![Nikolay Aleksandrov](/assets/img/avatar_default.png)
Before this patch the bridge used a fixed 256 element hash table which was fine for small use cases (in my tests it starts to degrade above 1000 entries), but it wasn't enough for medium or large scale deployments. Modern setups have thousands of participants in a single bridge, even only enabling vlans and adding a few thousand vlan entries will cause a few thousand fdbs to be automatically inserted per participating port. So we need to scale the fdb table considerably to cope with modern workloads, and this patch converts it to use a rhashtable for its operations thus improving the bridge scalability. Tests show the following results (10 runs each), at up to 1000 entries rhashtable is ~3% slower, at 2000 rhashtable is 30% faster, at 3000 it is 2 times faster and at 30000 it is 50 times faster. Obviously this happens because of the properties of the two constructs and is expected, rhashtable keeps pretty much a constant time even with 10000000 entries (tested), while the fixed hash table struggles considerably even above 10000. As a side effect this also reduces the net_bridge struct size from 3248 bytes to 1344 bytes. Also note that the key struct is 8 bytes. Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
135 lines
3.2 KiB
C
135 lines
3.2 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <linux/kernel.h>
|
|
#include <linux/list.h>
|
|
#include <linux/netdevice.h>
|
|
#include <linux/rtnetlink.h>
|
|
#include <linux/skbuff.h>
|
|
#include <net/switchdev.h>
|
|
|
|
#include "br_private.h"
|
|
|
|
static int br_switchdev_mark_get(struct net_bridge *br, struct net_device *dev)
|
|
{
|
|
struct net_bridge_port *p;
|
|
|
|
/* dev is yet to be added to the port list. */
|
|
list_for_each_entry(p, &br->port_list, list) {
|
|
if (switchdev_port_same_parent_id(dev, p->dev))
|
|
return p->offload_fwd_mark;
|
|
}
|
|
|
|
return ++br->offload_fwd_mark;
|
|
}
|
|
|
|
int nbp_switchdev_mark_set(struct net_bridge_port *p)
|
|
{
|
|
struct switchdev_attr attr = {
|
|
.orig_dev = p->dev,
|
|
.id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
|
|
};
|
|
int err;
|
|
|
|
ASSERT_RTNL();
|
|
|
|
err = switchdev_port_attr_get(p->dev, &attr);
|
|
if (err) {
|
|
if (err == -EOPNOTSUPP)
|
|
return 0;
|
|
return err;
|
|
}
|
|
|
|
p->offload_fwd_mark = br_switchdev_mark_get(p->br, p->dev);
|
|
|
|
return 0;
|
|
}
|
|
|
|
void nbp_switchdev_frame_mark(const struct net_bridge_port *p,
|
|
struct sk_buff *skb)
|
|
{
|
|
if (skb->offload_fwd_mark && !WARN_ON_ONCE(!p->offload_fwd_mark))
|
|
BR_INPUT_SKB_CB(skb)->offload_fwd_mark = p->offload_fwd_mark;
|
|
}
|
|
|
|
bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p,
|
|
const struct sk_buff *skb)
|
|
{
|
|
return !skb->offload_fwd_mark ||
|
|
BR_INPUT_SKB_CB(skb)->offload_fwd_mark != p->offload_fwd_mark;
|
|
}
|
|
|
|
/* Flags that can be offloaded to hardware */
|
|
#define BR_PORT_FLAGS_HW_OFFLOAD (BR_LEARNING | BR_FLOOD | \
|
|
BR_MCAST_FLOOD | BR_BCAST_FLOOD)
|
|
|
|
int br_switchdev_set_port_flag(struct net_bridge_port *p,
|
|
unsigned long flags,
|
|
unsigned long mask)
|
|
{
|
|
struct switchdev_attr attr = {
|
|
.orig_dev = p->dev,
|
|
.id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT,
|
|
};
|
|
int err;
|
|
|
|
if (mask & ~BR_PORT_FLAGS_HW_OFFLOAD)
|
|
return 0;
|
|
|
|
err = switchdev_port_attr_get(p->dev, &attr);
|
|
if (err == -EOPNOTSUPP)
|
|
return 0;
|
|
if (err)
|
|
return err;
|
|
|
|
/* Check if specific bridge flag attribute offload is supported */
|
|
if (!(attr.u.brport_flags_support & mask)) {
|
|
br_warn(p->br, "bridge flag offload is not supported %u(%s)\n",
|
|
(unsigned int)p->port_no, p->dev->name);
|
|
return -EOPNOTSUPP;
|
|
}
|
|
|
|
attr.id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS;
|
|
attr.flags = SWITCHDEV_F_DEFER;
|
|
attr.u.brport_flags = flags;
|
|
err = switchdev_port_attr_set(p->dev, &attr);
|
|
if (err) {
|
|
br_warn(p->br, "error setting offload flag on port %u(%s)\n",
|
|
(unsigned int)p->port_no, p->dev->name);
|
|
return err;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void
|
|
br_switchdev_fdb_call_notifiers(bool adding, const unsigned char *mac,
|
|
u16 vid, struct net_device *dev)
|
|
{
|
|
struct switchdev_notifier_fdb_info info;
|
|
unsigned long notifier_type;
|
|
|
|
info.addr = mac;
|
|
info.vid = vid;
|
|
notifier_type = adding ? SWITCHDEV_FDB_ADD_TO_DEVICE : SWITCHDEV_FDB_DEL_TO_DEVICE;
|
|
call_switchdev_notifiers(notifier_type, dev, &info.info);
|
|
}
|
|
|
|
void
|
|
br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type)
|
|
{
|
|
if (!fdb->added_by_user || !fdb->dst)
|
|
return;
|
|
|
|
switch (type) {
|
|
case RTM_DELNEIGH:
|
|
br_switchdev_fdb_call_notifiers(false, fdb->key.addr.addr,
|
|
fdb->key.vlan_id,
|
|
fdb->dst->dev);
|
|
break;
|
|
case RTM_NEWNEIGH:
|
|
br_switchdev_fdb_call_notifiers(true, fdb->key.addr.addr,
|
|
fdb->key.vlan_id,
|
|
fdb->dst->dev);
|
|
break;
|
|
}
|
|
}
|