@@ -9,6 +9,7 @@ menuconfig NET_DSA
tristate "Distributed Switch Architecture"
depends on HAVE_NET_DSA
depends on BRIDGE || BRIDGE=n
+ select GRO_CELLS
select NET_SWITCHDEV
select PHYLINK
select NET_DEVLINK
@@ -234,7 +234,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
if (dsa_skb_defer_rx_timestamp(p, skb))
return 0;
- netif_receive_skb(skb);
+ gro_cells_receive(&p->gcells, skb);
return 0;
}
@@ -11,6 +11,7 @@
#include <linux/netdevice.h>
#include <linux/netpoll.h>
#include <net/dsa.h>
+#include <net/gro_cells.h>
enum {
DSA_NOTIFIER_AGEING_TIME,
@@ -77,6 +78,8 @@ struct dsa_slave_priv {
struct pcpu_sw_netstats *stats64;
+ struct gro_cells gcells;
+
/* DSA port data, such as switch, port index, etc. */
struct dsa_port *dp;
@@ -1762,6 +1762,11 @@ int dsa_slave_create(struct dsa_port *port)
free_netdev(slave_dev);
return -ENOMEM;
}
+
+ ret = gro_cells_init(&p->gcells, slave_dev);
+ if (ret)
+ goto out_free;
+
p->dp = port;
INIT_LIST_HEAD(&p->mall_tc_list);
p->xmit = cpu_dp->tag_ops->xmit;
@@ -1781,7 +1786,7 @@ int dsa_slave_create(struct dsa_port *port)
ret = dsa_slave_phy_setup(slave_dev);
if (ret) {
netdev_err(master, "error %d setting up slave phy\n", ret);
- goto out_free;
+ goto out_gcells;
}
dsa_slave_notify(slave_dev, DSA_PORT_REGISTER);
@@ -1800,6 +1805,8 @@ int dsa_slave_create(struct dsa_port *port)
phylink_disconnect_phy(p->dp->pl);
rtnl_unlock();
phylink_destroy(p->dp->pl);
+out_gcells:
+ gro_cells_destroy(&p->gcells);
out_free:
free_percpu(p->stats64);
free_netdev(slave_dev);
@@ -1820,6 +1827,7 @@ void dsa_slave_destroy(struct net_device *slave_dev)
dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER);
unregister_netdev(slave_dev);
phylink_destroy(dp->pl);
+ gro_cells_destroy(&p->gcells);
free_percpu(p->stats64);
free_netdev(slave_dev);
}
gro_cells lib is used by different encapsulating netdevices, such as geneve, macsec, vxlan etc. to speed up decapsulated traffic processing. CPU tag is a sort of "encapsulation", and we can use the same mechs to greatly improve overall DSA performance. skbs are passed to the GRO layer after removing CPU tags, so we don't need any new packet offload types as it was firstly proposed by me in the first GRO-over-DSA variant [1]. The size of struct gro_cells is sizeof(void *), so hot struct dsa_slave_priv becomes only 4/8 bytes bigger, and all critical fields remain in one 32-byte cacheline. The other positive side effect is that drivers for network devices that can be shipped as CPU ports of DSA-driven switches can now use napi_gro_frags() to pass skbs to kernel. Packets built that way are completely non-linear and are likely being dropped without GRO. This was tested on to-be-mainlined-soon Ethernet driver that uses napi_gro_frags(), and the overall performance was on par with the variant from [1], sometimes even better due to minimal overhead. net.core.gro_normal_batch tuning may help to push it to the limit on particular setups and platforms. iperf3 IPoE VLAN NAT TCP forwarding (port1.218 -> port0) setup on 1.2 GHz MIPS board: 5.7-rc2 baseline: [ID] Interval Transfer Bitrate Retr [ 5] 0.00-120.01 sec 9.00 GBytes 644 Mbits/sec 413 sender [ 5] 0.00-120.00 sec 8.99 GBytes 644 Mbits/sec receiver Iface RX packets TX packets eth0 7097731 7097702 port0 426050 6671829 port1 6671681 425862 port1.218 6671677 425851 With this patch: [ID] Interval Transfer Bitrate Retr [ 5] 0.00-120.01 sec 12.2 GBytes 870 Mbits/sec 122 sender [ 5] 0.00-120.00 sec 12.2 GBytes 870 Mbits/sec receiver Iface RX packets TX packets eth0 9474792 9474777 port0 455200 353288 port1 9019592 455035 port1.218 353144 455024 v2: - Add some performance examples in the commit message; - No functional changes. [1] https://lore.kernel.org/netdev/20191230143028.27313-1-alobakin@dlink.ru/ Signed-off-by: Alexander Lobakin <bloodyreaper@yandex.ru> --- net/dsa/Kconfig | 1 + net/dsa/dsa.c | 2 +- net/dsa/dsa_priv.h | 3 +++ net/dsa/slave.c | 10 +++++++++- 4 files changed, 14 insertions(+), 2 deletions(-)