bcm53xx: enable & setup packet steering

Packet steering can improve NAT masquarade performance on Northstar by
40-50%. It makes reaching 940-942 Mb/s possible on BCM4708 (and
obviously BCM47094 too). Add scripts setting up the most optimal
Northstar setup.

Below are testing results for running iperf TCP traffic from LAN to WAN.
They were used to pick up golden values.

┌──────────┬──────────┬────────────────────┬────────────────────┐
│   eth0   │  br-lan  │ flow_offloading=0  │ flow_offloading=1  │
│          │          ├─────────┬──────────┼─────────┬──────────┤
│ rps_cpus │ rps_cpus │ BCM4708 │ BCM47094 │ BCM4708 │ BCM47094 │
├──────────┼──────────┼─────────┼──────────┼─────────┼──────────┤
│        0 │        0 │     387 │      671 │     707 │      941 │
│        0 │        1 │     343 │      576 │     705 │      941 │
│        0 │        2 │   ✓ 574 │    ✓ 941 │     704 │      940 │
│        1 │        0 │     320 │      549 │     561 │      941 │
│        1 │        1 │     327 │      551 │     553 │      941 │
│        1 │        2 │     523 │    ✓ 940 │     559 │      940 │
│        2 │        0 │     383 │      652 │   ✓ 940 │      941 │
│        2 │        1 │     448 │      754 │   ✓ 942 │      941 │
│        2 │        2 │     404 │      655 │   ✓ 941 │      941 │
└──────────┴──────────┴─────────┴──────────┴─────────┴──────────┘

Above tests were performed with all eth0 interrupts handled by CPU0.
Setting "echo 2 > /proc/irq/38/smp_affinity" was tested on BCM4708 but
it didn't increased speeds (just required different steering):

┌──────────┬──────────┬───────────┐
│   eth0   │  br-lan  │ flow_offl │
│   rx-0   │   rx-0   │ oading=0  │
│ rps_cpus │ rps_cpus │  BCM4708  │
├──────────┼──────────┼───────────┤
│        0 │        0 │       384 │
│        0 │        1 │     ✓ 574 │
│        0 │        2 │       348 │
│        1 │        0 │       383 │
│        1 │        1 │       412 │
│        1 │        2 │       448 │
│        2 │        0 │       321 │
│        2 │        1 │       520 │
│        2 │        2 │       327 │
└──────────┴──────────┴───────────┘

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>

target/linux/bcm53xx/base-files/etc/init.d/fastnetwork

@@ -0,0 +1,44 @@
+#!/bin/sh /etc/rc.common
+
+START=25
+USE_PROCD=1
+
+start_service() {
+	reload_service
+}
+
+service_triggers() {
+	procd_add_reload_trigger "network"
+	procd_add_reload_trigger "firewall"
+	procd_add_reload_interface_trigger "lan"
+}
+
+reload_service() {
+	local packet_steering="$(uci -q get network.@globals[0].packet_steering)"
+	local num_cpus="$(grep -c "^processor.*:" /proc/cpuinfo)"
+	local flow_offloading="$(uci -q get firewall.@defaults[0].flow_offloading)"
+	local flow_offloading_hw="$(uci -q get firewall.@defaults[0].flow_offloading_hw)"
+
+	# Any steering on 1 CPU (BCM47081) worsens network performance
+	[ "$num_cpus" != 2 ] && return
+
+	[ "$packet_steering" != 1 ] && {
+		echo 0 > /sys/class/net/br-lan/queues/rx-0/rps_cpus
+		echo 0 > /sys/class/net/eth0/queues/rx-0/rps_cpus
+		return
+	}
+
+	if [ ${flow_offloading_hw:-0} -gt 0 ]; then
+		# HW offloading
+		echo 0 > /sys/class/net/br-lan/queues/rx-0/rps_cpus
+		echo 0 > /sys/class/net/eth0/queues/rx-0/rps_cpus
+	elif [ ${flow_offloading:-0} -gt 0 ]; then
+		# SW offloading
+		# br-lan setup doesn't seem to matter for offloading case
+		echo 2 > /sys/class/net/eth0/queues/rx-0/rps_cpus
+	else
+		# Default
+		echo 2 > /sys/class/net/br-lan/queues/rx-0/rps_cpus
+		echo 0 > /sys/class/net/eth0/queues/rx-0/rps_cpus
+	fi
+}

target/linux/bcm53xx/base-files/etc/uci-defaults/05_packet_steering

@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+uci set network.@globals[0].packet_steering="1"