linux-stable/include/net/netns/ipv6.h
Eric Dumazet 9cb7c01342 ipv6: make ip6_rt_gc_expire an atomic_t
Reads and Writes to ip6_rt_gc_expire always have been racy,
as syzbot reported lately [1]

There is a possible risk of under-flow, leading
to unexpected high value passed to fib6_run_gc(),
although I have not observed this in the field.

Hosts hitting ip6_dst_gc() very hard are under pretty bad
state anyway.

[1]
BUG: KCSAN: data-race in ip6_dst_gc / ip6_dst_gc

read-write to 0xffff888102110744 of 4 bytes by task 13165 on cpu 1:
 ip6_dst_gc+0x1f3/0x220 net/ipv6/route.c:3311
 dst_alloc+0x9b/0x160 net/core/dst.c:86
 ip6_dst_alloc net/ipv6/route.c:344 [inline]
 icmp6_dst_alloc+0xb2/0x360 net/ipv6/route.c:3261
 mld_sendpack+0x2b9/0x580 net/ipv6/mcast.c:1807
 mld_send_cr net/ipv6/mcast.c:2119 [inline]
 mld_ifc_work+0x576/0x800 net/ipv6/mcast.c:2651
 process_one_work+0x3d3/0x720 kernel/workqueue.c:2289
 worker_thread+0x618/0xa70 kernel/workqueue.c:2436
 kthread+0x1a9/0x1e0 kernel/kthread.c:376
 ret_from_fork+0x1f/0x30

read-write to 0xffff888102110744 of 4 bytes by task 11607 on cpu 0:
 ip6_dst_gc+0x1f3/0x220 net/ipv6/route.c:3311
 dst_alloc+0x9b/0x160 net/core/dst.c:86
 ip6_dst_alloc net/ipv6/route.c:344 [inline]
 icmp6_dst_alloc+0xb2/0x360 net/ipv6/route.c:3261
 mld_sendpack+0x2b9/0x580 net/ipv6/mcast.c:1807
 mld_send_cr net/ipv6/mcast.c:2119 [inline]
 mld_ifc_work+0x576/0x800 net/ipv6/mcast.c:2651
 process_one_work+0x3d3/0x720 kernel/workqueue.c:2289
 worker_thread+0x618/0xa70 kernel/workqueue.c:2436
 kthread+0x1a9/0x1e0 kernel/kthread.c:376
 ret_from_fork+0x1f/0x30

value changed: 0x00000bb3 -> 0x00000ba9

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 11607 Comm: kworker/0:21 Not tainted 5.18.0-rc1-syzkaller-00037-g42e7a03d3bad-dirty #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: mld mld_ifc_work

Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20220413181333.649424-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-04-15 14:28:50 -07:00

129 lines
3.2 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* ipv6 in net namespaces
*/
#include <net/inet_frag.h>
#ifndef __NETNS_IPV6_H__
#define __NETNS_IPV6_H__
#include <net/dst_ops.h>
#include <uapi/linux/icmpv6.h>
struct ctl_table_header;
struct netns_sysctl_ipv6 {
#ifdef CONFIG_SYSCTL
struct ctl_table_header *hdr;
struct ctl_table_header *route_hdr;
struct ctl_table_header *icmp_hdr;
struct ctl_table_header *frags_hdr;
struct ctl_table_header *xfrm6_hdr;
#endif
int flush_delay;
int ip6_rt_max_size;
int ip6_rt_gc_min_interval;
int ip6_rt_gc_timeout;
int ip6_rt_gc_interval;
int ip6_rt_gc_elasticity;
int ip6_rt_mtu_expires;
int ip6_rt_min_advmss;
u32 multipath_hash_fields;
u8 multipath_hash_policy;
u8 bindv6only;
u8 flowlabel_consistency;
u8 auto_flowlabels;
int icmpv6_time;
u8 icmpv6_echo_ignore_all;
u8 icmpv6_echo_ignore_multicast;
u8 icmpv6_echo_ignore_anycast;
DECLARE_BITMAP(icmpv6_ratemask, ICMPV6_MSG_MAX + 1);
unsigned long *icmpv6_ratemask_ptr;
u8 anycast_src_echo_reply;
u8 ip_nonlocal_bind;
u8 fwmark_reflect;
u8 flowlabel_state_ranges;
int idgen_retries;
int idgen_delay;
int flowlabel_reflect;
int max_dst_opts_cnt;
int max_hbh_opts_cnt;
int max_dst_opts_len;
int max_hbh_opts_len;
int seg6_flowlabel;
u32 ioam6_id;
u64 ioam6_id_wide;
bool skip_notify_on_dev_down;
u8 fib_notify_on_flag_change;
};
struct netns_ipv6 {
/* Keep ip6_dst_ops at the beginning of netns_sysctl_ipv6 */
struct dst_ops ip6_dst_ops;
struct netns_sysctl_ipv6 sysctl;
struct ipv6_devconf *devconf_all;
struct ipv6_devconf *devconf_dflt;
struct inet_peer_base *peers;
struct fqdir *fqdir;
struct fib6_info *fib6_null_entry;
struct rt6_info *ip6_null_entry;
struct rt6_statistics *rt6_stats;
struct timer_list ip6_fib_timer;
struct hlist_head *fib_table_hash;
struct fib6_table *fib6_main_tbl;
struct list_head fib6_walkers;
rwlock_t fib6_walker_lock;
spinlock_t fib6_gc_lock;
atomic_t ip6_rt_gc_expire;
unsigned long ip6_rt_last_gc;
unsigned char flowlabel_has_excl;
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
bool fib6_has_custom_rules;
unsigned int fib6_rules_require_fldissect;
#ifdef CONFIG_IPV6_SUBTREES
unsigned int fib6_routes_require_src;
#endif
struct rt6_info *ip6_prohibit_entry;
struct rt6_info *ip6_blk_hole_entry;
struct fib6_table *fib6_local_tbl;
struct fib_rules_ops *fib6_rules_ops;
#endif
struct sock *ndisc_sk;
struct sock *tcp_sk;
struct sock *igmp_sk;
struct sock *mc_autojoin_sk;
struct hlist_head *inet6_addr_lst;
spinlock_t addrconf_hash_lock;
struct delayed_work addr_chk_work;
#ifdef CONFIG_IPV6_MROUTE
#ifndef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
struct mr_table *mrt6;
#else
struct list_head mr6_tables;
struct fib_rules_ops *mr6_rules_ops;
#endif
#endif
atomic_t dev_addr_genid;
atomic_t fib6_sernum;
struct seg6_pernet_data *seg6_data;
struct fib_notifier_ops *notifier_ops;
struct fib_notifier_ops *ip6mr_notifier_ops;
unsigned int ipmr_seq; /* protected by rtnl_mutex */
struct {
struct hlist_head head;
spinlock_t lock;
u32 seq;
} ip6addrlbl_table;
struct ioam6_pernet_data *ioam6_data;
};
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
struct netns_nf_frag {
struct fqdir *fqdir;
};
#endif
#endif