Merge branch 'flower-offload'

Amir Vadai says:

====================
cls_flower hardware offload support

Please see changes from V2 at the bottom.

This patchset introduces cls_flower hardware offload support over ConnectX-4
driver, more hardware vendors are welcome to use it too.

This patchset is based on John's infrastructure for tc offloading [2] to add
hardware offload support to the flower filter. It also extends the support to
an additional tc action - skbedit mark operation.
NIC driver that was used is ConnectX-4. Feature is off by default and could be
turned on using ethtool.

Some commands to use this code:

export TC=../iproute2/tc/tc
export ETH=ens9

ethtool  -K ens9 hw-tc-offload on

$TC qdisc add dev $ETH ingress

$TC filter add dev $ETH protocol ip prio 20 parent ffff: \
	flower ip_proto 1 \
	dst_mac 7c:fe:90:69:81:62 \
	src_mac 7c:fe:90:69:81:56 \
	dst_ip 11.11.11.11 \
	src_ip 11.11.11.12 \
	indev $ETH \
	action drop

$TC filter add dev $ETH protocol ip prio 30 parent ffff: \
	flower ip_proto 6 \
	indev $ETH \
	action skbedit mark 0x1234

$TC filter add dev $ETH protocol ip prio 10 parent ffff: \
	handle 0x1234 fw action pass

The code was tested and applied on top of commit 3ebeac1 ("Merge branch
'cxgb4-next'")

Changes from V2:
- patch 1/10 ("net/flower: Introduce hardware offload support")
  - Remove unused variable [Dave]
  - Don't fail command when HW can't offload filter [John]
- patch 3/10 ("net/sched: Macro instead of CONFIG_NET_CLS_ACT ifdef")
  - Mention in changelog that struct tc_action is now exposed out of the ifdef.
- patch 4/10 ("net/act_skbedit: Utility functions for mark action")
  - Document clearly that is_tcf_skbedit_mark() is returning true if and only
    if the only action is mark [Dave]
- patch 8/10 ("net/mlx5e: Introduce tc offload support")
  - make mlx5e_tc_add_flow() static

Changes from V1:
- patch 3/10 ("net/sched: Macro instead of CONFIG_NET_CLS_ACT ifdef")
  - fixed return value of tc_no_actions

Changes from V0:
- Use tc_no_actions and tc_for_each_action instead of ifdef CONFIG_NET_CLS_ACT
- Replace ENOTSUPP (and some EINVAL) with EOPNOTSUPP
- Name the flower command enum
- fl_hw_destroy_filter() to return void - nobody uses the return value
- mlx5e_tc_init() and mlx5e_tc_cleanup() to be called from the right places.
- When adding HW rule fails - fail the command
- Rules are added to be processed both by HW and SW unless SKIP_HW is given
- Adding patch 6/10 ("net/mlx5e: Relax ndo_setup_tc handle restriction")

Main changes from the RFC [1]:
- API
  - Using ndo_setup_tc() instead of switchdev
- act_skbedit, act_gact
  - Actions are not serialized to NIC driver, instead using access functions.
- cls_flower
  - prevent double classification by software by not adding
    successfuly offloaded filters to the hashtable
  - Fixed some bugs in original RFC with rule delete
- mlx5
  - Adding flow table to kernel namespace instead of a new namespace
  - s/offload/tc/ in many places
  - no need for a special kconfig since switchdev is not used
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 61 insertions, 7 deletions

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 342be6c..2a19fe1 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -78,11 +78,6 @@ static inline void tcf_lastuse_update(struct tcf_t *tm)
 		tm->lastuse = now;
 }
 
-#ifdef CONFIG_NET_CLS_ACT
-
-#define ACT_P_CREATED 1
-#define ACT_P_DELETED 1
-
 struct tc_action {
 	void			*priv;
 	const struct tc_action_ops	*ops;
@@ -92,6 +87,11 @@ struct tc_action {
 	struct tcf_hashinfo	*hinfo;
 };
 
+#ifdef CONFIG_NET_CLS_ACT
+
+#define ACT_P_CREATED 1
+#define ACT_P_DELETED 1
+
 struct tc_action_ops {
 	struct list_head head;
 	char    kind[IFNAMSIZ];
@@ -171,5 +171,16 @@ int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int);
 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);
 int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int);
+
+#define tc_no_actions(_exts) \
+	(list_empty(&(_exts)->actions))
+
+#define tc_for_each_action(_a, _exts) \
+	list_for_each_entry(a, &(_exts)->actions, list)
+#else /* CONFIG_NET_CLS_ACT */
+
+#define tc_no_actions(_exts) true
+#define tc_for_each_action(_a, _exts) while (0)
+
 #endif /* CONFIG_NET_CLS_ACT */
 #endif
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 8c8548c..d3d60dc 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -184,4 +184,17 @@ static inline bool flow_keys_have_l4(struct flow_keys *keys)
 
 u32 flow_hash_from_keys(struct flow_keys *keys);
 
+static inline bool dissector_uses_key(const struct flow_dissector *flow_dissector,
+				      enum flow_dissector_key_id key_id)
+{
+	return flow_dissector->used_keys & (1 << key_id);
+}
+
+static inline void *skb_flow_dissector_target(struct flow_dissector *flow_dissector,
+					      enum flow_dissector_key_id key_id,
+					      void *target_container)
+{
+	return ((char *)target_container) + flow_dissector->offset[key_id];
+}
+
 #endif
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index bea14ee..5b4e8f0 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -409,4 +409,18 @@ static inline bool tc_should_offload(struct net_device *dev, u32 flags)
 	return true;
 }
 
+enum tc_fl_command {
+	TC_CLSFLOWER_REPLACE,
+	TC_CLSFLOWER_DESTROY,
+};
+
+struct tc_cls_flower_offload {
+	enum tc_fl_command command;
+	u64 cookie;
+	struct flow_dissector *dissector;
+	struct fl_flow_key *mask;
+	struct fl_flow_key *key;
+	struct tcf_exts *exts;
+};
+
 #endif
diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h
index 04a3183..93c520b 100644
--- a/include/net/tc_act/tc_gact.h
+++ b/include/net/tc_act/tc_gact.h
@@ -16,9 +16,9 @@ struct tcf_gact {
 #define to_gact(a) \
 	container_of(a->priv, struct tcf_gact, common)
 
-#ifdef CONFIG_NET_CLS_ACT
 static inline bool is_tcf_gact_shot(const struct tc_action *a)
 {
+#ifdef CONFIG_NET_CLS_ACT
 	struct tcf_gact *gact;
 
 	if (a->ops && a->ops->type != TCA_ACT_GACT)
@@ -28,7 +28,7 @@ static inline bool is_tcf_gact_shot(const struct tc_action *a)
 	if (gact->tcf_action == TC_ACT_SHOT)
 		return true;
 
+#endif
 	return false;
 }
-#endif
 #endif /* __NET_TC_GACT_H */
diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h
index 0df9a0d..b496d5a 100644
--- a/include/net/tc_act/tc_skbedit.h
+++ b/include/net/tc_act/tc_skbedit.h
@@ -20,6 +20,7 @@
 #define __NET_TC_SKBEDIT_H
 
 #include <net/act_api.h>
+#include <linux/tc_act/tc_skbedit.h>
 
 struct tcf_skbedit {
 	struct tcf_common	common;
@@ -32,4 +33,19 @@ struct tcf_skbedit {
 #define to_skbedit(a) \
 	container_of(a->priv, struct tcf_skbedit, common)
 
+/* Return true iff action is mark */
+static inline bool is_tcf_skbedit_mark(const struct tc_action *a)
+{
+#ifdef CONFIG_NET_CLS_ACT
+	if (a->ops && a->ops->type == TCA_ACT_SKBEDIT)
+		return to_skbedit(a)->flags == SKBEDIT_F_MARK;
+#endif
+	return false;
+}
+
+static inline u32 tcf_skbedit_mark(const struct tc_action *a)
+{
+	return to_skbedit(a)->mark;
+}
+
 #endif /* __NET_TC_SKBEDIT_H */