Merge branch 'Implement-classifier-action-terse-dump-mode'

Vlad Buslov says:

====================
Implement classifier-action terse dump mode

Output rate of current upstream kernel TC filter dump implementation if
relatively low (~100k rules/sec depending on configuration). This
constraint impacts performance of software switch implementation that
rely on TC for their datapath implementation and periodically call TC
filter dump to update rules stats. Moreover, TC filter dump output a lot
of static data that don't change during the filter lifecycle (filter
key, specific action details, etc.) which constitutes significant
portion of payload on resulting netlink packets and increases amount of
syscalls necessary to dump all filters on particular Qdisc. In order to
significantly improve filter dump rate this patch sets implement new
mode of TC filter dump operation named "terse dump" mode. In this mode
only parameters necessary to identify the filter (handle, action cookie,
etc.) and data that can change during filter lifecycle (filter flags,
action stats, etc.) are preserved in dump output while everything else
is omitted.

Userspace API is implemented using new TCA_DUMP_FLAGS tlv with only
available flag value TCA_DUMP_FLAGS_TERSE. Internally, new API requires
individual classifier support (new tcf_proto_ops->terse_dump()
callback). Support for action terse dump is implemented in act API and
don't require changing individual action implementations.

The following table provides performance comparison between regular
filter dump and new terse dump mode for two classifier-action profiles:
one minimal config with L2 flower classifier and single gact action and
another heavier config with L2+5tuple flower classifier with
tunnel_key+mirred actions.

 Classifier-action type      |        dump |  terse dump | X improvement
                             | (rules/sec) | (rules/sec) |
-----------------------------+-------------+-------------+---------------
 L2 with gact                |       141.8 |       293.2 |          2.07
 L2+5tuple tunnel_key+mirred |        76.4 |       198.8 |          2.60

Benchmark details: to measure the rate tc filter dump and terse dump
commands are invoked on ingress Qdisc that have one million filters
configured using following commands.

> time sudo tc -s filter show dev ens1f0 ingress >/dev/null

> time sudo tc -s filter show terse dev ens1f0 ingress >/dev/null

Value in results table is calculated by dividing 1000000 total rules by
"real" time reported by time command.

Setup details: 2x Intel(R) Xeon(R) CPU E5-2620 v3 @ 2.40GHz, 32GB memory
====================

Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 12 insertions, 1 deletions

diff --git a/include/net/act_api.h b/include/net/act_api.h
index c24d7643548e..1b4bfc4437be 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -193,7 +193,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 				    bool rtnl_held,
 				    struct netlink_ext_ack *extack);
 int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind,
-		    int ref);
+		    int ref, bool terse);
 int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int);
 int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int);
 
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 04aa0649f3b0..ed65619cbc47 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -325,6 +325,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp,
 void tcf_exts_destroy(struct tcf_exts *exts);
 void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src);
 int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts);
+int tcf_exts_terse_dump(struct sk_buff *skb, struct tcf_exts *exts);
 int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts);
 
 /**
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index ab87a8b86a32..c510b03b9751 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -330,6 +330,10 @@ struct tcf_proto_ops {
 	int			(*dump)(struct net*, struct tcf_proto*, void *,
 					struct sk_buff *skb, struct tcmsg*,
 					bool);
+	int			(*terse_dump)(struct net *net,
+					      struct tcf_proto *tp, void *fh,
+					      struct sk_buff *skb,
+					      struct tcmsg *t, bool rtnl_held);
 	int			(*tmplt_dump)(struct sk_buff *skb,
 					      struct net *net,
 					      void *tmplt_priv);
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 4a8c5b745157..073e71ef6bdd 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -609,11 +609,17 @@ enum {
 	TCA_HW_OFFLOAD,
 	TCA_INGRESS_BLOCK,
 	TCA_EGRESS_BLOCK,
+	TCA_DUMP_FLAGS,
 	__TCA_MAX
 };
 
 #define TCA_MAX (__TCA_MAX - 1)
 
+#define TCA_DUMP_FLAGS_TERSE (1 << 0) /* Means that in dump user gets only basic
+				       * data necessary to identify the objects
+				       * (handle, cookie, etc.) and stats.
+				       */
+
 #define TCA_RTA(r)  ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcmsg))))
 #define TCA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcmsg))