PCI passthrough of 40G ethernet interface (Openstack/KVM)

From: jacob jacob <opstkusr@gmail.com>
To: QEMU Developers <qemu-devel@nongnu.org>, kvm-devel <kvm@vger.kernel.org>
Subject: PCI passthrough of 40G ethernet interface (Openstack/KVM)
Date: Thu, 12 Mar 2015 12:17:40 -0400	[thread overview]
Message-ID: <CA+AkT2g=vFxKAUrHzWDxPzfq_SNvOUJvzHe5YsX+p+p6Ad8hog@mail.gmail.com> (raw)

 Hi,

 Seeing failures when trying to do PCI passthrough of Intel XL710 40G
interface to KVM vm.
     0a:00.1 Ethernet controller: Intel Corporation Ethernet
Controller XL710 for 40GbE QSFP+ (rev 01)

>From dmesg on host:

> [80326.559674] kvm: zapping shadow pages for mmio generation wraparound
> [80327.271191] kvm [175994]: vcpu0 unhandled rdmsr: 0x1c9
> [80327.271689] kvm [175994]: vcpu0 unhandled rdmsr: 0x1a6
> [80327.272201] kvm [175994]: vcpu0 unhandled rdmsr: 0x1a7
> [80327.272681] kvm [175994]: vcpu0 unhandled rdmsr: 0x3f6
> [80327.376186] kvm [175994]: vcpu0 unhandled rdmsr: 0x606
>
 The pci device is still available in the VM but stat transfer fails.

 With the i40e driver, the data transfer fails.
 Relevant dmesg output:

>  [   11.544088] i40e 0000:00:05.0 eth1: NIC Link is Up 40 Gbps Full Duplex, Flow Control: None
> [   11.689178] i40e 0000:00:06.0 eth2: NIC Link is Up 40 Gbps Full Duplex, Flow Control: None
> [   16.704071] ------------[ cut here ]------------
> [   16.705053] WARNING: CPU: 1 PID: 0 at net/sched/sch_generic.c:303 dev_watchdog+0x23e/0x250()
> [   16.705053] NETDEV WATCHDOG: eth1 (i40e): transmit queue 1 timed out
> [   16.705053] Modules linked in: cirrus ttm drm_kms_helper i40e drm ppdev serio_raw i2c_piix4 virtio_net parport_pc ptp virtio_balloon crct10dif_pclmul pps_core parport pvpanic crc32_pclmul ghash_clmulni_intel virtio_blk crc32c_intel virtio_pci virtio_ring virtio ata_generic pata_acpi
> [   16.705053] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.18.7-200.fc21.x86_64 #1
> [   16.705053] Hardware name: Fedora Project OpenStack Nova, BIOS 1.7.5-20140709_153950- 04/01/2014
> [   16.705053]  0000000000000000 2e5932b294d0c473 ffff88043fc83d48 ffffffff8175e686
> [   16.705053]  0000000000000000 ffff88043fc83da0 ffff88043fc83d88 ffffffff810991d1
> [   16.705053]  ffff88042958f5c0 0000000000000001 ffff88042865f000 0000000000000001
> [   16.705053] Call Trace:
> [   16.705053]  <IRQ>  [<ffffffff8175e686>] dump_stack+0x46/0x58
> [   16.705053]  [<ffffffff810991d1>] warn_slowpath_common+0x81/0xa0
> [   16.705053]  [<ffffffff81099245>] warn_slowpath_fmt+0x55/0x70
> [   16.705053]  [<ffffffff8166e62e>] dev_watchdog+0x23e/0x250
> [   16.705053]  [<ffffffff8166e3f0>] ? dev_graft_qdisc+0x80/0x80
> [   16.705053]  [<ffffffff810fd52a>] call_timer_fn+0x3a/0x120
> [   16.705053]  [<ffffffff8166e3f0>] ? dev_graft_qdisc+0x80/0x80
> [   16.705053]  [<ffffffff810ff692>] run_timer_softirq+0x212/0x2f0
> [   16.705053]  [<ffffffff8109d7a4>] __do_softirq+0x124/0x2d0
> [   16.705053]  [<ffffffff8109db75>] irq_exit+0x125/0x130
> [   16.705053]  [<ffffffff817681d8>] smp_apic_timer_interrupt+0x48/0x60
> [   16.705053]  [<ffffffff817662bd>] apic_timer_interrupt+0x6d/0x80
> [   16.705053]  <EOI>  [<ffffffff811005c8>] ? hrtimer_start+0x18/0x20
> [   16.705053]  [<ffffffff8105ca96>] ? native_safe_halt+0x6/0x10
> [   16.705053]  [<ffffffff810f81d3>] ? rcu_eqs_enter+0xa3/0xb0
> [   16.705053]  [<ffffffff8101ec7f>] default_idle+0x1f/0xc0
> [   16.705053]  [<ffffffff8101f64f>] arch_cpu_idle+0xf/0x20
> [   16.705053]  [<ffffffff810dad35>] cpu_startup_entry+0x3c5/0x410
> [   16.705053]  [<ffffffff8104a2af>] start_secondary+0x1af/0x1f0
> [   16.705053] ---[ end trace 7bda53aeda558267 ]---
> [   16.705053] i40e 0000:00:05.0 eth1: tx_timeout recovery level 1
> [   16.705053] i40e 0000:00:05.0: i40e_vsi_control_tx: VSI seid 519 Tx ring 0 disable timeout
> [   16.744198] i40e 0000:00:05.0: i40e_vsi_control_tx: VSI seid 520 Tx ring 64 disable timeout
> [   16.779322] i40e 0000:00:05.0: i40e_ptp_init: added PHC on eth1
> [   16.791819] i40e 0000:00:05.0: PF 40 attempted to control timestamp mode on port 1, which is owned by PF 1
> [   16.933869] i40e 0000:00:05.0 eth1: NIC Link is Up 40 Gbps Full Duplex, Flow Control: None
> [   18.853624] SELinux: initialized (dev tmpfs, type tmpfs), uses transition SIDs
> [   22.720083] i40e 0000:00:05.0 eth1: tx_timeout recovery level 2
> [   22.826993] i40e 0000:00:05.0: i40e_vsi_control_tx: VSI seid 519 Tx ring 0 disable timeout
> [   22.935288] i40e 0000:00:05.0: i40e_vsi_control_tx: VSI seid 520 Tx ring 64 disable timeout
> [   23.669555] i40e 0000:00:05.0: i40e_ptp_init: added PHC on eth1
> [   23.682067] i40e 0000:00:05.0: PF 40 attempted to control timestamp mode on port 1, which is owned by PF 1
> [   23.722423] i40e 0000:00:05.0 eth1: NIC Link is Up 40 Gbps Full Duplex, Flow Control: None
> [   23.800206] i40e 0000:00:06.0: i40e_ptp_init: added PHC on eth2
> [   23.813804] i40e 0000:00:06.0: PF 48 attempted to control timestamp mode on port 0, which is owned by PF 0
> [   23.855275] i40e 0000:00:06.0 eth2: NIC Link is Up 40 Gbps Full Duplex, Flow Control: None
> [   38.720091] i40e 0000:00:05.0 eth1: tx_timeout recovery level 3
> [   38.725844] random: nonblocking pool is initialized
> [   38.729874] i40e 0000:00:06.0: HMC error interrupt
> [   38.733425] i40e 0000:00:06.0: i40e_vsi_control_tx: VSI seid 518 Tx ring 0 disable timeout
> [   38.738886] i40e 0000:00:06.0: i40e_vsi_control_tx: VSI seid 521 Tx ring 64 disable timeout
> [   39.689569] i40e 0000:00:06.0: i40e_ptp_init: added PHC on eth2
> [   39.704197] i40e 0000:00:06.0: PF 48 attempted to control timestamp mode on port 0, which is owned by PF 0
> [   39.746879] i40e 0000:00:06.0 eth2: NIC Link is Down
> [   39.838356] i40e 0000:00:05.0: i40e_ptp_init: added PHC on eth1
> [   39.851788] i40e 0000:00:05.0: PF 40 attempted to control timestamp mode on port 1, which is owned by PF 1
> [   39.892822] i40e 0000:00:05.0 eth1: NIC Link is Down
> [   43.011610] i40e 0000:00:06.0 eth2: NIC Link is Up 40 Gbps Full Duplex, Flow Control: None
> [   43.059976] i40e 0000:00:05.0 eth1: NIC Link is Up 40 Gbps Full Duplex, Flow Control: None

 Would appreciate any information on how to debug this issue further
and if the "unhandled rdmsr" logs from KVM indicate some issues with
the device passthrough.

 Thanks
 Jacob