Re: [PATCH 09/20] vfio/cxl: Implement CXL device detection and HDM register probing

[Dave Jiang]

On 3/11/26 1:34 PM, mhonap@xxxxxxxxxx wrote:
> From: Manish Honap <mhonap@xxxxxxxxxx>
> 
> Implement the core CXL Type-2 device detection and component register
> probing logic in vfio_pci_cxl_detect_and_init().
> 
> Three private helpers are introduced:
> 
>   vfio_cxl_create_device_state() allocates the per-device
>   vfio_pci_cxl_state structure using devm_cxl_dev_state_create() so
>   that lifetime is tied to the PCI device binding.
> 
>   vfio_cxl_find_bar() locates the PCI BAR that contains a given HPA
>   range, returning the BAR index and offset within it.
> 
>   vfio_cxl_setup_regs() uses the CXL core helpers cxl_find_regblock()
>   and cxl_probe_component_regs() to enumerate the HDM decoder register
>   block, then records its BAR index, offset and size in the CXL state.
> 
> vfio_pci_cxl_detect_and_init() orchestrates detection:
>   1. Check for CXL DVSEC via pcie_is_cxl() + pci_find_dvsec_capability().
>   2. Allocate CXL device state.
>   3. Temporarily call pci_enable_device_mem() for ioremap, then disable.
>   4. Probe component registers to find the HDM decoder block.
> 
> On any failure vdev->cxl is devm_kfree'd so that device falls back to
> plain PCI mode transparently.
> 
> Signed-off-by: Manish Honap <mhonap@xxxxxxxxxx>
> ---
>  drivers/vfio/pci/cxl/vfio_cxl_core.c | 151 +++++++++++++++++++++++++++
>  drivers/vfio/pci/cxl/vfio_cxl_priv.h |   8 ++
>  2 files changed, 159 insertions(+)
> 
> diff --git a/drivers/vfio/pci/cxl/vfio_cxl_core.c b/drivers/vfio/pci/cxl/vfio_cxl_core.c
> index 7698d94e16be..2da6da1c0605 100644
> --- a/drivers/vfio/pci/cxl/vfio_cxl_core.c
> +++ b/drivers/vfio/pci/cxl/vfio_cxl_core.c
> @@ -18,6 +18,114 @@
>  
>  MODULE_IMPORT_NS("CXL");
>  
> +static int vfio_cxl_create_device_state(struct vfio_pci_core_device *vdev,
> +					u16 dvsec)
> +{
> +	struct pci_dev *pdev = vdev->pdev;
> +	struct device *dev = &pdev->dev;
> +	struct vfio_pci_cxl_state *cxl;
> +	bool cxl_mem_capable, is_cxl_type3;
> +	u16 cap_word;
> +
> +	/*
> +	 * The devm allocation for the CXL state remains for the entire time
> +	 * the PCI device is bound to vfio-pci. From successful CXL init
> +	 * in probe until the device is released on unbind.
> +	 * No extra explicit free is needed; devm handles it when
> +	 * pdev->dev is released.
> +	 */
> +	vdev->cxl = devm_cxl_dev_state_create(dev,
> +					      CXL_DEVTYPE_DEVMEM,
> +					      pdev->dev.id, dvsec,
> +					      struct vfio_pci_cxl_state,
> +					      cxlds, false);
> +	if (!vdev->cxl)
> +		return -ENOMEM;
> +
> +	cxl = vdev->cxl;
> +	cxl->dvsec = dvsec;
> +
> +	pci_read_config_word(pdev, dvsec + CXL_DVSEC_CAPABILITY_OFFSET,
> +			     &cap_word);
> +
> +	cxl_mem_capable = !!(cap_word & CXL_DVSEC_MEM_CAPABLE);
> +	is_cxl_type3 = ((pdev->class >> 8) == PCI_CLASS_MEMORY_CXL);

Both of these can use FIELD_GET().

> +
> +	/*
> +	 * Type 2 = CXL memory capable but NOT Type 3 (e.g. accelerator/GPU)
> +	 * Unsupported for non cxl type-2 class of devices.
> +	 */
> +	if (!(cxl_mem_capable && !is_cxl_type3)) {
> +		devm_kfree(&pdev->dev, vdev->cxl);
> +		vdev->cxl = NULL;
> +		return -ENODEV;
> +	}
> +
> +	return 0;
> +}
> +
> +static int vfio_cxl_setup_regs(struct vfio_pci_core_device *vdev)
> +{
> +	struct vfio_pci_cxl_state *cxl = vdev->cxl;
> +	struct cxl_register_map *map = &cxl->cxlds.reg_map;
> +	resource_size_t offset, bar_offset, size;
> +	struct pci_dev *pdev = vdev->pdev;
> +	void __iomem *base;
> +	u32 count;
> +	int ret;
> +	u8 bar;
> +
> +	if (WARN_ON_ONCE(!pci_is_enabled(pdev)))
> +		return -EINVAL;
> +
> +	/* Find component register block via Register Locator DVSEC */
> +	ret = cxl_find_regblock(pdev, CXL_REGLOC_RBI_COMPONENT, map);
> +	if (ret)
> +		return ret;
> +
> +	/* Temporarily map the register block */
> +	base = ioremap(map->resource, map->max_size);

Request the mem region before mapping it?

DJ

> +	if (!base)
> +		return -ENOMEM;
> +
> +	/* Probe component register capabilities */
> +	cxl_probe_component_regs(&pdev->dev, base, &map->component_map);
> +
> +	/* Unmap immediately */
> +	iounmap(base);
> +
> +	/* Check if HDM decoder was found */
> +	if (!map->component_map.hdm_decoder.valid)
> +		return -ENODEV;
> +
> +	pci_dbg(pdev,
> +		"vfio_cxl: HDM decoder at offset=0x%lx, size=0x%lx\n",
> +		map->component_map.hdm_decoder.offset,
> +		map->component_map.hdm_decoder.size);
> +
> +	/* Get HDM register info */
> +	ret = cxl_get_hdm_reg_info(&cxl->cxlds, &count, &offset, &size);
> +	if (ret)
> +		return ret;
> +
> +	if (!count || !size)
> +		return -ENODEV;
> +
> +	cxl->hdm_count = count;
> +	cxl->hdm_reg_offset = offset;
> +	cxl->hdm_reg_size = size;
> +
> +	ret = cxl_regblock_get_bar_info(map, &bar, &bar_offset);
> +	if (ret)
> +		return ret;
> +
> +	cxl->comp_reg_bar = bar;
> +	cxl->comp_reg_offset = bar_offset;
> +	cxl->comp_reg_size = CXL_COMPONENT_REG_BLOCK_SIZE;
> +
> +	return 0;
> +}
> +
>  /**
>   * vfio_pci_cxl_detect_and_init - Detect and initialize CXL Type-2 device
>   * @vdev: VFIO PCI device
> @@ -28,8 +136,51 @@ MODULE_IMPORT_NS("CXL");
>   */
>  void vfio_pci_cxl_detect_and_init(struct vfio_pci_core_device *vdev)
>  {
> +	struct pci_dev *pdev = vdev->pdev;
> +	struct vfio_pci_cxl_state *cxl;
> +	u16 dvsec;
> +	int ret;
> +
> +	if (!pcie_is_cxl(pdev))
> +		return;
> +
> +	dvsec = pci_find_dvsec_capability(pdev,
> +					  PCI_VENDOR_ID_CXL,
> +					  PCI_DVSEC_CXL_DEVICE);
> +	if (!dvsec)
> +		return;
> +
> +	ret = vfio_cxl_create_device_state(vdev, dvsec);
> +	if (ret)
> +		return;
> +
> +	cxl = vdev->cxl;
> +
> +	/*
> +	 * Required for ioremap of the component register block and
> +	 * calls to cxl_probe_component_regs().
> +	 */
> +	ret = pci_enable_device_mem(pdev);
> +	if (ret)
> +		goto failed;
> +
> +	ret = vfio_cxl_setup_regs(vdev);
> +	if (ret) {
> +		pci_disable_device(pdev);
> +		goto failed;
> +	}
> +
> +	pci_disable_device(pdev);
> +
> +	return;
> +
> +failed:
> +	devm_kfree(&pdev->dev, vdev->cxl);
> +	vdev->cxl = NULL;
>  }
>  
>  void vfio_pci_cxl_cleanup(struct vfio_pci_core_device *vdev)
>  {
> +	if (!vdev->cxl)
> +		return;
>  }
> diff --git a/drivers/vfio/pci/cxl/vfio_cxl_priv.h b/drivers/vfio/pci/cxl/vfio_cxl_priv.h
> index 818a83a3809d..57fed39a80da 100644
> --- a/drivers/vfio/pci/cxl/vfio_cxl_priv.h
> +++ b/drivers/vfio/pci/cxl/vfio_cxl_priv.h
> @@ -26,4 +26,12 @@ struct vfio_pci_cxl_state {
>  	u8                           comp_reg_bar;
>  };
>  
> +/*
> + * CXL DVSEC for CXL Devices - register offsets within the DVSEC
> + * (CXL 2.0+ 8.1.3).
> + * Offsets are relative to the DVSEC capability base (cxl->dvsec).
> + */
> +#define CXL_DVSEC_CAPABILITY_OFFSET 0xa
> +#define CXL_DVSEC_MEM_CAPABLE	    BIT(2)
> +
>  #endif /* __LINUX_VFIO_CXL_PRIV_H */