[PATCH 06/20] vfio/cxl: Add UAPI for CXL Type-2 device passthrough

[<mhonap@nvidia.com>]

From: Manish Honap <mhonap@nvidia.com>

CXL capabilities include:
- hdm_count: Number of HDM decoders available
- capacity: Total device memory (DPA)
- flags: COMMITTED, PRECOMMITTED

This UAPI enables VMMs like QEMU to passthrough CXL Type-2 devices
(GPUs, accelerators) with coherent memory to VMs.

Also added user-kernel API definitions for CXL Type-2 device passthrough.
Document how VFIO_DEVICE_FLAGS_CXL relates to VFIO_DEVICE_FLAGS_PCI
and VFIO_DEVICE_FLAGS_CAPS, and add field and flag descriptions
for the CXL capability.

Signed-off-by: Manish Honap <mhonap@nvidia.com>
---
 include/uapi/linux/vfio.h | 52 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index ac2329f24141..7ec0f96cc2d9 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -215,6 +215,13 @@ struct vfio_device_info {
 #define VFIO_DEVICE_FLAGS_FSL_MC (1 << 6)	/* vfio-fsl-mc device */
 #define VFIO_DEVICE_FLAGS_CAPS	(1 << 7)	/* Info supports caps */
 #define VFIO_DEVICE_FLAGS_CDX	(1 << 8)	/* vfio-cdx device */
+/*
+ * CXL Type-2 device (memory coherent; e.g. GPU, accelerator). When set,
+ * VFIO_DEVICE_FLAGS_PCI is also set (same device is a PCI device). The
+ * capability chain (VFIO_DEVICE_FLAGS_CAPS) contains VFIO_DEVICE_INFO_CAP_CXL
+ * describing HDM decoders, DPA size, and CXL-specific options.
+ */
+#define VFIO_DEVICE_FLAGS_CXL   (1 << 9)        /* Device supports CXL */
 	__u32	num_regions;	/* Max region index + 1 */
 	__u32	num_irqs;	/* Max IRQ index + 1 */
 	__u32   cap_offset;	/* Offset within info struct of first cap */
@@ -257,6 +264,39 @@ struct vfio_device_info_cap_pci_atomic_comp {
 	__u32 reserved;
 };
 
+/*
+ * VFIO_DEVICE_INFO_CAP_CXL - CXL Type-2 device capability
+ *
+ * Present in the device info capability chain when VFIO_DEVICE_FLAGS_CXL
+ * is set. Describes Host Managed Device Memory (HDM) layout and CXL
+ * memory options so that userspace (e.g. QEMU) can expose the CXL region
+ * and component registers correctly to the guest.
+ */
+#define VFIO_DEVICE_INFO_CAP_CXL		6
+struct vfio_device_info_cap_cxl {
+	struct vfio_info_cap_header header;
+	__u8  hdm_count; /* Number of HDM decoders */
+	__u8  hdm_regs_bar_index; /* PCI BAR containing HDM registers */
+	__u16 pad;
+	__u32 flags;
+/* Decoder was committed by host firmware/BIOS */
+#define VFIO_CXL_CAP_COMMITTED		(1 << 0)
+/*
+ * Memory was pre-committed (firmware-programmed); VMM need not allocate
+ * from CXL pool
+ */
+#define VFIO_CXL_CAP_PRECOMMITTED	(1 << 1)
+	__u64 hdm_regs_size; /* Size in bytes of HDM register block */
+	__u64 hdm_regs_offset; /* Byte offset within the BAR to the HDM decoder block */
+	__u64 dpa_size; /* Device Physical Address (DPA) size in bytes */
+	/*
+	 * Region indices for the two CXL VFIO device regions.
+	 * Avoids forcing userspace to scan all regions by type/subtype.
+	 */
+	__u32  dpa_region_index;       /* VFIO_REGION_SUBTYPE_CXL */
+	__u32  comp_regs_region_index; /* VFIO_REGION_SUBTYPE_CXL_COMP_REGS */
+};
+
 /**
  * VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8,
  *				       struct vfio_region_info)
@@ -370,6 +410,18 @@ struct vfio_region_info_cap_type {
  */
 #define VFIO_REGION_SUBTYPE_IBM_NVLINK2_ATSD	(1)
 
+/* 1e98 vendor PCI sub-types (CXL Consortium) */
+/*
+ * CXL memory region. Use with region type
+ * (PCI_VENDOR_ID_CXL | VFIO_REGION_TYPE_PCI_VENDOR_TYPE).
+ * DPA memory region (fault+zap mmap)
+ */
+#define VFIO_REGION_SUBTYPE_CXL                 (1)
+/*
+ * HDM decoder register emulation region (read/write only, no mmap).
+ */
+#define VFIO_REGION_SUBTYPE_CXL_COMP_REGS       (2)
+
 /* sub-types for VFIO_REGION_TYPE_GFX */
 #define VFIO_REGION_SUBTYPE_GFX_EDID            (1)
 
-- 
2.25.1