summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-02-22 21:18:07 +0100
committerLinus Torvalds <torvalds@linux-foundation.org>2016-02-22 21:18:07 +0100
commitdea08e604408d0303e2332896c5fdd8c1f7d79a2 (patch)
treedbe8aa3fbfba7dc0e9878de152e8efe537b2b4b5 /net
parentMerge tag 'hwmon-for-linus-v4.5-rc6' of git://git.kernel.org/pub/scm/linux/ke... (diff)
parentMerge tag 'linux-can-fixes-for-4.5-20160221' of git://git.kernel.org/pub/scm/... (diff)
downloadlinux-dea08e604408d0303e2332896c5fdd8c1f7d79a2.tar.xz
linux-dea08e604408d0303e2332896c5fdd8c1f7d79a2.zip
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller: "Looks like a lot, but mostly driver fixes scattered all over as usual. Of note: 1) Add conditional sched in nf conntrack in cleanup to avoid NMI watchdogs. From Florian Westphal. 2) Fix deadlock in nfnetlink cttimeout, also from Floarian. 3) Fix handling of slaves in bonding ARP monitor validation, from Jay Vosburgh. 4) Callers of ip_cmsg_send() are responsible for freeing IP options, some were not doing so. Fix from Eric Dumazet. 5) Fix per-cpu bugs in mvneta driver, from Gregory CLEMENT. 6) Fix vlan handling in mv88e6xxx DSA driver, from Vivien Didelot. 7) bcm7xxx PHY driver bug fixes from Florian Fainelli. 8) Avoid unaligned accesses to protocol headers wrt. GRE, from Alexander Duyck. 9) SKB leaks and other problems in arc_emac driver, from Alexander Kochetkov. 10) tcp_v4_inbound_md5_hash() releases listener socket instead of request socket on error path, oops. Fix from Eric Dumazet. 11) Missing socket release in pppoe_rcv_core() that seems to have existed basically forever. From Guillaume Nault. 12) Missing slave_dev unregister in dsa_slave_create() error path, from Florian Fainelli. 13) crypto_alloc_hash() never returns NULL, fix return value check in __tcp_alloc_md5sig_pool. From Insu Yun. 14) Properly expire exception route entries in ipv4, from Xin Long. 15) Fix races in tcp/dccp listener socket dismantle, from Eric Dumazet. 16) Don't set IFF_TX_SKB_SHARING in vxlan, geneve, or GRE, it's not legal. These drivers modify the SKB on transmit. From Jiri Benc. 17) Fix regression in the initialziation of netdev->tx_queue_len. From Phil Sutter. 18) Missing unlock in tipc_nl_add_bc_link() error path, from Insu Yun. 19) SCTP port hash sizing does not properly ensure that table is a power of two in size. From Neil Horman. 20) Fix initializing of software copy of MAC address in fmvj18x_cs driver, from Ken Kawasaki" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (129 commits) bnx2x: Fix 84833 phy command handler bnx2x: Fix led setting for 84858 phy. bnx2x: Correct 84858 PHY fw version bnx2x: Fix 84833 RX CRC bnx2x: Fix link-forcing for KR2 net: ethernet: davicom: fix devicetree irq resource fmvj18x_cs: fix incorrect indexing of dev->dev_addr[] when copying the MAC address Driver: Vmxnet3: Update Rx ring 2 max size net: netcp: rework the code for get/set sw_data in dma desc soc: ti: knav_dma: rename pad in struct knav_dma_desc to sw_data net: ti: netcp: restore get/set_pad_info() functionality MAINTAINERS: Drop myself as xen netback maintainer sctp: Fix port hash table size computation can: ems_usb: Fix possible tx overflow Bluetooth: hci_core: Avoid mixing up req_complete and req_complete_skb net: bcmgenet: Fix internal PHY link state af_unix: Don't use continue to re-execute unix_stream_read_generic loop unix_diag: fix incorrect sign extension in unix_lookup_by_ino bnxt_en: Failure to update PHY is not fatal condition. bnxt_en: Remove unnecessary call to update PHY settings. ...
Diffstat (limited to 'net')
-rw-r--r--net/appletalk/ddp.c2
-rw-r--r--net/batman-adv/gateway_client.c7
-rw-r--r--net/batman-adv/hard-interface.c25
-rw-r--r--net/batman-adv/translation-table.c6
-rw-r--r--net/bluetooth/hci_core.c6
-rw-r--r--net/bridge/br_mdb.c4
-rw-r--r--net/caif/cfrfml.c2
-rw-r--r--net/core/dev.c8
-rw-r--r--net/core/flow_dissector.c7
-rw-r--r--net/dccp/ipv4.c14
-rw-r--r--net/dccp/ipv6.c14
-rw-r--r--net/dsa/slave.c2
-rw-r--r--net/ipv4/devinet.c2
-rw-r--r--net/ipv4/inet_connection_sock.c14
-rw-r--r--net/ipv4/ip_gre.c5
-rw-r--r--net/ipv4/ip_sockglue.c2
-rw-r--r--net/ipv4/ping.c4
-rw-r--r--net/ipv4/raw.c4
-rw-r--r--net/ipv4/route.c77
-rw-r--r--net/ipv4/tcp.c2
-rw-r--r--net/ipv4/tcp_input.c5
-rw-r--r--net/ipv4/tcp_ipv4.c20
-rw-r--r--net/ipv4/udp.c4
-rw-r--r--net/ipv6/addrconf.c2
-rw-r--r--net/ipv6/ip6_gre.c1
-rw-r--r--net/ipv6/netfilter/nf_nat_masquerade_ipv6.c74
-rw-r--r--net/ipv6/tcp_ipv6.c14
-rw-r--r--net/l2tp/l2tp_netlink.c18
-rw-r--r--net/netfilter/Kconfig2
-rw-r--r--net/netfilter/nf_conntrack_core.c5
-rw-r--r--net/netfilter/nfnetlink.c16
-rw-r--r--net/netfilter/nfnetlink_cttimeout.c2
-rw-r--r--net/netfilter/nft_counter.c4
-rw-r--r--net/netfilter/xt_TEE.c4
-rw-r--r--net/openvswitch/vport-vxlan.c2
-rw-r--r--net/sched/sch_api.c1
-rw-r--r--net/sctp/protocol.c46
-rw-r--r--net/tipc/link.c4
-rw-r--r--net/tipc/node.c12
-rw-r--r--net/unix/af_unix.c26
-rw-r--r--net/unix/diag.c2
-rw-r--r--net/vmw_vsock/af_vsock.c19
42 files changed, 357 insertions, 133 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/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 eab81bc80e5c..12e700332010 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -399,6 +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/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 56fdf4e0dce4..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);
}
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/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 0c36ef4a3f86..483ffdf5aa4d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -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 7f6ff037adaf..487ac67059e2 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1597,28 +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 9efd9ffdc34c..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;
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 1a5a70fb8551..5c8c84273028 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1387,7 +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);
@@ -1395,24 +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 de9cb19efb6a..5eb7694348b5 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -90,7 +90,7 @@ 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,
};
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/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 29be035f9c65..f75f847e688d 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -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/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;