summaryrefslogtreecommitdiffstats
path: root/kernel/net
diff options
context:
space:
mode:
authorJosé Pekkarinen <jose.pekkarinen@nokia.com>2015-10-19 08:35:30 +0300
committerJosé Pekkarinen <jose.pekkarinen@nokia.com>2015-10-19 08:35:30 +0300
commitec0a2ed6d8a5e555edef907895c041e285fdb495 (patch)
treea4c8d982f8ac820b1b60818df22ad3ccac2036d5 /kernel/net
parent342fa5dfa053559f47caad657132522496dcf1b3 (diff)
These changes are a raw update to a vanilla kernel 4.1.10, with the
recently announced rt patch patch-4.1.10-rt10.patch. No further changes needed. Change-Id: I9a0cf084498133b10771e744b6da4b29dff706ba Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>
Diffstat (limited to 'kernel/net')
-rw-r--r--kernel/net/bridge/br_forward.c1
-rw-r--r--kernel/net/bridge/br_mdb.c3
-rw-r--r--kernel/net/bridge/br_multicast.c4
-rw-r--r--kernel/net/bridge/br_netlink.c14
-rw-r--r--kernel/net/ceph/ceph_common.c7
-rw-r--r--kernel/net/core/datagram.c57
-rw-r--r--kernel/net/core/dev.c45
-rw-r--r--kernel/net/core/fib_rules.c14
-rw-r--r--kernel/net/core/pktgen.c4
-rw-r--r--kernel/net/core/request_sock.c8
-rw-r--r--kernel/net/core/rtnetlink.c187
-rw-r--r--kernel/net/core/skbuff.c2
-rw-r--r--kernel/net/core/sock_diag.c3
-rw-r--r--kernel/net/dsa/slave.c3
-rw-r--r--kernel/net/ipv4/datagram.c16
-rw-r--r--kernel/net/ipv4/fib_trie.c6
-rw-r--r--kernel/net/ipv4/inet_connection_sock.c2
-rw-r--r--kernel/net/ipv4/ip_fragment.c7
-rw-r--r--kernel/net/ipv4/ip_tunnel.c8
-rw-r--r--kernel/net/ipv4/tcp_ipv4.c2
-rw-r--r--kernel/net/ipv4/tcp_output.c1
-rw-r--r--kernel/net/ipv4/udp.c13
-rw-r--r--kernel/net/ipv6/datagram.c20
-rw-r--r--kernel/net/ipv6/exthdrs_offload.c2
-rw-r--r--kernel/net/ipv6/ip6_gre.c1
-rw-r--r--kernel/net/ipv6/ip6_input.c6
-rw-r--r--kernel/net/ipv6/ip6_offload.c2
-rw-r--r--kernel/net/ipv6/ip6mr.c2
-rw-r--r--kernel/net/ipv6/route.c201
-rw-r--r--kernel/net/ipv6/tcp_ipv6.c2
-rw-r--r--kernel/net/mac80211/tx.c3
-rw-r--r--kernel/net/netlink/af_netlink.c146
-rw-r--r--kernel/net/netlink/af_netlink.h10
-rw-r--r--kernel/net/nfc/nci/hci.c2
-rw-r--r--kernel/net/openvswitch/datapath.c4
-rw-r--r--kernel/net/openvswitch/flow_table.c23
-rw-r--r--kernel/net/openvswitch/flow_table.h2
-rw-r--r--kernel/net/packet/af_packet.c11
-rw-r--r--kernel/net/rds/info.c2
-rw-r--r--kernel/net/sched/act_api.c11
-rw-r--r--kernel/net/sched/act_bpf.c50
-rw-r--r--kernel/net/sched/cls_bpf.c2
-rw-r--r--kernel/net/sched/cls_flow.c5
-rw-r--r--kernel/net/sched/cls_fw.c30
-rw-r--r--kernel/net/sched/cls_u32.c13
-rw-r--r--kernel/net/sched/sch_fq_codel.c2
-rw-r--r--kernel/net/sctp/protocol.c64
-rw-r--r--kernel/net/sunrpc/xprt.c6
-rw-r--r--kernel/net/sunrpc/xprtsock.c21
-rw-r--r--kernel/net/tipc/socket.c1
50 files changed, 715 insertions, 336 deletions
diff --git a/kernel/net/bridge/br_forward.c b/kernel/net/bridge/br_forward.c
index e97572b5d..0ff6e1bbc 100644
--- a/kernel/net/bridge/br_forward.c
+++ b/kernel/net/bridge/br_forward.c
@@ -42,6 +42,7 @@ int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb)
} else {
skb_push(skb, ETH_HLEN);
br_drop_fake_rtable(skb);
+ skb_sender_cpu_clear(skb);
dev_queue_xmit(skb);
}
diff --git a/kernel/net/bridge/br_mdb.c b/kernel/net/bridge/br_mdb.c
index e29ad70b3..d1f910c0d 100644
--- a/kernel/net/bridge/br_mdb.c
+++ b/kernel/net/bridge/br_mdb.c
@@ -348,7 +348,6 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
return -ENOMEM;
rcu_assign_pointer(*pp, p);
- br_mdb_notify(br->dev, port, group, RTM_NEWMDB);
return 0;
}
@@ -371,6 +370,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br,
if (!p || p->br != br || p->state == BR_STATE_DISABLED)
return -EINVAL;
+ memset(&ip, 0, sizeof(ip));
ip.proto = entry->addr.proto;
if (ip.proto == htons(ETH_P_IP))
ip.u.ip4 = entry->addr.u.ip4;
@@ -417,6 +417,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
if (!netif_running(br->dev) || br->multicast_disabled)
return -EINVAL;
+ memset(&ip, 0, sizeof(ip));
ip.proto = entry->addr.proto;
if (ip.proto == htons(ETH_P_IP)) {
if (timer_pending(&br->ip4_other_query.timer))
diff --git a/kernel/net/bridge/br_multicast.c b/kernel/net/bridge/br_multicast.c
index ff667e18b..9ba383f5b 100644
--- a/kernel/net/bridge/br_multicast.c
+++ b/kernel/net/bridge/br_multicast.c
@@ -980,7 +980,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
ih = igmpv3_report_hdr(skb);
num = ntohs(ih->ngrec);
- len = sizeof(*ih);
+ len = skb_transport_offset(skb) + sizeof(*ih);
for (i = 0; i < num; i++) {
len += sizeof(*grec);
@@ -1035,7 +1035,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
icmp6h = icmp6_hdr(skb);
num = ntohs(icmp6h->icmp6_dataun.un_data16[1]);
- len = sizeof(*icmp6h);
+ len = skb_transport_offset(skb) + sizeof(*icmp6h);
for (i = 0; i < num; i++) {
__be16 *nsrcs, _nsrcs;
diff --git a/kernel/net/bridge/br_netlink.c b/kernel/net/bridge/br_netlink.c
index 4b5c23699..a7559ef31 100644
--- a/kernel/net/bridge/br_netlink.c
+++ b/kernel/net/bridge/br_netlink.c
@@ -112,6 +112,8 @@ static inline size_t br_port_info_size(void)
+ nla_total_size(1) /* IFLA_BRPORT_FAST_LEAVE */
+ nla_total_size(1) /* IFLA_BRPORT_LEARNING */
+ nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */
+ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */
+ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */
+ 0;
}
@@ -504,6 +506,8 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = {
[IFLA_BRPORT_FAST_LEAVE]= { .type = NLA_U8 },
[IFLA_BRPORT_LEARNING] = { .type = NLA_U8 },
[IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 },
+ [IFLA_BRPORT_PROXYARP] = { .type = NLA_U8 },
+ [IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 },
};
/* Change the state of the port and notify spanning tree */
@@ -711,9 +715,17 @@ static int br_port_slave_changelink(struct net_device *brdev,
struct nlattr *tb[],
struct nlattr *data[])
{
+ struct net_bridge *br = netdev_priv(brdev);
+ int ret;
+
if (!data)
return 0;
- return br_setport(br_port_get_rtnl(dev), data);
+
+ spin_lock_bh(&br->lock);
+ ret = br_setport(br_port_get_rtnl(dev), data);
+ spin_unlock_bh(&br->lock);
+
+ return ret;
}
static int br_port_fill_slave_info(struct sk_buff *skb,
diff --git a/kernel/net/ceph/ceph_common.c b/kernel/net/ceph/ceph_common.c
index 79e8f71ae..3f76eb84b 100644
--- a/kernel/net/ceph/ceph_common.c
+++ b/kernel/net/ceph/ceph_common.c
@@ -495,8 +495,11 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client)
struct ceph_options *opt = client->options;
size_t pos = m->count;
- if (opt->name)
- seq_printf(m, "name=%s,", opt->name);
+ if (opt->name) {
+ seq_puts(m, "name=");
+ seq_escape(m, opt->name, ", \t\n\\");
+ seq_putc(m, ',');
+ }
if (opt->key)
seq_puts(m, "secret=<hidden>,");
diff --git a/kernel/net/core/datagram.c b/kernel/net/core/datagram.c
index b80fb91bb..617088aee 100644
--- a/kernel/net/core/datagram.c
+++ b/kernel/net/core/datagram.c
@@ -131,6 +131,35 @@ out_noerr:
goto out;
}
+static struct sk_buff *skb_set_peeked(struct sk_buff *skb)
+{
+ struct sk_buff *nskb;
+
+ if (skb->peeked)
+ return skb;
+
+ /* We have to unshare an skb before modifying it. */
+ if (!skb_shared(skb))
+ goto done;
+
+ nskb = skb_clone(skb, GFP_ATOMIC);
+ if (!nskb)
+ return ERR_PTR(-ENOMEM);
+
+ skb->prev->next = nskb;
+ skb->next->prev = nskb;
+ nskb->prev = skb->prev;
+ nskb->next = skb->next;
+
+ consume_skb(skb);
+ skb = nskb;
+
+done:
+ skb->peeked = 1;
+
+ return skb;
+}
+
/**
* __skb_recv_datagram - Receive a datagram skbuff
* @sk: socket
@@ -165,7 +194,9 @@ out_noerr:
struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
int *peeked, int *off, int *err)
{
+ struct sk_buff_head *queue = &sk->sk_receive_queue;
struct sk_buff *skb, *last;
+ unsigned long cpu_flags;
long timeo;
/*
* Caller is allowed not to check sk->sk_err before skb_recv_datagram()
@@ -184,8 +215,6 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
* Look at current nfs client by the way...
* However, this function was correct in any case. 8)
*/
- unsigned long cpu_flags;
- struct sk_buff_head *queue = &sk->sk_receive_queue;
int _off = *off;
last = (struct sk_buff *)queue;
@@ -199,7 +228,12 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
_off -= skb->len;
continue;
}
- skb->peeked = 1;
+
+ skb = skb_set_peeked(skb);
+ error = PTR_ERR(skb);
+ if (IS_ERR(skb))
+ goto unlock_err;
+
atomic_inc(&skb->users);
} else
__skb_unlink(skb, queue);
@@ -223,6 +257,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
return NULL;
+unlock_err:
+ spin_unlock_irqrestore(&queue->lock, cpu_flags);
no_packet:
*err = error;
return NULL;
@@ -622,7 +658,8 @@ __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
!skb->csum_complete_sw)
netdev_rx_csum_fault(skb->dev);
}
- skb->csum_valid = !sum;
+ if (!skb_shared(skb))
+ skb->csum_valid = !sum;
return sum;
}
EXPORT_SYMBOL(__skb_checksum_complete_head);
@@ -642,11 +679,13 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb)
netdev_rx_csum_fault(skb->dev);
}
- /* Save full packet checksum */
- skb->csum = csum;
- skb->ip_summed = CHECKSUM_COMPLETE;
- skb->csum_complete_sw = 1;
- skb->csum_valid = !sum;
+ if (!skb_shared(skb)) {
+ /* Save full packet checksum */
+ skb->csum = csum;
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ skb->csum_complete_sw = 1;
+ skb->csum_valid = !sum;
+ }
return sum;
}
diff --git a/kernel/net/core/dev.c b/kernel/net/core/dev.c
index 349de9dba..f8c23dee5 100644
--- a/kernel/net/core/dev.c
+++ b/kernel/net/core/dev.c
@@ -673,10 +673,6 @@ int dev_get_iflink(const struct net_device *dev)
if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink)
return dev->netdev_ops->ndo_get_iflink(dev);
- /* If dev->rtnl_link_ops is set, it's a virtual interface. */
- if (dev->rtnl_link_ops)
- return 0;
-
return dev->ifindex;
}
EXPORT_SYMBOL(dev_get_iflink);
@@ -3349,6 +3345,8 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
local_irq_save(flags);
rps_lock(sd);
+ if (!netif_running(skb->dev))
+ goto drop;
qlen = skb_queue_len(&sd->input_pkt_queue);
if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
if (qlen) {
@@ -3370,6 +3368,7 @@ enqueue:
goto enqueue;
}
+drop:
sd->dropped++;
rps_unlock(sd);
@@ -3704,8 +3703,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
pt_prev = NULL;
- rcu_read_lock();
-
another_round:
skb->skb_iif = skb->dev->ifindex;
@@ -3715,7 +3712,7 @@ another_round:
skb->protocol == cpu_to_be16(ETH_P_8021AD)) {
skb = skb_vlan_untag(skb);
if (unlikely(!skb))
- goto unlock;
+ goto out;
}
#ifdef CONFIG_NET_CLS_ACT
@@ -3745,7 +3742,7 @@ skip_taps:
if (static_key_false(&ingress_needed)) {
skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
if (!skb)
- goto unlock;
+ goto out;
}
skb->tc_verd = 0;
@@ -3762,7 +3759,7 @@ ncls:
if (vlan_do_receive(&skb))
goto another_round;
else if (unlikely(!skb))
- goto unlock;
+ goto out;
}
rx_handler = rcu_dereference(skb->dev->rx_handler);
@@ -3774,7 +3771,7 @@ ncls:
switch (rx_handler(&skb)) {
case RX_HANDLER_CONSUMED:
ret = NET_RX_SUCCESS;
- goto unlock;
+ goto out;
case RX_HANDLER_ANOTHER:
goto another_round;
case RX_HANDLER_EXACT:
@@ -3828,8 +3825,7 @@ drop:
ret = NET_RX_DROP;
}
-unlock:
- rcu_read_unlock();
+out:
return ret;
}
@@ -3860,29 +3856,30 @@ static int __netif_receive_skb(struct sk_buff *skb)
static int netif_receive_skb_internal(struct sk_buff *skb)
{
+ int ret;
+
net_timestamp_check(netdev_tstamp_prequeue, skb);
if (skb_defer_rx_timestamp(skb))
return NET_RX_SUCCESS;
+ rcu_read_lock();
+
#ifdef CONFIG_RPS
if (static_key_false(&rps_needed)) {
struct rps_dev_flow voidflow, *rflow = &voidflow;
- int cpu, ret;
-
- rcu_read_lock();
-
- cpu = get_rps_cpu(skb->dev, skb, &rflow);
+ int cpu = get_rps_cpu(skb->dev, skb, &rflow);
if (cpu >= 0) {
ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
rcu_read_unlock();
return ret;
}
- rcu_read_unlock();
}
#endif
- return __netif_receive_skb(skb);
+ ret = __netif_receive_skb(skb);
+ rcu_read_unlock();
+ return ret;
}
/**
@@ -4432,8 +4429,10 @@ static int process_backlog(struct napi_struct *napi, int quota)
struct sk_buff *skb;
while ((skb = __skb_dequeue(&sd->process_queue))) {
+ rcu_read_lock();
local_irq_enable();
__netif_receive_skb(skb);
+ rcu_read_unlock();
local_irq_disable();
input_queue_head_incr(sd);
if (++work >= quota) {
@@ -6070,6 +6069,7 @@ static void rollback_registered_many(struct list_head *head)
unlist_netdevice(dev);
dev->reg_state = NETREG_UNREGISTERING;
+ on_each_cpu(flush_backlog, dev, 1);
}
synchronize_net();
@@ -6340,7 +6340,8 @@ static int netif_alloc_netdev_queues(struct net_device *dev)
struct netdev_queue *tx;
size_t sz = count * sizeof(*tx);
- BUG_ON(count < 1 || count > 0xffff);
+ if (count < 1 || count > 0xffff)
+ return -EINVAL;
tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
if (!tx) {
@@ -6693,8 +6694,6 @@ void netdev_run_todo(void)
dev->reg_state = NETREG_UNREGISTERED;
- on_each_cpu(flush_backlog, dev, 1);
-
netdev_wait_allrefs(dev);
/* paranoia */
@@ -7218,7 +7217,7 @@ static int dev_cpu_callback(struct notifier_block *nfb,
netif_rx_ni(skb);
input_queue_head_incr(oldsd);
}
- while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) {
+ while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
netif_rx_ni(skb);
input_queue_head_incr(oldsd);
}
diff --git a/kernel/net/core/fib_rules.c b/kernel/net/core/fib_rules.c
index 9a12668f7..0ad144fb0 100644
--- a/kernel/net/core/fib_rules.c
+++ b/kernel/net/core/fib_rules.c
@@ -615,15 +615,17 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb,
{
int idx = 0;
struct fib_rule *rule;
+ int err = 0;
rcu_read_lock();
list_for_each_entry_rcu(rule, &ops->rules_list, list) {
if (idx < cb->args[1])
goto skip;
- if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, RTM_NEWRULE,
- NLM_F_MULTI, ops) < 0)
+ err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, RTM_NEWRULE,
+ NLM_F_MULTI, ops);
+ if (err)
break;
skip:
idx++;
@@ -632,7 +634,7 @@ skip:
cb->args[1] = idx;
rules_ops_put(ops);
- return skb->len;
+ return err;
}
static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
@@ -648,7 +650,9 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
if (ops == NULL)
return -EAFNOSUPPORT;
- return dump_rules(skb, cb, ops);
+ dump_rules(skb, cb, ops);
+
+ return skb->len;
}
rcu_read_lock();
diff --git a/kernel/net/core/pktgen.c b/kernel/net/core/pktgen.c
index 508155b28..043ea1867 100644
--- a/kernel/net/core/pktgen.c
+++ b/kernel/net/core/pktgen.c
@@ -3490,8 +3490,10 @@ static int pktgen_thread_worker(void *arg)
pktgen_rem_thread(t);
/* Wait for kthread_stop */
- while (!kthread_should_stop()) {
+ for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
+ if (kthread_should_stop())
+ break;
schedule();
}
__set_current_state(TASK_RUNNING);
diff --git a/kernel/net/core/request_sock.c b/kernel/net/core/request_sock.c
index 87b22c0bc..b42f0e26f 100644
--- a/kernel/net/core/request_sock.c
+++ b/kernel/net/core/request_sock.c
@@ -103,10 +103,16 @@ void reqsk_queue_destroy(struct request_sock_queue *queue)
spin_lock_bh(&queue->syn_wait_lock);
while ((req = lopt->syn_table[i]) != NULL) {
lopt->syn_table[i] = req->dl_next;
+ /* Because of following del_timer_sync(),
+ * we must release the spinlock here
+ * or risk a dead lock.
+ */
+ spin_unlock_bh(&queue->syn_wait_lock);
atomic_inc(&lopt->qlen_dec);
- if (del_timer(&req->rsk_timer))
+ if (del_timer_sync(&req->rsk_timer))
reqsk_put(req);
reqsk_put(req);
+ spin_lock_bh(&queue->syn_wait_lock);
}
spin_unlock_bh(&queue->syn_wait_lock);
}
diff --git a/kernel/net/core/rtnetlink.c b/kernel/net/core/rtnetlink.c
index 8de368240..fe95cb704 100644
--- a/kernel/net/core/rtnetlink.c
+++ b/kernel/net/core/rtnetlink.c
@@ -1287,10 +1287,6 @@ static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
[IFLA_INFO_SLAVE_DATA] = { .type = NLA_NESTED },
};
-static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = {
- [IFLA_VF_INFO] = { .type = NLA_NESTED },
-};
-
static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
[IFLA_VF_MAC] = { .len = sizeof(struct ifla_vf_mac) },
[IFLA_VF_VLAN] = { .len = sizeof(struct ifla_vf_vlan) },
@@ -1437,96 +1433,98 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[])
return 0;
}
-static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
+static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
{
- int rem, err = -EINVAL;
- struct nlattr *vf;
const struct net_device_ops *ops = dev->netdev_ops;
+ int err = -EINVAL;
- nla_for_each_nested(vf, attr, rem) {
- switch (nla_type(vf)) {
- case IFLA_VF_MAC: {
- struct ifla_vf_mac *ivm;
- ivm = nla_data(vf);
- err = -EOPNOTSUPP;
- if (ops->ndo_set_vf_mac)
- err = ops->ndo_set_vf_mac(dev, ivm->vf,
- ivm->mac);
- break;
- }
- case IFLA_VF_VLAN: {
- struct ifla_vf_vlan *ivv;
- ivv = nla_data(vf);
- err = -EOPNOTSUPP;
- if (ops->ndo_set_vf_vlan)
- err = ops->ndo_set_vf_vlan(dev, ivv->vf,
- ivv->vlan,
- ivv->qos);
- break;
- }
- case IFLA_VF_TX_RATE: {
- struct ifla_vf_tx_rate *ivt;
- struct ifla_vf_info ivf;
- ivt = nla_data(vf);
- err = -EOPNOTSUPP;
- if (ops->ndo_get_vf_config)
- err = ops->ndo_get_vf_config(dev, ivt->vf,
- &ivf);
- if (err)
- break;
- err = -EOPNOTSUPP;
- if (ops->ndo_set_vf_rate)
- err = ops->ndo_set_vf_rate(dev, ivt->vf,
- ivf.min_tx_rate,
- ivt->rate);
- break;
- }
- case IFLA_VF_RATE: {
- struct ifla_vf_rate *ivt;
- ivt = nla_data(vf);
- err = -EOPNOTSUPP;
- if (ops->ndo_set_vf_rate)
- err = ops->ndo_set_vf_rate(dev, ivt->vf,
- ivt->min_tx_rate,
- ivt->max_tx_rate);
- break;
- }
- case IFLA_VF_SPOOFCHK: {
- struct ifla_vf_spoofchk *ivs;
- ivs = nla_data(vf);
- err = -EOPNOTSUPP;
- if (ops->ndo_set_vf_spoofchk)
- err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
- ivs->setting);
- break;
- }
- case IFLA_VF_LINK_STATE: {
- struct ifla_vf_link_state *ivl;
- ivl = nla_data(vf);
- err = -EOPNOTSUPP;
- if (ops->ndo_set_vf_link_state)
- err = ops->ndo_set_vf_link_state(dev, ivl->vf,
- ivl->link_state);
- break;
- }
- case IFLA_VF_RSS_QUERY_EN: {
- struct ifla_vf_rss_query_en *ivrssq_en;
+ if (tb[IFLA_VF_MAC]) {
+ struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]);
- ivrssq_en = nla_data(vf);
- err = -EOPNOTSUPP;
- if (ops->ndo_set_vf_rss_query_en)
- err = ops->ndo_set_vf_rss_query_en(dev,
- ivrssq_en->vf,
- ivrssq_en->setting);
- break;
- }
- default:
- err = -EINVAL;
- break;
- }
- if (err)
- break;
+ err = -EOPNOTSUPP;
+ if (ops->ndo_set_vf_mac)
+ err = ops->ndo_set_vf_mac(dev, ivm->vf,
+ ivm->mac);
+ if (err < 0)
+ return err;
+ }
+
+ if (tb[IFLA_VF_VLAN]) {
+ struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]);
+
+ err = -EOPNOTSUPP;
+ if (ops->ndo_set_vf_vlan)
+ err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan,
+ ivv->qos);
+ if (err < 0)
+ return err;
+ }
+
+ if (tb[IFLA_VF_TX_RATE]) {
+ struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]);
+ struct ifla_vf_info ivf;
+
+ err = -EOPNOTSUPP;
+ if (ops->ndo_get_vf_config)
+ err = ops->ndo_get_vf_config(dev, ivt->vf, &ivf);
+ if (err < 0)
+ return err;
+
+ err = -EOPNOTSUPP;
+ if (ops->ndo_set_vf_rate)
+ err = ops->ndo_set_vf_rate(dev, ivt->vf,
+ ivf.min_tx_rate,
+ ivt->rate);
+ if (err < 0)
+ return err;
+ }
+
+ if (tb[IFLA_VF_RATE]) {
+ struct ifla_vf_rate *ivt = nla_data(tb[IFLA_VF_RATE]);
+
+ err = -EOPNOTSUPP;
+ if (ops->ndo_set_vf_rate)
+ err = ops->ndo_set_vf_rate(dev, ivt->vf,
+ ivt->min_tx_rate,
+ ivt->max_tx_rate);
+ if (err < 0)
+ return err;
}
+
+ if (tb[IFLA_VF_SPOOFCHK]) {
+ struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]);
+
+ err = -EOPNOTSUPP;
+ if (ops->ndo_set_vf_spoofchk)
+ err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
+ ivs->setting);
+ if (err < 0)
+ return err;
+ }
+
+ if (tb[IFLA_VF_LINK_STATE]) {
+ struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]);
+
+ err = -EOPNOTSUPP;
+ if (ops->ndo_set_vf_link_state)
+ err = ops->ndo_set_vf_link_state(dev, ivl->vf,
+ ivl->link_state);
+ if (err < 0)
+ return err;
+ }
+
+ if (tb[IFLA_VF_RSS_QUERY_EN]) {
+ struct ifla_vf_rss_query_en *ivrssq_en;
+
+ err = -EOPNOTSUPP;
+ ivrssq_en = nla_data(tb[IFLA_VF_RSS_QUERY_EN]);
+ if (ops->ndo_set_vf_rss_query_en)
+ err = ops->ndo_set_vf_rss_query_en(dev, ivrssq_en->vf,
+ ivrssq_en->setting);
+ if (err < 0)
+ return err;
+ }
+
return err;
}
@@ -1722,14 +1720,21 @@ static int do_setlink(const struct sk_buff *skb,
}
if (tb[IFLA_VFINFO_LIST]) {
+ struct nlattr *vfinfo[IFLA_VF_MAX + 1];
struct nlattr *attr;
int rem;
+
nla_for_each_nested(attr, tb[IFLA_VFINFO_LIST], rem) {
- if (nla_type(attr) != IFLA_VF_INFO) {
+ if (nla_type(attr) != IFLA_VF_INFO ||
+ nla_len(attr) < NLA_HDRLEN) {
err = -EINVAL;
goto errout;
}
- err = do_setvfinfo(dev, attr);
+ err = nla_parse_nested(vfinfo, IFLA_VF_MAX, attr,
+ ifla_vf_policy);
+ if (err < 0)
+ goto errout;
+ err = do_setvfinfo(dev, vfinfo);
if (err < 0)
goto errout;
status |= DO_SETLINK_NOTIFY;
diff --git a/kernel/net/core/skbuff.c b/kernel/net/core/skbuff.c
index 98da59c44..fc09e8f3d 100644
--- a/kernel/net/core/skbuff.c
+++ b/kernel/net/core/skbuff.c
@@ -341,7 +341,7 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
if (skb && frag_size) {
skb->head_frag = 1;
- if (virt_to_head_page(data)->pfmemalloc)
+ if (page_is_pfmemalloc(virt_to_head_page(data)))
skb->pfmemalloc = 1;
}
return skb;
diff --git a/kernel/net/core/sock_diag.c b/kernel/net/core/sock_diag.c
index 74dddf84a..556ecf96a 100644
--- a/kernel/net/core/sock_diag.c
+++ b/kernel/net/core/sock_diag.c
@@ -86,6 +86,9 @@ int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
goto out;
fprog = filter->prog->orig_prog;
+ if (!fprog)
+ goto out;
+
flen = bpf_classic_proglen(fprog);
attr = nla_reserve(skb, attrtype, flen);
diff --git a/kernel/net/dsa/slave.c b/kernel/net/dsa/slave.c
index 827cda560..57978c5b2 100644
--- a/kernel/net/dsa/slave.c
+++ b/kernel/net/dsa/slave.c
@@ -732,7 +732,8 @@ static int dsa_slave_phy_connect(struct dsa_slave_priv *p,
return -ENODEV;
/* Use already configured phy mode */
- p->phy_interface = p->phy->interface;
+ if (p->phy_interface == PHY_INTERFACE_MODE_NA)
+ p->phy_interface = p->phy->interface;
phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
p->phy_interface);
diff --git a/kernel/net/ipv4/datagram.c b/kernel/net/ipv4/datagram.c
index 90c0e8386..574fad9cc 100644
--- a/kernel/net/ipv4/datagram.c
+++ b/kernel/net/ipv4/datagram.c
@@ -20,7 +20,7 @@
#include <net/route.h>
#include <net/tcp_states.h>
-int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct sockaddr_in *usin = (struct sockaddr_in *) uaddr;
@@ -39,8 +39,6 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
sk_dst_reset(sk);
- lock_sock(sk);
-
oif = sk->sk_bound_dev_if;
saddr = inet->inet_saddr;
if (ipv4_is_multicast(usin->sin_addr.s_addr)) {
@@ -82,9 +80,19 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
sk_dst_set(sk, &rt->dst);
err = 0;
out:
- release_sock(sk);
return err;
}
+EXPORT_SYMBOL(__ip4_datagram_connect);
+
+int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+ int res;
+
+ lock_sock(sk);
+ res = __ip4_datagram_connect(sk, uaddr, addr_len);
+ release_sock(sk);
+ return res;
+}
EXPORT_SYMBOL(ip4_datagram_connect);
/* Because UDP xmit path can manipulate sk_dst_cache without holding
diff --git a/kernel/net/ipv4/fib_trie.c b/kernel/net/ipv4/fib_trie.c
index 09b62e17d..0ca933db1 100644
--- a/kernel/net/ipv4/fib_trie.c
+++ b/kernel/net/ipv4/fib_trie.c
@@ -1780,8 +1780,6 @@ void fib_table_flush_external(struct fib_table *tb)
if (hlist_empty(&n->leaf)) {
put_child_root(pn, n->key, NULL);
node_free(n);
- } else {
- leaf_pull_suffix(pn, n);
}
}
}
@@ -1852,8 +1850,6 @@ int fib_table_flush(struct fib_table *tb)
if (hlist_empty(&n->leaf)) {
put_child_root(pn, n->key, NULL);
node_free(n);
- } else {
- leaf_pull_suffix(pn, n);
}
}
@@ -2457,7 +2453,7 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
key = l->key + 1;
iter->pos++;
- if (pos-- <= 0)
+ if (--pos <= 0)
break;
l = NULL;
diff --git a/kernel/net/ipv4/inet_connection_sock.c b/kernel/net/ipv4/inet_connection_sock.c
index 8976ca423..b27fc401c 100644
--- a/kernel/net/ipv4/inet_connection_sock.c
+++ b/kernel/net/ipv4/inet_connection_sock.c
@@ -584,7 +584,7 @@ static bool reqsk_queue_unlink(struct request_sock_queue *queue,
}
spin_unlock(&queue->syn_wait_lock);
- if (del_timer(&req->rsk_timer))
+ if (del_timer_sync(&req->rsk_timer))
reqsk_put(req);
return found;
}
diff --git a/kernel/net/ipv4/ip_fragment.c b/kernel/net/ipv4/ip_fragment.c
index cc1da6d9c..cae22a1a8 100644
--- a/kernel/net/ipv4/ip_fragment.c
+++ b/kernel/net/ipv4/ip_fragment.c
@@ -342,7 +342,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
ihl = ip_hdrlen(skb);
/* Determine the position of this fragment. */
- end = offset + skb->len - ihl;
+ end = offset + skb->len - skb_network_offset(skb) - ihl;
err = -EINVAL;
/* Is this the final fragment? */
@@ -372,7 +372,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
goto err;
err = -ENOMEM;
- if (!pskb_pull(skb, ihl))
+ if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
goto err;
err = pskb_trim_rcsum(skb, end - offset);
@@ -613,6 +613,9 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
iph->frag_off = qp->q.max_size ? htons(IP_DF) : 0;
iph->tot_len = htons(len);
iph->tos |= ecn;
+
+ ip_send_check(iph);
+
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
qp->q.fragments = NULL;
qp->q.fragments_tail = NULL;
diff --git a/kernel/net/ipv4/ip_tunnel.c b/kernel/net/ipv4/ip_tunnel.c
index 4c2c3ba4b..626d9e56a 100644
--- a/kernel/net/ipv4/ip_tunnel.c
+++ b/kernel/net/ipv4/ip_tunnel.c
@@ -586,7 +586,8 @@ int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
EXPORT_SYMBOL(ip_tunnel_encap);
static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
- struct rtable *rt, __be16 df)
+ struct rtable *rt, __be16 df,
+ const struct iphdr *inner_iph)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
int pkt_size = skb->len - tunnel->hlen - dev->hard_header_len;
@@ -603,7 +604,8 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
if (skb->protocol == htons(ETH_P_IP)) {
if (!skb_is_gso(skb) &&
- (df & htons(IP_DF)) && mtu < pkt_size) {
+ (inner_iph->frag_off & htons(IP_DF)) &&
+ mtu < pkt_size) {
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
return -E2BIG;
@@ -737,7 +739,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
goto tx_error;
}
- if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) {
+ if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph)) {
ip_rt_put(rt);
goto tx_error;
}
diff --git a/kernel/net/ipv4/tcp_ipv4.c b/kernel/net/ipv4/tcp_ipv4.c
index fc1c658ec..441ca6f38 100644
--- a/kernel/net/ipv4/tcp_ipv4.c
+++ b/kernel/net/ipv4/tcp_ipv4.c
@@ -1348,7 +1348,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
req = inet_csk_search_req(sk, th->source, iph->saddr, iph->daddr);
if (req) {
nsk = tcp_check_req(sk, skb, req, false);
- if (!nsk)
+ if (!nsk || nsk == sk)
reqsk_put(req);
return nsk;
}
diff --git a/kernel/net/ipv4/tcp_output.c b/kernel/net/ipv4/tcp_output.c
index a369e8a70..986440b24 100644
--- a/kernel/net/ipv4/tcp_output.c
+++ b/kernel/net/ipv4/tcp_output.c
@@ -2893,6 +2893,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
skb_reserve(skb, MAX_TCP_HEADER);
tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk),
TCPHDR_ACK | TCPHDR_RST);
+ skb_mstamp_get(&skb->skb_mstamp);
/* Send it off. */
if (tcp_transmit_skb(sk, skb, 0, priority))
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
diff --git a/kernel/net/ipv4/udp.c b/kernel/net/ipv4/udp.c
index 83aa604f9..1b8c5ba7d 100644
--- a/kernel/net/ipv4/udp.c
+++ b/kernel/net/ipv4/udp.c
@@ -1995,12 +1995,19 @@ void udp_v4_early_demux(struct sk_buff *skb)
skb->sk = sk;
skb->destructor = sock_efree;
- dst = sk->sk_rx_dst;
+ dst = READ_ONCE(sk->sk_rx_dst);
if (dst)
dst = dst_check(dst, 0);
- if (dst)
- skb_dst_set_noref(skb, dst);
+ if (dst) {
+ /* DST_NOCACHE can not be used without taking a reference */
+ if (dst->flags & DST_NOCACHE) {
+ if (likely(atomic_inc_not_zero(&dst->__refcnt)))
+ skb_dst_set(skb, dst);
+ } else {
+ skb_dst_set_noref(skb, dst);
+ }
+ }
}
int udp_rcv(struct sk_buff *skb)
diff --git a/kernel/net/ipv6/datagram.c b/kernel/net/ipv6/datagram.c
index 62d908e64..b10a88986 100644
--- a/kernel/net/ipv6/datagram.c
+++ b/kernel/net/ipv6/datagram.c
@@ -40,7 +40,7 @@ static bool ipv6_mapped_addr_any(const struct in6_addr *a)
return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0);
}
-int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
struct inet_sock *inet = inet_sk(sk);
@@ -56,7 +56,7 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
if (usin->sin6_family == AF_INET) {
if (__ipv6_only_sock(sk))
return -EAFNOSUPPORT;
- err = ip4_datagram_connect(sk, uaddr, addr_len);
+ err = __ip4_datagram_connect(sk, uaddr, addr_len);
goto ipv4_connected;
}
@@ -98,9 +98,9 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
sin.sin_addr.s_addr = daddr->s6_addr32[3];
sin.sin_port = usin->sin6_port;
- err = ip4_datagram_connect(sk,
- (struct sockaddr *) &sin,
- sizeof(sin));
+ err = __ip4_datagram_connect(sk,
+ (struct sockaddr *) &sin,
+ sizeof(sin));
ipv4_connected:
if (err)
@@ -204,6 +204,16 @@ out:
fl6_sock_release(flowlabel);
return err;
}
+
+int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+ int res;
+
+ lock_sock(sk);
+ res = __ip6_datagram_connect(sk, uaddr, addr_len);
+ release_sock(sk);
+ return res;
+}
EXPORT_SYMBOL_GPL(ip6_datagram_connect);
int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *uaddr,
diff --git a/kernel/net/ipv6/exthdrs_offload.c b/kernel/net/ipv6/exthdrs_offload.c
index 447a7fbd1..f5e2ba1c1 100644
--- a/kernel/net/ipv6/exthdrs_offload.c
+++ b/kernel/net/ipv6/exthdrs_offload.c
@@ -36,6 +36,6 @@ out:
return ret;
out_rt:
- inet_del_offload(&rthdr_offload, IPPROTO_ROUTING);
+ inet6_del_offload(&rthdr_offload, IPPROTO_ROUTING);
goto out;
}
diff --git a/kernel/net/ipv6/ip6_gre.c b/kernel/net/ipv6/ip6_gre.c
index a38d3ac0f..69f4f689f 100644
--- a/kernel/net/ipv6/ip6_gre.c
+++ b/kernel/net/ipv6/ip6_gre.c
@@ -361,6 +361,7 @@ static void ip6gre_tunnel_uninit(struct net_device *dev)
struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
ip6gre_tunnel_unlink(ign, t);
+ ip6_tnl_dst_reset(t);
dev_put(dev);
}
diff --git a/kernel/net/ipv6/ip6_input.c b/kernel/net/ipv6/ip6_input.c
index f2e464eba..57990c929 100644
--- a/kernel/net/ipv6/ip6_input.c
+++ b/kernel/net/ipv6/ip6_input.c
@@ -331,10 +331,10 @@ int ip6_mc_input(struct sk_buff *skb)
if (offset < 0)
goto out;
- if (!ipv6_is_mld(skb, nexthdr, offset))
- goto out;
+ if (ipv6_is_mld(skb, nexthdr, offset))
+ deliver = true;
- deliver = true;
+ goto out;
}
/* unknown RA - process it normally */
}
diff --git a/kernel/net/ipv6/ip6_offload.c b/kernel/net/ipv6/ip6_offload.c
index e893cd186..08b62047c 100644
--- a/kernel/net/ipv6/ip6_offload.c
+++ b/kernel/net/ipv6/ip6_offload.c
@@ -292,8 +292,6 @@ static struct packet_offload ipv6_packet_offload __read_mostly = {
static const struct net_offload sit_offload = {
.callbacks = {
.gso_segment = ipv6_gso_segment,
- .gro_receive = ipv6_gro_receive,
- .gro_complete = ipv6_gro_complete,
},
};
diff --git a/kernel/net/ipv6/ip6mr.c b/kernel/net/ipv6/ip6mr.c
index 74ceb73c1..5f36266b1 100644
--- a/kernel/net/ipv6/ip6mr.c
+++ b/kernel/net/ipv6/ip6mr.c
@@ -550,7 +550,7 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
if (it->cache == &mrt->mfc6_unres_queue)
spin_unlock_bh(&mfc_unres_lock);
- else if (it->cache == mrt->mfc6_cache_array)
+ else if (it->cache == &mrt->mfc6_cache_array[it->ct])
read_unlock(&mrt_lock);
}
diff --git a/kernel/net/ipv6/route.c b/kernel/net/ipv6/route.c
index c73ae5039..f371fefa7 100644
--- a/kernel/net/ipv6/route.c
+++ b/kernel/net/ipv6/route.c
@@ -1515,7 +1515,7 @@ static int ip6_convert_metrics(struct mx6_config *mxc,
return -EINVAL;
}
-int ip6_route_add(struct fib6_config *cfg)
+int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret)
{
int err;
struct net *net = cfg->fc_nlinfo.nl_net;
@@ -1523,7 +1523,6 @@ int ip6_route_add(struct fib6_config *cfg)
struct net_device *dev = NULL;
struct inet6_dev *idev = NULL;
struct fib6_table *table;
- struct mx6_config mxc = { .mx = NULL, };
int addr_type;
if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
@@ -1719,6 +1718,32 @@ install_route:
cfg->fc_nlinfo.nl_net = dev_net(dev);
+ *rt_ret = rt;
+
+ return 0;
+out:
+ if (dev)
+ dev_put(dev);
+ if (idev)
+ in6_dev_put(idev);
+ if (rt)
+ dst_free(&rt->dst);
+
+ *rt_ret = NULL;
+
+ return err;
+}
+
+int ip6_route_add(struct fib6_config *cfg)
+{
+ struct mx6_config mxc = { .mx = NULL, };
+ struct rt6_info *rt = NULL;
+ int err;
+
+ err = ip6_route_info_create(cfg, &rt);
+ if (err)
+ goto out;
+
err = ip6_convert_metrics(&mxc, cfg);
if (err)
goto out;
@@ -1726,14 +1751,12 @@ install_route:
err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc);
kfree(mxc.mx);
+
return err;
out:
- if (dev)
- dev_put(dev);
- if (idev)
- in6_dev_put(idev);
if (rt)
dst_free(&rt->dst);
+
return err;
}
@@ -2496,19 +2519,78 @@ errout:
return err;
}
-static int ip6_route_multipath(struct fib6_config *cfg, int add)
+struct rt6_nh {
+ struct rt6_info *rt6_info;
+ struct fib6_config r_cfg;
+ struct mx6_config mxc;
+ struct list_head next;
+};
+
+static void ip6_print_replace_route_err(struct list_head *rt6_nh_list)
+{
+ struct rt6_nh *nh;
+
+ list_for_each_entry(nh, rt6_nh_list, next) {
+ pr_warn("IPV6: multipath route replace failed (check consistency of installed routes): %pI6 nexthop %pI6 ifi %d\n",
+ &nh->r_cfg.fc_dst, &nh->r_cfg.fc_gateway,
+ nh->r_cfg.fc_ifindex);
+ }
+}
+
+static int ip6_route_info_append(struct list_head *rt6_nh_list,
+ struct rt6_info *rt, struct fib6_config *r_cfg)
+{
+ struct rt6_nh *nh;
+ struct rt6_info *rtnh;
+ int err = -EEXIST;
+
+ list_for_each_entry(nh, rt6_nh_list, next) {
+ /* check if rt6_info already exists */
+ rtnh = nh->rt6_info;
+
+ if (rtnh->dst.dev == rt->dst.dev &&
+ rtnh->rt6i_idev == rt->rt6i_idev &&
+ ipv6_addr_equal(&rtnh->rt6i_gateway,
+ &rt->rt6i_gateway))
+ return err;
+ }
+
+ nh = kzalloc(sizeof(*nh), GFP_KERNEL);
+ if (!nh)
+ return -ENOMEM;
+ nh->rt6_info = rt;
+ err = ip6_convert_metrics(&nh->mxc, r_cfg);
+ if (err) {
+ kfree(nh);
+ return err;
+ }
+ memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg));
+ list_add_tail(&nh->next, rt6_nh_list);
+
+ return 0;
+}
+
+static int ip6_route_multipath_add(struct fib6_config *cfg)
{
struct fib6_config r_cfg;
struct rtnexthop *rtnh;
+ struct rt6_info *rt;
+ struct rt6_nh *err_nh;
+ struct rt6_nh *nh, *nh_safe;
int remaining;
int attrlen;
- int err = 0, last_err = 0;
+ int err = 1;
+ int nhn = 0;
+ int replace = (cfg->fc_nlinfo.nlh &&
+ (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE));
+ LIST_HEAD(rt6_nh_list);
remaining = cfg->fc_mp_len;
-beginning:
rtnh = (struct rtnexthop *)cfg->fc_mp;
- /* Parse a Multipath Entry */
+ /* Parse a Multipath Entry and build a list (rt6_nh_list) of
+ * rt6_info structs per nexthop
+ */
while (rtnh_ok(rtnh, remaining)) {
memcpy(&r_cfg, cfg, sizeof(*cfg));
if (rtnh->rtnh_ifindex)
@@ -2524,22 +2606,32 @@ beginning:
r_cfg.fc_flags |= RTF_GATEWAY;
}
}
- err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg);
+
+ err = ip6_route_info_create(&r_cfg, &rt);
+ if (err)
+ goto cleanup;
+
+ err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg);
if (err) {
- last_err = err;
- /* If we are trying to remove a route, do not stop the
- * loop when ip6_route_del() fails (because next hop is
- * already gone), we should try to remove all next hops.
- */
- if (add) {
- /* If add fails, we should try to delete all
- * next hops that have been already added.
- */
- add = 0;
- remaining = cfg->fc_mp_len - remaining;
- goto beginning;
- }
+ dst_free(&rt->dst);
+ goto cleanup;
+ }
+
+ rtnh = rtnh_next(rtnh, &remaining);
+ }
+
+ err_nh = NULL;
+ list_for_each_entry(nh, &rt6_nh_list, next) {
+ err = __ip6_ins_rt(nh->rt6_info, &cfg->fc_nlinfo, &nh->mxc);
+ /* nh->rt6_info is used or freed at this point, reset to NULL*/
+ nh->rt6_info = NULL;
+ if (err) {
+ if (replace && nhn)
+ ip6_print_replace_route_err(&rt6_nh_list);
+ err_nh = nh;
+ goto add_errout;
}
+
/* Because each route is added like a single route we remove
* these flags after the first nexthop: if there is a collision,
* we have already failed to add the first nexthop:
@@ -2549,6 +2641,63 @@ beginning:
*/
cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
NLM_F_REPLACE);
+ nhn++;
+ }
+
+ goto cleanup;
+
+add_errout:
+ /* Delete routes that were already added */
+ list_for_each_entry(nh, &rt6_nh_list, next) {
+ if (err_nh == nh)
+ break;
+ ip6_route_del(&nh->r_cfg);
+ }
+
+cleanup:
+ list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) {
+ if (nh->rt6_info)
+ dst_free(&nh->rt6_info->dst);
+ if (nh->mxc.mx)
+ kfree(nh->mxc.mx);
+ list_del(&nh->next);
+ kfree(nh);
+ }
+
+ return err;
+}
+
+static int ip6_route_multipath_del(struct fib6_config *cfg)
+{
+ struct fib6_config r_cfg;
+ struct rtnexthop *rtnh;
+ int remaining;
+ int attrlen;
+ int err = 1, last_err = 0;
+
+ remaining = cfg->fc_mp_len;
+ rtnh = (struct rtnexthop *)cfg->fc_mp;
+
+ /* Parse a Multipath Entry */
+ while (rtnh_ok(rtnh, remaining)) {
+ memcpy(&r_cfg, cfg, sizeof(*cfg));
+ if (rtnh->rtnh_ifindex)
+ r_cfg.fc_ifindex = rtnh->rtnh_ifindex;
+
+ attrlen = rtnh_attrlen(rtnh);
+ if (attrlen > 0) {
+ struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
+
+ nla = nla_find(attrs, attrlen, RTA_GATEWAY);
+ if (nla) {
+ nla_memcpy(&r_cfg.fc_gateway, nla, 16);
+ r_cfg.fc_flags |= RTF_GATEWAY;
+ }
+ }
+ err = ip6_route_del(&r_cfg);
+ if (err)
+ last_err = err;
+
rtnh = rtnh_next(rtnh, &remaining);
}
@@ -2565,7 +2714,7 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
return err;
if (cfg.fc_mp)
- return ip6_route_multipath(&cfg, 0);
+ return ip6_route_multipath_del(&cfg);
else
return ip6_route_del(&cfg);
}
@@ -2580,7 +2729,7 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
return err;
if (cfg.fc_mp)
- return ip6_route_multipath(&cfg, 1);
+ return ip6_route_multipath_add(&cfg);
else
return ip6_route_add(&cfg);
}
diff --git a/kernel/net/ipv6/tcp_ipv6.c b/kernel/net/ipv6/tcp_ipv6.c
index 3adffb300..e541d68db 100644
--- a/kernel/net/ipv6/tcp_ipv6.c
+++ b/kernel/net/ipv6/tcp_ipv6.c
@@ -946,7 +946,7 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb)
&ipv6_hdr(skb)->daddr, tcp_v6_iif(skb));
if (req) {
nsk = tcp_check_req(sk, skb, req, false);
- if (!nsk)
+ if (!nsk || nsk == sk)
reqsk_put(req);
return nsk;
}
diff --git a/kernel/net/mac80211/tx.c b/kernel/net/mac80211/tx.c
index 667111ee6..5787f15a3 100644
--- a/kernel/net/mac80211/tx.c
+++ b/kernel/net/mac80211/tx.c
@@ -301,9 +301,6 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx)
if (tx->sdata->vif.type == NL80211_IFTYPE_WDS)
return TX_CONTINUE;
- if (tx->sdata->vif.type == NL80211_IFTYPE_MESH_POINT)
- return TX_CONTINUE;
-
if (tx->flags & IEEE80211_TX_PS_BUFFERED)
return TX_CONTINUE;
diff --git a/kernel/net/netlink/af_netlink.c b/kernel/net/netlink/af_netlink.c
index bf6e76643..980121e75 100644
--- a/kernel/net/netlink/af_netlink.c
+++ b/kernel/net/netlink/af_netlink.c
@@ -123,6 +123,24 @@ static inline u32 netlink_group_mask(u32 group)
return group ? 1 << (group - 1) : 0;
}
+static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb,
+ gfp_t gfp_mask)
+{
+ unsigned int len = skb_end_offset(skb);
+ struct sk_buff *new;
+
+ new = alloc_skb(len, gfp_mask);
+ if (new == NULL)
+ return NULL;
+
+ NETLINK_CB(new).portid = NETLINK_CB(skb).portid;
+ NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group;
+ NETLINK_CB(new).creds = NETLINK_CB(skb).creds;
+
+ memcpy(skb_put(new, len), skb->data, len);
+ return new;
+}
+
int netlink_add_tap(struct netlink_tap *nt)
{
if (unlikely(nt->dev->type != ARPHRD_NETLINK))
@@ -204,7 +222,11 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
int ret = -ENOMEM;
dev_hold(dev);
- nskb = skb_clone(skb, GFP_ATOMIC);
+
+ if (netlink_skb_is_mmaped(skb) || is_vmalloc_addr(skb->head))
+ nskb = netlink_to_full_skb(skb, GFP_ATOMIC);
+ else
+ nskb = skb_clone(skb, GFP_ATOMIC);
if (nskb) {
nskb->dev = dev;
nskb->protocol = htons((u16) sk->sk_protocol);
@@ -276,11 +298,6 @@ static void netlink_rcv_wake(struct sock *sk)
}
#ifdef CONFIG_NETLINK_MMAP
-static bool netlink_skb_is_mmaped(const struct sk_buff *skb)
-{
- return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
-}
-
static bool netlink_rx_is_mmaped(struct sock *sk)
{
return nlk_sk(sk)->rx_ring.pg_vec != NULL;
@@ -355,25 +372,52 @@ err1:
return NULL;
}
+
+static void
+__netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, bool tx_ring, void **pg_vec,
+ unsigned int order)
+{
+ struct netlink_sock *nlk = nlk_sk(sk);
+ struct sk_buff_head *queue;
+ struct netlink_ring *ring;
+
+ queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
+ ring = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
+
+ spin_lock_bh(&queue->lock);
+
+ ring->frame_max = req->nm_frame_nr - 1;
+ ring->head = 0;
+ ring->frame_size = req->nm_frame_size;
+ ring->pg_vec_pages = req->nm_block_size / PAGE_SIZE;
+
+ swap(ring->pg_vec_len, req->nm_block_nr);
+ swap(ring->pg_vec_order, order);
+ swap(ring->pg_vec, pg_vec);
+
+ __skb_queue_purge(queue);
+ spin_unlock_bh(&queue->lock);
+
+ WARN_ON(atomic_read(&nlk->mapped));
+
+ if (pg_vec)
+ free_pg_vec(pg_vec, order, req->nm_block_nr);
+}
+
static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
- bool closing, bool tx_ring)
+ bool tx_ring)
{
struct netlink_sock *nlk = nlk_sk(sk);
struct netlink_ring *ring;
- struct sk_buff_head *queue;
void **pg_vec = NULL;
unsigned int order = 0;
- int err;
ring = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
- queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
- if (!closing) {
- if (atomic_read(&nlk->mapped))
- return -EBUSY;
- if (atomic_read(&ring->pending))
- return -EBUSY;
- }
+ if (atomic_read(&nlk->mapped))
+ return -EBUSY;
+ if (atomic_read(&ring->pending))
+ return -EBUSY;
if (req->nm_block_nr) {
if (ring->pg_vec != NULL)
@@ -405,31 +449,19 @@ static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
return -EINVAL;
}
- err = -EBUSY;
mutex_lock(&nlk->pg_vec_lock);
- if (closing || atomic_read(&nlk->mapped) == 0) {
- err = 0;
- spin_lock_bh(&queue->lock);
-
- ring->frame_max = req->nm_frame_nr - 1;
- ring->head = 0;
- ring->frame_size = req->nm_frame_size;
- ring->pg_vec_pages = req->nm_block_size / PAGE_SIZE;
-
- swap(ring->pg_vec_len, req->nm_block_nr);
- swap(ring->pg_vec_order, order);
- swap(ring->pg_vec, pg_vec);
-
- __skb_queue_purge(queue);
- spin_unlock_bh(&queue->lock);
-
- WARN_ON(atomic_read(&nlk->mapped));
+ if (atomic_read(&nlk->mapped) == 0) {
+ __netlink_set_ring(sk, req, tx_ring, pg_vec, order);
+ mutex_unlock(&nlk->pg_vec_lock);
+ return 0;
}
+
mutex_unlock(&nlk->pg_vec_lock);
if (pg_vec)
free_pg_vec(pg_vec, order, req->nm_block_nr);
- return err;
+
+ return -EBUSY;
}
static void netlink_mm_open(struct vm_area_struct *vma)
@@ -817,7 +849,6 @@ static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb)
}
#else /* CONFIG_NETLINK_MMAP */
-#define netlink_skb_is_mmaped(skb) false
#define netlink_rx_is_mmaped(sk) false
#define netlink_tx_is_mmaped(sk) false
#define netlink_mmap sock_no_mmap
@@ -898,10 +929,10 @@ static void netlink_sock_destruct(struct sock *sk)
memset(&req, 0, sizeof(req));
if (nlk->rx_ring.pg_vec)
- netlink_set_ring(sk, &req, true, false);
+ __netlink_set_ring(sk, &req, false, NULL, 0);
memset(&req, 0, sizeof(req));
if (nlk->tx_ring.pg_vec)
- netlink_set_ring(sk, &req, true, true);
+ __netlink_set_ring(sk, &req, true, NULL, 0);
}
#endif /* CONFIG_NETLINK_MMAP */
@@ -1065,8 +1096,8 @@ static int netlink_insert(struct sock *sk, u32 portid)
lock_sock(sk);
- err = -EBUSY;
- if (nlk_sk(sk)->portid)
+ err = nlk_sk(sk)->portid == portid ? 0 : -EBUSY;
+ if (nlk_sk(sk)->bound)
goto err;
err = -ENOMEM;
@@ -1079,12 +1110,20 @@ static int netlink_insert(struct sock *sk, u32 portid)
err = __netlink_insert(table, sk);
if (err) {
+ /* In case the hashtable backend returns with -EBUSY
+ * from here, it must not escape to the caller.
+ */
+ if (unlikely(err == -EBUSY))
+ err = -EOVERFLOW;
if (err == -EEXIST)
err = -EADDRINUSE;
- nlk_sk(sk)->portid = 0;
sock_put(sk);
}
+ /* We need to ensure that the socket is hashed and visible. */
+ smp_wmb();
+ nlk_sk(sk)->bound = portid;
+
err:
release_sock(sk);
return err;
@@ -1464,6 +1503,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
int err;
long unsigned int groups = nladdr->nl_groups;
+ bool bound;
if (addr_len < sizeof(struct sockaddr_nl))
return -EINVAL;
@@ -1480,9 +1520,14 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
return err;
}
- if (nlk->portid)
+ bound = nlk->bound;
+ if (bound) {
+ /* Ensure nlk->portid is up-to-date. */
+ smp_rmb();
+
if (nladdr->nl_pid != nlk->portid)
return -EINVAL;
+ }
if (nlk->netlink_bind && groups) {
int group;
@@ -1498,7 +1543,10 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
}
}
- if (!nlk->portid) {
+ /* No need for barriers here as we return to user-space without
+ * using any of the bound attributes.
+ */
+ if (!bound) {
err = nladdr->nl_pid ?
netlink_insert(sk, nladdr->nl_pid) :
netlink_autobind(sock);
@@ -1546,7 +1594,10 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
!netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
return -EPERM;
- if (!nlk->portid)
+ /* No need for barriers here as we return to user-space without
+ * using any of the bound attributes.
+ */
+ if (!nlk->bound)
err = netlink_autobind(sock);
if (err == 0) {
@@ -2197,7 +2248,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
return -EINVAL;
if (copy_from_user(&req, optval, sizeof(req)))
return -EFAULT;
- err = netlink_set_ring(sk, &req, false,
+ err = netlink_set_ring(sk, &req,
optname == NETLINK_TX_RING);
break;
}
@@ -2303,10 +2354,13 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
dst_group = nlk->dst_group;
}
- if (!nlk->portid) {
+ if (!nlk->bound) {
err = netlink_autobind(sock);
if (err)
goto out;
+ } else {
+ /* Ensure nlk is hashed and visible. */
+ smp_rmb();
}
/* It's a really convoluted way for userland to ask for mmaped
diff --git a/kernel/net/netlink/af_netlink.h b/kernel/net/netlink/af_netlink.h
index 89008405d..14437d9b1 100644
--- a/kernel/net/netlink/af_netlink.h
+++ b/kernel/net/netlink/af_netlink.h
@@ -35,6 +35,7 @@ struct netlink_sock {
unsigned long state;
size_t max_recvmsg_len;
wait_queue_head_t wait;
+ bool bound;
bool cb_running;
struct netlink_callback cb;
struct mutex *cb_mutex;
@@ -59,6 +60,15 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk)
return container_of(sk, struct netlink_sock, sk);
}
+static inline bool netlink_skb_is_mmaped(const struct sk_buff *skb)
+{
+#ifdef CONFIG_NETLINK_MMAP
+ return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
+#else
+ return false;
+#endif /* CONFIG_NETLINK_MMAP */
+}
+
struct netlink_table {
struct rhashtable hash;
struct hlist_head mc_list;
diff --git a/kernel/net/nfc/nci/hci.c b/kernel/net/nfc/nci/hci.c
index ed54ec533..b33fed6d1 100644
--- a/kernel/net/nfc/nci/hci.c
+++ b/kernel/net/nfc/nci/hci.c
@@ -233,7 +233,7 @@ int nci_hci_send_cmd(struct nci_dev *ndev, u8 gate, u8 cmd,
r = nci_request(ndev, nci_hci_send_data_req, (unsigned long)&data,
msecs_to_jiffies(NCI_DATA_TIMEOUT));
- if (r == NCI_STATUS_OK)
+ if (r == NCI_STATUS_OK && skb)
*skb = conn_info->rx_skb;
return r;
diff --git a/kernel/net/openvswitch/datapath.c b/kernel/net/openvswitch/datapath.c
index 096c6276e..27e14962b 100644
--- a/kernel/net/openvswitch/datapath.c
+++ b/kernel/net/openvswitch/datapath.c
@@ -906,7 +906,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
if (error)
goto err_kfree_flow;
- ovs_flow_mask_key(&new_flow->key, &key, &mask);
+ ovs_flow_mask_key(&new_flow->key, &key, true, &mask);
/* Extract flow identifier. */
error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID],
@@ -1033,7 +1033,7 @@ static struct sw_flow_actions *get_flow_actions(const struct nlattr *a,
struct sw_flow_key masked_key;
int error;
- ovs_flow_mask_key(&masked_key, key, mask);
+ ovs_flow_mask_key(&masked_key, key, true, mask);
error = ovs_nla_copy_actions(a, &masked_key, &acts, log);
if (error) {
OVS_NLERR(log,
diff --git a/kernel/net/openvswitch/flow_table.c b/kernel/net/openvswitch/flow_table.c
index 4613df8c8..aa349514e 100644
--- a/kernel/net/openvswitch/flow_table.c
+++ b/kernel/net/openvswitch/flow_table.c
@@ -56,20 +56,21 @@ static u16 range_n_bytes(const struct sw_flow_key_range *range)
}
void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
- const struct sw_flow_mask *mask)
+ bool full, const struct sw_flow_mask *mask)
{
- const long *m = (const long *)((const u8 *)&mask->key +
- mask->range.start);
- const long *s = (const long *)((const u8 *)src +
- mask->range.start);
- long *d = (long *)((u8 *)dst + mask->range.start);
+ int start = full ? 0 : mask->range.start;
+ int len = full ? sizeof *dst : range_n_bytes(&mask->range);
+ const long *m = (const long *)((const u8 *)&mask->key + start);
+ const long *s = (const long *)((const u8 *)src + start);
+ long *d = (long *)((u8 *)dst + start);
int i;
- /* The memory outside of the 'mask->range' are not set since
- * further operations on 'dst' only uses contents within
- * 'mask->range'.
+ /* If 'full' is true then all of 'dst' is fully initialized. Otherwise,
+ * if 'full' is false the memory outside of the 'mask->range' is left
+ * uninitialized. This can be used as an optimization when further
+ * operations on 'dst' only use contents within 'mask->range'.
*/
- for (i = 0; i < range_n_bytes(&mask->range); i += sizeof(long))
+ for (i = 0; i < len; i += sizeof(long))
*d++ = *s++ & *m++;
}
@@ -473,7 +474,7 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
u32 hash;
struct sw_flow_key masked_key;
- ovs_flow_mask_key(&masked_key, unmasked, mask);
+ ovs_flow_mask_key(&masked_key, unmasked, false, mask);
hash = flow_hash(&masked_key, &mask->range);
head = find_bucket(ti, hash);
hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) {
diff --git a/kernel/net/openvswitch/flow_table.h b/kernel/net/openvswitch/flow_table.h
index 616eda10d..2dd9900f5 100644
--- a/kernel/net/openvswitch/flow_table.h
+++ b/kernel/net/openvswitch/flow_table.h
@@ -86,5 +86,5 @@ struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *,
bool ovs_flow_cmp(const struct sw_flow *, const struct sw_flow_match *);
void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
- const struct sw_flow_mask *mask);
+ bool full, const struct sw_flow_mask *mask);
#endif /* flow_table.h */
diff --git a/kernel/net/packet/af_packet.c b/kernel/net/packet/af_packet.c
index ef1eb2050..f9f259247 100644
--- a/kernel/net/packet/af_packet.c
+++ b/kernel/net/packet/af_packet.c
@@ -2308,7 +2308,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
}
tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
addr, hlen);
- if (tp_len > dev->mtu + dev->hard_header_len) {
+ if (likely(tp_len >= 0) &&
+ tp_len > dev->mtu + dev->hard_header_len) {
struct ethhdr *ehdr;
/* Earlier code assumed this would be a VLAN pkt,
* double-check this now that we have the actual
@@ -2689,7 +2690,7 @@ static int packet_release(struct socket *sock)
static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
{
struct packet_sock *po = pkt_sk(sk);
- const struct net_device *dev_curr;
+ struct net_device *dev_curr;
__be16 proto_curr;
bool need_rehook;
@@ -2713,15 +2714,13 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
po->num = proto;
po->prot_hook.type = proto;
-
- if (po->prot_hook.dev)
- dev_put(po->prot_hook.dev);
-
po->prot_hook.dev = dev;
po->ifindex = dev ? dev->ifindex : 0;
packet_cached_dev_assign(po, dev);
}
+ if (dev_curr)
+ dev_put(dev_curr);
if (proto == 0 || !need_rehook)
goto out_unlock;
diff --git a/kernel/net/rds/info.c b/kernel/net/rds/info.c
index 9a6b4f661..140a44a5f 100644
--- a/kernel/net/rds/info.c
+++ b/kernel/net/rds/info.c
@@ -176,7 +176,7 @@ int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval,
/* check for all kinds of wrapping and the like */
start = (unsigned long)optval;
- if (len < 0 || len + PAGE_SIZE - 1 < len || start + len < start) {
+ if (len < 0 || len > INT_MAX - PAGE_SIZE + 1 || start + len < start) {
ret = -EINVAL;
goto out;
}
diff --git a/kernel/net/sched/act_api.c b/kernel/net/sched/act_api.c
index 3d43e4979..f8d9c2a2c 100644
--- a/kernel/net/sched/act_api.c
+++ b/kernel/net/sched/act_api.c
@@ -45,7 +45,7 @@ void tcf_hash_destroy(struct tc_action *a)
}
EXPORT_SYMBOL(tcf_hash_destroy);
-int tcf_hash_release(struct tc_action *a, int bind)
+int __tcf_hash_release(struct tc_action *a, bool bind, bool strict)
{
struct tcf_common *p = a->priv;
int ret = 0;
@@ -53,7 +53,7 @@ int tcf_hash_release(struct tc_action *a, int bind)
if (p) {
if (bind)
p->tcfc_bindcnt--;
- else if (p->tcfc_bindcnt > 0)
+ else if (strict && p->tcfc_bindcnt > 0)
return -EPERM;
p->tcfc_refcnt--;
@@ -64,9 +64,10 @@ int tcf_hash_release(struct tc_action *a, int bind)
ret = 1;
}
}
+
return ret;
}
-EXPORT_SYMBOL(tcf_hash_release);
+EXPORT_SYMBOL(__tcf_hash_release);
static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb,
struct tc_action *a)
@@ -136,7 +137,7 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a)
head = &hinfo->htab[tcf_hash(i, hinfo->hmask)];
hlist_for_each_entry_safe(p, n, head, tcfc_head) {
a->priv = p;
- ret = tcf_hash_release(a, 0);
+ ret = __tcf_hash_release(a, false, true);
if (ret == ACT_P_DELETED) {
module_put(a->ops->owner);
n_i++;
@@ -413,7 +414,7 @@ int tcf_action_destroy(struct list_head *actions, int bind)
int ret = 0;
list_for_each_entry_safe(a, tmp, actions, list) {
- ret = tcf_hash_release(a, bind);
+ ret = __tcf_hash_release(a, bind, true);
if (ret == ACT_P_DELETED)
module_put(a->ops->owner);
else if (ret < 0)
diff --git a/kernel/net/sched/act_bpf.c b/kernel/net/sched/act_bpf.c
index dc6a2d324..521ffca91 100644
--- a/kernel/net/sched/act_bpf.c
+++ b/kernel/net/sched/act_bpf.c
@@ -27,9 +27,10 @@
struct tcf_bpf_cfg {
struct bpf_prog *filter;
struct sock_filter *bpf_ops;
- char *bpf_name;
+ const char *bpf_name;
u32 bpf_fd;
u16 bpf_num_ops;
+ bool is_ebpf;
};
static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act,
@@ -200,6 +201,7 @@ static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
cfg->bpf_ops = bpf_ops;
cfg->bpf_num_ops = bpf_num_ops;
cfg->filter = fp;
+ cfg->is_ebpf = false;
return 0;
}
@@ -234,18 +236,40 @@ static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
cfg->bpf_fd = bpf_fd;
cfg->bpf_name = name;
cfg->filter = fp;
+ cfg->is_ebpf = true;
return 0;
}
+static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg)
+{
+ if (cfg->is_ebpf)
+ bpf_prog_put(cfg->filter);
+ else
+ bpf_prog_destroy(cfg->filter);
+
+ kfree(cfg->bpf_ops);
+ kfree(cfg->bpf_name);
+}
+
+static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog,
+ struct tcf_bpf_cfg *cfg)
+{
+ cfg->is_ebpf = tcf_bpf_is_ebpf(prog);
+ cfg->filter = prog->filter;
+
+ cfg->bpf_ops = prog->bpf_ops;
+ cfg->bpf_name = prog->bpf_name;
+}
+
static int tcf_bpf_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action *act,
int replace, int bind)
{
struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
+ struct tcf_bpf_cfg cfg, old;
struct tc_act_bpf *parm;
struct tcf_bpf *prog;
- struct tcf_bpf_cfg cfg;
bool is_bpf, is_ebpf;
int ret;
@@ -294,6 +318,9 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
prog = to_bpf(act);
spin_lock_bh(&prog->tcf_lock);
+ if (ret != ACT_P_CREATED)
+ tcf_bpf_prog_fill_cfg(prog, &old);
+
prog->bpf_ops = cfg.bpf_ops;
prog->bpf_name = cfg.bpf_name;
@@ -309,29 +336,22 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
if (ret == ACT_P_CREATED)
tcf_hash_insert(act);
+ else
+ tcf_bpf_cfg_cleanup(&old);
return ret;
destroy_fp:
- if (is_ebpf)
- bpf_prog_put(cfg.filter);
- else
- bpf_prog_destroy(cfg.filter);
-
- kfree(cfg.bpf_ops);
- kfree(cfg.bpf_name);
-
+ tcf_bpf_cfg_cleanup(&cfg);
return ret;
}
static void tcf_bpf_cleanup(struct tc_action *act, int bind)
{
- const struct tcf_bpf *prog = act->priv;
+ struct tcf_bpf_cfg tmp;
- if (tcf_bpf_is_ebpf(prog))
- bpf_prog_put(prog->filter);
- else
- bpf_prog_destroy(prog->filter);
+ tcf_bpf_prog_fill_cfg(act->priv, &tmp);
+ tcf_bpf_cfg_cleanup(&tmp);
}
static struct tc_action_ops act_bpf_ops __read_mostly = {
diff --git a/kernel/net/sched/cls_bpf.c b/kernel/net/sched/cls_bpf.c
index 91bd9c194..c0b86f2bf 100644
--- a/kernel/net/sched/cls_bpf.c
+++ b/kernel/net/sched/cls_bpf.c
@@ -364,7 +364,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
goto errout;
if (oldprog) {
- list_replace_rcu(&prog->link, &oldprog->link);
+ list_replace_rcu(&oldprog->link, &prog->link);
tcf_unbind_filter(tp, &oldprog->res);
call_rcu(&oldprog->rcu, __cls_bpf_delete_prog);
} else {
diff --git a/kernel/net/sched/cls_flow.c b/kernel/net/sched/cls_flow.c
index a620c4e28..75df923f5 100644
--- a/kernel/net/sched/cls_flow.c
+++ b/kernel/net/sched/cls_flow.c
@@ -419,6 +419,8 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
if (!fnew)
goto err2;
+ tcf_exts_init(&fnew->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE);
+
fold = (struct flow_filter *)*arg;
if (fold) {
err = -EINVAL;
@@ -480,7 +482,6 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
fnew->mask = ~0U;
fnew->tp = tp;
get_random_bytes(&fnew->hashrnd, 4);
- tcf_exts_init(&fnew->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE);
}
fnew->perturb_timer.function = flow_perturbation;
@@ -520,7 +521,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
if (*arg == 0)
list_add_tail_rcu(&fnew->list, &head->filters);
else
- list_replace_rcu(&fnew->list, &fold->list);
+ list_replace_rcu(&fold->list, &fnew->list);
*arg = (unsigned long)fnew;
diff --git a/kernel/net/sched/cls_fw.c b/kernel/net/sched/cls_fw.c
index 715e01e59..f23a3b68b 100644
--- a/kernel/net/sched/cls_fw.c
+++ b/kernel/net/sched/cls_fw.c
@@ -33,7 +33,6 @@
struct fw_head {
u32 mask;
- bool mask_set;
struct fw_filter __rcu *ht[HTSIZE];
struct rcu_head rcu;
};
@@ -84,7 +83,7 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp,
}
}
} else {
- /* old method */
+ /* Old method: classify the packet using its skb mark. */
if (id && (TC_H_MAJ(id) == 0 ||
!(TC_H_MAJ(id ^ tp->q->handle)))) {
res->classid = id;
@@ -114,14 +113,9 @@ static unsigned long fw_get(struct tcf_proto *tp, u32 handle)
static int fw_init(struct tcf_proto *tp)
{
- struct fw_head *head;
-
- head = kzalloc(sizeof(struct fw_head), GFP_KERNEL);
- if (head == NULL)
- return -ENOBUFS;
-
- head->mask_set = false;
- rcu_assign_pointer(tp->root, head);
+ /* We don't allocate fw_head here, because in the old method
+ * we don't need it at all.
+ */
return 0;
}
@@ -252,7 +246,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
int err;
if (!opt)
- return handle ? -EINVAL : 0;
+ return handle ? -EINVAL : 0; /* Succeed if it is old method. */
err = nla_parse_nested(tb, TCA_FW_MAX, opt, fw_policy);
if (err < 0)
@@ -302,11 +296,17 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
if (!handle)
return -EINVAL;
- if (!head->mask_set) {
- head->mask = 0xFFFFFFFF;
+ if (!head) {
+ u32 mask = 0xFFFFFFFF;
if (tb[TCA_FW_MASK])
- head->mask = nla_get_u32(tb[TCA_FW_MASK]);
- head->mask_set = true;
+ mask = nla_get_u32(tb[TCA_FW_MASK]);
+
+ head = kzalloc(sizeof(*head), GFP_KERNEL);
+ if (!head)
+ return -ENOBUFS;
+ head->mask = mask;
+
+ rcu_assign_pointer(tp->root, head);
}
f = kzalloc(sizeof(struct fw_filter), GFP_KERNEL);
diff --git a/kernel/net/sched/cls_u32.c b/kernel/net/sched/cls_u32.c
index cab9e9b43..4fbb67430 100644
--- a/kernel/net/sched/cls_u32.c
+++ b/kernel/net/sched/cls_u32.c
@@ -490,6 +490,19 @@ static bool u32_destroy(struct tcf_proto *tp, bool force)
return false;
}
}
+
+ if (tp_c->refcnt > 1)
+ return false;
+
+ if (tp_c->refcnt == 1) {
+ struct tc_u_hnode *ht;
+
+ for (ht = rtnl_dereference(tp_c->hlist);
+ ht;
+ ht = rtnl_dereference(ht->next))
+ if (!ht_empty(ht))
+ return false;
+ }
}
if (root_ht && --root_ht->refcnt == 0)
diff --git a/kernel/net/sched/sch_fq_codel.c b/kernel/net/sched/sch_fq_codel.c
index c244c45b7..9291598b5 100644
--- a/kernel/net/sched/sch_fq_codel.c
+++ b/kernel/net/sched/sch_fq_codel.c
@@ -162,10 +162,10 @@ static unsigned int fq_codel_drop(struct Qdisc *sch)
skb = dequeue_head(flow);
len = qdisc_pkt_len(skb);
q->backlogs[idx] -= len;
- kfree_skb(skb);
sch->q.qlen--;
qdisc_qstats_drop(sch);
qdisc_qstats_backlog_dec(sch, skb);
+ kfree_skb(skb);
flow->dropped++;
return idx;
}
diff --git a/kernel/net/sctp/protocol.c b/kernel/net/sctp/protocol.c
index 53b7acde9..e13c3c3ea 100644
--- a/kernel/net/sctp/protocol.c
+++ b/kernel/net/sctp/protocol.c
@@ -1166,7 +1166,7 @@ static void sctp_v4_del_protocol(void)
unregister_inetaddr_notifier(&sctp_inetaddr_notifier);
}
-static int __net_init sctp_net_init(struct net *net)
+static int __net_init sctp_defaults_init(struct net *net)
{
int status;
@@ -1259,12 +1259,6 @@ static int __net_init sctp_net_init(struct net *net)
sctp_dbg_objcnt_init(net);
- /* Initialize the control inode/socket for handling OOTB packets. */
- if ((status = sctp_ctl_sock_init(net))) {
- pr_err("Failed to initialize the SCTP control sock\n");
- goto err_ctl_sock_init;
- }
-
/* Initialize the local address list. */
INIT_LIST_HEAD(&net->sctp.local_addr_list);
spin_lock_init(&net->sctp.local_addr_lock);
@@ -1280,9 +1274,6 @@ static int __net_init sctp_net_init(struct net *net)
return 0;
-err_ctl_sock_init:
- sctp_dbg_objcnt_exit(net);
- sctp_proc_exit(net);
err_init_proc:
cleanup_sctp_mibs(net);
err_init_mibs:
@@ -1291,15 +1282,12 @@ err_sysctl_register:
return status;
}
-static void __net_exit sctp_net_exit(struct net *net)
+static void __net_exit sctp_defaults_exit(struct net *net)
{
/* Free the local address list */
sctp_free_addr_wq(net);
sctp_free_local_addr_list(net);
- /* Free the control endpoint. */
- inet_ctl_sock_destroy(net->sctp.ctl_sock);
-
sctp_dbg_objcnt_exit(net);
sctp_proc_exit(net);
@@ -1307,9 +1295,32 @@ static void __net_exit sctp_net_exit(struct net *net)
sctp_sysctl_net_unregister(net);
}
-static struct pernet_operations sctp_net_ops = {
- .init = sctp_net_init,
- .exit = sctp_net_exit,
+static struct pernet_operations sctp_defaults_ops = {
+ .init = sctp_defaults_init,
+ .exit = sctp_defaults_exit,
+};
+
+static int __net_init sctp_ctrlsock_init(struct net *net)
+{
+ int status;
+
+ /* Initialize the control inode/socket for handling OOTB packets. */
+ status = sctp_ctl_sock_init(net);
+ if (status)
+ pr_err("Failed to initialize the SCTP control sock\n");
+
+ return status;
+}
+
+static void __net_init sctp_ctrlsock_exit(struct net *net)
+{
+ /* Free the control endpoint. */
+ inet_ctl_sock_destroy(net->sctp.ctl_sock);
+}
+
+static struct pernet_operations sctp_ctrlsock_ops = {
+ .init = sctp_ctrlsock_init,
+ .exit = sctp_ctrlsock_exit,
};
/* Initialize the universe into something sensible. */
@@ -1442,8 +1453,11 @@ static __init int sctp_init(void)
sctp_v4_pf_init();
sctp_v6_pf_init();
- status = sctp_v4_protosw_init();
+ status = register_pernet_subsys(&sctp_defaults_ops);
+ if (status)
+ goto err_register_defaults;
+ status = sctp_v4_protosw_init();
if (status)
goto err_protosw_init;
@@ -1451,9 +1465,9 @@ static __init int sctp_init(void)
if (status)
goto err_v6_protosw_init;
- status = register_pernet_subsys(&sctp_net_ops);
+ status = register_pernet_subsys(&sctp_ctrlsock_ops);
if (status)
- goto err_register_pernet_subsys;
+ goto err_register_ctrlsock;
status = sctp_v4_add_protocol();
if (status)
@@ -1469,12 +1483,14 @@ out:
err_v6_add_protocol:
sctp_v4_del_protocol();
err_add_protocol:
- unregister_pernet_subsys(&sctp_net_ops);
-err_register_pernet_subsys:
+ unregister_pernet_subsys(&sctp_ctrlsock_ops);
+err_register_ctrlsock:
sctp_v6_protosw_exit();
err_v6_protosw_init:
sctp_v4_protosw_exit();
err_protosw_init:
+ unregister_pernet_subsys(&sctp_defaults_ops);
+err_register_defaults:
sctp_v4_pf_exit();
sctp_v6_pf_exit();
sctp_sysctl_unregister();
@@ -1507,12 +1523,14 @@ static __exit void sctp_exit(void)
sctp_v6_del_protocol();
sctp_v4_del_protocol();
- unregister_pernet_subsys(&sctp_net_ops);
+ unregister_pernet_subsys(&sctp_ctrlsock_ops);
/* Free protosw registrations */
sctp_v6_protosw_exit();
sctp_v4_protosw_exit();
+ unregister_pernet_subsys(&sctp_defaults_ops);
+
/* Unregister with socket layer. */
sctp_v6_pf_exit();
sctp_v4_pf_exit();
diff --git a/kernel/net/sunrpc/xprt.c b/kernel/net/sunrpc/xprt.c
index 1d4fe24af..d109d308e 100644
--- a/kernel/net/sunrpc/xprt.c
+++ b/kernel/net/sunrpc/xprt.c
@@ -611,6 +611,7 @@ static void xprt_autoclose(struct work_struct *work)
xprt->ops->close(xprt);
clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
xprt_release_write(xprt, NULL);
+ wake_up_bit(&xprt->state, XPRT_LOCKED);
}
/**
@@ -720,6 +721,7 @@ void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie)
xprt->ops->release_xprt(xprt, NULL);
out:
spin_unlock_bh(&xprt->transport_lock);
+ wake_up_bit(&xprt->state, XPRT_LOCKED);
}
/**
@@ -1389,6 +1391,10 @@ out:
static void xprt_destroy(struct rpc_xprt *xprt)
{
dprintk("RPC: destroying transport %p\n", xprt);
+
+ /* Exclude transport connect/disconnect handlers */
+ wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_UNINTERRUPTIBLE);
+
del_timer_sync(&xprt->timer);
rpc_xprt_debugfs_unregister(xprt);
diff --git a/kernel/net/sunrpc/xprtsock.c b/kernel/net/sunrpc/xprtsock.c
index 66891e32c..5e3ad598d 100644
--- a/kernel/net/sunrpc/xprtsock.c
+++ b/kernel/net/sunrpc/xprtsock.c
@@ -834,6 +834,7 @@ static void xs_reset_transport(struct sock_xprt *transport)
sk->sk_user_data = NULL;
xs_restore_old_callbacks(transport, sk);
+ xprt_clear_connected(xprt);
write_unlock_bh(&sk->sk_callback_lock);
xs_sock_reset_connection_flags(xprt);
@@ -1433,6 +1434,7 @@ out:
static void xs_tcp_state_change(struct sock *sk)
{
struct rpc_xprt *xprt;
+ struct sock_xprt *transport;
read_lock_bh(&sk->sk_callback_lock);
if (!(xprt = xprt_from_sock(sk)))
@@ -1444,13 +1446,12 @@ static void xs_tcp_state_change(struct sock *sk)
sock_flag(sk, SOCK_ZAPPED),
sk->sk_shutdown);
+ transport = container_of(xprt, struct sock_xprt, xprt);
trace_rpc_socket_state_change(xprt, sk->sk_socket);
switch (sk->sk_state) {
case TCP_ESTABLISHED:
spin_lock(&xprt->transport_lock);
if (!xprt_test_and_set_connected(xprt)) {
- struct sock_xprt *transport = container_of(xprt,
- struct sock_xprt, xprt);
/* Reset TCP record info */
transport->tcp_offset = 0;
@@ -1459,6 +1460,8 @@ static void xs_tcp_state_change(struct sock *sk)
transport->tcp_flags =
TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID;
xprt->connect_cookie++;
+ clear_bit(XPRT_SOCK_CONNECTING, &transport->sock_state);
+ xprt_clear_connecting(xprt);
xprt_wake_pending_tasks(xprt, -EAGAIN);
}
@@ -1494,6 +1497,9 @@ static void xs_tcp_state_change(struct sock *sk)
smp_mb__after_atomic();
break;
case TCP_CLOSE:
+ if (test_and_clear_bit(XPRT_SOCK_CONNECTING,
+ &transport->sock_state))
+ xprt_clear_connecting(xprt);
xs_sock_mark_closed(xprt);
}
out:
@@ -2110,6 +2116,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
/* Tell the socket layer to start connecting... */
xprt->stat.connect_count++;
xprt->stat.connect_start = jiffies;
+ set_bit(XPRT_SOCK_CONNECTING, &transport->sock_state);
ret = kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK);
switch (ret) {
case 0:
@@ -2174,7 +2181,6 @@ static void xs_tcp_setup_socket(struct work_struct *work)
case -EINPROGRESS:
case -EALREADY:
xprt_unlock_connect(xprt, transport);
- xprt_clear_connecting(xprt);
return;
case -EINVAL:
/* Happens, for instance, if the user specified a link
@@ -2216,13 +2222,14 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task)
WARN_ON_ONCE(!xprt_lock_connect(xprt, task, transport));
- /* Start by resetting any existing state */
- xs_reset_transport(transport);
-
- if (transport->sock != NULL && !RPC_IS_SOFTCONN(task)) {
+ if (transport->sock != NULL) {
dprintk("RPC: xs_connect delayed xprt %p for %lu "
"seconds\n",
xprt, xprt->reestablish_timeout / HZ);
+
+ /* Start by resetting any existing state */
+ xs_reset_transport(transport);
+
queue_delayed_work(rpciod_workqueue,
&transport->connect_worker,
xprt->reestablish_timeout);
diff --git a/kernel/net/tipc/socket.c b/kernel/net/tipc/socket.c
index f485600c4..20cc6df07 100644
--- a/kernel/net/tipc/socket.c
+++ b/kernel/net/tipc/socket.c
@@ -2009,6 +2009,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 1);
if (res)
goto exit;
+ security_sk_clone(sock->sk, new_sock->sk);
new_sk = new_sock->sk;
new_tsock = tipc_sk(new_sk);