PCI Passthrough of SR-IOV Capable NIC doesn't show VFs

[flightofthebumble]

Hi Folks, I hope someone can help me with this issue, I have tried many different settings to get PCI Passthrough working, with available VF functionality on an Ubuntu 22 VM, without joy.

Equipment details:
I am running Proxmox VE 7.3-4 on a Dell r720. I have an Intel Corporation 82599ES 10-Gigabit SFI/SFP+ /Ethernet Server Adapter X520-2 installed.
On Proxmox shell, when I type lspci -vv I get the following result:

42:00.1 Ethernet controller: Intel Corporation 82599ES 10-Gigabit SFI/SFP+ Network Connection (rev 01)
Subsystem: Intel Corporation Ethernet Server Adapter X520-2
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR+ FastB2B- DisINTx+
Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
Latency: 0, Cache Line Size: 64 bytes
Interrupt: pin B routed to IRQ 42
NUMA node: 1
IOMMU group: 15
Region 0: Memory at d00c0000 (64-bit, non-prefetchable) [size=128K]
Region 2: I/O ports at bce0
Region 4: Memory at d00fc000 (64-bit, non-prefetchable) [size=16K]
Capabilities: [40] Power Management version 3
Flags: PMEClk- DSI+ D1- D2- AuxCurrent=0mA PME(D0+,D1-,D2-,D3hot+,D3cold-)
Status: D0 NoSoftRst- PME-Enable- DSel=0 DScale=1 PME-
Capabilities: [50] MSI: Enable- Count=1/1 Maskable+ 64bit+
Address: 0000000000000000 Data: 0000
Masking: 00000000 Pending: 00000000
Capabilities: [70] MSI-X: Enable+ Count=64 Masked-
Vector table: BAR=4 offset=00000000
PBA: BAR=4 offset=00002000
Capabilities: [a0] Express (v2) Endpoint, MSI 00
DevCap: MaxPayload 512 bytes, PhantFunc 0, Latency L0s <512ns, L1 <64us
ExtTag- AttnBtn- AttnInd- PwrInd- RBE+ FLReset+ SlotPowerLimit 0.000W
DevCtl: CorrErr+ NonFatalErr+ FatalErr+ UnsupReq+
RlxdOrd+ ExtTag- PhantFunc- AuxPwr- NoSnoop+ FLReset-
MaxPayload 256 bytes, MaxReadReq 512 bytes
DevSta: CorrErr- NonFatalErr- FatalErr- UnsupReq- AuxPwr- TransPend-
LnkCap: Port #0, Speed 5GT/s, Width x8, ASPM L0s, Exit Latency L0s <1us
ClockPM- Surprise- LLActRep- BwNot- ASPMOptComp-
LnkCtl: ASPM Disabled; RCB 64 bytes, Disabled- CommClk+
ExtSynch- ClockPM- AutWidDis- BWInt- AutBWInt-
LnkSta: Speed 5GT/s (ok), Width x8 (ok)
TrErr- Train- SlotClk+ DLActive- BWMgmt- ABWMgmt-
DevCap2: Completion Timeout: Range ABCD, TimeoutDis+ NROPrPrP- LTR-
10BitTagComp- 10BitTagReq- OBFF Not Supported, ExtFmt- EETLPPrefix-
EmergencyPowerReduction Not Supported, EmergencyPowerReductionInit-
FRS- TPHComp- ExtTPHComp-
AtomicOpsCap: 32bit- 64bit- 128bitCAS-
DevCtl2: Completion Timeout: 65ms to 210ms, TimeoutDis- LTR- OBFF Disabled,
AtomicOpsCtl: ReqEn-
LnkSta2: Current De-emphasis Level: -6dB, EqualizationComplete- EqualizationPhase1-
EqualizationPhase2- EqualizationPhase3- LinkEqualizationRequest-
Retimer- 2Retimers- CrosslinkRes: unsupported
Capabilities: [e0] Vital Product Data
Unknown small resource type 06, will not decode more.
Capabilities: [100 v1] Advanced Error Reporting
UESta: DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt- UnxCmplt- RxOF- MalfTLP- ECRC- UnsupReq- ACSViol-
UEMsk: DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt+ UnxCmplt+ RxOF- MalfTLP- ECRC- UnsupReq- ACSViol-
UESvrt: DLP+ SDES- TLP+ FCP+ CmpltTO+ CmpltAbrt- UnxCmplt- RxOF+ MalfTLP+ ECRC+ UnsupReq- ACSViol-
CESta: RxErr- BadTLP- BadDLLP- Rollover- Timeout- AdvNonFatalErr-
CEMsk: RxErr+ BadTLP+ BadDLLP+ Rollover+ Timeout+ AdvNonFatalErr+
AERCap: First Error Pointer: 00, ECRCGenCap+ ECRCGenEn- ECRCChkCap+ ECRCChkEn-
MultHdrRecCap- MultHdrRecEn- TLPPfxPres- HdrLogCap-
HeaderLog: 00000000 00000000 00000000 00000000
Capabilities: [140 v1] Device Serial Number 00-e0-ed-ff-ff-92-f6-88
Capabilities: [150 v1] Alternative Routing-ID Interpretation (ARI)
ARICap: MFVC- ACS-, Next Function: 0
ARICtl: MFVC- ACS-, Function Group: 0
Capabilities: [160 v1] Single Root I/O Virtualization (SR-IOV)
IOVCap: Migration-, Interrupt Message Number: 000
IOVCtl: Enable- Migration- Interrupt- MSE- ARIHierarchy-
IOVSta: Migration-
Initial VFs: 64, Total VFs: 64, Number of VFs: 0, Function Dependency Link: 01
VF offset: 128, stride: 2, Device ID: 10ed
Supported Page Size: 00000553, System Page Size: 00000001
Region 0: Memory at 00000000cc200000 (64-bit, prefetchable)
Region 3: Memory at 00000000cc300000 (64-bit, prefetchable)
VF Migration: offset: 00000000, BIR: 0
Kernel driver in use: vfio-pci
Kernel modules: ixgbe

^ with this in mind, I have successfully tested creating multiple VFs on Proxmox as a test, so I know the card is capable of SR-IOV.

I created an Ubuntu 22 Desktop VM, enabled NUMA, set CPU to host, 2 x sockets 4 cores per, q35, and added the card using PCI passthrough. PCi passthrough settings are All Functions/ROM-Bar ticked/PCI-Express ticked and Vendor/Device ID set.

When I run sudo lspci -vv on the Ubuntu VM, this is the result I get:

01:00.1 Ethernet controller: Intel Corporation 82599ES 10-Gigabit SFI/SFP+ Network Connection (rev 01)
Subsystem: Intel Corporation Ethernet Server Adapter X520-2
Physical Slot: 0
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR+ FastB2B- DisINTx+
Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
Latency: 0, Cache Line Size: 64 bytes
Interrupt: pin B routed to IRQ 17
Region 0: Memory at fe820000 (64-bit, non-prefetchable) [size=128K]
Region 2: I/O ports at 5020
Region 4: Memory at fe844000 (64-bit, non-prefetchable) [size=16K]
Capabilities: [40] Power Management version 3
Flags: PMEClk- DSI+ D1- D2- AuxCurrent=0mA PME(D0-,D1-,D2-,D3hot-,D3cold-)
Status: D0 NoSoftRst- PME-Enable- DSel=0 DScale=1 PME-
Capabilities: [50] MSI: Enable- Count=1/1 Maskable+ 64bit+
Address: 0000000000000000 Data: 0000
Masking: 00000000 Pending: 00000000
Capabilities: [70] MSI-X: Enable+ Count=64 Masked-
Vector table: BAR=4 offset=00000000
PBA: BAR=4 offset=00002000
Capabilities: [a0] Express (v2) Endpoint, MSI 00
DevCap: MaxPayload 512 bytes, PhantFunc 0, Latency L0s <512ns, L1 <64us
ExtTag- AttnBtn- AttnInd- PwrInd- RBE+ FLReset+ SlotPowerLimit 0.000W
DevCtl: CorrErr+ NonFatalErr+ FatalErr+ UnsupReq+
RlxdOrd+ ExtTag- PhantFunc- AuxPwr- NoSnoop+ FLReset-
MaxPayload 128 bytes, MaxReadReq 512 bytes
DevSta: CorrErr- NonFatalErr- FatalErr- UnsupReq- AuxPwr- TransPend-
LnkCap: Port #0, Speed 5GT/s, Width x8, ASPM L0s, Exit Latency L0s <1us
ClockPM- Surprise- LLActRep- BwNot- ASPMOptComp-
LnkCtl: ASPM Disabled; RCB 64 bytes, Disabled- CommClk+
ExtSynch- ClockPM- AutWidDis- BWInt- AutBWInt-
LnkSta: Speed 5GT/s (ok), Width x8 (ok)
TrErr- Train- SlotClk+ DLActive- BWMgmt- ABWMgmt-
DevCap2: Completion Timeout: Range ABCD, TimeoutDis+ NROPrPrP- LTR-
10BitTagComp- 10BitTagReq- OBFF Not Supported, ExtFmt- EETLPPrefix-
EmergencyPowerReduction Not Supported, EmergencyPowerReductionInit-
FRS- TPHComp- ExtTPHComp-
AtomicOpsCap: 32bit- 64bit- 128bitCAS-
DevCtl2: Completion Timeout: 65ms to 210ms, TimeoutDis- LTR- OBFF Disabled,
AtomicOpsCtl: ReqEn-
LnkSta2: Current De-emphasis Level: -6dB, EqualizationComplete- EqualizationPhase1-
EqualizationPhase2- EqualizationPhase3- LinkEqualizationRequest-
Retimer- 2Retimers- CrosslinkRes: unsupported
Capabilities: [e0] Vital Product Data
Unknown small resource type 06, will not decode more.
Capabilities: [100 v1] Advanced Error Reporting
UESta: DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt- UnxCmplt- RxOF- MalfTLP- ECRC- UnsupReq- ACSViol-
UEMsk: DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt+ UnxCmplt+ RxOF- MalfTLP- ECRC- UnsupReq- ACSViol-
UESvrt: DLP+ SDES- TLP+ FCP+ CmpltTO+ CmpltAbrt- UnxCmplt- RxOF+ MalfTLP+ ECRC+ UnsupReq- ACSViol-
CESta: RxErr- BadTLP- BadDLLP- Rollover- Timeout- AdvNonFatalErr-
CEMsk: RxErr+ BadTLP+ BadDLLP+ Rollover+ Timeout+ AdvNonFatalErr+
AERCap: First Error Pointer: 00, ECRCGenCap+ ECRCGenEn- ECRCChkCap+ ECRCChkEn-
MultHdrRecCap- MultHdrRecEn- TLPPfxPres- HdrLogCap-
HeaderLog: 00000000 00000000 00000000 00000000
Capabilities: [140 v1] Device Serial Number 00-e0-ed-ff-ff-92-f6-88
Kernel driver in use: ixgbe
Kernel modules: ixgbe


Running this command on the Ubuntu VM vs Proxmox CLI yields different results. Capabilities 100 onwards, including SR-IOV are missing. If anyone can provide pointers as to how I can add the SR-IOV functionality to the VM using PCI passthrough, that would be great - thanks.

 

[u9012063]

I'm also curios about whether this is supported.
I know VMware ESXi doesn't support it, you can not passthrough a SR-IOV NIC to VM, and create VFs inside the VM.
QEMU seems to support it, but I never tried. Wonder proxmox makes this case work or not
Thanks

 

[dcsapak]

QEMU seems to support it, but I never tried.

why do you think so ? i never saw any documentation that would indicate qemu supports that (if you have other infos, please share)

generally getting sr-iov in a guest will be hard (or impossible?) since the new devices would announce themselves on the host pci bus, not in the guest? so you'd suddenly have devices on the host that were created from a driver in the guest,
i don't think this can conceptually work easily

 

[u9012063]

because I'm using it everyday in our internal cloud, but I don't know how IT make it work.
So I can start a VM, in VM, load the network driver, create N number of VFs in VM, unload / load and do all kinds of testing

 

[dcsapak]

mhmm.. any chance you can get the qemu commandline from such a vm where you can sriov inside?


EDIT: i found out that there is a virutal 'igb' device that support virtualizing sr-iov, but it's not passing through a phyiscal card, but is emulated, maybe your internal cloud uses that?

 

[u9012063]

I will try to find out the setup or qemu command line. thanks