summaryrefslogtreecommitdiff
path: root/net/openvswitch
diff options
context:
space:
mode:
Diffstat (limited to 'net/openvswitch')
-rw-r--r--net/openvswitch/Kconfig11
-rw-r--r--net/openvswitch/Makefile4
-rw-r--r--net/openvswitch/actions.c286
-rw-r--r--net/openvswitch/datapath.c1089
-rw-r--r--net/openvswitch/datapath.h37
-rw-r--r--net/openvswitch/flow.c290
-rw-r--r--net/openvswitch/flow.h117
-rw-r--r--net/openvswitch/flow_netlink.c434
-rw-r--r--net/openvswitch/flow_netlink.h4
-rw-r--r--net/openvswitch/flow_table.c205
-rw-r--r--net/openvswitch/flow_table.h11
-rw-r--r--net/openvswitch/vport-geneve.c235
-rw-r--r--net/openvswitch/vport-gre.c56
-rw-r--r--net/openvswitch/vport-internal_dev.c26
-rw-r--r--net/openvswitch/vport-internal_dev.h2
-rw-r--r--net/openvswitch/vport-vxlan.c37
-rw-r--r--net/openvswitch/vport.c176
-rw-r--r--net/openvswitch/vport.h50
18 files changed, 2166 insertions, 904 deletions
diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig
index 6ecf491ad509..ba3bb8203b99 100644
--- a/net/openvswitch/Kconfig
+++ b/net/openvswitch/Kconfig
@@ -54,3 +54,14 @@ config OPENVSWITCH_VXLAN
Say N to exclude this support and reduce the binary size.
If unsure, say Y.
+
+config OPENVSWITCH_GENEVE
+ bool "Open vSwitch Geneve tunneling support"
+ depends on INET
+ depends on OPENVSWITCH
+ depends on GENEVE && !(OPENVSWITCH=y && GENEVE=m)
+ default y
+ ---help---
+ If you say Y here, then the Open vSwitch will be able create geneve vport.
+
+ Say N to exclude this support and reduce the binary size.
diff --git a/net/openvswitch/Makefile b/net/openvswitch/Makefile
index 3591cb5dae91..9a33a273c375 100644
--- a/net/openvswitch/Makefile
+++ b/net/openvswitch/Makefile
@@ -15,6 +15,10 @@ openvswitch-y := \
vport-internal_dev.o \
vport-netdev.o
+ifneq ($(CONFIG_OPENVSWITCH_GENEVE),)
+openvswitch-y += vport-geneve.o
+endif
+
ifneq ($(CONFIG_OPENVSWITCH_VXLAN),)
openvswitch-y += vport-vxlan.o
endif
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 65cfaa816075..006886dbee36 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2007-2013 Nicira, Inc.
+ * Copyright (c) 2007-2014 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
@@ -35,13 +35,83 @@
#include <net/sctp/checksum.h>
#include "datapath.h"
+#include "flow.h"
#include "vport.h"
static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
- const struct nlattr *attr, int len, bool keep_skb);
+ struct sw_flow_key *key,
+ const struct nlattr *attr, int len);
+
+struct deferred_action {
+ struct sk_buff *skb;
+ const struct nlattr *actions;
+
+ /* Store pkt_key clone when creating deferred action. */
+ struct sw_flow_key pkt_key;
+};
+
+#define DEFERRED_ACTION_FIFO_SIZE 10
+struct action_fifo {
+ int head;
+ int tail;
+ /* Deferred action fifo queue storage. */
+ struct deferred_action fifo[DEFERRED_ACTION_FIFO_SIZE];
+};
+
+static struct action_fifo __percpu *action_fifos;
+static DEFINE_PER_CPU(int, exec_actions_level);
+
+static void action_fifo_init(struct action_fifo *fifo)
+{
+ fifo->head = 0;
+ fifo->tail = 0;
+}
+
+static bool action_fifo_is_empty(struct action_fifo *fifo)
+{
+ return (fifo->head == fifo->tail);
+}
+
+static struct deferred_action *action_fifo_get(struct action_fifo *fifo)
+{
+ if (action_fifo_is_empty(fifo))
+ return NULL;
+
+ return &fifo->fifo[fifo->tail++];
+}
+
+static struct deferred_action *action_fifo_put(struct action_fifo *fifo)
+{
+ if (fifo->head >= DEFERRED_ACTION_FIFO_SIZE - 1)
+ return NULL;
+
+ return &fifo->fifo[fifo->head++];
+}
+
+/* Return true if fifo is not full */
+static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
+ struct sw_flow_key *key,
+ const struct nlattr *attr)
+{
+ struct action_fifo *fifo;
+ struct deferred_action *da;
+
+ fifo = this_cpu_ptr(action_fifos);
+ da = action_fifo_put(fifo);
+ if (da) {
+ da->skb = skb;
+ da->actions = attr;
+ da->pkt_key = *key;
+ }
+
+ return da;
+}
static int make_writable(struct sk_buff *skb, int write_len)
{
+ if (!pskb_may_pull(skb, write_len))
+ return -ENOMEM;
+
if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
return 0;
@@ -70,6 +140,8 @@ static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
vlan_set_encap_proto(skb, vhdr);
skb->mac_header += VLAN_HLEN;
+ if (skb_network_offset(skb) < ETH_HLEN)
+ skb_set_network_header(skb, ETH_HLEN);
skb_reset_mac_len(skb);
return 0;
@@ -134,8 +206,8 @@ static int set_eth_addr(struct sk_buff *skb,
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
- memcpy(eth_hdr(skb)->h_source, eth_key->eth_src, ETH_ALEN);
- memcpy(eth_hdr(skb)->h_dest, eth_key->eth_dst, ETH_ALEN);
+ ether_addr_copy(eth_hdr(skb)->h_source, eth_key->eth_src);
+ ether_addr_copy(eth_hdr(skb)->h_dest, eth_key->eth_dst);
ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
@@ -165,7 +237,7 @@ static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
}
csum_replace4(&nh->check, *addr, new_addr);
- skb->rxhash = 0;
+ skb_clear_hash(skb);
*addr = new_addr;
}
@@ -199,7 +271,7 @@ static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto,
if (recalculate_csum)
update_ipv6_checksum(skb, l4_proto, addr, new_addr);
- skb->rxhash = 0;
+ skb_clear_hash(skb);
memcpy(addr, new_addr, sizeof(__be32[4]));
}
@@ -296,7 +368,7 @@ static void set_tp_port(struct sk_buff *skb, __be16 *port,
{
inet_proto_csum_replace2(check, skb, *port, new_port, 0);
*port = new_port;
- skb->rxhash = 0;
+ skb_clear_hash(skb);
}
static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port)
@@ -310,7 +382,7 @@ static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port)
uh->check = CSUM_MANGLED_0;
} else {
*port = new_port;
- skb->rxhash = 0;
+ skb_clear_hash(skb);
}
}
@@ -381,7 +453,7 @@ static int set_sctp(struct sk_buff *skb,
/* Carry any checksum errors through. */
sh->checksum = old_csum ^ old_correct_csum ^ new_csum;
- skb->rxhash = 0;
+ skb_clear_hash(skb);
}
return 0;
@@ -405,16 +477,14 @@ static int do_output(struct datapath *dp, struct sk_buff *skb, int out_port)
}
static int output_userspace(struct datapath *dp, struct sk_buff *skb,
- const struct nlattr *attr)
+ struct sw_flow_key *key, const struct nlattr *attr)
{
struct dp_upcall_info upcall;
const struct nlattr *a;
int rem;
- BUG_ON(!OVS_CB(skb)->pkt_key);
-
upcall.cmd = OVS_PACKET_CMD_ACTION;
- upcall.key = OVS_CB(skb)->pkt_key;
+ upcall.key = key;
upcall.userdata = NULL;
upcall.portid = 0;
@@ -434,8 +504,13 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
return ovs_dp_upcall(dp, skb, &upcall);
}
+static bool last_action(const struct nlattr *a, int rem)
+{
+ return a->nla_len == rem;
+}
+
static int sample(struct datapath *dp, struct sk_buff *skb,
- const struct nlattr *attr)
+ struct sw_flow_key *key, const struct nlattr *attr)
{
const struct nlattr *acts_list = NULL;
const struct nlattr *a;
@@ -445,7 +520,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
a = nla_next(a, &rem)) {
switch (nla_type(a)) {
case OVS_SAMPLE_ATTR_PROBABILITY:
- if (net_random() >= nla_get_u32(a))
+ if (prandom_u32() >= nla_get_u32(a))
return 0;
break;
@@ -455,8 +530,50 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
}
}
- return do_execute_actions(dp, skb, nla_data(acts_list),
- nla_len(acts_list), true);
+ rem = nla_len(acts_list);
+ a = nla_data(acts_list);
+
+ /* Actions list is empty, do nothing */
+ if (unlikely(!rem))
+ return 0;
+
+ /* The only known usage of sample action is having a single user-space
+ * action. Treat this usage as a special case.
+ * The output_userspace() should clone the skb to be sent to the
+ * user space. This skb will be consumed by its caller.
+ */
+ if (likely(nla_type(a) == OVS_ACTION_ATTR_USERSPACE &&
+ last_action(a, rem)))
+ return output_userspace(dp, skb, key, a);
+
+ skb = skb_clone(skb, GFP_ATOMIC);
+ if (!skb)
+ /* Skip the sample action when out of memory. */
+ return 0;
+
+ if (!add_deferred_actions(skb, key, a)) {
+ if (net_ratelimit())
+ pr_warn("%s: deferred actions limit reached, dropping sample action\n",
+ ovs_dp_name(dp));
+
+ kfree_skb(skb);
+ }
+ return 0;
+}
+
+static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key,
+ const struct nlattr *attr)
+{
+ struct ovs_action_hash *hash_act = nla_data(attr);
+ u32 hash = 0;
+
+ /* OVS_HASH_ALG_L4 is the only possible hash algorithm. */
+ hash = skb_get_hash(skb);
+ hash = jhash_1word(hash, hash_act->hash_basis);
+ if (!hash)
+ hash = 0x1;
+
+ key->ovs_flow_hash = hash;
}
static int execute_set_action(struct sk_buff *skb,
@@ -473,8 +590,8 @@ static int execute_set_action(struct sk_buff *skb,
skb->mark = nla_get_u32(nested_attr);
break;
- case OVS_KEY_ATTR_IPV4_TUNNEL:
- OVS_CB(skb)->tun_key = nla_data(nested_attr);
+ case OVS_KEY_ATTR_TUNNEL_INFO:
+ OVS_CB(skb)->egress_tun_info = nla_data(nested_attr);
break;
case OVS_KEY_ATTR_ETHERNET:
@@ -505,9 +622,48 @@ static int execute_set_action(struct sk_buff *skb,
return err;
}
+static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
+ struct sw_flow_key *key,
+ const struct nlattr *a, int rem)
+{
+ struct deferred_action *da;
+ int err;
+
+ err = ovs_flow_key_update(skb, key);
+ if (err)
+ return err;
+
+ if (!last_action(a, rem)) {
+ /* Recirc action is the not the last action
+ * of the action list, need to clone the skb.
+ */
+ skb = skb_clone(skb, GFP_ATOMIC);
+
+ /* Skip the recirc action when out of memory, but
+ * continue on with the rest of the action list.
+ */
+ if (!skb)
+ return 0;
+ }
+
+ da = add_deferred_actions(skb, key, NULL);
+ if (da) {
+ da->pkt_key.recirc_id = nla_get_u32(a);
+ } else {
+ kfree_skb(skb);
+
+ if (net_ratelimit())
+ pr_warn("%s: deferred action limit reached, drop recirc action\n",
+ ovs_dp_name(dp));
+ }
+
+ return 0;
+}
+
/* Execute a list of actions against 'skb'. */
static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
- const struct nlattr *attr, int len, bool keep_skb)
+ struct sw_flow_key *key,
+ const struct nlattr *attr, int len)
{
/* Every output action needs a separate clone of 'skb', but the common
* case is just a single output action, so that doing a clone and
@@ -532,7 +688,11 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
break;
case OVS_ACTION_ATTR_USERSPACE:
- output_userspace(dp, skb, a);
+ output_userspace(dp, skb, key, a);
+ break;
+
+ case OVS_ACTION_ATTR_HASH:
+ execute_hash(skb, key, a);
break;
case OVS_ACTION_ATTR_PUSH_VLAN:
@@ -545,12 +705,25 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
err = pop_vlan(skb);
break;
+ case OVS_ACTION_ATTR_RECIRC:
+ err = execute_recirc(dp, skb, key, a, rem);
+ if (last_action(a, rem)) {
+ /* If this is the last action, the skb has
+ * been consumed or freed.
+ * Return immediately.
+ */
+ return err;
+ }
+ break;
+
case OVS_ACTION_ATTR_SET:
err = execute_set_action(skb, nla_data(a));
break;
case OVS_ACTION_ATTR_SAMPLE:
- err = sample(dp, skb, a);
+ err = sample(dp, skb, key, a);
+ if (unlikely(err)) /* skb already freed. */
+ return err;
break;
}
@@ -560,23 +733,72 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
}
}
- if (prev_port != -1) {
- if (keep_skb)
- skb = skb_clone(skb, GFP_ATOMIC);
-
+ if (prev_port != -1)
do_output(dp, skb, prev_port);
- } else if (!keep_skb)
+ else
consume_skb(skb);
return 0;
}
+static void process_deferred_actions(struct datapath *dp)
+{
+ struct action_fifo *fifo = this_cpu_ptr(action_fifos);
+
+ /* Do not touch the FIFO in case there is no deferred actions. */
+ if (action_fifo_is_empty(fifo))
+ return;
+
+ /* Finishing executing all deferred actions. */
+ do {
+ struct deferred_action *da = action_fifo_get(fifo);
+ struct sk_buff *skb = da->skb;
+ struct sw_flow_key *key = &da->pkt_key;
+ const struct nlattr *actions = da->actions;
+
+ if (actions)
+ do_execute_actions(dp, skb, key, actions,
+ nla_len(actions));
+ else
+ ovs_dp_process_packet(skb, key);
+ } while (!action_fifo_is_empty(fifo));
+
+ /* Reset FIFO for the next packet. */
+ action_fifo_init(fifo);
+}
+
/* Execute a list of actions against 'skb'. */
-int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb)
+int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
+ struct sw_flow_key *key)
{
- struct sw_flow_actions *acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts);
+ int level = this_cpu_read(exec_actions_level);
+ struct sw_flow_actions *acts;
+ int err;
+
+ acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts);
+
+ this_cpu_inc(exec_actions_level);
+ OVS_CB(skb)->egress_tun_info = NULL;
+ err = do_execute_actions(dp, skb, key,
+ acts->actions, acts->actions_len);
+
+ if (!level)
+ process_deferred_actions(dp);
- OVS_CB(skb)->tun_key = NULL;
- return do_execute_actions(dp, skb, acts->actions,
- acts->actions_len, false);
+ this_cpu_dec(exec_actions_level);
+ return err;
+}
+
+int action_fifos_init(void)
+{
+ action_fifos = alloc_percpu(struct action_fifo);
+ if (!action_fifos)
+ return -ENOMEM;
+
+ return 0;
+}
+
+void action_fifos_exit(void)
+{
+ free_percpu(action_fifos);
}
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 6f5e1dd3be2d..2e31d9e7f4dc 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2007-2013 Nicira, Inc.
+ * Copyright (c) 2007-2014 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
@@ -44,23 +44,48 @@
#include <linux/netfilter_ipv4.h>
#include <linux/inetdevice.h>
#include <linux/list.h>
-#include <linux/lockdep.h>
#include <linux/openvswitch.h>
#include <linux/rculist.h>
#include <linux/dmi.h>
-#include <linux/workqueue.h>
#include <net/genetlink.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include "datapath.h"
#include "flow.h"
+#include "flow_table.h"
#include "flow_netlink.h"
#include "vport-internal_dev.h"
#include "vport-netdev.h"
int ovs_net_id __read_mostly;
+static struct genl_family dp_packet_genl_family;
+static struct genl_family dp_flow_genl_family;
+static struct genl_family dp_datapath_genl_family;
+
+static const struct genl_multicast_group ovs_dp_flow_multicast_group = {
+ .name = OVS_FLOW_MCGROUP,
+};
+
+static const struct genl_multicast_group ovs_dp_datapath_multicast_group = {
+ .name = OVS_DATAPATH_MCGROUP,
+};
+
+static const struct genl_multicast_group ovs_dp_vport_multicast_group = {
+ .name = OVS_VPORT_MCGROUP,
+};
+
+/* Check if need to build a reply message.
+ * OVS userspace sets the NLM_F_ECHO flag if it needs the reply. */
+static bool ovs_must_notify(struct genl_family *family, struct genl_info *info,
+ unsigned int group)
+{
+ return info->nlhdr->nlmsg_flags & NLM_F_ECHO ||
+ genl_has_listeners(family, genl_info_net(info)->genl_sock,
+ group);
+}
+
static void ovs_notify(struct genl_family *family,
struct sk_buff *skb, struct genl_info *info)
{
@@ -108,10 +133,9 @@ int lockdep_ovsl_is_held(void)
#endif
static struct vport *new_vport(const struct vport_parms *);
-static int queue_gso_packets(struct net *, int dp_ifindex, struct sk_buff *,
+static int queue_gso_packets(struct datapath *dp, struct sk_buff *,
const struct dp_upcall_info *);
-static int queue_userspace_packet(struct net *, int dp_ifindex,
- struct sk_buff *,
+static int queue_userspace_packet(struct datapath *dp, struct sk_buff *,
const struct dp_upcall_info *);
/* Must be called with rcu_read_lock or ovs_mutex. */
@@ -161,7 +185,6 @@ static void destroy_dp_rcu(struct rcu_head *rcu)
{
struct datapath *dp = container_of(rcu, struct datapath, rcu);
- ovs_flow_tbl_destroy(&dp->table);
free_percpu(dp->stats_percpu);
release_net(ovs_dp_get_net(dp));
kfree(dp->ports);
@@ -174,6 +197,7 @@ static struct hlist_head *vport_hash_bucket(const struct datapath *dp,
return &dp->ports[port_no & (DP_VPORT_HASH_BUCKETS - 1)];
}
+/* Called with ovs_mutex or RCU read lock. */
struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no)
{
struct vport *vport;
@@ -214,70 +238,54 @@ void ovs_dp_detach_port(struct vport *p)
}
/* Must be called with rcu_read_lock. */
-void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb)
+void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
{
+ const struct vport *p = OVS_CB(skb)->input_vport;
struct datapath *dp = p->dp;
struct sw_flow *flow;
struct dp_stats_percpu *stats;
- struct sw_flow_key key;
u64 *stats_counter;
u32 n_mask_hit;
- int error;
stats = this_cpu_ptr(dp->stats_percpu);
- /* Extract flow from 'skb' into 'key'. */
- error = ovs_flow_extract(skb, p->port_no, &key);
- if (unlikely(error)) {
- kfree_skb(skb);
- return;
- }
-
/* Look up flow. */
- flow = ovs_flow_tbl_lookup(&dp->table, &key, &n_mask_hit);
+ flow = ovs_flow_tbl_lookup_stats(&dp->table, key, &n_mask_hit);
if (unlikely(!flow)) {
struct dp_upcall_info upcall;
+ int error;
upcall.cmd = OVS_PACKET_CMD_MISS;
- upcall.key = &key;
+ upcall.key = key;
upcall.userdata = NULL;
- upcall.portid = p->upcall_portid;
- ovs_dp_upcall(dp, skb, &upcall);
- consume_skb(skb);
+ upcall.portid = ovs_vport_find_upcall_portid(p, skb);
+ error = ovs_dp_upcall(dp, skb, &upcall);
+ if (unlikely(error))
+ kfree_skb(skb);
+ else
+ consume_skb(skb);
stats_counter = &stats->n_missed;
goto out;
}
OVS_CB(skb)->flow = flow;
- OVS_CB(skb)->pkt_key = &key;
+ ovs_flow_stats_update(OVS_CB(skb)->flow, key->tp.flags, skb);
+ ovs_execute_actions(dp, skb, key);
stats_counter = &stats->n_hit;
- ovs_flow_used(OVS_CB(skb)->flow, skb);
- ovs_execute_actions(dp, skb);
out:
/* Update datapath statistics. */
- u64_stats_update_begin(&stats->sync);
+ u64_stats_update_begin(&stats->syncp);
(*stats_counter)++;
stats->n_mask_hit += n_mask_hit;
- u64_stats_update_end(&stats->sync);
+ u64_stats_update_end(&stats->syncp);
}
-static struct genl_family dp_packet_genl_family = {
- .id = GENL_ID_GENERATE,
- .hdrsize = sizeof(struct ovs_header),
- .name = OVS_PACKET_FAMILY,
- .version = OVS_PACKET_VERSION,
- .maxattr = OVS_PACKET_ATTR_MAX,
- .netnsok = true,
- .parallel_ops = true,
-};
-
int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
const struct dp_upcall_info *upcall_info)
{
struct dp_stats_percpu *stats;
- int dp_ifindex;
int err;
if (upcall_info->portid == 0) {
@@ -285,16 +293,10 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
goto err;
}
- dp_ifindex = get_dpifindex(dp);
- if (!dp_ifindex) {
- err = -ENODEV;
- goto err;
- }
-
if (!skb_is_gso(skb))
- err = queue_userspace_packet(ovs_dp_get_net(dp), dp_ifindex, skb, upcall_info);
+ err = queue_userspace_packet(dp, skb, upcall_info);
else
- err = queue_gso_packets(ovs_dp_get_net(dp), dp_ifindex, skb, upcall_info);
+ err = queue_gso_packets(dp, skb, upcall_info);
if (err)
goto err;
@@ -303,15 +305,14 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
err:
stats = this_cpu_ptr(dp->stats_percpu);
- u64_stats_update_begin(&stats->sync);
+ u64_stats_update_begin(&stats->syncp);
stats->n_lost++;
- u64_stats_update_end(&stats->sync);
+ u64_stats_update_end(&stats->syncp);
return err;
}
-static int queue_gso_packets(struct net *net, int dp_ifindex,
- struct sk_buff *skb,
+static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
const struct dp_upcall_info *upcall_info)
{
unsigned short gso_type = skb_shinfo(skb)->gso_type;
@@ -320,14 +321,14 @@ static int queue_gso_packets(struct net *net, int dp_ifindex,
struct sk_buff *segs, *nskb;
int err;
- segs = __skb_gso_segment(skb, NETIF_F_SG | NETIF_F_HW_CSUM, false);
+ segs = __skb_gso_segment(skb, NETIF_F_SG, false);
if (IS_ERR(segs))
return PTR_ERR(segs);
/* Queue all of the segments. */
skb = segs;
do {
- err = queue_userspace_packet(net, dp_ifindex, skb, upcall_info);
+ err = queue_userspace_packet(dp, skb, upcall_info);
if (err)
break;
@@ -368,6 +369,8 @@ static size_t key_attr_size(void)
+ nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TTL */
+ nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
+ nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_CSUM */
+ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_OAM */
+ + nla_total_size(256) /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */
+ nla_total_size(4) /* OVS_KEY_ATTR_IN_PORT */
+ nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */
+ nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */
@@ -380,11 +383,11 @@ static size_t key_attr_size(void)
+ nla_total_size(28); /* OVS_KEY_ATTR_ND */
}
-static size_t upcall_msg_size(const struct sk_buff *skb,
- const struct nlattr *userdata)
+static size_t upcall_msg_size(const struct nlattr *userdata,
+ unsigned int hdrlen)
{
size_t size = NLMSG_ALIGN(sizeof(struct ovs_header))
- + nla_total_size(skb->len) /* OVS_PACKET_ATTR_PACKET */
+ + nla_total_size(hdrlen) /* OVS_PACKET_ATTR_PACKET */
+ nla_total_size(key_attr_size()); /* OVS_PACKET_ATTR_KEY */
/* OVS_PACKET_ATTR_USERDATA */
@@ -394,15 +397,24 @@ static size_t upcall_msg_size(const struct sk_buff *skb,
return size;
}
-static int queue_userspace_packet(struct net *net, int dp_ifindex,
- struct sk_buff *skb,
+static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
const struct dp_upcall_info *upcall_info)
{
struct ovs_header *upcall;
struct sk_buff *nskb = NULL;
- struct sk_buff *user_skb; /* to be queued to userspace */
+ struct sk_buff *user_skb = NULL; /* to be queued to userspace */
struct nlattr *nla;
- int err;
+ struct genl_info info = {
+ .dst_sk = ovs_dp_get_net(dp)->genl_sock,
+ .snd_portid = upcall_info->portid,
+ };
+ size_t len;
+ unsigned int hlen;
+ int err, dp_ifindex;
+
+ dp_ifindex = get_dpifindex(dp);
+ if (!dp_ifindex)
+ return -ENODEV;
if (vlan_tx_tag_present(skb)) {
nskb = skb_clone(skb, GFP_ATOMIC);
@@ -422,7 +434,22 @@ static int queue_userspace_packet(struct net *net, int dp_ifindex,
goto out;
}
- user_skb = genlmsg_new(upcall_msg_size(skb, upcall_info->userdata), GFP_ATOMIC);
+ /* Complete checksum if needed */
+ if (skb->ip_summed == CHECKSUM_PARTIAL &&
+ (err = skb_checksum_help(skb)))
+ goto out;
+
+ /* Older versions of OVS user space enforce alignment of the last
+ * Netlink attribute to NLA_ALIGNTO which would require extensive
+ * padding logic. Only perform zerocopy if padding is not required.
+ */
+ if (dp->user_features & OVS_DP_F_UNALIGNED)
+ hlen = skb_zerocopy_headlen(skb);
+ else
+ hlen = skb->len;
+
+ len = upcall_msg_size(upcall_info->userdata, hlen);
+ user_skb = genlmsg_new_unicast(len, &info, GFP_ATOMIC);
if (!user_skb) {
err = -ENOMEM;
goto out;
@@ -433,7 +460,8 @@ static int queue_userspace_packet(struct net *net, int dp_ifindex,
upcall->dp_ifindex = dp_ifindex;
nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_KEY);
- ovs_nla_put_flow(upcall_info->key, upcall_info->key, user_skb);
+ err = ovs_nla_put_flow(upcall_info->key, upcall_info->key, user_skb);
+ BUG_ON(err);
nla_nest_end(user_skb, nla);
if (upcall_info->userdata)
@@ -441,26 +469,38 @@ static int queue_userspace_packet(struct net *net, int dp_ifindex,
nla_len(upcall_info->userdata),
nla_data(upcall_info->userdata));
- nla = __nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, skb->len);
+ /* Only reserve room for attribute header, packet data is added
+ * in skb_zerocopy() */
+ if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) {
+ err = -ENOBUFS;
+ goto out;
+ }
+ nla->nla_len = nla_attr_size(skb->len);
+
+ err = skb_zerocopy(user_skb, skb, skb->len, hlen);
+ if (err)
+ goto out;
+
+ /* Pad OVS_PACKET_ATTR_PACKET if linear copy was performed */
+ if (!(dp->user_features & OVS_DP_F_UNALIGNED)) {
+ size_t plen = NLA_ALIGN(user_skb->len) - user_skb->len;
- skb_copy_and_csum_dev(skb, nla_data(nla));
+ if (plen > 0)
+ memset(skb_put(user_skb, plen), 0, plen);
+ }
- genlmsg_end(user_skb, upcall);
- err = genlmsg_unicast(net, user_skb, upcall_info->portid);
+ ((struct nlmsghdr *) user_skb->data)->nlmsg_len = user_skb->len;
+ err = genlmsg_unicast(ovs_dp_get_net(dp), user_skb, upcall_info->portid);
+ user_skb = NULL;
out:
+ if (err)
+ skb_tx_error(skb);
+ kfree_skb(user_skb);
kfree_skb(nskb);
return err;
}
-static void clear_stats(struct sw_flow *flow)
-{
- flow->used = 0;
- flow->tcp_flags = 0;
- flow->packet_count = 0;
- flow->byte_count = 0;
-}
-
static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
{
struct ovs_header *ovs_header = info->userhdr;
@@ -470,6 +510,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
struct sw_flow *flow;
struct datapath *dp;
struct ethhdr *eth;
+ struct vport *input_vport;
int len;
int err;
@@ -504,13 +545,11 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
if (IS_ERR(flow))
goto err_kfree_skb;
- err = ovs_flow_extract(packet, -1, &flow->key);
+ err = ovs_flow_key_extract_userspace(a[OVS_PACKET_ATTR_KEY], packet,
+ &flow->key);
if (err)
goto err_flow_free;
- err = ovs_nla_get_flow_metadata(flow, a[OVS_PACKET_ATTR_KEY]);
- if (err)
- goto err_flow_free;
acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_PACKET_ATTR_ACTIONS]));
err = PTR_ERR(acts);
if (IS_ERR(acts))
@@ -518,12 +557,13 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
err = ovs_nla_copy_actions(a[OVS_PACKET_ATTR_ACTIONS],
&flow->key, 0, &acts);
- rcu_assign_pointer(flow->sf_acts, acts);
if (err)
goto err_flow_free;
+ rcu_assign_pointer(flow->sf_acts, acts);
+
+ OVS_CB(packet)->egress_tun_info = NULL;
OVS_CB(packet)->flow = flow;
- OVS_CB(packet)->pkt_key = &flow->key;
packet->priority = flow->key.phy.priority;
packet->mark = flow->key.phy.skb_mark;
@@ -533,8 +573,17 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
if (!dp)
goto err_unlock;
+ input_vport = ovs_vport_rcu(dp, flow->key.phy.in_port);
+ if (!input_vport)
+ input_vport = ovs_vport_rcu(dp, OVSP_LOCAL);
+
+ if (!input_vport)
+ goto err_unlock;
+
+ OVS_CB(packet)->input_vport = input_vport;
+
local_bh_disable();
- err = ovs_execute_actions(dp, packet);
+ err = ovs_execute_actions(dp, packet, &flow->key);
local_bh_enable();
rcu_read_unlock();
@@ -565,6 +614,18 @@ static const struct genl_ops dp_packet_genl_ops[] = {
}
};
+static struct genl_family dp_packet_genl_family = {
+ .id = GENL_ID_GENERATE,
+ .hdrsize = sizeof(struct ovs_header),
+ .name = OVS_PACKET_FAMILY,
+ .version = OVS_PACKET_VERSION,
+ .maxattr = OVS_PACKET_ATTR_MAX,
+ .netnsok = true,
+ .parallel_ops = true,
+ .ops = dp_packet_genl_ops,
+ .n_ops = ARRAY_SIZE(dp_packet_genl_ops),
+};
+
static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats,
struct ovs_dp_megaflow_stats *mega_stats)
{
@@ -585,9 +646,9 @@ static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats,
percpu_stats = per_cpu_ptr(dp->stats_percpu, i);
do {
- start = u64_stats_fetch_begin_bh(&percpu_stats->sync);
+ start = u64_stats_fetch_begin_irq(&percpu_stats->syncp);
local_stats = *percpu_stats;
- } while (u64_stats_fetch_retry_bh(&percpu_stats->sync, start));
+ } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start));
stats->n_hit += local_stats.n_hit;
stats->n_missed += local_stats.n_missed;
@@ -596,26 +657,6 @@ static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats,
}
}
-static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
- [OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED },
- [OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED },
- [OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG },
-};
-
-static struct genl_family dp_flow_genl_family = {
- .id = GENL_ID_GENERATE,
- .hdrsize = sizeof(struct ovs_header),
- .name = OVS_FLOW_FAMILY,
- .version = OVS_FLOW_VERSION,
- .maxattr = OVS_FLOW_ATTR_MAX,
- .netnsok = true,
- .parallel_ops = true,
-};
-
-static struct genl_multicast_group ovs_dp_flow_multicast_group = {
- .name = OVS_FLOW_MCGROUP
-};
-
static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts)
{
return NLMSG_ALIGN(sizeof(struct ovs_header))
@@ -627,25 +668,25 @@ static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts)
+ nla_total_size(acts->actions_len); /* OVS_FLOW_ATTR_ACTIONS */
}
-/* Called with ovs_mutex. */
-static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
+/* Called with ovs_mutex or RCU read lock. */
+static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex,
struct sk_buff *skb, u32 portid,
u32 seq, u32 flags, u8 cmd)
{
const int skb_orig_len = skb->len;
struct nlattr *start;
struct ovs_flow_stats stats;
+ __be16 tcp_flags;
+ unsigned long used;
struct ovs_header *ovs_header;
struct nlattr *nla;
- unsigned long used;
- u8 tcp_flags;
int err;
ovs_header = genlmsg_put(skb, portid, seq, &dp_flow_genl_family, flags, cmd);
if (!ovs_header)
return -EMSGSIZE;
- ovs_header->dp_ifindex = get_dpifindex(dp);
+ ovs_header->dp_ifindex = dp_ifindex;
/* Fill flow key. */
nla = nla_nest_start(skb, OVS_FLOW_ATTR_KEY);
@@ -667,24 +708,18 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
nla_nest_end(skb, nla);
- spin_lock_bh(&flow->lock);
- used = flow->used;
- stats.n_packets = flow->packet_count;
- stats.n_bytes = flow->byte_count;
- tcp_flags = (u8)ntohs(flow->tcp_flags);
- spin_unlock_bh(&flow->lock);
+ ovs_flow_stats_get(flow, &stats, &used, &tcp_flags);
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))
+ 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 ((u8)ntohs(tcp_flags) &&
+ nla_put_u8(skb, OVS_FLOW_ATTR_TCP_FLAGS, (u8)ntohs(tcp_flags)))
goto nla_put_failure;
/* If OVS_FLOW_ATTR_ACTIONS doesn't fit, skip dumping the actions if
@@ -701,11 +736,10 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
if (start) {
const struct sw_flow_actions *sf_acts;
- sf_acts = rcu_dereference_check(flow->sf_acts,
- lockdep_ovsl_is_held());
-
+ sf_acts = rcu_dereference_ovsl(flow->sf_acts);
err = ovs_nla_put_actions(sf_acts->actions,
sf_acts->actions_len, skb);
+
if (!err)
nla_nest_end(skb, start);
else {
@@ -726,119 +760,128 @@ error:
return err;
}
-static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow)
+/* May not be called with RCU read lock. */
+static struct sk_buff *ovs_flow_cmd_alloc_info(const struct sw_flow_actions *acts,
+ struct genl_info *info,
+ bool always)
{
- const struct sw_flow_actions *sf_acts;
+ struct sk_buff *skb;
+
+ if (!always && !ovs_must_notify(&dp_flow_genl_family, info, 0))
+ return NULL;
- sf_acts = ovsl_dereference(flow->sf_acts);
+ skb = genlmsg_new_unicast(ovs_flow_cmd_msg_size(acts), info, GFP_KERNEL);
+ if (!skb)
+ return ERR_PTR(-ENOMEM);
- return genlmsg_new(ovs_flow_cmd_msg_size(sf_acts), GFP_KERNEL);
+ return skb;
}
-static struct sk_buff *ovs_flow_cmd_build_info(struct sw_flow *flow,
- struct datapath *dp,
- u32 portid, u32 seq, u8 cmd)
+/* Called with ovs_mutex. */
+static struct sk_buff *ovs_flow_cmd_build_info(const struct sw_flow *flow,
+ int dp_ifindex,
+ struct genl_info *info, u8 cmd,
+ bool always)
{
struct sk_buff *skb;
int retval;
- skb = ovs_flow_cmd_alloc_info(flow);
- if (!skb)
- return ERR_PTR(-ENOMEM);
+ skb = ovs_flow_cmd_alloc_info(ovsl_dereference(flow->sf_acts), info,
+ always);
+ if (IS_ERR_OR_NULL(skb))
+ return skb;
- retval = ovs_flow_cmd_fill_info(flow, dp, skb, portid, seq, 0, cmd);
+ retval = ovs_flow_cmd_fill_info(flow, dp_ifindex, skb,
+ info->snd_portid, info->snd_seq, 0,
+ cmd);
BUG_ON(retval < 0);
return skb;
}
-static struct sw_flow *__ovs_flow_tbl_lookup(struct flow_table *tbl,
- const struct sw_flow_key *key)
-{
- u32 __always_unused n_mask_hit;
-
- return ovs_flow_tbl_lookup(tbl, key, &n_mask_hit);
-}
-
-static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
+static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
{
struct nlattr **a = info->attrs;
struct ovs_header *ovs_header = info->userhdr;
- struct sw_flow_key key, masked_key;
- struct sw_flow *flow = NULL;
+ struct sw_flow *flow, *new_flow;
struct sw_flow_mask mask;
struct sk_buff *reply;
struct datapath *dp;
- struct sw_flow_actions *acts = NULL;
+ struct sw_flow_actions *acts;
struct sw_flow_match match;
int error;
- /* Extract key. */
+ /* Must have key and actions. */
error = -EINVAL;
if (!a[OVS_FLOW_ATTR_KEY])
goto error;
+ if (!a[OVS_FLOW_ATTR_ACTIONS])
+ goto error;
- ovs_match_init(&match, &key, &mask);
+ /* Most of the time we need to allocate a new flow, do it before
+ * locking.
+ */
+ new_flow = ovs_flow_alloc();
+ if (IS_ERR(new_flow)) {
+ error = PTR_ERR(new_flow);
+ goto error;
+ }
+
+ /* Extract key. */
+ ovs_match_init(&match, &new_flow->unmasked_key, &mask);
error = ovs_nla_get_match(&match,
a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]);
if (error)
- goto error;
+ goto err_kfree_flow;
+
+ ovs_flow_mask_key(&new_flow->key, &new_flow->unmasked_key, &mask);
/* Validate actions. */
- if (a[OVS_FLOW_ATTR_ACTIONS]) {
- acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS]));
- error = PTR_ERR(acts);
- if (IS_ERR(acts))
- goto error;
+ acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS]));
+ error = PTR_ERR(acts);
+ if (IS_ERR(acts))
+ goto err_kfree_flow;
- ovs_flow_mask_key(&masked_key, &key, &mask);
- error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS],
- &masked_key, 0, &acts);
- if (error) {
- OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
- goto err_kfree;
- }
- } else if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW) {
- error = -EINVAL;
- goto error;
+ error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key,
+ 0, &acts);
+ if (error) {
+ OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
+ goto err_kfree_acts;
+ }
+
+ reply = ovs_flow_cmd_alloc_info(acts, info, false);
+ if (IS_ERR(reply)) {
+ error = PTR_ERR(reply);
+ goto err_kfree_acts;
}
ovs_lock();
dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
- error = -ENODEV;
- if (!dp)
+ if (unlikely(!dp)) {
+ error = -ENODEV;
goto err_unlock_ovs;
-
+ }
/* Check if this is a duplicate flow */
- flow = __ovs_flow_tbl_lookup(&dp->table, &key);
- if (!flow) {
- /* Bail out if we're not allowed to create a new flow. */
- error = -ENOENT;
- if (info->genlhdr->cmd == OVS_FLOW_CMD_SET)
- goto err_unlock_ovs;
-
- /* Allocate flow. */
- flow = ovs_flow_alloc();
- if (IS_ERR(flow)) {
- error = PTR_ERR(flow);
- goto err_unlock_ovs;
- }
- clear_stats(flow);
-
- flow->key = masked_key;
- flow->unmasked_key = key;
- rcu_assign_pointer(flow->sf_acts, acts);
+ flow = ovs_flow_tbl_lookup(&dp->table, &new_flow->unmasked_key);
+ if (likely(!flow)) {
+ rcu_assign_pointer(new_flow->sf_acts, acts);
/* Put flow in bucket. */
- error = ovs_flow_tbl_insert(&dp->table, flow, &mask);
- if (error) {
+ error = ovs_flow_tbl_insert(&dp->table, new_flow, &mask);
+ if (unlikely(error)) {
acts = NULL;
- goto err_flow_free;
+ goto err_unlock_ovs;
}
- reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid,
- info->snd_seq, OVS_FLOW_CMD_NEW);
+ if (unlikely(reply)) {
+ error = ovs_flow_cmd_fill_info(new_flow,
+ ovs_header->dp_ifindex,
+ reply, info->snd_portid,
+ info->snd_seq, 0,
+ OVS_FLOW_CMD_NEW);
+ BUG_ON(error < 0);
+ }
+ ovs_unlock();
} else {
- /* We found a matching flow. */
struct sw_flow_actions *old_acts;
/* Bail out if we're not allowed to modify an existing flow.
@@ -847,47 +890,169 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
* request. We also accept NLM_F_EXCL in case that bug ever
* gets fixed.
*/
- error = -EEXIST;
- if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW &&
- info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL))
+ if (unlikely(info->nlhdr->nlmsg_flags & (NLM_F_CREATE
+ | NLM_F_EXCL))) {
+ error = -EEXIST;
goto err_unlock_ovs;
-
+ }
/* The unmasked key has to be the same for flow updates. */
- error = -EINVAL;
- if (!ovs_flow_cmp_unmasked_key(flow, &match)) {
- OVS_NLERR("Flow modification message rejected, unmasked key does not match.\n");
- goto err_unlock_ovs;
+ if (unlikely(!ovs_flow_cmp_unmasked_key(flow, &match))) {
+ flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+ if (!flow) {
+ error = -ENOENT;
+ goto err_unlock_ovs;
+ }
}
-
/* Update actions. */
old_acts = ovsl_dereference(flow->sf_acts);
rcu_assign_pointer(flow->sf_acts, acts);
+
+ if (unlikely(reply)) {
+ error = ovs_flow_cmd_fill_info(flow,
+ ovs_header->dp_ifindex,
+ reply, info->snd_portid,
+ info->snd_seq, 0,
+ OVS_FLOW_CMD_NEW);
+ BUG_ON(error < 0);
+ }
+ ovs_unlock();
+
ovs_nla_free_flow_actions(old_acts);
+ ovs_flow_free(new_flow, false);
+ }
+
+ if (reply)
+ ovs_notify(&dp_flow_genl_family, reply, info);
+ return 0;
+
+err_unlock_ovs:
+ ovs_unlock();
+ kfree_skb(reply);
+err_kfree_acts:
+ kfree(acts);
+err_kfree_flow:
+ ovs_flow_free(new_flow, false);
+error:
+ return error;
+}
- reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid,
- info->snd_seq, OVS_FLOW_CMD_NEW);
+static struct sw_flow_actions *get_flow_actions(const struct nlattr *a,
+ const struct sw_flow_key *key,
+ const struct sw_flow_mask *mask)
+{
+ struct sw_flow_actions *acts;
+ struct sw_flow_key masked_key;
+ int error;
- /* Clear stats. */
- if (a[OVS_FLOW_ATTR_CLEAR]) {
- spin_lock_bh(&flow->lock);
- clear_stats(flow);
- spin_unlock_bh(&flow->lock);
+ acts = ovs_nla_alloc_flow_actions(nla_len(a));
+ if (IS_ERR(acts))
+ return acts;
+
+ ovs_flow_mask_key(&masked_key, key, mask);
+ error = ovs_nla_copy_actions(a, &masked_key, 0, &acts);
+ if (error) {
+ OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
+ kfree(acts);
+ return ERR_PTR(error);
+ }
+
+ return acts;
+}
+
+static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nlattr **a = info->attrs;
+ struct ovs_header *ovs_header = info->userhdr;
+ struct sw_flow_key key;
+ struct sw_flow *flow;
+ struct sw_flow_mask mask;
+ struct sk_buff *reply = NULL;
+ struct datapath *dp;
+ struct sw_flow_actions *old_acts = NULL, *acts = NULL;
+ struct sw_flow_match match;
+ int error;
+
+ /* Extract key. */
+ error = -EINVAL;
+ if (!a[OVS_FLOW_ATTR_KEY])
+ goto error;
+
+ ovs_match_init(&match, &key, &mask);
+ error = ovs_nla_get_match(&match,
+ a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]);
+ if (error)
+ goto error;
+
+ /* Validate actions. */
+ if (a[OVS_FLOW_ATTR_ACTIONS]) {
+ acts = get_flow_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, &mask);
+ if (IS_ERR(acts)) {
+ error = PTR_ERR(acts);
+ goto error;
}
}
+
+ /* Can allocate before locking if have acts. */
+ if (acts) {
+ reply = ovs_flow_cmd_alloc_info(acts, info, false);
+ if (IS_ERR(reply)) {
+ error = PTR_ERR(reply);
+ goto err_kfree_acts;
+ }
+ }
+
+ ovs_lock();
+ dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+ if (unlikely(!dp)) {
+ error = -ENODEV;
+ goto err_unlock_ovs;
+ }
+ /* Check that the flow exists. */
+ flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+ if (unlikely(!flow)) {
+ error = -ENOENT;
+ goto err_unlock_ovs;
+ }
+
+ /* Update actions, if present. */
+ if (likely(acts)) {
+ old_acts = ovsl_dereference(flow->sf_acts);
+ rcu_assign_pointer(flow->sf_acts, acts);
+
+ if (unlikely(reply)) {
+ error = ovs_flow_cmd_fill_info(flow,
+ ovs_header->dp_ifindex,
+ reply, info->snd_portid,
+ info->snd_seq, 0,
+ OVS_FLOW_CMD_NEW);
+ BUG_ON(error < 0);
+ }
+ } else {
+ /* Could not alloc without acts before locking. */
+ reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex,
+ info, OVS_FLOW_CMD_NEW, false);
+ if (unlikely(IS_ERR(reply))) {
+ error = PTR_ERR(reply);
+ goto err_unlock_ovs;
+ }
+ }
+
+ /* Clear stats. */
+ if (a[OVS_FLOW_ATTR_CLEAR])
+ ovs_flow_stats_clear(flow);
ovs_unlock();
- if (!IS_ERR(reply))
+ if (reply)
ovs_notify(&dp_flow_genl_family, reply, info);
- else
- genl_set_err(&dp_flow_genl_family, sock_net(skb->sk), 0,
- 0, PTR_ERR(reply));
+ if (old_acts)
+ ovs_nla_free_flow_actions(old_acts);
+
return 0;
-err_flow_free:
- ovs_flow_free(flow, false);
err_unlock_ovs:
ovs_unlock();
-err_kfree:
+ kfree_skb(reply);
+err_kfree_acts:
kfree(acts);
error:
return error;
@@ -921,14 +1086,14 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
goto unlock;
}
- flow = __ovs_flow_tbl_lookup(&dp->table, &key);
- if (!flow || !ovs_flow_cmp_unmasked_key(flow, &match)) {
+ flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+ if (!flow) {
err = -ENOENT;
goto unlock;
}
- reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid,
- info->snd_seq, OVS_FLOW_CMD_NEW);
+ reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex, info,
+ OVS_FLOW_CMD_NEW, true);
if (IS_ERR(reply)) {
err = PTR_ERR(reply);
goto unlock;
@@ -952,45 +1117,53 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
struct sw_flow_match match;
int err;
+ if (likely(a[OVS_FLOW_ATTR_KEY])) {
+ ovs_match_init(&match, &key, NULL);
+ err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
+ if (unlikely(err))
+ return err;
+ }
+
ovs_lock();
dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
- if (!dp) {
+ if (unlikely(!dp)) {
err = -ENODEV;
goto unlock;
}
- if (!a[OVS_FLOW_ATTR_KEY]) {
+ if (unlikely(!a[OVS_FLOW_ATTR_KEY])) {
err = ovs_flow_tbl_flush(&dp->table);
goto unlock;
}
- ovs_match_init(&match, &key, NULL);
- err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
- if (err)
- goto unlock;
-
- flow = __ovs_flow_tbl_lookup(&dp->table, &key);
- if (!flow || !ovs_flow_cmp_unmasked_key(flow, &match)) {
+ flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+ if (unlikely(!flow)) {
err = -ENOENT;
goto unlock;
}
- reply = ovs_flow_cmd_alloc_info(flow);
- if (!reply) {
- err = -ENOMEM;
- goto unlock;
- }
-
ovs_flow_tbl_remove(&dp->table, flow);
+ ovs_unlock();
- err = ovs_flow_cmd_fill_info(flow, dp, reply, info->snd_portid,
- info->snd_seq, 0, OVS_FLOW_CMD_DEL);
- BUG_ON(err < 0);
+ reply = ovs_flow_cmd_alloc_info((const struct sw_flow_actions __force *) flow->sf_acts,
+ info, false);
+ if (likely(reply)) {
+ if (likely(!IS_ERR(reply))) {
+ rcu_read_lock(); /*To keep RCU checker happy. */
+ err = ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex,
+ reply, info->snd_portid,
+ info->snd_seq, 0,
+ OVS_FLOW_CMD_DEL);
+ rcu_read_unlock();
+ BUG_ON(err < 0);
+
+ ovs_notify(&dp_flow_genl_family, reply, info);
+ } else {
+ netlink_set_err(sock_net(skb->sk)->genl_sock, 0, 0, PTR_ERR(reply));
+ }
+ }
ovs_flow_free(flow, true);
- ovs_unlock();
-
- ovs_notify(&dp_flow_genl_family, reply, info);
return 0;
unlock:
ovs_unlock();
@@ -1021,7 +1194,7 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
if (!flow)
break;
- if (ovs_flow_cmd_fill_info(flow, dp, skb,
+ if (ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
OVS_FLOW_CMD_NEW) < 0)
@@ -1034,11 +1207,17 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
return skb->len;
}
+static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
+ [OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED },
+ [OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED },
+ [OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG },
+};
+
static const struct genl_ops dp_flow_genl_ops[] = {
{ .cmd = OVS_FLOW_CMD_NEW,
.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
.policy = flow_policy,
- .doit = ovs_flow_cmd_new_or_set
+ .doit = ovs_flow_cmd_new
},
{ .cmd = OVS_FLOW_CMD_DEL,
.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
@@ -1054,27 +1233,22 @@ static const struct genl_ops dp_flow_genl_ops[] = {
{ .cmd = OVS_FLOW_CMD_SET,
.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
.policy = flow_policy,
- .doit = ovs_flow_cmd_new_or_set,
+ .doit = ovs_flow_cmd_set,
},
};
-static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = {
- [OVS_DP_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
- [OVS_DP_ATTR_UPCALL_PID] = { .type = NLA_U32 },
-};
-
-static struct genl_family dp_datapath_genl_family = {
+static struct genl_family dp_flow_genl_family = {
.id = GENL_ID_GENERATE,
.hdrsize = sizeof(struct ovs_header),
- .name = OVS_DATAPATH_FAMILY,
- .version = OVS_DATAPATH_VERSION,
- .maxattr = OVS_DP_ATTR_MAX,
+ .name = OVS_FLOW_FAMILY,
+ .version = OVS_FLOW_VERSION,
+ .maxattr = OVS_FLOW_ATTR_MAX,
.netnsok = true,
.parallel_ops = true,
-};
-
-static struct genl_multicast_group ovs_dp_datapath_multicast_group = {
- .name = OVS_DATAPATH_MCGROUP
+ .ops = dp_flow_genl_ops,
+ .n_ops = ARRAY_SIZE(dp_flow_genl_ops),
+ .mcgrps = &ovs_dp_flow_multicast_group,
+ .n_mcgrps = 1,
};
static size_t ovs_dp_cmd_msg_size(void)
@@ -1084,10 +1258,12 @@ static size_t ovs_dp_cmd_msg_size(void)
msgsize += nla_total_size(IFNAMSIZ);
msgsize += nla_total_size(sizeof(struct ovs_dp_stats));
msgsize += nla_total_size(sizeof(struct ovs_dp_megaflow_stats));
+ msgsize += nla_total_size(sizeof(u32)); /* OVS_DP_ATTR_USER_FEATURES */
return msgsize;
}
+/* Called with ovs_mutex or RCU read lock. */
static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
u32 portid, u32 seq, u32 flags, u8 cmd)
{
@@ -1103,9 +1279,7 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
ovs_header->dp_ifindex = get_dpifindex(dp);
- rcu_read_lock();
err = nla_put_string(skb, OVS_DP_ATTR_NAME, ovs_dp_name(dp));
- rcu_read_unlock();
if (err)
goto nla_put_failure;
@@ -1119,6 +1293,9 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
&dp_megaflow_stats))
goto nla_put_failure;
+ if (nla_put_u32(skb, OVS_DP_ATTR_USER_FEATURES, dp->user_features))
+ goto nla_put_failure;
+
return genlmsg_end(skb, ovs_header);
nla_put_failure:
@@ -1127,25 +1304,12 @@ error:
return -EMSGSIZE;
}
-static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp, u32 portid,
- u32 seq, u8 cmd)
+static struct sk_buff *ovs_dp_cmd_alloc_info(struct genl_info *info)
{
- struct sk_buff *skb;
- int retval;
-
- skb = genlmsg_new(ovs_dp_cmd_msg_size(), GFP_KERNEL);
- if (!skb)
- return ERR_PTR(-ENOMEM);
-
- retval = ovs_dp_cmd_fill_info(dp, skb, portid, seq, 0, cmd);
- if (retval < 0) {
- kfree_skb(skb);
- return ERR_PTR(retval);
- }
- return skb;
+ return genlmsg_new_unicast(ovs_dp_cmd_msg_size(), info, GFP_KERNEL);
}
-/* Called with ovs_mutex. */
+/* Called with rcu_read_lock or ovs_mutex. */
static struct datapath *lookup_datapath(struct net *net,
struct ovs_header *ovs_header,
struct nlattr *a[OVS_DP_ATTR_MAX + 1])
@@ -1157,14 +1321,30 @@ static struct datapath *lookup_datapath(struct net *net,
else {
struct vport *vport;
- rcu_read_lock();
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();
}
return dp ? dp : ERR_PTR(-ENODEV);
}
+static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *info)
+{
+ struct datapath *dp;
+
+ dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
+ if (IS_ERR(dp))
+ return;
+
+ WARN(dp->user_features, "Dropping previously announced user features\n");
+ dp->user_features = 0;
+}
+
+static void ovs_dp_change(struct datapath *dp, struct nlattr **a)
+{
+ if (a[OVS_DP_ATTR_USER_FEATURES])
+ dp->user_features = nla_get_u32(a[OVS_DP_ATTR_USER_FEATURES]);
+}
+
static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
{
struct nlattr **a = info->attrs;
@@ -1179,12 +1359,14 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
if (!a[OVS_DP_ATTR_NAME] || !a[OVS_DP_ATTR_UPCALL_PID])
goto err;
- ovs_lock();
+ reply = ovs_dp_cmd_alloc_info(info);
+ if (!reply)
+ return -ENOMEM;
err = -ENOMEM;
dp = kzalloc(sizeof(*dp), GFP_KERNEL);
if (dp == NULL)
- goto err_unlock_ovs;
+ goto err_free_reply;
ovs_dp_set_net(dp, hold_net(sock_net(skb->sk)));
@@ -1193,18 +1375,12 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
if (err)
goto err_free_dp;
- dp->stats_percpu = alloc_percpu(struct dp_stats_percpu);
+ dp->stats_percpu = netdev_alloc_pcpu_stats(struct dp_stats_percpu);
if (!dp->stats_percpu) {
err = -ENOMEM;
goto err_destroy_table;
}
- for_each_possible_cpu(i) {
- struct dp_stats_percpu *dpath_stats;
- dpath_stats = per_cpu_ptr(dp->stats_percpu, i);
- u64_stats_init(&dpath_stats->sync);
- }
-
dp->ports = kmalloc(DP_VPORT_HASH_BUCKETS * sizeof(struct hlist_head),
GFP_KERNEL);
if (!dp->ports) {
@@ -1221,7 +1397,12 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
parms.options = NULL;
parms.dp = dp;
parms.port_no = OVSP_LOCAL;
- parms.upcall_portid = nla_get_u32(a[OVS_DP_ATTR_UPCALL_PID]);
+ parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID];
+
+ ovs_dp_change(dp, a);
+
+ /* So far only local changes have been made, now need the lock. */
+ ovs_lock();
vport = new_vport(&parms);
if (IS_ERR(vport)) {
@@ -1229,14 +1410,21 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
if (err == -EBUSY)
err = -EEXIST;
+ if (err == -EEXIST) {
+ /* An outdated user space instance that does not understand
+ * the concept of user_features has attempted to create a new
+ * datapath and is likely to reuse it. Drop all user features.
+ */
+ if (info->genlhdr->version < OVS_DP_VER_FEATURES)
+ ovs_dp_reset_user_features(skb, info);
+ }
+
goto err_destroy_ports_array;
}
- 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;
+ err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
+ info->snd_seq, 0, OVS_DP_CMD_NEW);
+ BUG_ON(err < 0);
ovs_net = net_generic(ovs_dp_get_net(dp), ovs_net_id);
list_add_tail_rcu(&dp->list_node, &ovs_net->dps);
@@ -1246,19 +1434,18 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
ovs_notify(&dp_datapath_genl_family, reply, info);
return 0;
-err_destroy_local_port:
- ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL));
err_destroy_ports_array:
+ ovs_unlock();
kfree(dp->ports);
err_destroy_percpu:
free_percpu(dp->stats_percpu);
err_destroy_table:
- ovs_flow_tbl_destroy(&dp->table);
+ ovs_flow_tbl_destroy(&dp->table, false);
err_free_dp:
release_net(ovs_dp_get_net(dp));
kfree(dp);
-err_unlock_ovs:
- ovs_unlock();
+err_free_reply:
+ kfree_skb(reply);
err:
return err;
}
@@ -1280,10 +1467,13 @@ static void __dp_destroy(struct datapath *dp)
list_del_rcu(&dp->list_node);
/* OVSP_LOCAL is datapath internal port. We need to make sure that
- * all port in datapath are destroyed first before freeing datapath.
+ * all ports in datapath are destroyed first before freeing datapath.
*/
ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL));
+ /* RCU destroy the flow table */
+ ovs_flow_tbl_destroy(&dp->table, true);
+
call_rcu(&dp->rcu, destroy_dp_rcu);
}
@@ -1293,17 +1483,19 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info)
struct datapath *dp;
int err;
+ reply = ovs_dp_cmd_alloc_info(info);
+ if (!reply)
+ return -ENOMEM;
+
ovs_lock();
dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
err = PTR_ERR(dp);
if (IS_ERR(dp))
- goto unlock;
+ goto err_unlock_free;
- 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))
- goto unlock;
+ err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
+ info->snd_seq, 0, OVS_DP_CMD_DEL);
+ BUG_ON(err < 0);
__dp_destroy(dp);
ovs_unlock();
@@ -1311,8 +1503,10 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info)
ovs_notify(&dp_datapath_genl_family, reply, info);
return 0;
-unlock:
+
+err_unlock_free:
ovs_unlock();
+ kfree_skb(reply);
return err;
}
@@ -1322,28 +1516,30 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info)
struct datapath *dp;
int err;
+ reply = ovs_dp_cmd_alloc_info(info);
+ if (!reply)
+ return -ENOMEM;
+
ovs_lock();
dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
err = PTR_ERR(dp);
if (IS_ERR(dp))
- goto unlock;
+ goto err_unlock_free;
- 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);
- genl_set_err(&dp_datapath_genl_family, sock_net(skb->sk), 0,
- 0, err);
- err = 0;
- goto unlock;
- }
+ ovs_dp_change(dp, info->attrs);
+
+ err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
+ info->snd_seq, 0, OVS_DP_CMD_NEW);
+ BUG_ON(err < 0);
ovs_unlock();
ovs_notify(&dp_datapath_genl_family, reply, info);
return 0;
-unlock:
+
+err_unlock_free:
ovs_unlock();
+ kfree_skb(reply);
return err;
}
@@ -1353,25 +1549,26 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info)
struct datapath *dp;
int err;
- ovs_lock();
+ reply = ovs_dp_cmd_alloc_info(info);
+ if (!reply)
+ return -ENOMEM;
+
+ rcu_read_lock();
dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
if (IS_ERR(dp)) {
err = PTR_ERR(dp);
- goto unlock;
- }
-
- 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);
- goto unlock;
+ goto err_unlock_free;
}
+ err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
+ info->snd_seq, 0, OVS_DP_CMD_NEW);
+ BUG_ON(err < 0);
+ rcu_read_unlock();
- ovs_unlock();
return genlmsg_reply(reply, info);
-unlock:
- ovs_unlock();
+err_unlock_free:
+ rcu_read_unlock();
+ kfree_skb(reply);
return err;
}
@@ -1398,6 +1595,12 @@ static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
return skb->len;
}
+static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = {
+ [OVS_DP_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
+ [OVS_DP_ATTR_UPCALL_PID] = { .type = NLA_U32 },
+ [OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 },
+};
+
static const struct genl_ops dp_datapath_genl_ops[] = {
{ .cmd = OVS_DP_CMD_NEW,
.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
@@ -1422,27 +1625,18 @@ static const struct genl_ops dp_datapath_genl_ops[] = {
},
};
-static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
- [OVS_VPORT_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
- [OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) },
- [OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 },
- [OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 },
- [OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 },
- [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED },
-};
-
-struct genl_family dp_vport_genl_family = {
+static struct genl_family dp_datapath_genl_family = {
.id = GENL_ID_GENERATE,
.hdrsize = sizeof(struct ovs_header),
- .name = OVS_VPORT_FAMILY,
- .version = OVS_VPORT_VERSION,
- .maxattr = OVS_VPORT_ATTR_MAX,
+ .name = OVS_DATAPATH_FAMILY,
+ .version = OVS_DATAPATH_VERSION,
+ .maxattr = OVS_DP_ATTR_MAX,
.netnsok = true,
.parallel_ops = true,
-};
-
-struct genl_multicast_group ovs_dp_vport_multicast_group = {
- .name = OVS_VPORT_MCGROUP
+ .ops = dp_datapath_genl_ops,
+ .n_ops = ARRAY_SIZE(dp_datapath_genl_ops),
+ .mcgrps = &ovs_dp_datapath_multicast_group,
+ .n_mcgrps = 1,
};
/* Called with ovs_mutex or RCU read lock. */
@@ -1462,8 +1656,8 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
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))
+ nla_put_string(skb, OVS_VPORT_ATTR_NAME,
+ vport->ops->get_name(vport)))
goto nla_put_failure;
ovs_vport_get_stats(vport, &vport_stats);
@@ -1471,6 +1665,9 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
&vport_stats))
goto nla_put_failure;
+ if (ovs_vport_get_upcall_portids(vport, skb))
+ goto nla_put_failure;
+
err = ovs_vport_get_options(vport, skb);
if (err == -EMSGSIZE)
goto error;
@@ -1484,7 +1681,12 @@ error:
return err;
}
-/* Called with ovs_mutex or RCU read lock. */
+static struct sk_buff *ovs_vport_cmd_alloc_info(void)
+{
+ return nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+}
+
+/* Called with ovs_mutex, only via ovs_dp_notify_wq(). */
struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid,
u32 seq, u8 cmd)
{
@@ -1546,33 +1748,35 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
u32 port_no;
int err;
- err = -EINVAL;
if (!a[OVS_VPORT_ATTR_NAME] || !a[OVS_VPORT_ATTR_TYPE] ||
!a[OVS_VPORT_ATTR_UPCALL_PID])
- goto exit;
+ return -EINVAL;
+
+ port_no = a[OVS_VPORT_ATTR_PORT_NO]
+ ? nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]) : 0;
+ if (port_no >= DP_MAX_PORTS)
+ return -EFBIG;
+
+ reply = ovs_vport_cmd_alloc_info();
+ if (!reply)
+ return -ENOMEM;
ovs_lock();
dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
err = -ENODEV;
if (!dp)
- goto exit_unlock;
-
- if (a[OVS_VPORT_ATTR_PORT_NO]) {
- port_no = nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]);
-
- err = -EFBIG;
- if (port_no >= DP_MAX_PORTS)
- goto exit_unlock;
+ goto exit_unlock_free;
+ if (port_no) {
vport = ovs_vport_ovsl(dp, port_no);
err = -EBUSY;
if (vport)
- goto exit_unlock;
+ goto exit_unlock_free;
} else {
for (port_no = 1; ; port_no++) {
if (port_no >= DP_MAX_PORTS) {
err = -EFBIG;
- goto exit_unlock;
+ goto exit_unlock_free;
}
vport = ovs_vport_ovsl(dp, port_no);
if (!vport)
@@ -1585,27 +1789,24 @@ 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_portid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]);
+ parms.upcall_portids = a[OVS_VPORT_ATTR_UPCALL_PID];
vport = new_vport(&parms);
err = PTR_ERR(vport);
if (IS_ERR(vport))
- goto exit_unlock;
+ goto exit_unlock_free;
- err = 0;
- 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;
- }
+ err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
+ info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+ BUG_ON(err < 0);
+ ovs_unlock();
ovs_notify(&dp_vport_genl_family, reply, info);
+ return 0;
-exit_unlock:
+exit_unlock_free:
ovs_unlock();
-exit:
+ kfree_skb(reply);
return err;
}
@@ -1616,32 +1817,36 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info)
struct vport *vport;
int err;
+ reply = ovs_vport_cmd_alloc_info();
+ if (!reply)
+ return -ENOMEM;
+
ovs_lock();
vport = lookup_vport(sock_net(skb->sk), info->userhdr, a);
err = PTR_ERR(vport);
if (IS_ERR(vport))
- goto exit_unlock;
+ goto exit_unlock_free;
if (a[OVS_VPORT_ATTR_TYPE] &&
nla_get_u32(a[OVS_VPORT_ATTR_TYPE]) != vport->ops->type) {
err = -EINVAL;
- goto exit_unlock;
- }
-
- reply = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!reply) {
- err = -ENOMEM;
- goto exit_unlock;
+ goto exit_unlock_free;
}
if (a[OVS_VPORT_ATTR_OPTIONS]) {
err = ovs_vport_set_options(vport, a[OVS_VPORT_ATTR_OPTIONS]);
if (err)
- goto exit_free;
+ goto exit_unlock_free;
}
- if (a[OVS_VPORT_ATTR_UPCALL_PID])
- vport->upcall_portid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]);
+
+ if (a[OVS_VPORT_ATTR_UPCALL_PID]) {
+ struct nlattr *ids = a[OVS_VPORT_ATTR_UPCALL_PID];
+
+ err = ovs_vport_set_upcall_portids(vport, ids);
+ if (err)
+ goto exit_unlock_free;
+ }
err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
info->snd_seq, 0, OVS_VPORT_CMD_NEW);
@@ -1651,10 +1856,9 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info)
ovs_notify(&dp_vport_genl_family, reply, info);
return 0;
-exit_free:
- kfree_skb(reply);
-exit_unlock:
+exit_unlock_free:
ovs_unlock();
+ kfree_skb(reply);
return err;
}
@@ -1665,30 +1869,33 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info)
struct vport *vport;
int err;
+ reply = ovs_vport_cmd_alloc_info();
+ if (!reply)
+ return -ENOMEM;
+
ovs_lock();
vport = lookup_vport(sock_net(skb->sk), info->userhdr, a);
err = PTR_ERR(vport);
if (IS_ERR(vport))
- goto exit_unlock;
+ goto exit_unlock_free;
if (vport->port_no == OVSP_LOCAL) {
err = -EINVAL;
- goto exit_unlock;
+ goto exit_unlock_free;
}
- 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;
+ err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
+ info->snd_seq, 0, OVS_VPORT_CMD_DEL);
+ BUG_ON(err < 0);
ovs_dp_detach_port(vport);
+ ovs_unlock();
ovs_notify(&dp_vport_genl_family, reply, info);
+ return 0;
-exit_unlock:
+exit_unlock_free:
ovs_unlock();
+ kfree_skb(reply);
return err;
}
@@ -1700,24 +1907,25 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info)
struct vport *vport;
int err;
+ reply = ovs_vport_cmd_alloc_info();
+ if (!reply)
+ return -ENOMEM;
+
rcu_read_lock();
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_portid,
- info->snd_seq, OVS_VPORT_CMD_NEW);
- err = PTR_ERR(reply);
- if (IS_ERR(reply))
- goto exit_unlock;
-
+ goto exit_unlock_free;
+ err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
+ info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+ BUG_ON(err < 0);
rcu_read_unlock();
return genlmsg_reply(reply, info);
-exit_unlock:
+exit_unlock_free:
rcu_read_unlock();
+ kfree_skb(reply);
return err;
}
@@ -1728,11 +1936,12 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
int bucket = cb->args[0], skip = cb->args[1];
int i, j = 0;
+ rcu_read_lock();
dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
- if (!dp)
+ if (!dp) {
+ rcu_read_unlock();
return -ENODEV;
-
- rcu_read_lock();
+ }
for (i = bucket; i < DP_VPORT_HASH_BUCKETS; i++) {
struct vport *vport;
@@ -1759,6 +1968,15 @@ out:
return skb->len;
}
+static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
+ [OVS_VPORT_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
+ [OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) },
+ [OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 },
+ [OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 },
+ [OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 },
+ [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED },
+};
+
static const struct genl_ops dp_vport_genl_ops[] = {
{ .cmd = OVS_VPORT_CMD_NEW,
.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
@@ -1783,26 +2001,25 @@ static const struct genl_ops dp_vport_genl_ops[] = {
},
};
-struct genl_family_and_ops {
- struct genl_family *family;
- const struct genl_ops *ops;
- int n_ops;
- const struct genl_multicast_group *group;
+struct genl_family dp_vport_genl_family = {
+ .id = GENL_ID_GENERATE,
+ .hdrsize = sizeof(struct ovs_header),
+ .name = OVS_VPORT_FAMILY,
+ .version = OVS_VPORT_VERSION,
+ .maxattr = OVS_VPORT_ATTR_MAX,
+ .netnsok = true,
+ .parallel_ops = true,
+ .ops = dp_vport_genl_ops,
+ .n_ops = ARRAY_SIZE(dp_vport_genl_ops),
+ .mcgrps = &ovs_dp_vport_multicast_group,
+ .n_mcgrps = 1,
};
-static const struct genl_family_and_ops dp_genl_families[] = {
- { &dp_datapath_genl_family,
- dp_datapath_genl_ops, ARRAY_SIZE(dp_datapath_genl_ops),
- &ovs_dp_datapath_multicast_group },
- { &dp_vport_genl_family,
- dp_vport_genl_ops, ARRAY_SIZE(dp_vport_genl_ops),
- &ovs_dp_vport_multicast_group },
- { &dp_flow_genl_family,
- dp_flow_genl_ops, ARRAY_SIZE(dp_flow_genl_ops),
- &ovs_dp_flow_multicast_group },
- { &dp_packet_genl_family,
- dp_packet_genl_ops, ARRAY_SIZE(dp_packet_genl_ops),
- NULL },
+static struct genl_family * const dp_genl_families[] = {
+ &dp_datapath_genl_family,
+ &dp_vport_genl_family,
+ &dp_flow_genl_family,
+ &dp_packet_genl_family,
};
static void dp_unregister_genl(int n_families)
@@ -1810,33 +2027,25 @@ static void dp_unregister_genl(int n_families)
int i;
for (i = 0; i < n_families; i++)
- genl_unregister_family(dp_genl_families[i].family);
+ genl_unregister_family(dp_genl_families[i]);
}
static int dp_register_genl(void)
{
- int n_registered;
int err;
int i;
- n_registered = 0;
for (i = 0; i < ARRAY_SIZE(dp_genl_families); i++) {
- const struct genl_family_and_ops *f = &dp_genl_families[i];
- f->family->ops = f->ops;
- f->family->n_ops = f->n_ops;
- f->family->mcgrps = f->group;
- f->family->n_mcgrps = f->group ? 1 : 0;
- err = genl_register_family(f->family);
+ err = genl_register_family(dp_genl_families[i]);
if (err)
goto error;
- n_registered++;
}
return 0;
error:
- dp_unregister_genl(n_registered);
+ dp_unregister_genl(i);
return err;
}
@@ -1877,10 +2086,18 @@ static int __init dp_init(void)
pr_info("Open vSwitch switching datapath\n");
- err = ovs_flow_init();
+ err = action_fifos_init();
if (err)
goto error;
+ err = ovs_internal_dev_rtnl_link_register();
+ if (err)
+ goto error_action_fifos_exit;
+
+ err = ovs_flow_init();
+ if (err)
+ goto error_unreg_rtnl_link;
+
err = ovs_vport_init();
if (err)
goto error_flow_exit;
@@ -1907,6 +2124,10 @@ error_vport_exit:
ovs_vport_exit();
error_flow_exit:
ovs_flow_exit();
+error_unreg_rtnl_link:
+ ovs_internal_dev_rtnl_link_unregister();
+error_action_fifos_exit:
+ action_fifos_exit();
error:
return err;
}
@@ -1919,6 +2140,8 @@ static void dp_cleanup(void)
rcu_barrier();
ovs_vport_exit();
ovs_flow_exit();
+ ovs_internal_dev_rtnl_link_unregister();
+ action_fifos_exit();
}
module_init(dp_init);
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 4067ea41be28..974135439c5c 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2007-2012 Nicira, Inc.
+ * Copyright (c) 2007-2014 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
@@ -55,7 +55,7 @@ struct dp_stats_percpu {
u64 n_missed;
u64 n_lost;
u64 n_mask_hit;
- struct u64_stats_sync sync;
+ struct u64_stats_sync syncp;
};
/**
@@ -88,19 +88,22 @@ struct datapath {
/* Network namespace ref. */
struct net *net;
#endif
+
+ u32 user_features;
};
/**
* struct ovs_skb_cb - OVS data in skb CB
* @flow: The flow associated with this packet. May be %NULL if no flow.
- * @pkt_key: The flow information extracted from the packet. Must be nonnull.
- * @tun_key: Key for the tunnel that encapsulated this packet. NULL if the
- * packet is not being tunneled.
+ * @egress_tun_key: Tunnel information about this packet on egress path.
+ * NULL if the packet is not being tunneled.
+ * @input_vport: The original vport packet came in on. This value is cached
+ * when a packet is received by OVS.
*/
struct ovs_skb_cb {
struct sw_flow *flow;
- struct sw_flow_key *pkt_key;
- struct ovs_key_ipv4_tunnel *tun_key;
+ struct ovs_tunnel_info *egress_tun_info;
+ struct vport *input_vport;
};
#define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
@@ -142,9 +145,11 @@ int lockdep_ovsl_is_held(void);
#define lockdep_ovsl_is_held() 1
#endif
-#define ASSERT_OVSL() WARN_ON(unlikely(!lockdep_ovsl_is_held()))
+#define ASSERT_OVSL() WARN_ON(!lockdep_ovsl_is_held())
#define ovsl_dereference(p) \
rcu_dereference_protected(p, lockdep_ovsl_is_held())
+#define rcu_dereference_ovsl(p) \
+ rcu_dereference_check(p, lockdep_ovsl_is_held())
static inline struct net *ovs_dp_get_net(struct datapath *dp)
{
@@ -178,9 +183,8 @@ static inline struct vport *ovs_vport_ovsl(const struct datapath *dp, int port_n
extern struct notifier_block ovs_dp_device_notifier;
extern struct genl_family dp_vport_genl_family;
-extern struct genl_multicast_group ovs_dp_vport_multicast_group;
-void ovs_dp_process_received_packet(struct vport *, struct sk_buff *);
+void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key);
void ovs_dp_detach_port(struct vport *);
int ovs_dp_upcall(struct datapath *, struct sk_buff *,
const struct dp_upcall_info *);
@@ -189,10 +193,17 @@ const char *ovs_dp_name(const struct datapath *dp);
struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq,
u8 cmd);
-int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb);
+int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
+ struct sw_flow_key *);
+
void ovs_dp_notify_wq(struct work_struct *work);
-#define OVS_NLERR(fmt, ...) \
- pr_info_once("netlink: " fmt, ##__VA_ARGS__)
+int action_fifos_init(void);
+void action_fifos_exit(void);
+#define OVS_NLERR(fmt, ...) \
+do { \
+ if (net_ratelimit()) \
+ pr_info("netlink: " fmt, ##__VA_ARGS__); \
+} while (0)
#endif /* datapath.h */
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index b409f5279601..62db02ba36bc 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2007-2013 Nicira, Inc.
+ * Copyright (c) 2007-2014 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
@@ -16,8 +16,6 @@
* 02110-1301, USA
*/
-#include "flow.h"
-#include "datapath.h"
#include <linux/uaccess.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
@@ -35,6 +33,7 @@
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/sctp.h>
+#include <linux/smp.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/icmp.h>
@@ -45,6 +44,10 @@
#include <net/ipv6.h>
#include <net/ndisc.h>
+#include "datapath.h"
+#include "flow.h"
+#include "flow_netlink.h"
+
u64 ovs_flow_used_time(unsigned long flow_jiffies)
{
struct timespec cur_ts;
@@ -60,23 +63,113 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies)
#define TCP_FLAGS_BE16(tp) (*(__be16 *)&tcp_flag_word(tp) & htons(0x0FFF))
-void ovs_flow_used(struct sw_flow *flow, struct sk_buff *skb)
+void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
+ struct sk_buff *skb)
{
- __be16 tcp_flags = 0;
+ struct flow_stats *stats;
+ int node = numa_node_id();
+
+ stats = rcu_dereference(flow->stats[node]);
+
+ /* Check if already have node-specific stats. */
+ if (likely(stats)) {
+ spin_lock(&stats->lock);
+ /* Mark if we write on the pre-allocated stats. */
+ if (node == 0 && unlikely(flow->stats_last_writer != node))
+ flow->stats_last_writer = node;
+ } else {
+ stats = rcu_dereference(flow->stats[0]); /* Pre-allocated. */
+ spin_lock(&stats->lock);
+
+ /* If the current NUMA-node is the only writer on the
+ * pre-allocated stats keep using them.
+ */
+ if (unlikely(flow->stats_last_writer != node)) {
+ /* A previous locker may have already allocated the
+ * stats, so we need to check again. If node-specific
+ * stats were already allocated, we update the pre-
+ * allocated stats as we have already locked them.
+ */
+ if (likely(flow->stats_last_writer != NUMA_NO_NODE)
+ && likely(!rcu_access_pointer(flow->stats[node]))) {
+ /* Try to allocate node-specific stats. */
+ struct flow_stats *new_stats;
+
+ new_stats =
+ kmem_cache_alloc_node(flow_stats_cache,
+ GFP_THISNODE |
+ __GFP_NOMEMALLOC,
+ node);
+ if (likely(new_stats)) {
+ new_stats->used = jiffies;
+ new_stats->packet_count = 1;
+ new_stats->byte_count = skb->len;
+ new_stats->tcp_flags = tcp_flags;
+ spin_lock_init(&new_stats->lock);
+
+ rcu_assign_pointer(flow->stats[node],
+ new_stats);
+ goto unlock;
+ }
+ }
+ flow->stats_last_writer = node;
+ }
+ }
+
+ stats->used = jiffies;
+ stats->packet_count++;
+ stats->byte_count += skb->len;
+ stats->tcp_flags |= tcp_flags;
+unlock:
+ spin_unlock(&stats->lock);
+}
+
+/* Must be called with rcu_read_lock or ovs_mutex. */
+void ovs_flow_stats_get(const struct sw_flow *flow,
+ struct ovs_flow_stats *ovs_stats,
+ unsigned long *used, __be16 *tcp_flags)
+{
+ int node;
+
+ *used = 0;
+ *tcp_flags = 0;
+ memset(ovs_stats, 0, sizeof(*ovs_stats));
- if ((flow->key.eth.type == htons(ETH_P_IP) ||
- flow->key.eth.type == htons(ETH_P_IPV6)) &&
- flow->key.ip.proto == IPPROTO_TCP &&
- likely(skb->len >= skb_transport_offset(skb) + sizeof(struct tcphdr))) {
- tcp_flags = TCP_FLAGS_BE16(tcp_hdr(skb));
+ for_each_node(node) {
+ struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[node]);
+
+ if (stats) {
+ /* Local CPU may write on non-local stats, so we must
+ * block bottom-halves here.
+ */
+ spin_lock_bh(&stats->lock);
+ if (!*used || time_after(stats->used, *used))
+ *used = stats->used;
+ *tcp_flags |= stats->tcp_flags;
+ ovs_stats->n_packets += stats->packet_count;
+ ovs_stats->n_bytes += stats->byte_count;
+ spin_unlock_bh(&stats->lock);
+ }
}
+}
- spin_lock(&flow->lock);
- flow->used = jiffies;
- flow->packet_count++;
- flow->byte_count += skb->len;
- flow->tcp_flags |= tcp_flags;
- spin_unlock(&flow->lock);
+/* Called with ovs_mutex. */
+void ovs_flow_stats_clear(struct sw_flow *flow)
+{
+ int node;
+
+ for_each_node(node) {
+ struct flow_stats *stats = ovsl_dereference(flow->stats[node]);
+
+ if (stats) {
+ spin_lock_bh(&stats->lock);
+ stats->used = 0;
+ stats->packet_count = 0;
+ stats->byte_count = 0;
+ stats->tcp_flags = 0;
+ spin_unlock_bh(&stats->lock);
+ }
+ }
}
static int check_header(struct sk_buff *skb, int len)
@@ -263,8 +356,8 @@ static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key,
/* The ICMPv6 type and code fields use the 16-bit transport port
* fields, so we need to store them in 16-bit network byte order.
*/
- key->ipv6.tp.src = htons(icmp->icmp6_type);
- key->ipv6.tp.dst = htons(icmp->icmp6_code);
+ key->tp.src = htons(icmp->icmp6_type);
+ key->tp.dst = htons(icmp->icmp6_code);
if (icmp->icmp6_code == 0 &&
(icmp->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION ||
@@ -303,14 +396,14 @@ static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key,
&& opt_len == 8) {
if (unlikely(!is_zero_ether_addr(key->ipv6.nd.sll)))
goto invalid;
- memcpy(key->ipv6.nd.sll,
- &nd->opt[offset+sizeof(*nd_opt)], ETH_ALEN);
+ ether_addr_copy(key->ipv6.nd.sll,
+ &nd->opt[offset+sizeof(*nd_opt)]);
} else if (nd_opt->nd_opt_type == ND_OPT_TARGET_LL_ADDR
&& opt_len == 8) {
if (unlikely(!is_zero_ether_addr(key->ipv6.nd.tll)))
goto invalid;
- memcpy(key->ipv6.nd.tll,
- &nd->opt[offset+sizeof(*nd_opt)], ETH_ALEN);
+ ether_addr_copy(key->ipv6.nd.tll,
+ &nd->opt[offset+sizeof(*nd_opt)]);
}
icmp_len -= opt_len;
@@ -329,10 +422,9 @@ invalid:
}
/**
- * ovs_flow_extract - extracts a flow key from an Ethernet frame.
+ * key_extract - extracts a flow key from an Ethernet frame.
* @skb: sk_buff that contains the frame, with skb->data pointing to the
* Ethernet header
- * @in_port: port number on which @skb was received.
* @key: output flow key
*
* The caller must ensure that skb->len >= ETH_HLEN.
@@ -351,18 +443,13 @@ invalid:
* of a correct length, otherwise the same as skb->network_header.
* For other key->eth.type values it is left untouched.
*/
-int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
+static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
{
int error;
struct ethhdr *eth;
- memset(key, 0, sizeof(*key));
-
- key->phy.priority = skb->priority;
- if (OVS_CB(skb)->tun_key)
- memcpy(&key->tun_key, OVS_CB(skb)->tun_key, sizeof(key->tun_key));
- key->phy.in_port = in_port;
- key->phy.skb_mark = skb->mark;
+ /* Flags are always used as part of stats */
+ key->tp.flags = 0;
skb_reset_mac_header(skb);
@@ -370,14 +457,15 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
* header in the linear data area.
*/
eth = eth_hdr(skb);
- memcpy(key->eth.src, eth->h_source, ETH_ALEN);
- memcpy(key->eth.dst, eth->h_dest, ETH_ALEN);
+ ether_addr_copy(key->eth.src, eth->h_source);
+ ether_addr_copy(key->eth.dst, eth->h_dest);
__skb_pull(skb, 2 * ETH_ALEN);
/* We are going to push all headers that we pull, so no need to
* update skb->csum here.
*/
+ key->eth.tci = 0;
if (vlan_tx_tag_present(skb))
key->eth.tci = htons(skb->vlan_tci);
else if (eth->h_proto == htons(ETH_P_8021Q))
@@ -398,6 +486,8 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
error = check_iphdr(skb);
if (unlikely(error)) {
+ memset(&key->ip, 0, sizeof(key->ip));
+ memset(&key->ipv4, 0, sizeof(key->ipv4));
if (error == -EINVAL) {
skb->transport_header = skb->network_header;
error = 0;
@@ -419,28 +509,37 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
return 0;
}
if (nh->frag_off & htons(IP_MF) ||
- skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+ skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
key->ip.frag = OVS_FRAG_TYPE_FIRST;
+ else
+ key->ip.frag = OVS_FRAG_TYPE_NONE;
/* Transport layer. */
if (key->ip.proto == IPPROTO_TCP) {
if (tcphdr_ok(skb)) {
struct tcphdr *tcp = tcp_hdr(skb);
- key->ipv4.tp.src = tcp->source;
- key->ipv4.tp.dst = tcp->dest;
- key->ipv4.tp.flags = TCP_FLAGS_BE16(tcp);
+ key->tp.src = tcp->source;
+ key->tp.dst = tcp->dest;
+ key->tp.flags = TCP_FLAGS_BE16(tcp);
+ } else {
+ memset(&key->tp, 0, sizeof(key->tp));
}
+
} else if (key->ip.proto == IPPROTO_UDP) {
if (udphdr_ok(skb)) {
struct udphdr *udp = udp_hdr(skb);
- key->ipv4.tp.src = udp->source;
- key->ipv4.tp.dst = udp->dest;
+ key->tp.src = udp->source;
+ key->tp.dst = udp->dest;
+ } else {
+ memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == IPPROTO_SCTP) {
if (sctphdr_ok(skb)) {
struct sctphdr *sctp = sctp_hdr(skb);
- key->ipv4.tp.src = sctp->source;
- key->ipv4.tp.dst = sctp->dest;
+ key->tp.src = sctp->source;
+ key->tp.dst = sctp->dest;
+ } else {
+ memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == IPPROTO_ICMP) {
if (icmphdr_ok(skb)) {
@@ -448,35 +547,46 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
/* The ICMP type and code fields use the 16-bit
* transport port fields, so we need to store
* them in 16-bit network byte order. */
- key->ipv4.tp.src = htons(icmp->type);
- key->ipv4.tp.dst = htons(icmp->code);
+ key->tp.src = htons(icmp->type);
+ key->tp.dst = htons(icmp->code);
+ } else {
+ memset(&key->tp, 0, sizeof(key->tp));
}
}
- } else if ((key->eth.type == htons(ETH_P_ARP) ||
- key->eth.type == htons(ETH_P_RARP)) && arphdr_ok(skb)) {
+ } else if (key->eth.type == htons(ETH_P_ARP) ||
+ key->eth.type == htons(ETH_P_RARP)) {
struct arp_eth_header *arp;
arp = (struct arp_eth_header *)skb_network_header(skb);
- if (arp->ar_hrd == htons(ARPHRD_ETHER)
- && arp->ar_pro == htons(ETH_P_IP)
- && arp->ar_hln == ETH_ALEN
- && arp->ar_pln == 4) {
+ if (arphdr_ok(skb) &&
+ arp->ar_hrd == htons(ARPHRD_ETHER) &&
+ arp->ar_pro == htons(ETH_P_IP) &&
+ arp->ar_hln == ETH_ALEN &&
+ arp->ar_pln == 4) {
/* We only match on the lower 8 bits of the opcode. */
if (ntohs(arp->ar_op) <= 0xff)
key->ip.proto = ntohs(arp->ar_op);
+ else
+ key->ip.proto = 0;
+
memcpy(&key->ipv4.addr.src, arp->ar_sip, sizeof(key->ipv4.addr.src));
memcpy(&key->ipv4.addr.dst, arp->ar_tip, sizeof(key->ipv4.addr.dst));
- memcpy(key->ipv4.arp.sha, arp->ar_sha, ETH_ALEN);
- memcpy(key->ipv4.arp.tha, arp->ar_tha, ETH_ALEN);
+ ether_addr_copy(key->ipv4.arp.sha, arp->ar_sha);
+ ether_addr_copy(key->ipv4.arp.tha, arp->ar_tha);
+ } else {
+ memset(&key->ip, 0, sizeof(key->ip));
+ memset(&key->ipv4, 0, sizeof(key->ipv4));
}
} else if (key->eth.type == htons(ETH_P_IPV6)) {
int nh_len; /* IPv6 Header + Extensions */
nh_len = parse_ipv6hdr(skb, key);
if (unlikely(nh_len < 0)) {
+ memset(&key->ip, 0, sizeof(key->ip));
+ memset(&key->ipv6.addr, 0, sizeof(key->ipv6.addr));
if (nh_len == -EINVAL) {
skb->transport_header = skb->network_header;
error = 0;
@@ -495,30 +605,90 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
if (key->ip.proto == NEXTHDR_TCP) {
if (tcphdr_ok(skb)) {
struct tcphdr *tcp = tcp_hdr(skb);
- key->ipv6.tp.src = tcp->source;
- key->ipv6.tp.dst = tcp->dest;
- key->ipv6.tp.flags = TCP_FLAGS_BE16(tcp);
+ key->tp.src = tcp->source;
+ key->tp.dst = tcp->dest;
+ key->tp.flags = TCP_FLAGS_BE16(tcp);
+ } else {
+ memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == NEXTHDR_UDP) {
if (udphdr_ok(skb)) {
struct udphdr *udp = udp_hdr(skb);
- key->ipv6.tp.src = udp->source;
- key->ipv6.tp.dst = udp->dest;
+ key->tp.src = udp->source;
+ key->tp.dst = udp->dest;
+ } else {
+ memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == NEXTHDR_SCTP) {
if (sctphdr_ok(skb)) {
struct sctphdr *sctp = sctp_hdr(skb);
- key->ipv6.tp.src = sctp->source;
- key->ipv6.tp.dst = sctp->dest;
+ key->tp.src = sctp->source;
+ key->tp.dst = sctp->dest;
+ } else {
+ memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == NEXTHDR_ICMP) {
if (icmp6hdr_ok(skb)) {
error = parse_icmpv6(skb, key, nh_len);
if (error)
return error;
+ } else {
+ memset(&key->tp, 0, sizeof(key->tp));
}
}
}
-
return 0;
}
+
+int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
+{
+ return key_extract(skb, key);
+}
+
+int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info,
+ struct sk_buff *skb, struct sw_flow_key *key)
+{
+ /* Extract metadata from packet. */
+ if (tun_info) {
+ memcpy(&key->tun_key, &tun_info->tunnel, sizeof(key->tun_key));
+
+ if (tun_info->options) {
+ BUILD_BUG_ON((1 << (sizeof(tun_info->options_len) *
+ 8)) - 1
+ > sizeof(key->tun_opts));
+ memcpy(GENEVE_OPTS(key, tun_info->options_len),
+ tun_info->options, tun_info->options_len);
+ key->tun_opts_len = tun_info->options_len;
+ } else {
+ key->tun_opts_len = 0;
+ }
+ } else {
+ key->tun_opts_len = 0;
+ memset(&key->tun_key, 0, sizeof(key->tun_key));
+ }
+
+ key->phy.priority = skb->priority;
+ key->phy.in_port = OVS_CB(skb)->input_vport->port_no;
+ key->phy.skb_mark = skb->mark;
+ key->ovs_flow_hash = 0;
+ key->recirc_id = 0;
+
+ /* Flags are always used as part of stats */
+ key->tp.flags = 0;
+
+ return key_extract(skb, key);
+}
+
+int ovs_flow_key_extract_userspace(const struct nlattr *attr,
+ struct sk_buff *skb,
+ struct sw_flow_key *key)
+{
+ int err;
+
+ /* Extract metadata from netlink attributes. */
+ err = ovs_nla_get_flow_metadata(attr, key);
+ if (err)
+ return err;
+
+ return key_extract(skb, key);
+}
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 1510f51dbf74..71813318c8c7 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2007-2013 Nicira, Inc.
+ * Copyright (c) 2007-2014 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
@@ -19,6 +19,7 @@
#ifndef FLOW_H
#define FLOW_H 1
+#include <linux/cache.h>
#include <linux/kernel.h>
#include <linux/netlink.h>
#include <linux/openvswitch.h>
@@ -46,31 +47,55 @@ struct ovs_key_ipv4_tunnel {
__be16 tun_flags;
u8 ipv4_tos;
u8 ipv4_ttl;
+} __packed __aligned(4); /* Minimize padding. */
+
+struct ovs_tunnel_info {
+ struct ovs_key_ipv4_tunnel tunnel;
+ struct geneve_opt *options;
+ u8 options_len;
};
-static inline void ovs_flow_tun_key_init(struct ovs_key_ipv4_tunnel *tun_key,
- const struct iphdr *iph, __be64 tun_id,
- __be16 tun_flags)
+/* Store options at the end of the array if they are less than the
+ * maximum size. This allows us to get the benefits of variable length
+ * matching for small options.
+ */
+#define GENEVE_OPTS(flow_key, opt_len) \
+ ((struct geneve_opt *)((flow_key)->tun_opts + \
+ FIELD_SIZEOF(struct sw_flow_key, tun_opts) - \
+ opt_len))
+
+static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
+ const struct iphdr *iph,
+ __be64 tun_id, __be16 tun_flags,
+ struct geneve_opt *opts,
+ u8 opts_len)
{
- tun_key->tun_id = tun_id;
- tun_key->ipv4_src = iph->saddr;
- tun_key->ipv4_dst = iph->daddr;
- tun_key->ipv4_tos = iph->tos;
- tun_key->ipv4_ttl = iph->ttl;
- tun_key->tun_flags = tun_flags;
+ tun_info->tunnel.tun_id = tun_id;
+ tun_info->tunnel.ipv4_src = iph->saddr;
+ tun_info->tunnel.ipv4_dst = iph->daddr;
+ tun_info->tunnel.ipv4_tos = iph->tos;
+ tun_info->tunnel.ipv4_ttl = iph->ttl;
+ tun_info->tunnel.tun_flags = tun_flags;
/* clear struct padding. */
- memset((unsigned char *) tun_key + OVS_TUNNEL_KEY_SIZE, 0,
- sizeof(*tun_key) - OVS_TUNNEL_KEY_SIZE);
+ memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE, 0,
+ sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE);
+
+ tun_info->options = opts;
+ tun_info->options_len = opts_len;
}
struct sw_flow_key {
+ u8 tun_opts[255];
+ u8 tun_opts_len;
struct ovs_key_ipv4_tunnel tun_key; /* Encapsulating tunnel key. */
struct {
u32 priority; /* Packet QoS priority. */
u32 skb_mark; /* SKB mark. */
u16 in_port; /* Input switch port (or DP_MAX_PORTS). */
- } phy;
+ } __packed phy; /* Safe when right after 'tun_key'. */
+ u32 ovs_flow_hash; /* Datapath computed hash value. */
+ u32 recirc_id; /* Recirculation ID. */
struct {
u8 src[ETH_ALEN]; /* Ethernet source address. */
u8 dst[ETH_ALEN]; /* Ethernet destination address. */
@@ -83,23 +108,21 @@ struct sw_flow_key {
u8 ttl; /* IP TTL/hop limit. */
u8 frag; /* One of OVS_FRAG_TYPE_*. */
} ip;
+ struct {
+ __be16 src; /* TCP/UDP/SCTP source port. */
+ __be16 dst; /* TCP/UDP/SCTP destination port. */
+ __be16 flags; /* TCP flags. */
+ } tp;
union {
struct {
struct {
__be32 src; /* IP source address. */
__be32 dst; /* IP destination address. */
} addr;
- union {
- struct {
- __be16 src; /* TCP/UDP/SCTP source port. */
- __be16 dst; /* TCP/UDP/SCTP destination port. */
- __be16 flags; /* TCP flags. */
- } tp;
- struct {
- u8 sha[ETH_ALEN]; /* ARP source hardware address. */
- u8 tha[ETH_ALEN]; /* ARP target hardware address. */
- } arp;
- };
+ struct {
+ u8 sha[ETH_ALEN]; /* ARP source hardware address. */
+ u8 tha[ETH_ALEN]; /* ARP target hardware address. */
+ } arp;
} ipv4;
struct {
struct {
@@ -108,11 +131,6 @@ struct sw_flow_key {
} addr;
__be32 label; /* IPv6 flow label. */
struct {
- __be16 src; /* TCP/UDP/SCTP source port. */
- __be16 dst; /* TCP/UDP/SCTP destination port. */
- __be16 flags; /* TCP flags. */
- } tp;
- struct {
struct in6_addr target; /* ND target address. */
u8 sll[ETH_ALEN]; /* ND source link layer address. */
u8 tll[ETH_ALEN]; /* ND target link layer address. */
@@ -122,8 +140,8 @@ struct sw_flow_key {
} __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */
struct sw_flow_key_range {
- size_t start;
- size_t end;
+ unsigned short int start;
+ unsigned short int end;
};
struct sw_flow_mask {
@@ -146,21 +164,30 @@ struct sw_flow_actions {
struct nlattr actions[];
};
+struct flow_stats {
+ u64 packet_count; /* Number of packets matched. */
+ u64 byte_count; /* Number of bytes matched. */
+ unsigned long used; /* Last used time (in jiffies). */
+ spinlock_t lock; /* Lock for atomic stats update. */
+ __be16 tcp_flags; /* Union of seen TCP flags. */
+};
+
struct sw_flow {
struct rcu_head rcu;
struct hlist_node hash_node[2];
u32 hash;
-
+ int stats_last_writer; /* NUMA-node id of the last writer on
+ * 'stats[0]'.
+ */
struct sw_flow_key key;
struct sw_flow_key unmasked_key;
struct sw_flow_mask *mask;
struct sw_flow_actions __rcu *sf_acts;
-
- spinlock_t lock; /* Lock for values below. */
- unsigned long used; /* Last used time (in jiffies). */
- u64 packet_count; /* Number of packets matched. */
- u64 byte_count; /* Number of bytes matched. */
- __be16 tcp_flags; /* Union of seen TCP flags. */
+ struct flow_stats __rcu *stats[]; /* One for each NUMA node. First one
+ * is allocated at flow creation time,
+ * the rest are allocated on demand
+ * while holding the 'stats[0].lock'.
+ */
};
struct arp_eth_header {
@@ -177,9 +204,19 @@ struct arp_eth_header {
unsigned char ar_tip[4]; /* target IP address */
} __packed;
-void ovs_flow_used(struct sw_flow *, struct sk_buff *);
+void ovs_flow_stats_update(struct sw_flow *, __be16 tcp_flags,
+ struct sk_buff *);
+void ovs_flow_stats_get(const struct sw_flow *, struct ovs_flow_stats *,
+ unsigned long *used, __be16 *tcp_flags);
+void ovs_flow_stats_clear(struct sw_flow *);
u64 ovs_flow_used_time(unsigned long flow_jiffies);
-int ovs_flow_extract(struct sk_buff *, u16 in_port, struct sw_flow_key *);
+int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key);
+int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info, struct sk_buff *skb,
+ struct sw_flow_key *key);
+/* Extract key from packet coming from userspace. */
+int ovs_flow_key_extract_userspace(const struct nlattr *attr,
+ struct sk_buff *skb,
+ struct sw_flow_key *key);
#endif /* flow.h */
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 2bc1bc1aca3b..368f23307911 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2007-2013 Nicira, Inc.
+ * Copyright (c) 2007-2014 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
@@ -16,6 +16,8 @@
* 02110-1301, USA
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include "flow.h"
#include "datapath.h"
#include <linux/uaccess.h>
@@ -40,6 +42,7 @@
#include <linux/icmp.h>
#include <linux/icmpv6.h>
#include <linux/rculist.h>
+#include <net/geneve.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ndisc.h>
@@ -86,18 +89,20 @@ static void update_range__(struct sw_flow_match *match,
} \
} while (0)
-#define SW_FLOW_KEY_MEMCPY(match, field, value_p, len, is_mask) \
- do { \
- update_range__(match, offsetof(struct sw_flow_key, field), \
- len, is_mask); \
- if (is_mask) { \
- if ((match)->mask) \
- memcpy(&(match)->mask->key.field, value_p, len);\
- } else { \
- memcpy(&(match)->key->field, value_p, len); \
- } \
+#define SW_FLOW_KEY_MEMCPY_OFFSET(match, offset, value_p, len, is_mask) \
+ do { \
+ update_range__(match, offset, len, is_mask); \
+ if (is_mask) \
+ memcpy((u8 *)&(match)->mask->key + offset, value_p, \
+ len); \
+ else \
+ memcpy((u8 *)(match)->key + offset, value_p, len); \
} while (0)
+#define SW_FLOW_KEY_MEMCPY(match, field, value_p, len, is_mask) \
+ SW_FLOW_KEY_MEMCPY_OFFSET(match, offsetof(struct sw_flow_key, field), \
+ value_p, len, is_mask)
+
static u16 range_n_bytes(const struct sw_flow_key_range *range)
{
return range->end - range->start;
@@ -202,11 +207,11 @@ static bool match_validate(const struct sw_flow_match *match,
if (match->mask && (match->mask->key.ip.proto == 0xff))
mask_allowed |= 1 << OVS_KEY_ATTR_ICMPV6;
- if (match->key->ipv6.tp.src ==
+ if (match->key->tp.src ==
htons(NDISC_NEIGHBOUR_SOLICITATION) ||
- match->key->ipv6.tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
+ match->key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
key_expected |= 1 << OVS_KEY_ATTR_ND;
- if (match->mask && (match->mask->key.ipv6.tp.src == htons(0xffff)))
+ if (match->mask && (match->mask->key.tp.src == htons(0xffff)))
mask_allowed |= 1 << OVS_KEY_ATTR_ND;
}
}
@@ -216,14 +221,14 @@ static bool match_validate(const struct sw_flow_match *match,
if ((key_attrs & key_expected) != key_expected) {
/* Key attributes check failed. */
OVS_NLERR("Missing expected key attributes (key_attrs=%llx, expected=%llx).\n",
- key_attrs, key_expected);
+ (unsigned long long)key_attrs, (unsigned long long)key_expected);
return false;
}
if ((mask_attrs & mask_allowed) != mask_attrs) {
/* Mask attributes check failed. */
OVS_NLERR("Contain more than allowed mask fields (mask_attrs=%llx, mask_allowed=%llx).\n",
- mask_attrs, mask_allowed);
+ (unsigned long long)mask_attrs, (unsigned long long)mask_allowed);
return false;
}
@@ -249,6 +254,8 @@ static const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
[OVS_KEY_ATTR_ICMPV6] = sizeof(struct ovs_key_icmpv6),
[OVS_KEY_ATTR_ARP] = sizeof(struct ovs_key_arp),
[OVS_KEY_ATTR_ND] = sizeof(struct ovs_key_nd),
+ [OVS_KEY_ATTR_RECIRC_ID] = sizeof(u32),
+ [OVS_KEY_ATTR_DP_HASH] = sizeof(u32),
[OVS_KEY_ATTR_TUNNEL] = -1,
};
@@ -331,6 +338,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
int rem;
bool ttl = false;
__be16 tun_flags = 0;
+ unsigned long opt_key_offset;
nla_for_each_nested(a, attr, rem) {
int type = nla_type(a);
@@ -342,6 +350,8 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
[OVS_TUNNEL_KEY_ATTR_TTL] = 1,
[OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = 0,
[OVS_TUNNEL_KEY_ATTR_CSUM] = 0,
+ [OVS_TUNNEL_KEY_ATTR_OAM] = 0,
+ [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = -1,
};
if (type > OVS_TUNNEL_KEY_ATTR_MAX) {
@@ -350,7 +360,8 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
return -EINVAL;
}
- if (ovs_tunnel_key_lens[type] != nla_len(a)) {
+ if (ovs_tunnel_key_lens[type] != nla_len(a) &&
+ ovs_tunnel_key_lens[type] != -1) {
OVS_NLERR("IPv4 tunnel attribute type has unexpected "
" length (type=%d, length=%d, expected=%d).\n",
type, nla_len(a), ovs_tunnel_key_lens[type]);
@@ -386,7 +397,63 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
case OVS_TUNNEL_KEY_ATTR_CSUM:
tun_flags |= TUNNEL_CSUM;
break;
+ case OVS_TUNNEL_KEY_ATTR_OAM:
+ tun_flags |= TUNNEL_OAM;
+ break;
+ case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS:
+ tun_flags |= TUNNEL_OPTIONS_PRESENT;
+ if (nla_len(a) > sizeof(match->key->tun_opts)) {
+ OVS_NLERR("Geneve option length exceeds maximum size (len %d, max %zu).\n",
+ nla_len(a),
+ sizeof(match->key->tun_opts));
+ return -EINVAL;
+ }
+
+ if (nla_len(a) % 4 != 0) {
+ OVS_NLERR("Geneve option length is not a multiple of 4 (len %d).\n",
+ nla_len(a));
+ return -EINVAL;
+ }
+
+ /* We need to record the length of the options passed
+ * down, otherwise packets with the same format but
+ * additional options will be silently matched.
+ */
+ if (!is_mask) {
+ SW_FLOW_KEY_PUT(match, tun_opts_len, nla_len(a),
+ false);
+ } else {
+ /* This is somewhat unusual because it looks at
+ * both the key and mask while parsing the
+ * attributes (and by extension assumes the key
+ * is parsed first). Normally, we would verify
+ * that each is the correct length and that the
+ * attributes line up in the validate function.
+ * However, that is difficult because this is
+ * variable length and we won't have the
+ * information later.
+ */
+ if (match->key->tun_opts_len != nla_len(a)) {
+ OVS_NLERR("Geneve option key length (%d) is different from mask length (%d).",
+ match->key->tun_opts_len,
+ nla_len(a));
+ return -EINVAL;
+ }
+
+ SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff,
+ true);
+ }
+
+ opt_key_offset = (unsigned long)GENEVE_OPTS(
+ (struct sw_flow_key *)0,
+ nla_len(a));
+ SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset,
+ nla_data(a), nla_len(a),
+ is_mask);
+ break;
default:
+ OVS_NLERR("Unknown IPv4 tunnel attribute (%d).\n",
+ type);
return -EINVAL;
}
}
@@ -413,45 +480,80 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
return 0;
}
-static int ipv4_tun_to_nlattr(struct sk_buff *skb,
- const struct ovs_key_ipv4_tunnel *tun_key,
- const struct ovs_key_ipv4_tunnel *output)
+static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
+ const struct ovs_key_ipv4_tunnel *output,
+ const struct geneve_opt *tun_opts,
+ int swkey_tun_opts_len)
{
- struct nlattr *nla;
-
- nla = nla_nest_start(skb, OVS_KEY_ATTR_TUNNEL);
- if (!nla)
- return -EMSGSIZE;
-
if (output->tun_flags & TUNNEL_KEY &&
nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id))
return -EMSGSIZE;
if (output->ipv4_src &&
- nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, output->ipv4_src))
+ nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, output->ipv4_src))
return -EMSGSIZE;
if (output->ipv4_dst &&
- nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, output->ipv4_dst))
+ nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, output->ipv4_dst))
return -EMSGSIZE;
if (output->ipv4_tos &&
- nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->ipv4_tos))
+ nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->ipv4_tos))
return -EMSGSIZE;
if (nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TTL, output->ipv4_ttl))
return -EMSGSIZE;
if ((output->tun_flags & TUNNEL_DONT_FRAGMENT) &&
- nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT))
+ nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT))
return -EMSGSIZE;
if ((output->tun_flags & TUNNEL_CSUM) &&
- nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM))
+ nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM))
+ return -EMSGSIZE;
+ if ((output->tun_flags & TUNNEL_OAM) &&
+ nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM))
+ return -EMSGSIZE;
+ if (tun_opts &&
+ nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS,
+ swkey_tun_opts_len, tun_opts))
return -EMSGSIZE;
- nla_nest_end(skb, nla);
return 0;
}
+static int ipv4_tun_to_nlattr(struct sk_buff *skb,
+ const struct ovs_key_ipv4_tunnel *output,
+ const struct geneve_opt *tun_opts,
+ int swkey_tun_opts_len)
+{
+ struct nlattr *nla;
+ int err;
+
+ nla = nla_nest_start(skb, OVS_KEY_ATTR_TUNNEL);
+ if (!nla)
+ return -EMSGSIZE;
+
+ err = __ipv4_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len);
+ if (err)
+ return err;
+
+ nla_nest_end(skb, nla);
+ return 0;
+}
+
static int metadata_from_nlattrs(struct sw_flow_match *match, u64 *attrs,
const struct nlattr **a, bool is_mask)
{
+ if (*attrs & (1 << OVS_KEY_ATTR_DP_HASH)) {
+ u32 hash_val = nla_get_u32(a[OVS_KEY_ATTR_DP_HASH]);
+
+ SW_FLOW_KEY_PUT(match, ovs_flow_hash, hash_val, is_mask);
+ *attrs &= ~(1 << OVS_KEY_ATTR_DP_HASH);
+ }
+
+ if (*attrs & (1 << OVS_KEY_ATTR_RECIRC_ID)) {
+ u32 recirc_id = nla_get_u32(a[OVS_KEY_ATTR_RECIRC_ID]);
+
+ SW_FLOW_KEY_PUT(match, recirc_id, recirc_id, is_mask);
+ *attrs &= ~(1 << OVS_KEY_ATTR_RECIRC_ID);
+ }
+
if (*attrs & (1 << OVS_KEY_ATTR_PRIORITY)) {
SW_FLOW_KEY_PUT(match, phy.priority,
nla_get_u32(a[OVS_KEY_ATTR_PRIORITY]), is_mask);
@@ -487,7 +589,7 @@ static int metadata_from_nlattrs(struct sw_flow_match *match, u64 *attrs,
return 0;
}
-static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
+static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
const struct nlattr **a, bool is_mask)
{
int err;
@@ -628,27 +730,18 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
const struct ovs_key_tcp *tcp_key;
tcp_key = nla_data(a[OVS_KEY_ATTR_TCP]);
- if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) {
- SW_FLOW_KEY_PUT(match, ipv4.tp.src,
- tcp_key->tcp_src, is_mask);
- SW_FLOW_KEY_PUT(match, ipv4.tp.dst,
- tcp_key->tcp_dst, is_mask);
- } else {
- SW_FLOW_KEY_PUT(match, ipv6.tp.src,
- tcp_key->tcp_src, is_mask);
- SW_FLOW_KEY_PUT(match, ipv6.tp.dst,
- tcp_key->tcp_dst, is_mask);
- }
+ SW_FLOW_KEY_PUT(match, tp.src, tcp_key->tcp_src, is_mask);
+ SW_FLOW_KEY_PUT(match, tp.dst, tcp_key->tcp_dst, is_mask);
attrs &= ~(1 << OVS_KEY_ATTR_TCP);
}
if (attrs & (1 << OVS_KEY_ATTR_TCP_FLAGS)) {
if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) {
- SW_FLOW_KEY_PUT(match, ipv4.tp.flags,
+ SW_FLOW_KEY_PUT(match, tp.flags,
nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]),
is_mask);
} else {
- SW_FLOW_KEY_PUT(match, ipv6.tp.flags,
+ SW_FLOW_KEY_PUT(match, tp.flags,
nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]),
is_mask);
}
@@ -659,17 +752,8 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
const struct ovs_key_udp *udp_key;
udp_key = nla_data(a[OVS_KEY_ATTR_UDP]);
- if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) {
- SW_FLOW_KEY_PUT(match, ipv4.tp.src,
- udp_key->udp_src, is_mask);
- SW_FLOW_KEY_PUT(match, ipv4.tp.dst,
- udp_key->udp_dst, is_mask);
- } else {
- SW_FLOW_KEY_PUT(match, ipv6.tp.src,
- udp_key->udp_src, is_mask);
- SW_FLOW_KEY_PUT(match, ipv6.tp.dst,
- udp_key->udp_dst, is_mask);
- }
+ SW_FLOW_KEY_PUT(match, tp.src, udp_key->udp_src, is_mask);
+ SW_FLOW_KEY_PUT(match, tp.dst, udp_key->udp_dst, is_mask);
attrs &= ~(1 << OVS_KEY_ATTR_UDP);
}
@@ -677,17 +761,8 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
const struct ovs_key_sctp *sctp_key;
sctp_key = nla_data(a[OVS_KEY_ATTR_SCTP]);
- if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) {
- SW_FLOW_KEY_PUT(match, ipv4.tp.src,
- sctp_key->sctp_src, is_mask);
- SW_FLOW_KEY_PUT(match, ipv4.tp.dst,
- sctp_key->sctp_dst, is_mask);
- } else {
- SW_FLOW_KEY_PUT(match, ipv6.tp.src,
- sctp_key->sctp_src, is_mask);
- SW_FLOW_KEY_PUT(match, ipv6.tp.dst,
- sctp_key->sctp_dst, is_mask);
- }
+ SW_FLOW_KEY_PUT(match, tp.src, sctp_key->sctp_src, is_mask);
+ SW_FLOW_KEY_PUT(match, tp.dst, sctp_key->sctp_dst, is_mask);
attrs &= ~(1 << OVS_KEY_ATTR_SCTP);
}
@@ -695,9 +770,9 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
const struct ovs_key_icmp *icmp_key;
icmp_key = nla_data(a[OVS_KEY_ATTR_ICMP]);
- SW_FLOW_KEY_PUT(match, ipv4.tp.src,
+ SW_FLOW_KEY_PUT(match, tp.src,
htons(icmp_key->icmp_type), is_mask);
- SW_FLOW_KEY_PUT(match, ipv4.tp.dst,
+ SW_FLOW_KEY_PUT(match, tp.dst,
htons(icmp_key->icmp_code), is_mask);
attrs &= ~(1 << OVS_KEY_ATTR_ICMP);
}
@@ -706,9 +781,9 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
const struct ovs_key_icmpv6 *icmpv6_key;
icmpv6_key = nla_data(a[OVS_KEY_ATTR_ICMPV6]);
- SW_FLOW_KEY_PUT(match, ipv6.tp.src,
+ SW_FLOW_KEY_PUT(match, tp.src,
htons(icmpv6_key->icmpv6_type), is_mask);
- SW_FLOW_KEY_PUT(match, ipv6.tp.dst,
+ SW_FLOW_KEY_PUT(match, tp.dst,
htons(icmpv6_key->icmpv6_code), is_mask);
attrs &= ~(1 << OVS_KEY_ATTR_ICMPV6);
}
@@ -861,7 +936,7 @@ int ovs_nla_get_match(struct sw_flow_match *match,
/**
* ovs_nla_get_flow_metadata - parses Netlink attributes into a flow key.
- * @flow: Receives extracted in_port, priority, tun_key and skb_mark.
+ * @key: Receives extracted in_port, priority, tun_key and skb_mark.
* @attr: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute
* sequence.
*
@@ -871,32 +946,24 @@ int ovs_nla_get_match(struct sw_flow_match *match,
* extracted from the packet itself.
*/
-int ovs_nla_get_flow_metadata(struct sw_flow *flow,
- const struct nlattr *attr)
+int ovs_nla_get_flow_metadata(const struct nlattr *attr,
+ struct sw_flow_key *key)
{
- struct ovs_key_ipv4_tunnel *tun_key = &flow->key.tun_key;
const struct nlattr *a[OVS_KEY_ATTR_MAX + 1];
+ struct sw_flow_match match;
u64 attrs = 0;
int err;
- struct sw_flow_match match;
-
- flow->key.phy.in_port = DP_MAX_PORTS;
- flow->key.phy.priority = 0;
- flow->key.phy.skb_mark = 0;
- memset(tun_key, 0, sizeof(flow->key.tun_key));
err = parse_flow_nlattrs(attr, a, &attrs);
if (err)
return -EINVAL;
memset(&match, 0, sizeof(match));
- match.key = &flow->key;
+ match.key = key;
- err = metadata_from_nlattrs(&match, &attrs, a, false);
- if (err)
- return err;
+ key->phy.in_port = DP_MAX_PORTS;
- return 0;
+ return metadata_from_nlattrs(&match, &attrs, a, false);
}
int ovs_nla_put_flow(const struct sw_flow_key *swkey,
@@ -906,13 +973,26 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
struct nlattr *nla, *encap;
bool is_mask = (swkey != output);
- if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority))
+ if (nla_put_u32(skb, OVS_KEY_ATTR_RECIRC_ID, output->recirc_id))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, OVS_KEY_ATTR_DP_HASH, output->ovs_flow_hash))
goto nla_put_failure;
- if ((swkey->tun_key.ipv4_dst || is_mask) &&
- ipv4_tun_to_nlattr(skb, &swkey->tun_key, &output->tun_key))
+ if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority))
goto nla_put_failure;
+ if ((swkey->tun_key.ipv4_dst || is_mask)) {
+ const struct geneve_opt *opts = NULL;
+
+ if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT)
+ opts = GENEVE_OPTS(output, swkey->tun_opts_len);
+
+ if (ipv4_tun_to_nlattr(skb, &output->tun_key, opts,
+ swkey->tun_opts_len))
+ goto nla_put_failure;
+ }
+
if (swkey->phy.in_port == DP_MAX_PORTS) {
if (is_mask && (output->phy.in_port == 0xffff))
if (nla_put_u32(skb, OVS_KEY_ATTR_IN_PORT, 0xffffffff))
@@ -934,8 +1014,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
goto nla_put_failure;
eth_key = nla_data(nla);
- memcpy(eth_key->eth_src, output->eth.src, ETH_ALEN);
- memcpy(eth_key->eth_dst, output->eth.dst, ETH_ALEN);
+ ether_addr_copy(eth_key->eth_src, output->eth.src);
+ ether_addr_copy(eth_key->eth_dst, output->eth.dst);
if (swkey->eth.tci || swkey->eth.type == htons(ETH_P_8021Q)) {
__be16 eth_type;
@@ -1007,8 +1087,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
arp_key->arp_sip = output->ipv4.addr.src;
arp_key->arp_tip = output->ipv4.addr.dst;
arp_key->arp_op = htons(output->ip.proto);
- memcpy(arp_key->arp_sha, output->ipv4.arp.sha, ETH_ALEN);
- memcpy(arp_key->arp_tha, output->ipv4.arp.tha, ETH_ALEN);
+ ether_addr_copy(arp_key->arp_sha, output->ipv4.arp.sha);
+ ether_addr_copy(arp_key->arp_tha, output->ipv4.arp.tha);
}
if ((swkey->eth.type == htons(ETH_P_IP) ||
@@ -1022,19 +1102,11 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
if (!nla)
goto nla_put_failure;
tcp_key = nla_data(nla);
- if (swkey->eth.type == htons(ETH_P_IP)) {
- tcp_key->tcp_src = output->ipv4.tp.src;
- tcp_key->tcp_dst = output->ipv4.tp.dst;
- if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS,
- output->ipv4.tp.flags))
- goto nla_put_failure;
- } else if (swkey->eth.type == htons(ETH_P_IPV6)) {
- tcp_key->tcp_src = output->ipv6.tp.src;
- tcp_key->tcp_dst = output->ipv6.tp.dst;
- if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS,
- output->ipv6.tp.flags))
- goto nla_put_failure;
- }
+ tcp_key->tcp_src = output->tp.src;
+ tcp_key->tcp_dst = output->tp.dst;
+ if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS,
+ output->tp.flags))
+ goto nla_put_failure;
} else if (swkey->ip.proto == IPPROTO_UDP) {
struct ovs_key_udp *udp_key;
@@ -1042,13 +1114,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
if (!nla)
goto nla_put_failure;
udp_key = nla_data(nla);
- if (swkey->eth.type == htons(ETH_P_IP)) {
- udp_key->udp_src = output->ipv4.tp.src;
- udp_key->udp_dst = output->ipv4.tp.dst;
- } else if (swkey->eth.type == htons(ETH_P_IPV6)) {
- udp_key->udp_src = output->ipv6.tp.src;
- udp_key->udp_dst = output->ipv6.tp.dst;
- }
+ udp_key->udp_src = output->tp.src;
+ udp_key->udp_dst = output->tp.dst;
} else if (swkey->ip.proto == IPPROTO_SCTP) {
struct ovs_key_sctp *sctp_key;
@@ -1056,13 +1123,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
if (!nla)
goto nla_put_failure;
sctp_key = nla_data(nla);
- if (swkey->eth.type == htons(ETH_P_IP)) {
- sctp_key->sctp_src = swkey->ipv4.tp.src;
- sctp_key->sctp_dst = swkey->ipv4.tp.dst;
- } else if (swkey->eth.type == htons(ETH_P_IPV6)) {
- sctp_key->sctp_src = swkey->ipv6.tp.src;
- sctp_key->sctp_dst = swkey->ipv6.tp.dst;
- }
+ sctp_key->sctp_src = output->tp.src;
+ sctp_key->sctp_dst = output->tp.dst;
} else if (swkey->eth.type == htons(ETH_P_IP) &&
swkey->ip.proto == IPPROTO_ICMP) {
struct ovs_key_icmp *icmp_key;
@@ -1071,8 +1133,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
if (!nla)
goto nla_put_failure;
icmp_key = nla_data(nla);
- icmp_key->icmp_type = ntohs(output->ipv4.tp.src);
- icmp_key->icmp_code = ntohs(output->ipv4.tp.dst);
+ icmp_key->icmp_type = ntohs(output->tp.src);
+ icmp_key->icmp_code = ntohs(output->tp.dst);
} else if (swkey->eth.type == htons(ETH_P_IPV6) &&
swkey->ip.proto == IPPROTO_ICMPV6) {
struct ovs_key_icmpv6 *icmpv6_key;
@@ -1082,8 +1144,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
if (!nla)
goto nla_put_failure;
icmpv6_key = nla_data(nla);
- icmpv6_key->icmpv6_type = ntohs(output->ipv6.tp.src);
- icmpv6_key->icmpv6_code = ntohs(output->ipv6.tp.dst);
+ icmpv6_key->icmpv6_type = ntohs(output->tp.src);
+ icmpv6_key->icmpv6_code = ntohs(output->tp.dst);
if (icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_SOLICITATION ||
icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_ADVERTISEMENT) {
@@ -1095,8 +1157,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
nd_key = nla_data(nla);
memcpy(nd_key->nd_target, &output->ipv6.nd.target,
sizeof(nd_key->nd_target));
- memcpy(nd_key->nd_sll, output->ipv6.nd.sll, ETH_ALEN);
- memcpy(nd_key->nd_tll, output->ipv6.nd.tll, ETH_ALEN);
+ ether_addr_copy(nd_key->nd_sll, output->ipv6.nd.sll);
+ ether_addr_copy(nd_key->nd_tll, output->ipv6.nd.tll);
}
}
}
@@ -1128,19 +1190,11 @@ struct sw_flow_actions *ovs_nla_alloc_flow_actions(int size)
return sfa;
}
-/* RCU callback used by ovs_nla_free_flow_actions. */
-static void rcu_free_acts_callback(struct rcu_head *rcu)
-{
- struct sw_flow_actions *sf_acts = container_of(rcu,
- struct sw_flow_actions, rcu);
- kfree(sf_acts);
-}
-
/* Schedules 'sf_acts' to be freed after the next RCU grace period.
* The caller must hold rcu_read_lock for this to be sensible. */
void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
{
- call_rcu(&sf_acts->rcu, rcu_free_acts_callback);
+ kfree_rcu(sf_acts, rcu);
}
static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
@@ -1178,13 +1232,14 @@ out:
return (struct nlattr *) ((unsigned char *)(*sfa) + next_offset);
}
-static int add_action(struct sw_flow_actions **sfa, int attrtype, void *data, int len)
+static struct nlattr *__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);
+ return a;
a->nla_type = attrtype;
a->nla_len = nla_attr_size(len);
@@ -1193,6 +1248,18 @@ static int add_action(struct sw_flow_actions **sfa, int attrtype, void *data, in
memcpy(nla_data(a), data, len);
memset((unsigned char *) a + a->nla_len, 0, nla_padlen(len));
+ return a;
+}
+
+static int add_action(struct sw_flow_actions **sfa, int attrtype,
+ void *data, int len)
+{
+ struct nlattr *a;
+
+ a = __add_action(sfa, attrtype, data, len);
+ if (IS_ERR(a))
+ return PTR_ERR(a);
+
return 0;
}
@@ -1269,13 +1336,10 @@ static int validate_and_copy_sample(const struct nlattr *attr,
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;
- }
+ if ((flow_key->eth.type == htons(ETH_P_IP) ||
+ flow_key->eth.type == htons(ETH_P_IPV6)) &&
+ (flow_key->tp.src || flow_key->tp.dst))
+ return 0;
return -EINVAL;
}
@@ -1301,6 +1365,8 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
{
struct sw_flow_match match;
struct sw_flow_key key;
+ struct ovs_tunnel_info *tun_info;
+ struct nlattr *a;
int err, start;
ovs_match_init(&match, &key, NULL);
@@ -1308,12 +1374,56 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
if (err)
return err;
+ if (key.tun_opts_len) {
+ struct geneve_opt *option = GENEVE_OPTS(&key,
+ key.tun_opts_len);
+ int opts_len = key.tun_opts_len;
+ bool crit_opt = false;
+
+ while (opts_len > 0) {
+ int len;
+
+ if (opts_len < sizeof(*option))
+ return -EINVAL;
+
+ len = sizeof(*option) + option->length * 4;
+ if (len > opts_len)
+ return -EINVAL;
+
+ crit_opt |= !!(option->type & GENEVE_CRIT_OPT_TYPE);
+
+ option = (struct geneve_opt *)((u8 *)option + len);
+ opts_len -= len;
+ };
+
+ key.tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0;
+ };
+
start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET);
if (start < 0)
return start;
- err = add_action(sfa, OVS_KEY_ATTR_IPV4_TUNNEL, &match.key->tun_key,
- sizeof(match.key->tun_key));
+ a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL,
+ sizeof(*tun_info) + key.tun_opts_len);
+ if (IS_ERR(a))
+ return PTR_ERR(a);
+
+ tun_info = nla_data(a);
+ tun_info->tunnel = key.tun_key;
+ tun_info->options_len = key.tun_opts_len;
+
+ if (tun_info->options_len) {
+ /* We need to store the options in the action itself since
+ * everything else will go away after flow setup. We can append
+ * it to tun_info and then point there.
+ */
+ memcpy((tun_info + 1), GENEVE_OPTS(&key, key.tun_opts_len),
+ key.tun_opts_len);
+ tun_info->options = (struct geneve_opt *)(tun_info + 1);
+ } else {
+ tun_info->options = NULL;
+ }
+
add_nested_action_end(*sfa, start);
return err;
@@ -1463,11 +1573,13 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
/* Expected argument lengths, (u32)-1 for variable length. */
static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = {
[OVS_ACTION_ATTR_OUTPUT] = sizeof(u32),
+ [OVS_ACTION_ATTR_RECIRC] = sizeof(u32),
[OVS_ACTION_ATTR_USERSPACE] = (u32)-1,
[OVS_ACTION_ATTR_PUSH_VLAN] = sizeof(struct ovs_action_push_vlan),
[OVS_ACTION_ATTR_POP_VLAN] = 0,
[OVS_ACTION_ATTR_SET] = (u32)-1,
- [OVS_ACTION_ATTR_SAMPLE] = (u32)-1
+ [OVS_ACTION_ATTR_SAMPLE] = (u32)-1,
+ [OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash)
};
const struct ovs_action_push_vlan *vlan;
int type = nla_type(a);
@@ -1494,6 +1606,18 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
return -EINVAL;
break;
+ case OVS_ACTION_ATTR_HASH: {
+ const struct ovs_action_hash *act_hash = nla_data(a);
+
+ switch (act_hash->hash_alg) {
+ case OVS_HASH_ALG_L4:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ break;
+ }
case OVS_ACTION_ATTR_POP_VLAN:
break;
@@ -1506,6 +1630,9 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
return -EINVAL;
break;
+ case OVS_ACTION_ATTR_RECIRC:
+ break;
+
case OVS_ACTION_ATTR_SET:
err = validate_set(a, key, sfa, &skip_copy);
if (err)
@@ -1579,17 +1706,22 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
int err;
switch (key_type) {
- case OVS_KEY_ATTR_IPV4_TUNNEL:
+ case OVS_KEY_ATTR_TUNNEL_INFO: {
+ struct ovs_tunnel_info *tun_info = nla_data(ovs_key);
+
start = nla_nest_start(skb, OVS_ACTION_ATTR_SET);
if (!start)
return -EMSGSIZE;
- err = ipv4_tun_to_nlattr(skb, nla_data(ovs_key),
- nla_data(ovs_key));
+ err = ipv4_tun_to_nlattr(skb, &tun_info->tunnel,
+ tun_info->options_len ?
+ tun_info->options : NULL,
+ tun_info->options_len);
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;
diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h
index 440151045d39..206e45add888 100644
--- a/net/openvswitch/flow_netlink.h
+++ b/net/openvswitch/flow_netlink.h
@@ -42,8 +42,8 @@ void ovs_match_init(struct sw_flow_match *match,
int ovs_nla_put_flow(const struct sw_flow_key *,
const struct sw_flow_key *, struct sk_buff *);
-int ovs_nla_get_flow_metadata(struct sw_flow *flow,
- const struct nlattr *attr);
+int ovs_nla_get_flow_metadata(const struct nlattr *, struct sw_flow_key *);
+
int ovs_nla_get_match(struct sw_flow_match *match,
const struct nlattr *,
const struct nlattr *);
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index e42542706087..cf2d853646f0 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -25,7 +25,7 @@
#include <linux/if_vlan.h>
#include <net/llc_pdu.h>
#include <linux/kernel.h>
-#include <linux/jhash.h>
+#include <linux/hash.h>
#include <linux/jiffies.h>
#include <linux/llc.h>
#include <linux/module.h>
@@ -44,12 +44,11 @@
#include <net/ipv6.h>
#include <net/ndisc.h>
-#include "datapath.h"
-
#define TBL_MIN_BUCKETS 1024
#define REHASH_INTERVAL (10 * 60 * HZ)
static struct kmem_cache *flow_cache;
+struct kmem_cache *flow_stats_cache __read_mostly;
static u16 range_n_bytes(const struct sw_flow_key_range *range)
{
@@ -59,8 +58,10 @@ static u16 range_n_bytes(const struct sw_flow_key_range *range)
void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
const struct sw_flow_mask *mask)
{
- const long *m = (long *)((u8 *)&mask->key + mask->range.start);
- const long *s = (long *)((u8 *)src + mask->range.start);
+ const long *m = (const long *)((const u8 *)&mask->key +
+ mask->range.start);
+ const long *s = (const long *)((const u8 *)src +
+ mask->range.start);
long *d = (long *)((u8 *)dst + mask->range.start);
int i;
@@ -75,16 +76,35 @@ void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
struct sw_flow *ovs_flow_alloc(void)
{
struct sw_flow *flow;
+ struct flow_stats *stats;
+ int node;
flow = kmem_cache_alloc(flow_cache, GFP_KERNEL);
if (!flow)
return ERR_PTR(-ENOMEM);
- spin_lock_init(&flow->lock);
flow->sf_acts = NULL;
flow->mask = NULL;
+ flow->stats_last_writer = NUMA_NO_NODE;
+
+ /* Initialize the default stat node. */
+ stats = kmem_cache_alloc_node(flow_stats_cache,
+ GFP_KERNEL | __GFP_ZERO, 0);
+ if (!stats)
+ goto err;
+
+ spin_lock_init(&stats->lock);
+
+ RCU_INIT_POINTER(flow->stats[0], stats);
+
+ for_each_node(node)
+ if (node != 0)
+ RCU_INIT_POINTER(flow->stats[node], NULL);
return flow;
+err:
+ kmem_cache_free(flow_cache, flow);
+ return ERR_PTR(-ENOMEM);
}
int ovs_flow_tbl_count(struct flow_table *table)
@@ -117,7 +137,13 @@ static struct flex_array *alloc_buckets(unsigned int n_buckets)
static void flow_free(struct sw_flow *flow)
{
- kfree((struct sf_flow_acts __force *)flow->sf_acts);
+ int node;
+
+ kfree((struct sw_flow_actions __force *)flow->sf_acts);
+ for_each_node(node)
+ if (flow->stats[node])
+ kmem_cache_free(flow_stats_cache,
+ (struct flow_stats __force *)flow->stats[node]);
kmem_cache_free(flow_cache, flow);
}
@@ -128,37 +154,11 @@ static void rcu_free_flow_callback(struct rcu_head *rcu)
flow_free(flow);
}
-static void rcu_free_sw_flow_mask_cb(struct rcu_head *rcu)
-{
- struct sw_flow_mask *mask = container_of(rcu, struct sw_flow_mask, rcu);
-
- kfree(mask);
-}
-
-static void flow_mask_del_ref(struct sw_flow_mask *mask, bool deferred)
-{
- if (!mask)
- return;
-
- BUG_ON(!mask->ref_count);
- mask->ref_count--;
-
- if (!mask->ref_count) {
- list_del_rcu(&mask->list);
- if (deferred)
- call_rcu(&mask->rcu, rcu_free_sw_flow_mask_cb);
- else
- kfree(mask);
- }
-}
-
void ovs_flow_free(struct sw_flow *flow, bool deferred)
{
if (!flow)
return;
- flow_mask_del_ref(flow->mask, deferred);
-
if (deferred)
call_rcu(&flow->rcu, rcu_free_flow_callback);
else
@@ -170,26 +170,9 @@ static void free_buckets(struct flex_array *buckets)
flex_array_free(buckets);
}
+
static void __table_instance_destroy(struct table_instance *ti)
{
- int i;
-
- if (ti->keep_flows)
- goto skip_flows;
-
- for (i = 0; i < ti->n_buckets; i++) {
- struct sw_flow *flow;
- struct hlist_head *head = flex_array_get(ti->buckets, i);
- struct hlist_node *n;
- int ver = ti->node_ver;
-
- hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) {
- hlist_del(&flow->hash_node[ver]);
- ovs_flow_free(flow, false);
- }
- }
-
-skip_flows:
free_buckets(ti->buckets);
kfree(ti);
}
@@ -240,20 +223,38 @@ static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu)
static void table_instance_destroy(struct table_instance *ti, bool deferred)
{
+ int i;
+
if (!ti)
return;
+ if (ti->keep_flows)
+ goto skip_flows;
+
+ for (i = 0; i < ti->n_buckets; i++) {
+ struct sw_flow *flow;
+ struct hlist_head *head = flex_array_get(ti->buckets, i);
+ struct hlist_node *n;
+ int ver = ti->node_ver;
+
+ hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) {
+ hlist_del_rcu(&flow->hash_node[ver]);
+ ovs_flow_free(flow, deferred);
+ }
+ }
+
+skip_flows:
if (deferred)
call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
else
__table_instance_destroy(ti);
}
-void ovs_flow_tbl_destroy(struct flow_table *table)
+void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred)
{
struct table_instance *ti = ovsl_dereference(table->ti);
- table_instance_destroy(ti, false);
+ table_instance_destroy(ti, deferred);
}
struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti,
@@ -356,13 +357,13 @@ int ovs_flow_tbl_flush(struct flow_table *flow_table)
static u32 flow_hash(const struct sw_flow_key *key, int key_start,
int key_end)
{
- u32 *hash_key = (u32 *)((u8 *)key + key_start);
+ const u32 *hash_key = (const u32 *)((const u8 *)key + key_start);
int hash_u32s = (key_end - key_start) >> 2;
/* Make sure number of hash bytes are multiple of u32. */
BUILD_BUG_ON(sizeof(long) % sizeof(u32));
- return jhash2(hash_key, hash_u32s, 0);
+ return arch_fast_hash2(hash_key, hash_u32s, 0);
}
static int flow_key_start(const struct sw_flow_key *key)
@@ -378,8 +379,8 @@ static bool cmp_key(const struct sw_flow_key *key1,
const struct sw_flow_key *key2,
int key_start, int key_end)
{
- const long *cp1 = (long *)((u8 *)key1 + key_start);
- const long *cp2 = (long *)((u8 *)key2 + key_start);
+ const long *cp1 = (const long *)((const u8 *)key1 + key_start);
+ const long *cp2 = (const long *)((const u8 *)key2 + key_start);
long diffs = 0;
int i;
@@ -429,11 +430,11 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
return NULL;
}
-struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
+struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *tbl,
const struct sw_flow_key *key,
u32 *n_mask_hit)
{
- struct table_instance *ti = rcu_dereference(tbl->ti);
+ struct table_instance *ti = rcu_dereference_ovsl(tbl->ti);
struct sw_flow_mask *mask;
struct sw_flow *flow;
@@ -447,6 +448,30 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
return NULL;
}
+struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
+ const struct sw_flow_key *key)
+{
+ u32 __always_unused n_mask_hit;
+
+ return ovs_flow_tbl_lookup_stats(tbl, key, &n_mask_hit);
+}
+
+struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
+ struct sw_flow_match *match)
+{
+ struct table_instance *ti = rcu_dereference_ovsl(tbl->ti);
+ struct sw_flow_mask *mask;
+ struct sw_flow *flow;
+
+ /* Always called under ovs-mutex. */
+ list_for_each_entry(mask, &tbl->mask_list, list) {
+ flow = masked_flow_lookup(ti, match->key, mask);
+ if (flow && ovs_flow_cmp_unmasked_key(flow, match)) /* Found */
+ return flow;
+ }
+ return NULL;
+}
+
int ovs_flow_tbl_num_masks(const struct flow_table *table)
{
struct sw_flow_mask *mask;
@@ -463,6 +488,25 @@ static struct table_instance *table_instance_expand(struct table_instance *ti)
return table_instance_rehash(ti, ti->n_buckets * 2);
}
+/* Remove 'mask' from the mask list, if it is not needed any more. */
+static void flow_mask_remove(struct flow_table *tbl, struct sw_flow_mask *mask)
+{
+ if (mask) {
+ /* ovs-lock is required to protect mask-refcount and
+ * mask list.
+ */
+ ASSERT_OVSL();
+ BUG_ON(!mask->ref_count);
+ mask->ref_count--;
+
+ if (!mask->ref_count) {
+ list_del_rcu(&mask->list);
+ kfree_rcu(mask, rcu);
+ }
+ }
+}
+
+/* Must be called with OVS mutex held. */
void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow)
{
struct table_instance *ti = ovsl_dereference(table->ti);
@@ -470,6 +514,11 @@ void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow)
BUG_ON(table->count == 0);
hlist_del_rcu(&flow->hash_node[ti->node_ver]);
table->count--;
+
+ /* RCU delete the mask. 'flow->mask' is not NULLed, as it should be
+ * accessible as long as the RCU read lock is held.
+ */
+ flow_mask_remove(table, flow->mask);
}
static struct sw_flow_mask *mask_alloc(void)
@@ -478,21 +527,16 @@ static struct sw_flow_mask *mask_alloc(void)
mask = kmalloc(sizeof(*mask), GFP_KERNEL);
if (mask)
- mask->ref_count = 0;
+ mask->ref_count = 1;
return mask;
}
-static void mask_add_ref(struct sw_flow_mask *mask)
-{
- mask->ref_count++;
-}
-
static bool mask_equal(const struct sw_flow_mask *a,
const struct sw_flow_mask *b)
{
- u8 *a_ = (u8 *)&a->key + a->range.start;
- u8 *b_ = (u8 *)&b->key + b->range.start;
+ const u8 *a_ = (const u8 *)&a->key + a->range.start;
+ const u8 *b_ = (const u8 *)&b->key + b->range.start;
return (a->range.end == b->range.end)
&& (a->range.start == b->range.start)
@@ -514,11 +558,7 @@ static struct sw_flow_mask *flow_mask_find(const struct flow_table *tbl,
return NULL;
}
-/**
- * add a new mask into the mask list.
- * The caller needs to make sure that 'mask' is not the same
- * as any masks that are already on the list.
- */
+/* Add 'mask' into the mask list, if it is not already there. */
static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow,
struct sw_flow_mask *new)
{
@@ -532,13 +572,16 @@ static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow,
mask->key = new->key;
mask->range = new->range;
list_add_rcu(&mask->list, &tbl->mask_list);
+ } else {
+ BUG_ON(!mask->ref_count);
+ mask->ref_count++;
}
- mask_add_ref(mask);
flow->mask = mask;
return 0;
}
+/* Must be called with OVS mutex held. */
int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
struct sw_flow_mask *mask)
{
@@ -577,16 +620,28 @@ int ovs_flow_init(void)
BUILD_BUG_ON(__alignof__(struct sw_flow_key) % __alignof__(long));
BUILD_BUG_ON(sizeof(struct sw_flow_key) % sizeof(long));
- flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow), 0,
- 0, NULL);
+ flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow)
+ + (num_possible_nodes()
+ * sizeof(struct flow_stats *)),
+ 0, 0, NULL);
if (flow_cache == NULL)
return -ENOMEM;
+ flow_stats_cache
+ = kmem_cache_create("sw_flow_stats", sizeof(struct flow_stats),
+ 0, SLAB_HWCACHE_ALIGN, NULL);
+ if (flow_stats_cache == NULL) {
+ kmem_cache_destroy(flow_cache);
+ flow_cache = NULL;
+ return -ENOMEM;
+ }
+
return 0;
}
/* Uninitializes the flow module. */
void ovs_flow_exit(void)
{
+ kmem_cache_destroy(flow_stats_cache);
kmem_cache_destroy(flow_cache);
}
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index fbe45d5ad07d..5918bff7f3f6 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -52,6 +52,8 @@ struct flow_table {
unsigned int count;
};
+extern struct kmem_cache *flow_stats_cache;
+
int ovs_flow_init(void);
void ovs_flow_exit(void);
@@ -60,7 +62,7 @@ void ovs_flow_free(struct sw_flow *, bool deferred);
int ovs_flow_tbl_init(struct flow_table *);
int ovs_flow_tbl_count(struct flow_table *table);
-void ovs_flow_tbl_destroy(struct flow_table *table);
+void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred);
int ovs_flow_tbl_flush(struct flow_table *flow_table);
int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
@@ -69,10 +71,13 @@ void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow);
int ovs_flow_tbl_num_masks(const struct flow_table *table);
struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *table,
u32 *bucket, u32 *idx);
-struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *,
+struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *,
const struct sw_flow_key *,
u32 *n_mask_hit);
-
+struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *,
+ const struct sw_flow_key *);
+struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
+ struct sw_flow_match *match);
bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
struct sw_flow_match *match);
diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c
new file mode 100644
index 000000000000..910b3ef2c0d5
--- /dev/null
+++ b/net/openvswitch/vport-geneve.c
@@ -0,0 +1,235 @@
+/*
+ * Copyright (c) 2014 Nicira, Inc.
+ *
+ * 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.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/version.h>
+
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/net.h>
+#include <linux/rculist.h>
+#include <linux/udp.h>
+#include <linux/if_vlan.h>
+
+#include <net/geneve.h>
+#include <net/icmp.h>
+#include <net/ip.h>
+#include <net/route.h>
+#include <net/udp.h>
+#include <net/xfrm.h>
+
+#include "datapath.h"
+#include "vport.h"
+
+/**
+ * struct geneve_port - Keeps track of open UDP ports
+ * @sock: The socket created for this port number.
+ * @name: vport name.
+ */
+struct geneve_port {
+ struct geneve_sock *gs;
+ char name[IFNAMSIZ];
+};
+
+static LIST_HEAD(geneve_ports);
+
+static inline struct geneve_port *geneve_vport(const struct vport *vport)
+{
+ return vport_priv(vport);
+}
+
+static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
+{
+ return (struct genevehdr *)(udp_hdr(skb) + 1);
+}
+
+/* Convert 64 bit tunnel ID to 24 bit VNI. */
+static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni)
+{
+#ifdef __BIG_ENDIAN
+ vni[0] = (__force __u8)(tun_id >> 16);
+ vni[1] = (__force __u8)(tun_id >> 8);
+ vni[2] = (__force __u8)tun_id;
+#else
+ vni[0] = (__force __u8)((__force u64)tun_id >> 40);
+ vni[1] = (__force __u8)((__force u64)tun_id >> 48);
+ vni[2] = (__force __u8)((__force u64)tun_id >> 56);
+#endif
+}
+
+/* Convert 24 bit VNI to 64 bit tunnel ID. */
+static __be64 vni_to_tunnel_id(__u8 *vni)
+{
+#ifdef __BIG_ENDIAN
+ return (vni[0] << 16) | (vni[1] << 8) | vni[2];
+#else
+ return (__force __be64)(((__force u64)vni[0] << 40) |
+ ((__force u64)vni[1] << 48) |
+ ((__force u64)vni[2] << 56));
+#endif
+}
+
+static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb)
+{
+ struct vport *vport = gs->rcv_data;
+ struct genevehdr *geneveh = geneve_hdr(skb);
+ int opts_len;
+ struct ovs_tunnel_info tun_info;
+ __be64 key;
+ __be16 flags;
+
+ opts_len = geneveh->opt_len * 4;
+
+ flags = TUNNEL_KEY | TUNNEL_OPTIONS_PRESENT |
+ (udp_hdr(skb)->check != 0 ? TUNNEL_CSUM : 0) |
+ (geneveh->oam ? TUNNEL_OAM : 0) |
+ (geneveh->critical ? TUNNEL_CRIT_OPT : 0);
+
+ key = vni_to_tunnel_id(geneveh->vni);
+
+ ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key, flags,
+ geneveh->options, opts_len);
+
+ ovs_vport_receive(vport, skb, &tun_info);
+}
+
+static int geneve_get_options(const struct vport *vport,
+ struct sk_buff *skb)
+{
+ struct geneve_port *geneve_port = geneve_vport(vport);
+ struct inet_sock *sk = inet_sk(geneve_port->gs->sock->sk);
+
+ if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(sk->inet_sport)))
+ return -EMSGSIZE;
+ return 0;
+}
+
+static void geneve_tnl_destroy(struct vport *vport)
+{
+ struct geneve_port *geneve_port = geneve_vport(vport);
+
+ geneve_sock_release(geneve_port->gs);
+
+ ovs_vport_deferred_free(vport);
+}
+
+static struct vport *geneve_tnl_create(const struct vport_parms *parms)
+{
+ struct net *net = ovs_dp_get_net(parms->dp);
+ struct nlattr *options = parms->options;
+ struct geneve_port *geneve_port;
+ struct geneve_sock *gs;
+ struct vport *vport;
+ struct nlattr *a;
+ int err;
+ u16 dst_port;
+
+ if (!options) {
+ err = -EINVAL;
+ goto error;
+ }
+
+ a = nla_find_nested(options, OVS_TUNNEL_ATTR_DST_PORT);
+ if (a && nla_len(a) == sizeof(u16)) {
+ dst_port = nla_get_u16(a);
+ } else {
+ /* Require destination port from userspace. */
+ err = -EINVAL;
+ goto error;
+ }
+
+ vport = ovs_vport_alloc(sizeof(struct geneve_port),
+ &ovs_geneve_vport_ops, parms);
+ if (IS_ERR(vport))
+ return vport;
+
+ geneve_port = geneve_vport(vport);
+ strncpy(geneve_port->name, parms->name, IFNAMSIZ);
+
+ gs = geneve_sock_add(net, htons(dst_port), geneve_rcv, vport, true, 0);
+ if (IS_ERR(gs)) {
+ ovs_vport_free(vport);
+ return (void *)gs;
+ }
+ geneve_port->gs = gs;
+
+ return vport;
+error:
+ return ERR_PTR(err);
+}
+
+static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb)
+{
+ struct ovs_key_ipv4_tunnel *tun_key;
+ struct ovs_tunnel_info *tun_info;
+ struct net *net = ovs_dp_get_net(vport->dp);
+ struct geneve_port *geneve_port = geneve_vport(vport);
+ __be16 dport = inet_sk(geneve_port->gs->sock->sk)->inet_sport;
+ __be16 sport;
+ struct rtable *rt;
+ struct flowi4 fl;
+ u8 vni[3];
+ __be16 df;
+ int err;
+
+ tun_info = OVS_CB(skb)->egress_tun_info;
+ if (unlikely(!tun_info)) {
+ err = -EINVAL;
+ goto error;
+ }
+
+ tun_key = &tun_info->tunnel;
+
+ /* Route lookup */
+ memset(&fl, 0, sizeof(fl));
+ fl.daddr = tun_key->ipv4_dst;
+ fl.saddr = tun_key->ipv4_src;
+ fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
+ fl.flowi4_mark = skb->mark;
+ fl.flowi4_proto = IPPROTO_UDP;
+
+ rt = ip_route_output_key(net, &fl);
+ if (IS_ERR(rt)) {
+ err = PTR_ERR(rt);
+ goto error;
+ }
+
+ df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
+ sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true);
+ tunnel_id_to_vni(tun_key->tun_id, vni);
+ skb->ignore_df = 1;
+
+ err = geneve_xmit_skb(geneve_port->gs, rt, skb, fl.saddr,
+ tun_key->ipv4_dst, tun_key->ipv4_tos,
+ tun_key->ipv4_ttl, df, sport, dport,
+ tun_key->tun_flags, vni,
+ tun_info->options_len, (u8 *)tun_info->options,
+ false);
+ if (err < 0)
+ ip_rt_put(rt);
+error:
+ return err;
+}
+
+static const char *geneve_get_name(const struct vport *vport)
+{
+ struct geneve_port *geneve_port = geneve_vport(vport);
+
+ return geneve_port->name;
+}
+
+const struct vport_ops ovs_geneve_vport_ops = {
+ .type = OVS_VPORT_TYPE_GENEVE,
+ .create = geneve_tnl_create,
+ .destroy = geneve_tnl_destroy,
+ .get_name = geneve_get_name,
+ .get_options = geneve_get_options,
+ .send = geneve_tnl_send,
+};
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index a3d6951602db..108b82da2fd9 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2007-2013 Nicira, Inc.
+ * Copyright (c) 2007-2014 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
@@ -63,8 +63,10 @@ static __be16 filter_tnl_flags(__be16 flags)
static struct sk_buff *__build_header(struct sk_buff *skb,
int tunnel_hlen)
{
- const struct ovs_key_ipv4_tunnel *tun_key = OVS_CB(skb)->tun_key;
struct tnl_ptk_info tpi;
+ const struct ovs_key_ipv4_tunnel *tun_key;
+
+ tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
skb = gre_handle_offloads(skb, !!(tun_key->tun_flags & TUNNEL_CSUM));
if (IS_ERR(skb))
@@ -92,7 +94,7 @@ static __be64 key_to_tunnel_id(__be32 key, __be32 seq)
static int gre_rcv(struct sk_buff *skb,
const struct tnl_ptk_info *tpi)
{
- struct ovs_key_ipv4_tunnel tun_key;
+ struct ovs_tunnel_info tun_info;
struct ovs_net *ovs_net;
struct vport *vport;
__be64 key;
@@ -103,16 +105,33 @@ static int gre_rcv(struct sk_buff *skb,
return PACKET_REJECT;
key = key_to_tunnel_id(tpi->key, tpi->seq);
- ovs_flow_tun_key_init(&tun_key, ip_hdr(skb), key,
- filter_tnl_flags(tpi->flags));
+ ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key,
+ filter_tnl_flags(tpi->flags), NULL, 0);
- ovs_vport_receive(vport, skb, &tun_key);
+ ovs_vport_receive(vport, skb, &tun_info);
return PACKET_RCVD;
}
+/* Called with rcu_read_lock and BH disabled. */
+static int gre_err(struct sk_buff *skb, u32 info,
+ const struct tnl_ptk_info *tpi)
+{
+ struct ovs_net *ovs_net;
+ struct vport *vport;
+
+ ovs_net = net_generic(dev_net(skb->dev), ovs_net_id);
+ vport = rcu_dereference(ovs_net->vport_net.gre_vport);
+
+ if (unlikely(!vport))
+ return PACKET_REJECT;
+ else
+ return PACKET_RCVD;
+}
+
static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
{
struct net *net = ovs_dp_get_net(vport->dp);
+ struct ovs_key_ipv4_tunnel *tun_key;
struct flowi4 fl;
struct rtable *rt;
int min_headroom;
@@ -120,16 +139,17 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
__be16 df;
int err;
- if (unlikely(!OVS_CB(skb)->tun_key)) {
+ if (unlikely(!OVS_CB(skb)->egress_tun_info)) {
err = -EINVAL;
goto error;
}
+ tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
/* Route lookup */
memset(&fl, 0, sizeof(fl));
- fl.daddr = OVS_CB(skb)->tun_key->ipv4_dst;
- fl.saddr = OVS_CB(skb)->tun_key->ipv4_src;
- fl.flowi4_tos = RT_TOS(OVS_CB(skb)->tun_key->ipv4_tos);
+ fl.daddr = tun_key->ipv4_dst;
+ fl.saddr = tun_key->ipv4_src;
+ fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
fl.flowi4_mark = skb->mark;
fl.flowi4_proto = IPPROTO_GRE;
@@ -137,7 +157,7 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
if (IS_ERR(rt))
return PTR_ERR(rt);
- tunnel_hlen = ip_gre_calc_hlen(OVS_CB(skb)->tun_key->tun_flags);
+ tunnel_hlen = ip_gre_calc_hlen(tun_key->tun_flags);
min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
+ tunnel_hlen + sizeof(struct iphdr)
@@ -169,15 +189,14 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
goto err_free_rt;
}
- df = OVS_CB(skb)->tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
+ df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
htons(IP_DF) : 0;
- skb->local_df = 1;
+ skb->ignore_df = 1;
- return iptunnel_xmit(rt, skb, fl.saddr,
- OVS_CB(skb)->tun_key->ipv4_dst, IPPROTO_GRE,
- OVS_CB(skb)->tun_key->ipv4_tos,
- OVS_CB(skb)->tun_key->ipv4_ttl, df, false);
+ return iptunnel_xmit(skb->sk, rt, skb, fl.saddr,
+ tun_key->ipv4_dst, IPPROTO_GRE,
+ tun_key->ipv4_tos, tun_key->ipv4_ttl, df, false);
err_free_rt:
ip_rt_put(rt);
error:
@@ -186,6 +205,7 @@ error:
static struct gre_cisco_protocol gre_protocol = {
.handler = gre_rcv,
+ .err_handler = gre_err,
.priority = 1,
};
@@ -256,7 +276,7 @@ static void gre_tnl_destroy(struct vport *vport)
ovs_net = net_generic(net, ovs_net_id);
- rcu_assign_pointer(ovs_net->vport_net.gre_vport, NULL);
+ RCU_INIT_POINTER(ovs_net->vport_net.gre_vport, NULL);
ovs_vport_deferred_free(vport);
gre_exit();
}
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 729c68763fe7..84516126e5f3 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -26,6 +26,7 @@
#include <net/dst.h>
#include <net/xfrm.h>
+#include <net/rtnetlink.h>
#include "datapath.h"
#include "vport-internal_dev.h"
@@ -121,6 +122,10 @@ static const struct net_device_ops internal_dev_netdev_ops = {
.ndo_get_stats64 = internal_dev_get_stats,
};
+static struct rtnl_link_ops internal_dev_link_ops __read_mostly = {
+ .kind = "openvswitch",
+};
+
static void do_setup(struct net_device *netdev)
{
ether_setup(netdev);
@@ -130,15 +135,19 @@ static void do_setup(struct net_device *netdev)
netdev->priv_flags &= ~IFF_TX_SKB_SHARING;
netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
netdev->destructor = internal_dev_destructor;
- SET_ETHTOOL_OPS(netdev, &internal_dev_ethtool_ops);
+ netdev->ethtool_ops = &internal_dev_ethtool_ops;
+ netdev->rtnl_link_ops = &internal_dev_link_ops;
netdev->tx_queue_len = 0;
netdev->features = NETIF_F_LLTX | NETIF_F_SG | NETIF_F_FRAGLIST |
- NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE;
+ NETIF_F_HIGHDMA | NETIF_F_HW_CSUM |
+ NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL;
netdev->vlan_features = netdev->features;
+ netdev->hw_enc_features = netdev->features;
netdev->features |= NETIF_F_HW_VLAN_CTAG_TX;
netdev->hw_features = netdev->features & ~NETIF_F_LLTX;
+
eth_hw_addr_random(netdev);
}
@@ -159,7 +168,8 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
netdev_vport = netdev_vport_priv(vport);
netdev_vport->dev = alloc_netdev(sizeof(struct internal_dev),
- parms->name, do_setup);
+ parms->name, NET_NAME_UNKNOWN,
+ do_setup);
if (!netdev_vport->dev) {
err = -ENOMEM;
goto error_free_vport;
@@ -248,3 +258,13 @@ struct vport *ovs_internal_dev_get_vport(struct net_device *netdev)
return internal_dev_priv(netdev)->vport;
}
+
+int ovs_internal_dev_rtnl_link_register(void)
+{
+ return rtnl_link_register(&internal_dev_link_ops);
+}
+
+void ovs_internal_dev_rtnl_link_unregister(void)
+{
+ rtnl_link_unregister(&internal_dev_link_ops);
+}
diff --git a/net/openvswitch/vport-internal_dev.h b/net/openvswitch/vport-internal_dev.h
index 9a7d30ecc6a2..1b179a190cff 100644
--- a/net/openvswitch/vport-internal_dev.h
+++ b/net/openvswitch/vport-internal_dev.h
@@ -24,5 +24,7 @@
int ovs_is_internal_dev(const struct net_device *);
struct vport *ovs_internal_dev_get_vport(struct net_device *);
+int ovs_internal_dev_rtnl_link_register(void);
+void ovs_internal_dev_rtnl_link_unregister(void);
#endif /* vport-internal_dev.h */
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index e797a50ac2be..2735e01dca73 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2013 Nicira, Inc.
+ * Copyright (c) 2014 Nicira, Inc.
* Copyright (c) 2013 Cisco Systems, Inc.
*
* This program is free software; you can redistribute it and/or
@@ -58,7 +58,7 @@ static inline struct vxlan_port *vxlan_vport(const struct vport *vport)
/* Called with rcu_read_lock and BH disabled. */
static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni)
{
- struct ovs_key_ipv4_tunnel tun_key;
+ struct ovs_tunnel_info tun_info;
struct vport *vport = vs->data;
struct iphdr *iph;
__be64 key;
@@ -66,9 +66,9 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni)
/* Save outer tunnel values */
iph = ip_hdr(skb);
key = cpu_to_be64(ntohl(vx_vni) >> 8);
- ovs_flow_tun_key_init(&tun_key, iph, key, TUNNEL_KEY);
+ ovs_flow_tun_info_init(&tun_info, iph, key, TUNNEL_KEY, NULL, 0);
- ovs_vport_receive(vport, skb, &tun_key);
+ ovs_vport_receive(vport, skb, &tun_info);
}
static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb)
@@ -122,7 +122,7 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
vxlan_port = vxlan_vport(vport);
strncpy(vxlan_port->name, parms->name, IFNAMSIZ);
- vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, false);
+ vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, 0);
if (IS_ERR(vs)) {
ovs_vport_free(vport);
return (void *)vs;
@@ -140,24 +140,24 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
struct net *net = ovs_dp_get_net(vport->dp);
struct vxlan_port *vxlan_port = vxlan_vport(vport);
__be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport;
+ struct ovs_key_ipv4_tunnel *tun_key;
struct rtable *rt;
struct flowi4 fl;
__be16 src_port;
- int port_min;
- int port_max;
__be16 df;
int err;
- if (unlikely(!OVS_CB(skb)->tun_key)) {
+ if (unlikely(!OVS_CB(skb)->egress_tun_info)) {
err = -EINVAL;
goto error;
}
+ tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
/* Route lookup */
memset(&fl, 0, sizeof(fl));
- fl.daddr = OVS_CB(skb)->tun_key->ipv4_dst;
- fl.saddr = OVS_CB(skb)->tun_key->ipv4_src;
- fl.flowi4_tos = RT_TOS(OVS_CB(skb)->tun_key->ipv4_tos);
+ fl.daddr = tun_key->ipv4_dst;
+ fl.saddr = tun_key->ipv4_src;
+ fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
fl.flowi4_mark = skb->mark;
fl.flowi4_proto = IPPROTO_UDP;
@@ -167,20 +167,19 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
goto error;
}
- df = OVS_CB(skb)->tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
+ df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
htons(IP_DF) : 0;
- skb->local_df = 1;
+ skb->ignore_df = 1;
- inet_get_local_port_range(net, &port_min, &port_max);
- src_port = vxlan_src_port(port_min, port_max, skb);
+ src_port = udp_flow_src_port(net, skb, 0, 0, true);
err = vxlan_xmit_skb(vxlan_port->vs, rt, skb,
- fl.saddr, OVS_CB(skb)->tun_key->ipv4_dst,
- OVS_CB(skb)->tun_key->ipv4_tos,
- OVS_CB(skb)->tun_key->ipv4_ttl, df,
+ fl.saddr, tun_key->ipv4_dst,
+ tun_key->ipv4_tos, tun_key->ipv4_ttl, df,
src_port, dst_port,
- htonl(be64_to_cpu(OVS_CB(skb)->tun_key->tun_id) << 8));
+ htonl(be64_to_cpu(tun_key->tun_id) << 8),
+ false);
if (err < 0)
ip_rt_put(rt);
error:
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index d830a95f03a4..53001b020ca7 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2007-2012 Nicira, Inc.
+ * Copyright (c) 2007-2014 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
@@ -33,6 +33,9 @@
#include "vport.h"
#include "vport-internal_dev.h"
+static void ovs_vport_record_error(struct vport *,
+ enum vport_err_type err_type);
+
/* List of statically compiled vport implementations. Don't forget to also
* add yours to the list at the bottom of vport.h. */
static const struct vport_ops *vport_ops_list[] = {
@@ -45,6 +48,9 @@ static const struct vport_ops *vport_ops_list[] = {
#ifdef CONFIG_OPENVSWITCH_VXLAN
&ovs_vxlan_vport_ops,
#endif
+#ifdef CONFIG_OPENVSWITCH_GENEVE
+ &ovs_geneve_vport_ops,
+#endif
};
/* Protected by RCU read lock for reading, ovs_mutex for writing. */
@@ -118,7 +124,6 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
{
struct vport *vport;
size_t alloc_size;
- int i;
alloc_size = sizeof(struct vport);
if (priv_size) {
@@ -132,25 +137,20 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
vport->dp = parms->dp;
vport->port_no = parms->port_no;
- vport->upcall_portid = parms->upcall_portid;
vport->ops = ops;
INIT_HLIST_NODE(&vport->dp_hash_node);
- vport->percpu_stats = alloc_percpu(struct pcpu_tstats);
- if (!vport->percpu_stats) {
+ if (ovs_vport_set_upcall_portids(vport, parms->upcall_portids)) {
kfree(vport);
- return ERR_PTR(-ENOMEM);
+ return ERR_PTR(-EINVAL);
}
- for_each_possible_cpu(i) {
- struct pcpu_tstats *vport_stats;
- vport_stats = per_cpu_ptr(vport->percpu_stats, i);
- u64_stats_init(&vport_stats->syncp);
+ vport->percpu_stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+ if (!vport->percpu_stats) {
+ kfree(vport);
+ return ERR_PTR(-ENOMEM);
}
-
- spin_lock_init(&vport->stats_lock);
-
return vport;
}
@@ -166,6 +166,10 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
*/
void ovs_vport_free(struct vport *vport)
{
+ /* vport is freed from RCU callback or error path, Therefore
+ * it is safe to use raw dereference.
+ */
+ kfree(rcu_dereference_raw(vport->upcall_portids));
free_percpu(vport->percpu_stats);
kfree(vport);
}
@@ -265,26 +269,22 @@ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats)
* netdev-stats can be directly read over netlink-ioctl.
*/
- spin_lock_bh(&vport->stats_lock);
-
- stats->rx_errors = vport->err_stats.rx_errors;
- stats->tx_errors = vport->err_stats.tx_errors;
- stats->tx_dropped = vport->err_stats.tx_dropped;
- stats->rx_dropped = vport->err_stats.rx_dropped;
-
- spin_unlock_bh(&vport->stats_lock);
+ stats->rx_errors = atomic_long_read(&vport->err_stats.rx_errors);
+ stats->tx_errors = atomic_long_read(&vport->err_stats.tx_errors);
+ stats->tx_dropped = atomic_long_read(&vport->err_stats.tx_dropped);
+ stats->rx_dropped = atomic_long_read(&vport->err_stats.rx_dropped);
for_each_possible_cpu(i) {
- const struct pcpu_tstats *percpu_stats;
- struct pcpu_tstats local_stats;
+ const struct pcpu_sw_netstats *percpu_stats;
+ struct pcpu_sw_netstats local_stats;
unsigned int start;
percpu_stats = per_cpu_ptr(vport->percpu_stats, i);
do {
- start = u64_stats_fetch_begin_bh(&percpu_stats->syncp);
+ start = u64_stats_fetch_begin_irq(&percpu_stats->syncp);
local_stats = *percpu_stats;
- } while (u64_stats_fetch_retry_bh(&percpu_stats->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start));
stats->rx_bytes += local_stats.rx_bytes;
stats->rx_packets += local_stats.rx_packets;
@@ -332,6 +332,99 @@ int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb)
}
/**
+ * ovs_vport_set_upcall_portids - set upcall portids of @vport.
+ *
+ * @vport: vport to modify.
+ * @ids: new configuration, an array of port ids.
+ *
+ * Sets the vport's upcall_portids to @ids.
+ *
+ * Returns 0 if successful, -EINVAL if @ids is zero length or cannot be parsed
+ * as an array of U32.
+ *
+ * Must be called with ovs_mutex.
+ */
+int ovs_vport_set_upcall_portids(struct vport *vport, struct nlattr *ids)
+{
+ struct vport_portids *old, *vport_portids;
+
+ if (!nla_len(ids) || nla_len(ids) % sizeof(u32))
+ return -EINVAL;
+
+ old = ovsl_dereference(vport->upcall_portids);
+
+ vport_portids = kmalloc(sizeof(*vport_portids) + nla_len(ids),
+ GFP_KERNEL);
+ if (!vport_portids)
+ return -ENOMEM;
+
+ vport_portids->n_ids = nla_len(ids) / sizeof(u32);
+ vport_portids->rn_ids = reciprocal_value(vport_portids->n_ids);
+ nla_memcpy(vport_portids->ids, ids, nla_len(ids));
+
+ rcu_assign_pointer(vport->upcall_portids, vport_portids);
+
+ if (old)
+ kfree_rcu(old, rcu);
+ return 0;
+}
+
+/**
+ * ovs_vport_get_upcall_portids - get the upcall_portids of @vport.
+ *
+ * @vport: vport from which to retrieve the portids.
+ * @skb: sk_buff where portids should be appended.
+ *
+ * Retrieves the configuration of the given vport, appending the
+ * %OVS_VPORT_ATTR_UPCALL_PID attribute which is the array of upcall
+ * portids to @skb.
+ *
+ * Returns 0 if successful, -EMSGSIZE if @skb has insufficient room.
+ * If an error occurs, @skb is left unmodified. Must be called with
+ * ovs_mutex or rcu_read_lock.
+ */
+int ovs_vport_get_upcall_portids(const struct vport *vport,
+ struct sk_buff *skb)
+{
+ struct vport_portids *ids;
+
+ ids = rcu_dereference_ovsl(vport->upcall_portids);
+
+ if (vport->dp->user_features & OVS_DP_F_VPORT_PIDS)
+ return nla_put(skb, OVS_VPORT_ATTR_UPCALL_PID,
+ ids->n_ids * sizeof(u32), (void *)ids->ids);
+ else
+ return nla_put_u32(skb, OVS_VPORT_ATTR_UPCALL_PID, ids->ids[0]);
+}
+
+/**
+ * ovs_vport_find_upcall_portid - find the upcall portid to send upcall.
+ *
+ * @vport: vport from which the missed packet is received.
+ * @skb: skb that the missed packet was received.
+ *
+ * Uses the skb_get_hash() to select the upcall portid to send the
+ * upcall.
+ *
+ * Returns the portid of the target socket. Must be called with rcu_read_lock.
+ */
+u32 ovs_vport_find_upcall_portid(const struct vport *p, struct sk_buff *skb)
+{
+ struct vport_portids *ids;
+ u32 ids_index;
+ u32 hash;
+
+ ids = rcu_dereference(p->upcall_portids);
+
+ if (ids->n_ids == 1 && ids->ids[0] == 0)
+ return 0;
+
+ hash = skb_get_hash(skb);
+ ids_index = hash - ids->n_ids * reciprocal_divide(hash, ids->rn_ids);
+ return ids->ids[ids_index];
+}
+
+/**
* ovs_vport_receive - pass up received packet to the datapath for processing
*
* @vport: vport that received the packet
@@ -342,9 +435,11 @@ int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb)
* skb->data should point to the Ethernet header.
*/
void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
- struct ovs_key_ipv4_tunnel *tun_key)
+ struct ovs_tunnel_info *tun_info)
{
- struct pcpu_tstats *stats;
+ struct pcpu_sw_netstats *stats;
+ struct sw_flow_key key;
+ int error;
stats = this_cpu_ptr(vport->percpu_stats);
u64_stats_update_begin(&stats->syncp);
@@ -352,8 +447,15 @@ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
stats->rx_bytes += skb->len;
u64_stats_update_end(&stats->syncp);
- OVS_CB(skb)->tun_key = tun_key;
- ovs_dp_process_received_packet(vport, skb);
+ OVS_CB(skb)->input_vport = vport;
+ OVS_CB(skb)->egress_tun_info = NULL;
+ /* Extract flow from 'skb' into 'key'. */
+ error = ovs_flow_key_extract(tun_info, skb, &key);
+ if (unlikely(error)) {
+ kfree_skb(skb);
+ return;
+ }
+ ovs_dp_process_packet(skb, &key);
}
/**
@@ -370,7 +472,7 @@ int ovs_vport_send(struct vport *vport, struct sk_buff *skb)
int sent = vport->ops->send(vport, skb);
if (likely(sent > 0)) {
- struct pcpu_tstats *stats;
+ struct pcpu_sw_netstats *stats;
stats = this_cpu_ptr(vport->percpu_stats);
@@ -396,29 +498,27 @@ int ovs_vport_send(struct vport *vport, struct sk_buff *skb)
* If using the vport generic stats layer indicate that an error of the given
* type has occurred.
*/
-void ovs_vport_record_error(struct vport *vport, enum vport_err_type err_type)
+static void ovs_vport_record_error(struct vport *vport,
+ enum vport_err_type err_type)
{
- spin_lock(&vport->stats_lock);
-
switch (err_type) {
case VPORT_E_RX_DROPPED:
- vport->err_stats.rx_dropped++;
+ atomic_long_inc(&vport->err_stats.rx_dropped);
break;
case VPORT_E_RX_ERROR:
- vport->err_stats.rx_errors++;
+ atomic_long_inc(&vport->err_stats.rx_errors);
break;
case VPORT_E_TX_DROPPED:
- vport->err_stats.tx_dropped++;
+ atomic_long_inc(&vport->err_stats.tx_dropped);
break;
case VPORT_E_TX_ERROR:
- vport->err_stats.tx_errors++;
+ atomic_long_inc(&vport->err_stats.tx_errors);
break;
}
- spin_unlock(&vport->stats_lock);
}
static void free_vport_rcu(struct rcu_head *rcu)
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index 1a9fbcec6e1b..8942125de3a6 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -23,6 +23,7 @@
#include <linux/list.h>
#include <linux/netlink.h>
#include <linux/openvswitch.h>
+#include <linux/reciprocal_div.h>
#include <linux/skbuff.h>
#include <linux/spinlock.h>
#include <linux/u64_stats_sync.h>
@@ -34,7 +35,6 @@ struct vport_parms;
/* The following definitions are for users of the vport subsytem: */
-/* The following definitions are for users of the vport subsytem: */
struct vport_net {
struct vport __rcu *gre_vport;
};
@@ -52,44 +52,60 @@ void ovs_vport_get_stats(struct vport *, struct ovs_vport_stats *);
int ovs_vport_set_options(struct vport *, struct nlattr *options);
int ovs_vport_get_options(const struct vport *, struct sk_buff *);
+int ovs_vport_set_upcall_portids(struct vport *, struct nlattr *pids);
+int ovs_vport_get_upcall_portids(const struct vport *, struct sk_buff *);
+u32 ovs_vport_find_upcall_portid(const struct vport *, struct sk_buff *);
+
int ovs_vport_send(struct vport *, struct sk_buff *);
/* The following definitions are for implementers of vport devices: */
struct vport_err_stats {
- u64 rx_dropped;
- u64 rx_errors;
- u64 tx_dropped;
- u64 tx_errors;
+ atomic_long_t rx_dropped;
+ atomic_long_t rx_errors;
+ atomic_long_t tx_dropped;
+ atomic_long_t tx_errors;
+};
+/**
+ * struct vport_portids - array of netlink portids of a vport.
+ * must be protected by rcu.
+ * @rn_ids: The reciprocal value of @n_ids.
+ * @rcu: RCU callback head for deferred destruction.
+ * @n_ids: Size of @ids array.
+ * @ids: Array storing the Netlink socket pids to be used for packets received
+ * on this port that miss the flow table.
+ */
+struct vport_portids {
+ struct reciprocal_value rn_ids;
+ struct rcu_head rcu;
+ u32 n_ids;
+ u32 ids[];
};
/**
* struct vport - one port within a datapath
* @rcu: RCU callback head for deferred destruction.
* @dp: Datapath to which this port belongs.
- * @upcall_portid: The Netlink port to use for packets received on this port that
- * miss the flow table.
+ * @upcall_portids: RCU protected 'struct vport_portids'.
* @port_no: Index into @dp's @ports array.
* @hash_node: Element in @dev_table hash table in vport.c.
* @dp_hash_node: Element in @datapath->ports hash table in datapath.c.
* @ops: Class structure.
* @percpu_stats: Points to per-CPU statistics used and maintained by vport
- * @stats_lock: Protects @err_stats;
* @err_stats: Points to error statistics used and maintained by vport
*/
struct vport {
struct rcu_head rcu;
struct datapath *dp;
- u32 upcall_portid;
+ struct vport_portids __rcu *upcall_portids;
u16 port_no;
struct hlist_node hash_node;
struct hlist_node dp_hash_node;
const struct vport_ops *ops;
- struct pcpu_tstats __percpu *percpu_stats;
+ struct pcpu_sw_netstats __percpu *percpu_stats;
- spinlock_t stats_lock;
struct vport_err_stats err_stats;
};
@@ -111,7 +127,7 @@ struct vport_parms {
/* For ovs_vport_alloc(). */
struct datapath *dp;
u16 port_no;
- u32 upcall_portid;
+ struct nlattr *upcall_portids;
};
/**
@@ -172,7 +188,7 @@ void ovs_vport_deferred_free(struct vport *vport);
*/
static inline void *vport_priv(const struct vport *vport)
{
- return (u8 *)vport + ALIGN(sizeof(struct vport), VPORT_ALIGN);
+ return (u8 *)(uintptr_t)vport + ALIGN(sizeof(struct vport), VPORT_ALIGN);
}
/**
@@ -185,14 +201,13 @@ static inline void *vport_priv(const struct vport *vport)
* the result of a hash table lookup. @priv must point to the start of the
* private data area.
*/
-static inline struct vport *vport_from_priv(const void *priv)
+static inline struct vport *vport_from_priv(void *priv)
{
- return (struct vport *)(priv - ALIGN(sizeof(struct vport), VPORT_ALIGN));
+ return (struct vport *)((u8 *)priv - ALIGN(sizeof(struct vport), VPORT_ALIGN));
}
void ovs_vport_receive(struct vport *, struct sk_buff *,
- struct ovs_key_ipv4_tunnel *);
-void ovs_vport_record_error(struct vport *, enum vport_err_type err_type);
+ struct ovs_tunnel_info *);
/* List of statically compiled vport implementations. Don't forget to also
* add yours to the list at the top of vport.c. */
@@ -200,6 +215,7 @@ extern const struct vport_ops ovs_netdev_vport_ops;
extern const struct vport_ops ovs_internal_vport_ops;
extern const struct vport_ops ovs_gre_vport_ops;
extern const struct vport_ops ovs_vxlan_vport_ops;
+extern const struct vport_ops ovs_geneve_vport_ops;
static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb,
const void *start, unsigned int len)
generated by cgit v1.2.3 (git 2.25.1) at 2025-12-11 00:32:25 +0000