matthieu/frr
1
0
Fork 0
forked from Mirror/frr
Code Pull requests Activity
frr/zebra/zebra_vxlan.h
Rajasekar Raja aa4786642c zebra: vlan to dplane Offload from main 
Trigger: Zebra core seen when we convert l2vni to l3vni and back

BackTrace:
/usr/lib/x86_64-linux-gnu/frr/libfrr.so.0(_zlog_assert_failed+0xe9) [0x7f4af96989d9]
/usr/lib/frr/zebra(zebra_vxlan_if_vni_up+0x250) [0x5561022ae030]
/usr/lib/frr/zebra(netlink_vlan_change+0x2f4) [0x5561021fd354]
/usr/lib/frr/zebra(netlink_parse_info+0xff) [0x55610220d37f]
/usr/lib/frr/zebra(+0xc264a) [0x55610220d64a]
/usr/lib/x86_64-linux-gnu/frr/libfrr.so.0(thread_call+0x7d) [0x7f4af967e96d]
/usr/lib/x86_64-linux-gnu/frr/libfrr.so.0(frr_run+0xe8) [0x7f4af9637588]
/usr/lib/frr/zebra(main+0x402) [0x5561021f4d32]
/lib/x86_64-linux-gnu/libc.so.6(+0x2724a) [0x7f4af932624a]
/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0x85) [0x7f4af9326305]
/usr/lib/frr/zebra(_start+0x21) [0x5561021f72f1]

Root Cause:
In working case,
 - We get a RTM_NEWLINK whose ctx is enqueued by zebra dplane and
   dequeued by zebra main and processed i.e.
   (102000 is deleted from vxlan99) before we handle RTM_NEWVLAN.
 - So in handling of NEWVLAN (vxlan99) we bail out since find with
   vlan id 703 does not exist.

root@leaf2:mgmt:/var/log/frr# cat ~/raja_logs/working/nocras.log  | grep "RTM_NEWLINK\|QUEUED\|vxlan99\|in thread"
2024/07/18 23:09:33.741105 ZEBRA: [KMXEB-K771Y] netlink_parse_info: netlink-dp-in (NS 0) type RTM_NEWLINK(16), len=616, seq=0, pid=0
2024/07/18 23:09:33.744061 ZEBRA: [K8FXY-V65ZJ] Intf dplane ctx 0x7f2244000cf0, op INTF_INSTALL, ifindex (65), result QUEUED
2024/07/18 23:09:33.767240 ZEBRA: [KMXEB-K771Y] netlink_parse_info: netlink-dp-in (NS 0) type RTM_NEWLINK(16), len=508, seq=0, pid=0
2024/07/18 23:09:33.767380 ZEBRA: [K8FXY-V65ZJ] Intf dplane ctx 0x7f2244000cf0, op INTF_INSTALL, ifindex (73), result QUEUED
2024/07/18 23:09:33.767389 ZEBRA: [NVFT0-HS1EX] INTF_INSTALL for vxlan99(73)
2024/07/18 23:09:33.767404 ZEBRA: [TQR2A-H2RFY] Vlan-Vni(1186:1186-6000002:6000002) update for VxLAN IF vxlan99(73)
2024/07/18 23:09:33.767422 ZEBRA: [TP4VP-XZ627] Del L2-VNI 102000 intf vxlan99(73)
2024/07/18 23:09:33.767858 ZEBRA: [QYXB9-6RNNK] RTM_NEWVLAN bridge IF vxlan99 NS 0
2024/07/18 23:09:33.767866 ZEBRA: [KKZGZ-8PCDW] Cannot find VNI for VID (703) IF vxlan99 for vlan state update >>>>BAIL OUT

In failure case,
 - The NEWVLAN is received first even before processing RTM_NEWLINK.
 - Since the vxlan id 102000 is not removed from the vxlan99,
   the find with vlan id 703 returns the 102000 one and we invoke
   zebra_vxlan_if_vni_up where the interfaces don't match and assert.

root@leaf2:mgmt:/var/log/frr# cat ~/raja_logs/noworking/crash.log | grep "RTM_NEWLINK\|QUEUED\|vxlan99\|in thread"
2024/07/18 22:26:43.829370 ZEBRA: [KMXEB-K771Y] netlink_parse_info: netlink-dp-in (NS 0) type RTM_NEWLINK(16), len=616, seq=0, pid=0
2024/07/18 22:26:43.829646 ZEBRA: [K8FXY-V65ZJ] Intf dplane ctx 0x7fe07c026d30, op INTF_INSTALL, ifindex (65), result QUEUED
2024/07/18 22:26:43.853930 ZEBRA: [QYXB9-6RNNK] RTM_NEWVLAN bridge IF vxlan99 NS 0
2024/07/18 22:26:43.853949 ZEBRA: [K61WJ-XQQ3X] Intf vxlan99(73) L2-VNI 102000 is UP >>> VLAN PROCESSED BEFORE INTF EVENT
2024/07/18 22:26:43.853951 ZEBRA: [SPV50-BX2RP] RAJA zevpn_vxlanif vxlan48 and ifp vxlan99
2024/07/18 22:26:43.854005 ZEBRA: [KMXEB-K771Y] netlink_parse_info: netlink-dp-in (NS 0) type RTM_NEWLINK(16), len=508, seq=0, pid=0
2024/07/18 22:26:43.854241 ZEBRA: [KMXEB-K771Y] netlink_parse_info: netlink-dp-in (NS 0) type RTM_NEWLINK(16), len=516, seq=0, pid=0
2024/07/18 22:26:43.854251 ZEBRA: [KMXEB-K771Y] netlink_parse_info: netlink-dp-in (NS 0) type RTM_NEWLINK(16), len=544, seq=0, pid=0
ZEBRA: in thread kernel_read scheduled from zebra/kernel_netlink.c:505 kernel_read()

Fix:
Similar to #13396, where link change
handling was offloaded to dplane, same is being done for vlan events.

Note: Prior to this change, zebra main thread was interested in the
RTNLGRP_BRVLAN. So all the kernel events pertaining to vlan was
handled by zebra main.

With this change change as well the handling of vlan events is still
with Zebra main. However we offload it via Dplane thread.

Ticket :#3878175

Signed-off-by: Rajasekar Raja <rajasekarr@nvidia.com>
2024-09-26 20:17:35 -07:00

230 lines
9.3 KiB
C
Raw Blame History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Zebra VxLAN (EVPN) Data structures and definitions
* These are public definitions referenced by other files.
* Copyright (C) 2016, 2017 Cumulus Networks, Inc.
*/
#ifndef _ZEBRA_VXLAN_H
#define _ZEBRA_VXLAN_H
#include <zebra.h>
#include <zebra/zebra_router.h>
#include "linklist.h"
#include "if.h"
#include "vlan.h"
#include "vxlan.h"
#include "lib/json.h"
#include "zebra/zebra_vrf.h"
#include "zebra/zserv.h"
#include "zebra/zebra_dplane.h"
#include "zebra/interface.h"
#ifdef __cplusplus
extern "C" {
#endif
/* Is EVPN enabled? */
#define EVPN_ENABLED(zvrf) (zvrf)->advertise_all_vni
static inline int is_evpn_enabled(void)
{
return EVPN_ENABLED(zebra_vrf_get_evpn());
}
static inline int
is_vxlan_flooding_head_end(void)
{
struct zebra_vrf *zvrf = zebra_vrf_get_evpn();
return (zvrf->vxlan_flood_ctrl == VXLAN_FLOOD_HEAD_END_REPL);
}
/* VxLAN interface change flags of interest. */
#define ZEBRA_VXLIF_LOCAL_IP_CHANGE (1 << 0)
#define ZEBRA_VXLIF_MASTER_CHANGE (1 << 1)
#define ZEBRA_VXLIF_VLAN_CHANGE (1 << 2)
#define ZEBRA_VXLIF_MCAST_GRP_CHANGE (1 << 3)
#define ZEBRA_VXLIF_MASTER_MAC_CHANGE (1 << 4)
#define ZEBRA_VXLIF_VNI_UPDATE(__flags) \
((__flags) & (ZEBRA_VXLIF_VLAN_CHANGE | ZEBRA_VXLIF_MCAST_GRP_CHANGE))
#define ZEBRA_VXLIF_UPDATE(__flags) \
((__flags) & (ZEBRA_VXLIF_LOCAL_IP_CHANGE | ZEBRA_VXLIF_MASTER_CHANGE))
#define VNI_STR_LEN 32
/* ZAPI message handlers */
extern void zebra_vxlan_remote_macip_add(ZAPI_HANDLER_ARGS);
extern void zebra_vxlan_remote_macip_del(ZAPI_HANDLER_ARGS);
extern void zebra_vxlan_remote_vtep_add_zapi(ZAPI_HANDLER_ARGS);
extern void zebra_vxlan_remote_vtep_del_zapi(ZAPI_HANDLER_ARGS);
void zebra_vxlan_remote_vtep_add(vrf_id_t vrf_id, vni_t vni,
struct in_addr vtep_ip, int flood_control);
extern void zebra_vxlan_remote_vtep_del(vrf_id_t vrf_id, vni_t vni,
struct in_addr vtep_ip);
extern void zebra_vxlan_flood_control(ZAPI_HANDLER_ARGS);
extern void zebra_vxlan_advertise_subnet(ZAPI_HANDLER_ARGS);
extern void zebra_vxlan_advertise_svi_macip(ZAPI_HANDLER_ARGS);
extern void zebra_vxlan_advertise_gw_macip(ZAPI_HANDLER_ARGS);
extern void zebra_vxlan_advertise_all_vni(ZAPI_HANDLER_ARGS);
extern void zebra_vxlan_dup_addr_detection(ZAPI_HANDLER_ARGS);
extern void zebra_vxlan_sg_replay(ZAPI_HANDLER_ARGS);
extern int is_l3vni_for_prefix_routes_only(vni_t vni);
extern ifindex_t get_l3vni_svi_ifindex(vrf_id_t vrf_id);
extern ifindex_t get_l3vni_vxlan_ifindex(vrf_id_t vrf_id);
extern vni_t get_l3vni_vni(vrf_id_t vrf_id);
extern bool is_vrf_l3vni_svd_backed(vrf_id_t vrf_id);
extern int zebra_vxlan_vrf_delete(struct zebra_vrf *zvrf);
extern int zebra_vxlan_vrf_enable(struct zebra_vrf *zvrf);
extern int zebra_vxlan_vrf_disable(struct zebra_vrf *zvrf);
extern int zebra_vxlan_vrf_delete(struct zebra_vrf *zvrf);
extern void zebra_vxlan_print_specific_nh_l3vni(struct vty *vty, vni_t l3vni,
struct ipaddr *ip, bool uj);
extern void zebra_vxlan_print_evpn(struct vty *vty, bool uj);
extern void zebra_vxlan_print_specific_rmac_l3vni(struct vty *vty, vni_t l3vni,
struct ethaddr *rmac,
bool use_json);
extern void zebra_vxlan_print_macs_vni(struct vty *vty, struct zebra_vrf *zvrf,
vni_t vni, bool use_json, bool detail);
extern void zebra_vxlan_print_macs_all_vni(struct vty *vty,
struct zebra_vrf *zvrf,
bool print_dup,
bool use_json);
extern void zebra_vxlan_print_macs_all_vni_detail(struct vty *vty,
struct zebra_vrf *zvrf,
bool print_dup,
bool use_json);
extern void zebra_vxlan_print_macs_all_vni_vtep(struct vty *vty,
struct zebra_vrf *zvrf,
struct in_addr vtep_ip,
bool use_json);
extern void zebra_vxlan_print_specific_mac_vni(struct vty *vty,
struct zebra_vrf *zvrf,
vni_t vni, struct ethaddr *mac,
bool use_json);
extern void zebra_vxlan_print_macs_vni_vtep(struct vty *vty,
struct zebra_vrf *zvrf, vni_t vni,
struct in_addr vtep_ip,
bool use_json);
extern void zebra_vxlan_print_macs_vni_dad(struct vty *vty,
struct zebra_vrf *zvrf, vni_t vni,
bool use_json);
extern void zebra_vxlan_print_neigh_vni(struct vty *vty, struct zebra_vrf *zvrf,
vni_t vni, bool use_json);
extern void zebra_vxlan_print_neigh_all_vni(struct vty *vty,
struct zebra_vrf *zvrf,
bool print_dup,
bool use_json);
extern void zebra_vxlan_print_neigh_all_vni_detail(struct vty *vty,
struct zebra_vrf *zvrf,
bool print_dup,
bool use_json);
extern void zebra_vxlan_print_specific_neigh_vni(struct vty *vty,
struct zebra_vrf *zvrf,
vni_t vni, struct ipaddr *ip,
bool use_json);
extern void zebra_vxlan_print_neigh_vni_vtep(struct vty *vty,
struct zebra_vrf *zvrf, vni_t vni,
struct in_addr vtep_ip,
bool use_json);
extern void zebra_vxlan_print_neigh_vni_dad(struct vty *vty,
struct zebra_vrf *zvrf, vni_t vni,
bool use_json);
extern void zebra_vxlan_print_vni(struct vty *vty, struct zebra_vrf *zvrf,
vni_t vni, bool use_json,
json_object *json_array);
extern void zebra_vxlan_print_vnis(struct vty *vty, struct zebra_vrf *zvrf,
bool use_json);
extern void zebra_vxlan_print_vnis_detail(struct vty *vty,
struct zebra_vrf *zvrf,
bool use_json);
extern void zebra_vxlan_print_rmacs_l3vni(struct vty *vty, vni_t vni,
bool use_json);
extern void zebra_vxlan_print_rmacs_all_l3vni(struct vty *vty, bool use_json);
extern void zebra_vxlan_print_nh_l3vni(struct vty *vty, vni_t vni,
bool use_json);
extern void zebra_vxlan_print_nh_svd(struct vty *vty, bool use_json);
extern void zebra_vxlan_print_nh_all_l3vni(struct vty *vty, bool use_json);
extern void zebra_vxlan_print_l3vni(struct vty *vty, vni_t vni, bool use_json);
extern void zebra_vxlan_print_vrf_vni(struct vty *vty, struct zebra_vrf *zvrf,
json_object *json_vrfs);
extern int zebra_vxlan_add_del_gw_macip(struct interface *ifp,
const struct prefix *p, int add);
extern int zebra_vxlan_svi_up(struct interface *ifp, struct interface *link_if);
extern int zebra_vxlan_svi_down(struct interface *ifp,
struct interface *link_if);
extern int zebra_vxlan_handle_kernel_neigh_update(
struct interface *ifp, struct interface *link_if, struct ipaddr *ip,
struct ethaddr *macaddr, uint16_t state, bool is_ext,
bool is_router, bool local_inactive, bool dp_static);
extern int zebra_vxlan_handle_kernel_neigh_del(struct interface *ifp,
struct interface *link_if,
struct ipaddr *ip);
extern int zebra_vxlan_local_mac_add_update(struct interface *ifp,
struct interface *br_if,
struct ethaddr *mac, vlanid_t vid,
bool sticky, bool local_inactive,
bool dp_static);
extern int zebra_vxlan_local_mac_del(struct interface *ifp,
struct interface *br_if,
struct ethaddr *mac, vlanid_t vid);
extern int zebra_vxlan_check_readd_vtep(struct interface *ifp, vni_t vni,
struct in_addr vtep_ip);
extern int zebra_vxlan_if_up(struct interface *ifp);
extern int zebra_vxlan_if_down(struct interface *ifp);
extern int zebra_vxlan_if_add(struct interface *ifp);
extern int zebra_vxlan_if_update(struct interface *ifp,
struct zebra_vxlan_if_update_ctx *ctx);
extern int zebra_vxlan_if_del(struct interface *ifp);
extern void zebra_vxlan_process_vrf_vni_cmd(struct zebra_vrf *zvrf, vni_t vni,
int filter, int add);
extern void zebra_vxlan_init_tables(struct zebra_vrf *zvrf);
extern void zebra_vxlan_close_tables(struct zebra_vrf *);
extern void zebra_vxlan_cleanup_tables(struct zebra_vrf *);
extern void zebra_vxlan_init(void);
extern void zebra_vxlan_terminate(void);
extern void zebra_vxlan_disable(void);
extern void zebra_vxlan_evpn_vrf_route_add(vrf_id_t vrf_id,
const struct ethaddr *rmac,
const struct ipaddr *ip,
const struct prefix *host_prefix);
extern void zebra_vxlan_evpn_vrf_route_del(vrf_id_t vrf_id,
struct ipaddr *vtep_ip,
struct prefix *host_prefix);
extern int zebra_vxlan_clear_dup_detect_vni_mac(struct zebra_vrf *zvrf,
vni_t vni,
struct ethaddr *macaddr,
char *errmsg,
size_t errmsg_len);
extern int zebra_vxlan_clear_dup_detect_vni_ip(struct zebra_vrf *zvrf,
vni_t vni, struct ipaddr *ip,
char *errmsg, size_t errmsg_len);
extern int zebra_vxlan_clear_dup_detect_vni_all(struct zebra_vrf *zvrf);
extern int zebra_vxlan_clear_dup_detect_vni(struct zebra_vrf *zvrf, vni_t vni);
extern void zebra_vxlan_handle_result(struct zebra_dplane_ctx *ctx);
extern void zebra_evpn_init(void);
extern void zebra_vxlan_macvlan_up(struct interface *ifp);
extern void zebra_vxlan_macvlan_down(struct interface *ifp);
extern int vni_list_cmp(void *p1, void *p2);
extern int zebra_vxlan_dp_network_mac_add(struct interface *ifp,
struct interface *br_if,
struct ethaddr *macaddr, vlanid_t vid,
vni_t vni, uint32_t nhg_id,
bool sticky, bool dp_static);
extern int zebra_vxlan_dp_network_mac_del(struct interface *ifp,
struct interface *br_if,
struct ethaddr *macaddr, vlanid_t vid,
vni_t vni);
extern void zebra_vxlan_set_accept_bgp_seq(bool set);
extern bool zebra_vxlan_get_accept_bgp_seq(void);
extern void zebra_vlan_dplane_result(struct zebra_dplane_ctx *ctx);
#ifdef __cplusplus
}
#endif
#endif /* _ZEBRA_VXLAN_H */
View git blame Copy permalink