summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/atm/mpc.c2
-rw-r--r--net/bridge/br_multicast.c2
-rw-r--r--net/core/dev.c295
-rw-r--r--net/core/dev_ioctl.c7
-rw-r--r--net/core/ethtool.c81
-rw-r--r--net/core/filter.c8
-rw-r--r--net/core/flow_dissector.c115
-rw-r--r--net/core/netpoll.c7
-rw-r--r--net/core/pktgen.c28
-rw-r--r--net/core/rtnetlink.c66
-rw-r--r--net/core/secure_seq.c6
-rw-r--r--net/core/skbuff.c99
-rw-r--r--net/core/sock.c32
-rw-r--r--net/core/timestamping.c43
-rw-r--r--net/decnet/af_decnet.c3
-rw-r--r--net/decnet/dn_dev.c3
-rw-r--r--net/decnet/dn_timer.c3
-rw-r--r--net/dsa/Kconfig3
-rw-r--r--net/dsa/Makefile1
-rw-r--r--net/dsa/dsa.c48
-rw-r--r--net/dsa/dsa_priv.h16
-rw-r--r--net/dsa/slave.c165
-rw-r--r--net/dsa/tag_brcm.c173
-rw-r--r--net/dsa/tag_dsa.c8
-rw-r--r--net/dsa/tag_edsa.c8
-rw-r--r--net/dsa/tag_trailer.c8
-rw-r--r--net/ethernet/eth.c34
-rw-r--r--net/ipv4/fib_frontend.c14
-rw-r--r--net/ipv4/fib_semantics.c8
-rw-r--r--net/ipv4/gre_demux.c4
-rw-r--r--net/ipv4/gre_offload.c44
-rw-r--r--net/ipv4/igmp.c33
-rw-r--r--net/ipv4/inet_hashtables.c2
-rw-r--r--net/ipv4/ip_sockglue.c15
-rw-r--r--net/ipv4/ipconfig.c3
-rw-r--r--net/ipv4/netfilter/ipt_CLUSTERIP.c2
-rw-r--r--net/ipv4/route.c14
-rw-r--r--net/ipv4/syncookies.c2
-rw-r--r--net/ipv4/sysctl_net_ipv4.c10
-rw-r--r--net/ipv4/tcp_bic.c11
-rw-r--r--net/ipv4/tcp_cong.c5
-rw-r--r--net/ipv4/tcp_cubic.c18
-rw-r--r--net/ipv4/tcp_diag.c5
-rw-r--r--net/ipv4/tcp_highspeed.c145
-rw-r--r--net/ipv4/tcp_htcp.c6
-rw-r--r--net/ipv4/tcp_hybla.c1
-rw-r--r--net/ipv4/tcp_illinois.c3
-rw-r--r--net/ipv4/tcp_input.c31
-rw-r--r--net/ipv4/tcp_ipv4.c12
-rw-r--r--net/ipv4/tcp_minisocks.c2
-rw-r--r--net/ipv4/tcp_offload.c27
-rw-r--r--net/ipv4/tcp_output.c42
-rw-r--r--net/ipv4/tcp_probe.c6
-rw-r--r--net/ipv4/tcp_scalable.c2
-rw-r--r--net/ipv4/tcp_timer.c7
-rw-r--r--net/ipv4/tcp_vegas.c3
-rw-r--r--net/ipv4/tcp_veno.c1
-rw-r--r--net/ipv4/tcp_westwood.c7
-rw-r--r--net/ipv4/tcp_yeah.c9
-rw-r--r--net/ipv4/udp.c13
-rw-r--r--net/ipv4/udp_offload.c71
-rw-r--r--net/ipv6/addrconf.c12
-rw-r--r--net/ipv6/af_inet6.c12
-rw-r--r--net/ipv6/ah6.c21
-rw-r--r--net/ipv6/datagram.c23
-rw-r--r--net/ipv6/esp6.c15
-rw-r--r--net/ipv6/exthdrs.c2
-rw-r--r--net/ipv6/icmp.c10
-rw-r--r--net/ipv6/inet6_connection_sock.c6
-rw-r--r--net/ipv6/inet6_hashtables.c7
-rw-r--r--net/ipv6/ip6_flowlabel.c19
-rw-r--r--net/ipv6/ip6_icmp.c2
-rw-r--r--net/ipv6/ip6_input.c6
-rw-r--r--net/ipv6/ip6_offload.c2
-rw-r--r--net/ipv6/ip6_output.c21
-rw-r--r--net/ipv6/ip6_tunnel.c32
-rw-r--r--net/ipv6/ip6mr.c4
-rw-r--r--net/ipv6/ipcomp6.c6
-rw-r--r--net/ipv6/ipv6_sockglue.c26
-rw-r--r--net/ipv6/mcast.c125
-rw-r--r--net/ipv6/mip6.c10
-rw-r--r--net/ipv6/ndisc.c17
-rw-r--r--net/ipv6/output_core.c2
-rw-r--r--net/ipv6/proc.c2
-rw-r--r--net/ipv6/raw.c8
-rw-r--r--net/ipv6/reassembly.c12
-rw-r--r--net/ipv6/route.c22
-rw-r--r--net/ipv6/sit.c12
-rw-r--r--net/ipv6/syncookies.c2
-rw-r--r--net/ipv6/sysctl_net_ipv6.c10
-rw-r--r--net/ipv6/tcp_ipv6.c4
-rw-r--r--net/ipv6/tcpv6_offload.c26
-rw-r--r--net/ipv6/tunnel6.c4
-rw-r--r--net/ipv6/udp.c26
-rw-r--r--net/ipv6/udp_offload.c43
-rw-r--r--net/ipv6/xfrm6_input.c6
-rw-r--r--net/ipv6/xfrm6_output.c1
-rw-r--r--net/ipv6/xfrm6_policy.c22
-rw-r--r--net/ipv6/xfrm6_state.c14
-rw-r--r--net/ipv6/xfrm6_tunnel.c4
-rw-r--r--net/l2tp/l2tp_core.c4
-rw-r--r--net/netfilter/nf_conntrack_core.c4
-rw-r--r--net/netfilter/nf_conntrack_expect.c3
-rw-r--r--net/netfilter/nf_conntrack_netlink.c2
-rw-r--r--net/netfilter/nf_conntrack_standalone.c2
-rw-r--r--net/netfilter/nf_nat_core.c5
-rw-r--r--net/netfilter/xt_HMARK.c2
-rw-r--r--net/netfilter/xt_cluster.c3
-rw-r--r--net/netfilter/xt_hashlimit.c2
-rw-r--r--net/openvswitch/flow.c2
-rw-r--r--net/packet/af_packet.c12
-rw-r--r--net/rose/rose_link.c3
-rw-r--r--net/rxrpc/ar-error.c14
-rw-r--r--net/rxrpc/ar-input.c9
-rw-r--r--net/sched/act_police.c4
-rw-r--r--net/sched/sch_fq.c4
-rw-r--r--net/sched/sch_fq_codel.c3
-rw-r--r--net/sched/sch_generic.c25
-rw-r--r--net/sched/sch_htb.c6
-rw-r--r--net/sched/sch_tbf.c6
-rw-r--r--net/sched/sch_teql.c5
-rw-r--r--net/sctp/input.c8
-rw-r--r--net/tipc/Makefile2
-rw-r--r--net/tipc/bcast.c8
-rw-r--r--net/tipc/config.c4
-rw-r--r--net/tipc/core.c9
-rw-r--r--net/tipc/core.h6
-rw-r--r--net/tipc/link.c120
-rw-r--r--net/tipc/link.h7
-rw-r--r--net/tipc/msg.c38
-rw-r--r--net/tipc/msg.h5
-rw-r--r--net/tipc/name_distr.c139
-rw-r--r--net/tipc/name_distr.h1
-rw-r--r--net/tipc/name_table.c9
-rw-r--r--net/tipc/net.c3
-rw-r--r--net/tipc/node.c90
-rw-r--r--net/tipc/node.h7
-rw-r--r--net/tipc/port.c514
-rw-r--r--net/tipc/port.h190
-rw-r--r--net/tipc/ref.c266
-rw-r--r--net/tipc/ref.h48
-rw-r--r--net/tipc/socket.c884
-rw-r--r--net/tipc/socket.h55
-rw-r--r--net/tipc/subscr.c1
-rw-r--r--net/tipc/sysctl.c7
145 files changed, 2571 insertions, 2410 deletions
diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index e8e0e7a8a23..0e982222d42 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -599,7 +599,7 @@ static netdev_tx_t mpc_send_packet(struct sk_buff *skb,
}
non_ip:
- return mpc->old_ops->ndo_start_xmit(skb, dev);
+ return __netdev_start_xmit(mpc->old_ops, skb, dev, false);
}
static int atm_mpoa_vcc_attach(struct atm_vcc *vcc, void __user *arg)
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 7751c92c8c5..648d79ccf46 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1822,7 +1822,7 @@ static void br_multicast_query_expired(struct net_bridge *br,
if (query->startup_sent < br->multicast_startup_query_count)
query->startup_sent++;
- rcu_assign_pointer(querier, NULL);
+ RCU_INIT_POINTER(querier, NULL);
br_multicast_send_query(br, NULL, query);
spin_unlock(&br->multicast_lock);
}
diff --git a/net/core/dev.c b/net/core/dev.c
index ab9a16530c3..3c6a967e583 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2485,52 +2485,6 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
return 0;
}
-struct dev_gso_cb {
- void (*destructor)(struct sk_buff *skb);
-};
-
-#define DEV_GSO_CB(skb) ((struct dev_gso_cb *)(skb)->cb)
-
-static void dev_gso_skb_destructor(struct sk_buff *skb)
-{
- struct dev_gso_cb *cb;
-
- kfree_skb_list(skb->next);
- skb->next = NULL;
-
- cb = DEV_GSO_CB(skb);
- if (cb->destructor)
- cb->destructor(skb);
-}
-
-/**
- * dev_gso_segment - Perform emulated hardware segmentation on skb.
- * @skb: buffer to segment
- * @features: device features as applicable to this skb
- *
- * This function segments the given skb and stores the list of segments
- * in skb->next.
- */
-static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
-{
- struct sk_buff *segs;
-
- segs = skb_gso_segment(skb, features);
-
- /* Verifying header integrity only. */
- if (!segs)
- return 0;
-
- if (IS_ERR(segs))
- return PTR_ERR(segs);
-
- skb->next = segs;
- DEV_GSO_CB(skb)->destructor = skb->destructor;
- skb->destructor = dev_gso_skb_destructor;
-
- return 0;
-}
-
/* If MPLS offload request, verify we are testing hardware MPLS features
* instead of standard features for the netdev.
*/
@@ -2605,119 +2559,125 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
}
EXPORT_SYMBOL(netif_skb_features);
-int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
- struct netdev_queue *txq)
+static int xmit_one(struct sk_buff *skb, struct net_device *dev,
+ struct netdev_queue *txq, bool more)
{
- const struct net_device_ops *ops = dev->netdev_ops;
+ unsigned int len;
+ int rc;
+
+ if (!list_empty(&ptype_all))
+ dev_queue_xmit_nit(skb, dev);
+
+ len = skb->len;
+ trace_net_dev_start_xmit(skb, dev);
+ rc = netdev_start_xmit(skb, dev, txq, more);
+ trace_net_dev_xmit(skb, rc, dev, len);
+
+ return rc;
+}
+
+struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *dev,
+ struct netdev_queue *txq, int *ret)
+{
+ struct sk_buff *skb = first;
int rc = NETDEV_TX_OK;
- unsigned int skb_len;
- if (likely(!skb->next)) {
- netdev_features_t features;
+ while (skb) {
+ struct sk_buff *next = skb->next;
- /*
- * If device doesn't need skb->dst, release it right now while
- * its hot in this cpu cache
- */
- if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
- skb_dst_drop(skb);
+ skb->next = NULL;
+ rc = xmit_one(skb, dev, txq, next != NULL);
+ if (unlikely(!dev_xmit_complete(rc))) {
+ skb->next = next;
+ goto out;
+ }
- features = netif_skb_features(skb);
+ skb = next;
+ if (netif_xmit_stopped(txq) && skb) {
+ rc = NETDEV_TX_BUSY;
+ break;
+ }
+ }
- if (vlan_tx_tag_present(skb) &&
- !vlan_hw_offload_capable(features, skb->vlan_proto)) {
- skb = __vlan_put_tag(skb, skb->vlan_proto,
- vlan_tx_tag_get(skb));
- if (unlikely(!skb))
- goto out;
+out:
+ *ret = rc;
+ return skb;
+}
+struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, netdev_features_t features)
+{
+ if (vlan_tx_tag_present(skb) &&
+ !vlan_hw_offload_capable(features, skb->vlan_proto)) {
+ skb = __vlan_put_tag(skb, skb->vlan_proto,
+ vlan_tx_tag_get(skb));
+ if (skb)
skb->vlan_tci = 0;
- }
+ }
+ return skb;
+}
- /* If encapsulation offload request, verify we are testing
- * hardware encapsulation features instead of standard
- * features for the netdev
- */
- if (skb->encapsulation)
- features &= dev->hw_enc_features;
+struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev)
+{
+ netdev_features_t features;
- if (netif_needs_gso(skb, features)) {
- if (unlikely(dev_gso_segment(skb, features)))
- goto out_kfree_skb;
- if (skb->next)
- goto gso;
- } else {
- if (skb_needs_linearize(skb, features) &&
- __skb_linearize(skb))
- goto out_kfree_skb;
+ if (skb->next)
+ return skb;
- /* If packet is not checksummed and device does not
- * support checksumming for this protocol, complete
- * checksumming here.
- */
- if (skb->ip_summed == CHECKSUM_PARTIAL) {
- if (skb->encapsulation)
- skb_set_inner_transport_header(skb,
- skb_checksum_start_offset(skb));
- else
- skb_set_transport_header(skb,
- skb_checksum_start_offset(skb));
- if (!(features & NETIF_F_ALL_CSUM) &&
- skb_checksum_help(skb))
- goto out_kfree_skb;
- }
- }
+ /* If device doesn't need skb->dst, release it right now while
+ * its hot in this cpu cache
+ */
+ if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
+ skb_dst_drop(skb);
- if (!list_empty(&ptype_all))
- dev_queue_xmit_nit(skb, dev);
+ features = netif_skb_features(skb);
+ skb = validate_xmit_vlan(skb, features);
+ if (unlikely(!skb))
+ goto out_null;
- skb_len = skb->len;
- trace_net_dev_start_xmit(skb, dev);
- rc = ops->ndo_start_xmit(skb, dev);
- trace_net_dev_xmit(skb, rc, dev, skb_len);
- if (rc == NETDEV_TX_OK)
- txq_trans_update(txq);
- return rc;
- }
+ /* If encapsulation offload request, verify we are testing
+ * hardware encapsulation features instead of standard
+ * features for the netdev
+ */
+ if (skb->encapsulation)
+ features &= dev->hw_enc_features;
-gso:
- do {
- struct sk_buff *nskb = skb->next;
+ if (netif_needs_gso(skb, features)) {
+ struct sk_buff *segs;
- skb->next = nskb->next;
- nskb->next = NULL;
+ segs = skb_gso_segment(skb, features);
+ kfree_skb(skb);
+ if (IS_ERR(segs))
+ segs = NULL;
+ skb = segs;
+ } else {
+ if (skb_needs_linearize(skb, features) &&
+ __skb_linearize(skb))
+ goto out_kfree_skb;
- if (!list_empty(&ptype_all))
- dev_queue_xmit_nit(nskb, dev);
-
- skb_len = nskb->len;
- trace_net_dev_start_xmit(nskb, dev);
- rc = ops->ndo_start_xmit(nskb, dev);
- trace_net_dev_xmit(nskb, rc, dev, skb_len);
- if (unlikely(rc != NETDEV_TX_OK)) {
- if (rc & ~NETDEV_TX_MASK)
- goto out_kfree_gso_skb;
- nskb->next = skb->next;
- skb->next = nskb;
- return rc;
+ /* If packet is not checksummed and device does not
+ * support checksumming for this protocol, complete
+ * checksumming here.
+ */
+ if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ if (skb->encapsulation)
+ skb_set_inner_transport_header(skb,
+ skb_checksum_start_offset(skb));
+ else
+ skb_set_transport_header(skb,
+ skb_checksum_start_offset(skb));
+ if (!(features & NETIF_F_ALL_CSUM) &&
+ skb_checksum_help(skb))
+ goto out_kfree_skb;
}
- txq_trans_update(txq);
- if (unlikely(netif_xmit_stopped(txq) && skb->next))
- return NETDEV_TX_BUSY;
- } while (skb->next);
-
-out_kfree_gso_skb:
- if (likely(skb->next == NULL)) {
- skb->destructor = DEV_GSO_CB(skb)->destructor;
- consume_skb(skb);
- return rc;
}
+
+ return skb;
+
out_kfree_skb:
kfree_skb(skb);
-out:
- return rc;
+out_null:
+ return NULL;
}
-EXPORT_SYMBOL_GPL(dev_hard_start_xmit);
static void qdisc_pkt_len_init(struct sk_buff *skb)
{
@@ -2785,7 +2745,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
qdisc_bstats_update(q, skb);
- if (sch_direct_xmit(skb, q, dev, txq, root_lock)) {
+ skb = validate_xmit_skb(skb, dev);
+ if (skb && sch_direct_xmit(skb, q, dev, txq, root_lock)) {
if (unlikely(contended)) {
spin_unlock(&q->busylock);
contended = false;
@@ -2925,11 +2886,15 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT)
goto recursion_alert;
+ skb = validate_xmit_skb(skb, dev);
+ if (!skb)
+ goto drop;
+
HARD_TX_LOCK(dev, txq, cpu);
if (!netif_xmit_stopped(txq)) {
__this_cpu_inc(xmit_recursion);
- rc = dev_hard_start_xmit(skb, dev, txq);
+ skb = dev_hard_start_xmit(skb, dev, txq, &rc);
__this_cpu_dec(xmit_recursion);
if (dev_xmit_complete(rc)) {
HARD_TX_UNLOCK(dev, txq);
@@ -2950,10 +2915,11 @@ recursion_alert:
}
rc = -ENETDOWN;
+drop:
rcu_read_unlock_bh();
atomic_long_inc(&dev->tx_dropped);
- kfree_skb(skb);
+ kfree_skb_list(skb);
return rc;
out:
rcu_read_unlock_bh();
@@ -3130,8 +3096,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
}
if (map) {
- tcpu = map->cpus[((u64) hash * map->len) >> 32];
-
+ tcpu = map->cpus[reciprocal_scale(hash, map->len)];
if (cpu_online(tcpu)) {
cpu = tcpu;
goto done;
@@ -3965,11 +3930,10 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
if (!(skb->dev->features & NETIF_F_GRO))
goto normal;
- if (skb_is_gso(skb) || skb_has_frag_list(skb))
+ if (skb_is_gso(skb) || skb_has_frag_list(skb) || skb->csum_bad)
goto normal;
gro_list_prepare(napi, skb);
- NAPI_GRO_CB(skb)->csum = skb->csum; /* Needed for CHECKSUM_COMPLETE */
rcu_read_lock();
list_for_each_entry_rcu(ptype, head, list) {
@@ -3983,6 +3947,22 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
NAPI_GRO_CB(skb)->free = 0;
NAPI_GRO_CB(skb)->udp_mark = 0;
+ /* Setup for GRO checksum validation */
+ switch (skb->ip_summed) {
+ case CHECKSUM_COMPLETE:
+ NAPI_GRO_CB(skb)->csum = skb->csum;
+ NAPI_GRO_CB(skb)->csum_valid = 1;
+ NAPI_GRO_CB(skb)->csum_cnt = 0;
+ break;
+ case CHECKSUM_UNNECESSARY:
+ NAPI_GRO_CB(skb)->csum_cnt = skb->csum_level + 1;
+ NAPI_GRO_CB(skb)->csum_valid = 0;
+ break;
+ default:
+ NAPI_GRO_CB(skb)->csum_cnt = 0;
+ NAPI_GRO_CB(skb)->csum_valid = 0;
+ }
+
pp = ptype->callbacks.gro_receive(&napi->gro_list, skb);
break;
}
@@ -4212,6 +4192,31 @@ gro_result_t napi_gro_frags(struct napi_struct *napi)
}
EXPORT_SYMBOL(napi_gro_frags);
+/* Compute the checksum from gro_offset and return the folded value
+ * after adding in any pseudo checksum.
+ */
+__sum16 __skb_gro_checksum_complete(struct sk_buff *skb)
+{
+ __wsum wsum;
+ __sum16 sum;
+
+ wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), 0);
+
+ /* NAPI_GRO_CB(skb)->csum holds pseudo checksum */
+ sum = csum_fold(csum_add(NAPI_GRO_CB(skb)->csum, wsum));
+ if (likely(!sum)) {
+ if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+ !skb->csum_complete_sw)
+ netdev_rx_csum_fault(skb->dev);
+ }
+
+ NAPI_GRO_CB(skb)->csum = wsum;
+ NAPI_GRO_CB(skb)->csum_valid = 1;
+
+ return sum;
+}
+EXPORT_SYMBOL(__skb_gro_checksum_complete);
+
/*
* net_rps_action_and_irq_enable sends any pending IPI's for rps.
* Note: called with local irq disabled, but exits with local irq enabled.
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index cf999e09bcd..72e899a3efd 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -365,11 +365,8 @@ void dev_load(struct net *net, const char *name)
no_module = !dev;
if (no_module && capable(CAP_NET_ADMIN))
no_module = request_module("netdev-%s", name);
- if (no_module && capable(CAP_SYS_MODULE)) {
- if (!request_module("%s", name))
- pr_warn("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n",
- name);
- }
+ if (no_module && capable(CAP_SYS_MODULE))
+ request_module("%s", name);
}
EXPORT_SYMBOL(dev_load);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 17cb912793f..27e61b88652 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1621,6 +1621,80 @@ static int ethtool_get_module_eeprom(struct net_device *dev,
modinfo.eeprom_len);
}
+static int ethtool_tunable_valid(const struct ethtool_tunable *tuna)
+{
+ switch (tuna->id) {
+ case ETHTOOL_RX_COPYBREAK:
+ if (tuna->len != sizeof(u32) ||
+ tuna->type_id != ETHTOOL_TUNABLE_U32)
+ return -EINVAL;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int ethtool_get_tunable(struct net_device *dev, void __user *useraddr)
+{
+ int ret;
+ struct ethtool_tunable tuna;
+ const struct ethtool_ops *ops = dev->ethtool_ops;
+ void *data;
+
+ if (!ops->get_tunable)
+ return -EOPNOTSUPP;
+ if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
+ return -EFAULT;
+ ret = ethtool_tunable_valid(&tuna);
+ if (ret)
+ return ret;
+ data = kmalloc(tuna.len, GFP_USER);
+ if (!data)
+ return -ENOMEM;
+ ret = ops->get_tunable(dev, &tuna, data);
+ if (ret)
+ goto out;
+ useraddr += sizeof(tuna);
+ ret = -EFAULT;
+ if (copy_to_user(useraddr, data, tuna.len))
+ goto out;
+ ret = 0;
+
+out:
+ kfree(data);
+ return ret;
+}
+
+static int ethtool_set_tunable(struct net_device *dev, void __user *useraddr)
+{
+ int ret;
+ struct ethtool_tunable tuna;
+ const struct ethtool_ops *ops = dev->ethtool_ops;
+ void *data;
+
+ if (!ops->set_tunable)
+ return -EOPNOTSUPP;
+ if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
+ return -EFAULT;
+ ret = ethtool_tunable_valid(&tuna);
+ if (ret)
+ return ret;
+ data = kmalloc(tuna.len, GFP_USER);
+ if (!data)
+ return -ENOMEM;
+ useraddr += sizeof(tuna);
+ ret = -EFAULT;
+ if (copy_from_user(data, useraddr, tuna.len))
+ goto out;
+ ret = ops->set_tunable(dev, &tuna, data);
+
+out:
+ kfree(data);
+ return ret;
+}
+
/* The main entry point in this file. Called from net/core/dev_ioctl.c */
int dev_ethtool(struct net *net, struct ifreq *ifr)
@@ -1670,6 +1744,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_GCHANNELS:
case ETHTOOL_GET_TS_INFO:
case ETHTOOL_GEEE:
+ case ETHTOOL_GTUNABLE:
break;
default:
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
@@ -1857,6 +1932,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_GMODULEEEPROM:
rc = ethtool_get_module_eeprom(dev, useraddr);
break;
+ case ETHTOOL_GTUNABLE:
+ rc = ethtool_get_tunable(dev, useraddr);
+ break;
+ case ETHTOOL_STUNABLE:
+ rc = ethtool_set_tunable(dev, useraddr);
+ break;
default:
rc = -EOPNOTSUPP;
}
diff --git a/net/core/filter.c b/net/core/filter.c
index d814b8a89d0..fa5b7d0f77a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -113,7 +113,7 @@ static unsigned int pkt_type_offset(void)
static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
{
- return __skb_get_poff((struct sk_buff *)(unsigned long) ctx);
+ return skb_get_poff((struct sk_buff *)(unsigned long) ctx);
}
static u64 __skb_get_nlattr(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
@@ -933,7 +933,7 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
/* Expand fp for appending the new filter representation. */
old_fp = fp;
- fp = krealloc(old_fp, bpf_prog_size(new_len), GFP_KERNEL);
+ fp = bpf_prog_realloc(old_fp, bpf_prog_size(new_len), 0);
if (!fp) {
/* The old_fp is still around in case we couldn't
* allocate new memory, so uncharge on that one.
@@ -1013,7 +1013,7 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog)
if (fprog->filter == NULL)
return -EINVAL;
- fp = kmalloc(bpf_prog_size(fprog->len), GFP_KERNEL);
+ fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0);
if (!fp)
return -ENOMEM;
@@ -1069,7 +1069,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
if (fprog->filter == NULL)
return -EINVAL;
- prog = kmalloc(bpf_fsize, GFP_KERNEL);
+ prog = bpf_prog_alloc(bpf_fsize, 0);
if (!prog)
return -ENOMEM;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 5f362c1d033..8560dea5880 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -13,6 +13,7 @@
#include <linux/if_pppox.h>
#include <linux/ppp_defs.h>
#include <net/flow_keys.h>
+#include <scsi/fc/fc_fcoe.h>
/* copy saddr & daddr, possibly using 64bit load/store
* Equivalent to : flow->src = iph->saddr;
@@ -26,36 +27,61 @@ static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *i
}
/**
- * skb_flow_get_ports - extract the upper layer ports and return them
- * @skb: buffer to extract the ports from
+ * __skb_flow_get_ports - extract the upper layer ports and return them
+ * @skb: sk_buff to extract the ports from
* @thoff: transport header offset
* @ip_proto: protocol for which to get port offset
+ * @data: raw buffer pointer to the packet, if NULL use skb->data
+ * @hlen: packet header length, if @data is NULL use skb_headlen(skb)
*
* The function will try to retrieve the ports at offset thoff + poff where poff
* is the protocol port offset returned from proto_ports_offset
*/
-__be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto)
+__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
+ void *data, int hlen)
{
int poff = proto_ports_offset(ip_proto);
+ if (!data) {
+ data = skb->data;
+ hlen = skb_headlen(skb);
+ }
+
if (poff >= 0) {
__be32 *ports, _ports;
- ports = skb_header_pointer(skb, thoff + poff,
- sizeof(_ports), &_ports);
+ ports = __skb_header_pointer(skb, thoff + poff,
+ sizeof(_ports), data, hlen, &_ports);
if (ports)
return *ports;
}
return 0;
}
-EXPORT_SYMBOL(skb_flow_get_ports);
+EXPORT_SYMBOL(__skb_flow_get_ports);
-bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
+/**
+ * __skb_flow_dissect - extract the flow_keys struct and return it
+ * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
+ * @data: raw buffer pointer to the packet, if NULL use skb->data
+ * @proto: protocol for which to get the flow, if @data is NULL use skb->protocol
+ * @nhoff: network header offset, if @data is NULL use skb_network_offset(skb)
+ * @hlen: packet header length, if @data is NULL use skb_headlen(skb)
+ *
+ * The function will try to retrieve the struct flow_keys from either the skbuff
+ * or a raw buffer specified by the rest parameters
+ */
+bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
+ void *data, __be16 proto, int nhoff, int hlen)
{
- int nhoff = skb_network_offset(skb);
u8 ip_proto;
- __be16 proto = skb->protocol;
+
+ if (!data) {
+ data = skb->data;
+ proto = skb->protocol;
+ nhoff = skb_network_offset(skb);
+ hlen = skb_headlen(skb);
+ }
memset(flow, 0, sizeof(*flow));
@@ -65,7 +91,7 @@ again:
const struct iphdr *iph;
struct iphdr _iph;
ip:
- iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
+ iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
if (!iph || iph->ihl < 5)
return false;
nhoff += iph->ihl * 4;
@@ -83,7 +109,7 @@ ip:
__be32 flow_label;
ipv6:
- iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
+ iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
if (!iph)
return false;
@@ -92,6 +118,13 @@ ipv6:
flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr);
nhoff += sizeof(struct ipv6hdr);
+ /* skip the flow label processing if skb is NULL. The
+ * assumption here is that if there is no skb we are not
+ * looking for flow info as much as we are length.
+ */
+ if (!skb)
+ break;
+
flow_label = ip6_flowlabel(iph);
if (flow_label) {
/* Awesome, IPv6 packet has a flow label so we can
@@ -113,7 +146,7 @@ ipv6:
const struct vlan_hdr *vlan;
struct vlan_hdr _vlan;
- vlan = skb_header_pointer(skb, nhoff, sizeof(_vlan), &_vlan);
+ vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), data, hlen, &_vlan);
if (!vlan)
return false;
@@ -126,7 +159,7 @@ ipv6:
struct pppoe_hdr hdr;
__be16 proto;
} *hdr, _hdr;
- hdr = skb_header_pointer(skb, nhoff, sizeof(_hdr), &_hdr);
+ hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
if (!hdr)
return false;
proto = hdr->proto;
@@ -140,6 +173,9 @@ ipv6:
return false;
}
}
+ case htons(ETH_P_FCOE):
+ flow->thoff = (u16)(nhoff + FCOE_HEADER_LEN);
+ /* fall through */
default:
return false;
}
@@ -151,7 +187,7 @@ ipv6:
__be16 proto;
} *hdr, _hdr;
- hdr = skb_header_pointer(skb, nhoff, sizeof(_hdr), &_hdr);
+ hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
if (!hdr)
return false;
/*
@@ -171,8 +207,9 @@ ipv6:
const struct ethhdr *eth;
struct ethhdr _eth;
- eth = skb_header_pointer(skb, nhoff,
- sizeof(_eth), &_eth);
+ eth = __skb_header_pointer(skb, nhoff,
+ sizeof(_eth),
+ data, hlen, &_eth);
if (!eth)
return false;
proto = eth->h_proto;
@@ -194,12 +231,12 @@ ipv6:
flow->n_proto = proto;
flow->ip_proto = ip_proto;
- flow->ports = skb_flow_get_ports(skb, nhoff, ip_proto);
+ flow->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, data, hlen);
flow->thoff = (u16) nhoff;
return true;
}
-EXPORT_SYMBOL(skb_flow_dissect);
+EXPORT_SYMBOL(__skb_flow_dissect);
static u32 hashrnd __read_mostly;
static __always_inline void __flow_hash_secret_init(void)
@@ -286,30 +323,22 @@ u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb,
qcount = dev->tc_to_txq[tc].count;
}
- return (u16) (((u64)skb_get_hash(skb) * qcount) >> 32) + qoffset;
+ return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset;
}
EXPORT_SYMBOL(__skb_tx_hash);
-/* __skb_get_poff() returns the offset to the payload as far as it could
- * be dissected. The main user is currently BPF, so that we can dynamically
- * truncate packets without needing to push actual payload to the user
- * space and can analyze headers only, instead.
- */
-u32 __skb_get_poff(const struct sk_buff *skb)
+u32 __skb_get_poff(const struct sk_buff *skb, void *data,
+ const struct flow_keys *keys, int hlen)
{
- struct flow_keys keys;
- u32 poff = 0;
-
- if (!skb_flow_dissect(skb, &keys))
- return 0;
+ u32 poff = keys->thoff;
- poff += keys.thoff;
- switch (keys.ip_proto) {
+ switch (keys->ip_proto) {
case IPPROTO_TCP: {
const struct tcphdr *tcph;
struct tcphdr _tcph;
- tcph = skb_header_pointer(skb, poff, sizeof(_tcph), &_tcph);
+ tcph = __skb_header_pointer(skb, poff, sizeof(_tcph),
+ data, hlen, &_tcph);
if (!tcph)
return poff;
@@ -343,6 +372,21 @@ u32 __skb_get_poff(const struct sk_buff *skb)
return poff;
}
+/* skb_get_poff() returns the offset to the payload as far as it could
+ * be dissected. The main user is currently BPF, so that we can dynamically
+ * truncate packets without needing to push actual payload to the user
+ * space and can analyze headers only, instead.
+ */
+u32 skb_get_poff(const struct sk_buff *skb)
+{
+ struct flow_keys keys;
+
+ if (!skb_flow_dissect(skb, &keys))
+ return 0;
+
+ return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb));
+}
+
static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
{
#ifdef CONFIG_XPS
@@ -359,9 +403,8 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
if (map->len == 1)
queue_index = map->queues[0];
else
- queue_index = map->queues[
- ((u64)skb_get_hash(skb) * map->len) >> 32];
-
+ queue_index = map->queues[reciprocal_scale(skb_get_hash(skb),
+ map->len)];
if (unlikely(queue_index >= dev->real_num_tx_queues))
queue_index = -1;
}
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 907fb5e36c0..e6645b4f330 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -72,7 +72,6 @@ module_param(carrier_timeout, uint, 0644);
static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq)
{
- const struct net_device_ops *ops = dev->netdev_ops;
int status = NETDEV_TX_OK;
netdev_features_t features;
@@ -92,9 +91,7 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
skb->vlan_tci = 0;
}
- status = ops->ndo_start_xmit(skb, dev);
- if (status == NETDEV_TX_OK)
- txq_trans_update(txq);
+ status = netdev_start_xmit(skb, dev, txq, false);
out:
return status;
@@ -116,7 +113,7 @@ static void queue_process(struct work_struct *work)
continue;
}
- txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
+ txq = skb_get_tx_queue(dev, skb);
local_irq_save(flags);
HARD_TX_LOCK(dev, txq, smp_processor_id());
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 8b849ddfef2..21cb4839bc9 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -202,6 +202,7 @@
#define F_QUEUE_MAP_CPU (1<<14) /* queue map mirrors smp_processor_id() */
#define F_NODE (1<<15) /* Node memory alloc*/
#define F_UDPCSUM (1<<16) /* Include UDP checksum */
+#define F_NO_TIMESTAMP (1<<17) /* Don't timestamp packets (default TS) */
/* Thread control flag bits */
#define T_STOP (1<<0) /* Stop run */
@@ -638,6 +639,9 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
if (pkt_dev->flags & F_UDPCSUM)
seq_puts(seq, "UDPCSUM ");
+ if (pkt_dev->flags & F_NO_TIMESTAMP)
+ seq_puts(seq, "NO_TIMESTAMP ");
+
if (pkt_dev->flags & F_MPLS_RND)
seq_puts(seq, "MPLS_RND ");
@@ -1243,6 +1247,9 @@ static ssize_t pktgen_if_write(struct file *file,
else if (strcmp(f, "!UDPCSUM") == 0)
pkt_dev->flags &= ~F_UDPCSUM;
+ else if (strcmp(f, "NO_TIMESTAMP") == 0)
+ pkt_dev->flags |= F_NO_TIMESTAMP;
+
else {
sprintf(pg_result,
"Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s",
@@ -1251,6 +1258,7 @@ static ssize_t pktgen_if_write(struct file *file,
"MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, "
"MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, "
"QUEUE_MAP_RND, QUEUE_MAP_CPU, UDPCSUM, "
+ "NO_TIMESTAMP, "
#ifdef CONFIG_XFRM
"IPSEC, "
#endif
@@ -2685,9 +2693,14 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb,
pgh->pgh_magic = htonl(PKTGEN_MAGIC);
pgh->seq_num = htonl(pkt_dev->seq_num);
- do_gettimeofday(&timestamp);
- pgh->tv_sec = htonl(timestamp.tv_sec);
- pgh->tv_usec = htonl(timestamp.tv_usec);
+ if (pkt_dev->flags & F_NO_TIMESTAMP) {
+ pgh->tv_sec = 0;
+ pgh->tv_usec = 0;
+ } else {
+ do_gettimeofday(&timestamp);
+ pgh->tv_sec = htonl(timestamp.tv_sec);
+ pgh->tv_usec = htonl(timestamp.tv_usec);
+ }
}
static struct sk_buff *pktgen_alloc_skb(struct net_device *dev,
@@ -3285,10 +3298,7 @@ static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev)
static void pktgen_xmit(struct pktgen_dev *pkt_dev)
{
struct net_device *odev = pkt_dev->odev;
- netdev_tx_t (*xmit)(struct sk_buff *, struct net_device *)
- = odev->netdev_ops->ndo_start_xmit;
struct netdev_queue *txq;
- u16 queue_map;
int ret;
/* If device is offline, then don't send */
@@ -3326,8 +3336,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
if (pkt_dev->delay && pkt_dev->last_ok)
spin(pkt_dev, pkt_dev->next_tx);
- queue_map = skb_get_queue_mapping(pkt_dev->skb);
- txq = netdev_get_tx_queue(odev, queue_map);
+ txq = skb_get_tx_queue(odev, pkt_dev->skb);
local_bh_disable();
@@ -3339,11 +3348,10 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
goto unlock;
}
atomic_inc(&(pkt_dev->skb->users));
- ret = (*xmit)(pkt_dev->skb, odev);
+ ret = netdev_start_xmit(pkt_dev->skb, odev, txq, false);
switch (ret) {
case NETDEV_TX_OK:
- txq_trans_update(txq);
pkt_dev->last_ok = 1;
pkt_dev->sofar++;
pkt_dev->seq_num++;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f0493e3b747..a6882686ca3 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1481,9 +1481,12 @@ static int do_set_master(struct net_device *dev, int ifindex)
return 0;
}
+#define DO_SETLINK_MODIFIED 0x01
+/* notify flag means notify + modified. */
+#define DO_SETLINK_NOTIFY 0x03
static int do_setlink(const struct sk_buff *skb,
struct net_device *dev, struct ifinfomsg *ifm,
- struct nlattr **tb, char *ifname, int modified)
+ struct nlattr **tb, char *ifname, int status)
{
const struct net_device_ops *ops = dev->netdev_ops;
int err;
@@ -1502,7 +1505,7 @@ static int do_setlink(const struct sk_buff *skb,
put_net(net);
if (err)
goto errout;
- modified = 1;
+ status |= DO_SETLINK_MODIFIED;
}
if (tb[IFLA_MAP]) {
@@ -1531,7 +1534,7 @@ static int do_setlink(const struct sk_buff *skb,
if (err < 0)
goto errout;
- modified = 1;
+ status |= DO_SETLINK_NOTIFY;
}
if (tb[IFLA_ADDRESS]) {
@@ -1551,19 +1554,19 @@ static int do_setlink(const struct sk_buff *skb,
kfree(sa);
if (err)
goto errout;
- modified = 1;
+ status |= DO_SETLINK_MODIFIED;
}
if (tb[IFLA_MTU]) {
err = dev_set_mtu(dev, nla_get_u32(tb[IFLA_MTU]));
if (err < 0)
goto errout;
- modified = 1;
+ status |= DO_SETLINK_MODIFIED;
}
if (tb[IFLA_GROUP]) {
dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP]));
- modified = 1;
+ status |= DO_SETLINK_NOTIFY;
}
/*
@@ -1575,7 +1578,7 @@ static int do_setlink(const struct sk_buff *skb,
err = dev_change_name(dev, ifname);
if (err < 0)
goto errout;
- modified = 1;
+ status |= DO_SETLINK_MODIFIED;
}
if (tb[IFLA_IFALIAS]) {
@@ -1583,7 +1586,7 @@ static int do_setlink(const struct sk_buff *skb,
nla_len(tb[IFLA_IFALIAS]));
if (err < 0)
goto errout;
- modified = 1;
+ status |= DO_SETLINK_NOTIFY;
}
if (tb[IFLA_BROADCAST]) {
@@ -1601,25 +1604,35 @@ static int do_setlink(const struct sk_buff *skb,
err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]));
if (err)
goto errout;
- modified = 1;
+ status |= DO_SETLINK_MODIFIED;
}
if (tb[IFLA_CARRIER]) {
err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER]));
if (err)
goto errout;
- modified = 1;
+ status |= DO_SETLINK_MODIFIED;
}
- if (tb[IFLA_TXQLEN])
- dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]);
+ if (tb[IFLA_TXQLEN]) {
+ unsigned long value = nla_get_u32(tb[IFLA_TXQLEN]);
+
+ if (dev->tx_queue_len ^ value)
+ status |= DO_SETLINK_NOTIFY;
+
+ dev->tx_queue_len = value;
+ }
if (tb[IFLA_OPERSTATE])
set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));
if (tb[IFLA_LINKMODE]) {
+ unsigned char value = nla_get_u8(tb[IFLA_LINKMODE]);
+
write_lock_bh(&dev_base_lock);
- dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]);
+ if (dev->link_mode ^ value)
+ status |= DO_SETLINK_NOTIFY;
+ dev->link_mode = value;
write_unlock_bh(&dev_base_lock);
}
@@ -1634,7 +1647,7 @@ static int do_setlink(const struct sk_buff *skb,
err = do_setvfinfo(dev, attr);
if (err < 0)
goto errout;
- modified = 1;
+ status |= DO_SETLINK_NOTIFY;
}
}
err = 0;
@@ -1664,7 +1677,7 @@ static int do_setlink(const struct sk_buff *skb,
err = ops->ndo_set_vf_port(dev, vf, port);
if (err < 0)
goto errout;
- modified = 1;
+ status |= DO_SETLINK_NOTIFY;
}
}
err = 0;
@@ -1682,7 +1695,7 @@ static int do_setlink(const struct sk_buff *skb,
err = ops->ndo_set_vf_port(dev, PORT_SELF_VF, port);
if (err < 0)
goto errout;
- modified = 1;
+ status |= DO_SETLINK_NOTIFY;
}
if (tb[IFLA_AF_SPEC]) {
@@ -1699,15 +1712,20 @@ static int do_setlink(const struct sk_buff *skb,
if (err < 0)
goto errout;
- modified = 1;
+ status |= DO_SETLINK_NOTIFY;
}
}
err = 0;
errout:
- if (err < 0 && modified)
- net_warn_ratelimited("A link change request failed with some changes committed already. Interface %s may have been left with an inconsistent configuration, please check.\n",
- dev->name);
+ if (status & DO_SETLINK_MODIFIED) {
+ if (status & DO_SETLINK_NOTIFY)
+ netdev_state_change(dev);
+
+ if (err < 0)
+ net_warn_ratelimited("A link change request failed with some changes committed already. Interface %s may have been left with an inconsistent configuration, please check.\n",
+ dev->name);
+ }
return err;
}
@@ -1989,7 +2007,7 @@ replay:
}
if (dev) {
- int modified = 0;
+ int status = 0;
if (nlh->nlmsg_flags & NLM_F_EXCL)
return -EEXIST;
@@ -2004,7 +2022,7 @@ replay:
err = ops->changelink(dev, tb, data);
if (err < 0)
return err;
- modified = 1;
+ status |= DO_SETLINK_NOTIFY;
}
if (linkinfo[IFLA_INFO_SLAVE_DATA]) {
@@ -2015,10 +2033,10 @@ replay:
tb, slave_data);
if (err < 0)
return err;
- modified = 1;
+ status |= DO_SETLINK_NOTIFY;
}
- return do_setlink(skb, dev, ifm, tb, ifname, modified);
+ return do_setlink(skb, dev, ifm, tb, ifname, status);
}
if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index ba71212f025..51dd3193a33 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -35,7 +35,7 @@ static u32 seq_scale(u32 seq)
* overlaps less than one time per MSL (2 minutes).
* Choosing a clock of 64 ns period is OK. (period of 274 s)
*/
- return seq + (ktime_to_ns(ktime_get_real()) >> 6);
+ return seq + (ktime_get_real_ns() >> 6);
}
#endif
@@ -135,7 +135,7 @@ u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
md5_transform(hash, net_secret);
seq = hash[0] | (((u64)hash[1]) << 32);
- seq += ktime_to_ns(ktime_get_real());
+ seq += ktime_get_real_ns();
seq &= (1ull << 48) - 1;
return seq;
@@ -163,7 +163,7 @@ u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
md5_transform(hash, secret);
seq = hash[0] | (((u64)hash[1]) << 32);
- seq += ktime_to_ns(ktime_get_real());
+ seq += ktime_get_real_ns();
seq &= (1ull << 48) - 1;
return seq;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index da1378a3e2c..a18dfb02d94 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3491,32 +3491,53 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(sock_queue_err_skb);
-void __skb_tstamp_tx(struct sk_buff *orig_skb,
- struct skb_shared_hwtstamps *hwtstamps,
- struct sock *sk, int tstype)
+struct sk_buff *sock_dequeue_err_skb(struct sock *sk)
{
- struct sock_exterr_skb *serr;
- struct sk_buff *skb;
- int err;
+ struct sk_buff_head *q = &sk->sk_error_queue;
+ struct sk_buff *skb, *skb_next;
+ int err = 0;
- if (!sk)
- return;
+ spin_lock_bh(&q->lock);
+ skb = __skb_dequeue(q);
+ if (skb && (skb_next = skb_peek(q)))
+ err = SKB_EXT_ERR(skb_next)->ee.ee_errno;
+ spin_unlock_bh(&q->lock);
- if (hwtstamps) {
- *skb_hwtstamps(orig_skb) =
- *hwtstamps;
- } else {
- /*
- * no hardware time stamps available,
- * so keep the shared tx_flags and only
- * store software time stamp
- */
- orig_skb->tstamp = ktime_get_real();
+ sk->sk_err = err;
+ if (err)
+ sk->sk_error_report(sk);
+
+ return skb;
+}
+EXPORT_SYMBOL(sock_dequeue_err_skb);
+
+struct sk_buff *skb_clone_sk(struct sk_buff *skb)
+{
+ struct sock *sk = skb->sk;
+ struct sk_buff *clone;
+
+ if (!sk || !atomic_inc_not_zero(&sk->sk_refcnt))
+ return NULL;
+
+ clone = skb_clone(skb, GFP_ATOMIC);
+ if (!clone) {
+ sock_put(sk);
+ return NULL;
}
- skb = skb_clone(orig_skb, GFP_ATOMIC);
- if (!skb)
- return;
+ clone->sk = sk;
+ clone->destructor = sock_efree;
+
+ return clone;
+}
+EXPORT_SYMBOL(skb_clone_sk);
+
+static void __skb_complete_tx_timestamp(struct sk_buff *skb,
+ struct sock *sk,
+ int tstype)
+{
+ struct sock_exterr_skb *serr;
+ int err;
serr = SKB_EXT_ERR(skb);
memset(serr, 0, sizeof(*serr));
@@ -3534,6 +3555,42 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
if (err)
kfree_skb(skb);
}
+
+void skb_complete_tx_timestamp(struct sk_buff *skb,
+ struct skb_shared_hwtstamps *hwtstamps)
+{
+ struct sock *sk = skb->sk;
+
+ /* take a reference to prevent skb_orphan() from freeing the socket */
+ sock_hold(sk);
+
+ *skb_hwtstamps(skb) = *hwtstamps;
+ __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
+
+ sock_put(sk);
+}
+EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
+
+void __skb_tstamp_tx(struct sk_buff *orig_skb,
+ struct skb_shared_hwtstamps *hwtstamps,
+ struct sock *sk, int tstype)
+{
+ struct sk_buff *skb;
+
+ if (!sk)
+ return;
+
+ if (hwtstamps)
+ *skb_hwtstamps(orig_skb) = *hwtstamps;
+ else
+ orig_skb->tstamp = ktime_get_real();
+
+ skb = skb_clone(orig_skb, GFP_ATOMIC);
+ if (!skb)
+ return;
+
+ __skb_complete_tx_timestamp(skb, sk, tstype);
+}
EXPORT_SYMBOL_GPL(__skb_tstamp_tx);
void skb_tstamp_tx(struct sk_buff *orig_skb,
diff --git a/net/core/sock.c b/net/core/sock.c
index d372b4bd3f9..6f436b5e496 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -437,7 +437,6 @@ static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
int err;
- int skb_len;
unsigned long flags;
struct sk_buff_head *list = &sk->sk_receive_queue;
@@ -459,13 +458,6 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
skb->dev = NULL;
skb_set_owner_r(skb, sk);
- /* Cache the SKB length before we tack it onto the receive
- * queue. Once it is added it no longer belongs to us and
- * may be freed by other threads of control pulling packets
- * from the queue.
- */
- skb_len = skb->len;
-
/* we escape from rcu protected region, make sure we dont leak
* a norefcounted dst
*/
@@ -1645,18 +1637,24 @@ void sock_rfree(struct sk_buff *skb)
}
EXPORT_SYMBOL(sock_rfree);
+void sock_efree(struct sk_buff *skb)
+{
+ sock_put(skb->sk);
+}
+EXPORT_SYMBOL(sock_efree);
+
+#ifdef CONFIG_INET
void sock_edemux(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
-#ifdef CONFIG_INET
if (sk->sk_state == TCP_TIME_WAIT)
inet_twsk_put(inet_twsk(sk));
else
-#endif
sock_put(sk);
}
EXPORT_SYMBOL(sock_edemux);
+#endif
kuid_t sock_i_uid(struct sock *sk)
{
@@ -2498,11 +2496,11 @@ int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len,
int level, int type)
{
struct sock_exterr_skb *serr;
- struct sk_buff *skb, *skb2;
+ struct sk_buff *skb;
int copied, err;
err = -EAGAIN;
- skb = skb_dequeue(&sk->sk_error_queue);
+ skb = sock_dequeue_err_skb(sk);
if (skb == NULL)
goto out;
@@ -2523,16 +2521,6 @@ int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len,
msg->msg_flags |= MSG_ERRQUEUE;
err = copied;
- /* Reset and regenerate socket error */
- spin_lock_bh(&sk->sk_error_queue.lock);
- sk->sk_err = 0;
- if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) {
- sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
- spin_unlock_bh(&sk->sk_error_queue.lock);
- sk->sk_error_report(sk);
- } else
- spin_unlock_bh(&sk->sk_error_queue.lock);
-
out_free_skb:
kfree_skb(skb);
out:
diff --git a/net/core/timestamping.c b/net/core/timestamping.c
index a8770391ea5..43d3dd62fcc 100644
--- a/net/core/timestamping.c
+++ b/net/core/timestamping.c
@@ -36,10 +36,9 @@ void skb_clone_tx_timestamp(struct sk_buff *skb)
{
struct phy_device *phydev;
struct sk_buff *clone;
- struct sock *sk = skb->sk;
unsigned int type;
- if (!sk)
+ if (!skb->sk)
return;
type = classify(skb);
@@ -48,50 +47,14 @@ void skb_clone_tx_timestamp(struct sk_buff *skb)
phydev = skb->dev->phydev;
if (likely(phydev->drv->txtstamp)) {
- if (!atomic_inc_not_zero(&sk->sk_refcnt))
+ clone = skb_clone_sk(skb);
+ if (!clone)
return;
-
- clone = skb_clone(skb, GFP_ATOMIC);
- if (!clone) {
- sock_put(sk);
- return;
- }
-
- clone->sk = sk;
phydev->drv->txtstamp(phydev, clone, type);
}
}
EXPORT_SYMBOL_GPL(skb_clone_tx_timestamp);
-void skb_complete_tx_timestamp(struct sk_buff *skb,
- struct skb_shared_hwtstamps *hwtstamps)
-{
- struct sock *sk = skb->sk;
- struct sock_exterr_skb *serr;
- int err;
-
- if (!hwtstamps) {
- sock_put(sk);
- kfree_skb(skb);
- return;
- }
-
- *skb_hwtstamps(skb) = *hwtstamps;
-
- serr = SKB_EXT_ERR(skb);
- memset(serr, 0, sizeof(*serr));
- serr->ee.ee_errno = ENOMSG;
- serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
- skb->sk = NULL;
-
- err = sock_queue_err_skb(sk, skb);
-
- sock_put(sk);
- if (err)
- kfree_skb(skb);
-}
-EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
-
bool skb_defer_rx_timestamp(struct sk_buff *skb)
{
struct phy_device *phydev;
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index ae011b46c07..25733d53814 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -127,6 +127,7 @@ Version 0.0.6 2.1.110 07-aug-98 Eduardo Marcelo Serrat
#include <linux/stat.h>
#include <linux/init.h>
#include <linux/poll.h>
+#include <linux/jiffies.h>
#include <net/net_namespace.h>
#include <net/neighbour.h>
#include <net/dst.h>
@@ -598,7 +599,7 @@ int dn_destroy_timer(struct sock *sk)
if (sk->sk_socket)
return 0;
- if ((jiffies - scp->stamp) >= (HZ * decnet_time_wait)) {
+ if (time_after_eq(jiffies, scp->stamp + HZ * decnet_time_wait)) {
dn_unhash_sock(sk);
sock_put(sk);
return 1;
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index 3b726f31c64..4400da7739d 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -41,6 +41,7 @@
#include <linux/sysctl.h>
#include <linux/notifier.h>
#include <linux/slab.h>
+#include <linux/jiffies.h>
#include <asm/uaccess.h>
#include <net/net_namespace.h>
#include <net/neighbour.h>
@@ -875,7 +876,7 @@ static void dn_send_endnode_hello(struct net_device *dev, struct dn_ifaddr *ifa)
static int dn_am_i_a_router(struct dn_neigh *dn, struct dn_dev *dn_db, struct dn_ifaddr *ifa)
{
/* First check time since device went up */
- if ((jiffies - dn_db->uptime) < DRDELAY)
+ if (time_before(jiffies, dn_db->uptime + DRDELAY))
return 0;
/* If there is no router, then yes... */
diff --git a/net/decnet/dn_timer.c b/net/decnet/dn_timer.c
index d9c150cc59a..1d330fd43dc 100644
--- a/net/decnet/dn_timer.c
+++ b/net/decnet/dn_timer.c
@@ -23,6 +23,7 @@
#include <linux/spinlock.h>
#include <net/sock.h>
#include <linux/atomic.h>
+#include <linux/jiffies.h>
#include <net/flow.h>
#include <net/dn.h>
@@ -91,7 +92,7 @@ static void dn_slow_timer(unsigned long arg)
* since the last successful transmission.
*/
if (scp->keepalive && scp->keepalive_fxn && (scp->state == DN_RUN)) {
- if ((jiffies - scp->stamp) >= scp->keepalive)
+ if (time_after_eq(jiffies, scp->stamp + scp->keepalive))
scp->keepalive_fxn(sk);
}
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index f5eede1d6cb..a585fd6352e 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -12,6 +12,9 @@ config NET_DSA
if NET_DSA
# tagging formats
+config NET_DSA_TAG_BRCM
+ bool
+
config NET_DSA_TAG_DSA
bool
diff --git a/net/dsa/Makefile b/net/dsa/Makefile
index 7b9fcbbeda5..da06ed1df62 100644
--- a/net/dsa/Makefile
+++ b/net/dsa/Makefile
@@ -3,6 +3,7 @@ obj-$(CONFIG_NET_DSA) += dsa_core.o
dsa_core-y += dsa.o slave.o
# tagging formats
+dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o
dsa_core-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o
dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o
dsa_core-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 0a49632fac4..61f145c4455 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -144,6 +144,11 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index,
goto out;
}
+ /* Make the built-in MII bus mask match the number of ports,
+ * switch drivers can override this later
+ */
+ ds->phys_mii_mask = ds->phys_port_mask;
+
/*
* If the CPU connects to this switch, set the switch tree
* tagging protocol to the preferred tagging format of this
@@ -410,6 +415,7 @@ static int dsa_of_probe(struct platform_device *pdev)
chip_index++;
cd = &pd->chip[chip_index];
+ cd->of_node = child;
cd->mii_bus = &mdio_bus->dev;
sw_addr = of_get_property(child, "reg", NULL);
@@ -431,6 +437,8 @@ static int dsa_of_probe(struct platform_device *pdev)
if (!port_name)
continue;
+ cd->port_dn[port_index] = port;
+
cd->port_names[port_index] = kstrdup(port_name,
GFP_KERNEL);
if (!cd->port_names[port_index]) {
@@ -608,7 +616,26 @@ static void dsa_shutdown(struct platform_device *pdev)
{
}
+static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt, struct net_device *orig_dev)
+{
+ struct dsa_switch_tree *dst = dev->dsa_ptr;
+
+ if (unlikely(dst == NULL)) {
+ kfree_skb(skb);
+ return 0;
+ }
+
+ return dst->ops->rcv(skb, dev, pt, orig_dev);
+}
+
+static struct packet_type dsa_pack_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_XDSA),
+ .func = dsa_switch_rcv,
+};
+
static const struct of_device_id dsa_of_match_table[] = {
+ { .compatible = "brcm,bcm7445-switch-v4.0" },
{ .compatible = "marvell,dsa", },
{}
};
@@ -633,30 +660,15 @@ static int __init dsa_init_module(void)
if (rc)
return rc;
-#ifdef CONFIG_NET_DSA_TAG_DSA
- dev_add_pack(&dsa_packet_type);
-#endif
-#ifdef CONFIG_NET_DSA_TAG_EDSA
- dev_add_pack(&edsa_packet_type);
-#endif
-#ifdef CONFIG_NET_DSA_TAG_TRAILER
- dev_add_pack(&trailer_packet_type);
-#endif
+ dev_add_pack(&dsa_pack_type);
+
return 0;
}
module_init(dsa_init_module);
static void __exit dsa_cleanup_module(void)
{
-#ifdef CONFIG_NET_DSA_TAG_TRAILER
- dev_remove_pack(&trailer_packet_type);
-#endif
-#ifdef CONFIG_NET_DSA_TAG_EDSA
- dev_remove_pack(&edsa_packet_type);
-#endif
-#ifdef CONFIG_NET_DSA_TAG_DSA
- dev_remove_pack(&dsa_packet_type);
-#endif
+ dev_remove_pack(&dsa_pack_type);
platform_driver_unregister(&dsa_driver);
}
module_exit(dsa_cleanup_module);
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index d4cf5cc747e..98afed4d92b 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -33,6 +33,10 @@ struct dsa_slave_priv {
* to this port.
*/
struct phy_device *phy;
+ phy_interface_t phy_interface;
+ int old_link;
+ int old_pause;
+ int old_duplex;
};
/* dsa.c */
@@ -45,16 +49,16 @@ struct net_device *dsa_slave_create(struct dsa_switch *ds,
int port, char *name);
/* tag_dsa.c */
-netdev_tx_t dsa_xmit(struct sk_buff *skb, struct net_device *dev);
-extern struct packet_type dsa_packet_type;
+extern const struct dsa_device_ops dsa_netdev_ops;
/* tag_edsa.c */
-netdev_tx_t edsa_xmit(struct sk_buff *skb, struct net_device *dev);
-extern struct packet_type edsa_packet_type;
+extern const struct dsa_device_ops edsa_netdev_ops;
/* tag_trailer.c */
-netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev);
-extern struct packet_type trailer_packet_type;
+extern const struct dsa_device_ops trailer_netdev_ops;
+
+/* tag_brcm.c */
+extern const struct dsa_device_ops brcm_netdev_ops;
#endif
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 45a1e34c89e..7333a4aebb7 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -12,6 +12,8 @@
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/phy.h>
+#include <linux/of_net.h>
+#include <linux/of_mdio.h>
#include "dsa_priv.h"
/* slave mii_bus handling ***************************************************/
@@ -19,7 +21,7 @@ static int dsa_slave_phy_read(struct mii_bus *bus, int addr, int reg)
{
struct dsa_switch *ds = bus->priv;
- if (ds->phys_port_mask & (1 << addr))
+ if (ds->phys_mii_mask & (1 << addr))
return ds->drv->phy_read(ds, addr, reg);
return 0xffff;
@@ -29,7 +31,7 @@ static int dsa_slave_phy_write(struct mii_bus *bus, int addr, int reg, u16 val)
{
struct dsa_switch *ds = bus->priv;
- if (ds->phys_port_mask & (1 << addr))
+ if (ds->phys_mii_mask & (1 << addr))
return ds->drv->phy_write(ds, addr, reg, val);
return 0;
@@ -171,6 +173,25 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
return -EOPNOTSUPP;
}
+static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_switch_tree *dst = p->parent->dst;
+
+ return dst->ops->xmit(skb, dev);
+}
+
+static netdev_tx_t dsa_slave_notag_xmit(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ struct dsa_slave_priv *p = netdev_priv(dev);
+
+ skb->dev = p->parent->dst->master_netdev;
+ dev_queue_xmit(skb);
+
+ return NETDEV_TX_OK;
+}
+
/* ethtool operations *******************************************************/
static int
@@ -293,44 +314,107 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = {
.get_sset_count = dsa_slave_get_sset_count,
};
-#ifdef CONFIG_NET_DSA_TAG_DSA
-static const struct net_device_ops dsa_netdev_ops = {
- .ndo_init = dsa_slave_init,
- .ndo_open = dsa_slave_open,
- .ndo_stop = dsa_slave_close,
- .ndo_start_xmit = dsa_xmit,
- .ndo_change_rx_flags = dsa_slave_change_rx_flags,
- .ndo_set_rx_mode = dsa_slave_set_rx_mode,
- .ndo_set_mac_address = dsa_slave_set_mac_address,
- .ndo_do_ioctl = dsa_slave_ioctl,
-};
-#endif
-#ifdef CONFIG_NET_DSA_TAG_EDSA
-static const struct net_device_ops edsa_netdev_ops = {
+static const struct net_device_ops dsa_slave_netdev_ops = {
.ndo_init = dsa_slave_init,
.ndo_open = dsa_slave_open,
.ndo_stop = dsa_slave_close,
- .ndo_start_xmit = edsa_xmit,
+ .ndo_start_xmit = dsa_slave_xmit,
.ndo_change_rx_flags = dsa_slave_change_rx_flags,
.ndo_set_rx_mode = dsa_slave_set_rx_mode,
.ndo_set_mac_address = dsa_slave_set_mac_address,
.ndo_do_ioctl = dsa_slave_ioctl,
};
-#endif
-#ifdef CONFIG_NET_DSA_TAG_TRAILER
-static const struct net_device_ops trailer_netdev_ops = {
- .ndo_init = dsa_slave_init,
- .ndo_open = dsa_slave_open,
- .ndo_stop = dsa_slave_close,
- .ndo_start_xmit = trailer_xmit,
- .ndo_change_rx_flags = dsa_slave_change_rx_flags,
- .ndo_set_rx_mode = dsa_slave_set_rx_mode,
- .ndo_set_mac_address = dsa_slave_set_mac_address,
- .ndo_do_ioctl = dsa_slave_ioctl,
+
+static const struct dsa_device_ops notag_netdev_ops = {
+ .xmit = dsa_slave_notag_xmit,
+ .rcv = NULL,
};
-#endif
+
+static void dsa_slave_adjust_link(struct net_device *dev)
+{
+ struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_switch *ds = p->parent;
+ unsigned int status_changed = 0;
+
+ if (p->old_link != p->phy->link) {
+ status_changed = 1;
+ p->old_link = p->phy->link;
+ }
+
+ if (p->old_duplex != p->phy->duplex) {
+ status_changed = 1;
+ p->old_duplex = p->phy->duplex;
+ }
+
+ if (p->old_pause != p->phy->pause) {
+ status_changed = 1;
+ p->old_pause = p->phy->pause;
+ }
+
+ if (ds->drv->adjust_link && status_changed)
+ ds->drv->adjust_link(ds, p->port, p->phy);
+
+ if (status_changed)
+ phy_print_status(p->phy);
+}
+
+static int dsa_slave_fixed_link_update(struct net_device *dev,
+ struct fixed_phy_status *status)
+{
+ struct dsa_slave_priv *p = netdev_priv(dev);
+ struct dsa_switch *ds = p->parent;
+
+ if (ds->drv->fixed_link_update)
+ ds->drv->fixed_link_update(ds, p->port, status);
+
+ return 0;
+}
/* slave device setup *******************************************************/
+static void dsa_slave_phy_setup(struct dsa_slave_priv *p,
+ struct net_device *slave_dev)
+{
+ struct dsa_switch *ds = p->parent;
+ struct dsa_chip_data *cd = ds->pd;
+ struct device_node *phy_dn, *port_dn;
+ bool phy_is_fixed = false;
+ int ret;
+
+ port_dn = cd->port_dn[p->port];
+ p->phy_interface = of_get_phy_mode(port_dn);
+
+ phy_dn = of_parse_phandle(port_dn, "phy-handle", 0);
+ if (of_phy_is_fixed_link(port_dn)) {
+ /* In the case of a fixed PHY, the DT node associated
+ * to the fixed PHY is the Port DT node
+ */
+ ret = of_phy_register_fixed_link(port_dn);
+ if (ret) {
+ pr_err("failed to register fixed PHY\n");
+ return;
+ }
+ phy_is_fixed = true;
+ phy_dn = port_dn;
+ }
+
+ if (phy_dn)
+ p->phy = of_phy_connect(slave_dev, phy_dn,
+ dsa_slave_adjust_link, 0,
+ p->phy_interface);
+
+ if (p->phy && phy_is_fixed)
+ fixed_phy_set_link_update(p->phy, dsa_slave_fixed_link_update);
+
+ /* We could not connect to a designated PHY, so use the switch internal
+ * MDIO bus instead
+ */
+ if (!p->phy)
+ p->phy = ds->slave_mii_bus->phy_map[p->port];
+ else
+ pr_info("attached PHY at address %d [%s]\n",
+ p->phy->addr, p->phy->drv->name);
+}
+
struct net_device *
dsa_slave_create(struct dsa_switch *ds, struct device *parent,
int port, char *name)
@@ -349,35 +433,48 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent,
slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
eth_hw_addr_inherit(slave_dev, master);
slave_dev->tx_queue_len = 0;
+ slave_dev->netdev_ops = &dsa_slave_netdev_ops;
switch (ds->dst->tag_protocol) {
#ifdef CONFIG_NET_DSA_TAG_DSA
case htons(ETH_P_DSA):
- slave_dev->netdev_ops = &dsa_netdev_ops;
+ ds->dst->ops = &dsa_netdev_ops;
break;
#endif
#ifdef CONFIG_NET_DSA_TAG_EDSA
case htons(ETH_P_EDSA):
- slave_dev->netdev_ops = &edsa_netdev_ops;
+ ds->dst->ops = &edsa_netdev_ops;
break;
#endif
#ifdef CONFIG_NET_DSA_TAG_TRAILER
case htons(ETH_P_TRAILER):
- slave_dev->netdev_ops = &trailer_netdev_ops;
+ ds->dst->ops = &trailer_netdev_ops;
+ break;
+#endif
+#ifdef CONFIG_NET_DSA_TAG_BRCM
+ case htons(ETH_P_BRCMTAG):
+ ds->dst->ops = &brcm_netdev_ops;
break;
#endif
default:
- BUG();
+ ds->dst->ops = &notag_netdev_ops;
+ break;
}
SET_NETDEV_DEV(slave_dev, parent);
+ slave_dev->dev.of_node = ds->pd->port_dn[port];
slave_dev->vlan_features = master->vlan_features;
p = netdev_priv(slave_dev);
p->dev = slave_dev;
p->parent = ds;
p->port = port;
- p->phy = ds->slave_mii_bus->phy_map[port];
+
+ p->old_pause = -1;
+ p->old_link = -1;
+ p->old_duplex = -1;
+
+ dsa_slave_phy_setup(p, slave_dev);
ret = register_netdev(slave_dev);
if (ret) {
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
new file mode 100644
index 00000000000..e0b759ec209
--- /dev/null
+++ b/net/dsa/tag_brcm.c
@@ -0,0 +1,173 @@
+/*
+ * Broadcom tag support
+ *
+ * Copyright (C) 2014 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/slab.h>
+#include "dsa_priv.h"
+
+/* This tag length is 4 bytes, older ones were 6 bytes, we do not
+ * handle them
+ */
+#define BRCM_TAG_LEN 4
+
+/* Tag is constructed and desconstructed using byte by byte access
+ * because the tag is placed after the MAC Source Address, which does
+ * not make it 4-bytes aligned, so this might cause unaligned accesses
+ * on most systems where this is used.
+ */
+
+/* Ingress and egress opcodes */
+#define BRCM_OPCODE_SHIFT 5
+#define BRCM_OPCODE_MASK 0x7
+
+/* Ingress fields */
+/* 1st byte in the tag */
+#define BRCM_IG_TC_SHIFT 2
+#define BRCM_IG_TC_MASK 0x7
+/* 2nd byte in the tag */
+#define BRCM_IG_TE_MASK 0x3
+#define BRCM_IG_TS_SHIFT 7
+/* 3rd byte in the tag */
+#define BRCM_IG_DSTMAP2_MASK 1
+#define BRCM_IG_DSTMAP1_MASK 0xff
+
+/* Egress fields */
+
+/* 2nd byte in the tag */
+#define BRCM_EG_CID_MASK 0xff
+
+/* 3rd byte in the tag */
+#define BRCM_EG_RC_MASK 0xff
+#define BRCM_EG_RC_RSVD (3 << 6)
+#define BRCM_EG_RC_EXCEPTION (1 << 5)
+#define BRCM_EG_RC_PROT_SNOOP (1 << 4)
+#define BRCM_EG_RC_PROT_TERM (1 << 3)
+#define BRCM_EG_RC_SWITCH (1 << 2)
+#define BRCM_EG_RC_MAC_LEARN (1 << 1)
+#define BRCM_EG_RC_MIRROR (1 << 0)
+#define BRCM_EG_TC_SHIFT 5
+#define BRCM_EG_TC_MASK 0x7
+#define BRCM_EG_PID_MASK 0x1f
+
+static netdev_tx_t brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct dsa_slave_priv *p = netdev_priv(dev);
+ u8 *brcm_tag;
+
+ dev->stats.tx_packets++;
+ dev->stats.tx_bytes += skb->len;
+
+ if (skb_cow_head(skb, BRCM_TAG_LEN) < 0)
+ goto out_free;
+
+ skb_push(skb, BRCM_TAG_LEN);
+
+ memmove(skb->data, skb->data + BRCM_TAG_LEN, 2 * ETH_ALEN);
+
+ /* Build the tag after the MAC Source Address */
+ brcm_tag = skb->data + 2 * ETH_ALEN;
+
+ /* Set the ingress opcode, traffic class, tag enforcment is
+ * deprecated
+ */
+ brcm_tag[0] = (1 << BRCM_OPCODE_SHIFT) |
+ ((skb->priority << BRCM_IG_TC_SHIFT) & BRCM_IG_TC_MASK);
+ brcm_tag[1] = 0;
+ brcm_tag[2] = 0;
+ if (p->port == 8)
+ brcm_tag[2] = BRCM_IG_DSTMAP2_MASK;
+ brcm_tag[3] = (1 << p->port) & BRCM_IG_DSTMAP1_MASK;
+
+ /* Queue the SKB for transmission on the parent interface, but
+ * do not modify its EtherType
+ */
+ skb->protocol = htons(ETH_P_BRCMTAG);
+ skb->dev = p->parent->dst->master_netdev;
+ dev_queue_xmit(skb);
+
+ return NETDEV_TX_OK;
+
+out_free:
+ kfree_skb(skb);
+ return NETDEV_TX_OK;
+}
+
+static int brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt, struct net_device *orig_dev)
+{
+ struct dsa_switch_tree *dst = dev->dsa_ptr;
+ struct dsa_switch *ds;
+ int source_port;
+ u8 *brcm_tag;
+
+ if (unlikely(dst == NULL))
+ goto out_drop;
+
+ ds = dst->ds[0];
+
+ skb = skb_unshare(skb, GFP_ATOMIC);
+ if (skb == NULL)
+ goto out;
+
+ if (unlikely(!pskb_may_pull(skb, BRCM_TAG_LEN)))
+ goto out_drop;
+
+ /* skb->data points to the EtherType, the tag is right before it */
+ brcm_tag = skb->data - 2;
+
+ /* The opcode should never be different than 0b000 */
+ if (unlikely((brcm_tag[0] >> BRCM_OPCODE_SHIFT) & BRCM_OPCODE_MASK))
+ goto out_drop;
+
+ /* We should never see a reserved reason code without knowing how to
+ * handle it
+ */
+ WARN_ON(brcm_tag[2] & BRCM_EG_RC_RSVD);
+
+ /* Locate which port this is coming from */
+ source_port = brcm_tag[3] & BRCM_EG_PID_MASK;
+
+ /* Validate port against switch setup, either the port is totally */
+ if (source_port >= DSA_MAX_PORTS || ds->ports[source_port] == NULL)
+ goto out_drop;
+
+ /* Remove Broadcom tag and update checksum */
+ skb_pull_rcsum(skb, BRCM_TAG_LEN);
+
+ /* Move the Ethernet DA and SA */
+ memmove(skb->data - ETH_HLEN,
+ skb->data - ETH_HLEN - BRCM_TAG_LEN,
+ 2 * ETH_ALEN);
+
+ skb_push(skb, ETH_HLEN);
+ skb->pkt_type = PACKET_HOST;
+ skb->dev = ds->ports[source_port];
+ skb->protocol = eth_type_trans(skb, skb->dev);
+
+ skb->dev->stats.rx_packets++;
+ skb->dev->stats.rx_bytes += skb->len;
+
+ netif_receive_skb(skb);
+
+ return 0;
+
+out_drop:
+ kfree_skb(skb);
+out:
+ return 0;
+}
+
+const struct dsa_device_ops brcm_netdev_ops = {
+ .xmit = brcm_tag_xmit,
+ .rcv = brcm_tag_rcv,
+};
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index cacce1e22f9..d7dbc5bda5c 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -16,7 +16,7 @@
#define DSA_HLEN 4
-netdev_tx_t dsa_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t dsa_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct dsa_slave_priv *p = netdev_priv(dev);
u8 *dsa_header;
@@ -186,7 +186,7 @@ out:
return 0;
}
-struct packet_type dsa_packet_type __read_mostly = {
- .type = cpu_to_be16(ETH_P_DSA),
- .func = dsa_rcv,
+const struct dsa_device_ops dsa_netdev_ops = {
+ .xmit = dsa_xmit,
+ .rcv = dsa_rcv,
};
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index e70c43c25e6..6b30abe8918 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -17,7 +17,7 @@
#define DSA_HLEN 4
#define EDSA_HLEN 8
-netdev_tx_t edsa_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t edsa_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct dsa_slave_priv *p = netdev_priv(dev);
u8 *edsa_header;
@@ -205,7 +205,7 @@ out:
return 0;
}
-struct packet_type edsa_packet_type __read_mostly = {
- .type = cpu_to_be16(ETH_P_EDSA),
- .func = edsa_rcv,
+const struct dsa_device_ops edsa_netdev_ops = {
+ .xmit = edsa_xmit,
+ .rcv = edsa_rcv,
};
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 94bc260d015..5fe9444842c 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -14,7 +14,7 @@
#include <linux/slab.h>
#include "dsa_priv.h"
-netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct dsa_slave_priv *p = netdev_priv(dev);
struct sk_buff *nskb;
@@ -114,7 +114,7 @@ out:
return 0;
}
-struct packet_type trailer_packet_type __read_mostly = {
- .type = cpu_to_be16(ETH_P_TRAILER),
- .func = trailer_rcv,
+const struct dsa_device_ops trailer_netdev_ops = {
+ .xmit = trailer_xmit,
+ .rcv = trailer_rcv,
};
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index f405e059240..33a140e1583 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -146,6 +146,33 @@ int eth_rebuild_header(struct sk_buff *skb)
EXPORT_SYMBOL(eth_rebuild_header);
/**
+ * eth_get_headlen - determine the the length of header for an ethernet frame
+ * @data: pointer to start of frame
+ * @len: total length of frame
+ *
+ * Make a best effort attempt to pull the length for all of the headers for
+ * a given frame in a linear buffer.
+ */
+u32 eth_get_headlen(void *data, unsigned int len)
+{
+ const struct ethhdr *eth = (const struct ethhdr *)data;
+ struct flow_keys keys;
+
+ /* this should never happen, but better safe than sorry */
+ if (len < sizeof(*eth))
+ return len;
+
+ /* parse any remaining L2/L3 headers, check for L4 */
+ if (!__skb_flow_dissect(NULL, &keys, data,
+ eth->h_proto, sizeof(*eth), len))
+ return max_t(u32, keys.thoff, sizeof(*eth));
+
+ /* parse for any L4 headers */
+ return min_t(u32, __skb_get_poff(NULL, data, &keys, len), len);
+}
+EXPORT_SYMBOL(eth_get_headlen);
+
+/**
* eth_type_trans - determine the packet's protocol ID.
* @skb: received socket data
* @dev: receiving network device
@@ -181,11 +208,8 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
* variants has been configured on the receiving interface,
* and if so, set skb->protocol without looking at the packet.
*/
- if (unlikely(netdev_uses_dsa_tags(dev)))
- return htons(ETH_P_DSA);
-
- if (unlikely(netdev_uses_trailer_tags(dev)))
- return htons(ETH_P_TRAILER);
+ if (unlikely(netdev_uses_dsa(dev)))
+ return htons(ETH_P_XDSA);
if (likely(ntohs(eth->h_proto) >= ETH_P_802_3_MIN))
return eth->h_proto;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 255aa9946fe..23104a3f292 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -243,7 +243,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
u8 tos, int oif, struct net_device *dev,
int rpf, struct in_device *idev, u32 *itag)
{
- int ret, no_addr, accept_local;
+ int ret, no_addr;
struct fib_result res;
struct flowi4 fl4;
struct net *net;
@@ -258,16 +258,17 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
no_addr = idev->ifa_list == NULL;
- accept_local = IN_DEV_ACCEPT_LOCAL(idev);
fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0;
net = dev_net(dev);
if (fib_lookup(net, &fl4, &res))
goto last_resort;
- if (res.type != RTN_UNICAST) {
- if (res.type != RTN_LOCAL || !accept_local)
- goto e_inval;
- }
+ if (res.type != RTN_UNICAST &&
+ (res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev)))
+ goto e_inval;
+ if (!rpf && !fib_num_tclassid_users(dev_net(dev)) &&
+ (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev)))
+ goto last_resort;
fib_combine_itag(itag, &res);
dev_match = false;
@@ -321,6 +322,7 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev);
if (!r && !fib_num_tclassid_users(dev_net(dev)) &&
+ IN_DEV_ACCEPT_LOCAL(idev) &&
(dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) {
*itag = 0;
return 0;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index b10cd43a472..5b6efb3d230 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -157,9 +157,12 @@ static void rt_fibinfo_free(struct rtable __rcu **rtp)
static void free_nh_exceptions(struct fib_nh *nh)
{
- struct fnhe_hash_bucket *hash = nh->nh_exceptions;
+ struct fnhe_hash_bucket *hash;
int i;
+ hash = rcu_dereference_protected(nh->nh_exceptions, 1);
+ if (!hash)
+ return;
for (i = 0; i < FNHE_HASH_SIZE; i++) {
struct fib_nh_exception *fnhe;
@@ -205,8 +208,7 @@ static void free_fib_info_rcu(struct rcu_head *head)
change_nexthops(fi) {
if (nexthop_nh->nh_dev)
dev_put(nexthop_nh->nh_dev);
- if (nexthop_nh->nh_exceptions)
- free_nh_exceptions(nexthop_nh);
+ free_nh_exceptions(nexthop_nh);
rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output);
rt_fibinfo_free(&nexthop_nh->nh_rth_input);
} endfor_nexthops(fi);
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 0485bf7f8f0..7e0756da873 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -125,6 +125,10 @@ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
*csum_err = true;
return -EINVAL;
}
+
+ skb_checksum_try_convert(skb, IPPROTO_GRE, 0,
+ null_compute_pseudo);
+
options++;
}
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 6556263c8fa..d3fe2ac0516 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -119,28 +119,6 @@ out:
return segs;
}
-/* Compute the whole skb csum in s/w and store it, then verify GRO csum
- * starting from gro_offset.
- */
-static __sum16 gro_skb_checksum(struct sk_buff *skb)
-{
- __sum16 sum;
-
- skb->csum = skb_checksum(skb, 0, skb->len, 0);
- NAPI_GRO_CB(skb)->csum = csum_sub(skb->csum,
- csum_partial(skb->data, skb_gro_offset(skb), 0));
- sum = csum_fold(NAPI_GRO_CB(skb)->csum);
- if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) {
- if (unlikely(!sum) && !skb->csum_complete_sw)
- netdev_rx_csum_fault(skb->dev);
- } else {
- skb->ip_summed = CHECKSUM_COMPLETE;
- skb->csum_complete_sw = 1;
- }
-
- return sum;
-}
-
static struct sk_buff **gre_gro_receive(struct sk_buff **head,
struct sk_buff *skb)
{
@@ -192,22 +170,16 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
if (unlikely(!greh))
goto out_unlock;
}
- if (greh->flags & GRE_CSUM) { /* Need to verify GRE csum first */
- __sum16 csum = 0;
-
- if (skb->ip_summed == CHECKSUM_COMPLETE)
- csum = csum_fold(NAPI_GRO_CB(skb)->csum);
- /* Don't trust csum error calculated/reported by h/w */
- if (skb->ip_summed == CHECKSUM_NONE || csum != 0)
- csum = gro_skb_checksum(skb);
-
- /* GRE CSUM is the 1's complement of the 1's complement sum
- * of the GRE hdr plus payload so it should add up to 0xffff
- * (and 0 after csum_fold()) just like the IPv4 hdr csum.
- */
- if (csum)
+
+ /* Don't bother verifying checksum if we're going to flush anyway. */
+ if ((greh->flags & GRE_CSUM) && !NAPI_GRO_CB(skb)->flush) {
+ if (skb_gro_checksum_simple_validate(skb))
goto out_unlock;
+
+ skb_gro_checksum_try_convert(skb, IPPROTO_GRE, 0,
+ null_compute_pseudo);
}
+
flush = 0;
for (p = *head; p; p = p->next) {
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index f10eab46228..4146153d875 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -117,7 +117,7 @@
#define IGMP_V2_Unsolicited_Report_Interval (10*HZ)
#define IGMP_V3_Unsolicited_Report_Interval (1*HZ)
#define IGMP_Query_Response_Interval (10*HZ)
-#define IGMP_Unsolicited_Report_Count 2
+#define IGMP_Query_Robustness_Variable 2
#define IGMP_Initial_Report_Delay (1)
@@ -756,8 +756,7 @@ static void igmp_ifc_event(struct in_device *in_dev)
{
if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev))
return;
- in_dev->mr_ifc_count = in_dev->mr_qrv ? in_dev->mr_qrv :
- IGMP_Unsolicited_Report_Count;
+ in_dev->mr_ifc_count = in_dev->mr_qrv ?: sysctl_igmp_qrv;
igmp_ifc_start_timer(in_dev, 1);
}
@@ -1086,8 +1085,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im)
pmc->interface = im->interface;
in_dev_hold(in_dev);
pmc->multiaddr = im->multiaddr;
- pmc->crcount = in_dev->mr_qrv ? in_dev->mr_qrv :
- IGMP_Unsolicited_Report_Count;
+ pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv;
pmc->sfmode = im->sfmode;
if (pmc->sfmode == MCAST_INCLUDE) {
struct ip_sf_list *psf;
@@ -1226,8 +1224,7 @@ static void igmp_group_added(struct ip_mc_list *im)
}
/* else, v3 */
- im->crcount = in_dev->mr_qrv ? in_dev->mr_qrv :
- IGMP_Unsolicited_Report_Count;
+ im->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv;
igmp_ifc_event(in_dev);
#endif
}
@@ -1322,7 +1319,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
spin_lock_init(&im->lock);
#ifdef CONFIG_IP_MULTICAST
setup_timer(&im->timer, igmp_timer_expire, (unsigned long)im);
- im->unsolicit_count = IGMP_Unsolicited_Report_Count;
+ im->unsolicit_count = sysctl_igmp_qrv;
#endif
im->next_rcu = in_dev->mc_list;
@@ -1460,7 +1457,7 @@ void ip_mc_init_dev(struct in_device *in_dev)
(unsigned long)in_dev);
setup_timer(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire,
(unsigned long)in_dev);
- in_dev->mr_qrv = IGMP_Unsolicited_Report_Count;
+ in_dev->mr_qrv = sysctl_igmp_qrv;
#endif
spin_lock_init(&in_dev->mc_tomb_lock);
@@ -1474,6 +1471,9 @@ void ip_mc_up(struct in_device *in_dev)
ASSERT_RTNL();
+#ifdef CONFIG_IP_MULTICAST
+ in_dev->mr_qrv = sysctl_igmp_qrv;
+#endif
ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS);
for_each_pmc_rtnl(in_dev, pmc)
@@ -1540,7 +1540,9 @@ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr)
*/
int sysctl_igmp_max_memberships __read_mostly = IP_MAX_MEMBERSHIPS;
int sysctl_igmp_max_msf __read_mostly = IP_MAX_MSF;
-
+#ifdef CONFIG_IP_MULTICAST
+int sysctl_igmp_qrv __read_mostly = IGMP_Query_Robustness_Variable;
+#endif
static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode,
__be32 *psfsrc)
@@ -1575,8 +1577,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode,
#ifdef CONFIG_IP_MULTICAST
if (psf->sf_oldin &&
!IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) {
- psf->sf_crcount = in_dev->mr_qrv ? in_dev->mr_qrv :
- IGMP_Unsolicited_Report_Count;
+ psf->sf_crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv;
psf->sf_next = pmc->tomb;
pmc->tomb = psf;
rv = 1;
@@ -1639,8 +1640,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
/* filter mode change */
pmc->sfmode = MCAST_INCLUDE;
#ifdef CONFIG_IP_MULTICAST
- pmc->crcount = in_dev->mr_qrv ? in_dev->mr_qrv :
- IGMP_Unsolicited_Report_Count;
+ pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv;
in_dev->mr_ifc_count = pmc->crcount;
for (psf = pmc->sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
@@ -1818,8 +1818,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
#ifdef CONFIG_IP_MULTICAST
/* else no filters; keep old mode for reports */
- pmc->crcount = in_dev->mr_qrv ? in_dev->mr_qrv :
- IGMP_Unsolicited_Report_Count;
+ pmc->crcount = in_dev->mr_qrv ?: sysctl_igmp_qrv;
in_dev->mr_ifc_count = pmc->crcount;
for (psf = pmc->sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
@@ -2539,7 +2538,7 @@ static int igmp_mc_seq_show(struct seq_file *seq, void *v)
querier = "NONE";
#endif
- if (rcu_dereference(state->in_dev->mc_list) == im) {
+ if (rcu_access_pointer(state->in_dev->mc_list) == im) {
seq_printf(seq, "%d\t%-10s: %5d %7s\n",
state->dev->ifindex, state->dev->name, state->in_dev->mc_count, querier);
}
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 43116e8c8e1..9111a4e2215 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -229,7 +229,7 @@ begin:
}
} else if (score == hiscore && reuseport) {
matches++;
- if (((u64)phash * matches) >> 32 == 0)
+ if (reciprocal_scale(phash, matches) == 0)
result = sk;
phash = next_pseudo_random32(phash);
}
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 5cb830c7899..455e75bcb16 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -405,7 +405,7 @@ void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 inf
int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
{
struct sock_exterr_skb *serr;
- struct sk_buff *skb, *skb2;
+ struct sk_buff *skb;
DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
struct {
struct sock_extended_err ee;
@@ -415,7 +415,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
int copied;
err = -EAGAIN;
- skb = skb_dequeue(&sk->sk_error_queue);
+ skb = sock_dequeue_err_skb(sk);
if (skb == NULL)
goto out;
@@ -462,17 +462,6 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
msg->msg_flags |= MSG_ERRQUEUE;
err = copied;
- /* Reset and regenerate socket error */
- spin_lock_bh(&sk->sk_error_queue.lock);
- sk->sk_err = 0;
- skb2 = skb_peek(&sk->sk_error_queue);
- if (skb2 != NULL) {
- sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
- spin_unlock_bh(&sk->sk_error_queue.lock);
- sk->sk_error_report(sk);
- } else
- spin_unlock_bh(&sk->sk_error_queue.lock);
-
out_free_skb:
kfree_skb(skb);
out:
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 5bbef4fdcb4..648fa1490ea 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -262,7 +262,8 @@ static int __init ic_open_devs(void)
/* wait for a carrier on at least one device */
start = jiffies;
next_msg = start + msecs_to_jiffies(CONF_CARRIER_TIMEOUT/12);
- while (jiffies - start < msecs_to_jiffies(CONF_CARRIER_TIMEOUT)) {
+ while (time_before(jiffies, start +
+ msecs_to_jiffies(CONF_CARRIER_TIMEOUT))) {
int wait, elapsed;
for_each_netdev(&init_net, dev)
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 2510c02c2d2..e90f83a3415 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -285,7 +285,7 @@ clusterip_hashfn(const struct sk_buff *skb,
}
/* node numbers are 1..n, not 0..n */
- return (((u64)hashval * config->num_total_nodes) >> 32) + 1;
+ return reciprocal_scale(hashval, config->num_total_nodes) + 1;
}
static inline int
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index eaa4b000c7b..234a43e233d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -596,12 +596,12 @@ static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash)
static inline u32 fnhe_hashfun(__be32 daddr)
{
+ static u32 fnhe_hashrnd __read_mostly;
u32 hval;
- hval = (__force u32) daddr;
- hval ^= (hval >> 11) ^ (hval >> 22);
-
- return hval & (FNHE_HASH_SIZE - 1);
+ net_get_random_once(&fnhe_hashrnd, sizeof(fnhe_hashrnd));
+ hval = jhash_1word((__force u32) daddr, fnhe_hashrnd);
+ return hash_32(hval, FNHE_HASH_SHIFT);
}
static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe)
@@ -628,12 +628,12 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
spin_lock_bh(&fnhe_lock);
- hash = nh->nh_exceptions;
+ hash = rcu_dereference(nh->nh_exceptions);
if (!hash) {
hash = kzalloc(FNHE_HASH_SIZE * sizeof(*hash), GFP_ATOMIC);
if (!hash)
goto out_unlock;
- nh->nh_exceptions = hash;
+ rcu_assign_pointer(nh->nh_exceptions, hash);
}
hash += hval;
@@ -1242,7 +1242,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
{
- struct fnhe_hash_bucket *hash = nh->nh_exceptions;
+ struct fnhe_hash_bucket *hash = rcu_dereference(nh->nh_exceptions);
struct fib_nh_exception *fnhe;
u32 hval;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index c0c75688896..0431a8f3c8f 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -25,7 +25,7 @@
extern int sysctl_tcp_syncookies;
-static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS];
+static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
#define COOKIEBITS 24 /* Upper bits store count */
#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 79a007c5255..45d156dacd6 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -450,6 +450,16 @@ static struct ctl_table ipv4_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec
},
+#ifdef CONFIG_IP_MULTICAST
+ {
+ .procname = "igmp_qrv",
+ .data = &sysctl_igmp_qrv,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one
+ },
+#endif
{
.procname = "inet_peer_threshold",
.data = &inet_peer_threshold,
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index d5de69bc04f..bb395d46a38 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -17,7 +17,6 @@
#include <linux/module.h>
#include <net/tcp.h>
-
#define BICTCP_BETA_SCALE 1024 /* Scale factor beta calculation
* max_cwnd = snd_cwnd * beta
*/
@@ -46,11 +45,10 @@ MODULE_PARM_DESC(initial_ssthresh, "initial value of slow start threshold");
module_param(smooth_part, int, 0644);
MODULE_PARM_DESC(smooth_part, "log(B/(B*Smin))/log(B/(B-1))+B, # of RTT from Wmax-B to Wmax");
-
/* BIC TCP Parameters */
struct bictcp {
u32 cnt; /* increase cwnd by 1 after ACKs */
- u32 last_max_cwnd; /* last maximum snd_cwnd */
+ u32 last_max_cwnd; /* last maximum snd_cwnd */
u32 loss_cwnd; /* congestion window at last loss */
u32 last_cwnd; /* the last snd_cwnd */
u32 last_time; /* time when updated last_cwnd */
@@ -103,7 +101,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
/* binary increase */
if (cwnd < ca->last_max_cwnd) {
- __u32 dist = (ca->last_max_cwnd - cwnd)
+ __u32 dist = (ca->last_max_cwnd - cwnd)
/ BICTCP_B;
if (dist > max_increment)
@@ -154,7 +152,6 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
bictcp_update(ca, tp->snd_cwnd);
tcp_cong_avoid_ai(tp, ca->cnt);
}
-
}
/*
@@ -177,7 +174,6 @@ static u32 bictcp_recalc_ssthresh(struct sock *sk)
ca->loss_cwnd = tp->snd_cwnd;
-
if (tp->snd_cwnd <= low_window)
return max(tp->snd_cwnd >> 1U, 2U);
else
@@ -188,6 +184,7 @@ static u32 bictcp_undo_cwnd(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
const struct bictcp *ca = inet_csk_ca(sk);
+
return max(tp->snd_cwnd, ca->loss_cwnd);
}
@@ -206,12 +203,12 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt)
if (icsk->icsk_ca_state == TCP_CA_Open) {
struct bictcp *ca = inet_csk_ca(sk);
+
cnt -= ca->delayed_ack >> ACK_RATIO_SHIFT;
ca->delayed_ack += cnt;
}
}
-
static struct tcp_congestion_ops bictcp __read_mostly = {
.init = bictcp_init,
.ssthresh = bictcp_recalc_ssthresh,
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 7b09d8b49fa..80248f56c89 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -142,7 +142,6 @@ static int __init tcp_congestion_default(void)
}
late_initcall(tcp_congestion_default);
-
/* Build string with list of available congestion control values */
void tcp_get_available_congestion_control(char *buf, size_t maxlen)
{
@@ -154,7 +153,6 @@ void tcp_get_available_congestion_control(char *buf, size_t maxlen)
offs += snprintf(buf + offs, maxlen - offs,
"%s%s",
offs == 0 ? "" : " ", ca->name);
-
}
rcu_read_unlock();
}
@@ -186,7 +184,6 @@ void tcp_get_allowed_congestion_control(char *buf, size_t maxlen)
offs += snprintf(buf + offs, maxlen - offs,
"%s%s",
offs == 0 ? "" : " ", ca->name);
-
}
rcu_read_unlock();
}
@@ -230,7 +227,6 @@ out:
return ret;
}
-
/* Change congestion control for socket */
int tcp_set_congestion_control(struct sock *sk, const char *name)
{
@@ -337,6 +333,7 @@ EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid);
u32 tcp_reno_ssthresh(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
+
return max(tp->snd_cwnd >> 1U, 2U);
}
EXPORT_SYMBOL_GPL(tcp_reno_ssthresh);
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index a9bd8a4828a..20de0118c98 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -82,12 +82,13 @@ MODULE_PARM_DESC(hystart_ack_delta, "spacing between ack's indicating train (mse
/* BIC TCP Parameters */
struct bictcp {
u32 cnt; /* increase cwnd by 1 after ACKs */
- u32 last_max_cwnd; /* last maximum snd_cwnd */
+ u32 last_max_cwnd; /* last maximum snd_cwnd */
u32 loss_cwnd; /* congestion window at last loss */
u32 last_cwnd; /* the last snd_cwnd */
u32 last_time; /* time when updated last_cwnd */
u32 bic_origin_point;/* origin point of bic function */
- u32 bic_K; /* time to origin point from the beginning of the current epoch */
+ u32 bic_K; /* time to origin point
+ from the beginning of the current epoch */
u32 delay_min; /* min delay (msec << 3) */
u32 epoch_start; /* beginning of an epoch */
u32 ack_cnt; /* number of acks */
@@ -219,7 +220,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
ca->last_time = tcp_time_stamp;
if (ca->epoch_start == 0) {
- ca->epoch_start = tcp_time_stamp; /* record the beginning of an epoch */
+ ca->epoch_start = tcp_time_stamp; /* record beginning */
ca->ack_cnt = 1; /* start counting */
ca->tcp_cwnd = cwnd; /* syn with cubic */
@@ -263,9 +264,9 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
/* c/rtt * (t-K)^3 */
delta = (cube_rtt_scale * offs * offs * offs) >> (10+3*BICTCP_HZ);
- if (t < ca->bic_K) /* below origin*/
+ if (t < ca->bic_K) /* below origin*/
bic_target = ca->bic_origin_point - delta;
- else /* above origin*/
+ else /* above origin*/
bic_target = ca->bic_origin_point + delta;
/* cubic function - calc bictcp_cnt*/
@@ -285,13 +286,14 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
/* TCP Friendly */
if (tcp_friendliness) {
u32 scale = beta_scale;
+
delta = (cwnd * scale) >> 3;
while (ca->ack_cnt > delta) { /* update tcp cwnd */
ca->ack_cnt -= delta;
ca->tcp_cwnd++;
}
- if (ca->tcp_cwnd > cwnd){ /* if bic is slower than tcp */
+ if (ca->tcp_cwnd > cwnd) { /* if bic is slower than tcp */
delta = ca->tcp_cwnd - cwnd;
max_cnt = cwnd / delta;
if (ca->cnt > max_cnt)
@@ -320,7 +322,6 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
bictcp_update(ca, tp->snd_cwnd);
tcp_cong_avoid_ai(tp, ca->cnt);
}
-
}
static u32 bictcp_recalc_ssthresh(struct sock *sk)
@@ -452,7 +453,8 @@ static int __init cubictcp_register(void)
* based on SRTT of 100ms
*/
- beta_scale = 8*(BICTCP_BETA_SCALE+beta)/ 3 / (BICTCP_BETA_SCALE - beta);
+ beta_scale = 8*(BICTCP_BETA_SCALE+beta) / 3
+ / (BICTCP_BETA_SCALE - beta);
cube_rtt_scale = (bic_scale * 10); /* 1024*c/rtt */
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index ed3f2ad42e0..0d73f9ddb55 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -9,7 +9,6 @@
* 2 of the License, or (at your option) any later version.
*/
-
#include <linux/module.h>
#include <linux/inet_diag.h>
@@ -35,13 +34,13 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
}
static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
- struct inet_diag_req_v2 *r, struct nlattr *bc)
+ struct inet_diag_req_v2 *r, struct nlattr *bc)
{
inet_diag_dump_icsk(&tcp_hashinfo, skb, cb, r, bc);
}
static int tcp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
- struct inet_diag_req_v2 *req)
+ struct inet_diag_req_v2 *req)
{
return inet_diag_dump_one_icsk(&tcp_hashinfo, in_skb, nlh, req);
}
diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c
index 1c4908280d9..882c08aae2f 100644
--- a/net/ipv4/tcp_highspeed.c
+++ b/net/ipv4/tcp_highspeed.c
@@ -9,7 +9,6 @@
#include <linux/module.h>
#include <net/tcp.h>
-
/* From AIMD tables from RFC 3649 appendix B,
* with fixed-point MD scaled <<8.
*/
@@ -17,78 +16,78 @@ static const struct hstcp_aimd_val {
unsigned int cwnd;
unsigned int md;
} hstcp_aimd_vals[] = {
- { 38, 128, /* 0.50 */ },
- { 118, 112, /* 0.44 */ },
- { 221, 104, /* 0.41 */ },
- { 347, 98, /* 0.38 */ },
- { 495, 93, /* 0.37 */ },
- { 663, 89, /* 0.35 */ },
- { 851, 86, /* 0.34 */ },
- { 1058, 83, /* 0.33 */ },
- { 1284, 81, /* 0.32 */ },
- { 1529, 78, /* 0.31 */ },
- { 1793, 76, /* 0.30 */ },
- { 2076, 74, /* 0.29 */ },
- { 2378, 72, /* 0.28 */ },
- { 2699, 71, /* 0.28 */ },
- { 3039, 69, /* 0.27 */ },
- { 3399, 68, /* 0.27 */ },
- { 3778, 66, /* 0.26 */ },
- { 4177, 65, /* 0.26 */ },
- { 4596, 64, /* 0.25 */ },
- { 5036, 62, /* 0.25 */ },
- { 5497, 61, /* 0.24 */ },
- { 5979, 60, /* 0.24 */ },
- { 6483, 59, /* 0.23 */ },
- { 7009, 58, /* 0.23 */ },
- { 7558, 57, /* 0.22 */ },
- { 8130, 56, /* 0.22 */ },
- { 8726, 55, /* 0.22 */ },
- { 9346, 54, /* 0.21 */ },
- { 9991, 53, /* 0.21 */ },
- { 10661, 52, /* 0.21 */ },
- { 11358, 52, /* 0.20 */ },
- { 12082, 51, /* 0.20 */ },
- { 12834, 50, /* 0.20 */ },
- { 13614, 49, /* 0.19 */ },
- { 14424, 48, /* 0.19 */ },
- { 15265, 48, /* 0.19 */ },
- { 16137, 47, /* 0.19 */ },
- { 17042, 46, /* 0.18 */ },
- { 17981, 45, /* 0.18 */ },
- { 18955, 45, /* 0.18 */ },
- { 19965, 44, /* 0.17 */ },
- { 21013, 43, /* 0.17 */ },
- { 22101, 43, /* 0.17 */ },
- { 23230, 42, /* 0.17 */ },
- { 24402, 41, /* 0.16 */ },
- { 25618, 41, /* 0.16 */ },
- { 26881, 40, /* 0.16 */ },
- { 28193, 39, /* 0.16 */ },
- { 29557, 39, /* 0.15 */ },
- { 30975, 38, /* 0.15 */ },
- { 32450, 38, /* 0.15 */ },
- { 33986, 37, /* 0.15 */ },
- { 35586, 36, /* 0.14 */ },
- { 37253, 36, /* 0.14 */ },
- { 38992, 35, /* 0.14 */ },
- { 40808, 35, /* 0.14 */ },
- { 42707, 34, /* 0.13 */ },
- { 44694, 33, /* 0.13 */ },
- { 46776, 33, /* 0.13 */ },
- { 48961, 32, /* 0.13 */ },
- { 51258, 32, /* 0.13 */ },
- { 53677, 31, /* 0.12 */ },
- { 56230, 30, /* 0.12 */ },
- { 58932, 30, /* 0.12 */ },
- { 61799, 29, /* 0.12 */ },
- { 64851, 28, /* 0.11 */ },
- { 68113, 28, /* 0.11 */ },
- { 71617, 27, /* 0.11 */ },
- { 75401, 26, /* 0.10 */ },
- { 79517, 26, /* 0.10 */ },
- { 84035, 25, /* 0.10 */ },
- { 89053, 24, /* 0.10 */ },
+ { 38, 128, /* 0.50 */ },
+ { 118, 112, /* 0.44 */ },
+ { 221, 104, /* 0.41 */ },
+ { 347, 98, /* 0.38 */ },
+ { 495, 93, /* 0.37 */ },
+ { 663, 89, /* 0.35 */ },
+ { 851, 86, /* 0.34 */ },
+ { 1058, 83, /* 0.33 */ },
+ { 1284, 81, /* 0.32 */ },
+ { 1529, 78, /* 0.31 */ },
+ { 1793, 76, /* 0.30 */ },
+ { 2076, 74, /* 0.29 */ },
+ { 2378, 72, /* 0.28 */ },
+ { 2699, 71, /* 0.28 */ },
+ { 3039, 69, /* 0.27 */ },
+ { 3399, 68, /* 0.27 */ },
+ { 3778, 66, /* 0.26 */ },
+ { 4177, 65, /* 0.26 */ },
+ { 4596, 64, /* 0.25 */ },
+ { 5036, 62, /* 0.25 */ },
+ { 5497, 61, /* 0.24 */ },
+ { 5979, 60, /* 0.24 */ },
+ { 6483, 59, /* 0.23 */ },
+ { 7009, 58, /* 0.23 */ },
+ { 7558, 57, /* 0.22 */ },
+ { 8130, 56, /* 0.22 */ },
+ { 8726, 55, /* 0.22 */ },
+ { 9346, 54, /* 0.21 */ },
+ { 9991, 53, /* 0.21 */ },
+ { 10661, 52, /* 0.21 */ },
+ { 11358, 52, /* 0.20 */ },
+ { 12082, 51, /* 0.20 */ },
+ { 12834, 50, /* 0.20 */ },
+ { 13614, 49, /* 0.19 */ },
+ { 14424, 48, /* 0.19 */ },
+ { 15265, 48, /* 0.19 */ },
+ { 16137, 47, /* 0.19 */ },
+ { 17042, 46, /* 0.18 */ },
+ { 17981, 45, /* 0.18 */ },
+ { 18955, 45, /* 0.18 */ },
+ { 19965, 44, /* 0.17 */ },
+ { 21013, 43, /* 0.17 */ },
+ { 22101, 43, /* 0.17 */ },
+ { 23230, 42, /* 0.17 */ },
+ { 24402, 41, /* 0.16 */ },
+ { 25618, 41, /* 0.16 */ },
+ { 26881, 40, /* 0.16 */ },
+ { 28193, 39, /* 0.16 */ },
+ { 29557, 39, /* 0.15 */ },
+ { 30975, 38, /* 0.15 */ },
+ { 32450, 38, /* 0.15 */ },
+ { 33986, 37, /* 0.15 */ },
+ { 35586, 36, /* 0.14 */ },
+ { 37253, 36, /* 0.14 */ },
+ { 38992, 35, /* 0.14 */ },
+ { 40808, 35, /* 0.14 */ },
+ { 42707, 34, /* 0.13 */ },
+ { 44694, 33, /* 0.13 */ },
+ { 46776, 33, /* 0.13 */ },
+ { 48961, 32, /* 0.13 */ },
+ { 51258, 32, /* 0.13 */ },
+ { 53677, 31, /* 0.12 */ },
+ { 56230, 30, /* 0.12 */ },
+ { 58932, 30, /* 0.12 */ },
+ { 61799, 29, /* 0.12 */ },
+ { 64851, 28, /* 0.11 */ },
+ { 68113, 28, /* 0.11 */ },
+ { 71617, 27, /* 0.11 */ },
+ { 75401, 26, /* 0.10 */ },
+ { 79517, 26, /* 0.10 */ },
+ { 84035, 25, /* 0.10 */ },
+ { 89053, 24, /* 0.10 */ },
};
#define HSTCP_AIMD_MAX ARRAY_SIZE(hstcp_aimd_vals)
diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c
index 031361311a8..58469fff6c1 100644
--- a/net/ipv4/tcp_htcp.c
+++ b/net/ipv4/tcp_htcp.c
@@ -98,7 +98,8 @@ static inline void measure_rtt(struct sock *sk, u32 srtt)
}
}
-static void measure_achieved_throughput(struct sock *sk, u32 pkts_acked, s32 rtt)
+static void measure_achieved_throughput(struct sock *sk,
+ u32 pkts_acked, s32 rtt)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
const struct tcp_sock *tp = tcp_sk(sk);
@@ -148,8 +149,8 @@ static inline void htcp_beta_update(struct htcp *ca, u32 minRTT, u32 maxRTT)
if (use_bandwidth_switch) {
u32 maxB = ca->maxB;
u32 old_maxB = ca->old_maxB;
- ca->old_maxB = ca->maxB;
+ ca->old_maxB = ca->maxB;
if (!between(5 * maxB, 4 * old_maxB, 6 * old_maxB)) {
ca->beta = BETA_MIN;
ca->modeswitch = 0;
@@ -270,6 +271,7 @@ static void htcp_state(struct sock *sk, u8 new_state)
case TCP_CA_Open:
{
struct htcp *ca = inet_csk_ca(sk);
+
if (ca->undo_last_cong) {
ca->last_cong = jiffies;
ca->undo_last_cong = 0;
diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c
index d8f8f05a495..f963b274f2b 100644
--- a/net/ipv4/tcp_hybla.c
+++ b/net/ipv4/tcp_hybla.c
@@ -29,7 +29,6 @@ static int rtt0 = 25;
module_param(rtt0, int, 0644);
MODULE_PARM_DESC(rtt0, "reference rout trip time (ms)");
-
/* This is called to refresh values for hybla parameters */
static inline void hybla_recalc_param (struct sock *sk)
{
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index 5999b3972e6..1d5a30a90ad 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -284,7 +284,7 @@ static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked)
delta = (tp->snd_cwnd_cnt * ca->alpha) >> ALPHA_SHIFT;
if (delta >= tp->snd_cwnd) {
tp->snd_cwnd = min(tp->snd_cwnd + delta / tp->snd_cwnd,
- (u32) tp->snd_cwnd_clamp);
+ (u32)tp->snd_cwnd_clamp);
tp->snd_cwnd_cnt = 0;
}
}
@@ -299,7 +299,6 @@ static u32 tcp_illinois_ssthresh(struct sock *sk)
return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->beta) >> BETA_SHIFT), 2U);
}
-
/* Extract info for Tcp socket info provided via netlink. */
static void tcp_illinois_info(struct sock *sk, u32 ext,
struct sk_buff *skb)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a906e0200ff..f97003ad0af 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1888,21 +1888,21 @@ static inline void tcp_reset_reno_sack(struct tcp_sock *tp)
tp->sacked_out = 0;
}
-static void tcp_clear_retrans_partial(struct tcp_sock *tp)
+void tcp_clear_retrans(struct tcp_sock *tp)
{
tp->retrans_out = 0;
tp->lost_out = 0;
-
tp->undo_marker = 0;
tp->undo_retrans = -1;
+ tp->fackets_out = 0;
+ tp->sacked_out = 0;
}
-void tcp_clear_retrans(struct tcp_sock *tp)
+static inline void tcp_init_undo(struct tcp_sock *tp)
{
- tcp_clear_retrans_partial(tp);
-
- tp->fackets_out = 0;
- tp->sacked_out = 0;
+ tp->undo_marker = tp->snd_una;
+ /* Retransmission still in flight may cause DSACKs later. */
+ tp->undo_retrans = tp->retrans_out ? : -1;
}
/* Enter Loss state. If we detect SACK reneging, forget all SACK information
@@ -1925,18 +1925,18 @@ void tcp_enter_loss(struct sock *sk)
tp->prior_ssthresh = tcp_current_ssthresh(sk);
tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
tcp_ca_event(sk, CA_EVENT_LOSS);
+ tcp_init_undo(tp);
}
tp->snd_cwnd = 1;
tp->snd_cwnd_cnt = 0;
tp->snd_cwnd_stamp = tcp_time_stamp;
- tcp_clear_retrans_partial(tp);
+ tp->retrans_out = 0;
+ tp->lost_out = 0;
if (tcp_is_reno(tp))
tcp_reset_reno_sack(tp);
- tp->undo_marker = tp->snd_una;
-
skb = tcp_write_queue_head(sk);
is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED);
if (is_reneg) {
@@ -1950,9 +1950,6 @@ void tcp_enter_loss(struct sock *sk)
if (skb == tcp_send_head(sk))
break;
- if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
- tp->undo_marker = 0;
-
TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || is_reneg) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
@@ -2671,8 +2668,7 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack)
NET_INC_STATS_BH(sock_net(sk), mib_idx);
tp->prior_ssthresh = 0;
- tp->undo_marker = tp->snd_una;
- tp->undo_retrans = tp->retrans_out ? : -1;
+ tcp_init_undo(tp);
if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
if (!ece_ack)
@@ -2971,7 +2967,8 @@ void tcp_rearm_rto(struct sock *sk)
if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
struct sk_buff *skb = tcp_write_queue_head(sk);
- const u32 rto_time_stamp = TCP_SKB_CB(skb)->when + rto;
+ const u32 rto_time_stamp =
+ tcp_skb_timestamp(skb) + rto;
s32 delta = (s32)(rto_time_stamp - tcp_time_stamp);
/* delta may not be positive if the socket is locked
* when the retrans timer fires and is rescheduled.
@@ -5910,7 +5907,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
struct request_sock *req;
struct tcp_sock *tp = tcp_sk(sk);
struct dst_entry *dst = NULL;
- __u32 isn = TCP_SKB_CB(skb)->when;
+ __u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn;
bool want_cookie = false, fastopen;
struct flowi fl;
struct tcp_fastopen_cookie foc = { .len = -1 };
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index cd17f009aed..3f9bc3f0bba 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -90,7 +90,6 @@ int sysctl_tcp_tw_reuse __read_mostly;
int sysctl_tcp_low_latency __read_mostly;
EXPORT_SYMBOL(sysctl_tcp_low_latency);
-
#ifdef CONFIG_TCP_MD5SIG
static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
__be32 daddr, __be32 saddr, const struct tcphdr *th);
@@ -438,8 +437,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
skb = tcp_write_queue_head(sk);
BUG_ON(!skb);
- remaining = icsk->icsk_rto - min(icsk->icsk_rto,
- tcp_time_stamp - TCP_SKB_CB(skb)->when);
+ remaining = icsk->icsk_rto -
+ min(icsk->icsk_rto,
+ tcp_time_stamp - tcp_skb_timestamp(skb));
if (remaining) {
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
@@ -1269,7 +1269,7 @@ struct request_sock_ops tcp_request_sock_ops __read_mostly = {
.send_ack = tcp_v4_reqsk_send_ack,
.destructor = tcp_v4_reqsk_destructor,
.send_reset = tcp_v4_send_reset,
- .syn_ack_timeout = tcp_syn_ack_timeout,
+ .syn_ack_timeout = tcp_syn_ack_timeout,
};
static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
@@ -1628,7 +1628,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
skb->len - th->doff * 4);
TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
- TCP_SKB_CB(skb)->when = 0;
+ TCP_SKB_CB(skb)->tcp_tw_isn = 0;
TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
TCP_SKB_CB(skb)->sacked = 0;
@@ -2183,7 +2183,7 @@ int tcp_seq_open(struct inode *inode, struct file *file)
s = ((struct seq_file *)file->private_data)->private;
s->family = afinfo->family;
- s->last_pos = 0;
+ s->last_pos = 0;
return 0;
}
EXPORT_SYMBOL(tcp_seq_open);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 1649988bd1b..a058f411d3a 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -232,7 +232,7 @@ kill:
u32 isn = tcptw->tw_snd_nxt + 65535 + 2;
if (isn == 0)
isn++;
- TCP_SKB_CB(skb)->when = isn;
+ TCP_SKB_CB(skb)->tcp_tw_isn = isn;
return TCP_TW_SYN;
}
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index bc1b83cb830..72912533a19 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -288,35 +288,14 @@ static int tcp_v4_gso_send_check(struct sk_buff *skb)
static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
{
- /* Use the IP hdr immediately proceeding for this transport */
- const struct iphdr *iph = skb_gro_network_header(skb);
- __wsum wsum;
-
/* Don't bother verifying checksum if we're going to flush anyway. */
- if (NAPI_GRO_CB(skb)->flush)
- goto skip_csum;
-
- wsum = NAPI_GRO_CB(skb)->csum;
-
- switch (skb->ip_summed) {
- case CHECKSUM_NONE:
- wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb),
- 0);
-
- /* fall through */
-
- case CHECKSUM_COMPLETE:
- if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr,
- wsum)) {
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- break;
- }
-
+ if (!NAPI_GRO_CB(skb)->flush &&
+ skb_gro_checksum_validate(skb, IPPROTO_TCP,
+ inet_gro_compute_pseudo)) {
NAPI_GRO_CB(skb)->flush = 1;
return NULL;
}
-skip_csum:
return tcp_gro_receive(head, skb);
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5a7c41fbc6d..7f1280dcad5 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -550,7 +550,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
if (likely(sysctl_tcp_timestamps && *md5 == NULL)) {
opts->options |= OPTION_TS;
- opts->tsval = TCP_SKB_CB(skb)->when + tp->tsoffset;
+ opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset;
opts->tsecr = tp->rx_opt.ts_recent;
remaining -= TCPOLEN_TSTAMP_ALIGNED;
}
@@ -618,7 +618,7 @@ static unsigned int tcp_synack_options(struct sock *sk,
}
if (likely(ireq->tstamp_ok)) {
opts->options |= OPTION_TS;
- opts->tsval = TCP_SKB_CB(skb)->when;
+ opts->tsval = tcp_skb_timestamp(skb);
opts->tsecr = req->ts_recent;
remaining -= TCPOLEN_TSTAMP_ALIGNED;
}
@@ -647,7 +647,6 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
struct tcp_out_options *opts,
struct tcp_md5sig_key **md5)
{
- struct tcp_skb_cb *tcb = skb ? TCP_SKB_CB(skb) : NULL;
struct tcp_sock *tp = tcp_sk(sk);
unsigned int size = 0;
unsigned int eff_sacks;
@@ -666,7 +665,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
if (likely(tp->rx_opt.tstamp_ok)) {
opts->options |= OPTION_TS;
- opts->tsval = tcb ? tcb->when + tp->tsoffset : 0;
+ opts->tsval = skb ? tcp_skb_timestamp(skb) + tp->tsoffset : 0;
opts->tsecr = tp->rx_opt.ts_recent;
size += TCPOLEN_TSTAMP_ALIGNED;
}
@@ -886,8 +885,6 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
skb = skb_clone(skb, gfp_mask);
if (unlikely(!skb))
return -ENOBUFS;
- /* Our usage of tstamp should remain private */
- skb->tstamp.tv64 = 0;
}
inet = inet_sk(sk);
@@ -975,7 +972,10 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,
tcp_skb_pcount(skb));
+ /* Our usage of tstamp should remain private */
+ skb->tstamp.tv64 = 0;
err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
+
if (likely(err <= 0))
return err;
@@ -1146,10 +1146,6 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
buff->ip_summed = skb->ip_summed;
- /* Looks stupid, but our code really uses when of
- * skbs, which it never sent before. --ANK
- */
- TCP_SKB_CB(buff)->when = TCP_SKB_CB(skb)->when;
buff->tstamp = skb->tstamp;
tcp_fragment_tstamp(skb, buff);
@@ -1874,8 +1870,8 @@ static int tcp_mtu_probe(struct sock *sk)
tcp_init_tso_segs(sk, nskb, nskb->len);
/* We're ready to send. If this fails, the probe will
- * be resegmented into mss-sized pieces by tcp_write_xmit(). */
- TCP_SKB_CB(nskb)->when = tcp_time_stamp;
+ * be resegmented into mss-sized pieces by tcp_write_xmit().
+ */
if (!tcp_transmit_skb(sk, nskb, 1, GFP_ATOMIC)) {
/* Decrement cwnd here because we are sending
* effectively two packets. */
@@ -1935,8 +1931,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
BUG_ON(!tso_segs);
if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) {
- /* "when" is used as a start point for the retransmit timer */
- TCP_SKB_CB(skb)->when = tcp_time_stamp;
+ /* "skb_mstamp" is used as a start point for the retransmit timer */
+ skb_mstamp_get(&skb->skb_mstamp);
goto repair; /* Skip network transmission */
}
@@ -2000,8 +1996,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
break;
- TCP_SKB_CB(skb)->when = tcp_time_stamp;
-
if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
break;
@@ -2499,7 +2493,6 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
/* Make a copy, if the first transmission SKB clone we made
* is still in somebody's hands, else make a clone.
*/
- TCP_SKB_CB(skb)->when = tcp_time_stamp;
/* make sure skb->data is aligned on arches that require it
* and check if ack-trimming & collapsing extended the headroom
@@ -2544,7 +2537,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
/* Save stamp of the first retransmit. */
if (!tp->retrans_stamp)
- tp->retrans_stamp = TCP_SKB_CB(skb)->when;
+ tp->retrans_stamp = tcp_skb_timestamp(skb);
/* snd_nxt is stored to detect loss of retransmitted segment,
* see tcp_input.c tcp_sacktag_write_queue().
@@ -2752,7 +2745,6 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk),
TCPHDR_ACK | TCPHDR_RST);
/* Send it off. */
- TCP_SKB_CB(skb)->when = tcp_time_stamp;
if (tcp_transmit_skb(sk, skb, 0, priority))
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
@@ -2791,7 +2783,6 @@ int tcp_send_synack(struct sock *sk)
TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ACK;
TCP_ECN_send_synack(tcp_sk(sk), skb);
}
- TCP_SKB_CB(skb)->when = tcp_time_stamp;
return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
}
@@ -2835,10 +2826,10 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
memset(&opts, 0, sizeof(opts));
#ifdef CONFIG_SYN_COOKIES
if (unlikely(req->cookie_ts))
- TCP_SKB_CB(skb)->when = cookie_init_timestamp(req);
+ skb->skb_mstamp.stamp_jiffies = cookie_init_timestamp(req);
else
#endif
- TCP_SKB_CB(skb)->when = tcp_time_stamp;
+ skb_mstamp_get(&skb->skb_mstamp);
tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, &md5,
foc) + sizeof(*th);
@@ -3086,7 +3077,7 @@ int tcp_connect(struct sock *sk)
skb_reserve(buff, MAX_TCP_HEADER);
tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);
- tp->retrans_stamp = TCP_SKB_CB(buff)->when = tcp_time_stamp;
+ tp->retrans_stamp = tcp_time_stamp;
tcp_connect_queue_skb(sk, buff);
TCP_ECN_send_syn(sk, buff);
@@ -3194,7 +3185,7 @@ void tcp_send_ack(struct sock *sk)
tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK);
/* Send it off, this clears delayed acks for us. */
- TCP_SKB_CB(buff)->when = tcp_time_stamp;
+ skb_mstamp_get(&buff->skb_mstamp);
tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC));
}
@@ -3226,7 +3217,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
* send it.
*/
tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK);
- TCP_SKB_CB(skb)->when = tcp_time_stamp;
+ skb_mstamp_get(&skb->skb_mstamp);
return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC);
}
@@ -3270,7 +3261,6 @@ int tcp_write_wakeup(struct sock *sk)
tcp_set_skb_tso_segs(sk, skb, mss);
TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
- TCP_SKB_CB(skb)->when = tcp_time_stamp;
err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
if (!err)
tcp_event_new_data_sent(sk, skb);
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index 3b66610d415..ebf5ff57526 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -83,7 +83,6 @@ static struct {
struct tcp_log *log;
} tcp_probe;
-
static inline int tcp_probe_used(void)
{
return (tcp_probe.head - tcp_probe.tail) & (bufsize - 1);
@@ -101,7 +100,6 @@ static inline int tcp_probe_avail(void)
si4.sin_addr.s_addr = inet->inet_##mem##addr; \
} while (0) \
-
/*
* Hook inserted to be called before each receive packet.
* Note: arguments must match tcp_rcv_established()!
@@ -194,8 +192,8 @@ static int tcpprobe_sprint(char *tbuf, int n)
return scnprintf(tbuf, n,
"%lu.%09lu %pISpc %pISpc %d %#x %#x %u %u %u %u %u\n",
- (unsigned long) tv.tv_sec,
- (unsigned long) tv.tv_nsec,
+ (unsigned long)tv.tv_sec,
+ (unsigned long)tv.tv_nsec,
&p->src, &p->dst, p->length, p->snd_nxt, p->snd_una,
p->snd_cwnd, p->ssthresh, p->snd_wnd, p->srtt, p->rcv_wnd);
}
diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c
index 8250949b885..6824afb65d9 100644
--- a/net/ipv4/tcp_scalable.c
+++ b/net/ipv4/tcp_scalable.c
@@ -31,10 +31,10 @@ static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked)
static u32 tcp_scalable_ssthresh(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
+
return max(tp->snd_cwnd - (tp->snd_cwnd>>TCP_SCALABLE_MD_SCALE), 2U);
}
-
static struct tcp_congestion_ops tcp_scalable __read_mostly = {
.ssthresh = tcp_scalable_ssthresh,
.cong_avoid = tcp_scalable_cong_avoid,
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index df90cd1ce37..a339e7ba05a 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -135,10 +135,9 @@ static bool retransmits_timed_out(struct sock *sk,
if (!inet_csk(sk)->icsk_retransmits)
return false;
- if (unlikely(!tcp_sk(sk)->retrans_stamp))
- start_ts = TCP_SKB_CB(tcp_write_queue_head(sk))->when;
- else
- start_ts = tcp_sk(sk)->retrans_stamp;
+ start_ts = tcp_sk(sk)->retrans_stamp;
+ if (unlikely(!start_ts))
+ start_ts = tcp_skb_timestamp(tcp_write_queue_head(sk));
if (likely(timeout == 0)) {
linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base);
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index b40ad897f94..a6afde666ab 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -51,7 +51,6 @@ MODULE_PARM_DESC(beta, "upper bound of packets in network");
module_param(gamma, int, 0644);
MODULE_PARM_DESC(gamma, "limit on increase (scale by 2)");
-
/* There are several situations when we must "re-start" Vegas:
*
* o when a connection is established
@@ -133,7 +132,6 @@ EXPORT_SYMBOL_GPL(tcp_vegas_pkts_acked);
void tcp_vegas_state(struct sock *sk, u8 ca_state)
{
-
if (ca_state == TCP_CA_Open)
vegas_enable(sk);
else
@@ -285,7 +283,6 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked)
/* Use normal slow start */
else if (tp->snd_cwnd <= tp->snd_ssthresh)
tcp_slow_start(tp, acked);
-
}
/* Extract info for Tcp socket info provided via netlink. */
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index 8276977d2c8..a4d2d2d88dc 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -175,7 +175,6 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
} else
tp->snd_cwnd_cnt++;
}
-
}
if (tp->snd_cwnd < 2)
tp->snd_cwnd = 2;
diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c
index b94a04ae2ed..81911a92356 100644
--- a/net/ipv4/tcp_westwood.c
+++ b/net/ipv4/tcp_westwood.c
@@ -42,7 +42,6 @@ struct westwood {
u8 reset_rtt_min; /* Reset RTT min to next RTT sample*/
};
-
/* TCP Westwood functions and constants */
#define TCP_WESTWOOD_RTT_MIN (HZ/20) /* 50ms */
#define TCP_WESTWOOD_INIT_RTT (20*HZ) /* maybe too conservative?! */
@@ -153,7 +152,6 @@ static inline void update_rtt_min(struct westwood *w)
w->rtt_min = min(w->rtt, w->rtt_min);
}
-
/*
* @westwood_fast_bw
* It is called when we are in fast path. In particular it is called when
@@ -208,7 +206,6 @@ static inline u32 westwood_acked_count(struct sock *sk)
return w->cumul_ack;
}
-
/*
* TCP Westwood
* Here limit is evaluated as Bw estimation*RTTmin (for obtaining it
@@ -219,6 +216,7 @@ static u32 tcp_westwood_bw_rttmin(const struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
const struct westwood *w = inet_csk_ca(sk);
+
return max_t(u32, (w->bw_est * w->rtt_min) / tp->mss_cache, 2);
}
@@ -254,12 +252,12 @@ static void tcp_westwood_event(struct sock *sk, enum tcp_ca_event event)
}
}
-
/* Extract info for Tcp socket info provided via netlink. */
static void tcp_westwood_info(struct sock *sk, u32 ext,
struct sk_buff *skb)
{
const struct westwood *ca = inet_csk_ca(sk);
+
if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
struct tcpvegas_info info = {
.tcpv_enabled = 1,
@@ -271,7 +269,6 @@ static void tcp_westwood_info(struct sock *sk, u32 ext,
}
}
-
static struct tcp_congestion_ops tcp_westwood __read_mostly = {
.init = tcp_westwood_init,
.ssthresh = tcp_reno_ssthresh,
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index 599b79b8eac..cd727321859 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -54,10 +54,8 @@ static void tcp_yeah_init(struct sock *sk)
/* Ensure the MD arithmetic works. This is somewhat pedantic,
* since I don't think we will see a cwnd this large. :) */
tp->snd_cwnd_clamp = min_t(u32, tp->snd_cwnd_clamp, 0xffffffff/128);
-
}
-
static void tcp_yeah_pkts_acked(struct sock *sk, u32 pkts_acked, s32 rtt_us)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -84,7 +82,7 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked)
/* Scalable */
tp->snd_cwnd_cnt += yeah->pkts_acked;
- if (tp->snd_cwnd_cnt > min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT)){
+ if (tp->snd_cwnd_cnt > min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT)) {
if (tp->snd_cwnd < tp->snd_cwnd_clamp)
tp->snd_cwnd++;
tp->snd_cwnd_cnt = 0;
@@ -120,7 +118,6 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked)
*/
if (after(ack, yeah->vegas.beg_snd_nxt)) {
-
/* We do the Vegas calculations only if we got enough RTT
* samples that we can be reasonably sure that we got
* at least one RTT sample that wasn't from a delayed ACK.
@@ -189,7 +186,6 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked)
}
yeah->lastQ = queue;
-
}
/* Save the extent of the current window so we can use this
@@ -205,7 +201,8 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked)
}
}
-static u32 tcp_yeah_ssthresh(struct sock *sk) {
+static u32 tcp_yeah_ssthresh(struct sock *sk)
+{
const struct tcp_sock *tp = tcp_sk(sk);
struct yeah *yeah = inet_csk_ca(sk);
u32 reduction;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index f57c0e4c232..cd0db5471bb 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -99,6 +99,7 @@
#include <linux/slab.h>
#include <net/tcp_states.h>
#include <linux/skbuff.h>
+#include <linux/netdevice.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <net/net_namespace.h>
@@ -224,7 +225,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
remaining = (high - low) + 1;
rand = prandom_u32();
- first = (((u64)rand * remaining) >> 32) + low;
+ first = reciprocal_scale(rand, remaining) + low;
/*
* force rand to be an odd multiple of UDP_HTABLE_SIZE
*/
@@ -448,7 +449,7 @@ begin:
}
} else if (score == badness && reuseport) {
matches++;
- if (((u64)hash * matches) >> 32 == 0)
+ if (reciprocal_scale(hash, matches) == 0)
result = sk;
hash = next_pseudo_random32(hash);
}
@@ -529,7 +530,7 @@ begin:
}
} else if (score == badness && reuseport) {
matches++;
- if (((u64)hash * matches) >> 32 == 0)
+ if (reciprocal_scale(hash, matches) == 0)
result = sk;
hash = next_pseudo_random32(hash);
}
@@ -1787,6 +1788,10 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
if (sk != NULL) {
int ret;
+ if (udp_sk(sk)->convert_csum && uh->check && !IS_UDPLITE(sk))
+ skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+ inet_compute_pseudo);
+
ret = udp_queue_rcv_skb(sk, skb);
sock_put(sk);
@@ -1967,7 +1972,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
return;
skb->sk = sk;
- skb->destructor = sock_edemux;
+ skb->destructor = sock_efree;
dst = sk->sk_rx_dst;
if (dst)
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 59035bc3008..84e0e05c9c0 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -228,30 +228,24 @@ unlock:
}
EXPORT_SYMBOL(udp_del_offload);
-static struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
+ struct udphdr *uh)
{
struct udp_offload_priv *uo_priv;
struct sk_buff *p, **pp = NULL;
- struct udphdr *uh, *uh2;
- unsigned int hlen, off;
+ struct udphdr *uh2;
+ unsigned int off = skb_gro_offset(skb);
int flush = 1;
if (NAPI_GRO_CB(skb)->udp_mark ||
- (!skb->encapsulation && skb->ip_summed != CHECKSUM_COMPLETE))
+ (skb->ip_summed != CHECKSUM_PARTIAL &&
+ NAPI_GRO_CB(skb)->csum_cnt == 0 &&
+ !NAPI_GRO_CB(skb)->csum_valid))
goto out;
/* mark that this skb passed once through the udp gro layer */
NAPI_GRO_CB(skb)->udp_mark = 1;
- off = skb_gro_offset(skb);
- hlen = off + sizeof(*uh);
- uh = skb_gro_header_fast(skb, off);
- if (skb_gro_header_hard(skb, hlen)) {
- uh = skb_gro_header_slow(skb, hlen, off);
- if (unlikely(!uh))
- goto out;
- }
-
rcu_read_lock();
uo_priv = rcu_dereference(udp_offload_base);
for (; uo_priv != NULL; uo_priv = rcu_dereference(uo_priv->next)) {
@@ -269,7 +263,12 @@ unflush:
continue;
uh2 = (struct udphdr *)(p->data + off);
- if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) {
+
+ /* Match ports and either checksums are either both zero
+ * or nonzero.
+ */
+ if ((*(u32 *)&uh->source != *(u32 *)&uh2->source) ||
+ (!uh->check ^ !uh2->check)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
@@ -286,7 +285,33 @@ out:
return pp;
}
-static int udp_gro_complete(struct sk_buff *skb, int nhoff)
+static struct sk_buff **udp4_gro_receive(struct sk_buff **head,
+ struct sk_buff *skb)
+{
+ struct udphdr *uh = udp_gro_udphdr(skb);
+
+ if (unlikely(!uh))
+ goto flush;
+
+ /* Don't bother verifying checksum if we're going to flush anyway. */
+ if (!NAPI_GRO_CB(skb)->flush)
+ goto skip;
+
+ if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
+ inet_gro_compute_pseudo))
+ goto flush;
+ else if (uh->check)
+ skb_gro_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+ inet_gro_compute_pseudo);
+skip:
+ return udp_gro_receive(head, skb, uh);
+
+flush:
+ NAPI_GRO_CB(skb)->flush = 1;
+ return NULL;
+}
+
+int udp_gro_complete(struct sk_buff *skb, int nhoff)
{
struct udp_offload_priv *uo_priv;
__be16 newlen = htons(skb->len - nhoff);
@@ -311,12 +336,24 @@ static int udp_gro_complete(struct sk_buff *skb, int nhoff)
return err;
}
+int udp4_gro_complete(struct sk_buff *skb, int nhoff)
+{
+ const struct iphdr *iph = ip_hdr(skb);
+ struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
+
+ if (uh->check)
+ uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr,
+ iph->daddr, 0);
+
+ return udp_gro_complete(skb, nhoff);
+}
+
static const struct net_offload udpv4_offload = {
.callbacks = {
.gso_send_check = udp4_ufo_send_check,
.gso_segment = udp4_ufo_fragment,
- .gro_receive = udp_gro_receive,
- .gro_complete = udp_gro_complete,
+ .gro_receive = udp4_gro_receive,
+ .gro_complete = udp4_gro_complete,
},
};
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index fc1fac2a052..ad4598fcc41 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -180,7 +180,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.rtr_solicits = MAX_RTR_SOLICITATIONS,
.rtr_solicit_interval = RTR_SOLICITATION_INTERVAL,
.rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY,
- .use_tempaddr = 0,
+ .use_tempaddr = 0,
.temp_valid_lft = TEMP_VALID_LIFETIME,
.temp_prefered_lft = TEMP_PREFERRED_LIFETIME,
.regen_max_retry = REGEN_MAX_RETRY,
@@ -1105,8 +1105,8 @@ retry:
spin_unlock_bh(&ifp->lock);
regen_advance = idev->cnf.regen_max_retry *
- idev->cnf.dad_transmits *
- NEIGH_VAR(idev->nd_parms, RETRANS_TIME) / HZ;
+ idev->cnf.dad_transmits *
+ NEIGH_VAR(idev->nd_parms, RETRANS_TIME) / HZ;
write_unlock_bh(&idev->lock);
/* A temporary address is created only if this calculated Preferred
@@ -3030,7 +3030,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
struct hlist_head *h = &inet6_addr_lst[i];
spin_lock_bh(&addrconf_hash_lock);
- restart:
+restart:
hlist_for_each_entry_rcu(ifa, h, addr_lst) {
if (ifa->idev == idev) {
hlist_del_init_rcu(&ifa->addr_lst);
@@ -3542,8 +3542,8 @@ static void __net_exit if6_proc_net_exit(struct net *net)
}
static struct pernet_operations if6_proc_net_ops = {
- .init = if6_proc_net_init,
- .exit = if6_proc_net_exit,
+ .init = if6_proc_net_init,
+ .exit = if6_proc_net_exit,
};
int __init if6_proc_init(void)
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 2daa3a133e4..b9393e6a21f 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -7,15 +7,15 @@
*
* Adapted from linux/net/ipv4/af_inet.c
*
- * Fixes:
+ * Fixes:
* piggy, Karl Knutson : Socket protocol table
- * Hideaki YOSHIFUJI : sin6_scope_id support
- * Arnaldo Melo : check proc_net_create return, cleanups
+ * Hideaki YOSHIFUJI : sin6_scope_id support
+ * Arnaldo Melo : check proc_net_create return, cleanups
*
* This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
*/
#define pr_fmt(fmt) "IPv6: " fmt
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 72a4930bdc0..fcffd4e522c 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -17,10 +17,10 @@
* Authors
*
* Mitsuru KANDA @USAGI : IPv6 Support
- * Kazunori MIYAZAWA @USAGI :
- * Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ * Kazunori MIYAZAWA @USAGI :
+ * Kunihiro Ishiguro <kunihiro@ipinfusion.com>
*
- * This file is derived from net/ipv4/ah.c.
+ * This file is derived from net/ipv4/ah.c.
*/
#define pr_fmt(fmt) "IPv6: " fmt
@@ -284,7 +284,7 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir)
ipv6_rearrange_rthdr(iph, exthdr.rth);
break;
- default :
+ default:
return 0;
}
@@ -478,7 +478,7 @@ static void ah6_input_done(struct crypto_async_request *base, int err)
auth_data = ah_tmp_auth(work_iph, hdr_len);
icv = ah_tmp_icv(ahp->ahash, auth_data, ahp->icv_trunc_len);
- err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0;
+ err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0;
if (err)
goto out;
@@ -622,7 +622,7 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb)
goto out_free;
}
- err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0;
+ err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0;
if (err)
goto out_free;
@@ -647,8 +647,8 @@ static int ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct net *net = dev_net(skb->dev);
- struct ipv6hdr *iph = (struct ipv6hdr*)skb->data;
- struct ip_auth_hdr *ah = (struct ip_auth_hdr*)(skb->data+offset);
+ struct ipv6hdr *iph = (struct ipv6hdr *)skb->data;
+ struct ip_auth_hdr *ah = (struct ip_auth_hdr *)(skb->data+offset);
struct xfrm_state *x;
if (type != ICMPV6_PKT_TOOBIG &&
@@ -755,11 +755,10 @@ static int ah6_rcv_cb(struct sk_buff *skb, int err)
return 0;
}
-static const struct xfrm_type ah6_type =
-{
+static const struct xfrm_type ah6_type = {
.description = "AH6",
.owner = THIS_MODULE,
- .proto = IPPROTO_AH,
+ .proto = IPPROTO_AH,
.flags = XFRM_TYPE_REPLAY_PROT,
.init_state = ah6_init_state,
.destructor = ah6_destroy,
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 2753319524f..2cdc38338be 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -43,13 +43,13 @@ static bool ipv6_mapped_addr_any(const struct in6_addr *a)
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);
- struct ipv6_pinfo *np = inet6_sk(sk);
- struct in6_addr *daddr, *final_p, final;
+ struct inet_sock *inet = inet_sk(sk);
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct in6_addr *daddr, *final_p, final;
struct dst_entry *dst;
struct flowi6 fl6;
struct ip6_flowlabel *flowlabel = NULL;
- struct ipv6_txoptions *opt;
+ struct ipv6_txoptions *opt;
int addr_type;
int err;
@@ -332,7 +332,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct sock_exterr_skb *serr;
- struct sk_buff *skb, *skb2;
+ struct sk_buff *skb;
DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name);
struct {
struct sock_extended_err ee;
@@ -342,7 +342,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
int copied;
err = -EAGAIN;
- skb = skb_dequeue(&sk->sk_error_queue);
+ skb = sock_dequeue_err_skb(sk);
if (skb == NULL)
goto out;
@@ -415,17 +415,6 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
msg->msg_flags |= MSG_ERRQUEUE;
err = copied;
- /* Reset and regenerate socket error */
- spin_lock_bh(&sk->sk_error_queue.lock);
- sk->sk_err = 0;
- if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) {
- sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
- spin_unlock_bh(&sk->sk_error_queue.lock);
- sk->sk_error_report(sk);
- } else {
- spin_unlock_bh(&sk->sk_error_queue.lock);
- }
-
out_free_skb:
kfree_skb(skb);
out:
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index d15da137714..83fc3a385a2 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -17,10 +17,10 @@
* Authors
*
* Mitsuru KANDA @USAGI : IPv6 Support
- * Kazunori MIYAZAWA @USAGI :
- * Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ * Kazunori MIYAZAWA @USAGI :
+ * Kunihiro Ishiguro <kunihiro@ipinfusion.com>
*
- * This file is derived from net/ipv4/esp.c
+ * This file is derived from net/ipv4/esp.c
*/
#define pr_fmt(fmt) "IPv6: " fmt
@@ -598,7 +598,7 @@ static int esp6_init_state(struct xfrm_state *x)
case XFRM_MODE_BEET:
if (x->sel.family != AF_INET6)
x->props.header_len += IPV4_BEET_PHMAXLEN +
- (sizeof(struct ipv6hdr) - sizeof(struct iphdr));
+ (sizeof(struct ipv6hdr) - sizeof(struct iphdr));
break;
case XFRM_MODE_TRANSPORT:
break;
@@ -621,11 +621,10 @@ static int esp6_rcv_cb(struct sk_buff *skb, int err)
return 0;
}
-static const struct xfrm_type esp6_type =
-{
+static const struct xfrm_type esp6_type = {
.description = "ESP6",
- .owner = THIS_MODULE,
- .proto = IPPROTO_ESP,
+ .owner = THIS_MODULE,
+ .proto = IPPROTO_ESP,
.flags = XFRM_TYPE_REPLAY_PROT,
.init_state = esp6_init_state,
.destructor = esp6_destroy,
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 8d67900aa00..bfde361b613 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -142,7 +142,7 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb)
default: /* Other TLV code so scan list */
if (optlen > len)
goto bad;
- for (curr=procs; curr->type >= 0; curr++) {
+ for (curr = procs; curr->type >= 0; curr++) {
if (curr->type == nh[off]) {
/* type specific length/alignment
checks will be performed in the
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 06ba3e58320..394bb824fe4 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -503,7 +503,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
msg.type = type;
len = skb->len - msg.offset;
- len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) -sizeof(struct icmp6hdr));
+ len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(struct icmp6hdr));
if (len < 0) {
LIMIT_NETDEBUG(KERN_DEBUG "icmp: len problem\n");
goto out_dst_release;
@@ -636,7 +636,7 @@ void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info)
/* now skip over extension headers */
inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
&nexthdr, &frag_off);
- if (inner_offset<0)
+ if (inner_offset < 0)
goto out;
} else {
inner_offset = sizeof(struct ipv6hdr);
@@ -808,7 +808,7 @@ void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6,
memset(fl6, 0, sizeof(*fl6));
fl6->saddr = *saddr;
fl6->daddr = *daddr;
- fl6->flowi6_proto = IPPROTO_ICMPV6;
+ fl6->flowi6_proto = IPPROTO_ICMPV6;
fl6->fl6_icmp_type = type;
fl6->fl6_icmp_code = 0;
fl6->flowi6_oif = oif;
@@ -875,8 +875,8 @@ static void __net_exit icmpv6_sk_exit(struct net *net)
}
static struct pernet_operations icmpv6_sk_ops = {
- .init = icmpv6_sk_init,
- .exit = icmpv6_sk_exit,
+ .init = icmpv6_sk_init,
+ .exit = icmpv6_sk_exit,
};
int __init icmpv6_init(void)
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index a245e5ddffb..29b32206e49 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -63,7 +63,6 @@ int inet6_csk_bind_conflict(const struct sock *sk,
return sk2 != NULL;
}
-
EXPORT_SYMBOL_GPL(inet6_csk_bind_conflict);
struct dst_entry *inet6_csk_route_req(struct sock *sk,
@@ -144,7 +143,6 @@ struct request_sock *inet6_csk_search_req(const struct sock *sk,
return NULL;
}
-
EXPORT_SYMBOL_GPL(inet6_csk_search_req);
void inet6_csk_reqsk_queue_hash_add(struct sock *sk,
@@ -160,10 +158,9 @@ void inet6_csk_reqsk_queue_hash_add(struct sock *sk,
reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout);
inet_csk_reqsk_queue_added(sk, timeout);
}
-
EXPORT_SYMBOL_GPL(inet6_csk_reqsk_queue_hash_add);
-void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr)
+void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr)
{
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr;
@@ -175,7 +172,6 @@ void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr)
sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
sk->sk_bound_dev_if);
}
-
EXPORT_SYMBOL_GPL(inet6_csk_addr2sockaddr);
static inline
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 262e13c02ec..051dffb49c9 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -6,7 +6,7 @@
* Generic INET6 transport hashtables
*
* Authors: Lotsa people, from code originally in tcp, generalised here
- * by Arnaldo Carvalho de Melo <acme@mandriva.com>
+ * by Arnaldo Carvalho de Melo <acme@mandriva.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
@@ -198,7 +198,7 @@ begin:
}
} else if (score == hiscore && reuseport) {
matches++;
- if (((u64)phash * matches) >> 32 == 0)
+ if (reciprocal_scale(phash, matches) == 0)
result = sk;
phash = next_pseudo_random32(phash);
}
@@ -222,7 +222,6 @@ begin:
rcu_read_unlock();
return result;
}
-
EXPORT_SYMBOL_GPL(inet6_lookup_listener);
struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
@@ -238,7 +237,6 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
return sk;
}
-
EXPORT_SYMBOL_GPL(inet6_lookup);
static int __inet6_check_established(struct inet_timewait_death_row *death_row,
@@ -324,5 +322,4 @@ int inet6_hash_connect(struct inet_timewait_death_row *death_row,
return __inet_hash_connect(death_row, sk, inet6_sk_port_offset(sk),
__inet6_check_established, __inet6_hash);
}
-
EXPORT_SYMBOL_GPL(inet6_hash_connect);
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 4052694c6f2..3dd7d4ebd7c 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -136,7 +136,7 @@ static void ip6_fl_gc(unsigned long dummy)
spin_lock(&ip6_fl_lock);
- for (i=0; i<=FL_HASH_MASK; i++) {
+ for (i = 0; i <= FL_HASH_MASK; i++) {
struct ip6_flowlabel *fl;
struct ip6_flowlabel __rcu **flp;
@@ -239,7 +239,7 @@ static struct ip6_flowlabel *fl_intern(struct net *net,
/* Socket flowlabel lists */
-struct ip6_flowlabel * fl6_sock_lookup(struct sock *sk, __be32 label)
+struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label)
{
struct ipv6_fl_socklist *sfl;
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -259,7 +259,6 @@ struct ip6_flowlabel * fl6_sock_lookup(struct sock *sk, __be32 label)
rcu_read_unlock_bh();
return NULL;
}
-
EXPORT_SYMBOL_GPL(fl6_sock_lookup);
void fl6_free_socklist(struct sock *sk)
@@ -293,11 +292,11 @@ void fl6_free_socklist(struct sock *sk)
following rthdr.
*/
-struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions * opt_space,
- struct ip6_flowlabel * fl,
- struct ipv6_txoptions * fopt)
+struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
+ struct ip6_flowlabel *fl,
+ struct ipv6_txoptions *fopt)
{
- struct ipv6_txoptions * fl_opt = fl->opt;
+ struct ipv6_txoptions *fl_opt = fl->opt;
if (fopt == NULL || fopt->opt_flen == 0)
return fl_opt;
@@ -388,7 +387,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
goto done;
msg.msg_controllen = olen;
- msg.msg_control = (void*)(fl->opt+1);
+ msg.msg_control = (void *)(fl->opt+1);
memset(&flowi6, 0, sizeof(flowi6));
err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, fl->opt,
@@ -517,7 +516,7 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
struct net *net = sock_net(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_flowlabel_req freq;
- struct ipv6_fl_socklist *sfl1=NULL;
+ struct ipv6_fl_socklist *sfl1 = NULL;
struct ipv6_fl_socklist *sfl;
struct ipv6_fl_socklist __rcu **sflp;
struct ip6_flowlabel *fl, *fl1 = NULL;
@@ -542,7 +541,7 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
}
spin_lock_bh(&ip6_sk_fl_lock);
for (sflp = &np->ipv6_fl_list;
- (sfl = rcu_dereference(*sflp))!=NULL;
+ (sfl = rcu_dereference(*sflp)) != NULL;
sflp = &sfl->next) {
if (sfl->fl->label == freq.flr_label) {
if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK))
diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c
index 4578e23834f..14dacc544c3 100644
--- a/net/ipv6/ip6_icmp.c
+++ b/net/ipv6/ip6_icmp.c
@@ -13,7 +13,7 @@ static ip6_icmp_send_t __rcu *ip6_icmp_send;
int inet6_register_icmp_sender(ip6_icmp_send_t *fn)
{
return (cmpxchg((ip6_icmp_send_t **)&ip6_icmp_send, NULL, fn) == NULL) ?
- 0 : -EBUSY;
+ 0 : -EBUSY;
}
EXPORT_SYMBOL(inet6_register_icmp_sender);
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 51d54dc376f..a3084ab5df6 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -15,8 +15,8 @@
*/
/* Changes
*
- * Mitsuru KANDA @USAGI and
- * YOSHIFUJI Hideaki @USAGI: Remove ipv6_parse_exthdrs().
+ * Mitsuru KANDA @USAGI and
+ * YOSHIFUJI Hideaki @USAGI: Remove ipv6_parse_exthdrs().
*/
#include <linux/errno.h>
@@ -65,7 +65,7 @@ int ip6_rcv_finish(struct sk_buff *skb)
int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
const struct ipv6hdr *hdr;
- u32 pkt_len;
+ u32 pkt_len;
struct inet6_dev *idev;
struct net *net = dev_net(skb->dev);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 65eda2a8af4..5bcda338bce 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -244,7 +244,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
continue;
iph2 = (struct ipv6hdr *)(p->data + off);
- first_word = *(__be32 *)iph ^ *(__be32 *)iph2 ;
+ first_word = *(__be32 *)iph ^ *(__be32 *)iph2;
/* All fields must match except length and Traffic Class.
* XXX skbs on the gro_list have all been parsed and pulled
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 315a55d6607..b7a3e7b3378 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -20,7 +20,7 @@
* etc.
*
* H. von Brand : Added missing #include <linux/string.h>
- * Imran Patel : frag id should be in NBO
+ * Imran Patel : frag id should be in NBO
* Kazunori MIYAZAWA @USAGI
* : add ip6_append_data and related functions
* for datagram xmit
@@ -233,7 +233,6 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
kfree_skb(skb);
return -EMSGSIZE;
}
-
EXPORT_SYMBOL(ip6_xmit);
static int ip6_call_ra_chain(struct sk_buff *skb, int sel)
@@ -555,14 +554,14 @@ static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
{
struct sk_buff *frag;
- struct rt6_info *rt = (struct rt6_info*)skb_dst(skb);
+ struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
struct ipv6hdr *tmp_hdr;
struct frag_hdr *fh;
unsigned int mtu, hlen, left, len;
int hroom, troom;
__be32 frag_id = 0;
- int ptr, offset = 0, err=0;
+ int ptr, offset = 0, err = 0;
u8 *prevhdr, nexthdr = 0;
struct net *net = dev_net(skb_dst(skb)->dev);
@@ -637,7 +636,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
}
__skb_pull(skb, hlen);
- fh = (struct frag_hdr*)__skb_push(skb, sizeof(struct frag_hdr));
+ fh = (struct frag_hdr *)__skb_push(skb, sizeof(struct frag_hdr));
__skb_push(skb, hlen);
skb_reset_network_header(skb);
memcpy(skb_network_header(skb), tmp_hdr, hlen);
@@ -662,7 +661,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
if (frag) {
frag->ip_summed = CHECKSUM_NONE;
skb_reset_transport_header(frag);
- fh = (struct frag_hdr*)__skb_push(frag, sizeof(struct frag_hdr));
+ fh = (struct frag_hdr *)__skb_push(frag, sizeof(struct frag_hdr));
__skb_push(frag, hlen);
skb_reset_network_header(frag);
memcpy(skb_network_header(frag), tmp_hdr,
@@ -681,7 +680,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
}
err = output(skb);
- if(!err)
+ if (!err)
IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
IPSTATS_MIB_FRAGCREATES);
@@ -742,7 +741,7 @@ slow_path:
/*
* Keep copying data until we run out.
*/
- while(left > 0) {
+ while (left > 0) {
len = left;
/* IF: it doesn't fit, use 'mtu' - the data space left */
if (len > mtu)
@@ -865,7 +864,7 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
/* Yes, checking route validity in not connected
* case is not very simple. Take into account,
* that we do not support routing by source, TOS,
- * and MSG_DONTROUTE --ANK (980726)
+ * and MSG_DONTROUTE --ANK (980726)
*
* 1. ip6_rt_check(): If route was host route,
* check that cached destination is current.
@@ -1049,7 +1048,7 @@ static inline int ip6_ufo_append_data(struct sock *sk,
int getfrag(void *from, char *to, int offset, int len,
int odd, struct sk_buff *skb),
void *from, int length, int hh_len, int fragheaderlen,
- int transhdrlen, int mtu,unsigned int flags,
+ int transhdrlen, int mtu, unsigned int flags,
struct rt6_info *rt)
{
@@ -1072,7 +1071,7 @@ static inline int ip6_ufo_append_data(struct sock *sk,
skb_reserve(skb, hh_len);
/* create space for UDP/IP header */
- skb_put(skb,fragheaderlen + transhdrlen);
+ skb_put(skb, fragheaderlen + transhdrlen);
/* initialize network header pointer */
skb_reset_network_header(skb);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index f9de5a69507..e01bd039929 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -408,12 +408,12 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
{
const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) raw;
__u8 nexthdr = ipv6h->nexthdr;
- __u16 off = sizeof (*ipv6h);
+ __u16 off = sizeof(*ipv6h);
while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) {
__u16 optlen = 0;
struct ipv6_opt_hdr *hdr;
- if (raw + off + sizeof (*hdr) > skb->data &&
+ if (raw + off + sizeof(*hdr) > skb->data &&
!pskb_may_pull(skb, raw - skb->data + off + sizeof (*hdr)))
break;
@@ -530,7 +530,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
mtu = IPV6_MIN_MTU;
t->dev->mtu = mtu;
- if ((len = sizeof (*ipv6h) + ntohs(ipv6h->payload_len)) > mtu) {
+ if ((len = sizeof(*ipv6h) + ntohs(ipv6h->payload_len)) > mtu) {
rel_type = ICMPV6_PKT_TOOBIG;
rel_code = 0;
rel_info = mtu;
@@ -991,7 +991,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
t->parms.name);
goto tx_err_dst_release;
}
- mtu = dst_mtu(dst) - sizeof (*ipv6h);
+ mtu = dst_mtu(dst) - sizeof(*ipv6h);
if (encap_limit >= 0) {
max_headroom += 8;
mtu -= 8;
@@ -1083,7 +1083,7 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
encap_limit = t->parms.encap_limit;
- memcpy(&fl6, &t->fl.u.ip6, sizeof (fl6));
+ memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_IPIP;
dsfield = ipv4_get_dsfield(iph);
@@ -1135,7 +1135,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
} else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
encap_limit = t->parms.encap_limit;
- memcpy(&fl6, &t->fl.u.ip6, sizeof (fl6));
+ memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_IPV6;
dsfield = ipv6_get_dsfield(ipv6h);
@@ -1229,11 +1229,11 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
if (rt->dst.dev) {
dev->hard_header_len = rt->dst.dev->hard_header_len +
- sizeof (struct ipv6hdr);
+ sizeof(struct ipv6hdr);
- dev->mtu = rt->dst.dev->mtu - sizeof (struct ipv6hdr);
+ dev->mtu = rt->dst.dev->mtu - sizeof(struct ipv6hdr);
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
- dev->mtu-=8;
+ dev->mtu -= 8;
if (dev->mtu < IPV6_MIN_MTU)
dev->mtu = IPV6_MIN_MTU;
@@ -1350,7 +1350,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
switch (cmd) {
case SIOCGETTUNNEL:
if (dev == ip6n->fb_tnl_dev) {
- if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p))) {
+ if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
err = -EFAULT;
break;
}
@@ -1362,7 +1362,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
memset(&p, 0, sizeof(p));
}
ip6_tnl_parm_to_user(&p, &t->parms);
- if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof (p))) {
+ if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) {
err = -EFAULT;
}
break;
@@ -1372,7 +1372,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
break;
err = -EFAULT;
- if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p)))
+ if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
break;
err = -EINVAL;
if (p.proto != IPPROTO_IPV6 && p.proto != IPPROTO_IPIP &&
@@ -1407,7 +1407,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
if (dev == ip6n->fb_tnl_dev) {
err = -EFAULT;
- if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof (p)))
+ if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
break;
err = -ENOENT;
ip6_tnl_parm_from_user(&p1, &p);
@@ -1482,11 +1482,11 @@ static void ip6_tnl_dev_setup(struct net_device *dev)
dev->destructor = ip6_dev_free;
dev->type = ARPHRD_TUNNEL6;
- dev->hard_header_len = LL_MAX_HEADER + sizeof (struct ipv6hdr);
- dev->mtu = ETH_DATA_LEN - sizeof (struct ipv6hdr);
+ dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr);
+ dev->mtu = ETH_DATA_LEN - sizeof(struct ipv6hdr);
t = netdev_priv(dev);
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
- dev->mtu-=8;
+ dev->mtu -= 8;
dev->flags |= IFF_NOARP;
dev->addr_len = sizeof(struct in6_addr);
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index f9a3fd320d1..0171f08325c 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -845,7 +845,7 @@ static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c)
atomic_dec(&mrt->cache_resolve_queue_len);
- while((skb = skb_dequeue(&c->mfc_un.unres.unresolved)) != NULL) {
+ while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved)) != NULL) {
if (ipv6_hdr(skb)->version == 0) {
struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr));
nlh->nlmsg_type = NLMSG_ERROR;
@@ -1103,7 +1103,7 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt,
* Play the pending entries through our router
*/
- while((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) {
+ while ((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) {
if (ipv6_hdr(skb)->version == 0) {
struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr));
diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c
index d1c793cffcb..1b9316e1386 100644
--- a/net/ipv6/ipcomp6.c
+++ b/net/ipv6/ipcomp6.c
@@ -181,8 +181,7 @@ static int ipcomp6_rcv_cb(struct sk_buff *skb, int err)
return 0;
}
-static const struct xfrm_type ipcomp6_type =
-{
+static const struct xfrm_type ipcomp6_type = {
.description = "IPCOMP6",
.owner = THIS_MODULE,
.proto = IPPROTO_COMP,
@@ -193,8 +192,7 @@ static const struct xfrm_type ipcomp6_type =
.hdr_offset = xfrm6_find_1stfragopt,
};
-static struct xfrm6_protocol ipcomp6_protocol =
-{
+static struct xfrm6_protocol ipcomp6_protocol = {
.handler = xfrm6_rcv,
.cb_handler = ipcomp6_rcv_cb,
.err_handler = ipcomp6_err,
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 0c289982796..e1a9583bb41 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -66,12 +66,12 @@ int ip6_ra_control(struct sock *sk, int sel)
if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_RAW)
return -ENOPROTOOPT;
- new_ra = (sel>=0) ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL;
+ new_ra = (sel >= 0) ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL;
write_lock_bh(&ip6_ra_lock);
- for (rap = &ip6_ra_chain; (ra=*rap) != NULL; rap = &ra->next) {
+ for (rap = &ip6_ra_chain; (ra = *rap) != NULL; rap = &ra->next) {
if (ra->sk == sk) {
- if (sel>=0) {
+ if (sel >= 0) {
write_unlock_bh(&ip6_ra_lock);
kfree(new_ra);
return -EADDRINUSE;
@@ -130,7 +130,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
int retv = -ENOPROTOOPT;
if (optval == NULL)
- val=0;
+ val = 0;
else {
if (optlen >= sizeof(int)) {
if (get_user(val, (int __user *) optval))
@@ -139,7 +139,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
val = 0;
}
- valbool = (val!=0);
+ valbool = (val != 0);
if (ip6_mroute_opt(optname))
return ip6_mroute_setsockopt(sk, optname, optval, optlen);
@@ -474,7 +474,7 @@ sticky_done:
goto done;
msg.msg_controllen = optlen;
- msg.msg_control = (void*)(opt+1);
+ msg.msg_control = (void *)(opt+1);
retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk,
&junk, &junk);
@@ -687,7 +687,7 @@ done:
retv = -ENOBUFS;
break;
}
- gsf = kmalloc(optlen,GFP_KERNEL);
+ gsf = kmalloc(optlen, GFP_KERNEL);
if (!gsf) {
retv = -ENOBUFS;
break;
@@ -873,7 +873,6 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname,
#endif
return err;
}
-
EXPORT_SYMBOL(ipv6_setsockopt);
#ifdef CONFIG_COMPAT
@@ -909,7 +908,6 @@ int compat_ipv6_setsockopt(struct sock *sk, int level, int optname,
#endif
return err;
}
-
EXPORT_SYMBOL(compat_ipv6_setsockopt);
#endif
@@ -921,7 +919,7 @@ static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt,
if (!opt)
return 0;
- switch(optname) {
+ switch (optname) {
case IPV6_HOPOPTS:
hdr = opt->hopopt;
break;
@@ -1284,9 +1282,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
return -ENOPROTOOPT;
}
len = min_t(unsigned int, sizeof(int), len);
- if(put_user(len, optlen))
+ if (put_user(len, optlen))
return -EFAULT;
- if(copy_to_user(optval,&val,len))
+ if (copy_to_user(optval, &val, len))
return -EFAULT;
return 0;
}
@@ -1299,7 +1297,7 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname,
if (level == SOL_IP && sk->sk_type != SOCK_RAW)
return udp_prot.getsockopt(sk, level, optname, optval, optlen);
- if(level != SOL_IPV6)
+ if (level != SOL_IPV6)
return -ENOPROTOOPT;
err = do_ipv6_getsockopt(sk, level, optname, optval, optlen, 0);
@@ -1321,7 +1319,6 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname,
#endif
return err;
}
-
EXPORT_SYMBOL(ipv6_getsockopt);
#ifdef CONFIG_COMPAT
@@ -1364,7 +1361,6 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname,
#endif
return err;
}
-
EXPORT_SYMBOL(compat_ipv6_getsockopt);
#endif
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index a23b655a762..6833dd07b2c 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -121,6 +121,7 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
#define IPV6_MLD_MAX_MSF 64
int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF;
+int sysctl_mld_qrv __read_mostly = MLD_QRV_DEFAULT;
/*
* socket join on multicast group
@@ -237,7 +238,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
spin_lock(&ipv6_sk_mc_lock);
for (lnk = &np->ipv6_mc_list;
(mc_lst = rcu_dereference_protected(*lnk,
- lockdep_is_held(&ipv6_sk_mc_lock))) !=NULL ;
+ lockdep_is_held(&ipv6_sk_mc_lock))) != NULL;
lnk = &mc_lst->next) {
if ((ifindex == 0 || mc_lst->ifindex == ifindex) &&
ipv6_addr_equal(&mc_lst->addr, addr)) {
@@ -400,7 +401,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk,
if (!psl)
goto done; /* err = -EADDRNOTAVAIL */
rv = !0;
- for (i=0; i<psl->sl_count; i++) {
+ for (i = 0; i < psl->sl_count; i++) {
rv = !ipv6_addr_equal(&psl->sl_addr[i], source);
if (rv == 0)
break;
@@ -417,7 +418,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk,
/* update the interface filter */
ip6_mc_del_src(idev, group, omode, 1, source, 1);
- for (j=i+1; j<psl->sl_count; j++)
+ for (j = i+1; j < psl->sl_count; j++)
psl->sl_addr[j-1] = psl->sl_addr[j];
psl->sl_count--;
err = 0;
@@ -443,19 +444,19 @@ int ip6_mc_source(int add, int omode, struct sock *sk,
newpsl->sl_max = count;
newpsl->sl_count = count - IP6_SFBLOCK;
if (psl) {
- for (i=0; i<psl->sl_count; i++)
+ for (i = 0; i < psl->sl_count; i++)
newpsl->sl_addr[i] = psl->sl_addr[i];
sock_kfree_s(sk, psl, IP6_SFLSIZE(psl->sl_max));
}
pmc->sflist = psl = newpsl;
}
rv = 1; /* > 0 for insert logic below if sl_count is 0 */
- for (i=0; i<psl->sl_count; i++) {
+ for (i = 0; i < psl->sl_count; i++) {
rv = !ipv6_addr_equal(&psl->sl_addr[i], source);
if (rv == 0) /* There is an error in the address. */
goto done;
}
- for (j=psl->sl_count-1; j>=i; j--)
+ for (j = psl->sl_count-1; j >= i; j--)
psl->sl_addr[j+1] = psl->sl_addr[j];
psl->sl_addr[i] = *source;
psl->sl_count++;
@@ -524,7 +525,7 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf)
goto done;
}
newpsl->sl_max = newpsl->sl_count = gsf->gf_numsrc;
- for (i=0; i<newpsl->sl_count; ++i) {
+ for (i = 0; i < newpsl->sl_count; ++i) {
struct sockaddr_in6 *psin6;
psin6 = (struct sockaddr_in6 *)&gsf->gf_slist[i];
@@ -616,7 +617,7 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
* on ipv6_sk_mc_lock and a write lock on pmc->sflock. We
* have the socket lock, so reading here is safe.
*/
- for (i=0; i<copycount; i++) {
+ for (i = 0; i < copycount; i++) {
struct sockaddr_in6 *psin6;
struct sockaddr_storage ss;
@@ -658,7 +659,7 @@ bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr,
} else {
int i;
- for (i=0; i<psl->sl_count; i++) {
+ for (i = 0; i < psl->sl_count; i++) {
if (ipv6_addr_equal(&psl->sl_addr[i], src_addr))
break;
}
@@ -772,7 +773,7 @@ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
pmc->mca_tomb = im->mca_tomb;
pmc->mca_sources = im->mca_sources;
im->mca_tomb = im->mca_sources = NULL;
- for (psf=pmc->mca_sources; psf; psf=psf->sf_next)
+ for (psf = pmc->mca_sources; psf; psf = psf->sf_next)
psf->sf_crcount = pmc->mca_crcount;
}
spin_unlock_bh(&im->mca_lock);
@@ -790,7 +791,7 @@ static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *pmca)
spin_lock_bh(&idev->mc_lock);
pmc_prev = NULL;
- for (pmc=idev->mc_tomb; pmc; pmc=pmc->next) {
+ for (pmc = idev->mc_tomb; pmc; pmc = pmc->next) {
if (ipv6_addr_equal(&pmc->mca_addr, pmca))
break;
pmc_prev = pmc;
@@ -804,7 +805,7 @@ static void mld_del_delrec(struct inet6_dev *idev, const struct in6_addr *pmca)
spin_unlock_bh(&idev->mc_lock);
if (pmc) {
- for (psf=pmc->mca_tomb; psf; psf=psf_next) {
+ for (psf = pmc->mca_tomb; psf; psf = psf_next) {
psf_next = psf->sf_next;
kfree(psf);
}
@@ -831,14 +832,14 @@ static void mld_clear_delrec(struct inet6_dev *idev)
/* clear dead sources, too */
read_lock_bh(&idev->lock);
- for (pmc=idev->mc_list; pmc; pmc=pmc->next) {
+ for (pmc = idev->mc_list; pmc; pmc = pmc->next) {
struct ip6_sf_list *psf, *psf_next;
spin_lock_bh(&pmc->mca_lock);
psf = pmc->mca_tomb;
pmc->mca_tomb = NULL;
spin_unlock_bh(&pmc->mca_lock);
- for (; psf; psf=psf_next) {
+ for (; psf; psf = psf_next) {
psf_next = psf->sf_next;
kfree(psf);
}
@@ -931,7 +932,7 @@ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr)
ASSERT_RTNL();
write_lock_bh(&idev->lock);
- for (map = &idev->mc_list; (ma=*map) != NULL; map = &ma->next) {
+ for (map = &idev->mc_list; (ma = *map) != NULL; map = &ma->next) {
if (ipv6_addr_equal(&ma->mca_addr, addr)) {
if (--ma->mca_users == 0) {
*map = ma->next;
@@ -982,7 +983,7 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group,
idev = __in6_dev_get(dev);
if (idev) {
read_lock_bh(&idev->lock);
- for (mc = idev->mc_list; mc; mc=mc->next) {
+ for (mc = idev->mc_list; mc; mc = mc->next) {
if (ipv6_addr_equal(&mc->mca_addr, group))
break;
}
@@ -991,7 +992,7 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group,
struct ip6_sf_list *psf;
spin_lock_bh(&mc->mca_lock);
- for (psf=mc->mca_sources;psf;psf=psf->sf_next) {
+ for (psf = mc->mca_sources; psf; psf = psf->sf_next) {
if (ipv6_addr_equal(&psf->sf_addr, src_addr))
break;
}
@@ -1000,7 +1001,7 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group,
psf->sf_count[MCAST_EXCLUDE] !=
mc->mca_sfcount[MCAST_EXCLUDE];
else
- rv = mc->mca_sfcount[MCAST_EXCLUDE] !=0;
+ rv = mc->mca_sfcount[MCAST_EXCLUDE] != 0;
spin_unlock_bh(&mc->mca_lock);
} else
rv = true; /* don't filter unspecified source */
@@ -1091,10 +1092,10 @@ static bool mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs,
int i, scount;
scount = 0;
- for (psf=pmc->mca_sources; psf; psf=psf->sf_next) {
+ for (psf = pmc->mca_sources; psf; psf = psf->sf_next) {
if (scount == nsrcs)
break;
- for (i=0; i<nsrcs; i++) {
+ for (i = 0; i < nsrcs; i++) {
/* skip inactive filters */
if (psf->sf_count[MCAST_INCLUDE] ||
pmc->mca_sfcount[MCAST_EXCLUDE] !=
@@ -1124,10 +1125,10 @@ static bool mld_marksources(struct ifmcaddr6 *pmc, int nsrcs,
/* mark INCLUDE-mode sources */
scount = 0;
- for (psf=pmc->mca_sources; psf; psf=psf->sf_next) {
+ for (psf = pmc->mca_sources; psf; psf = psf->sf_next) {
if (scount == nsrcs)
break;
- for (i=0; i<nsrcs; i++) {
+ for (i = 0; i < nsrcs; i++) {
if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) {
psf->sf_gsresp = 1;
scount++;
@@ -1205,15 +1206,16 @@ static void mld_update_qrv(struct inet6_dev *idev,
* and SHOULD NOT be one. Catch this here if we ever run
* into such a case in future.
*/
+ const int min_qrv = min(MLD_QRV_DEFAULT, sysctl_mld_qrv);
WARN_ON(idev->mc_qrv == 0);
if (mlh2->mld2q_qrv > 0)
idev->mc_qrv = mlh2->mld2q_qrv;
- if (unlikely(idev->mc_qrv < 2)) {
+ if (unlikely(idev->mc_qrv < min_qrv)) {
net_warn_ratelimited("IPv6: MLD: clamping QRV from %u to %u!\n",
- idev->mc_qrv, MLD_QRV_DEFAULT);
- idev->mc_qrv = MLD_QRV_DEFAULT;
+ idev->mc_qrv, min_qrv);
+ idev->mc_qrv = min_qrv;
}
}
@@ -1378,13 +1380,13 @@ int igmp6_event_query(struct sk_buff *skb)
read_lock_bh(&idev->lock);
if (group_type == IPV6_ADDR_ANY) {
- for (ma = idev->mc_list; ma; ma=ma->next) {
+ for (ma = idev->mc_list; ma; ma = ma->next) {
spin_lock_bh(&ma->mca_lock);
igmp6_group_queried(ma, max_delay);
spin_unlock_bh(&ma->mca_lock);
}
} else {
- for (ma = idev->mc_list; ma; ma=ma->next) {
+ for (ma = idev->mc_list; ma; ma = ma->next) {
if (!ipv6_addr_equal(group, &ma->mca_addr))
continue;
spin_lock_bh(&ma->mca_lock);
@@ -1448,7 +1450,7 @@ int igmp6_event_report(struct sk_buff *skb)
*/
read_lock_bh(&idev->lock);
- for (ma = idev->mc_list; ma; ma=ma->next) {
+ for (ma = idev->mc_list; ma; ma = ma->next) {
if (ipv6_addr_equal(&ma->mca_addr, &mld->mld_mca)) {
spin_lock(&ma->mca_lock);
if (del_timer(&ma->mca_timer))
@@ -1512,7 +1514,7 @@ mld_scount(struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted)
struct ip6_sf_list *psf;
int scount = 0;
- for (psf=pmc->mca_sources; psf; psf=psf->sf_next) {
+ for (psf = pmc->mca_sources; psf; psf = psf->sf_next) {
if (!is_in(pmc, psf, type, gdeleted, sdeleted))
continue;
scount++;
@@ -1726,7 +1728,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
}
first = 1;
psf_prev = NULL;
- for (psf=*psf_list; psf; psf=psf_next) {
+ for (psf = *psf_list; psf; psf = psf_next) {
struct in6_addr *psrc;
psf_next = psf->sf_next;
@@ -1805,7 +1807,7 @@ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc)
read_lock_bh(&idev->lock);
if (!pmc) {
- for (pmc=idev->mc_list; pmc; pmc=pmc->next) {
+ for (pmc = idev->mc_list; pmc; pmc = pmc->next) {
if (pmc->mca_flags & MAF_NOREPORT)
continue;
spin_lock_bh(&pmc->mca_lock);
@@ -1838,7 +1840,7 @@ static void mld_clear_zeros(struct ip6_sf_list **ppsf)
struct ip6_sf_list *psf_prev, *psf_next, *psf;
psf_prev = NULL;
- for (psf=*ppsf; psf; psf = psf_next) {
+ for (psf = *ppsf; psf; psf = psf_next) {
psf_next = psf->sf_next;
if (psf->sf_crcount == 0) {
if (psf_prev)
@@ -1862,7 +1864,7 @@ static void mld_send_cr(struct inet6_dev *idev)
/* deleted MCA's */
pmc_prev = NULL;
- for (pmc=idev->mc_tomb; pmc; pmc=pmc_next) {
+ for (pmc = idev->mc_tomb; pmc; pmc = pmc_next) {
pmc_next = pmc->next;
if (pmc->mca_sfmode == MCAST_INCLUDE) {
type = MLD2_BLOCK_OLD_SOURCES;
@@ -1895,7 +1897,7 @@ static void mld_send_cr(struct inet6_dev *idev)
spin_unlock(&idev->mc_lock);
/* change recs */
- for (pmc=idev->mc_list; pmc; pmc=pmc->next) {
+ for (pmc = idev->mc_list; pmc; pmc = pmc->next) {
spin_lock_bh(&pmc->mca_lock);
if (pmc->mca_sfcount[MCAST_EXCLUDE]) {
type = MLD2_BLOCK_OLD_SOURCES;
@@ -2032,7 +2034,7 @@ static void mld_send_initial_cr(struct inet6_dev *idev)
skb = NULL;
read_lock_bh(&idev->lock);
- for (pmc=idev->mc_list; pmc; pmc=pmc->next) {
+ for (pmc = idev->mc_list; pmc; pmc = pmc->next) {
spin_lock_bh(&pmc->mca_lock);
if (pmc->mca_sfcount[MCAST_EXCLUDE])
type = MLD2_CHANGE_TO_EXCLUDE;
@@ -2077,7 +2079,7 @@ static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode,
int rv = 0;
psf_prev = NULL;
- for (psf=pmc->mca_sources; psf; psf=psf->sf_next) {
+ for (psf = pmc->mca_sources; psf; psf = psf->sf_next) {
if (ipv6_addr_equal(&psf->sf_addr, psfsrc))
break;
psf_prev = psf;
@@ -2118,7 +2120,7 @@ static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca,
if (!idev)
return -ENODEV;
read_lock_bh(&idev->lock);
- for (pmc=idev->mc_list; pmc; pmc=pmc->next) {
+ for (pmc = idev->mc_list; pmc; pmc = pmc->next) {
if (ipv6_addr_equal(pmca, &pmc->mca_addr))
break;
}
@@ -2138,7 +2140,7 @@ static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca,
pmc->mca_sfcount[sfmode]--;
}
err = 0;
- for (i=0; i<sfcount; i++) {
+ for (i = 0; i < sfcount; i++) {
int rv = ip6_mc_del1_src(pmc, sfmode, &psfsrc[i]);
changerec |= rv > 0;
@@ -2154,7 +2156,7 @@ static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca,
pmc->mca_sfmode = MCAST_INCLUDE;
pmc->mca_crcount = idev->mc_qrv;
idev->mc_ifc_count = pmc->mca_crcount;
- for (psf=pmc->mca_sources; psf; psf = psf->sf_next)
+ for (psf = pmc->mca_sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
mld_ifc_event(pmc->idev);
} else if (sf_setstate(pmc) || changerec)
@@ -2173,7 +2175,7 @@ static int ip6_mc_add1_src(struct ifmcaddr6 *pmc, int sfmode,
struct ip6_sf_list *psf, *psf_prev;
psf_prev = NULL;
- for (psf=pmc->mca_sources; psf; psf=psf->sf_next) {
+ for (psf = pmc->mca_sources; psf; psf = psf->sf_next) {
if (ipv6_addr_equal(&psf->sf_addr, psfsrc))
break;
psf_prev = psf;
@@ -2198,7 +2200,7 @@ static void sf_markstate(struct ifmcaddr6 *pmc)
struct ip6_sf_list *psf;
int mca_xcount = pmc->mca_sfcount[MCAST_EXCLUDE];
- for (psf=pmc->mca_sources; psf; psf=psf->sf_next)
+ for (psf = pmc->mca_sources; psf; psf = psf->sf_next)
if (pmc->mca_sfcount[MCAST_EXCLUDE]) {
psf->sf_oldin = mca_xcount ==
psf->sf_count[MCAST_EXCLUDE] &&
@@ -2215,7 +2217,7 @@ static int sf_setstate(struct ifmcaddr6 *pmc)
int new_in, rv;
rv = 0;
- for (psf=pmc->mca_sources; psf; psf=psf->sf_next) {
+ for (psf = pmc->mca_sources; psf; psf = psf->sf_next) {
if (pmc->mca_sfcount[MCAST_EXCLUDE]) {
new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] &&
!psf->sf_count[MCAST_INCLUDE];
@@ -2225,8 +2227,8 @@ static int sf_setstate(struct ifmcaddr6 *pmc)
if (!psf->sf_oldin) {
struct ip6_sf_list *prev = NULL;
- for (dpsf=pmc->mca_tomb; dpsf;
- dpsf=dpsf->sf_next) {
+ for (dpsf = pmc->mca_tomb; dpsf;
+ dpsf = dpsf->sf_next) {
if (ipv6_addr_equal(&dpsf->sf_addr,
&psf->sf_addr))
break;
@@ -2248,7 +2250,7 @@ static int sf_setstate(struct ifmcaddr6 *pmc)
* add or update "delete" records if an active filter
* is now inactive
*/
- for (dpsf=pmc->mca_tomb; dpsf; dpsf=dpsf->sf_next)
+ for (dpsf = pmc->mca_tomb; dpsf; dpsf = dpsf->sf_next)
if (ipv6_addr_equal(&dpsf->sf_addr,
&psf->sf_addr))
break;
@@ -2282,7 +2284,7 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca,
if (!idev)
return -ENODEV;
read_lock_bh(&idev->lock);
- for (pmc=idev->mc_list; pmc; pmc=pmc->next) {
+ for (pmc = idev->mc_list; pmc; pmc = pmc->next) {
if (ipv6_addr_equal(pmca, &pmc->mca_addr))
break;
}
@@ -2298,7 +2300,7 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca,
if (!delta)
pmc->mca_sfcount[sfmode]++;
err = 0;
- for (i=0; i<sfcount; i++) {
+ for (i = 0; i < sfcount; i++) {
err = ip6_mc_add1_src(pmc, sfmode, &psfsrc[i]);
if (err)
break;
@@ -2308,7 +2310,7 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca,
if (!delta)
pmc->mca_sfcount[sfmode]--;
- for (j=0; j<i; j++)
+ for (j = 0; j < i; j++)
ip6_mc_del1_src(pmc, sfmode, &psfsrc[j]);
} else if (isexclude != (pmc->mca_sfcount[MCAST_EXCLUDE] != 0)) {
struct ip6_sf_list *psf;
@@ -2322,7 +2324,7 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca,
pmc->mca_crcount = idev->mc_qrv;
idev->mc_ifc_count = pmc->mca_crcount;
- for (psf=pmc->mca_sources; psf; psf = psf->sf_next)
+ for (psf = pmc->mca_sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
mld_ifc_event(idev);
} else if (sf_setstate(pmc))
@@ -2336,12 +2338,12 @@ static void ip6_mc_clear_src(struct ifmcaddr6 *pmc)
{
struct ip6_sf_list *psf, *nextpsf;
- for (psf=pmc->mca_tomb; psf; psf=nextpsf) {
+ for (psf = pmc->mca_tomb; psf; psf = nextpsf) {
nextpsf = psf->sf_next;
kfree(psf);
}
pmc->mca_tomb = NULL;
- for (psf=pmc->mca_sources; psf; psf=nextpsf) {
+ for (psf = pmc->mca_sources; psf; psf = nextpsf) {
nextpsf = psf->sf_next;
kfree(psf);
}
@@ -2485,13 +2487,21 @@ void ipv6_mc_down(struct inet6_dev *idev)
mld_gq_stop_timer(idev);
mld_dad_stop_timer(idev);
- for (i = idev->mc_list; i; i=i->next)
+ for (i = idev->mc_list; i; i = i->next)
igmp6_group_dropped(i);
read_unlock_bh(&idev->lock);
mld_clear_delrec(idev);
}
+static void ipv6_mc_reset(struct inet6_dev *idev)
+{
+ idev->mc_qrv = sysctl_mld_qrv;
+ idev->mc_qi = MLD_QI_DEFAULT;
+ idev->mc_qri = MLD_QRI_DEFAULT;
+ idev->mc_v1_seen = 0;
+ idev->mc_maxdelay = unsolicited_report_interval(idev);
+}
/* Device going up */
@@ -2502,7 +2512,8 @@ void ipv6_mc_up(struct inet6_dev *idev)
/* Install multicast list, except for all-nodes (already installed) */
read_lock_bh(&idev->lock);
- for (i = idev->mc_list; i; i=i->next)
+ ipv6_mc_reset(idev);
+ for (i = idev->mc_list; i; i = i->next)
igmp6_group_added(i);
read_unlock_bh(&idev->lock);
}
@@ -2522,13 +2533,7 @@ void ipv6_mc_init_dev(struct inet6_dev *idev)
(unsigned long)idev);
setup_timer(&idev->mc_dad_timer, mld_dad_timer_expire,
(unsigned long)idev);
-
- idev->mc_qrv = MLD_QRV_DEFAULT;
- idev->mc_qi = MLD_QI_DEFAULT;
- idev->mc_qri = MLD_QRI_DEFAULT;
-
- idev->mc_maxdelay = unsolicited_report_interval(idev);
- idev->mc_v1_seen = 0;
+ ipv6_mc_reset(idev);
write_unlock_bh(&idev->lock);
}
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index db9b6cbc9db..f61429d391d 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -336,11 +336,10 @@ static void mip6_destopt_destroy(struct xfrm_state *x)
{
}
-static const struct xfrm_type mip6_destopt_type =
-{
+static const struct xfrm_type mip6_destopt_type = {
.description = "MIP6DESTOPT",
.owner = THIS_MODULE,
- .proto = IPPROTO_DSTOPTS,
+ .proto = IPPROTO_DSTOPTS,
.flags = XFRM_TYPE_NON_FRAGMENT | XFRM_TYPE_LOCAL_COADDR,
.init_state = mip6_destopt_init_state,
.destructor = mip6_destopt_destroy,
@@ -469,11 +468,10 @@ static void mip6_rthdr_destroy(struct xfrm_state *x)
{
}
-static const struct xfrm_type mip6_rthdr_type =
-{
+static const struct xfrm_type mip6_rthdr_type = {
.description = "MIP6RT",
.owner = THIS_MODULE,
- .proto = IPPROTO_ROUTING,
+ .proto = IPPROTO_ROUTING,
.flags = XFRM_TYPE_NON_FRAGMENT | XFRM_TYPE_REMOTE_COADDR,
.init_state = mip6_rthdr_init_state,
.destructor = mip6_rthdr_destroy,
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 339078f95d1..4cb45c1079a 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -175,7 +175,7 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
type = cur->nd_opt_type;
do {
cur = ((void *)cur) + (cur->nd_opt_len << 3);
- } while(cur < end && cur->nd_opt_type != type);
+ } while (cur < end && cur->nd_opt_type != type);
return cur <= end && cur->nd_opt_type == type ? cur : NULL;
}
@@ -192,7 +192,7 @@ static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur,
return NULL;
do {
cur = ((void *)cur) + (cur->nd_opt_len << 3);
- } while(cur < end && !ndisc_is_useropt(cur));
+ } while (cur < end && !ndisc_is_useropt(cur));
return cur <= end && ndisc_is_useropt(cur) ? cur : NULL;
}
@@ -284,7 +284,6 @@ int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev,
}
return -EINVAL;
}
-
EXPORT_SYMBOL(ndisc_mc_map);
static u32 ndisc_hash(const void *pkey,
@@ -296,7 +295,7 @@ static u32 ndisc_hash(const void *pkey,
static int ndisc_constructor(struct neighbour *neigh)
{
- struct in6_addr *addr = (struct in6_addr*)&neigh->primary_key;
+ struct in6_addr *addr = (struct in6_addr *)&neigh->primary_key;
struct net_device *dev = neigh->dev;
struct inet6_dev *in6_dev;
struct neigh_parms *parms;
@@ -344,7 +343,7 @@ static int ndisc_constructor(struct neighbour *neigh)
static int pndisc_constructor(struct pneigh_entry *n)
{
- struct in6_addr *addr = (struct in6_addr*)&n->key;
+ struct in6_addr *addr = (struct in6_addr *)&n->key;
struct in6_addr maddr;
struct net_device *dev = n->dev;
@@ -357,7 +356,7 @@ static int pndisc_constructor(struct pneigh_entry *n)
static void pndisc_destructor(struct pneigh_entry *n)
{
- struct in6_addr *addr = (struct in6_addr*)&n->key;
+ struct in6_addr *addr = (struct in6_addr *)&n->key;
struct in6_addr maddr;
struct net_device *dev = n->dev;
@@ -1065,7 +1064,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
int optlen;
unsigned int pref = 0;
- __u8 * opt = (__u8 *)(ra_msg + 1);
+ __u8 *opt = (__u8 *)(ra_msg + 1);
optlen = (skb_tail_pointer(skb) - skb_transport_header(skb)) -
sizeof(struct ra_msg);
@@ -1319,7 +1318,7 @@ skip_linkparms:
continue;
if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen)
continue;
- rt6_route_rcv(skb->dev, (u8*)p, (p->nd_opt_len) << 3,
+ rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3,
&ipv6_hdr(skb)->saddr);
}
}
@@ -1352,7 +1351,7 @@ skip_routeinfo:
__be32 n;
u32 mtu;
- memcpy(&n, ((u8*)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu));
+ memcpy(&n, ((u8 *)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu));
mtu = ntohl(n);
if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) {
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 5ec867e4a8b..fc24c390af0 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -35,7 +35,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
if (found_rhdr)
return offset;
break;
- default :
+ default:
return offset;
}
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 2d6f860e5c1..1752cd0b488 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -8,7 +8,7 @@
* except it reports the sockets in the INET6 address family.
*
* Authors: David S. Miller (davem@caip.rutgers.edu)
- * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
+ * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 39d44226e40..896af880797 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -889,7 +889,7 @@ back_from_confirm:
else {
lock_sock(sk);
err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov,
- len, 0, hlimit, tclass, opt, &fl6, (struct rt6_info*)dst,
+ len, 0, hlimit, tclass, opt, &fl6, (struct rt6_info *)dst,
msg->msg_flags, dontfrag);
if (err)
@@ -902,7 +902,7 @@ done:
dst_release(dst);
out:
fl6_sock_release(flowlabel);
- return err<0?err:len;
+ return err < 0 ? err : len;
do_confirm:
dst_confirm(dst);
if (!(msg->msg_flags & MSG_PROBE) || len)
@@ -1045,7 +1045,7 @@ static int do_rawv6_getsockopt(struct sock *sk, int level, int optname,
struct raw6_sock *rp = raw6_sk(sk);
int val, len;
- if (get_user(len,optlen))
+ if (get_user(len, optlen))
return -EFAULT;
switch (optname) {
@@ -1069,7 +1069,7 @@ static int do_rawv6_getsockopt(struct sock *sk, int level, int optname,
if (put_user(len, optlen))
return -EFAULT;
- if (copy_to_user(optval,&val,len))
+ if (copy_to_user(optval, &val, len))
return -EFAULT;
return 0;
}
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index c6557d9f780..1a157ca2ebc 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -62,13 +62,12 @@
static const char ip6_frag_cache_name[] = "ip6-frags";
-struct ip6frag_skb_cb
-{
+struct ip6frag_skb_cb {
struct inet6_skb_parm h;
int offset;
};
-#define FRAG6_CB(skb) ((struct ip6frag_skb_cb*)((skb)->cb))
+#define FRAG6_CB(skb) ((struct ip6frag_skb_cb *)((skb)->cb))
static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
{
@@ -289,7 +288,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
goto found;
}
prev = NULL;
- for(next = fq->q.fragments; next != NULL; next = next->next) {
+ for (next = fq->q.fragments; next != NULL; next = next->next) {
if (FRAG6_CB(next)->offset >= offset)
break; /* bingo! */
prev = next;
@@ -529,7 +528,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS);
/* Jumbo payload inhibits frag. header */
- if (hdr->payload_len==0)
+ if (hdr->payload_len == 0)
goto fail_hdr;
if (!pskb_may_pull(skb, (skb_transport_offset(skb) +
@@ -575,8 +574,7 @@ fail_hdr:
return -1;
}
-static const struct inet6_protocol frag_protocol =
-{
+static const struct inet6_protocol frag_protocol = {
.handler = ipv6_frag_rcv,
.flags = INET6_PROTO_NOPOLICY,
};
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index f23fbd28a50..f74b0417bd6 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -813,7 +813,7 @@ out:
}
-struct dst_entry * ip6_route_lookup(struct net *net, struct flowi6 *fl6,
+struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
int flags)
{
return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_lookup);
@@ -843,7 +843,6 @@ struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
return NULL;
}
-
EXPORT_SYMBOL(rt6_lookup);
/* ip6_ins_rt is called with FREE table->tb6_lock.
@@ -1024,7 +1023,7 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table
return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags);
}
-struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk,
+struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
struct flowi6 *fl6)
{
int flags = 0;
@@ -1041,7 +1040,6 @@ struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk,
return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output);
}
-
EXPORT_SYMBOL(ip6_route_output);
struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig)
@@ -1149,7 +1147,7 @@ static void ip6_link_failure(struct sk_buff *skb)
static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
{
- struct rt6_info *rt6 = (struct rt6_info*)dst;
+ struct rt6_info *rt6 = (struct rt6_info *)dst;
dst_confirm(dst);
if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) {
@@ -1924,7 +1922,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
return NULL;
read_lock_bh(&table->tb6_lock);
- fn = fib6_locate(&table->tb6_root, prefix ,prefixlen, NULL, 0);
+ fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0);
if (!fn)
goto out;
@@ -1983,7 +1981,7 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev
return NULL;
read_lock_bh(&table->tb6_lock);
- for (rt = table->tb6_root.leaf; rt; rt=rt->dst.rt6_next) {
+ for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) {
if (dev == rt->dst.dev &&
((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
ipv6_addr_equal(&rt->rt6i_gateway, addr))
@@ -2068,7 +2066,7 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg)
struct in6_rtmsg rtmsg;
int err;
- switch(cmd) {
+ switch (cmd) {
case SIOCADDRT: /* Add a route */
case SIOCDELRT: /* Delete a route */
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
@@ -2191,7 +2189,7 @@ int ip6_route_get_saddr(struct net *net,
unsigned int prefs,
struct in6_addr *saddr)
{
- struct inet6_dev *idev = ip6_dst_idev((struct dst_entry*)rt);
+ struct inet6_dev *idev = ip6_dst_idev((struct dst_entry *)rt);
int err = 0;
if (rt->rt6i_prefsrc.plen)
*saddr = rt->rt6i_prefsrc.addr;
@@ -2486,7 +2484,7 @@ beginning:
return last_err;
}
-static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh)
+static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct fib6_config cfg;
int err;
@@ -2501,7 +2499,7 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh)
return ip6_route_del(&cfg);
}
-static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh)
+static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct fib6_config cfg;
int err;
@@ -2693,7 +2691,7 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg)
prefix, 0, NLM_F_MULTI);
}
-static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh)
+static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(in_skb->sk);
struct nlattr *tb[RTA_MAX+1];
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 6163f851dc0..86e3fa81f85 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -812,9 +812,9 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
const struct ipv6hdr *iph6 = ipv6_hdr(skb);
u8 tos = tunnel->parms.iph.tos;
__be16 df = tiph->frag_off;
- struct rtable *rt; /* Route to the other host */
- struct net_device *tdev; /* Device to other host */
- unsigned int max_headroom; /* The extra header space needed */
+ struct rtable *rt; /* Route to the other host */
+ struct net_device *tdev; /* Device to other host */
+ unsigned int max_headroom; /* The extra header space needed */
__be32 dst = tiph->daddr;
struct flowi4 fl4;
int mtu;
@@ -1123,7 +1123,7 @@ static int ipip6_tunnel_update_6rd(struct ip_tunnel *t,
#endif
static int
-ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
+ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
int err = 0;
struct ip_tunnel_parm p;
@@ -1339,10 +1339,10 @@ static void ipip6_dev_free(struct net_device *dev)
static void ipip6_tunnel_setup(struct net_device *dev)
{
dev->netdev_ops = &ipip6_netdev_ops;
- dev->destructor = ipip6_dev_free;
+ dev->destructor = ipip6_dev_free;
dev->type = ARPHRD_SIT;
- dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr);
+ dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr);
dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr);
dev->flags = IFF_NOARP;
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 83cea1d3946..c643dc907ce 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -24,7 +24,7 @@
#define COOKIEBITS 24 /* Upper bits store count */
#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
-static u32 syncookie6_secret[2][16-4+SHA_DIGEST_WORDS];
+static u32 syncookie6_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
/* RFC 2460, Section 8.3:
* [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..]
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index 0c56c93619e..c5c10fafcfe 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -16,6 +16,8 @@
#include <net/addrconf.h>
#include <net/inet_frag.h>
+static int one = 1;
+
static struct ctl_table ipv6_table_template[] = {
{
.procname = "bindv6only",
@@ -63,6 +65,14 @@ static struct ctl_table ipv6_rotable[] = {
.mode = 0644,
.proc_handler = proc_dointvec
},
+ {
+ .procname = "mld_qrv",
+ .data = &sysctl_mld_qrv,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one
+ },
{ }
};
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 29964c3d363..5b3c70ff7a7 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -738,7 +738,7 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk,
ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
ireq->ir_iif = inet6_iif(skb);
- if (!TCP_SKB_CB(skb)->when &&
+ if (!TCP_SKB_CB(skb)->tcp_tw_isn &&
(ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo ||
np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim ||
np->rxopt.bits.rxohlim || np->repflow)) {
@@ -1412,7 +1412,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
skb->len - th->doff*4);
TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
- TCP_SKB_CB(skb)->when = 0;
+ TCP_SKB_CB(skb)->tcp_tw_isn = 0;
TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
TCP_SKB_CB(skb)->sacked = 0;
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 01b0ff9a0c2..dbb3d9262bf 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -35,34 +35,14 @@ static int tcp_v6_gso_send_check(struct sk_buff *skb)
static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
struct sk_buff *skb)
{
- const struct ipv6hdr *iph = skb_gro_network_header(skb);
- __wsum wsum;
-
/* Don't bother verifying checksum if we're going to flush anyway. */
- if (NAPI_GRO_CB(skb)->flush)
- goto skip_csum;
-
- wsum = NAPI_GRO_CB(skb)->csum;
-
- switch (skb->ip_summed) {
- case CHECKSUM_NONE:
- wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb),
- wsum);
-
- /* fall through */
-
- case CHECKSUM_COMPLETE:
- if (!tcp_v6_check(skb_gro_len(skb), &iph->saddr, &iph->daddr,
- wsum)) {
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- break;
- }
-
+ if (!NAPI_GRO_CB(skb)->flush &&
+ skb_gro_checksum_validate(skb, IPPROTO_TCP,
+ ip6_gro_compute_pseudo)) {
NAPI_GRO_CB(skb)->flush = 1;
return NULL;
}
-skip_csum:
return tcp_gro_receive(head, skb);
}
diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c
index 2c4e4c5c761..3c758007b32 100644
--- a/net/ipv6/tunnel6.c
+++ b/net/ipv6/tunnel6.c
@@ -15,7 +15,7 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*
* Authors Mitsuru KANDA <mk@linux-ipv6.org>
- * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
+ * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
*/
#define pr_fmt(fmt) "IPv6: " fmt
@@ -64,7 +64,6 @@ err:
return ret;
}
-
EXPORT_SYMBOL(xfrm6_tunnel_register);
int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family)
@@ -92,7 +91,6 @@ int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family)
return ret;
}
-
EXPORT_SYMBOL(xfrm6_tunnel_deregister);
#define for_each_tunnel_rcu(head, handler) \
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4836af8f582..f6ba535b6fe 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -243,7 +243,7 @@ begin:
goto exact_match;
} else if (score == badness && reuseport) {
matches++;
- if (((u64)hash * matches) >> 32 == 0)
+ if (reciprocal_scale(hash, matches) == 0)
result = sk;
hash = next_pseudo_random32(hash);
}
@@ -323,7 +323,7 @@ begin:
}
} else if (score == badness && reuseport) {
matches++;
- if (((u64)hash * matches) >> 32 == 0)
+ if (reciprocal_scale(hash, matches) == 0)
result = sk;
hash = next_pseudo_random32(hash);
}
@@ -373,8 +373,8 @@ EXPORT_SYMBOL_GPL(udp6_lib_lookup);
/*
- * This should be easy, if there is something there we
- * return it, otherwise we block.
+ * This should be easy, if there is something there we
+ * return it, otherwise we block.
*/
int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
@@ -530,7 +530,7 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
const struct in6_addr *saddr = &hdr->saddr;
const struct in6_addr *daddr = &hdr->daddr;
- struct udphdr *uh = (struct udphdr*)(skb->data+offset);
+ struct udphdr *uh = (struct udphdr *)(skb->data+offset);
struct sock *sk;
int err;
struct net *net = dev_net(skb->dev);
@@ -596,7 +596,7 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
static __inline__ void udpv6_err(struct sk_buff *skb,
struct inet6_skb_parm *opt, u8 type,
- u8 code, int offset, __be32 info )
+ u8 code, int offset, __be32 info)
{
__udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
}
@@ -891,6 +891,10 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
goto csum_error;
}
+ if (udp_sk(sk)->convert_csum && uh->check && !IS_UDPLITE(sk))
+ skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+ ip6_compute_pseudo);
+
ret = udpv6_queue_rcv_skb(sk, skb);
sock_put(sk);
@@ -960,10 +964,10 @@ static void udp_v6_flush_pending_frames(struct sock *sk)
}
/**
- * udp6_hwcsum_outgoing - handle outgoing HW checksumming
- * @sk: socket we are sending on
- * @skb: sk_buff containing the filled-in UDP header
- * (checksum field must be zeroed out)
+ * udp6_hwcsum_outgoing - handle outgoing HW checksumming
+ * @sk: socket we are sending on
+ * @skb: sk_buff containing the filled-in UDP header
+ * (checksum field must be zeroed out)
*/
static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
const struct in6_addr *saddr,
@@ -1294,7 +1298,7 @@ do_append_data:
getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen,
sizeof(struct udphdr), hlimit, tclass, opt, &fl6,
- (struct rt6_info*)dst,
+ (struct rt6_info *)dst,
corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag);
if (err)
udp_v6_flush_pending_frames(sk);
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 0ae3d98f83e..89cb9a9b853 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -10,6 +10,7 @@
* UDPv6 GSO support
*/
#include <linux/skbuff.h>
+#include <linux/netdevice.h>
#include <net/protocol.h>
#include <net/ipv6.h>
#include <net/udp.h>
@@ -127,10 +128,52 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
out:
return segs;
}
+
+static struct sk_buff **udp6_gro_receive(struct sk_buff **head,
+ struct sk_buff *skb)
+{
+ struct udphdr *uh = udp_gro_udphdr(skb);
+
+ if (unlikely(!uh))
+ goto flush;
+
+ /* Don't bother verifying checksum if we're going to flush anyway. */
+ if (!NAPI_GRO_CB(skb)->flush)
+ goto skip;
+
+ if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
+ ip6_gro_compute_pseudo))
+ goto flush;
+ else if (uh->check)
+ skb_gro_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+ ip6_gro_compute_pseudo);
+
+skip:
+ return udp_gro_receive(head, skb, uh);
+
+flush:
+ NAPI_GRO_CB(skb)->flush = 1;
+ return NULL;
+}
+
+int udp6_gro_complete(struct sk_buff *skb, int nhoff)
+{
+ const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+ struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
+
+ if (uh->check)
+ uh->check = ~udp_v6_check(skb->len - nhoff, &ipv6h->saddr,
+ &ipv6h->daddr, 0);
+
+ return udp_gro_complete(skb, nhoff);
+}
+
static const struct net_offload udpv6_offload = {
.callbacks = {
.gso_send_check = udp6_ufo_send_check,
.gso_segment = udp6_ufo_fragment,
+ .gro_receive = udp6_gro_receive,
+ .gro_complete = udp6_gro_complete,
},
};
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index f8c3cf842f5..f48fbe4d16f 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -3,8 +3,8 @@
*
* Authors:
* Mitsuru KANDA @USAGI
- * Kazunori MIYAZAWA @USAGI
- * Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ * Kazunori MIYAZAWA @USAGI
+ * Kunihiro Ishiguro <kunihiro@ipinfusion.com>
* YOSHIFUJI Hideaki @USAGI
* IPv6 support
*/
@@ -52,7 +52,6 @@ int xfrm6_rcv(struct sk_buff *skb)
return xfrm6_rcv_spi(skb, skb_network_header(skb)[IP6CB(skb)->nhoff],
0);
}
-
EXPORT_SYMBOL(xfrm6_rcv);
int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
@@ -142,5 +141,4 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
drop:
return -1;
}
-
EXPORT_SYMBOL(xfrm6_input_addr);
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 433672d07d0..ca3f29b98ae 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -25,7 +25,6 @@ int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb,
{
return ip6_find_1stfragopt(skb, prevhdr);
}
-
EXPORT_SYMBOL(xfrm6_find_1stfragopt);
static int xfrm6_local_dontfrag(struct sk_buff *skb)
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 2a0bbda2c76..ac49f84fe2c 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -3,11 +3,11 @@
*
* Authors:
* Mitsuru KANDA @USAGI
- * Kazunori MIYAZAWA @USAGI
- * Kunihiro Ishiguro <kunihiro@ipinfusion.com>
- * IPv6 support
- * YOSHIFUJI Hideaki
- * Split up af-specific portion
+ * Kazunori MIYAZAWA @USAGI
+ * Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ * IPv6 support
+ * YOSHIFUJI Hideaki
+ * Split up af-specific portion
*
*/
@@ -84,7 +84,7 @@ static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst,
int nfheader_len)
{
if (dst->ops->family == AF_INET6) {
- struct rt6_info *rt = (struct rt6_info*)dst;
+ struct rt6_info *rt = (struct rt6_info *)dst;
if (rt->rt6i_node)
path->path_cookie = rt->rt6i_node->fn_sernum;
}
@@ -97,7 +97,7 @@ static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst,
static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
const struct flowi *fl)
{
- struct rt6_info *rt = (struct rt6_info*)xdst->route;
+ struct rt6_info *rt = (struct rt6_info *)xdst->route;
xdst->u.dst.dev = dev;
dev_hold(dev);
@@ -296,7 +296,7 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
.family = AF_INET6,
.dst_ops = &xfrm6_dst_ops,
.dst_lookup = xfrm6_dst_lookup,
- .get_saddr = xfrm6_get_saddr,
+ .get_saddr = xfrm6_get_saddr,
.decode_session = _decode_session6,
.get_tos = xfrm6_get_tos,
.init_dst = xfrm6_init_dst,
@@ -319,9 +319,9 @@ static void xfrm6_policy_fini(void)
static struct ctl_table xfrm6_policy_table[] = {
{
.procname = "xfrm6_gc_thresh",
- .data = &init_net.xfrm.xfrm6_dst_ops.gc_thresh,
- .maxlen = sizeof(int),
- .mode = 0644,
+ .data = &init_net.xfrm.xfrm6_dst_ops.gc_thresh,
+ .maxlen = sizeof(int),
+ .mode = 0644,
.proc_handler = proc_dointvec,
},
{ }
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index 3fc970135fc..8a1f9c0d2a1 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -3,11 +3,11 @@
*
* Authors:
* Mitsuru KANDA @USAGI
- * Kazunori MIYAZAWA @USAGI
- * Kunihiro Ishiguro <kunihiro@ipinfusion.com>
- * IPv6 support
- * YOSHIFUJI Hideaki @USAGI
- * Split up af-specific portion
+ * Kazunori MIYAZAWA @USAGI
+ * Kunihiro Ishiguro <kunihiro@ipinfusion.com>
+ * IPv6 support
+ * YOSHIFUJI Hideaki @USAGI
+ * Split up af-specific portion
*
*/
@@ -45,10 +45,10 @@ xfrm6_init_temprop(struct xfrm_state *x, const struct xfrm_tmpl *tmpl,
const xfrm_address_t *daddr, const xfrm_address_t *saddr)
{
x->id = tmpl->id;
- if (ipv6_addr_any((struct in6_addr*)&x->id.daddr))
+ if (ipv6_addr_any((struct in6_addr *)&x->id.daddr))
memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr));
memcpy(&x->props.saddr, &tmpl->saddr, sizeof(x->props.saddr));
- if (ipv6_addr_any((struct in6_addr*)&x->props.saddr))
+ if (ipv6_addr_any((struct in6_addr *)&x->props.saddr))
memcpy(&x->props.saddr, saddr, sizeof(x->props.saddr));
x->props.mode = tmpl->mode;
x->props.reqid = tmpl->reqid;
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 1c66465a42d..5743044cd66 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -15,7 +15,7 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*
* Authors Mitsuru KANDA <mk@linux-ipv6.org>
- * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
+ * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
*
* Based on net/ipv4/xfrm4_tunnel.c
*
@@ -110,7 +110,6 @@ __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr)
rcu_read_unlock_bh();
return htonl(spi);
}
-
EXPORT_SYMBOL(xfrm6_tunnel_spi_lookup);
static int __xfrm6_tunnel_spi_check(struct net *net, u32 spi)
@@ -187,7 +186,6 @@ __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr)
return htonl(spi);
}
-
EXPORT_SYMBOL(xfrm6_tunnel_alloc_spi);
static void x6spi_destroy_rcu(struct rcu_head *head)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 1109d3bb8da..2aa2b6c15f2 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -148,7 +148,7 @@ do { \
atomic_read(&_t->ref_count)); \
l2tp_tunnel_inc_refcount_1(_t); \
} while (0)
-#define l2tp_tunnel_dec_refcount(_t)
+#define l2tp_tunnel_dec_refcount(_t) \
do { \
pr_debug("l2tp_tunnel_dec_refcount: %s:%d %s: cnt=%d\n", \
__func__, __LINE__, (_t)->name, \
@@ -1392,6 +1392,8 @@ static int l2tp_tunnel_sock_create(struct net *net,
if (err < 0)
goto out;
+ udp_set_convert_csum(sock->sk, true);
+
break;
case L2TP_ENCAPTYPE_IP:
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index de88c4ab514..5016a692908 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -142,7 +142,7 @@ static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, u16 zone)
static u32 __hash_bucket(u32 hash, unsigned int size)
{
- return ((u64)hash * size) >> 32;
+ return reciprocal_scale(hash, size);
}
static u32 hash_bucket(u32 hash, const struct net *net)
@@ -358,7 +358,7 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report)
tstamp = nf_conn_tstamp_find(ct);
if (tstamp && tstamp->stop == 0)
- tstamp->stop = ktime_to_ns(ktime_get_real());
+ tstamp->stop = ktime_get_real_ns();
if (nf_ct_is_dying(ct))
goto delete;
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index f87e8f68ad4..91a1837acd0 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -83,7 +83,8 @@ static unsigned int nf_ct_expect_dst_hash(const struct nf_conntrack_tuple *tuple
hash = jhash2(tuple->dst.u3.all, ARRAY_SIZE(tuple->dst.u3.all),
(((tuple->dst.protonum ^ tuple->src.l3num) << 16) |
(__force __u16)tuple->dst.u.all) ^ nf_conntrack_hash_rnd);
- return ((u64)hash * nf_ct_expect_hsize) >> 32;
+
+ return reciprocal_scale(hash, nf_ct_expect_hsize);
}
struct nf_conntrack_expect *
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 355a5c4ef76..1bd9ed9e62f 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1737,7 +1737,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone,
}
tstamp = nf_conn_tstamp_find(ct);
if (tstamp)
- tstamp->start = ktime_to_ns(ktime_get_real());
+ tstamp->start = ktime_get_real_ns();
err = nf_conntrack_hash_check_insert(ct);
if (err < 0)
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index f641751dba9..cf65a1e040d 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -101,7 +101,7 @@ static void *ct_seq_start(struct seq_file *seq, loff_t *pos)
{
struct ct_iter_state *st = seq->private;
- st->time_now = ktime_to_ns(ktime_get_real());
+ st->time_now = ktime_get_real_ns();
rcu_read_lock();
return ct_get_idx(seq, *pos);
}
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 552f97cd9fd..4e0b47831d4 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -126,7 +126,8 @@ hash_by_src(const struct net *net, u16 zone,
/* Original src, to ensure we map it consistently if poss. */
hash = jhash2((u32 *)&tuple->src, sizeof(tuple->src) / sizeof(u32),
tuple->dst.protonum ^ zone ^ nf_conntrack_hash_rnd);
- return ((u64)hash * net->ct.nat_htable_size) >> 32;
+
+ return reciprocal_scale(hash, net->ct.nat_htable_size);
}
/* Is this tuple already taken? (not by us) */
@@ -274,7 +275,7 @@ find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple,
}
var_ipp->all[i] = (__force __u32)
- htonl(minip + (((u64)j * dist) >> 32));
+ htonl(minip + reciprocal_scale(j, dist));
if (var_ipp->all[i] != range->max_addr.all[i])
full_range = true;
diff --git a/net/netfilter/xt_HMARK.c b/net/netfilter/xt_HMARK.c
index 73b73f687c5..02afaf48a72 100644
--- a/net/netfilter/xt_HMARK.c
+++ b/net/netfilter/xt_HMARK.c
@@ -126,7 +126,7 @@ hmark_hash(struct hmark_tuple *t, const struct xt_hmark_info *info)
hash = jhash_3words(src, dst, t->uports.v32, info->hashrnd);
hash = hash ^ (t->proto & info->proto_mask);
- return (((u64)hash * info->hmodulus) >> 32) + info->hoffset;
+ return reciprocal_scale(hash, info->hmodulus) + info->hoffset;
}
static void
diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c
index f4af1bfafb1..96fa26b20b6 100644
--- a/net/netfilter/xt_cluster.c
+++ b/net/netfilter/xt_cluster.c
@@ -55,7 +55,8 @@ xt_cluster_hash(const struct nf_conn *ct,
WARN_ON(1);
break;
}
- return (((u64)hash * info->total_nodes) >> 32);
+
+ return reciprocal_scale(hash, info->total_nodes);
}
static inline bool
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 47dc6836830..52eb3e03458 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -135,7 +135,7 @@ hash_dst(const struct xt_hashlimit_htable *ht, const struct dsthash_dst *dst)
* give results between [0 and cfg.size-1] and same hash distribution,
* but using a multiply, less expensive than a divide
*/
- return ((u64)hash * ht->cfg.size) >> 32;
+ return reciprocal_scale(hash, ht->cfg.size);
}
static struct dsthash_ent *
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index d07ab538fc9..7064da92f42 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -89,7 +89,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
* allocated stats as we have already locked them.
*/
if (likely(flow->stats_last_writer != NUMA_NO_NODE)
- && likely(!rcu_dereference(flow->stats[node]))) {
+ && likely(!rcu_access_pointer(flow->stats[node]))) {
/* Try to allocate node-specific stats. */
struct flow_stats *new_stats;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 93896d2092f..87d20f48ff0 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -240,11 +240,9 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po);
static int packet_direct_xmit(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
- const struct net_device_ops *ops = dev->netdev_ops;
netdev_features_t features;
struct netdev_queue *txq;
int ret = NETDEV_TX_BUSY;
- u16 queue_map;
if (unlikely(!netif_running(dev) ||
!netif_carrier_ok(dev)))
@@ -255,17 +253,13 @@ static int packet_direct_xmit(struct sk_buff *skb)
__skb_linearize(skb))
goto drop;
- queue_map = skb_get_queue_mapping(skb);
- txq = netdev_get_tx_queue(dev, queue_map);
+ txq = skb_get_tx_queue(dev, skb);
local_bh_disable();
HARD_TX_LOCK(dev, txq, smp_processor_id());
- if (!netif_xmit_frozen_or_drv_stopped(txq)) {
- ret = ops->ndo_start_xmit(skb, dev);
- if (ret == NETDEV_TX_OK)
- txq_trans_update(txq);
- }
+ if (!netif_xmit_frozen_or_drv_stopped(txq))
+ ret = netdev_start_xmit(skb, dev, txq, false);
HARD_TX_UNLOCK(dev, txq);
local_bh_enable();
diff --git a/net/rose/rose_link.c b/net/rose/rose_link.c
index bc5514211b0..e873d7d9f85 100644
--- a/net/rose/rose_link.c
+++ b/net/rose/rose_link.c
@@ -160,7 +160,8 @@ void rose_link_rx_restart(struct sk_buff *skb, struct rose_neigh *neigh, unsigne
break;
case ROSE_DIAGNOSTIC:
- printk(KERN_WARNING "ROSE: received diagnostic #%d - %02X %02X %02X\n", skb->data[3], skb->data[4], skb->data[5], skb->data[6]);
+ pr_warn("ROSE: received diagnostic #%d - %3ph\n", skb->data[3],
+ skb->data + 4);
break;
default:
diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c
index db57458c824..74c0fcd3683 100644
--- a/net/rxrpc/ar-error.c
+++ b/net/rxrpc/ar-error.c
@@ -37,7 +37,7 @@ void rxrpc_UDP_error_report(struct sock *sk)
_enter("%p{%d}", sk, local->debug_id);
- skb = skb_dequeue(&sk->sk_error_queue);
+ skb = sock_dequeue_err_skb(sk);
if (!skb) {
_leave("UDP socket errqueue empty");
return;
@@ -111,18 +111,6 @@ void rxrpc_UDP_error_report(struct sock *sk)
skb_queue_tail(&trans->error_queue, skb);
rxrpc_queue_work(&trans->error_handler);
- /* reset and regenerate socket error */
- spin_lock_bh(&sk->sk_error_queue.lock);
- sk->sk_err = 0;
- skb = skb_peek(&sk->sk_error_queue);
- if (skb) {
- sk->sk_err = SKB_EXT_ERR(skb)->ee.ee_errno;
- spin_unlock_bh(&sk->sk_error_queue.lock);
- sk->sk_error_report(sk);
- } else {
- spin_unlock_bh(&sk->sk_error_queue.lock);
- }
-
_leave("");
}
diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c
index 63b21e580de..481f89f9378 100644
--- a/net/rxrpc/ar-input.c
+++ b/net/rxrpc/ar-input.c
@@ -45,7 +45,7 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb,
struct rxrpc_skb_priv *sp;
struct rxrpc_sock *rx = call->socket;
struct sock *sk;
- int skb_len, ret;
+ int ret;
_enter(",,%d,%d", force, terminal);
@@ -101,13 +101,6 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb,
rx->interceptor(sk, call->user_call_ID, skb);
spin_unlock_bh(&sk->sk_receive_queue.lock);
} else {
-
- /* Cache the SKB length before we tack it onto the
- * receive queue. Once it is added it no longer
- * belongs to us and may be freed by other threads of
- * control pulling packets from the queue */
- skb_len = skb->len;
-
_net("post skb %p", skb);
__skb_queue_tail(&sk->sk_receive_queue, skb);
spin_unlock_bh(&sk->sk_receive_queue.lock);
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 0566e4606a4..f32bcb09491 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -231,7 +231,7 @@ override:
if (ret != ACT_P_CREATED)
return ret;
- police->tcfp_t_c = ktime_to_ns(ktime_get());
+ police->tcfp_t_c = ktime_get_ns();
police->tcf_index = parm->index ? parm->index :
tcf_hash_new_index(hinfo);
h = tcf_hash(police->tcf_index, POL_TAB_MASK);
@@ -279,7 +279,7 @@ static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a,
return police->tcfp_result;
}
- now = ktime_to_ns(ktime_get());
+ now = ktime_get_ns();
toks = min_t(s64, now - police->tcfp_t_c,
police->tcfp_burst);
if (police->peak_present) {
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index ba32c2b005d..e12f997e1b4 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -416,7 +416,7 @@ static void fq_check_throttled(struct fq_sched_data *q, u64 now)
static struct sk_buff *fq_dequeue(struct Qdisc *sch)
{
struct fq_sched_data *q = qdisc_priv(sch);
- u64 now = ktime_to_ns(ktime_get());
+ u64 now = ktime_get_ns();
struct fq_flow_head *head;
struct sk_buff *skb;
struct fq_flow *f;
@@ -787,7 +787,7 @@ nla_put_failure:
static int fq_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
{
struct fq_sched_data *q = qdisc_priv(sch);
- u64 now = ktime_to_ns(ktime_get());
+ u64 now = ktime_get_ns();
struct tc_fq_qd_stats st = {
.gc_flows = q->stat_gc_flows,
.highprio_packets = q->stat_internal_packets,
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 063b726bf1f..cc56c8bb9be 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -77,7 +77,8 @@ static unsigned int fq_codel_hash(const struct fq_codel_sched_data *q,
hash = jhash_3words((__force u32)keys.dst,
(__force u32)keys.src ^ keys.ip_proto,
(__force u32)keys.ports, q->perturbation);
- return ((u64)hash * q->flows_cnt) >> 32;
+
+ return reciprocal_scale(hash, q->flows_cnt);
}
static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch,
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index fc04fe93c2d..19696ebe9eb 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -63,15 +63,18 @@ static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
if (unlikely(skb)) {
/* check the reason of requeuing without tx lock first */
- txq = netdev_get_tx_queue(txq->dev, skb_get_queue_mapping(skb));
+ txq = skb_get_tx_queue(txq->dev, skb);
if (!netif_xmit_frozen_or_stopped(txq)) {
q->gso_skb = NULL;
q->q.qlen--;
} else
skb = NULL;
} else {
- if (!(q->flags & TCQ_F_ONETXQUEUE) || !netif_xmit_frozen_or_stopped(txq))
+ if (!(q->flags & TCQ_F_ONETXQUEUE) || !netif_xmit_frozen_or_stopped(txq)) {
skb = q->dequeue(q);
+ if (skb)
+ skb = validate_xmit_skb(skb, qdisc_dev(q));
+ }
}
return skb;
@@ -90,7 +93,7 @@ static inline int handle_dev_cpu_collision(struct sk_buff *skb,
* detect it by checking xmit owner and drop the packet when
* deadloop is detected. Return OK to try the next skb.
*/
- kfree_skb(skb);
+ kfree_skb_list(skb);
net_warn_ratelimited("Dead loop on netdevice %s, fix it urgently!\n",
dev_queue->dev->name);
ret = qdisc_qlen(q);
@@ -107,9 +110,9 @@ static inline int handle_dev_cpu_collision(struct sk_buff *skb,
}
/*
- * Transmit one skb, and handle the return status as required. Holding the
- * __QDISC___STATE_RUNNING bit guarantees that only one CPU can execute this
- * function.
+ * Transmit possibly several skbs, and handle the return status as
+ * required. Holding the __QDISC___STATE_RUNNING bit guarantees that
+ * only one CPU can execute this function.
*
* Returns to the caller:
* 0 - queue is empty or throttled.
@@ -126,7 +129,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
HARD_TX_LOCK(dev, txq, smp_processor_id());
if (!netif_xmit_frozen_or_stopped(txq))
- ret = dev_hard_start_xmit(skb, dev, txq);
+ skb = dev_hard_start_xmit(skb, dev, txq, &ret);
HARD_TX_UNLOCK(dev, txq);
@@ -183,10 +186,12 @@ static inline int qdisc_restart(struct Qdisc *q)
skb = dequeue_skb(q);
if (unlikely(!skb))
return 0;
+
WARN_ON_ONCE(skb_dst_is_noref(skb));
+
root_lock = qdisc_lock(q);
dev = qdisc_dev(q);
- txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
+ txq = skb_get_tx_queue(dev, skb);
return sch_direct_xmit(skb, q, dev, txq, root_lock);
}
@@ -616,7 +621,7 @@ void qdisc_reset(struct Qdisc *qdisc)
ops->reset(qdisc);
if (qdisc->gso_skb) {
- kfree_skb(qdisc->gso_skb);
+ kfree_skb_list(qdisc->gso_skb);
qdisc->gso_skb = NULL;
qdisc->q.qlen = 0;
}
@@ -652,7 +657,7 @@ void qdisc_destroy(struct Qdisc *qdisc)
module_put(ops->owner);
dev_put(qdisc_dev(qdisc));
- kfree_skb(qdisc->gso_skb);
+ kfree_skb_list(qdisc->gso_skb);
/*
* gen_estimator est_timer() might access qdisc->q.lock,
* wait a RCU grace period before freeing qdisc.
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 9f949abcace..aea942ce600 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -895,7 +895,7 @@ ok:
if (!sch->q.qlen)
goto fin;
- q->now = ktime_to_ns(ktime_get());
+ q->now = ktime_get_ns();
start_at = jiffies;
next_event = q->now + 5LLU * NSEC_PER_SEC;
@@ -1225,7 +1225,7 @@ static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl,
parent->un.leaf.q = new_q ? new_q : &noop_qdisc;
parent->tokens = parent->buffer;
parent->ctokens = parent->cbuffer;
- parent->t_c = ktime_to_ns(ktime_get());
+ parent->t_c = ktime_get_ns();
parent->cmode = HTB_CAN_SEND;
}
@@ -1455,7 +1455,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
cl->tokens = PSCHED_TICKS2NS(hopt->buffer);
cl->ctokens = PSCHED_TICKS2NS(hopt->cbuffer);
cl->mbuffer = 60ULL * NSEC_PER_SEC; /* 1min */
- cl->t_c = ktime_to_ns(ktime_get());
+ cl->t_c = ktime_get_ns();
cl->cmode = HTB_CAN_SEND;
/* attach to the hash list and parent's family */
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 18ff6343370..0c39b754083 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -239,7 +239,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc *sch)
s64 ptoks = 0;
unsigned int len = qdisc_pkt_len(skb);
- now = ktime_to_ns(ktime_get());
+ now = ktime_get_ns();
toks = min_t(s64, now - q->t_c, q->buffer);
if (tbf_peak_present(q)) {
@@ -292,7 +292,7 @@ static void tbf_reset(struct Qdisc *sch)
qdisc_reset(q->qdisc);
sch->q.qlen = 0;
- q->t_c = ktime_to_ns(ktime_get());
+ q->t_c = ktime_get_ns();
q->tokens = q->buffer;
q->ptokens = q->mtu;
qdisc_watchdog_cancel(&q->watchdog);
@@ -431,7 +431,7 @@ static int tbf_init(struct Qdisc *sch, struct nlattr *opt)
if (opt == NULL)
return -EINVAL;
- q->t_c = ktime_to_ns(ktime_get());
+ q->t_c = ktime_get_ns();
qdisc_watchdog_init(&q->watchdog, sch);
q->qdisc = &noop_qdisc;
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index bd33793b527..aaa8d03ed05 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -301,7 +301,6 @@ restart:
do {
struct net_device *slave = qdisc_dev(q);
struct netdev_queue *slave_txq = netdev_get_tx_queue(slave, 0);
- const struct net_device_ops *slave_ops = slave->netdev_ops;
if (slave_txq->qdisc_sleeping != q)
continue;
@@ -317,8 +316,8 @@ restart:
unsigned int length = qdisc_pkt_len(skb);
if (!netif_xmit_frozen_or_stopped(slave_txq) &&
- slave_ops->ndo_start_xmit(skb, slave) == NETDEV_TX_OK) {
- txq_trans_update(slave_txq);
+ netdev_start_xmit(skb, slave, slave_txq, false) ==
+ NETDEV_TX_OK) {
__netif_tx_unlock(slave_txq);
master->slaves = NEXT_SLAVE(q);
netif_wake_queue(dev);
diff --git a/net/sctp/input.c b/net/sctp/input.c
index c1b99129451..b6493b3f11a 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -133,9 +133,13 @@ int sctp_rcv(struct sk_buff *skb)
__skb_pull(skb, skb_transport_offset(skb));
if (skb->len < sizeof(struct sctphdr))
goto discard_it;
- if (!sctp_checksum_disable && !skb_csum_unnecessary(skb) &&
- sctp_rcv_checksum(net, skb) < 0)
+
+ skb->csum_valid = 0; /* Previous value not applicable */
+ if (skb_csum_unnecessary(skb))
+ __skb_decr_checksum_unnecessary(skb);
+ else if (!sctp_checksum_disable && sctp_rcv_checksum(net, skb) < 0)
goto discard_it;
+ skb->csum_valid = 1;
skb_pull(skb, sizeof(struct sctphdr));
diff --git a/net/tipc/Makefile b/net/tipc/Makefile
index a080c66d819..b8a13caad59 100644
--- a/net/tipc/Makefile
+++ b/net/tipc/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_TIPC) := tipc.o
tipc-y += addr.o bcast.o bearer.o config.o \
core.o link.o discover.o msg.o \
name_distr.o subscr.o name_table.o net.o \
- netlink.o node.o node_subscr.o port.o ref.o \
+ netlink.o node.o node_subscr.o \
socket.o log.o eth_media.o server.o
tipc-$(CONFIG_TIPC_MEDIA_IB) += ib_media.o
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index dd13bfa0933..b2bbe69b255 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -37,7 +37,6 @@
#include "core.h"
#include "link.h"
-#include "port.h"
#include "socket.h"
#include "msg.h"
#include "bcast.h"
@@ -300,8 +299,8 @@ void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked)
tipc_link_push_queue(bcl);
bclink_set_last_sent();
}
- if (unlikely(released && !list_empty(&bcl->waiting_ports)))
- tipc_link_wakeup_ports(bcl, 0);
+ if (unlikely(released && !skb_queue_empty(&bcl->waiting_sks)))
+ bclink->node.action_flags |= TIPC_WAKEUP_USERS;
exit:
tipc_bclink_unlock();
}
@@ -840,9 +839,10 @@ int tipc_bclink_init(void)
sprintf(bcbearer->media.name, "tipc-broadcast");
spin_lock_init(&bclink->lock);
- INIT_LIST_HEAD(&bcl->waiting_ports);
+ __skb_queue_head_init(&bcl->waiting_sks);
bcl->next_out_no = 1;
spin_lock_init(&bclink->node.lock);
+ __skb_queue_head_init(&bclink->node.waiting_sks);
bcl->owner = &bclink->node;
bcl->max_pkt = MAX_PKT_DEFAULT_MCAST;
tipc_link_set_queue_limits(bcl, BCLINK_WIN_DEFAULT);
diff --git a/net/tipc/config.c b/net/tipc/config.c
index 2b42403ad33..876f4c6a263 100644
--- a/net/tipc/config.c
+++ b/net/tipc/config.c
@@ -35,7 +35,7 @@
*/
#include "core.h"
-#include "port.h"
+#include "socket.h"
#include "name_table.h"
#include "config.h"
#include "server.h"
@@ -266,7 +266,7 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area
rep_tlv_buf = tipc_media_get_names();
break;
case TIPC_CMD_SHOW_PORTS:
- rep_tlv_buf = tipc_port_get_ports();
+ rep_tlv_buf = tipc_sk_socks_show();
break;
case TIPC_CMD_SHOW_STATS:
rep_tlv_buf = tipc_show_stats();
diff --git a/net/tipc/core.c b/net/tipc/core.c
index 676d18015dd..a5737b8407d 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -35,11 +35,10 @@
*/
#include "core.h"
-#include "ref.h"
#include "name_table.h"
#include "subscr.h"
#include "config.h"
-#include "port.h"
+#include "socket.h"
#include <linux/module.h>
@@ -85,7 +84,7 @@ static void tipc_core_stop(void)
tipc_netlink_stop();
tipc_subscr_stop();
tipc_nametbl_stop();
- tipc_ref_table_stop();
+ tipc_sk_ref_table_stop();
tipc_socket_stop();
tipc_unregister_sysctl();
}
@@ -99,7 +98,7 @@ static int tipc_core_start(void)
get_random_bytes(&tipc_random, sizeof(tipc_random));
- err = tipc_ref_table_init(tipc_max_ports, tipc_random);
+ err = tipc_sk_ref_table_init(tipc_max_ports, tipc_random);
if (err)
goto out_reftbl;
@@ -139,7 +138,7 @@ out_socket:
out_netlink:
tipc_nametbl_stop();
out_nametbl:
- tipc_ref_table_stop();
+ tipc_sk_ref_table_stop();
out_reftbl:
return err;
}
diff --git a/net/tipc/core.h b/net/tipc/core.h
index bb26ed1ee96..f773b148722 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -81,6 +81,7 @@ extern u32 tipc_own_addr __read_mostly;
extern int tipc_max_ports __read_mostly;
extern int tipc_net_id __read_mostly;
extern int sysctl_tipc_rmem[3] __read_mostly;
+extern int sysctl_tipc_named_timeout __read_mostly;
/*
* Other global variables
@@ -187,8 +188,11 @@ static inline void k_term_timer(struct timer_list *timer)
struct tipc_skb_cb {
void *handle;
- bool deferred;
struct sk_buff *tail;
+ bool deferred;
+ bool wakeup_pending;
+ u16 chain_sz;
+ u16 chain_imp;
};
#define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0]))
diff --git a/net/tipc/link.c b/net/tipc/link.c
index fb1485dc673..65410e18b8a 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -36,7 +36,6 @@
#include "core.h"
#include "link.h"
-#include "port.h"
#include "socket.h"
#include "name_distr.h"
#include "discover.h"
@@ -275,7 +274,7 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
link_init_max_pkt(l_ptr);
l_ptr->next_out_no = 1;
- INIT_LIST_HEAD(&l_ptr->waiting_ports);
+ __skb_queue_head_init(&l_ptr->waiting_sks);
link_reset_statistics(l_ptr);
@@ -322,66 +321,47 @@ void tipc_link_delete_list(unsigned int bearer_id, bool shutting_down)
}
/**
- * link_schedule_port - schedule port for deferred sending
- * @l_ptr: pointer to link
- * @origport: reference to sending port
- * @sz: amount of data to be sent
- *
- * Schedules port for renewed sending of messages after link congestion
- * has abated.
+ * link_schedule_user - schedule user for wakeup after congestion
+ * @link: congested link
+ * @oport: sending port
+ * @chain_sz: size of buffer chain that was attempted sent
+ * @imp: importance of message attempted sent
+ * Create pseudo msg to send back to user when congestion abates
*/
-static int link_schedule_port(struct tipc_link *l_ptr, u32 origport, u32 sz)
+static bool link_schedule_user(struct tipc_link *link, u32 oport,
+ uint chain_sz, uint imp)
{
- struct tipc_port *p_ptr;
- struct tipc_sock *tsk;
+ struct sk_buff *buf;
- spin_lock_bh(&tipc_port_list_lock);
- p_ptr = tipc_port_lock(origport);
- if (p_ptr) {
- if (!list_empty(&p_ptr->wait_list))
- goto exit;
- tsk = tipc_port_to_sock(p_ptr);
- tsk->link_cong = 1;
- p_ptr->waiting_pkts = 1 + ((sz - 1) / l_ptr->max_pkt);
- list_add_tail(&p_ptr->wait_list, &l_ptr->waiting_ports);
- l_ptr->stats.link_congs++;
-exit:
- tipc_port_unlock(p_ptr);
- }
- spin_unlock_bh(&tipc_port_list_lock);
- return -ELINKCONG;
+ buf = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, tipc_own_addr,
+ tipc_own_addr, oport, 0, 0);
+ if (!buf)
+ return false;
+ TIPC_SKB_CB(buf)->chain_sz = chain_sz;
+ TIPC_SKB_CB(buf)->chain_imp = imp;
+ __skb_queue_tail(&link->waiting_sks, buf);
+ link->stats.link_congs++;
+ return true;
}
-void tipc_link_wakeup_ports(struct tipc_link *l_ptr, int all)
+/**
+ * link_prepare_wakeup - prepare users for wakeup after congestion
+ * @link: congested link
+ * Move a number of waiting users, as permitted by available space in
+ * the send queue, from link wait queue to node wait queue for wakeup
+ */
+static void link_prepare_wakeup(struct tipc_link *link)
{
- struct tipc_port *p_ptr;
- struct tipc_sock *tsk;
- struct tipc_port *temp_p_ptr;
- int win = l_ptr->queue_limit[0] - l_ptr->out_queue_size;
-
- if (all)
- win = 100000;
- if (win <= 0)
- return;
- if (!spin_trylock_bh(&tipc_port_list_lock))
- return;
- if (link_congested(l_ptr))
- goto exit;
- list_for_each_entry_safe(p_ptr, temp_p_ptr, &l_ptr->waiting_ports,
- wait_list) {
- if (win <= 0)
+ struct sk_buff_head *wq = &link->waiting_sks;
+ struct sk_buff *buf;
+ uint pend_qsz = link->out_queue_size;
+
+ for (buf = skb_peek(wq); buf; buf = skb_peek(wq)) {
+ if (pend_qsz >= link->queue_limit[TIPC_SKB_CB(buf)->chain_imp])
break;
- tsk = tipc_port_to_sock(p_ptr);
- list_del_init(&p_ptr->wait_list);
- spin_lock_bh(p_ptr->lock);
- tsk->link_cong = 0;
- tipc_sock_wakeup(tsk);
- win -= p_ptr->waiting_pkts;
- spin_unlock_bh(p_ptr->lock);
+ pend_qsz += TIPC_SKB_CB(buf)->chain_sz;
+ __skb_queue_tail(&link->owner->waiting_sks, __skb_dequeue(wq));
}
-
-exit:
- spin_unlock_bh(&tipc_port_list_lock);
}
/**
@@ -423,6 +403,7 @@ void tipc_link_reset(struct tipc_link *l_ptr)
u32 prev_state = l_ptr->state;
u32 checkpoint = l_ptr->next_in_no;
int was_active_link = tipc_link_is_active(l_ptr);
+ struct tipc_node *owner = l_ptr->owner;
msg_set_session(l_ptr->pmsg, ((msg_session(l_ptr->pmsg) + 1) & 0xffff));
@@ -450,9 +431,10 @@ void tipc_link_reset(struct tipc_link *l_ptr)
kfree_skb(l_ptr->proto_msg_queue);
l_ptr->proto_msg_queue = NULL;
kfree_skb_list(l_ptr->oldest_deferred_in);
- if (!list_empty(&l_ptr->waiting_ports))
- tipc_link_wakeup_ports(l_ptr, 1);
-
+ if (!skb_queue_empty(&l_ptr->waiting_sks)) {
+ skb_queue_splice_init(&l_ptr->waiting_sks, &owner->waiting_sks);
+ owner->action_flags |= TIPC_WAKEUP_USERS;
+ }
l_ptr->retransm_queue_head = 0;
l_ptr->retransm_queue_size = 0;
l_ptr->last_out = NULL;
@@ -688,19 +670,23 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event)
static int tipc_link_cong(struct tipc_link *link, struct sk_buff *buf)
{
struct tipc_msg *msg = buf_msg(buf);
- uint psz = msg_size(msg);
uint imp = tipc_msg_tot_importance(msg);
u32 oport = msg_tot_origport(msg);
- if (likely(imp <= TIPC_CRITICAL_IMPORTANCE)) {
- if (!msg_errcode(msg) && !msg_reroute_cnt(msg)) {
- link_schedule_port(link, oport, psz);
- return -ELINKCONG;
- }
- } else {
+ if (unlikely(imp > TIPC_CRITICAL_IMPORTANCE)) {
pr_warn("%s<%s>, send queue full", link_rst_msg, link->name);
tipc_link_reset(link);
+ goto drop;
}
+ if (unlikely(msg_errcode(msg)))
+ goto drop;
+ if (unlikely(msg_reroute_cnt(msg)))
+ goto drop;
+ if (TIPC_SKB_CB(buf)->wakeup_pending)
+ return -ELINKCONG;
+ if (link_schedule_user(link, oport, TIPC_SKB_CB(buf)->chain_sz, imp))
+ return -ELINKCONG;
+drop:
kfree_skb_list(buf);
return -EHOSTUNREACH;
}
@@ -1202,8 +1188,10 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr)
if (unlikely(l_ptr->next_out))
tipc_link_push_queue(l_ptr);
- if (unlikely(!list_empty(&l_ptr->waiting_ports)))
- tipc_link_wakeup_ports(l_ptr, 0);
+ if (released && !skb_queue_empty(&l_ptr->waiting_sks)) {
+ link_prepare_wakeup(l_ptr);
+ l_ptr->owner->action_flags |= TIPC_WAKEUP_USERS;
+ }
/* Process the incoming packet */
if (unlikely(!link_working_working(l_ptr))) {
diff --git a/net/tipc/link.h b/net/tipc/link.h
index 782983ccd32..b567a3427fd 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -1,7 +1,7 @@
/*
* net/tipc/link.h: Include file for TIPC link code
*
- * Copyright (c) 1995-2006, 2013, Ericsson AB
+ * Copyright (c) 1995-2006, 2013-2014, Ericsson AB
* Copyright (c) 2004-2005, 2010-2011, Wind River Systems
* All rights reserved.
*
@@ -133,7 +133,7 @@ struct tipc_stats {
* @retransm_queue_size: number of messages to retransmit
* @retransm_queue_head: sequence number of first message to retransmit
* @next_out: ptr to first unsent outbound message in queue
- * @waiting_ports: linked list of ports waiting for link congestion to abate
+ * @waiting_sks: linked list of sockets waiting for link congestion to abate
* @long_msg_seq_no: next identifier to use for outbound fragmented messages
* @reasm_buf: head of partially reassembled inbound message fragments
* @stats: collects statistics regarding link activity
@@ -194,7 +194,7 @@ struct tipc_link {
u32 retransm_queue_size;
u32 retransm_queue_head;
struct sk_buff *next_out;
- struct list_head waiting_ports;
+ struct sk_buff_head waiting_sks;
/* Fragmentation/reassembly */
u32 long_msg_seq_no;
@@ -235,7 +235,6 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int prob,
void tipc_link_push_queue(struct tipc_link *l_ptr);
u32 tipc_link_defer_pkt(struct sk_buff **head, struct sk_buff **tail,
struct sk_buff *buf);
-void tipc_link_wakeup_ports(struct tipc_link *l_ptr, int all);
void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window);
void tipc_link_retransmit(struct tipc_link *l_ptr,
struct sk_buff *start, u32 retransmits);
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 9680be6d388..74745a47d72 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -56,8 +56,35 @@ void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, u32 hsize,
msg_set_size(m, hsize);
msg_set_prevnode(m, tipc_own_addr);
msg_set_type(m, type);
- msg_set_orignode(m, tipc_own_addr);
- msg_set_destnode(m, destnode);
+ if (hsize > SHORT_H_SIZE) {
+ msg_set_orignode(m, tipc_own_addr);
+ msg_set_destnode(m, destnode);
+ }
+}
+
+struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz,
+ uint data_sz, u32 dnode, u32 onode,
+ u32 dport, u32 oport, int errcode)
+{
+ struct tipc_msg *msg;
+ struct sk_buff *buf;
+
+ buf = tipc_buf_acquire(hdr_sz + data_sz);
+ if (unlikely(!buf))
+ return NULL;
+
+ msg = buf_msg(buf);
+ tipc_msg_init(msg, user, type, hdr_sz, dnode);
+ msg_set_size(msg, hdr_sz + data_sz);
+ msg_set_prevnode(msg, onode);
+ msg_set_origport(msg, oport);
+ msg_set_destport(msg, dport);
+ msg_set_errcode(msg, errcode);
+ if (hdr_sz > SHORT_H_SIZE) {
+ msg_set_orignode(msg, onode);
+ msg_set_destnode(msg, dnode);
+ }
+ return buf;
}
/* tipc_buf_append(): Append a buffer to the fragment list of another buffer
@@ -155,7 +182,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct iovec const *iov,
struct sk_buff *buf, *prev;
char *pktpos;
int rc;
-
+ uint chain_sz = 0;
msg_set_size(mhdr, msz);
/* No fragmentation needed? */
@@ -166,6 +193,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct iovec const *iov,
return -ENOMEM;
skb_copy_to_linear_data(buf, mhdr, mhsz);
pktpos = buf->data + mhsz;
+ TIPC_SKB_CB(buf)->chain_sz = 1;
if (!dsz || !memcpy_fromiovecend(pktpos, iov, offset, dsz))
return dsz;
rc = -EFAULT;
@@ -182,6 +210,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct iovec const *iov,
*chain = buf = tipc_buf_acquire(pktmax);
if (!buf)
return -ENOMEM;
+ chain_sz = 1;
pktpos = buf->data;
skb_copy_to_linear_data(buf, &pkthdr, INT_H_SIZE);
pktpos += INT_H_SIZE;
@@ -215,6 +244,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct iovec const *iov,
rc = -ENOMEM;
goto error;
}
+ chain_sz++;
prev->next = buf;
msg_set_type(&pkthdr, FRAGMENT);
msg_set_size(&pkthdr, pktsz);
@@ -224,7 +254,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct iovec const *iov,
pktrem = pktsz - INT_H_SIZE;
} while (1);
-
+ TIPC_SKB_CB(*chain)->chain_sz = chain_sz;
msg_set_type(buf_msg(buf), LAST_FRAGMENT);
return dsz;
error:
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index 462fa194a6a..0ea7b695ac4 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -442,6 +442,7 @@ static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m)
#define NAME_DISTRIBUTOR 11
#define MSG_FRAGMENTER 12
#define LINK_CONFIG 13
+#define SOCK_WAKEUP 14 /* pseudo user */
/*
* Connection management protocol message types
@@ -732,6 +733,10 @@ int tipc_msg_eval(struct sk_buff *buf, u32 *dnode);
void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, u32 hsize,
u32 destnode);
+struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz,
+ uint data_sz, u32 dnode, u32 onode,
+ u32 dport, u32 oport, int errcode);
+
int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf);
bool tipc_msg_bundle(struct sk_buff *bbuf, struct sk_buff *buf, u32 mtu);
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index dcc15bcd569..780ef710a84 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -1,7 +1,7 @@
/*
* net/tipc/name_distr.c: TIPC name distribution code
*
- * Copyright (c) 2000-2006, Ericsson AB
+ * Copyright (c) 2000-2006, 2014, Ericsson AB
* Copyright (c) 2005, 2010-2011, Wind River Systems
* All rights reserved.
*
@@ -71,6 +71,21 @@ static struct publ_list *publ_lists[] = {
};
+int sysctl_tipc_named_timeout __read_mostly = 2000;
+
+/**
+ * struct tipc_dist_queue - queue holding deferred name table updates
+ */
+static struct list_head tipc_dist_queue = LIST_HEAD_INIT(tipc_dist_queue);
+
+struct distr_queue_item {
+ struct distr_item i;
+ u32 dtype;
+ u32 node;
+ unsigned long expires;
+ struct list_head next;
+};
+
/**
* publ_to_item - add publication info to a publication message
*/
@@ -263,54 +278,104 @@ static void named_purge_publ(struct publication *publ)
}
/**
+ * tipc_update_nametbl - try to process a nametable update and notify
+ * subscribers
+ *
+ * tipc_nametbl_lock must be held.
+ * Returns the publication item if successful, otherwise NULL.
+ */
+struct publication *tipc_update_nametbl(struct distr_item *i, u32 node,
+ u32 dtype)
+{
+ struct publication *publ = NULL;
+
+ if (dtype == PUBLICATION) {
+ publ = tipc_nametbl_insert_publ(ntohl(i->type), ntohl(i->lower),
+ ntohl(i->upper),
+ TIPC_CLUSTER_SCOPE, node,
+ ntohl(i->ref), ntohl(i->key));
+ if (publ) {
+ tipc_nodesub_subscribe(&publ->subscr, node, publ,
+ (net_ev_handler)
+ named_purge_publ);
+ }
+ } else if (dtype == WITHDRAWAL) {
+ publ = tipc_nametbl_remove_publ(ntohl(i->type), ntohl(i->lower),
+ node, ntohl(i->ref),
+ ntohl(i->key));
+ if (publ) {
+ tipc_nodesub_unsubscribe(&publ->subscr);
+ kfree(publ);
+ }
+ } else {
+ pr_warn("Unrecognized name table message received\n");
+ }
+ return publ;
+}
+
+/**
+ * tipc_named_add_backlog - add a failed name table update to the backlog
+ *
+ */
+static void tipc_named_add_backlog(struct distr_item *i, u32 type, u32 node)
+{
+ struct distr_queue_item *e;
+ unsigned long now = get_jiffies_64();
+
+ e = kzalloc(sizeof(*e), GFP_ATOMIC);
+ if (!e)
+ return;
+ e->dtype = type;
+ e->node = node;
+ e->expires = now + msecs_to_jiffies(sysctl_tipc_named_timeout);
+ memcpy(e, i, sizeof(*i));
+ list_add_tail(&e->next, &tipc_dist_queue);
+}
+
+/**
+ * tipc_named_process_backlog - try to process any pending name table updates
+ * from the network.
+ */
+void tipc_named_process_backlog(void)
+{
+ struct distr_queue_item *e, *tmp;
+ char addr[16];
+ unsigned long now = get_jiffies_64();
+
+ list_for_each_entry_safe(e, tmp, &tipc_dist_queue, next) {
+ if (time_after(e->expires, now)) {
+ if (!tipc_update_nametbl(&e->i, e->node, e->dtype))
+ continue;
+ } else {
+ tipc_addr_string_fill(addr, e->node);
+ pr_warn_ratelimited("Dropping name table update (%d) of {%u, %u, %u} from %s key=%u\n",
+ e->dtype, ntohl(e->i.type),
+ ntohl(e->i.lower),
+ ntohl(e->i.upper),
+ addr, ntohl(e->i.key));
+ }
+ list_del(&e->next);
+ kfree(e);
+ }
+}
+
+/**
* tipc_named_rcv - process name table update message sent by another node
*/
void tipc_named_rcv(struct sk_buff *buf)
{
- struct publication *publ;
struct tipc_msg *msg = buf_msg(buf);
struct distr_item *item = (struct distr_item *)msg_data(msg);
u32 count = msg_data_sz(msg) / ITEM_SIZE;
+ u32 node = msg_orignode(msg);
write_lock_bh(&tipc_nametbl_lock);
while (count--) {
- if (msg_type(msg) == PUBLICATION) {
- publ = tipc_nametbl_insert_publ(ntohl(item->type),
- ntohl(item->lower),
- ntohl(item->upper),
- TIPC_CLUSTER_SCOPE,
- msg_orignode(msg),
- ntohl(item->ref),
- ntohl(item->key));
- if (publ) {
- tipc_nodesub_subscribe(&publ->subscr,
- msg_orignode(msg),
- publ,
- (net_ev_handler)
- named_purge_publ);
- }
- } else if (msg_type(msg) == WITHDRAWAL) {
- publ = tipc_nametbl_remove_publ(ntohl(item->type),
- ntohl(item->lower),
- msg_orignode(msg),
- ntohl(item->ref),
- ntohl(item->key));
-
- if (publ) {
- tipc_nodesub_unsubscribe(&publ->subscr);
- kfree(publ);
- } else {
- pr_err("Unable to remove publication by node 0x%x\n"
- " (type=%u, lower=%u, ref=%u, key=%u)\n",
- msg_orignode(msg), ntohl(item->type),
- ntohl(item->lower), ntohl(item->ref),
- ntohl(item->key));
- }
- } else {
- pr_warn("Unrecognized name table message received\n");
- }
+ if (!tipc_update_nametbl(item, node, msg_type(msg)))
+ tipc_named_add_backlog(item, msg_type(msg), node);
item++;
}
+ tipc_named_process_backlog();
write_unlock_bh(&tipc_nametbl_lock);
kfree_skb(buf);
}
diff --git a/net/tipc/name_distr.h b/net/tipc/name_distr.h
index 8afe32b7fc9..b9e75feb343 100644
--- a/net/tipc/name_distr.h
+++ b/net/tipc/name_distr.h
@@ -73,5 +73,6 @@ void named_cluster_distribute(struct sk_buff *buf);
void tipc_named_node_up(u32 dnode);
void tipc_named_rcv(struct sk_buff *buf);
void tipc_named_reinit(void);
+void tipc_named_process_backlog(void);
#endif
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 9d7d37d9518..3a6a0a7c075 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -39,7 +39,6 @@
#include "name_table.h"
#include "name_distr.h"
#include "subscr.h"
-#include "port.h"
#define TIPC_NAMETBL_SIZE 1024 /* must be a power of 2 */
@@ -262,8 +261,6 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq,
/* Lower end overlaps existing entry => need an exact match */
if ((sseq->lower != lower) || (sseq->upper != upper)) {
- pr_warn("Cannot publish {%u,%u,%u}, overlap error\n",
- type, lower, upper);
return NULL;
}
@@ -285,8 +282,6 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq,
/* Fail if upper end overlaps into an existing entry */
if ((inspos < nseq->first_free) &&
(upper >= nseq->sseqs[inspos].lower)) {
- pr_warn("Cannot publish {%u,%u,%u}, overlap error\n",
- type, lower, upper);
return NULL;
}
@@ -678,6 +673,8 @@ struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper,
if (likely(publ)) {
table.local_publ_count++;
buf = tipc_named_publish(publ);
+ /* Any pending external events? */
+ tipc_named_process_backlog();
}
write_unlock_bh(&tipc_nametbl_lock);
@@ -699,6 +696,8 @@ int tipc_nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key)
if (likely(publ)) {
table.local_publ_count--;
buf = tipc_named_withdraw(publ);
+ /* Any pending external events? */
+ tipc_named_process_backlog();
write_unlock_bh(&tipc_nametbl_lock);
list_del_init(&publ->pport_list);
kfree(publ);
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 7fcc94998fe..93b9944a6a8 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -38,7 +38,6 @@
#include "net.h"
#include "name_distr.h"
#include "subscr.h"
-#include "port.h"
#include "socket.h"
#include "node.h"
#include "config.h"
@@ -111,7 +110,7 @@ int tipc_net_start(u32 addr)
tipc_own_addr = addr;
tipc_named_reinit();
- tipc_port_reinit();
+ tipc_sk_reinit();
res = tipc_bclink_init();
if (res)
return res;
diff --git a/net/tipc/node.c b/net/tipc/node.c
index f7069299943..17e6378c4df 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -38,6 +38,7 @@
#include "config.h"
#include "node.h"
#include "name_distr.h"
+#include "socket.h"
#define NODE_HTABLE_SIZE 512
@@ -50,6 +51,13 @@ static u32 tipc_num_nodes;
static u32 tipc_num_links;
static DEFINE_SPINLOCK(node_list_lock);
+struct tipc_sock_conn {
+ u32 port;
+ u32 peer_port;
+ u32 peer_node;
+ struct list_head list;
+};
+
/*
* A trivial power-of-two bitmask technique is used for speed, since this
* operation is done for every incoming TIPC packet. The number of hash table
@@ -100,6 +108,8 @@ struct tipc_node *tipc_node_create(u32 addr)
INIT_HLIST_NODE(&n_ptr->hash);
INIT_LIST_HEAD(&n_ptr->list);
INIT_LIST_HEAD(&n_ptr->nsub);
+ INIT_LIST_HEAD(&n_ptr->conn_sks);
+ __skb_queue_head_init(&n_ptr->waiting_sks);
hlist_add_head_rcu(&n_ptr->hash, &node_htable[tipc_hashfn(addr)]);
@@ -136,6 +146,71 @@ void tipc_node_stop(void)
spin_unlock_bh(&node_list_lock);
}
+int tipc_node_add_conn(u32 dnode, u32 port, u32 peer_port)
+{
+ struct tipc_node *node;
+ struct tipc_sock_conn *conn;
+
+ if (in_own_node(dnode))
+ return 0;
+
+ node = tipc_node_find(dnode);
+ if (!node) {
+ pr_warn("Connecting sock to node 0x%x failed\n", dnode);
+ return -EHOSTUNREACH;
+ }
+ conn = kmalloc(sizeof(*conn), GFP_ATOMIC);
+ if (!conn)
+ return -EHOSTUNREACH;
+ conn->peer_node = dnode;
+ conn->port = port;
+ conn->peer_port = peer_port;
+
+ tipc_node_lock(node);
+ list_add_tail(&conn->list, &node->conn_sks);
+ tipc_node_unlock(node);
+ return 0;
+}
+
+void tipc_node_remove_conn(u32 dnode, u32 port)
+{
+ struct tipc_node *node;
+ struct tipc_sock_conn *conn, *safe;
+
+ if (in_own_node(dnode))
+ return;
+
+ node = tipc_node_find(dnode);
+ if (!node)
+ return;
+
+ tipc_node_lock(node);
+ list_for_each_entry_safe(conn, safe, &node->conn_sks, list) {
+ if (port != conn->port)
+ continue;
+ list_del(&conn->list);
+ kfree(conn);
+ }
+ tipc_node_unlock(node);
+}
+
+void tipc_node_abort_sock_conns(struct list_head *conns)
+{
+ struct tipc_sock_conn *conn, *safe;
+ struct sk_buff *buf;
+
+ list_for_each_entry_safe(conn, safe, conns, list) {
+ buf = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG,
+ SHORT_H_SIZE, 0, tipc_own_addr,
+ conn->peer_node, conn->port,
+ conn->peer_port, TIPC_ERR_NO_NODE);
+ if (likely(buf))
+ tipc_sk_rcv(buf);
+ list_del(&conn->list);
+ kfree(conn);
+ }
+}
+
/**
* tipc_node_link_up - handle addition of link
*
@@ -474,6 +549,8 @@ int tipc_node_get_linkname(u32 bearer_id, u32 addr, char *linkname, size_t len)
void tipc_node_unlock(struct tipc_node *node)
{
LIST_HEAD(nsub_list);
+ LIST_HEAD(conn_sks);
+ struct sk_buff_head waiting_sks;
u32 addr = 0;
if (likely(!node->action_flags)) {
@@ -481,8 +558,14 @@ void tipc_node_unlock(struct tipc_node *node)
return;
}
+ __skb_queue_head_init(&waiting_sks);
+ if (node->action_flags & TIPC_WAKEUP_USERS) {
+ skb_queue_splice_init(&node->waiting_sks, &waiting_sks);
+ node->action_flags &= ~TIPC_WAKEUP_USERS;
+ }
if (node->action_flags & TIPC_NOTIFY_NODE_DOWN) {
list_replace_init(&node->nsub, &nsub_list);
+ list_replace_init(&node->conn_sks, &conn_sks);
node->action_flags &= ~TIPC_NOTIFY_NODE_DOWN;
}
if (node->action_flags & TIPC_NOTIFY_NODE_UP) {
@@ -491,8 +574,15 @@ void tipc_node_unlock(struct tipc_node *node)
}
spin_unlock_bh(&node->lock);
+ while (!skb_queue_empty(&waiting_sks))
+ tipc_sk_rcv(__skb_dequeue(&waiting_sks));
+
+ if (!list_empty(&conn_sks))
+ tipc_node_abort_sock_conns(&conn_sks);
+
if (!list_empty(&nsub_list))
tipc_nodesub_notify(&nsub_list);
+
if (addr)
tipc_named_node_up(addr);
}
diff --git a/net/tipc/node.h b/net/tipc/node.h
index b61716a8218..522d6f3157b 100644
--- a/net/tipc/node.h
+++ b/net/tipc/node.h
@@ -58,7 +58,8 @@ enum {
TIPC_WAIT_PEER_LINKS_DOWN = (1 << 1),
TIPC_WAIT_OWN_LINKS_DOWN = (1 << 2),
TIPC_NOTIFY_NODE_DOWN = (1 << 3),
- TIPC_NOTIFY_NODE_UP = (1 << 4)
+ TIPC_NOTIFY_NODE_UP = (1 << 4),
+ TIPC_WAKEUP_USERS = (1 << 5)
};
/**
@@ -115,6 +116,8 @@ struct tipc_node {
int working_links;
u32 signature;
struct list_head nsub;
+ struct sk_buff_head waiting_sks;
+ struct list_head conn_sks;
struct rcu_head rcu;
};
@@ -133,6 +136,8 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space)
struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space);
int tipc_node_get_linkname(u32 bearer_id, u32 node, char *linkname, size_t len);
void tipc_node_unlock(struct tipc_node *node);
+int tipc_node_add_conn(u32 dnode, u32 port, u32 peer_port);
+void tipc_node_remove_conn(u32 dnode, u32 port);
static inline void tipc_node_lock(struct tipc_node *node)
{
diff --git a/net/tipc/port.c b/net/tipc/port.c
deleted file mode 100644
index 7e096a5e770..00000000000
--- a/net/tipc/port.c
+++ /dev/null
@@ -1,514 +0,0 @@
-/*
- * net/tipc/port.c: TIPC port code
- *
- * Copyright (c) 1992-2007, 2014, Ericsson AB
- * Copyright (c) 2004-2008, 2010-2013, Wind River Systems
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- * contributors may be used to endorse or promote products derived from
- * this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include "core.h"
-#include "config.h"
-#include "port.h"
-#include "name_table.h"
-#include "socket.h"
-
-/* Connection management: */
-#define PROBING_INTERVAL 3600000 /* [ms] => 1 h */
-
-#define MAX_REJECT_SIZE 1024
-
-DEFINE_SPINLOCK(tipc_port_list_lock);
-
-static LIST_HEAD(ports);
-static void port_handle_node_down(unsigned long ref);
-static struct sk_buff *port_build_self_abort_msg(struct tipc_port *, u32 err);
-static struct sk_buff *port_build_peer_abort_msg(struct tipc_port *, u32 err);
-static void port_timeout(unsigned long ref);
-
-/**
- * tipc_port_peer_msg - verify message was sent by connected port's peer
- *
- * Handles cases where the node's network address has changed from
- * the default of <0.0.0> to its configured setting.
- */
-int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg)
-{
- u32 peernode;
- u32 orignode;
-
- if (msg_origport(msg) != tipc_port_peerport(p_ptr))
- return 0;
-
- orignode = msg_orignode(msg);
- peernode = tipc_port_peernode(p_ptr);
- return (orignode == peernode) ||
- (!orignode && (peernode == tipc_own_addr)) ||
- (!peernode && (orignode == tipc_own_addr));
-}
-
-/* tipc_port_init - intiate TIPC port and lock it
- *
- * Returns obtained reference if initialization is successful, zero otherwise
- */
-u32 tipc_port_init(struct tipc_port *p_ptr,
- const unsigned int importance)
-{
- struct tipc_msg *msg;
- u32 ref;
-
- ref = tipc_ref_acquire(p_ptr, &p_ptr->lock);
- if (!ref) {
- pr_warn("Port registration failed, ref. table exhausted\n");
- return 0;
- }
-
- p_ptr->max_pkt = MAX_PKT_DEFAULT;
- p_ptr->ref = ref;
- INIT_LIST_HEAD(&p_ptr->wait_list);
- INIT_LIST_HEAD(&p_ptr->subscription.nodesub_list);
- k_init_timer(&p_ptr->timer, (Handler)port_timeout, ref);
- INIT_LIST_HEAD(&p_ptr->publications);
- INIT_LIST_HEAD(&p_ptr->port_list);
-
- /*
- * Must hold port list lock while initializing message header template
- * to ensure a change to node's own network address doesn't result
- * in template containing out-dated network address information
- */
- spin_lock_bh(&tipc_port_list_lock);
- msg = &p_ptr->phdr;
- tipc_msg_init(msg, importance, TIPC_NAMED_MSG, NAMED_H_SIZE, 0);
- msg_set_origport(msg, ref);
- list_add_tail(&p_ptr->port_list, &ports);
- spin_unlock_bh(&tipc_port_list_lock);
- return ref;
-}
-
-void tipc_port_destroy(struct tipc_port *p_ptr)
-{
- struct sk_buff *buf = NULL;
- struct tipc_msg *msg = NULL;
- u32 peer;
-
- tipc_withdraw(p_ptr, 0, NULL);
-
- spin_lock_bh(p_ptr->lock);
- tipc_ref_discard(p_ptr->ref);
- spin_unlock_bh(p_ptr->lock);
-
- k_cancel_timer(&p_ptr->timer);
- if (p_ptr->connected) {
- buf = port_build_peer_abort_msg(p_ptr, TIPC_ERR_NO_PORT);
- tipc_nodesub_unsubscribe(&p_ptr->subscription);
- msg = buf_msg(buf);
- peer = msg_destnode(msg);
- tipc_link_xmit(buf, peer, msg_link_selector(msg));
- }
- spin_lock_bh(&tipc_port_list_lock);
- list_del(&p_ptr->port_list);
- list_del(&p_ptr->wait_list);
- spin_unlock_bh(&tipc_port_list_lock);
- k_term_timer(&p_ptr->timer);
-}
-
-/*
- * port_build_proto_msg(): create connection protocol message for port
- *
- * On entry the port must be locked and connected.
- */
-static struct sk_buff *port_build_proto_msg(struct tipc_port *p_ptr,
- u32 type, u32 ack)
-{
- struct sk_buff *buf;
- struct tipc_msg *msg;
-
- buf = tipc_buf_acquire(INT_H_SIZE);
- if (buf) {
- msg = buf_msg(buf);
- tipc_msg_init(msg, CONN_MANAGER, type, INT_H_SIZE,
- tipc_port_peernode(p_ptr));
- msg_set_destport(msg, tipc_port_peerport(p_ptr));
- msg_set_origport(msg, p_ptr->ref);
- msg_set_msgcnt(msg, ack);
- buf->next = NULL;
- }
- return buf;
-}
-
-static void port_timeout(unsigned long ref)
-{
- struct tipc_port *p_ptr = tipc_port_lock(ref);
- struct sk_buff *buf = NULL;
- struct tipc_msg *msg = NULL;
-
- if (!p_ptr)
- return;
-
- if (!p_ptr->connected) {
- tipc_port_unlock(p_ptr);
- return;
- }
-
- /* Last probe answered ? */
- if (p_ptr->probing_state == TIPC_CONN_PROBING) {
- buf = port_build_self_abort_msg(p_ptr, TIPC_ERR_NO_PORT);
- } else {
- buf = port_build_proto_msg(p_ptr, CONN_PROBE, 0);
- p_ptr->probing_state = TIPC_CONN_PROBING;
- k_start_timer(&p_ptr->timer, p_ptr->probing_interval);
- }
- tipc_port_unlock(p_ptr);
- msg = buf_msg(buf);
- tipc_link_xmit(buf, msg_destnode(msg), msg_link_selector(msg));
-}
-
-
-static void port_handle_node_down(unsigned long ref)
-{
- struct tipc_port *p_ptr = tipc_port_lock(ref);
- struct sk_buff *buf = NULL;
- struct tipc_msg *msg = NULL;
-
- if (!p_ptr)
- return;
- buf = port_build_self_abort_msg(p_ptr, TIPC_ERR_NO_NODE);
- tipc_port_unlock(p_ptr);
- msg = buf_msg(buf);
- tipc_link_xmit(buf, msg_destnode(msg), msg_link_selector(msg));
-}
-
-
-static struct sk_buff *port_build_self_abort_msg(struct tipc_port *p_ptr, u32 err)
-{
- struct sk_buff *buf = port_build_peer_abort_msg(p_ptr, err);
-
- if (buf) {
- struct tipc_msg *msg = buf_msg(buf);
- msg_swap_words(msg, 4, 5);
- msg_swap_words(msg, 6, 7);
- buf->next = NULL;
- }
- return buf;
-}
-
-
-static struct sk_buff *port_build_peer_abort_msg(struct tipc_port *p_ptr, u32 err)
-{
- struct sk_buff *buf;
- struct tipc_msg *msg;
- u32 imp;
-
- if (!p_ptr->connected)
- return NULL;
-
- buf = tipc_buf_acquire(BASIC_H_SIZE);
- if (buf) {
- msg = buf_msg(buf);
- memcpy(msg, &p_ptr->phdr, BASIC_H_SIZE);
- msg_set_hdr_sz(msg, BASIC_H_SIZE);
- msg_set_size(msg, BASIC_H_SIZE);
- imp = msg_importance(msg);
- if (imp < TIPC_CRITICAL_IMPORTANCE)
- msg_set_importance(msg, ++imp);
- msg_set_errcode(msg, err);
- buf->next = NULL;
- }
- return buf;
-}
-
-static int port_print(struct tipc_port *p_ptr, char *buf, int len, int full_id)
-{
- struct publication *publ;
- int ret;
-
- if (full_id)
- ret = tipc_snprintf(buf, len, "<%u.%u.%u:%u>:",
- tipc_zone(tipc_own_addr),
- tipc_cluster(tipc_own_addr),
- tipc_node(tipc_own_addr), p_ptr->ref);
- else
- ret = tipc_snprintf(buf, len, "%-10u:", p_ptr->ref);
-
- if (p_ptr->connected) {
- u32 dport = tipc_port_peerport(p_ptr);
- u32 destnode = tipc_port_peernode(p_ptr);
-
- ret += tipc_snprintf(buf + ret, len - ret,
- " connected to <%u.%u.%u:%u>",
- tipc_zone(destnode),
- tipc_cluster(destnode),
- tipc_node(destnode), dport);
- if (p_ptr->conn_type != 0)
- ret += tipc_snprintf(buf + ret, len - ret,
- " via {%u,%u}", p_ptr->conn_type,
- p_ptr->conn_instance);
- } else if (p_ptr->published) {
- ret += tipc_snprintf(buf + ret, len - ret, " bound to");
- list_for_each_entry(publ, &p_ptr->publications, pport_list) {
- if (publ->lower == publ->upper)
- ret += tipc_snprintf(buf + ret, len - ret,
- " {%u,%u}", publ->type,
- publ->lower);
- else
- ret += tipc_snprintf(buf + ret, len - ret,
- " {%u,%u,%u}", publ->type,
- publ->lower, publ->upper);
- }
- }
- ret += tipc_snprintf(buf + ret, len - ret, "\n");
- return ret;
-}
-
-struct sk_buff *tipc_port_get_ports(void)
-{
- struct sk_buff *buf;
- struct tlv_desc *rep_tlv;
- char *pb;
- int pb_len;
- struct tipc_port *p_ptr;
- int str_len = 0;
-
- buf = tipc_cfg_reply_alloc(TLV_SPACE(ULTRA_STRING_MAX_LEN));
- if (!buf)
- return NULL;
- rep_tlv = (struct tlv_desc *)buf->data;
- pb = TLV_DATA(rep_tlv);
- pb_len = ULTRA_STRING_MAX_LEN;
-
- spin_lock_bh(&tipc_port_list_lock);
- list_for_each_entry(p_ptr, &ports, port_list) {
- spin_lock_bh(p_ptr->lock);
- str_len += port_print(p_ptr, pb, pb_len, 0);
- spin_unlock_bh(p_ptr->lock);
- }
- spin_unlock_bh(&tipc_port_list_lock);
- str_len += 1; /* for "\0" */
- skb_put(buf, TLV_SPACE(str_len));
- TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len);
-
- return buf;
-}
-
-void tipc_port_reinit(void)
-{
- struct tipc_port *p_ptr;
- struct tipc_msg *msg;
-
- spin_lock_bh(&tipc_port_list_lock);
- list_for_each_entry(p_ptr, &ports, port_list) {
- msg = &p_ptr->phdr;
- msg_set_prevnode(msg, tipc_own_addr);
- msg_set_orignode(msg, tipc_own_addr);
- }
- spin_unlock_bh(&tipc_port_list_lock);
-}
-
-void tipc_acknowledge(u32 ref, u32 ack)
-{
- struct tipc_port *p_ptr;
- struct sk_buff *buf = NULL;
- struct tipc_msg *msg;
-
- p_ptr = tipc_port_lock(ref);
- if (!p_ptr)
- return;
- if (p_ptr->connected)
- buf = port_build_proto_msg(p_ptr, CONN_ACK, ack);
-
- tipc_port_unlock(p_ptr);
- if (!buf)
- return;
- msg = buf_msg(buf);
- tipc_link_xmit(buf, msg_destnode(msg), msg_link_selector(msg));
-}
-
-int tipc_publish(struct tipc_port *p_ptr, unsigned int scope,
- struct tipc_name_seq const *seq)
-{
- struct publication *publ;
- u32 key;
-
- if (p_ptr->connected)
- return -EINVAL;
- key = p_ptr->ref + p_ptr->pub_count + 1;
- if (key == p_ptr->ref)
- return -EADDRINUSE;
-
- publ = tipc_nametbl_publish(seq->type, seq->lower, seq->upper,
- scope, p_ptr->ref, key);
- if (publ) {
- list_add(&publ->pport_list, &p_ptr->publications);
- p_ptr->pub_count++;
- p_ptr->published = 1;
- return 0;
- }
- return -EINVAL;
-}
-
-int tipc_withdraw(struct tipc_port *p_ptr, unsigned int scope,
- struct tipc_name_seq const *seq)
-{
- struct publication *publ;
- struct publication *tpubl;
- int res = -EINVAL;
-
- if (!seq) {
- list_for_each_entry_safe(publ, tpubl,
- &p_ptr->publications, pport_list) {
- tipc_nametbl_withdraw(publ->type, publ->lower,
- publ->ref, publ->key);
- }
- res = 0;
- } else {
- list_for_each_entry_safe(publ, tpubl,
- &p_ptr->publications, pport_list) {
- if (publ->scope != scope)
- continue;
- if (publ->type != seq->type)
- continue;
- if (publ->lower != seq->lower)
- continue;
- if (publ->upper != seq->upper)
- break;
- tipc_nametbl_withdraw(publ->type, publ->lower,
- publ->ref, publ->key);
- res = 0;
- break;
- }
- }
- if (list_empty(&p_ptr->publications))
- p_ptr->published = 0;
- return res;
-}
-
-int tipc_port_connect(u32 ref, struct tipc_portid const *peer)
-{
- struct tipc_port *p_ptr;
- int res;
-
- p_ptr = tipc_port_lock(ref);
- if (!p_ptr)
- return -EINVAL;
- res = __tipc_port_connect(ref, p_ptr, peer);
- tipc_port_unlock(p_ptr);
- return res;
-}
-
-/*
- * __tipc_port_connect - connect to a remote peer
- *
- * Port must be locked.
- */
-int __tipc_port_connect(u32 ref, struct tipc_port *p_ptr,
- struct tipc_portid const *peer)
-{
- struct tipc_msg *msg;
- int res = -EINVAL;
-
- if (p_ptr->published || p_ptr->connected)
- goto exit;
- if (!peer->ref)
- goto exit;
-
- msg = &p_ptr->phdr;
- msg_set_destnode(msg, peer->node);
- msg_set_destport(msg, peer->ref);
- msg_set_type(msg, TIPC_CONN_MSG);
- msg_set_lookup_scope(msg, 0);
- msg_set_hdr_sz(msg, SHORT_H_SIZE);
-
- p_ptr->probing_interval = PROBING_INTERVAL;
- p_ptr->probing_state = TIPC_CONN_OK;
- p_ptr->connected = 1;
- k_start_timer(&p_ptr->timer, p_ptr->probing_interval);
-
- tipc_nodesub_subscribe(&p_ptr->subscription, peer->node,
- (void *)(unsigned long)ref,
- (net_ev_handler)port_handle_node_down);
- res = 0;
-exit:
- p_ptr->max_pkt = tipc_node_get_mtu(peer->node, ref);
- return res;
-}
-
-/*
- * __tipc_disconnect - disconnect port from peer
- *
- * Port must be locked.
- */
-int __tipc_port_disconnect(struct tipc_port *tp_ptr)
-{
- if (tp_ptr->connected) {
- tp_ptr->connected = 0;
- /* let timer expire on it's own to avoid deadlock! */
- tipc_nodesub_unsubscribe(&tp_ptr->subscription);
- return 0;
- }
-
- return -ENOTCONN;
-}
-
-/*
- * tipc_port_disconnect(): Disconnect port form peer.
- * This is a node local operation.
- */
-int tipc_port_disconnect(u32 ref)
-{
- struct tipc_port *p_ptr;
- int res;
-
- p_ptr = tipc_port_lock(ref);
- if (!p_ptr)
- return -EINVAL;
- res = __tipc_port_disconnect(p_ptr);
- tipc_port_unlock(p_ptr);
- return res;
-}
-
-/*
- * tipc_port_shutdown(): Send a SHUTDOWN msg to peer and disconnect
- */
-int tipc_port_shutdown(u32 ref)
-{
- struct tipc_msg *msg;
- struct tipc_port *p_ptr;
- struct sk_buff *buf = NULL;
-
- p_ptr = tipc_port_lock(ref);
- if (!p_ptr)
- return -EINVAL;
-
- buf = port_build_peer_abort_msg(p_ptr, TIPC_CONN_SHUTDOWN);
- tipc_port_unlock(p_ptr);
- msg = buf_msg(buf);
- tipc_link_xmit(buf, msg_destnode(msg), msg_link_selector(msg));
- return tipc_port_disconnect(ref);
-}
diff --git a/net/tipc/port.h b/net/tipc/port.h
deleted file mode 100644
index 3087da39ee4..00000000000
--- a/net/tipc/port.h
+++ /dev/null
@@ -1,190 +0,0 @@
-/*
- * net/tipc/port.h: Include file for TIPC port code
- *
- * Copyright (c) 1994-2007, 2014, Ericsson AB
- * Copyright (c) 2004-2007, 2010-2013, Wind River Systems
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- * contributors may be used to endorse or promote products derived from
- * this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
-
-#ifndef _TIPC_PORT_H
-#define _TIPC_PORT_H
-
-#include "ref.h"
-#include "net.h"
-#include "msg.h"
-#include "node_subscr.h"
-
-#define TIPC_CONNACK_INTV 256
-#define TIPC_FLOWCTRL_WIN (TIPC_CONNACK_INTV * 2)
-#define TIPC_CONN_OVERLOAD_LIMIT ((TIPC_FLOWCTRL_WIN * 2 + 1) * \
- SKB_TRUESIZE(TIPC_MAX_USER_MSG_SIZE))
-
-/**
- * struct tipc_port - TIPC port structure
- * @lock: pointer to spinlock for controlling access to port
- * @connected: non-zero if port is currently connected to a peer port
- * @conn_type: TIPC type used when connection was established
- * @conn_instance: TIPC instance used when connection was established
- * @published: non-zero if port has one or more associated names
- * @max_pkt: maximum packet size "hint" used when building messages sent by port
- * @ref: unique reference to port in TIPC object registry
- * @phdr: preformatted message header used when sending messages
- * @port_list: adjacent ports in TIPC's global list of ports
- * @wait_list: adjacent ports in list of ports waiting on link congestion
- * @waiting_pkts:
- * @publications: list of publications for port
- * @pub_count: total # of publications port has made during its lifetime
- * @probing_state:
- * @probing_interval:
- * @timer_ref:
- * @subscription: "node down" subscription used to terminate failed connections
- */
-struct tipc_port {
- spinlock_t *lock;
- int connected;
- u32 conn_type;
- u32 conn_instance;
- int published;
- u32 max_pkt;
- u32 ref;
- struct tipc_msg phdr;
- struct list_head port_list;
- struct list_head wait_list;
- u32 waiting_pkts;
- struct list_head publications;
- u32 pub_count;
- u32 probing_state;
- u32 probing_interval;
- struct timer_list timer;
- struct tipc_node_subscr subscription;
-};
-
-extern spinlock_t tipc_port_list_lock;
-struct tipc_port_list;
-
-/*
- * TIPC port manipulation routines
- */
-u32 tipc_port_init(struct tipc_port *p_ptr,
- const unsigned int importance);
-
-void tipc_acknowledge(u32 port_ref, u32 ack);
-
-void tipc_port_destroy(struct tipc_port *p_ptr);
-
-int tipc_publish(struct tipc_port *p_ptr, unsigned int scope,
- struct tipc_name_seq const *name_seq);
-
-int tipc_withdraw(struct tipc_port *p_ptr, unsigned int scope,
- struct tipc_name_seq const *name_seq);
-
-int tipc_port_connect(u32 portref, struct tipc_portid const *port);
-
-int tipc_port_disconnect(u32 portref);
-
-int tipc_port_shutdown(u32 ref);
-
-/*
- * The following routines require that the port be locked on entry
- */
-int __tipc_port_disconnect(struct tipc_port *tp_ptr);
-int __tipc_port_connect(u32 ref, struct tipc_port *p_ptr,
- struct tipc_portid const *peer);
-int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg);
-
-struct sk_buff *tipc_port_get_ports(void);
-void tipc_port_reinit(void);
-
-/**
- * tipc_port_lock - lock port instance referred to and return its pointer
- */
-static inline struct tipc_port *tipc_port_lock(u32 ref)
-{
- return (struct tipc_port *)tipc_ref_lock(ref);
-}
-
-/**
- * tipc_port_unlock - unlock a port instance
- *
- * Can use pointer instead of tipc_ref_unlock() since port is already locked.
- */
-static inline void tipc_port_unlock(struct tipc_port *p_ptr)
-{
- spin_unlock_bh(p_ptr->lock);
-}
-
-static inline u32 tipc_port_peernode(struct tipc_port *p_ptr)
-{
- return msg_destnode(&p_ptr->phdr);
-}
-
-static inline u32 tipc_port_peerport(struct tipc_port *p_ptr)
-{
- return msg_destport(&p_ptr->phdr);
-}
-
-static inline bool tipc_port_unreliable(struct tipc_port *port)
-{
- return msg_src_droppable(&port->phdr) != 0;
-}
-
-static inline void tipc_port_set_unreliable(struct tipc_port *port,
- bool unreliable)
-{
- msg_set_src_droppable(&port->phdr, unreliable ? 1 : 0);
-}
-
-static inline bool tipc_port_unreturnable(struct tipc_port *port)
-{
- return msg_dest_droppable(&port->phdr) != 0;
-}
-
-static inline void tipc_port_set_unreturnable(struct tipc_port *port,
- bool unreturnable)
-{
- msg_set_dest_droppable(&port->phdr, unreturnable ? 1 : 0);
-}
-
-
-static inline int tipc_port_importance(struct tipc_port *port)
-{
- return msg_importance(&port->phdr);
-}
-
-static inline int tipc_port_set_importance(struct tipc_port *port, int imp)
-{
- if (imp > TIPC_CRITICAL_IMPORTANCE)
- return -EINVAL;
- msg_set_importance(&port->phdr, (u32)imp);
- return 0;
-}
-
-#endif
diff --git a/net/tipc/ref.c b/net/tipc/ref.c
deleted file mode 100644
index 3d4ecd754ee..00000000000
--- a/net/tipc/ref.c
+++ /dev/null
@@ -1,266 +0,0 @@
-/*
- * net/tipc/ref.c: TIPC object registry code
- *
- * Copyright (c) 1991-2006, Ericsson AB
- * Copyright (c) 2004-2007, Wind River Systems
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- * contributors may be used to endorse or promote products derived from
- * this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include "core.h"
-#include "ref.h"
-
-/**
- * struct reference - TIPC object reference entry
- * @object: pointer to object associated with reference entry
- * @lock: spinlock controlling access to object
- * @ref: reference value for object (combines instance & array index info)
- */
-struct reference {
- void *object;
- spinlock_t lock;
- u32 ref;
-};
-
-/**
- * struct tipc_ref_table - table of TIPC object reference entries
- * @entries: pointer to array of reference entries
- * @capacity: array index of first unusable entry
- * @init_point: array index of first uninitialized entry
- * @first_free: array index of first unused object reference entry
- * @last_free: array index of last unused object reference entry
- * @index_mask: bitmask for array index portion of reference values
- * @start_mask: initial value for instance value portion of reference values
- */
-struct ref_table {
- struct reference *entries;
- u32 capacity;
- u32 init_point;
- u32 first_free;
- u32 last_free;
- u32 index_mask;
- u32 start_mask;
-};
-
-/*
- * Object reference table consists of 2**N entries.
- *
- * State Object ptr Reference
- * ----- ---------- ---------
- * In use non-NULL XXXX|own index
- * (XXXX changes each time entry is acquired)
- * Free NULL YYYY|next free index
- * (YYYY is one more than last used XXXX)
- * Uninitialized NULL 0
- *
- * Entry 0 is not used; this allows index 0 to denote the end of the free list.
- *
- * Note that a reference value of 0 does not necessarily indicate that an
- * entry is uninitialized, since the last entry in the free list could also
- * have a reference value of 0 (although this is unlikely).
- */
-
-static struct ref_table tipc_ref_table;
-
-static DEFINE_SPINLOCK(ref_table_lock);
-
-/**
- * tipc_ref_table_init - create reference table for objects
- */
-int tipc_ref_table_init(u32 requested_size, u32 start)
-{
- struct reference *table;
- u32 actual_size;
-
- /* account for unused entry, then round up size to a power of 2 */
-
- requested_size++;
- for (actual_size = 16; actual_size < requested_size; actual_size <<= 1)
- /* do nothing */ ;
-
- /* allocate table & mark all entries as uninitialized */
- table = vzalloc(actual_size * sizeof(struct reference));
- if (table == NULL)
- return -ENOMEM;
-
- tipc_ref_table.entries = table;
- tipc_ref_table.capacity = requested_size;
- tipc_ref_table.init_point = 1;
- tipc_ref_table.first_free = 0;
- tipc_ref_table.last_free = 0;
- tipc_ref_table.index_mask = actual_size - 1;
- tipc_ref_table.start_mask = start & ~tipc_ref_table.index_mask;
-
- return 0;
-}
-
-/**
- * tipc_ref_table_stop - destroy reference table for objects
- */
-void tipc_ref_table_stop(void)
-{
- vfree(tipc_ref_table.entries);
- tipc_ref_table.entries = NULL;
-}
-
-/**
- * tipc_ref_acquire - create reference to an object
- *
- * Register an object pointer in reference table and lock the object.
- * Returns a unique reference value that is used from then on to retrieve the
- * object pointer, or to determine that the object has been deregistered.
- *
- * Note: The object is returned in the locked state so that the caller can
- * register a partially initialized object, without running the risk that
- * the object will be accessed before initialization is complete.
- */
-u32 tipc_ref_acquire(void *object, spinlock_t **lock)
-{
- u32 index;
- u32 index_mask;
- u32 next_plus_upper;
- u32 ref;
- struct reference *entry = NULL;
-
- if (!object) {
- pr_err("Attempt to acquire ref. to non-existent obj\n");
- return 0;
- }
- if (!tipc_ref_table.entries) {
- pr_err("Ref. table not found in acquisition attempt\n");
- return 0;
- }
-
- /* take a free entry, if available; otherwise initialize a new entry */
- spin_lock_bh(&ref_table_lock);
- if (tipc_ref_table.first_free) {
- index = tipc_ref_table.first_free;
- entry = &(tipc_ref_table.entries[index]);
- index_mask = tipc_ref_table.index_mask;
- next_plus_upper = entry->ref;
- tipc_ref_table.first_free = next_plus_upper & index_mask;
- ref = (next_plus_upper & ~index_mask) + index;
- } else if (tipc_ref_table.init_point < tipc_ref_table.capacity) {
- index = tipc_ref_table.init_point++;
- entry = &(tipc_ref_table.entries[index]);
- spin_lock_init(&entry->lock);
- ref = tipc_ref_table.start_mask + index;
- } else {
- ref = 0;
- }
- spin_unlock_bh(&ref_table_lock);
-
- /*
- * Grab the lock so no one else can modify this entry
- * While we assign its ref value & object pointer
- */
- if (entry) {
- spin_lock_bh(&entry->lock);
- entry->ref = ref;
- entry->object = object;
- *lock = &entry->lock;
- /*
- * keep it locked, the caller is responsible
- * for unlocking this when they're done with it
- */
- }
-
- return ref;
-}
-
-/**
- * tipc_ref_discard - invalidate references to an object
- *
- * Disallow future references to an object and free up the entry for re-use.
- * Note: The entry's spin_lock may still be busy after discard
- */
-void tipc_ref_discard(u32 ref)
-{
- struct reference *entry;
- u32 index;
- u32 index_mask;
-
- if (!tipc_ref_table.entries) {
- pr_err("Ref. table not found during discard attempt\n");
- return;
- }
-
- index_mask = tipc_ref_table.index_mask;
- index = ref & index_mask;
- entry = &(tipc_ref_table.entries[index]);
-
- spin_lock_bh(&ref_table_lock);
-
- if (!entry->object) {
- pr_err("Attempt to discard ref. to non-existent obj\n");
- goto exit;
- }
- if (entry->ref != ref) {
- pr_err("Attempt to discard non-existent reference\n");
- goto exit;
- }
-
- /*
- * mark entry as unused; increment instance part of entry's reference
- * to invalidate any subsequent references
- */
- entry->object = NULL;
- entry->ref = (ref & ~index_mask) + (index_mask + 1);
-
- /* append entry to free entry list */
- if (tipc_ref_table.first_free == 0)
- tipc_ref_table.first_free = index;
- else
- tipc_ref_table.entries[tipc_ref_table.last_free].ref |= index;
- tipc_ref_table.last_free = index;
-
-exit:
- spin_unlock_bh(&ref_table_lock);
-}
-
-/**
- * tipc_ref_lock - lock referenced object and return pointer to it
- */
-void *tipc_ref_lock(u32 ref)
-{
- if (likely(tipc_ref_table.entries)) {
- struct reference *entry;
-
- entry = &tipc_ref_table.entries[ref &
- tipc_ref_table.index_mask];
- if (likely(entry->ref != 0)) {
- spin_lock_bh(&entry->lock);
- if (likely((entry->ref == ref) && (entry->object)))
- return entry->object;
- spin_unlock_bh(&entry->lock);
- }
- }
- return NULL;
-}
diff --git a/net/tipc/ref.h b/net/tipc/ref.h
deleted file mode 100644
index d01aa1df63b..00000000000
--- a/net/tipc/ref.h
+++ /dev/null
@@ -1,48 +0,0 @@
-/*
- * net/tipc/ref.h: Include file for TIPC object registry code
- *
- * Copyright (c) 1991-2006, Ericsson AB
- * Copyright (c) 2005-2006, Wind River Systems
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- * contributors may be used to endorse or promote products derived from
- * this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
-
-#ifndef _TIPC_REF_H
-#define _TIPC_REF_H
-
-int tipc_ref_table_init(u32 requested_size, u32 start);
-void tipc_ref_table_stop(void);
-
-u32 tipc_ref_acquire(void *object, spinlock_t **lock);
-void tipc_ref_discard(u32 ref);
-
-void *tipc_ref_lock(u32 ref);
-
-#endif
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index ff8c8118d56..75275c5cf92 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -35,17 +35,67 @@
*/
#include "core.h"
-#include "port.h"
#include "name_table.h"
#include "node.h"
#include "link.h"
#include <linux/export.h>
+#include "config.h"
+#include "socket.h"
#define SS_LISTENING -1 /* socket is listening */
#define SS_READY -2 /* socket is connectionless */
-#define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */
-#define TIPC_FWD_MSG 1
+#define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */
+#define CONN_PROBING_INTERVAL 3600000 /* [ms] => 1 h */
+#define TIPC_FWD_MSG 1
+#define TIPC_CONN_OK 0
+#define TIPC_CONN_PROBING 1
+
+/**
+ * struct tipc_sock - TIPC socket structure
+ * @sk: socket - interacts with 'port' and with user via the socket API
+ * @connected: non-zero if port is currently connected to a peer port
+ * @conn_type: TIPC type used when connection was established
+ * @conn_instance: TIPC instance used when connection was established
+ * @published: non-zero if port has one or more associated names
+ * @max_pkt: maximum packet size "hint" used when building messages sent by port
+ * @ref: unique reference to port in TIPC object registry
+ * @phdr: preformatted message header used when sending messages
+ * @port_list: adjacent ports in TIPC's global list of ports
+ * @publications: list of publications for port
+ * @pub_count: total # of publications port has made during its lifetime
+ * @probing_state:
+ * @probing_interval:
+ * @timer:
+ * @port: port - interacts with 'sk' and with the rest of the TIPC stack
+ * @peer_name: the peer of the connection, if any
+ * @conn_timeout: the time we can wait for an unresponded setup request
+ * @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue
+ * @link_cong: non-zero if owner must sleep because of link congestion
+ * @sent_unacked: # messages sent by socket, and not yet acked by peer
+ * @rcv_unacked: # messages read by user, but not yet acked back to peer
+ */
+struct tipc_sock {
+ struct sock sk;
+ int connected;
+ u32 conn_type;
+ u32 conn_instance;
+ int published;
+ u32 max_pkt;
+ u32 ref;
+ struct tipc_msg phdr;
+ struct list_head sock_list;
+ struct list_head publications;
+ u32 pub_count;
+ u32 probing_state;
+ u32 probing_interval;
+ struct timer_list timer;
+ uint conn_timeout;
+ atomic_t dupl_rcvcnt;
+ bool link_cong;
+ uint sent_unacked;
+ uint rcv_unacked;
+};
static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb);
static void tipc_data_ready(struct sock *sk);
@@ -53,6 +103,16 @@ static void tipc_write_space(struct sock *sk);
static int tipc_release(struct socket *sock);
static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags);
static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p);
+static void tipc_sk_timeout(unsigned long ref);
+static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
+ struct tipc_name_seq const *seq);
+static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
+ struct tipc_name_seq const *seq);
+static u32 tipc_sk_ref_acquire(struct tipc_sock *tsk);
+static void tipc_sk_ref_discard(u32 ref);
+static struct tipc_sock *tipc_sk_get(u32 ref);
+static struct tipc_sock *tipc_sk_get_next(u32 *ref);
+static void tipc_sk_put(struct tipc_sock *tsk);
static const struct proto_ops packet_ops;
static const struct proto_ops stream_ops;
@@ -106,24 +166,75 @@ static struct proto tipc_proto_kern;
* - port reference
*/
-#include "socket.h"
+static u32 tsk_peer_node(struct tipc_sock *tsk)
+{
+ return msg_destnode(&tsk->phdr);
+}
+
+static u32 tsk_peer_port(struct tipc_sock *tsk)
+{
+ return msg_destport(&tsk->phdr);
+}
+
+static bool tsk_unreliable(struct tipc_sock *tsk)
+{
+ return msg_src_droppable(&tsk->phdr) != 0;
+}
+
+static void tsk_set_unreliable(struct tipc_sock *tsk, bool unreliable)
+{
+ msg_set_src_droppable(&tsk->phdr, unreliable ? 1 : 0);
+}
+
+static bool tsk_unreturnable(struct tipc_sock *tsk)
+{
+ return msg_dest_droppable(&tsk->phdr) != 0;
+}
+
+static void tsk_set_unreturnable(struct tipc_sock *tsk, bool unreturnable)
+{
+ msg_set_dest_droppable(&tsk->phdr, unreturnable ? 1 : 0);
+}
+
+static int tsk_importance(struct tipc_sock *tsk)
+{
+ return msg_importance(&tsk->phdr);
+}
+
+static int tsk_set_importance(struct tipc_sock *tsk, int imp)
+{
+ if (imp > TIPC_CRITICAL_IMPORTANCE)
+ return -EINVAL;
+ msg_set_importance(&tsk->phdr, (u32)imp);
+ return 0;
+}
+
+static struct tipc_sock *tipc_sk(const struct sock *sk)
+{
+ return container_of(sk, struct tipc_sock, sk);
+}
+
+static int tsk_conn_cong(struct tipc_sock *tsk)
+{
+ return tsk->sent_unacked >= TIPC_FLOWCTRL_WIN;
+}
/**
- * advance_rx_queue - discard first buffer in socket receive queue
+ * tsk_advance_rx_queue - discard first buffer in socket receive queue
*
* Caller must hold socket lock
*/
-static void advance_rx_queue(struct sock *sk)
+static void tsk_advance_rx_queue(struct sock *sk)
{
kfree_skb(__skb_dequeue(&sk->sk_receive_queue));
}
/**
- * reject_rx_queue - reject all buffers in socket receive queue
+ * tsk_rej_rx_queue - reject all buffers in socket receive queue
*
* Caller must hold socket lock
*/
-static void reject_rx_queue(struct sock *sk)
+static void tsk_rej_rx_queue(struct sock *sk)
{
struct sk_buff *buf;
u32 dnode;
@@ -134,6 +245,38 @@ static void reject_rx_queue(struct sock *sk)
}
}
+/* tsk_peer_msg - verify if message was sent by connected port's peer
+ *
+ * Handles cases where the node's network address has changed from
+ * the default of <0.0.0> to its configured setting.
+ */
+static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg)
+{
+ u32 peer_port = tsk_peer_port(tsk);
+ u32 orig_node;
+ u32 peer_node;
+
+ if (unlikely(!tsk->connected))
+ return false;
+
+ if (unlikely(msg_origport(msg) != peer_port))
+ return false;
+
+ orig_node = msg_orignode(msg);
+ peer_node = tsk_peer_node(tsk);
+
+ if (likely(orig_node == peer_node))
+ return true;
+
+ if (!orig_node && (peer_node == tipc_own_addr))
+ return true;
+
+ if (!peer_node && (orig_node == tipc_own_addr))
+ return true;
+
+ return false;
+}
+
/**
* tipc_sk_create - create a TIPC socket
* @net: network namespace (must be default network)
@@ -153,7 +296,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
socket_state state;
struct sock *sk;
struct tipc_sock *tsk;
- struct tipc_port *port;
+ struct tipc_msg *msg;
u32 ref;
/* Validate arguments */
@@ -188,20 +331,24 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
return -ENOMEM;
tsk = tipc_sk(sk);
- port = &tsk->port;
-
- ref = tipc_port_init(port, TIPC_LOW_IMPORTANCE);
+ ref = tipc_sk_ref_acquire(tsk);
if (!ref) {
- pr_warn("Socket registration failed, ref. table exhausted\n");
- sk_free(sk);
+ pr_warn("Socket create failed; reference table exhausted\n");
return -ENOMEM;
}
+ tsk->max_pkt = MAX_PKT_DEFAULT;
+ tsk->ref = ref;
+ INIT_LIST_HEAD(&tsk->publications);
+ msg = &tsk->phdr;
+ tipc_msg_init(msg, TIPC_LOW_IMPORTANCE, TIPC_NAMED_MSG,
+ NAMED_H_SIZE, 0);
+ msg_set_origport(msg, ref);
/* Finish initializing socket data structures */
sock->ops = ops;
sock->state = state;
-
sock_init_data(sock, sk);
+ k_init_timer(&tsk->timer, (Handler)tipc_sk_timeout, ref);
sk->sk_backlog_rcv = tipc_backlog_rcv;
sk->sk_rcvbuf = sysctl_tipc_rmem[1];
sk->sk_data_ready = tipc_data_ready;
@@ -209,12 +356,11 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
tsk->conn_timeout = CONN_TIMEOUT_DEFAULT;
tsk->sent_unacked = 0;
atomic_set(&tsk->dupl_rcvcnt, 0);
- tipc_port_unlock(port);
if (sock->state == SS_READY) {
- tipc_port_set_unreturnable(port, true);
+ tsk_set_unreturnable(tsk, true);
if (sock->type == SOCK_DGRAM)
- tipc_port_set_unreliable(port, true);
+ tsk_set_unreliable(tsk, true);
}
return 0;
}
@@ -308,7 +454,6 @@ static int tipc_release(struct socket *sock)
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk;
- struct tipc_port *port;
struct sk_buff *buf;
u32 dnode;
@@ -320,13 +465,13 @@ static int tipc_release(struct socket *sock)
return 0;
tsk = tipc_sk(sk);
- port = &tsk->port;
lock_sock(sk);
/*
* Reject all unreceived messages, except on an active connection
* (which disconnects locally & sends a 'FIN+' to peer)
*/
+ dnode = tsk_peer_node(tsk);
while (sock->state != SS_DISCONNECTING) {
buf = __skb_dequeue(&sk->sk_receive_queue);
if (buf == NULL)
@@ -337,17 +482,27 @@ static int tipc_release(struct socket *sock)
if ((sock->state == SS_CONNECTING) ||
(sock->state == SS_CONNECTED)) {
sock->state = SS_DISCONNECTING;
- tipc_port_disconnect(port->ref);
+ tsk->connected = 0;
+ tipc_node_remove_conn(dnode, tsk->ref);
}
if (tipc_msg_reverse(buf, &dnode, TIPC_ERR_NO_PORT))
tipc_link_xmit(buf, dnode, 0);
}
}
- /* Destroy TIPC port; also disconnects an active connection and
- * sends a 'FIN-' to peer.
- */
- tipc_port_destroy(port);
+ tipc_sk_withdraw(tsk, 0, NULL);
+ tipc_sk_ref_discard(tsk->ref);
+ k_cancel_timer(&tsk->timer);
+ if (tsk->connected) {
+ buf = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG,
+ SHORT_H_SIZE, 0, dnode, tipc_own_addr,
+ tsk_peer_port(tsk),
+ tsk->ref, TIPC_ERR_NO_PORT);
+ if (buf)
+ tipc_link_xmit(buf, dnode, tsk->ref);
+ tipc_node_remove_conn(dnode, tsk->ref);
+ }
+ k_term_timer(&tsk->timer);
/* Discard any remaining (connection-based) messages in receive queue */
__skb_queue_purge(&sk->sk_receive_queue);
@@ -355,7 +510,6 @@ static int tipc_release(struct socket *sock)
/* Reject any messages that accumulated in backlog queue */
sock->state = SS_DISCONNECTING;
release_sock(sk);
-
sock_put(sk);
sock->sk = NULL;
@@ -387,7 +541,7 @@ static int tipc_bind(struct socket *sock, struct sockaddr *uaddr,
lock_sock(sk);
if (unlikely(!uaddr_len)) {
- res = tipc_withdraw(&tsk->port, 0, NULL);
+ res = tipc_sk_withdraw(tsk, 0, NULL);
goto exit;
}
@@ -415,8 +569,8 @@ static int tipc_bind(struct socket *sock, struct sockaddr *uaddr,
}
res = (addr->scope > 0) ?
- tipc_publish(&tsk->port, addr->scope, &addr->addr.nameseq) :
- tipc_withdraw(&tsk->port, -addr->scope, &addr->addr.nameseq);
+ tipc_sk_publish(tsk, addr->scope, &addr->addr.nameseq) :
+ tipc_sk_withdraw(tsk, -addr->scope, &addr->addr.nameseq);
exit:
release_sock(sk);
return res;
@@ -446,10 +600,10 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
if ((sock->state != SS_CONNECTED) &&
((peer != 2) || (sock->state != SS_DISCONNECTING)))
return -ENOTCONN;
- addr->addr.id.ref = tipc_port_peerport(&tsk->port);
- addr->addr.id.node = tipc_port_peernode(&tsk->port);
+ addr->addr.id.ref = tsk_peer_port(tsk);
+ addr->addr.id.node = tsk_peer_node(tsk);
} else {
- addr->addr.id.ref = tsk->port.ref;
+ addr->addr.id.ref = tsk->ref;
addr->addr.id.node = tipc_own_addr;
}
@@ -518,7 +672,7 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,
break;
case SS_READY:
case SS_CONNECTED:
- if (!tsk->link_cong && !tipc_sk_conn_cong(tsk))
+ if (!tsk->link_cong && !tsk_conn_cong(tsk))
mask |= POLLOUT;
/* fall thru' */
case SS_CONNECTING:
@@ -549,7 +703,7 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq,
struct iovec *iov, size_t dsz, long timeo)
{
struct sock *sk = sock->sk;
- struct tipc_msg *mhdr = &tipc_sk(sk)->port.phdr;
+ struct tipc_msg *mhdr = &tipc_sk(sk)->phdr;
struct sk_buff *buf;
uint mtu;
int rc;
@@ -579,6 +733,7 @@ new_mtu:
goto new_mtu;
if (rc != -ELINKCONG)
break;
+ tipc_sk(sk)->link_cong = 1;
rc = tipc_wait_for_sndmsg(sock, &timeo);
if (rc)
kfree_skb_list(buf);
@@ -638,20 +793,19 @@ static int tipc_sk_proto_rcv(struct tipc_sock *tsk, u32 *dnode,
struct sk_buff *buf)
{
struct tipc_msg *msg = buf_msg(buf);
- struct tipc_port *port = &tsk->port;
int conn_cong;
/* Ignore if connection cannot be validated: */
- if (!port->connected || !tipc_port_peer_msg(port, msg))
+ if (!tsk_peer_msg(tsk, msg))
goto exit;
- port->probing_state = TIPC_CONN_OK;
+ tsk->probing_state = TIPC_CONN_OK;
if (msg_type(msg) == CONN_ACK) {
- conn_cong = tipc_sk_conn_cong(tsk);
+ conn_cong = tsk_conn_cong(tsk);
tsk->sent_unacked -= msg_msgcnt(msg);
if (conn_cong)
- tipc_sock_wakeup(tsk);
+ tsk->sk.sk_write_space(&tsk->sk);
} else if (msg_type(msg) == CONN_PROBE) {
if (!tipc_msg_reverse(buf, dnode, TIPC_OK))
return TIPC_OK;
@@ -742,8 +896,7 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock,
DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
- struct tipc_port *port = &tsk->port;
- struct tipc_msg *mhdr = &port->phdr;
+ struct tipc_msg *mhdr = &tsk->phdr;
struct iovec *iov = m->msg_iov;
u32 dnode, dport;
struct sk_buff *buf;
@@ -774,13 +927,13 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock,
rc = -EISCONN;
goto exit;
}
- if (tsk->port.published) {
+ if (tsk->published) {
rc = -EOPNOTSUPP;
goto exit;
}
if (dest->addrtype == TIPC_ADDR_NAME) {
- tsk->port.conn_type = dest->addr.name.name.type;
- tsk->port.conn_instance = dest->addr.name.name.instance;
+ tsk->conn_type = dest->addr.name.name.type;
+ tsk->conn_instance = dest->addr.name.name.instance;
}
}
rc = dest_name_check(dest, m);
@@ -820,13 +973,14 @@ static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock,
}
new_mtu:
- mtu = tipc_node_get_mtu(dnode, tsk->port.ref);
+ mtu = tipc_node_get_mtu(dnode, tsk->ref);
rc = tipc_msg_build(mhdr, iov, 0, dsz, mtu, &buf);
if (rc < 0)
goto exit;
do {
- rc = tipc_link_xmit(buf, dnode, tsk->port.ref);
+ TIPC_SKB_CB(buf)->wakeup_pending = tsk->link_cong;
+ rc = tipc_link_xmit(buf, dnode, tsk->ref);
if (likely(rc >= 0)) {
if (sock->state != SS_READY)
sock->state = SS_CONNECTING;
@@ -835,10 +989,9 @@ new_mtu:
}
if (rc == -EMSGSIZE)
goto new_mtu;
-
if (rc != -ELINKCONG)
break;
-
+ tsk->link_cong = 1;
rc = tipc_wait_for_sndmsg(sock, &timeo);
if (rc)
kfree_skb_list(buf);
@@ -873,8 +1026,8 @@ static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p)
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
done = sk_wait_event(sk, timeo_p,
(!tsk->link_cong &&
- !tipc_sk_conn_cong(tsk)) ||
- !tsk->port.connected);
+ !tsk_conn_cong(tsk)) ||
+ !tsk->connected);
finish_wait(sk_sleep(sk), &wait);
} while (!done);
return 0;
@@ -897,11 +1050,10 @@ static int tipc_send_stream(struct kiocb *iocb, struct socket *sock,
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
- struct tipc_port *port = &tsk->port;
- struct tipc_msg *mhdr = &port->phdr;
+ struct tipc_msg *mhdr = &tsk->phdr;
struct sk_buff *buf;
DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
- u32 ref = port->ref;
+ u32 ref = tsk->ref;
int rc = -EINVAL;
long timeo;
u32 dnode;
@@ -929,16 +1081,16 @@ static int tipc_send_stream(struct kiocb *iocb, struct socket *sock,
}
timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT);
- dnode = tipc_port_peernode(port);
+ dnode = tsk_peer_node(tsk);
next:
- mtu = port->max_pkt;
+ mtu = tsk->max_pkt;
send = min_t(uint, dsz - sent, TIPC_MAX_USER_MSG_SIZE);
rc = tipc_msg_build(mhdr, m->msg_iov, sent, send, mtu, &buf);
if (unlikely(rc < 0))
goto exit;
do {
- if (likely(!tipc_sk_conn_cong(tsk))) {
+ if (likely(!tsk_conn_cong(tsk))) {
rc = tipc_link_xmit(buf, dnode, ref);
if (likely(!rc)) {
tsk->sent_unacked++;
@@ -948,11 +1100,12 @@ next:
goto next;
}
if (rc == -EMSGSIZE) {
- port->max_pkt = tipc_node_get_mtu(dnode, ref);
+ tsk->max_pkt = tipc_node_get_mtu(dnode, ref);
goto next;
}
if (rc != -ELINKCONG)
break;
+ tsk->link_cong = 1;
}
rc = tipc_wait_for_sndpkt(sock, &timeo);
if (rc)
@@ -984,29 +1137,25 @@ static int tipc_send_packet(struct kiocb *iocb, struct socket *sock,
return tipc_send_stream(iocb, sock, m, dsz);
}
-/**
- * auto_connect - complete connection setup to a remote port
- * @tsk: tipc socket structure
- * @msg: peer's response message
- *
- * Returns 0 on success, errno otherwise
+/* tipc_sk_finish_conn - complete the setup of a connection
*/
-static int auto_connect(struct tipc_sock *tsk, struct tipc_msg *msg)
+static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port,
+ u32 peer_node)
{
- struct tipc_port *port = &tsk->port;
- struct socket *sock = tsk->sk.sk_socket;
- struct tipc_portid peer;
-
- peer.ref = msg_origport(msg);
- peer.node = msg_orignode(msg);
-
- __tipc_port_connect(port->ref, port, &peer);
-
- if (msg_importance(msg) > TIPC_CRITICAL_IMPORTANCE)
- return -EINVAL;
- msg_set_importance(&port->phdr, (u32)msg_importance(msg));
- sock->state = SS_CONNECTED;
- return 0;
+ struct tipc_msg *msg = &tsk->phdr;
+
+ msg_set_destnode(msg, peer_node);
+ msg_set_destport(msg, peer_port);
+ msg_set_type(msg, TIPC_CONN_MSG);
+ msg_set_lookup_scope(msg, 0);
+ msg_set_hdr_sz(msg, SHORT_H_SIZE);
+
+ tsk->probing_interval = CONN_PROBING_INTERVAL;
+ tsk->probing_state = TIPC_CONN_OK;
+ tsk->connected = 1;
+ k_start_timer(&tsk->timer, tsk->probing_interval);
+ tipc_node_add_conn(peer_node, tsk->ref, peer_port);
+ tsk->max_pkt = tipc_node_get_mtu(peer_node, tsk->ref);
}
/**
@@ -1033,17 +1182,17 @@ static void set_orig_addr(struct msghdr *m, struct tipc_msg *msg)
}
/**
- * anc_data_recv - optionally capture ancillary data for received message
+ * tipc_sk_anc_data_recv - optionally capture ancillary data for received message
* @m: descriptor for message info
* @msg: received message header
- * @tport: TIPC port associated with message
+ * @tsk: TIPC port associated with message
*
* Note: Ancillary data is not captured if not requested by receiver.
*
* Returns 0 if successful, otherwise errno
*/
-static int anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
- struct tipc_port *tport)
+static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
+ struct tipc_sock *tsk)
{
u32 anc_data[3];
u32 err;
@@ -1086,10 +1235,10 @@ static int anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
anc_data[2] = msg_nameupper(msg);
break;
case TIPC_CONN_MSG:
- has_name = (tport->conn_type != 0);
- anc_data[0] = tport->conn_type;
- anc_data[1] = tport->conn_instance;
- anc_data[2] = tport->conn_instance;
+ has_name = (tsk->conn_type != 0);
+ anc_data[0] = tsk->conn_type;
+ anc_data[1] = tsk->conn_instance;
+ anc_data[2] = tsk->conn_instance;
break;
default:
has_name = 0;
@@ -1103,6 +1252,24 @@ static int anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
return 0;
}
+static void tipc_sk_send_ack(struct tipc_sock *tsk, uint ack)
+{
+ struct sk_buff *buf = NULL;
+ struct tipc_msg *msg;
+ u32 peer_port = tsk_peer_port(tsk);
+ u32 dnode = tsk_peer_node(tsk);
+
+ if (!tsk->connected)
+ return;
+ buf = tipc_msg_create(CONN_MANAGER, CONN_ACK, INT_H_SIZE, 0, dnode,
+ tipc_own_addr, peer_port, tsk->ref, TIPC_OK);
+ if (!buf)
+ return;
+ msg = buf_msg(buf);
+ msg_set_msgcnt(msg, ack);
+ tipc_link_xmit(buf, dnode, msg_link_selector(msg));
+}
+
static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
{
struct sock *sk = sock->sk;
@@ -1153,7 +1320,6 @@ static int tipc_recvmsg(struct kiocb *iocb, struct socket *sock,
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
- struct tipc_port *port = &tsk->port;
struct sk_buff *buf;
struct tipc_msg *msg;
long timeo;
@@ -1188,7 +1354,7 @@ restart:
/* Discard an empty non-errored message & try again */
if ((!sz) && (!err)) {
- advance_rx_queue(sk);
+ tsk_advance_rx_queue(sk);
goto restart;
}
@@ -1196,7 +1362,7 @@ restart:
set_orig_addr(m, msg);
/* Capture ancillary data (optional) */
- res = anc_data_recv(m, msg, port);
+ res = tipc_sk_anc_data_recv(m, msg, tsk);
if (res)
goto exit;
@@ -1223,10 +1389,10 @@ restart:
if (likely(!(flags & MSG_PEEK))) {
if ((sock->state != SS_READY) &&
(++tsk->rcv_unacked >= TIPC_CONNACK_INTV)) {
- tipc_acknowledge(port->ref, tsk->rcv_unacked);
+ tipc_sk_send_ack(tsk, tsk->rcv_unacked);
tsk->rcv_unacked = 0;
}
- advance_rx_queue(sk);
+ tsk_advance_rx_queue(sk);
}
exit:
release_sock(sk);
@@ -1250,7 +1416,6 @@ static int tipc_recv_stream(struct kiocb *iocb, struct socket *sock,
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
- struct tipc_port *port = &tsk->port;
struct sk_buff *buf;
struct tipc_msg *msg;
long timeo;
@@ -1288,14 +1453,14 @@ restart:
/* Discard an empty non-errored message & try again */
if ((!sz) && (!err)) {
- advance_rx_queue(sk);
+ tsk_advance_rx_queue(sk);
goto restart;
}
/* Optionally capture sender's address & ancillary data of first msg */
if (sz_copied == 0) {
set_orig_addr(m, msg);
- res = anc_data_recv(m, msg, port);
+ res = tipc_sk_anc_data_recv(m, msg, tsk);
if (res)
goto exit;
}
@@ -1334,10 +1499,10 @@ restart:
/* Consume received message (optional) */
if (likely(!(flags & MSG_PEEK))) {
if (unlikely(++tsk->rcv_unacked >= TIPC_CONNACK_INTV)) {
- tipc_acknowledge(port->ref, tsk->rcv_unacked);
+ tipc_sk_send_ack(tsk, tsk->rcv_unacked);
tsk->rcv_unacked = 0;
}
- advance_rx_queue(sk);
+ tsk_advance_rx_queue(sk);
}
/* Loop around if more data is required */
@@ -1396,12 +1561,9 @@ static void tipc_data_ready(struct sock *sk)
static int filter_connect(struct tipc_sock *tsk, struct sk_buff **buf)
{
struct sock *sk = &tsk->sk;
- struct tipc_port *port = &tsk->port;
struct socket *sock = sk->sk_socket;
struct tipc_msg *msg = buf_msg(*buf);
-
int retval = -TIPC_ERR_NO_PORT;
- int res;
if (msg_mcast(msg))
return retval;
@@ -1409,16 +1571,23 @@ static int filter_connect(struct tipc_sock *tsk, struct sk_buff **buf)
switch ((int)sock->state) {
case SS_CONNECTED:
/* Accept only connection-based messages sent by peer */
- if (msg_connected(msg) && tipc_port_peer_msg(port, msg)) {
+ if (tsk_peer_msg(tsk, msg)) {
if (unlikely(msg_errcode(msg))) {
sock->state = SS_DISCONNECTING;
- __tipc_port_disconnect(port);
+ tsk->connected = 0;
+ /* let timer expire on it's own */
+ tipc_node_remove_conn(tsk_peer_node(tsk),
+ tsk->ref);
}
retval = TIPC_OK;
}
break;
case SS_CONNECTING:
/* Accept only ACK or NACK message */
+
+ if (unlikely(!msg_connected(msg)))
+ break;
+
if (unlikely(msg_errcode(msg))) {
sock->state = SS_DISCONNECTING;
sk->sk_err = ECONNREFUSED;
@@ -1426,17 +1595,17 @@ static int filter_connect(struct tipc_sock *tsk, struct sk_buff **buf)
break;
}
- if (unlikely(!msg_connected(msg)))
- break;
-
- res = auto_connect(tsk, msg);
- if (res) {
+ if (unlikely(msg_importance(msg) > TIPC_CRITICAL_IMPORTANCE)) {
sock->state = SS_DISCONNECTING;
- sk->sk_err = -res;
+ sk->sk_err = EINVAL;
retval = TIPC_OK;
break;
}
+ tipc_sk_finish_conn(tsk, msg_origport(msg), msg_orignode(msg));
+ msg_set_importance(&tsk->phdr, msg_importance(msg));
+ sock->state = SS_CONNECTED;
+
/* If an incoming message is an 'ACK-', it should be
* discarded here because it doesn't contain useful
* data. In addition, we should try to wake up
@@ -1518,6 +1687,13 @@ static int filter_rcv(struct sock *sk, struct sk_buff *buf)
if (unlikely(msg_user(msg) == CONN_MANAGER))
return tipc_sk_proto_rcv(tsk, &onode, buf);
+ if (unlikely(msg_user(msg) == SOCK_WAKEUP)) {
+ kfree_skb(buf);
+ tsk->link_cong = 0;
+ sk->sk_write_space(sk);
+ return TIPC_OK;
+ }
+
/* Reject message if it is wrong sort of message for socket */
if (msg_type(msg) > TIPC_DIRECT_MSG)
return -TIPC_ERR_NO_PORT;
@@ -1585,7 +1761,6 @@ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *buf)
int tipc_sk_rcv(struct sk_buff *buf)
{
struct tipc_sock *tsk;
- struct tipc_port *port;
struct sock *sk;
u32 dport = msg_destport(buf_msg(buf));
int rc = TIPC_OK;
@@ -1593,13 +1768,11 @@ int tipc_sk_rcv(struct sk_buff *buf)
u32 dnode;
/* Validate destination and message */
- port = tipc_port_lock(dport);
- if (unlikely(!port)) {
+ tsk = tipc_sk_get(dport);
+ if (unlikely(!tsk)) {
rc = tipc_msg_eval(buf, &dnode);
goto exit;
}
-
- tsk = tipc_port_to_sock(port);
sk = &tsk->sk;
/* Queue message */
@@ -1615,8 +1788,7 @@ int tipc_sk_rcv(struct sk_buff *buf)
rc = -TIPC_ERR_OVERLOAD;
}
bh_unlock_sock(sk);
- tipc_port_unlock(port);
-
+ tipc_sk_put(tsk);
if (likely(!rc))
return 0;
exit:
@@ -1803,10 +1975,8 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
{
struct sock *new_sk, *sk = sock->sk;
struct sk_buff *buf;
- struct tipc_port *new_port;
+ struct tipc_sock *new_tsock;
struct tipc_msg *msg;
- struct tipc_portid peer;
- u32 new_ref;
long timeo;
int res;
@@ -1828,8 +1998,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
goto exit;
new_sk = new_sock->sk;
- new_port = &tipc_sk(new_sk)->port;
- new_ref = new_port->ref;
+ new_tsock = tipc_sk(new_sk);
msg = buf_msg(buf);
/* we lock on new_sk; but lockdep sees the lock on sk */
@@ -1839,18 +2008,16 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
* Reject any stray messages received by new socket
* before the socket lock was taken (very, very unlikely)
*/
- reject_rx_queue(new_sk);
+ tsk_rej_rx_queue(new_sk);
/* Connect new socket to it's peer */
- peer.ref = msg_origport(msg);
- peer.node = msg_orignode(msg);
- tipc_port_connect(new_ref, &peer);
+ tipc_sk_finish_conn(new_tsock, msg_origport(msg), msg_orignode(msg));
new_sock->state = SS_CONNECTED;
- tipc_port_set_importance(new_port, msg_importance(msg));
+ tsk_set_importance(new_tsock, msg_importance(msg));
if (msg_named(msg)) {
- new_port->conn_type = msg_nametype(msg);
- new_port->conn_instance = msg_nameinst(msg);
+ new_tsock->conn_type = msg_nametype(msg);
+ new_tsock->conn_instance = msg_nameinst(msg);
}
/*
@@ -1860,7 +2027,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
if (!msg_data_sz(msg)) {
struct msghdr m = {NULL,};
- advance_rx_queue(sk);
+ tsk_advance_rx_queue(sk);
tipc_send_packet(NULL, new_sock, &m, 0);
} else {
__skb_dequeue(&sk->sk_receive_queue);
@@ -1886,9 +2053,8 @@ static int tipc_shutdown(struct socket *sock, int how)
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
- struct tipc_port *port = &tsk->port;
struct sk_buff *buf;
- u32 peer;
+ u32 dnode;
int res;
if (how != SHUT_RDWR)
@@ -1908,15 +2074,21 @@ restart:
kfree_skb(buf);
goto restart;
}
- tipc_port_disconnect(port->ref);
- if (tipc_msg_reverse(buf, &peer, TIPC_CONN_SHUTDOWN))
- tipc_link_xmit(buf, peer, 0);
+ if (tipc_msg_reverse(buf, &dnode, TIPC_CONN_SHUTDOWN))
+ tipc_link_xmit(buf, dnode, tsk->ref);
+ tipc_node_remove_conn(dnode, tsk->ref);
} else {
- tipc_port_shutdown(port->ref);
+ dnode = tsk_peer_node(tsk);
+ buf = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
+ TIPC_CONN_MSG, SHORT_H_SIZE,
+ 0, dnode, tipc_own_addr,
+ tsk_peer_port(tsk),
+ tsk->ref, TIPC_CONN_SHUTDOWN);
+ tipc_link_xmit(buf, dnode, tsk->ref);
}
-
+ tsk->connected = 0;
sock->state = SS_DISCONNECTING;
-
+ tipc_node_remove_conn(dnode, tsk->ref);
/* fall through */
case SS_DISCONNECTING:
@@ -1937,6 +2109,432 @@ restart:
return res;
}
+static void tipc_sk_timeout(unsigned long ref)
+{
+ struct tipc_sock *tsk;
+ struct sock *sk;
+ struct sk_buff *buf = NULL;
+ u32 peer_port, peer_node;
+
+ tsk = tipc_sk_get(ref);
+ if (!tsk)
+ return;
+
+ sk = &tsk->sk;
+ bh_lock_sock(sk);
+ if (!tsk->connected) {
+ bh_unlock_sock(sk);
+ goto exit;
+ }
+ peer_port = tsk_peer_port(tsk);
+ peer_node = tsk_peer_node(tsk);
+
+ if (tsk->probing_state == TIPC_CONN_PROBING) {
+ /* Previous probe not answered -> self abort */
+ buf = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG,
+ SHORT_H_SIZE, 0, tipc_own_addr,
+ peer_node, ref, peer_port,
+ TIPC_ERR_NO_PORT);
+ } else {
+ buf = tipc_msg_create(CONN_MANAGER, CONN_PROBE, INT_H_SIZE,
+ 0, peer_node, tipc_own_addr,
+ peer_port, ref, TIPC_OK);
+ tsk->probing_state = TIPC_CONN_PROBING;
+ k_start_timer(&tsk->timer, tsk->probing_interval);
+ }
+ bh_unlock_sock(sk);
+ if (buf)
+ tipc_link_xmit(buf, peer_node, ref);
+exit:
+ tipc_sk_put(tsk);
+}
+
+static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
+ struct tipc_name_seq const *seq)
+{
+ struct publication *publ;
+ u32 key;
+
+ if (tsk->connected)
+ return -EINVAL;
+ key = tsk->ref + tsk->pub_count + 1;
+ if (key == tsk->ref)
+ return -EADDRINUSE;
+
+ publ = tipc_nametbl_publish(seq->type, seq->lower, seq->upper,
+ scope, tsk->ref, key);
+ if (unlikely(!publ))
+ return -EINVAL;
+
+ list_add(&publ->pport_list, &tsk->publications);
+ tsk->pub_count++;
+ tsk->published = 1;
+ return 0;
+}
+
+static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
+ struct tipc_name_seq const *seq)
+{
+ struct publication *publ;
+ struct publication *safe;
+ int rc = -EINVAL;
+
+ list_for_each_entry_safe(publ, safe, &tsk->publications, pport_list) {
+ if (seq) {
+ if (publ->scope != scope)
+ continue;
+ if (publ->type != seq->type)
+ continue;
+ if (publ->lower != seq->lower)
+ continue;
+ if (publ->upper != seq->upper)
+ break;
+ tipc_nametbl_withdraw(publ->type, publ->lower,
+ publ->ref, publ->key);
+ rc = 0;
+ break;
+ }
+ tipc_nametbl_withdraw(publ->type, publ->lower,
+ publ->ref, publ->key);
+ rc = 0;
+ }
+ if (list_empty(&tsk->publications))
+ tsk->published = 0;
+ return rc;
+}
+
+static int tipc_sk_show(struct tipc_sock *tsk, char *buf,
+ int len, int full_id)
+{
+ struct publication *publ;
+ int ret;
+
+ if (full_id)
+ ret = tipc_snprintf(buf, len, "<%u.%u.%u:%u>:",
+ tipc_zone(tipc_own_addr),
+ tipc_cluster(tipc_own_addr),
+ tipc_node(tipc_own_addr), tsk->ref);
+ else
+ ret = tipc_snprintf(buf, len, "%-10u:", tsk->ref);
+
+ if (tsk->connected) {
+ u32 dport = tsk_peer_port(tsk);
+ u32 destnode = tsk_peer_node(tsk);
+
+ ret += tipc_snprintf(buf + ret, len - ret,
+ " connected to <%u.%u.%u:%u>",
+ tipc_zone(destnode),
+ tipc_cluster(destnode),
+ tipc_node(destnode), dport);
+ if (tsk->conn_type != 0)
+ ret += tipc_snprintf(buf + ret, len - ret,
+ " via {%u,%u}", tsk->conn_type,
+ tsk->conn_instance);
+ } else if (tsk->published) {
+ ret += tipc_snprintf(buf + ret, len - ret, " bound to");
+ list_for_each_entry(publ, &tsk->publications, pport_list) {
+ if (publ->lower == publ->upper)
+ ret += tipc_snprintf(buf + ret, len - ret,
+ " {%u,%u}", publ->type,
+ publ->lower);
+ else
+ ret += tipc_snprintf(buf + ret, len - ret,
+ " {%u,%u,%u}", publ->type,
+ publ->lower, publ->upper);
+ }
+ }
+ ret += tipc_snprintf(buf + ret, len - ret, "\n");
+ return ret;
+}
+
+struct sk_buff *tipc_sk_socks_show(void)
+{
+ struct sk_buff *buf;
+ struct tlv_desc *rep_tlv;
+ char *pb;
+ int pb_len;
+ struct tipc_sock *tsk;
+ int str_len = 0;
+ u32 ref = 0;
+
+ buf = tipc_cfg_reply_alloc(TLV_SPACE(ULTRA_STRING_MAX_LEN));
+ if (!buf)
+ return NULL;
+ rep_tlv = (struct tlv_desc *)buf->data;
+ pb = TLV_DATA(rep_tlv);
+ pb_len = ULTRA_STRING_MAX_LEN;
+
+ tsk = tipc_sk_get_next(&ref);
+ for (; tsk; tsk = tipc_sk_get_next(&ref)) {
+ lock_sock(&tsk->sk);
+ str_len += tipc_sk_show(tsk, pb + str_len,
+ pb_len - str_len, 0);
+ release_sock(&tsk->sk);
+ tipc_sk_put(tsk);
+ }
+ str_len += 1; /* for "\0" */
+ skb_put(buf, TLV_SPACE(str_len));
+ TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len);
+
+ return buf;
+}
+
+/* tipc_sk_reinit: set non-zero address in all existing sockets
+ * when we go from standalone to network mode.
+ */
+void tipc_sk_reinit(void)
+{
+ struct tipc_msg *msg;
+ u32 ref = 0;
+ struct tipc_sock *tsk = tipc_sk_get_next(&ref);
+
+ for (; tsk; tsk = tipc_sk_get_next(&ref)) {
+ lock_sock(&tsk->sk);
+ msg = &tsk->phdr;
+ msg_set_prevnode(msg, tipc_own_addr);
+ msg_set_orignode(msg, tipc_own_addr);
+ release_sock(&tsk->sk);
+ tipc_sk_put(tsk);
+ }
+}
+
+/**
+ * struct reference - TIPC socket reference entry
+ * @tsk: pointer to socket associated with reference entry
+ * @ref: reference value for socket (combines instance & array index info)
+ */
+struct reference {
+ struct tipc_sock *tsk;
+ u32 ref;
+};
+
+/**
+ * struct tipc_ref_table - table of TIPC socket reference entries
+ * @entries: pointer to array of reference entries
+ * @capacity: array index of first unusable entry
+ * @init_point: array index of first uninitialized entry
+ * @first_free: array index of first unused socket reference entry
+ * @last_free: array index of last unused socket reference entry
+ * @index_mask: bitmask for array index portion of reference values
+ * @start_mask: initial value for instance value portion of reference values
+ */
+struct ref_table {
+ struct reference *entries;
+ u32 capacity;
+ u32 init_point;
+ u32 first_free;
+ u32 last_free;
+ u32 index_mask;
+ u32 start_mask;
+};
+
+/* Socket reference table consists of 2**N entries.
+ *
+ * State Socket ptr Reference
+ * ----- ---------- ---------
+ * In use non-NULL XXXX|own index
+ * (XXXX changes each time entry is acquired)
+ * Free NULL YYYY|next free index
+ * (YYYY is one more than last used XXXX)
+ * Uninitialized NULL 0
+ *
+ * Entry 0 is not used; this allows index 0 to denote the end of the free list.
+ *
+ * Note that a reference value of 0 does not necessarily indicate that an
+ * entry is uninitialized, since the last entry in the free list could also
+ * have a reference value of 0 (although this is unlikely).
+ */
+
+static struct ref_table tipc_ref_table;
+
+static DEFINE_RWLOCK(ref_table_lock);
+
+/**
+ * tipc_ref_table_init - create reference table for sockets
+ */
+int tipc_sk_ref_table_init(u32 req_sz, u32 start)
+{
+ struct reference *table;
+ u32 actual_sz;
+
+ /* account for unused entry, then round up size to a power of 2 */
+
+ req_sz++;
+ for (actual_sz = 16; actual_sz < req_sz; actual_sz <<= 1) {
+ /* do nothing */
+ };
+
+ /* allocate table & mark all entries as uninitialized */
+ table = vzalloc(actual_sz * sizeof(struct reference));
+ if (table == NULL)
+ return -ENOMEM;
+
+ tipc_ref_table.entries = table;
+ tipc_ref_table.capacity = req_sz;
+ tipc_ref_table.init_point = 1;
+ tipc_ref_table.first_free = 0;
+ tipc_ref_table.last_free = 0;
+ tipc_ref_table.index_mask = actual_sz - 1;
+ tipc_ref_table.start_mask = start & ~tipc_ref_table.index_mask;
+
+ return 0;
+}
+
+/**
+ * tipc_ref_table_stop - destroy reference table for sockets
+ */
+void tipc_sk_ref_table_stop(void)
+{
+ if (!tipc_ref_table.entries)
+ return;
+ vfree(tipc_ref_table.entries);
+ tipc_ref_table.entries = NULL;
+}
+
+/* tipc_ref_acquire - create reference to a socket
+ *
+ * Register an socket pointer in the reference table.
+ * Returns a unique reference value that is used from then on to retrieve the
+ * socket pointer, or to determine if the socket has been deregistered.
+ */
+u32 tipc_sk_ref_acquire(struct tipc_sock *tsk)
+{
+ u32 index;
+ u32 index_mask;
+ u32 next_plus_upper;
+ u32 ref = 0;
+ struct reference *entry;
+
+ if (unlikely(!tsk)) {
+ pr_err("Attempt to acquire ref. to non-existent obj\n");
+ return 0;
+ }
+ if (unlikely(!tipc_ref_table.entries)) {
+ pr_err("Ref. table not found in acquisition attempt\n");
+ return 0;
+ }
+
+ /* Take a free entry, if available; otherwise initialize a new one */
+ write_lock_bh(&ref_table_lock);
+ index = tipc_ref_table.first_free;
+ entry = &tipc_ref_table.entries[index];
+
+ if (likely(index)) {
+ index = tipc_ref_table.first_free;
+ entry = &tipc_ref_table.entries[index];
+ index_mask = tipc_ref_table.index_mask;
+ next_plus_upper = entry->ref;
+ tipc_ref_table.first_free = next_plus_upper & index_mask;
+ ref = (next_plus_upper & ~index_mask) + index;
+ entry->tsk = tsk;
+ } else if (tipc_ref_table.init_point < tipc_ref_table.capacity) {
+ index = tipc_ref_table.init_point++;
+ entry = &tipc_ref_table.entries[index];
+ ref = tipc_ref_table.start_mask + index;
+ }
+
+ if (ref) {
+ entry->ref = ref;
+ entry->tsk = tsk;
+ }
+ write_unlock_bh(&ref_table_lock);
+ return ref;
+}
+
+/* tipc_sk_ref_discard - invalidate reference to an socket
+ *
+ * Disallow future references to an socket and free up the entry for re-use.
+ */
+void tipc_sk_ref_discard(u32 ref)
+{
+ struct reference *entry;
+ u32 index;
+ u32 index_mask;
+
+ if (unlikely(!tipc_ref_table.entries)) {
+ pr_err("Ref. table not found during discard attempt\n");
+ return;
+ }
+
+ index_mask = tipc_ref_table.index_mask;
+ index = ref & index_mask;
+ entry = &tipc_ref_table.entries[index];
+
+ write_lock_bh(&ref_table_lock);
+
+ if (unlikely(!entry->tsk)) {
+ pr_err("Attempt to discard ref. to non-existent socket\n");
+ goto exit;
+ }
+ if (unlikely(entry->ref != ref)) {
+ pr_err("Attempt to discard non-existent reference\n");
+ goto exit;
+ }
+
+ /* Mark entry as unused; increment instance part of entry's
+ * reference to invalidate any subsequent references
+ */
+
+ entry->tsk = NULL;
+ entry->ref = (ref & ~index_mask) + (index_mask + 1);
+
+ /* Append entry to free entry list */
+ if (unlikely(tipc_ref_table.first_free == 0))
+ tipc_ref_table.first_free = index;
+ else
+ tipc_ref_table.entries[tipc_ref_table.last_free].ref |= index;
+ tipc_ref_table.last_free = index;
+exit:
+ write_unlock_bh(&ref_table_lock);
+}
+
+/* tipc_sk_get - find referenced socket and return pointer to it
+ */
+struct tipc_sock *tipc_sk_get(u32 ref)
+{
+ struct reference *entry;
+ struct tipc_sock *tsk;
+
+ if (unlikely(!tipc_ref_table.entries))
+ return NULL;
+ read_lock_bh(&ref_table_lock);
+ entry = &tipc_ref_table.entries[ref & tipc_ref_table.index_mask];
+ tsk = entry->tsk;
+ if (likely(tsk && (entry->ref == ref)))
+ sock_hold(&tsk->sk);
+ else
+ tsk = NULL;
+ read_unlock_bh(&ref_table_lock);
+ return tsk;
+}
+
+/* tipc_sk_get_next - lock & return next socket after referenced one
+*/
+struct tipc_sock *tipc_sk_get_next(u32 *ref)
+{
+ struct reference *entry;
+ struct tipc_sock *tsk = NULL;
+ uint index = *ref & tipc_ref_table.index_mask;
+
+ read_lock_bh(&ref_table_lock);
+ while (++index < tipc_ref_table.capacity) {
+ entry = &tipc_ref_table.entries[index];
+ if (!entry->tsk)
+ continue;
+ tsk = entry->tsk;
+ sock_hold(&tsk->sk);
+ *ref = entry->ref;
+ break;
+ }
+ read_unlock_bh(&ref_table_lock);
+ return tsk;
+}
+
+static void tipc_sk_put(struct tipc_sock *tsk)
+{
+ sock_put(&tsk->sk);
+}
+
/**
* tipc_setsockopt - set socket option
* @sock: socket structure
@@ -1955,7 +2553,6 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
- struct tipc_port *port = &tsk->port;
u32 value;
int res;
@@ -1973,16 +2570,16 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
switch (opt) {
case TIPC_IMPORTANCE:
- res = tipc_port_set_importance(port, value);
+ res = tsk_set_importance(tsk, value);
break;
case TIPC_SRC_DROPPABLE:
if (sock->type != SOCK_STREAM)
- tipc_port_set_unreliable(port, value);
+ tsk_set_unreliable(tsk, value);
else
res = -ENOPROTOOPT;
break;
case TIPC_DEST_DROPPABLE:
- tipc_port_set_unreturnable(port, value);
+ tsk_set_unreturnable(tsk, value);
break;
case TIPC_CONN_TIMEOUT:
tipc_sk(sk)->conn_timeout = value;
@@ -2015,7 +2612,6 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt,
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
- struct tipc_port *port = &tsk->port;
int len;
u32 value;
int res;
@@ -2032,16 +2628,16 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt,
switch (opt) {
case TIPC_IMPORTANCE:
- value = tipc_port_importance(port);
+ value = tsk_importance(tsk);
break;
case TIPC_SRC_DROPPABLE:
- value = tipc_port_unreliable(port);
+ value = tsk_unreliable(tsk);
break;
case TIPC_DEST_DROPPABLE:
- value = tipc_port_unreturnable(port);
+ value = tsk_unreturnable(tsk);
break;
case TIPC_CONN_TIMEOUT:
- value = tipc_sk(sk)->conn_timeout;
+ value = tsk->conn_timeout;
/* no need to set "res", since already 0 at this point */
break;
case TIPC_NODE_RECVQ_DEPTH:
diff --git a/net/tipc/socket.h b/net/tipc/socket.h
index 43b75b3cece..baa43d03901 100644
--- a/net/tipc/socket.h
+++ b/net/tipc/socket.h
@@ -35,56 +35,17 @@
#ifndef _TIPC_SOCK_H
#define _TIPC_SOCK_H
-#include "port.h"
#include <net/sock.h>
-#define TIPC_CONN_OK 0
-#define TIPC_CONN_PROBING 1
-
-/**
- * struct tipc_sock - TIPC socket structure
- * @sk: socket - interacts with 'port' and with user via the socket API
- * @port: port - interacts with 'sk' and with the rest of the TIPC stack
- * @peer_name: the peer of the connection, if any
- * @conn_timeout: the time we can wait for an unresponded setup request
- * @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue
- * @link_cong: non-zero if owner must sleep because of link congestion
- * @sent_unacked: # messages sent by socket, and not yet acked by peer
- * @rcv_unacked: # messages read by user, but not yet acked back to peer
- */
-
-struct tipc_sock {
- struct sock sk;
- struct tipc_port port;
- unsigned int conn_timeout;
- atomic_t dupl_rcvcnt;
- int link_cong;
- uint sent_unacked;
- uint rcv_unacked;
-};
-
-static inline struct tipc_sock *tipc_sk(const struct sock *sk)
-{
- return container_of(sk, struct tipc_sock, sk);
-}
-
-static inline struct tipc_sock *tipc_port_to_sock(const struct tipc_port *port)
-{
- return container_of(port, struct tipc_sock, port);
-}
-
-static inline void tipc_sock_wakeup(struct tipc_sock *tsk)
-{
- tsk->sk.sk_write_space(&tsk->sk);
-}
-
-static inline int tipc_sk_conn_cong(struct tipc_sock *tsk)
-{
- return tsk->sent_unacked >= TIPC_FLOWCTRL_WIN;
-}
-
+#define TIPC_CONNACK_INTV 256
+#define TIPC_FLOWCTRL_WIN (TIPC_CONNACK_INTV * 2)
+#define TIPC_CONN_OVERLOAD_LIMIT ((TIPC_FLOWCTRL_WIN * 2 + 1) * \
+ SKB_TRUESIZE(TIPC_MAX_USER_MSG_SIZE))
int tipc_sk_rcv(struct sk_buff *buf);
-
+struct sk_buff *tipc_sk_socks_show(void);
void tipc_sk_mcast_rcv(struct sk_buff *buf);
+void tipc_sk_reinit(void);
+int tipc_sk_ref_table_init(u32 requested_size, u32 start);
+void tipc_sk_ref_table_stop(void);
#endif
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 642437231ad..31b5cb232a4 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -36,7 +36,6 @@
#include "core.h"
#include "name_table.h"
-#include "port.h"
#include "subscr.h"
/**
diff --git a/net/tipc/sysctl.c b/net/tipc/sysctl.c
index f3fef93325a..1a779b1e851 100644
--- a/net/tipc/sysctl.c
+++ b/net/tipc/sysctl.c
@@ -47,6 +47,13 @@ static struct ctl_table tipc_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "named_timeout",
+ .data = &sysctl_tipc_named_timeout,
+ .maxlen = sizeof(sysctl_tipc_named_timeout),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
{}
};