From: Pablo Neira Ayuso <pablo@netfilter.org>
To: netfilter-devel@vger.kernel.org
Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org,
Felix Fietkau <nbd@nbd.name>
Subject: [PATCH net-next 01/23] net: resolve forwarding path from virtual netdevice and HW destination address
Date: Thu, 11 Mar 2021 01:35:42 +0100 [thread overview]
Message-ID: <20210311003604.22199-2-pablo@netfilter.org> (raw)
In-Reply-To: <20210311003604.22199-1-pablo@netfilter.org>
This patch adds dev_fill_forward_path() which resolves the path to reach
the real netdevice from the IP forwarding side. This function takes as
input the netdevice and the destination hardware address and it walks
down the devices calling .ndo_fill_forward_path() for each device until
the real device is found.
For instance, assuming the following topology:
IP forwarding
/ \
br0 eth0
/ \
eth1 eth2
.
.
.
ethX
ab:cd:ef:ab:cd:ef
where eth1 and eth2 are bridge ports and eth0 provides WAN connectivity.
ethX is the interface in another box which is connected to the eth1
bridge port.
For packets going through IP forwarding to br0 whose destination MAC
address is ab:cd:ef:ab:cd:ef, dev_fill_forward_path() provides the
following path:
br0 -> eth1
.ndo_fill_forward_path for br0 looks up at the FDB for the bridge port
from the destination MAC address to get the bridge port eth1.
This information allows to create a fast path that bypasses the classic
bridge and IP forwarding paths, so packets go directly from the bridge
port eth1 to eth0 (wan interface) and vice versa.
fast path
.------------------------.
/ \
| IP forwarding |
| / \ \/
| br0 eth0
. / \
-> eth1 eth2
.
.
.
ethX
ab:cd:ef:ab:cd:ef
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/linux/netdevice.h | 27 +++++++++++++++++++++++
net/core/dev.c | 46 +++++++++++++++++++++++++++++++++++++++
2 files changed, 73 insertions(+)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5b67ea89d5f2..70eb88a4adbb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -831,6 +831,27 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
struct sk_buff *skb,
struct net_device *sb_dev);
+enum net_device_path_type {
+ DEV_PATH_ETHERNET = 0,
+};
+
+struct net_device_path {
+ enum net_device_path_type type;
+ const struct net_device *dev;
+};
+
+#define NET_DEVICE_PATH_STACK_MAX 5
+
+struct net_device_path_stack {
+ int num_paths;
+ struct net_device_path path[NET_DEVICE_PATH_STACK_MAX];
+};
+
+struct net_device_path_ctx {
+ const struct net_device *dev;
+ const u8 *daddr;
+};
+
enum tc_setup_type {
TC_SETUP_QDISC_MQPRIO,
TC_SETUP_CLSU32,
@@ -1265,6 +1286,8 @@ struct netdev_net_notifier {
* struct net_device *(*ndo_get_peer_dev)(struct net_device *dev);
* If a device is paired with a peer device, return the peer instance.
* The caller must be under RCU read context.
+ * int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path);
+ * Get the forwarding path to reach the real device from the HW destination address
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
@@ -1471,6 +1494,8 @@ struct net_device_ops {
int (*ndo_tunnel_ctl)(struct net_device *dev,
struct ip_tunnel_parm *p, int cmd);
struct net_device * (*ndo_get_peer_dev)(struct net_device *dev);
+ int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx,
+ struct net_device_path *path);
};
/**
@@ -2844,6 +2869,8 @@ void dev_remove_offload(struct packet_offload *po);
int dev_get_iflink(const struct net_device *dev);
int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb);
+int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
+ struct net_device_path_stack *stack);
struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags,
unsigned short mask);
struct net_device *dev_get_by_name(struct net *net, const char *name);
diff --git a/net/core/dev.c b/net/core/dev.c
index 6c5967e80132..e9a00a00afee 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -848,6 +848,52 @@ int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
}
EXPORT_SYMBOL_GPL(dev_fill_metadata_dst);
+static struct net_device_path *dev_fwd_path(struct net_device_path_stack *stack)
+{
+ int k = stack->num_paths++;
+
+ if (WARN_ON_ONCE(k >= NET_DEVICE_PATH_STACK_MAX))
+ return NULL;
+
+ return &stack->path[k];
+}
+
+int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
+ struct net_device_path_stack *stack)
+{
+ const struct net_device *last_dev;
+ struct net_device_path_ctx ctx = {
+ .dev = dev,
+ .daddr = daddr,
+ };
+ struct net_device_path *path;
+ int ret = 0;
+
+ stack->num_paths = 0;
+ while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) {
+ last_dev = ctx.dev;
+ path = dev_fwd_path(stack);
+ if (!path)
+ return -1;
+
+ memset(path, 0, sizeof(struct net_device_path));
+ ret = ctx.dev->netdev_ops->ndo_fill_forward_path(&ctx, path);
+ if (ret < 0)
+ return -1;
+
+ if (WARN_ON_ONCE(last_dev == ctx.dev))
+ return -1;
+ }
+ path = dev_fwd_path(stack);
+ if (!path)
+ return -1;
+ path->type = DEV_PATH_ETHERNET;
+ path->dev = ctx.dev;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(dev_fill_forward_path);
+
/**
* __dev_get_by_name - find a device by its name
* @net: the applicable net namespace
--
2.20.1
next prev parent reply other threads:[~2021-03-11 0:37 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-11 0:35 [PATCH net-next 00/23] netfilter: flowtable enhancements Pablo Neira Ayuso
2021-03-11 0:35 ` Pablo Neira Ayuso [this message]
2021-03-11 0:35 ` [PATCH net-next 02/23] net: 8021q: resolve forwarding path for vlan devices Pablo Neira Ayuso
2021-03-11 0:35 ` [PATCH net-next 03/23] net: bridge: resolve forwarding path for bridge devices Pablo Neira Ayuso
2021-03-11 0:35 ` [PATCH net-next 04/23] net: bridge: resolve forwarding path for VLAN tag actions in " Pablo Neira Ayuso
2021-03-11 0:35 ` [PATCH net-next 05/23] net: ppp: resolve forwarding path for bridge pppoe devices Pablo Neira Ayuso
2021-03-11 0:35 ` [PATCH net-next 06/23] net: dsa: resolve forwarding path for dsa slave ports Pablo Neira Ayuso
2021-03-11 0:35 ` [PATCH net-next 07/23] netfilter: flowtable: add xmit path types Pablo Neira Ayuso
2021-03-11 0:35 ` [PATCH net-next 08/23] netfilter: flowtable: use dev_fill_forward_path() to obtain ingress device Pablo Neira Ayuso
2021-03-11 0:35 ` [PATCH net-next 09/23] netfilter: flowtable: use dev_fill_forward_path() to obtain egress device Pablo Neira Ayuso
2021-03-11 0:35 ` [PATCH net-next 10/23] netfilter: flowtable: add vlan support Pablo Neira Ayuso
2021-03-11 0:35 ` [PATCH net-next 11/23] netfilter: flowtable: add bridge vlan filtering support Pablo Neira Ayuso
2021-03-11 0:35 ` [PATCH net-next 12/23] netfilter: flowtable: add pppoe support Pablo Neira Ayuso
2021-03-11 0:35 ` [PATCH net-next 13/23] netfilter: flowtable: add dsa support Pablo Neira Ayuso
2021-03-11 0:35 ` [PATCH net-next 14/23] selftests: netfilter: flowtable bridge and vlan support Pablo Neira Ayuso
2021-03-11 0:35 ` [PATCH net-next 15/23] netfilter: flowtable: add offload support for xmit path types Pablo Neira Ayuso
2021-03-11 0:35 ` [PATCH net-next 16/23] netfilter: nft_flow_offload: use direct xmit if hardware offload is enabled Pablo Neira Ayuso
2021-03-11 0:35 ` [PATCH net-next 17/23] netfilter: flowtable: bridge vlan hardware offload and switchdev Pablo Neira Ayuso
2021-03-11 0:35 ` [PATCH net-next 18/23] net: flow_offload: add FLOW_ACTION_PPPOE_PUSH Pablo Neira Ayuso
2021-03-11 0:36 ` [PATCH net-next 19/23] netfilter: flowtable: support for FLOW_ACTION_PPPOE_PUSH Pablo Neira Ayuso
2021-03-11 0:36 ` [PATCH net-next 20/23] dsa: slave: add support for TC_SETUP_FT Pablo Neira Ayuso
2021-03-11 0:36 ` [PATCH net-next 21/23] net: ethernet: mtk_eth_soc: add support for initializing the PPE Pablo Neira Ayuso
2021-03-11 0:36 ` [PATCH net-next 22/23] net: ethernet: mtk_eth_soc: add flow offloading support Pablo Neira Ayuso
2021-03-11 0:36 ` [PATCH net-next 23/23] net: ethernet: mtk_eth_soc: fix parsing packets in GDM Pablo Neira Ayuso
2021-03-12 7:36 ` Felix Fietkau
2021-03-11 20:47 ` [PATCH net-next 00/23] netfilter: flowtable enhancements Jakub Kicinski
2021-03-11 21:45 ` Pablo Neira Ayuso
2021-03-11 22:31 ` David Miller
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210311003604.22199-2-pablo@netfilter.org \
--to=pablo@netfilter.org \
--cc=davem@davemloft.net \
--cc=kuba@kernel.org \
--cc=nbd@nbd.name \
--cc=netdev@vger.kernel.org \
--cc=netfilter-devel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).