[dpdk-dev] i40e_aq_get_phy_capabilities() fails when using SFP+ with no link

[Zhang, Helin]

Hi Aaron

Is the SFP+ (Finisar FTLX8571D3BCL) supported and validated by Intel?
It seems there is some PHY issue in this case.

Regards,
Helin

-----Original Message-----
From: Olivier MATZ [mailto:olivier.matz at 6wind.com] 
Sent: Tuesday, January 10, 2017 11:29 PM
To: Christos Ricudis <ricudis.christos at gmail.com>
Cc: dev at dpdk.org; Zhang, Helin <helin.zhang at intel.com>; Wu, Jingjing <jingjing.wu at intel.com>
Subject: Re: [dpdk-dev] i40e_aq_get_phy_capabilities() fails when using SFP+ with no link

Hi Christos,

+CC i40e maintainers

On Tue, 10 Jan 2017 20:32:26 +0800, Christos Ricudis <ricudis.christos at gmail.com> wrote:
> Hello,
> 
> Using a X710 based 4-port 4x10Gbit NIC, I have came across the 
> following issue on the i40e PMD:
> 
> When an optical SFP+ (Finisar FTLX8571D3BCL) is used with no active 
> link partner on the other end of the link (or fiber completely 
> disconnected from the SFP+), i40e_aq_get_phy_capabilities() (called by 
> i40e_dev_sync_phy_type() on port initialization), fails with a
> 0x05 return value (EIO) on the AQ response structure. The struct 
> i40e_aq_get_phy_abilities_resp buffer passed to the Get Phy Abilities 
> command is unmodified upon return.
> 
> This prevents DPDK 16.11 from initializing the port, and ultimately 
> fails with the following error:
> 
> PMD: eth_i40e_dev_init(): Failed to sync phy type: -95
> 
> The change introducing this issue was
> http://dpdk.org/ml/archives/dev/2016-September/047663.html
> 
> Reading the X710 datasheet, I notice that no specific mention is given 
> on the meaning of EIO as a response to Get PHY Abilities command 
> (opcode 0x0600), whereas in most other commands, an explicit mention 
> of the meaning of the possible error status responses is given.
> 
> This behaviour is the same across the following NVM releases: 
> 
> FW 4.33 API 1.2 NVM 04.04.02 eetrack 800018a6 FW 4.40 API 1.4 NVM 
> 04.05.03 eetrack 80001cd8 FW 5.0 API 1.5 NVM 05.00.04 eetrack 800024da
> 
> I will try to get around the issue by falling back to PHY capabilities 
> detection using the device ID in the case
> i40e_aq_get_phy_capabilities() fails, but conceptually the 
> capabilities of the PHY should not be dependent on whether PHY detects 
> an active link or not.
> 
> I’d be happy to do more testing on this issue per your 
> recommendations.
> 
> Moreover, while trying to debug this issue, I managed to get both 3 
> NIC adapters on my test system on a state where the PHY has apparently 
> died - no link indication at all on any ports. A reboot solved this, 
> and I am now trying to replicate this behaviour under more controlled 
> conditions.
> 

I'm currently running into a similar issue (I think). I can reproduce it with testpmd with the following case:

  set link_check off
  port stop 0
  # don't wait between these 2 commands
  port start 0

I added some logs that are displayed after the port start:

  PMD: i40e_set_tx_function(): Vector tx finally be used.
  PMD: i40e_set_rx_function(): Vector rx enabled, please make sure RX
    burst size no less than 4 (port=0).
  PMD: i40e_dev_rx_queue_start():  >>
  PMD: i40e_dev_tx_queue_start():  >>
  PMD: i40e_dev_start(): applying link settings...
  PMD: i40e_apply_link_speed(): abilities = 38, speed = 0
  PMD: i40e_phy_conf_link(): i40e_aq_get_phy_capabilities failed -7
  PMD: i40e_dev_start(): Fail to apply link setting
  PMD: i40e_dev_clear_queues():  >>

The -7 corresponds to I40E_ERR_UNKNOWN_PHY. This happens in
i40e_aq_get_phy_capabilities() in the following code, which makes me think it's the same problem than yours:

	if (hw->aq.asq_last_status == I40E_AQ_RC_EIO)
		status = I40E_ERR_UNKNOWN_PHY;

A workaround in my usecase is to wait a bit between the stop and the start.

Any help is welcome.

Regards,
Olivier