[ovs-dev] [patch net-next RFC 10/12] openvswitch: add support for datapath hardware offload
Jiri Pirko
jiri at resnulli.us
Thu Aug 21 16:19:03 UTC 2014
Benefit from the possibility to work with flows in switch devices and
use the swdev api to offload flow datapath.
Signed-off-by: Jiri Pirko <jiri at resnulli.us>
---
include/linux/sw_flow.h | 14 +++
net/openvswitch/Makefile | 3 +-
net/openvswitch/datapath.c | 33 ++++++
net/openvswitch/datapath.h | 3 +
net/openvswitch/flow_table.c | 1 +
net/openvswitch/hw_offload.c | 235 +++++++++++++++++++++++++++++++++++++++++
net/openvswitch/hw_offload.h | 22 ++++
net/openvswitch/vport-netdev.c | 3 +
net/openvswitch/vport.h | 2 +
9 files changed, 315 insertions(+), 1 deletion(-)
create mode 100644 net/openvswitch/hw_offload.c
create mode 100644 net/openvswitch/hw_offload.h
diff --git a/include/linux/sw_flow.h b/include/linux/sw_flow.h
index b622fde..079d065 100644
--- a/include/linux/sw_flow.h
+++ b/include/linux/sw_flow.h
@@ -80,7 +80,21 @@ struct sw_flow_mask {
struct sw_flow_key key;
};
+enum sw_flow_action_type {
+ SW_FLOW_ACTION_TYPE_OUTPUT,
+ SW_FLOW_ACTION_TYPE_VLAN_PUSH,
+ SW_FLOW_ACTION_TYPE_VLAN_POP,
+};
+
struct sw_flow_action {
+ enum sw_flow_action_type type;
+ union {
+ struct net_device *output_dev;
+ struct {
+ __be16 vlan_proto;
+ u16 vlan_tci;
+ } vlan;
+ };
};
struct sw_flow_actions {
diff --git a/net/openvswitch/Makefile b/net/openvswitch/Makefile
index 3591cb5..5152437 100644
--- a/net/openvswitch/Makefile
+++ b/net/openvswitch/Makefile
@@ -13,7 +13,8 @@ openvswitch-y := \
flow_table.o \
vport.o \
vport-internal_dev.o \
- vport-netdev.o
+ vport-netdev.o \
+ hw_offload.o
ifneq ($(CONFIG_OPENVSWITCH_VXLAN),)
openvswitch-y += vport-vxlan.o
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 75bb07f..3e43e1d 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -57,6 +57,7 @@
#include "flow_netlink.h"
#include "vport-internal_dev.h"
#include "vport-netdev.h"
+#include "hw_offload.h"
int ovs_net_id __read_mostly;
@@ -864,6 +865,9 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
acts = NULL;
goto err_unlock_ovs;
}
+ error = ovs_hw_flow_insert(dp, new_flow);
+ if (error)
+ pr_warn("failed to insert flow into hw\n");
if (unlikely(reply)) {
error = ovs_flow_cmd_fill_info(new_flow,
@@ -896,10 +900,18 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
goto err_unlock_ovs;
}
}
+ error = ovs_hw_flow_remove(dp, flow);
+ if (error)
+ pr_warn("failed to remove flow from hw\n");
+
/* Update actions. */
old_acts = ovsl_dereference(flow->sf_acts);
rcu_assign_pointer(flow->sf_acts, acts);
+ error = ovs_hw_flow_insert(dp, flow);
+ if (error)
+ pr_warn("failed to insert flow into hw\n");
+
if (unlikely(reply)) {
error = ovs_flow_cmd_fill_info(flow,
ovs_header->dp_ifindex,
@@ -993,9 +1005,17 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
/* Update actions, if present. */
if (likely(acts)) {
+ error = ovs_hw_flow_remove(dp, flow);
+ if (error)
+ pr_warn("failed to remove flow from hw\n");
+
old_acts = ovsl_dereference(flow->sf_acts);
rcu_assign_pointer(flow->sf_acts, acts);
+ error = ovs_hw_flow_insert(dp, flow);
+ if (error)
+ pr_warn("failed to insert flow into hw\n");
+
if (unlikely(reply)) {
error = ovs_flow_cmd_fill_info(flow,
ovs_header->dp_ifindex,
@@ -1109,6 +1129,9 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
}
if (unlikely(!a[OVS_FLOW_ATTR_KEY])) {
+ err = ovs_hw_flow_flush(dp);
+ if (err)
+ pr_warn("failed to flush flows from hw\n");
err = ovs_flow_tbl_flush(&dp->table);
goto unlock;
}
@@ -1120,6 +1143,9 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
}
ovs_flow_tbl_remove(&dp->table, flow);
+ err = ovs_hw_flow_remove(dp, flow);
+ if (err)
+ pr_warn("failed to remove flow from hw\n");
ovs_unlock();
reply = ovs_flow_cmd_alloc_info((const struct ovs_flow_actions __force *) flow->sf_acts,
@@ -1368,6 +1394,8 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++)
INIT_HLIST_HEAD(&dp->ports[i]);
+ INIT_LIST_HEAD(&dp->swdev_rep_list);
+
/* Set up our datapath device. */
parms.name = nla_data(a[OVS_DP_ATTR_NAME]);
parms.type = OVS_VPORT_TYPE_INTERNAL;
@@ -1431,6 +1459,7 @@ err:
static void __dp_destroy(struct datapath *dp)
{
int i;
+ int err;
for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) {
struct vport *vport;
@@ -1448,6 +1477,10 @@ static void __dp_destroy(struct datapath *dp)
*/
ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL));
+ err = ovs_hw_flow_flush(dp);
+ if (err)
+ pr_warn("failed to flush flows from hw\n");
+
/* RCU destroy the flow table */
ovs_flow_tbl_destroy(&dp->table, true);
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 291f5a0..9dc11a6 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -90,6 +90,9 @@ struct datapath {
#endif
u32 user_features;
+
+ /* List of switchdev representative ports */
+ struct list_head swdev_rep_list;
};
/**
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index e7d9a41..c01e4cb 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -85,6 +85,7 @@ struct ovs_flow *ovs_flow_alloc(void)
flow->sf_acts = NULL;
flow->flow.mask = NULL;
+ flow->flow.actions = NULL;
flow->stats_last_writer = NUMA_NO_NODE;
/* Initialize the default stat node. */
diff --git a/net/openvswitch/hw_offload.c b/net/openvswitch/hw_offload.c
new file mode 100644
index 0000000..edb8a68
--- /dev/null
+++ b/net/openvswitch/hw_offload.c
@@ -0,0 +1,235 @@
+/*
+ * Copyright (c) 2014 Jiri Pirko <jiri at resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/sw_flow.h>
+#include <linux/switchdev.h>
+
+#include "datapath.h"
+#include "vport-netdev.h"
+
+static int sw_flow_action_create(struct datapath *dp,
+ struct sw_flow_actions **p_actions,
+ struct ovs_flow_actions *acts)
+{
+ const struct nlattr *attr = acts->actions;
+ int len = acts->actions_len;
+ const struct nlattr *a;
+ int rem;
+ struct sw_flow_actions *actions;
+ struct sw_flow_action *cur;
+ size_t count = 0;
+ int err;
+
+ for (a = attr, rem = len; rem > 0; a = nla_next(a, &rem))
+ count++;
+
+ actions = kzalloc(sizeof(struct sw_flow_actions) +
+ sizeof(struct sw_flow_action) * count,
+ GFP_KERNEL);
+ if (!actions)
+ return -ENOMEM;
+ actions->count = count;
+
+ cur = actions->actions;
+ for (a = attr, rem = len; rem > 0; a = nla_next(a, &rem)) {
+ switch (nla_type(a)) {
+ case OVS_ACTION_ATTR_OUTPUT:
+ {
+ struct vport *vport;
+
+ vport = ovs_vport_ovsl_rcu(dp, nla_get_u32(a));
+ cur->type = SW_FLOW_ACTION_TYPE_OUTPUT;
+ cur->output_dev = vport->ops->get_netdev(vport);
+ }
+ break;
+
+ case OVS_ACTION_ATTR_PUSH_VLAN:
+ {
+ const struct ovs_action_push_vlan *vlan;
+
+ vlan = nla_data(a);
+ cur->type = SW_FLOW_ACTION_TYPE_VLAN_PUSH;
+ cur->vlan.vlan_proto = vlan->vlan_tpid;
+ cur->vlan.vlan_tci = vlan->vlan_tci;
+ }
+ break;
+
+ case OVS_ACTION_ATTR_POP_VLAN:
+ cur->type = SW_FLOW_ACTION_TYPE_VLAN_POP;
+ break;
+
+ default:
+ err = -EOPNOTSUPP;
+ goto errout;
+ }
+ cur++;
+ }
+ *p_actions = actions;
+ return 0;
+
+errout:
+ kfree(actions);
+ return err;
+}
+
+int ovs_hw_flow_insert(struct datapath *dp, struct ovs_flow *flow)
+{
+ struct sw_flow_actions *actions;
+ struct vport *vport;
+ struct net_device *dev;
+ int err;
+
+ ASSERT_OVSL();
+ BUG_ON(flow->flow.actions);
+
+ err = sw_flow_action_create(dp, &actions, flow->sf_acts);
+ if (err)
+ return err;
+ flow->flow.actions = actions;
+
+ list_for_each_entry(vport, &dp->swdev_rep_list, swdev_rep_list) {
+ dev = vport->ops->get_netdev(vport);
+ BUG_ON(!dev);
+ err = swdev_flow_insert(dev, &flow->flow);
+ if (err == -ENODEV) /* out device is not in this switch */
+ continue;
+ if (err)
+ break;
+ }
+
+ if (err) {
+ kfree(actions);
+ flow->flow.actions = NULL;
+ }
+ return err;
+}
+
+int ovs_hw_flow_remove(struct datapath *dp, struct ovs_flow *flow)
+{
+ struct vport *vport;
+ struct net_device *dev;
+ int err = 0;
+
+ ASSERT_OVSL();
+ list_for_each_entry(vport, &dp->swdev_rep_list, swdev_rep_list) {
+ dev = vport->ops->get_netdev(vport);
+ BUG_ON(!dev);
+ err = swdev_flow_remove(dev, &flow->flow);
+ if (err == -ENODEV) /* out device is not in this switch */
+ continue;
+ if (err)
+ break;
+ }
+ kfree(flow->flow.actions);
+ flow->flow.actions = NULL;
+ return err;
+}
+
+int ovs_hw_flow_flush(struct datapath *dp)
+{
+ struct table_instance *ti;
+ int i;
+ int ver;
+ int err;
+
+ ti = ovsl_dereference(dp->table.ti);
+ ver = ti->node_ver;
+
+ for (i = 0; i < ti->n_buckets; i++) {
+ struct ovs_flow *flow;
+ struct hlist_head *head = flex_array_get(ti->buckets, i);
+
+ hlist_for_each_entry(flow, head, hash_node[ver]) {
+ err = ovs_hw_flow_remove(dp, flow);
+ if (err)
+ return err;
+ }
+ }
+ return 0;
+}
+
+static bool __is_vport_in_swdev_rep_list(struct datapath *dp,
+ struct vport *vport)
+{
+ struct vport *cur_vport;
+
+ list_for_each_entry(cur_vport, &dp->swdev_rep_list, swdev_rep_list) {
+ if (cur_vport == vport)
+ return true;
+ }
+ return false;
+}
+
+static struct vport *__find_vport_by_swdev_id(struct datapath *dp,
+ struct vport *vport)
+{
+ struct net_device *dev;
+ struct vport *cur_vport;
+ struct netdev_phys_item_id id;
+ struct netdev_phys_item_id cur_id;
+ int i;
+ int err;
+
+ err = swdev_get_id(vport->ops->get_netdev(vport), &id);
+ if (err)
+ return ERR_PTR(err);
+
+ for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) {
+ hlist_for_each_entry(cur_vport, &dp->ports[i], dp_hash_node) {
+ if (cur_vport->ops->type != OVS_VPORT_TYPE_NETDEV)
+ continue;
+ if (cur_vport == vport)
+ continue;
+ dev = cur_vport->ops->get_netdev(cur_vport);
+ if (!dev)
+ continue;
+ err = swdev_get_id(dev, &cur_id);
+ if (err)
+ continue;
+ if (netdev_phys_item_ids_match(&id, &cur_id))
+ return cur_vport;
+ }
+ }
+ return ERR_PTR(-ENOENT);
+}
+
+void ovs_hw_port_add(struct datapath *dp, struct vport *vport)
+{
+ struct vport *found_vport;
+
+ ASSERT_OVSL();
+ /* The representative list contains always one port per switch dev id */
+ found_vport = __find_vport_by_swdev_id(dp, vport);
+ if (IS_ERR(found_vport) && PTR_ERR(found_vport) == -ENOENT) {
+ list_add(&vport->swdev_rep_list, &dp->swdev_rep_list);
+ pr_debug("%s added to rep_list\n", vport->ops->get_name(vport));
+ }
+}
+
+void ovs_hw_port_del(struct datapath *dp, struct vport *vport)
+{
+ struct vport *found_vport;
+
+ ASSERT_OVSL();
+ if (!__is_vport_in_swdev_rep_list(dp, vport))
+ return;
+
+ list_del(&vport->swdev_rep_list);
+ pr_debug("%s deleted from rep_list\n", vport->ops->get_name(vport));
+ found_vport = __find_vport_by_swdev_id(dp, vport);
+ if (!IS_ERR(found_vport)) {
+ list_add(&found_vport->swdev_rep_list, &dp->swdev_rep_list);
+ pr_debug("%s added to rep_list instead\n",
+ found_vport->ops->get_name(found_vport));
+ }
+}
diff --git a/net/openvswitch/hw_offload.h b/net/openvswitch/hw_offload.h
new file mode 100644
index 0000000..83972d7
--- /dev/null
+++ b/net/openvswitch/hw_offload.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright (c) 2014 Jiri Pirko <jiri at resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef HW_OFFLOAD_H
+#define HW_OFFLOAD_H 1
+
+#include "datapath.h"
+#include "flow.h"
+
+int ovs_hw_flow_insert(struct datapath *dp, struct ovs_flow *flow);
+int ovs_hw_flow_remove(struct datapath *dp, struct ovs_flow *flow);
+int ovs_hw_flow_flush(struct datapath *dp);
+void ovs_hw_port_add(struct datapath *dp, struct vport *vport);
+void ovs_hw_port_del(struct datapath *dp, struct vport *vport);
+
+#endif
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index aaf3d14..c5953de 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -32,6 +32,7 @@
#include "datapath.h"
#include "vport-internal_dev.h"
#include "vport-netdev.h"
+#include "hw_offload.h"
struct netdev_vport {
struct rcu_head rcu;
@@ -136,6 +137,7 @@ static struct vport *netdev_create(const struct vport_parms *parms)
dev_set_promiscuity(netdev_vport->dev, 1);
netdev_vport->dev->priv_flags |= IFF_OVS_DATAPATH;
rtnl_unlock();
+ ovs_hw_port_add(vport->dp, vport);
return vport;
@@ -176,6 +178,7 @@ static void netdev_destroy(struct vport *vport)
{
struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
+ ovs_hw_port_del(vport->dp, vport);
rtnl_lock();
if (netdev_vport->dev->priv_flags & IFF_OVS_DATAPATH)
ovs_netdev_detach_dev(vport);
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index f434271..c28604a 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -110,6 +110,8 @@ struct vport {
spinlock_t stats_lock;
struct vport_err_stats err_stats;
+
+ struct list_head swdev_rep_list;
};
/**
--
1.9.3
More information about the dev
mailing list