Resguardo inicial

linux-7.2.3/drivers/cxl/Kconfig

@@ -0,0 +1,246 @@
+# SPDX-License-Identifier: GPL-2.0-only
+menuconfig CXL_BUS
+	tristate "CXL (Compute Express Link) Devices Support"
+	depends on PCI
+	select FW_LOADER
+	select FW_UPLOAD
+	select PCI_DOE
+	select FIRMWARE_TABLE
+	select NUMA_KEEP_MEMINFO if NUMA_MEMBLKS
+	select FWCTL if CXL_FEATURES
+	help
+	  CXL is a bus that is electrically compatible with PCI Express, but
+	  layers three protocols on that signalling (CXL.io, CXL.cache, and
+	  CXL.mem). The CXL.cache protocol allows devices to hold cachelines
+	  locally, the CXL.mem protocol allows devices to be fully coherent
+	  memory targets, the CXL.io protocol is equivalent to PCI Express.
+	  Say 'y' to enable support for the configuration and management of
+	  devices supporting these protocols.
+
+if CXL_BUS
+
+config CXL_PCI
+	tristate "PCI manageability"
+	default CXL_BUS
+	select CXL_MEM
+	help
+	  The CXL specification defines a "CXL memory device" sub-class in the
+	  PCI "memory controller" base class of devices. Device's identified by
+	  this class code provide support for volatile and / or persistent
+	  memory to be mapped into the system address map (Host-managed Device
+	  Memory (HDM)).
+
+	  Say 'y/m' to enable a driver that will attach to CXL memory expander
+	  devices enumerated by the memory device class code for configuration
+	  and management primarily via the mailbox interface. See Chapter 2.3
+	  Type 3 CXL Device in the CXL 2.0 specification for more details.
+
+	  If unsure say 'm'.
+
+config CXL_MEM_RAW_COMMANDS
+	bool "RAW Command Interface for Memory Devices"
+	depends on CXL_PCI
+	help
+	  Enable CXL RAW command interface.
+
+	  The CXL driver ioctl interface may assign a kernel ioctl command
+	  number for each specification defined opcode. At any given point in
+	  time the number of opcodes that the specification defines and a device
+	  may implement may exceed the kernel's set of associated ioctl function
+	  numbers. The mismatch is either by omission, specification is too new,
+	  or by design. When prototyping new hardware, or developing / debugging
+	  the driver it is useful to be able to submit any possible command to
+	  the hardware, even commands that may crash the kernel due to their
+	  potential impact to memory currently in use by the kernel.
+
+	  If developing CXL hardware or the driver say Y, otherwise say N.
+
+config CXL_ACPI
+	tristate "CXL ACPI: Platform Support"
+	depends on ACPI
+	depends on ACPI_NUMA
+	depends on CXL_PMEM || !CXL_PMEM
+	default CXL_BUS
+	select ACPI_TABLE_LIB
+	select ACPI_HMAT
+	select CXL_PORT
+	help
+	  Enable support for host managed device memory (HDM) resources
+	  published by a platform's ACPI CXL memory layout description.  See
+	  Chapter 9.14.1 CXL Early Discovery Table (CEDT) in the CXL 2.0
+	  specification, and CXL Fixed Memory Window Structures (CEDT.CFMWS)
+	  (https://www.computeexpresslink.org/spec-landing). The CXL core
+	  consumes these resource to publish the root of a cxl_port decode
+	  hierarchy to map regions that represent System RAM, or Persistent
+	  Memory regions to be managed by LIBNVDIMM.
+
+	  If unsure say 'm'.
+
+config CXL_PMEM
+	tristate "CXL PMEM: Persistent Memory Support"
+	depends on LIBNVDIMM
+	default CXL_BUS
+	help
+	  In addition to typical memory resources a platform may also advertise
+	  support for persistent memory attached via CXL. This support is
+	  managed via a bridge driver from CXL to the LIBNVDIMM system
+	  subsystem. Say 'y/m' to enable support for enumerating and
+	  provisioning the persistent memory capacity of CXL memory expanders.
+
+	  If unsure say 'm'.
+
+config CXL_MEM
+	tristate "CXL: Memory Expansion"
+	default CXL_BUS
+	help
+	  The CXL.mem protocol allows a device to act as a provider of "System
+	  RAM" and/or "Persistent Memory" that is fully coherent as if the
+	  memory were attached to the typical CPU memory controller. This is
+	  known as HDM "Host-managed Device Memory".
+
+	  Say 'y/m' to enable a driver that will attach to CXL.mem devices for
+	  memory expansion and control of HDM. See Chapter 9.13 in the CXL 2.0
+	  specification for a detailed description of HDM.
+
+	  If unsure say 'm'.
+
+config CXL_FEATURES
+	bool "CXL: Features"
+	depends on CXL_PCI
+	help
+	  Enable support for CXL Features. A CXL device that includes a mailbox
+	  supports commands that allows listing, getting, and setting of
+	  optionally defined features such as memory sparing or post package
+	  sparing. Vendors may define custom features for the device.
+
+	  If unsure say 'n'
+
+config CXL_EDAC_MEM_FEATURES
+	bool "CXL: EDAC Memory Features"
+	depends on EXPERT
+	depends on CXL_MEM
+	depends on CXL_FEATURES
+	depends on EDAC >= CXL_BUS
+	help
+	  The CXL EDAC memory feature is optional and allows host to
+	  control the EDAC memory features configurations of CXL memory
+	  expander devices.
+
+	  Say 'y' if you have an expert need to change default settings
+	  of a memory RAS feature established by the platform/device.
+	  Otherwise say 'n'.
+
+config CXL_EDAC_SCRUB
+	bool "Enable CXL Patrol Scrub Control (Patrol Read)"
+	depends on CXL_EDAC_MEM_FEATURES
+	depends on EDAC_SCRUB
+	help
+	  The CXL EDAC scrub control is optional and allows host to
+	  control the scrub feature configurations of CXL memory expander
+	  devices.
+
+	  When enabled 'cxl_mem' and 'cxl_region' EDAC devices are
+	  published with memory scrub control attributes as described by
+	  Documentation/ABI/testing/sysfs-edac-scrub.
+
+	  Say 'y' if you have an expert need to change default settings
+	  of a memory scrub feature established by the platform/device
+	  (e.g. scrub rates for the patrol scrub feature).
+	  Otherwise say 'n'.
+
+config CXL_EDAC_ECS
+	bool "Enable CXL Error Check Scrub (Repair)"
+	depends on CXL_EDAC_MEM_FEATURES
+	depends on EDAC_ECS
+	help
+	  The CXL EDAC ECS control is optional and allows host to
+	  control the ECS feature configurations of CXL memory expander
+	  devices.
+
+	  When enabled 'cxl_mem' EDAC devices are published with memory
+	  ECS control attributes as described by
+	  Documentation/ABI/testing/sysfs-edac-ecs.
+
+	  Say 'y' if you have an expert need to change default settings
+	  of a memory ECS feature established by the platform/device.
+	  Otherwise say 'n'.
+
+config CXL_EDAC_MEM_REPAIR
+	bool "Enable CXL Memory Repair"
+	depends on CXL_EDAC_MEM_FEATURES
+	depends on EDAC_MEM_REPAIR
+	help
+	  The CXL EDAC memory repair control is optional and allows host
+	  to control the memory repair features (e.g. sparing, PPR)
+	  configurations of CXL memory expander devices.
+
+	  When enabled, the memory repair feature requires an additional
+	  memory of approximately 43KB to store CXL DRAM and CXL general
+	  media event records.
+
+	  When enabled 'cxl_mem' EDAC devices are published with memory
+	  repair control attributes as described by
+	  Documentation/ABI/testing/sysfs-edac-memory-repair.
+
+	  Say 'y' if you have an expert need to change default settings
+	  of a memory repair feature established by the platform/device.
+	  Otherwise say 'n'.
+
+config CXL_PORT
+	default CXL_BUS
+	tristate
+
+config CXL_SUSPEND
+	def_bool y
+	depends on SUSPEND && CXL_MEM
+
+config CXL_REGION
+	bool "CXL: Region Support"
+	default CXL_BUS
+	# For MAX_PHYSMEM_BITS
+	depends on SPARSEMEM
+	select MEMREGION
+	select GET_FREE_REGION
+	help
+	  Enable the CXL core to enumerate and provision CXL regions. A CXL
+	  region is defined by one or more CXL expanders that decode a given
+	  system-physical address range. For CXL regions established by
+	  platform-firmware this option enables memory error handling to
+	  identify the devices participating in a given interleaved memory
+	  range. Otherwise, platform-firmware managed CXL is enabled by being
+	  placed in the system address map and does not need a driver.
+
+	  If unsure say 'y'
+
+config CXL_REGION_INVALIDATION_TEST
+	bool "CXL: Region Cache Management Bypass (TEST)"
+	depends on CXL_REGION
+	help
+	  CXL Region management and security operations potentially invalidate
+	  the content of CPU caches without notifying those caches to
+	  invalidate the affected cachelines. The CXL Region driver attempts
+	  to invalidate caches when those events occur.  If that invalidation
+	  fails the region will fail to enable.  Reasons for cache
+	  invalidation failure are due to the CPU not providing a cache
+	  invalidation mechanism. For example usage of wbinvd is restricted to
+	  bare metal x86. However, for testing purposes toggling this option
+	  can disable that data integrity safety and proceed with enabling
+	  regions when there might be conflicting contents in the CPU cache.
+
+	  If unsure, or if this kernel is meant for production environments,
+	  say N.
+
+config CXL_MCE
+	def_bool y
+	depends on X86_MCE && MEMORY_FAILURE
+
+config CXL_RAS
+	def_bool y
+	depends on ACPI_APEI_GHES && PCIEAER && CXL_BUS
+
+config CXL_ATL
+	def_bool y
+	depends on CXL_REGION
+	depends on ACPI_PRMT && AMD_NB
+
+endif

linux-7.2.3/drivers/cxl/Makefile

@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# Order is important here for the built-in case:
+# - 'core' first for fundamental init
+# - 'port' before platform root drivers like 'acpi' so that CXL-root ports
+#   are immediately enabled
+# - 'mem' and 'pmem' before endpoint drivers so that memdevs are
+#   immediately enabled
+# - 'pci' last, also mirrors the hardware enumeration hierarchy
+obj-y += core/
+obj-$(CONFIG_CXL_PORT) += cxl_port.o
+obj-$(CONFIG_CXL_ACPI) += cxl_acpi.o
+obj-$(CONFIG_CXL_PMEM) += cxl_pmem.o
+obj-$(CONFIG_CXL_MEM) += cxl_mem.o
+obj-$(CONFIG_CXL_PCI) += cxl_pci.o
+
+cxl_port-y := port.o
+cxl_acpi-y := acpi.o
+cxl_pmem-y := pmem.o security.o
+cxl_mem-y := mem.o
+cxl_pci-y := pci.o

linux-7.2.3/drivers/cxl/core/Makefile

@@ -0,0 +1,24 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_CXL_BUS) += cxl_core.o
+obj-$(CONFIG_CXL_SUSPEND) += suspend.o
+
+ccflags-y += -I$(srctree)/drivers/cxl
+CFLAGS_trace.o = -DTRACE_INCLUDE_PATH=. -I$(src)
+
+cxl_core-y := port.o
+cxl_core-y += pmem.o
+cxl_core-y += regs.o
+cxl_core-y += memdev.o
+cxl_core-y += mbox.o
+cxl_core-y += pci.o
+cxl_core-y += hdm.o
+cxl_core-y += pmu.o
+cxl_core-y += cdat.o
+cxl_core-$(CONFIG_TRACING) += trace.o
+cxl_core-$(CONFIG_CXL_REGION) += region.o region_pmem.o region_dax.o
+cxl_core-$(CONFIG_CXL_MCE) += mce.o
+cxl_core-$(CONFIG_CXL_FEATURES) += features.o
+cxl_core-$(CONFIG_CXL_EDAC_MEM_FEATURES) += edac.o
+cxl_core-$(CONFIG_CXL_RAS) += ras.o
+cxl_core-$(CONFIG_CXL_RAS) += ras_rch.o
+cxl_core-$(CONFIG_CXL_ATL) += atl.o

linux-7.2.3/drivers/cxl/core/atl.c

@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025 Advanced Micro Devices, Inc.
+ */
+
+#include <linux/prmt.h>
+#include <linux/pci.h>
+#include <linux/acpi.h>
+
+#include <cxlmem.h>
+#include "core.h"
+
+/*
+ * PRM Address Translation - CXL DPA to System Physical Address
+ *
+ * Reference:
+ *
+ * AMD Family 1Ah Models 00h–0Fh and Models 10h–1Fh
+ * ACPI v6.5 Porting Guide, Publication # 58088
+ */
+
+static const guid_t prm_cxl_dpa_spa_guid =
+	GUID_INIT(0xee41b397, 0x25d4, 0x452c, 0xad, 0x54, 0x48, 0xc6, 0xe3,
+		  0x48, 0x0b, 0x94);
+
+struct prm_cxl_dpa_spa_data {
+	u64 dpa;
+	u8 reserved;
+	u8 devfn;
+	u8 bus;
+	u8 segment;
+	u64 *spa;
+} __packed;
+
+static u64 prm_cxl_dpa_spa(struct pci_dev *pci_dev, u64 dpa)
+{
+	struct prm_cxl_dpa_spa_data data;
+	u64 spa;
+	int rc;
+
+	data = (struct prm_cxl_dpa_spa_data) {
+		.dpa     = dpa,
+		.devfn   = pci_dev->devfn,
+		.bus     = pci_dev->bus->number,
+		.segment = pci_domain_nr(pci_dev->bus),
+		.spa     = &spa,
+	};
+
+	rc = acpi_call_prm_handler(prm_cxl_dpa_spa_guid, &data);
+	if (rc) {
+		pci_dbg(pci_dev, "failed to get SPA for %#llx: %d\n", dpa, rc);
+		return ULLONG_MAX;
+	}
+
+	pci_dbg(pci_dev, "PRM address translation: DPA -> SPA: %#llx -> %#llx\n", dpa, spa);
+
+	return spa;
+}
+
+static int cxl_prm_setup_root(struct cxl_root *cxl_root, void *data)
+{
+	struct cxl_region_context *ctx = data;
+	struct cxl_endpoint_decoder *cxled = ctx->cxled;
+	struct cxl_decoder *cxld = &cxled->cxld;
+	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
+	struct range hpa_range = ctx->hpa_range;
+	struct pci_dev *pci_dev;
+	u64 spa_len, len;
+	u64 addr, base_spa, base;
+	int ways, gran;
+
+	/*
+	 * When Normalized Addressing is enabled, the endpoint maintains a 1:1
+	 * mapping between HPA and DPA. If disabled, skip address translation
+	 * and perform only a range check.
+	 */
+	if (hpa_range.start != cxled->dpa_res->start)
+		return 0;
+
+	/*
+	 * Endpoints are programmed passthrough in Normalized Addressing mode.
+	 */
+	if (ctx->interleave_ways != 1) {
+		dev_dbg(&cxld->dev, "unexpected interleaving config: ways: %d granularity: %d\n",
+			ctx->interleave_ways, ctx->interleave_granularity);
+		return -ENXIO;
+	}
+
+	if (!cxlmd || !dev_is_pci(cxlmd->dev.parent)) {
+		dev_dbg(&cxld->dev, "No endpoint found: %s, range %#llx-%#llx\n",
+			dev_name(cxld->dev.parent), hpa_range.start,
+			hpa_range.end);
+		return -ENXIO;
+	}
+
+	pci_dev = to_pci_dev(cxlmd->dev.parent);
+
+	/* Translate HPA range to SPA. */
+	base = hpa_range.start;
+	hpa_range.start = prm_cxl_dpa_spa(pci_dev, hpa_range.start);
+	hpa_range.end = prm_cxl_dpa_spa(pci_dev, hpa_range.end);
+	base_spa = hpa_range.start;
+
+	if (hpa_range.start == ULLONG_MAX || hpa_range.end == ULLONG_MAX) {
+		dev_dbg(cxld->dev.parent,
+			"CXL address translation: Failed to translate HPA range: %#llx-%#llx:%#llx-%#llx(%s)\n",
+			hpa_range.start, hpa_range.end, ctx->hpa_range.start,
+			ctx->hpa_range.end, dev_name(&cxld->dev));
+		return -ENXIO;
+	}
+
+	/*
+	 * Since translated addresses include the interleaving offsets, align
+	 * the range to 256 MB.
+	 */
+	hpa_range.start = ALIGN_DOWN(hpa_range.start, SZ_256M);
+	hpa_range.end = ALIGN(hpa_range.end, SZ_256M) - 1;
+
+	len = range_len(&ctx->hpa_range);
+	spa_len = range_len(&hpa_range);
+	if (!len || !spa_len || spa_len % len) {
+		dev_dbg(cxld->dev.parent,
+			"CXL address translation: HPA range not contiguous: %#llx-%#llx:%#llx-%#llx(%s)\n",
+			hpa_range.start, hpa_range.end, ctx->hpa_range.start,
+			ctx->hpa_range.end, dev_name(&cxld->dev));
+		return -ENXIO;
+	}
+
+	ways = spa_len / len;
+	gran = SZ_256;
+
+	/*
+	 * Determine interleave granularity
+	 *
+	 * Note: The position of the chunk from one interleaving block to the
+	 * next may vary and thus cannot be considered constant. Address offsets
+	 * larger than the interleaving block size cannot be used to calculate
+	 * the granularity.
+	 */
+	if (ways > 1) {
+		while (gran <= SZ_16M) {
+			addr = prm_cxl_dpa_spa(pci_dev, base + gran);
+			if (addr != base_spa + gran)
+				break;
+			gran <<= 1;
+		}
+	}
+
+	if (gran > SZ_16M) {
+		dev_dbg(cxld->dev.parent,
+			"CXL address translation: Cannot determine granularity: %#llx-%#llx:%#llx-%#llx(%s)\n",
+			hpa_range.start, hpa_range.end, ctx->hpa_range.start,
+			ctx->hpa_range.end, dev_name(&cxld->dev));
+		return -ENXIO;
+	}
+
+	/*
+	 * The current kernel implementation does not support endpoint
+	 * setup with Normalized Addressing. It only translates an
+	 * endpoint's DPA to the SPA range of the host bridge.
+	 * Therefore, the endpoint address range cannot be determined,
+	 * making a non-auto setup impossible. If a decoder requires
+	 * address translation, reprogramming should be disabled and
+	 * the decoder locked.
+	 *
+	 * The BIOS, however, provides all the necessary address
+	 * translation data, which the kernel can use to reconfigure
+	 * endpoint decoders with normalized addresses. Locking the
+	 * decoders in the BIOS would prevent a capable kernel (or
+	 * other operating systems) from shutting down auto-generated
+	 * regions and managing resources dynamically.
+	 *
+	 * Indicate that Normalized Addressing is enabled.
+	 */
+	cxld->flags |= CXL_DECODER_F_LOCK;
+	cxld->flags |= CXL_DECODER_F_NORMALIZED_ADDRESSING;
+
+	ctx->hpa_range = hpa_range;
+	ctx->interleave_ways = ways;
+	ctx->interleave_granularity = gran;
+
+	dev_dbg(&cxld->dev,
+		"address mapping found for %s (hpa -> spa): %#llx+%#llx -> %#llx+%#llx ways:%d granularity:%d\n",
+		dev_name(cxlmd->dev.parent), base, len, hpa_range.start,
+		spa_len, ways, gran);
+
+	return 0;
+}
+
+void cxl_setup_prm_address_translation(struct cxl_root *cxl_root)
+{
+	struct device *host = cxl_root->port.uport_dev;
+	u64 spa;
+	struct prm_cxl_dpa_spa_data data = { .spa = &spa };
+	int rc;
+
+	/*
+	 * Applies only to PCIe Host Bridges which are children of the CXL Root
+	 * Device (HID=“ACPI0017”). Check this and drop cxl_test instances.
+	 */
+	if (!acpi_match_device(host->driver->acpi_match_table, host))
+		return;
+
+	/* Check kernel (-EOPNOTSUPP) and firmware support (-ENODEV) */
+	rc = acpi_call_prm_handler(prm_cxl_dpa_spa_guid, &data);
+	if (rc == -EOPNOTSUPP || rc == -ENODEV)
+		return;
+
+	cxl_root->ops.translation_setup_root = cxl_prm_setup_root;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_setup_prm_address_translation, "CXL");

linux-7.2.3/drivers/cxl/core/core.h

@@ -0,0 +1,233 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2020 Intel Corporation. */
+
+#ifndef __CXL_CORE_H__
+#define __CXL_CORE_H__
+
+#include <cxl/mailbox.h>
+#include <linux/rwsem.h>
+
+extern const struct device_type cxl_nvdimm_bridge_type;
+extern const struct device_type cxl_nvdimm_type;
+extern const struct device_type cxl_pmu_type;
+
+extern struct attribute_group cxl_base_attribute_group;
+
+enum cxl_detach_mode {
+	DETACH_ONLY,
+	DETACH_INVALIDATE,
+};
+
+#ifdef CONFIG_CXL_REGION
+
+struct cxl_region_context {
+	struct cxl_endpoint_decoder *cxled;
+	struct range hpa_range;
+	int interleave_ways;
+	int interleave_granularity;
+};
+
+extern struct device_attribute dev_attr_create_pmem_region;
+extern struct device_attribute dev_attr_create_ram_region;
+extern struct device_attribute dev_attr_delete_region;
+extern struct device_attribute dev_attr_region;
+extern const struct device_type cxl_pmem_region_type;
+extern const struct device_type cxl_dax_region_type;
+extern const struct device_type cxl_region_type;
+
+int cxl_decoder_detach(struct cxl_region *cxlr,
+		       struct cxl_endpoint_decoder *cxled, int pos,
+		       enum cxl_detach_mode mode);
+
+#define CXL_REGION_ATTR(x) (&dev_attr_##x.attr)
+#define CXL_REGION_TYPE(x) (&cxl_region_type)
+#define SET_CXL_REGION_ATTR(x) (&dev_attr_##x.attr),
+#define CXL_PMEM_REGION_TYPE(x) (&cxl_pmem_region_type)
+#define CXL_DAX_REGION_TYPE(x) (&cxl_dax_region_type)
+int cxl_region_init(void);
+void cxl_region_exit(void);
+int cxl_get_poison_by_endpoint(struct cxl_port *port);
+struct cxl_region *cxl_dpa_to_region(const struct cxl_memdev *cxlmd, u64 dpa);
+u64 cxl_dpa_to_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd,
+		   u64 dpa);
+int devm_cxl_add_dax_region(struct cxl_region *cxlr);
+int devm_cxl_add_pmem_region(struct cxl_region *cxlr);
+void kill_regions(struct cxl_root_decoder *cxlrd);
+
+#else
+static inline u64 cxl_dpa_to_hpa(struct cxl_region *cxlr,
+				 const struct cxl_memdev *cxlmd, u64 dpa)
+{
+	return ULLONG_MAX;
+}
+static inline
+struct cxl_region *cxl_dpa_to_region(const struct cxl_memdev *cxlmd, u64 dpa)
+{
+	return NULL;
+}
+static inline int cxl_get_poison_by_endpoint(struct cxl_port *port)
+{
+	return 0;
+}
+static inline int cxl_decoder_detach(struct cxl_region *cxlr,
+				     struct cxl_endpoint_decoder *cxled,
+				     int pos, enum cxl_detach_mode mode)
+{
+	return 0;
+}
+static inline int cxl_region_init(void)
+{
+	return 0;
+}
+static inline void cxl_region_exit(void)
+{
+}
+static inline void kill_regions(struct cxl_root_decoder *cxlrd) { };
+#define CXL_REGION_ATTR(x) NULL
+#define CXL_REGION_TYPE(x) NULL
+#define SET_CXL_REGION_ATTR(x)
+#define CXL_PMEM_REGION_TYPE(x) NULL
+#define CXL_DAX_REGION_TYPE(x) NULL
+#endif
+
+struct cxl_send_command;
+struct cxl_mem_query_commands;
+int cxl_query_cmd(struct cxl_mailbox *cxl_mbox,
+		  struct cxl_mem_query_commands __user *q);
+int cxl_send_cmd(struct cxl_mailbox *cxl_mbox, struct cxl_send_command __user *s);
+void __iomem *devm_cxl_iomap_block(struct device *dev, resource_size_t addr,
+				   resource_size_t length);
+
+struct dentry *cxl_debugfs_create_dir(const char *dir);
+int cxl_dpa_set_part(struct cxl_endpoint_decoder *cxled,
+		     enum cxl_partition_mode mode);
+int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, u64 size);
+int cxl_dpa_free(struct cxl_endpoint_decoder *cxled);
+resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled);
+resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled);
+bool cxl_resource_contains_addr(const struct resource *res, const resource_size_t addr);
+
+enum cxl_rcrb {
+	CXL_RCRB_DOWNSTREAM,
+	CXL_RCRB_UPSTREAM,
+};
+struct cxl_rcrb_info;
+resource_size_t __rcrb_to_component(struct device *dev,
+				    struct cxl_rcrb_info *ri,
+				    enum cxl_rcrb which);
+u16 cxl_rcrb_to_aer(struct device *dev, resource_size_t rcrb);
+
+#define PCI_RCRB_CAP_LIST_ID_MASK	GENMASK(7, 0)
+#define PCI_RCRB_CAP_HDR_ID_MASK	GENMASK(7, 0)
+#define PCI_RCRB_CAP_HDR_NEXT_MASK	GENMASK(15, 8)
+#define PCI_CAP_EXP_SIZEOF		0x3c
+
+struct cxl_rwsem {
+	/*
+	 * All changes to HPA (interleave configuration) occur with this
+	 * lock held for write.
+	 */
+	struct rw_semaphore region;
+	/*
+	 * All changes to a device DPA space occur with this lock held
+	 * for write.
+	 */
+	struct rw_semaphore dpa;
+};
+
+extern struct cxl_rwsem cxl_rwsem;
+
+int cxl_memdev_init(void);
+void cxl_memdev_exit(void);
+void cxl_mbox_init(void);
+
+enum cxl_poison_trace_type {
+	CXL_POISON_TRACE_LIST,
+	CXL_POISON_TRACE_INJECT,
+	CXL_POISON_TRACE_CLEAR,
+};
+
+enum poison_cmd_enabled_bits;
+bool cxl_memdev_has_poison_cmd(struct cxl_memdev *cxlmd,
+			       enum poison_cmd_enabled_bits cmd);
+
+long cxl_pci_get_latency(struct pci_dev *pdev);
+int cxl_pci_get_bandwidth(struct pci_dev *pdev, struct access_coordinate *c);
+int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port,
+					struct access_coordinate *c);
+
+static inline struct device *port_to_host(struct cxl_port *port)
+{
+	struct cxl_port *parent = is_cxl_root(port) ? NULL :
+				  to_cxl_port(port->dev.parent);
+
+	/*
+	 * The host of CXL root port and the first level of ports is
+	 * the platform firmware device, the host of all other ports
+	 * is their parent port.
+	 */
+	if (!parent)
+		return port->uport_dev;
+	else if (is_cxl_root(parent))
+		return parent->uport_dev;
+	else
+		return &parent->dev;
+}
+
+static inline struct device *dport_to_host(struct cxl_dport *dport)
+{
+	struct cxl_port *port = dport->port;
+
+	if (is_cxl_root(port))
+		return port->uport_dev;
+	return &port->dev;
+}
+#ifdef CONFIG_CXL_RAS
+int cxl_ras_init(void);
+void cxl_ras_exit(void);
+bool cxl_handle_ras(struct device *dev, void __iomem *ras_base);
+void cxl_handle_cor_ras(struct device *dev, void __iomem *ras_base);
+void cxl_dport_map_rch_aer(struct cxl_dport *dport);
+void cxl_disable_rch_root_ints(struct cxl_dport *dport);
+void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds);
+void devm_cxl_dport_ras_setup(struct cxl_dport *dport);
+#else
+static inline int cxl_ras_init(void)
+{
+	return 0;
+}
+static inline void cxl_ras_exit(void) { }
+static inline bool cxl_handle_ras(struct device *dev, void __iomem *ras_base)
+{
+	return false;
+}
+static inline void cxl_handle_cor_ras(struct device *dev, void __iomem *ras_base) { }
+static inline void cxl_dport_map_rch_aer(struct cxl_dport *dport) { }
+static inline void cxl_disable_rch_root_ints(struct cxl_dport *dport) { }
+static inline void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds) { }
+static inline void devm_cxl_dport_ras_setup(struct cxl_dport *dport) { }
+#endif /* CONFIG_CXL_RAS */
+
+int cxl_gpf_port_setup(struct cxl_dport *dport);
+
+struct cxl_hdm;
+int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm,
+			struct cxl_endpoint_dvsec_info *info);
+int cxl_port_get_possible_dports(struct cxl_port *port);
+
+#ifdef CONFIG_CXL_FEATURES
+struct cxl_feat_entry *
+cxl_feature_info(struct cxl_features_state *cxlfs, const uuid_t *uuid);
+size_t cxl_get_feature(struct cxl_mailbox *cxl_mbox, const uuid_t *feat_uuid,
+		       enum cxl_get_feat_selection selection,
+		       void *feat_out, size_t feat_out_size, u16 offset,
+		       u16 *return_code);
+int cxl_set_feature(struct cxl_mailbox *cxl_mbox, const uuid_t *feat_uuid,
+		    u8 feat_version, const void *feat_data,
+		    size_t feat_data_size, u32 feat_flag, u16 offset,
+		    u16 *return_code);
+#endif
+
+resource_size_t cxl_rcd_component_reg_phys(struct device *dev,
+					   struct cxl_dport *dport);
+#endif /* __CXL_CORE_H__ */

linux-7.2.3/drivers/cxl/core/features.c

@@ -0,0 +1,706 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2024-2025 Intel Corporation. All rights reserved. */
+#include <linux/fwctl.h>
+#include <linux/device.h>
+#include <cxl/mailbox.h>
+#include <cxl/features.h>
+#include <uapi/fwctl/cxl.h>
+#include "cxl.h"
+#include "core.h"
+#include "cxlmem.h"
+
+/**
+ * DOC: cxl features
+ *
+ * CXL Features:
+ * A CXL device that includes a mailbox supports commands that allows
+ * listing, getting, and setting of optionally defined features such
+ * as memory sparing or post package sparing. Vendors may define custom
+ * features for the device.
+ */
+
+/* All the features below are exclusive to the kernel */
+static const uuid_t cxl_exclusive_feats[] = {
+	CXL_FEAT_PATROL_SCRUB_UUID,
+	CXL_FEAT_ECS_UUID,
+	CXL_FEAT_SPPR_UUID,
+	CXL_FEAT_HPPR_UUID,
+	CXL_FEAT_CACHELINE_SPARING_UUID,
+	CXL_FEAT_ROW_SPARING_UUID,
+	CXL_FEAT_BANK_SPARING_UUID,
+	CXL_FEAT_RANK_SPARING_UUID,
+};
+
+static bool is_cxl_feature_exclusive_by_uuid(const uuid_t *uuid)
+{
+	for (int i = 0; i < ARRAY_SIZE(cxl_exclusive_feats); i++) {
+		if (uuid_equal(uuid, &cxl_exclusive_feats[i]))
+			return true;
+	}
+
+	return false;
+}
+
+static bool is_cxl_feature_exclusive(struct cxl_feat_entry *entry)
+{
+	return is_cxl_feature_exclusive_by_uuid(&entry->uuid);
+}
+
+struct cxl_features_state *to_cxlfs(struct cxl_dev_state *cxlds)
+{
+	return cxlds->cxlfs;
+}
+EXPORT_SYMBOL_NS_GPL(to_cxlfs, "CXL");
+
+static int cxl_get_supported_features_count(struct cxl_mailbox *cxl_mbox)
+{
+	struct cxl_mbox_get_sup_feats_out mbox_out;
+	struct cxl_mbox_get_sup_feats_in mbox_in;
+	struct cxl_mbox_cmd mbox_cmd;
+	int rc;
+
+	memset(&mbox_in, 0, sizeof(mbox_in));
+	mbox_in.count = cpu_to_le32(sizeof(mbox_out));
+	memset(&mbox_out, 0, sizeof(mbox_out));
+	mbox_cmd = (struct cxl_mbox_cmd) {
+		.opcode = CXL_MBOX_OP_GET_SUPPORTED_FEATURES,
+		.size_in = sizeof(mbox_in),
+		.payload_in = &mbox_in,
+		.size_out = sizeof(mbox_out),
+		.payload_out = &mbox_out,
+		.min_out = sizeof(mbox_out),
+	};
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
+	if (rc < 0)
+		return rc;
+
+	return le16_to_cpu(mbox_out.supported_feats);
+}
+
+static struct cxl_feat_entries *
+get_supported_features(struct cxl_features_state *cxlfs)
+{
+	int remain_feats, max_size, max_feats, start, rc, hdr_size;
+	struct cxl_mailbox *cxl_mbox = &cxlfs->cxlds->cxl_mbox;
+	int feat_size = sizeof(struct cxl_feat_entry);
+	struct cxl_mbox_get_sup_feats_in mbox_in;
+	struct cxl_feat_entry *entry;
+	struct cxl_mbox_cmd mbox_cmd;
+	int user_feats = 0;
+	int count;
+
+	count = cxl_get_supported_features_count(cxl_mbox);
+	if (count <= 0)
+		return NULL;
+
+	struct cxl_feat_entries *entries __free(kvfree) =
+		kvmalloc_flex(*entries, ent, count);
+	if (!entries)
+		return NULL;
+
+	struct cxl_mbox_get_sup_feats_out *mbox_out __free(kvfree) =
+		kvmalloc(cxl_mbox->payload_size, GFP_KERNEL);
+	if (!mbox_out)
+		return NULL;
+
+	hdr_size = struct_size(mbox_out, ents, 0);
+	max_size = cxl_mbox->payload_size - hdr_size;
+	/* max feat entries that can fit in mailbox max payload size */
+	max_feats = max_size / feat_size;
+	entry = entries->ent;
+
+	start = 0;
+	remain_feats = count;
+	do {
+		int retrieved, alloc_size, copy_feats;
+		int num_entries;
+
+		if (remain_feats > max_feats) {
+			alloc_size = struct_size(mbox_out, ents, max_feats);
+			remain_feats = remain_feats - max_feats;
+			copy_feats = max_feats;
+		} else {
+			alloc_size = struct_size(mbox_out, ents, remain_feats);
+			copy_feats = remain_feats;
+			remain_feats = 0;
+		}
+
+		memset(&mbox_in, 0, sizeof(mbox_in));
+		mbox_in.count = cpu_to_le32(alloc_size);
+		mbox_in.start_idx = cpu_to_le16(start);
+		memset(mbox_out, 0, alloc_size);
+		mbox_cmd = (struct cxl_mbox_cmd) {
+			.opcode = CXL_MBOX_OP_GET_SUPPORTED_FEATURES,
+			.size_in = sizeof(mbox_in),
+			.payload_in = &mbox_in,
+			.size_out = alloc_size,
+			.payload_out = mbox_out,
+			.min_out = hdr_size,
+		};
+		rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
+		if (rc < 0)
+			return NULL;
+
+		if (mbox_cmd.size_out <= hdr_size)
+			return NULL;
+
+		/*
+		 * Make sure retrieved out buffer is multiple of feature
+		 * entries.
+		 */
+		retrieved = mbox_cmd.size_out - hdr_size;
+		if (retrieved % feat_size)
+			return NULL;
+
+		num_entries = le16_to_cpu(mbox_out->num_entries);
+		/*
+		 * If the reported output entries * defined entry size !=
+		 * retrieved output bytes, then the output package is incorrect.
+		 */
+		if (num_entries * feat_size != retrieved)
+			return NULL;
+
+		memcpy(entry, mbox_out->ents, retrieved);
+		for (int i = 0; i < num_entries; i++) {
+			if (!is_cxl_feature_exclusive(entry + i))
+				user_feats++;
+		}
+		entry += num_entries;
+		/*
+		 * If the number of output entries is less than expected, add the
+		 * remaining entries to the next batch.
+		 */
+		remain_feats += copy_feats - num_entries;
+		start += num_entries;
+	} while (remain_feats);
+
+	entries->num_features = count;
+	entries->num_user_features = user_feats;
+
+	return no_free_ptr(entries);
+}
+
+static void free_cxlfs(void *_cxlfs)
+{
+	struct cxl_features_state *cxlfs = _cxlfs;
+	struct cxl_dev_state *cxlds = cxlfs->cxlds;
+
+	cxlds->cxlfs = NULL;
+	kvfree(cxlfs->entries);
+	kfree(cxlfs);
+}
+
+/**
+ * devm_cxl_setup_features() - Allocate and initialize features context
+ * @cxlds: CXL device context
+ *
+ * Return 0 on success or -errno on failure.
+ */
+int devm_cxl_setup_features(struct cxl_dev_state *cxlds)
+{
+	struct cxl_mailbox *cxl_mbox = &cxlds->cxl_mbox;
+
+	if (cxl_mbox->feat_cap < CXL_FEATURES_RO)
+		return -ENODEV;
+
+	struct cxl_features_state *cxlfs __free(kfree) =
+		kzalloc_obj(*cxlfs);
+	if (!cxlfs)
+		return -ENOMEM;
+
+	cxlfs->cxlds = cxlds;
+
+	cxlfs->entries = get_supported_features(cxlfs);
+	if (!cxlfs->entries)
+		return -ENOMEM;
+
+	cxlds->cxlfs = cxlfs;
+
+	return devm_add_action_or_reset(cxlds->dev, free_cxlfs, no_free_ptr(cxlfs));
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_setup_features, "CXL");
+
+size_t cxl_get_feature(struct cxl_mailbox *cxl_mbox, const uuid_t *feat_uuid,
+		       enum cxl_get_feat_selection selection,
+		       void *feat_out, size_t feat_out_size, u16 offset,
+		       u16 *return_code)
+{
+	size_t data_to_rd_size, size_out;
+	struct cxl_mbox_get_feat_in pi;
+	struct cxl_mbox_cmd mbox_cmd;
+	size_t data_rcvd_size = 0;
+	int rc;
+
+	if (return_code)
+		*return_code = CXL_MBOX_CMD_RC_INPUT;
+
+	if (!feat_out || !feat_out_size)
+		return 0;
+
+	size_out = min(feat_out_size, cxl_mbox->payload_size);
+	uuid_copy(&pi.uuid, feat_uuid);
+	pi.selection = selection;
+	do {
+		data_to_rd_size = min(feat_out_size - data_rcvd_size,
+				      cxl_mbox->payload_size);
+		pi.offset = cpu_to_le16(offset + data_rcvd_size);
+		pi.count = cpu_to_le16(data_to_rd_size);
+
+		mbox_cmd = (struct cxl_mbox_cmd) {
+			.opcode = CXL_MBOX_OP_GET_FEATURE,
+			.size_in = sizeof(pi),
+			.payload_in = &pi,
+			.size_out = size_out,
+			.payload_out = feat_out + data_rcvd_size,
+			.min_out = data_to_rd_size,
+		};
+		rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
+		if (rc < 0 || !mbox_cmd.size_out) {
+			if (return_code)
+				*return_code = mbox_cmd.return_code;
+			return 0;
+		}
+		data_rcvd_size += mbox_cmd.size_out;
+	} while (data_rcvd_size < feat_out_size);
+
+	if (return_code)
+		*return_code = CXL_MBOX_CMD_RC_SUCCESS;
+
+	return data_rcvd_size;
+}
+
+/*
+ * FEAT_DATA_MIN_PAYLOAD_SIZE - min extra number of bytes should be
+ * available in the mailbox for storing the actual feature data so that
+ * the feature data transfer would work as expected.
+ */
+#define FEAT_DATA_MIN_PAYLOAD_SIZE 10
+int cxl_set_feature(struct cxl_mailbox *cxl_mbox,
+		    const uuid_t *feat_uuid, u8 feat_version,
+		    const void *feat_data, size_t feat_data_size,
+		    u32 feat_flag, u16 offset, u16 *return_code)
+{
+	size_t data_in_size, data_sent_size = 0;
+	struct cxl_mbox_cmd mbox_cmd;
+	size_t hdr_size;
+
+	if (return_code)
+		*return_code = CXL_MBOX_CMD_RC_INPUT;
+
+	struct cxl_mbox_set_feat_in *pi __free(kfree) =
+			kzalloc(cxl_mbox->payload_size, GFP_KERNEL);
+	if (!pi)
+		return -ENOMEM;
+
+	uuid_copy(&pi->uuid, feat_uuid);
+	pi->version = feat_version;
+	feat_flag &= ~CXL_SET_FEAT_FLAG_DATA_TRANSFER_MASK;
+	feat_flag |= CXL_SET_FEAT_FLAG_DATA_SAVED_ACROSS_RESET;
+	hdr_size = sizeof(pi->hdr);
+	/*
+	 * Check minimum mbox payload size is available for
+	 * the feature data transfer.
+	 */
+	if (hdr_size + FEAT_DATA_MIN_PAYLOAD_SIZE > cxl_mbox->payload_size)
+		return -ENOMEM;
+
+	if (hdr_size + feat_data_size <= cxl_mbox->payload_size) {
+		pi->flags = cpu_to_le32(feat_flag |
+					CXL_SET_FEAT_FLAG_FULL_DATA_TRANSFER);
+		data_in_size = feat_data_size;
+	} else {
+		pi->flags = cpu_to_le32(feat_flag |
+					CXL_SET_FEAT_FLAG_INITIATE_DATA_TRANSFER);
+		data_in_size = cxl_mbox->payload_size - hdr_size;
+	}
+
+	do {
+		int rc;
+
+		pi->offset = cpu_to_le16(offset + data_sent_size);
+		memcpy(pi->feat_data, feat_data + data_sent_size, data_in_size);
+		mbox_cmd = (struct cxl_mbox_cmd) {
+			.opcode = CXL_MBOX_OP_SET_FEATURE,
+			.size_in = hdr_size + data_in_size,
+			.payload_in = pi,
+		};
+		rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
+		if (rc < 0) {
+			if (return_code)
+				*return_code = mbox_cmd.return_code;
+			return rc;
+		}
+
+		data_sent_size += data_in_size;
+		if (data_sent_size >= feat_data_size) {
+			if (return_code)
+				*return_code = CXL_MBOX_CMD_RC_SUCCESS;
+			return 0;
+		}
+
+		if ((feat_data_size - data_sent_size) <= (cxl_mbox->payload_size - hdr_size)) {
+			data_in_size = feat_data_size - data_sent_size;
+			pi->flags = cpu_to_le32(feat_flag |
+						CXL_SET_FEAT_FLAG_FINISH_DATA_TRANSFER);
+		} else {
+			pi->flags = cpu_to_le32(feat_flag |
+						CXL_SET_FEAT_FLAG_CONTINUE_DATA_TRANSFER);
+		}
+	} while (true);
+}
+
+/* FWCTL support */
+
+static inline struct cxl_memdev *fwctl_to_memdev(struct fwctl_device *fwctl_dev)
+{
+	return to_cxl_memdev(fwctl_dev->dev.parent);
+}
+
+static int cxlctl_open_uctx(struct fwctl_uctx *uctx)
+{
+	return 0;
+}
+
+static void cxlctl_close_uctx(struct fwctl_uctx *uctx)
+{
+}
+
+struct cxl_feat_entry *
+cxl_feature_info(struct cxl_features_state *cxlfs,
+		 const uuid_t *uuid)
+{
+	struct cxl_feat_entry *feat;
+
+	if (!cxlfs || !cxlfs->entries)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	for (int i = 0; i < cxlfs->entries->num_features; i++) {
+		feat = &cxlfs->entries->ent[i];
+		if (uuid_equal(uuid, &feat->uuid))
+			return feat;
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static void *cxlctl_get_supported_features(struct cxl_features_state *cxlfs,
+					   const struct fwctl_rpc_cxl *rpc_in,
+					   size_t *out_len)
+{
+	const struct cxl_mbox_get_sup_feats_in *feat_in;
+	struct cxl_mbox_get_sup_feats_out *feat_out;
+	struct cxl_feat_entry *pos;
+	size_t out_size;
+	int requested;
+	u32 count;
+	u16 start;
+	int i;
+
+	if (rpc_in->op_size != sizeof(*feat_in))
+		return ERR_PTR(-EINVAL);
+
+	feat_in = &rpc_in->get_sup_feats_in;
+	count = le32_to_cpu(feat_in->count);
+	start = le16_to_cpu(feat_in->start_idx);
+	requested = count / sizeof(*pos);
+
+	/*
+	 * Make sure that the total requested number of entries is not greater
+	 * than the total number of supported features allowed for userspace.
+	 */
+	if (start >= cxlfs->entries->num_features)
+		return ERR_PTR(-EINVAL);
+
+	requested = min_t(int, requested, cxlfs->entries->num_features - start);
+
+	out_size = sizeof(struct fwctl_rpc_cxl_out) +
+		struct_size(feat_out, ents, requested);
+
+	struct fwctl_rpc_cxl_out *rpc_out __free(kvfree) =
+		kvzalloc(out_size, GFP_KERNEL);
+	if (!rpc_out)
+		return ERR_PTR(-ENOMEM);
+
+	rpc_out->size = struct_size(feat_out, ents, requested);
+	feat_out = &rpc_out->get_sup_feats_out;
+	feat_out->num_entries = cpu_to_le16(requested);
+
+	for (i = start, pos = &feat_out->ents[0];
+	     i < cxlfs->entries->num_features; i++, pos++) {
+		if (i - start == requested)
+			break;
+
+		memcpy(pos, &cxlfs->entries->ent[i], sizeof(*pos));
+		/*
+		 * If the feature is exclusive, set the set_feat_size to 0 to
+		 * indicate that the feature is not changeable.
+		 */
+		if (is_cxl_feature_exclusive(pos)) {
+			u32 flags;
+
+			pos->set_feat_size = 0;
+			flags = le32_to_cpu(pos->flags);
+			flags &= ~CXL_FEATURE_F_CHANGEABLE;
+			pos->flags = cpu_to_le32(flags);
+		}
+	}
+
+	feat_out->supported_feats = cpu_to_le16(cxlfs->entries->num_features);
+	rpc_out->retval = CXL_MBOX_CMD_RC_SUCCESS;
+	*out_len = out_size;
+
+	return no_free_ptr(rpc_out);
+}
+
+static void *cxlctl_get_feature(struct cxl_features_state *cxlfs,
+				const struct fwctl_rpc_cxl *rpc_in,
+				size_t *out_len)
+{
+	struct cxl_mailbox *cxl_mbox = &cxlfs->cxlds->cxl_mbox;
+	const struct cxl_mbox_get_feat_in *feat_in;
+	u16 offset, count, return_code;
+	size_t out_size = *out_len;
+
+	if (rpc_in->op_size != sizeof(*feat_in))
+		return ERR_PTR(-EINVAL);
+
+	feat_in = &rpc_in->get_feat_in;
+	offset = le16_to_cpu(feat_in->offset);
+	count = le16_to_cpu(feat_in->count);
+
+	if (!count)
+		return ERR_PTR(-EINVAL);
+
+	struct fwctl_rpc_cxl_out *rpc_out __free(kvfree) =
+		kvzalloc(out_size, GFP_KERNEL);
+	if (!rpc_out)
+		return ERR_PTR(-ENOMEM);
+
+	out_size = cxl_get_feature(cxl_mbox, &feat_in->uuid,
+				   feat_in->selection, rpc_out->payload,
+				   count, offset, &return_code);
+	*out_len = sizeof(struct fwctl_rpc_cxl_out);
+	if (!out_size) {
+		rpc_out->size = 0;
+		rpc_out->retval = return_code;
+		return no_free_ptr(rpc_out);
+	}
+
+	rpc_out->size = out_size;
+	rpc_out->retval = CXL_MBOX_CMD_RC_SUCCESS;
+	*out_len += out_size;
+
+	return no_free_ptr(rpc_out);
+}
+
+static void *cxlctl_set_feature(struct cxl_features_state *cxlfs,
+				const struct fwctl_rpc_cxl *rpc_in,
+				size_t *out_len)
+{
+	struct cxl_mailbox *cxl_mbox = &cxlfs->cxlds->cxl_mbox;
+	const struct cxl_mbox_set_feat_in *feat_in;
+	size_t out_size, data_size;
+	u16 offset, return_code;
+	u32 flags;
+	int rc;
+
+	if (rpc_in->op_size <= sizeof(feat_in->hdr))
+		return ERR_PTR(-EINVAL);
+
+	feat_in = &rpc_in->set_feat_in;
+
+	if (is_cxl_feature_exclusive_by_uuid(&feat_in->uuid))
+		return ERR_PTR(-EPERM);
+
+	offset = le16_to_cpu(feat_in->offset);
+	flags = le32_to_cpu(feat_in->flags);
+	out_size = *out_len;
+
+	struct fwctl_rpc_cxl_out *rpc_out __free(kvfree) =
+		kvzalloc(out_size, GFP_KERNEL);
+	if (!rpc_out)
+		return ERR_PTR(-ENOMEM);
+
+	rpc_out->size = 0;
+
+	data_size = rpc_in->op_size - sizeof(feat_in->hdr);
+	rc = cxl_set_feature(cxl_mbox, &feat_in->uuid,
+			     feat_in->version, feat_in->feat_data,
+			     data_size, flags, offset, &return_code);
+	*out_len = sizeof(*rpc_out);
+	if (rc) {
+		rpc_out->retval = return_code;
+		return no_free_ptr(rpc_out);
+	}
+
+	rpc_out->retval = CXL_MBOX_CMD_RC_SUCCESS;
+
+	return no_free_ptr(rpc_out);
+}
+
+static bool cxlctl_validate_set_features(struct cxl_features_state *cxlfs,
+					 const struct fwctl_rpc_cxl *rpc_in,
+					 enum fwctl_rpc_scope scope)
+{
+	u16 effects, imm_mask, reset_mask;
+	struct cxl_feat_entry *feat;
+	u32 flags;
+
+	if (rpc_in->op_size < sizeof(uuid_t))
+		return false;
+
+	feat = cxl_feature_info(cxlfs, &rpc_in->set_feat_in.uuid);
+	if (IS_ERR(feat))
+		return false;
+
+	/* Ensure that the attribute is changeable */
+	flags = le32_to_cpu(feat->flags);
+	if (!(flags & CXL_FEATURE_F_CHANGEABLE))
+		return false;
+
+	effects = le16_to_cpu(feat->effects);
+
+	/*
+	 * Reserved bits are set, rejecting since the effects is not
+	 * comprehended by the driver.
+	 */
+	if (effects & CXL_CMD_EFFECTS_RESERVED) {
+		dev_warn_once(cxlfs->cxlds->dev,
+			      "Reserved bits set in the Feature effects field!\n");
+		return false;
+	}
+
+	/* Currently no user background command support */
+	if (effects & CXL_CMD_BACKGROUND)
+		return false;
+
+	/* Effects cause immediate change, highest security scope is needed */
+	imm_mask = CXL_CMD_CONFIG_CHANGE_IMMEDIATE |
+		   CXL_CMD_DATA_CHANGE_IMMEDIATE |
+		   CXL_CMD_POLICY_CHANGE_IMMEDIATE |
+		   CXL_CMD_LOG_CHANGE_IMMEDIATE;
+
+	reset_mask = CXL_CMD_CONFIG_CHANGE_COLD_RESET |
+		     CXL_CMD_CONFIG_CHANGE_CONV_RESET |
+		     CXL_CMD_CONFIG_CHANGE_CXL_RESET;
+
+	/* If no immediate or reset effect set, The hardware has a bug */
+	if (!(effects & imm_mask) && !(effects & reset_mask))
+		return false;
+
+	/*
+	 * If the Feature setting causes immediate configuration change
+	 * then we need the full write permission policy.
+	 */
+	if (effects & imm_mask && scope >= FWCTL_RPC_DEBUG_WRITE_FULL)
+		return true;
+
+	/*
+	 * If the Feature setting only causes configuration change
+	 * after a reset, then the lesser level of write permission
+	 * policy is ok.
+	 */
+	if (!(effects & imm_mask) && scope >= FWCTL_RPC_DEBUG_WRITE)
+		return true;
+
+	return false;
+}
+
+static bool cxlctl_validate_hw_command(struct cxl_features_state *cxlfs,
+				       const struct fwctl_rpc_cxl *rpc_in,
+				       enum fwctl_rpc_scope scope,
+				       u16 opcode)
+{
+	struct cxl_mailbox *cxl_mbox = &cxlfs->cxlds->cxl_mbox;
+
+	switch (opcode) {
+	case CXL_MBOX_OP_GET_SUPPORTED_FEATURES:
+	case CXL_MBOX_OP_GET_FEATURE:
+		return cxl_mbox->feat_cap >= CXL_FEATURES_RO;
+	case CXL_MBOX_OP_SET_FEATURE:
+		if (cxl_mbox->feat_cap < CXL_FEATURES_RW)
+			return false;
+		return cxlctl_validate_set_features(cxlfs, rpc_in, scope);
+	default:
+		return false;
+	}
+}
+
+static void *cxlctl_handle_commands(struct cxl_features_state *cxlfs,
+				    const struct fwctl_rpc_cxl *rpc_in,
+				    size_t *out_len, u16 opcode)
+{
+	switch (opcode) {
+	case CXL_MBOX_OP_GET_SUPPORTED_FEATURES:
+		return cxlctl_get_supported_features(cxlfs, rpc_in, out_len);
+	case CXL_MBOX_OP_GET_FEATURE:
+		return cxlctl_get_feature(cxlfs, rpc_in, out_len);
+	case CXL_MBOX_OP_SET_FEATURE:
+		return cxlctl_set_feature(cxlfs, rpc_in, out_len);
+	default:
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+}
+
+static void *cxlctl_fw_rpc(struct fwctl_uctx *uctx, enum fwctl_rpc_scope scope,
+			   void *in, size_t in_len, size_t *out_len)
+{
+	struct fwctl_device *fwctl_dev = uctx->fwctl;
+	struct cxl_memdev *cxlmd = fwctl_to_memdev(fwctl_dev);
+	struct cxl_features_state *cxlfs = to_cxlfs(cxlmd->cxlds);
+	const struct fwctl_rpc_cxl *rpc_in = in;
+	u16 opcode = rpc_in->opcode;
+
+	if (!cxlctl_validate_hw_command(cxlfs, rpc_in, scope, opcode))
+		return ERR_PTR(-EINVAL);
+
+	return cxlctl_handle_commands(cxlfs, rpc_in, out_len, opcode);
+}
+
+static const struct fwctl_ops cxlctl_ops = {
+	.device_type = FWCTL_DEVICE_TYPE_CXL,
+	.uctx_size = sizeof(struct fwctl_uctx),
+	.open_uctx = cxlctl_open_uctx,
+	.close_uctx = cxlctl_close_uctx,
+	.fw_rpc = cxlctl_fw_rpc,
+};
+
+DEFINE_FREE(free_fwctl_dev, struct fwctl_device *, if (_T) fwctl_put(_T))
+
+static void free_memdev_fwctl(void *_fwctl_dev)
+{
+	struct fwctl_device *fwctl_dev = _fwctl_dev;
+
+	fwctl_unregister(fwctl_dev);
+	fwctl_put(fwctl_dev);
+}
+
+int devm_cxl_setup_fwctl(struct device *host, struct cxl_memdev *cxlmd)
+{
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_features_state *cxlfs;
+	int rc;
+
+	cxlfs = to_cxlfs(cxlds);
+	if (!cxlfs)
+		return -ENODEV;
+
+	/* No need to setup FWCTL if there are no user allowed features found */
+	if (!cxlfs->entries->num_user_features)
+		return -ENODEV;
+
+	struct fwctl_device *fwctl_dev __free(free_fwctl_dev) =
+		_fwctl_alloc_device(&cxlmd->dev, &cxlctl_ops, sizeof(*fwctl_dev));
+	if (!fwctl_dev)
+		return -ENOMEM;
+
+	rc = fwctl_register(fwctl_dev);
+	if (rc)
+		return rc;
+
+	return devm_add_action_or_reset(host, free_memdev_fwctl,
+					no_free_ptr(fwctl_dev));
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_setup_fwctl, "CXL");
+
+MODULE_IMPORT_NS("FWCTL");

linux-7.2.3/drivers/cxl/core/mce.c

@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2024 Intel Corporation. All rights reserved. */
+#include <linux/mm.h>
+#include <linux/notifier.h>
+#include <linux/set_memory.h>
+#include <asm/mce.h>
+#include <cxlmem.h>
+#include "mce.h"
+
+static int cxl_handle_mce(struct notifier_block *nb, unsigned long val,
+			  void *data)
+{
+	struct cxl_memdev_state *mds = container_of(nb, struct cxl_memdev_state,
+						    mce_notifier);
+	struct cxl_memdev *cxlmd = mds->cxlds.cxlmd;
+	struct cxl_port *endpoint = cxlmd->endpoint;
+	struct mce *mce = data;
+	u64 spa, spa_alias;
+	unsigned long pfn;
+
+	if (!mce || !mce_usable_address(mce))
+		return NOTIFY_DONE;
+
+	if (!endpoint)
+		return NOTIFY_DONE;
+
+	spa = mce->addr & MCI_ADDR_PHYSADDR;
+
+	pfn = spa >> PAGE_SHIFT;
+	if (!pfn_valid(pfn))
+		return NOTIFY_DONE;
+
+	spa_alias = cxl_port_get_spa_cache_alias(endpoint, spa);
+	if (spa_alias == ~0ULL)
+		return NOTIFY_DONE;
+
+	pfn = spa_alias >> PAGE_SHIFT;
+
+	/*
+	 * Take down the aliased memory page. The original memory page flagged
+	 * by the MCE will be taken cared of by the standard MCE handler.
+	 */
+	dev_emerg(mds->cxlds.dev, "Offlining aliased SPA address0: %#llx\n",
+		  spa_alias);
+	if (!memory_failure(pfn, 0))
+		set_mce_nospec(pfn);
+
+	return NOTIFY_OK;
+}
+
+static void cxl_unregister_mce_notifier(void *mce_notifier)
+{
+	mce_unregister_decode_chain(mce_notifier);
+}
+
+int devm_cxl_register_mce_notifier(struct device *dev,
+				   struct notifier_block *mce_notifier)
+{
+	mce_notifier->notifier_call = cxl_handle_mce;
+	mce_notifier->priority = MCE_PRIO_UC;
+	mce_register_decode_chain(mce_notifier);
+
+	return devm_add_action_or_reset(dev, cxl_unregister_mce_notifier,
+					mce_notifier);
+}

linux-7.2.3/drivers/cxl/core/mce.h

@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2024 Intel Corporation. All rights reserved. */
+#ifndef _CXL_CORE_MCE_H_
+#define _CXL_CORE_MCE_H_
+
+#include <linux/notifier.h>
+
+#ifdef CONFIG_CXL_MCE
+int devm_cxl_register_mce_notifier(struct device *dev,
+				   struct notifier_block *mce_notifier);
+#else
+static inline int
+devm_cxl_register_mce_notifier(struct device *dev,
+			       struct notifier_block *mce_notifier)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+#endif

linux-7.2.3/drivers/cxl/core/pci.c

@@ -0,0 +1,928 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2021 Intel Corporation. All rights reserved. */
+#include <linux/units.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/device.h>
+#include <linux/delay.h>
+#include <linux/pci.h>
+#include <linux/pci-doe.h>
+#include <linux/aer.h>
+#include <cxlpci.h>
+#include <cxlmem.h>
+#include <cxl.h>
+#include "core.h"
+#include "trace.h"
+
+/**
+ * DOC: cxl core pci
+ *
+ * Compute Express Link protocols are layered on top of PCIe. CXL core provides
+ * a set of helpers for CXL interactions which occur via PCIe.
+ */
+
+static unsigned short media_ready_timeout = 60;
+module_param(media_ready_timeout, ushort, 0644);
+MODULE_PARM_DESC(media_ready_timeout, "seconds to wait for media ready");
+
+static int pci_get_port_num(struct pci_dev *pdev)
+{
+	u32 lnkcap;
+	int type;
+
+	type = pci_pcie_type(pdev);
+	if (type != PCI_EXP_TYPE_DOWNSTREAM && type != PCI_EXP_TYPE_ROOT_PORT)
+		return -EINVAL;
+
+	if (pci_read_config_dword(pdev, pci_pcie_cap(pdev) + PCI_EXP_LNKCAP,
+				  &lnkcap))
+		return -ENXIO;
+
+	return FIELD_GET(PCI_EXP_LNKCAP_PN, lnkcap);
+}
+
+/**
+ * devm_cxl_add_dport_by_dev - allocate a dport by dport device
+ * @port: cxl_port that hosts the dport
+ * @dport_dev: 'struct device' of the dport
+ *
+ * Returns the allocated dport on success or ERR_PTR() of -errno on error
+ */
+struct cxl_dport *devm_cxl_add_dport_by_dev(struct cxl_port *port,
+					    struct device *dport_dev)
+{
+	struct cxl_register_map map;
+	struct pci_dev *pdev;
+	int port_num, rc;
+
+	if (!dev_is_pci(dport_dev))
+		return ERR_PTR(-EINVAL);
+
+	pdev = to_pci_dev(dport_dev);
+	port_num = pci_get_port_num(pdev);
+	if (port_num < 0)
+		return ERR_PTR(port_num);
+
+	rc = cxl_find_regblock(pdev, CXL_REGLOC_RBI_COMPONENT, &map);
+	if (rc)
+		return ERR_PTR(rc);
+
+	device_lock_assert(&port->dev);
+	return devm_cxl_add_dport(port, dport_dev, port_num, map.resource);
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_add_dport_by_dev, "CXL");
+
+static int cxl_dvsec_mem_range_valid(struct cxl_dev_state *cxlds, int id)
+{
+	struct pci_dev *pdev = to_pci_dev(cxlds->dev);
+	int d = cxlds->cxl_dvsec;
+	bool valid = false;
+	int rc, i;
+	u32 temp;
+
+	if (id > CXL_DVSEC_RANGE_MAX)
+		return -EINVAL;
+
+	/* Check MEM INFO VALID bit first, give up after 1s */
+	i = 1;
+	do {
+		rc = pci_read_config_dword(pdev,
+					   d + PCI_DVSEC_CXL_RANGE_SIZE_LOW(id),
+					   &temp);
+		if (rc)
+			return pcibios_err_to_errno(rc);
+
+		valid = FIELD_GET(PCI_DVSEC_CXL_MEM_INFO_VALID, temp);
+		if (valid)
+			break;
+		msleep(1000);
+	} while (i--);
+
+	if (!valid) {
+		dev_err(&pdev->dev,
+			"Timeout awaiting memory range %d valid after 1s.\n",
+			id);
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static int cxl_dvsec_mem_range_active(struct cxl_dev_state *cxlds, int id)
+{
+	struct pci_dev *pdev = to_pci_dev(cxlds->dev);
+	int d = cxlds->cxl_dvsec;
+	bool active = false;
+	int rc, i;
+	u32 temp;
+
+	if (id > CXL_DVSEC_RANGE_MAX)
+		return -EINVAL;
+
+	/* Check MEM ACTIVE bit, up to 60s timeout by default */
+	for (i = media_ready_timeout; i; i--) {
+		rc = pci_read_config_dword(
+			pdev, d + PCI_DVSEC_CXL_RANGE_SIZE_LOW(id), &temp);
+		if (rc)
+			return pcibios_err_to_errno(rc);
+
+		active = FIELD_GET(PCI_DVSEC_CXL_MEM_ACTIVE, temp);
+		if (active)
+			break;
+		msleep(1000);
+	}
+
+	if (!active) {
+		dev_err(&pdev->dev,
+			"timeout awaiting memory active after %d seconds\n",
+			media_ready_timeout);
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+/*
+ * Wait up to @media_ready_timeout for the device to report memory
+ * active.
+ */
+int cxl_await_media_ready(struct cxl_dev_state *cxlds)
+{
+	struct pci_dev *pdev = to_pci_dev(cxlds->dev);
+	int d = cxlds->cxl_dvsec;
+	int rc, i, hdm_count;
+	u64 md_status;
+	u16 cap;
+
+	rc = pci_read_config_word(pdev,
+				  d + PCI_DVSEC_CXL_CAP, &cap);
+	if (rc)
+		return pcibios_err_to_errno(rc);
+
+	hdm_count = FIELD_GET(PCI_DVSEC_CXL_HDM_COUNT, cap);
+	for (i = 0; i < hdm_count; i++) {
+		rc = cxl_dvsec_mem_range_valid(cxlds, i);
+		if (rc)
+			return rc;
+	}
+
+	for (i = 0; i < hdm_count; i++) {
+		rc = cxl_dvsec_mem_range_active(cxlds, i);
+		if (rc)
+			return rc;
+	}
+
+	md_status = readq(cxlds->regs.memdev + CXLMDEV_STATUS_OFFSET);
+	if (!CXLMDEV_READY(md_status))
+		return -EIO;
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_await_media_ready, "CXL");
+
+static int cxl_set_mem_enable(struct cxl_dev_state *cxlds, u16 val)
+{
+	struct pci_dev *pdev = to_pci_dev(cxlds->dev);
+	int d = cxlds->cxl_dvsec;
+	u16 ctrl;
+	int rc;
+
+	rc = pci_read_config_word(pdev, d + PCI_DVSEC_CXL_CTRL, &ctrl);
+	if (rc)
+		return pcibios_err_to_errno(rc);
+
+	if ((ctrl & PCI_DVSEC_CXL_MEM_ENABLE) == val)
+		return 1;
+	ctrl &= ~PCI_DVSEC_CXL_MEM_ENABLE;
+	ctrl |= val;
+
+	rc = pci_write_config_word(pdev, d + PCI_DVSEC_CXL_CTRL, ctrl);
+	if (rc)
+		return pcibios_err_to_errno(rc);
+
+	return 0;
+}
+
+static void clear_mem_enable(void *cxlds)
+{
+	cxl_set_mem_enable(cxlds, 0);
+}
+
+static int devm_cxl_enable_mem(struct device *host, struct cxl_dev_state *cxlds)
+{
+	int rc;
+
+	rc = cxl_set_mem_enable(cxlds, PCI_DVSEC_CXL_MEM_ENABLE);
+	if (rc < 0)
+		return rc;
+	if (rc > 0)
+		return 0;
+	return devm_add_action_or_reset(host, clear_mem_enable, cxlds);
+}
+
+/* require dvsec ranges to be covered by a locked platform window */
+static int dvsec_range_allowed(struct device *dev, const void *arg)
+{
+	const struct range *dev_range = arg;
+	struct cxl_decoder *cxld;
+
+	if (!is_root_decoder(dev))
+		return 0;
+
+	cxld = to_cxl_decoder(dev);
+
+	if (!(cxld->flags & CXL_DECODER_F_RAM))
+		return 0;
+
+	return range_contains(&cxld->hpa_range, dev_range);
+}
+
+static void disable_hdm(void *_cxlhdm)
+{
+	u32 global_ctrl;
+	struct cxl_hdm *cxlhdm = _cxlhdm;
+	void __iomem *hdm = cxlhdm->regs.hdm_decoder;
+
+	global_ctrl = readl(hdm + CXL_HDM_DECODER_CTRL_OFFSET);
+	writel(global_ctrl & ~CXL_HDM_DECODER_ENABLE,
+	       hdm + CXL_HDM_DECODER_CTRL_OFFSET);
+}
+
+static int devm_cxl_enable_hdm(struct device *host, struct cxl_hdm *cxlhdm)
+{
+	void __iomem *hdm = cxlhdm->regs.hdm_decoder;
+	u32 global_ctrl;
+
+	global_ctrl = readl(hdm + CXL_HDM_DECODER_CTRL_OFFSET);
+	writel(global_ctrl | CXL_HDM_DECODER_ENABLE,
+	       hdm + CXL_HDM_DECODER_CTRL_OFFSET);
+
+	return devm_add_action_or_reset(host, disable_hdm, cxlhdm);
+}
+
+int cxl_dvsec_rr_decode(struct cxl_dev_state *cxlds,
+			struct cxl_endpoint_dvsec_info *info)
+{
+	struct pci_dev *pdev = to_pci_dev(cxlds->dev);
+	struct device *dev = cxlds->dev;
+	int hdm_count, rc, i, ranges = 0;
+	int d = cxlds->cxl_dvsec;
+	u16 cap, ctrl;
+
+	if (!d) {
+		dev_dbg(dev, "No DVSEC Capability\n");
+		return -ENXIO;
+	}
+
+	rc = pci_read_config_word(pdev, d + PCI_DVSEC_CXL_CAP, &cap);
+	if (rc)
+		return pcibios_err_to_errno(rc);
+
+	if (!(cap & PCI_DVSEC_CXL_MEM_CAPABLE)) {
+		dev_dbg(dev, "Not MEM Capable\n");
+		return -ENXIO;
+	}
+
+	/*
+	 * It is not allowed by spec for MEM.capable to be set and have 0 legacy
+	 * HDM decoders (values > 2 are also undefined as of CXL 2.0). As this
+	 * driver is for a spec defined class code which must be CXL.mem
+	 * capable, there is no point in continuing to enable CXL.mem.
+	 */
+	hdm_count = FIELD_GET(PCI_DVSEC_CXL_HDM_COUNT, cap);
+	if (!hdm_count || hdm_count > 2)
+		return -EINVAL;
+
+	/*
+	 * The current DVSEC values are moot if the memory capability is
+	 * disabled, and they will remain moot after the HDM Decoder
+	 * capability is enabled.
+	 */
+	rc = pci_read_config_word(pdev, d + PCI_DVSEC_CXL_CTRL, &ctrl);
+	if (rc)
+		return pcibios_err_to_errno(rc);
+
+	info->mem_enabled = FIELD_GET(PCI_DVSEC_CXL_MEM_ENABLE, ctrl);
+	if (!info->mem_enabled)
+		return 0;
+
+	for (i = 0; i < hdm_count; i++) {
+		u64 base, size;
+		u32 temp;
+
+		rc = cxl_dvsec_mem_range_valid(cxlds, i);
+		if (rc)
+			return rc;
+
+		rc = pci_read_config_dword(
+			pdev, d + PCI_DVSEC_CXL_RANGE_SIZE_HIGH(i), &temp);
+		if (rc)
+			return pcibios_err_to_errno(rc);
+
+		size = (u64)temp << 32;
+
+		rc = pci_read_config_dword(
+			pdev, d + PCI_DVSEC_CXL_RANGE_SIZE_LOW(i), &temp);
+		if (rc)
+			return pcibios_err_to_errno(rc);
+
+		size |= temp & PCI_DVSEC_CXL_MEM_SIZE_LOW;
+		if (!size) {
+			continue;
+		}
+
+		rc = pci_read_config_dword(
+			pdev, d + PCI_DVSEC_CXL_RANGE_BASE_HIGH(i), &temp);
+		if (rc)
+			return pcibios_err_to_errno(rc);
+
+		base = (u64)temp << 32;
+
+		rc = pci_read_config_dword(
+			pdev, d + PCI_DVSEC_CXL_RANGE_BASE_LOW(i), &temp);
+		if (rc)
+			return pcibios_err_to_errno(rc);
+
+		base |= temp & PCI_DVSEC_CXL_MEM_BASE_LOW;
+
+		info->dvsec_range[ranges++] = (struct range) {
+			.start = base,
+			.end = base + size - 1
+		};
+	}
+
+	info->ranges = ranges;
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_dvsec_rr_decode, "CXL");
+
+/**
+ * cxl_hdm_decode_init() - Setup HDM decoding for the endpoint
+ * @cxlds: Device state
+ * @cxlhdm: Mapped HDM decoder Capability
+ * @info: Cached DVSEC range registers info
+ *
+ * Try to enable the endpoint's HDM Decoder Capability
+ */
+int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm,
+			struct cxl_endpoint_dvsec_info *info)
+{
+	void __iomem *hdm = cxlhdm->regs.hdm_decoder;
+	struct cxl_port *port = cxlhdm->port;
+	struct device *dev = cxlds->dev;
+	struct cxl_port *root;
+	int i, rc, allowed;
+	u32 global_ctrl = 0;
+
+	if (hdm)
+		global_ctrl = readl(hdm + CXL_HDM_DECODER_CTRL_OFFSET);
+
+	/*
+	 * If the HDM Decoder Capability is already enabled then assume
+	 * that some other agent like platform firmware set it up.
+	 */
+	if (global_ctrl & CXL_HDM_DECODER_ENABLE || (!hdm && info->mem_enabled))
+		return devm_cxl_enable_mem(&port->dev, cxlds);
+
+	/*
+	 * If the HDM Decoder Capability does not exist and DVSEC was
+	 * not setup, the DVSEC based emulation cannot be used.
+	 */
+	if (!hdm)
+		return -ENODEV;
+
+	/* The HDM Decoder Capability exists but is globally disabled. */
+
+	/*
+	 * If the DVSEC CXL Range registers are not enabled, just
+	 * enable and use the HDM Decoder Capability registers.
+	 */
+	if (!info->mem_enabled) {
+		rc = devm_cxl_enable_hdm(&port->dev, cxlhdm);
+		if (rc)
+			return rc;
+
+		return devm_cxl_enable_mem(&port->dev, cxlds);
+	}
+
+	/*
+	 * Per CXL 2.0 Section 8.1.3.8.3 and 8.1.3.8.4 DVSEC CXL Range 1 Base
+	 * [High,Low] when HDM operation is enabled the range register values
+	 * are ignored by the device, but the spec also recommends matching the
+	 * DVSEC Range 1,2 to HDM Decoder Range 0,1. So, non-zero info->ranges
+	 * are expected even though Linux does not require or maintain that
+	 * match. Check if at least one DVSEC range is enabled and allowed by
+	 * the platform. That is, the DVSEC range must be covered by a locked
+	 * platform window (CFMWS). Fail otherwise as the endpoint's decoders
+	 * cannot be used.
+	 */
+
+	root = to_cxl_port(port->dev.parent);
+	while (!is_cxl_root(root) && is_cxl_port(root->dev.parent))
+		root = to_cxl_port(root->dev.parent);
+	if (!is_cxl_root(root)) {
+		dev_err(dev, "Failed to acquire root port for HDM enable\n");
+		return -ENODEV;
+	}
+
+	for (i = 0, allowed = 0; i < info->ranges; i++) {
+		struct device *cxld_dev;
+
+		cxld_dev = device_find_child(&root->dev, &info->dvsec_range[i],
+					     dvsec_range_allowed);
+		if (!cxld_dev) {
+			dev_dbg(dev, "DVSEC Range%d denied by platform\n", i);
+			continue;
+		}
+		dev_dbg(dev, "DVSEC Range%d allowed by platform\n", i);
+		put_device(cxld_dev);
+		allowed++;
+	}
+
+	if (!allowed) {
+		dev_err(dev, "Range register decodes outside platform defined CXL ranges.\n");
+		return -ENXIO;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_hdm_decode_init, "CXL");
+
+#define CXL_DOE_TABLE_ACCESS_REQ_CODE		0x000000ff
+#define   CXL_DOE_TABLE_ACCESS_REQ_CODE_READ	0
+#define CXL_DOE_TABLE_ACCESS_TABLE_TYPE		0x0000ff00
+#define   CXL_DOE_TABLE_ACCESS_TABLE_TYPE_CDATA	0
+#define CXL_DOE_TABLE_ACCESS_ENTRY_HANDLE	0xffff0000
+#define CXL_DOE_TABLE_ACCESS_LAST_ENTRY		0xffff
+#define CXL_DOE_PROTOCOL_TABLE_ACCESS 2
+
+#define CDAT_DOE_REQ(entry_handle) cpu_to_le32				\
+	(FIELD_PREP(CXL_DOE_TABLE_ACCESS_REQ_CODE,			\
+		    CXL_DOE_TABLE_ACCESS_REQ_CODE_READ) |		\
+	 FIELD_PREP(CXL_DOE_TABLE_ACCESS_TABLE_TYPE,			\
+		    CXL_DOE_TABLE_ACCESS_TABLE_TYPE_CDATA) |		\
+	 FIELD_PREP(CXL_DOE_TABLE_ACCESS_ENTRY_HANDLE, (entry_handle)))
+
+static int cxl_cdat_get_length(struct device *dev,
+			       struct pci_doe_mb *doe_mb,
+			       size_t *length)
+{
+	__le32 request = CDAT_DOE_REQ(0);
+	__le32 response[2];
+	int rc;
+
+	rc = pci_doe(doe_mb, PCI_VENDOR_ID_CXL,
+		     CXL_DOE_PROTOCOL_TABLE_ACCESS,
+		     &request, sizeof(request),
+		     &response, sizeof(response));
+	if (rc < 0) {
+		dev_err(dev, "DOE failed: %d", rc);
+		return rc;
+	}
+	if (rc < sizeof(response))
+		return -EIO;
+
+	*length = le32_to_cpu(response[1]);
+	dev_dbg(dev, "CDAT length %zu\n", *length);
+
+	return 0;
+}
+
+static int cxl_cdat_read_table(struct device *dev,
+			       struct pci_doe_mb *doe_mb,
+			       struct cdat_doe_rsp *rsp, size_t *length)
+{
+	size_t received, remaining = *length;
+	unsigned int entry_handle = 0;
+	union cdat_data *data;
+	__le32 saved_dw = 0;
+
+	do {
+		__le32 request = CDAT_DOE_REQ(entry_handle);
+		int rc;
+
+		rc = pci_doe(doe_mb, PCI_VENDOR_ID_CXL,
+			     CXL_DOE_PROTOCOL_TABLE_ACCESS,
+			     &request, sizeof(request),
+			     rsp, sizeof(*rsp) + remaining);
+		if (rc < 0) {
+			dev_err(dev, "DOE failed: %d", rc);
+			return rc;
+		}
+
+		if (rc < sizeof(*rsp))
+			return -EIO;
+
+		data = (union cdat_data *)rsp->data;
+		received = rc - sizeof(*rsp);
+
+		if (entry_handle == 0) {
+			if (received != sizeof(data->header))
+				return -EIO;
+		} else {
+			if (received < sizeof(data->entry) ||
+			    received != le16_to_cpu(data->entry.length))
+				return -EIO;
+		}
+
+		/* Get the CXL table access header entry handle */
+		entry_handle = FIELD_GET(CXL_DOE_TABLE_ACCESS_ENTRY_HANDLE,
+					 le32_to_cpu(rsp->doe_header));
+
+		/*
+		 * Table Access Response Header overwrote the last DW of
+		 * previous entry, so restore that DW
+		 */
+		rsp->doe_header = saved_dw;
+		remaining -= received;
+		rsp = (void *)rsp + received;
+		saved_dw = rsp->doe_header;
+	} while (entry_handle != CXL_DOE_TABLE_ACCESS_LAST_ENTRY);
+
+	/* Length in CDAT header may exceed concatenation of CDAT entries */
+	*length -= remaining;
+
+	return 0;
+}
+
+static unsigned char cdat_checksum(void *buf, size_t size)
+{
+	unsigned char sum, *data = buf;
+	size_t i;
+
+	for (sum = 0, i = 0; i < size; i++)
+		sum += data[i];
+	return sum;
+}
+
+/**
+ * read_cdat_data - Read the CDAT data on this port
+ * @port: Port to read data from
+ *
+ * This call will sleep waiting for responses from the DOE mailbox.
+ */
+void read_cdat_data(struct cxl_port *port)
+{
+	struct device *uport = port->uport_dev;
+	struct device *dev = &port->dev;
+	struct pci_doe_mb *doe_mb;
+	struct pci_dev *pdev = NULL;
+	struct cxl_memdev *cxlmd;
+	struct cdat_doe_rsp *buf;
+	size_t table_length, length;
+	int rc;
+
+	if (is_cxl_memdev(uport)) {
+		struct device *host;
+
+		cxlmd = to_cxl_memdev(uport);
+		host = cxlmd->dev.parent;
+		if (dev_is_pci(host))
+			pdev = to_pci_dev(host);
+	} else if (dev_is_pci(uport)) {
+		pdev = to_pci_dev(uport);
+	}
+
+	if (!pdev)
+		return;
+
+	doe_mb = pci_find_doe_mailbox(pdev, PCI_VENDOR_ID_CXL,
+				      CXL_DOE_PROTOCOL_TABLE_ACCESS);
+	if (!doe_mb) {
+		dev_dbg(dev, "No CDAT mailbox\n");
+		return;
+	}
+
+	port->cdat_available = true;
+
+	if (cxl_cdat_get_length(dev, doe_mb, &length)) {
+		dev_dbg(dev, "No CDAT length\n");
+		return;
+	}
+
+	/*
+	 * The begin of the CDAT buffer needs space for additional 4
+	 * bytes for the DOE header. Table data starts afterwards.
+	 */
+	buf = devm_kzalloc(dev, sizeof(*buf) + length, GFP_KERNEL);
+	if (!buf)
+		goto err;
+
+	table_length = length;
+
+	rc = cxl_cdat_read_table(dev, doe_mb, buf, &length);
+	if (rc)
+		goto err;
+
+	if (table_length != length)
+		dev_warn(dev, "Malformed CDAT table length (%zu:%zu), discarding trailing data\n",
+			table_length, length);
+
+	if (cdat_checksum(buf->data, length))
+		goto err;
+
+	port->cdat.table = buf->data;
+	port->cdat.length = length;
+
+	return;
+err:
+	/* Don't leave table data allocated on error */
+	devm_kfree(dev, buf);
+	dev_err(dev, "Failed to read/validate CDAT.\n");
+}
+EXPORT_SYMBOL_NS_GPL(read_cdat_data, "CXL");
+
+static int cxl_flit_size(struct pci_dev *pdev)
+{
+	if (cxl_pci_flit_256(pdev))
+		return 256;
+
+	return 68;
+}
+
+/**
+ * cxl_pci_get_latency - calculate the link latency for the PCIe link
+ * @pdev: PCI device
+ *
+ * return: calculated latency or 0 for no latency
+ *
+ * CXL Memory Device SW Guide v1.0 2.11.4 Link latency calculation
+ * Link latency = LinkPropagationLatency + FlitLatency + RetimerLatency
+ * LinkProgationLatency is negligible, so 0 will be used
+ * RetimerLatency is assumed to be negligible and 0 will be used
+ * FlitLatency = FlitSize / LinkBandwidth
+ * FlitSize is defined by spec. CXL rev3.0 4.2.1.
+ * 68B flit is used up to 32GT/s. >32GT/s, 256B flit size is used.
+ * The FlitLatency is converted to picoseconds.
+ */
+long cxl_pci_get_latency(struct pci_dev *pdev)
+{
+	long bw;
+
+	bw = pcie_link_speed_mbps(pdev);
+	if (bw < 0)
+		return 0;
+	bw /= BITS_PER_BYTE;
+
+	return cxl_flit_size(pdev) * MEGA / bw;
+}
+
+static int __cxl_endpoint_decoder_reset_detected(struct device *dev, void *data)
+{
+	struct cxl_port *port = data;
+	struct cxl_decoder *cxld;
+	struct cxl_hdm *cxlhdm;
+	void __iomem *hdm;
+	u32 ctrl;
+
+	if (!is_endpoint_decoder(dev))
+		return 0;
+
+	cxld = to_cxl_decoder(dev);
+	if ((cxld->flags & CXL_DECODER_F_ENABLE) == 0)
+		return 0;
+
+	cxlhdm = dev_get_drvdata(&port->dev);
+	hdm = cxlhdm->regs.hdm_decoder;
+	ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(cxld->id));
+
+	return !FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl);
+}
+
+bool cxl_endpoint_decoder_reset_detected(struct cxl_port *port)
+{
+	return device_for_each_child(&port->dev, port,
+				     __cxl_endpoint_decoder_reset_detected);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_endpoint_decoder_reset_detected, "CXL");
+
+static int cxl_rcrb_get_comp_regs(struct pci_dev *pdev,
+				  struct cxl_register_map *map,
+				  struct cxl_dport *dport)
+{
+	resource_size_t component_reg_phys;
+
+	*map = (struct cxl_register_map) {
+		.host = &pdev->dev,
+		.resource = CXL_RESOURCE_NONE,
+	};
+
+	component_reg_phys = cxl_rcd_component_reg_phys(&pdev->dev, dport);
+	if (component_reg_phys == CXL_RESOURCE_NONE)
+		return -ENXIO;
+
+	map->resource = component_reg_phys;
+	map->reg_type = CXL_REGLOC_RBI_COMPONENT;
+	map->max_size = CXL_COMPONENT_REG_BLOCK_SIZE;
+
+	return 0;
+}
+
+int cxl_pci_setup_regs(struct pci_dev *pdev, enum cxl_regloc_type type,
+		       struct cxl_register_map *map)
+{
+	int rc;
+
+	rc = cxl_find_regblock(pdev, type, map);
+
+	/*
+	 * If the Register Locator DVSEC does not exist, check if it
+	 * is an RCH and try to extract the Component Registers from
+	 * an RCRB.
+	 */
+	if (rc && type == CXL_REGLOC_RBI_COMPONENT && is_cxl_restricted(pdev)) {
+		struct cxl_dport *dport;
+		struct cxl_port *port __free(put_cxl_port) =
+			cxl_pci_find_port(pdev, &dport);
+		if (!port)
+			return -EPROBE_DEFER;
+
+		rc = cxl_rcrb_get_comp_regs(pdev, map, dport);
+		if (rc)
+			return rc;
+
+		rc = cxl_dport_map_rcd_linkcap(pdev, dport);
+		if (rc)
+			return rc;
+
+	} else if (rc) {
+		return rc;
+	}
+
+	return cxl_setup_regs(map);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_pci_setup_regs, "CXL");
+
+int cxl_pci_get_bandwidth(struct pci_dev *pdev, struct access_coordinate *c)
+{
+	int speed, bw;
+	u16 lnksta;
+	u32 width;
+
+	speed = pcie_link_speed_mbps(pdev);
+	if (speed < 0)
+		return speed;
+	speed /= BITS_PER_BYTE;
+
+	pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnksta);
+	width = FIELD_GET(PCI_EXP_LNKSTA_NLW, lnksta);
+	bw = speed * width;
+
+	for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+		c[i].read_bandwidth = bw;
+		c[i].write_bandwidth = bw;
+	}
+
+	return 0;
+}
+
+/*
+ * Set max timeout such that platforms will optimize GPF flow to avoid
+ * the implied worst-case scenario delays. On a sane platform, all
+ * devices should always complete GPF within the energy budget of
+ * the GPF flow. The kernel does not have enough information to pick
+ * anything better than "maximize timeouts and hope it works".
+ *
+ * A misbehaving device could block forward progress of GPF for all
+ * the other devices, exhausting the energy budget of the platform.
+ * However, the spec seems to assume that moving on from slow to respond
+ * devices is a virtue. It is not possible to know that, in actuality,
+ * the slow to respond device is *the* most critical device in the
+ * system to wait.
+ */
+#define GPF_TIMEOUT_BASE_MAX 2
+#define GPF_TIMEOUT_SCALE_MAX 7 /* 10 seconds */
+
+u16 cxl_gpf_get_dvsec(struct device *dev)
+{
+	struct pci_dev *pdev;
+	bool is_port = true;
+	u16 dvsec;
+
+	if (!dev_is_pci(dev))
+		return 0;
+
+	pdev = to_pci_dev(dev);
+	if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ENDPOINT)
+		is_port = false;
+
+	dvsec = pci_find_dvsec_capability(pdev, PCI_VENDOR_ID_CXL,
+			is_port ? PCI_DVSEC_CXL_PORT_GPF : PCI_DVSEC_CXL_DEVICE_GPF);
+	if (!dvsec)
+		dev_warn(dev, "%s GPF DVSEC not present\n",
+			 is_port ? "Port" : "Device");
+	return dvsec;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_gpf_get_dvsec, "CXL");
+
+static int update_gpf_port_dvsec(struct pci_dev *pdev, int dvsec, int phase)
+{
+	u64 base, scale;
+	int rc, offset;
+	u16 ctrl;
+
+	switch (phase) {
+	case 1:
+		offset = PCI_DVSEC_CXL_PORT_GPF_PHASE_1_CONTROL;
+		base = PCI_DVSEC_CXL_PORT_GPF_PHASE_1_TMO_BASE;
+		scale = PCI_DVSEC_CXL_PORT_GPF_PHASE_1_TMO_SCALE;
+		break;
+	case 2:
+		offset = PCI_DVSEC_CXL_PORT_GPF_PHASE_2_CONTROL;
+		base = PCI_DVSEC_CXL_PORT_GPF_PHASE_2_TMO_BASE;
+		scale = PCI_DVSEC_CXL_PORT_GPF_PHASE_2_TMO_SCALE;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	rc = pci_read_config_word(pdev, dvsec + offset, &ctrl);
+	if (rc)
+		return rc;
+
+	if (FIELD_GET(base, ctrl) == GPF_TIMEOUT_BASE_MAX &&
+	    FIELD_GET(scale, ctrl) == GPF_TIMEOUT_SCALE_MAX)
+		return 0;
+
+	ctrl = FIELD_PREP(base, GPF_TIMEOUT_BASE_MAX);
+	ctrl |= FIELD_PREP(scale, GPF_TIMEOUT_SCALE_MAX);
+
+	rc = pci_write_config_word(pdev, dvsec + offset, ctrl);
+	if (!rc)
+		pci_dbg(pdev, "Port GPF phase %d timeout: %d0 secs\n",
+			phase, GPF_TIMEOUT_BASE_MAX);
+
+	return rc;
+}
+
+int cxl_gpf_port_setup(struct cxl_dport *dport)
+{
+	if (!dport)
+		return -EINVAL;
+
+	if (!dport->gpf_dvsec) {
+		struct pci_dev *pdev;
+		int dvsec;
+
+		dvsec = cxl_gpf_get_dvsec(dport->dport_dev);
+		if (!dvsec)
+			return -EINVAL;
+
+		dport->gpf_dvsec = dvsec;
+		pdev = to_pci_dev(dport->dport_dev);
+		update_gpf_port_dvsec(pdev, dport->gpf_dvsec, 1);
+		update_gpf_port_dvsec(pdev, dport->gpf_dvsec, 2);
+	}
+
+	return 0;
+}
+
+struct cxl_walk_context {
+	struct pci_bus *bus;
+	struct cxl_port *port;
+	int type;
+	int error;
+	int count;
+};
+
+static int count_dports(struct pci_dev *pdev, void *data)
+{
+	struct cxl_walk_context *ctx = data;
+	int type = pci_pcie_type(pdev);
+
+	if (pdev->bus != ctx->bus)
+		return 0;
+	if (!pci_is_pcie(pdev))
+		return 0;
+	if (type != ctx->type)
+		return 0;
+
+	ctx->count++;
+	return 0;
+}
+
+int cxl_port_get_possible_dports(struct cxl_port *port)
+{
+	struct pci_bus *bus = cxl_port_to_pci_bus(port);
+	struct cxl_walk_context ctx;
+	int type;
+
+	if (!bus) {
+		dev_err(&port->dev, "No PCI bus found for port %s\n",
+			dev_name(&port->dev));
+		return -ENXIO;
+	}
+
+	if (pci_is_root_bus(bus))
+		type = PCI_EXP_TYPE_ROOT_PORT;
+	else
+		type = PCI_EXP_TYPE_DOWNSTREAM;
+
+	ctx = (struct cxl_walk_context) {
+		.bus = bus,
+		.type = type,
+	};
+	pci_walk_bus(bus, count_dports, &ctx);
+
+	return ctx.count;
+}

linux-7.2.3/drivers/cxl/core/pmem.c

@@ -0,0 +1,310 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2020 Intel Corporation. */
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/idr.h>
+#include <cxlmem.h>
+#include <cxl.h>
+#include "core.h"
+
+/**
+ * DOC: cxl pmem
+ *
+ * The core CXL PMEM infrastructure supports persistent memory
+ * provisioning and serves as a bridge to the LIBNVDIMM subsystem. A CXL
+ * 'bridge' device is added at the root of a CXL device topology if
+ * platform firmware advertises at least one persistent memory capable
+ * CXL window. That root-level bridge corresponds to a LIBNVDIMM 'bus'
+ * device. Then for each cxl_memdev in the CXL device topology a bridge
+ * device is added to host a LIBNVDIMM dimm object. When these bridges
+ * are registered native LIBNVDIMM uapis are translated to CXL
+ * operations, for example, namespace label access commands.
+ */
+
+static DEFINE_IDA(cxl_nvdimm_bridge_ida);
+
+static void cxl_nvdimm_bridge_release(struct device *dev)
+{
+	struct cxl_nvdimm_bridge *cxl_nvb = to_cxl_nvdimm_bridge(dev);
+
+	ida_free(&cxl_nvdimm_bridge_ida, cxl_nvb->id);
+	kfree(cxl_nvb);
+}
+
+static const struct attribute_group *cxl_nvdimm_bridge_attribute_groups[] = {
+	&cxl_base_attribute_group,
+	NULL,
+};
+
+const struct device_type cxl_nvdimm_bridge_type = {
+	.name = "cxl_nvdimm_bridge",
+	.release = cxl_nvdimm_bridge_release,
+	.groups = cxl_nvdimm_bridge_attribute_groups,
+};
+
+struct cxl_nvdimm_bridge *to_cxl_nvdimm_bridge(struct device *dev)
+{
+	if (dev_WARN_ONCE(dev, dev->type != &cxl_nvdimm_bridge_type,
+			  "not a cxl_nvdimm_bridge device\n"))
+		return NULL;
+	return container_of(dev, struct cxl_nvdimm_bridge, dev);
+}
+EXPORT_SYMBOL_NS_GPL(to_cxl_nvdimm_bridge, "CXL");
+
+/**
+ * cxl_find_nvdimm_bridge() - find a bridge device relative to a port
+ * @port: any descendant port of an nvdimm-bridge associated
+ *        root-cxl-port
+ */
+struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_port *port)
+{
+	struct cxl_root *cxl_root __free(put_cxl_root) = find_cxl_root(port);
+	struct device *dev;
+
+	if (!cxl_root)
+		return NULL;
+
+	dev = device_find_child(&cxl_root->port.dev,
+				&cxl_nvdimm_bridge_type,
+				device_match_type);
+
+	if (!dev)
+		return NULL;
+
+	return to_cxl_nvdimm_bridge(dev);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_find_nvdimm_bridge, "CXL");
+
+static struct lock_class_key cxl_nvdimm_bridge_key;
+
+static struct cxl_nvdimm_bridge *cxl_nvdimm_bridge_alloc(struct cxl_port *port)
+{
+	struct cxl_nvdimm_bridge *cxl_nvb;
+	struct device *dev;
+	int rc;
+
+	cxl_nvb = kzalloc_obj(*cxl_nvb);
+	if (!cxl_nvb)
+		return ERR_PTR(-ENOMEM);
+
+	rc = ida_alloc(&cxl_nvdimm_bridge_ida, GFP_KERNEL);
+	if (rc < 0)
+		goto err;
+	cxl_nvb->id = rc;
+
+	dev = &cxl_nvb->dev;
+	cxl_nvb->port = port;
+	device_initialize(dev);
+	lockdep_set_class(&dev->mutex, &cxl_nvdimm_bridge_key);
+	device_set_pm_not_required(dev);
+	dev->parent = &port->dev;
+	dev->bus = &cxl_bus_type;
+	dev->type = &cxl_nvdimm_bridge_type;
+
+	return cxl_nvb;
+
+err:
+	kfree(cxl_nvb);
+	return ERR_PTR(rc);
+}
+
+static void unregister_nvb(void *_cxl_nvb)
+{
+	struct cxl_nvdimm_bridge *cxl_nvb = _cxl_nvb;
+
+	device_unregister(&cxl_nvb->dev);
+}
+
+static bool cxl_nvdimm_bridge_failed_attach(struct cxl_nvdimm_bridge *cxl_nvb)
+{
+	struct device *dev = &cxl_nvb->dev;
+
+	guard(device)(dev);
+	/* If the device has no driver, then it failed to attach. */
+	return dev->driver == NULL;
+}
+
+struct cxl_nvdimm_bridge *__devm_cxl_add_nvdimm_bridge(struct device *host,
+						       struct cxl_port *port)
+{
+	struct cxl_nvdimm_bridge *cxl_nvb;
+	struct device *dev;
+	int rc;
+
+	if (!IS_ENABLED(CONFIG_CXL_PMEM))
+		return ERR_PTR(-ENXIO);
+
+	cxl_nvb = cxl_nvdimm_bridge_alloc(port);
+	if (IS_ERR(cxl_nvb))
+		return cxl_nvb;
+
+	dev = &cxl_nvb->dev;
+	rc = dev_set_name(dev, "nvdimm-bridge%d", cxl_nvb->id);
+	if (rc)
+		goto err;
+
+	rc = device_add(dev);
+	if (rc)
+		goto err;
+
+	if (cxl_nvdimm_bridge_failed_attach(cxl_nvb)) {
+		unregister_nvb(cxl_nvb);
+		return ERR_PTR(-ENODEV);
+	}
+
+	rc = devm_add_action_or_reset(host, unregister_nvb, cxl_nvb);
+	if (rc)
+		return ERR_PTR(rc);
+
+	return cxl_nvb;
+
+err:
+	put_device(dev);
+	return ERR_PTR(rc);
+}
+EXPORT_SYMBOL_FOR_MODULES(__devm_cxl_add_nvdimm_bridge, "cxl_pmem");
+
+static void cxl_nvdimm_release(struct device *dev)
+{
+	struct cxl_nvdimm *cxl_nvd = to_cxl_nvdimm(dev);
+
+	kfree(cxl_nvd);
+}
+
+static const struct attribute_group *cxl_nvdimm_attribute_groups[] = {
+	&cxl_base_attribute_group,
+	NULL,
+};
+
+const struct device_type cxl_nvdimm_type = {
+	.name = "cxl_nvdimm",
+	.release = cxl_nvdimm_release,
+	.groups = cxl_nvdimm_attribute_groups,
+};
+
+bool is_cxl_nvdimm(struct device *dev)
+{
+	return dev->type == &cxl_nvdimm_type;
+}
+EXPORT_SYMBOL_NS_GPL(is_cxl_nvdimm, "CXL");
+
+struct cxl_nvdimm *to_cxl_nvdimm(struct device *dev)
+{
+	if (dev_WARN_ONCE(dev, !is_cxl_nvdimm(dev),
+			  "not a cxl_nvdimm device\n"))
+		return NULL;
+	return container_of(dev, struct cxl_nvdimm, dev);
+}
+EXPORT_SYMBOL_NS_GPL(to_cxl_nvdimm, "CXL");
+
+static struct lock_class_key cxl_nvdimm_key;
+
+static struct cxl_nvdimm *cxl_nvdimm_alloc(struct cxl_nvdimm_bridge *cxl_nvb,
+					   struct cxl_memdev *cxlmd)
+{
+	struct cxl_nvdimm *cxl_nvd;
+	struct device *dev;
+
+	cxl_nvd = kzalloc_obj(*cxl_nvd);
+	if (!cxl_nvd)
+		return ERR_PTR(-ENOMEM);
+
+	dev = &cxl_nvd->dev;
+	cxl_nvd->cxlmd = cxlmd;
+	cxlmd->cxl_nvd = cxl_nvd;
+	device_initialize(dev);
+	lockdep_set_class(&dev->mutex, &cxl_nvdimm_key);
+	device_set_pm_not_required(dev);
+	dev->parent = &cxlmd->dev;
+	dev->bus = &cxl_bus_type;
+	dev->type = &cxl_nvdimm_type;
+	/*
+	 * A "%llx" string is 17-bytes vs dimm_id that is max
+	 * NVDIMM_KEY_DESC_LEN
+	 */
+	BUILD_BUG_ON(sizeof(cxl_nvd->dev_id) < 17 ||
+		     sizeof(cxl_nvd->dev_id) > NVDIMM_KEY_DESC_LEN);
+	sprintf(cxl_nvd->dev_id, "%llx", cxlmd->cxlds->serial);
+
+	return cxl_nvd;
+}
+
+static void cxlmd_release_nvdimm(void *_cxlmd)
+{
+	struct cxl_memdev *cxlmd = _cxlmd;
+	struct cxl_nvdimm *cxl_nvd = cxlmd->cxl_nvd;
+	struct cxl_nvdimm_bridge *cxl_nvb = cxlmd->cxl_nvb;
+
+	cxl_nvd->cxlmd = NULL;
+	cxlmd->cxl_nvd = NULL;
+	cxlmd->cxl_nvb = NULL;
+	device_unregister(&cxl_nvd->dev);
+	put_device(&cxl_nvb->dev);
+}
+
+/**
+ * devm_cxl_add_nvdimm() - add a bridge between a cxl_memdev and an nvdimm
+ * @host: host device for devm operations
+ * @port: any port in the CXL topology to find the nvdimm-bridge device
+ * @cxlmd: parent of the to be created cxl_nvdimm device
+ *
+ * Return: 0 on success negative error code on failure.
+ */
+int devm_cxl_add_nvdimm(struct device *host, struct cxl_port *port,
+			struct cxl_memdev *cxlmd)
+{
+	struct cxl_nvdimm_bridge *cxl_nvb;
+	struct cxl_nvdimm *cxl_nvd;
+	struct device *dev;
+	int rc;
+
+	cxl_nvb = cxl_find_nvdimm_bridge(port);
+	if (!cxl_nvb)
+		return -ENODEV;
+
+	/*
+	 * Take the uport_dev lock to guard against race of nvdimm_bus object.
+	 * cxl_acpi_probe() registers the nvdimm_bus and is done under the
+	 * root port uport_dev lock.
+	 *
+	 * Take the cxl_nvb device lock to ensure that cxl_nvb driver is in a
+	 * consistent state. And the driver registers nvdimm_bus.
+	 */
+	guard(device)(cxl_nvb->port->uport_dev);
+	guard(device)(&cxl_nvb->dev);
+	if (!cxl_nvb->nvdimm_bus) {
+		rc = -ENODEV;
+		goto err_alloc;
+	}
+
+	cxl_nvd = cxl_nvdimm_alloc(cxl_nvb, cxlmd);
+	if (IS_ERR(cxl_nvd)) {
+		rc = PTR_ERR(cxl_nvd);
+		goto err_alloc;
+	}
+	cxlmd->cxl_nvb = cxl_nvb;
+
+	dev = &cxl_nvd->dev;
+	rc = dev_set_name(dev, "pmem%d", cxlmd->id);
+	if (rc)
+		goto err;
+
+	rc = device_add(dev);
+	if (rc)
+		goto err;
+
+	dev_dbg(host, "register %s\n", dev_name(dev));
+
+	/* @cxlmd carries a reference on @cxl_nvb until cxlmd_release_nvdimm */
+	return devm_add_action_or_reset(host, cxlmd_release_nvdimm, cxlmd);
+
+err:
+	put_device(dev);
+err_alloc:
+	cxlmd->cxl_nvb = NULL;
+	cxlmd->cxl_nvd = NULL;
+	put_device(&cxl_nvb->dev);
+
+	return rc;
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_add_nvdimm, "CXL");

linux-7.2.3/drivers/cxl/core/pmu.c

@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2023 Huawei. All rights reserved. */
+
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/idr.h>
+#include <cxlmem.h>
+#include <pmu.h>
+#include <cxl.h>
+#include "core.h"
+
+static void cxl_pmu_release(struct device *dev)
+{
+	struct cxl_pmu *pmu = to_cxl_pmu(dev);
+
+	kfree(pmu);
+}
+
+const struct device_type cxl_pmu_type = {
+	.name = "cxl_pmu",
+	.release = cxl_pmu_release,
+};
+
+static void remove_dev(void *dev)
+{
+	device_unregister(dev);
+}
+
+int devm_cxl_pmu_add(struct device *parent, struct cxl_pmu_regs *regs,
+		     int assoc_id, int index, enum cxl_pmu_type type)
+{
+	struct cxl_pmu *pmu;
+	struct device *dev;
+	int rc;
+
+	pmu = kzalloc_obj(*pmu);
+	if (!pmu)
+		return -ENOMEM;
+
+	pmu->assoc_id = assoc_id;
+	pmu->index = index;
+	pmu->type = type;
+	pmu->base = regs->pmu;
+	dev = &pmu->dev;
+	device_initialize(dev);
+	device_set_pm_not_required(dev);
+	dev->parent = parent;
+	dev->bus = &cxl_bus_type;
+	dev->type = &cxl_pmu_type;
+	switch (pmu->type) {
+	case CXL_PMU_MEMDEV:
+		rc = dev_set_name(dev, "pmu_mem%d.%d", assoc_id, index);
+		break;
+	}
+	if (rc)
+		goto err;
+
+	rc = device_add(dev);
+	if (rc)
+		goto err;
+
+	return devm_add_action_or_reset(parent, remove_dev, dev);
+
+err:
+	put_device(&pmu->dev);
+	return rc;
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_pmu_add, "CXL");

linux-7.2.3/drivers/cxl/core/ras.c

@@ -0,0 +1,338 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2025 AMD Corporation. All rights reserved. */
+
+#include <linux/pci.h>
+#include <linux/aer.h>
+#include <cxl/event.h>
+#include <cxlmem.h>
+#include <cxlpci.h>
+#include "trace.h"
+
+/* Check that UCE header definition is maintained to keep ABI intact  */
+static_assert(CXL_HEADERLOG_TRACE_SIZE_U32 == 128,
+	      "rasdaemon ABI requires exactly 128 u32s");
+
+static void cxl_cper_trace_corr_port_prot_err(struct pci_dev *pdev,
+					      struct cxl_ras_capability_regs ras_cap)
+{
+	u32 status = ras_cap.cor_status & ~ras_cap.cor_mask;
+
+	trace_cxl_port_aer_correctable_error(&pdev->dev, status);
+}
+
+static void cxl_cper_trace_uncorr_port_prot_err(struct pci_dev *pdev,
+						struct cxl_ras_capability_regs ras_cap)
+{
+	u32 hl[CXL_HEADERLOG_TRACE_SIZE_U32] = {};
+	u32 status = ras_cap.uncor_status & ~ras_cap.uncor_mask;
+	u32 fe;
+
+	if (hweight32(status) > 1)
+		fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
+				   ras_cap.cap_control));
+	else
+		fe = status;
+
+	memcpy(hl, ras_cap.header_log, CXL_HEADERLOG_SIZE);
+	trace_cxl_port_aer_uncorrectable_error(&pdev->dev, status, fe, hl);
+}
+
+static void cxl_cper_trace_corr_prot_err(struct cxl_memdev *cxlmd,
+					 struct cxl_ras_capability_regs ras_cap)
+{
+	u32 status = ras_cap.cor_status & ~ras_cap.cor_mask;
+
+	trace_cxl_aer_correctable_error(cxlmd, status);
+}
+
+static void
+cxl_cper_trace_uncorr_prot_err(struct cxl_memdev *cxlmd,
+			       struct cxl_ras_capability_regs ras_cap)
+{
+	u32 hl[CXL_HEADERLOG_TRACE_SIZE_U32] = {};
+	u32 status = ras_cap.uncor_status & ~ras_cap.uncor_mask;
+	u32 fe;
+
+	if (hweight32(status) > 1)
+		fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
+				   ras_cap.cap_control));
+	else
+		fe = status;
+
+	/*
+	 * ras_cap.header_log[] holds CXL_HEADERLOG_SIZE_U32 (16) hardware
+	 * dwords.  Copy them into the front of a zero-filled
+	 * CXL_HEADERLOG_TRACE_SIZE_U32 (128) u32 staging buffer so the trace
+	 * event memcpy sees a full 512-byte source and the userspace ABI
+	 * (rasdaemon) is preserved.
+	 */
+	memcpy(hl, ras_cap.header_log, CXL_HEADERLOG_SIZE);
+	trace_cxl_aer_uncorrectable_error(cxlmd, status, fe, hl);
+}
+
+static int match_memdev_by_parent(struct device *dev, const void *uport)
+{
+	if (is_cxl_memdev(dev) && dev->parent == uport)
+		return 1;
+	return 0;
+}
+
+void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data)
+{
+	unsigned int devfn = PCI_DEVFN(data->prot_err.agent_addr.device,
+				       data->prot_err.agent_addr.function);
+	struct pci_dev *pdev __free(pci_dev_put) =
+		pci_get_domain_bus_and_slot(data->prot_err.agent_addr.segment,
+					    data->prot_err.agent_addr.bus,
+					    devfn);
+	struct cxl_memdev *cxlmd;
+	int port_type;
+
+	if (!pdev)
+		return;
+
+	port_type = pci_pcie_type(pdev);
+	if (port_type == PCI_EXP_TYPE_ROOT_PORT ||
+	    port_type == PCI_EXP_TYPE_DOWNSTREAM ||
+	    port_type == PCI_EXP_TYPE_UPSTREAM) {
+		if (data->severity == AER_CORRECTABLE)
+			cxl_cper_trace_corr_port_prot_err(pdev, data->ras_cap);
+		else
+			cxl_cper_trace_uncorr_port_prot_err(pdev, data->ras_cap);
+
+		return;
+	}
+
+	guard(device)(&pdev->dev);
+	if (!pdev->dev.driver)
+		return;
+
+	struct device *mem_dev __free(put_device) = bus_find_device(
+		&cxl_bus_type, NULL, pdev, match_memdev_by_parent);
+	if (!mem_dev)
+		return;
+
+	cxlmd = to_cxl_memdev(mem_dev);
+	if (data->severity == AER_CORRECTABLE)
+		cxl_cper_trace_corr_prot_err(cxlmd, data->ras_cap);
+	else
+		cxl_cper_trace_uncorr_prot_err(cxlmd, data->ras_cap);
+}
+EXPORT_SYMBOL_GPL(cxl_cper_handle_prot_err);
+
+static void cxl_cper_prot_err_work_fn(struct work_struct *work)
+{
+	struct cxl_cper_prot_err_work_data wd;
+
+	while (cxl_cper_prot_err_kfifo_get(&wd))
+		cxl_cper_handle_prot_err(&wd);
+}
+static DECLARE_WORK(cxl_cper_prot_err_work, cxl_cper_prot_err_work_fn);
+
+int cxl_ras_init(void)
+{
+	return cxl_cper_register_prot_err_work(&cxl_cper_prot_err_work);
+}
+
+void cxl_ras_exit(void)
+{
+	cxl_cper_unregister_prot_err_work(&cxl_cper_prot_err_work);
+	cancel_work_sync(&cxl_cper_prot_err_work);
+}
+
+static void cxl_dport_map_ras(struct cxl_dport *dport)
+{
+	struct cxl_register_map *map = &dport->reg_map;
+	struct device *dev = dport->dport_dev;
+
+	if (!map->component_map.ras.valid)
+		dev_dbg(dev, "RAS registers not found\n");
+	else if (cxl_map_component_regs(map, &dport->regs.component,
+					BIT(CXL_CM_CAP_CAP_ID_RAS)))
+		dev_dbg(dev, "Failed to map RAS capability.\n");
+}
+
+/**
+ * devm_cxl_dport_ras_setup - Setup CXL RAS report on this dport
+ * @dport: the cxl_dport that needs to be initialized
+ */
+void devm_cxl_dport_ras_setup(struct cxl_dport *dport)
+{
+	dport->reg_map.host = dport_to_host(dport);
+	cxl_dport_map_ras(dport);
+}
+
+void devm_cxl_dport_rch_ras_setup(struct cxl_dport *dport)
+{
+	struct pci_host_bridge *host_bridge;
+
+	if (!dev_is_pci(dport->dport_dev))
+		return;
+
+	devm_cxl_dport_ras_setup(dport);
+
+	host_bridge = to_pci_host_bridge(dport->dport_dev);
+	if (!host_bridge->native_aer)
+		return;
+
+	cxl_dport_map_rch_aer(dport);
+	cxl_disable_rch_root_ints(dport);
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_dport_rch_ras_setup, "CXL");
+
+void devm_cxl_port_ras_setup(struct cxl_port *port)
+{
+	struct cxl_register_map *map = &port->reg_map;
+
+	if (!map->component_map.ras.valid) {
+		dev_dbg(&port->dev, "RAS registers not found\n");
+		return;
+	}
+
+	map->host = &port->dev;
+	if (cxl_map_component_regs(map, &port->regs,
+				   BIT(CXL_CM_CAP_CAP_ID_RAS)))
+		dev_dbg(&port->dev, "Failed to map RAS capability\n");
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_port_ras_setup, "CXL");
+
+void cxl_handle_cor_ras(struct device *dev, void __iomem *ras_base)
+{
+	void __iomem *addr;
+	u32 status;
+
+	if (!ras_base)
+		return;
+
+	addr = ras_base + CXL_RAS_CORRECTABLE_STATUS_OFFSET;
+	status = readl(addr);
+	if (status & CXL_RAS_CORRECTABLE_STATUS_MASK) {
+		writel(status & CXL_RAS_CORRECTABLE_STATUS_MASK, addr);
+		trace_cxl_aer_correctable_error(to_cxl_memdev(dev), status);
+	}
+}
+
+/* CXL spec rev3.0 8.2.4.16.1 */
+static void header_log_copy(void __iomem *ras_base, u32 *log)
+{
+	void __iomem *addr;
+	u32 *log_addr;
+	int i;
+
+	addr = ras_base + CXL_RAS_HEADER_LOG_OFFSET;
+	log_addr = log;
+
+	for (i = 0; i < CXL_HEADERLOG_SIZE_U32; i++) {
+		*log_addr = readl(addr);
+		log_addr++;
+		addr += sizeof(u32);
+	}
+}
+
+/*
+ * Log the state of the RAS status registers and prepare them to log the
+ * next error status. Return 1 if reset needed.
+ */
+bool cxl_handle_ras(struct device *dev, void __iomem *ras_base)
+{
+	u32 hl[CXL_HEADERLOG_TRACE_SIZE_U32] = {};
+	void __iomem *addr;
+	u32 status;
+	u32 fe;
+
+	if (!ras_base)
+		return false;
+
+	addr = ras_base + CXL_RAS_UNCORRECTABLE_STATUS_OFFSET;
+	status = readl(addr);
+	if (!(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK))
+		return false;
+
+	/* If multiple errors, log header points to first error from ctrl reg */
+	if (hweight32(status) > 1) {
+		void __iomem *rcc_addr =
+			ras_base + CXL_RAS_CAP_CONTROL_OFFSET;
+
+		fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
+				   readl(rcc_addr)));
+	} else {
+		fe = status;
+	}
+
+	header_log_copy(ras_base, hl);
+	trace_cxl_aer_uncorrectable_error(to_cxl_memdev(dev), status, fe, hl);
+	writel(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK, addr);
+
+	return true;
+}
+
+void cxl_cor_error_detected(struct pci_dev *pdev)
+{
+	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
+	struct cxl_memdev *cxlmd = cxlds->cxlmd;
+	struct device *dev = &cxlds->cxlmd->dev;
+
+	scoped_guard(device, dev) {
+		if (!dev->driver) {
+			dev_warn(&pdev->dev,
+				 "%s: memdev disabled, abort error handling\n",
+				 dev_name(dev));
+			return;
+		}
+
+		if (cxlds->rcd)
+			cxl_handle_rdport_errors(cxlds);
+
+		cxl_handle_cor_ras(&cxlds->cxlmd->dev, cxlmd->endpoint->regs.ras);
+	}
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cor_error_detected, "CXL");
+
+pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
+				    pci_channel_state_t state)
+{
+	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
+	struct cxl_memdev *cxlmd = cxlds->cxlmd;
+	struct device *dev = &cxlmd->dev;
+	bool ue;
+
+	scoped_guard(device, dev) {
+		if (!dev->driver) {
+			dev_warn(&pdev->dev,
+				 "%s: memdev disabled, abort error handling\n",
+				 dev_name(dev));
+			return PCI_ERS_RESULT_DISCONNECT;
+		}
+
+		if (cxlds->rcd)
+			cxl_handle_rdport_errors(cxlds);
+		/*
+		 * A frozen channel indicates an impending reset which is fatal to
+		 * CXL.mem operation, and will likely crash the system. On the off
+		 * chance the situation is recoverable dump the status of the RAS
+		 * capability registers and bounce the active state of the memdev.
+		 */
+		ue = cxl_handle_ras(&cxlds->cxlmd->dev, cxlmd->endpoint->regs.ras);
+	}
+
+	switch (state) {
+	case pci_channel_io_normal:
+		if (ue) {
+			device_release_driver(dev);
+			return PCI_ERS_RESULT_NEED_RESET;
+		}
+		return PCI_ERS_RESULT_CAN_RECOVER;
+	case pci_channel_io_frozen:
+		dev_warn(&pdev->dev,
+			 "%s: frozen state error detected, disable CXL.mem\n",
+			 dev_name(dev));
+		device_release_driver(dev);
+		return PCI_ERS_RESULT_NEED_RESET;
+	case pci_channel_io_perm_failure:
+		dev_warn(&pdev->dev,
+			 "failure state error detected, request disconnect\n");
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_error_detected, "CXL");

linux-7.2.3/drivers/cxl/core/ras_rch.c

@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2025 AMD Corporation. All rights reserved. */
+
+#include <linux/types.h>
+#include <linux/aer.h>
+#include "cxl.h"
+#include "core.h"
+#include "cxlmem.h"
+
+void cxl_dport_map_rch_aer(struct cxl_dport *dport)
+{
+	resource_size_t aer_phys;
+	struct device *host;
+	u16 aer_cap;
+
+	aer_cap = cxl_rcrb_to_aer(dport->dport_dev, dport->rcrb.base);
+	if (aer_cap) {
+		host = dport->reg_map.host;
+		aer_phys = aer_cap + dport->rcrb.base;
+		dport->regs.dport_aer =
+			devm_cxl_iomap_block(host, aer_phys,
+					     sizeof(struct aer_capability_regs));
+	}
+}
+
+void cxl_disable_rch_root_ints(struct cxl_dport *dport)
+{
+	void __iomem *aer_base = dport->regs.dport_aer;
+	u32 aer_cmd_mask, aer_cmd;
+
+	if (!aer_base)
+		return;
+
+	/*
+	 * Disable RCH root port command interrupts.
+	 * CXL 3.0 12.2.1.1 - RCH Downstream Port-detected Errors
+	 *
+	 * This sequence may not be necessary. CXL spec states disabling
+	 * the root cmd register's interrupts is required. But, PCI spec
+	 * shows these are disabled by default on reset.
+	 */
+	aer_cmd_mask = (PCI_ERR_ROOT_CMD_COR_EN |
+			PCI_ERR_ROOT_CMD_NONFATAL_EN |
+			PCI_ERR_ROOT_CMD_FATAL_EN);
+	aer_cmd = readl(aer_base + PCI_ERR_ROOT_COMMAND);
+	aer_cmd &= ~aer_cmd_mask;
+	writel(aer_cmd, aer_base + PCI_ERR_ROOT_COMMAND);
+}
+
+/*
+ * Copy the AER capability registers using 32 bit read accesses.
+ * This is necessary because RCRB AER capability is MMIO mapped. Clear the
+ * status after copying.
+ *
+ * @aer_base: base address of AER capability block in RCRB
+ * @aer_regs: destination for copying AER capability
+ */
+static bool cxl_rch_get_aer_info(void __iomem *aer_base,
+				 struct aer_capability_regs *aer_regs)
+{
+	int read_cnt = sizeof(struct aer_capability_regs) / sizeof(u32);
+	u32 *aer_regs_buf = (u32 *)aer_regs;
+	int n;
+
+	if (!aer_base)
+		return false;
+
+	/* Use readl() to guarantee 32-bit accesses */
+	for (n = 0; n < read_cnt; n++)
+		aer_regs_buf[n] = readl(aer_base + n * sizeof(u32));
+
+	writel(aer_regs->uncor_status, aer_base + PCI_ERR_UNCOR_STATUS);
+	writel(aer_regs->cor_status, aer_base + PCI_ERR_COR_STATUS);
+
+	return true;
+}
+
+/* Get AER severity. Return false if there is no error. */
+static bool cxl_rch_get_aer_severity(struct aer_capability_regs *aer_regs,
+				     int *severity)
+{
+	if (aer_regs->uncor_status & ~aer_regs->uncor_mask) {
+		if (aer_regs->uncor_status & PCI_ERR_ROOT_FATAL_RCV)
+			*severity = AER_FATAL;
+		else
+			*severity = AER_NONFATAL;
+		return true;
+	}
+
+	if (aer_regs->cor_status & ~aer_regs->cor_mask) {
+		*severity = AER_CORRECTABLE;
+		return true;
+	}
+
+	return false;
+}
+
+void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds)
+{
+	struct pci_dev *pdev = to_pci_dev(cxlds->dev);
+	struct aer_capability_regs aer_regs;
+	struct cxl_dport *dport;
+	int severity;
+
+	struct cxl_port *port __free(put_cxl_port) =
+		cxl_pci_find_port(pdev, &dport);
+	if (!port)
+		return;
+
+	if (!cxl_rch_get_aer_info(dport->regs.dport_aer, &aer_regs))
+		return;
+
+	if (!cxl_rch_get_aer_severity(&aer_regs, &severity))
+		return;
+
+	pci_print_aer(pdev, severity, &aer_regs);
+	if (severity == AER_CORRECTABLE)
+		cxl_handle_cor_ras(&cxlds->cxlmd->dev, dport->regs.ras);
+	else
+		cxl_handle_ras(&cxlds->cxlmd->dev, dport->regs.ras);
+}

linux-7.2.3/drivers/cxl/core/region_dax.c

@@ -0,0 +1,106 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright(c) 2022 Intel Corporation. All rights reserved.
+ * Copyright(c) 2026 Meta Technologies Inc. All rights reserved.
+ */
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <cxlmem.h>
+#include <cxl.h>
+#include "core.h"
+
+static void cxl_dax_region_release(struct device *dev)
+{
+	struct cxl_dax_region *cxlr_dax = to_cxl_dax_region(dev);
+
+	kfree(cxlr_dax);
+}
+
+static const struct attribute_group *cxl_dax_region_attribute_groups[] = {
+	&cxl_base_attribute_group,
+	NULL
+};
+
+const struct device_type cxl_dax_region_type = {
+	.name = "cxl_dax_region",
+	.release = cxl_dax_region_release,
+	.groups = cxl_dax_region_attribute_groups,
+};
+
+static bool is_cxl_dax_region(struct device *dev)
+{
+	return dev->type == &cxl_dax_region_type;
+}
+
+struct cxl_dax_region *to_cxl_dax_region(struct device *dev)
+{
+	if (dev_WARN_ONCE(dev, !is_cxl_dax_region(dev),
+			  "not a cxl_dax_region device\n"))
+		return NULL;
+	return container_of(dev, struct cxl_dax_region, dev);
+}
+EXPORT_SYMBOL_NS_GPL(to_cxl_dax_region, "CXL");
+
+static struct lock_class_key cxl_dax_region_key;
+
+static struct cxl_dax_region *cxl_dax_region_alloc(struct cxl_region *cxlr)
+{
+	struct cxl_region_params *p = &cxlr->params;
+	struct cxl_dax_region *cxlr_dax;
+	struct device *dev;
+
+	guard(rwsem_read)(&cxl_rwsem.region);
+	if (p->state != CXL_CONFIG_COMMIT)
+		return ERR_PTR(-ENXIO);
+
+	cxlr_dax = kzalloc_obj(*cxlr_dax);
+	if (!cxlr_dax)
+		return ERR_PTR(-ENOMEM);
+
+	cxlr_dax->hpa_range.start = p->res->start;
+	cxlr_dax->hpa_range.end = p->res->end;
+
+	dev = &cxlr_dax->dev;
+	cxlr_dax->cxlr = cxlr;
+	device_initialize(dev);
+	lockdep_set_class(&dev->mutex, &cxl_dax_region_key);
+	device_set_pm_not_required(dev);
+	dev->parent = &cxlr->dev;
+	dev->bus = &cxl_bus_type;
+	dev->type = &cxl_dax_region_type;
+
+	return cxlr_dax;
+}
+
+static void cxlr_dax_unregister(void *_cxlr_dax)
+{
+	struct cxl_dax_region *cxlr_dax = _cxlr_dax;
+
+	device_unregister(&cxlr_dax->dev);
+}
+
+int devm_cxl_add_dax_region(struct cxl_region *cxlr)
+{
+	struct device *dev;
+	int rc;
+
+	struct cxl_dax_region *cxlr_dax __free(put_cxl_dax_region) =
+		cxl_dax_region_alloc(cxlr);
+	if (IS_ERR(cxlr_dax))
+		return PTR_ERR(cxlr_dax);
+
+	dev = &cxlr_dax->dev;
+	rc = dev_set_name(dev, "dax_region%d", cxlr->id);
+	if (rc)
+		return rc;
+
+	rc = device_add(dev);
+	if (rc)
+		return rc;
+
+	dev_dbg(&cxlr->dev, "%s: register %s\n", dev_name(dev->parent),
+		dev_name(dev));
+
+	return devm_add_action_or_reset(&cxlr->dev, cxlr_dax_unregister,
+					no_free_ptr(cxlr_dax));
+}

linux-7.2.3/drivers/cxl/core/region_pmem.c

@@ -0,0 +1,191 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <cxlmem.h>
+#include <cxl.h>
+#include "core.h"
+
+static void cxl_pmem_region_release(struct device *dev)
+{
+	struct cxl_pmem_region *cxlr_pmem = to_cxl_pmem_region(dev);
+	int i;
+
+	for (i = 0; i < cxlr_pmem->nr_mappings; i++) {
+		struct cxl_memdev *cxlmd = cxlr_pmem->mapping[i].cxlmd;
+
+		put_device(&cxlmd->dev);
+	}
+
+	kfree(cxlr_pmem);
+}
+
+static const struct attribute_group *cxl_pmem_region_attribute_groups[] = {
+	&cxl_base_attribute_group,
+	NULL
+};
+
+const struct device_type cxl_pmem_region_type = {
+	.name = "cxl_pmem_region",
+	.release = cxl_pmem_region_release,
+	.groups = cxl_pmem_region_attribute_groups,
+};
+
+bool is_cxl_pmem_region(struct device *dev)
+{
+	return dev->type == &cxl_pmem_region_type;
+}
+EXPORT_SYMBOL_NS_GPL(is_cxl_pmem_region, "CXL");
+
+struct cxl_pmem_region *to_cxl_pmem_region(struct device *dev)
+{
+	if (dev_WARN_ONCE(dev, !is_cxl_pmem_region(dev),
+			  "not a cxl_pmem_region device\n"))
+		return NULL;
+	return container_of(dev, struct cxl_pmem_region, dev);
+}
+EXPORT_SYMBOL_NS_GPL(to_cxl_pmem_region, "CXL");
+
+static struct lock_class_key cxl_pmem_region_key;
+
+static int cxl_pmem_region_alloc(struct cxl_region *cxlr)
+{
+	struct cxl_region_params *p = &cxlr->params;
+	struct cxl_nvdimm_bridge *cxl_nvb;
+	struct device *dev;
+	int i;
+
+	guard(rwsem_read)(&cxl_rwsem.region);
+	if (p->state != CXL_CONFIG_COMMIT)
+		return -ENXIO;
+
+	struct cxl_pmem_region *cxlr_pmem __free(kfree) =
+		kzalloc_flex(*cxlr_pmem, mapping, p->nr_targets);
+	if (!cxlr_pmem)
+		return -ENOMEM;
+
+	cxlr_pmem->hpa_range.start = p->res->start;
+	cxlr_pmem->hpa_range.end = p->res->end;
+
+	/* Snapshot the region configuration underneath the cxl_rwsem.region */
+	cxlr_pmem->nr_mappings = p->nr_targets;
+	for (i = 0; i < p->nr_targets; i++) {
+		struct cxl_endpoint_decoder *cxled = p->targets[i];
+		struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
+		struct cxl_pmem_region_mapping *m = &cxlr_pmem->mapping[i];
+
+		/*
+		 * Regions never span CXL root devices, so by definition the
+		 * bridge for one device is the same for all.
+		 */
+		if (i == 0) {
+			cxl_nvb = cxl_find_nvdimm_bridge(cxlmd->endpoint);
+			if (!cxl_nvb)
+				return -ENODEV;
+			cxlr->cxl_nvb = cxl_nvb;
+		}
+		m->cxlmd = cxlmd;
+		get_device(&cxlmd->dev);
+		m->start = cxled->dpa_res->start;
+		m->size = resource_size(cxled->dpa_res);
+		m->position = i;
+	}
+
+	dev = &cxlr_pmem->dev;
+	device_initialize(dev);
+	lockdep_set_class(&dev->mutex, &cxl_pmem_region_key);
+	device_set_pm_not_required(dev);
+	dev->parent = &cxlr->dev;
+	dev->bus = &cxl_bus_type;
+	dev->type = &cxl_pmem_region_type;
+	cxlr_pmem->cxlr = cxlr;
+	cxlr->cxlr_pmem = no_free_ptr(cxlr_pmem);
+
+	return 0;
+}
+
+static void cxlr_pmem_unregister(void *_cxlr_pmem)
+{
+	struct cxl_pmem_region *cxlr_pmem = _cxlr_pmem;
+	struct cxl_region *cxlr = cxlr_pmem->cxlr;
+	struct cxl_nvdimm_bridge *cxl_nvb = cxlr->cxl_nvb;
+
+	/*
+	 * Either the bridge is in ->remove() context under the device_lock(),
+	 * or cxlr_release_nvdimm() is cancelling the bridge's release action
+	 * for @cxlr_pmem and doing it itself (while manually holding the bridge
+	 * lock).
+	 */
+	device_lock_assert(&cxl_nvb->dev);
+	cxlr->cxlr_pmem = NULL;
+	cxlr_pmem->cxlr = NULL;
+	device_unregister(&cxlr_pmem->dev);
+}
+
+static void cxlr_release_nvdimm(void *_cxlr)
+{
+	struct cxl_region *cxlr = _cxlr;
+	struct cxl_nvdimm_bridge *cxl_nvb = cxlr->cxl_nvb;
+
+	scoped_guard(device, &cxl_nvb->dev) {
+		if (cxlr->cxlr_pmem)
+			devm_release_action(&cxl_nvb->dev, cxlr_pmem_unregister,
+					    cxlr->cxlr_pmem);
+	}
+	cxlr->cxl_nvb = NULL;
+	put_device(&cxl_nvb->dev);
+}
+
+/**
+ * devm_cxl_add_pmem_region() - add a cxl_region-to-nd_region bridge
+ * @cxlr: parent CXL region for this pmem region bridge device
+ *
+ * Return: 0 on success negative error code on failure.
+ */
+int devm_cxl_add_pmem_region(struct cxl_region *cxlr)
+{
+	struct cxl_pmem_region *cxlr_pmem;
+	struct cxl_nvdimm_bridge *cxl_nvb;
+	struct device *dev;
+	int rc;
+
+	rc = cxl_pmem_region_alloc(cxlr);
+	if (rc)
+		return rc;
+	cxlr_pmem = cxlr->cxlr_pmem;
+	cxl_nvb = cxlr->cxl_nvb;
+
+	dev = &cxlr_pmem->dev;
+	rc = dev_set_name(dev, "pmem_region%d", cxlr->id);
+	if (rc)
+		goto err;
+
+	rc = device_add(dev);
+	if (rc)
+		goto err;
+
+	dev_dbg(&cxlr->dev, "%s: register %s\n", dev_name(dev->parent),
+		dev_name(dev));
+
+	scoped_guard(device, &cxl_nvb->dev) {
+		if (cxl_nvb->dev.driver)
+			rc = devm_add_action_or_reset(&cxl_nvb->dev,
+						      cxlr_pmem_unregister,
+						      cxlr_pmem);
+		else
+			rc = -ENXIO;
+	}
+
+	if (rc)
+		goto err_bridge;
+
+	/* @cxlr carries a reference on @cxl_nvb until cxlr_release_nvdimm */
+	return devm_add_action_or_reset(&cxlr->dev, cxlr_release_nvdimm, cxlr);
+
+err:
+	put_device(dev);
+err_bridge:
+	put_device(&cxl_nvb->dev);
+	cxlr->cxl_nvb = NULL;
+	return rc;
+}

linux-7.2.3/drivers/cxl/core/regs.c

@@ -0,0 +1,643 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2020 Intel Corporation. */
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <cxlmem.h>
+#include <cxlpci.h>
+#include <pmu.h>
+
+#include "core.h"
+
+/**
+ * DOC: cxl registers
+ *
+ * CXL device capabilities are enumerated by PCI DVSEC (Designated
+ * Vendor-specific) and / or descriptors provided by platform firmware.
+ * They can be defined as a set like the device and component registers
+ * mandated by CXL Section 8.1.12.2 Memory Device PCIe Capabilities and
+ * Extended Capabilities, or they can be individual capabilities
+ * appended to bridged and endpoint devices.
+ *
+ * Provide common infrastructure for enumerating and mapping these
+ * discrete capabilities.
+ */
+
+/**
+ * cxl_probe_component_regs() - Detect CXL Component register blocks
+ * @dev: Host device of the @base mapping
+ * @base: Mapping containing the HDM Decoder Capability Header
+ * @map: Map object describing the register block information found
+ *
+ * See CXL 2.0 8.2.4 Component Register Layout and Definition
+ * See CXL 2.0 8.2.5.5 CXL Device Register Interface
+ *
+ * Probe for component register information and return it in map object.
+ */
+void cxl_probe_component_regs(struct device *dev, void __iomem *base,
+			      struct cxl_component_reg_map *map)
+{
+	int cap, cap_count;
+	u32 cap_array;
+
+	*map = (struct cxl_component_reg_map) { 0 };
+
+	/*
+	 * CXL.cache and CXL.mem registers are at offset 0x1000 as defined in
+	 * CXL 2.0 8.2.4 Table 141.
+	 */
+	base += CXL_CM_OFFSET;
+
+	cap_array = readl(base + CXL_CM_CAP_HDR_OFFSET);
+
+	if (FIELD_GET(CXL_CM_CAP_HDR_ID_MASK, cap_array) != CM_CAP_HDR_CAP_ID) {
+		dev_dbg(dev,
+			"Couldn't locate the CXL.cache and CXL.mem capability array header.\n");
+		return;
+	}
+
+	/* It's assumed that future versions will be backward compatible */
+	cap_count = FIELD_GET(CXL_CM_CAP_HDR_ARRAY_SIZE_MASK, cap_array);
+
+	for (cap = 1; cap <= cap_count; cap++) {
+		void __iomem *register_block;
+		struct cxl_reg_map *rmap;
+		u16 cap_id, offset;
+		u32 length, hdr;
+
+		hdr = readl(base + cap * 0x4);
+
+		cap_id = FIELD_GET(CXL_CM_CAP_HDR_ID_MASK, hdr);
+		offset = FIELD_GET(CXL_CM_CAP_PTR_MASK, hdr);
+		register_block = base + offset;
+		hdr = readl(register_block);
+
+		rmap = NULL;
+		switch (cap_id) {
+		case CXL_CM_CAP_CAP_ID_HDM: {
+			int decoder_cnt;
+
+			dev_dbg(dev, "found HDM decoder capability (0x%x)\n",
+				offset);
+
+			decoder_cnt = cxl_hdm_decoder_count(hdr);
+			length = 0x20 * decoder_cnt + 0x10;
+			rmap = &map->hdm_decoder;
+			break;
+		}
+		case CXL_CM_CAP_CAP_ID_RAS:
+			dev_dbg(dev, "found RAS capability (0x%x)\n",
+				offset);
+			length = CXL_RAS_CAPABILITY_LENGTH;
+			rmap = &map->ras;
+			break;
+		default:
+			dev_dbg(dev, "Unknown CM cap ID: %d (0x%x)\n", cap_id,
+				offset);
+			break;
+		}
+
+		if (!rmap)
+			continue;
+		rmap->valid = true;
+		rmap->id = cap_id;
+		rmap->offset = CXL_CM_OFFSET + offset;
+		rmap->size = length;
+	}
+}
+EXPORT_SYMBOL_NS_GPL(cxl_probe_component_regs, "CXL");
+
+/**
+ * cxl_probe_device_regs() - Detect CXL Device register blocks
+ * @dev: Host device of the @base mapping
+ * @base: Mapping of CXL 2.0 8.2.8 CXL Device Register Interface
+ * @map: Map object describing the register block information found
+ *
+ * Probe for device register information and return it in map object.
+ */
+void cxl_probe_device_regs(struct device *dev, void __iomem *base,
+			   struct cxl_device_reg_map *map)
+{
+	int cap, cap_count;
+	u64 cap_array;
+
+	*map = (struct cxl_device_reg_map){ 0 };
+
+	cap_array = readq(base + CXLDEV_CAP_ARRAY_OFFSET);
+	if (FIELD_GET(CXLDEV_CAP_ARRAY_ID_MASK, cap_array) !=
+	    CXLDEV_CAP_ARRAY_CAP_ID)
+		return;
+
+	cap_count = FIELD_GET(CXLDEV_CAP_ARRAY_COUNT_MASK, cap_array);
+
+	for (cap = 1; cap <= cap_count; cap++) {
+		struct cxl_reg_map *rmap;
+		u32 offset, length;
+		u16 cap_id;
+
+		cap_id = FIELD_GET(CXLDEV_CAP_HDR_CAP_ID_MASK,
+				   readl(base + cap * 0x10));
+		offset = readl(base + cap * 0x10 + 0x4);
+		length = readl(base + cap * 0x10 + 0x8);
+
+		rmap = NULL;
+		switch (cap_id) {
+		case CXLDEV_CAP_CAP_ID_DEVICE_STATUS:
+			dev_dbg(dev, "found Status capability (0x%x)\n", offset);
+			rmap = &map->status;
+			break;
+		case CXLDEV_CAP_CAP_ID_PRIMARY_MAILBOX:
+			dev_dbg(dev, "found Mailbox capability (0x%x)\n", offset);
+			rmap = &map->mbox;
+			break;
+		case CXLDEV_CAP_CAP_ID_SECONDARY_MAILBOX:
+			dev_dbg(dev, "found Secondary Mailbox capability (0x%x)\n", offset);
+			break;
+		case CXLDEV_CAP_CAP_ID_MEMDEV:
+			dev_dbg(dev, "found Memory Device capability (0x%x)\n", offset);
+			rmap = &map->memdev;
+			break;
+		default:
+			if (cap_id >= 0x8000)
+				dev_dbg(dev, "Vendor cap ID: %#x offset: %#x\n", cap_id, offset);
+			else
+				dev_dbg(dev, "Unknown cap ID: %#x offset: %#x\n", cap_id, offset);
+			break;
+		}
+
+		if (!rmap)
+			continue;
+		rmap->valid = true;
+		rmap->id = cap_id;
+		rmap->offset = offset;
+		rmap->size = length;
+	}
+}
+EXPORT_SYMBOL_NS_GPL(cxl_probe_device_regs, "CXL");
+
+void __iomem *devm_cxl_iomap_block(struct device *dev, resource_size_t addr,
+				   resource_size_t length)
+{
+	void __iomem *ret_val;
+	struct resource *res;
+
+	if (WARN_ON_ONCE(addr == CXL_RESOURCE_NONE))
+		return NULL;
+
+	res = devm_request_mem_region(dev, addr, length, dev_name(dev));
+	if (!res) {
+		resource_size_t end = addr + length - 1;
+
+		dev_err(dev, "Failed to request region %pa-%pa\n", &addr, &end);
+		return NULL;
+	}
+
+	ret_val = devm_ioremap(dev, addr, length);
+	if (!ret_val)
+		dev_err(dev, "Failed to map region %pr\n", res);
+
+	return ret_val;
+}
+
+int cxl_map_component_regs(const struct cxl_register_map *map,
+			   struct cxl_component_regs *regs,
+			   unsigned long map_mask)
+{
+	struct device *host = map->host;
+	struct mapinfo {
+		const struct cxl_reg_map *rmap;
+		void __iomem **addr;
+	} mapinfo[] = {
+		{ &map->component_map.hdm_decoder, &regs->hdm_decoder },
+		{ &map->component_map.ras, &regs->ras },
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(mapinfo); i++) {
+		struct mapinfo *mi = &mapinfo[i];
+		resource_size_t addr;
+		resource_size_t length;
+
+		if (!mi->rmap->valid)
+			continue;
+		if (!test_bit(mi->rmap->id, &map_mask))
+			continue;
+		addr = map->resource + mi->rmap->offset;
+		length = mi->rmap->size;
+		*(mi->addr) = devm_cxl_iomap_block(host, addr, length);
+		if (!*(mi->addr))
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_map_component_regs, "CXL");
+
+int cxl_map_device_regs(const struct cxl_register_map *map,
+			struct cxl_device_regs *regs)
+{
+	struct device *host = map->host;
+	resource_size_t phys_addr = map->resource;
+	struct mapinfo {
+		const struct cxl_reg_map *rmap;
+		void __iomem **addr;
+	} mapinfo[] = {
+		{ &map->device_map.status, &regs->status, },
+		{ &map->device_map.mbox, &regs->mbox, },
+		{ &map->device_map.memdev, &regs->memdev, },
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(mapinfo); i++) {
+		struct mapinfo *mi = &mapinfo[i];
+		resource_size_t length;
+		resource_size_t addr;
+
+		if (!mi->rmap->valid)
+			continue;
+
+		addr = phys_addr + mi->rmap->offset;
+		length = mi->rmap->size;
+		*(mi->addr) = devm_cxl_iomap_block(host, addr, length);
+		if (!*(mi->addr))
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_map_device_regs, "CXL");
+
+static bool cxl_decode_regblock(struct pci_dev *pdev, u32 reg_lo, u32 reg_hi,
+				struct cxl_register_map *map)
+{
+	u8 reg_type = FIELD_GET(PCI_DVSEC_CXL_REG_LOCATOR_BLOCK_ID, reg_lo);
+	int bar = FIELD_GET(PCI_DVSEC_CXL_REG_LOCATOR_BIR, reg_lo);
+	u64 offset = ((u64)reg_hi << 32) |
+		     (reg_lo & PCI_DVSEC_CXL_REG_LOCATOR_BLOCK_OFF_LOW);
+
+	if (offset > pci_resource_len(pdev, bar)) {
+		dev_warn(&pdev->dev,
+			 "BAR%d: %pr: too small (offset: %pa, type: %d)\n", bar,
+			 &pdev->resource[bar], &offset, reg_type);
+		return false;
+	}
+
+	map->reg_type = reg_type;
+	map->resource = pci_resource_start(pdev, bar) + offset;
+	map->max_size = pci_resource_len(pdev, bar) - offset;
+	return true;
+}
+
+/*
+ * __cxl_find_regblock_instance() - Locate a register block or count instances by type / index
+ * Use CXL_INSTANCES_COUNT for @index if counting instances.
+ *
+ * __cxl_find_regblock_instance() may return:
+ * 0 - if register block enumerated.
+ * >= 0 - if counting instances.
+ * < 0 - error code otherwise.
+ */
+static int __cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type,
+					struct cxl_register_map *map, int index)
+{
+	u32 regloc_size, regblocks;
+	int instance = 0;
+	int regloc, i;
+
+	*map = (struct cxl_register_map) {
+		.host = &pdev->dev,
+		.resource = CXL_RESOURCE_NONE,
+	};
+
+	regloc = pci_find_dvsec_capability(pdev, PCI_VENDOR_ID_CXL,
+					   PCI_DVSEC_CXL_REG_LOCATOR);
+	if (!regloc)
+		return -ENXIO;
+
+	pci_read_config_dword(pdev, regloc + PCI_DVSEC_HEADER1, &regloc_size);
+	regloc_size = PCI_DVSEC_HEADER1_LEN(regloc_size);
+
+	regloc += PCI_DVSEC_CXL_REG_LOCATOR_BLOCK1;
+	regblocks = (regloc_size - PCI_DVSEC_CXL_REG_LOCATOR_BLOCK1) / 8;
+
+	for (i = 0; i < regblocks; i++, regloc += 8) {
+		u32 reg_lo, reg_hi;
+
+		pci_read_config_dword(pdev, regloc, &reg_lo);
+		pci_read_config_dword(pdev, regloc + 4, &reg_hi);
+
+		if (!cxl_decode_regblock(pdev, reg_lo, reg_hi, map))
+			continue;
+
+		if (map->reg_type == type) {
+			if (index == instance)
+				return 0;
+			instance++;
+		}
+	}
+
+	map->resource = CXL_RESOURCE_NONE;
+	if (index == CXL_INSTANCES_COUNT)
+		return instance;
+
+	return -ENODEV;
+}
+
+/**
+ * cxl_find_regblock_instance() - Locate a register block by type / index
+ * @pdev: The CXL PCI device to enumerate.
+ * @type: Register Block Indicator id
+ * @map: Enumeration output, clobbered on error
+ * @index: Index into which particular instance of a regblock wanted in the
+ *	   order found in register locator DVSEC.
+ *
+ * Return: 0 if register block enumerated, negative error code otherwise
+ *
+ * A CXL DVSEC may point to one or more register blocks, search for them
+ * by @type and @index.
+ */
+int cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type,
+			       struct cxl_register_map *map, unsigned int index)
+{
+	return __cxl_find_regblock_instance(pdev, type, map, index);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_find_regblock_instance, "CXL");
+
+/**
+ * cxl_find_regblock() - Locate register blocks by type
+ * @pdev: The CXL PCI device to enumerate.
+ * @type: Register Block Indicator id
+ * @map: Enumeration output, clobbered on error
+ *
+ * Return: 0 if register block enumerated, negative error code otherwise
+ *
+ * A CXL DVSEC may point to one or more register blocks, search for them
+ * by @type.
+ */
+int cxl_find_regblock(struct pci_dev *pdev, enum cxl_regloc_type type,
+		      struct cxl_register_map *map)
+{
+	return __cxl_find_regblock_instance(pdev, type, map, 0);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_find_regblock, "CXL");
+
+/**
+ * cxl_count_regblock() - Count instances of a given regblock type.
+ * @pdev: The CXL PCI device to enumerate.
+ * @type: Register Block Indicator id
+ *
+ * Some regblocks may be repeated. Count how many instances.
+ *
+ * Return: non-negative count of matching regblocks, negative error code otherwise.
+ */
+int cxl_count_regblock(struct pci_dev *pdev, enum cxl_regloc_type type)
+{
+	struct cxl_register_map map;
+
+	return __cxl_find_regblock_instance(pdev, type, &map, CXL_INSTANCES_COUNT);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_count_regblock, "CXL");
+
+int cxl_map_pmu_regs(struct cxl_register_map *map, struct cxl_pmu_regs *regs)
+{
+	struct device *dev = map->host;
+	resource_size_t phys_addr;
+
+	phys_addr = map->resource;
+	regs->pmu = devm_cxl_iomap_block(dev, phys_addr, CXL_PMU_REGMAP_SIZE);
+	if (!regs->pmu)
+		return -ENOMEM;
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_map_pmu_regs, "CXL");
+
+static int cxl_map_regblock(struct cxl_register_map *map)
+{
+	struct device *host = map->host;
+
+	map->base = ioremap(map->resource, map->max_size);
+	if (!map->base) {
+		dev_err(host, "failed to map registers\n");
+		return -ENOMEM;
+	}
+
+	dev_dbg(host, "Mapped CXL Memory Device resource %pa\n", &map->resource);
+	return 0;
+}
+
+static void cxl_unmap_regblock(struct cxl_register_map *map)
+{
+	iounmap(map->base);
+	map->base = NULL;
+}
+
+static int cxl_probe_regs(struct cxl_register_map *map)
+{
+	struct cxl_component_reg_map *comp_map;
+	struct cxl_device_reg_map *dev_map;
+	struct device *host = map->host;
+	void __iomem *base = map->base;
+
+	switch (map->reg_type) {
+	case CXL_REGLOC_RBI_COMPONENT:
+		comp_map = &map->component_map;
+		cxl_probe_component_regs(host, base, comp_map);
+		dev_dbg(host, "Set up component registers\n");
+		break;
+	case CXL_REGLOC_RBI_MEMDEV:
+		dev_map = &map->device_map;
+		cxl_probe_device_regs(host, base, dev_map);
+		if (!dev_map->status.valid || !dev_map->mbox.valid ||
+		    !dev_map->memdev.valid) {
+			dev_err(host, "registers not found: %s%s%s\n",
+				!dev_map->status.valid ? "status " : "",
+				!dev_map->mbox.valid ? "mbox " : "",
+				!dev_map->memdev.valid ? "memdev " : "");
+			return -ENXIO;
+		}
+
+		dev_dbg(host, "Probing device registers...\n");
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+int cxl_setup_regs(struct cxl_register_map *map)
+{
+	int rc;
+
+	rc = cxl_map_regblock(map);
+	if (rc)
+		return rc;
+
+	rc = cxl_probe_regs(map);
+	cxl_unmap_regblock(map);
+
+	return rc;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_setup_regs, "CXL");
+
+u16 cxl_rcrb_to_aer(struct device *dev, resource_size_t rcrb)
+{
+	void __iomem *addr;
+	u16 offset = 0;
+	u32 cap_hdr;
+
+	if (WARN_ON_ONCE(rcrb == CXL_RESOURCE_NONE))
+		return 0;
+
+	if (!request_mem_region(rcrb, SZ_4K, dev_name(dev)))
+		return 0;
+
+	addr = ioremap(rcrb, SZ_4K);
+	if (!addr)
+		goto out;
+
+	cap_hdr = readl(addr + offset);
+	while (PCI_EXT_CAP_ID(cap_hdr) != PCI_EXT_CAP_ID_ERR) {
+		offset = PCI_EXT_CAP_NEXT(cap_hdr);
+
+		/* Offset 0 terminates capability list. */
+		if (!offset)
+			break;
+		cap_hdr = readl(addr + offset);
+	}
+
+	if (offset)
+		dev_dbg(dev, "found AER extended capability (0x%x)\n", offset);
+
+	iounmap(addr);
+out:
+	release_mem_region(rcrb, SZ_4K);
+
+	return offset;
+}
+
+static resource_size_t cxl_rcrb_to_linkcap(struct device *dev, struct cxl_dport *dport)
+{
+	resource_size_t rcrb = dport->rcrb.base;
+	void __iomem *addr;
+	u32 cap_hdr;
+	u16 offset;
+
+	if (!request_mem_region(rcrb, SZ_4K, "CXL RCRB"))
+		return CXL_RESOURCE_NONE;
+
+	addr = ioremap(rcrb, SZ_4K);
+	if (!addr) {
+		dev_err(dev, "Failed to map region %pr\n", addr);
+		release_mem_region(rcrb, SZ_4K);
+		return CXL_RESOURCE_NONE;
+	}
+
+	offset = FIELD_GET(PCI_RCRB_CAP_LIST_ID_MASK, readw(addr + PCI_CAPABILITY_LIST));
+	cap_hdr = readl(addr + offset);
+	while ((FIELD_GET(PCI_RCRB_CAP_HDR_ID_MASK, cap_hdr)) != PCI_CAP_ID_EXP) {
+		offset = FIELD_GET(PCI_RCRB_CAP_HDR_NEXT_MASK, cap_hdr);
+		if (offset == 0 || offset > SZ_4K) {
+			offset = 0;
+			break;
+		}
+		cap_hdr = readl(addr + offset);
+	}
+
+	iounmap(addr);
+	release_mem_region(rcrb, SZ_4K);
+	if (!offset)
+		return CXL_RESOURCE_NONE;
+
+	return offset;
+}
+
+int cxl_dport_map_rcd_linkcap(struct pci_dev *pdev, struct cxl_dport *dport)
+{
+	void __iomem *dport_pcie_cap = NULL;
+	resource_size_t pos;
+	struct cxl_rcrb_info *ri;
+
+	ri = &dport->rcrb;
+	pos = cxl_rcrb_to_linkcap(&pdev->dev, dport);
+	if (pos == CXL_RESOURCE_NONE)
+		return -ENXIO;
+
+	dport_pcie_cap = devm_cxl_iomap_block(&pdev->dev,
+					      ri->base + pos,
+					      PCI_CAP_EXP_SIZEOF);
+	dport->regs.rcd_pcie_cap = dport_pcie_cap;
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_dport_map_rcd_linkcap, "CXL");
+
+resource_size_t __rcrb_to_component(struct device *dev, struct cxl_rcrb_info *ri,
+				    enum cxl_rcrb which)
+{
+	resource_size_t component_reg_phys;
+	resource_size_t rcrb = ri->base;
+	void __iomem *addr;
+	u32 bar0, bar1;
+	u32 id;
+
+	if (which == CXL_RCRB_UPSTREAM)
+		rcrb += SZ_4K;
+
+	/*
+	 * RCRB's BAR[0..1] point to component block containing CXL
+	 * subsystem component registers. MEMBAR extraction follows
+	 * the PCI Base spec here, esp. 64 bit extraction and memory
+	 * ranges alignment (6.0, 7.5.1.2.1).
+	 */
+	if (!request_mem_region(rcrb, SZ_4K, "CXL RCRB"))
+		return CXL_RESOURCE_NONE;
+	addr = ioremap(rcrb, SZ_4K);
+	if (!addr) {
+		dev_err(dev, "Failed to map region %pr\n", addr);
+		release_mem_region(rcrb, SZ_4K);
+		return CXL_RESOURCE_NONE;
+	}
+
+	id = readl(addr + PCI_VENDOR_ID);
+	bar0 = readl(addr + PCI_BASE_ADDRESS_0);
+	bar1 = readl(addr + PCI_BASE_ADDRESS_1);
+	iounmap(addr);
+	release_mem_region(rcrb, SZ_4K);
+
+	/*
+	 * Sanity check, see CXL 3.0 Figure 9-8 CXL Device that Does Not
+	 * Remap Upstream Port and Component Registers
+	 */
+	if (id == U32_MAX) {
+		if (which == CXL_RCRB_DOWNSTREAM)
+			dev_err(dev, "Failed to access Downstream Port RCRB\n");
+		return CXL_RESOURCE_NONE;
+	}
+	/* The RCRB is a Memory Window, and the MEM_TYPE_1M bit is obsolete */
+	if (bar0 & (PCI_BASE_ADDRESS_MEM_TYPE_1M | PCI_BASE_ADDRESS_SPACE_IO))
+		return CXL_RESOURCE_NONE;
+
+	component_reg_phys = bar0 & PCI_BASE_ADDRESS_MEM_MASK;
+	if (bar0 & PCI_BASE_ADDRESS_MEM_TYPE_64)
+		component_reg_phys |= ((u64)bar1) << 32;
+
+	if (!component_reg_phys)
+		return CXL_RESOURCE_NONE;
+
+	/* MEMBAR is block size (64k) aligned. */
+	if (!IS_ALIGNED(component_reg_phys, CXL_COMPONENT_REG_BLOCK_SIZE))
+		return CXL_RESOURCE_NONE;
+
+	return component_reg_phys;
+}
+
+resource_size_t cxl_rcd_component_reg_phys(struct device *dev,
+					   struct cxl_dport *dport)
+{
+	if (!dport->rch)
+		return CXL_RESOURCE_NONE;
+	return __rcrb_to_component(dev, &dport->rcrb, CXL_RCRB_UPSTREAM);
+}

linux-7.2.3/drivers/cxl/core/suspend.c

@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+#include <linux/atomic.h>
+#include <linux/export.h>
+#include "cxlmem.h"
+
+static atomic_t mem_active;
+
+bool cxl_mem_active(void)
+{
+	return atomic_read(&mem_active) != 0;
+}
+
+void cxl_mem_active_inc(void)
+{
+	atomic_inc(&mem_active);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_mem_active_inc, "CXL");
+
+void cxl_mem_active_dec(void)
+{
+	atomic_dec(&mem_active);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_mem_active_dec, "CXL");

linux-7.2.3/drivers/cxl/core/trace.c

@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+
+#include <cxl.h>
+#include "core.h"
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"

linux-7.2.3/drivers/cxl/cxl.h

@@ -0,0 +1,932 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2020 Intel Corporation. */
+
+#ifndef __CXL_H__
+#define __CXL_H__
+
+#include <linux/libnvdimm.h>
+#include <linux/bitfield.h>
+#include <linux/notifier.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+#include <linux/node.h>
+#include <linux/io.h>
+#include <linux/range.h>
+#include <cxl/cxl.h>
+
+extern const struct nvdimm_security_ops *cxl_security_ops;
+
+/**
+ * DOC: cxl objects
+ *
+ * The CXL core objects like ports, decoders, and regions are shared
+ * between the subsystem drivers cxl_acpi, cxl_pci, and core drivers
+ * (port-driver, region-driver, nvdimm object-drivers... etc).
+ */
+
+/* CXL 2.0 8.2.4 CXL Component Register Layout and Definition */
+#define CXL_COMPONENT_REG_BLOCK_SIZE SZ_64K
+
+/* CXL 2.0 8.2.5 CXL.cache and CXL.mem Registers*/
+#define CXL_CM_OFFSET 0x1000
+#define CXL_CM_CAP_HDR_OFFSET 0x0
+#define   CXL_CM_CAP_HDR_ID_MASK GENMASK(15, 0)
+#define     CM_CAP_HDR_CAP_ID 1
+#define   CXL_CM_CAP_HDR_VERSION_MASK GENMASK(19, 16)
+#define     CM_CAP_HDR_CAP_VERSION 1
+#define   CXL_CM_CAP_HDR_CACHE_MEM_VERSION_MASK GENMASK(23, 20)
+#define     CM_CAP_HDR_CACHE_MEM_VERSION 1
+#define   CXL_CM_CAP_HDR_ARRAY_SIZE_MASK GENMASK(31, 24)
+#define CXL_CM_CAP_PTR_MASK GENMASK(31, 20)
+
+#define   CXL_CM_CAP_CAP_ID_RAS 0x2
+#define   CXL_CM_CAP_CAP_ID_HDM 0x5
+#define   CXL_CM_CAP_CAP_HDM_VERSION 1
+
+/* HDM decoders CXL 2.0 8.2.5.12 CXL HDM Decoder Capability Structure */
+#define CXL_HDM_DECODER_CAP_OFFSET 0x0
+#define   CXL_HDM_DECODER_COUNT_MASK GENMASK(3, 0)
+#define   CXL_HDM_DECODER_TARGET_COUNT_MASK GENMASK(7, 4)
+#define   CXL_HDM_DECODER_INTERLEAVE_11_8 BIT(8)
+#define   CXL_HDM_DECODER_INTERLEAVE_14_12 BIT(9)
+#define   CXL_HDM_DECODER_INTERLEAVE_3_6_12_WAY BIT(11)
+#define   CXL_HDM_DECODER_INTERLEAVE_16_WAY BIT(12)
+#define CXL_HDM_DECODER_CTRL_OFFSET 0x4
+#define   CXL_HDM_DECODER_ENABLE BIT(1)
+#define CXL_HDM_DECODER0_BASE_LOW_OFFSET(i) (0x20 * (i) + 0x10)
+#define CXL_HDM_DECODER0_BASE_HIGH_OFFSET(i) (0x20 * (i) + 0x14)
+#define CXL_HDM_DECODER0_SIZE_LOW_OFFSET(i) (0x20 * (i) + 0x18)
+#define CXL_HDM_DECODER0_SIZE_HIGH_OFFSET(i) (0x20 * (i) + 0x1c)
+#define CXL_HDM_DECODER0_CTRL_OFFSET(i) (0x20 * (i) + 0x20)
+#define   CXL_HDM_DECODER0_CTRL_IG_MASK GENMASK(3, 0)
+#define   CXL_HDM_DECODER0_CTRL_IW_MASK GENMASK(7, 4)
+#define   CXL_HDM_DECODER0_CTRL_LOCK BIT(8)
+#define   CXL_HDM_DECODER0_CTRL_COMMIT BIT(9)
+#define   CXL_HDM_DECODER0_CTRL_COMMITTED BIT(10)
+#define   CXL_HDM_DECODER0_CTRL_COMMIT_ERROR BIT(11)
+#define   CXL_HDM_DECODER0_CTRL_HOSTONLY BIT(12)
+#define CXL_HDM_DECODER0_TL_LOW(i) (0x20 * (i) + 0x24)
+#define CXL_HDM_DECODER0_TL_HIGH(i) (0x20 * (i) + 0x28)
+#define CXL_HDM_DECODER0_SKIP_LOW(i) CXL_HDM_DECODER0_TL_LOW(i)
+#define CXL_HDM_DECODER0_SKIP_HIGH(i) CXL_HDM_DECODER0_TL_HIGH(i)
+
+/* HDM decoder control register constants CXL 3.0 8.2.5.19.7 */
+#define CXL_DECODER_MIN_GRANULARITY 256
+#define CXL_DECODER_MAX_ENCODED_IG 6
+
+static inline int cxl_hdm_decoder_count(u32 cap_hdr)
+{
+	int val = FIELD_GET(CXL_HDM_DECODER_COUNT_MASK, cap_hdr);
+
+	switch (val) {
+	case 0:
+		return 1;
+	case 1 ... 8:
+		return val * 2;
+	case 9 ... 12:
+		return (val - 4) * 4;
+	default:
+		return -ENXIO;
+	}
+}
+
+/* Encode defined in CXL 2.0 8.2.5.12.7 HDM Decoder Control Register */
+static inline int eig_to_granularity(u16 eig, int *granularity)
+{
+	if (eig > CXL_DECODER_MAX_ENCODED_IG)
+		return -EINVAL;
+	*granularity = CXL_DECODER_MIN_GRANULARITY << eig;
+	return 0;
+}
+
+/* Encode defined in CXL ECN "3, 6, 12 and 16-way memory Interleaving" */
+static inline int eiw_to_ways(u8 eiw, int *ways)
+{
+	switch (eiw) {
+	case 0 ... 4:
+		*ways = 1 << eiw;
+		break;
+	case 8 ... 10:
+		*ways = 3 << (eiw - 8);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static inline int granularity_to_eig(int granularity, u16 *eig)
+{
+	*eig = 0;
+	if (granularity > SZ_16K || granularity < CXL_DECODER_MIN_GRANULARITY ||
+	    !is_power_of_2(granularity))
+		return -EINVAL;
+	*eig = ilog2(granularity) - 8;
+	return 0;
+}
+
+static inline int ways_to_eiw(unsigned int ways, u8 *eiw)
+{
+	*eiw = 0;
+	if (ways > 16)
+		return -EINVAL;
+	if (is_power_of_2(ways)) {
+		*eiw = ilog2(ways);
+		return 0;
+	}
+	if (ways % 3)
+		return -EINVAL;
+	ways /= 3;
+	if (!is_power_of_2(ways))
+		return -EINVAL;
+	*eiw = ilog2(ways) + 8;
+	return 0;
+}
+
+/* RAS Registers CXL 2.0 8.2.5.9 CXL RAS Capability Structure */
+#define CXL_RAS_UNCORRECTABLE_STATUS_OFFSET 0x0
+#define   CXL_RAS_UNCORRECTABLE_STATUS_MASK (GENMASK(16, 14) | GENMASK(11, 0))
+#define CXL_RAS_UNCORRECTABLE_MASK_OFFSET 0x4
+#define   CXL_RAS_UNCORRECTABLE_MASK_MASK (GENMASK(16, 14) | GENMASK(11, 0))
+#define   CXL_RAS_UNCORRECTABLE_MASK_F256B_MASK BIT(8)
+#define CXL_RAS_UNCORRECTABLE_SEVERITY_OFFSET 0x8
+#define   CXL_RAS_UNCORRECTABLE_SEVERITY_MASK (GENMASK(16, 14) | GENMASK(11, 0))
+#define CXL_RAS_CORRECTABLE_STATUS_OFFSET 0xC
+#define   CXL_RAS_CORRECTABLE_STATUS_MASK GENMASK(6, 0)
+#define CXL_RAS_CORRECTABLE_MASK_OFFSET 0x10
+#define   CXL_RAS_CORRECTABLE_MASK_MASK GENMASK(6, 0)
+#define CXL_RAS_CAP_CONTROL_OFFSET 0x14
+#define CXL_RAS_CAP_CONTROL_FE_MASK GENMASK(5, 0)
+#define CXL_RAS_HEADER_LOG_OFFSET 0x18
+#define CXL_RAS_CAPABILITY_LENGTH 0x58
+#define CXL_HEADERLOG_SIZE SZ_64
+#define CXL_HEADERLOG_SIZE_U32 (CXL_HEADERLOG_SIZE / sizeof(u32))
+
+/*
+ * The RAS UCE trace event header array was originally sized at SZ_512/sizeof(u32)
+ * = 128 u32s due to a bug. Userspace tools (rasdaemon) have grown a dependency
+ * on that 512-byte layout. Keep the trace array at 128 u32s to preserve the
+ * ABI; only CXL_HEADERLOG_SIZE_U32 (16) dwords are valid hardware data, the
+ * remainder are zero-filled.
+ */
+#define CXL_HEADERLOG_TRACE_SIZE SZ_512
+#define CXL_HEADERLOG_TRACE_SIZE_U32 (CXL_HEADERLOG_TRACE_SIZE / sizeof(u32))
+
+/* CXL 2.0 8.2.8.1 Device Capabilities Array Register */
+#define CXLDEV_CAP_ARRAY_OFFSET 0x0
+#define   CXLDEV_CAP_ARRAY_CAP_ID 0
+#define   CXLDEV_CAP_ARRAY_ID_MASK GENMASK_ULL(15, 0)
+#define   CXLDEV_CAP_ARRAY_COUNT_MASK GENMASK_ULL(47, 32)
+/* CXL 2.0 8.2.8.2 CXL Device Capability Header Register */
+#define CXLDEV_CAP_HDR_CAP_ID_MASK GENMASK(15, 0)
+/* CXL 2.0 8.2.8.2.1 CXL Device Capabilities */
+#define CXLDEV_CAP_CAP_ID_DEVICE_STATUS 0x1
+#define CXLDEV_CAP_CAP_ID_PRIMARY_MAILBOX 0x2
+#define CXLDEV_CAP_CAP_ID_SECONDARY_MAILBOX 0x3
+#define CXLDEV_CAP_CAP_ID_MEMDEV 0x4000
+
+/* CXL 3.0 8.2.8.3.1 Event Status Register */
+#define CXLDEV_DEV_EVENT_STATUS_OFFSET		0x00
+#define CXLDEV_EVENT_STATUS_INFO		BIT(0)
+#define CXLDEV_EVENT_STATUS_WARN		BIT(1)
+#define CXLDEV_EVENT_STATUS_FAIL		BIT(2)
+#define CXLDEV_EVENT_STATUS_FATAL		BIT(3)
+
+#define CXLDEV_EVENT_STATUS_ALL (CXLDEV_EVENT_STATUS_INFO |	\
+				 CXLDEV_EVENT_STATUS_WARN |	\
+				 CXLDEV_EVENT_STATUS_FAIL |	\
+				 CXLDEV_EVENT_STATUS_FATAL)
+
+/* CXL rev 3.0 section 8.2.9.2.4; Table 8-52 */
+#define CXLDEV_EVENT_INT_MODE_MASK	GENMASK(1, 0)
+#define CXLDEV_EVENT_INT_MSGNUM_MASK	GENMASK(7, 4)
+
+/* CXL 2.0 8.2.8.4 Mailbox Registers */
+#define CXLDEV_MBOX_CAPS_OFFSET 0x00
+#define   CXLDEV_MBOX_CAP_PAYLOAD_SIZE_MASK GENMASK(4, 0)
+#define   CXLDEV_MBOX_CAP_BG_CMD_IRQ BIT(6)
+#define   CXLDEV_MBOX_CAP_IRQ_MSGNUM_MASK GENMASK(10, 7)
+#define CXLDEV_MBOX_CTRL_OFFSET 0x04
+#define   CXLDEV_MBOX_CTRL_DOORBELL BIT(0)
+#define   CXLDEV_MBOX_CTRL_BG_CMD_IRQ BIT(2)
+#define CXLDEV_MBOX_CMD_OFFSET 0x08
+#define   CXLDEV_MBOX_CMD_COMMAND_OPCODE_MASK GENMASK_ULL(15, 0)
+#define   CXLDEV_MBOX_CMD_PAYLOAD_LENGTH_MASK GENMASK_ULL(36, 16)
+#define CXLDEV_MBOX_STATUS_OFFSET 0x10
+#define   CXLDEV_MBOX_STATUS_BG_CMD BIT(0)
+#define   CXLDEV_MBOX_STATUS_RET_CODE_MASK GENMASK_ULL(47, 32)
+#define CXLDEV_MBOX_BG_CMD_STATUS_OFFSET 0x18
+#define   CXLDEV_MBOX_BG_CMD_COMMAND_OPCODE_MASK GENMASK_ULL(15, 0)
+#define   CXLDEV_MBOX_BG_CMD_COMMAND_PCT_MASK GENMASK_ULL(22, 16)
+#define   CXLDEV_MBOX_BG_CMD_COMMAND_RC_MASK GENMASK_ULL(47, 32)
+#define   CXLDEV_MBOX_BG_CMD_COMMAND_VENDOR_MASK GENMASK_ULL(63, 48)
+#define CXLDEV_MBOX_PAYLOAD_OFFSET 0x20
+
+void cxl_probe_component_regs(struct device *dev, void __iomem *base,
+			      struct cxl_component_reg_map *map);
+void cxl_probe_device_regs(struct device *dev, void __iomem *base,
+			   struct cxl_device_reg_map *map);
+int cxl_map_component_regs(const struct cxl_register_map *map,
+			   struct cxl_component_regs *regs,
+			   unsigned long map_mask);
+int cxl_map_device_regs(const struct cxl_register_map *map,
+			struct cxl_device_regs *regs);
+int cxl_map_pmu_regs(struct cxl_register_map *map, struct cxl_pmu_regs *regs);
+
+#define CXL_INSTANCES_COUNT -1
+enum cxl_regloc_type;
+int cxl_count_regblock(struct pci_dev *pdev, enum cxl_regloc_type type);
+int cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type,
+			       struct cxl_register_map *map, unsigned int index);
+int cxl_find_regblock(struct pci_dev *pdev, enum cxl_regloc_type type,
+		      struct cxl_register_map *map);
+int cxl_setup_regs(struct cxl_register_map *map);
+struct cxl_dport;
+int cxl_dport_map_rcd_linkcap(struct pci_dev *pdev, struct cxl_dport *dport);
+
+#define CXL_RESOURCE_NONE ((resource_size_t) -1)
+#define CXL_TARGET_STRLEN 20
+
+/*
+ * cxl_decoder flags that define the type of memory / devices this
+ * decoder supports as well as configuration lock status See "CXL 2.0
+ * 8.2.5.12.7 CXL HDM Decoder 0 Control Register" for details.
+ * Additionally indicate whether decoder settings were autodetected,
+ * user customized.
+ */
+#define CXL_DECODER_F_RAM   BIT(0)
+#define CXL_DECODER_F_PMEM  BIT(1)
+#define CXL_DECODER_F_TYPE2 BIT(2)
+#define CXL_DECODER_F_TYPE3 BIT(3)
+#define CXL_DECODER_F_LOCK  BIT(4)
+#define CXL_DECODER_F_ENABLE    BIT(5)
+#define CXL_DECODER_F_NORMALIZED_ADDRESSING BIT(6)
+#define CXL_DECODER_F_RESET_MASK (CXL_DECODER_F_ENABLE | CXL_DECODER_F_LOCK)
+
+enum cxl_decoder_type {
+	CXL_DECODER_DEVMEM = 2,
+	CXL_DECODER_HOSTONLYMEM = 3,
+};
+
+/*
+ * Current specification goes up to 8, double that seems a reasonable
+ * software max for the foreseeable future
+ */
+#define CXL_DECODER_MAX_INTERLEAVE 16
+
+#define CXL_QOS_CLASS_INVALID -1
+
+/**
+ * struct cxl_decoder - Common CXL HDM Decoder Attributes
+ * @dev: this decoder's device
+ * @id: kernel device name id
+ * @hpa_range: Host physical address range mapped by this decoder
+ * @interleave_ways: number of cxl_dports in this decode
+ * @interleave_granularity: data stride per dport
+ * @target_type: accelerator vs expander (type2 vs type3) selector
+ * @region: currently assigned region for this decoder
+ * @flags: memory type capabilities and locking
+ * @target_map: cached copy of hardware port-id list, available at init
+ *              before all @dport objects have been instantiated. While
+ *              dport id is 8bit, CFMWS interleave targets are 32bits.
+ * @commit: device/decoder-type specific callback to commit settings to hw
+ * @reset: device/decoder-type specific callback to reset hw settings
+*/
+struct cxl_decoder {
+	struct device dev;
+	int id;
+	struct range hpa_range;
+	int interleave_ways;
+	int interleave_granularity;
+	enum cxl_decoder_type target_type;
+	struct cxl_region *region;
+	unsigned long flags;
+	u32 target_map[CXL_DECODER_MAX_INTERLEAVE];
+	int (*commit)(struct cxl_decoder *cxld);
+	void (*reset)(struct cxl_decoder *cxld);
+};
+
+/*
+ * Track whether this decoder is free for userspace provisioning, reserved for
+ * region autodiscovery, whether it is started connecting (awaiting other
+ * peers), or has completed auto assembly.
+ */
+enum cxl_decoder_state {
+	CXL_DECODER_STATE_MANUAL,
+	CXL_DECODER_STATE_AUTO,
+	CXL_DECODER_STATE_AUTO_STAGED,
+};
+
+/**
+ * struct cxl_endpoint_decoder - Endpoint  / SPA to DPA decoder
+ * @cxld: base cxl_decoder_object
+ * @dpa_res: actively claimed DPA span of this decoder
+ * @skip: offset into @dpa_res where @cxld.hpa_range maps
+ * @state: autodiscovery state
+ * @part: partition index this decoder maps
+ * @pos: interleave position in @cxld.region
+ */
+struct cxl_endpoint_decoder {
+	struct cxl_decoder cxld;
+	struct resource *dpa_res;
+	resource_size_t skip;
+	enum cxl_decoder_state state;
+	int part;
+	int pos;
+};
+
+/**
+ * struct cxl_switch_decoder - Switch specific CXL HDM Decoder
+ * @cxld: base cxl_decoder object
+ * @nr_targets: number of elements in @target
+ * @target: active ordered target list in current decoder configuration
+ *
+ * The 'switch' decoder type represents the decoder instances of cxl_port's that
+ * route from the root of a CXL memory decode topology to the endpoints. They
+ * come in two flavors, root-level decoders, statically defined by platform
+ * firmware, and mid-level decoders, where interleave-granularity,
+ * interleave-width, and the target list are mutable.
+ */
+struct cxl_switch_decoder {
+	struct cxl_decoder cxld;
+	int nr_targets;
+	struct cxl_dport *target[];
+};
+
+struct cxl_root_decoder;
+/**
+ * struct cxl_rd_ops - CXL root decoder callback operations
+ * @hpa_to_spa: Convert host physical address to system physical address
+ * @spa_to_hpa: Convert system physical address to host physical address
+ */
+struct cxl_rd_ops {
+	u64 (*hpa_to_spa)(struct cxl_root_decoder *cxlrd, u64 hpa);
+	u64 (*spa_to_hpa)(struct cxl_root_decoder *cxlrd, u64 spa);
+};
+
+/**
+ * struct cxl_root_decoder - Static platform CXL address decoder
+ * @res: host / parent resource for region allocations
+ * @cache_size: extended linear cache size if exists, otherwise zero.
+ * @region_id: region id for next region provisioning event
+ * @platform_data: platform specific configuration data
+ * @regions_lock: sync region discovery, construction, and deletion
+ * @regions: regions to remove at root decoder destruct time
+ * @dead: root decoder dead to region creation
+ * @qos_class: QoS performance class cookie
+ * @ops: CXL root decoder operations
+ * @cxlsd: base cxl switch decoder
+ */
+struct cxl_root_decoder {
+	struct resource *res;
+	resource_size_t cache_size;
+	atomic_t region_id;
+	void *platform_data;
+	struct mutex regions_lock;
+	struct xarray regions;
+	bool dead;
+	int qos_class;
+	struct cxl_rd_ops ops;
+	struct cxl_switch_decoder cxlsd;
+};
+
+/*
+ * enum cxl_config_state - State machine for region configuration
+ * @CXL_CONFIG_IDLE: Any sysfs attribute can be written freely
+ * @CXL_CONFIG_INTERLEAVE_ACTIVE: region size has been set, no more
+ * changes to interleave_ways or interleave_granularity
+ * @CXL_CONFIG_ACTIVE: All targets have been added the region is now
+ * active
+ * @CXL_CONFIG_RESET_PENDING: see commit_store()
+ * @CXL_CONFIG_COMMIT: Soft-config has been committed to hardware
+ */
+enum cxl_config_state {
+	CXL_CONFIG_IDLE,
+	CXL_CONFIG_INTERLEAVE_ACTIVE,
+	CXL_CONFIG_ACTIVE,
+	CXL_CONFIG_RESET_PENDING,
+	CXL_CONFIG_COMMIT,
+};
+
+/**
+ * struct cxl_region_params - region settings
+ * @state: allow the driver to lockdown further parameter changes
+ * @uuid: unique id for persistent regions
+ * @interleave_ways: number of endpoints in the region
+ * @interleave_granularity: capacity each endpoint contributes to a stripe
+ * @res: allocated iomem capacity for this region
+ * @targets: active ordered targets in current decoder configuration
+ * @nr_targets: number of targets
+ * @cache_size: extended linear cache size if exists, otherwise zero.
+ *
+ * State transitions are protected by cxl_rwsem.region
+ */
+struct cxl_region_params {
+	enum cxl_config_state state;
+	uuid_t uuid;
+	int interleave_ways;
+	int interleave_granularity;
+	struct resource *res;
+	struct cxl_endpoint_decoder *targets[CXL_DECODER_MAX_INTERLEAVE];
+	int nr_targets;
+	resource_size_t cache_size;
+};
+
+/*
+ * Indicate whether this region has been assembled by autodetection or
+ * userspace assembly. Prevent endpoint decoders outside of automatic
+ * detection from being added to the region.
+ */
+#define CXL_REGION_F_AUTO 0
+
+/*
+ * Require that a committed region successfully complete a teardown once
+ * any of its associated decoders have been torn down. This maintains
+ * the commit state for the region since there are committed decoders,
+ * but blocks cxl_region_probe().
+ */
+#define CXL_REGION_F_NEEDS_RESET 1
+
+/*
+ * Indicate whether this region is locked due to 1 or more decoders that have
+ * been locked. The approach of all or nothing is taken with regard to the
+ * locked attribute. CXL_REGION_F_NEEDS_RESET should not be set if this flag is
+ * set.
+ */
+#define CXL_REGION_F_LOCK 2
+
+/*
+ * Indicate Normalized Addressing. Use it to disable SPA conversion if
+ * HPA != SPA and an address translation callback handler does not
+ * exist. Flag is needed by AMD Zen5 platforms.
+ */
+#define CXL_REGION_F_NORMALIZED_ADDRESSING 3
+
+/**
+ * struct cxl_region - CXL region
+ * @dev: This region's device
+ * @id: This region's id. Id is globally unique across all regions
+ * @cxlrd: Region's root decoder
+ * @hpa_range: Address range occupied by the region
+ * @mode: Operational mode of the mapped capacity
+ * @type: Endpoint decoder target type
+ * @cxl_nvb: nvdimm bridge for coordinating @cxlr_pmem setup / shutdown
+ * @cxlr_pmem: (for pmem regions) cached copy of the nvdimm bridge
+ * @flags: Region state flags
+ * @params: active + config params for the region
+ * @coord: QoS access coordinates for the region
+ * @node_notifier: notifier for setting the access coordinates to node
+ * @adist_notifier: notifier for calculating the abstract distance of node
+ */
+struct cxl_region {
+	struct device dev;
+	int id;
+	struct cxl_root_decoder *cxlrd;
+	struct range hpa_range;
+	enum cxl_partition_mode mode;
+	enum cxl_decoder_type type;
+	struct cxl_nvdimm_bridge *cxl_nvb;
+	struct cxl_pmem_region *cxlr_pmem;
+	unsigned long flags;
+	struct cxl_region_params params;
+	struct access_coordinate coord[ACCESS_COORDINATE_MAX];
+	struct notifier_block node_notifier;
+	struct notifier_block adist_notifier;
+};
+
+struct cxl_nvdimm_bridge {
+	int id;
+	struct device dev;
+	struct cxl_port *port;
+	struct nvdimm_bus *nvdimm_bus;
+	struct nvdimm_bus_descriptor nd_desc;
+};
+
+#define CXL_DEV_ID_LEN 19
+
+enum {
+	CXL_NVD_F_INVALIDATED = 0,
+};
+
+struct cxl_nvdimm {
+	struct device dev;
+	struct cxl_memdev *cxlmd;
+	u8 dev_id[CXL_DEV_ID_LEN]; /* for nvdimm, string of 'serial' */
+	u64 dirty_shutdowns;
+	unsigned long flags;
+};
+
+struct cxl_pmem_region_mapping {
+	struct cxl_memdev *cxlmd;
+	struct cxl_nvdimm *cxl_nvd;
+	u64 start;
+	u64 size;
+	int position;
+};
+
+struct cxl_pmem_region {
+	struct device dev;
+	struct cxl_region *cxlr;
+	struct nd_region *nd_region;
+	struct range hpa_range;
+	int nr_mappings;
+	struct cxl_pmem_region_mapping mapping[];
+};
+
+struct cxl_dax_region {
+	struct device dev;
+	struct cxl_region *cxlr;
+	struct range hpa_range;
+};
+
+/**
+ * struct cxl_port - logical collection of upstream port devices and
+ *		     downstream port devices to construct a CXL memory
+ *		     decode hierarchy.
+ * @dev: this port's device
+ * @uport_dev: PCI or platform device implementing the upstream port capability
+ * @host_bridge: Shortcut to the platform attach point for this port
+ * @id: id for port device-name
+ * @dports: cxl_dport instances referenced by decoders
+ * @endpoints: cxl_ep instances, endpoints that are a descendant of this port
+ * @regions: cxl_region_ref instances, regions mapped by this port
+ * @parent_dport: dport that points to this port in the parent
+ * @decoder_ida: allocator for decoder ids
+ * @reg_map: component and ras register mapping parameters
+ * @regs: mapped component registers
+ * @nr_dports: number of entries in @dports
+ * @hdm_end: track last allocated HDM decoder instance for allocation ordering
+ * @commit_end: cursor to track highest committed decoder for commit ordering
+ * @dead: last ep has been removed, force port re-creation
+ * @depth: How deep this port is relative to the root. depth 0 is the root.
+ * @cdat: Cached CDAT data
+ * @cdat_available: Should a CDAT attribute be available in sysfs
+ * @pci_latency: Upstream latency in picoseconds
+ * @component_reg_phys: Physical address of component register
+ */
+struct cxl_port {
+	struct device dev;
+	struct device *uport_dev;
+	struct device *host_bridge;
+	int id;
+	struct xarray dports;
+	struct xarray endpoints;
+	struct xarray regions;
+	struct cxl_dport *parent_dport;
+	struct ida decoder_ida;
+	struct cxl_register_map reg_map;
+	struct cxl_component_regs regs;
+	int nr_dports;
+	int hdm_end;
+	int commit_end;
+	bool dead;
+	unsigned int depth;
+	struct cxl_cdat {
+		void *table;
+		size_t length;
+	} cdat;
+	bool cdat_available;
+	long pci_latency;
+	resource_size_t component_reg_phys;
+};
+
+struct cxl_root;
+
+struct cxl_root_ops {
+	int (*qos_class)(struct cxl_root *cxl_root,
+			 struct access_coordinate *coord, int entries,
+			 int *qos_class);
+	int (*translation_setup_root)(struct cxl_root *cxl_root, void *data);
+};
+
+/**
+ * struct cxl_root - logical collection of root cxl_port items
+ *
+ * @port: cxl_port member
+ * @ops: cxl root operations
+ */
+struct cxl_root {
+	struct cxl_port port;
+	struct cxl_root_ops ops;
+};
+
+static inline struct cxl_root *
+to_cxl_root(const struct cxl_port *port)
+{
+	return container_of(port, struct cxl_root, port);
+}
+
+static inline struct cxl_dport *
+cxl_find_dport_by_dev(struct cxl_port *port, const struct device *dport_dev)
+{
+	return xa_load(&port->dports, (unsigned long)dport_dev);
+}
+
+struct cxl_rcrb_info {
+	resource_size_t base;
+	u16 aer_cap;
+};
+
+/**
+ * struct cxl_dport - CXL downstream port
+ * @dport_dev: PCI bridge or firmware device representing the downstream link
+ * @reg_map: component and ras register mapping parameters
+ * @port_id: unique hardware identifier for dport in decoder target list
+ * @rcrb: Data about the Root Complex Register Block layout
+ * @rch: Indicate whether this dport was enumerated in RCH or VH mode
+ * @port: reference to cxl_port that contains this downstream port
+ * @regs: Dport parsed register blocks
+ * @coord: access coordinates (bandwidth and latency performance attributes)
+ * @link_latency: calculated PCIe downstream latency
+ * @gpf_dvsec: Cached GPF port DVSEC
+ */
+struct cxl_dport {
+	struct device *dport_dev;
+	struct cxl_register_map reg_map;
+	int port_id;
+	struct cxl_rcrb_info rcrb;
+	bool rch;
+	struct cxl_port *port;
+	struct cxl_regs regs;
+	struct access_coordinate coord[ACCESS_COORDINATE_MAX];
+	long link_latency;
+	int gpf_dvsec;
+};
+
+/**
+ * struct cxl_ep - track an endpoint's interest in a port
+ * @ep: device that hosts a generic CXL endpoint (expander or accelerator)
+ * @dport: which dport routes to this endpoint on @port
+ * @next: cxl switch port across the link attached to @dport NULL if
+ *	  attached to an endpoint
+ */
+struct cxl_ep {
+	struct device *ep;
+	struct cxl_dport *dport;
+	struct cxl_port *next;
+};
+
+/**
+ * struct cxl_region_ref - track a region's interest in a port
+ * @port: point in topology to install this reference
+ * @decoder: decoder assigned for @region in @port
+ * @region: region for this reference
+ * @endpoints: cxl_ep references for region members beneath @port
+ * @nr_targets_set: track how many targets have been programmed during setup
+ * @nr_eps: number of endpoints beneath @port
+ * @nr_targets: number of distinct targets needed to reach @nr_eps
+ */
+struct cxl_region_ref {
+	struct cxl_port *port;
+	struct cxl_decoder *decoder;
+	struct cxl_region *region;
+	struct xarray endpoints;
+	int nr_targets_set;
+	int nr_eps;
+	int nr_targets;
+};
+
+/*
+ * The platform firmware device hosting the root is also the top of the
+ * CXL port topology. All other CXL ports have another CXL port as their
+ * parent and their ->uport_dev / host device is out-of-line of the port
+ * ancestry.
+ */
+static inline bool is_cxl_root(struct cxl_port *port)
+{
+	return port->uport_dev == port->dev.parent;
+}
+
+/* Address translation functions exported to cxl_translate test module only */
+int cxl_validate_translation_params(u8 eiw, u16 eig, int pos);
+u64 cxl_calculate_hpa_offset(u64 dpa_offset, int pos, u8 eiw, u16 eig);
+u64 cxl_calculate_dpa_offset(u64 hpa_offset, u8 eiw, u16 eig);
+int cxl_calculate_position(u64 hpa_offset, u8 eiw, u16 eig);
+struct cxl_cxims_data {
+	int nr_maps;
+	u64 xormaps[] __counted_by(nr_maps);
+};
+
+#if IS_ENABLED(CONFIG_CXL_ACPI)
+u64 cxl_do_xormap_calc(struct cxl_cxims_data *cximsd, u64 addr, int hbiw);
+#else
+static inline u64 cxl_do_xormap_calc(struct cxl_cxims_data *cximsd, u64 addr, int hbiw)
+{
+	return ULLONG_MAX;
+}
+#endif
+
+int cxl_num_decoders_committed(struct cxl_port *port);
+bool is_cxl_port(const struct device *dev);
+struct cxl_port *to_cxl_port(const struct device *dev);
+struct cxl_port *parent_port_of(struct cxl_port *port);
+void cxl_port_commit_reap(struct cxl_decoder *cxld);
+struct pci_bus;
+int devm_cxl_register_pci_bus(struct device *host, struct device *uport_dev,
+			      struct pci_bus *bus);
+struct pci_bus *cxl_port_to_pci_bus(struct cxl_port *port);
+struct cxl_port *devm_cxl_add_port(struct device *host,
+				   struct device *uport_dev,
+				   resource_size_t component_reg_phys,
+				   struct cxl_dport *parent_dport);
+struct cxl_root *devm_cxl_add_root(struct device *host);
+int devm_cxl_add_endpoint(struct device *host, struct cxl_memdev *cxlmd,
+			  struct cxl_dport *parent_dport);
+struct cxl_root *find_cxl_root(struct cxl_port *port);
+
+DEFINE_FREE(put_cxl_root, struct cxl_root *, if (_T) put_device(&_T->port.dev))
+DEFINE_FREE(put_cxl_port, struct cxl_port *, if (!IS_ERR_OR_NULL(_T)) put_device(&_T->dev))
+DEFINE_FREE(put_cxl_root_decoder, struct cxl_root_decoder *, if (!IS_ERR_OR_NULL(_T)) put_device(&_T->cxlsd.cxld.dev))
+DEFINE_FREE(put_cxl_region, struct cxl_region *, if (!IS_ERR_OR_NULL(_T)) put_device(&_T->dev))
+DEFINE_FREE(put_cxl_dax_region, struct cxl_dax_region *, if (!IS_ERR_OR_NULL(_T)) put_device(&_T->dev))
+
+int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd);
+void cxl_bus_rescan(void);
+void cxl_bus_drain(void);
+struct cxl_port *cxl_pci_find_port(struct pci_dev *pdev,
+				   struct cxl_dport **dport);
+struct cxl_port *cxl_mem_find_port(struct cxl_memdev *cxlmd,
+				   struct cxl_dport **dport);
+bool schedule_cxl_memdev_detach(struct cxl_memdev *cxlmd);
+
+struct cxl_dport *devm_cxl_add_dport(struct cxl_port *port,
+				     struct device *dport, int port_id,
+				     resource_size_t component_reg_phys);
+struct cxl_dport *devm_cxl_add_rch_dport(struct cxl_port *port,
+					 struct device *dport_dev, int port_id,
+					 resource_size_t rcrb);
+
+#ifdef CONFIG_CXL_ATL
+void cxl_setup_prm_address_translation(struct cxl_root *cxl_root);
+#else
+static inline
+void cxl_setup_prm_address_translation(struct cxl_root *cxl_root) {}
+#endif
+
+struct cxl_decoder *to_cxl_decoder(struct device *dev);
+struct cxl_root_decoder *to_cxl_root_decoder(struct device *dev);
+struct cxl_switch_decoder *to_cxl_switch_decoder(struct device *dev);
+struct cxl_endpoint_decoder *to_cxl_endpoint_decoder(struct device *dev);
+bool is_root_decoder(struct device *dev);
+bool is_switch_decoder(struct device *dev);
+bool is_endpoint_decoder(struct device *dev);
+struct cxl_root_decoder *cxl_root_decoder_alloc(struct cxl_port *port,
+						unsigned int nr_targets);
+struct cxl_switch_decoder *cxl_switch_decoder_alloc(struct cxl_port *port,
+						    unsigned int nr_targets);
+int cxl_decoder_add(struct cxl_decoder *cxld);
+struct cxl_endpoint_decoder *cxl_endpoint_decoder_alloc(struct cxl_port *port);
+int cxl_decoder_add_locked(struct cxl_decoder *cxld);
+int cxl_decoder_autoremove(struct device *host, struct cxl_decoder *cxld);
+static inline int cxl_root_decoder_autoremove(struct device *host,
+					      struct cxl_root_decoder *cxlrd)
+{
+	return cxl_decoder_autoremove(host, &cxlrd->cxlsd.cxld);
+}
+int cxl_endpoint_autoremove(struct cxl_memdev *cxlmd, struct cxl_port *endpoint);
+
+/**
+ * struct cxl_endpoint_dvsec_info - Cached DVSEC info
+ * @mem_enabled: cached value of mem_enabled in the DVSEC at init time
+ * @ranges: Number of active HDM ranges this device uses.
+ * @port: endpoint port associated with this info instance
+ * @dvsec_range: cached attributes of the ranges in the DVSEC, PCIE_DEVICE
+ */
+struct cxl_endpoint_dvsec_info {
+	bool mem_enabled;
+	int ranges;
+	struct cxl_port *port;
+	struct range dvsec_range[2];
+};
+
+int devm_cxl_switch_port_decoders_setup(struct cxl_port *port);
+int devm_cxl_endpoint_decoders_setup(struct cxl_port *port);
+void cxl_port_update_decoder_targets(struct cxl_port *port,
+				     struct cxl_dport *dport);
+int cxl_port_setup_regs(struct cxl_port *port,
+			resource_size_t component_reg_phys);
+
+struct cxl_dev_state;
+int cxl_dvsec_rr_decode(struct cxl_dev_state *cxlds,
+			struct cxl_endpoint_dvsec_info *info);
+
+bool is_cxl_region(struct device *dev);
+
+extern const struct bus_type cxl_bus_type;
+
+/*
+ * Note, add_dport() is expressly for the cxl_port driver. TODO: investigate a
+ * type-safe driver model where probe()/remove() take the type of object implied
+ * by @id and the add_dport() op only defined for the CXL_DEVICE_PORT driver
+ * template.
+ */
+struct cxl_driver {
+	const char *name;
+	int (*probe)(struct device *dev);
+	void (*remove)(struct device *dev);
+	struct cxl_dport *(*add_dport)(struct cxl_port *port,
+				       struct device *dport_dev);
+	struct device_driver drv;
+	int id;
+};
+
+#define to_cxl_drv(__drv)	container_of_const(__drv, struct cxl_driver, drv)
+
+int __cxl_driver_register(struct cxl_driver *cxl_drv, struct module *owner,
+			  const char *modname);
+#define cxl_driver_register(x) __cxl_driver_register(x, THIS_MODULE, KBUILD_MODNAME)
+void cxl_driver_unregister(struct cxl_driver *cxl_drv);
+
+#define module_cxl_driver(__cxl_driver) \
+	module_driver(__cxl_driver, cxl_driver_register, cxl_driver_unregister)
+
+#define CXL_DEVICE_NVDIMM_BRIDGE	1
+#define CXL_DEVICE_NVDIMM		2
+#define CXL_DEVICE_PORT			3
+#define CXL_DEVICE_ROOT			4
+#define CXL_DEVICE_MEMORY_EXPANDER	5
+#define CXL_DEVICE_REGION		6
+#define CXL_DEVICE_PMEM_REGION		7
+#define CXL_DEVICE_DAX_REGION		8
+#define CXL_DEVICE_PMU			9
+
+#define MODULE_ALIAS_CXL(type) MODULE_ALIAS("cxl:t" __stringify(type) "*")
+#define CXL_MODALIAS_FMT "cxl:t%d"
+
+struct cxl_nvdimm_bridge *to_cxl_nvdimm_bridge(struct device *dev);
+struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host,
+						     struct cxl_port *port);
+struct cxl_nvdimm_bridge *__devm_cxl_add_nvdimm_bridge(struct device *host,
+						       struct cxl_port *port);
+struct cxl_nvdimm *to_cxl_nvdimm(struct device *dev);
+bool is_cxl_nvdimm(struct device *dev);
+int devm_cxl_add_nvdimm(struct device *host, struct cxl_port *port,
+			struct cxl_memdev *cxlmd);
+struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_port *port);
+
+#ifdef CONFIG_CXL_REGION
+bool is_cxl_pmem_region(struct device *dev);
+struct cxl_pmem_region *to_cxl_pmem_region(struct device *dev);
+int cxl_add_to_region(struct cxl_endpoint_decoder *cxled);
+struct cxl_dax_region *to_cxl_dax_region(struct device *dev);
+u64 cxl_port_get_spa_cache_alias(struct cxl_port *endpoint, u64 spa);
+bool cxl_region_contains_resource(const struct resource *res);
+#else
+static inline bool is_cxl_pmem_region(struct device *dev)
+{
+	return false;
+}
+static inline struct cxl_pmem_region *to_cxl_pmem_region(struct device *dev)
+{
+	return NULL;
+}
+static inline int cxl_add_to_region(struct cxl_endpoint_decoder *cxled)
+{
+	return 0;
+}
+static inline struct cxl_dax_region *to_cxl_dax_region(struct device *dev)
+{
+	return NULL;
+}
+static inline u64 cxl_port_get_spa_cache_alias(struct cxl_port *endpoint,
+					       u64 spa)
+{
+	return 0;
+}
+static inline bool cxl_region_contains_resource(const struct resource *res)
+{
+	return false;
+}
+#endif
+
+void cxl_endpoint_parse_cdat(struct cxl_port *port);
+void cxl_switch_parse_cdat(struct cxl_dport *dport);
+
+int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
+				      struct access_coordinate *coord);
+void cxl_region_perf_data_calculate(struct cxl_region *cxlr,
+				    struct cxl_endpoint_decoder *cxled);
+void cxl_region_shared_upstream_bandwidth_update(struct cxl_region *cxlr);
+
+void cxl_memdev_update_perf(struct cxl_memdev *cxlmd);
+
+void cxl_coordinates_combine(struct access_coordinate *out,
+			     struct access_coordinate *c1,
+			     struct access_coordinate *c2);
+
+bool cxl_endpoint_decoder_reset_detected(struct cxl_port *port);
+struct cxl_dport *devm_cxl_add_dport_by_dev(struct cxl_port *port,
+					    struct device *dport_dev);
+
+/*
+ * Unit test builds overrides this to __weak, find the 'strong' version
+ * of these symbols in tools/testing/cxl/.
+ */
+#ifndef __mock
+#define __mock static
+#endif
+
+u16 cxl_gpf_get_dvsec(struct device *dev);
+
+#endif /* __CXL_H__ */

linux-7.2.3/drivers/cxl/cxlmem.h

@@ -0,0 +1,876 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2020-2021 Intel Corporation. */
+#ifndef __CXL_MEM_H__
+#define __CXL_MEM_H__
+#include <uapi/linux/cxl_mem.h>
+#include <linux/pci.h>
+#include <linux/cdev.h>
+#include <linux/uuid.h>
+#include <linux/node.h>
+#include <cxl/event.h>
+#include <cxl/mailbox.h>
+#include "cxl.h"
+
+/* CXL 2.0 8.2.8.5.1.1 Memory Device Status Register */
+#define CXLMDEV_STATUS_OFFSET 0x0
+#define   CXLMDEV_DEV_FATAL BIT(0)
+#define   CXLMDEV_FW_HALT BIT(1)
+#define   CXLMDEV_STATUS_MEDIA_STATUS_MASK GENMASK(3, 2)
+#define     CXLMDEV_MS_NOT_READY 0
+#define     CXLMDEV_MS_READY 1
+#define     CXLMDEV_MS_ERROR 2
+#define     CXLMDEV_MS_DISABLED 3
+#define CXLMDEV_READY(status)                                                  \
+	(FIELD_GET(CXLMDEV_STATUS_MEDIA_STATUS_MASK, status) ==                \
+	 CXLMDEV_MS_READY)
+#define   CXLMDEV_MBOX_IF_READY BIT(4)
+#define   CXLMDEV_RESET_NEEDED_MASK GENMASK(7, 5)
+#define     CXLMDEV_RESET_NEEDED_NOT 0
+#define     CXLMDEV_RESET_NEEDED_COLD 1
+#define     CXLMDEV_RESET_NEEDED_WARM 2
+#define     CXLMDEV_RESET_NEEDED_HOT 3
+#define     CXLMDEV_RESET_NEEDED_CXL 4
+#define CXLMDEV_RESET_NEEDED(status)                                           \
+	(FIELD_GET(CXLMDEV_RESET_NEEDED_MASK, status) !=                       \
+	 CXLMDEV_RESET_NEEDED_NOT)
+
+/**
+ * struct cxl_memdev - CXL bus object representing a Type-3 Memory Device
+ * @dev: driver core device object
+ * @cdev: char dev core object for ioctl operations
+ * @cxlds: The device state backing this device
+ * @detach_work: active memdev lost a port in its ancestry
+ * @cxl_nvb: coordinate removal of @cxl_nvd if present
+ * @cxl_nvd: optional bridge to an nvdimm if the device supports pmem
+ * @endpoint: connection to the CXL port topology for this memory device
+ * @attach: creator of this memdev depends on CXL link attach to operate
+ * @id: id number of this memdev instance.
+ * @depth: endpoint port depth
+ * @scrub_cycle: current scrub cycle set for this device
+ * @scrub_region_id: id number of a backed region (if any) for which current scrub cycle set
+ * @err_rec_array: List of xarrarys to store the memdev error records to
+ *		   check attributes for a memory repair operation are from
+ *		   current boot.
+ */
+struct cxl_memdev {
+	struct device dev;
+	struct cdev cdev;
+	struct cxl_dev_state *cxlds;
+	struct work_struct detach_work;
+	struct cxl_nvdimm_bridge *cxl_nvb;
+	struct cxl_nvdimm *cxl_nvd;
+	struct cxl_port *endpoint;
+	const struct cxl_memdev_attach *attach;
+	int id;
+	int depth;
+	u8 scrub_cycle;
+	int scrub_region_id;
+	struct cxl_mem_err_rec *err_rec_array;
+};
+
+static inline struct cxl_memdev *to_cxl_memdev(struct device *dev)
+{
+	return container_of(dev, struct cxl_memdev, dev);
+}
+
+static inline struct cxl_port *cxled_to_port(struct cxl_endpoint_decoder *cxled)
+{
+	return to_cxl_port(cxled->cxld.dev.parent);
+}
+
+static inline struct cxl_port *cxlrd_to_port(struct cxl_root_decoder *cxlrd)
+{
+	return to_cxl_port(cxlrd->cxlsd.cxld.dev.parent);
+}
+
+static inline struct cxl_memdev *
+cxled_to_memdev(struct cxl_endpoint_decoder *cxled)
+{
+	struct cxl_port *port = to_cxl_port(cxled->cxld.dev.parent);
+
+	return to_cxl_memdev(port->uport_dev);
+}
+
+bool is_cxl_memdev(const struct device *dev);
+static inline bool is_cxl_endpoint(struct cxl_port *port)
+{
+	return is_cxl_memdev(port->uport_dev);
+}
+
+struct cxl_memdev_attach {
+	int (*probe)(struct cxl_memdev *cxlmd);
+};
+
+/**
+ * struct cxl_attach_region - coordinate mapping a region at memdev registration
+ * @attach: common core attachment descriptor
+ * @hpa_range: physical address range of the region
+ *
+ * For the common simple case of a CXL device with private (non-general purpose
+ * / "accelerator") memory, enumerate firmware instantiated region, or
+ * instantiate a region for the device's capacity. Destroy the region on detach.
+ */
+struct cxl_attach_region {
+	struct cxl_memdev_attach attach;
+	struct range hpa_range;
+};
+
+#ifdef CONFIG_CXL_REGION
+int cxl_memdev_attach_region(struct cxl_memdev *cxlmd);
+#else
+static inline int cxl_memdev_attach_region(struct cxl_memdev *cxlmd)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+struct cxl_memdev *devm_cxl_add_classdev(struct cxl_dev_state *cxlds);
+struct cxl_memdev *__devm_cxl_add_memdev(struct cxl_dev_state *cxlds,
+					 const struct cxl_memdev_attach *attach);
+int devm_cxl_sanitize_setup_notifier(struct device *host,
+				     struct cxl_memdev *cxlmd);
+struct cxl_memdev_state;
+int devm_cxl_setup_fw_upload(struct device *host, struct cxl_memdev_state *mds);
+int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
+			 resource_size_t base, resource_size_t len,
+			 resource_size_t skipped);
+
+struct cxl_dpa_info {
+	u64 size;
+	struct cxl_dpa_part_info {
+		struct range range;
+		enum cxl_partition_mode mode;
+	} part[CXL_NR_PARTITIONS_MAX];
+	int nr_partitions;
+};
+
+int cxl_dpa_setup(struct cxl_dev_state *cxlds, const struct cxl_dpa_info *info);
+
+static inline struct cxl_ep *cxl_ep_load(struct cxl_port *port,
+					 struct cxl_memdev *cxlmd)
+{
+	if (!port)
+		return NULL;
+
+	return xa_load(&port->endpoints, (unsigned long)&cxlmd->dev);
+}
+
+/*
+ * Per CXL 3.0 Section 8.2.8.4.5.1
+ */
+#define CMD_CMD_RC_TABLE							\
+	C(SUCCESS, 0, NULL),							\
+	C(BACKGROUND, -ENXIO, "background cmd started successfully"),           \
+	C(INPUT, -ENXIO, "cmd input was invalid"),				\
+	C(UNSUPPORTED, -ENXIO, "cmd is not supported"),				\
+	C(INTERNAL, -ENXIO, "internal device error"),				\
+	C(RETRY, -ENXIO, "temporary error, retry once"),			\
+	C(BUSY, -ENXIO, "ongoing background operation"),			\
+	C(MEDIADISABLED, -ENXIO, "media access is disabled"),			\
+	C(FWINPROGRESS, -ENXIO,	"one FW package can be transferred at a time"), \
+	C(FWOOO, -ENXIO, "FW package content was transferred out of order"),    \
+	C(FWAUTH, -ENXIO, "FW package authentication failed"),			\
+	C(FWSLOT, -ENXIO, "FW slot is not supported for requested operation"),  \
+	C(FWROLLBACK, -ENXIO, "rolled back to the previous active FW"),         \
+	C(FWRESET, -ENXIO, "FW failed to activate, needs cold reset"),		\
+	C(HANDLE, -ENXIO, "one or more Event Record Handles were invalid"),     \
+	C(PADDR, -EFAULT, "physical address specified is invalid"),		\
+	C(POISONLMT, -EBUSY, "poison injection limit has been reached"),        \
+	C(MEDIAFAILURE, -ENXIO, "permanent issue with the media"),		\
+	C(ABORT, -ENXIO, "background cmd was aborted by device"),               \
+	C(SECURITY, -ENXIO, "not valid in the current security state"),         \
+	C(PASSPHRASE, -ENXIO, "phrase doesn't match current set passphrase"),   \
+	C(MBUNSUPPORTED, -ENXIO, "unsupported on the mailbox it was issued on"),\
+	C(PAYLOADLEN, -ENXIO, "invalid payload length"),			\
+	C(LOG, -ENXIO, "invalid or unsupported log page"),			\
+	C(INTERRUPTED, -ENXIO, "asynchronous event occured"),			\
+	C(FEATUREVERSION, -ENXIO, "unsupported feature version"),		\
+	C(FEATURESELVALUE, -ENXIO, "unsupported feature selection value"),	\
+	C(FEATURETRANSFERIP, -ENXIO, "feature transfer in progress"),		\
+	C(FEATURETRANSFEROOO, -ENXIO, "feature transfer out of order"),		\
+	C(RESOURCEEXHAUSTED, -ENXIO, "resources are exhausted"),		\
+	C(EXTLIST, -ENXIO, "invalid Extent List"),				\
+
+#undef C
+#define C(a, b, c) CXL_MBOX_CMD_RC_##a
+enum  { CMD_CMD_RC_TABLE };
+#undef C
+#define C(a, b, c) { b, c }
+struct cxl_mbox_cmd_rc {
+	int err;
+	const char *desc;
+};
+
+static const
+struct cxl_mbox_cmd_rc cxl_mbox_cmd_rctable[] ={ CMD_CMD_RC_TABLE };
+#undef C
+
+static inline const char *cxl_mbox_cmd_rc2str(struct cxl_mbox_cmd *mbox_cmd)
+{
+	return cxl_mbox_cmd_rctable[mbox_cmd->return_code].desc;
+}
+
+static inline int cxl_mbox_cmd_rc2errno(struct cxl_mbox_cmd *mbox_cmd)
+{
+	return cxl_mbox_cmd_rctable[mbox_cmd->return_code].err;
+}
+
+/*
+ * CXL 2.0 - Memory capacity multiplier
+ * See Section 8.2.9.5
+ *
+ * Volatile, Persistent, and Partition capacities are specified to be in
+ * multiples of 256MB - define a multiplier to convert to/from bytes.
+ */
+#define CXL_CAPACITY_MULTIPLIER SZ_256M
+
+/*
+ * Event Interrupt Policy
+ *
+ * CXL rev 3.0 section 8.2.9.2.4; Table 8-52
+ */
+enum cxl_event_int_mode {
+	CXL_INT_NONE		= 0x00,
+	CXL_INT_MSI_MSIX	= 0x01,
+	CXL_INT_FW		= 0x02
+};
+struct cxl_event_interrupt_policy {
+	u8 info_settings;
+	u8 warn_settings;
+	u8 failure_settings;
+	u8 fatal_settings;
+} __packed;
+
+/**
+ * struct cxl_event_state - Event log driver state
+ *
+ * @buf: Buffer to receive event data
+ * @log_lock: Serialize event_buf and log use
+ */
+struct cxl_event_state {
+	struct cxl_get_event_payload *buf;
+	struct mutex log_lock;
+};
+
+/* Device enabled poison commands */
+enum poison_cmd_enabled_bits {
+	CXL_POISON_ENABLED_LIST,
+	CXL_POISON_ENABLED_INJECT,
+	CXL_POISON_ENABLED_CLEAR,
+	CXL_POISON_ENABLED_SCAN_CAPS,
+	CXL_POISON_ENABLED_SCAN_MEDIA,
+	CXL_POISON_ENABLED_SCAN_RESULTS,
+	CXL_POISON_ENABLED_MAX
+};
+
+/* Device enabled security commands */
+enum security_cmd_enabled_bits {
+	CXL_SEC_ENABLED_SANITIZE,
+	CXL_SEC_ENABLED_SECURE_ERASE,
+	CXL_SEC_ENABLED_GET_SECURITY_STATE,
+	CXL_SEC_ENABLED_SET_PASSPHRASE,
+	CXL_SEC_ENABLED_DISABLE_PASSPHRASE,
+	CXL_SEC_ENABLED_UNLOCK,
+	CXL_SEC_ENABLED_FREEZE_SECURITY,
+	CXL_SEC_ENABLED_PASSPHRASE_SECURE_ERASE,
+	CXL_SEC_ENABLED_MAX
+};
+
+/**
+ * struct cxl_poison_state - Driver poison state info
+ *
+ * @max_errors: Maximum media error records held in device cache
+ * @enabled_cmds: All poison commands enabled in the CEL
+ * @list_out: The poison list payload returned by device
+ * @mutex: Protect reads of the poison list
+ *
+ * Reads of the poison list are synchronized to ensure that a reader
+ * does not get an incomplete list because their request overlapped
+ * (was interrupted or preceded by) another read request of the same
+ * DPA range. CXL Spec 3.0 Section 8.2.9.8.4.1
+ */
+struct cxl_poison_state {
+	u32 max_errors;
+	DECLARE_BITMAP(enabled_cmds, CXL_POISON_ENABLED_MAX);
+	struct cxl_mbox_poison_out *list_out;
+	struct mutex mutex;  /* Protect reads of poison list */
+};
+
+/*
+ * Get FW Info
+ * CXL rev 3.0 section 8.2.9.3.1; Table 8-56
+ */
+struct cxl_mbox_get_fw_info {
+	u8 num_slots;
+	u8 slot_info;
+	u8 activation_cap;
+	u8 reserved[13];
+	char slot_1_revision[16];
+	char slot_2_revision[16];
+	char slot_3_revision[16];
+	char slot_4_revision[16];
+} __packed;
+
+#define CXL_FW_INFO_SLOT_INFO_CUR_MASK			GENMASK(2, 0)
+#define CXL_FW_INFO_SLOT_INFO_NEXT_MASK			GENMASK(5, 3)
+#define CXL_FW_INFO_SLOT_INFO_NEXT_SHIFT		3
+#define CXL_FW_INFO_ACTIVATION_CAP_HAS_LIVE_ACTIVATE	BIT(0)
+
+/*
+ * Transfer FW Input Payload
+ * CXL rev 3.0 section 8.2.9.3.2; Table 8-57
+ */
+struct cxl_mbox_transfer_fw {
+	u8 action;
+	u8 slot;
+	u8 reserved[2];
+	__le32 offset;
+	u8 reserved2[0x78];
+	u8 data[];
+} __packed;
+
+#define CXL_FW_TRANSFER_ACTION_FULL	0x0
+#define CXL_FW_TRANSFER_ACTION_INITIATE	0x1
+#define CXL_FW_TRANSFER_ACTION_CONTINUE	0x2
+#define CXL_FW_TRANSFER_ACTION_END	0x3
+#define CXL_FW_TRANSFER_ACTION_ABORT	0x4
+
+/*
+ * CXL rev 3.0 section 8.2.9.3.2 mandates 128-byte alignment for FW packages
+ * and for each part transferred in a Transfer FW command.
+ */
+#define CXL_FW_TRANSFER_ALIGNMENT	128
+
+/*
+ * Activate FW Input Payload
+ * CXL rev 3.0 section 8.2.9.3.3; Table 8-58
+ */
+struct cxl_mbox_activate_fw {
+	u8 action;
+	u8 slot;
+} __packed;
+
+#define CXL_FW_ACTIVATE_ONLINE		0x0
+#define CXL_FW_ACTIVATE_OFFLINE		0x1
+
+/* FW state bits */
+#define CXL_FW_STATE_BITS		32
+#define CXL_FW_CANCEL			0
+
+/**
+ * struct cxl_fw_state - Firmware upload / activation state
+ *
+ * @state: fw_uploader state bitmask
+ * @oneshot: whether the fw upload fits in a single transfer
+ * @num_slots: Number of FW slots available
+ * @cur_slot: Slot number currently active
+ * @next_slot: Slot number for the new firmware
+ */
+struct cxl_fw_state {
+	DECLARE_BITMAP(state, CXL_FW_STATE_BITS);
+	bool oneshot;
+	int num_slots;
+	int cur_slot;
+	int next_slot;
+};
+
+/**
+ * struct cxl_security_state - Device security state
+ *
+ * @state: state of last security operation
+ * @enabled_cmds: All security commands enabled in the CEL
+ * @poll_tmo_secs: polling timeout
+ * @sanitize_active: sanitize completion pending
+ * @poll_dwork: polling work item
+ * @sanitize_node: sanitation sysfs file to notify
+ */
+struct cxl_security_state {
+	unsigned long state;
+	DECLARE_BITMAP(enabled_cmds, CXL_SEC_ENABLED_MAX);
+	int poll_tmo_secs;
+	bool sanitize_active;
+	struct delayed_work poll_dwork;
+	struct kernfs_node *sanitize_node;
+};
+
+static inline resource_size_t cxl_pmem_size(struct cxl_dev_state *cxlds)
+{
+	/*
+	 * Static PMEM may be at partition index 0 when there is no static RAM
+	 * capacity.
+	 */
+	for (int i = 0; i < cxlds->nr_partitions; i++)
+		if (cxlds->part[i].mode == CXL_PARTMODE_PMEM)
+			return resource_size(&cxlds->part[i].res);
+	return 0;
+}
+
+static inline struct cxl_dev_state *mbox_to_cxlds(struct cxl_mailbox *cxl_mbox)
+{
+	return dev_get_drvdata(cxl_mbox->host);
+}
+
+/**
+ * struct cxl_memdev_state - Generic Type-3 Memory Device Class driver data
+ *
+ * CXL 8.1.12.1 PCI Header - Class Code Register Memory Device defines
+ * common memory device functionality like the presence of a mailbox and
+ * the functionality related to that like Identify Memory Device and Get
+ * Partition Info
+ * @cxlds: Core driver state common across Type-2 and Type-3 devices
+ * @lsa_size: Size of Label Storage Area
+ *                (CXL 2.0 8.2.9.5.1.1 Identify Memory Device)
+ * @firmware_version: Firmware version for the memory device.
+ * @total_bytes: sum of all possible capacities
+ * @volatile_only_bytes: hard volatile capacity
+ * @persistent_only_bytes: hard persistent capacity
+ * @partition_align_bytes: alignment size for partition-able capacity
+ * @active_volatile_bytes: sum of hard + soft volatile
+ * @active_persistent_bytes: sum of hard + soft persistent
+ * @event: event log driver state
+ * @poison: poison driver state info
+ * @security: security driver state info
+ * @fw: firmware upload / activation state
+ * @mce_notifier: MCE notifier
+ *
+ * See CXL 3.0 8.2.9.8.2 Capacity Configuration and Label Storage for
+ * details on capacity parameters.
+ */
+struct cxl_memdev_state {
+	struct cxl_dev_state cxlds;
+	size_t lsa_size;
+	char firmware_version[0x10];
+	u64 total_bytes;
+	u64 volatile_only_bytes;
+	u64 persistent_only_bytes;
+	u64 partition_align_bytes;
+	u64 active_volatile_bytes;
+	u64 active_persistent_bytes;
+
+	struct cxl_event_state event;
+	struct cxl_poison_state poison;
+	struct cxl_security_state security;
+	struct cxl_fw_state fw;
+	struct notifier_block mce_notifier;
+};
+
+static inline struct cxl_memdev_state *
+to_cxl_memdev_state(struct cxl_dev_state *cxlds)
+{
+	if (cxlds->type != CXL_DEVTYPE_CLASSMEM)
+		return NULL;
+	return container_of(cxlds, struct cxl_memdev_state, cxlds);
+}
+
+enum cxl_opcode {
+	CXL_MBOX_OP_INVALID		= 0x0000,
+	CXL_MBOX_OP_RAW			= CXL_MBOX_OP_INVALID,
+	CXL_MBOX_OP_GET_EVENT_RECORD	= 0x0100,
+	CXL_MBOX_OP_CLEAR_EVENT_RECORD	= 0x0101,
+	CXL_MBOX_OP_GET_EVT_INT_POLICY	= 0x0102,
+	CXL_MBOX_OP_SET_EVT_INT_POLICY	= 0x0103,
+	CXL_MBOX_OP_GET_FW_INFO		= 0x0200,
+	CXL_MBOX_OP_TRANSFER_FW		= 0x0201,
+	CXL_MBOX_OP_ACTIVATE_FW		= 0x0202,
+	CXL_MBOX_OP_GET_TIMESTAMP	= 0x0300,
+	CXL_MBOX_OP_SET_TIMESTAMP	= 0x0301,
+	CXL_MBOX_OP_GET_SUPPORTED_LOGS	= 0x0400,
+	CXL_MBOX_OP_GET_LOG		= 0x0401,
+	CXL_MBOX_OP_GET_LOG_CAPS	= 0x0402,
+	CXL_MBOX_OP_CLEAR_LOG           = 0x0403,
+	CXL_MBOX_OP_GET_SUP_LOG_SUBLIST = 0x0405,
+	CXL_MBOX_OP_GET_SUPPORTED_FEATURES	= 0x0500,
+	CXL_MBOX_OP_GET_FEATURE		= 0x0501,
+	CXL_MBOX_OP_SET_FEATURE		= 0x0502,
+	CXL_MBOX_OP_DO_MAINTENANCE	= 0x0600,
+	CXL_MBOX_OP_IDENTIFY		= 0x4000,
+	CXL_MBOX_OP_GET_PARTITION_INFO	= 0x4100,
+	CXL_MBOX_OP_SET_PARTITION_INFO	= 0x4101,
+	CXL_MBOX_OP_GET_LSA		= 0x4102,
+	CXL_MBOX_OP_SET_LSA		= 0x4103,
+	CXL_MBOX_OP_GET_HEALTH_INFO	= 0x4200,
+	CXL_MBOX_OP_GET_ALERT_CONFIG	= 0x4201,
+	CXL_MBOX_OP_SET_ALERT_CONFIG	= 0x4202,
+	CXL_MBOX_OP_GET_SHUTDOWN_STATE	= 0x4203,
+	CXL_MBOX_OP_SET_SHUTDOWN_STATE	= 0x4204,
+	CXL_MBOX_OP_GET_POISON		= 0x4300,
+	CXL_MBOX_OP_INJECT_POISON	= 0x4301,
+	CXL_MBOX_OP_CLEAR_POISON	= 0x4302,
+	CXL_MBOX_OP_GET_SCAN_MEDIA_CAPS	= 0x4303,
+	CXL_MBOX_OP_SCAN_MEDIA		= 0x4304,
+	CXL_MBOX_OP_GET_SCAN_MEDIA	= 0x4305,
+	CXL_MBOX_OP_SANITIZE		= 0x4400,
+	CXL_MBOX_OP_SECURE_ERASE	= 0x4401,
+	CXL_MBOX_OP_GET_SECURITY_STATE	= 0x4500,
+	CXL_MBOX_OP_SET_PASSPHRASE	= 0x4501,
+	CXL_MBOX_OP_DISABLE_PASSPHRASE	= 0x4502,
+	CXL_MBOX_OP_UNLOCK		= 0x4503,
+	CXL_MBOX_OP_FREEZE_SECURITY	= 0x4504,
+	CXL_MBOX_OP_PASSPHRASE_SECURE_ERASE	= 0x4505,
+	CXL_MBOX_OP_MAX			= 0x10000
+};
+
+#define DEFINE_CXL_CEL_UUID                                                    \
+	UUID_INIT(0xda9c0b5, 0xbf41, 0x4b78, 0x8f, 0x79, 0x96, 0xb1, 0x62,     \
+		  0x3b, 0x3f, 0x17)
+
+#define DEFINE_CXL_VENDOR_DEBUG_UUID                                           \
+	UUID_INIT(0x5e1819d9, 0x11a9, 0x400c, 0x81, 0x1f, 0xd6, 0x07, 0x19,     \
+		  0x40, 0x3d, 0x86)
+
+struct cxl_mbox_get_supported_logs {
+	__le16 entries;
+	u8 rsvd[6];
+	struct cxl_gsl_entry {
+		uuid_t uuid;
+		__le32 size;
+	} __packed entry[];
+}  __packed;
+
+struct cxl_cel_entry {
+	__le16 opcode;
+	__le16 effect;
+} __packed;
+
+struct cxl_mbox_get_log {
+	uuid_t uuid;
+	__le32 offset;
+	__le32 length;
+} __packed;
+
+/* See CXL 2.0 Table 175 Identify Memory Device Output Payload */
+struct cxl_mbox_identify {
+	char fw_revision[0x10];
+	__le64 total_capacity;
+	__le64 volatile_capacity;
+	__le64 persistent_capacity;
+	__le64 partition_align;
+	__le16 info_event_log_size;
+	__le16 warning_event_log_size;
+	__le16 failure_event_log_size;
+	__le16 fatal_event_log_size;
+	__le32 lsa_size;
+	u8 poison_list_max_mer[3];
+	__le16 inject_poison_limit;
+	u8 poison_caps;
+	u8 qos_telemetry_caps;
+} __packed;
+
+/*
+ * General Media Event Record UUID
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+#define CXL_EVENT_GEN_MEDIA_UUID                                            \
+	UUID_INIT(0xfbcd0a77, 0xc260, 0x417f, 0x85, 0xa9, 0x08, 0x8b, 0x16, \
+		  0x21, 0xeb, 0xa6)
+
+/*
+ * DRAM Event Record UUID
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ */
+#define CXL_EVENT_DRAM_UUID                                                 \
+	UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, \
+		  0x5c, 0x96, 0x24)
+
+/*
+ * Memory Module Event Record UUID
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+#define CXL_EVENT_MEM_MODULE_UUID                                           \
+	UUID_INIT(0xfe927475, 0xdd59, 0x4339, 0xa5, 0x86, 0x79, 0xba, 0xb1, \
+		  0x13, 0xb7, 0x74)
+
+/*
+ * Memory Sparing Event Record UUID
+ * CXL rev 3.2 section 8.2.10.2.1.4: Table 8-60
+ */
+#define CXL_EVENT_MEM_SPARING_UUID                                          \
+	UUID_INIT(0xe71f3a40, 0x2d29, 0x4092, 0x8a, 0x39, 0x4d, 0x1c, 0x96, \
+		  0x6c, 0x7c, 0x65)
+
+/*
+ * Get Event Records output payload
+ * CXL rev 3.0 section 8.2.9.2.2; Table 8-50
+ */
+#define CXL_GET_EVENT_FLAG_OVERFLOW		BIT(0)
+#define CXL_GET_EVENT_FLAG_MORE_RECORDS		BIT(1)
+struct cxl_get_event_payload {
+	u8 flags;
+	u8 reserved1;
+	__le16 overflow_err_count;
+	__le64 first_overflow_timestamp;
+	__le64 last_overflow_timestamp;
+	__le16 record_count;
+	u8 reserved2[10];
+	struct cxl_event_record_raw records[];
+} __packed;
+
+/*
+ * CXL rev 3.0 section 8.2.9.2.2; Table 8-49
+ */
+enum cxl_event_log_type {
+	CXL_EVENT_TYPE_INFO = 0x00,
+	CXL_EVENT_TYPE_WARN,
+	CXL_EVENT_TYPE_FAIL,
+	CXL_EVENT_TYPE_FATAL,
+	CXL_EVENT_TYPE_MAX
+};
+
+/*
+ * Clear Event Records input payload
+ * CXL rev 3.0 section 8.2.9.2.3; Table 8-51
+ */
+struct cxl_mbox_clear_event_payload {
+	u8 event_log;		/* enum cxl_event_log_type */
+	u8 clear_flags;
+	u8 nr_recs;
+	u8 reserved[3];
+	__le16 handles[];
+} __packed;
+#define CXL_CLEAR_EVENT_MAX_HANDLES U8_MAX
+
+struct cxl_mbox_get_partition_info {
+	__le64 active_volatile_cap;
+	__le64 active_persistent_cap;
+	__le64 next_volatile_cap;
+	__le64 next_persistent_cap;
+} __packed;
+
+struct cxl_mbox_get_lsa {
+	__le32 offset;
+	__le32 length;
+} __packed;
+
+struct cxl_mbox_set_lsa {
+	__le32 offset;
+	__le32 reserved;
+	u8 data[];
+} __packed;
+
+struct cxl_mbox_set_partition_info {
+	__le64 volatile_capacity;
+	u8 flags;
+} __packed;
+
+#define  CXL_SET_PARTITION_IMMEDIATE_FLAG	BIT(0)
+
+/* Get Health Info Output Payload CXL 3.2 Spec 8.2.10.9.3.1 Table 8-148 */
+struct cxl_mbox_get_health_info_out {
+	u8 health_status;
+	u8 media_status;
+	u8 additional_status;
+	u8 life_used;
+	__le16 device_temperature;
+	__le32 dirty_shutdown_cnt;
+	__le32 corrected_volatile_error_cnt;
+	__le32 corrected_persistent_error_cnt;
+} __packed;
+
+/* Set Shutdown State Input Payload CXL 3.2 Spec 8.2.10.9.3.5 Table 8-152 */
+struct cxl_mbox_set_shutdown_state_in {
+	u8 state;
+} __packed;
+
+/* Set Timestamp CXL 3.0 Spec 8.2.9.4.2 */
+struct cxl_mbox_set_timestamp_in {
+	__le64 timestamp;
+
+} __packed;
+
+/* Get Poison List  CXL 3.0 Spec 8.2.9.8.4.1 */
+struct cxl_mbox_poison_in {
+	__le64 offset;
+	__le64 length;
+} __packed;
+
+struct cxl_mbox_poison_out {
+	u8 flags;
+	u8 rsvd1;
+	__le64 overflow_ts;
+	__le16 count;
+	u8 rsvd2[20];
+	struct cxl_poison_record {
+		__le64 address;
+		__le32 length;
+		__le32 rsvd;
+	} __packed record[];
+} __packed;
+
+/*
+ * Get Poison List address field encodes the starting
+ * address of poison, and the source of the poison.
+ */
+#define CXL_POISON_START_MASK		GENMASK_ULL(63, 6)
+#define CXL_POISON_SOURCE_MASK		GENMASK(2, 0)
+
+/* Get Poison List record length is in units of 64 bytes */
+#define CXL_POISON_LEN_MULT	64
+
+/* Kernel defined maximum for a list of poison errors */
+#define CXL_POISON_LIST_MAX	1024
+
+/* Get Poison List: Payload out flags */
+#define CXL_POISON_FLAG_MORE            BIT(0)
+#define CXL_POISON_FLAG_OVERFLOW        BIT(1)
+#define CXL_POISON_FLAG_SCANNING        BIT(2)
+
+/* Get Poison List: Poison Source */
+#define CXL_POISON_SOURCE_UNKNOWN	0
+#define CXL_POISON_SOURCE_EXTERNAL	1
+#define CXL_POISON_SOURCE_INTERNAL	2
+#define CXL_POISON_SOURCE_INJECTED	3
+#define CXL_POISON_SOURCE_VENDOR	7
+
+/* Inject & Clear Poison  CXL 3.0 Spec 8.2.9.8.4.2/3 */
+struct cxl_mbox_inject_poison {
+	__le64 address;
+};
+
+/* Clear Poison  CXL 3.0 Spec 8.2.9.8.4.3 */
+struct cxl_mbox_clear_poison {
+	__le64 address;
+	u8 write_data[CXL_POISON_LEN_MULT];
+} __packed;
+
+/**
+ * struct cxl_mem_command - Driver representation of a memory device command
+ * @info: Command information as it exists for the UAPI
+ * @opcode: The actual bits used for the mailbox protocol
+ * @flags: Set of flags effecting driver behavior.
+ *
+ *  * %CXL_CMD_FLAG_FORCE_ENABLE: In cases of error, commands with this flag
+ *    will be enabled by the driver regardless of what hardware may have
+ *    advertised.
+ *
+ * The cxl_mem_command is the driver's internal representation of commands that
+ * are supported by the driver. Some of these commands may not be supported by
+ * the hardware. The driver will use @info to validate the fields passed in by
+ * the user then submit the @opcode to the hardware.
+ *
+ * See struct cxl_command_info.
+ */
+struct cxl_mem_command {
+	struct cxl_command_info info;
+	enum cxl_opcode opcode;
+	u32 flags;
+#define CXL_CMD_FLAG_FORCE_ENABLE BIT(0)
+};
+
+#define CXL_PMEM_SEC_STATE_USER_PASS_SET	0x01
+#define CXL_PMEM_SEC_STATE_MASTER_PASS_SET	0x02
+#define CXL_PMEM_SEC_STATE_LOCKED		0x04
+#define CXL_PMEM_SEC_STATE_FROZEN		0x08
+#define CXL_PMEM_SEC_STATE_USER_PLIMIT		0x10
+#define CXL_PMEM_SEC_STATE_MASTER_PLIMIT	0x20
+
+/* set passphrase input payload */
+struct cxl_set_pass {
+	u8 type;
+	u8 reserved[31];
+	/* CXL field using NVDIMM define, same length */
+	u8 old_pass[NVDIMM_PASSPHRASE_LEN];
+	u8 new_pass[NVDIMM_PASSPHRASE_LEN];
+} __packed;
+
+/* disable passphrase input payload */
+struct cxl_disable_pass {
+	u8 type;
+	u8 reserved[31];
+	u8 pass[NVDIMM_PASSPHRASE_LEN];
+} __packed;
+
+/* passphrase secure erase payload */
+struct cxl_pass_erase {
+	u8 type;
+	u8 reserved[31];
+	u8 pass[NVDIMM_PASSPHRASE_LEN];
+} __packed;
+
+enum {
+	CXL_PMEM_SEC_PASS_MASTER = 0,
+	CXL_PMEM_SEC_PASS_USER,
+};
+
+int cxl_internal_send_cmd(struct cxl_mailbox *cxl_mbox,
+			  struct cxl_mbox_cmd *cmd);
+int cxl_dev_state_identify(struct cxl_memdev_state *mds);
+int cxl_await_media_ready(struct cxl_dev_state *cxlds);
+int cxl_enumerate_cmds(struct cxl_memdev_state *mds);
+int cxl_mem_dpa_fetch(struct cxl_memdev_state *mds, struct cxl_dpa_info *info);
+struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev, u64 serial,
+						 u16 dvsec);
+void set_exclusive_cxl_commands(struct cxl_memdev_state *mds,
+				unsigned long *cmds);
+void clear_exclusive_cxl_commands(struct cxl_memdev_state *mds,
+				  unsigned long *cmds);
+void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status);
+void cxl_event_trace_record(struct cxl_memdev *cxlmd,
+			    enum cxl_event_log_type type,
+			    enum cxl_event_type event_type,
+			    const uuid_t *uuid, union cxl_event *evt);
+int cxl_get_dirty_count(struct cxl_memdev_state *mds, u32 *count);
+int cxl_arm_dirty_shutdown(struct cxl_memdev_state *mds);
+int cxl_set_timestamp(struct cxl_memdev_state *mds);
+int cxl_poison_state_init(struct cxl_memdev_state *mds);
+int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len,
+		       struct cxl_region *cxlr);
+int cxl_trigger_poison_list(struct cxl_memdev *cxlmd);
+int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa);
+int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa);
+int cxl_inject_poison_locked(struct cxl_memdev *cxlmd, u64 dpa);
+int cxl_clear_poison_locked(struct cxl_memdev *cxlmd, u64 dpa);
+
+#ifdef CONFIG_CXL_EDAC_MEM_FEATURES
+int devm_cxl_memdev_edac_register(struct cxl_memdev *cxlmd);
+int devm_cxl_region_edac_register(struct cxl_region *cxlr);
+int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, union cxl_event *evt);
+int cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt);
+#else
+static inline int devm_cxl_memdev_edac_register(struct cxl_memdev *cxlmd)
+{ return 0; }
+static inline int devm_cxl_region_edac_register(struct cxl_region *cxlr)
+{ return 0; }
+static inline int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd,
+					  union cxl_event *evt)
+{ return 0; }
+static inline int cxl_store_rec_dram(struct cxl_memdev *cxlmd,
+				     union cxl_event *evt)
+{ return 0; }
+#endif
+
+#ifdef CONFIG_CXL_SUSPEND
+void cxl_mem_active_inc(void);
+void cxl_mem_active_dec(void);
+#else
+static inline void cxl_mem_active_inc(void)
+{
+}
+static inline void cxl_mem_active_dec(void)
+{
+}
+#endif
+
+int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd);
+
+/**
+ * struct cxl_hdm - HDM Decoder registers and cached / decoded capabilities
+ * @regs: mapped registers, see devm_cxl_setup_hdm()
+ * @decoder_count: number of decoders for this port
+ * @target_count: for switch decoders, max downstream port targets
+ * @interleave_mask: interleave granularity capability, see check_interleave_cap()
+ * @iw_cap_mask: bitmask of supported interleave ways, see check_interleave_cap()
+ * @port: mapped cxl_port, see devm_cxl_setup_hdm()
+ */
+struct cxl_hdm {
+	struct cxl_component_regs regs;
+	int decoder_count;
+	unsigned int target_count;
+	unsigned int interleave_mask;
+	unsigned long iw_cap_mask;
+	struct cxl_port *port;
+};
+
+struct seq_file;
+struct dentry *cxl_debugfs_create_dir(const char *dir);
+void cxl_dpa_debug(struct seq_file *file, struct cxl_dev_state *cxlds);
+#endif /* __CXL_MEM_H__ */

linux-7.2.3/drivers/cxl/cxlpci.h

@@ -0,0 +1,117 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2020 Intel Corporation. All rights reserved. */
+#ifndef __CXL_PCI_H__
+#define __CXL_PCI_H__
+#include <linux/pci.h>
+#include "cxl.h"
+
+#define CXL_MEMORY_PROGIF	0x10
+
+/*
+ * NOTE: Currently all the functions which are enabled for CXL require their
+ * vectors to be in the first 16.  Use this as the default max.
+ */
+#define CXL_PCI_DEFAULT_MAX_VECTORS 16
+
+/* 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
+};
+
+/*
+ * Table Access DOE, CDAT Read Entry Response
+ *
+ * Spec refs:
+ *
+ * CXL 3.1 8.1.11, Table 8-14: Read Entry Response
+ * CDAT Specification 1.03: 2 CDAT Data Structures
+ */
+
+struct cdat_header {
+	__le32 length;
+	u8 revision;
+	u8 checksum;
+	u8 reserved[6];
+	__le32 sequence;
+} __packed;
+
+struct cdat_entry_header {
+	u8 type;
+	u8 reserved;
+	__le16 length;
+} __packed;
+
+/*
+ * The DOE CDAT read response contains a CDAT read entry (either the
+ * CDAT header or a structure).
+ */
+union cdat_data {
+	struct cdat_header header;
+	struct cdat_entry_header entry;
+} __packed;
+
+/* There is an additional CDAT response header of 4 bytes. */
+struct cdat_doe_rsp {
+	__le32 doe_header;
+	u8 data[];
+} __packed;
+
+/*
+ * CXL v3.0 6.2.3 Table 6-4
+ * The table indicates that if PCIe Flit Mode is set, then CXL is in 256B flits
+ * mode, otherwise it's 68B flits mode.
+ */
+static inline bool cxl_pci_flit_256(struct pci_dev *pdev)
+{
+	u16 lnksta2;
+
+	pcie_capability_read_word(pdev, PCI_EXP_LNKSTA2, &lnksta2);
+	return lnksta2 & PCI_EXP_LNKSTA2_FLIT;
+}
+
+/*
+ * Assume that the caller has already validated that @pdev has CXL
+ * capabilities, any RCiEP with CXL capabilities is treated as a
+ * Restricted CXL Device (RCD) and finds upstream port and endpoint
+ * registers in a Root Complex Register Block (RCRB).
+ */
+static inline bool is_cxl_restricted(struct pci_dev *pdev)
+{
+	return pci_pcie_type(pdev) == PCI_EXP_TYPE_RC_END;
+}
+
+struct cxl_dev_state;
+void read_cdat_data(struct cxl_port *port);
+
+#ifdef CONFIG_CXL_RAS
+void cxl_cor_error_detected(struct pci_dev *pdev);
+pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
+				    pci_channel_state_t state);
+void devm_cxl_dport_rch_ras_setup(struct cxl_dport *dport);
+void devm_cxl_port_ras_setup(struct cxl_port *port);
+#else
+static inline void cxl_cor_error_detected(struct pci_dev *pdev) { }
+
+static inline pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
+						  pci_channel_state_t state)
+{
+	return PCI_ERS_RESULT_NONE;
+}
+
+static inline void devm_cxl_dport_rch_ras_setup(struct cxl_dport *dport)
+{
+}
+
+static inline void devm_cxl_port_ras_setup(struct cxl_port *port)
+{
+}
+#endif
+
+int cxl_pci_setup_regs(struct pci_dev *pdev, enum cxl_regloc_type type,
+		       struct cxl_register_map *map);
+#endif /* __CXL_PCI_H__ */

linux-7.2.3/drivers/cxl/mem.c

@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include "cxlmem.h"
+#include "cxlpci.h"
+
+/**
+ * DOC: cxl mem
+ *
+ * CXL memory endpoint devices and switches are CXL capable devices that are
+ * participating in CXL.mem protocol. Their functionality builds on top of the
+ * CXL.io protocol that allows enumerating and configuring components via
+ * standard PCI mechanisms.
+ *
+ * The cxl_mem driver owns kicking off the enumeration of this CXL.mem
+ * capability. With the detection of a CXL capable endpoint, the driver will
+ * walk up to find the platform specific port it is connected to, and determine
+ * if there are intervening switches in the path. If there are switches, a
+ * secondary action is to enumerate those (implemented in cxl_core). Finally the
+ * cxl_mem driver adds the device it is bound to as a CXL endpoint-port for use
+ * in higher level operations.
+ */
+
+static void enable_suspend(void *data)
+{
+	cxl_mem_active_dec();
+}
+
+static void remove_debugfs(void *dentry)
+{
+	debugfs_remove_recursive(dentry);
+}
+
+static int cxl_mem_dpa_show(struct seq_file *file, void *data)
+{
+	struct device *dev = file->private;
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+
+	cxl_dpa_debug(file, cxlmd->cxlds);
+
+	return 0;
+}
+
+static int cxl_debugfs_poison_inject(void *data, u64 dpa)
+{
+	struct cxl_memdev *cxlmd = data;
+	int rc;
+
+	ACQUIRE(device_intr, devlock)(&cxlmd->dev);
+	if ((rc = ACQUIRE_ERR(device_intr, &devlock)))
+		return rc;
+
+	return cxl_inject_poison(cxlmd, dpa);
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(cxl_poison_inject_fops, NULL,
+			 cxl_debugfs_poison_inject, "%llx\n");
+
+static int cxl_debugfs_poison_clear(void *data, u64 dpa)
+{
+	struct cxl_memdev *cxlmd = data;
+	int rc;
+
+	ACQUIRE(device_intr, devlock)(&cxlmd->dev);
+	if ((rc = ACQUIRE_ERR(device_intr, &devlock)))
+		return rc;
+
+	return cxl_clear_poison(cxlmd, dpa);
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(cxl_poison_clear_fops, NULL,
+			 cxl_debugfs_poison_clear, "%llx\n");
+
+static void cxl_memdev_poison_enable(struct cxl_memdev_state *mds,
+				     struct cxl_memdev *cxlmd,
+				     struct dentry *dentry)
+{
+	/*
+	 * Avoid poison debugfs for DEVMEM aka accelerators as they rely on
+	 * cxl_memdev_state.
+	 */
+	if (!mds)
+		return;
+
+	if (test_bit(CXL_POISON_ENABLED_INJECT, mds->poison.enabled_cmds))
+		debugfs_create_file("inject_poison", 0200, dentry, cxlmd,
+				    &cxl_poison_inject_fops);
+
+	if (test_bit(CXL_POISON_ENABLED_CLEAR, mds->poison.enabled_cmds))
+		debugfs_create_file("clear_poison", 0200, dentry, cxlmd,
+				    &cxl_poison_clear_fops);
+}
+
+static int cxl_mem_probe(struct device *dev)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct device *endpoint_parent;
+	struct cxl_dport *dport;
+	struct dentry *dentry;
+	int rc;
+
+	if (!cxlds->media_ready)
+		return -EBUSY;
+
+	/*
+	 * Someone is trying to reattach this device after it lost its port
+	 * connection (an endpoint port previously registered by this memdev was
+	 * disabled). This racy check is ok because if the port is still gone,
+	 * no harm done, and if the port hierarchy comes back it will re-trigger
+	 * this probe. Port rescan and memdev detach work share the same
+	 * single-threaded workqueue.
+	 */
+	if (work_pending(&cxlmd->detach_work))
+		return -EBUSY;
+
+	dentry = cxl_debugfs_create_dir(dev_name(dev));
+	debugfs_create_devm_seqfile(dev, "dpamem", dentry, cxl_mem_dpa_show);
+
+	cxl_memdev_poison_enable(mds, cxlmd, dentry);
+
+	rc = devm_add_action_or_reset(dev, remove_debugfs, dentry);
+	if (rc)
+		return rc;
+
+	rc = devm_cxl_enumerate_ports(cxlmd);
+	if (rc)
+		return rc;
+
+	struct cxl_port *parent_port __free(put_cxl_port) =
+		cxl_mem_find_port(cxlmd, &dport);
+	if (!parent_port) {
+		dev_err(dev, "CXL port topology not found\n");
+		return -ENXIO;
+	}
+
+	if (cxl_pmem_size(cxlds) && IS_ENABLED(CONFIG_CXL_PMEM)) {
+		rc = devm_cxl_add_nvdimm(dev, parent_port, cxlmd);
+		if (rc) {
+			if (rc == -ENODEV)
+				dev_info(dev, "PMEM disabled by platform\n");
+			return rc;
+		}
+	}
+
+	if (dport->rch)
+		endpoint_parent = parent_port->uport_dev;
+	else
+		endpoint_parent = &parent_port->dev;
+
+	scoped_guard(device, endpoint_parent) {
+		if (!endpoint_parent->driver) {
+			dev_err(dev, "CXL port topology %s not enabled\n",
+				dev_name(endpoint_parent));
+			return -ENXIO;
+		}
+
+		rc = devm_cxl_add_endpoint(endpoint_parent, cxlmd, dport);
+		if (rc)
+			return rc;
+	}
+
+	if (cxlmd->attach) {
+		rc = cxlmd->attach->probe(cxlmd);
+		if (rc)
+			return rc;
+	}
+
+	rc = devm_cxl_memdev_edac_register(cxlmd);
+	if (rc)
+		dev_dbg(dev, "CXL memdev EDAC registration failed rc=%d\n", rc);
+
+	/*
+	 * The kernel may be operating out of CXL memory on this device,
+	 * there is no spec defined way to determine whether this device
+	 * preserves contents over suspend, and there is no simple way
+	 * to arrange for the suspend image to avoid CXL memory which
+	 * would setup a circular dependency between PCI resume and save
+	 * state restoration.
+	 *
+	 * TODO: support suspend when all the regions this device is
+	 * hosting are locked and covered by the system address map,
+	 * i.e. platform firmware owns restoring the HDM configuration
+	 * that it locked.
+	 */
+	cxl_mem_active_inc();
+	return devm_add_action_or_reset(dev, enable_suspend, NULL);
+}
+
+/**
+ * devm_cxl_add_classdev - Add a CXL memory class-code device
+ * @cxlds: CXL device state to associate with the memdev
+ *
+ * Upon return the device will have had a chance to attach to the
+ * cxl_mem driver, but may fail to attach if the CXL topology is not ready
+ * (hardware CXL link down, or software platform CXL root not attached).
+ *
+ * The parent of the resulting device and the devm context for allocations is
+ * @cxlds->dev.
+ */
+struct cxl_memdev *devm_cxl_add_classdev(struct cxl_dev_state *cxlds)
+{
+	return __devm_cxl_add_memdev(cxlds, NULL);
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_add_classdev, "CXL");
+
+/**
+ * devm_cxl_probe_mem - Add a CXL memory device and probe its region
+ * @cxlds: CXL device state to associate with the memdev
+ * @hpa_range: CXL.mem physical address range result
+ *
+ * Upon return the device will have had a chance to attach to the
+ * cxl_mem driver, but may fail to attach if the CXL topology is not ready
+ * (hardware CXL link down, or software platform CXL root not attached).
+ *
+ * Failure to probe the memdev and/or setup a region for the memdev
+ * results in this function failing.
+ *
+ * The parent of the resulting device and the devm context for allocations is
+ * @cxlds->dev.
+ */
+struct cxl_memdev *devm_cxl_probe_mem(struct cxl_dev_state *cxlds,
+				      struct range *hpa_range)
+{
+	struct cxl_attach_region *attach =
+		devm_kmalloc(cxlds->dev, sizeof(*attach), GFP_KERNEL);
+	struct cxl_memdev *cxlmd;
+
+	if (!attach)
+		return ERR_PTR(-ENOMEM);
+
+	*attach = (struct cxl_attach_region) {
+		.attach = {
+			   .probe = cxl_memdev_attach_region,
+		},
+		.hpa_range = { 0, -1 },
+	};
+
+	cxlmd = __devm_cxl_add_memdev(cxlds, &attach->attach);
+	*hpa_range = attach->hpa_range;
+	return cxlmd;
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_probe_mem, "CXL");
+
+static ssize_t trigger_poison_list_store(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf, size_t len)
+{
+	bool trigger;
+	int rc;
+
+	if (kstrtobool(buf, &trigger) || !trigger)
+		return -EINVAL;
+
+	rc = cxl_trigger_poison_list(to_cxl_memdev(dev));
+
+	return rc ? rc : len;
+}
+static DEVICE_ATTR_WO(trigger_poison_list);
+
+static bool cxl_poison_attr_visible(struct kobject *kobj, struct attribute *a)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+
+	if (!mds ||
+	    !test_bit(CXL_POISON_ENABLED_LIST, mds->poison.enabled_cmds))
+		return false;
+
+	return true;
+}
+
+static umode_t cxl_mem_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	if (a == &dev_attr_trigger_poison_list.attr &&
+	    !cxl_poison_attr_visible(kobj, a))
+		return 0;
+
+	return a->mode;
+}
+
+static struct attribute *cxl_mem_attrs[] = {
+	&dev_attr_trigger_poison_list.attr,
+	NULL
+};
+
+static struct attribute_group cxl_mem_group = {
+	.attrs = cxl_mem_attrs,
+	.is_visible = cxl_mem_visible,
+};
+
+__ATTRIBUTE_GROUPS(cxl_mem);
+
+static struct cxl_driver cxl_mem_driver = {
+	.name = "cxl_mem",
+	.probe = cxl_mem_probe,
+	.id = CXL_DEVICE_MEMORY_EXPANDER,
+	.drv = {
+		.probe_type = PROBE_FORCE_SYNCHRONOUS,
+		.dev_groups = cxl_mem_groups,
+	},
+};
+
+module_cxl_driver(cxl_mem_driver);
+
+MODULE_DESCRIPTION("CXL: Memory Expansion");
+MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS("CXL");
+MODULE_ALIAS_CXL(CXL_DEVICE_MEMORY_EXPANDER);

linux-7.2.3/drivers/cxl/pmem.c

@@ -0,0 +1,562 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2021 Intel Corporation. All rights reserved. */
+#include <linux/libnvdimm.h>
+#include <linux/unaligned.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/ndctl.h>
+#include <linux/async.h>
+#include <linux/slab.h>
+#include <linux/nd.h>
+#include "cxlmem.h"
+#include "cxl.h"
+
+static __read_mostly DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX);
+
+/**
+ * devm_cxl_add_nvdimm_bridge() - add the root of a LIBNVDIMM topology
+ * @host: platform firmware root device
+ * @port: CXL port at the root of a CXL topology
+ *
+ * Return: bridge device that can host cxl_nvdimm objects
+ */
+struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host,
+						     struct cxl_port *port)
+{
+	return __devm_cxl_add_nvdimm_bridge(host, port);
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_add_nvdimm_bridge, "CXL");
+
+static void clear_exclusive(void *mds)
+{
+	clear_exclusive_cxl_commands(mds, exclusive_cmds);
+}
+
+static void unregister_nvdimm(void *nvdimm)
+{
+	nvdimm_delete(nvdimm);
+}
+
+static ssize_t provider_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
+
+	return sysfs_emit(buf, "%s\n", dev_name(&cxl_nvd->dev));
+}
+static DEVICE_ATTR_RO(provider);
+
+static ssize_t id_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
+	struct cxl_dev_state *cxlds = cxl_nvd->cxlmd->cxlds;
+
+	return sysfs_emit(buf, "%lld\n", cxlds->serial);
+}
+static DEVICE_ATTR_RO(id);
+
+static ssize_t dirty_shutdown_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
+
+	return sysfs_emit(buf, "%llu\n", cxl_nvd->dirty_shutdowns);
+}
+static DEVICE_ATTR_RO(dirty_shutdown);
+
+static struct attribute *cxl_dimm_attributes[] = {
+	&dev_attr_id.attr,
+	&dev_attr_provider.attr,
+	&dev_attr_dirty_shutdown.attr,
+	NULL
+};
+
+#define CXL_INVALID_DIRTY_SHUTDOWN_COUNT ULLONG_MAX
+static umode_t cxl_dimm_visible(struct kobject *kobj,
+				struct attribute *a, int n)
+{
+	if (a == &dev_attr_dirty_shutdown.attr) {
+		struct device *dev = kobj_to_dev(kobj);
+		struct nvdimm *nvdimm = to_nvdimm(dev);
+		struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
+
+		if (cxl_nvd->dirty_shutdowns ==
+		    CXL_INVALID_DIRTY_SHUTDOWN_COUNT)
+			return 0;
+	}
+
+	return a->mode;
+}
+
+static const struct attribute_group cxl_dimm_attribute_group = {
+	.name = "cxl",
+	.attrs = cxl_dimm_attributes,
+	.is_visible = cxl_dimm_visible
+};
+
+static const struct attribute_group *cxl_dimm_attribute_groups[] = {
+	&cxl_dimm_attribute_group,
+	NULL
+};
+
+static void cxl_nvdimm_arm_dirty_shutdown_tracking(struct cxl_nvdimm *cxl_nvd)
+{
+	struct cxl_memdev *cxlmd = cxl_nvd->cxlmd;
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+	struct device *dev = &cxl_nvd->dev;
+	u32 count;
+
+	/*
+	 * Dirty tracking is enabled and exposed to the user, only when:
+	 *   - dirty shutdown on the device can be set, and,
+	 *   - the device has a Device GPF DVSEC (albeit unused), and,
+	 *   - the Get Health Info cmd can retrieve the device's dirty count.
+	 */
+	cxl_nvd->dirty_shutdowns = CXL_INVALID_DIRTY_SHUTDOWN_COUNT;
+
+	if (cxl_arm_dirty_shutdown(mds)) {
+		dev_warn(dev, "GPF: could not set dirty shutdown state\n");
+		return;
+	}
+
+	if (!cxl_gpf_get_dvsec(cxlds->dev))
+		return;
+
+	if (cxl_get_dirty_count(mds, &count)) {
+		dev_warn(dev, "GPF: could not retrieve dirty count\n");
+		return;
+	}
+
+	cxl_nvd->dirty_shutdowns = count;
+}
+
+static int cxl_nvdimm_probe(struct device *dev)
+{
+	struct cxl_nvdimm *cxl_nvd = to_cxl_nvdimm(dev);
+	struct cxl_memdev *cxlmd = cxl_nvd->cxlmd;
+	struct cxl_nvdimm_bridge *cxl_nvb = cxlmd->cxl_nvb;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+	unsigned long flags = 0, cmd_mask = 0;
+	struct nvdimm *nvdimm;
+	int rc;
+
+	if (test_bit(CXL_NVD_F_INVALIDATED, &cxl_nvd->flags))
+		return -EBUSY;
+
+	set_exclusive_cxl_commands(mds, exclusive_cmds);
+	rc = devm_add_action_or_reset(dev, clear_exclusive, mds);
+	if (rc)
+		return rc;
+
+	set_bit(NDD_LABELING, &flags);
+	set_bit(NDD_REGISTER_SYNC, &flags);
+	set_bit(ND_CMD_GET_CONFIG_SIZE, &cmd_mask);
+	set_bit(ND_CMD_GET_CONFIG_DATA, &cmd_mask);
+	set_bit(ND_CMD_SET_CONFIG_DATA, &cmd_mask);
+
+	/*
+	 * Set dirty shutdown now, with the expectation that the device
+	 * clear it upon a successful GPF flow. The exception to this
+	 * is upon Viral detection, per CXL 3.2 section 12.4.2.
+	 */
+	cxl_nvdimm_arm_dirty_shutdown_tracking(cxl_nvd);
+
+	nvdimm = __nvdimm_create(cxl_nvb->nvdimm_bus, cxl_nvd,
+				 cxl_dimm_attribute_groups, flags,
+				 cmd_mask, 0, NULL, cxl_nvd->dev_id,
+				 cxl_security_ops, NULL);
+	if (!nvdimm)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, nvdimm);
+	return devm_add_action_or_reset(dev, unregister_nvdimm, nvdimm);
+}
+
+static struct cxl_driver cxl_nvdimm_driver = {
+	.name = "cxl_nvdimm",
+	.probe = cxl_nvdimm_probe,
+	.id = CXL_DEVICE_NVDIMM,
+	.drv = {
+		.suppress_bind_attrs = true,
+	},
+};
+
+static int cxl_pmem_get_config_size(struct cxl_memdev_state *mds,
+				    struct nd_cmd_get_config_size *cmd,
+				    unsigned int buf_len)
+{
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
+
+	if (sizeof(*cmd) > buf_len)
+		return -EINVAL;
+
+	*cmd = (struct nd_cmd_get_config_size){
+		.config_size = mds->lsa_size,
+		.max_xfer =
+			cxl_mbox->payload_size - sizeof(struct cxl_mbox_set_lsa),
+	};
+
+	return 0;
+}
+
+static int cxl_pmem_get_config_data(struct cxl_memdev_state *mds,
+				    struct nd_cmd_get_config_data_hdr *cmd,
+				    unsigned int buf_len)
+{
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
+	struct cxl_mbox_get_lsa get_lsa;
+	struct cxl_mbox_cmd mbox_cmd;
+	int rc;
+
+	if (sizeof(*cmd) > buf_len)
+		return -EINVAL;
+	if (struct_size(cmd, out_buf, cmd->in_length) > buf_len)
+		return -EINVAL;
+
+	get_lsa = (struct cxl_mbox_get_lsa) {
+		.offset = cpu_to_le32(cmd->in_offset),
+		.length = cpu_to_le32(cmd->in_length),
+	};
+	mbox_cmd = (struct cxl_mbox_cmd) {
+		.opcode = CXL_MBOX_OP_GET_LSA,
+		.payload_in = &get_lsa,
+		.size_in = sizeof(get_lsa),
+		.size_out = cmd->in_length,
+		.payload_out = cmd->out_buf,
+	};
+
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
+	cmd->status = 0;
+
+	return rc;
+}
+
+static int cxl_pmem_set_config_data(struct cxl_memdev_state *mds,
+				    struct nd_cmd_set_config_hdr *cmd,
+				    unsigned int buf_len)
+{
+	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
+	struct cxl_mbox_set_lsa *set_lsa;
+	struct cxl_mbox_cmd mbox_cmd;
+	int rc;
+
+	if (sizeof(*cmd) > buf_len)
+		return -EINVAL;
+
+	/* 4-byte status follows the input data in the payload */
+	if (size_add(struct_size(cmd, in_buf, cmd->in_length), 4) > buf_len)
+		return -EINVAL;
+
+	set_lsa =
+		kvzalloc_flex(*set_lsa, data, cmd->in_length);
+	if (!set_lsa)
+		return -ENOMEM;
+
+	*set_lsa = (struct cxl_mbox_set_lsa) {
+		.offset = cpu_to_le32(cmd->in_offset),
+	};
+	memcpy(set_lsa->data, cmd->in_buf, cmd->in_length);
+	mbox_cmd = (struct cxl_mbox_cmd) {
+		.opcode = CXL_MBOX_OP_SET_LSA,
+		.payload_in = set_lsa,
+		.size_in = struct_size(set_lsa, data, cmd->in_length),
+	};
+
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
+
+	/*
+	 * Set "firmware" status (4-packed bytes at the end of the input
+	 * payload.
+	 */
+	put_unaligned(0, (u32 *) &cmd->in_buf[cmd->in_length]);
+	kvfree(set_lsa);
+
+	return rc;
+}
+
+static int cxl_pmem_nvdimm_ctl(struct nvdimm *nvdimm, unsigned int cmd,
+			       void *buf, unsigned int buf_len)
+{
+	struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
+	unsigned long cmd_mask = nvdimm_cmd_mask(nvdimm);
+	struct cxl_memdev *cxlmd = cxl_nvd->cxlmd;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+
+	if (!test_bit(cmd, &cmd_mask))
+		return -ENOTTY;
+
+	switch (cmd) {
+	case ND_CMD_GET_CONFIG_SIZE:
+		return cxl_pmem_get_config_size(mds, buf, buf_len);
+	case ND_CMD_GET_CONFIG_DATA:
+		return cxl_pmem_get_config_data(mds, buf, buf_len);
+	case ND_CMD_SET_CONFIG_DATA:
+		return cxl_pmem_set_config_data(mds, buf, buf_len);
+	default:
+		return -ENOTTY;
+	}
+}
+
+static int cxl_pmem_ctl(struct nvdimm_bus_descriptor *nd_desc,
+			struct nvdimm *nvdimm, unsigned int cmd, void *buf,
+			unsigned int buf_len, int *cmd_rc)
+{
+	/*
+	 * No firmware response to translate, let the transport error
+	 * code take precedence.
+	 */
+	*cmd_rc = 0;
+
+	if (!nvdimm)
+		return -ENOTTY;
+	return cxl_pmem_nvdimm_ctl(nvdimm, cmd, buf, buf_len);
+}
+
+static int detach_nvdimm(struct device *dev, void *data)
+{
+	struct cxl_nvdimm *cxl_nvd;
+	bool release = false;
+
+	if (!is_cxl_nvdimm(dev))
+		return 0;
+
+	scoped_guard(device, dev) {
+		if (dev->driver) {
+			cxl_nvd = to_cxl_nvdimm(dev);
+			if (cxl_nvd->cxlmd && cxl_nvd->cxlmd->cxl_nvb == data) {
+				release = true;
+				set_bit(CXL_NVD_F_INVALIDATED, &cxl_nvd->flags);
+			}
+		}
+	}
+	if (release)
+		device_release_driver(dev);
+	return 0;
+}
+
+static void unregister_nvdimm_bus(void *_cxl_nvb)
+{
+	struct cxl_nvdimm_bridge *cxl_nvb = _cxl_nvb;
+	struct nvdimm_bus *nvdimm_bus = cxl_nvb->nvdimm_bus;
+
+	bus_for_each_dev(&cxl_bus_type, NULL, cxl_nvb, detach_nvdimm);
+
+	cxl_nvb->nvdimm_bus = NULL;
+	nvdimm_bus_unregister(nvdimm_bus);
+}
+
+static int cxl_nvdimm_bridge_probe(struct device *dev)
+{
+	struct cxl_nvdimm_bridge *cxl_nvb = to_cxl_nvdimm_bridge(dev);
+
+	cxl_nvb->nd_desc = (struct nvdimm_bus_descriptor) {
+		.provider_name = "CXL",
+		.module = THIS_MODULE,
+		.ndctl = cxl_pmem_ctl,
+	};
+
+	cxl_nvb->nvdimm_bus =
+		nvdimm_bus_register(&cxl_nvb->dev, &cxl_nvb->nd_desc);
+
+	if (!cxl_nvb->nvdimm_bus)
+		return -ENOMEM;
+
+	return devm_add_action_or_reset(dev, unregister_nvdimm_bus, cxl_nvb);
+}
+
+static struct cxl_driver cxl_nvdimm_bridge_driver = {
+	.name = "cxl_nvdimm_bridge",
+	.probe = cxl_nvdimm_bridge_probe,
+	.id = CXL_DEVICE_NVDIMM_BRIDGE,
+	.drv = {
+		.probe_type = PROBE_FORCE_SYNCHRONOUS,
+		.suppress_bind_attrs = true,
+	},
+};
+
+static void unregister_nvdimm_region(void *nd_region)
+{
+	nvdimm_region_delete(nd_region);
+}
+
+static void cxlr_pmem_remove_resource(void *res)
+{
+	remove_resource(res);
+}
+
+struct cxl_pmem_region_info {
+	u64 offset;
+	u64 serial;
+};
+
+static int cxl_pmem_region_probe(struct device *dev)
+{
+	struct nd_mapping_desc mappings[CXL_DECODER_MAX_INTERLEAVE];
+	struct cxl_pmem_region *cxlr_pmem = to_cxl_pmem_region(dev);
+	struct cxl_region *cxlr = cxlr_pmem->cxlr;
+	struct cxl_nvdimm_bridge *cxl_nvb = cxlr->cxl_nvb;
+	struct cxl_pmem_region_info *info = NULL;
+	struct nd_interleave_set *nd_set;
+	struct nd_region_desc ndr_desc;
+	struct cxl_nvdimm *cxl_nvd;
+	struct nvdimm *nvdimm;
+	struct resource *res;
+	int rc, i = 0;
+
+	memset(&mappings, 0, sizeof(mappings));
+	memset(&ndr_desc, 0, sizeof(ndr_desc));
+
+	res = devm_kzalloc(dev, sizeof(*res), GFP_KERNEL);
+	if (!res)
+		return -ENOMEM;
+
+	res->name = "Persistent Memory";
+	res->start = cxlr_pmem->hpa_range.start;
+	res->end = cxlr_pmem->hpa_range.end;
+	res->flags = IORESOURCE_MEM;
+	res->desc = IORES_DESC_PERSISTENT_MEMORY;
+
+	rc = insert_resource(&iomem_resource, res);
+	if (rc)
+		return rc;
+
+	rc = devm_add_action_or_reset(dev, cxlr_pmem_remove_resource, res);
+	if (rc)
+		return rc;
+
+	ndr_desc.res = res;
+	ndr_desc.provider_data = cxlr_pmem;
+
+	ndr_desc.numa_node = memory_add_physaddr_to_nid(res->start);
+	ndr_desc.target_node = phys_to_target_node(res->start);
+	if (ndr_desc.target_node == NUMA_NO_NODE) {
+		ndr_desc.target_node = ndr_desc.numa_node;
+		dev_dbg(&cxlr->dev, "changing target node from %d to %d",
+			NUMA_NO_NODE, ndr_desc.target_node);
+	}
+
+	nd_set = devm_kzalloc(dev, sizeof(*nd_set), GFP_KERNEL);
+	if (!nd_set)
+		return -ENOMEM;
+
+	ndr_desc.memregion = cxlr->id;
+	set_bit(ND_REGION_CXL, &ndr_desc.flags);
+	set_bit(ND_REGION_PERSIST_MEMCTRL, &ndr_desc.flags);
+
+	info = kmalloc_objs(*info, cxlr_pmem->nr_mappings);
+	if (!info)
+		return -ENOMEM;
+
+	for (i = 0; i < cxlr_pmem->nr_mappings; i++) {
+		struct cxl_pmem_region_mapping *m = &cxlr_pmem->mapping[i];
+		struct cxl_memdev *cxlmd = m->cxlmd;
+		struct cxl_dev_state *cxlds = cxlmd->cxlds;
+
+		cxl_nvd = cxlmd->cxl_nvd;
+		nvdimm = dev_get_drvdata(&cxl_nvd->dev);
+		if (!nvdimm) {
+			dev_dbg(dev, "[%d]: %s: no nvdimm found\n", i,
+				dev_name(&cxlmd->dev));
+			rc = -ENODEV;
+			goto out_nvd;
+		}
+
+		if (cxlds->serial == 0) {
+			/* include missing alongside invalid in this error message. */
+			dev_err(dev, "%s: invalid or missing serial number\n",
+				dev_name(&cxlmd->dev));
+			rc = -ENXIO;
+			goto out_nvd;
+		}
+		info[i].serial = cxlds->serial;
+		info[i].offset = m->start;
+
+		m->cxl_nvd = cxl_nvd;
+		mappings[i] = (struct nd_mapping_desc) {
+			.nvdimm = nvdimm,
+			.start = m->start,
+			.size = m->size,
+			.position = i,
+		};
+	}
+	ndr_desc.num_mappings = cxlr_pmem->nr_mappings;
+	ndr_desc.mapping = mappings;
+
+	/*
+	 * TODO enable CXL labels which skip the need for 'interleave-set cookie'
+	 */
+	nd_set->cookie1 =
+		nd_fletcher64(info, sizeof(*info) * cxlr_pmem->nr_mappings, 0);
+	nd_set->cookie2 = nd_set->cookie1;
+	ndr_desc.nd_set = nd_set;
+
+	cxlr_pmem->nd_region =
+		nvdimm_pmem_region_create(cxl_nvb->nvdimm_bus, &ndr_desc);
+	if (!cxlr_pmem->nd_region) {
+		rc = -ENOMEM;
+		goto out_nvd;
+	}
+
+	rc = devm_add_action_or_reset(dev, unregister_nvdimm_region,
+				      cxlr_pmem->nd_region);
+out_nvd:
+	kfree(info);
+
+	return rc;
+}
+
+static struct cxl_driver cxl_pmem_region_driver = {
+	.name = "cxl_pmem_region",
+	.probe = cxl_pmem_region_probe,
+	.id = CXL_DEVICE_PMEM_REGION,
+	.drv = {
+		.suppress_bind_attrs = true,
+	},
+};
+
+static __init int cxl_pmem_init(void)
+{
+	int rc;
+
+	set_bit(CXL_MEM_COMMAND_ID_SET_SHUTDOWN_STATE, exclusive_cmds);
+	set_bit(CXL_MEM_COMMAND_ID_SET_LSA, exclusive_cmds);
+
+	rc = cxl_driver_register(&cxl_nvdimm_bridge_driver);
+	if (rc)
+		return rc;
+
+	rc = cxl_driver_register(&cxl_nvdimm_driver);
+	if (rc)
+		goto err_nvdimm;
+
+	rc = cxl_driver_register(&cxl_pmem_region_driver);
+	if (rc)
+		goto err_region;
+
+	return 0;
+
+err_region:
+	cxl_driver_unregister(&cxl_nvdimm_driver);
+err_nvdimm:
+	cxl_driver_unregister(&cxl_nvdimm_bridge_driver);
+	return rc;
+}
+
+static __exit void cxl_pmem_exit(void)
+{
+	cxl_driver_unregister(&cxl_pmem_region_driver);
+	cxl_driver_unregister(&cxl_nvdimm_driver);
+	cxl_driver_unregister(&cxl_nvdimm_bridge_driver);
+}
+
+MODULE_DESCRIPTION("CXL PMEM: Persistent Memory Support");
+MODULE_LICENSE("GPL v2");
+subsys_initcall(cxl_pmem_init);
+module_exit(cxl_pmem_exit);
+MODULE_IMPORT_NS("CXL");
+MODULE_ALIAS_CXL(CXL_DEVICE_NVDIMM_BRIDGE);
+MODULE_ALIAS_CXL(CXL_DEVICE_NVDIMM);
+MODULE_ALIAS_CXL(CXL_DEVICE_PMEM_REGION);

linux-7.2.3/drivers/cxl/pmu.h

@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright(c) 2023 Huawei
+ * CXL Specification rev 3.0 Setion 8.2.7 (CPMU Register Interface)
+ */
+#ifndef CXL_PMU_H
+#define CXL_PMU_H
+#include <linux/device.h>
+
+enum cxl_pmu_type {
+	CXL_PMU_MEMDEV,
+};
+
+#define CXL_PMU_REGMAP_SIZE 0xe00 /* Table 8-32 CXL 3.0 specification */
+struct cxl_pmu {
+	struct device dev;
+	void __iomem *base;
+	int assoc_id;
+	int index;
+	enum cxl_pmu_type type;
+};
+
+#define to_cxl_pmu(dev) container_of(dev, struct cxl_pmu, dev)
+struct cxl_pmu_regs;
+int devm_cxl_pmu_add(struct device *parent, struct cxl_pmu_regs *regs,
+		     int assoc_id, int idx, enum cxl_pmu_type type);
+
+#endif

linux-7.2.3/drivers/cxl/port.c

@@ -0,0 +1,344 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+#include <linux/aer.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include "cxlmem.h"
+#include "cxlpci.h"
+
+/**
+ * DOC: cxl port
+ *
+ * The port driver enumerates dport via PCI and scans for HDM
+ * (Host-managed-Device-Memory) decoder resources via the
+ * @component_reg_phys value passed in by the agent that registered the
+ * port. All descendant ports of a CXL root port (described by platform
+ * firmware) are managed in this drivers context. Each driver instance
+ * is responsible for tearing down the driver context of immediate
+ * descendant ports. The locking for this is validated by
+ * CONFIG_PROVE_LOCKING.
+ *
+ * The primary service this driver provides is presenting APIs to other
+ * drivers to utilize the decoders, and indicating to userspace (via bind
+ * status) the connectivity of the CXL.mem protocol throughout the
+ * PCIe topology.
+ */
+
+static void schedule_detach(void *cxlmd)
+{
+	schedule_cxl_memdev_detach(cxlmd);
+}
+
+static int discover_region(struct device *dev, void *unused)
+{
+	struct cxl_endpoint_decoder *cxled;
+	int rc;
+
+	if (!is_endpoint_decoder(dev))
+		return 0;
+
+	cxled = to_cxl_endpoint_decoder(dev);
+	if ((cxled->cxld.flags & CXL_DECODER_F_ENABLE) == 0)
+		return 0;
+
+	if (cxled->state != CXL_DECODER_STATE_AUTO)
+		return 0;
+
+	/*
+	 * Region enumeration is opportunistic, if this add-event fails,
+	 * continue to the next endpoint decoder.
+	 */
+	rc = cxl_add_to_region(cxled);
+	if (rc)
+		dev_dbg(dev, "failed to add to region: %#llx-%#llx\n",
+			cxled->cxld.hpa_range.start, cxled->cxld.hpa_range.end);
+
+	return 0;
+}
+
+static int cxl_switch_port_probe(struct cxl_port *port)
+{
+	/* Reset nr_dports for rebind of driver */
+	port->nr_dports = 0;
+
+	/* Cache the data early to ensure is_visible() works */
+	read_cdat_data(port);
+
+	return 0;
+}
+
+static int cxl_ras_unmask(struct cxl_port *port)
+{
+	struct pci_dev *pdev;
+	void __iomem *addr;
+	u32 orig_val, val, mask;
+	u16 cap;
+	int rc;
+
+	if (!dev_is_pci(port->uport_dev))
+		return 0;
+	pdev = to_pci_dev(port->uport_dev);
+
+	if (!port->regs.ras) {
+		pci_dbg(pdev, "No RAS registers.\n");
+		return 0;
+	}
+
+	/* BIOS has PCIe AER error control */
+	if (!pcie_aer_is_native(pdev))
+		return 0;
+
+	rc = pcie_capability_read_word(pdev, PCI_EXP_DEVCTL, &cap);
+	if (rc)
+		return rc;
+
+	if (cap & PCI_EXP_DEVCTL_URRE) {
+		addr = port->regs.ras + CXL_RAS_UNCORRECTABLE_MASK_OFFSET;
+		orig_val = readl(addr);
+
+		mask = CXL_RAS_UNCORRECTABLE_MASK_MASK |
+		       CXL_RAS_UNCORRECTABLE_MASK_F256B_MASK;
+		val = orig_val & ~mask;
+		writel(val, addr);
+		pci_dbg(pdev, "Uncorrectable RAS Errors Mask: %#x -> %#x\n",
+			orig_val, val);
+	}
+
+	if (cap & PCI_EXP_DEVCTL_CERE) {
+		addr = port->regs.ras + CXL_RAS_CORRECTABLE_MASK_OFFSET;
+		orig_val = readl(addr);
+		val = orig_val & ~CXL_RAS_CORRECTABLE_MASK_MASK;
+		writel(val, addr);
+		pci_dbg(pdev, "Correctable RAS Errors Mask: %#x -> %#x\n",
+			orig_val, val);
+	}
+
+	return 0;
+}
+
+static int cxl_endpoint_port_probe(struct cxl_port *port)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
+	struct cxl_dport *dport = port->parent_dport;
+	int rc;
+
+	/* Cache the data early to ensure is_visible() works */
+	read_cdat_data(port);
+	cxl_endpoint_parse_cdat(port);
+
+	get_device(&cxlmd->dev);
+	rc = devm_add_action_or_reset(&port->dev, schedule_detach, cxlmd);
+	if (rc)
+		return rc;
+
+	rc = devm_cxl_endpoint_decoders_setup(port);
+	if (rc)
+		return rc;
+
+	/*
+	 * With VH (CXL Virtual Host) topology the cxl_port::add_dport() method
+	 * handles RAS setup for downstream ports. With RCH (CXL Restricted CXL
+	 * Host) topologies the downstream port is enumerated early by platform
+	 * firmware, but the RCRB (root complex register block) is not mapped
+	 * until after the cxl_pci driver attaches to the RCIeP (root complex
+	 * integrated endpoint).
+	 */
+	if (dport->rch)
+		devm_cxl_dport_rch_ras_setup(dport);
+
+	devm_cxl_port_ras_setup(port);
+	if (cxl_ras_unmask(port))
+		dev_dbg(&port->dev, "failed to unmask RAS interrupts\n");
+
+	/*
+	 * Now that all endpoint decoders are successfully enumerated, try to
+	 * assemble regions from committed decoders
+	 */
+	device_for_each_child(&port->dev, NULL, discover_region);
+
+	return 0;
+}
+
+static int cxl_port_probe(struct device *dev)
+{
+	struct cxl_port *port = to_cxl_port(dev);
+
+	if (is_cxl_endpoint(port))
+		return cxl_endpoint_port_probe(port);
+	return cxl_switch_port_probe(port);
+}
+
+static ssize_t CDAT_read(struct file *filp, struct kobject *kobj,
+			 const struct bin_attribute *bin_attr, char *buf,
+			 loff_t offset, size_t count)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct cxl_port *port = to_cxl_port(dev);
+
+	if (!port->cdat_available)
+		return -ENXIO;
+
+	if (!port->cdat.table)
+		return 0;
+
+	return memory_read_from_buffer(buf, count, &offset,
+				       port->cdat.table,
+				       port->cdat.length);
+}
+
+static const BIN_ATTR_ADMIN_RO(CDAT, 0);
+
+static umode_t cxl_port_bin_attr_is_visible(struct kobject *kobj,
+					    const struct bin_attribute *attr, int i)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct cxl_port *port = to_cxl_port(dev);
+
+	if ((attr == &bin_attr_CDAT) && port->cdat_available)
+		return attr->attr.mode;
+
+	return 0;
+}
+
+static const struct bin_attribute *const cxl_cdat_bin_attributes[] = {
+	&bin_attr_CDAT,
+	NULL,
+};
+
+static const struct attribute_group cxl_cdat_attribute_group = {
+	.bin_attrs = cxl_cdat_bin_attributes,
+	.is_bin_visible = cxl_port_bin_attr_is_visible,
+};
+
+static const struct attribute_group *cxl_port_attribute_groups[] = {
+	&cxl_cdat_attribute_group,
+	NULL,
+};
+
+/* note this implicitly casts the group back to its @port */
+DEFINE_FREE(cxl_port_release_dr_group, struct cxl_port *,
+	    if (_T) devres_release_group(&_T->dev, _T))
+
+static struct cxl_dport *cxl_port_add_dport(struct cxl_port *port,
+					    struct device *dport_dev)
+{
+	struct cxl_dport *dport;
+	int rc;
+
+	/* Temp group for all "first dport" and "per dport" setup actions */
+	void *port_dr_group __free(cxl_port_release_dr_group) =
+		devres_open_group(&port->dev, port, GFP_KERNEL);
+	if (!port_dr_group)
+		return ERR_PTR(-ENOMEM);
+
+	if (port->nr_dports == 0) {
+		/*
+		 * Some host bridges are known to not have component regsisters
+		 * available until a root port has trained CXL. Perform that
+		 * setup now.
+		 */
+		rc = cxl_port_setup_regs(port, port->component_reg_phys);
+		if (rc)
+			return ERR_PTR(rc);
+
+		rc = devm_cxl_switch_port_decoders_setup(port);
+		if (rc)
+			return ERR_PTR(rc);
+
+		/*
+		 * RAS setup is optional, either driver operation can continue
+		 * on failure, or the device does not implement RAS registers.
+		 */
+		devm_cxl_port_ras_setup(port);
+	}
+
+	dport = devm_cxl_add_dport_by_dev(port, dport_dev);
+	if (IS_ERR(dport))
+		return dport;
+
+	/* This group was only needed for early exit above */
+	devres_remove_group(&port->dev, no_free_ptr(port_dr_group));
+
+	cxl_switch_parse_cdat(dport);
+
+	/* New dport added, update the decoder targets */
+	cxl_port_update_decoder_targets(port, dport);
+
+	dev_dbg(&port->dev, "dport%d:%s added\n", dport->port_id,
+		dev_name(dport_dev));
+
+	return dport;
+}
+
+static struct cxl_driver cxl_port_driver = {
+	.name = "cxl_port",
+	.probe = cxl_port_probe,
+	.add_dport = cxl_port_add_dport,
+	.id = CXL_DEVICE_PORT,
+	.drv = {
+		.probe_type = PROBE_FORCE_SYNCHRONOUS,
+		.dev_groups = cxl_port_attribute_groups,
+	},
+};
+
+int devm_cxl_add_endpoint(struct device *host, struct cxl_memdev *cxlmd,
+			  struct cxl_dport *parent_dport)
+{
+	struct cxl_port *parent_port = parent_dport->port;
+	struct cxl_port *endpoint, *iter, *down;
+	int rc;
+
+	/*
+	 * Now that the path to the root is established record all the
+	 * intervening ports in the chain.
+	 */
+	for (iter = parent_port, down = NULL; !is_cxl_root(iter);
+	     down = iter, iter = to_cxl_port(iter->dev.parent)) {
+		struct cxl_ep *ep;
+
+		ep = cxl_ep_load(iter, cxlmd);
+		ep->next = down;
+	}
+
+	/* Note: endpoint port component registers are derived from @cxlds */
+	endpoint = devm_cxl_add_port(host, &cxlmd->dev, CXL_RESOURCE_NONE,
+				     parent_dport);
+	if (IS_ERR(endpoint))
+		return PTR_ERR(endpoint);
+
+	rc = cxl_endpoint_autoremove(cxlmd, endpoint);
+	if (rc)
+		return rc;
+
+	if (!endpoint->dev.driver) {
+		dev_err(&cxlmd->dev, "%s failed probe\n",
+			dev_name(&endpoint->dev));
+		return -ENXIO;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_FOR_MODULES(devm_cxl_add_endpoint, "cxl_mem");
+
+static int __init cxl_port_init(void)
+{
+	return cxl_driver_register(&cxl_port_driver);
+}
+/*
+ * Be ready to immediately enable ports emitted by the platform CXL root
+ * (e.g. cxl_acpi) when CONFIG_CXL_PORT=y.
+ */
+subsys_initcall(cxl_port_init);
+
+static void __exit cxl_port_exit(void)
+{
+	cxl_driver_unregister(&cxl_port_driver);
+}
+module_exit(cxl_port_exit);
+
+MODULE_DESCRIPTION("CXL: Port enumeration and services");
+MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS("CXL");
+MODULE_ALIAS_CXL(CXL_DEVICE_PORT);

linux-7.2.3/drivers/cxl/security.c

@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+#include <linux/libnvdimm.h>
+#include <linux/unaligned.h>
+#include <linux/module.h>
+#include <linux/async.h>
+#include <linux/slab.h>
+#include <linux/memregion.h>
+#include "cxlmem.h"
+#include "cxl.h"
+
+static unsigned long cxl_pmem_get_security_flags(struct nvdimm *nvdimm,
+						 enum nvdimm_passphrase_type ptype)
+{
+	struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
+	struct cxl_memdev *cxlmd = cxl_nvd->cxlmd;
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
+	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
+	unsigned long security_flags = 0;
+	struct cxl_get_security_output {
+		__le32 flags;
+	} out;
+	struct cxl_mbox_cmd mbox_cmd;
+	u32 sec_out;
+	int rc;
+
+	mbox_cmd = (struct cxl_mbox_cmd) {
+		.opcode = CXL_MBOX_OP_GET_SECURITY_STATE,
+		.size_out = sizeof(out),
+		.payload_out = &out,
+	};
+
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
+	if (rc < 0)
+		return 0;
+
+	sec_out = le32_to_cpu(out.flags);
+	/* cache security state */
+	mds->security.state = sec_out;
+
+	if (ptype == NVDIMM_MASTER) {
+		if (sec_out & CXL_PMEM_SEC_STATE_MASTER_PASS_SET)
+			set_bit(NVDIMM_SECURITY_UNLOCKED, &security_flags);
+		else
+			set_bit(NVDIMM_SECURITY_DISABLED, &security_flags);
+		if (sec_out & CXL_PMEM_SEC_STATE_MASTER_PLIMIT)
+			set_bit(NVDIMM_SECURITY_FROZEN, &security_flags);
+		return security_flags;
+	}
+
+	if (sec_out & CXL_PMEM_SEC_STATE_USER_PASS_SET) {
+		if (sec_out & CXL_PMEM_SEC_STATE_FROZEN ||
+		    sec_out & CXL_PMEM_SEC_STATE_USER_PLIMIT)
+			set_bit(NVDIMM_SECURITY_FROZEN, &security_flags);
+
+		if (sec_out & CXL_PMEM_SEC_STATE_LOCKED)
+			set_bit(NVDIMM_SECURITY_LOCKED, &security_flags);
+		else
+			set_bit(NVDIMM_SECURITY_UNLOCKED, &security_flags);
+	} else {
+		set_bit(NVDIMM_SECURITY_DISABLED, &security_flags);
+	}
+
+	return security_flags;
+}
+
+static int cxl_pmem_security_change_key(struct nvdimm *nvdimm,
+					const struct nvdimm_key_data *old_data,
+					const struct nvdimm_key_data *new_data,
+					enum nvdimm_passphrase_type ptype)
+{
+	struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
+	struct cxl_memdev *cxlmd = cxl_nvd->cxlmd;
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
+	struct cxl_mbox_cmd mbox_cmd;
+	struct cxl_set_pass set_pass;
+
+	set_pass = (struct cxl_set_pass) {
+		.type = ptype == NVDIMM_MASTER ? CXL_PMEM_SEC_PASS_MASTER :
+						 CXL_PMEM_SEC_PASS_USER,
+	};
+	memcpy(set_pass.old_pass, old_data->data, NVDIMM_PASSPHRASE_LEN);
+	memcpy(set_pass.new_pass, new_data->data, NVDIMM_PASSPHRASE_LEN);
+
+	mbox_cmd = (struct cxl_mbox_cmd) {
+		.opcode = CXL_MBOX_OP_SET_PASSPHRASE,
+		.size_in = sizeof(set_pass),
+		.payload_in = &set_pass,
+	};
+
+	return cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
+}
+
+static int __cxl_pmem_security_disable(struct nvdimm *nvdimm,
+				       const struct nvdimm_key_data *key_data,
+				       enum nvdimm_passphrase_type ptype)
+{
+	struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
+	struct cxl_memdev *cxlmd = cxl_nvd->cxlmd;
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
+	struct cxl_disable_pass dis_pass;
+	struct cxl_mbox_cmd mbox_cmd;
+
+	dis_pass = (struct cxl_disable_pass) {
+		.type = ptype == NVDIMM_MASTER ? CXL_PMEM_SEC_PASS_MASTER :
+						 CXL_PMEM_SEC_PASS_USER,
+	};
+	memcpy(dis_pass.pass, key_data->data, NVDIMM_PASSPHRASE_LEN);
+
+	mbox_cmd = (struct cxl_mbox_cmd) {
+		.opcode = CXL_MBOX_OP_DISABLE_PASSPHRASE,
+		.size_in = sizeof(dis_pass),
+		.payload_in = &dis_pass,
+	};
+
+	return cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
+}
+
+static int cxl_pmem_security_disable(struct nvdimm *nvdimm,
+				     const struct nvdimm_key_data *key_data)
+{
+	return __cxl_pmem_security_disable(nvdimm, key_data, NVDIMM_USER);
+}
+
+static int cxl_pmem_security_disable_master(struct nvdimm *nvdimm,
+					    const struct nvdimm_key_data *key_data)
+{
+	return __cxl_pmem_security_disable(nvdimm, key_data, NVDIMM_MASTER);
+}
+
+static int cxl_pmem_security_freeze(struct nvdimm *nvdimm)
+{
+	struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
+	struct cxl_memdev *cxlmd = cxl_nvd->cxlmd;
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
+	struct cxl_mbox_cmd mbox_cmd = {
+		.opcode = CXL_MBOX_OP_FREEZE_SECURITY,
+	};
+
+	return cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
+}
+
+static int cxl_pmem_security_unlock(struct nvdimm *nvdimm,
+				    const struct nvdimm_key_data *key_data)
+{
+	struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
+	struct cxl_memdev *cxlmd = cxl_nvd->cxlmd;
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
+	u8 pass[NVDIMM_PASSPHRASE_LEN];
+	struct cxl_mbox_cmd mbox_cmd;
+	int rc;
+
+	memcpy(pass, key_data->data, NVDIMM_PASSPHRASE_LEN);
+	mbox_cmd = (struct cxl_mbox_cmd) {
+		.opcode = CXL_MBOX_OP_UNLOCK,
+		.size_in = NVDIMM_PASSPHRASE_LEN,
+		.payload_in = pass,
+	};
+
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
+	if (rc < 0)
+		return rc;
+
+	return 0;
+}
+
+static int cxl_pmem_security_passphrase_erase(struct nvdimm *nvdimm,
+					      const struct nvdimm_key_data *key,
+					      enum nvdimm_passphrase_type ptype)
+{
+	struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
+	struct cxl_memdev *cxlmd = cxl_nvd->cxlmd;
+	struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox;
+	struct cxl_mbox_cmd mbox_cmd;
+	struct cxl_pass_erase erase;
+	int rc;
+
+	erase = (struct cxl_pass_erase) {
+		.type = ptype == NVDIMM_MASTER ? CXL_PMEM_SEC_PASS_MASTER :
+						 CXL_PMEM_SEC_PASS_USER,
+	};
+	memcpy(erase.pass, key->data, NVDIMM_PASSPHRASE_LEN);
+	mbox_cmd = (struct cxl_mbox_cmd) {
+		.opcode = CXL_MBOX_OP_PASSPHRASE_SECURE_ERASE,
+		.size_in = sizeof(erase),
+		.payload_in = &erase,
+	};
+
+	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
+	if (rc < 0)
+		return rc;
+
+	return 0;
+}
+
+static const struct nvdimm_security_ops __cxl_security_ops = {
+	.get_flags = cxl_pmem_get_security_flags,
+	.change_key = cxl_pmem_security_change_key,
+	.disable = cxl_pmem_security_disable,
+	.freeze = cxl_pmem_security_freeze,
+	.unlock = cxl_pmem_security_unlock,
+	.erase = cxl_pmem_security_passphrase_erase,
+	.disable_master = cxl_pmem_security_disable_master,
+};
+
+const struct nvdimm_security_ops *cxl_security_ops = &__cxl_security_ops;