From: Eric Dumazet edumazet@google.com
commit 0a6e6b3c7db6c34e3d149f09cd714972f8753e3f upstream.
In the past, free_fib_info() was supposed to be called under RTNL protection.
This eventually was no longer the case.
Instead of enforcing RTNL it seems we simply can move fib_info_cnt changes to occur when fib_info_lock is held.
v2: David Laight suggested to update fib_info_cnt only when an entry is added/deleted to/from the hash table, as fib_info_cnt is used to make sure hash table size is optimal.
BUG: KCSAN: data-race in fib_create_info / free_fib_info
write to 0xffffffff86e243a0 of 4 bytes by task 26429 on cpu 0: fib_create_info+0xe78/0x3440 net/ipv4/fib_semantics.c:1428 fib_table_insert+0x148/0x10c0 net/ipv4/fib_trie.c:1224 fib_magic+0x195/0x1e0 net/ipv4/fib_frontend.c:1087 fib_add_ifaddr+0xd0/0x2e0 net/ipv4/fib_frontend.c:1109 fib_netdev_event+0x178/0x510 net/ipv4/fib_frontend.c:1466 notifier_call_chain kernel/notifier.c:83 [inline] raw_notifier_call_chain+0x53/0xb0 kernel/notifier.c:391 __dev_notify_flags+0x1d3/0x3b0 dev_change_flags+0xa2/0xc0 net/core/dev.c:8872 do_setlink+0x810/0x2410 net/core/rtnetlink.c:2719 rtnl_group_changelink net/core/rtnetlink.c:3242 [inline] __rtnl_newlink net/core/rtnetlink.c:3396 [inline] rtnl_newlink+0xb10/0x13b0 net/core/rtnetlink.c:3506 rtnetlink_rcv_msg+0x745/0x7e0 net/core/rtnetlink.c:5571 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2496 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5589 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x5fc/0x6c0 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x726/0x840 net/netlink/af_netlink.c:1921 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg net/socket.c:724 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2409 ___sys_sendmsg net/socket.c:2463 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2492 __do_sys_sendmsg net/socket.c:2501 [inline] __se_sys_sendmsg net/socket.c:2499 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2499 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae
read to 0xffffffff86e243a0 of 4 bytes by task 31505 on cpu 1: free_fib_info+0x35/0x80 net/ipv4/fib_semantics.c:252 fib_info_put include/net/ip_fib.h:575 [inline] nsim_fib4_rt_destroy drivers/net/netdevsim/fib.c:294 [inline] nsim_fib4_rt_replace drivers/net/netdevsim/fib.c:403 [inline] nsim_fib4_rt_insert drivers/net/netdevsim/fib.c:431 [inline] nsim_fib4_event drivers/net/netdevsim/fib.c:461 [inline] nsim_fib_event drivers/net/netdevsim/fib.c:881 [inline] nsim_fib_event_work+0x15ca/0x2cf0 drivers/net/netdevsim/fib.c:1477 process_one_work+0x3fc/0x980 kernel/workqueue.c:2298 process_scheduled_works kernel/workqueue.c:2361 [inline] worker_thread+0x7df/0xa70 kernel/workqueue.c:2447 kthread+0x2c7/0x2e0 kernel/kthread.c:327 ret_from_fork+0x1f/0x30
value changed: 0x00000d2d -> 0x00000d2e
Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 31505 Comm: kworker/1:21 Not tainted 5.16.0-rc6-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: events nsim_fib_event_work
Fixes: 48bb9eb47b27 ("netdevsim: fib: Add dummy implementation for FIB offload") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Cc: David Laight David.Laight@ACULAB.COM Cc: Ido Schimmel idosch@mellanox.com Cc: Jiri Pirko jiri@mellanox.com Reviewed-by: Ido Schimmel idosch@nvidia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/fib_semantics.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)
--- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -251,7 +251,6 @@ void free_fib_info(struct fib_info *fi) pr_warn("Freeing alive fib_info %p\n", fi); return; } - fib_info_cnt--;
call_rcu(&fi->rcu, free_fib_info_rcu); } @@ -262,6 +261,10 @@ void fib_release_info(struct fib_info *f spin_lock_bh(&fib_info_lock); if (fi && --fi->fib_treeref == 0) { hlist_del(&fi->fib_hash); + + /* Paired with READ_ONCE() in fib_create_info(). */ + WRITE_ONCE(fib_info_cnt, fib_info_cnt - 1); + if (fi->fib_prefsrc) hlist_del(&fi->fib_lhash); if (fi->nh) { @@ -1431,7 +1434,9 @@ struct fib_info *fib_create_info(struct #endif
err = -ENOBUFS; - if (fib_info_cnt >= fib_info_hash_size) { + + /* Paired with WRITE_ONCE() in fib_release_info() */ + if (READ_ONCE(fib_info_cnt) >= fib_info_hash_size) { unsigned int new_size = fib_info_hash_size << 1; struct hlist_head *new_info_hash; struct hlist_head *new_laddrhash; @@ -1463,7 +1468,6 @@ struct fib_info *fib_create_info(struct return ERR_PTR(err); }
- fib_info_cnt++; fi->fib_net = net; fi->fib_protocol = cfg->fc_protocol; fi->fib_scope = cfg->fc_scope; @@ -1590,6 +1594,7 @@ link_it: fi->fib_treeref++; refcount_set(&fi->fib_clntref, 1); spin_lock_bh(&fib_info_lock); + fib_info_cnt++; hlist_add_head(&fi->fib_hash, &fib_info_hash[fib_info_hashfn(fi)]); if (fi->fib_prefsrc) {