/*
- * Copyright (c) 2007-2012 Nicira Networks.
+ * Copyright (c) 2007-2012 Nicira, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
#include <linux/version.h>
#include <linux/ethtool.h>
#include <linux/wait.h>
-#include <asm/system.h>
#include <asm/div64.h>
#include <linux/highmem.h>
#include <linux/netfilter_bridge.h>
#include "vport-internal_dev.h"
#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,18) || \
- LINUX_VERSION_CODE >= KERNEL_VERSION(3,3,0)
-#error Kernels before 2.6.18 or after 3.2 are not supported by this version of Open vSwitch.
+ LINUX_VERSION_CODE >= KERNEL_VERSION(3,6,0)
+#error Kernels before 2.6.18 or after 3.5 are not supported by this version of Open vSwitch.
#endif
#define REHASH_FLOW_INTERVAL (10 * 60 * HZ)
/* Must be called with rcu_read_lock or RTNL lock. */
const char *ovs_dp_name(const struct datapath *dp)
{
- struct vport *vport = rcu_dereference_rtnl(dp->ports[OVSP_LOCAL]);
+ struct vport *vport = ovs_vport_rtnl_rcu(dp, OVSP_LOCAL);
return vport->ops->get_name(vport);
}
rcu_read_lock();
- local = rcu_dereference(dp->ports[OVSP_LOCAL]);
+ local = ovs_vport_rcu(dp, OVSP_LOCAL);
if (local)
ifindex = local->ops->get_ifindex(local);
else
hdr->ifi_flags = port->ops->get_dev_flags(port);
hdr->ifi_change = 0;
- NLA_PUT_STRING(skb, IFLA_IFNAME, port->ops->get_name(port));
- NLA_PUT_U32(skb, IFLA_MASTER, get_dpifindex(dp));
- NLA_PUT_U32(skb, IFLA_MTU, port->ops->get_mtu(port));
+ if (nla_put_string(skb, IFLA_IFNAME, port->ops->get_name(port)) ||
+ nla_put_u32(skb, IFLA_MASTER, get_dpifindex(dp)) ||
+ nla_put_u32(skb, IFLA_MTU, port->ops->get_mtu(port)) ||
#ifdef IFLA_OPERSTATE
- NLA_PUT_U8(skb, IFLA_OPERSTATE,
- port->ops->is_running(port)
- ? port->ops->get_operstate(port)
- : IF_OPER_DOWN);
+ nla_put_u8(skb, IFLA_OPERSTATE,
+ port->ops->is_running(port) ?
+ port->ops->get_operstate(port) :
+ IF_OPER_DOWN) ||
#endif
-
- NLA_PUT(skb, IFLA_ADDRESS, ETH_ALEN, port->ops->get_addr(port));
+ nla_put(skb, IFLA_ADDRESS, ETH_ALEN, port->ops->get_addr(port)))
+ goto nla_put_failure;
return nlmsg_end(skb, nlh);
ovs_flow_tbl_destroy((__force struct flow_table *)dp->table);
free_percpu(dp->stats_percpu);
release_net(ovs_dp_get_net(dp));
+ kfree(dp->ports);
kobject_put(&dp->ifobj);
}
+static struct hlist_head *vport_hash_bucket(const struct datapath *dp,
+ u16 port_no)
+{
+ return &dp->ports[port_no & (DP_VPORT_HASH_BUCKETS - 1)];
+}
+
+struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no)
+{
+ struct vport *vport;
+ struct hlist_node *n;
+ struct hlist_head *head;
+
+ head = vport_hash_bucket(dp, port_no);
+ hlist_for_each_entry_rcu(vport, n, head, dp_hash_node) {
+ if (vport->port_no == port_no)
+ return vport;
+ }
+ return NULL;
+}
+
/* Called with RTNL lock and genl_lock. */
static struct vport *new_vport(const struct vport_parms *parms)
{
vport = ovs_vport_add(parms);
if (!IS_ERR(vport)) {
struct datapath *dp = parms->dp;
+ struct hlist_head *head = vport_hash_bucket(dp, vport->port_no);
- rcu_assign_pointer(dp->ports[parms->port_no], vport);
- list_add(&vport->node, &dp->port_list);
-
+ hlist_add_head_rcu(&vport->dp_hash_node, head);
dp_ifinfo_notify(RTM_NEWLINK, vport);
}
-
return vport;
}
if (p->port_no != OVSP_LOCAL)
ovs_dp_sysfs_del_if(p);
+
dp_ifinfo_notify(RTM_DELLINK, p);
/* First drop references to device. */
- list_del(&p->node);
- rcu_assign_pointer(p->dp->ports[p->port_no], NULL);
+ hlist_del_rcu(&p->dp_hash_node);
/* Then destroy it. */
ovs_vport_del(p);
struct sk_buff *skb,
const struct dp_upcall_info *upcall_info)
{
+ unsigned short gso_type = skb_shinfo(skb)->gso_type;
struct dp_upcall_info later_info;
struct sw_flow_key later_key;
struct sk_buff *segs, *nskb;
int err;
segs = skb_gso_segment(skb, NETIF_F_SG | NETIF_F_HW_CSUM);
- if (IS_ERR(skb))
- return PTR_ERR(skb);
+ if (IS_ERR(segs))
+ return PTR_ERR(segs);
/* Queue all of the segments. */
skb = segs;
if (err)
break;
- if (skb == segs && skb_shinfo(skb)->gso_type & SKB_GSO_UDP) {
+ if (skb == segs && gso_type & SKB_GSO_UDP) {
/* The initial flow key extracted by ovs_flow_extract()
* in this case is for a first fragment, so we need to
* properly mark later fragments.
return validate_actions(actions, key, depth + 1);
}
+static int validate_tp_port(const struct sw_flow_key *flow_key)
+{
+ if (flow_key->eth.type == htons(ETH_P_IP)) {
+ if (flow_key->ipv4.tp.src || flow_key->ipv4.tp.dst)
+ return 0;
+ } else if (flow_key->eth.type == htons(ETH_P_IPV6)) {
+ if (flow_key->ipv6.tp.src || flow_key->ipv6.tp.dst)
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
static int validate_set(const struct nlattr *a,
const struct sw_flow_key *flow_key)
{
if (flow_key->eth.type != htons(ETH_P_IP))
return -EINVAL;
- if (!flow_key->ipv4.addr.src || !flow_key->ipv4.addr.dst)
+ if (!flow_key->ip.proto)
return -EINVAL;
ipv4_key = nla_data(ovs_key);
if (flow_key->ip.proto != IPPROTO_TCP)
return -EINVAL;
- if (!flow_key->ipv4.tp.src || !flow_key->ipv4.tp.dst)
- return -EINVAL;
-
- break;
+ return validate_tp_port(flow_key);
case OVS_KEY_ATTR_UDP:
if (flow_key->ip.proto != IPPROTO_UDP)
return -EINVAL;
- if (!flow_key->ipv4.tp.src || !flow_key->ipv4.tp.dst)
- return -EINVAL;
- break;
+ return validate_tp_port(flow_key);
default:
return -EINVAL;
tcp_flags = flow->tcp_flags;
spin_unlock_bh(&flow->lock);
- if (used)
- NLA_PUT_U64(skb, OVS_FLOW_ATTR_USED, ovs_flow_used_time(used));
+ if (used &&
+ nla_put_u64(skb, OVS_FLOW_ATTR_USED, ovs_flow_used_time(used)))
+ goto nla_put_failure;
- if (stats.n_packets)
- NLA_PUT(skb, OVS_FLOW_ATTR_STATS,
- sizeof(struct ovs_flow_stats), &stats);
+ if (stats.n_packets &&
+ nla_put(skb, OVS_FLOW_ATTR_STATS,
+ sizeof(struct ovs_flow_stats), &stats))
+ goto nla_put_failure;
- if (tcp_flags)
- NLA_PUT_U8(skb, OVS_FLOW_ATTR_TCP_FLAGS, tcp_flags);
+ if (tcp_flags &&
+ nla_put_u8(skb, OVS_FLOW_ATTR_TCP_FLAGS, tcp_flags))
+ goto nla_put_failure;
/* If OVS_FLOW_ATTR_ACTIONS doesn't fit, skip dumping the actions if
* this is the first flow to be dumped into 'skb'. This is unusual for
goto nla_put_failure;
get_dp_stats(dp, &dp_stats);
- NLA_PUT(skb, OVS_DP_ATTR_STATS, sizeof(struct ovs_dp_stats), &dp_stats);
+ if (nla_put(skb, OVS_DP_ATTR_STATS, sizeof(struct ovs_dp_stats), &dp_stats))
+ goto nla_put_failure;
return genlmsg_end(skb, ovs_header);
struct datapath *dp;
struct vport *vport;
struct ovs_net *ovs_net;
- int err;
+ int err, i;
err = -EINVAL;
if (!a[OVS_DP_ATTR_NAME] || !a[OVS_DP_ATTR_UPCALL_PID])
if (dp == NULL)
goto err_unlock_rtnl;
- INIT_LIST_HEAD(&dp->port_list);
-
/* Initialize kobject for bridge. This will be added as
* /sys/class/net/<devname>/brif later, if sysfs is enabled. */
dp->ifobj.kset = NULL;
}
ovs_dp_set_net(dp, hold_net(sock_net(skb->sk)));
+ dp->ports = kmalloc(DP_VPORT_HASH_BUCKETS * sizeof(struct hlist_head),
+ GFP_KERNEL);
+ if (!dp->ports) {
+ err = -ENOMEM;
+ goto err_destroy_percpu;
+ }
+
+ for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++)
+ INIT_HLIST_HEAD(&dp->ports[i]);
+
/* Set up our datapath device. */
parms.name = nla_data(a[OVS_DP_ATTR_NAME]);
parms.type = OVS_VPORT_TYPE_INTERNAL;
if (err == -EBUSY)
err = -EEXIST;
- goto err_destroy_percpu;
+ goto err_destroy_ports_array;
}
reply = ovs_dp_cmd_build_info(dp, info->snd_pid,
return 0;
err_destroy_local_port:
- ovs_dp_detach_port(rtnl_dereference(dp->ports[OVSP_LOCAL]));
+ ovs_dp_detach_port(ovs_vport_rtnl(dp, OVSP_LOCAL));
+err_destroy_ports_array:
+ kfree(dp->ports);
err_destroy_percpu:
free_percpu(dp->stats_percpu);
err_destroy_table:
/* Called with genl_mutex. */
static void __dp_destroy(struct datapath *dp)
{
- struct vport *vport, *next_vport;
+ int i;
rtnl_lock();
- list_for_each_entry_safe(vport, next_vport, &dp->port_list, node)
- if (vport->port_no != OVSP_LOCAL)
- ovs_dp_detach_port(vport);
+
+ for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) {
+ struct vport *vport;
+ struct hlist_node *node, *n;
+
+ hlist_for_each_entry_safe(vport, node, n, &dp->ports[i], dp_hash_node)
+ if (vport->port_no != OVSP_LOCAL)
+ ovs_dp_detach_port(vport);
+ }
ovs_dp_sysfs_del_dp(dp);
list_del(&dp->list_node);
- ovs_dp_detach_port(rtnl_dereference(dp->ports[OVSP_LOCAL]));
+ ovs_dp_detach_port(ovs_vport_rtnl(dp, OVSP_LOCAL));
/* rtnl_unlock() will wait until all the references to devices that
* are pending unregistration have been dropped. We do it here to
ovs_header->dp_ifindex = get_dpifindex(vport->dp);
- NLA_PUT_U32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no);
- NLA_PUT_U32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type);
- NLA_PUT_STRING(skb, OVS_VPORT_ATTR_NAME, vport->ops->get_name(vport));
- NLA_PUT_U32(skb, OVS_VPORT_ATTR_UPCALL_PID, vport->upcall_pid);
+ if (nla_put_u32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no) ||
+ nla_put_u32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type) ||
+ nla_put_string(skb, OVS_VPORT_ATTR_NAME, vport->ops->get_name(vport)) ||
+ nla_put_u32(skb, OVS_VPORT_ATTR_UPCALL_PID, vport->upcall_pid))
+ goto nla_put_failure;
ovs_vport_get_stats(vport, &vport_stats);
- NLA_PUT(skb, OVS_VPORT_ATTR_STATS, sizeof(struct ovs_vport_stats),
- &vport_stats);
+ if (nla_put(skb, OVS_VPORT_ATTR_STATS, sizeof(struct ovs_vport_stats),
+ &vport_stats))
+ goto nla_put_failure;
- NLA_PUT(skb, OVS_VPORT_ATTR_ADDRESS, ETH_ALEN,
- vport->ops->get_addr(vport));
+ if (nla_put(skb, OVS_VPORT_ATTR_ADDRESS, ETH_ALEN,
+ vport->ops->get_addr(vport)))
+ goto nla_put_failure;
err = ovs_vport_get_options(vport, skb);
if (err == -EMSGSIZE)
vport = ovs_vport_locate(net, nla_data(a[OVS_VPORT_ATTR_NAME]));
if (!vport)
return ERR_PTR(-ENODEV);
+ if (ovs_header->dp_ifindex &&
+ ovs_header->dp_ifindex != get_dpifindex(vport->dp))
+ return ERR_PTR(-ENODEV);
return vport;
} else if (a[OVS_VPORT_ATTR_PORT_NO]) {
u32 port_no = nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]);
if (!dp)
return ERR_PTR(-ENODEV);
- vport = rcu_dereference_rtnl(dp->ports[port_no]);
+ vport = ovs_vport_rtnl_rcu(dp, port_no);
if (!vport)
return ERR_PTR(-ENOENT);
return vport;
if (port_no >= DP_MAX_PORTS)
goto exit_unlock;
- vport = rtnl_dereference(dp->ports[port_no]);
+ vport = ovs_vport_rtnl(dp, port_no);
err = -EBUSY;
if (vport)
goto exit_unlock;
err = -EFBIG;
goto exit_unlock;
}
- vport = rtnl_dereference(dp->ports[port_no]);
+ vport = ovs_vport_rtnl(dp, port_no);
if (!vport)
break;
}
err = ovs_vport_set_options(vport, a[OVS_VPORT_ATTR_OPTIONS]);
if (!err)
err = change_vport(vport, a);
+ else
+ goto exit_unlock;
if (!err && a[OVS_VPORT_ATTR_UPCALL_PID])
vport->upcall_pid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]);
reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq,
OVS_VPORT_CMD_NEW);
if (IS_ERR(reply)) {
- err = PTR_ERR(reply);
netlink_set_err(GENL_SOCK(sock_net(skb->sk)), 0,
- ovs_dp_vport_multicast_group.id, err);
- return 0;
+ ovs_dp_vport_multicast_group.id, PTR_ERR(reply));
+ goto exit_unlock;
}
genl_notify(reply, genl_info_net(info), info->snd_pid,
{
struct ovs_header *ovs_header = genlmsg_data(nlmsg_data(cb->nlh));
struct datapath *dp;
- u32 port_no;
- int retval;
+ int bucket = cb->args[0], skip = cb->args[1];
+ int i, j = 0;
dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
if (!dp)
return -ENODEV;
rcu_read_lock();
- for (port_no = cb->args[0]; port_no < DP_MAX_PORTS; port_no++) {
+ for (i = bucket; i < DP_VPORT_HASH_BUCKETS; i++) {
struct vport *vport;
-
- vport = rcu_dereference(dp->ports[port_no]);
- if (!vport)
- continue;
-
- if (ovs_vport_cmd_fill_info(vport, skb, NETLINK_CB(cb->skb).pid,
- cb->nlh->nlmsg_seq, NLM_F_MULTI,
- OVS_VPORT_CMD_NEW) < 0)
- break;
+ struct hlist_node *n;
+
+ j = 0;
+ hlist_for_each_entry_rcu(vport, n, &dp->ports[i], dp_hash_node) {
+ if (j >= skip &&
+ ovs_vport_cmd_fill_info(vport, skb,
+ NETLINK_CB(cb->skb).pid,
+ cb->nlh->nlmsg_seq,
+ NLM_F_MULTI,
+ OVS_VPORT_CMD_NEW) < 0)
+ goto out;
+
+ j++;
+ }
+ skip = 0;
}
+out:
rcu_read_unlock();
- cb->args[0] = port_no;
- retval = skb->len;
+ cb->args[0] = i;
+ cb->args[1] = j;
- return retval;
+ return skb->len;
}
static struct genl_ops dp_vport_genl_ops[] = {
BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > sizeof(dummy_skb->cb));
pr_info("Open vSwitch switching datapath %s, built "__DATE__" "__TIME__"\n",
- VERSION BUILDNR);
+ VERSION);
err = genl_exec_init();
if (err)