X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=datapath%2Fdatapath.c;h=f78c23255289e3f20f6dc88edb57334e8b4b65eb;hb=b57d5819ca17da7eb237e5f9343c780937776438;hp=4d95e04db747a6c3fad616384b44773cf802b96b;hpb=850b6b3b9f8c38b42e315c2c07d232a33b82da3e;p=sliver-openvswitch.git diff --git a/datapath/datapath.c b/datapath/datapath.c index 4d95e04db..f78c23255 100644 --- a/datapath/datapath.c +++ b/datapath/datapath.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2011 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 @@ -39,7 +39,6 @@ #include #include #include -#include #include #include #include @@ -50,21 +49,27 @@ #include #include #include +#include +#include #include "checksum.h" #include "datapath.h" #include "flow.h" +#include "genl_exec.h" #include "vlan.h" #include "tunnel.h" #include "vport-internal_dev.h" #if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,18) || \ - LINUX_VERSION_CODE > KERNEL_VERSION(3,2,0) -#error Kernels before 2.6.18 or after 3.2 are not supported by this version of Open vSwitch. + LINUX_VERSION_CODE >= KERNEL_VERSION(3,9,0) +#error Kernels before 2.6.18 or after 3.8 are not supported by this version of Open vSwitch. #endif -int (*ovs_dp_ioctl_hook)(struct net_device *dev, struct ifreq *rq, int cmd); -EXPORT_SYMBOL(ovs_dp_ioctl_hook); +#define REHASH_FLOW_INTERVAL (10 * 60 * HZ) +static void rehash_flow_table(struct work_struct *work); +static DECLARE_DELAYED_WORK(rehash_flow_wq, rehash_flow_table); + +int ovs_net_id __read_mostly; /** * DOC: Locking: @@ -83,25 +88,21 @@ EXPORT_SYMBOL(ovs_dp_ioctl_hook); * each other. */ -/* Global list of datapaths to enable dumping them all out. - * Protected by genl_mutex. - */ -static LIST_HEAD(dps); - static struct vport *new_vport(const struct vport_parms *); -static int queue_gso_packets(int dp_ifindex, struct sk_buff *, +static int queue_gso_packets(struct net *, int dp_ifindex, struct sk_buff *, const struct dp_upcall_info *); -static int queue_userspace_packet(int dp_ifindex, struct sk_buff *, +static int queue_userspace_packet(struct net *, int dp_ifindex, + struct sk_buff *, const struct dp_upcall_info *); /* Must be called with rcu_read_lock, genl_mutex, or RTNL lock. */ -static struct datapath *get_dp(int dp_ifindex) +static struct datapath *get_dp(struct net *net, int dp_ifindex) { struct datapath *dp = NULL; struct net_device *dev; rcu_read_lock(); - dev = dev_get_by_index_rcu(&init_net, dp_ifindex); + dev = dev_get_by_index_rcu(net, dp_ifindex); if (dev) { struct vport *vport = ovs_internal_dev_get_vport(dev); if (vport) @@ -115,7 +116,7 @@ static struct datapath *get_dp(int dp_ifindex) /* 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); } @@ -126,7 +127,7 @@ static int get_dpifindex(struct datapath *dp) 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 @@ -137,108 +138,35 @@ static int get_dpifindex(struct datapath *dp) return ifindex; } -static size_t br_nlmsg_size(void) -{ - return NLMSG_ALIGN(sizeof(struct ifinfomsg)) - + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ - + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ - + nla_total_size(4) /* IFLA_MASTER */ - + nla_total_size(4) /* IFLA_MTU */ - + nla_total_size(1); /* IFLA_OPERSTATE */ -} - -/* Caller must hold RTNL lock. */ -static int dp_fill_ifinfo(struct sk_buff *skb, - const struct vport *port, - int event, unsigned int flags) -{ - struct datapath *dp = port->dp; - struct ifinfomsg *hdr; - struct nlmsghdr *nlh; - - if (!port->ops->get_ifindex) - return -ENODEV; - - nlh = nlmsg_put(skb, 0, 0, event, sizeof(*hdr), flags); - if (nlh == NULL) - return -EMSGSIZE; - - hdr = nlmsg_data(nlh); - hdr->ifi_family = AF_BRIDGE; - hdr->__ifi_pad = 0; - hdr->ifi_type = ARPHRD_ETHER; - hdr->ifi_index = port->ops->get_ifindex(port); - 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)); -#ifdef IFLA_OPERSTATE - 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)); - - return nlmsg_end(skb, nlh); - -nla_put_failure: - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; -} - -/* Caller must hold RTNL lock. */ -static void dp_ifinfo_notify(int event, struct vport *port) +static void destroy_dp_rcu(struct rcu_head *rcu) { - struct sk_buff *skb; - int err; - - skb = nlmsg_new(br_nlmsg_size(), GFP_KERNEL); - if (!skb) { - err = -ENOBUFS; - goto err; - } - - err = dp_fill_ifinfo(skb, port, event, 0); - if (err < 0) { - if (err == -ENODEV) { - goto out; - } else { - /* -EMSGSIZE implies BUG in br_nlmsg_size() */ - WARN_ON(err == -EMSGSIZE); - goto err; - } - } - - rtnl_notify(skb, &init_net, 0, RTNLGRP_LINK, NULL, GFP_KERNEL); + struct datapath *dp = container_of(rcu, struct datapath, rcu); - return; -err: - rtnl_set_sk_err(&init_net, RTNLGRP_LINK, err); -out: - kfree_skb(skb); + 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); + kfree(dp); } -static void release_dp(struct kobject *kobj) +static struct hlist_head *vport_hash_bucket(const struct datapath *dp, + u16 port_no) { - struct datapath *dp = container_of(kobj, struct datapath, ifobj); - kfree(dp); + return &dp->ports[port_no & (DP_VPORT_HASH_BUCKETS - 1)]; } -static struct kobj_type dp_ktype = { - .release = release_dp -}; - -static void destroy_dp_rcu(struct rcu_head *rcu) +struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no) { - struct datapath *dp = container_of(rcu, struct datapath, rcu); + struct vport *vport; + struct hlist_node *n; + struct hlist_head *head; - ovs_flow_tbl_destroy((__force struct flow_table *)dp->table); - free_percpu(dp->stats_percpu); - kobject_put(&dp->ifobj); + 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. */ @@ -249,13 +177,10 @@ 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); - - dp_ifinfo_notify(RTM_NEWLINK, vport); + hlist_add_head_rcu(&vport->dp_hash_node, head); } - return vport; } @@ -264,13 +189,8 @@ void ovs_dp_detach_port(struct vport *p) { ASSERT_RTNL(); - 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); @@ -285,7 +205,7 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb) u64 *stats_counter; int error; - stats = per_cpu_ptr(dp->stats_percpu, smp_processor_id()); + stats = this_cpu_ptr(dp->stats_percpu); if (!OVS_CB(skb)->flow) { struct sw_flow_key key; @@ -307,7 +227,7 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb) upcall.cmd = OVS_PACKET_CMD_MISS; upcall.key = &key; upcall.userdata = NULL; - upcall.pid = p->upcall_pid; + upcall.portid = p->upcall_portid; ovs_dp_upcall(dp, skb, &upcall); consume_skb(skb); stats_counter = &stats->n_missed; @@ -333,7 +253,8 @@ static struct genl_family dp_packet_genl_family = { .hdrsize = sizeof(struct ovs_header), .name = OVS_PACKET_FAMILY, .version = OVS_PACKET_VERSION, - .maxattr = OVS_PACKET_ATTR_MAX + .maxattr = OVS_PACKET_ATTR_MAX, + SET_NETNSOK }; int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb, @@ -343,7 +264,7 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb, int dp_ifindex; int err; - if (upcall_info->pid == 0) { + if (upcall_info->portid == 0) { err = -ENOTCONN; goto err; } @@ -357,16 +278,16 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb, forward_ip_summed(skb, true); if (!skb_is_gso(skb)) - err = queue_userspace_packet(dp_ifindex, skb, upcall_info); + err = queue_userspace_packet(ovs_dp_get_net(dp), dp_ifindex, skb, upcall_info); else - err = queue_gso_packets(dp_ifindex, skb, upcall_info); + err = queue_gso_packets(ovs_dp_get_net(dp), dp_ifindex, skb, upcall_info); if (err) goto err; return 0; err: - stats = per_cpu_ptr(dp->stats_percpu, smp_processor_id()); + stats = this_cpu_ptr(dp->stats_percpu); u64_stats_update_begin(&stats->sync); stats->n_lost++; @@ -375,28 +296,30 @@ err: return err; } -static int queue_gso_packets(int dp_ifindex, struct sk_buff *skb, +static int queue_gso_packets(struct net *net, int dp_ifindex, + 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); + segs = __skb_gso_segment(skb, NETIF_F_SG | NETIF_F_HW_CSUM, false); + if (IS_ERR(segs)) + return PTR_ERR(segs); /* Queue all of the segments. */ skb = segs; do { - err = queue_userspace_packet(dp_ifindex, skb, upcall_info); + err = queue_userspace_packet(net, dp_ifindex, skb, upcall_info); if (err) break; - if (skb == segs && skb_shinfo(skb)->gso_type & SKB_GSO_UDP) { - /* The initial flow key extracted by flow_extract() in - * this case is for a first fragment, so we need to + 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. */ later_key = *upcall_info->key; @@ -420,7 +343,8 @@ static int queue_gso_packets(int dp_ifindex, struct sk_buff *skb, return err; } -static int queue_userspace_packet(int dp_ifindex, struct sk_buff *skb, +static int queue_userspace_packet(struct net *net, int dp_ifindex, + struct sk_buff *skb, const struct dp_upcall_info *upcall_info) { struct ovs_header *upcall; @@ -475,7 +399,7 @@ static int queue_userspace_packet(int dp_ifindex, struct sk_buff *skb, skb_copy_and_csum_dev(skb, nla_data(nla)); - err = genlmsg_unicast(&init_net, user_skb, upcall_info->pid); + err = genlmsg_unicast(net, user_skb, upcall_info->portid); out: kfree_skb(nskb); @@ -483,15 +407,10 @@ out: } /* Called with genl_mutex. */ -static int flush_flows(int dp_ifindex) +static int flush_flows(struct datapath *dp) { struct flow_table *old_table; struct flow_table *new_table; - struct datapath *dp; - - dp = get_dp(dp_ifindex); - if (!dp) - return -ENODEV; old_table = genl_dereference(dp->table); new_table = ovs_flow_tbl_alloc(TBL_MIN_BUCKETS); @@ -504,16 +423,89 @@ static int flush_flows(int dp_ifindex) return 0; } -static int validate_actions(const struct nlattr *attr, - const struct sw_flow_key *key, int depth); +static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, int attr_len) +{ + + struct sw_flow_actions *acts; + int new_acts_size; + int req_size = NLA_ALIGN(attr_len); + int next_offset = offsetof(struct sw_flow_actions, actions) + + (*sfa)->actions_len; -static int validate_sample(const struct nlattr *attr, - const struct sw_flow_key *key, int depth) + if (req_size <= (ksize(*sfa) - next_offset)) + goto out; + + new_acts_size = ksize(*sfa) * 2; + + if (new_acts_size > MAX_ACTIONS_BUFSIZE) { + if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) + return ERR_PTR(-EMSGSIZE); + new_acts_size = MAX_ACTIONS_BUFSIZE; + } + + acts = ovs_flow_actions_alloc(new_acts_size); + if (IS_ERR(acts)) + return (void *)acts; + + memcpy(acts->actions, (*sfa)->actions, (*sfa)->actions_len); + acts->actions_len = (*sfa)->actions_len; + kfree(*sfa); + *sfa = acts; + +out: + (*sfa)->actions_len += req_size; + return (struct nlattr *) ((unsigned char *)(*sfa) + next_offset); +} + +static int add_action(struct sw_flow_actions **sfa, int attrtype, void *data, int len) +{ + struct nlattr *a; + + a = reserve_sfa_size(sfa, nla_attr_size(len)); + if (IS_ERR(a)) + return PTR_ERR(a); + + a->nla_type = attrtype; + a->nla_len = nla_attr_size(len); + + if (data) + memcpy(nla_data(a), data, len); + memset((unsigned char *) a + a->nla_len, 0, nla_padlen(len)); + + return 0; +} + +static inline int add_nested_action_start(struct sw_flow_actions **sfa, int attrtype) +{ + int used = (*sfa)->actions_len; + int err; + + err = add_action(sfa, attrtype, NULL, 0); + if (err) + return err; + + return used; +} + +static inline void add_nested_action_end(struct sw_flow_actions *sfa, int st_offset) +{ + struct nlattr *a = (struct nlattr *) ((unsigned char *)sfa->actions + st_offset); + + a->nla_len = sfa->actions_len - st_offset; +} + +static int validate_and_copy_actions(const struct nlattr *attr, + const struct sw_flow_key *key, int depth, + struct sw_flow_actions **sfa); + +static int validate_and_copy_sample(const struct nlattr *attr, + const struct sw_flow_key *key, int depth, + struct sw_flow_actions **sfa) { const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1]; const struct nlattr *probability, *actions; const struct nlattr *a; - int rem; + int rem, start, err, st_acts; memset(attrs, 0, sizeof(attrs)); nla_for_each_nested(a, attr, rem) { @@ -532,11 +524,65 @@ static int validate_sample(const struct nlattr *attr, actions = attrs[OVS_SAMPLE_ATTR_ACTIONS]; if (!actions || (nla_len(actions) && nla_len(actions) < NLA_HDRLEN)) return -EINVAL; - return validate_actions(actions, key, depth + 1); + + /* validation done, copy sample action. */ + start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE); + if (start < 0) + return start; + err = add_action(sfa, OVS_SAMPLE_ATTR_PROBABILITY, nla_data(probability), sizeof(u32)); + if (err) + return err; + st_acts = add_nested_action_start(sfa, OVS_SAMPLE_ATTR_ACTIONS); + if (st_acts < 0) + return st_acts; + + err = validate_and_copy_actions(actions, key, depth + 1, sfa); + if (err) + return err; + + add_nested_action_end(*sfa, st_acts); + add_nested_action_end(*sfa, start); + + return 0; +} + +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_and_copy_set_tun(const struct nlattr *attr, + struct sw_flow_actions **sfa) +{ + struct ovs_key_ipv4_tunnel tun_key; + int err, start; + + err = ipv4_tun_from_nlattr(nla_data(attr), &tun_key); + if (err) + return err; + + start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET); + if (start < 0) + return start; + + err = add_action(sfa, OVS_KEY_ATTR_IPV4_TUNNEL, &tun_key, sizeof(tun_key)); + add_nested_action_end(*sfa, start); + + return err; } static int validate_set(const struct nlattr *a, - const struct sw_flow_key *flow_key) + const struct sw_flow_key *flow_key, + struct sw_flow_actions **sfa, + bool *set_tun) { const struct nlattr *ovs_key = nla_data(a); int key_type = nla_type(ovs_key); @@ -546,22 +592,39 @@ static int validate_set(const struct nlattr *a, return -EINVAL; if (key_type > OVS_KEY_ATTR_MAX || - nla_len(ovs_key) != ovs_key_lens[key_type]) + (ovs_key_lens[key_type] != nla_len(ovs_key) && + ovs_key_lens[key_type] != -1)) return -EINVAL; switch (key_type) { const struct ovs_key_ipv4 *ipv4_key; + const struct ovs_key_ipv6 *ipv6_key; + int err; case OVS_KEY_ATTR_PRIORITY: case OVS_KEY_ATTR_TUN_ID: case OVS_KEY_ATTR_ETHERNET: break; + case OVS_KEY_ATTR_SKB_MARK: +#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,20) && !defined(CONFIG_NETFILTER) + if (nla_get_u32(ovs_key) != 0) + return -EINVAL; +#endif + break; + + case OVS_KEY_ATTR_TUNNEL: + *set_tun = true; + err = validate_and_copy_set_tun(a, sfa); + if (err) + return err; + break; + case OVS_KEY_ATTR_IPV4: 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); @@ -573,22 +636,36 @@ static int validate_set(const struct nlattr *a, break; - case OVS_KEY_ATTR_TCP: - if (flow_key->ip.proto != IPPROTO_TCP) + case OVS_KEY_ATTR_IPV6: + if (flow_key->eth.type != htons(ETH_P_IPV6)) return -EINVAL; - if (!flow_key->ipv4.tp.src || !flow_key->ipv4.tp.dst) + if (!flow_key->ip.proto) + return -EINVAL; + + ipv6_key = nla_data(ovs_key); + if (ipv6_key->ipv6_proto != flow_key->ip.proto) + return -EINVAL; + + if (ipv6_key->ipv6_frag != flow_key->ip.frag) + return -EINVAL; + + if (ntohl(ipv6_key->ipv6_label) & 0xFFF00000) return -EINVAL; break; + case OVS_KEY_ATTR_TCP: + if (flow_key->ip.proto != IPPROTO_TCP) + return -EINVAL; + + 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; @@ -618,8 +695,24 @@ static int validate_userspace(const struct nlattr *attr) return 0; } -static int validate_actions(const struct nlattr *attr, - const struct sw_flow_key *key, int depth) +static int copy_action(const struct nlattr *from, + struct sw_flow_actions **sfa) +{ + int totlen = NLA_ALIGN(from->nla_len); + struct nlattr *to; + + to = reserve_sfa_size(sfa, from->nla_len); + if (IS_ERR(to)) + return PTR_ERR(to); + + memcpy(to, from, totlen); + return 0; +} + +static int validate_and_copy_actions(const struct nlattr *attr, + const struct sw_flow_key *key, + int depth, + struct sw_flow_actions **sfa) { const struct nlattr *a; int rem, err; @@ -639,12 +732,14 @@ static int validate_actions(const struct nlattr *attr, }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); + bool skip_copy; if (type > OVS_ACTION_ATTR_MAX || (action_lens[type] != nla_len(a) && action_lens[type] != (u32)-1)) return -EINVAL; + skip_copy = false; switch (type) { case OVS_ACTION_ATTR_UNSPEC: return -EINVAL; @@ -673,20 +768,26 @@ static int validate_actions(const struct nlattr *attr, break; case OVS_ACTION_ATTR_SET: - err = validate_set(a, key); + err = validate_set(a, key, sfa, &skip_copy); if (err) return err; break; case OVS_ACTION_ATTR_SAMPLE: - err = validate_sample(a, key, depth); + err = validate_and_copy_sample(a, key, depth, sfa); if (err) return err; + skip_copy = true; break; default: return -EINVAL; } + if (!skip_copy) { + err = copy_action(a, sfa); + if (err) + return err; + } } if (rem > 0) @@ -750,32 +851,27 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) err = ovs_flow_extract(packet, -1, &flow->key, &key_len); if (err) - goto err_flow_put; - - err = ovs_flow_metadata_from_nlattrs(&flow->key.phy.priority, - &flow->key.phy.in_port, - &flow->key.phy.tun_id, - a[OVS_PACKET_ATTR_KEY]); - if (err) - goto err_flow_put; + goto err_flow_free; - err = validate_actions(a[OVS_PACKET_ATTR_ACTIONS], &flow->key, 0); + err = ovs_flow_metadata_from_nlattrs(flow, key_len, a[OVS_PACKET_ATTR_KEY]); if (err) - goto err_flow_put; - - flow->hash = ovs_flow_hash(&flow->key, key_len); - - acts = ovs_flow_actions_alloc(a[OVS_PACKET_ATTR_ACTIONS]); + goto err_flow_free; + acts = ovs_flow_actions_alloc(nla_len(a[OVS_PACKET_ATTR_ACTIONS])); err = PTR_ERR(acts); if (IS_ERR(acts)) - goto err_flow_put; + goto err_flow_free; + + err = validate_and_copy_actions(a[OVS_PACKET_ATTR_ACTIONS], &flow->key, 0, &acts); rcu_assign_pointer(flow->sf_acts, acts); + if (err) + goto err_flow_free; OVS_CB(packet)->flow = flow; packet->priority = flow->key.phy.priority; + skb_set_mark(packet, flow->key.phy.skb_mark); rcu_read_lock(); - dp = get_dp(ovs_header->dp_ifindex); + dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); err = -ENODEV; if (!dp) goto err_unlock; @@ -785,13 +881,13 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) local_bh_enable(); rcu_read_unlock(); - ovs_flow_put(flow); + ovs_flow_free(flow); return err; err_unlock: rcu_read_unlock(); -err_flow_put: - ovs_flow_put(flow); +err_flow_free: + ovs_flow_free(flow); err_kfree_skb: kfree_skb(packet); err: @@ -849,20 +945,115 @@ static struct genl_family dp_flow_genl_family = { .hdrsize = sizeof(struct ovs_header), .name = OVS_FLOW_FAMILY, .version = OVS_FLOW_VERSION, - .maxattr = OVS_FLOW_ATTR_MAX + .maxattr = OVS_FLOW_ATTR_MAX, + SET_NETNSOK }; static struct genl_multicast_group ovs_dp_flow_multicast_group = { .name = OVS_FLOW_MCGROUP }; +static int actions_to_attr(const struct nlattr *attr, int len, struct sk_buff *skb); +static int sample_action_to_attr(const struct nlattr *attr, struct sk_buff *skb) +{ + const struct nlattr *a; + struct nlattr *start; + int err = 0, rem; + + start = nla_nest_start(skb, OVS_ACTION_ATTR_SAMPLE); + if (!start) + return -EMSGSIZE; + + nla_for_each_nested(a, attr, rem) { + int type = nla_type(a); + struct nlattr *st_sample; + + switch (type) { + case OVS_SAMPLE_ATTR_PROBABILITY: + if (nla_put(skb, OVS_SAMPLE_ATTR_PROBABILITY, sizeof(u32), nla_data(a))) + return -EMSGSIZE; + break; + case OVS_SAMPLE_ATTR_ACTIONS: + st_sample = nla_nest_start(skb, OVS_SAMPLE_ATTR_ACTIONS); + if (!st_sample) + return -EMSGSIZE; + err = actions_to_attr(nla_data(a), nla_len(a), skb); + if (err) + return err; + nla_nest_end(skb, st_sample); + break; + } + } + + nla_nest_end(skb, start); + return err; +} + +static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) +{ + const struct nlattr *ovs_key = nla_data(a); + int key_type = nla_type(ovs_key); + struct nlattr *start; + int err; + + switch (key_type) { + case OVS_KEY_ATTR_IPV4_TUNNEL: + start = nla_nest_start(skb, OVS_ACTION_ATTR_SET); + if (!start) + return -EMSGSIZE; + + err = ipv4_tun_to_nlattr(skb, nla_data(ovs_key)); + if (err) + return err; + nla_nest_end(skb, start); + break; + default: + if (nla_put(skb, OVS_ACTION_ATTR_SET, nla_len(a), ovs_key)) + return -EMSGSIZE; + break; + } + + return 0; +} + +static int actions_to_attr(const struct nlattr *attr, int len, struct sk_buff *skb) +{ + const struct nlattr *a; + int rem, err; + + nla_for_each_attr(a, attr, len, rem) { + int type = nla_type(a); + + switch (type) { + case OVS_ACTION_ATTR_SET: + err = set_action_to_attr(a, skb); + if (err) + return err; + break; + + case OVS_ACTION_ATTR_SAMPLE: + err = sample_action_to_attr(a, skb); + if (err) + return err; + break; + default: + if (nla_put(skb, type, nla_len(a), nla_data(a))) + return -EMSGSIZE; + break; + } + } + + return 0; +} + /* Called with genl_lock. */ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, - struct sk_buff *skb, u32 pid, + struct sk_buff *skb, u32 portid, u32 seq, u32 flags, u8 cmd) { const int skb_orig_len = skb->len; const struct sw_flow_actions *sf_acts; + struct nlattr *start; struct ovs_flow_stats stats; struct ovs_header *ovs_header; struct nlattr *nla; @@ -873,7 +1064,7 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, sf_acts = rcu_dereference_protected(flow->sf_acts, lockdep_genl_is_held()); - ovs_header = genlmsg_put(skb, pid, seq, &dp_flow_genl_family, flags, cmd); + ovs_header = genlmsg_put(skb, portid, seq, &dp_flow_genl_family, flags, cmd); if (!ovs_header) return -EMSGSIZE; @@ -894,15 +1085,18 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, 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 @@ -914,10 +1108,19 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, * This can only fail for dump operations because the skb is always * properly sized for single flows. */ - err = nla_put(skb, OVS_FLOW_ATTR_ACTIONS, sf_acts->actions_len, - sf_acts->actions); - if (err < 0 && skb_orig_len) - goto error; + start = nla_nest_start(skb, OVS_FLOW_ATTR_ACTIONS); + if (start) { + err = actions_to_attr(sf_acts->actions, sf_acts->actions_len, skb); + if (!err) + nla_nest_end(skb, start); + else { + if (skb_orig_len) + goto error; + + nla_nest_cancel(skb, start); + } + } else if (skb_orig_len) + goto nla_put_failure; return genlmsg_end(skb, ovs_header); @@ -954,7 +1157,7 @@ static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow) static struct sk_buff *ovs_flow_cmd_build_info(struct sw_flow *flow, struct datapath *dp, - u32 pid, u32 seq, u8 cmd) + u32 portid, u32 seq, u8 cmd) { struct sk_buff *skb; int retval; @@ -963,7 +1166,7 @@ static struct sk_buff *ovs_flow_cmd_build_info(struct sw_flow *flow, if (!skb) return ERR_PTR(-ENOMEM); - retval = ovs_flow_cmd_fill_info(flow, dp, skb, pid, seq, 0, cmd); + retval = ovs_flow_cmd_fill_info(flow, dp, skb, portid, seq, 0, cmd); BUG_ON(retval < 0); return skb; } @@ -977,6 +1180,7 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) struct sk_buff *reply; struct datapath *dp; struct flow_table *table; + struct sw_flow_actions *acts = NULL; int error; int key_len; @@ -990,28 +1194,31 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) /* Validate actions. */ if (a[OVS_FLOW_ATTR_ACTIONS]) { - error = validate_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, 0); - if (error) + acts = ovs_flow_actions_alloc(nla_len(a[OVS_FLOW_ATTR_ACTIONS])); + error = PTR_ERR(acts); + if (IS_ERR(acts)) goto error; + + error = validate_and_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, 0, &acts); + if (error) + goto err_kfree; } else if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW) { error = -EINVAL; goto error; } - dp = get_dp(ovs_header->dp_ifindex); + dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); error = -ENODEV; if (!dp) - goto error; + goto err_kfree; table = genl_dereference(dp->table); flow = ovs_flow_tbl_lookup(table, &key, key_len); if (!flow) { - struct sw_flow_actions *acts; - /* Bail out if we're not allowed to create a new flow. */ error = -ENOENT; if (info->genlhdr->cmd == OVS_FLOW_CMD_SET) - goto error; + goto err_kfree; /* Expand table, if necessary, to make room. */ if (ovs_flow_tbl_need_to_expand(table)) { @@ -1029,29 +1236,21 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) flow = ovs_flow_alloc(); if (IS_ERR(flow)) { error = PTR_ERR(flow); - goto error; + goto err_kfree; } - flow->key = key; clear_stats(flow); - /* Obtain actions. */ - acts = ovs_flow_actions_alloc(a[OVS_FLOW_ATTR_ACTIONS]); - error = PTR_ERR(acts); - if (IS_ERR(acts)) - goto error_free_flow; rcu_assign_pointer(flow->sf_acts, acts); /* Put flow in bucket. */ - flow->hash = ovs_flow_hash(&key, key_len); - ovs_flow_tbl_insert(table, flow); + ovs_flow_tbl_insert(table, flow, &key, key_len); - reply = ovs_flow_cmd_build_info(flow, dp, info->snd_pid, + reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid, info->snd_seq, OVS_FLOW_CMD_NEW); } else { /* We found a matching flow. */ struct sw_flow_actions *old_acts; - struct nlattr *acts_attrs; /* Bail out if we're not allowed to modify an existing flow. * We accept NLM_F_CREATE in place of the intended NLM_F_EXCL @@ -1062,28 +1261,15 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) error = -EEXIST; if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW && info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) - goto error; + goto err_kfree; /* Update actions. */ old_acts = rcu_dereference_protected(flow->sf_acts, lockdep_genl_is_held()); - acts_attrs = a[OVS_FLOW_ATTR_ACTIONS]; - if (acts_attrs && - (old_acts->actions_len != nla_len(acts_attrs) || - memcmp(old_acts->actions, nla_data(acts_attrs), - old_acts->actions_len))) { - struct sw_flow_actions *new_acts; - - new_acts = ovs_flow_actions_alloc(acts_attrs); - error = PTR_ERR(new_acts); - if (IS_ERR(new_acts)) - goto error; - - rcu_assign_pointer(flow->sf_acts, new_acts); - ovs_flow_deferred_free_acts(old_acts); - } + rcu_assign_pointer(flow->sf_acts, acts); + ovs_flow_deferred_free_acts(old_acts); - reply = ovs_flow_cmd_build_info(flow, dp, info->snd_pid, + reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid, info->snd_seq, OVS_FLOW_CMD_NEW); /* Clear stats. */ @@ -1095,17 +1281,16 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) } if (!IS_ERR(reply)) - genl_notify(reply, genl_info_net(info), info->snd_pid, + genl_notify(reply, genl_info_net(info), info->snd_portid, ovs_dp_flow_multicast_group.id, info->nlhdr, GFP_KERNEL); else - netlink_set_err(INIT_NET_GENL_SOCK, 0, - ovs_dp_flow_multicast_group.id, - PTR_ERR(reply)); + netlink_set_err(GENL_SOCK(sock_net(skb->sk)), 0, + ovs_dp_flow_multicast_group.id, PTR_ERR(reply)); return 0; -error_free_flow: - ovs_flow_put(flow); +err_kfree: + kfree(acts); error: return error; } @@ -1128,7 +1313,7 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info) if (err) return err; - dp = get_dp(ovs_header->dp_ifindex); + dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); if (!dp) return -ENODEV; @@ -1137,7 +1322,7 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info) if (!flow) return -ENOENT; - reply = ovs_flow_cmd_build_info(flow, dp, info->snd_pid, + reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid, info->snd_seq, OVS_FLOW_CMD_NEW); if (IS_ERR(reply)) return PTR_ERR(reply); @@ -1157,16 +1342,17 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) int err; int key_len; + dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); + if (!dp) + return -ENODEV; + if (!a[OVS_FLOW_ATTR_KEY]) - return flush_flows(ovs_header->dp_ifindex); + return flush_flows(dp); + err = ovs_flow_from_nlattrs(&key, &key_len, a[OVS_FLOW_ATTR_KEY]); if (err) return err; - dp = get_dp(ovs_header->dp_ifindex); - if (!dp) - return -ENODEV; - table = genl_dereference(dp->table); flow = ovs_flow_tbl_lookup(table, &key, key_len); if (!flow) @@ -1178,13 +1364,13 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) ovs_flow_tbl_remove(table, flow); - err = ovs_flow_cmd_fill_info(flow, dp, reply, info->snd_pid, + err = ovs_flow_cmd_fill_info(flow, dp, reply, info->snd_portid, info->snd_seq, 0, OVS_FLOW_CMD_DEL); BUG_ON(err < 0); ovs_flow_deferred_free(flow); - genl_notify(reply, genl_info_net(info), info->snd_pid, + genl_notify(reply, genl_info_net(info), info->snd_portid, ovs_dp_flow_multicast_group.id, info->nlhdr, GFP_KERNEL); return 0; } @@ -1195,7 +1381,7 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) struct datapath *dp; struct flow_table *table; - dp = get_dp(ovs_header->dp_ifindex); + dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); if (!dp) return -ENODEV; @@ -1212,7 +1398,7 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) break; if (ovs_flow_cmd_fill_info(flow, dp, skb, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, OVS_FLOW_CMD_NEW) < 0) break; @@ -1259,7 +1445,8 @@ static struct genl_family dp_datapath_genl_family = { .hdrsize = sizeof(struct ovs_header), .name = OVS_DATAPATH_FAMILY, .version = OVS_DATAPATH_VERSION, - .maxattr = OVS_DP_ATTR_MAX + .maxattr = OVS_DP_ATTR_MAX, + SET_NETNSOK }; static struct genl_multicast_group ovs_dp_datapath_multicast_group = { @@ -1267,13 +1454,13 @@ static struct genl_multicast_group ovs_dp_datapath_multicast_group = { }; static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, - u32 pid, u32 seq, u32 flags, u8 cmd) + u32 portid, u32 seq, u32 flags, u8 cmd) { struct ovs_header *ovs_header; struct ovs_dp_stats dp_stats; int err; - ovs_header = genlmsg_put(skb, pid, seq, &dp_datapath_genl_family, + ovs_header = genlmsg_put(skb, portid, seq, &dp_datapath_genl_family, flags, cmd); if (!ovs_header) goto error; @@ -1287,7 +1474,8 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, 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); @@ -1297,7 +1485,7 @@ error: return -EMSGSIZE; } -static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp, u32 pid, +static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp, u32 portid, u32 seq, u8 cmd) { struct sk_buff *skb; @@ -1307,7 +1495,7 @@ static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp, u32 pid, if (!skb) return ERR_PTR(-ENOMEM); - retval = ovs_dp_cmd_fill_info(dp, skb, pid, seq, 0, cmd); + retval = ovs_dp_cmd_fill_info(dp, skb, portid, seq, 0, cmd); if (retval < 0) { kfree_skb(skb); return ERR_PTR(retval); @@ -1321,18 +1509,19 @@ static int ovs_dp_cmd_validate(struct nlattr *a[OVS_DP_ATTR_MAX + 1]) } /* Called with genl_mutex and optionally with RTNL lock also. */ -static struct datapath *lookup_datapath(struct ovs_header *ovs_header, +static struct datapath *lookup_datapath(struct net *net, + struct ovs_header *ovs_header, struct nlattr *a[OVS_DP_ATTR_MAX + 1]) { struct datapath *dp; if (!a[OVS_DP_ATTR_NAME]) - dp = get_dp(ovs_header->dp_ifindex); + dp = get_dp(net, ovs_header->dp_ifindex); else { struct vport *vport; rcu_read_lock(); - vport = ovs_vport_locate(nla_data(a[OVS_DP_ATTR_NAME])); + vport = ovs_vport_locate(net, nla_data(a[OVS_DP_ATTR_NAME])); dp = vport && vport->port_no == OVSP_LOCAL ? vport->dp : NULL; rcu_read_unlock(); } @@ -1346,7 +1535,8 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) struct sk_buff *reply; struct datapath *dp; struct vport *vport; - int err; + struct ovs_net *ovs_net; + int err, i; err = -EINVAL; if (!a[OVS_DP_ATTR_NAME] || !a[OVS_DP_ATTR_UPCALL_PID]) @@ -1357,20 +1547,13 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) goto err; rtnl_lock(); - err = -ENODEV; - if (!try_module_get(THIS_MODULE)) - goto err_unlock_rtnl; err = -ENOMEM; dp = kzalloc(sizeof(*dp), GFP_KERNEL); if (dp == NULL) - goto err_put_module; - INIT_LIST_HEAD(&dp->port_list); + goto err_unlock_rtnl; - /* Initialize kobject for bridge. This will be added as - * /sys/class/net//brif later, if sysfs is enabled. */ - dp->ifobj.kset = NULL; - kobject_init(&dp->ifobj, &dp_ktype); + ovs_dp_set_net(dp, hold_net(sock_net(skb->sk))); /* Allocate table. */ err = -ENOMEM; @@ -1384,13 +1567,23 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) goto err_destroy_table; } + 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; parms.options = NULL; parms.dp = dp; parms.port_no = OVSP_LOCAL; - parms.upcall_pid = nla_get_u32(a[OVS_DP_ATTR_UPCALL_PID]); + parms.upcall_portid = nla_get_u32(a[OVS_DP_ATTR_UPCALL_PID]); vport = new_vport(&parms); if (IS_ERR(vport)) { @@ -1398,71 +1591,60 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) if (err == -EBUSY) err = -EEXIST; - goto err_destroy_percpu; + goto err_destroy_ports_array; } - reply = ovs_dp_cmd_build_info(dp, info->snd_pid, + reply = ovs_dp_cmd_build_info(dp, info->snd_portid, info->snd_seq, OVS_DP_CMD_NEW); err = PTR_ERR(reply); if (IS_ERR(reply)) goto err_destroy_local_port; - list_add_tail(&dp->list_node, &dps); - ovs_dp_sysfs_add_dp(dp); + ovs_net = net_generic(ovs_dp_get_net(dp), ovs_net_id); + list_add_tail(&dp->list_node, &ovs_net->dps); rtnl_unlock(); - genl_notify(reply, genl_info_net(info), info->snd_pid, + genl_notify(reply, genl_info_net(info), info->snd_portid, ovs_dp_datapath_multicast_group.id, info->nlhdr, GFP_KERNEL); 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: ovs_flow_tbl_destroy(genl_dereference(dp->table)); err_free_dp: + release_net(ovs_dp_get_net(dp)); kfree(dp); -err_put_module: - module_put(THIS_MODULE); err_unlock_rtnl: rtnl_unlock(); err: return err; } -static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info) +/* Called with genl_mutex. */ +static void __dp_destroy(struct datapath *dp) { - struct vport *vport, *next_vport; - struct sk_buff *reply; - struct datapath *dp; - int err; - - err = ovs_dp_cmd_validate(info->attrs); - if (err) - goto exit; + int i; rtnl_lock(); - dp = lookup_datapath(info->userhdr, info->attrs); - err = PTR_ERR(dp); - if (IS_ERR(dp)) - goto exit_unlock; - reply = ovs_dp_cmd_build_info(dp, info->snd_pid, - info->snd_seq, OVS_DP_CMD_DEL); - err = PTR_ERR(reply); - if (IS_ERR(reply)) - goto exit_unlock; + for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { + struct vport *vport; + struct hlist_node *node, *n; - list_for_each_entry_safe(vport, next_vport, &dp->port_list, node) - if (vport->port_no != OVSP_LOCAL) - ovs_dp_detach_port(vport); + 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 @@ -1472,18 +1654,36 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info) rtnl_unlock(); call_rcu(&dp->rcu, destroy_dp_rcu); - module_put(THIS_MODULE); +} + +static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info) +{ + struct sk_buff *reply; + struct datapath *dp; + int err; + + err = ovs_dp_cmd_validate(info->attrs); + if (err) + return err; + + dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); + err = PTR_ERR(dp); + if (IS_ERR(dp)) + return err; + + reply = ovs_dp_cmd_build_info(dp, info->snd_portid, + info->snd_seq, OVS_DP_CMD_DEL); + err = PTR_ERR(reply); + if (IS_ERR(reply)) + return err; + + __dp_destroy(dp); - genl_notify(reply, genl_info_net(info), info->snd_pid, + genl_notify(reply, genl_info_net(info), info->snd_portid, ovs_dp_datapath_multicast_group.id, info->nlhdr, GFP_KERNEL); return 0; - -exit_unlock: - rtnl_unlock(); -exit: - return err; } static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info) @@ -1496,20 +1696,20 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info) if (err) return err; - dp = lookup_datapath(info->userhdr, info->attrs); + dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); if (IS_ERR(dp)) return PTR_ERR(dp); - reply = ovs_dp_cmd_build_info(dp, info->snd_pid, + reply = ovs_dp_cmd_build_info(dp, info->snd_portid, info->snd_seq, OVS_DP_CMD_NEW); if (IS_ERR(reply)) { err = PTR_ERR(reply); - netlink_set_err(INIT_NET_GENL_SOCK, 0, + netlink_set_err(GENL_SOCK(sock_net(skb->sk)), 0, ovs_dp_datapath_multicast_group.id, err); return 0; } - genl_notify(reply, genl_info_net(info), info->snd_pid, + genl_notify(reply, genl_info_net(info), info->snd_portid, ovs_dp_datapath_multicast_group.id, info->nlhdr, GFP_KERNEL); @@ -1526,11 +1726,11 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info) if (err) return err; - dp = lookup_datapath(info->userhdr, info->attrs); + dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); if (IS_ERR(dp)) return PTR_ERR(dp); - reply = ovs_dp_cmd_build_info(dp, info->snd_pid, + reply = ovs_dp_cmd_build_info(dp, info->snd_portid, info->snd_seq, OVS_DP_CMD_NEW); if (IS_ERR(reply)) return PTR_ERR(reply); @@ -1540,14 +1740,14 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info) static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) { + struct ovs_net *ovs_net = net_generic(sock_net(skb->sk), ovs_net_id); struct datapath *dp; int skip = cb->args[0]; int i = 0; - list_for_each_entry(dp, &dps, list_node) { - if (i < skip) - continue; - if (ovs_dp_cmd_fill_info(dp, skb, NETLINK_CB(cb->skb).pid, + list_for_each_entry(dp, &ovs_net->dps, list_node) { + if (i >= skip && + ovs_dp_cmd_fill_info(dp, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, OVS_DP_CMD_NEW) < 0) break; @@ -1587,10 +1787,8 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { #ifdef HAVE_NLA_NUL_STRING [OVS_VPORT_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, [OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) }, - [OVS_VPORT_ATTR_ADDRESS] = { .len = ETH_ALEN }, #else [OVS_VPORT_ATTR_STATS] = { .minlen = sizeof(struct ovs_vport_stats) }, - [OVS_VPORT_ATTR_ADDRESS] = { .minlen = ETH_ALEN }, #endif [OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 }, [OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 }, @@ -1603,7 +1801,8 @@ static struct genl_family dp_vport_genl_family = { .hdrsize = sizeof(struct ovs_header), .name = OVS_VPORT_FAMILY, .version = OVS_VPORT_VERSION, - .maxattr = OVS_VPORT_ATTR_MAX + .maxattr = OVS_VPORT_ATTR_MAX, + SET_NETNSOK }; struct genl_multicast_group ovs_dp_vport_multicast_group = { @@ -1612,30 +1811,29 @@ struct genl_multicast_group ovs_dp_vport_multicast_group = { /* Called with RTNL lock or RCU read lock. */ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, - u32 pid, u32 seq, u32 flags, u8 cmd) + u32 portid, u32 seq, u32 flags, u8 cmd) { struct ovs_header *ovs_header; struct ovs_vport_stats vport_stats; int err; - ovs_header = genlmsg_put(skb, pid, seq, &dp_vport_genl_family, + ovs_header = genlmsg_put(skb, portid, seq, &dp_vport_genl_family, flags, cmd); if (!ovs_header) return -EMSGSIZE; 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_portid)) + 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); - - NLA_PUT(skb, OVS_VPORT_ATTR_ADDRESS, ETH_ALEN, - vport->ops->get_addr(vport)); + if (nla_put(skb, OVS_VPORT_ATTR_STATS, sizeof(struct ovs_vport_stats), + &vport_stats)) + goto nla_put_failure; err = ovs_vport_get_options(vport, skb); if (err == -EMSGSIZE) @@ -1651,7 +1849,7 @@ error: } /* Called with RTNL lock or RCU read lock. */ -struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 pid, +struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid, u32 seq, u8 cmd) { struct sk_buff *skb; @@ -1661,7 +1859,7 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 pid, if (!skb) return ERR_PTR(-ENOMEM); - retval = ovs_vport_cmd_fill_info(vport, skb, pid, seq, 0, cmd); + retval = ovs_vport_cmd_fill_info(vport, skb, portid, seq, 0, cmd); if (retval < 0) { kfree_skb(skb); return ERR_PTR(retval); @@ -1675,16 +1873,20 @@ static int ovs_vport_cmd_validate(struct nlattr *a[OVS_VPORT_ATTR_MAX + 1]) } /* Called with RTNL lock or RCU read lock. */ -static struct vport *lookup_vport(struct ovs_header *ovs_header, +static struct vport *lookup_vport(struct net *net, + struct ovs_header *ovs_header, struct nlattr *a[OVS_VPORT_ATTR_MAX + 1]) { struct datapath *dp; struct vport *vport; if (a[OVS_VPORT_ATTR_NAME]) { - vport = ovs_vport_locate(nla_data(a[OVS_VPORT_ATTR_NAME])); + 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]); @@ -1692,33 +1894,18 @@ static struct vport *lookup_vport(struct ovs_header *ovs_header, if (port_no >= DP_MAX_PORTS) return ERR_PTR(-EFBIG); - dp = get_dp(ovs_header->dp_ifindex); + dp = get_dp(net, ovs_header->dp_ifindex); 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 ERR_PTR(-ENODEV); return vport; } else return ERR_PTR(-EINVAL); } -/* Called with RTNL lock. */ -static int change_vport(struct vport *vport, - struct nlattr *a[OVS_VPORT_ATTR_MAX + 1]) -{ - int err = 0; - - if (a[OVS_VPORT_ATTR_STATS]) - ovs_vport_set_stats(vport, nla_data(a[OVS_VPORT_ATTR_STATS])); - - if (a[OVS_VPORT_ATTR_ADDRESS]) - err = ovs_vport_set_addr(vport, nla_data(a[OVS_VPORT_ATTR_ADDRESS])); - - return err; -} - static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; @@ -1740,7 +1927,7 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) goto exit; rtnl_lock(); - dp = get_dp(ovs_header->dp_ifindex); + dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); err = -ENODEV; if (!dp) goto exit_unlock; @@ -1752,7 +1939,7 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) 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; @@ -1762,7 +1949,7 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) err = -EFBIG; goto exit_unlock; } - vport = rtnl_dereference(dp->ports[port_no]); + vport = ovs_vport_rtnl(dp, port_no); if (!vport) break; } @@ -1773,31 +1960,26 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) parms.options = a[OVS_VPORT_ATTR_OPTIONS]; parms.dp = dp; parms.port_no = port_no; - parms.upcall_pid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]); + parms.upcall_portid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]); vport = new_vport(&parms); err = PTR_ERR(vport); if (IS_ERR(vport)) goto exit_unlock; - ovs_dp_sysfs_add_if(vport); + if (a[OVS_VPORT_ATTR_STATS]) + ovs_vport_set_stats(vport, nla_data(a[OVS_VPORT_ATTR_STATS])); - err = change_vport(vport, a); - if (!err) { - 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); - } - if (err) { + reply = ovs_vport_cmd_build_info(vport, info->snd_portid, info->snd_seq, + OVS_VPORT_CMD_NEW); + if (IS_ERR(reply)) { + err = PTR_ERR(reply); ovs_dp_detach_port(vport); goto exit_unlock; } - genl_notify(reply, genl_info_net(info), info->snd_pid, + genl_notify(reply, genl_info_net(info), info->snd_portid, ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL); - exit_unlock: rtnl_unlock(); exit: @@ -1816,7 +1998,7 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) goto exit; rtnl_lock(); - vport = lookup_vport(info->userhdr, a); + vport = lookup_vport(sock_net(skb->sk), info->userhdr, a); err = PTR_ERR(vport); if (IS_ERR(vport)) goto exit_unlock; @@ -1828,21 +2010,24 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) if (!err && a[OVS_VPORT_ATTR_OPTIONS]) err = ovs_vport_set_options(vport, a[OVS_VPORT_ATTR_OPTIONS]); - if (!err) - err = change_vport(vport, a); - if (!err && a[OVS_VPORT_ATTR_UPCALL_PID]) - vport->upcall_pid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]); + if (err) + goto exit_unlock; - reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq, - OVS_VPORT_CMD_NEW); + if (a[OVS_VPORT_ATTR_STATS]) + ovs_vport_set_stats(vport, nla_data(a[OVS_VPORT_ATTR_STATS])); + + if (a[OVS_VPORT_ATTR_UPCALL_PID]) + vport->upcall_portid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]); + + reply = ovs_vport_cmd_build_info(vport, info->snd_portid, + info->snd_seq, OVS_VPORT_CMD_NEW); if (IS_ERR(reply)) { - err = PTR_ERR(reply); - netlink_set_err(INIT_NET_GENL_SOCK, 0, - ovs_dp_vport_multicast_group.id, err); - return 0; + netlink_set_err(GENL_SOCK(sock_net(skb->sk)), 0, + ovs_dp_vport_multicast_group.id, PTR_ERR(reply)); + goto exit_unlock; } - genl_notify(reply, genl_info_net(info), info->snd_pid, + genl_notify(reply, genl_info_net(info), info->snd_portid, ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL); exit_unlock: @@ -1863,7 +2048,7 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) goto exit; rtnl_lock(); - vport = lookup_vport(info->userhdr, a); + vport = lookup_vport(sock_net(skb->sk), info->userhdr, a); err = PTR_ERR(vport); if (IS_ERR(vport)) goto exit_unlock; @@ -1873,15 +2058,16 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) goto exit_unlock; } - reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq, - OVS_VPORT_CMD_DEL); + reply = ovs_vport_cmd_build_info(vport, info->snd_portid, + info->snd_seq, OVS_VPORT_CMD_DEL); err = PTR_ERR(reply); if (IS_ERR(reply)) goto exit_unlock; + err = 0; ovs_dp_detach_port(vport); - genl_notify(reply, genl_info_net(info), info->snd_pid, + genl_notify(reply, genl_info_net(info), info->snd_portid, ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL); exit_unlock: @@ -1903,13 +2089,13 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info) goto exit; rcu_read_lock(); - vport = lookup_vport(ovs_header, a); + vport = lookup_vport(sock_net(skb->sk), ovs_header, a); err = PTR_ERR(vport); if (IS_ERR(vport)) goto exit_unlock; - reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq, - OVS_VPORT_CMD_NEW); + reply = ovs_vport_cmd_build_info(vport, info->snd_portid, + info->snd_seq, OVS_VPORT_CMD_NEW); err = PTR_ERR(reply); if (IS_ERR(reply)) goto exit_unlock; @@ -1928,32 +2114,39 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) { 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(ovs_header->dp_ifindex); + 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).portid, + 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[] = { @@ -2040,20 +2233,90 @@ error: return err; } +static int __rehash_flow_table(void *dummy) +{ + struct datapath *dp; + struct net *net; + + rtnl_lock(); + for_each_net(net) { + struct ovs_net *ovs_net = net_generic(net, ovs_net_id); + + list_for_each_entry(dp, &ovs_net->dps, list_node) { + struct flow_table *old_table = genl_dereference(dp->table); + struct flow_table *new_table; + + new_table = ovs_flow_tbl_rehash(old_table); + if (!IS_ERR(new_table)) { + rcu_assign_pointer(dp->table, new_table); + ovs_flow_tbl_deferred_destroy(old_table); + } + } + } + rtnl_unlock(); + return 0; +} + +static void rehash_flow_table(struct work_struct *work) +{ + genl_exec(__rehash_flow_table, NULL); + schedule_delayed_work(&rehash_flow_wq, REHASH_FLOW_INTERVAL); +} + +static int dp_destroy_all(void *data) +{ + struct datapath *dp, *dp_next; + struct ovs_net *ovs_net = data; + + list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node) + __dp_destroy(dp); + + return 0; +} + +static int __net_init ovs_init_net(struct net *net) +{ + struct ovs_net *ovs_net = net_generic(net, ovs_net_id); + + INIT_LIST_HEAD(&ovs_net->dps); + return 0; +} + +static void __net_exit ovs_exit_net(struct net *net) +{ + struct ovs_net *ovs_net = net_generic(net, ovs_net_id); + + genl_exec(dp_destroy_all, ovs_net); +} + +static struct pernet_operations ovs_net_ops = { + .init = ovs_init_net, + .exit = ovs_exit_net, + .id = &ovs_net_id, + .size = sizeof(struct ovs_net), +}; + static int __init dp_init(void) { - struct sk_buff *dummy_skb; int err; - BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > sizeof(dummy_skb->cb)); + BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > FIELD_SIZEOF(struct sk_buff, cb)); pr_info("Open vSwitch switching datapath %s, built "__DATE__" "__TIME__"\n", - VERSION BUILDNR); + VERSION); - err = ovs_tnl_init(); + err = genl_exec_init(); if (err) goto error; + err = ovs_workqueues_init(); + if (err) + goto error_genl_exec; + + err = ovs_tnl_init(); + if (err) + goto error_wq; + err = ovs_flow_init(); if (err) goto error_tnl_exit; @@ -2062,36 +2325,52 @@ static int __init dp_init(void) if (err) goto error_flow_exit; - err = register_netdevice_notifier(&ovs_dp_device_notifier); + err = register_pernet_device(&ovs_net_ops); if (err) goto error_vport_exit; + err = register_netdevice_notifier(&ovs_dp_device_notifier); + if (err) + goto error_netns_exit; + err = dp_register_genl(); if (err < 0) goto error_unreg_notifier; + schedule_delayed_work(&rehash_flow_wq, REHASH_FLOW_INTERVAL); + return 0; error_unreg_notifier: unregister_netdevice_notifier(&ovs_dp_device_notifier); +error_netns_exit: + unregister_pernet_device(&ovs_net_ops); error_vport_exit: ovs_vport_exit(); error_flow_exit: ovs_flow_exit(); error_tnl_exit: ovs_tnl_exit(); +error_wq: + ovs_workqueues_exit(); +error_genl_exec: + genl_exec_exit(); error: return err; } static void dp_cleanup(void) { - rcu_barrier(); + cancel_delayed_work_sync(&rehash_flow_wq); dp_unregister_genl(ARRAY_SIZE(dp_genl_families)); unregister_netdevice_notifier(&ovs_dp_device_notifier); + unregister_pernet_device(&ovs_net_ops); + rcu_barrier(); ovs_vport_exit(); ovs_flow_exit(); ovs_tnl_exit(); + ovs_workqueues_exit(); + genl_exec_exit(); } module_init(dp_init); @@ -2099,3 +2378,4 @@ module_exit(dp_cleanup); MODULE_DESCRIPTION("Open vSwitch switching datapath"); MODULE_LICENSE("GPL"); +MODULE_VERSION(VERSION);