KVM: Don't pre-reserve xarray entries when storing empty/NULL attributesgrafted

Skip the xarray reservation loop when clearing all memory attributes, as
storing NULL only erases the entry and never needs to allocate, so no
reservation (and no cleanup of a failed one) is required in that case.

Suggested-by: Sean Christopherson <seanjc@google.com>
Cc: David Ballesteros <davimaba.v@proton.me>
Signed-off-by: Zeng Chi <zengchi@kylinos.cn>
Link: https://patch.msgid.link/20260921102442.1232375-1-zeng_chi911@163.com
[sean: split to separate patch]
Signed-off-by: Sean Christopherson <seanjc@google.com>

6 files changed, 793 insertions, 0 deletions

diff --git a/include/cxl/cxl.h b/include/cxl/cxl.h
new file mode 100644
index 000000000..802b143de
--- /dev/null
+++ b/include/cxl/cxl.h
@@ -0,0 +1,231 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2020 Intel Corporation. */
+/* Copyright(c) 2026 Advanced Micro Devices, Inc. */
+
+#ifndef __CXL_CXL_H__
+#define __CXL_CXL_H__
+
+#include <linux/node.h>
+#include <linux/ioport.h>
+#include <cxl/mailbox.h>
+
+/**
+ * enum cxl_devtype - delineate type-2 from a generic type-3 device
+ * @CXL_DEVTYPE_DEVMEM: Vendor specific CXL Type-2 device implementing HDM-D or
+ *			 HDM-DB, no requirement that this device implements a
+ *			 mailbox, or other memory-device-standard manageability
+ *			 flows.
+ * @CXL_DEVTYPE_CLASSMEM: Common class definition of a CXL Type-3 device with
+ *			   HDM-H and class-mandatory memory device registers
+ */
+enum cxl_devtype {
+	CXL_DEVTYPE_DEVMEM,
+	CXL_DEVTYPE_CLASSMEM,
+};
+
+struct device;
+
+/*
+ * Using struct_group() allows for per register-block-type helper routines,
+ * without requiring block-type agnostic code to include the prefix.
+ */
+struct cxl_regs {
+	/*
+	 * Common set of CXL Component register block base pointers
+	 * @hdm_decoder: CXL 2.0 8.2.5.12 CXL HDM Decoder Capability Structure
+	 * @ras: CXL 2.0 8.2.5.9 CXL RAS Capability Structure
+	 */
+	struct_group_tagged(cxl_component_regs, component,
+		void __iomem *hdm_decoder;
+		void __iomem *ras;
+	);
+	/*
+	 * Common set of CXL Device register block base pointers
+	 * @status: CXL 2.0 8.2.8.3 Device Status Registers
+	 * @mbox: CXL 2.0 8.2.8.4 Mailbox Registers
+	 * @memdev: CXL 2.0 8.2.8.5 Memory Device Registers
+	 */
+	struct_group_tagged(cxl_device_regs, device_regs,
+		void __iomem *status, *mbox, *memdev;
+	);
+
+	struct_group_tagged(cxl_pmu_regs, pmu_regs,
+		void __iomem *pmu;
+	);
+
+	/*
+	 * RCH downstream port specific RAS register
+	 * @aer: CXL 3.0 8.2.1.1 RCH Downstream Port RCRB
+	 */
+	struct_group_tagged(cxl_rch_regs, rch_regs,
+		void __iomem *dport_aer;
+	);
+
+	/*
+	 * RCD upstream port specific PCIe cap register
+	 * @pcie_cap: CXL 3.0 8.2.1.2 RCD Upstream Port RCRB
+	 */
+	struct_group_tagged(cxl_rcd_regs, rcd_regs,
+		void __iomem *rcd_pcie_cap;
+	);
+};
+
+struct cxl_reg_map {
+	bool valid;
+	int id;
+	unsigned long offset;
+	unsigned long size;
+};
+
+struct cxl_component_reg_map {
+	struct cxl_reg_map hdm_decoder;
+	struct cxl_reg_map ras;
+};
+
+struct cxl_device_reg_map {
+	struct cxl_reg_map status;
+	struct cxl_reg_map mbox;
+	struct cxl_reg_map memdev;
+};
+
+struct cxl_pmu_reg_map {
+	struct cxl_reg_map pmu;
+};
+
+/**
+ * struct cxl_register_map - DVSEC harvested register block mapping parameters
+ * @host: device for devm operations and logging
+ * @base: virtual base of the register-block-BAR + @block_offset
+ * @resource: physical resource base of the register block
+ * @max_size: maximum mapping size to perform register search
+ * @reg_type: see enum cxl_regloc_type
+ * @component_map: cxl_reg_map for component registers
+ * @device_map: cxl_reg_maps for device registers
+ * @pmu_map: cxl_reg_maps for CXL Performance Monitoring Units
+ */
+struct cxl_register_map {
+	struct device *host;
+	void __iomem *base;
+	resource_size_t resource;
+	resource_size_t max_size;
+	u8 reg_type;
+	union {
+		struct cxl_component_reg_map component_map;
+		struct cxl_device_reg_map device_map;
+		struct cxl_pmu_reg_map pmu_map;
+	};
+};
+
+/**
+ * struct cxl_dpa_perf - DPA performance property entry
+ * @dpa_range: range for DPA address
+ * @coord: QoS performance data (i.e. latency, bandwidth)
+ * @cdat_coord: raw QoS performance data from CDAT
+ * @qos_class: QoS Class cookies
+ */
+struct cxl_dpa_perf {
+	struct range dpa_range;
+	struct access_coordinate coord[ACCESS_COORDINATE_MAX];
+	struct access_coordinate cdat_coord[ACCESS_COORDINATE_MAX];
+	int qos_class;
+};
+
+enum cxl_partition_mode {
+	CXL_PARTMODE_RAM,
+	CXL_PARTMODE_PMEM,
+};
+
+/**
+ * struct cxl_dpa_partition - DPA partition descriptor
+ * @res: shortcut to the partition in the DPA resource tree (cxlds->dpa_res)
+ * @perf: performance attributes of the partition from CDAT
+ * @mode: operation mode for the DPA capacity, e.g. ram, pmem, dynamic...
+ */
+struct cxl_dpa_partition {
+	struct resource res;
+	struct cxl_dpa_perf perf;
+	enum cxl_partition_mode mode;
+};
+
+#define CXL_NR_PARTITIONS_MAX 2
+
+/**
+ * struct cxl_dev_state - The driver device state
+ *
+ * cxl_dev_state represents the CXL driver/device state.  It provides an
+ * interface to mailbox commands as well as some cached data about the device.
+ * Currently only memory devices are represented.
+ *
+ * @dev: The device associated with this CXL state
+ * @cxlmd: The device representing the CXL.mem capabilities of @dev
+ * @reg_map: component and ras register mapping parameters
+ * @regs: Parsed register blocks
+ * @cxl_dvsec: Offset to the PCIe device DVSEC
+ * @rcd: operating in RCD mode (CXL 3.0 9.11.8 CXL Devices Attached to an RCH)
+ * @media_ready: Indicate whether the device media is usable
+ * @dpa_res: Overall DPA resource tree for the device
+ * @part: DPA partition array
+ * @nr_partitions: Number of DPA partitions
+ * @serial: PCIe Device Serial Number
+ * @type: Generic Memory Class device or Vendor Specific Memory device
+ * @cxl_mbox: CXL mailbox context
+ * @cxlfs: CXL features context
+ */
+struct cxl_dev_state {
+	/* public for Type2 drivers */
+	struct device *dev;
+	struct cxl_memdev *cxlmd;
+
+	/* private for Type2 drivers */
+	struct cxl_register_map reg_map;
+	struct cxl_device_regs regs;
+	int cxl_dvsec;
+	bool rcd;
+	bool media_ready;
+	struct resource dpa_res;
+	struct cxl_dpa_partition part[CXL_NR_PARTITIONS_MAX];
+	unsigned int nr_partitions;
+	u64 serial;
+	enum cxl_devtype type;
+	struct cxl_mailbox cxl_mbox;
+#ifdef CONFIG_CXL_FEATURES
+	struct cxl_features_state *cxlfs;
+#endif
+};
+
+struct cxl_dev_state *_devm_cxl_dev_state_create(struct device *dev,
+						 enum cxl_devtype type,
+						 u64 serial, u16 dvsec,
+						 size_t size, bool has_mbox);
+
+/**
+ * cxl_dev_state_create - safely create and cast a cxl dev state embedded in a
+ * driver specific struct.
+ *
+ * @parent: device behind the request
+ * @type: CXL device type
+ * @serial: device identification
+ * @dvsec: dvsec capability offset
+ * @drv_struct: driver struct embedding a cxl_dev_state struct
+ * @member: name of the struct cxl_dev_state member in drv_struct
+ * @mbox: true if mailbox supported
+ *
+ * Returns a pointer to the drv_struct allocated and embedding a cxl_dev_state
+ * struct initialized.
+ *
+ * Introduced for Type2 driver support.
+ */
+#define devm_cxl_dev_state_create(parent, type, serial, dvsec, drv_struct, member, mbox)	\
+	({										\
+		static_assert(__same_type(struct cxl_dev_state,				\
+			      ((drv_struct *)NULL)->member));				\
+		static_assert(offsetof(drv_struct, member) == 0);			\
+		(drv_struct *)_devm_cxl_dev_state_create(parent, type, serial, dvsec,	\
+						      sizeof(drv_struct), mbox);	\
+	})
+
+struct cxl_memdev *devm_cxl_probe_mem(struct cxl_dev_state *cxlds,
+				      struct range *range);
+
+int cxl_set_capacity(struct cxl_dev_state *cxlds, u64 capacity);
+#endif /* __CXL_CXL_H__ */
diff --git a/include/cxl/einj.h b/include/cxl/einj.h
new file mode 100644
index 000000000..624ff6ff4
--- /dev/null
+++ b/include/cxl/einj.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * CXL protocol Error INJection support.
+ *
+ * Copyright (c) 2023 Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Author: Ben Cheatham <benjamin.cheatham@amd.com>
+ */
+#ifndef EINJ_CXL_H
+#define EINJ_CXL_H
+
+#include <linux/errno.h>
+#include <linux/types.h>
+
+struct pci_dev;
+struct seq_file;
+
+#if IS_ENABLED(CONFIG_ACPI_APEI_EINJ_CXL)
+int einj_cxl_available_error_type_show(struct seq_file *m, void *v);
+int einj_cxl_inject_error(struct pci_dev *dport_dev, u64 type);
+int einj_cxl_inject_rch_error(u64 rcrb, u64 type);
+bool einj_cxl_is_initialized(void);
+#else /* !IS_ENABLED(CONFIG_ACPI_APEI_EINJ_CXL) */
+static inline int einj_cxl_available_error_type_show(struct seq_file *m,
+						     void *v)
+{
+	return -ENXIO;
+}
+
+static inline int einj_cxl_inject_error(struct pci_dev *dport_dev, u64 type)
+{
+	return -ENXIO;
+}
+
+static inline int einj_cxl_inject_rch_error(u64 rcrb, u64 type)
+{
+	return -ENXIO;
+}
+
+static inline bool einj_cxl_is_initialized(void) { return false; }
+#endif /* CONFIG_ACPI_APEI_EINJ_CXL */
+
+#endif /* EINJ_CXL_H */
diff --git a/include/cxl/event.h b/include/cxl/event.h
new file mode 100644
index 000000000..b5673384d
--- /dev/null
+++ b/include/cxl/event.h
@@ -0,0 +1,336 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2023 Intel Corporation. */
+#ifndef _LINUX_CXL_EVENT_H
+#define _LINUX_CXL_EVENT_H
+
+#include <linux/types.h>
+#include <linux/uuid.h>
+#include <linux/workqueue_types.h>
+
+/*
+ * Common Event Record Format
+ * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
+ */
+struct cxl_event_record_hdr {
+	u8 length;
+	u8 flags[3];
+	__le16 handle;
+	__le16 related_handle;
+	__le64 timestamp;
+	u8 maint_op_class;
+	u8 maint_op_sub_class;
+	__le16 ld_id;
+	u8 head_id;
+	u8 reserved[11];
+} __packed;
+
+struct cxl_event_media_hdr {
+	struct cxl_event_record_hdr hdr;
+	__le64 phys_addr;
+	u8 descriptor;
+	u8 type;
+	u8 transaction_type;
+	/*
+	 * The meaning of Validity Flags from bit 2 is
+	 * different across DRAM and General Media records
+	 */
+	u8 validity_flags[2];
+	u8 channel;
+	u8 rank;
+} __packed;
+
+#define CXL_EVENT_RECORD_DATA_LENGTH 0x50
+struct cxl_event_generic {
+	struct cxl_event_record_hdr hdr;
+	u8 data[CXL_EVENT_RECORD_DATA_LENGTH];
+} __packed;
+
+/*
+ * General Media Event Record
+ * CXL rev 3.1 Section 8.2.9.2.1.1; Table 8-45
+ */
+#define CXL_EVENT_GEN_MED_COMP_ID_SIZE	0x10
+struct cxl_event_gen_media {
+	struct cxl_event_media_hdr media_hdr;
+	u8 device[3];
+	u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
+	u8 cme_threshold_ev_flags;
+	u8 cme_count[3];
+	u8 sub_type;
+	u8 reserved[41];
+} __packed;
+
+/*
+ * DRAM Event Record - DER
+ * CXL rev 3.1 section 8.2.9.2.1.2; Table 8-46
+ */
+#define CXL_EVENT_DER_CORRECTION_MASK_SIZE	0x20
+struct cxl_event_dram {
+	struct cxl_event_media_hdr media_hdr;
+	u8 nibble_mask[3];
+	u8 bank_group;
+	u8 bank;
+	u8 row[3];
+	u8 column[2];
+	u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE];
+	u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
+	u8 sub_channel;
+	u8 cme_threshold_ev_flags;
+	u8 cvme_count[3];
+	u8 sub_type;
+	u8 reserved;
+} __packed;
+
+/*
+ * Get Health Info Record
+ * CXL rev 3.1 section 8.2.9.9.3.1; Table 8-133
+ */
+struct cxl_get_health_info {
+	u8 health_status;
+	u8 media_status;
+	u8 add_status;
+	u8 life_used;
+	u8 device_temp[2];
+	u8 dirty_shutdown_cnt[4];
+	u8 cor_vol_err_cnt[4];
+	u8 cor_per_err_cnt[4];
+} __packed;
+
+/*
+ * Memory Module Event Record
+ * CXL rev 3.1 section 8.2.9.2.1.3; Table 8-47
+ */
+struct cxl_event_mem_module {
+	struct cxl_event_record_hdr hdr;
+	u8 event_type;
+	struct cxl_get_health_info info;
+	u8 validity_flags[2];
+	u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
+	u8 event_sub_type;
+	u8 reserved[0x2a];
+} __packed;
+
+/*
+ * Memory Sparing Event Record - MSER
+ * CXL rev 3.2 section 8.2.10.2.1.4; Table 8-60
+ */
+struct cxl_event_mem_sparing {
+	struct cxl_event_record_hdr hdr;
+	/*
+	 * The fields maintenance operation class and maintenance operation
+	 * subclass defined in the Memory Sparing Event Record are the
+	 * duplication of the same in the common event record. Thus defined
+	 * as reserved and to be removed after the spec correction.
+	 */
+	u8 rsv1;
+	u8 rsv2;
+	u8 flags;
+	u8 result;
+	__le16 validity_flags;
+	u8 reserved1[6];
+	__le16 res_avail;
+	u8 channel;
+	u8 rank;
+	u8 nibble_mask[3];
+	u8 bank_group;
+	u8 bank;
+	u8 row[3];
+	__le16 column;
+	u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
+	u8 sub_channel;
+	u8 reserved2[0x25];
+} __packed;
+
+union cxl_event {
+	struct cxl_event_generic generic;
+	struct cxl_event_gen_media gen_media;
+	struct cxl_event_dram dram;
+	struct cxl_event_mem_module mem_module;
+	struct cxl_event_mem_sparing mem_sparing;
+	/* dram & gen_media event header */
+	struct cxl_event_media_hdr media_hdr;
+} __packed;
+
+/*
+ * Common Event Record Format; in event logs
+ * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
+ */
+struct cxl_event_record_raw {
+	uuid_t id;
+	union cxl_event event;
+} __packed;
+
+enum cxl_event_type {
+	CXL_CPER_EVENT_GENERIC,
+	CXL_CPER_EVENT_GEN_MEDIA,
+	CXL_CPER_EVENT_DRAM,
+	CXL_CPER_EVENT_MEM_MODULE,
+	CXL_CPER_EVENT_MEM_SPARING,
+};
+
+#define CPER_CXL_DEVICE_ID_VALID		BIT(0)
+#define CPER_CXL_DEVICE_SN_VALID		BIT(1)
+#define CPER_CXL_COMP_EVENT_LOG_VALID		BIT(2)
+struct cxl_cper_event_rec {
+	struct {
+		u32 length;
+		u64 validation_bits;
+		struct cper_cxl_event_devid {
+			u16 vendor_id;
+			u16 device_id;
+			u8 func_num;
+			u8 device_num;
+			u8 bus_num;
+			u16 segment_num;
+			u16 slot_num; /* bits 2:0 reserved */
+			u8 reserved;
+		} __packed device_id;
+		struct cper_cxl_event_sn {
+			u32 lower_dw;
+			u32 upper_dw;
+		} __packed dev_serial_num;
+	} __packed hdr;
+
+	union cxl_event event;
+} __packed;
+
+struct cxl_cper_work_data {
+	enum cxl_event_type event_type;
+	struct cxl_cper_event_rec rec;
+};
+
+#define PROT_ERR_VALID_AGENT_TYPE		BIT_ULL(0)
+#define PROT_ERR_VALID_AGENT_ADDRESS		BIT_ULL(1)
+#define PROT_ERR_VALID_DEVICE_ID		BIT_ULL(2)
+#define PROT_ERR_VALID_SERIAL_NUMBER		BIT_ULL(3)
+#define PROT_ERR_VALID_CAPABILITY		BIT_ULL(4)
+#define PROT_ERR_VALID_DVSEC			BIT_ULL(5)
+#define PROT_ERR_VALID_ERROR_LOG		BIT_ULL(6)
+
+/*
+ * The layout of the enumeration and the values matches CXL Agent Type
+ * field in the UEFI 2.10 Section N.2.13,
+ */
+enum {
+	RCD,	/* Restricted CXL Device */
+	RCH_DP,	/* Restricted CXL Host Downstream Port */
+	DEVICE,	/* CXL Device */
+	LD,	/* CXL Logical Device */
+	FMLD,	/* CXL Fabric Manager managed Logical Device */
+	RP,	/* CXL Root Port */
+	DSP,	/* CXL Downstream Switch Port */
+	USP,	/* CXL Upstream Switch Port */
+};
+
+#pragma pack(1)
+
+/* Compute Express Link Protocol Error Section, UEFI v2.10 sec N.2.13 */
+struct cxl_cper_sec_prot_err {
+	u64 valid_bits;
+	u8 agent_type;
+	u8 reserved[7];
+
+	/*
+	 * Except for RCH Downstream Port, all the remaining CXL Agent
+	 * types are uniquely identified by the PCIe compatible SBDF number.
+	 */
+	union {
+		u64 rcrb_base_addr;
+		struct {
+			u8 function;
+			u8 device;
+			u8 bus;
+			u16 segment;
+			u8 reserved_1[3];
+		};
+	} agent_addr;
+
+	struct {
+		u16 vendor_id;
+		u16 device_id;
+		u16 subsystem_vendor_id;
+		u16 subsystem_id;
+		u8 class_code[2];
+		u16 slot;
+		u8 reserved_1[4];
+	} device_id;
+
+	struct {
+		u32 lower_dw;
+		u32 upper_dw;
+	} dev_serial_num;
+
+	u8 capability[60];
+	u16 dvsec_len;
+	u16 err_len;
+	u8 reserved_2[4];
+};
+
+#pragma pack()
+
+/* CXL RAS Capability Structure, CXL v3.0 sec 8.2.4.16 */
+struct cxl_ras_capability_regs {
+	u32 uncor_status;
+	u32 uncor_mask;
+	u32 uncor_severity;
+	u32 cor_status;
+	u32 cor_mask;
+	u32 cap_control;
+	u32 header_log[16];
+};
+
+struct cxl_cper_prot_err_work_data {
+	struct cxl_cper_sec_prot_err prot_err;
+	struct cxl_ras_capability_regs ras_cap;
+	int severity;
+};
+
+#ifdef CONFIG_ACPI_APEI_GHES
+int cxl_cper_register_work(struct work_struct *work);
+void cxl_cper_unregister_work(struct work_struct *work);
+int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd);
+void cxl_cper_register_prot_err_work(struct work_struct *work);
+void cxl_cper_unregister_prot_err_work(void);
+int cxl_cper_prot_err_kfifo_get(struct cxl_cper_prot_err_work_data *wd);
+#else
+static inline int cxl_cper_register_work(struct work_struct *work)
+{
+	return 0;
+}
+
+static inline void cxl_cper_unregister_work(struct work_struct *work) { }
+static inline int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd)
+{
+	return 0;
+}
+static inline void cxl_cper_register_prot_err_work(struct work_struct *work) { }
+static inline void cxl_cper_unregister_prot_err_work(void) { }
+static inline int cxl_cper_prot_err_kfifo_get(struct cxl_cper_prot_err_work_data *wd)
+{
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+int cxl_cper_sec_prot_err_valid(struct cxl_cper_sec_prot_err *prot_err);
+int cxl_cper_setup_prot_err_work_data(struct cxl_cper_prot_err_work_data *wd,
+				      struct cxl_cper_sec_prot_err *prot_err,
+				      int severity);
+#else
+static inline int
+cxl_cper_sec_prot_err_valid(struct cxl_cper_sec_prot_err *prot_err)
+{
+	return -EOPNOTSUPP;
+}
+static inline int
+cxl_cper_setup_prot_err_work_data(struct cxl_cper_prot_err_work_data *wd,
+				  struct cxl_cper_sec_prot_err *prot_err,
+				  int severity)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *wd);
+
+#endif /* _LINUX_CXL_EVENT_H */
diff --git a/include/cxl/features.h b/include/cxl/features.h
new file mode 100644
index 000000000..b9297693d
--- /dev/null
+++ b/include/cxl/features.h
@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2024-2025 Intel Corporation. */
+#ifndef __CXL_FEATURES_H__
+#define __CXL_FEATURES_H__
+
+#include <linux/uuid.h>
+#include <linux/fwctl.h>
+#include <uapi/cxl/features.h>
+
+/* Feature UUIDs used by the kernel */
+#define CXL_FEAT_PATROL_SCRUB_UUID						\
+	UUID_INIT(0x96dad7d6, 0xfde8, 0x482b, 0xa7, 0x33, 0x75, 0x77, 0x4e,	\
+		  0x06, 0xdb, 0x8a)
+
+#define CXL_FEAT_ECS_UUID							\
+	UUID_INIT(0xe5b13f22, 0x2328, 0x4a14, 0xb8, 0xba, 0xb9, 0x69, 0x1e,	\
+		  0x89, 0x33, 0x86)
+
+#define CXL_FEAT_SPPR_UUID							\
+	UUID_INIT(0x892ba475, 0xfad8, 0x474e, 0x9d, 0x3e, 0x69, 0x2c, 0x91,	\
+		  0x75, 0x68, 0xbb)
+
+#define CXL_FEAT_HPPR_UUID							\
+	UUID_INIT(0x80ea4521, 0x786f, 0x4127, 0xaf, 0xb1, 0xec, 0x74, 0x59,	\
+		  0xfb, 0x0e, 0x24)
+
+#define CXL_FEAT_CACHELINE_SPARING_UUID						\
+	UUID_INIT(0x96C33386, 0x91dd, 0x44c7, 0x9e, 0xcb, 0xfd, 0xaf, 0x65,	\
+		  0x03, 0xba, 0xc4)
+
+#define CXL_FEAT_ROW_SPARING_UUID						\
+	UUID_INIT(0x450ebf67, 0xb135, 0x4f97, 0xa4, 0x98, 0xc2, 0xd5, 0x7f,	\
+		  0x27, 0x9b, 0xed)
+
+#define CXL_FEAT_BANK_SPARING_UUID						\
+	UUID_INIT(0x78b79636, 0x90ac, 0x4b64, 0xa4, 0xef, 0xfa, 0xac, 0x5d,	\
+		  0x18, 0xa8, 0x63)
+
+#define CXL_FEAT_RANK_SPARING_UUID						\
+	UUID_INIT(0x34dbaff5, 0x0552, 0x4281, 0x8f, 0x76, 0xda, 0x0b, 0x5e,	\
+		  0x7a, 0x76, 0xa7)
+
+/* Feature commands capability supported by a device */
+enum cxl_features_capability {
+	CXL_FEATURES_NONE = 0,
+	CXL_FEATURES_RO,
+	CXL_FEATURES_RW,
+};
+
+/**
+ * struct cxl_features_state - The Features state for the device
+ * @cxlds: Pointer to CXL device state
+ * @entries: CXl feature entry context
+ */
+struct cxl_features_state {
+	struct cxl_dev_state *cxlds;
+	struct cxl_feat_entries {
+		int num_features;
+		int num_user_features;
+		struct cxl_feat_entry ent[] __counted_by(num_features);
+	} *entries;
+};
+
+struct cxl_mailbox;
+struct cxl_memdev;
+#ifdef CONFIG_CXL_FEATURES
+struct cxl_features_state *to_cxlfs(struct cxl_dev_state *cxlds);
+int devm_cxl_setup_features(struct cxl_dev_state *cxlds);
+int devm_cxl_setup_fwctl(struct device *host, struct cxl_memdev *cxlmd);
+#else
+static inline struct cxl_features_state *to_cxlfs(struct cxl_dev_state *cxlds)
+{
+	return NULL;
+}
+
+static inline int devm_cxl_setup_features(struct cxl_dev_state *cxlds)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int devm_cxl_setup_fwctl(struct device *host,
+				       struct cxl_memdev *cxlmd)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+#endif
diff --git a/include/cxl/mailbox.h b/include/cxl/mailbox.h
new file mode 100644
index 000000000..d008b9db0
--- /dev/null
+++ b/include/cxl/mailbox.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2024 Intel Corporation. */
+#ifndef __CXL_MBOX_H__
+#define __CXL_MBOX_H__
+#include <linux/rcuwait.h>
+#include <cxl/features.h>
+#include <uapi/linux/cxl_mem.h>
+
+/**
+ * struct cxl_mbox_cmd - A command to be submitted to hardware.
+ * @opcode: (input) The command set and command submitted to hardware.
+ * @payload_in: (input) Pointer to the input payload.
+ * @payload_out: (output) Pointer to the output payload. Must be allocated by
+ *		 the caller.
+ * @size_in: (input) Number of bytes to load from @payload_in.
+ * @size_out: (input) Max number of bytes loaded into @payload_out.
+ *            (output) Number of bytes generated by the device. For fixed size
+ *            outputs commands this is always expected to be deterministic. For
+ *            variable sized output commands, it tells the exact number of bytes
+ *            written.
+ * @min_out: (input) internal command output payload size validation
+ * @poll_count: (input) Number of timeouts to attempt.
+ * @poll_interval_ms: (input) Time between mailbox background command polling
+ *                    interval timeouts.
+ * @return_code: (output) Error code returned from hardware.
+ *
+ * This is the primary mechanism used to send commands to the hardware.
+ * All the fields except @payload_* correspond exactly to the fields described in
+ * Command Register section of the CXL 2.0 8.2.8.4.5. @payload_in and
+ * @payload_out are written to, and read from the Command Payload Registers
+ * defined in CXL 2.0 8.2.8.4.8.
+ */
+struct cxl_mbox_cmd {
+	u16 opcode;
+	void *payload_in;
+	void *payload_out;
+	size_t size_in;
+	size_t size_out;
+	size_t min_out;
+	int poll_count;
+	int poll_interval_ms;
+	u16 return_code;
+};
+
+/**
+ * struct cxl_mailbox - context for CXL mailbox operations
+ * @host: device that hosts the mailbox
+ * @enabled_cmds: mailbox commands that are enabled by the driver
+ * @exclusive_cmds: mailbox commands that are exclusive to the kernel
+ * @payload_size: Size of space for payload
+ *                (CXL 3.1 8.2.8.4.3 Mailbox Capabilities Register)
+ * @mbox_mutex: mutex protects device mailbox and firmware
+ * @feat_mutex: serializes multi-part Get/Set Feature transfers
+ * @mbox_wait: rcuwait for mailbox
+ * @mbox_send: @dev specific transport for transmitting mailbox commands
+ * @feat_cap: Features capability
+ */
+struct cxl_mailbox {
+	struct device *host;
+	DECLARE_BITMAP(enabled_cmds, CXL_MEM_COMMAND_ID_MAX);
+	DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX);
+	size_t payload_size;
+	struct mutex mbox_mutex; /* lock to protect mailbox context */
+	struct mutex feat_mutex;
+	struct rcuwait mbox_wait;
+	int (*mbox_send)(struct cxl_mailbox *cxl_mbox, struct cxl_mbox_cmd *cmd);
+	enum cxl_features_capability feat_cap;
+};
+
+int cxl_mailbox_init(struct cxl_mailbox *cxl_mbox, struct device *host);
+
+#endif
diff --git a/include/cxl/pci.h b/include/cxl/pci.h
new file mode 100644
index 000000000..3e0000015
--- /dev/null
+++ b/include/cxl/pci.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2020 Intel Corporation. All rights reserved. */
+
+#ifndef __CXL_CXL_PCI_H__
+#define __CXL_CXL_PCI_H__
+
+/* Register Block Identifier (RBI) */
+enum cxl_regloc_type {
+	CXL_REGLOC_RBI_EMPTY = 0,
+	CXL_REGLOC_RBI_COMPONENT,
+	CXL_REGLOC_RBI_VIRT,
+	CXL_REGLOC_RBI_MEMDEV,
+	CXL_REGLOC_RBI_PMU,
+	CXL_REGLOC_RBI_TYPES
+};
+
+struct cxl_register_map;
+struct pci_dev;
+
+int cxl_pci_setup_regs(struct pci_dev *pdev, enum cxl_regloc_type type,
+		       struct cxl_register_map *map);
+#endif