Re: [PATCH 10/20] vfio/cxl: CXL region management
From: Dave Jiang
Date: Thu Mar 12 2026 - 18:55:52 EST
On 3/11/26 1:34 PM, mhonap@xxxxxxxxxx wrote:
> From: Manish Honap <mhonap@xxxxxxxxxx>
>
> Add CXL region management for future guest access.
>
> Region Management makes use of APIs provided by CXL_CORE as below:
>
> CREATE_REGION flow:
> 1. Validate request (size, decoder availability)
> 2. Allocate HPA via cxl_get_hpa_freespace()
> 3. Allocate DPA via cxl_request_dpa()
> 4. Create region via cxl_create_region() - commits HDM decoder!
> 5. Get HPA range via cxl_get_region_range()
>
> DESTROY_REGION flow:
> 1. Detach decoder via cxl_decoder_detach()
> 2. Free DPA via cxl_dpa_free()
> 3. Release root decoder via cxl_put_root_decoder()
>
> Signed-off-by: Manish Honap <mhonap@xxxxxxxxxx>
> ---
> drivers/vfio/pci/cxl/vfio_cxl_core.c | 118 ++++++++++++++++++++++++++-
> drivers/vfio/pci/cxl/vfio_cxl_priv.h | 5 ++
> drivers/vfio/pci/vfio_pci_priv.h | 8 ++
> 3 files changed, 130 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/vfio/pci/cxl/vfio_cxl_core.c b/drivers/vfio/pci/cxl/vfio_cxl_core.c
> index 2da6da1c0605..9c71f592e74e 100644
> --- a/drivers/vfio/pci/cxl/vfio_cxl_core.c
> +++ b/drivers/vfio/pci/cxl/vfio_cxl_core.c
> @@ -126,6 +126,112 @@ static int vfio_cxl_setup_regs(struct vfio_pci_core_device *vdev)
> return 0;
> }
>
> +int vfio_cxl_create_cxl_region(struct vfio_pci_core_device *vdev, resource_size_t size)
> +{
> + struct vfio_pci_cxl_state *cxl = vdev->cxl;
> + resource_size_t max_size;
> + int ret;
> +
> + if (cxl->precommitted)
> + return 0;
> +
> + cxl->cxlrd = cxl_get_hpa_freespace(cxl->cxlmd, 1,
> + CXL_DECODER_F_RAM |
> + CXL_DECODER_F_TYPE2,
> + &max_size);
Not sure what VFIO subsystem's policy is on scoped base resource cleanup, but a __free() here can get you out of managing put() of the root decoder.
> + if (IS_ERR(cxl->cxlrd))
> + return PTR_ERR(cxl->cxlrd);
> +
> + /* Insufficient HPA space */
> + if (max_size < size) {
> + cxl_put_root_decoder(cxl->cxlrd);
> + cxl->cxlrd = NULL;
> + return -ENOSPC;
> + }
> +
> + cxl->cxled = cxl_request_dpa(cxl->cxlmd, CXL_PARTMODE_RAM, size);
Same comment here about __free().
> + if (IS_ERR(cxl->cxled)) {
> + ret = PTR_ERR(cxl->cxled);
> + goto err_free_hpa;
> + }
> +
> + cxl->region = cxl_create_region(cxl->cxlrd, &cxl->cxled, 1);
> + if (IS_ERR(cxl->region)) {
> + ret = PTR_ERR(cxl->region);
> + goto err_free_dpa;
> + }
> +
> + return 0;
> +
> +err_free_dpa:
> + cxl_dpa_free(cxl->cxled);
> +err_free_hpa:
> + if (cxl->cxlrd)
> + cxl_put_root_decoder(cxl->cxlrd);
> +
> + return ret;
> +}
> +
> +void vfio_cxl_destroy_cxl_region(struct vfio_pci_core_device *vdev)
> +{
> + struct vfio_pci_cxl_state *cxl = vdev->cxl;
> +
> + if (!cxl->region)
> + return;
> +
> + cxl_unregister_region(cxl->region);
> + cxl->region = NULL;
> +
> + if (cxl->precommitted)
> + return;
> +
> + cxl_dpa_free(cxl->cxled);
> + cxl_put_root_decoder(cxl->cxlrd);
> +}
> +
> +static int vfio_cxl_create_region_helper(struct vfio_pci_core_device *vdev,
> + resource_size_t capacity)
> +{
> + struct vfio_pci_cxl_state *cxl = vdev->cxl;
> + struct pci_dev *pdev = vdev->pdev;
> + int ret;
> +
> + if (cxl->precommitted) {
> + cxl->cxled = cxl_get_committed_decoder(cxl->cxlmd,
> + &cxl->region);
> + if (IS_ERR(cxl->cxled))
> + return PTR_ERR(cxl->cxled);
> + } else {
> + ret = vfio_cxl_create_cxl_region(vdev, capacity);
> + if (ret)
> + return ret;
> + }
> +
> + if (cxl->region) {
Maybe if you do 'if (!cxl->region)' first and just exit, then you don't need to indent the normal code path.
> + struct range range;
> +
> + ret = cxl_get_region_range(cxl->region, &range);
> + if (ret)
> + goto failed;
> +
> + cxl->region_hpa = range.start;
> + cxl->region_size = range_len(&range);
> +
> + pci_dbg(pdev, "Precommitted decoder: HPA 0x%llx size %lu MB\n",
> + cxl->region_hpa, cxl->region_size >> 20);
> + } else {
> + pci_err(pdev, "Failed to create CXL region\n");
> + ret = -ENODEV;
> + goto failed;
> + }
> +
> + return 0;
> +
> +failed:
> + vfio_cxl_destroy_cxl_region(vdev);
> + return ret;
> +}
> +
> /**
> * vfio_pci_cxl_detect_and_init - Detect and initialize CXL Type-2 device
> * @vdev: VFIO PCI device
> @@ -172,6 +278,12 @@ void vfio_pci_cxl_detect_and_init(struct vfio_pci_core_device *vdev)
>
> pci_disable_device(pdev);
>
> + ret = vfio_cxl_create_region_helper(vdev, SZ_256M);
Maybe a comment on why this size?
DJ
> + if (ret)
> + goto failed;
> +
> + cxl->precommitted = true;
> +
> return;
>
> failed:
> @@ -181,6 +293,10 @@ void vfio_pci_cxl_detect_and_init(struct vfio_pci_core_device *vdev)
>
> void vfio_pci_cxl_cleanup(struct vfio_pci_core_device *vdev)
> {
> - if (!vdev->cxl)
> + struct vfio_pci_cxl_state *cxl = vdev->cxl;
> +
> + if (!cxl || !cxl->region)
> return;
> +
> + vfio_cxl_destroy_cxl_region(vdev);
> }
> diff --git a/drivers/vfio/pci/cxl/vfio_cxl_priv.h b/drivers/vfio/pci/cxl/vfio_cxl_priv.h
> index 57fed39a80da..985680842a13 100644
> --- a/drivers/vfio/pci/cxl/vfio_cxl_priv.h
> +++ b/drivers/vfio/pci/cxl/vfio_cxl_priv.h
> @@ -17,6 +17,10 @@ struct vfio_pci_cxl_state {
> struct cxl_memdev *cxlmd;
> struct cxl_root_decoder *cxlrd;
> struct cxl_endpoint_decoder *cxled;
> + struct cxl_region *region;
> + resource_size_t region_hpa;
> + size_t region_size;
> + void __iomem *region_vaddr;
> resource_size_t hdm_reg_offset;
> size_t hdm_reg_size;
> resource_size_t comp_reg_offset;
> @@ -24,6 +28,7 @@ struct vfio_pci_cxl_state {
> u32 hdm_count;
> u16 dvsec;
> u8 comp_reg_bar;
> + bool precommitted;
> };
>
> /*
> diff --git a/drivers/vfio/pci/vfio_pci_priv.h b/drivers/vfio/pci/vfio_pci_priv.h
> index d7df5538dcde..818d99f098bf 100644
> --- a/drivers/vfio/pci/vfio_pci_priv.h
> +++ b/drivers/vfio/pci/vfio_pci_priv.h
> @@ -137,6 +137,9 @@ static inline void vfio_pci_dma_buf_move(struct vfio_pci_core_device *vdev,
>
> void vfio_pci_cxl_detect_and_init(struct vfio_pci_core_device *vdev);
> void vfio_pci_cxl_cleanup(struct vfio_pci_core_device *vdev);
> +int vfio_cxl_create_cxl_region(struct vfio_pci_core_device *vdev,
> + resource_size_t size);
> +void vfio_cxl_destroy_cxl_region(struct vfio_pci_core_device *vdev);
>
> #else
>
> @@ -144,6 +147,11 @@ static inline void
> vfio_pci_cxl_detect_and_init(struct vfio_pci_core_device *vdev) { }
> static inline void
> vfio_pci_cxl_cleanup(struct vfio_pci_core_device *vdev) { }
> +static inline int vfio_cxl_create_cxl_region(struct vfio_pci_core_device *vdev,
> + resource_size_t size)
> +{ return 0; }
> +static inline void
> +vfio_cxl_destroy_cxl_region(struct vfio_pci_core_device *vdev) { }
>
> #endif /* CONFIG_VFIO_CXL_CORE */
>