openvswitch: Restructure datapath.c and flow.c

Over the time datapath.c and flow.c has became pretty large files.
Following patch restructures functionality of component into three
different components:

flow.c: contains flow extract.
flow_netlink.c: netlink flow api.
flow_table.c: flow table api.

This patch restructures code without changing logic.

Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
This commit is contained in:
Pravin B Shelar 2013-10-03 18:16:47 -07:00 committed by Jesse Gross
parent f0627cfa24
commit e64457191a
9 changed files with 2354 additions and 2181 deletions

View File

@ -9,6 +9,8 @@ openvswitch-y := \
datapath.o \
dp_notify.o \
flow.o \
flow_netlink.o \
flow_table.o \
vport.o \
vport-internal_dev.o \
vport-netdev.o

View File

@ -55,10 +55,10 @@
#include "datapath.h"
#include "flow.h"
#include "flow_netlink.h"
#include "vport-internal_dev.h"
#include "vport-netdev.h"
#define REHASH_FLOW_INTERVAL (10 * 60 * HZ)
int ovs_net_id __read_mostly;
@ -235,7 +235,7 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb)
}
/* Look up flow. */
flow = ovs_flow_lookup(rcu_dereference(dp->table), &key);
flow = ovs_flow_tbl_lookup(rcu_dereference(dp->table), &key);
if (unlikely(!flow)) {
struct dp_upcall_info upcall;
@ -433,7 +433,7 @@ 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_flow_to_nlattrs(upcall_info->key, upcall_info->key, user_skb);
ovs_nla_put_flow(upcall_info->key, upcall_info->key, user_skb);
nla_nest_end(user_skb, nla);
if (upcall_info->userdata)
@ -470,381 +470,6 @@ static int flush_flows(struct datapath *dp)
return 0;
}
static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, int attr_len)
{
struct sw_flow_actions *acts;
int new_acts_size;
int req_size = NLA_ALIGN(attr_len);
int next_offset = offsetof(struct sw_flow_actions, actions) +
(*sfa)->actions_len;
if (req_size <= (ksize(*sfa) - next_offset))
goto out;
new_acts_size = ksize(*sfa) * 2;
if (new_acts_size > MAX_ACTIONS_BUFSIZE) {
if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size)
return ERR_PTR(-EMSGSIZE);
new_acts_size = MAX_ACTIONS_BUFSIZE;
}
acts = ovs_flow_actions_alloc(new_acts_size);
if (IS_ERR(acts))
return (void *)acts;
memcpy(acts->actions, (*sfa)->actions, (*sfa)->actions_len);
acts->actions_len = (*sfa)->actions_len;
kfree(*sfa);
*sfa = acts;
out:
(*sfa)->actions_len += req_size;
return (struct nlattr *) ((unsigned char *)(*sfa) + next_offset);
}
static int add_action(struct sw_flow_actions **sfa, int attrtype, void *data, int len)
{
struct nlattr *a;
a = reserve_sfa_size(sfa, nla_attr_size(len));
if (IS_ERR(a))
return PTR_ERR(a);
a->nla_type = attrtype;
a->nla_len = nla_attr_size(len);
if (data)
memcpy(nla_data(a), data, len);
memset((unsigned char *) a + a->nla_len, 0, nla_padlen(len));
return 0;
}
static inline int add_nested_action_start(struct sw_flow_actions **sfa, int attrtype)
{
int used = (*sfa)->actions_len;
int err;
err = add_action(sfa, attrtype, NULL, 0);
if (err)
return err;
return used;
}
static inline void add_nested_action_end(struct sw_flow_actions *sfa, int st_offset)
{
struct nlattr *a = (struct nlattr *) ((unsigned char *)sfa->actions + st_offset);
a->nla_len = sfa->actions_len - st_offset;
}
static int validate_and_copy_actions(const struct nlattr *attr,
const struct sw_flow_key *key, int depth,
struct sw_flow_actions **sfa);
static int validate_and_copy_sample(const struct nlattr *attr,
const struct sw_flow_key *key, int depth,
struct sw_flow_actions **sfa)
{
const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
const struct nlattr *probability, *actions;
const struct nlattr *a;
int rem, start, err, st_acts;
memset(attrs, 0, sizeof(attrs));
nla_for_each_nested(a, attr, rem) {
int type = nla_type(a);
if (!type || type > OVS_SAMPLE_ATTR_MAX || attrs[type])
return -EINVAL;
attrs[type] = a;
}
if (rem)
return -EINVAL;
probability = attrs[OVS_SAMPLE_ATTR_PROBABILITY];
if (!probability || nla_len(probability) != sizeof(u32))
return -EINVAL;
actions = attrs[OVS_SAMPLE_ATTR_ACTIONS];
if (!actions || (nla_len(actions) && nla_len(actions) < NLA_HDRLEN))
return -EINVAL;
/* validation done, copy sample action. */
start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE);
if (start < 0)
return start;
err = add_action(sfa, OVS_SAMPLE_ATTR_PROBABILITY, nla_data(probability), sizeof(u32));
if (err)
return err;
st_acts = add_nested_action_start(sfa, OVS_SAMPLE_ATTR_ACTIONS);
if (st_acts < 0)
return st_acts;
err = validate_and_copy_actions(actions, key, depth + 1, sfa);
if (err)
return err;
add_nested_action_end(*sfa, st_acts);
add_nested_action_end(*sfa, start);
return 0;
}
static int validate_tp_port(const struct sw_flow_key *flow_key)
{
if (flow_key->eth.type == htons(ETH_P_IP)) {
if (flow_key->ipv4.tp.src || flow_key->ipv4.tp.dst)
return 0;
} else if (flow_key->eth.type == htons(ETH_P_IPV6)) {
if (flow_key->ipv6.tp.src || flow_key->ipv6.tp.dst)
return 0;
}
return -EINVAL;
}
static int validate_and_copy_set_tun(const struct nlattr *attr,
struct sw_flow_actions **sfa)
{
struct sw_flow_match match;
struct sw_flow_key key;
int err, start;
ovs_match_init(&match, &key, NULL);
err = ovs_ipv4_tun_from_nlattr(nla_data(attr), &match, false);
if (err)
return err;
start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET);
if (start < 0)
return start;
err = add_action(sfa, OVS_KEY_ATTR_IPV4_TUNNEL, &match.key->tun_key,
sizeof(match.key->tun_key));
add_nested_action_end(*sfa, start);
return err;
}
static int validate_set(const struct nlattr *a,
const struct sw_flow_key *flow_key,
struct sw_flow_actions **sfa,
bool *set_tun)
{
const struct nlattr *ovs_key = nla_data(a);
int key_type = nla_type(ovs_key);
/* There can be only one key in a action */
if (nla_total_size(nla_len(ovs_key)) != nla_len(a))
return -EINVAL;
if (key_type > OVS_KEY_ATTR_MAX ||
(ovs_key_lens[key_type] != nla_len(ovs_key) &&
ovs_key_lens[key_type] != -1))
return -EINVAL;
switch (key_type) {
const struct ovs_key_ipv4 *ipv4_key;
const struct ovs_key_ipv6 *ipv6_key;
int err;
case OVS_KEY_ATTR_PRIORITY:
case OVS_KEY_ATTR_SKB_MARK:
case OVS_KEY_ATTR_ETHERNET:
break;
case OVS_KEY_ATTR_TUNNEL:
*set_tun = true;
err = validate_and_copy_set_tun(a, sfa);
if (err)
return err;
break;
case OVS_KEY_ATTR_IPV4:
if (flow_key->eth.type != htons(ETH_P_IP))
return -EINVAL;
if (!flow_key->ip.proto)
return -EINVAL;
ipv4_key = nla_data(ovs_key);
if (ipv4_key->ipv4_proto != flow_key->ip.proto)
return -EINVAL;
if (ipv4_key->ipv4_frag != flow_key->ip.frag)
return -EINVAL;
break;
case OVS_KEY_ATTR_IPV6:
if (flow_key->eth.type != htons(ETH_P_IPV6))
return -EINVAL;
if (!flow_key->ip.proto)
return -EINVAL;
ipv6_key = nla_data(ovs_key);
if (ipv6_key->ipv6_proto != flow_key->ip.proto)
return -EINVAL;
if (ipv6_key->ipv6_frag != flow_key->ip.frag)
return -EINVAL;
if (ntohl(ipv6_key->ipv6_label) & 0xFFF00000)
return -EINVAL;
break;
case OVS_KEY_ATTR_TCP:
if (flow_key->ip.proto != IPPROTO_TCP)
return -EINVAL;
return validate_tp_port(flow_key);
case OVS_KEY_ATTR_UDP:
if (flow_key->ip.proto != IPPROTO_UDP)
return -EINVAL;
return validate_tp_port(flow_key);
case OVS_KEY_ATTR_SCTP:
if (flow_key->ip.proto != IPPROTO_SCTP)
return -EINVAL;
return validate_tp_port(flow_key);
default:
return -EINVAL;
}
return 0;
}
static int validate_userspace(const struct nlattr *attr)
{
static const struct nla_policy userspace_policy[OVS_USERSPACE_ATTR_MAX + 1] = {
[OVS_USERSPACE_ATTR_PID] = {.type = NLA_U32 },
[OVS_USERSPACE_ATTR_USERDATA] = {.type = NLA_UNSPEC },
};
struct nlattr *a[OVS_USERSPACE_ATTR_MAX + 1];
int error;
error = nla_parse_nested(a, OVS_USERSPACE_ATTR_MAX,
attr, userspace_policy);
if (error)
return error;
if (!a[OVS_USERSPACE_ATTR_PID] ||
!nla_get_u32(a[OVS_USERSPACE_ATTR_PID]))
return -EINVAL;
return 0;
}
static int copy_action(const struct nlattr *from,
struct sw_flow_actions **sfa)
{
int totlen = NLA_ALIGN(from->nla_len);
struct nlattr *to;
to = reserve_sfa_size(sfa, from->nla_len);
if (IS_ERR(to))
return PTR_ERR(to);
memcpy(to, from, totlen);
return 0;
}
static int validate_and_copy_actions(const struct nlattr *attr,
const struct sw_flow_key *key,
int depth,
struct sw_flow_actions **sfa)
{
const struct nlattr *a;
int rem, err;
if (depth >= SAMPLE_ACTION_DEPTH)
return -EOVERFLOW;
nla_for_each_nested(a, attr, rem) {
/* 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_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
};
const struct ovs_action_push_vlan *vlan;
int type = nla_type(a);
bool skip_copy;
if (type > OVS_ACTION_ATTR_MAX ||
(action_lens[type] != nla_len(a) &&
action_lens[type] != (u32)-1))
return -EINVAL;
skip_copy = false;
switch (type) {
case OVS_ACTION_ATTR_UNSPEC:
return -EINVAL;
case OVS_ACTION_ATTR_USERSPACE:
err = validate_userspace(a);
if (err)
return err;
break;
case OVS_ACTION_ATTR_OUTPUT:
if (nla_get_u32(a) >= DP_MAX_PORTS)
return -EINVAL;
break;
case OVS_ACTION_ATTR_POP_VLAN:
break;
case OVS_ACTION_ATTR_PUSH_VLAN:
vlan = nla_data(a);
if (vlan->vlan_tpid != htons(ETH_P_8021Q))
return -EINVAL;
if (!(vlan->vlan_tci & htons(VLAN_TAG_PRESENT)))
return -EINVAL;
break;
case OVS_ACTION_ATTR_SET:
err = validate_set(a, key, sfa, &skip_copy);
if (err)
return err;
break;
case OVS_ACTION_ATTR_SAMPLE:
err = validate_and_copy_sample(a, key, depth, sfa);
if (err)
return err;
skip_copy = true;
break;
default:
return -EINVAL;
}
if (!skip_copy) {
err = copy_action(a, sfa);
if (err)
return err;
}
}
if (rem > 0)
return -EINVAL;
return 0;
}
static void clear_stats(struct sw_flow *flow)
{
flow->used = 0;
@ -900,15 +525,16 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
if (err)
goto err_flow_free;
err = ovs_flow_metadata_from_nlattrs(flow, a[OVS_PACKET_ATTR_KEY]);
err = ovs_nla_get_flow_metadata(flow, a[OVS_PACKET_ATTR_KEY]);
if (err)
goto err_flow_free;
acts = ovs_flow_actions_alloc(nla_len(a[OVS_PACKET_ATTR_ACTIONS]));
acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_PACKET_ATTR_ACTIONS]));
err = PTR_ERR(acts);
if (IS_ERR(acts))
goto err_flow_free;
err = validate_and_copy_actions(a[OVS_PACKET_ATTR_ACTIONS], &flow->key, 0, &acts);
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;
@ -1003,100 +629,6 @@ static struct genl_multicast_group ovs_dp_flow_multicast_group = {
.name = OVS_FLOW_MCGROUP
};
static int actions_to_attr(const struct nlattr *attr, int len, struct sk_buff *skb);
static int sample_action_to_attr(const struct nlattr *attr, struct sk_buff *skb)
{
const struct nlattr *a;
struct nlattr *start;
int err = 0, rem;
start = nla_nest_start(skb, OVS_ACTION_ATTR_SAMPLE);
if (!start)
return -EMSGSIZE;
nla_for_each_nested(a, attr, rem) {
int type = nla_type(a);
struct nlattr *st_sample;
switch (type) {
case OVS_SAMPLE_ATTR_PROBABILITY:
if (nla_put(skb, OVS_SAMPLE_ATTR_PROBABILITY, sizeof(u32), nla_data(a)))
return -EMSGSIZE;
break;
case OVS_SAMPLE_ATTR_ACTIONS:
st_sample = nla_nest_start(skb, OVS_SAMPLE_ATTR_ACTIONS);
if (!st_sample)
return -EMSGSIZE;
err = actions_to_attr(nla_data(a), nla_len(a), skb);
if (err)
return err;
nla_nest_end(skb, st_sample);
break;
}
}
nla_nest_end(skb, start);
return err;
}
static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
{
const struct nlattr *ovs_key = nla_data(a);
int key_type = nla_type(ovs_key);
struct nlattr *start;
int err;
switch (key_type) {
case OVS_KEY_ATTR_IPV4_TUNNEL:
start = nla_nest_start(skb, OVS_ACTION_ATTR_SET);
if (!start)
return -EMSGSIZE;
err = ovs_ipv4_tun_to_nlattr(skb, nla_data(ovs_key),
nla_data(ovs_key));
if (err)
return err;
nla_nest_end(skb, start);
break;
default:
if (nla_put(skb, OVS_ACTION_ATTR_SET, nla_len(a), ovs_key))
return -EMSGSIZE;
break;
}
return 0;
}
static int actions_to_attr(const struct nlattr *attr, int len, struct sk_buff *skb)
{
const struct nlattr *a;
int rem, err;
nla_for_each_attr(a, attr, len, rem) {
int type = nla_type(a);
switch (type) {
case OVS_ACTION_ATTR_SET:
err = set_action_to_attr(a, skb);
if (err)
return err;
break;
case OVS_ACTION_ATTR_SAMPLE:
err = sample_action_to_attr(a, skb);
if (err)
return err;
break;
default:
if (nla_put(skb, type, nla_len(a), nla_data(a)))
return -EMSGSIZE;
break;
}
}
return 0;
}
static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts)
{
return NLMSG_ALIGN(sizeof(struct ovs_header))
@ -1133,8 +665,7 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
if (!nla)
goto nla_put_failure;
err = ovs_flow_to_nlattrs(&flow->unmasked_key,
&flow->unmasked_key, skb);
err = ovs_nla_put_flow(&flow->unmasked_key, &flow->unmasked_key, skb);
if (err)
goto error;
nla_nest_end(skb, nla);
@ -1143,7 +674,7 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
if (!nla)
goto nla_put_failure;
err = ovs_flow_to_nlattrs(&flow->key, &flow->mask->key, skb);
err = ovs_nla_put_flow(&flow->key, &flow->mask->key, skb);
if (err)
goto error;
@ -1186,7 +717,8 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
sf_acts = rcu_dereference_check(flow->sf_acts,
lockdep_ovsl_is_held());
err = actions_to_attr(sf_acts->actions, sf_acts->actions_len, skb);
err = ovs_nla_put_actions(sf_acts->actions,
sf_acts->actions_len, skb);
if (!err)
nla_nest_end(skb, start);
else {
@ -1252,21 +784,21 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
goto error;
ovs_match_init(&match, &key, &mask);
error = ovs_match_from_nlattrs(&match,
a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_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 = ovs_flow_actions_alloc(nla_len(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;
ovs_flow_key_mask(&masked_key, &key, &mask);
error = validate_and_copy_actions(a[OVS_FLOW_ATTR_ACTIONS],
&masked_key, 0, &acts);
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;
@ -1285,7 +817,7 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
table = ovsl_dereference(dp->table);
/* Check if this is a duplicate flow */
flow = ovs_flow_lookup(table, &key);
flow = ovs_flow_tbl_lookup(table, &key);
if (!flow) {
struct flow_table *new_table = NULL;
struct sw_flow_mask *mask_p;
@ -1336,7 +868,7 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
rcu_assign_pointer(flow->sf_acts, acts);
/* Put flow in bucket. */
ovs_flow_insert(table, flow);
ovs_flow_tbl_insert(table, flow);
reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid,
info->snd_seq, OVS_FLOW_CMD_NEW);
@ -1357,7 +889,7 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
/* The unmasked key has to be the same for flow updates. */
error = -EINVAL;
if (!ovs_flow_cmp_unmasked_key(flow, &key, match.range.end)) {
if (!ovs_flow_cmp_unmasked_key(flow, &match)) {
OVS_NLERR("Flow modification message rejected, unmasked key does not match.\n");
goto err_unlock_ovs;
}
@ -1365,7 +897,7 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
/* Update actions. */
old_acts = ovsl_dereference(flow->sf_acts);
rcu_assign_pointer(flow->sf_acts, acts);
ovs_flow_deferred_free_acts(old_acts);
ovs_nla_free_flow_actions(old_acts);
reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid,
info->snd_seq, OVS_FLOW_CMD_NEW);
@ -1414,7 +946,7 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
}
ovs_match_init(&match, &key, NULL);
err = ovs_match_from_nlattrs(&match, a[OVS_FLOW_ATTR_KEY], NULL);
err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
if (err)
return err;
@ -1426,8 +958,8 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
}
table = ovsl_dereference(dp->table);
flow = ovs_flow_lookup_unmasked_key(table, &match);
if (!flow) {
flow = ovs_flow_tbl_lookup(table, &key);
if (!flow || !ovs_flow_cmp_unmasked_key(flow, &match)) {
err = -ENOENT;
goto unlock;
}
@ -1471,13 +1003,13 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
}
ovs_match_init(&match, &key, NULL);
err = ovs_match_from_nlattrs(&match, a[OVS_FLOW_ATTR_KEY], NULL);
err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
if (err)
goto unlock;
table = ovsl_dereference(dp->table);
flow = ovs_flow_lookup_unmasked_key(table, &match);
if (!flow) {
flow = ovs_flow_tbl_lookup(table, &key);
if (!flow || !ovs_flow_cmp_unmasked_key(flow, &match)) {
err = -ENOENT;
goto unlock;
}
@ -1488,7 +1020,7 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
goto unlock;
}
ovs_flow_remove(table, flow);
ovs_flow_tbl_remove(table, flow);
err = ovs_flow_cmd_fill_info(flow, dp, reply, info->snd_portid,
info->snd_seq, 0, OVS_FLOW_CMD_DEL);
@ -1524,7 +1056,7 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
bucket = cb->args[0];
obj = cb->args[1];
flow = ovs_flow_dump_next(table, &bucket, &obj);
flow = ovs_flow_tbl_dump_next(table, &bucket, &obj);
if (!flow)
break;
@ -1700,7 +1232,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
}
dp->ports = kmalloc(DP_VPORT_HASH_BUCKETS * sizeof(struct hlist_head),
GFP_KERNEL);
GFP_KERNEL);
if (!dp->ports) {
err = -ENOMEM;
goto err_destroy_percpu;

View File

@ -27,6 +27,7 @@
#include <linux/u64_stats_sync.h>
#include "flow.h"
#include "flow_table.h"
#include "vport.h"
#define DP_MAX_PORTS USHRT_MAX

File diff suppressed because it is too large Load Diff

View File

@ -33,14 +33,6 @@
#include <net/inet_ecn.h>
struct sk_buff;
struct sw_flow_mask;
struct flow_table;
struct sw_flow_actions {
struct rcu_head rcu;
u32 actions_len;
struct nlattr actions[];
};
/* Used to memset ovs_key_ipv4_tunnel padding. */
#define OVS_TUNNEL_KEY_SIZE \
@ -127,6 +119,31 @@ 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;
};
struct sw_flow_mask {
int ref_count;
struct rcu_head rcu;
struct list_head list;
struct sw_flow_key_range range;
struct sw_flow_key key;
};
struct sw_flow_match {
struct sw_flow_key *key;
struct sw_flow_key_range range;
struct sw_flow_mask *mask;
};
struct sw_flow_actions {
struct rcu_head rcu;
u32 actions_len;
struct nlattr actions[];
};
struct sw_flow {
struct rcu_head rcu;
struct hlist_node hash_node[2];
@ -144,20 +161,6 @@ struct sw_flow {
u8 tcp_flags; /* Union of seen TCP flags. */
};
struct sw_flow_key_range {
size_t start;
size_t end;
};
struct sw_flow_match {
struct sw_flow_key *key;
struct sw_flow_key_range range;
struct sw_flow_mask *mask;
};
void ovs_match_init(struct sw_flow_match *match,
struct sw_flow_key *key, struct sw_flow_mask *mask);
struct arp_eth_header {
__be16 ar_hrd; /* format of hardware address */
__be16 ar_pro; /* format of protocol address */
@ -172,88 +175,9 @@ struct arp_eth_header {
unsigned char ar_tip[4]; /* target IP address */
} __packed;
int ovs_flow_init(void);
void ovs_flow_exit(void);
struct sw_flow *ovs_flow_alloc(void);
void ovs_flow_deferred_free(struct sw_flow *);
void ovs_flow_free(struct sw_flow *, bool deferred);
struct sw_flow_actions *ovs_flow_actions_alloc(int actions_len);
void ovs_flow_deferred_free_acts(struct sw_flow_actions *);
int ovs_flow_extract(struct sk_buff *, u16 in_port, struct sw_flow_key *);
void ovs_flow_used(struct sw_flow *, struct sk_buff *);
u64 ovs_flow_used_time(unsigned long flow_jiffies);
int ovs_flow_to_nlattrs(const struct sw_flow_key *,
const struct sw_flow_key *, struct sk_buff *);
int ovs_match_from_nlattrs(struct sw_flow_match *match,
const struct nlattr *,
const struct nlattr *);
int ovs_flow_metadata_from_nlattrs(struct sw_flow *flow,
const struct nlattr *attr);
#define MAX_ACTIONS_BUFSIZE (32 * 1024)
#define TBL_MIN_BUCKETS 1024
int ovs_flow_extract(struct sk_buff *, u16 in_port, struct sw_flow_key *);
struct flow_table {
struct flex_array *buckets;
unsigned int count, n_buckets;
struct rcu_head rcu;
struct list_head *mask_list;
int node_ver;
u32 hash_seed;
bool keep_flows;
};
static inline int ovs_flow_tbl_count(struct flow_table *table)
{
return table->count;
}
static inline int ovs_flow_tbl_need_to_expand(struct flow_table *table)
{
return (table->count > table->n_buckets);
}
struct sw_flow *ovs_flow_lookup(struct flow_table *,
const struct sw_flow_key *);
struct sw_flow *ovs_flow_lookup_unmasked_key(struct flow_table *table,
struct sw_flow_match *match);
void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred);
struct flow_table *ovs_flow_tbl_alloc(int new_size);
struct flow_table *ovs_flow_tbl_expand(struct flow_table *table);
struct flow_table *ovs_flow_tbl_rehash(struct flow_table *table);
void ovs_flow_insert(struct flow_table *table, struct sw_flow *flow);
void ovs_flow_remove(struct flow_table *table, struct sw_flow *flow);
struct sw_flow *ovs_flow_dump_next(struct flow_table *table, u32 *bucket, u32 *idx);
extern const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1];
int ovs_ipv4_tun_from_nlattr(const struct nlattr *attr,
struct sw_flow_match *match, bool is_mask);
int ovs_ipv4_tun_to_nlattr(struct sk_buff *skb,
const struct ovs_key_ipv4_tunnel *tun_key,
const struct ovs_key_ipv4_tunnel *output);
bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
const struct sw_flow_key *key, int key_end);
struct sw_flow_mask {
int ref_count;
struct rcu_head rcu;
struct list_head list;
struct sw_flow_key_range range;
struct sw_flow_key key;
};
struct sw_flow_mask *ovs_sw_flow_mask_alloc(void);
void ovs_sw_flow_mask_add_ref(struct sw_flow_mask *);
void ovs_sw_flow_mask_del_ref(struct sw_flow_mask *, bool deferred);
void ovs_sw_flow_mask_insert(struct flow_table *, struct sw_flow_mask *);
struct sw_flow_mask *ovs_sw_flow_mask_find(const struct flow_table *,
const struct sw_flow_mask *);
void ovs_flow_key_mask(struct sw_flow_key *dst, const struct sw_flow_key *src,
const struct sw_flow_mask *mask);
#endif /* flow.h */

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,60 @@
/*
* Copyright (c) 2007-2013 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
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
* 02110-1301, USA
*/
#ifndef FLOW_NETLINK_H
#define FLOW_NETLINK_H 1
#include <linux/kernel.h>
#include <linux/netlink.h>
#include <linux/openvswitch.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/rcupdate.h>
#include <linux/if_ether.h>
#include <linux/in6.h>
#include <linux/jiffies.h>
#include <linux/time.h>
#include <linux/flex_array.h>
#include <net/inet_ecn.h>
#include <net/ip_tunnels.h>
#include "flow.h"
void ovs_match_init(struct sw_flow_match *match,
struct sw_flow_key *key, struct sw_flow_mask *mask);
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_match(struct sw_flow_match *match,
const struct nlattr *,
const struct nlattr *);
int ovs_nla_copy_actions(const struct nlattr *attr,
const struct sw_flow_key *key, int depth,
struct sw_flow_actions **sfa);
int ovs_nla_put_actions(const struct nlattr *attr,
int len, struct sk_buff *skb);
struct sw_flow_actions *ovs_nla_alloc_flow_actions(int actions_len);
void ovs_nla_free_flow_actions(struct sw_flow_actions *);
#endif /* flow_netlink.h */

View File

@ -0,0 +1,517 @@
/*
* Copyright (c) 2007-2013 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
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
* 02110-1301, USA
*/
#include "flow.h"
#include "datapath.h"
#include <linux/uaccess.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
#include <net/llc_pdu.h>
#include <linux/kernel.h>
#include <linux/jhash.h>
#include <linux/jiffies.h>
#include <linux/llc.h>
#include <linux/module.h>
#include <linux/in.h>
#include <linux/rcupdate.h>
#include <linux/if_arp.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/sctp.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/icmp.h>
#include <linux/icmpv6.h>
#include <linux/rculist.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ndisc.h>
static struct kmem_cache *flow_cache;
static u16 range_n_bytes(const struct sw_flow_key_range *range)
{
return range->end - range->start;
}
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);
long *d = (long *)((u8 *)dst + mask->range.start);
int i;
/* The memory outside of the 'mask->range' are not set since
* further operations on 'dst' only uses contents within
* 'mask->range'.
*/
for (i = 0; i < range_n_bytes(&mask->range); i += sizeof(long))
*d++ = *s++ & *m++;
}
struct sw_flow *ovs_flow_alloc(void)
{
struct sw_flow *flow;
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;
return flow;
}
static struct flex_array *alloc_buckets(unsigned int n_buckets)
{
struct flex_array *buckets;
int i, err;
buckets = flex_array_alloc(sizeof(struct hlist_head),
n_buckets, GFP_KERNEL);
if (!buckets)
return NULL;
err = flex_array_prealloc(buckets, 0, n_buckets, GFP_KERNEL);
if (err) {
flex_array_free(buckets);
return NULL;
}
for (i = 0; i < n_buckets; i++)
INIT_HLIST_HEAD((struct hlist_head *)
flex_array_get(buckets, i));
return buckets;
}
static void flow_free(struct sw_flow *flow)
{
kfree((struct sf_flow_acts __force *)flow->sf_acts);
kmem_cache_free(flow_cache, flow);
}
static void rcu_free_flow_callback(struct rcu_head *rcu)
{
struct sw_flow *flow = container_of(rcu, struct sw_flow, rcu);
flow_free(flow);
}
void ovs_flow_free(struct sw_flow *flow, bool deferred)
{
if (!flow)
return;
ovs_sw_flow_mask_del_ref(flow->mask, deferred);
if (deferred)
call_rcu(&flow->rcu, rcu_free_flow_callback);
else
flow_free(flow);
}
static void free_buckets(struct flex_array *buckets)
{
flex_array_free(buckets);
}
static void __flow_tbl_destroy(struct flow_table *table)
{
int i;
if (table->keep_flows)
goto skip_flows;
for (i = 0; i < table->n_buckets; i++) {
struct sw_flow *flow;
struct hlist_head *head = flex_array_get(table->buckets, i);
struct hlist_node *n;
int ver = table->node_ver;
hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) {
hlist_del(&flow->hash_node[ver]);
ovs_flow_free(flow, false);
}
}
BUG_ON(!list_empty(table->mask_list));
kfree(table->mask_list);
skip_flows:
free_buckets(table->buckets);
kfree(table);
}
static struct flow_table *__flow_tbl_alloc(int new_size)
{
struct flow_table *table = kmalloc(sizeof(*table), GFP_KERNEL);
if (!table)
return NULL;
table->buckets = alloc_buckets(new_size);
if (!table->buckets) {
kfree(table);
return NULL;
}
table->n_buckets = new_size;
table->count = 0;
table->node_ver = 0;
table->keep_flows = false;
get_random_bytes(&table->hash_seed, sizeof(u32));
table->mask_list = NULL;
return table;
}
struct flow_table *ovs_flow_tbl_alloc(int new_size)
{
struct flow_table *table = __flow_tbl_alloc(new_size);
if (!table)
return NULL;
table->mask_list = kmalloc(sizeof(struct list_head), GFP_KERNEL);
if (!table->mask_list) {
table->keep_flows = true;
__flow_tbl_destroy(table);
return NULL;
}
INIT_LIST_HEAD(table->mask_list);
return table;
}
static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu)
{
struct flow_table *table = container_of(rcu, struct flow_table, rcu);
__flow_tbl_destroy(table);
}
void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred)
{
if (!table)
return;
if (deferred)
call_rcu(&table->rcu, flow_tbl_destroy_rcu_cb);
else
__flow_tbl_destroy(table);
}
struct sw_flow *ovs_flow_tbl_dump_next(struct flow_table *table,
u32 *bucket, u32 *last)
{
struct sw_flow *flow;
struct hlist_head *head;
int ver;
int i;
ver = table->node_ver;
while (*bucket < table->n_buckets) {
i = 0;
head = flex_array_get(table->buckets, *bucket);
hlist_for_each_entry_rcu(flow, head, hash_node[ver]) {
if (i < *last) {
i++;
continue;
}
*last = i + 1;
return flow;
}
(*bucket)++;
*last = 0;
}
return NULL;
}
static struct hlist_head *find_bucket(struct flow_table *table, u32 hash)
{
hash = jhash_1word(hash, table->hash_seed);
return flex_array_get(table->buckets,
(hash & (table->n_buckets - 1)));
}
static void __tbl_insert(struct flow_table *table, struct sw_flow *flow)
{
struct hlist_head *head;
head = find_bucket(table, flow->hash);
hlist_add_head_rcu(&flow->hash_node[table->node_ver], head);
table->count++;
}
static void flow_table_copy_flows(struct flow_table *old,
struct flow_table *new)
{
int old_ver;
int i;
old_ver = old->node_ver;
new->node_ver = !old_ver;
/* Insert in new table. */
for (i = 0; i < old->n_buckets; i++) {
struct sw_flow *flow;
struct hlist_head *head;
head = flex_array_get(old->buckets, i);
hlist_for_each_entry(flow, head, hash_node[old_ver])
__tbl_insert(new, flow);
}
new->mask_list = old->mask_list;
old->keep_flows = true;
}
static struct flow_table *__flow_tbl_rehash(struct flow_table *table,
int n_buckets)
{
struct flow_table *new_table;
new_table = __flow_tbl_alloc(n_buckets);
if (!new_table)
return ERR_PTR(-ENOMEM);
flow_table_copy_flows(table, new_table);
return new_table;
}
struct flow_table *ovs_flow_tbl_rehash(struct flow_table *table)
{
return __flow_tbl_rehash(table, table->n_buckets);
}
struct flow_table *ovs_flow_tbl_expand(struct flow_table *table)
{
return __flow_tbl_rehash(table, table->n_buckets * 2);
}
static u32 flow_hash(const struct sw_flow_key *key, int key_start,
int key_end)
{
u32 *hash_key = (u32 *)((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);
}
static int flow_key_start(const struct sw_flow_key *key)
{
if (key->tun_key.ipv4_dst)
return 0;
else
return rounddown(offsetof(struct sw_flow_key, phy),
sizeof(long));
}
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);
long diffs = 0;
int i;
for (i = key_start; i < key_end; i += sizeof(long))
diffs |= *cp1++ ^ *cp2++;
return diffs == 0;
}
static bool flow_cmp_masked_key(const struct sw_flow *flow,
const struct sw_flow_key *key,
int key_start, int key_end)
{
return cmp_key(&flow->key, key, key_start, key_end);
}
bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
struct sw_flow_match *match)
{
struct sw_flow_key *key = match->key;
int key_start = flow_key_start(key);
int key_end = match->range.end;
return cmp_key(&flow->unmasked_key, key, key_start, key_end);
}
static struct sw_flow *masked_flow_lookup(struct flow_table *table,
const struct sw_flow_key *unmasked,
struct sw_flow_mask *mask)
{
struct sw_flow *flow;
struct hlist_head *head;
int key_start = mask->range.start;
int key_end = mask->range.end;
u32 hash;
struct sw_flow_key masked_key;
ovs_flow_mask_key(&masked_key, unmasked, mask);
hash = flow_hash(&masked_key, key_start, key_end);
head = find_bucket(table, hash);
hlist_for_each_entry_rcu(flow, head, hash_node[table->node_ver]) {
if (flow->mask == mask &&
flow_cmp_masked_key(flow, &masked_key,
key_start, key_end))
return flow;
}
return NULL;
}
struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
const struct sw_flow_key *key)
{
struct sw_flow *flow = NULL;
struct sw_flow_mask *mask;
list_for_each_entry_rcu(mask, tbl->mask_list, list) {
flow = masked_flow_lookup(tbl, key, mask);
if (flow) /* Found */
break;
}
return flow;
}
void ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow)
{
flow->hash = flow_hash(&flow->key, flow->mask->range.start,
flow->mask->range.end);
__tbl_insert(table, flow);
}
void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow)
{
BUG_ON(table->count == 0);
hlist_del_rcu(&flow->hash_node[table->node_ver]);
table->count--;
}
struct sw_flow_mask *ovs_sw_flow_mask_alloc(void)
{
struct sw_flow_mask *mask;
mask = kmalloc(sizeof(*mask), GFP_KERNEL);
if (mask)
mask->ref_count = 0;
return mask;
}
void ovs_sw_flow_mask_add_ref(struct sw_flow_mask *mask)
{
mask->ref_count++;
}
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);
}
void ovs_sw_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);
}
}
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;
return (a->range.end == b->range.end)
&& (a->range.start == b->range.start)
&& (memcmp(a_, b_, range_n_bytes(&a->range)) == 0);
}
struct sw_flow_mask *ovs_sw_flow_mask_find(const struct flow_table *tbl,
const struct sw_flow_mask *mask)
{
struct list_head *ml;
list_for_each(ml, tbl->mask_list) {
struct sw_flow_mask *m;
m = container_of(ml, struct sw_flow_mask, list);
if (mask_equal(mask, m))
return m;
}
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.
*/
void ovs_sw_flow_mask_insert(struct flow_table *tbl, struct sw_flow_mask *mask)
{
list_add_rcu(&mask->list, tbl->mask_list);
}
/* Initializes the flow module.
* Returns zero if successful or a negative error code. */
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);
if (flow_cache == NULL)
return -ENOMEM;
return 0;
}
/* Uninitializes the flow module. */
void ovs_flow_exit(void)
{
kmem_cache_destroy(flow_cache);
}

View File

@ -0,0 +1,91 @@
/*
* Copyright (c) 2007-2013 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
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
* 02110-1301, USA
*/
#ifndef FLOW_TABLE_H
#define FLOW_TABLE_H 1
#include <linux/kernel.h>
#include <linux/netlink.h>
#include <linux/openvswitch.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/rcupdate.h>
#include <linux/if_ether.h>
#include <linux/in6.h>
#include <linux/jiffies.h>
#include <linux/time.h>
#include <linux/flex_array.h>
#include <net/inet_ecn.h>
#include <net/ip_tunnels.h>
#include "flow.h"
#define TBL_MIN_BUCKETS 1024
struct flow_table {
struct flex_array *buckets;
unsigned int count, n_buckets;
struct rcu_head rcu;
struct list_head *mask_list;
int node_ver;
u32 hash_seed;
bool keep_flows;
};
int ovs_flow_init(void);
void ovs_flow_exit(void);
struct sw_flow *ovs_flow_alloc(void);
void ovs_flow_free(struct sw_flow *, bool deferred);
static inline int ovs_flow_tbl_count(struct flow_table *table)
{
return table->count;
}
static inline int ovs_flow_tbl_need_to_expand(struct flow_table *table)
{
return (table->count > table->n_buckets);
}
struct flow_table *ovs_flow_tbl_alloc(int new_size);
struct flow_table *ovs_flow_tbl_expand(struct flow_table *table);
struct flow_table *ovs_flow_tbl_rehash(struct flow_table *table);
void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred);
void ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow);
void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow);
struct sw_flow *ovs_flow_tbl_dump_next(struct flow_table *table,
u32 *bucket, u32 *idx);
struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *,
const struct sw_flow_key *);
bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
struct sw_flow_match *match);
struct sw_flow_mask *ovs_sw_flow_mask_alloc(void);
void ovs_sw_flow_mask_add_ref(struct sw_flow_mask *);
void ovs_sw_flow_mask_del_ref(struct sw_flow_mask *, bool deferred);
void ovs_sw_flow_mask_insert(struct flow_table *, struct sw_flow_mask *);
struct sw_flow_mask *ovs_sw_flow_mask_find(const struct flow_table *,
const struct sw_flow_mask *);
void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
const struct sw_flow_mask *mask);
#endif /* flow_table.h */