revive an old QLogic IBA7322 Infiniband card on CentOS8.2

Question

I have a few HP Blades Gen7 equipped with QLogic Infiniband cards IBA7322 which I would like to use with CentOS 8. The problem I have is that I cannot find the right drivers for them. All the information I find is either old, or the links don't work (e.g. the marvell download links).

I can see the card with lspci but other than that I didn't have any luck turning it on (so to say).

Can anyone point me in some sort of direction with this problem?

Cheers.

Edit:

results from lspci -vv:

01:00.0 InfiniBand: QLogic Corp. IBA7322 QDR InfiniBand HCA (rev 02)
        Subsystem: Hewlett-Packard Company Device 178a
        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-
        Interrupt: pin A routed to IRQ 10
        Region 0: Memory at fd400000 (64-bit, non-prefetchable) [size=4M]
        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=0 PME-
        Capabilities: [70] Express (v2) Endpoint, MSI 00
                DevCap: MaxPayload 512 bytes, PhantFunc 0, Latency L0s <64ns, L1 <1us
                        ExtTag- AttnBtn- AttnInd- PwrInd- RBE+ FLReset- SlotPowerLimit 0.000W
                DevCtl: Report errors: Correctable+ Non-Fatal+ Fatal+ Unsupported+
                        RlxdOrd+ ExtTag- PhantFunc- AuxPwr- NoSnoop-
                        MaxPayload 128 bytes, MaxReadReq 4096 bytes
                DevSta: CorrErr- UncorrErr- FatalErr- UnsuppReq- AuxPwr- TransPend-
                LnkCap: Port #0, Speed 5GT/s, Width x8, ASPM L0s, Exit Latency L0s <4us
                        ClockPM- Surprise- LLActRep- BwNot- ASPMOptComp-
                LnkCtl: ASPM Disabled; RCB 64 bytes Disabled- CommClk+
                        ExtSynch- ClockPM- AutWidDis- BWInt- AutBWInt-
                LnkSta: Speed 5GT/s, Width x8, TrErr- Train- SlotClk+ DLActive- BWMgmt- ABWMgmt-
                DevCap2: Completion Timeout: Not Supported, TimeoutDis+, LTR-, OBFF Not Supported
                         AtomicOpsCap: 32bit- 64bit- 128bitCAS-
                DevCtl2: Completion Timeout: 50us to 50ms, TimeoutDis-, LTR-, OBFF Disabled
                         AtomicOpsCtl: ReqEn-
                LnkCtl2: Target Link Speed: 5GT/s, EnterCompliance- SpeedDis-
                         Transmit Margin: Normal Operating Range, EnterModifiedCompliance- ComplianceSOS-
                         Compliance De-emphasis: -6dB
                LnkSta2: Current De-emphasis Level: -6dB, EqualizationComplete-, EqualizationPhase1-
                         EqualizationPhase2-, EqualizationPhase3-, LinkEqualizationRequest-
        Capabilities: [b0] MSI-X: Enable- Count=32 Masked-
                Vector table: BAR=0 offset=00008000
                PBA: BAR=0 offset=00009000
        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- NonFatalErr-
                CEMsk:  RxErr- BadTLP- BadDLLP- Rollover- Timeout- NonFatalErr-
                AERCap: First Error Pointer: 00, ECRCGenCap+ ECRCGenEn- ECRCChkCap+ ECRCChkEn-
                        MultHdrRecCap- MultHdrRecEn- TLPPfxPres- HdrLogCap-
                HeaderLog: 00000000 00000000 00000000 00000000

Answer 1

The first thing to do is to get the PCI vendor and device IDs for the hardware in question. Your card appears to be 1077:7322. A quick look at the Linux Driver Database tells me this card uses the ib_qib driver.

I took a look through the RHEL documentation of removed drivers in RHEL 8, but did not see this driver. However, I fired up a RHEL 8 VM and the driver is no longer present and is not enabled in the corresponding kernel configuration. It is present in RHEL 7 though.

What people usually do in such a circumstance, in order to use the old hardware, is to use the elrepo repository, which for RHEL 8 contains the missing ib_qib driver (and several other drivers that Red Hat dropped). For example:

dnf install https://www.elrepo.org/elrepo-release-8.el8.elrepo.noarch.rpm
dnf install kmod-ib_qib

Answer 2

after many many trials my friend threw a hail Mary and recompiled the 4.19 kernel on Rocky 8.5 and enabled the qib driver. It was there all along it was just not compiled in the default kernel.

Now we got the old QLogic card working again. It is connected to a (gasp!) Mellanox Infiniband Switch that is running the Subnet Manager.

The nodes are able to communicate at 40 Gbps between them and they are also able to communicate with the much newer 100Gbps Mellanox ConnectX5 cards too.

All is good in infiniband-land now!

Hope this helps someone and if there are any questions I'll do my best to answer them. Just keep in mind that I am in no way an expert in these things. Just a guy that had to figure something out and make an old equipment relevant again!