frr/zebra/zebra_router.c

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

359 lines
9.4 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/* Zebra Router Code.
* Copyright (C) 2018 Cumulus Networks, Inc.
* Donald Sharp
*/
#include "zebra.h"
#include <pthread.h>
#include "lib/frratomic.h"
#include "zebra_router.h"
#include "zebra_pbr.h"
#include "zebra_vxlan.h"
#include "zebra_mlag.h"
#include "zebra_nhg.h"
#include "zebra_neigh.h"
#include "zebra/zebra_tc.h"
#include "debug.h"
#include "zebra_script.h"
zebra: Bring up 514 BGP neighbor sessions Issue: When 514 inerfaces/neighbors are configured, it creates socket error, "Cannot allocate memory", when back to back V6 RA messages are tried to be sent over the socket. This prevents interface, to know its peer's link local address. Socket error comes when 1) try to join ICMPv6 all router multicast group, back to back for all interfaces 2)send back to back RA for all interfaces Fix: 1)For ICMPv6 join case, we check if the interface has already joined all router group, if not try to join. On failure, retry joining after random amount of time determined 1 ms to ICMPV6_JOIN_TIMER_EXP_MS(100 ms) 2) For RA issue case, batch sending of RA mesages using wheel timer Testing: Monitor BGP session running sh bgp summary command Before fix: r1# sh bgp summary IPv4 Unicast Summary: BGP router identifier 192.168.1.1, local AS number 1001 VRF default vrf-id 0 BGP table version 0 RIB entries 0, using 0 bytes of memory Peers 515, using 12 MiB of memory Neighbor V AS MsgRcvd MsgSent TblVer InQ OutQ Up/Down State/PfxRcd PfxSnt Desc r1-eth0 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth1 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth2 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth3 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth4 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth5 4 1002 89 90 0 0 0 00:07:10 0 0 N/A …..<snip>... r1-eth252 4 1002 31 29 0 0 0 00:02:08 0 0 N/A r1-eth253 4 1002 31 29 0 0 0 00:02:08 0 0 N/A r1-eth254 4 1002 31 29 0 0 0 00:02:08 0 0 N/A r1-eth255 4 1002 31 29 0 0 0 00:02:08 0 0 N/A r1-eth256 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth257 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth258 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth259 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth260 4 0 0 0 0 0 0 never Idle 0 N/A ……..<snip>….. r1-eth511 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth512 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth513 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth514 4 0 0 0 0 0 0 never Idle 0 N/A After fix: r1# show bgp summary IPv4 Unicast Summary: BGP router identifier 192.168.1.1, local AS number 1001 VRF default vrf-id 0 BGP table version 0 RIB entries 0, using 0 bytes of memory Peers 515, using 12 MiB of memory Neighbor V AS MsgRcvd MsgSent TblVer InQ OutQ Up/Down State/PfxRcd PfxSnt Desc r1-eth0 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth1 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth2 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth3 4 1002 64 67 0 0 0 00:05:09 0 0 N/A r1-eth4 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth5 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth6 4 1002 67 70 0 0 0 00:05:22 0 0 N/A r1-eth7 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth8 4 1002 87 87 0 0 0 00:07:04 0 0 N/A .... r1-eth499 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth500 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth501 4 1002 19 22 0 0 0 00:01:21 0 0 N/A r1-eth502 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth503 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth504 4 1002 20 23 0 0 0 00:01:30 0 0 N/A r1-eth505 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth506 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth507 4 1002 22 25 0 0 0 00:01:39 0 0 N/A r1-eth508 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth509 4 1002 17 20 0 0 0 00:01:13 0 0 N/A r1-eth510 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth511 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth512 4 1002 19 22 0 0 0 00:01:22 0 0 N/A r1-eth513 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth514 4 1002 43 43 0 0 0 00:03:22 0 0 N/A Signed-off-by: Soumya Roy <souroy@nvidia.com>
2025-02-15 03:13:37 +01:00
#include "wheel.h"
DEFINE_MTYPE_STATIC(ZEBRA, RIB_TABLE_INFO, "RIB table info");
DEFINE_MTYPE_STATIC(ZEBRA, ZEBRA_RT_TABLE, "Zebra VRF table");
struct zebra_router zrouter = {
.multipath_num = MULTIPATH_NUM,
};
static inline int
zebra_router_table_entry_compare(const struct zebra_router_table *e1,
const struct zebra_router_table *e2);
RB_GENERATE(zebra_router_table_head, zebra_router_table,
zebra_router_table_entry, zebra_router_table_entry_compare);
static inline int
zebra_router_table_entry_compare(const struct zebra_router_table *e1,
const struct zebra_router_table *e2)
{
if (e1->tableid < e2->tableid)
return -1;
if (e1->tableid > e2->tableid)
return 1;
if (e1->ns_id < e2->ns_id)
return -1;
if (e1->ns_id > e2->ns_id)
return 1;
if (e1->afi < e2->afi)
return -1;
if (e1->afi > e2->afi)
return 1;
return (e1->safi - e2->safi);
}
struct zebra_router_table *zebra_router_find_zrt(struct zebra_vrf *zvrf,
uint32_t tableid, afi_t afi,
safi_t safi)
{
struct zebra_router_table finder;
struct zebra_router_table *zrt;
memset(&finder, 0, sizeof(finder));
finder.afi = afi;
finder.safi = safi;
finder.tableid = tableid;
finder.ns_id = zvrf->zns->ns_id;
zrt = RB_FIND(zebra_router_table_head, &zrouter.tables, &finder);
return zrt;
}
struct zebra_router_table *zebra_router_find_next_zrt(struct zebra_vrf *zvrf,
uint32_t tableid,
afi_t afi, safi_t safi)
{
struct zebra_router_table finder;
struct zebra_router_table *zrt;
memset(&finder, 0, sizeof(finder));
finder.afi = afi;
finder.safi = safi;
finder.tableid = tableid;
finder.ns_id = zvrf->zns->ns_id;
zrt = RB_NFIND(zebra_router_table_head, &zrouter.tables, &finder);
if (zrt->afi == afi && zrt->safi == safi && zrt->tableid == tableid &&
zrt->ns_id == finder.ns_id)
zrt = RB_NEXT(zebra_router_table_head, zrt);
return zrt;
}
struct route_table *zebra_router_find_table(struct zebra_vrf *zvrf,
uint32_t tableid, afi_t afi,
safi_t safi)
{
struct zebra_router_table finder;
struct zebra_router_table *zrt;
memset(&finder, 0, sizeof(finder));
finder.afi = afi;
finder.safi = safi;
finder.tableid = tableid;
finder.ns_id = zvrf->zns->ns_id;
zrt = RB_FIND(zebra_router_table_head, &zrouter.tables, &finder);
if (zrt)
return zrt->table;
else
return NULL;
}
struct route_table *zebra_router_get_table(struct zebra_vrf *zvrf,
uint32_t tableid, afi_t afi,
safi_t safi)
{
struct zebra_router_table finder;
struct zebra_router_table *zrt;
struct rib_table_info *info;
memset(&finder, 0, sizeof(finder));
finder.afi = afi;
finder.safi = safi;
finder.tableid = tableid;
finder.ns_id = zvrf->zns->ns_id;
zrt = RB_FIND(zebra_router_table_head, &zrouter.tables, &finder);
if (zrt)
return zrt->table;
zrt = XCALLOC(MTYPE_ZEBRA_RT_TABLE, sizeof(*zrt));
zrt->tableid = tableid;
zrt->afi = afi;
zrt->safi = safi;
zrt->ns_id = zvrf->zns->ns_id;
zrt->table =
(afi == AFI_IP6) ? srcdest_table_init() : route_table_init();
info = XCALLOC(MTYPE_RIB_TABLE_INFO, sizeof(*info));
info->zvrf = zvrf;
info->afi = afi;
info->safi = safi;
info->table_id = tableid;
route_table_set_info(zrt->table, info);
zrt->table->cleanup = zebra_rtable_node_cleanup;
RB_INSERT(zebra_router_table_head, &zrouter.tables, zrt);
return zrt->table;
}
void zebra_router_show_table_summary(struct vty *vty)
{
struct zebra_router_table *zrt;
vty_out(vty,
"VRF NS ID VRF ID AFI SAFI Table Count\n");
vty_out(vty,
"---------------------------------------------------------------------------\n");
RB_FOREACH (zrt, zebra_router_table_head, &zrouter.tables) {
struct rib_table_info *info = route_table_get_info(zrt->table);
vty_out(vty, "%-16s%5d %9d %7s %15s %8d %10lu\n", info->zvrf->vrf->name,
zrt->ns_id, info->zvrf->vrf->vrf_id,
afi2str(zrt->afi), safi2str(zrt->safi),
zrt->tableid,
zrt->table->count);
}
}
void zebra_router_sweep_route(void)
{
struct zebra_router_table *zrt;
RB_FOREACH (zrt, zebra_router_table_head, &zrouter.tables) {
if (zrt->ns_id != NS_DEFAULT)
continue;
rib_sweep_table(zrt->table);
}
}
void zebra_router_sweep_nhgs(void)
{
zebra_nhg_sweep_table(zrouter.nhgs_id);
}
static void zebra_router_free_table(struct zebra_router_table *zrt)
{
void *table_info;
table_info = route_table_get_info(zrt->table);
route_table_finish(zrt->table);
zebra: Upon vrf deletion, actually release this data. When a vrf is deleted we need to tell the zebra_router that we have finished using the tables we are keeping track of. This will allow us to properly cleanup the data structures associated with them. This fixes this valgrind error found: ==8579== Invalid read of size 8 ==8579== at 0x430034: zvrf_id (zebra_vrf.h:167) ==8579== by 0x432366: rib_process (zebra_rib.c:1580) ==8579== by 0x432366: process_subq (zebra_rib.c:2092) ==8579== by 0x432366: meta_queue_process (zebra_rib.c:2188) ==8579== by 0x48C99FE: work_queue_run (workqueue.c:291) ==8579== by 0x48C3788: thread_call (thread.c:1607) ==8579== by 0x48A2E9E: frr_run (libfrr.c:1011) ==8579== by 0x41316A: main (main.c:473) ==8579== Address 0x5aeb750 is 0 bytes inside a block of size 4,424 free'd ==8579== at 0x4839A0C: free (vg_replace_malloc.c:540) ==8579== by 0x438914: zebra_vrf_delete (zebra_vrf.c:279) ==8579== by 0x48C4225: vrf_delete (vrf.c:243) ==8579== by 0x48C4225: vrf_delete (vrf.c:217) ==8579== by 0x4151CE: netlink_vrf_change (if_netlink.c:364) ==8579== by 0x416810: netlink_link_change (if_netlink.c:1189) ==8579== by 0x41C1FC: netlink_parse_info (kernel_netlink.c:904) ==8579== by 0x41C2D3: kernel_read (kernel_netlink.c:389) ==8579== by 0x48C3788: thread_call (thread.c:1607) ==8579== by 0x48A2E9E: frr_run (libfrr.c:1011) ==8579== by 0x41316A: main (main.c:473) ==8579== Block was alloc'd at ==8579== at 0x483AB1A: calloc (vg_replace_malloc.c:762) ==8579== by 0x48A6030: qcalloc (memory.c:110) ==8579== by 0x4389EF: zebra_vrf_alloc (zebra_vrf.c:382) ==8579== by 0x438A42: zebra_vrf_new (zebra_vrf.c:93) ==8579== by 0x48C40AD: vrf_get (vrf.c:209) ==8579== by 0x415144: netlink_vrf_change (if_netlink.c:319) ==8579== by 0x415E90: netlink_interface (if_netlink.c:653) ==8579== by 0x41C1FC: netlink_parse_info (kernel_netlink.c:904) ==8579== by 0x4163E8: interface_lookup_netlink (if_netlink.c:760) ==8579== by 0x42BB37: zebra_ns_enable (zebra_ns.c:130) ==8579== by 0x42BC5E: zebra_ns_init (zebra_ns.c:208) ==8579== by 0x4130F4: main (main.c:401) This can be found by: `ip link del <VRF DEVICE NAME>` then `ip link add <NAME> type vrf table X` again and then attempting to use the vrf. Signed-off-by: Donald Sharp <sharpd@cumulusnetworks.com>
2019-02-28 15:11:41 +01:00
RB_REMOVE(zebra_router_table_head, &zrouter.tables, zrt);
XFREE(MTYPE_RIB_TABLE_INFO, table_info);
XFREE(MTYPE_ZEBRA_RT_TABLE, zrt);
}
zebra: Upon vrf deletion, actually release this data. When a vrf is deleted we need to tell the zebra_router that we have finished using the tables we are keeping track of. This will allow us to properly cleanup the data structures associated with them. This fixes this valgrind error found: ==8579== Invalid read of size 8 ==8579== at 0x430034: zvrf_id (zebra_vrf.h:167) ==8579== by 0x432366: rib_process (zebra_rib.c:1580) ==8579== by 0x432366: process_subq (zebra_rib.c:2092) ==8579== by 0x432366: meta_queue_process (zebra_rib.c:2188) ==8579== by 0x48C99FE: work_queue_run (workqueue.c:291) ==8579== by 0x48C3788: thread_call (thread.c:1607) ==8579== by 0x48A2E9E: frr_run (libfrr.c:1011) ==8579== by 0x41316A: main (main.c:473) ==8579== Address 0x5aeb750 is 0 bytes inside a block of size 4,424 free'd ==8579== at 0x4839A0C: free (vg_replace_malloc.c:540) ==8579== by 0x438914: zebra_vrf_delete (zebra_vrf.c:279) ==8579== by 0x48C4225: vrf_delete (vrf.c:243) ==8579== by 0x48C4225: vrf_delete (vrf.c:217) ==8579== by 0x4151CE: netlink_vrf_change (if_netlink.c:364) ==8579== by 0x416810: netlink_link_change (if_netlink.c:1189) ==8579== by 0x41C1FC: netlink_parse_info (kernel_netlink.c:904) ==8579== by 0x41C2D3: kernel_read (kernel_netlink.c:389) ==8579== by 0x48C3788: thread_call (thread.c:1607) ==8579== by 0x48A2E9E: frr_run (libfrr.c:1011) ==8579== by 0x41316A: main (main.c:473) ==8579== Block was alloc'd at ==8579== at 0x483AB1A: calloc (vg_replace_malloc.c:762) ==8579== by 0x48A6030: qcalloc (memory.c:110) ==8579== by 0x4389EF: zebra_vrf_alloc (zebra_vrf.c:382) ==8579== by 0x438A42: zebra_vrf_new (zebra_vrf.c:93) ==8579== by 0x48C40AD: vrf_get (vrf.c:209) ==8579== by 0x415144: netlink_vrf_change (if_netlink.c:319) ==8579== by 0x415E90: netlink_interface (if_netlink.c:653) ==8579== by 0x41C1FC: netlink_parse_info (kernel_netlink.c:904) ==8579== by 0x4163E8: interface_lookup_netlink (if_netlink.c:760) ==8579== by 0x42BB37: zebra_ns_enable (zebra_ns.c:130) ==8579== by 0x42BC5E: zebra_ns_init (zebra_ns.c:208) ==8579== by 0x4130F4: main (main.c:401) This can be found by: `ip link del <VRF DEVICE NAME>` then `ip link add <NAME> type vrf table X` again and then attempting to use the vrf. Signed-off-by: Donald Sharp <sharpd@cumulusnetworks.com>
2019-02-28 15:11:41 +01:00
void zebra_router_release_table(struct zebra_vrf *zvrf, uint32_t tableid,
afi_t afi, safi_t safi)
{
struct zebra_router_table finder;
struct zebra_router_table *zrt;
memset(&finder, 0, sizeof(finder));
finder.afi = afi;
finder.safi = safi;
finder.tableid = tableid;
finder.ns_id = zvrf->zns->ns_id;
zrt = RB_FIND(zebra_router_table_head, &zrouter.tables, &finder);
if (!zrt)
return;
zebra_router_free_table(zrt);
}
uint32_t zebra_router_get_next_sequence(void)
{
return 1
+ atomic_fetch_add_explicit(&zrouter.sequence_num, 1,
memory_order_relaxed);
}
zebra: Bring up 514 BGP neighbor sessions Issue: When 514 inerfaces/neighbors are configured, it creates socket error, "Cannot allocate memory", when back to back V6 RA messages are tried to be sent over the socket. This prevents interface, to know its peer's link local address. Socket error comes when 1) try to join ICMPv6 all router multicast group, back to back for all interfaces 2)send back to back RA for all interfaces Fix: 1)For ICMPv6 join case, we check if the interface has already joined all router group, if not try to join. On failure, retry joining after random amount of time determined 1 ms to ICMPV6_JOIN_TIMER_EXP_MS(100 ms) 2) For RA issue case, batch sending of RA mesages using wheel timer Testing: Monitor BGP session running sh bgp summary command Before fix: r1# sh bgp summary IPv4 Unicast Summary: BGP router identifier 192.168.1.1, local AS number 1001 VRF default vrf-id 0 BGP table version 0 RIB entries 0, using 0 bytes of memory Peers 515, using 12 MiB of memory Neighbor V AS MsgRcvd MsgSent TblVer InQ OutQ Up/Down State/PfxRcd PfxSnt Desc r1-eth0 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth1 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth2 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth3 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth4 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth5 4 1002 89 90 0 0 0 00:07:10 0 0 N/A …..<snip>... r1-eth252 4 1002 31 29 0 0 0 00:02:08 0 0 N/A r1-eth253 4 1002 31 29 0 0 0 00:02:08 0 0 N/A r1-eth254 4 1002 31 29 0 0 0 00:02:08 0 0 N/A r1-eth255 4 1002 31 29 0 0 0 00:02:08 0 0 N/A r1-eth256 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth257 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth258 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth259 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth260 4 0 0 0 0 0 0 never Idle 0 N/A ……..<snip>….. r1-eth511 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth512 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth513 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth514 4 0 0 0 0 0 0 never Idle 0 N/A After fix: r1# show bgp summary IPv4 Unicast Summary: BGP router identifier 192.168.1.1, local AS number 1001 VRF default vrf-id 0 BGP table version 0 RIB entries 0, using 0 bytes of memory Peers 515, using 12 MiB of memory Neighbor V AS MsgRcvd MsgSent TblVer InQ OutQ Up/Down State/PfxRcd PfxSnt Desc r1-eth0 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth1 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth2 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth3 4 1002 64 67 0 0 0 00:05:09 0 0 N/A r1-eth4 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth5 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth6 4 1002 67 70 0 0 0 00:05:22 0 0 N/A r1-eth7 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth8 4 1002 87 87 0 0 0 00:07:04 0 0 N/A .... r1-eth499 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth500 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth501 4 1002 19 22 0 0 0 00:01:21 0 0 N/A r1-eth502 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth503 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth504 4 1002 20 23 0 0 0 00:01:30 0 0 N/A r1-eth505 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth506 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth507 4 1002 22 25 0 0 0 00:01:39 0 0 N/A r1-eth508 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth509 4 1002 17 20 0 0 0 00:01:13 0 0 N/A r1-eth510 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth511 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth512 4 1002 19 22 0 0 0 00:01:22 0 0 N/A r1-eth513 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth514 4 1002 43 43 0 0 0 00:03:22 0 0 N/A Signed-off-by: Soumya Roy <souroy@nvidia.com>
2025-02-15 03:13:37 +01:00
static inline unsigned int interface_hash_key(const void *arg)
{
const struct interface *ifp = arg;
return ifp->ifindex;
}
void zebra_router_terminate(void)
{
struct zebra_router_table *zrt, *tmp;
zebra: Bring up 514 BGP neighbor sessions Issue: When 514 inerfaces/neighbors are configured, it creates socket error, "Cannot allocate memory", when back to back V6 RA messages are tried to be sent over the socket. This prevents interface, to know its peer's link local address. Socket error comes when 1) try to join ICMPv6 all router multicast group, back to back for all interfaces 2)send back to back RA for all interfaces Fix: 1)For ICMPv6 join case, we check if the interface has already joined all router group, if not try to join. On failure, retry joining after random amount of time determined 1 ms to ICMPV6_JOIN_TIMER_EXP_MS(100 ms) 2) For RA issue case, batch sending of RA mesages using wheel timer Testing: Monitor BGP session running sh bgp summary command Before fix: r1# sh bgp summary IPv4 Unicast Summary: BGP router identifier 192.168.1.1, local AS number 1001 VRF default vrf-id 0 BGP table version 0 RIB entries 0, using 0 bytes of memory Peers 515, using 12 MiB of memory Neighbor V AS MsgRcvd MsgSent TblVer InQ OutQ Up/Down State/PfxRcd PfxSnt Desc r1-eth0 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth1 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth2 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth3 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth4 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth5 4 1002 89 90 0 0 0 00:07:10 0 0 N/A …..<snip>... r1-eth252 4 1002 31 29 0 0 0 00:02:08 0 0 N/A r1-eth253 4 1002 31 29 0 0 0 00:02:08 0 0 N/A r1-eth254 4 1002 31 29 0 0 0 00:02:08 0 0 N/A r1-eth255 4 1002 31 29 0 0 0 00:02:08 0 0 N/A r1-eth256 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth257 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth258 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth259 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth260 4 0 0 0 0 0 0 never Idle 0 N/A ……..<snip>….. r1-eth511 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth512 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth513 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth514 4 0 0 0 0 0 0 never Idle 0 N/A After fix: r1# show bgp summary IPv4 Unicast Summary: BGP router identifier 192.168.1.1, local AS number 1001 VRF default vrf-id 0 BGP table version 0 RIB entries 0, using 0 bytes of memory Peers 515, using 12 MiB of memory Neighbor V AS MsgRcvd MsgSent TblVer InQ OutQ Up/Down State/PfxRcd PfxSnt Desc r1-eth0 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth1 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth2 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth3 4 1002 64 67 0 0 0 00:05:09 0 0 N/A r1-eth4 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth5 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth6 4 1002 67 70 0 0 0 00:05:22 0 0 N/A r1-eth7 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth8 4 1002 87 87 0 0 0 00:07:04 0 0 N/A .... r1-eth499 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth500 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth501 4 1002 19 22 0 0 0 00:01:21 0 0 N/A r1-eth502 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth503 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth504 4 1002 20 23 0 0 0 00:01:30 0 0 N/A r1-eth505 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth506 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth507 4 1002 22 25 0 0 0 00:01:39 0 0 N/A r1-eth508 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth509 4 1002 17 20 0 0 0 00:01:13 0 0 N/A r1-eth510 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth511 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth512 4 1002 19 22 0 0 0 00:01:22 0 0 N/A r1-eth513 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth514 4 1002 43 43 0 0 0 00:03:22 0 0 N/A Signed-off-by: Soumya Roy <souroy@nvidia.com>
2025-02-15 03:13:37 +01:00
if (zrouter.ra_wheel) {
wheel_delete(zrouter.ra_wheel);
zrouter.ra_wheel = NULL;
}
EVENT_OFF(zrouter.t_rib_sweep);
RB_FOREACH_SAFE (zrt, zebra_router_table_head, &zrouter.tables, tmp)
zebra_router_free_table(zrt);
work_queue_free_and_null(&zrouter.ribq);
meta_queue_free(zrouter.mq, NULL);
zebra_vxlan_disable();
zebra_mlag_terminate();
zebra_neigh_terminate();
2020-04-01 21:31:40 +02:00
/* Free NHE in ID table only since it has unhashable entries as well */
hash_iterate(zrouter.nhgs_id, zebra_nhg_hash_free_zero_id, NULL);
hash_clean_and_free(&zrouter.nhgs_id, zebra_nhg_hash_free);
hash_clean_and_free(&zrouter.nhgs, NULL);
hash_clean_and_free(&zrouter.rules_hash, zebra_pbr_rules_free);
hash_clean_and_free(&zrouter.ipset_entry_hash,
zebra_pbr_ipset_entry_free);
hash_clean_and_free(&zrouter.ipset_hash, zebra_pbr_ipset_free);
hash_clean_and_free(&zrouter.iptable_hash, zebra_pbr_iptable_free);
zebra: Set Free Functions for Traffic Control Hash Tables Configure hash table cleanup with specific free functions for `zrouter.filter_hash`, `zrouter.qdisc_hash`, and `zrouter.class_hash`. This ensures proper memory cleanup, addressing memory leaks. The ASan leak log for reference: ``` *********************************************************************************** Address Sanitizer Error detected in tc_basic.test_tc_basic/r1.asan.zebra.15495 ================================================================= ==15495==ERROR: LeakSanitizer: detected memory leaks Direct leak of 176 byte(s) in 1 object(s) allocated from: #0 0x7fd5660ffd28 in __interceptor_calloc (/usr/lib/x86_64-linux-gnu/libasan.so.4+0xded28) #1 0x7fd565afe238 in qcalloc lib/memory.c:105 #2 0x5564521c6c9e in tc_filter_alloc_intern zebra/zebra_tc.c:389 #3 0x7fd565ac49e8 in hash_get lib/hash.c:147 #4 0x5564521c7c74 in zebra_tc_filter_add zebra/zebra_tc.c:409 #5 0x55645210755a in zread_tc_filter zebra/zapi_msg.c:3428 #6 0x5564521127c1 in zserv_handle_commands zebra/zapi_msg.c:4004 #7 0x5564522208b2 in zserv_process_messages zebra/zserv.c:520 #8 0x7fd565b9e034 in event_call lib/event.c:1974 #9 0x7fd565ae142b in frr_run lib/libfrr.c:1214 #10 0x5564520c14b1 in main zebra/main.c:492 #11 0x7fd564ec2c86 in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x21c86) Direct leak of 40 byte(s) in 1 object(s) allocated from: #0 0x7fd5660ffd28 in __interceptor_calloc (/usr/lib/x86_64-linux-gnu/libasan.so.4+0xded28) #1 0x7fd565afe238 in qcalloc lib/memory.c:105 #2 0x5564521c6c6e in tc_class_alloc_intern zebra/zebra_tc.c:239 #3 0x7fd565ac49e8 in hash_get lib/hash.c:147 #4 0x5564521c784f in zebra_tc_class_add zebra/zebra_tc.c:293 #5 0x556452107ce5 in zread_tc_class zebra/zapi_msg.c:3315 #6 0x5564521127c1 in zserv_handle_commands zebra/zapi_msg.c:4004 #7 0x5564522208b2 in zserv_process_messages zebra/zserv.c:520 #8 0x7fd565b9e034 in event_call lib/event.c:1974 #9 0x7fd565ae142b in frr_run lib/libfrr.c:1214 #10 0x5564520c14b1 in main zebra/main.c:492 #11 0x7fd564ec2c86 in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x21c86) Direct leak of 12 byte(s) in 1 object(s) allocated from: #0 0x7fd5660ffd28 in __interceptor_calloc (/usr/lib/x86_64-linux-gnu/libasan.so.4+0xded28) #1 0x7fd565afe238 in qcalloc lib/memory.c:105 #2 0x5564521c6c3e in tc_qdisc_alloc_intern zebra/zebra_tc.c:128 #3 0x7fd565ac49e8 in hash_get lib/hash.c:147 #4 0x5564521c753b in zebra_tc_qdisc_install zebra/zebra_tc.c:184 #5 0x556452108203 in zread_tc_qdisc zebra/zapi_msg.c:3286 #6 0x5564521127c1 in zserv_handle_commands zebra/zapi_msg.c:4004 #7 0x5564522208b2 in zserv_process_messages zebra/zserv.c:520 #8 0x7fd565b9e034 in event_call lib/event.c:1974 #9 0x7fd565ae142b in frr_run lib/libfrr.c:1214 #10 0x5564520c14b1 in main zebra/main.c:492 #11 0x7fd564ec2c86 in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x21c86) SUMMARY: AddressSanitizer: 228 byte(s) leaked in 3 allocation(s). *********************************************************************************** ``` Signed-off-by: Keelan Cannoo <keelan.cannoo@icloud.com>
2023-11-29 13:33:54 +01:00
hash_clean_and_free(&zrouter.filter_hash, (void (*)(void *)) zebra_tc_filter_free);
hash_clean_and_free(&zrouter.qdisc_hash, (void (*)(void *)) zebra_tc_qdisc_free);
hash_clean_and_free(&zrouter.class_hash, (void (*)(void *)) zebra_tc_class_free);
#ifdef HAVE_SCRIPTING
zebra_script_destroy();
#endif
zebra_vxlan_terminate();
/* OS-specific deinit */
kernel_router_terminate();
}
bool zebra_router_notify_on_ack(void)
{
return !zrouter.asic_offloaded || zrouter.notify_on_ack;
}
void zebra_router_init(bool asic_offload, bool notify_on_ack,
bool v6_with_v4_nexthop)
{
zrouter.sequence_num = 0;
zrouter.protodown_r_bit = FRR_PROTODOWN_REASON_DEFAULT_BIT;
zrouter.allow_delete = false;
zrouter.packets_to_process = ZEBRA_ZAPI_PACKETS_TO_PROCESS;
zrouter.nhg_keep = ZEBRA_DEFAULT_NHG_KEEP_TIMER;
zebra: Bring up 514 BGP neighbor sessions Issue: When 514 inerfaces/neighbors are configured, it creates socket error, "Cannot allocate memory", when back to back V6 RA messages are tried to be sent over the socket. This prevents interface, to know its peer's link local address. Socket error comes when 1) try to join ICMPv6 all router multicast group, back to back for all interfaces 2)send back to back RA for all interfaces Fix: 1)For ICMPv6 join case, we check if the interface has already joined all router group, if not try to join. On failure, retry joining after random amount of time determined 1 ms to ICMPV6_JOIN_TIMER_EXP_MS(100 ms) 2) For RA issue case, batch sending of RA mesages using wheel timer Testing: Monitor BGP session running sh bgp summary command Before fix: r1# sh bgp summary IPv4 Unicast Summary: BGP router identifier 192.168.1.1, local AS number 1001 VRF default vrf-id 0 BGP table version 0 RIB entries 0, using 0 bytes of memory Peers 515, using 12 MiB of memory Neighbor V AS MsgRcvd MsgSent TblVer InQ OutQ Up/Down State/PfxRcd PfxSnt Desc r1-eth0 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth1 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth2 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth3 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth4 4 1002 89 90 0 0 0 00:07:10 0 0 N/A r1-eth5 4 1002 89 90 0 0 0 00:07:10 0 0 N/A …..<snip>... r1-eth252 4 1002 31 29 0 0 0 00:02:08 0 0 N/A r1-eth253 4 1002 31 29 0 0 0 00:02:08 0 0 N/A r1-eth254 4 1002 31 29 0 0 0 00:02:08 0 0 N/A r1-eth255 4 1002 31 29 0 0 0 00:02:08 0 0 N/A r1-eth256 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth257 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth258 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth259 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth260 4 0 0 0 0 0 0 never Idle 0 N/A ……..<snip>….. r1-eth511 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth512 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth513 4 0 0 0 0 0 0 never Idle 0 N/A r1-eth514 4 0 0 0 0 0 0 never Idle 0 N/A After fix: r1# show bgp summary IPv4 Unicast Summary: BGP router identifier 192.168.1.1, local AS number 1001 VRF default vrf-id 0 BGP table version 0 RIB entries 0, using 0 bytes of memory Peers 515, using 12 MiB of memory Neighbor V AS MsgRcvd MsgSent TblVer InQ OutQ Up/Down State/PfxRcd PfxSnt Desc r1-eth0 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth1 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth2 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth3 4 1002 64 67 0 0 0 00:05:09 0 0 N/A r1-eth4 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth5 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth6 4 1002 67 70 0 0 0 00:05:22 0 0 N/A r1-eth7 4 1002 87 87 0 0 0 00:07:04 0 0 N/A r1-eth8 4 1002 87 87 0 0 0 00:07:04 0 0 N/A .... r1-eth499 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth500 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth501 4 1002 19 22 0 0 0 00:01:21 0 0 N/A r1-eth502 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth503 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth504 4 1002 20 23 0 0 0 00:01:30 0 0 N/A r1-eth505 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth506 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth507 4 1002 22 25 0 0 0 00:01:39 0 0 N/A r1-eth508 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth509 4 1002 17 20 0 0 0 00:01:13 0 0 N/A r1-eth510 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth511 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth512 4 1002 19 22 0 0 0 00:01:22 0 0 N/A r1-eth513 4 1002 43 43 0 0 0 00:03:22 0 0 N/A r1-eth514 4 1002 43 43 0 0 0 00:03:22 0 0 N/A Signed-off-by: Soumya Roy <souroy@nvidia.com>
2025-02-15 03:13:37 +01:00
/*Init V6 RA batching stuffs*/
zrouter.ra_wheel = wheel_init(zrouter.master, RTADV_TIMER_WHEEL_PERIOD_MS,
RTADV_TIMER_WHEEL_SLOTS_NO, interface_hash_key, process_rtadv,
NULL);
zebra_vxlan_init();
zebra_mlag_init();
zebra_neigh_init();
zrouter.rules_hash = hash_create_size(8, zebra_pbr_rules_hash_key,
zebra_pbr_rules_hash_equal,
"Rules Hash");
zrouter.ipset_hash =
hash_create_size(8, zebra_pbr_ipset_hash_key,
zebra_pbr_ipset_hash_equal, "IPset Hash");
zrouter.ipset_entry_hash = hash_create_size(
8, zebra_pbr_ipset_entry_hash_key,
zebra_pbr_ipset_entry_hash_equal, "IPset Hash Entry");
zrouter.iptable_hash = hash_create_size(8, zebra_pbr_iptable_hash_key,
zebra_pbr_iptable_hash_equal,
"IPtable Hash Entry");
zrouter.nhgs =
hash_create_size(8, zebra_nhg_hash_key, zebra_nhg_hash_equal,
"Zebra Router Nexthop Groups");
zrouter.nhgs_id =
hash_create_size(8, zebra_nhg_id_key, zebra_nhg_hash_id_equal,
"Zebra Router Nexthop Groups ID index");
zrouter.qdisc_hash =
hash_create_size(8, zebra_tc_qdisc_hash_key,
zebra_tc_qdisc_hash_equal, "TC (qdisc) Hash");
zrouter.class_hash = hash_create_size(8, zebra_tc_class_hash_key,
zebra_tc_class_hash_equal,
"TC (classes) Hash");
zrouter.filter_hash = hash_create_size(8, zebra_tc_filter_hash_key,
zebra_tc_filter_hash_equal,
"TC (filter) Hash");
zrouter.asic_offloaded = asic_offload;
zrouter.notify_on_ack = notify_on_ack;
zrouter.v6_with_v4_nexthop = v6_with_v4_nexthop;
/*
* If you start using asic_notification_nexthop_control
* come talk to the FRR community about what you are doing
* We would like to know.
*/
#if CONFDATE > 20251231
CPP_NOTICE(
"Remove zrouter.asic_notification_nexthop_control as that it's not being maintained or used");
#endif
zrouter.asic_notification_nexthop_control = false;
zrouter.nexthop_weight_scale_value = 254;
#ifdef HAVE_SCRIPTING
zebra_script_init();
#endif
/* OS-specific init */
kernel_router_init();
}