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
| ||
|
Date: Mon, 6 Dec 2021 16:05:11 +0800 From: xiangxia.m.yue@...il.com To: netdev@...r.kernel.org Cc: Tonghao Zhang <xiangxia.m.yue@...il.com>, Jamal Hadi Salim <jhs@...atatu.com>, Cong Wang <xiyou.wangcong@...il.com>, Jiri Pirko <jiri@...nulli.us>, "David S. Miller" <davem@...emloft.net>, Jakub Kicinski <kuba@...nel.org>, Jonathan Lemon <jonathan.lemon@...il.com>, Eric Dumazet <edumazet@...gle.com>, Alexander Lobakin <alobakin@...me>, Paolo Abeni <pabeni@...hat.com>, Talal Ahmad <talalahmad@...gle.com>, Kevin Hao <haokexin@...il.com>, Ilias Apalodimas <ilias.apalodimas@...aro.org>, Kees Cook <keescook@...omium.org>, Kumar Kartikeya Dwivedi <memxor@...il.com>, Antoine Tenart <atenart@...nel.org>, Wei Wang <weiwan@...gle.com>, Arnd Bergmann <arnd@...db.de> Subject: [net-next v1 1/2] net: sched: use queue_mapping to pick tx queue From: Tonghao Zhang <xiangxia.m.yue@...il.com> This patch fix issue: * If we install tc filters with act_skbedit in clsact hook. It doesn't work, because *netdev_core_pick_tx will overwrite queue_mapping. $ tc filter add dev $NETDEV egress .. action skbedit queue_mapping 1 And this patch is useful: * In containter networking environment, one kind of pod/containter/ net-namespace (e.g. P1, P2) which outbound traffic limited, can use one specific tx queue which used HTB/TBF Qdisc. But other kind of pods (e.g. Pn) can use other specific tx queue too, which used fifio Qdisc. Then the lock contention of HTB/TBF Qdisc will not affect Pn. +----+ +----+ +----+ | P1 | | P2 | | Pn | +----+ +----+ +----+ | | | +-----------+-----------+ | | clsact/skbedit | MQ v +-----------+-----------+ | q0 | q1 | qn v v v HTB HTB ... FIFO Cc: Jamal Hadi Salim <jhs@...atatu.com> Cc: Cong Wang <xiyou.wangcong@...il.com> Cc: Jiri Pirko <jiri@...nulli.us> Cc: "David S. Miller" <davem@...emloft.net> Cc: Jakub Kicinski <kuba@...nel.org> Cc: Jonathan Lemon <jonathan.lemon@...il.com> Cc: Eric Dumazet <edumazet@...gle.com> Cc: Alexander Lobakin <alobakin@...me> Cc: Paolo Abeni <pabeni@...hat.com> Cc: Talal Ahmad <talalahmad@...gle.com> Cc: Kevin Hao <haokexin@...il.com> Cc: Ilias Apalodimas <ilias.apalodimas@...aro.org> Cc: Kees Cook <keescook@...omium.org> Cc: Kumar Kartikeya Dwivedi <memxor@...il.com> Cc: Antoine Tenart <atenart@...nel.org> Cc: Wei Wang <weiwan@...gle.com> Cc: Arnd Bergmann <arnd@...db.de> Signed-off-by: Tonghao Zhang <xiangxia.m.yue@...il.com> --- include/linux/skbuff.h | 1 + net/core/dev.c | 12 +++++++++--- net/sched/act_skbedit.c | 4 +++- 3 files changed, 13 insertions(+), 4 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index eae4bd3237a4..b6ea4b920409 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -856,6 +856,7 @@ struct sk_buff { #endif #ifdef CONFIG_NET_CLS_ACT __u8 tc_skip_classify:1; + __u8 tc_skip_txqueue:1; __u8 tc_at_ingress:1; #endif __u8 redirected:1; diff --git a/net/core/dev.c b/net/core/dev.c index aba8acc1238c..fb9d4eee29ee 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3975,10 +3975,16 @@ struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, { int queue_index = 0; -#ifdef CONFIG_XPS - u32 sender_cpu = skb->sender_cpu - 1; +#ifdef CONFIG_NET_CLS_ACT + if (skb->tc_skip_txqueue) { + queue_index = netdev_cap_txqueue(dev, + skb_get_queue_mapping(skb)); + return netdev_get_tx_queue(dev, queue_index); + } +#endif - if (sender_cpu >= (u32)NR_CPUS) +#ifdef CONFIG_XPS + if ((skb->sender_cpu - 1) >= (u32)NR_CPUS) skb->sender_cpu = raw_smp_processor_id() + 1; #endif diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index d30ecbfc8f84..940091a7c7f0 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -58,8 +58,10 @@ static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a, } } if (params->flags & SKBEDIT_F_QUEUE_MAPPING && - skb->dev->real_num_tx_queues > params->queue_mapping) + skb->dev->real_num_tx_queues > params->queue_mapping) { + skb->tc_skip_txqueue = 1; skb_set_queue_mapping(skb, params->queue_mapping); + } if (params->flags & SKBEDIT_F_MARK) { skb->mark &= ~params->mask; skb->mark |= params->mark & params->mask; -- 2.27.0
Powered by blists - more mailing lists