netdev - [PATCH net-next 4/4] act_mirred: use ACT

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <95034fe41fa132b2216686eeb41deaefd997e85b.1531473946.git.pabeni@redhat.com>
Date:   Fri, 13 Jul 2018 11:55:02 +0200
From:   Paolo Abeni <pabeni@...hat.com>
To:     netdev@...r.kernel.org
Cc:     Jamal Hadi Salim <jhs@...atatu.com>,
        Cong Wang <xiyou.wangcong@...il.com>,
        Jiri Pirko <jiri@...nulli.us>,
        Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>,
        Marcelo Ricardo Leitner <marcelo.leitner@...il.com>
Subject: [PATCH net-next 4/4] act_mirred: use ACT_REDIRECT when possible

When mirred is invoked from the ingress path, and it wants to redirect
the processed packet, it can now use the ACT_REDIRECT action,
filling the tcf_result accordingly.

This avoids a skb_clone() in the TC S/W data path giving a ~10%
improvement in forwarding performances. Overall TC S/W performances
are now comparable to the kernel openswitch datapath.

Signed-off-by: Paolo Abeni <pabeni@...hat.com>
---
 net/sched/act_mirred.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index eeb335f03102..b19317426117 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -175,6 +175,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 	struct net_device *dev;
 	struct sk_buff *skb2;
 	int retval, err = 0;
+	bool want_ingress;
 	int m_eaction;
 	int mac_len;
 
@@ -185,6 +186,17 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 	m_eaction = READ_ONCE(m->tcfm_eaction);
 	retval = READ_ONCE(m->tcf_action);
 	dev = rcu_dereference_bh(m->tcfm_dev);
+	want_ingress = tcf_mirred_act_wants_ingress(m_eaction);
+	if (skb_at_tc_ingress(skb) && tcf_mirred_is_act_redirect(m_eaction)) {
+		skb->tc_redirected = 1;
+		skb->tc_from_ingress = 1;
+
+		/* the core redirect code will check dev and its status */
+		TCF_RESULT_SET_REDIRECT(res, dev, want_ingress);
+		res->qstats = this_cpu_ptr(m->common.cpu_qstats);
+		return TC_ACT_REDIRECT;
+	}
+
 	if (unlikely(!dev)) {
 		pr_notice_once("tc mirred: target device is gone\n");
 		goto out;
@@ -204,8 +216,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 	 * and devices expect a mac header on xmit, then mac push/pull is
 	 * needed.
 	 */
-	if (skb_at_tc_ingress(skb) != tcf_mirred_act_wants_ingress(m_eaction) &&
-	    m_mac_header_xmit) {
+	if (skb_at_tc_ingress(skb) != want_ingress && m_mac_header_xmit) {
 		if (!skb_at_tc_ingress(skb)) {
 			/* caught at egress, act ingress: pull mac */
 			mac_len = skb_network_header(skb) - skb_mac_header(skb);
-- 
2.17.1