From: Laurent Hardy <laurent.hardy@6wind.com>
To: "Dai, Wei" <wei.dai@intel.com>,
Olivier Matz <olivier.matz@6wind.com>,
"dev@dpdk.org" <dev@dpdk.org>,
"Zhang, Helin" <helin.zhang@intel.com>,
"Ananyev, Konstantin" <konstantin.ananyev@intel.com>
Subject: Re: [dpdk-dev] [PATCH v2] net/ixgbe: ensure link status is updated
Date: Mon, 03 Apr 2017 15:23:20 +0200 [thread overview]
Message-ID: <58E24CC8.1080406@6wind.com> (raw)
In-Reply-To: <49759EB36A64CF4892C1AFEC9231E8D650A23CB0@PGSMSX101.gar.corp.intel.com>
Hi Wei,
Thanks for your reply.
If autoneg is false, then we set a default speed to the highest value
before performing the link setup.
You are right, there is no relevant reason to keep this check on speed
mask.
should be:
+ if (!autoneg)
+ speed = IXGBE_LINK_SPEED_10GB_FULL;
Patch has been tested using testpmd with following setups:
Autoneg setup:
=========
- On dut, both ports of 82599 are connected to a switch with 1Gb ports
- auto-negotiate option is enabled on switch
Defined speed setup:
============
- set link speed to 1Gb on both ports of the switch connected to the dut
Test plan:
======
- set down ports on switch before starting testpmd on dut
- start testpmd, then set up ports on switch
- show port on dut through testpmd
without patch:
---------------------
testpmd> show port info 0
********************* Infos for port 0 *********************
MAC address: 00:1B:21:C7:3B:84
Driver name: net_ixgbe
Connect to socket: 0
memory allocation on the socket: 0
Link status: down
Link speed: 0 Mbps
Link duplex: half-duplex
Promiscuous mode: enabled
Allmulticast mode: disabled
Maximum number of MAC addresses: 127
Maximum number of MAC addresses of hash filtering: 4096
VLAN offload:
strip on
filter on
qinq(extend) off
Hash key size in bytes: 40
Redirection table size: 128
Supported flow types:
ipv4
ipv4-tcp
ipv4-udp
ipv6
ipv6-tcp
ipv6-udp
unknown
unknown
unknown
Max possible RX queues: 128
Max possible number of RXDs per queue: 4096
Min possible number of RXDs per queue: 32
RXDs number alignment: 8
Max possible TX queues: 64
Max possible number of TXDs per queue: 4096
Min possible number of TXDs per queue: 32
TXDs number alignment: 8
With patch:
---------------
testpmd> show port info 0
********************* Infos for port 0 *********************
MAC address: 00:1B:21:C7:3B:84
Driver name: net_ixgbe
Connect to socket: 0
memory allocation on the socket: 0
Link status: up
Link speed: 1000 Mbps
Link duplex: full-duplex
Promiscuous mode: enabled
Allmulticast mode: disabled
Maximum number of MAC addresses: 127
Maximum number of MAC addresses of hash filtering: 4096
VLAN offload:
strip on
filter on
qinq(extend) off
Hash key size in bytes: 40
Redirection table size: 128
Supported flow types:
ipv4
ipv4-tcp
ipv4-udp
ipv6
ipv6-tcp
ipv6-udp
unknown
unknown
unknown
Max possible RX queues: 128
Max possible number of RXDs per queue: 4096
Min possible number of RXDs per queue: 32
RXDs number alignment: 8
Max possible TX queues: 64
Max possible number of TXDs per queue: 4096
Min possible number of TXDs per queue: 32
TXDs number alignment: 8
Thanks & regards,
Laurent
On 03/30/2017 06:32 PM, Dai, Wei wrote:
> Hi, Olivier
>
> Has anyone already tested this patch ?
> Can you present some useful info on how to test it ?
> Can I use ethtool with some argument to downgrade or upgrade the rate of peer port ?
>
> I have just run testpmd with 82599, the hw->phy. autoneg_advertised is 0 after rte_eal_init() and rte_eth_dev_start().
> So I think the codes in if (!speed) { ... } is likely to be run.
> I agree with most of your codes.
> But why to limit speed of NIC to 10Gbps if autoneg is false and 10Gbps is supported ?
> In this case, how about setting multiple speed ?
>
> Thanks
> -Wei
>
>
>> -----Original Message-----
>> From: Olivier Matz [mailto:olivier.matz@6wind.com]
>> Sent: Thursday, March 30, 2017 5:20 PM
>> To: dev@dpdk.org; Zhang, Helin <helin.zhang@intel.com>; Ananyev,
>> Konstantin <konstantin.ananyev@intel.com>; Dai, Wei <wei.dai@intel.com>
>> Cc: laurent.hardy@6wind.com
>> Subject: Re: [dpdk-dev] [PATCH v2] net/ixgbe: ensure link status is updated
>>
>> Hi,
>>
>> Can this patch be applied?
>>
>> Thanks,
>> Olivier
>>
>>
>> On Thu, 16 Feb 2017 17:32:01 +0100, Olivier Matz <olivier.matz@6wind.com>
>> wrote:
>>> From: Laurent Hardy <laurent.hardy@6wind.com>
>>>
>>> In case of fiber and link speed set to 1Gb at peer side (with autoneg
>>> or with defined speed), link status could be not properly updated at
>>> time cable is plugged-in.
>>> Indeed if cable was not plugged when device has been configured and
>>> started then link status will not be updated properly with new speed
>>> as no link setup will be triggered.
>>>
>>> To avoid this issue, IXGBE_FLAG_NEED_LINK_CONFIG is set to try a link
>>> setup each time link_update() is triggered and current link status is
>>> down. When cable is plugged-in, link setup will be performed via
>>> ixgbe_setup_link().
>>>
>>> Signed-off-by: Laurent Hardy <laurent.hardy@6wind.com>
>>> ---
>>>
>>> v1 -> v2:
>>> - rebase on top of head (change flag to 1<<4)
>>> - fix regression with copper links: only update link for fiber links
>>>
>>> drivers/net/ixgbe/ixgbe_ethdev.c | 21 +++++++++++++++++++++
>>> drivers/net/ixgbe/ixgbe_ethdev.h | 1 +
>>> 2 files changed, 22 insertions(+)
>>>
>>> diff --git a/drivers/net/ixgbe/ixgbe_ethdev.c
>>> b/drivers/net/ixgbe/ixgbe_ethdev.c
>>> index 0b89598..1114106 100644
>>> --- a/drivers/net/ixgbe/ixgbe_ethdev.c
>>> +++ b/drivers/net/ixgbe/ixgbe_ethdev.c
>>> @@ -2357,6 +2357,7 @@ ixgbe_dev_configure(struct rte_eth_dev *dev)
>>>
>>> /* set flag to update link status after init */
>>> intr->flags |= IXGBE_FLAG_NEED_LINK_UPDATE;
>>> + intr->flags |= IXGBE_FLAG_NEED_LINK_CONFIG;
>>>
>>> /*
>>> * Initialize to TRUE. If any of Rx queues doesn't meet the bulk @@
>>> -3515,8 +3516,12 @@ ixgbe_dev_link_update(struct rte_eth_dev *dev, int
>> wait_to_complete)
>>> struct ixgbe_hw *hw =
>> IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private);
>>> struct rte_eth_link link, old;
>>> ixgbe_link_speed link_speed = IXGBE_LINK_SPEED_UNKNOWN;
>>> + struct ixgbe_interrupt *intr =
>>> + IXGBE_DEV_PRIVATE_TO_INTR(dev->data->dev_private);
>>> int link_up;
>>> int diag;
>>> + u32 speed = 0;
>>> + bool autoneg = false;
>>>
>>> link.link_status = ETH_LINK_DOWN;
>>> link.link_speed = 0;
>>> @@ -3526,6 +3531,20 @@ ixgbe_dev_link_update(struct rte_eth_dev *dev,
>>> int wait_to_complete)
>>>
>>> hw->mac.get_link_status = true;
>>>
>>> + if ((intr->flags & IXGBE_FLAG_NEED_LINK_CONFIG) &&
>>> + hw->mac.ops.get_media_type(hw) == ixgbe_media_type_fiber) {
>>> + speed = hw->phy.autoneg_advertised;
>>> + if (!speed) {
>>> + ixgbe_get_link_capabilities(hw, &speed, &autoneg);
>>> + /* setup the highest link when no autoneg */
>>> + if (!autoneg) {
>>> + if (speed & IXGBE_LINK_SPEED_10GB_FULL)
>>> + speed = IXGBE_LINK_SPEED_10GB_FULL;
>>> + }
>>> + }
>>> + ixgbe_setup_link(hw, speed, true);
>>> + }
>>> +
>>> /* check if it needs to wait to complete, if lsc interrupt is enabled */
>>> if (wait_to_complete == 0 || dev->data->dev_conf.intr_conf.lsc != 0)
>>> diag = ixgbe_check_link(hw, &link_speed, &link_up, 0); @@ -3543,10
>>> +3562,12 @@ ixgbe_dev_link_update(struct rte_eth_dev *dev, int
>>> wait_to_complete)
>>>
>>> if (link_up == 0) {
>>> rte_ixgbe_dev_atomic_write_link_status(dev, &link);
>>> + intr->flags |= IXGBE_FLAG_NEED_LINK_CONFIG;
>>> if (link.link_status == old.link_status)
>>> return -1;
>>> return 0;
>>> }
>>> + intr->flags &= ~IXGBE_FLAG_NEED_LINK_CONFIG;
>>> link.link_status = ETH_LINK_UP;
>>> link.link_duplex = ETH_LINK_FULL_DUPLEX;
>>>
>>> diff --git a/drivers/net/ixgbe/ixgbe_ethdev.h
>>> b/drivers/net/ixgbe/ixgbe_ethdev.h
>>> index aabbb00..bed4379 100644
>>> --- a/drivers/net/ixgbe/ixgbe_ethdev.h
>>> +++ b/drivers/net/ixgbe/ixgbe_ethdev.h
>>> @@ -45,6 +45,7 @@
>>> #define IXGBE_FLAG_MAILBOX (uint32_t)(1 << 1)
>>> #define IXGBE_FLAG_PHY_INTERRUPT (uint32_t)(1 << 2)
>>> #define IXGBE_FLAG_MACSEC (uint32_t)(1 << 3)
>>> +#define IXGBE_FLAG_NEED_LINK_CONFIG (uint32_t)(1 << 4)
>>>
>>> /*
>>> * Defines that were not part of ixgbe_type.h as they are not used by
>>> the
next prev parent reply other threads:[~2017-04-03 13:23 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-11-17 17:29 [dpdk-dev] [PATCH] " Laurent Hardy
2016-11-28 17:27 ` Laurent Hardy
2016-12-08 17:10 ` Ferruh Yigit
2017-02-01 14:14 ` Thomas Monjalon
2017-02-08 15:51 ` Dai, Wei
2017-02-08 17:03 ` Olivier MATZ
2017-02-13 3:17 ` Dai, Wei
2017-02-16 16:32 ` [dpdk-dev] [PATCH v2] " Olivier Matz
2017-03-30 9:19 ` Olivier Matz
2017-03-30 16:32 ` Dai, Wei
2017-04-03 13:23 ` Laurent Hardy [this message]
2017-04-10 13:36 ` Ferruh Yigit
2017-04-11 12:13 ` Laurent Hardy
2017-04-12 8:21 ` [dpdk-dev] [PATCH] " Laurent Hardy
2017-04-18 14:33 ` Dai, Wei
2017-04-27 15:03 ` [dpdk-dev] [PATCH v4] " Laurent Hardy
2017-04-28 0:43 ` Dai, Wei
2017-04-28 5:23 ` Ferruh Yigit
2017-05-17 13:31 ` Roger B Melton
2017-05-22 18:54 ` [dpdk-dev] 2nd try: problem with ixgbe_dev_link_update() for multi-speed fiber [was] " Roger B. Melton
2017-05-23 7:24 ` Dai, Wei
2017-05-23 7:41 ` Dai, Wei
2017-05-24 14:40 ` Roger B. Melton
2017-05-24 18:38 ` Roger B. Melton
2017-06-02 16:15 ` Roger B. Melton
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=58E24CC8.1080406@6wind.com \
--to=laurent.hardy@6wind.com \
--cc=dev@dpdk.org \
--cc=helin.zhang@intel.com \
--cc=konstantin.ananyev@intel.com \
--cc=olivier.matz@6wind.com \
--cc=wei.dai@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).