mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-27 21:03:32 +00:00
6a9a45616b
commit e131a56348 upstream.
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>
Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: Pali Rohár <pali@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
57 lines
1 KiB
Text
57 lines
1 KiB
Text
config HAVE_NET_DSA
|
|
def_bool y
|
|
depends on INET && NETDEVICES && !S390
|
|
|
|
# Drivers must select NET_DSA and the appropriate tagging format
|
|
|
|
config NET_DSA
|
|
tristate "Distributed Switch Architecture"
|
|
depends on HAVE_NET_DSA && MAY_USE_DEVLINK
|
|
depends on BRIDGE || BRIDGE=n
|
|
select GRO_CELLS
|
|
select NET_SWITCHDEV
|
|
select PHYLINK
|
|
---help---
|
|
Say Y if you want to enable support for the hardware switches supported
|
|
by the Distributed Switch Architecture.
|
|
|
|
if NET_DSA
|
|
|
|
config NET_DSA_LEGACY
|
|
bool "Support for older platform device and Device Tree registration"
|
|
default y
|
|
---help---
|
|
Say Y if you want to enable support for the older platform device and
|
|
deprecated Device Tree binding registration.
|
|
|
|
This feature is scheduled for removal in 4.17.
|
|
|
|
# tagging formats
|
|
config NET_DSA_TAG_BRCM
|
|
bool
|
|
|
|
config NET_DSA_TAG_BRCM_PREPEND
|
|
bool
|
|
|
|
config NET_DSA_TAG_DSA
|
|
bool
|
|
|
|
config NET_DSA_TAG_EDSA
|
|
bool
|
|
|
|
config NET_DSA_TAG_KSZ
|
|
bool
|
|
|
|
config NET_DSA_TAG_LAN9303
|
|
bool
|
|
|
|
config NET_DSA_TAG_MTK
|
|
bool
|
|
|
|
config NET_DSA_TAG_TRAILER
|
|
bool
|
|
|
|
config NET_DSA_TAG_QCA
|
|
bool
|
|
|
|
endif
|