESRCH) + ret = 0; + return ret; + } nlmsg_free(msg); @@ -147,8 +152,13 @@ static int l2tp_session_notify(struct genl_family *family, ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq, NLM_F_ACK, session, cmd); - if (ret >= 0) - return genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + if (ret >= 0) { + ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + /* We don't care if no one is listening */ + if (ret == -ESRCH) + ret = 0; + return ret; + } nlmsg_free(msg); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 8c067e6663a1..95e757c377f9 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -891,7 +891,7 @@ config NETFILTER_XT_TARGET_TEE depends on IPV6 || IPV6=n depends on !NF_CONNTRACK || NF_CONNTRACK select NF_DUP_IPV4 - select NF_DUP_IPV6 if IP6_NF_IPTABLES != n + select NF_DUP_IPV6 if IPV6 ---help--- This option adds a "TEE" target with which a packet can be cloned and this clone be rerouted to another nexthop. diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 58882de06bd7..f60b4fdeeb8c 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1412,6 +1412,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), } spin_unlock(lockp); local_bh_enable(); + cond_resched(); } for_each_possible_cpu(cpu) { @@ -1424,6 +1425,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), set_bit(IPS_DYING_BIT, &ct->status); } spin_unlock_bh(&pcpu->lock); + cond_resched(); } return NULL; found: @@ -1440,6 +1442,8 @@ void nf_ct_iterate_cleanup(struct net *net, struct nf_conn *ct; unsigned int bucket = 0; + might_sleep(); + while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) { /* Time to push up daises... */ if (del_timer(&ct->timeout)) @@ -1448,6 +1452,7 @@ void nf_ct_iterate_cleanup(struct net *net, /* ... else the timer will get him soon. */ nf_ct_put(ct); + cond_resched(); } } EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index a7ba23353dab..857ae89633af 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -311,14 +311,14 @@ replay: #endif { nfnl_unlock(subsys_id); - netlink_ack(skb, nlh, -EOPNOTSUPP); + netlink_ack(oskb, nlh, -EOPNOTSUPP); return kfree_skb(skb); } } if (!ss->commit || !ss->abort) { nfnl_unlock(subsys_id); - netlink_ack(skb, nlh, -EOPNOTSUPP); + netlink_ack(oskb, nlh, -EOPNOTSUPP); return kfree_skb(skb); } @@ -328,10 +328,12 @@ replay: nlh = nlmsg_hdr(skb); err = 0; - if (nlmsg_len(nlh) < sizeof(struct nfgenmsg) || - skb->len < nlh->nlmsg_len) { - err = -EINVAL; - goto ack; + if (nlh->nlmsg_len < NLMSG_HDRLEN || + skb->len < nlh->nlmsg_len || + nlmsg_len(nlh) < sizeof(struct nfgenmsg)) { + nfnl_err_reset(&err_list); + status |= NFNL_BATCH_FAILURE; + goto done; } /* Only requests are handled by the kernel */ @@ -406,7 +408,7 @@ ack: * pointing to the batch header. */ nfnl_err_reset(&err_list); - netlink_ack(skb, nlmsg_hdr(oskb), -ENOMEM); + netlink_ack(oskb, nlmsg_hdr(oskb), -ENOMEM); status |= NFNL_BATCH_FAILURE; goto done; } diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 94837d236ab0..2671b9deb103 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -312,7 +312,7 @@ static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout) hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode) untimeout(h, timeout); } - nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); } local_bh_enable(); } diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index c7808fc19719..c9743f78f219 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -100,7 +100,7 @@ static int nft_counter_init(const struct nft_ctx *ctx, cpu_stats = netdev_alloc_pcpu_stats(struct nft_counter_percpu); if (cpu_stats == NULL) - return ENOMEM; + return -ENOMEM; preempt_disable(); this_cpu = this_cpu_ptr(cpu_stats); @@ -138,7 +138,7 @@ static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src) cpu_stats = __netdev_alloc_pcpu_stats(struct nft_counter_percpu, GFP_ATOMIC); if (cpu_stats == NULL) - return ENOMEM; + return -ENOMEM; preempt_disable(); this_cpu = this_cpu_ptr(cpu_stats); diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index 3eff7b67cdf2..6e57a3966dc5 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -38,7 +38,7 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par) return XT_CONTINUE; } -#if IS_ENABLED(CONFIG_NF_DUP_IPV6) +#if IS_ENABLED(CONFIG_IPV6) static unsigned int tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) { @@ -131,7 +131,7 @@ static struct xt_target tee_tg_reg[] __read_mostly = { .destroy = tee_tg_destroy, .me = THIS_MODULE, }, -#if IS_ENABLED(CONFIG_NF_DUP_IPV6) +#if IS_ENABLED(CONFIG_IPV6) { .name = "TEE", .revision = 1, diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 1605691d9414..5eb7694348b5 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -90,7 +90,9 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) int err; struct vxlan_config conf = { .no_share = true, - .flags = VXLAN_F_COLLECT_METADATA, + .flags = VXLAN_F_COLLECT_METADATA | VXLAN_F_UDP_ZERO_CSUM6_RX, + /* Don't restrict the packets that can be sent by MTU */ + .mtu = IP_MAX_MTU, }; if (!options) { diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index b5c2cf2aa6d4..af1acf009866 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1852,6 +1852,7 @@ reset: } tp = old_tp; + protocol = tc_skb_protocol(skb); goto reclassify; #endif } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index ab0d538a74ed..1099e99a53c4 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -60,6 +60,8 @@ #include <net/inet_common.h> #include <net/inet_ecn.h> +#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024) + /* Global data structures. */ struct sctp_globals sctp_globals __read_mostly; @@ -1355,6 +1357,8 @@ static __init int sctp_init(void) unsigned long limit; int max_share; int order; + int num_entries; + int max_entry_order; sock_skb_cb_check_size(sizeof(struct sctp_ulpevent)); @@ -1407,14 +1411,24 @@ static __init int sctp_init(void) /* Size and allocate the association hash table. * The methodology is similar to that of the tcp hash tables. + * Though not identical. Start by getting a goal size */ if (totalram_pages >= (128 * 1024)) goal = totalram_pages >> (22 - PAGE_SHIFT); else goal = totalram_pages >> (24 - PAGE_SHIFT); - for (order = 0; (1UL << order) < goal; order++) - ; + /* Then compute the page order for said goal */ + order = get_order(goal); + + /* Now compute the required page order for the maximum sized table we + * want to create + */ + max_entry_order = get_order(MAX_SCTP_PORT_HASH_ENTRIES * + sizeof(struct sctp_bind_hashbucket)); + + /* Limit the page order by that maximum hash table size */ + order = min(order, max_entry_order); /* Allocate and initialize the endpoint hash table. */ sctp_ep_hashsize = 64; @@ -1430,20 +1444,35 @@ static __init int sctp_init(void) INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain); } - /* Allocate and initialize the SCTP port hash table. */ + /* Allocate and initialize the SCTP port hash table. + * Note that order is initalized to start at the max sized + * table we want to support. If we can't get that many pages + * reduce the order and try again + */ do { - sctp_port_hashsize = (1UL << order) * PAGE_SIZE / - sizeof(struct sctp_bind_hashbucket); - if ((sctp_port_hashsize > (64 * 1024)) && order > 0) - continue; sctp_port_hashtable = (struct sctp_bind_hashbucket *) __get_free_pages(GFP_KERNEL | __GFP_NOWARN, order); } while (!sctp_port_hashtable && --order > 0); + if (!sctp_port_hashtable) { pr_err("Failed bind hash alloc\n"); status = -ENOMEM; goto err_bhash_alloc; } + + /* Now compute the number of entries that will fit in the + * port hash space we allocated + */ + num_entries = (1UL << order) * PAGE_SIZE / + sizeof(struct sctp_bind_hashbucket); + + /* And finish by rounding it down to the nearest power of two + * this wastes some memory of course, but its needed because + * the hash function operates based on the assumption that + * that the number of entries is a power of two + */ + sctp_port_hashsize = rounddown_pow_of_two(num_entries); + for (i = 0; i < sctp_port_hashsize; i++) { spin_lock_init(&sctp_port_hashtable[i].lock); INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain); @@ -1452,7 +1481,8 @@ static __init int sctp_init(void) if (sctp_transport_hashtable_init()) goto err_thash_alloc; - pr_info("Hash tables configured (bind %d)\n", sctp_port_hashsize); + pr_info("Hash tables configured (bind %d/%d)\n", sctp_port_hashsize, + num_entries); sctp_sysctl_register(); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 5ca2ebfe0be8..e878da0949db 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5538,6 +5538,7 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, struct sctp_hmac_algo_param *hmacs; __u16 data_len = 0; u32 num_idents; + int i; if (!ep->auth_enable) return -EACCES; @@ -5555,8 +5556,12 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, return -EFAULT; if (put_user(num_idents, &p->shmac_num_idents)) return -EFAULT; - if (copy_to_user(p->shmac_idents, hmacs->hmac_ids, data_len)) - return -EFAULT; + for (i = 0; i < num_idents; i++) { + __u16 hmacid = ntohs(hmacs->hmac_ids[i]); + + if (copy_to_user(&p->shmac_idents[i], &hmacid, sizeof(__u16))) + return -EFAULT; + } return 0; } diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 2b32fd602669..273bc3a35425 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1225,7 +1225,7 @@ int qword_get(char **bpp, char *dest, int bufsize) if (bp[0] == '\\' && bp[1] == 'x') { /* HEX STRING */ bp += 2; - while (len < bufsize) { + while (len < bufsize - 1) { int h, l; h = hex_to_bin(bp[0]); diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index c14f3a4bff68..b289e106540b 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -80,13 +80,13 @@ fmr_op_init(struct rpcrdma_xprt *r_xprt) if (!r) goto out; - r->r.fmr.physaddrs = kmalloc(RPCRDMA_MAX_FMR_SGES * - sizeof(u64), GFP_KERNEL); - if (!r->r.fmr.physaddrs) + r->fmr.physaddrs = kmalloc(RPCRDMA_MAX_FMR_SGES * + sizeof(u64), GFP_KERNEL); + if (!r->fmr.physaddrs) goto out_free; - r->r.fmr.fmr = ib_alloc_fmr(pd, mr_access_flags, &fmr_attr); - if (IS_ERR(r->r.fmr.fmr)) + r->fmr.fmr = ib_alloc_fmr(pd, mr_access_flags, &fmr_attr); + if (IS_ERR(r->fmr.fmr)) goto out_fmr_err; list_add(&r->mw_list, &buf->rb_mws); @@ -95,9 +95,9 @@ fmr_op_init(struct rpcrdma_xprt *r_xprt) return 0; out_fmr_err: - rc = PTR_ERR(r->r.fmr.fmr); + rc = PTR_ERR(r->fmr.fmr); dprintk("RPC: %s: ib_alloc_fmr status %i\n", __func__, rc); - kfree(r->r.fmr.physaddrs); + kfree(r->fmr.physaddrs); out_free: kfree(r); out: @@ -109,7 +109,7 @@ __fmr_unmap(struct rpcrdma_mw *r) { LIST_HEAD(l); - list_add(&r->r.fmr.fmr->list, &l); + list_add(&r->fmr.fmr->list, &l); return ib_unmap_fmr(&l); } @@ -148,7 +148,7 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, nsegs = RPCRDMA_MAX_FMR_SGES; for (i = 0; i < nsegs;) { rpcrdma_map_one(device, seg, direction); - mw->r.fmr.physaddrs[i] = seg->mr_dma; + mw->fmr.physaddrs[i] = seg->mr_dma; len += seg->mr_len; ++seg; ++i; @@ -158,13 +158,13 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, break; } - rc = ib_map_phys_fmr(mw->r.fmr.fmr, mw->r.fmr.physaddrs, + rc = ib_map_phys_fmr(mw->fmr.fmr, mw->fmr.physaddrs, i, seg1->mr_dma); if (rc) goto out_maperr; seg1->rl_mw = mw; - seg1->mr_rkey = mw->r.fmr.fmr->rkey; + seg1->mr_rkey = mw->fmr.fmr->rkey; seg1->mr_base = seg1->mr_dma + pageoff; seg1->mr_nsegs = i; seg1->mr_len = len; @@ -219,7 +219,7 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) seg = &req->rl_segments[i]; mw = seg->rl_mw; - list_add(&mw->r.fmr.fmr->list, &unmap_list); + list_add(&mw->fmr.fmr->list, &unmap_list); i += seg->mr_nsegs; } @@ -281,9 +281,9 @@ fmr_op_destroy(struct rpcrdma_buffer *buf) while (!list_empty(&buf->rb_all)) { r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all); list_del(&r->mw_all); - kfree(r->r.fmr.physaddrs); + kfree(r->fmr.physaddrs); - rc = ib_dealloc_fmr(r->r.fmr.fmr); + rc = ib_dealloc_fmr(r->fmr.fmr); if (rc) dprintk("RPC: %s: ib_dealloc_fmr failed %i\n", __func__, rc); diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index e16567389e28..c250924a9fd3 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -109,20 +109,20 @@ static void __frwr_recovery_worker(struct work_struct *work) { struct rpcrdma_mw *r = container_of(work, struct rpcrdma_mw, - r.frmr.fr_work); - struct rpcrdma_xprt *r_xprt = r->r.frmr.fr_xprt; + frmr.fr_work); + struct rpcrdma_xprt *r_xprt = r->frmr.fr_xprt; unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth; struct ib_pd *pd = r_xprt->rx_ia.ri_pd; - if (ib_dereg_mr(r->r.frmr.fr_mr)) + if (ib_dereg_mr(r->frmr.fr_mr)) goto out_fail; - r->r.frmr.fr_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, depth); - if (IS_ERR(r->r.frmr.fr_mr)) + r->frmr.fr_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, depth); + if (IS_ERR(r->frmr.fr_mr)) goto out_fail; dprintk("RPC: %s: recovered FRMR %p\n", __func__, r); - r->r.frmr.fr_state = FRMR_IS_INVALID; + r->frmr.fr_state = FRMR_IS_INVALID; rpcrdma_put_mw(r_xprt, r); return; @@ -137,15 +137,15 @@ out_fail: static void __frwr_queue_recovery(struct rpcrdma_mw *r) { - INIT_WORK(&r->r.frmr.fr_work, __frwr_recovery_worker); - queue_work(frwr_recovery_wq, &r->r.frmr.fr_work); + INIT_WORK(&r->frmr.fr_work, __frwr_recovery_worker); + queue_work(frwr_recovery_wq, &r->frmr.fr_work); } static int __frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device, unsigned int depth) { - struct rpcrdma_frmr *f = &r->r.frmr; + struct rpcrdma_frmr *f = &r->frmr; int rc; f->fr_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, depth); @@ -158,6 +158,8 @@ __frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device, sg_init_table(f->sg, depth); + init_completion(&f->fr_linv_done); + return 0; out_mr_err: @@ -179,11 +181,11 @@ __frwr_release(struct rpcrdma_mw *r) { int rc; - rc = ib_dereg_mr(r->r.frmr.fr_mr); + rc = ib_dereg_mr(r->frmr.fr_mr); if (rc) dprintk("RPC: %s: ib_dereg_mr status %i\n", __func__, rc); - kfree(r->r.frmr.sg); + kfree(r->frmr.sg); } static int @@ -244,39 +246,76 @@ frwr_op_maxpages(struct rpcrdma_xprt *r_xprt) rpcrdma_max_segments(r_xprt) * ia->ri_max_frmr_depth); } -/* If FAST_REG or LOCAL_INV failed, indicate the frmr needs - * to be reset. +static void +__frwr_sendcompletion_flush(struct ib_wc *wc, struct rpcrdma_frmr *frmr, + const char *wr) +{ + frmr->fr_state = FRMR_IS_STALE; + if (wc->status != IB_WC_WR_FLUSH_ERR) + pr_err("rpcrdma: %s: %s (%u/0x%x)\n", + wr, ib_wc_status_msg(wc->status), + wc->status, wc->vendor_err); +} + +/** + * frwr_wc_fastreg - Invoked by RDMA provider for each polled FastReg WC + * @cq: completion queue (ignored) + * @wc: completed WR * - * WARNING: Only wr_id and status are reliable at this point */ static void -__frwr_sendcompletion_flush(struct ib_wc *wc, struct rpcrdma_mw *r) +frwr_wc_fastreg(struct ib_cq *cq, struct ib_wc *wc) { - if (likely(wc->status == IB_WC_SUCCESS)) - return; - - /* WARNING: Only wr_id and status are reliable at this point */ - r = (struct rpcrdma_mw *)(unsigned long)wc->wr_id; - if (wc->status == IB_WC_WR_FLUSH_ERR) - dprintk("RPC: %s: frmr %p flushed\n", __func__, r); - else - pr_warn("RPC: %s: frmr %p error, status %s (%d)\n", - __func__, r, ib_wc_status_msg(wc->status), wc->status); + struct rpcrdma_frmr *frmr; + struct ib_cqe *cqe; - r->r.frmr.fr_state = FRMR_IS_STALE; + /* WARNING: Only wr_cqe and status are reliable at this point */ + if (wc->status != IB_WC_SUCCESS) { + cqe = wc->wr_cqe; + frmr = container_of(cqe, struct rpcrdma_frmr, fr_cqe); + __frwr_sendcompletion_flush(wc, frmr, "fastreg"); + } } +/** + * frwr_wc_localinv - Invoked by RDMA provider for each polled LocalInv WC + * @cq: completion queue (ignored) + * @wc: completed WR + * + */ static void -frwr_sendcompletion(struct ib_wc *wc) +frwr_wc_localinv(struct ib_cq *cq, struct ib_wc *wc) { - struct rpcrdma_mw *r = (struct rpcrdma_mw *)(unsigned long)wc->wr_id; - struct rpcrdma_frmr *f = &r->r.frmr; + struct rpcrdma_frmr *frmr; + struct ib_cqe *cqe; - if (unlikely(wc->status != IB_WC_SUCCESS)) - __frwr_sendcompletion_flush(wc, r); + /* WARNING: Only wr_cqe and status are reliable at this point */ + if (wc->status != IB_WC_SUCCESS) { + cqe = wc->wr_cqe; + frmr = container_of(cqe, struct rpcrdma_frmr, fr_cqe); + __frwr_sendcompletion_flush(wc, frmr, "localinv"); + } +} - if (f->fr_waiter) - complete(&f->fr_linv_done); +/** + * frwr_wc_localinv - Invoked by RDMA provider for each polled LocalInv WC + * @cq: completion queue (ignored) + * @wc: completed WR + * + * Awaken anyone waiting for an MR to finish being fenced. + */ +static void +frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc) +{ + struct rpcrdma_frmr *frmr; + struct ib_cqe *cqe; + + /* WARNING: Only wr_cqe and status are reliable at this point */ + cqe = wc->wr_cqe; + frmr = container_of(cqe, struct rpcrdma_frmr, fr_cqe); + if (wc->status != IB_WC_SUCCESS) + __frwr_sendcompletion_flush(wc, frmr, "localinv"); + complete_all(&frmr->fr_linv_done); } static int @@ -313,8 +352,7 @@ frwr_op_init(struct rpcrdma_xprt *r_xprt) list_add(&r->mw_list, &buf->rb_mws); list_add(&r->mw_all, &buf->rb_all); - r->mw_sendcompletion = frwr_sendcompletion; - r->r.frmr.fr_xprt = r_xprt; + r->frmr.fr_xprt = r_xprt; } return 0; @@ -347,10 +385,9 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, mw = rpcrdma_get_mw(r_xprt); if (!mw) return -ENOMEM; - } while (mw->r.frmr.fr_state != FRMR_IS_INVALID); - frmr = &mw->r.frmr; + } while (mw->frmr.fr_state != FRMR_IS_INVALID); + frmr = &mw->frmr; frmr->fr_state = FRMR_IS_VALID; - frmr->fr_waiter = false; mr = frmr->fr_mr; reg_wr = &frmr->fr_regwr; @@ -400,7 +437,8 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, reg_wr->wr.next = NULL; reg_wr->wr.opcode = IB_WR_REG_MR; - reg_wr->wr.wr_id = (uintptr_t)mw; + frmr->fr_cqe.done = frwr_wc_fastreg; + reg_wr->wr.wr_cqe = &frmr->fr_cqe; reg_wr->wr.num_sge = 0; reg_wr->wr.send_flags = 0; reg_wr->mr = mr; @@ -434,15 +472,15 @@ static struct ib_send_wr * __frwr_prepare_linv_wr(struct rpcrdma_mr_seg *seg) { struct rpcrdma_mw *mw = seg->rl_mw; - struct rpcrdma_frmr *f = &mw->r.frmr; + struct rpcrdma_frmr *f = &mw->frmr; struct ib_send_wr *invalidate_wr; - f->fr_waiter = false; f->fr_state = FRMR_IS_INVALID; invalidate_wr = &f->fr_invwr; memset(invalidate_wr, 0, sizeof(*invalidate_wr)); - invalidate_wr->wr_id = (unsigned long)(void *)mw; + f->fr_cqe.done = frwr_wc_localinv; + invalidate_wr->wr_cqe = &f->fr_cqe; invalidate_wr->opcode = IB_WR_LOCAL_INV; invalidate_wr->ex.invalidate_rkey = f->fr_mr->rkey; @@ -455,7 +493,7 @@ __frwr_dma_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, { struct ib_device *device = r_xprt->rx_ia.ri_device; struct rpcrdma_mw *mw = seg->rl_mw; - struct rpcrdma_frmr *f = &mw->r.frmr; + struct rpcrdma_frmr *f = &mw->frmr; seg->rl_mw = NULL; @@ -504,15 +542,15 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) i += seg->mr_nsegs; } - f = &seg->rl_mw->r.frmr; + f = &seg->rl_mw->frmr; /* Strong send queue ordering guarantees that when the * last WR in the chain completes, all WRs in the chain * are complete. */ f->fr_invwr.send_flags = IB_SEND_SIGNALED; - f->fr_waiter = true; - init_completion(&f->fr_linv_done); + f->fr_cqe.done = frwr_wc_localinv_wake; + reinit_completion(&f->fr_linv_done); INIT_CQCOUNT(&r_xprt->rx_ep); /* Transport disconnect drains the receive CQ before it @@ -520,14 +558,18 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) * unless ri_id->qp is a valid pointer. */ rc = ib_post_send(ia->ri_id->qp, invalidate_wrs, &bad_wr); - if (rc) + if (rc) { pr_warn("%s: ib_post_send failed %i\n", __func__, rc); + rdma_disconnect(ia->ri_id); + goto unmap; + } wait_for_completion(&f->fr_linv_done); /* ORDER: Now DMA unmap all of the req's MRs, and return * them to the free MW list. */ +unmap: for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { seg = &req->rl_segments[i]; @@ -549,7 +591,7 @@ frwr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg) struct rpcrdma_mr_seg *seg1 = seg; struct rpcrdma_ia *ia = &r_xprt->rx_ia; struct rpcrdma_mw *mw = seg1->rl_mw; - struct rpcrdma_frmr *frmr = &mw->r.frmr; + struct rpcrdma_frmr *frmr = &mw->frmr; struct ib_send_wr *invalidate_wr, *bad_wr; int rc, nsegs = seg->mr_nsegs; @@ -557,10 +599,11 @@ frwr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg) seg1->rl_mw = NULL; frmr->fr_state = FRMR_IS_INVALID; - invalidate_wr = &mw->r.frmr.fr_invwr; + invalidate_wr = &mw->frmr.fr_invwr; memset(invalidate_wr, 0, sizeof(*invalidate_wr)); - invalidate_wr->wr_id = (uintptr_t)mw; + frmr->fr_cqe.done = frwr_wc_localinv; + invalidate_wr->wr_cqe = &frmr->fr_cqe; invalidate_wr->opcode = IB_WR_LOCAL_INV; invalidate_wr->ex.invalidate_rkey = frmr->fr_mr->rkey; DECR_CQCOUNT(&r_xprt->rx_ep); diff --git a/net/sunrpc/xprtrdma/physical_ops.c b/net/sunrpc/xprtrdma/physical_ops.c index dbb302ecf590..481b9b6f4a15 100644 --- a/net/sunrpc/xprtrdma/physical_ops.c +++ b/net/sunrpc/xprtrdma/physical_ops.c @@ -68,7 +68,6 @@ physical_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, rpcrdma_map_one(ia->ri_device, seg, rpcrdma_data_dir(writing)); seg->mr_rkey = ia->ri_dma_mr->rkey; seg->mr_base = seg->mr_dma; - seg->mr_nsegs = 1; return 1; } diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 0f28f2d743ed..888823bb6dae 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -132,6 +132,33 @@ rpcrdma_tail_pullup(struct xdr_buf *buf) return tlen; } +/* Split "vec" on page boundaries into segments. FMR registers pages, + * not a byte range. Other modes coalesce these segments into a single + * MR when they can. + */ +static int +rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg, + int n, int nsegs) +{ + size_t page_offset; + u32 remaining; + char *base; + + base = vec->iov_base; + page_offset = offset_in_page(base); + remaining = vec->iov_len; + while (remaining && n < nsegs) { + seg[n].mr_page = NULL; + seg[n].mr_offset = base; + seg[n].mr_len = min_t(u32, PAGE_SIZE - page_offset, remaining); + remaining -= seg[n].mr_len; + base += seg[n].mr_len; + ++n; + page_offset = 0; + } + return n; +} + /* * Chunk assembly from upper layer xdr_buf. * @@ -150,11 +177,10 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos, int page_base; struct page **ppages; - if (pos == 0 && xdrbuf->head[0].iov_len) { - seg[n].mr_page = NULL; - seg[n].mr_offset = xdrbuf->head[0].iov_base; - seg[n].mr_len = xdrbuf->head[0].iov_len; - ++n; + if (pos == 0) { + n = rpcrdma_convert_kvec(&xdrbuf->head[0], seg, n, nsegs); + if (n == nsegs) + return -EIO; } len = xdrbuf->page_len; @@ -192,13 +218,9 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos, * xdr pad bytes, saving the server an RDMA operation. */ if (xdrbuf->tail[0].iov_len < 4 && xprt_rdma_pad_optimize) return n; + n = rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, n, nsegs); if (n == nsegs) - /* Tail remains, but we're out of segments */ return -EIO; - seg[n].mr_page = NULL; - seg[n].mr_offset = xdrbuf->tail[0].iov_base; - seg[n].mr_len = xdrbuf->tail[0].iov_len; - ++n; } return n; @@ -773,20 +795,17 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep) struct rpcrdma_xprt *r_xprt = rep->rr_rxprt; struct rpc_xprt *xprt = &r_xprt->rx_xprt; __be32 *iptr; - int rdmalen, status; + int rdmalen, status, rmerr; unsigned long cwnd; - u32 credits; dprintk("RPC: %s: incoming rep %p\n", __func__, rep); if (rep->rr_len == RPCRDMA_BAD_LEN) goto out_badstatus; - if (rep->rr_len < RPCRDMA_HDRLEN_MIN) + if (rep->rr_len < RPCRDMA_HDRLEN_ERR) goto out_shortreply; headerp = rdmab_to_msg(rep->rr_rdmabuf); - if (headerp->rm_vers != rpcrdma_version) - goto out_badversion; #if defined(CONFIG_SUNRPC_BACKCHANNEL) if (rpcrdma_is_bcall(headerp)) goto out_bcall; @@ -809,15 +828,16 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep) */ list_del_init(&rqst->rq_list); spin_unlock_bh(&xprt->transport_lock); - dprintk("RPC: %s: reply 0x%p completes request 0x%p\n" - " RPC request 0x%p xid 0x%08x\n", - __func__, rep, req, rqst, - be32_to_cpu(headerp->rm_xid)); + dprintk("RPC: %s: reply %p completes request %p (xid 0x%08x)\n", + __func__, rep, req, be32_to_cpu(headerp->rm_xid)); /* from here on, the reply is no longer an orphan */ req->rl_reply = rep; xprt->reestablish_timeout = 0; + if (headerp->rm_vers != rpcrdma_version) + goto out_badversion; + /* check for expected message types */ /* The order of some of these tests is important. */ switch (headerp->rm_type) { @@ -878,6 +898,9 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep) status = rdmalen; break; + case rdma_error: + goto out_rdmaerr; + badheader: default: dprintk("%s: invalid rpcrdma reply header (type %d):" @@ -893,6 +916,7 @@ badheader: break; } +out: /* Invalidate and flush the data payloads before waking the * waiting application. This guarantees the memory region is * properly fenced from the server before the application @@ -903,15 +927,9 @@ badheader: if (req->rl_nchunks) r_xprt->rx_ia.ri_ops->ro_unmap_sync(r_xprt, req); - credits = be32_to_cpu(headerp->rm_credit); - if (credits == 0) - credits = 1; /* don't deadlock */ - else if (credits > r_xprt->rx_buf.rb_max_requests) - credits = r_xprt->rx_buf.rb_max_requests; - spin_lock_bh(&xprt->transport_lock); cwnd = xprt->cwnd; - xprt->cwnd = credits << RPC_CWNDSHIFT; + xprt->cwnd = atomic_read(&r_xprt->rx_buf.rb_credits) << RPC_CWNDSHIFT; if (xprt->cwnd > cwnd) xprt_release_rqst_cong(rqst->rq_task); @@ -935,13 +953,43 @@ out_bcall: return; #endif -out_shortreply: - dprintk("RPC: %s: short/invalid reply\n", __func__); - goto repost; - +/* If the incoming reply terminated a pending RPC, the next + * RPC call will post a replacement receive buffer as it is + * being marshaled. + */ out_badversion: dprintk("RPC: %s: invalid version %d\n", __func__, be32_to_cpu(headerp->rm_vers)); + status = -EIO; + r_xprt->rx_stats.bad_reply_count++; + goto out; + +out_rdmaerr: + rmerr = be32_to_cpu(headerp->rm_body.rm_error.rm_err); + switch (rmerr) { + case ERR_VERS: + pr_err("%s: server reports header version error (%u-%u)\n", + __func__, + be32_to_cpu(headerp->rm_body.rm_error.rm_vers_low), + be32_to_cpu(headerp->rm_body.rm_error.rm_vers_high)); + break; + case ERR_CHUNK: + pr_err("%s: server reports header decoding error\n", + __func__); + break; + default: + pr_err("%s: server reports unknown error %d\n", + __func__, rmerr); + } + status = -EREMOTEIO; + r_xprt->rx_stats.bad_reply_count++; + goto out; + +/* If no pending RPC transaction was matched, post a replacement + * receive buffer before returning. + */ +out_shortreply: + dprintk("RPC: %s: short/invalid reply\n", __func__); goto repost; out_nomatch: diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 878f1bfb1db9..f5ed9f982cd7 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -112,89 +112,65 @@ rpcrdma_qp_async_error_upcall(struct ib_event *event, void *context) } } +/** + * rpcrdma_wc_send - Invoked by RDMA provider for each polled Send WC + * @cq: completion queue (ignored) + * @wc: completed WR + * + */ static void -rpcrdma_cq_async_error_upcall(struct ib_event *event, void *context) +rpcrdma_wc_send(struct ib_cq *cq, struct ib_wc *wc) { - struct rpcrdma_ep *ep = context; - - pr_err("RPC: %s: %s on device %s ep %p\n", - __func__, ib_event_msg(event->event), - event->device->name, context); - if (ep->rep_connected == 1) { - ep->rep_connected = -EIO; - rpcrdma_conn_func(ep); - wake_up_all(&ep->rep_connect_wait); - } + /* WARNING: Only wr_cqe and status are reliable at this point */ + if (wc->status != IB_WC_SUCCESS && wc->status != IB_WC_WR_FLUSH_ERR) + pr_err("rpcrdma: Send: %s (%u/0x%x)\n", + ib_wc_status_msg(wc->status), + wc->status, wc->vendor_err); } static void -rpcrdma_sendcq_process_wc(struct ib_wc *wc) +rpcrdma_receive_worker(struct work_struct *work) { - /* WARNING: Only wr_id and status are reliable at this point */ - if (wc->wr_id == RPCRDMA_IGNORE_COMPLETION) { - if (wc->status != IB_WC_SUCCESS && - wc->status != IB_WC_WR_FLUSH_ERR) - pr_err("RPC: %s: SEND: %s\n", - __func__, ib_wc_status_msg(wc->status)); - } else { - struct rpcrdma_mw *r; + struct rpcrdma_rep *rep = + container_of(work, struct rpcrdma_rep, rr_work); - r = (struct rpcrdma_mw *)(unsigned long)wc->wr_id; - r->mw_sendcompletion(wc); - } + rpcrdma_reply_handler(rep); } -/* The common case is a single send completion is waiting. By - * passing two WC entries to ib_poll_cq, a return code of 1 - * means there is exactly one WC waiting and no more. We don't - * have to invoke ib_poll_cq again to know that the CQ has been - * properly drained. +/* Perform basic sanity checking to avoid using garbage + * to update the credit grant value. */ static void -rpcrdma_sendcq_poll(struct ib_cq *cq) +rpcrdma_update_granted_credits(struct rpcrdma_rep *rep) { - struct ib_wc *pos, wcs[2]; - int count, rc; + struct rpcrdma_msg *rmsgp = rdmab_to_msg(rep->rr_rdmabuf); + struct rpcrdma_buffer *buffer = &rep->rr_rxprt->rx_buf; + u32 credits; - do { - pos = wcs; + if (rep->rr_len < RPCRDMA_HDRLEN_ERR) + return; - rc = ib_poll_cq(cq, ARRAY_SIZE(wcs), pos); - if (rc < 0) - break; + credits = be32_to_cpu(rmsgp->rm_credit); + if (credits == 0) + credits = 1; /* don't deadlock */ + else if (credits > buffer->rb_max_requests) + credits = buffer->rb_max_requests; - count = rc; - while (count-- > 0) - rpcrdma_sendcq_process_wc(pos++); - } while (rc == ARRAY_SIZE(wcs)); - return; + atomic_set(&buffer->rb_credits, credits); } -/* Handle provider send completion upcalls. +/** + * rpcrdma_receive_wc - Invoked by RDMA provider for each polled Receive WC + * @cq: completion queue (ignored) + * @wc: completed WR + * */ static void -rpcrdma_sendcq_upcall(struct ib_cq *cq, void *cq_context) +rpcrdma_receive_wc(struct ib_cq *cq, struct ib_wc *wc) { - do { - rpcrdma_sendcq_poll(cq); - } while (ib_req_notify_cq(cq, IB_CQ_NEXT_COMP | - IB_CQ_REPORT_MISSED_EVENTS) > 0); -} - -static void -rpcrdma_receive_worker(struct work_struct *work) -{ - struct rpcrdma_rep *rep = - container_of(work, struct rpcrdma_rep, rr_work); - - rpcrdma_reply_handler(rep); -} - -static void -rpcrdma_recvcq_process_wc(struct ib_wc *wc) -{ - struct rpcrdma_rep *rep = - (struct rpcrdma_rep *)(unsigned long)wc->wr_id; + struct ib_cqe *cqe = wc->wr_cqe; + struct rpcrdma_rep *rep = container_of(cqe, struct rpcrdma_rep, + rr_cqe); /* WARNING: Only wr_id and status are reliable at this point */ if (wc->status != IB_WC_SUCCESS) @@ -211,7 +187,8 @@ rpcrdma_recvcq_process_wc(struct ib_wc *wc) ib_dma_sync_single_for_cpu(rep->rr_device, rdmab_addr(rep->rr_rdmabuf), rep->rr_len, DMA_FROM_DEVICE); - prefetch(rdmab_to_msg(rep->rr_rdmabuf)); + + rpcrdma_update_granted_credits(rep); out_schedule: queue_work(rpcrdma_receive_wq, &rep->rr_work); @@ -219,57 +196,20 @@ out_schedule: out_fail: if (wc->status != IB_WC_WR_FLUSH_ERR) - pr_err("RPC: %s: rep %p: %s\n", - __func__, rep, ib_wc_status_msg(wc->status)); + pr_err("rpcrdma: Recv: %s (%u/0x%x)\n", + ib_wc_status_msg(wc->status), + wc->status, wc->vendor_err); rep->rr_len = RPCRDMA_BAD_LEN; goto out_schedule; } -/* The wc array is on stack: automatic memory is always CPU-local. - * - * struct ib_wc is 64 bytes, making the poll array potentially - * large. But this is at the bottom of the call chain. Further - * substantial work is done in another thread. - */ -static void -rpcrdma_recvcq_poll(struct ib_cq *cq) -{ - struct ib_wc *pos, wcs[4]; - int count, rc; - - do { - pos = wcs; - - rc = ib_poll_cq(cq, ARRAY_SIZE(wcs), pos); - if (rc < 0) - break; - - count = rc; - while (count-- > 0) - rpcrdma_recvcq_process_wc(pos++); - } while (rc == ARRAY_SIZE(wcs)); -} - -/* Handle provider receive completion upcalls. - */ -static void -rpcrdma_recvcq_upcall(struct ib_cq *cq, void *cq_context) -{ - do { - rpcrdma_recvcq_poll(cq); - } while (ib_req_notify_cq(cq, IB_CQ_NEXT_COMP | - IB_CQ_REPORT_MISSED_EVENTS) > 0); -} - static void rpcrdma_flush_cqs(struct rpcrdma_ep *ep) { struct ib_wc wc; while (ib_poll_cq(ep->rep_attr.recv_cq, 1, &wc) > 0) - rpcrdma_recvcq_process_wc(&wc); - while (ib_poll_cq(ep->rep_attr.send_cq, 1, &wc) > 0) - rpcrdma_sendcq_process_wc(&wc); + rpcrdma_receive_wc(NULL, &wc); } static int @@ -330,6 +270,7 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) connected: dprintk("RPC: %s: %sconnected\n", __func__, connstate > 0 ? "" : "dis"); + atomic_set(&xprt->rx_buf.rb_credits, 1); ep->rep_connected = connstate; rpcrdma_conn_func(ep); wake_up_all(&ep->rep_connect_wait); @@ -560,9 +501,8 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, struct rpcrdma_create_data_internal *cdata) { struct ib_cq *sendcq, *recvcq; - struct ib_cq_init_attr cq_attr = {}; unsigned int max_qp_wr; - int rc, err; + int rc; if (ia->ri_device->attrs.max_sge < RPCRDMA_MAX_IOVS) { dprintk("RPC: %s: insufficient sge's available\n", @@ -614,9 +554,9 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, init_waitqueue_head(&ep->rep_connect_wait); INIT_DELAYED_WORK(&ep->rep_connect_worker, rpcrdma_connect_worker); - cq_attr.cqe = ep->rep_attr.cap.max_send_wr + 1; - sendcq = ib_create_cq(ia->ri_device, rpcrdma_sendcq_upcall, - rpcrdma_cq_async_error_upcall, NULL, &cq_attr); + sendcq = ib_alloc_cq(ia->ri_device, NULL, + ep->rep_attr.cap.max_send_wr + 1, + 0, IB_POLL_SOFTIRQ); if (IS_ERR(sendcq)) { rc = PTR_ERR(sendcq); dprintk("RPC: %s: failed to create send CQ: %i\n", @@ -624,16 +564,9 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, goto out1; } - rc = ib_req_notify_cq(sendcq, IB_CQ_NEXT_COMP); - if (rc) { - dprintk("RPC: %s: ib_req_notify_cq failed: %i\n", - __func__, rc); - goto out2; - } - - cq_attr.cqe = ep->rep_attr.cap.max_recv_wr + 1; - recvcq = ib_create_cq(ia->ri_device, rpcrdma_recvcq_upcall, - rpcrdma_cq_async_error_upcall, NULL, &cq_attr); + recvcq = ib_alloc_cq(ia->ri_device, NULL, + ep->rep_attr.cap.max_recv_wr + 1, + 0, IB_POLL_SOFTIRQ); if (IS_ERR(recvcq)) { rc = PTR_ERR(recvcq); dprintk("RPC: %s: failed to create recv CQ: %i\n", @@ -641,14 +574,6 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, goto out2; } - rc = ib_req_notify_cq(recvcq, IB_CQ_NEXT_COMP); - if (rc) { - dprintk("RPC: %s: ib_req_notify_cq failed: %i\n", - __func__, rc); - ib_destroy_cq(recvcq); - goto out2; - } - ep->rep_attr.send_cq = sendcq; ep->rep_attr.recv_cq = recvcq; @@ -673,10 +598,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, return 0; out2: - err = ib_destroy_cq(sendcq); - if (err) - dprintk("RPC: %s: ib_destroy_cq returned %i\n", - __func__, err); + ib_free_cq(sendcq); out1: if (ia->ri_dma_mr) ib_dereg_mr(ia->ri_dma_mr); @@ -711,15 +633,8 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) ia->ri_id->qp = NULL; } - rc = ib_destroy_cq(ep->rep_attr.recv_cq); - if (rc) - dprintk("RPC: %s: ib_destroy_cq returned %i\n", - __func__, rc); - - rc = ib_destroy_cq(ep->rep_attr.send_cq); - if (rc) - dprintk("RPC: %s: ib_destroy_cq returned %i\n", - __func__, rc); + ib_free_cq(ep->rep_attr.recv_cq); + ib_free_cq(ep->rep_attr.send_cq); if (ia->ri_dma_mr) { rc = ib_dereg_mr(ia->ri_dma_mr); @@ -898,6 +813,7 @@ rpcrdma_create_req(struct rpcrdma_xprt *r_xprt) spin_lock(&buffer->rb_reqslock); list_add(&req->rl_all, &buffer->rb_allreqs); spin_unlock(&buffer->rb_reqslock); + req->rl_cqe.done = rpcrdma_wc_send; req->rl_buffer = &r_xprt->rx_buf; return req; } @@ -923,6 +839,7 @@ rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt) } rep->rr_device = ia->ri_device; + rep->rr_cqe.done = rpcrdma_receive_wc; rep->rr_rxprt = r_xprt; INIT_WORK(&rep->rr_work, rpcrdma_receive_worker); return rep; @@ -943,6 +860,7 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) buf->rb_max_requests = r_xprt->rx_data.max_requests; buf->rb_bc_srv_max_requests = 0; spin_lock_init(&buf->rb_lock); + atomic_set(&buf->rb_credits, 1); rc = ia->ri_ops->ro_init(r_xprt); if (rc) @@ -1259,7 +1177,7 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, } send_wr.next = NULL; - send_wr.wr_id = RPCRDMA_IGNORE_COMPLETION; + send_wr.wr_cqe = &req->rl_cqe; send_wr.sg_list = iov; send_wr.num_sge = req->rl_niovs; send_wr.opcode = IB_WR_SEND; @@ -1297,7 +1215,7 @@ rpcrdma_ep_post_recv(struct rpcrdma_ia *ia, int rc; recv_wr.next = NULL; - recv_wr.wr_id = (u64) (unsigned long) rep; + recv_wr.wr_cqe = &rep->rr_cqe; recv_wr.sg_list = &rep->rr_rdmabuf->rg_iov; recv_wr.num_sge = 1; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 38fe11b09875..2ebc743cb96f 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -95,10 +95,6 @@ struct rpcrdma_ep { #define INIT_CQCOUNT(ep) atomic_set(&(ep)->rep_cqcount, (ep)->rep_cqinit) #define DECR_CQCOUNT(ep) atomic_sub_return(1, &(ep)->rep_cqcount) -/* Force completion handler to ignore the signal - */ -#define RPCRDMA_IGNORE_COMPLETION (0ULL) - /* Pre-allocate extra Work Requests for handling backward receives * and sends. This is a fixed value because the Work Queues are * allocated when the forward channel is set up. @@ -171,6 +167,7 @@ rdmab_to_msg(struct rpcrdma_regbuf *rb) struct rpcrdma_buffer; struct rpcrdma_rep { + struct ib_cqe rr_cqe; unsigned int rr_len; struct ib_device *rr_device; struct rpcrdma_xprt *rr_rxprt; @@ -204,11 +201,11 @@ struct rpcrdma_frmr { struct scatterlist *sg; int sg_nents; struct ib_mr *fr_mr; + struct ib_cqe fr_cqe; enum rpcrdma_frmr_state fr_state; + struct completion fr_linv_done; struct work_struct fr_work; struct rpcrdma_xprt *fr_xprt; - bool fr_waiter; - struct completion fr_linv_done;; union { struct ib_reg_wr fr_regwr; struct ib_send_wr fr_invwr; @@ -224,8 +221,7 @@ struct rpcrdma_mw { union { struct rpcrdma_fmr fmr; struct rpcrdma_frmr frmr; - } r; - void (*mw_sendcompletion)(struct ib_wc *); + }; struct list_head mw_list; struct list_head mw_all; }; @@ -281,6 +277,7 @@ struct rpcrdma_req { struct rpcrdma_regbuf *rl_sendbuf; struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS]; + struct ib_cqe rl_cqe; struct list_head rl_all; bool rl_backchannel; }; @@ -311,6 +308,7 @@ struct rpcrdma_buffer { struct list_head rb_send_bufs; struct list_head rb_recv_bufs; u32 rb_max_requests; + atomic_t rb_credits; /* most recent credit grant */ u32 rb_bc_srv_max_requests; spinlock_t rb_reqslock; /* protect rb_allreqs */ diff --git a/net/tipc/link.c b/net/tipc/link.c index 0c2944fb9ae0..347cdc99ed09 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1973,8 +1973,10 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_LINK_GET); - if (!hdr) + if (!hdr) { + tipc_bcast_unlock(net); return -EMSGSIZE; + } attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK); if (!attrs) diff --git a/net/tipc/node.c b/net/tipc/node.c index fa97d9649a28..9d7a16fc5ca4 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -346,12 +346,6 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities) skb_queue_head_init(&n->bc_entry.inputq2); for (i = 0; i < MAX_BEARERS; i++) spin_lock_init(&n->links[i].lock); - hlist_add_head_rcu(&n->hash, &tn->node_htable[tipc_hashfn(addr)]); - list_for_each_entry_rcu(temp_node, &tn->node_list, list) { - if (n->addr < temp_node->addr) - break; - } - list_add_tail_rcu(&n->list, &temp_node->list); n->state = SELF_DOWN_PEER_LEAVING; n->signature = INVALID_NODE_SIG; n->active_links[0] = INVALID_BEARER_ID; @@ -372,6 +366,12 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities) tipc_node_get(n); setup_timer(&n->timer, tipc_node_timeout, (unsigned long)n); n->keepalive_intv = U32_MAX; + hlist_add_head_rcu(&n->hash, &tn->node_htable[tipc_hashfn(addr)]); + list_for_each_entry_rcu(temp_node, &tn->node_list, list) { + if (n->addr < temp_node->addr) + break; + } + list_add_tail_rcu(&n->list, &temp_node->list); exit: spin_unlock_bh(&tn->node_list_lock); return n; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 49d5093eb055..f75f847e688d 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1496,7 +1496,7 @@ static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) UNIXCB(skb).fp = NULL; for (i = scm->fp->count-1; i >= 0; i--) - unix_notinflight(scm->fp->fp[i]); + unix_notinflight(scm->fp->user, scm->fp->fp[i]); } static void unix_destruct_scm(struct sk_buff *skb) @@ -1561,7 +1561,7 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) return -ENOMEM; for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->fp[i]); + unix_inflight(scm->fp->user, scm->fp->fp[i]); return max_level; } @@ -1781,7 +1781,12 @@ restart_locked: goto out_unlock; } - if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { + /* other == sk && unix_peer(other) != sk if + * - unix_peer(sk) == NULL, destination address bound to sk + * - unix_peer(sk) == sk by time of get but disconnected before lock + */ + if (other != sk && + unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { if (timeo) { timeo = unix_wait_for_peer(other, timeo); @@ -2277,13 +2282,15 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) size_t size = state->size; unsigned int last_len; - err = -EINVAL; - if (sk->sk_state != TCP_ESTABLISHED) + if (unlikely(sk->sk_state != TCP_ESTABLISHED)) { + err = -EINVAL; goto out; + } - err = -EOPNOTSUPP; - if (flags & MSG_OOB) + if (unlikely(flags & MSG_OOB)) { + err = -EOPNOTSUPP; goto out; + } target = sock_rcvlowat(sk, flags & MSG_WAITALL, size); timeo = sock_rcvtimeo(sk, noblock); @@ -2305,6 +2312,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) bool drop_skb; struct sk_buff *skb, *last; +redo: unix_state_lock(sk); if (sock_flag(sk, SOCK_DEAD)) { err = -ECONNRESET; @@ -2329,9 +2337,11 @@ again: goto unlock; unix_state_unlock(sk); - err = -EAGAIN; - if (!timeo) + if (!timeo) { + err = -EAGAIN; break; + } + mutex_unlock(&u->readlock); timeo = unix_stream_data_wait(sk, timeo, last, @@ -2344,7 +2354,7 @@ again: } mutex_lock(&u->readlock); - continue; + goto redo; unlock: unix_state_unlock(sk); break; diff --git a/net/unix/diag.c b/net/unix/diag.c index c512f64d5287..4d9679701a6d 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -220,7 +220,7 @@ done: return skb->len; } -static struct sock *unix_lookup_by_ino(int ino) +static struct sock *unix_lookup_by_ino(unsigned int ino) { int i; struct sock *sk; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 8fcdc2283af5..6a0d48525fcf 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -116,7 +116,7 @@ struct sock *unix_get_socket(struct file *filp) * descriptor if it is for an AF_UNIX socket. */ -void unix_inflight(struct file *fp) +void unix_inflight(struct user_struct *user, struct file *fp) { struct sock *s = unix_get_socket(fp); @@ -133,11 +133,11 @@ void unix_inflight(struct file *fp) } unix_tot_inflight++; } - fp->f_cred->user->unix_inflight++; + user->unix_inflight++; spin_unlock(&unix_gc_lock); } -void unix_notinflight(struct file *fp) +void unix_notinflight(struct user_struct *user, struct file *fp) { struct sock *s = unix_get_socket(fp); @@ -152,7 +152,7 @@ void unix_notinflight(struct file *fp) list_del_init(&u->link); unix_tot_inflight--; } - fp->f_cred->user->unix_inflight--; + user->unix_inflight--; spin_unlock(&unix_gc_lock); } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 7fd1220fbfa0..bbe65dcb9738 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1557,8 +1557,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, if (err < 0) goto out; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - while (total_written < len) { ssize_t written; @@ -1578,7 +1576,9 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, goto out_wait; release_sock(sk); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); timeout = schedule_timeout(timeout); + finish_wait(sk_sleep(sk), &wait); lock_sock(sk); if (signal_pending(current)) { err = sock_intr_errno(timeout); @@ -1588,8 +1588,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, goto out_wait; } - prepare_to_wait(sk_sleep(sk), &wait, - TASK_INTERRUPTIBLE); } /* These checks occur both as part of and after the loop @@ -1635,7 +1633,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, out_wait: if (total_written > 0) err = total_written; - finish_wait(sk_sleep(sk), &wait); out: release_sock(sk); return err; @@ -1716,7 +1713,6 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (err < 0) goto out; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); while (1) { s64 ready = vsock_stream_has_data(vsk); @@ -1727,7 +1723,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, */ err = -ENOMEM; - goto out_wait; + goto out; } else if (ready > 0) { ssize_t read; @@ -1750,7 +1746,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, vsk, target, read, !(flags & MSG_PEEK), &recv_data); if (err < 0) - goto out_wait; + goto out; if (read >= target || flags & MSG_PEEK) break; @@ -1773,7 +1769,9 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, break; release_sock(sk); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); timeout = schedule_timeout(timeout); + finish_wait(sk_sleep(sk), &wait); lock_sock(sk); if (signal_pending(current)) { @@ -1783,9 +1781,6 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, err = -EAGAIN; break; } - - prepare_to_wait(sk_sleep(sk), &wait, - TASK_INTERRUPTIBLE); } } @@ -1816,8 +1811,6 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, err = copied; } -out_wait: - finish_wait(sk_sleep(sk), &wait); out: release_sock(sk); return err; |