Merge branch 'net-sched-skip_sw'

Asbjørn Sloth Tønnesen says:

====================
make skip_sw actually skip software

During development of flower-route[1], which I
recently presented at FOSDEM[2], I noticed that
CPU usage, would increase the more rules I installed
into the hardware for IP forwarding offloading.

Since we use TC flower offload for the hottest
prefixes, and leave the long tail to the normal (non-TC)
Linux network stack for slow-path IP forwarding.
We therefore need both the hardware and software
datapath to perform well.

I found that skip_sw rules, are quite expensive
in the kernel datapath, since they must be evaluated
and matched upon, before the kernel checks the
skip_sw flag.

This patchset optimizes the case where all rules
are skip_sw, by implementing a TC bypass for these
cases, where TC is only used as a control plane
for the hardware path.

v4:
- Rebased onto net-next, now that net-next is open again

v3: https://lore.kernel.org/netdev/20240306165813.656931-1-ast@fiberby.net/
- Patch 3:
  - Fix source_inline
  - Fix build failure, when CONFIG_NET_CLS without CONFIG_NET_CLS_ACT.

v2: https://lore.kernel.org/netdev/20240305144404.569632-1-ast@fiberby.net/
- Patch 1:
  - Add Reviewed-By from Jiri Pirko
- Patch 2:
  - Move code, to avoid forward declaration (Jiri).
- Patch 3
  - Refactor to use a static key.
  - Add performance data for trapping, or sending
    a packet to a non-existent chain (as suggested by Marcelo).

v1: https://lore.kernel.org/netdev/20240215160458.1727237-1-ast@fiberby.net/

[1] flower-route
    https://github.com/fiberby-dk/flower-route

[2] FOSDEM talk
    https://fosdem.org/2024/schedule/event/fosdem-2024-3337-flying-higher-hardware-offloading-with-bird/
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/pkt_cls.h

@@ -74,6 +74,15 @@ static inline bool tcf_block_non_null_shared(struct tcf_block *block)
 	return block && block->index;
 }
 
+#ifdef CONFIG_NET_CLS_ACT
+DECLARE_STATIC_KEY_FALSE(tcf_bypass_check_needed_key);
+
+static inline bool tcf_block_bypass_sw(struct tcf_block *block)
+{
+	return block && block->bypass_wanted;
+}
+#endif
+
 static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
 {
 	WARN_ON(tcf_block_shared(block));

include/net/sch_generic.h

@@ -422,6 +422,7 @@ struct tcf_proto {
 	 */
 	spinlock_t		lock;
 	bool			deleting;
+	bool			counted;
 	refcount_t		refcnt;
 	struct rcu_head		rcu;
 	struct hlist_node	destroy_ht_node;
@@ -471,6 +472,9 @@ struct tcf_block {
 	struct flow_block flow_block;
 	struct list_head owner_list;
 	bool keep_dst;
+	bool bypass_wanted;
+	atomic_t filtercnt; /* Number of filters */
+	atomic_t skipswcnt; /* Number of skip_sw filters */
 	atomic_t offloadcnt; /* Number of oddloaded filters */
 	unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */
 	unsigned int lockeddevcnt; /* Number of devs that require rtnl lock. */

net/core/dev.c

@@ -2083,6 +2083,11 @@ void net_dec_egress_queue(void)
 EXPORT_SYMBOL_GPL(net_dec_egress_queue);
 #endif
 
+#ifdef CONFIG_NET_CLS_ACT
+DEFINE_STATIC_KEY_FALSE(tcf_bypass_check_needed_key);
+EXPORT_SYMBOL(tcf_bypass_check_needed_key);
+#endif
+
 DEFINE_STATIC_KEY_FALSE(netstamp_needed_key);
 EXPORT_SYMBOL(netstamp_needed_key);
 #ifdef CONFIG_JUMP_LABEL
@@ -3937,6 +3942,11 @@ static int tc_run(struct tcx_entry *entry, struct sk_buff *skb,
 	if (!miniq)
 		return ret;
 
+	if (static_branch_unlikely(&tcf_bypass_check_needed_key)) {
+		if (tcf_block_bypass_sw(miniq->block))
+			return ret;
+	}
+
 	tc_skb_cb(skb)->mru = 0;
 	tc_skb_cb(skb)->post_ct = false;
 	tcf_set_drop_reason(skb, *drop_reason);

net/sched/cls_api.c

@@ -410,12 +410,48 @@ static void tcf_proto_get(struct tcf_proto *tp)
 	refcount_inc(&tp->refcnt);
 }
 
+static void tcf_maintain_bypass(struct tcf_block *block)
+{
+	int filtercnt = atomic_read(&block->filtercnt);
+	int skipswcnt = atomic_read(&block->skipswcnt);
+	bool bypass_wanted = filtercnt > 0 && filtercnt == skipswcnt;
+
+	if (bypass_wanted != block->bypass_wanted) {
+#ifdef CONFIG_NET_CLS_ACT
+		if (bypass_wanted)
+			static_branch_inc(&tcf_bypass_check_needed_key);
+		else
+			static_branch_dec(&tcf_bypass_check_needed_key);
+#endif
+		block->bypass_wanted = bypass_wanted;
+	}
+}
+
+static void tcf_block_filter_cnt_update(struct tcf_block *block, bool *counted, bool add)
+{
+	lockdep_assert_not_held(&block->cb_lock);
+
+	down_write(&block->cb_lock);
+	if (*counted != add) {
+		if (add) {
+			atomic_inc(&block->filtercnt);
+			*counted = true;
+		} else {
+			atomic_dec(&block->filtercnt);
+			*counted = false;
+		}
+	}
+	tcf_maintain_bypass(block);
+	up_write(&block->cb_lock);
+}
+
 static void tcf_chain_put(struct tcf_chain *chain);
 
 static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held,
 			      bool sig_destroy, struct netlink_ext_ack *extack)
 {
 	tp->ops->destroy(tp, rtnl_held, extack);
+	tcf_block_filter_cnt_update(tp->chain->block, &tp->counted, false);
 	if (sig_destroy)
 		tcf_proto_signal_destroyed(tp->chain, tp);
 	tcf_chain_put(tp->chain);
@@ -2364,6 +2400,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 	err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
 			      flags, extack);
 	if (err == 0) {
+		tcf_block_filter_cnt_update(block, &tp->counted, true);
 		tfilter_notify(net, skb, n, tp, block, q, parent, fh,
 			       RTM_NEWTFILTER, false, rtnl_held, extack);
 		tfilter_put(tp, fh);
@@ -3483,6 +3520,8 @@ static void tcf_block_offload_inc(struct tcf_block *block, u32 *flags)
 	if (*flags & TCA_CLS_FLAGS_IN_HW)
 		return;
 	*flags |= TCA_CLS_FLAGS_IN_HW;
+	if (tc_skip_sw(*flags))
+		atomic_inc(&block->skipswcnt);
 	atomic_inc(&block->offloadcnt);
 }
 
@@ -3491,6 +3530,8 @@ static void tcf_block_offload_dec(struct tcf_block *block, u32 *flags)
 	if (!(*flags & TCA_CLS_FLAGS_IN_HW))
 		return;
 	*flags &= ~TCA_CLS_FLAGS_IN_HW;
+	if (tc_skip_sw(*flags))
+		atomic_dec(&block->skipswcnt);
 	atomic_dec(&block->offloadcnt);
 }