| 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: <1482952410-50003-4-git-send-email-willemdebruijn.kernel@gmail.com>
Date: Wed, 28 Dec 2016 14:13:27 -0500
From: Willem de Bruijn <willemdebruijn.kernel@...il.com>
To: netdev@...r.kernel.org
Cc: davem@...emloft.net, fw@...len.de, dborkman@...earbox.net,
jhs@...atatu.com, alexei.starovoitov@...il.com,
Willem de Bruijn <willemb@...gle.com>
Subject: [PATCH net-next rfc 3/6] net-tc: extract skip classify bit from tc_verd
From: Willem de Bruijn <willemb@...gle.com>
Packets sent by the IFB device skip subsequent tc classification.
A single bit governs this state. Move it out of tc_verd in
anticipation of removing that __u16 completely.
The new bitfield tc_skip_classify temporarily uses one bit of a
hole, until tc_verd is removed completely in a follow-up patch.
Remove the bit hole comment. It could be 2, 3, 4 or 5 bits long.
With that many options, little value in documenting it.
Introduce a helper function to deduplicate the logic in the two
sites that check this bit.
The field tc_skip_classify is set only in IFB on skbs cloned in
act_mirred, so original packet sources do not have to clear the
bit when reusing packets (notably, pktgen and octeon).
Signed-off-by: Willem de Bruijn <willemb@...gle.com>
---
drivers/net/ifb.c | 2 +-
include/linux/skbuff.h | 5 ++++-
include/net/sch_generic.h | 11 +++++++++++
include/uapi/linux/pkt_cls.h | 6 ------
net/core/dev.c | 10 +++-------
net/sched/act_api.c | 8 +++-----
6 files changed, 22 insertions(+), 20 deletions(-)
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index 66c0eea..4299ac1 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -81,7 +81,7 @@ static void ifb_ri_tasklet(unsigned long _txp)
u32 from = G_TC_FROM(skb->tc_verd);
skb->tc_verd = 0;
- skb->tc_verd = SET_TC_NCLS(skb->tc_verd);
+ skb->tc_skip_classify = 1;
u64_stats_update_begin(&txp->tsync);
txp->tx_packets++;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b53c0cf..570f60e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -589,6 +589,7 @@ static inline bool skb_mstamp_after(const struct skb_mstamp *t1,
* @pkt_type: Packet class
* @fclone: skbuff clone status
* @ipvs_property: skbuff is owned by ipvs
+ * @tc_skip_classify: do not classify packet. set by IFB device
* @peeked: this packet has been seen already, so stats have been
* done for it, don't do them again
* @nf_trace: netfilter packet trace flag
@@ -749,7 +750,9 @@ struct sk_buff {
#ifdef CONFIG_NET_SWITCHDEV
__u8 offload_fwd_mark:1;
#endif
- /* 2, 4 or 5 bit hole */
+#ifdef CONFIG_NET_CLS_ACT
+ __u8 tc_skip_classify:1;
+#endif
#ifdef CONFIG_NET_SCHED
__u16 tc_index; /* traffic control index */
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 498f81b..857356f 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -418,6 +418,17 @@ static inline bool skb_at_tc_ingress(const struct sk_buff *skb)
#endif
}
+static inline bool skb_skip_tc_classify(struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_CLS_ACT
+ if (skb->tc_skip_classify) {
+ skb->tc_skip_classify = 0;
+ return true;
+ }
+#endif
+ return false;
+}
+
/* Reset all TX qdiscs greater then index of a device. */
static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i)
{
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index bba23db..1eed5d7 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -22,8 +22,6 @@ bit 6,7: Where this packet was last seen
1: on the Ingress
2: on the Egress
-bit 8: when set --> Request not to classify on ingress.
-
*
* */
@@ -36,10 +34,6 @@ bit 8: when set --> Request not to classify on ingress.
#define AT_INGRESS 0x1
#define AT_EGRESS 0x2
-#define TC_NCLS _TC_MAKEMASK1(8)
-#define SET_TC_NCLS(v) ( TC_NCLS | (v & ~TC_NCLS))
-#define CLR_TC_NCLS(v) ( v & ~TC_NCLS)
-
#define S_TC_AT _TC_MAKE32(12)
#define M_TC_AT _TC_MAKEMASK(2,S_TC_AT)
#define G_TC_AT(x) _TC_GETVALUE(x,S_TC_AT,M_TC_AT)
diff --git a/net/core/dev.c b/net/core/dev.c
index 8db5a0b..7b41d97 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4089,12 +4089,8 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
goto out;
}
-#ifdef CONFIG_NET_CLS_ACT
- if (skb->tc_verd & TC_NCLS) {
- skb->tc_verd = CLR_TC_NCLS(skb->tc_verd);
- goto ncls;
- }
-#endif
+ if (skb_skip_tc_classify(skb))
+ goto skip_classify;
if (pfmemalloc)
goto skip_taps;
@@ -4124,8 +4120,8 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
#endif
#ifdef CONFIG_NET_CLS_ACT
skb->tc_verd = 0;
-ncls:
#endif
+skip_classify:
if (pfmemalloc && !skb_pfmemalloc_protocol(skb))
goto drop;
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 2095c83..7afaf8e 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -426,11 +426,9 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
{
int ret = -1, i;
- if (skb->tc_verd & TC_NCLS) {
- skb->tc_verd = CLR_TC_NCLS(skb->tc_verd);
- ret = TC_ACT_OK;
- goto exec_done;
- }
+ if (skb_skip_tc_classify(skb))
+ return TC_ACT_OK;
+
for (i = 0; i < nr_actions; i++) {
const struct tc_action *a = actions[i];
--
2.8.0.rc3.226.g39d4020
Powered by blists - more mailing lists