[dpdk-dev] Problem with using VF: Initialization Failure: -15

Rosen, Rami rami.rosen at intel.com
Fri Apr 13 09:03:23 CEST 2018


Hi, Michal,

First, I believe that such questions suit better to the dpdk-users mailing list.

>I've investigated the issue, and the problem is with:
>diag = hw->mac.ops.reset_hw(hw);
>which calls:
>e1000_reset_hw_vf
>and it calls:
>e1000_read_posted_mbx
>Which returns: E1000_ERR_MBX (-15)

Are you sure about it ? the path that you present in your investigation 
is from drivers/net/e1000, whereas the test that you ran is on top of ixgbe, 
which has a different PMD driver (drivers/net/ixgbe). The setup that you describe does not use e1000 device at all, according to my understanding.

Regards,
Rami Rosen


-----Original Message-----
From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Weglicki, MichalX
Sent: Wednesday, April 11, 2018 15:01
To: dev at dpdk.org
Subject: [dpdk-dev] Problem with using VF: Initialization Failure: -15

Hello,

I'm trying to test very simple scenario, creating two VFs and testing it with test-pmd. Unfortunately I can't make it to work DPDK Version: v17.11 (I've checked also 18.02)
NIC: Niantic 82599ES 10-Gigabit SFI/SFP+ Network Connection 10fb
Kernel: 4.4.0-116-generic #140-Ubuntu SMP Mon Feb 12 21:23:04 UTC 2018 x86_64 x86_64 x86_64 GNU/Linux

Steps:
Creating two VFs. Binding each VF to a driver (I also tried vfio_pci with same results):
../dpdk/usertools/dpdk-devbind.py --bind=igb_uio 0000:81:10.0 ../dpdk/usertools/dpdk-devbind.py --bind=igb_uio 0000:81:10.1

./testpmd -c 0x3 -n 4 --socket-mem 512 -- --burst=64 -i --txqflags=0xf00 --disable-hw-vlan
EAL: Detected 56 lcore(s)
EAL: Probing VFIO support...
EAL: VFIO support initialized
EAL: PCI device 0000:03:00.0 on NUMA socket -1
EAL:   Invalid NUMA socket, default to 0
EAL:   probe driver: 8086:1521 net_e1000_igb
EAL: PCI device 0000:03:00.3 on NUMA socket -1
EAL:   Invalid NUMA socket, default to 0
EAL:   probe driver: 8086:1521 net_e1000_igb
EAL: PCI device 0000:05:00.0 on NUMA socket -1
EAL:   Invalid NUMA socket, default to 0
EAL:   probe driver: 8086:10fb net_ixgbe
EAL: PCI device 0000:05:00.1 on NUMA socket -1
EAL:   Invalid NUMA socket, default to 0
EAL:   probe driver: 8086:10fb net_ixgbe
EAL: PCI device 0000:81:00.0 on NUMA socket -1
EAL:   Invalid NUMA socket, default to 0
EAL:   probe driver: 8086:10fb net_ixgbe
EAL: PCI device 0000:81:00.1 on NUMA socket -1
EAL:   Invalid NUMA socket, default to 0
EAL:   probe driver: 8086:10fb net_ixgbe
EAL: PCI device 0000:81:10.0 on NUMA socket -1
EAL:   Invalid NUMA socket, default to 0
EAL:   probe driver: 8086:10ed net_ixgbe_vf
PMD: eth_ixgbevf_dev_init(): VF Initialization Failure: -15
EAL: Requested device 0000:81:10.0 cannot be used
EAL: PCI device 0000:81:10.1 on NUMA socket -1
EAL:   Invalid NUMA socket, default to 0
EAL:   probe driver: 8086:10ed net_ixgbe_vf
PMD: eth_ixgbevf_dev_init(): VF Initialization Failure: -15
EAL: Requested device 0000:81:10.1 cannot be used
EAL: PCI device 0000:83:00.0 on NUMA socket -1
EAL:   Invalid NUMA socket, default to 0
EAL:   probe driver: 8086:10fb net_ixgbe
EAL: PCI device 0000:83:00.1 on NUMA socket -1
EAL:   Invalid NUMA socket, default to 0
EAL:   probe driver: 8086:10fb net_ixgbe
EAL: No probed ethernet devices
Interactive-mode selected

I've investigated the issue, and the problem is with:
diag = hw->mac.ops.reset_hw(hw);
which calls:
e1000_reset_hw_vf
and it calls:
e1000_read_posted_mbx
Which returns: E1000_ERR_MBX (-15)

Is this common issue, or some configuration problem?

Thank you all in advance.

Br,
Michal.


More information about the dev mailing list