> -----Original Message-----
> From: Jonathan Cameron <[email protected]>
> Sent: Thursday, November 12, 2026 7:22 AM
> To: Manish Honap <[email protected]>
> Cc: Alex Williamson <[email protected]>; [email protected];
> [email protected]; [email protected]; Zhi Wang
> <[email protected]>; [email protected]; [email protected];
> [email protected]; [email protected]; [email protected]; Ankit
> Agrawal <[email protected]>; Vikram Sethi <[email protected]>; Shameer
> Kolothum Thodi <[email protected]>; Matt Ochs
> <[email protected]>; Neo Jia <[email protected]>; Krishnakant Jaju
> <[email protected]>; [email protected]; [email protected];
> Yukiya Takaki <[email protected]>
> Subject: Re: [RFC 00/18] hw/cxl: Add a CXL Type-2 device
> 
> External email: Use caution opening links or attachments
> 
> 
> On Fri, 6 Nov 2026 09:28:53 +0530
> <[email protected]> wrote:
> 
> > From: Manish Honap <[email protected]>
> >
> > Hello,
> >
> > This series adds cxl-type2, an emulated CXL Type-2 device with
> > volatile device memory. It is emulated in such a way that all the
> > Linux checks are satisfied so that CXL passthrough using vfio-pci
> > (vfio-cxl) can be developed and tested in a guest without Type-2 hardware.
> >
> > This series builds on the Type-2 model from Zhi's series (carried in
> > Cédric's tree) and carries one fix from Shuai's tree. Shuai's tree
> > also set up the decoders through device properties and stubbed CXL
> > Reset; the firmware setup and CXL Reset here are new code.
> > Carried patches keep their authors, with a note for each change.
> >
> > The device:
> > - PCI ID 1b36:0017 and the processing accelerator class 0x1200;
> > - PCIe DVSEC for CXL Devices with CXL.cache, CXL.mem, one HDM range,
> >   cache write-back and invalidate, CXL Reset and Mem Clr; Register
> >   Locator and Flex Bus Port DVSECs;
> > - CXL.cache advertised but not modelled. The device sends no CXL.cache
> >   requests, and its memory is host RAM, which is coherent already. A
> >   cache write-back and invalidate completes at once. The capability is
> >   set because vfio-cxl takes a device as Type-2 only when it reports
> >   both CXL.cache and CXL.mem;
> > - component registers with one HDM decoder;
> > - slot 0, function 0 below a CXL root port of a pxb-cxl, memory in one
> >   fixed memory window selected with fmw-index, cold plug only (no
> >   hotplug or unplug), not migratable.
> >
> > No Linux driver claims the device on its own. cxl_pci does not bind to
> > the accelerator class, and sfc, the other driver that calls the CXL
> > core Type-2 interface, matches only its own devices. A guest binds
> > cxl-type2 to vfio-pci, which hands it to vfio-cxl. Testing the CXL
> > core
> > Type-2 interface without vfio-cxl needs a driver for 1b36:0017 that
> > calls it. There is none yet.
> >
> > QEMU has no firmware that commits the HDM decoders of a CXL route at
> > boot, and Linux attaches a Type-2 device only to a committed region
> > (devm_cxl_probe_mem()). So QEMU does that step itself.
> 
> Just in case you missed it, Yukiya Takaki is looking at bios programmed flows.
> https://lore.kernel.org/all/[email protected]/
> 
> My immediate thought is follow a similar flow to the one I suggested in that
> patch. Doing CXL setup in QEMU but the PCI enumeration in the bios doesn't
> seem like a sustainable model to me. I'd much prefer to see a bios flow with
> just the QEMU generate tables updated in a similar fashion to how DSDT is
> updated for PXBs.
> 
> Alternative for you (assuming you care more about arm than x86) might be to
> just use the SBSA model and do the full enumeration in firmware.
> 
> Unfortunately I have quite a large backlog so might be a while before I get a
> chance to take a close look at this series (or the kernel ones!)
> 
> Jonathan
> 

Thank you Jonathan; I will take a look at the suggested series and SBSA model 
for this.

Reply via email to