| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CANn89iLhd4iD-pDVJHzKqWbf16u9KyNtgV41X3sd=iy15jDQtQ@mail.gmail.com>
Date: Wed, 27 Mar 2024 14:23:20 +0100
From: Eric Dumazet <edumazet@...gle.com>
To: Jamal Hadi Salim <jhs@...atatu.com>
Cc: davem@...emloft.net, kuba@...nel.org, pabeni@...hat.com, jiri@...nulli.us,
xiyou.wangcong@...il.com, netdev@...r.kernel.org, renmingshuai@...wei.com,
Victor Nogueira <victor@...atatu.com>
Subject: Re: [PATCH RFC net 1/1] net/sched: Fix mirred to self recursion
On Wed, Mar 27, 2024 at 12:03 AM Jamal Hadi Salim <jhs@...atatu.com> wrote:
>
> When the mirred action is used on a classful egress qdisc and a packet is
> mirrored or redirected to self we hit a qdisc lock deadlock.
> See trace below.
>
> [..... other info removed for brevity....]
> [ 82.890906]
> [ 82.890906] ============================================
> [ 82.890906] WARNING: possible recursive locking detected
> [ 82.890906] 6.8.0-05205-g77fadd89fe2d-dirty #213 Tainted: G W
> [ 82.890906] --------------------------------------------
> [ 82.890906] ping/418 is trying to acquire lock:
> [ 82.890906] ffff888006994110 (&sch->q.lock){+.-.}-{3:3}, at:
> __dev_queue_xmit+0x1778/0x3550
> [ 82.890906]
> [ 82.890906] but task is already holding lock:
> [ 82.890906] ffff888006994110 (&sch->q.lock){+.-.}-{3:3}, at:
> __dev_queue_xmit+0x1778/0x3550
> [ 82.890906]
> [ 82.890906] other info that might help us debug this:
> [ 82.890906] Possible unsafe locking scenario:
> [ 82.890906]
> [ 82.890906] CPU0
> [ 82.890906] ----
> [ 82.890906] lock(&sch->q.lock);
> [ 82.890906] lock(&sch->q.lock);
> [ 82.890906]
> [ 82.890906] *** DEADLOCK ***
> [ 82.890906]
> [..... other info removed for brevity....]
>
> Example setup (eth0->eth0) to recreate
> tc qdisc add dev eth0 root handle 1: htb default 30
> tc filter add dev eth0 handle 1: protocol ip prio 2 matchall \
> action mirred egress redirect dev eth0
>
> Another example(eth0->eth1->eth0) to recreate
> tc qdisc add dev eth0 root handle 1: htb default 30
> tc filter add dev eth0 handle 1: protocol ip prio 2 matchall \
> action mirred egress redirect dev eth1
>
> tc qdisc add dev eth1 root handle 1: htb default 30
> tc filter add dev eth1 handle 1: protocol ip prio 2 matchall \
> action mirred egress redirect dev eth0
>
> We fix this by adding a per-cpu, per-qdisc recursion counter which is
> incremented the first time a root qdisc is entered and on a second attempt
> enter the same root qdisc from the top, the packet is dropped to break the
> loop.
>
> Reported-by: renmingshuai@...wei.com
> Closes: https://lore.kernel.org/netdev/20240314111713.5979-1-renmingshuai@huawei.com/
> Fixes: 3bcb846ca4cf ("net: get rid of spin_trylock() in net_tx_action()")
> Fixes: e578d9c02587 ("net: sched: use counter to break reclassify loops")
> Co-developed-by: Victor Nogueira <victor@...atatu.com>
> Signed-off-by: Victor Nogueira <victor@...atatu.com>
> Signed-off-by: Jamal Hadi Salim <jhs@...atatu.com>
> ---
> include/net/sch_generic.h | 2 ++
> net/core/dev.c | 9 +++++++++
> net/sched/sch_api.c | 12 ++++++++++++
> net/sched/sch_generic.c | 2 ++
> 4 files changed, 25 insertions(+)
>
> diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
> index cefe0c4bdae3..f9f99df037ed 100644
> --- a/include/net/sch_generic.h
> +++ b/include/net/sch_generic.h
> @@ -125,6 +125,8 @@ struct Qdisc {
> spinlock_t busylock ____cacheline_aligned_in_smp;
> spinlock_t seqlock;
>
> + u16 __percpu *xmit_recursion;
> +
> struct rcu_head rcu;
> netdevice_tracker dev_tracker;
> /* private data */
> diff --git a/net/core/dev.c b/net/core/dev.c
> index 9a67003e49db..2b712388c06f 100644
> --- a/net/core/dev.c
> +++ b/net/core/dev.c
> @@ -3789,6 +3789,13 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
> if (unlikely(contended))
> spin_lock(&q->busylock);
This could hang here (busylock)
>
> + if (__this_cpu_read(*q->xmit_recursion) > 0) {
> + __qdisc_drop(skb, &to_free);
> + rc = NET_XMIT_DROP;
> + goto free_skb_list;
> + }
I do not think we want to add yet another cache line miss and
complexity in tx fast path.
I think that mirred should use a separate queue to kick a transmit
from the top level.
(Like netif_rx() does)
Using a softnet.xmit_qdisc_recursion (not a qdisc-per-cpu thing),
would allow mirred to bypass this additional queue
in most cases.
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cb37817d6382c29117afd8ce54db6dba94f8c930..62ba5ef554860496ee928f7ed6b7c3ea46b8ee1d
100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3217,7 +3217,8 @@ struct softnet_data {
#endif
/* written and read only by owning cpu: */
struct {
- u16 recursion;
+ u8 recursion;
+ u8 qdisc_recursion;
u8 more;
#ifdef CONFIG_NET_EGRESS
u8 skip_txqueue;
diff --git a/net/core/dev.c b/net/core/dev.c
index 9a67003e49db87f3f92b6c6296b3e7a5ca9d9171..7ac59835edef657e9558d4d4fc0a76b171aace93
100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4298,7 +4298,9 @@ int __dev_queue_xmit(struct sk_buff *skb, struct
net_device *sb_dev)
trace_net_dev_queue(skb);
if (q->enqueue) {
+ __this_cpu_inc(softnet_data.xmit.qdisc_recursion);
rc = __dev_xmit_skb(skb, q, dev, txq);
+ __this_cpu_dec(softnet_data.xmit.qdisc_recursion);
goto out;
}
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 5b38143659249e66718348e0ec4ed3c7bc21c13d..0f5f02e6744397d33ae2a72670ba7131aaa6942e
100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -237,8 +237,13 @@ tcf_mirred_forward(bool at_ingress, bool
want_ingress, struct sk_buff *skb)
{
int err;
- if (!want_ingress)
- err = tcf_dev_queue_xmit(skb, dev_queue_xmit);
+ if (!want_ingress) {
+ if (__this_cpu_read(softnet_data.xmit.qdisc_recursion)) {
+ // Queue to top level, or drop
+ } else {
+ err = tcf_dev_queue_xmit(skb, dev_queue_xmit);
+ }
+ }
else if (!at_ingress)
err = netif_rx(skb);
else
Powered by blists - more mailing lists