diff options
author | Ido Schimmel <idosch@nvidia.com> | 2023-07-15 18:36:05 +0300 |
---|---|---|
committer | Paolo Abeni <pabeni@redhat.com> | 2023-07-18 12:49:57 +0200 |
commit | 2033ab90380d46e0e9f0520fd6776a73d107fd95 (patch) | |
tree | c7a66a146eed88c2a537d92e5d4100c2ab6cdbf0 /drivers/net/vrf.c | |
parent | 03803083a9b4d88886fb059458682301a8c7219a (diff) | |
download | lwn-2033ab90380d46e0e9f0520fd6776a73d107fd95.tar.gz lwn-2033ab90380d46e0e9f0520fd6776a73d107fd95.zip |
vrf: Fix lockdep splat in output path
Cited commit converted the neighbour code to use the standard RCU
variant instead of the RCU-bh variant, but the VRF code still uses
rcu_read_lock_bh() / rcu_read_unlock_bh() around the neighbour lookup
code in its IPv4 and IPv6 output paths, resulting in lockdep splats
[1][2]. Can be reproduced using [3].
Fix by switching to rcu_read_lock() / rcu_read_unlock().
[1]
=============================
WARNING: suspicious RCU usage
6.5.0-rc1-custom-g9c099e6dbf98 #403 Not tainted
-----------------------------
include/net/neighbour.h:302 suspicious rcu_dereference_check() usage!
other info that might help us debug this:
rcu_scheduler_active = 2, debug_locks = 1
2 locks held by ping/183:
#0: ffff888105ea1d80 (sk_lock-AF_INET){+.+.}-{0:0}, at: raw_sendmsg+0xc6c/0x33c0
#1: ffffffff85b46820 (rcu_read_lock_bh){....}-{1:2}, at: vrf_output+0x2e3/0x2030
stack backtrace:
CPU: 0 PID: 183 Comm: ping Not tainted 6.5.0-rc1-custom-g9c099e6dbf98 #403
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-1.fc37 04/01/2014
Call Trace:
<TASK>
dump_stack_lvl+0xc1/0xf0
lockdep_rcu_suspicious+0x211/0x3b0
vrf_output+0x1380/0x2030
ip_push_pending_frames+0x125/0x2a0
raw_sendmsg+0x200d/0x33c0
inet_sendmsg+0xa2/0xe0
__sys_sendto+0x2aa/0x420
__x64_sys_sendto+0xe5/0x1c0
do_syscall_64+0x38/0x80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
[2]
=============================
WARNING: suspicious RCU usage
6.5.0-rc1-custom-g9c099e6dbf98 #403 Not tainted
-----------------------------
include/net/neighbour.h:302 suspicious rcu_dereference_check() usage!
other info that might help us debug this:
rcu_scheduler_active = 2, debug_locks = 1
2 locks held by ping6/182:
#0: ffff888114b63000 (sk_lock-AF_INET6){+.+.}-{0:0}, at: rawv6_sendmsg+0x1602/0x3e50
#1: ffffffff85b46820 (rcu_read_lock_bh){....}-{1:2}, at: vrf_output6+0xe9/0x1310
stack backtrace:
CPU: 0 PID: 182 Comm: ping6 Not tainted 6.5.0-rc1-custom-g9c099e6dbf98 #403
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-1.fc37 04/01/2014
Call Trace:
<TASK>
dump_stack_lvl+0xc1/0xf0
lockdep_rcu_suspicious+0x211/0x3b0
vrf_output6+0xd32/0x1310
ip6_local_out+0xb4/0x1a0
ip6_send_skb+0xbc/0x340
ip6_push_pending_frames+0xe5/0x110
rawv6_sendmsg+0x2e6e/0x3e50
inet_sendmsg+0xa2/0xe0
__sys_sendto+0x2aa/0x420
__x64_sys_sendto+0xe5/0x1c0
do_syscall_64+0x38/0x80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
[3]
#!/bin/bash
ip link add name vrf-red up numtxqueues 2 type vrf table 10
ip link add name swp1 up master vrf-red type dummy
ip address add 192.0.2.1/24 dev swp1
ip address add 2001:db8:1::1/64 dev swp1
ip neigh add 192.0.2.2 lladdr 00:11:22:33:44:55 nud perm dev swp1
ip neigh add 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud perm dev swp1
ip vrf exec vrf-red ping 192.0.2.2 -c 1 &> /dev/null
ip vrf exec vrf-red ping6 2001:db8:1::2 -c 1 &> /dev/null
Fixes: 09eed1192cec ("neighbour: switch to standard rcu, instead of rcu_bh")
Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Link: https://lore.kernel.org/netdev/CA+G9fYtEr-=GbcXNDYo3XOkwR+uYgehVoDjsP0pFLUpZ_AZcyg@mail.gmail.com/
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230715153605.4068066-1-idosch@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Diffstat (limited to 'drivers/net/vrf.c')
-rw-r--r-- | drivers/net/vrf.c | 12 |
1 files changed, 6 insertions, 6 deletions
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index bdb3a76a352e..6043e63b42f9 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -664,7 +664,7 @@ static int vrf_finish_output6(struct net *net, struct sock *sk, skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; - rcu_read_lock_bh(); + rcu_read_lock(); nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) @@ -672,10 +672,10 @@ static int vrf_finish_output6(struct net *net, struct sock *sk, if (!IS_ERR(neigh)) { sock_confirm_neigh(skb, neigh); ret = neigh_output(neigh, skb, false); - rcu_read_unlock_bh(); + rcu_read_unlock(); return ret; } - rcu_read_unlock_bh(); + rcu_read_unlock(); IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); @@ -889,7 +889,7 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s } } - rcu_read_lock_bh(); + rcu_read_lock(); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { @@ -898,11 +898,11 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s sock_confirm_neigh(skb, neigh); /* if crossing protocols, can not use the cached header */ ret = neigh_output(neigh, skb, is_v6gw); - rcu_read_unlock_bh(); + rcu_read_unlock(); return ret; } - rcu_read_unlock_bh(); + rcu_read_unlock(); vrf_tx_error(skb->dev, skb); return -EINVAL; } |