Thread (2 messages) 2 messages, 1 author, 2021-03-31

RE: [PATCH net-next v3 0/6] stmmac: Add XDP support

From: Ong, Boon Leong <hidden>
Date: 2021-03-31 15:34:09
Also in: bpf, lkml, netdev

Pls ignore this. I will resend the real v3. Sorry for glitch on my part. 
quoted hunk ↗ jump to hunk
-----Original Message-----
From: Ong, Boon Leong <redacted>
Sent: Wednesday, March 31, 2021 11:36 PM
To: Giuseppe Cavallaro <redacted>; Alexandre Torgue
[off-list ref]; Jose Abreu [off-list ref]; David S .
Miller [off-list ref]; Jakub Kicinski [off-list ref]; Alexei
Starovoitov [off-list ref]; Daniel Borkmann [off-list ref];
Jesper Dangaard Brouer [off-list ref]; John Fastabend
[off-list ref]
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>; Andrii Nakryiko
[off-list ref]; Martin KaFai Lau [off-list ref]; Song Liu
[off-list ref]; Yonghong Song [off-list ref]; KP Singh
[off-list ref]; netdev@vger.kernel.org; linux-stm32@st-md-
mailman.stormreply.com; linux-arm-kernel@lists.infradead.org; linux-
kernel@vger.kernel.org; bpf@vger.kernel.org; Ong, Boon Leong
[off-list ref]
Subject: [PATCH net-next v3 0/6] stmmac: Add XDP support

Hi,

This is the v3 patch series for adding XDP support to stmmac driver.

Summary of the changes in v3 (per feedback from Jakub Kicinski):-

4/6: Factor in XDP buffer header and tail adjustment by XDP prog.

5/6: Added 'nq->trans_start = jiffies' to avoid TX time-out for XDP_TX.

6/6: Added 'nq->trans_start = jiffies' to avoid TX time-out for
    ndo_xdp_xmit.

I retested this patch series on all the test steps listed in v1 and the
results look good as expected. I also used xdp_adjust_tail test app in
samples/bpf for checking out XDP head and tail adjustment introduced in
4/6 and the result below looks correct too.


###########################################################
#############

DUT > root@intel-corei7-64:~ $ ./xdp_adjust_tail -i eth0 -P 400 -N
==========================
icmp "packet too big" sent:          0 pkts
icmp "packet too big" sent:          0 pkts
icmp "packet too big" sent:          0 pkts
icmp "packet too big" sent:          0 pkts
icmp "packet too big" sent:          1 pkts
icmp "packet too big" sent:          1 pkts
icmp "packet too big" sent:          1 pkts
icmp "packet too big" sent:          2 pkts
icmp "packet too big" sent:          4 pkts
icmp "packet too big" sent:          6 pkts
icmp "packet too big" sent:          8 pkts
icmp "packet too big" sent:          9 pkts
icmp "packet too big" sent:         10 pkts
icmp "packet too big" sent:         10 pkts

LP > root@intel-corei7-64:~# ping 169.254.1.11 -s 300
PING 169.254.1.11 (169.254.1.11) 300(328) bytes of data.
308 bytes from 169.254.1.11: icmp_seq=1 ttl=64 time=1.17 ms
308 bytes from 169.254.1.11: icmp_seq=2 ttl=64 time=0.575 ms
308 bytes from 169.254.1.11: icmp_seq=3 ttl=64 time=0.582 ms
308 bytes from 169.254.1.11: icmp_seq=4 ttl=64 time=0.595 ms
308 bytes from 169.254.1.11: icmp_seq=5 ttl=64 time=0.585 ms
308 bytes from 169.254.1.11: icmp_seq=6 ttl=64 time=0.591 ms
308 bytes from 169.254.1.11: icmp_seq=7 ttl=64 time=0.599 ms
^C
--- 169.254.1.11 ping statistics ---
7 packets transmitted, 7 received, 0% packet loss, time 6103ms
rtt min/avg/max/mdev = 0.575/0.670/1.166/0.202 ms

LP >  root@intel-corei7-64:~# ping 169.254.1.11 -s 500
PING 169.254.1.11 (169.254.1.11) 500(528) bytes of data.
From 169.254.1.11 icmp_seq=1 Frag needed and DF set (mtu = 436)
From 169.254.1.11 icmp_seq=2 Frag needed and DF set (mtu = 436)
From 169.254.1.11 icmp_seq=3 Frag needed and DF set (mtu = 436)
From 169.254.1.11 icmp_seq=4 Frag needed and DF set (mtu = 436)
From 169.254.1.11 icmp_seq=5 Frag needed and DF set (mtu = 436)
From 169.254.1.11 icmp_seq=6 Frag needed and DF set (mtu = 436)


###########################################################
#############

History of the previous patch series:

v2: https://patchwork.kernel.org/project/netdevbpf/list/?series=457757
v1: https://patchwork.kernel.org/project/netdevbpf/list/?series=457139

It will be great if community can help to test or review the v3 patch
series on your platform and provide me any new feedback if any.

Thank you very much.
Boon Leong

Ong Boon Leong (6):
 net: stmmac: set IRQ affinity hint for multi MSI vectors
 net: stmmac: make SPH enable/disable to be configurable
 net: stmmac: arrange Tx tail pointer update to
   stmmac_flush_tx_descriptors
 net: stmmac: Add initial XDP support
 net: stmmac: Add support for XDP_TX action
 net: stmmac: Add support for XDP_REDIRECT action

drivers/net/ethernet/stmicro/stmmac/Makefile  |   1 +
drivers/net/ethernet/stmicro/stmmac/stmmac.h  |  35 +-
.../net/ethernet/stmicro/stmmac/stmmac_main.c | 529 +++++++++++++++-
--
.../net/ethernet/stmicro/stmmac/stmmac_xdp.c  |  40 ++
.../net/ethernet/stmicro/stmmac/stmmac_xdp.h  |  12 +
5 files changed, 537 insertions(+), 80 deletions(-)
create mode 100644 drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c
create mode 100644 drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.h

--
2.25.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help