linux/net/bridge/br_vlan_tunnel.c

225 lines
5.2 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
/*
* Bridge per vlan tunnel port dst_metadata handling code
*
* Authors:
* Roopa Prabhu <roopa@cumulusnetworks.com>
*/
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/slab.h>
#include <net/switchdev.h>
#include <net/dst_metadata.h>
#include "br_private.h"
#include "br_private_tunnel.h"
static inline int br_vlan_tunid_cmp(struct rhashtable_compare_arg *arg,
const void *ptr)
{
const struct net_bridge_vlan *vle = ptr;
__be64 tunid = *(__be64 *)arg->key;
return vle->tinfo.tunnel_id != tunid;
}
static const struct rhashtable_params br_vlan_tunnel_rht_params = {
.head_offset = offsetof(struct net_bridge_vlan, tnode),
.key_offset = offsetof(struct net_bridge_vlan, tinfo.tunnel_id),
.key_len = sizeof(__be64),
.nelem_hint = 3,
.obj_cmpfn = br_vlan_tunid_cmp,
.automatic_shrinking = true,
};
static struct net_bridge_vlan *br_vlan_tunnel_lookup(struct rhashtable *tbl,
__be64 tunnel_id)
{
return rhashtable_lookup_fast(tbl, &tunnel_id,
br_vlan_tunnel_rht_params);
}
static void vlan_tunnel_info_release(struct net_bridge_vlan *vlan)
{
struct metadata_dst *tdst = rtnl_dereference(vlan->tinfo.tunnel_dst);
WRITE_ONCE(vlan->tinfo.tunnel_id, 0);
RCU_INIT_POINTER(vlan->tinfo.tunnel_dst, NULL);
dst_release(&tdst->dst);
}
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
void vlan_tunnel_info_del(struct net_bridge_vlan_group *vg,
struct net_bridge_vlan *vlan)
{
if (!rcu_access_pointer(vlan->tinfo.tunnel_dst))
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
return;
rhashtable_remove_fast(&vg->tunnel_hash, &vlan->tnode,
br_vlan_tunnel_rht_params);
vlan_tunnel_info_release(vlan);
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
}
static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg,
struct net_bridge_vlan *vlan, u32 tun_id)
{
struct metadata_dst *metadata = rtnl_dereference(vlan->tinfo.tunnel_dst);
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
__be64 key = key32_to_tunnel_id(cpu_to_be32(tun_id));
int err;
if (metadata)
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
return -EEXIST;
metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY,
key, 0);
if (!metadata)
return -EINVAL;
metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_BRIDGE;
rcu_assign_pointer(vlan->tinfo.tunnel_dst, metadata);
WRITE_ONCE(vlan->tinfo.tunnel_id, key);
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
err = rhashtable_lookup_insert_fast(&vg->tunnel_hash, &vlan->tnode,
br_vlan_tunnel_rht_params);
if (err)
goto out;
return 0;
out:
vlan_tunnel_info_release(vlan);
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
return err;
}
/* Must be protected by RTNL.
* Must be called with vid in range from 1 to 4094 inclusive.
*/
int nbp_vlan_tunnel_info_add(const struct net_bridge_port *port, u16 vid,
u32 tun_id)
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
{
struct net_bridge_vlan_group *vg;
struct net_bridge_vlan *vlan;
ASSERT_RTNL();
vg = nbp_vlan_group(port);
vlan = br_vlan_find(vg, vid);
if (!vlan)
return -EINVAL;
return __vlan_tunnel_info_add(vg, vlan, tun_id);
}
/* Must be protected by RTNL.
* Must be called with vid in range from 1 to 4094 inclusive.
*/
int nbp_vlan_tunnel_info_delete(const struct net_bridge_port *port, u16 vid)
bridge: per vlan dst_metadata netlink support This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-01 14:59:54 +08:00
{
struct net_bridge_vlan_group *vg;
struct net_bridge_vlan *v;
ASSERT_RTNL();
vg = nbp_vlan_group(port);
v = br_vlan_find(vg, vid);
if (!v)
return -ENOENT;
vlan_tunnel_info_del(vg, v);
return 0;
}
static void __vlan_tunnel_info_flush(struct net_bridge_vlan_group *vg)
{
struct net_bridge_vlan *vlan, *tmp;
list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist)
vlan_tunnel_info_del(vg, vlan);
}
void nbp_vlan_tunnel_info_flush(struct net_bridge_port *port)
{
struct net_bridge_vlan_group *vg;
ASSERT_RTNL();
vg = nbp_vlan_group(port);
__vlan_tunnel_info_flush(vg);
}
int vlan_tunnel_init(struct net_bridge_vlan_group *vg)
{
return rhashtable_init(&vg->tunnel_hash, &br_vlan_tunnel_rht_params);
}
void vlan_tunnel_deinit(struct net_bridge_vlan_group *vg)
{
rhashtable_destroy(&vg->tunnel_hash);
}
void br_handle_ingress_vlan_tunnel(struct sk_buff *skb,
struct net_bridge_port *p,
struct net_bridge_vlan_group *vg)
{
struct ip_tunnel_info *tinfo = skb_tunnel_info(skb);
struct net_bridge_vlan *vlan;
if (!vg || !tinfo)
return;
/* if already tagged, ignore */
if (skb_vlan_tagged(skb))
return;
/* lookup vid, given tunnel id */
vlan = br_vlan_tunnel_lookup(&vg->tunnel_hash, tinfo->key.tun_id);
if (!vlan)
return;
skb_dst_drop(skb);
__vlan_hwaccel_put_tag(skb, p->br->vlan_proto, vlan->vid);
}
int br_handle_egress_vlan_tunnel(struct sk_buff *skb,
struct net_bridge_vlan *vlan)
{
struct metadata_dst *tunnel_dst;
__be64 tunnel_id;
int err;
if (!vlan)
return 0;
tunnel_id = READ_ONCE(vlan->tinfo.tunnel_id);
if (!tunnel_id || unlikely(!skb_vlan_tag_present(skb)))
return 0;
skb_dst_drop(skb);
err = skb_vlan_pop(skb);
if (err)
return err;
bridge: Add backup nexthop ID support Add a new bridge port attribute that allows attaching a nexthop object ID to an skb that is redirected to a backup bridge port with VLAN tunneling enabled. Specifically, when redirecting a known unicast packet, read the backup nexthop ID from the bridge port that lost its carrier and set it in the bridge control block of the skb before forwarding it via the backup port. Note that reading the ID from the bridge port should not result in a cache miss as the ID is added next to the 'backup_port' field that was already accessed. After this change, the 'state' field still stays on the first cache line, together with other data path related fields such as 'flags and 'vlgrp': struct net_bridge_port { struct net_bridge * br; /* 0 8 */ struct net_device * dev; /* 8 8 */ netdevice_tracker dev_tracker; /* 16 0 */ struct list_head list; /* 16 16 */ long unsigned int flags; /* 32 8 */ struct net_bridge_vlan_group * vlgrp; /* 40 8 */ struct net_bridge_port * backup_port; /* 48 8 */ u32 backup_nhid; /* 56 4 */ u8 priority; /* 60 1 */ u8 state; /* 61 1 */ u16 port_no; /* 62 2 */ /* --- cacheline 1 boundary (64 bytes) --- */ [...] } __attribute__((__aligned__(8))); When forwarding an skb via a bridge port that has VLAN tunneling enabled, check if the backup nexthop ID stored in the bridge control block is valid (i.e., not zero). If so, instead of attaching the pre-allocated metadata (that only has the tunnel key set), allocate a new metadata, set both the tunnel key and the nexthop object ID and attach it to the skb. By default, do not dump the new attribute to user space as a value of zero is an invalid nexthop object ID. The above is useful for EVPN multihoming. When one of the links composing an Ethernet Segment (ES) fails, traffic needs to be redirected towards the host via one of the other ES peers. For example, if a host is multihomed to three different VTEPs, the backup port of each ES link needs to be set to the VXLAN device and the backup nexthop ID needs to point to an FDB nexthop group that includes the IP addresses of the other two VTEPs. The VXLAN driver will extract the ID from the metadata of the redirected skb, calculate its flow hash and forward it towards one of the other VTEPs. If the ID does not exist, or represents an invalid nexthop object, the VXLAN driver will drop the skb. This relieves the bridge driver from the need to validate the ID. Signed-off-by: Ido Schimmel <idosch@nvidia.com> Acked-by: Nikolay Aleksandrov <razor@blackwall.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-07-17 16:12:28 +08:00
if (BR_INPUT_SKB_CB(skb)->backup_nhid) {
tunnel_dst = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY,
tunnel_id, 0);
if (!tunnel_dst)
return -ENOMEM;
tunnel_dst->u.tun_info.mode |= IP_TUNNEL_INFO_TX |
IP_TUNNEL_INFO_BRIDGE;
tunnel_dst->u.tun_info.key.nhid =
BR_INPUT_SKB_CB(skb)->backup_nhid;
skb_dst_set(skb, &tunnel_dst->dst);
return 0;
}
tunnel_dst = rcu_dereference(vlan->tinfo.tunnel_dst);
net: bridge: fix vlan tunnel dst refcnt when egressing The egress tunnel code uses dst_clone() and directly sets the result which is wrong because the entry might have 0 refcnt or be already deleted, causing number of problems. It also triggers the WARN_ON() in dst_hold()[1] when a refcnt couldn't be taken. Fix it by using dst_hold_safe() and checking if a reference was actually taken before setting the dst. [1] dmesg WARN_ON log and following refcnt errors WARNING: CPU: 5 PID: 38 at include/net/dst.h:230 br_handle_egress_vlan_tunnel+0x10b/0x134 [bridge] Modules linked in: 8021q garp mrp bridge stp llc bonding ipv6 virtio_net CPU: 5 PID: 38 Comm: ksoftirqd/5 Kdump: loaded Tainted: G W 5.13.0-rc3+ #360 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-1.fc33 04/01/2014 RIP: 0010:br_handle_egress_vlan_tunnel+0x10b/0x134 [bridge] Code: e8 85 bc 01 e1 45 84 f6 74 90 45 31 f6 85 db 48 c7 c7 a0 02 19 a0 41 0f 94 c6 31 c9 31 d2 44 89 f6 e8 64 bc 01 e1 85 db 75 02 <0f> 0b 31 c9 31 d2 44 89 f6 48 c7 c7 70 02 19 a0 e8 4b bc 01 e1 49 RSP: 0018:ffff8881003d39e8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffffffffa01902a0 RBP: ffff8881040c6700 R08: 0000000000000000 R09: 0000000000000001 R10: 2ce93d0054fe0d00 R11: 54fe0d00000e0000 R12: ffff888109515000 R13: 0000000000000000 R14: 0000000000000001 R15: 0000000000000401 FS: 0000000000000000(0000) GS:ffff88822bf40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f42ba70f030 CR3: 0000000109926000 CR4: 00000000000006e0 Call Trace: br_handle_vlan+0xbc/0xca [bridge] __br_forward+0x23/0x164 [bridge] deliver_clone+0x41/0x48 [bridge] br_handle_frame_finish+0x36f/0x3aa [bridge] ? skb_dst+0x2e/0x38 [bridge] ? br_handle_ingress_vlan_tunnel+0x3e/0x1c8 [bridge] ? br_handle_frame_finish+0x3aa/0x3aa [bridge] br_handle_frame+0x2c3/0x377 [bridge] ? __skb_pull+0x33/0x51 ? vlan_do_receive+0x4f/0x36a ? br_handle_frame_finish+0x3aa/0x3aa [bridge] __netif_receive_skb_core+0x539/0x7c6 ? __list_del_entry_valid+0x16e/0x1c2 __netif_receive_skb_list_core+0x6d/0xd6 netif_receive_skb_list_internal+0x1d9/0x1fa gro_normal_list+0x22/0x3e dev_gro_receive+0x55b/0x600 ? detach_buf_split+0x58/0x140 napi_gro_receive+0x94/0x12e virtnet_poll+0x15d/0x315 [virtio_net] __napi_poll+0x2c/0x1c9 net_rx_action+0xe6/0x1fb __do_softirq+0x115/0x2d8 run_ksoftirqd+0x18/0x20 smpboot_thread_fn+0x183/0x19c ? smpboot_unregister_percpu_thread+0x66/0x66 kthread+0x10a/0x10f ? kthread_mod_delayed_work+0xb6/0xb6 ret_from_fork+0x22/0x30 ---[ end trace 49f61b07f775fd2b ]--- dst_release: dst:00000000c02d677a refcnt:-1 dst_release underflow Cc: stable@vger.kernel.org Fixes: 11538d039ac6 ("bridge: vlan dst_metadata hooks in ingress and egress paths") Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-10 20:04:11 +08:00
if (tunnel_dst && dst_hold_safe(&tunnel_dst->dst))
skb_dst_set(skb, &tunnel_dst->dst);
return 0;
}