From: Tobias Waldekranz <tobias@xxxxxxxxxxxxxx>
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->v4: none
Signed-off-by: Tobias Waldekranz <tobias@xxxxxxxxxxxxxx>
Signed-off-by: Vladimir Oltean <vladimir.oltean@xxxxxxx>
Reviewed-by: Grygorii Strashko <grygorii.strashko@xxxxxx>
---
net/bridge/br_if.c | 2 +-
net/bridge/br_private.h | 21 ++++++++++++++++-----
net/bridge/br_switchdev.c | 16 ++++++++--------
3 files changed, 25 insertions(+), 14 deletions(-)
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 6e4a32354a13..838a277e3cf7 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -643,7 +643,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
if (err)
goto err5;
- err = nbp_switchdev_mark_set(p);
+ err = nbp_switchdev_hwdom_set(p);
if (err)
goto err6;
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 2b48b204205e..54e29a8576a1 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -329,7 +329,10 @@ struct net_bridge_port {
struct netpoll *np;
#endif
#ifdef CONFIG_NET_SWITCHDEV
- int offload_fwd_mark;
+ /* Identifier used to group ports that share the same switchdev
+ * hardware domain.
+ */
+ int hwdom;
#endif
u16 group_fwd_mask;
u16 backup_redirected_cnt;
@@ -476,7 +479,10 @@ struct net_bridge {
u32 auto_cnt;
#ifdef CONFIG_NET_SWITCHDEV
- int offload_fwd_mark;
+ /* Counter used to make sure that hardware domains get unique
+ * identifiers in case a bridge spans multiple switchdev instances.
+ */
+ int last_hwdom;
#endif
struct hlist_head fdb_list;
@@ -506,7 +512,12 @@ struct br_input_skb_cb {
#endif
#ifdef CONFIG_NET_SWITCHDEV
- int offload_fwd_mark;
+ /* The switchdev hardware domain from which this packet was received.
+ * If skb->offload_fwd_mark was set, then this packet was already
+ * forwarded by hardware to the other ports in the source hardware
+ * domain, otherwise it wasn't.
+ */
+ int src_hwdom;
#endif
};
@@ -1645,7 +1656,7 @@ static inline void br_sysfs_delbr(struct net_device *dev) { return; }
/* br_switchdev.c */
#ifdef CONFIG_NET_SWITCHDEV
-int nbp_switchdev_mark_set(struct net_bridge_port *p);
+int nbp_switchdev_hwdom_set(struct net_bridge_port *p);
void nbp_switchdev_frame_mark(const struct net_bridge_port *p,
struct sk_buff *skb);
bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p,
@@ -1665,7 +1676,7 @@ static inline void br_switchdev_frame_unmark(struct sk_buff *skb)
skb->offload_fwd_mark = 0;
}
#else
-static inline int nbp_switchdev_mark_set(struct net_bridge_port *p)
+static inline int nbp_switchdev_hwdom_set(struct net_bridge_port *p)
{
return 0;
}
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index d3adee0f91f9..833fd30482c2 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -8,20 +8,20 @@
#include "br_private.h"
-static int br_switchdev_mark_get(struct net_bridge *br, struct net_device *dev)
+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->offload_fwd_mark;
+ return p->hwdom;
}
- return ++br->offload_fwd_mark;
+ return ++br->last_hwdom;
}
-int nbp_switchdev_mark_set(struct net_bridge_port *p)
+int nbp_switchdev_hwdom_set(struct net_bridge_port *p)
{
struct netdev_phys_item_id ppid = { };
int err;
@@ -35,7 +35,7 @@ int nbp_switchdev_mark_set(struct net_bridge_port *p)
return err;
}
- p->offload_fwd_mark = br_switchdev_mark_get(p->br, p->dev);
+ p->hwdom = br_switchdev_hwdom_get(p->br, p->dev);
return 0;
}
@@ -43,15 +43,15 @@ int nbp_switchdev_mark_set(struct net_bridge_port *p)
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;
+ 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)->offload_fwd_mark != p->offload_fwd_mark;
+ BR_INPUT_SKB_CB(skb)->src_hwdom != p->hwdom;
}
/* Flags that can be offloaded to hardware */
--
2.25.1
