aboutsummaryrefslogtreecommitdiffstats
path: root/net/openvswitch
diff options
context:
space:
mode:
Diffstat (limited to 'net/openvswitch')
-rw-r--r--net/openvswitch/actions.c4
-rw-r--r--net/openvswitch/datapath.c778
-rw-r--r--net/openvswitch/datapath.h8
-rw-r--r--net/openvswitch/flow.c188
-rw-r--r--net/openvswitch/flow.h53
-rw-r--r--net/openvswitch/flow_netlink.c186
-rw-r--r--net/openvswitch/flow_netlink.h1
-rw-r--r--net/openvswitch/flow_table.c121
-rw-r--r--net/openvswitch/flow_table.h4
-rw-r--r--net/openvswitch/vport-gre.c4
-rw-r--r--net/openvswitch/vport-internal_dev.c2
-rw-r--r--net/openvswitch/vport-vxlan.c7
-rw-r--r--net/openvswitch/vport.h6
13 files changed, 724 insertions, 638 deletions
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 2c77e7b1a913..c36856a457ca 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -134,8 +134,8 @@ 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);
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index a3276e3c4feb..0d407bca81e3 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -44,11 +44,11 @@
#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 <linux/genetlink.h>
+#include <net/genetlink.h>
#include <net/genetlink.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
@@ -62,6 +62,31 @@
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 struct genl_multicast_group ovs_dp_flow_multicast_group = {
+ .name = OVS_FLOW_MCGROUP
+};
+
+static struct genl_multicast_group ovs_dp_datapath_multicast_group = {
+ .name = OVS_DATAPATH_MCGROUP
+};
+
+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_info *info,
+ const struct genl_multicast_group *grp)
+{
+ return info->nlhdr->nlmsg_flags & NLM_F_ECHO ||
+ netlink_has_listeners(genl_info_net(info)->genl_sock, 0);
+}
+
static void ovs_notify(struct genl_family *family,
struct sk_buff *skb, struct genl_info *info)
{
@@ -173,6 +198,7 @@ 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;
@@ -262,16 +288,6 @@ out:
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)
{
@@ -524,7 +540,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
packet->protocol = htons(ETH_P_802_2);
/* Build an sw_flow for sending this packet. */
- flow = ovs_flow_alloc(false);
+ flow = ovs_flow_alloc();
err = PTR_ERR(flow);
if (IS_ERR(flow))
goto err_kfree_skb;
@@ -590,6 +606,18 @@ 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)
{
@@ -621,26 +649,6 @@ 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))
@@ -652,8 +660,8 @@ 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)
{
@@ -670,7 +678,7 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
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);
@@ -693,6 +701,7 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
nla_nest_end(skb, nla);
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;
@@ -720,9 +729,9 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
const struct sw_flow_actions *sf_acts;
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 {
@@ -743,113 +752,128 @@ error:
return err;
}
-static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow,
- struct genl_info *info)
+/* 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)
{
- size_t len;
+ struct sk_buff *skb;
+
+ if (!always && !ovs_must_notify(info, &ovs_dp_flow_multicast_group))
+ return NULL;
- len = ovs_flow_cmd_msg_size(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_unicast(len, info, GFP_KERNEL);
+ return skb;
}
-static struct sk_buff *ovs_flow_cmd_build_info(struct sw_flow *flow,
- struct datapath *dp,
- struct genl_info *info,
- 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, info);
- if (!skb)
- return ERR_PTR(-ENOMEM);
+ skb = ovs_flow_cmd_alloc_info(ovsl_dereference(flow->sf_acts), info,
+ always);
+ if (!skb || IS_ERR(skb))
+ return skb;
- retval = ovs_flow_cmd_fill_info(flow, dp, skb, info->snd_portid,
- info->snd_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 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;
- bool exact_5tuple;
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);
- error = ovs_nla_get_match(&match, &exact_5tuple,
+ /* 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(!exact_5tuple);
- if (IS_ERR(flow)) {
- error = PTR_ERR(flow);
- goto err_unlock_ovs;
- }
-
- 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, 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.
@@ -858,40 +882,154 @@ 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. */
- if (!ovs_flow_cmp_unmasked_key(flow, &match))
+ if (unlikely(!ovs_flow_cmp_unmasked_key(flow, &match))) {
+ error = -EEXIST;
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;
+}
+
+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, masked_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 = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS]));
+ error = PTR_ERR(acts);
+ if (IS_ERR(acts))
+ goto error;
+
+ 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_acts;
+ }
+ }
+
+ /* 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;
+ }
+ }
- reply = ovs_flow_cmd_build_info(flow, dp, info, OVS_FLOW_CMD_NEW);
+ 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(&dp->table, &key);
+ if (unlikely(!flow)) {
+ error = -ENOENT;
+ goto err_unlock_ovs;
+ }
+ /* The unmasked key has to be the same for flow updates. */
+ if (unlikely(!ovs_flow_cmp_unmasked_key(flow, &match))) {
+ error = -EEXIST;
+ 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);
- /* Clear stats. */
- if (a[OVS_FLOW_ATTR_CLEAR])
- ovs_flow_stats_clear(flow);
+ 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;
@@ -914,7 +1052,7 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
}
ovs_match_init(&match, &key, NULL);
- err = ovs_nla_get_match(&match, NULL, a[OVS_FLOW_ATTR_KEY], NULL);
+ err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
if (err)
return err;
@@ -931,7 +1069,8 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
goto unlock;
}
- reply = ovs_flow_cmd_build_info(flow, dp, info, 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;
@@ -955,45 +1094,53 @@ 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, NULL, 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)) {
+ if (unlikely(!flow || !ovs_flow_cmp_unmasked_key(flow, &match))) {
err = -ENOENT;
goto unlock;
}
- reply = ovs_flow_cmd_alloc_info(flow, info);
- 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();
@@ -1024,7 +1171,7 @@ 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)
@@ -1037,11 +1184,17 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
return skb->len;
}
-static const struct genl_ops dp_flow_genl_ops[] = {
+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_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. */
@@ -1057,28 +1210,22 @@ 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 },
- [OVS_DP_ATTR_USER_FEATURES] = { .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)
@@ -1093,6 +1240,7 @@ static size_t ovs_dp_cmd_msg_size(void)
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)
{
@@ -1108,9 +1256,7 @@ 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;
@@ -1135,25 +1281,12 @@ error:
return -EMSGSIZE;
}
-static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp,
- struct genl_info *info, u8 cmd)
+static struct sk_buff *ovs_dp_cmd_alloc_info(struct genl_info *info)
{
- struct sk_buff *skb;
- int retval;
-
- skb = genlmsg_new_unicast(ovs_dp_cmd_msg_size(), info, GFP_KERNEL);
- if (!skb)
- return ERR_PTR(-ENOMEM);
-
- retval = ovs_dp_cmd_fill_info(dp, skb, info->snd_portid, info->snd_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])
@@ -1165,10 +1298,8 @@ 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);
}
@@ -1205,12 +1336,14 @@ 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)));
@@ -1245,6 +1378,9 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
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)) {
err = PTR_ERR(vport);
@@ -1263,10 +1399,9 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
goto err_destroy_ports_array;
}
- reply = ovs_dp_cmd_build_info(dp, info, 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);
@@ -1276,9 +1411,8 @@ 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);
@@ -1287,8 +1421,8 @@ err_destroy_table:
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;
}
@@ -1326,16 +1460,19 @@ 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, 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();
@@ -1343,8 +1480,10 @@ 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;
}
@@ -1354,29 +1493,30 @@ 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;
ovs_dp_change(dp, info->attrs);
- reply = ovs_dp_cmd_build_info(dp, info, 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;
- }
+ 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;
}
@@ -1386,24 +1526,26 @@ 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, 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;
}
@@ -1430,7 +1572,13 @@ static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
return skb->len;
}
-static const struct genl_ops dp_datapath_genl_ops[] = {
+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 struct genl_ops dp_datapath_genl_ops[] = {
{ .cmd = OVS_DP_CMD_NEW,
.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
.policy = datapath_policy,
@@ -1454,27 +1602,18 @@ 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,
-};
-
-static 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. */
@@ -1516,7 +1655,12 @@ 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)
{
@@ -1578,33 +1722,35 @@ 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)
@@ -1622,22 +1768,19 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
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;
}
@@ -1648,28 +1791,26 @@ 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])
@@ -1683,10 +1824,9 @@ 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;
}
@@ -1697,30 +1837,33 @@ 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;
}
@@ -1732,24 +1875,25 @@ 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;
}
@@ -1792,7 +1936,16 @@ out:
return skb->len;
}
-static const struct genl_ops dp_vport_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 },
+};
+
+static struct genl_ops dp_vport_genl_ops[] = {
{ .cmd = OVS_VPORT_CMD_NEW,
.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
.policy = vport_policy,
@@ -1816,26 +1969,25 @@ 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)
@@ -1843,33 +1995,25 @@ 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;
}
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 05317380fc03..7ede507500d7 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -194,7 +194,9 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq,
int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb);
void ovs_dp_notify_wq(struct work_struct *work);
-#define OVS_NLERR(fmt, ...) \
- pr_info_once("netlink: " fmt, ##__VA_ARGS__)
-
+#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 2998989e76db..334751cb1528 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -64,88 +64,110 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies)
void ovs_flow_stats_update(struct sw_flow *flow, struct sk_buff *skb)
{
struct flow_stats *stats;
- __be16 tcp_flags = 0;
-
- if (!flow->stats.is_percpu)
- stats = flow->stats.stat;
- else
- stats = this_cpu_ptr(flow->stats.cpu_stats);
-
- if ((flow->key.eth.type == htons(ETH_P_IP) ||
- flow->key.eth.type == htons(ETH_P_IPV6)) &&
- flow->key.ip.frag != OVS_FRAG_TYPE_LATER &&
- flow->key.ip.proto == IPPROTO_TCP &&
- likely(skb->len >= skb_transport_offset(skb) + sizeof(struct tcphdr))) {
- tcp_flags = TCP_FLAGS_BE16(tcp_hdr(skb));
+ __be16 tcp_flags = flow->key.tp.flags;
+ 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_dereference(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;
+ }
}
- spin_lock(&stats->lock);
stats->used = jiffies;
stats->packet_count++;
stats->byte_count += skb->len;
stats->tcp_flags |= tcp_flags;
+unlock:
spin_unlock(&stats->lock);
}
-static void stats_read(struct flow_stats *stats,
- struct ovs_flow_stats *ovs_stats,
- unsigned long *used, __be16 *tcp_flags)
-{
- spin_lock(&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(&stats->lock);
-}
-
-void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *ovs_stats,
+/* 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 cpu;
+ int node;
*used = 0;
*tcp_flags = 0;
memset(ovs_stats, 0, sizeof(*ovs_stats));
- local_bh_disable();
- if (!flow->stats.is_percpu) {
- stats_read(flow->stats.stat, ovs_stats, used, tcp_flags);
- } else {
- for_each_possible_cpu(cpu) {
- struct flow_stats *stats;
+ for_each_node(node) {
+ struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[node]);
- stats = per_cpu_ptr(flow->stats.cpu_stats, cpu);
- stats_read(stats, ovs_stats, used, tcp_flags);
+ 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);
}
}
- local_bh_enable();
-}
-
-static void stats_reset(struct flow_stats *stats)
-{
- spin_lock(&stats->lock);
- stats->used = 0;
- stats->packet_count = 0;
- stats->byte_count = 0;
- stats->tcp_flags = 0;
- spin_unlock(&stats->lock);
}
+/* Called with ovs_mutex. */
void ovs_flow_stats_clear(struct sw_flow *flow)
{
- int cpu;
-
- local_bh_disable();
- if (!flow->stats.is_percpu) {
- stats_reset(flow->stats.stat);
- } else {
- for_each_possible_cpu(cpu) {
- stats_reset(per_cpu_ptr(flow->stats.cpu_stats, cpu));
+ 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);
}
}
- local_bh_enable();
}
static int check_header(struct sk_buff *skb, int len)
@@ -332,8 +354,8 @@ 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 ||
@@ -372,14 +394,14 @@ 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;
@@ -439,8 +461,8 @@ 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
@@ -495,21 +517,21 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
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 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 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 if (key->ip.proto == IPPROTO_ICMP) {
if (icmphdr_ok(skb)) {
@@ -517,8 +539,8 @@ 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);
}
}
@@ -538,8 +560,8 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
key->ip.proto = ntohs(arp->ar_op);
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 if (key->eth.type == htons(ETH_P_IPV6)) {
int nh_len; /* IPv6 Header + Extensions */
@@ -564,21 +586,21 @@ 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 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 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 if (key->ip.proto == NEXTHDR_ICMP) {
if (icmp6hdr_ok(skb)) {
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 2d770e28a3a3..ac395d2cd821 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -47,7 +47,7 @@ struct ovs_key_ipv4_tunnel {
__be16 tun_flags;
u8 ipv4_tos;
u8 ipv4_ttl;
-};
+} __packed __aligned(4); /* Minimize padding. */
static inline void ovs_flow_tun_key_init(struct ovs_key_ipv4_tunnel *tun_key,
const struct iphdr *iph, __be64 tun_id,
@@ -71,7 +71,7 @@ struct sw_flow_key {
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'. */
struct {
u8 src[ETH_ALEN]; /* Ethernet source address. */
u8 dst[ETH_ALEN]; /* Ethernet destination address. */
@@ -84,23 +84,21 @@ 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 {
@@ -109,11 +107,6 @@ 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. */
@@ -155,24 +148,22 @@ struct flow_stats {
__be16 tcp_flags; /* Union of seen TCP flags. */
};
-struct sw_flow_stats {
- bool is_percpu;
- union {
- struct flow_stats *stat;
- struct flow_stats __percpu *cpu_stats;
- };
-};
-
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;
- struct sw_flow_stats stats;
+ 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 {
@@ -189,10 +180,10 @@ struct arp_eth_header {
unsigned char ar_tip[4]; /* target IP address */
} __packed;
-void ovs_flow_stats_update(struct sw_flow *flow, struct sk_buff *skb);
-void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *stats,
+void ovs_flow_stats_update(struct sw_flow *, 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 *flow);
+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 *);
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 4d000acaed0d..d757848da89c 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -16,6 +16,8 @@
* 02110-1301, USA
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include "flow.h"
#include "datapath.h"
#include <linux/uaccess.h>
@@ -202,11 +204,11 @@ 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 +218,14 @@ 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;
}
@@ -266,20 +268,6 @@ static bool is_all_zero(const u8 *fp, size_t size)
return true;
}
-static bool is_all_set(const u8 *fp, size_t size)
-{
- int i;
-
- if (!fp)
- return false;
-
- for (i = 0; i < size; i++)
- if (fp[i] != 0xff)
- return false;
-
- return true;
-}
-
static int __parse_flow_nlattrs(const struct nlattr *attr,
const struct nlattr *a[],
u64 *attrsp, bool nz)
@@ -501,9 +489,8 @@ 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, bool *exact_5tuple,
- u64 attrs, const struct nlattr **a,
- bool is_mask)
+static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
+ const struct nlattr **a, bool is_mask)
{
int err;
u64 orig_attrs = attrs;
@@ -560,11 +547,6 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, bool *exact_5tuple
SW_FLOW_KEY_PUT(match, eth.type, htons(ETH_P_802_2), is_mask);
}
- if (is_mask && exact_5tuple) {
- if (match->mask->key.eth.type != htons(0xffff))
- *exact_5tuple = false;
- }
-
if (attrs & (1 << OVS_KEY_ATTR_IPV4)) {
const struct ovs_key_ipv4 *ipv4_key;
@@ -587,13 +569,6 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, bool *exact_5tuple
SW_FLOW_KEY_PUT(match, ipv4.addr.dst,
ipv4_key->ipv4_dst, is_mask);
attrs &= ~(1 << OVS_KEY_ATTR_IPV4);
-
- if (is_mask && exact_5tuple && *exact_5tuple) {
- if (ipv4_key->ipv4_proto != 0xff ||
- ipv4_key->ipv4_src != htonl(0xffffffff) ||
- ipv4_key->ipv4_dst != htonl(0xffffffff))
- *exact_5tuple = false;
- }
}
if (attrs & (1 << OVS_KEY_ATTR_IPV6)) {
@@ -625,13 +600,6 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, bool *exact_5tuple
is_mask);
attrs &= ~(1 << OVS_KEY_ATTR_IPV6);
-
- if (is_mask && exact_5tuple && *exact_5tuple) {
- if (ipv6_key->ipv6_proto != 0xff ||
- !is_all_set((u8 *)ipv6_key->ipv6_src, sizeof(match->key->ipv6.addr.src)) ||
- !is_all_set((u8 *)ipv6_key->ipv6_dst, sizeof(match->key->ipv6.addr.dst)))
- *exact_5tuple = false;
- }
}
if (attrs & (1 << OVS_KEY_ATTR_ARP)) {
@@ -662,32 +630,18 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, bool *exact_5tuple
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 (is_mask && exact_5tuple && *exact_5tuple &&
- (tcp_key->tcp_src != htons(0xffff) ||
- tcp_key->tcp_dst != htons(0xffff)))
- *exact_5tuple = false;
}
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);
}
@@ -698,40 +652,17 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, bool *exact_5tuple
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);
-
- if (is_mask && exact_5tuple && *exact_5tuple &&
- (udp_key->udp_src != htons(0xffff) ||
- udp_key->udp_dst != htons(0xffff)))
- *exact_5tuple = false;
}
if (attrs & (1 << OVS_KEY_ATTR_SCTP)) {
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);
}
@@ -739,9 +670,9 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, bool *exact_5tuple
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);
}
@@ -750,9 +681,9 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, bool *exact_5tuple
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);
}
@@ -800,7 +731,6 @@ static void sw_flow_mask_set(struct sw_flow_mask *mask,
* attribute specifies the mask field of the wildcarded flow.
*/
int ovs_nla_get_match(struct sw_flow_match *match,
- bool *exact_5tuple,
const struct nlattr *key,
const struct nlattr *mask)
{
@@ -848,13 +778,10 @@ int ovs_nla_get_match(struct sw_flow_match *match,
}
}
- err = ovs_key_from_nlattrs(match, NULL, key_attrs, a, false);
+ err = ovs_key_from_nlattrs(match, key_attrs, a, false);
if (err)
return err;
- if (exact_5tuple)
- *exact_5tuple = true;
-
if (mask) {
err = parse_flow_mask_nlattrs(mask, a, &mask_attrs);
if (err)
@@ -892,7 +819,7 @@ int ovs_nla_get_match(struct sw_flow_match *match,
}
}
- err = ovs_key_from_nlattrs(match, exact_5tuple, mask_attrs, a, true);
+ err = ovs_key_from_nlattrs(match, mask_attrs, a, true);
if (err)
return err;
} else {
@@ -982,8 +909,8 @@ 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;
@@ -1055,8 +982,8 @@ 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) ||
@@ -1070,19 +997,11 @@ 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;
@@ -1090,13 +1009,8 @@ 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;
@@ -1104,13 +1018,8 @@ 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;
@@ -1119,8 +1028,8 @@ 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;
@@ -1130,8 +1039,8 @@ 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) {
@@ -1143,8 +1052,8 @@ 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);
}
}
}
@@ -1309,13 +1218,10 @@ 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;
}
diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h
index b31fbe28bc7a..440151045d39 100644
--- a/net/openvswitch/flow_netlink.h
+++ b/net/openvswitch/flow_netlink.h
@@ -45,7 +45,6 @@ int ovs_nla_put_flow(const struct sw_flow_key *,
int ovs_nla_get_flow_metadata(struct sw_flow *flow,
const struct nlattr *attr);
int ovs_nla_get_match(struct sw_flow_match *match,
- bool *exact_5tuple,
const struct nlattr *,
const struct nlattr *);
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index 3c268b3d71c3..574c3abc9b30 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -48,6 +48,7 @@
#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)
{
@@ -57,8 +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;
@@ -70,10 +73,11 @@ void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
*d++ = *s++ & *m++;
}
-struct sw_flow *ovs_flow_alloc(bool percpu_stats)
+struct sw_flow *ovs_flow_alloc(void)
{
struct sw_flow *flow;
- int cpu;
+ struct flow_stats *stats;
+ int node;
flow = kmem_cache_alloc(flow_cache, GFP_KERNEL);
if (!flow)
@@ -81,27 +85,22 @@ struct sw_flow *ovs_flow_alloc(bool percpu_stats)
flow->sf_acts = NULL;
flow->mask = NULL;
+ flow->stats_last_writer = NUMA_NO_NODE;
- flow->stats.is_percpu = percpu_stats;
+ /* Initialize the default stat node. */
+ stats = kmem_cache_alloc_node(flow_stats_cache,
+ GFP_KERNEL | __GFP_ZERO, 0);
+ if (!stats)
+ goto err;
- if (!percpu_stats) {
- flow->stats.stat = kzalloc(sizeof(*flow->stats.stat), GFP_KERNEL);
- if (!flow->stats.stat)
- goto err;
+ spin_lock_init(&stats->lock);
- spin_lock_init(&flow->stats.stat->lock);
- } else {
- flow->stats.cpu_stats = alloc_percpu(struct flow_stats);
- if (!flow->stats.cpu_stats)
- goto err;
+ RCU_INIT_POINTER(flow->stats[0], stats);
- for_each_possible_cpu(cpu) {
- struct flow_stats *cpu_stats;
+ for_each_node(node)
+ if (node != 0)
+ RCU_INIT_POINTER(flow->stats[node], NULL);
- cpu_stats = per_cpu_ptr(flow->stats.cpu_stats, cpu);
- spin_lock_init(&cpu_stats->lock);
- }
- }
return flow;
err:
kmem_cache_free(flow_cache, flow);
@@ -138,11 +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);
- if (flow->stats.is_percpu)
- free_percpu(flow->stats.cpu_stats);
- else
- kfree(flow->stats.stat);
+ 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);
}
@@ -158,25 +159,6 @@ void ovs_flow_free(struct sw_flow *flow, bool deferred)
if (!flow)
return;
- if (flow->mask) {
- struct sw_flow_mask *mask = flow->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);
- if (deferred)
- kfree_rcu(mask, rcu);
- else
- kfree(mask);
- }
- }
-
if (deferred)
call_rcu(&flow->rcu, rcu_free_flow_callback);
else
@@ -375,7 +357,7 @@ 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. */
@@ -397,8 +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;
@@ -490,6 +472,25 @@ 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);
@@ -497,6 +498,11 @@ 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)
@@ -513,8 +519,8 @@ static struct sw_flow_mask *mask_alloc(void)
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)
@@ -559,6 +565,7 @@ static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow,
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)
{
@@ -597,16 +604,28 @@ 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 baaeb101924d..ca8a5820f615 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -52,10 +52,12 @@ struct flow_table {
unsigned int count;
};
+extern struct kmem_cache *flow_stats_cache;
+
int ovs_flow_init(void);
void ovs_flow_exit(void);
-struct sw_flow *ovs_flow_alloc(bool percpu_stats);
+struct sw_flow *ovs_flow_alloc(void);
void ovs_flow_free(struct sw_flow *, bool deferred);
int ovs_flow_tbl_init(struct flow_table *);
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index ebb6e2442554..35ec4fed09e2 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -172,7 +172,7 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
df = OVS_CB(skb)->tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
htons(IP_DF) : 0;
- skb->local_df = 1;
+ skb->ignore_df = 1;
return iptunnel_xmit(skb->sk, rt, skb, fl.saddr,
OVS_CB(skb)->tun_key->ipv4_dst, IPPROTO_GRE,
@@ -256,7 +256,7 @@ 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..789af9280e77 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -130,7 +130,7 @@ 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->tx_queue_len = 0;
netdev->features = NETIF_F_LLTX | NETIF_F_SG | NETIF_F_FRAGLIST |
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index e797a50ac2be..0edbd95c60e7 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -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;
@@ -170,7 +170,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
df = OVS_CB(skb)->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);
@@ -180,7 +180,8 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
OVS_CB(skb)->tun_key->ipv4_tos,
OVS_CB(skb)->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(OVS_CB(skb)->tun_key->tun_id) << 8),
+ false);
if (err < 0)
ip_rt_put(rt);
error:
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index d7e50a17396c..8d721e62f388 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -172,7 +172,7 @@ 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);
}
/**
@@ -185,9 +185,9 @@ 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 *,
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.