aboutsummaryrefslogtreecommitdiffstats
path: root/net/openvswitch
diff options
context:
space:
mode:
Diffstat (limited to 'net/openvswitch')
-rw-r--r--net/openvswitch/Kconfig3
-rw-r--r--net/openvswitch/actions.c32
-rw-r--r--net/openvswitch/conntrack.c145
-rw-r--r--net/openvswitch/conntrack.h9
-rw-r--r--net/openvswitch/datapath.c9
-rw-r--r--net/openvswitch/datapath.h1
-rw-r--r--net/openvswitch/flow.h2
-rw-r--r--net/openvswitch/flow_netlink.c133
-rw-r--r--net/openvswitch/flow_netlink.h6
-rw-r--r--net/openvswitch/flow_table.c26
-rw-r--r--net/openvswitch/flow_table.h2
-rw-r--r--net/openvswitch/vport-geneve.c13
-rw-r--r--net/openvswitch/vport-gre.c8
-rw-r--r--net/openvswitch/vport-internal_dev.c46
-rw-r--r--net/openvswitch/vport-vxlan.c19
-rw-r--r--net/openvswitch/vport.c109
-rw-r--r--net/openvswitch/vport.h35
17 files changed, 288 insertions, 310 deletions
diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig
index 2a071f470d57..d143aa9f6654 100644
--- a/net/openvswitch/Kconfig
+++ b/net/openvswitch/Kconfig
@@ -5,7 +5,8 @@
config OPENVSWITCH
tristate "Open vSwitch"
depends on INET
- depends on (!NF_CONNTRACK || NF_CONNTRACK)
+ depends on !NF_CONNTRACK || \
+ (NF_CONNTRACK && (!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6))
select LIBCRC32C
select MPLS
select NET_MPLS_GSO
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 315f5330b6e5..dba635d086b2 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -684,7 +684,7 @@ static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru,
{
if (skb_network_offset(skb) > MAX_L2_LEN) {
OVS_NLERR(1, "L2 header too long to fragment");
- return;
+ goto err;
}
if (ethertype == htons(ETH_P_IP)) {
@@ -708,8 +708,7 @@ static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru,
struct rt6_info ovs_rt;
if (!v6ops) {
- kfree_skb(skb);
- return;
+ goto err;
}
prepare_frag(vport, skb);
@@ -728,8 +727,12 @@ static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru,
WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.",
ovs_vport_name(vport), ntohs(ethertype), mru,
vport->dev->mtu);
- kfree_skb(skb);
+ goto err;
}
+
+ return;
+err:
+ kfree_skb(skb);
}
static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
@@ -765,7 +768,6 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key, const struct nlattr *attr,
const struct nlattr *actions, int actions_len)
{
- struct ip_tunnel_info info;
struct dp_upcall_info upcall;
const struct nlattr *a;
int rem;
@@ -793,11 +795,9 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
if (vport) {
int err;
- upcall.egress_tun_info = &info;
- err = ovs_vport_get_egress_tun_info(vport, skb,
- &upcall);
- if (err)
- upcall.egress_tun_info = NULL;
+ err = dev_fill_metadata_dst(vport->dev, skb);
+ if (!err)
+ upcall.egress_tun_info = skb_tunnel_info(skb);
}
break;
@@ -968,7 +968,7 @@ static int execute_masked_set_action(struct sk_buff *skb,
case OVS_KEY_ATTR_CT_STATE:
case OVS_KEY_ATTR_CT_ZONE:
case OVS_KEY_ATTR_CT_MARK:
- case OVS_KEY_ATTR_CT_LABEL:
+ case OVS_KEY_ATTR_CT_LABELS:
err = -EINVAL;
break;
}
@@ -1099,12 +1099,18 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
break;
case OVS_ACTION_ATTR_CT:
+ if (!is_flow_key_valid(key)) {
+ err = ovs_flow_key_update(skb, key);
+ if (err)
+ return err;
+ }
+
err = ovs_ct_execute(ovs_dp_get_net(dp), skb, key,
nla_data(a));
/* Hide stolen IP fragments from user space. */
- if (err == -EINPROGRESS)
- return 0;
+ if (err)
+ return err == -EINPROGRESS ? 0 : err;
break;
}
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index e8e524ad8a01..50095820edb7 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -37,9 +37,9 @@ struct md_mark {
};
/* Metadata label for masked write to conntrack label. */
-struct md_label {
- struct ovs_key_ct_label value;
- struct ovs_key_ct_label mask;
+struct md_labels {
+ struct ovs_key_ct_labels value;
+ struct ovs_key_ct_labels mask;
};
/* Conntrack action context for execution. */
@@ -47,10 +47,10 @@ struct ovs_conntrack_info {
struct nf_conntrack_helper *helper;
struct nf_conntrack_zone zone;
struct nf_conn *ct;
- u32 flags;
+ u8 commit : 1;
u16 family;
struct md_mark mark;
- struct md_label label;
+ struct md_labels labels;
};
static u16 key_to_nfproto(const struct sw_flow_key *key)
@@ -109,21 +109,21 @@ static u32 ovs_ct_get_mark(const struct nf_conn *ct)
#endif
}
-static void ovs_ct_get_label(const struct nf_conn *ct,
- struct ovs_key_ct_label *label)
+static void ovs_ct_get_labels(const struct nf_conn *ct,
+ struct ovs_key_ct_labels *labels)
{
struct nf_conn_labels *cl = ct ? nf_ct_labels_find(ct) : NULL;
if (cl) {
size_t len = cl->words * sizeof(long);
- if (len > OVS_CT_LABEL_LEN)
- len = OVS_CT_LABEL_LEN;
- else if (len < OVS_CT_LABEL_LEN)
- memset(label, 0, OVS_CT_LABEL_LEN);
- memcpy(label, cl->bits, len);
+ if (len > OVS_CT_LABELS_LEN)
+ len = OVS_CT_LABELS_LEN;
+ else if (len < OVS_CT_LABELS_LEN)
+ memset(labels, 0, OVS_CT_LABELS_LEN);
+ memcpy(labels, cl->bits, len);
} else {
- memset(label, 0, OVS_CT_LABEL_LEN);
+ memset(labels, 0, OVS_CT_LABELS_LEN);
}
}
@@ -134,7 +134,7 @@ static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state,
key->ct.state = state;
key->ct.zone = zone->id;
key->ct.mark = ovs_ct_get_mark(ct);
- ovs_ct_get_label(ct, &key->ct.label);
+ ovs_ct_get_labels(ct, &key->ct.labels);
}
/* Update 'key' based on skb->nfct. If 'post_ct' is true, then OVS has
@@ -151,6 +151,8 @@ static void ovs_ct_update_key(const struct sk_buff *skb,
ct = nf_ct_get(skb, &ctinfo);
if (ct) {
state = ovs_ct_get_state(ctinfo);
+ if (!nf_ct_is_confirmed(ct))
+ state |= OVS_CS_F_NEW;
if (ct->master)
state |= OVS_CS_F_RELATED;
zone = nf_ct_zone(ct);
@@ -167,7 +169,7 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key)
int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb)
{
- if (nla_put_u8(skb, OVS_KEY_ATTR_CT_STATE, key->ct.state))
+ if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, key->ct.state))
return -EMSGSIZE;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
@@ -179,8 +181,8 @@ int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb)
return -EMSGSIZE;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
- nla_put(skb, OVS_KEY_ATTR_CT_LABEL, sizeof(key->ct.label),
- &key->ct.label))
+ nla_put(skb, OVS_KEY_ATTR_CT_LABELS, sizeof(key->ct.labels),
+ &key->ct.labels))
return -EMSGSIZE;
return 0;
@@ -213,18 +215,15 @@ static int ovs_ct_set_mark(struct sk_buff *skb, struct sw_flow_key *key,
#endif
}
-static int ovs_ct_set_label(struct sk_buff *skb, struct sw_flow_key *key,
- const struct ovs_key_ct_label *label,
- const struct ovs_key_ct_label *mask)
+static int ovs_ct_set_labels(struct sk_buff *skb, struct sw_flow_key *key,
+ const struct ovs_key_ct_labels *labels,
+ const struct ovs_key_ct_labels *mask)
{
enum ip_conntrack_info ctinfo;
struct nf_conn_labels *cl;
struct nf_conn *ct;
int err;
- if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS))
- return -ENOTSUPP;
-
/* The connection could be invalid, in which case set_label is no-op.*/
ct = nf_ct_get(skb, &ctinfo);
if (!ct)
@@ -235,15 +234,15 @@ static int ovs_ct_set_label(struct sk_buff *skb, struct sw_flow_key *key,
nf_ct_labels_ext_add(ct);
cl = nf_ct_labels_find(ct);
}
- if (!cl || cl->words * sizeof(long) < OVS_CT_LABEL_LEN)
+ if (!cl || cl->words * sizeof(long) < OVS_CT_LABELS_LEN)
return -ENOSPC;
- err = nf_connlabels_replace(ct, (u32 *)label, (u32 *)mask,
- OVS_CT_LABEL_LEN / sizeof(u32));
+ err = nf_connlabels_replace(ct, (u32 *)labels, (u32 *)mask,
+ OVS_CT_LABELS_LEN / sizeof(u32));
if (err)
return err;
- ovs_ct_get_label(ct, &key->ct.label);
+ ovs_ct_get_labels(ct, &key->ct.labels);
return 0;
}
@@ -275,13 +274,15 @@ static int ovs_ct_helper(struct sk_buff *skb, u16 proto)
case NFPROTO_IPV6: {
u8 nexthdr = ipv6_hdr(skb)->nexthdr;
__be16 frag_off;
+ int ofs;
- protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
- &nexthdr, &frag_off);
- if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
+ ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
+ &frag_off);
+ if (ofs < 0 || (frag_off & htons(~0x7)) != 0) {
pr_debug("proto header not found\n");
return NF_ACCEPT;
}
+ protoff = ofs;
break;
}
default:
@@ -292,6 +293,9 @@ static int ovs_ct_helper(struct sk_buff *skb, u16 proto)
return helper->help(skb, protoff, ct, ctinfo);
}
+/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero
+ * value if 'skb' is freed.
+ */
static int handle_fragments(struct net *net, struct sw_flow_key *key,
u16 zone, struct sk_buff *skb)
{
@@ -307,8 +311,8 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key,
return err;
ovs_cb.mru = IPCB(skb)->frag_max_size;
- } else if (key->eth.type == htons(ETH_P_IPV6)) {
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
+ } else if (key->eth.type == htons(ETH_P_IPV6)) {
enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
struct sk_buff *reasm;
@@ -317,17 +321,25 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key,
if (!reasm)
return -EINPROGRESS;
- if (skb == reasm)
+ if (skb == reasm) {
+ kfree_skb(skb);
return -EINVAL;
+ }
+
+ /* Don't free 'skb' even though it is one of the original
+ * fragments, as we're going to morph it into the head.
+ */
+ skb_get(skb);
+ nf_ct_frag6_consume_orig(reasm);
key->ip.proto = ipv6_hdr(reasm)->nexthdr;
skb_morph(skb, reasm);
+ skb->next = reasm->next;
consume_skb(reasm);
ovs_cb.mru = IP6CB(skb)->frag_max_size;
-#else
- return -EPFNOSUPPORT;
#endif
} else {
+ kfree_skb(skb);
return -EPFNOSUPPORT;
}
@@ -375,7 +387,7 @@ static bool skb_nfct_cached(const struct net *net, const struct sk_buff *skb,
return true;
}
-static int __ovs_ct_lookup(struct net *net, const struct sw_flow_key *key,
+static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
const struct ovs_conntrack_info *info,
struct sk_buff *skb)
{
@@ -406,6 +418,8 @@ static int __ovs_ct_lookup(struct net *net, const struct sw_flow_key *key,
}
}
+ ovs_ct_update_key(skb, key, true);
+
return 0;
}
@@ -428,8 +442,6 @@ static int ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
err = __ovs_ct_lookup(net, key, info, skb);
if (err)
return err;
-
- ovs_ct_update_key(skb, key, true);
}
return 0;
@@ -458,22 +470,23 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key,
if (nf_conntrack_confirm(skb) != NF_ACCEPT)
return -EINVAL;
- ovs_ct_update_key(skb, key, true);
-
return 0;
}
-static bool label_nonzero(const struct ovs_key_ct_label *label)
+static bool labels_nonzero(const struct ovs_key_ct_labels *labels)
{
size_t i;
- for (i = 0; i < sizeof(*label); i++)
- if (label->ct_label[i])
+ for (i = 0; i < sizeof(*labels); i++)
+ if (labels->ct_labels[i])
return true;
return false;
}
+/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero
+ * value if 'skb' is freed.
+ */
int ovs_ct_execute(struct net *net, struct sk_buff *skb,
struct sw_flow_key *key,
const struct ovs_conntrack_info *info)
@@ -491,7 +504,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb,
return err;
}
- if (info->flags & OVS_CT_F_COMMIT)
+ if (info->commit)
err = ovs_ct_commit(net, key, info, skb);
else
err = ovs_ct_lookup(net, key, info, skb);
@@ -504,11 +517,13 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb,
if (err)
goto err;
}
- if (label_nonzero(&info->label.mask))
- err = ovs_ct_set_label(skb, key, &info->label.value,
- &info->label.mask);
+ if (labels_nonzero(&info->labels.mask))
+ err = ovs_ct_set_labels(skb, key, &info->labels.value,
+ &info->labels.mask);
err:
skb_push(skb, nh_ofs);
+ if (err)
+ kfree_skb(skb);
return err;
}
@@ -537,14 +552,13 @@ static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name,
}
static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = {
- [OVS_CT_ATTR_FLAGS] = { .minlen = sizeof(u32),
- .maxlen = sizeof(u32) },
+ [OVS_CT_ATTR_COMMIT] = { .minlen = 0, .maxlen = 0 },
[OVS_CT_ATTR_ZONE] = { .minlen = sizeof(u16),
.maxlen = sizeof(u16) },
[OVS_CT_ATTR_MARK] = { .minlen = sizeof(struct md_mark),
.maxlen = sizeof(struct md_mark) },
- [OVS_CT_ATTR_LABEL] = { .minlen = sizeof(struct md_label),
- .maxlen = sizeof(struct md_label) },
+ [OVS_CT_ATTR_LABELS] = { .minlen = sizeof(struct md_labels),
+ .maxlen = sizeof(struct md_labels) },
[OVS_CT_ATTR_HELPER] = { .minlen = 1,
.maxlen = NF_CT_HELPER_NAME_LEN }
};
@@ -574,8 +588,8 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
}
switch (type) {
- case OVS_CT_ATTR_FLAGS:
- info->flags = nla_get_u32(a);
+ case OVS_CT_ATTR_COMMIT:
+ info->commit = true;
break;
#ifdef CONFIG_NF_CONNTRACK_ZONES
case OVS_CT_ATTR_ZONE:
@@ -586,15 +600,23 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
case OVS_CT_ATTR_MARK: {
struct md_mark *mark = nla_data(a);
+ if (!mark->mask) {
+ OVS_NLERR(log, "ct_mark mask cannot be 0");
+ return -EINVAL;
+ }
info->mark = *mark;
break;
}
#endif
#ifdef CONFIG_NF_CONNTRACK_LABELS
- case OVS_CT_ATTR_LABEL: {
- struct md_label *label = nla_data(a);
+ case OVS_CT_ATTR_LABELS: {
+ struct md_labels *labels = nla_data(a);
- info->label = *label;
+ if (!labels_nonzero(&labels->mask)) {
+ OVS_NLERR(log, "ct_labels mask cannot be 0");
+ return -EINVAL;
+ }
+ info->labels = *labels;
break;
}
#endif
@@ -631,7 +653,7 @@ bool ovs_ct_verify(struct net *net, enum ovs_key_attr attr)
attr == OVS_KEY_ATTR_CT_MARK)
return true;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
- attr == OVS_KEY_ATTR_CT_LABEL) {
+ attr == OVS_KEY_ATTR_CT_LABELS) {
struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
return ovs_net->xt_label;
@@ -699,18 +721,19 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info,
if (!start)
return -EMSGSIZE;
- if (nla_put_u32(skb, OVS_CT_ATTR_FLAGS, ct_info->flags))
+ if (ct_info->commit && nla_put_flag(skb, OVS_CT_ATTR_COMMIT))
return -EMSGSIZE;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
nla_put_u16(skb, OVS_CT_ATTR_ZONE, ct_info->zone.id))
return -EMSGSIZE;
- if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) &&
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && ct_info->mark.mask &&
nla_put(skb, OVS_CT_ATTR_MARK, sizeof(ct_info->mark),
&ct_info->mark))
return -EMSGSIZE;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
- nla_put(skb, OVS_CT_ATTR_LABEL, sizeof(ct_info->label),
- &ct_info->label))
+ labels_nonzero(&ct_info->labels.mask) &&
+ nla_put(skb, OVS_CT_ATTR_LABELS, sizeof(ct_info->labels),
+ &ct_info->labels))
return -EMSGSIZE;
if (ct_info->helper) {
if (nla_put_string(skb, OVS_CT_ATTR_HELPER,
@@ -735,7 +758,7 @@ void ovs_ct_free_action(const struct nlattr *a)
void ovs_ct_init(struct net *net)
{
- unsigned int n_bits = sizeof(struct ovs_key_ct_label) * BITS_PER_BYTE;
+ unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE;
struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
if (nf_connlabels_get(net, n_bits)) {
diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h
index 43f5dd7a5577..a7544f405c16 100644
--- a/net/openvswitch/conntrack.h
+++ b/net/openvswitch/conntrack.h
@@ -34,6 +34,10 @@ int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *,
void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key);
int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb);
void ovs_ct_free_action(const struct nlattr *a);
+
+#define CT_SUPPORTED_MASK (OVS_CS_F_NEW | OVS_CS_F_ESTABLISHED | \
+ OVS_CS_F_RELATED | OVS_CS_F_REPLY_DIR | \
+ OVS_CS_F_INVALID | OVS_CS_F_TRACKED)
#else
#include <linux/errno.h>
@@ -63,6 +67,7 @@ static inline int ovs_ct_execute(struct net *net, struct sk_buff *skb,
struct sw_flow_key *key,
const struct ovs_conntrack_info *info)
{
+ kfree_skb(skb);
return -ENOTSUPP;
}
@@ -72,7 +77,7 @@ static inline void ovs_ct_fill_key(const struct sk_buff *skb,
key->ct.state = 0;
key->ct.zone = 0;
key->ct.mark = 0;
- memset(&key->ct.label, 0, sizeof(key->ct.label));
+ memset(&key->ct.labels, 0, sizeof(key->ct.labels));
}
static inline int ovs_ct_put_key(const struct sw_flow_key *key,
@@ -82,5 +87,7 @@ static inline int ovs_ct_put_key(const struct sw_flow_key *key,
}
static inline void ovs_ct_free_action(const struct nlattr *a) { }
+
+#define CT_SUPPORTED_MASK 0
#endif /* CONFIG_NF_CONNTRACK */
#endif /* ovs_conntrack.h */
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 6fbd2decb19e..c5d08ee37730 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -490,9 +490,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
if (upcall_info->egress_tun_info) {
nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_EGRESS_TUN_KEY);
- err = ovs_nla_put_egress_tunnel_key(user_skb,
- upcall_info->egress_tun_info,
- upcall_info->egress_tun_opts);
+ err = ovs_nla_put_tunnel_info(user_skb,
+ upcall_info->egress_tun_info);
BUG_ON(err);
nla_nest_end(user_skb, nla);
}
@@ -952,7 +951,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
if (error)
goto err_kfree_flow;
- ovs_flow_mask_key(&new_flow->key, &key, &mask);
+ ovs_flow_mask_key(&new_flow->key, &key, true, &mask);
/* Extract flow identifier. */
error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID],
@@ -1080,7 +1079,7 @@ static struct sw_flow_actions *get_flow_actions(struct net *net,
struct sw_flow_key masked_key;
int error;
- ovs_flow_mask_key(&masked_key, key, mask);
+ ovs_flow_mask_key(&masked_key, key, true, mask);
error = ovs_nla_copy_actions(net, a, &masked_key, &acts, log);
if (error) {
OVS_NLERR(log,
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index f88038a99f44..67bdecd9fdc1 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -117,7 +117,6 @@ struct ovs_skb_cb {
*/
struct dp_upcall_info {
struct ip_tunnel_info *egress_tun_info;
- const void *egress_tun_opts;
const struct nlattr *userdata;
const struct nlattr *actions;
int actions_len;
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index fe527d2dd4b7..8cfa15a08668 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -116,7 +116,7 @@ struct sw_flow_key {
u16 zone;
u32 mark;
u8 state;
- struct ovs_key_ct_label label;
+ struct ovs_key_ct_labels labels;
} ct;
} __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index c92d6a262bc5..38536c137c54 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -57,6 +57,7 @@ struct ovs_len_tbl {
};
#define OVS_ATTR_NESTED -1
+#define OVS_ATTR_VARIABLE -2
static void update_range(struct sw_flow_match *match,
size_t offset, size_t size, bool is_mask)
@@ -290,10 +291,10 @@ size_t ovs_key_attr_size(void)
+ nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */
+ nla_total_size(4) /* OVS_KEY_ATTR_DP_HASH */
+ nla_total_size(4) /* OVS_KEY_ATTR_RECIRC_ID */
- + nla_total_size(1) /* OVS_KEY_ATTR_CT_STATE */
+ + nla_total_size(4) /* OVS_KEY_ATTR_CT_STATE */
+ nla_total_size(2) /* OVS_KEY_ATTR_CT_ZONE */
+ nla_total_size(4) /* OVS_KEY_ATTR_CT_MARK */
- + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABEL */
+ + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABELS */
+ nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */
+ nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */
+ nla_total_size(4) /* OVS_KEY_ATTR_VLAN */
@@ -304,6 +305,10 @@ size_t ovs_key_attr_size(void)
+ nla_total_size(28); /* OVS_KEY_ATTR_ND */
}
+static const struct ovs_len_tbl ovs_vxlan_ext_key_lens[OVS_VXLAN_EXT_MAX + 1] = {
+ [OVS_VXLAN_EXT_GBP] = { .len = sizeof(u32) },
+};
+
static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] = {
[OVS_TUNNEL_KEY_ATTR_ID] = { .len = sizeof(u64) },
[OVS_TUNNEL_KEY_ATTR_IPV4_SRC] = { .len = sizeof(u32) },
@@ -315,8 +320,9 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1]
[OVS_TUNNEL_KEY_ATTR_TP_SRC] = { .len = sizeof(u16) },
[OVS_TUNNEL_KEY_ATTR_TP_DST] = { .len = sizeof(u16) },
[OVS_TUNNEL_KEY_ATTR_OAM] = { .len = 0 },
- [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = { .len = OVS_ATTR_NESTED },
- [OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS] = { .len = OVS_ATTR_NESTED },
+ [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = { .len = OVS_ATTR_VARIABLE },
+ [OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS] = { .len = OVS_ATTR_NESTED,
+ .next = ovs_vxlan_ext_key_lens },
};
/* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */
@@ -343,12 +349,19 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
[OVS_KEY_ATTR_TUNNEL] = { .len = OVS_ATTR_NESTED,
.next = ovs_tunnel_key_lens, },
[OVS_KEY_ATTR_MPLS] = { .len = sizeof(struct ovs_key_mpls) },
- [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u8) },
+ [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u32) },
[OVS_KEY_ATTR_CT_ZONE] = { .len = sizeof(u16) },
[OVS_KEY_ATTR_CT_MARK] = { .len = sizeof(u32) },
- [OVS_KEY_ATTR_CT_LABEL] = { .len = sizeof(struct ovs_key_ct_label) },
+ [OVS_KEY_ATTR_CT_LABELS] = { .len = sizeof(struct ovs_key_ct_labels) },
};
+static bool check_attr_len(unsigned int attr_len, unsigned int expected_len)
+{
+ return expected_len == attr_len ||
+ expected_len == OVS_ATTR_NESTED ||
+ expected_len == OVS_ATTR_VARIABLE;
+}
+
static bool is_all_zero(const u8 *fp, size_t size)
{
int i;
@@ -388,7 +401,7 @@ static int __parse_flow_nlattrs(const struct nlattr *attr,
}
expected_len = ovs_key_lens[type].len;
- if (nla_len(nla) != expected_len && expected_len != OVS_ATTR_NESTED) {
+ if (!check_attr_len(nla_len(nla), expected_len)) {
OVS_NLERR(log, "Key %d has unexpected len %d expected %d",
type, nla_len(nla), expected_len);
return -EINVAL;
@@ -473,29 +486,50 @@ static int genev_tun_opt_from_nlattr(const struct nlattr *a,
return 0;
}
-static const struct nla_policy vxlan_opt_policy[OVS_VXLAN_EXT_MAX + 1] = {
- [OVS_VXLAN_EXT_GBP] = { .type = NLA_U32 },
-};
-
-static int vxlan_tun_opt_from_nlattr(const struct nlattr *a,
+static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr,
struct sw_flow_match *match, bool is_mask,
bool log)
{
- struct nlattr *tb[OVS_VXLAN_EXT_MAX+1];
+ struct nlattr *a;
+ int rem;
unsigned long opt_key_offset;
struct vxlan_metadata opts;
- int err;
BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts));
- err = nla_parse_nested(tb, OVS_VXLAN_EXT_MAX, a, vxlan_opt_policy);
- if (err < 0)
- return err;
-
memset(&opts, 0, sizeof(opts));
+ nla_for_each_nested(a, attr, rem) {
+ int type = nla_type(a);
- if (tb[OVS_VXLAN_EXT_GBP])
- opts.gbp = nla_get_u32(tb[OVS_VXLAN_EXT_GBP]);
+ if (type > OVS_VXLAN_EXT_MAX) {
+ OVS_NLERR(log, "VXLAN extension %d out of range max %d",
+ type, OVS_VXLAN_EXT_MAX);
+ return -EINVAL;
+ }
+
+ if (!check_attr_len(nla_len(a),
+ ovs_vxlan_ext_key_lens[type].len)) {
+ OVS_NLERR(log, "VXLAN extension %d has unexpected len %d expected %d",
+ type, nla_len(a),
+ ovs_vxlan_ext_key_lens[type].len);
+ return -EINVAL;
+ }
+
+ switch (type) {
+ case OVS_VXLAN_EXT_GBP:
+ opts.gbp = nla_get_u32(a);
+ break;
+ default:
+ OVS_NLERR(log, "Unknown VXLAN extension attribute %d",
+ type);
+ return -EINVAL;
+ }
+ }
+ if (rem) {
+ OVS_NLERR(log, "VXLAN extension message has %d unknown bytes.",
+ rem);
+ return -EINVAL;
+ }
if (!is_mask)
SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), false);
@@ -528,8 +562,8 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
return -EINVAL;
}
- if (ovs_tunnel_key_lens[type].len != nla_len(a) &&
- ovs_tunnel_key_lens[type].len != OVS_ATTR_NESTED) {
+ if (!check_attr_len(nla_len(a),
+ ovs_tunnel_key_lens[type].len)) {
OVS_NLERR(log, "Tunnel attr %d has unexpected len %d expected %d",
type, nla_len(a), ovs_tunnel_key_lens[type].len);
return -EINVAL;
@@ -683,7 +717,7 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
if ((output->tun_flags & TUNNEL_OAM) &&
nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM))
return -EMSGSIZE;
- if (tun_opts) {
+ if (swkey_tun_opts_len) {
if (output->tun_flags & TUNNEL_GENEVE_OPT &&
nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS,
swkey_tun_opts_len, tun_opts))
@@ -715,13 +749,12 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb,
return 0;
}
-int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb,
- const struct ip_tunnel_info *egress_tun_info,
- const void *egress_tun_opts)
+int ovs_nla_put_tunnel_info(struct sk_buff *skb,
+ struct ip_tunnel_info *tun_info)
{
- return __ipv4_tun_to_nlattr(skb, &egress_tun_info->key,
- egress_tun_opts,
- egress_tun_info->options_len);
+ return __ipv4_tun_to_nlattr(skb, &tun_info->key,
+ ip_tunnel_info_opts(tun_info),
+ tun_info->options_len);
}
static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match,
@@ -780,7 +813,13 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match,
if (*attrs & (1 << OVS_KEY_ATTR_CT_STATE) &&
ovs_ct_verify(net, OVS_KEY_ATTR_CT_STATE)) {
- u8 ct_state = nla_get_u8(a[OVS_KEY_ATTR_CT_STATE]);
+ u32 ct_state = nla_get_u32(a[OVS_KEY_ATTR_CT_STATE]);
+
+ if (ct_state & ~CT_SUPPORTED_MASK) {
+ OVS_NLERR(log, "ct_state flags %08x unsupported",
+ ct_state);
+ return -EINVAL;
+ }
SW_FLOW_KEY_PUT(match, ct.state, ct_state, is_mask);
*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_STATE);
@@ -799,14 +838,14 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match,
SW_FLOW_KEY_PUT(match, ct.mark, mark, is_mask);
*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_MARK);
}
- if (*attrs & (1 << OVS_KEY_ATTR_CT_LABEL) &&
- ovs_ct_verify(net, OVS_KEY_ATTR_CT_LABEL)) {
- const struct ovs_key_ct_label *cl;
+ if (*attrs & (1 << OVS_KEY_ATTR_CT_LABELS) &&
+ ovs_ct_verify(net, OVS_KEY_ATTR_CT_LABELS)) {
+ const struct ovs_key_ct_labels *cl;
- cl = nla_data(a[OVS_KEY_ATTR_CT_LABEL]);
- SW_FLOW_KEY_MEMCPY(match, ct.label, cl->ct_label,
+ cl = nla_data(a[OVS_KEY_ATTR_CT_LABELS]);
+ SW_FLOW_KEY_MEMCPY(match, ct.labels, cl->ct_labels,
sizeof(*cl), is_mask);
- *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABEL);
+ *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABELS);
}
return 0;
}
@@ -1052,10 +1091,16 @@ static void nlattr_set(struct nlattr *attr, u8 val,
/* The nlattr stream should already have been validated */
nla_for_each_nested(nla, attr, rem) {
- if (tbl && tbl[nla_type(nla)].len == OVS_ATTR_NESTED)
- nlattr_set(nla, val, tbl[nla_type(nla)].next);
- else
+ if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) {
+ if (tbl[nla_type(nla)].next)
+ tbl = tbl[nla_type(nla)].next;
+ nlattr_set(nla, val, tbl);
+ } else {
memset(nla_data(nla), val, nla_len(nla));
+ }
+
+ if (nla_type(nla) == OVS_KEY_ATTR_CT_STATE)
+ *(u32 *)nla_data(nla) &= CT_SUPPORTED_MASK;
}
}
@@ -1922,8 +1967,7 @@ static int validate_set(const struct nlattr *a,
key_len /= 2;
if (key_type > OVS_KEY_ATTR_MAX ||
- (ovs_key_lens[key_type].len != key_len &&
- ovs_key_lens[key_type].len != OVS_ATTR_NESTED))
+ !check_attr_len(key_len, ovs_key_lens[key_type].len))
return -EINVAL;
if (masked && !validate_masked(nla_data(ovs_key), key_len))
@@ -1937,7 +1981,7 @@ static int validate_set(const struct nlattr *a,
case OVS_KEY_ATTR_PRIORITY:
case OVS_KEY_ATTR_SKB_MARK:
case OVS_KEY_ATTR_CT_MARK:
- case OVS_KEY_ATTR_CT_LABEL:
+ case OVS_KEY_ATTR_CT_LABELS:
case OVS_KEY_ATTR_ETHERNET:
break;
@@ -2338,10 +2382,7 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
if (!start)
return -EMSGSIZE;
- err = ipv4_tun_to_nlattr(skb, &tun_info->key,
- tun_info->options_len ?
- ip_tunnel_info_opts(tun_info) : NULL,
- tun_info->options_len);
+ err = ovs_nla_put_tunnel_info(skb, tun_info);
if (err)
return err;
nla_nest_end(skb, start);
diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h
index 6ca3f0baf449..47dd142eca1c 100644
--- a/net/openvswitch/flow_netlink.h
+++ b/net/openvswitch/flow_netlink.h
@@ -55,9 +55,9 @@ int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb);
int ovs_nla_get_match(struct net *, struct sw_flow_match *,
const struct nlattr *key, const struct nlattr *mask,
bool log);
-int ovs_nla_put_egress_tunnel_key(struct sk_buff *,
- const struct ip_tunnel_info *,
- const void *egress_tun_opts);
+
+int ovs_nla_put_tunnel_info(struct sk_buff *skb,
+ struct ip_tunnel_info *tun_info);
bool ovs_nla_get_ufid(struct sw_flow_id *, const struct nlattr *, bool log);
int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid,
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index d22d8e948d0f..c7f74aab34b9 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -57,20 +57,21 @@ 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)
+ bool full, const struct sw_flow_mask *mask)
{
- 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 start = full ? 0 : mask->range.start;
+ int len = full ? sizeof *dst : range_n_bytes(&mask->range);
+ const long *m = (const long *)((const u8 *)&mask->key + start);
+ const long *s = (const long *)((const u8 *)src + start);
+ long *d = (long *)((u8 *)dst + start);
int i;
- /* The memory outside of the 'mask->range' are not set since
- * further operations on 'dst' only uses contents within
- * 'mask->range'.
+ /* If 'full' is true then all of 'dst' is fully initialized. Otherwise,
+ * if 'full' is false the memory outside of the 'mask->range' is left
+ * uninitialized. This can be used as an optimization when further
+ * operations on 'dst' only use contents within 'mask->range'.
*/
- for (i = 0; i < range_n_bytes(&mask->range); i += sizeof(long))
+ for (i = 0; i < len; i += sizeof(long))
*d++ = *s++ & *m++;
}
@@ -92,7 +93,8 @@ struct sw_flow *ovs_flow_alloc(void)
/* Initialize the default stat node. */
stats = kmem_cache_alloc_node(flow_stats_cache,
- GFP_KERNEL | __GFP_ZERO, 0);
+ GFP_KERNEL | __GFP_ZERO,
+ node_online(0) ? 0 : NUMA_NO_NODE);
if (!stats)
goto err;
@@ -475,7 +477,7 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
u32 hash;
struct sw_flow_key masked_key;
- ovs_flow_mask_key(&masked_key, unmasked, mask);
+ ovs_flow_mask_key(&masked_key, unmasked, false, mask);
hash = flow_hash(&masked_key, &mask->range);
head = find_bucket(ti, hash);
hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) {
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index 616eda10d955..2dd9900f533d 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -86,5 +86,5 @@ struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *,
bool ovs_flow_cmp(const struct sw_flow *, const struct sw_flow_match *);
void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
- const struct sw_flow_mask *mask);
+ bool full, const struct sw_flow_mask *mask);
#endif /* flow_table.h */
diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c
index 2735e9c4a3b8..5f8aaaaa0785 100644
--- a/net/openvswitch/vport-geneve.c
+++ b/net/openvswitch/vport-geneve.c
@@ -52,18 +52,6 @@ static int geneve_get_options(const struct vport *vport,
return 0;
}
-static int geneve_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
- struct dp_upcall_info *upcall)
-{
- struct geneve_port *geneve_port = geneve_vport(vport);
- struct net *net = ovs_dp_get_net(vport->dp);
- __be16 dport = htons(geneve_port->port_no);
- __be16 sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true);
-
- return ovs_tunnel_get_egress_info(upcall, ovs_dp_get_net(vport->dp),
- skb, IPPROTO_UDP, sport, dport);
-}
-
static struct vport *geneve_tnl_create(const struct vport_parms *parms)
{
struct net *net = ovs_dp_get_net(parms->dp);
@@ -130,7 +118,6 @@ static struct vport_ops ovs_geneve_vport_ops = {
.get_options = geneve_get_options,
.send = ovs_netdev_send,
.owner = THIS_MODULE,
- .get_egress_tun_info = geneve_get_egress_tun_info,
};
static int __init ovs_geneve_tnl_init(void)
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index 4d24481669c9..64225bf5eb40 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -84,18 +84,10 @@ static struct vport *gre_create(const struct vport_parms *parms)
return ovs_netdev_link(vport, parms->name);
}
-static int gre_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
- struct dp_upcall_info *upcall)
-{
- return ovs_tunnel_get_egress_info(upcall, ovs_dp_get_net(vport->dp),
- skb, IPPROTO_GRE, 0, 0);
-}
-
static struct vport_ops ovs_gre_vport_ops = {
.type = OVS_VPORT_TYPE_GRE,
.create = gre_create,
.send = ovs_netdev_send,
- .get_egress_tun_info = gre_get_egress_tun_info,
.destroy = ovs_netdev_tunnel_destroy,
.owner = THIS_MODULE,
};
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 388b8a6bf112..b3934126daa8 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -106,12 +106,45 @@ static void internal_dev_destructor(struct net_device *dev)
free_netdev(dev);
}
+static struct rtnl_link_stats64 *
+internal_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
+{
+ int i;
+
+ memset(stats, 0, sizeof(*stats));
+ stats->rx_errors = dev->stats.rx_errors;
+ stats->tx_errors = dev->stats.tx_errors;
+ stats->tx_dropped = dev->stats.tx_dropped;
+ stats->rx_dropped = dev->stats.rx_dropped;
+
+ for_each_possible_cpu(i) {
+ const struct pcpu_sw_netstats *percpu_stats;
+ struct pcpu_sw_netstats local_stats;
+ unsigned int start;
+
+ percpu_stats = per_cpu_ptr(dev->tstats, i);
+
+ do {
+ start = u64_stats_fetch_begin_irq(&percpu_stats->syncp);
+ local_stats = *percpu_stats;
+ } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start));
+
+ stats->rx_bytes += local_stats.rx_bytes;
+ stats->rx_packets += local_stats.rx_packets;
+ stats->tx_bytes += local_stats.tx_bytes;
+ stats->tx_packets += local_stats.tx_packets;
+ }
+
+ return stats;
+}
+
static const struct net_device_ops internal_dev_netdev_ops = {
.ndo_open = internal_dev_open,
.ndo_stop = internal_dev_stop,
.ndo_start_xmit = internal_dev_xmit,
.ndo_set_mac_address = eth_mac_addr,
.ndo_change_mtu = internal_dev_change_mtu,
+ .ndo_get_stats64 = internal_get_stats,
};
static struct rtnl_link_ops internal_dev_link_ops __read_mostly = {
@@ -161,6 +194,11 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
err = -ENOMEM;
goto error_free_vport;
}
+ vport->dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+ if (!vport->dev->tstats) {
+ err = -ENOMEM;
+ goto error_free_netdev;
+ }
dev_net_set(vport->dev, ovs_dp_get_net(vport->dp));
internal_dev = internal_dev_priv(vport->dev);
@@ -173,7 +211,7 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
rtnl_lock();
err = register_netdevice(vport->dev);
if (err)
- goto error_free_netdev;
+ goto error_unlock;
dev_set_promiscuity(vport->dev, 1);
rtnl_unlock();
@@ -181,8 +219,10 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
return vport;
-error_free_netdev:
+error_unlock:
rtnl_unlock();
+ free_percpu(vport->dev->tstats);
+error_free_netdev:
free_netdev(vport->dev);
error_free_vport:
ovs_vport_free(vport);
@@ -198,7 +238,7 @@ static void internal_dev_destroy(struct vport *vport)
/* unregister_netdevice() waits for an RCU grace period. */
unregister_netdevice(vport->dev);
-
+ free_percpu(vport->dev->tstats);
rtnl_unlock();
}
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index c11413d5075f..e1c9c0888037 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -146,31 +146,12 @@ static struct vport *vxlan_create(const struct vport_parms *parms)
return ovs_netdev_link(vport, parms->name);
}
-static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
- struct dp_upcall_info *upcall)
-{
- struct vxlan_dev *vxlan = netdev_priv(vport->dev);
- struct net *net = ovs_dp_get_net(vport->dp);
- __be16 dst_port = vxlan_dev_dst_port(vxlan);
- __be16 src_port;
- int port_min;
- int port_max;
-
- inet_get_local_port_range(net, &port_min, &port_max);
- src_port = udp_flow_src_port(net, skb, 0, 0, true);
-
- return ovs_tunnel_get_egress_info(upcall, net,
- skb, IPPROTO_UDP,
- src_port, dst_port);
-}
-
static struct vport_ops ovs_vxlan_netdev_vport_ops = {
.type = OVS_VPORT_TYPE_VXLAN,
.create = vxlan_create,
.destroy = ovs_netdev_tunnel_destroy,
.get_options = vxlan_get_options,
.send = ovs_netdev_send,
- .get_egress_tun_info = vxlan_get_egress_tun_info,
};
static int __init ovs_vxlan_tnl_init(void)
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index dc81dc619aa2..320c765ce44a 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -280,35 +280,19 @@ void ovs_vport_del(struct vport *vport)
*/
void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats)
{
- struct net_device *dev = vport->dev;
- int i;
-
- memset(stats, 0, sizeof(*stats));
- stats->rx_errors = dev->stats.rx_errors;
- stats->tx_errors = dev->stats.tx_errors;
- stats->tx_dropped = dev->stats.tx_dropped;
- stats->rx_dropped = dev->stats.rx_dropped;
-
- stats->rx_dropped += atomic_long_read(&dev->rx_dropped);
- stats->tx_dropped += atomic_long_read(&dev->tx_dropped);
-
- for_each_possible_cpu(i) {
- const struct pcpu_sw_netstats *percpu_stats;
- struct pcpu_sw_netstats local_stats;
- unsigned int start;
-
- percpu_stats = per_cpu_ptr(dev->tstats, i);
-
- do {
- start = u64_stats_fetch_begin_irq(&percpu_stats->syncp);
- local_stats = *percpu_stats;
- } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start));
-
- stats->rx_bytes += local_stats.rx_bytes;
- stats->rx_packets += local_stats.rx_packets;
- stats->tx_bytes += local_stats.tx_bytes;
- stats->tx_packets += local_stats.tx_packets;
- }
+ const struct rtnl_link_stats64 *dev_stats;
+ struct rtnl_link_stats64 temp;
+
+ dev_stats = dev_get_stats(vport->dev, &temp);
+ stats->rx_errors = dev_stats->rx_errors;
+ stats->tx_errors = dev_stats->tx_errors;
+ stats->tx_dropped = dev_stats->tx_dropped;
+ stats->rx_dropped = dev_stats->rx_dropped;
+
+ stats->rx_bytes = dev_stats->rx_bytes;
+ stats->rx_packets = dev_stats->rx_packets;
+ stats->tx_bytes = dev_stats->tx_bytes;
+ stats->tx_packets = dev_stats->tx_packets;
}
/**
@@ -460,6 +444,15 @@ int ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
OVS_CB(skb)->input_vport = vport;
OVS_CB(skb)->mru = 0;
+ if (unlikely(dev_net(skb->dev) != ovs_dp_get_net(vport->dp))) {
+ u32 mark;
+
+ mark = skb->mark;
+ skb_scrub_packet(skb, true);
+ skb->mark = mark;
+ tun_info = NULL;
+ }
+
/* Extract flow from 'skb' into 'key'. */
error = ovs_flow_key_extract(tun_info, skb, &key);
if (unlikely(error)) {
@@ -486,61 +479,3 @@ void ovs_vport_deferred_free(struct vport *vport)
call_rcu(&vport->rcu, free_vport_rcu);
}
EXPORT_SYMBOL_GPL(ovs_vport_deferred_free);
-
-int ovs_tunnel_get_egress_info(struct dp_upcall_info *upcall,
- struct net *net,
- struct sk_buff *skb,
- u8 ipproto,
- __be16 tp_src,
- __be16 tp_dst)
-{
- struct ip_tunnel_info *egress_tun_info = upcall->egress_tun_info;
- const struct ip_tunnel_info *tun_info = skb_tunnel_info(skb);
- const struct ip_tunnel_key *tun_key;
- u32 skb_mark = skb->mark;
- struct rtable *rt;
- struct flowi4 fl;
-
- if (unlikely(!tun_info))
- return -EINVAL;
- if (ip_tunnel_info_af(tun_info) != AF_INET)
- return -EINVAL;
-
- tun_key = &tun_info->key;
-
- /* Route lookup to get srouce IP address.
- * The process may need to be changed if the corresponding process
- * in vports ops changed.
- */
- rt = ovs_tunnel_route_lookup(net, tun_key, skb_mark, &fl, ipproto);
- if (IS_ERR(rt))
- return PTR_ERR(rt);
-
- ip_rt_put(rt);
-
- /* Generate egress_tun_info based on tun_info,
- * saddr, tp_src and tp_dst
- */
- ip_tunnel_key_init(&egress_tun_info->key,
- fl.saddr, tun_key->u.ipv4.dst,
- tun_key->tos,
- tun_key->ttl,
- tp_src, tp_dst,
- tun_key->tun_id,
- tun_key->tun_flags);
- egress_tun_info->options_len = tun_info->options_len;
- egress_tun_info->mode = tun_info->mode;
- upcall->egress_tun_opts = ip_tunnel_info_opts(egress_tun_info);
- return 0;
-}
-EXPORT_SYMBOL_GPL(ovs_tunnel_get_egress_info);
-
-int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
- struct dp_upcall_info *upcall)
-{
- /* get_egress_tun_info() is only implemented on tunnel ports. */
- if (unlikely(!vport->ops->get_egress_tun_info))
- return -EINVAL;
-
- return vport->ops->get_egress_tun_info(vport, skb, upcall);
-}
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index a413f3ae6a7b..d341ad6f3afe 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -27,7 +27,6 @@
#include <linux/skbuff.h>
#include <linux/spinlock.h>
#include <linux/u64_stats_sync.h>
-#include <net/route.h>
#include "datapath.h"
@@ -53,16 +52,6 @@ int ovs_vport_set_upcall_portids(struct vport *, const struct nlattr *pids);
int ovs_vport_get_upcall_portids(const struct vport *, struct sk_buff *);
u32 ovs_vport_find_upcall_portid(const struct vport *, struct sk_buff *);
-int ovs_tunnel_get_egress_info(struct dp_upcall_info *upcall,
- struct net *net,
- struct sk_buff *,
- u8 ipproto,
- __be16 tp_src,
- __be16 tp_dst);
-
-int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
- struct dp_upcall_info *upcall);
-
/**
* struct vport_portids - array of netlink portids of a vport.
* must be protected by rcu.
@@ -140,8 +129,6 @@ struct vport_parms {
* have any configuration.
* @send: Send a packet on the device.
* zero for dropped packets or negative for error.
- * @get_egress_tun_info: Get the egress tunnel 5-tuple and other info for
- * a packet.
*/
struct vport_ops {
enum ovs_vport_type type;
@@ -154,9 +141,6 @@ struct vport_ops {
int (*get_options)(const struct vport *, struct sk_buff *);
void (*send)(struct vport *, struct sk_buff *);
- int (*get_egress_tun_info)(struct vport *, struct sk_buff *,
- struct dp_upcall_info *upcall);
-
struct module *owner;
struct list_head list;
};
@@ -215,25 +199,6 @@ static inline const char *ovs_vport_name(struct vport *vport)
int ovs_vport_ops_register(struct vport_ops *ops);
void ovs_vport_ops_unregister(struct vport_ops *ops);
-static inline struct rtable *ovs_tunnel_route_lookup(struct net *net,
- const struct ip_tunnel_key *key,
- u32 mark,
- struct flowi4 *fl,
- u8 protocol)
-{
- struct rtable *rt;
-
- memset(fl, 0, sizeof(*fl));
- fl->daddr = key->u.ipv4.dst;
- fl->saddr = key->u.ipv4.src;
- fl->flowi4_tos = RT_TOS(key->tos);
- fl->flowi4_mark = mark;
- fl->flowi4_proto = protocol;
-
- rt = ip_route_output_key(net, fl);
- return rt;
-}
-
static inline void ovs_vport_send(struct vport *vport, struct sk_buff *skb)
{
vport->ops->send(vport, skb);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.