mirror_ubuntu-kernels/net/bridge/br_switchdev.c
Tobias Waldekranz f7cf972f93 net: bridge: disambiguate offload_fwd_mark
Before this change, four related - but distinct - concepts where named
offload_fwd_mark:

- skb->offload_fwd_mark: Set by the switchdev driver if the underlying
  hardware has already forwarded this frame to the other ports in the
  same hardware domain.

- nbp->offload_fwd_mark: An idetifier used to group ports that share
  the same hardware forwarding domain.

- br->offload_fwd_mark: Counter used to make sure that unique IDs are
  used in cases where a bridge contains ports from multiple hardware
  domains.

- skb->cb->offload_fwd_mark: The hardware domain on which the frame
  ingressed and was forwarded.

Introduce the term "hardware forwarding domain" ("hwdom") in the
bridge to denote a set of ports with the following property:

    If an skb with skb->offload_fwd_mark set, is received on a port
    belonging to hwdom N, that frame has already been forwarded to all
    other ports in hwdom N.

By decoupling the name from "offload_fwd_mark", we can extend the
term's definition in the future - e.g. to add constraints that
describe expected egress behavior - without overloading the meaning of
"offload_fwd_mark".

- nbp->offload_fwd_mark thus becomes nbp->hwdom.

- br->offload_fwd_mark becomes br->last_hwdom.

- skb->cb->offload_fwd_mark becomes skb->cb->src_hwdom. The slight
  change in naming here mandates a slight change in behavior of the
  nbp_switchdev_frame_mark() function. Previously, it only set this
  value in skb->cb for packets with skb->offload_fwd_mark true (ones
  which were forwarded in hardware). Whereas now we always track the
  incoming hwdom for all packets coming from a switchdev (even for the
  packets which weren't forwarded in hardware, such as STP BPDUs, IGMP
  reports etc). As all uses of skb->cb->offload_fwd_mark were already
  gated behind checks of skb->offload_fwd_mark, this will not introduce
  any functional change, but it paves the way for future changes where
  the ingressing hwdom must be known for frames coming from a switchdev
  regardless of whether they were forwarded in hardware or not
  (basically, if the skb comes from a switchdev, skb->cb->src_hwdom now
  always tracks which one).

  A typical example where this is relevant: the switchdev has a fixed
  configuration to trap STP BPDUs, but STP is not running on the bridge
  and the group_fwd_mask allows them to be forwarded. Say we have this
  setup:

        br0
       / | \
      /  |  \
  swp0 swp1 swp2

  A BPDU comes in on swp0 and is trapped to the CPU; the driver does not
  set skb->offload_fwd_mark. The bridge determines that the frame should
  be forwarded to swp{1,2}. It is imperative that forward offloading is
  _not_ allowed in this case, as the source hwdom is already "poisoned".

  Recording the source hwdom allows this case to be handled properly.

v2->v3: added code comments
v3->v6: none

Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-22 00:26:23 -07:00

159 lines
3.7 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_hwdom_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 (netdev_port_same_parent_id(dev, p->dev))
return p->hwdom;
}
return ++br->last_hwdom;
}
int nbp_switchdev_hwdom_set(struct net_bridge_port *p)
{
struct netdev_phys_item_id ppid = { };
int err;
ASSERT_RTNL();
err = dev_get_port_parent_id(p->dev, &ppid, true);
if (err) {
if (err == -EOPNOTSUPP)
return 0;
return err;
}
p->hwdom = br_switchdev_hwdom_get(p->br, p->dev);
return 0;
}
void nbp_switchdev_frame_mark(const struct net_bridge_port *p,
struct sk_buff *skb)
{
if (p->hwdom)
BR_INPUT_SKB_CB(skb)->src_hwdom = p->hwdom;
}
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)->src_hwdom != p->hwdom;
}
/* 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 netlink_ext_ack *extack)
{
struct switchdev_attr attr = {
.orig_dev = p->dev,
};
struct switchdev_notifier_port_attr_info info = {
.attr = &attr,
};
int err;
mask &= BR_PORT_FLAGS_HW_OFFLOAD;
if (!mask)
return 0;
attr.id = SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS;
attr.u.brport_flags.val = flags;
attr.u.brport_flags.mask = mask;
/* We run from atomic context here */
err = call_switchdev_notifiers(SWITCHDEV_PORT_ATTR_SET, p->dev,
&info.info, extack);
err = notifier_to_errno(err);
if (err == -EOPNOTSUPP)
return 0;
if (err) {
if (extack && !extack->_msg)
NL_SET_ERR_MSG_MOD(extack,
"bridge flag offload is not supported");
return -EOPNOTSUPP;
}
attr.id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS;
attr.flags = SWITCHDEV_F_DEFER;
err = switchdev_port_attr_set(p->dev, &attr, extack);
if (err) {
if (extack && !extack->_msg)
NL_SET_ERR_MSG_MOD(extack,
"error setting offload flag on port");
return err;
}
return 0;
}
void
br_switchdev_fdb_notify(struct net_bridge *br,
const struct net_bridge_fdb_entry *fdb, int type)
{
const struct net_bridge_port *dst = READ_ONCE(fdb->dst);
struct net_device *dev = dst ? dst->dev : br->dev;
struct switchdev_notifier_fdb_info info = {
.addr = fdb->key.addr.addr,
.vid = fdb->key.vlan_id,
.added_by_user = test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags),
.is_local = test_bit(BR_FDB_LOCAL, &fdb->flags),
.offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags),
};
switch (type) {
case RTM_DELNEIGH:
call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_DEVICE,
dev, &info.info, NULL);
break;
case RTM_NEWNEIGH:
call_switchdev_notifiers(SWITCHDEV_FDB_ADD_TO_DEVICE,
dev, &info.info, NULL);
break;
}
}
int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags,
struct netlink_ext_ack *extack)
{
struct switchdev_obj_port_vlan v = {
.obj.orig_dev = dev,
.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
.flags = flags,
.vid = vid,
};
return switchdev_port_obj_add(dev, &v.obj, extack);
}
int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid)
{
struct switchdev_obj_port_vlan v = {
.obj.orig_dev = dev,
.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
.vid = vid,
};
return switchdev_port_obj_del(dev, &v.obj);
}