netdev - [PATCH net-next v3 5/5] act_mirred: use TC_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: <612f6fb5b0cdddcbbc2d99f65b148b7f3b8b9a27.1532437050.git.pabeni@redhat.com>
Date:   Tue, 24 Jul 2018 22:06:43 +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>,
        Daniel Borkmann <daniel@...earbox.net>,
        Marcelo Ricardo Leitner <marcelo.leitner@...il.com>,
        Eyal Birger <eyal.birger@...il.com>,
        "David S. Miller" <davem@...emloft.net>
Subject: [PATCH net-next v3 5/5] act_mirred: use TC_ACT_REINJECT when possible

When mirred is invoked from the ingress path, and it wants to redirect
the processed packet, it can now use the TC_ACT_REINJECT action,
filling the tcf_result accordingly, and avoiding a per packet
skb_clone().

Overall this gives a ~10% improvement in forwarding performance for the
TC S/W data path and TC S/W performances are now comparable to the
kernel openvswitch datapath.

v1 -> v2: use ACT_MIRRED instead of ACT_REDIRECT
v2 -> v3: updated after action rename, fixed a typo into the commit
	message

Signed-off-by: Paolo Abeni <pabeni@...hat.com>
---
 net/sched/act_mirred.c | 34 ++++++++++++++++++++++++----------
 1 file changed, 24 insertions(+), 10 deletions(-)

diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index eeb335f03102..368187312136 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -25,6 +25,7 @@
 #include <net/net_namespace.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
 #include <linux/tc_act/tc_mirred.h>
 #include <net/tc_act/tc_mirred.h>
 
@@ -171,10 +172,12 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 		      struct tcf_result *res)
 {
 	struct tcf_mirred *m = to_mirred(a);
+	struct sk_buff *skb2 = skb;
 	bool m_mac_header_xmit;
 	struct net_device *dev;
-	struct sk_buff *skb2;
 	int retval, err = 0;
+	bool want_ingress;
+	bool is_redirect;
 	int m_eaction;
 	int mac_len;
 
@@ -196,16 +199,19 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 		goto out;
 	}
 
-	skb2 = skb_clone(skb, GFP_ATOMIC);
-	if (!skb2)
-		goto out;
+	is_redirect = tcf_mirred_is_act_redirect(m_eaction);
+	if (!skb_at_tc_ingress(skb) || !is_redirect) {
+		skb2 = skb_clone(skb, GFP_ATOMIC);
+		if (!skb2)
+			goto out;
+	}
 
 	/* If action's target direction differs than filter's direction,
 	 * 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) {
+	want_ingress = tcf_mirred_act_wants_ingress(m_eaction);
+	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);
@@ -216,15 +222,23 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 		}
 	}
 
+	skb2->skb_iif = skb->dev->ifindex;
+	skb2->dev = dev;
+
 	/* mirror is always swallowed */
-	if (tcf_mirred_is_act_redirect(m_eaction)) {
+	if (is_redirect) {
 		skb2->tc_redirected = 1;
 		skb2->tc_from_ingress = skb2->tc_at_ingress;
+
+		/* let's the caller reinject the packet, if possible */
+		if (skb_at_tc_ingress(skb)) {
+			res->ingress = want_ingress;
+			res->qstats = this_cpu_ptr(m->common.cpu_qstats);
+			return TC_ACT_REINJECT;
+		}
 	}
 
-	skb2->skb_iif = skb->dev->ifindex;
-	skb2->dev = dev;
-	if (!tcf_mirred_act_wants_ingress(m_eaction))
+	if (!want_ingress)
 		err = dev_queue_xmit(skb2);
 	else
 		err = netif_receive_skb(skb2);
-- 
2.17.1