Merge tag 'cxl-for-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl

Pull Compute Express Link (CXL) updates from Dan Williams:
 "To date Linux has been dependent on platform-firmware to map CXL RAM
  regions and handle events / errors from devices. With this update we
  can now parse / update the CXL memory layout, and report events /
  errors from devices. This is a precursor for the CXL subsystem to
  handle the end-to-end "RAS" flow for CXL memory. i.e. the flow that
  for DDR-attached-DRAM is handled by the EDAC driver where it maps
  system physical address events to a field-replaceable-unit (FRU /
  endpoint device). In general, CXL has the potential to standardize
  what has historically been a pile of memory-controller-specific error
  handling logic.

  Another change of note is the default policy for handling RAM-backed
  device-dax instances. Previously the default access mode was "device",
  mmap(2) a device special file to access memory. The new default is
  "kmem" where the address range is assigned to the core-mm via
  add_memory_driver_managed(). This saves typical users from wondering
  why their platform memory is not visible via free(1) and stuck behind
  a device-file. At the same time it allows expert users to deploy
  policy to, for example, get dedicated access to high performance
  memory, or hide low performance memory from general purpose kernel
  allocations. This affects not only CXL, but also systems with
  high-bandwidth-memory that platform-firmware tags with the
  EFI_MEMORY_SP (special purpose) designation.

  Summary:

   - CXL RAM region enumeration: instantiate 'struct cxl_region' objects
     for platform firmware created memory regions

   - CXL RAM region provisioning: complement the existing PMEM region
     creation support with RAM region support

   - "Soft Reservation" policy change: Online (memory hot-add)
     soft-reserved memory (EFI_MEMORY_SP) by default, but still allow
     for setting aside such memory for dedicated access via device-dax.

   - CXL Events and Interrupts: Takeover CXL event handling from
     platform-firmware (ACPI calls this CXL Memory Error Reporting) and
     export CXL Events via Linux Trace Events.

   - Convey CXL _OSC results to drivers: Similar to PCI, let the CXL
     subsystem interrogate the result of CXL _OSC negotiation.

   - Emulate CXL DVSEC Range Registers as "decoders": Allow for
     first-generation devices that pre-date the definition of the CXL
     HDM Decoder Capability to translate the CXL DVSEC Range Registers
     into 'struct cxl_decoder' objects.

   - Set timestamp: Per spec, set the device timestamp in case of
     hotplug, or if platform-firwmare failed to set it.

   - General fixups: linux-next build issues, non-urgent fixes for
     pre-production hardware, unit test fixes, spelling and debug
     message improvements"

* tag 'cxl-for-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl: (66 commits)
  dax/kmem: Fix leak of memory-hotplug resources
  cxl/mem: Add kdoc param for event log driver state
  cxl/trace: Add serial number to trace points
  cxl/trace: Add host output to trace points
  cxl/trace: Standardize device information output
  cxl/pci: Remove locked check for dvsec_range_allowed()
  cxl/hdm: Add emulation when HDM decoders are not committed
  cxl/hdm: Create emulated cxl_hdm for devices that do not have HDM decoders
  cxl/hdm: Emulate HDM decoder from DVSEC range registers
  cxl/pci: Refactor cxl_hdm_decode_init()
  cxl/port: Export cxl_dvsec_rr_decode() to cxl_port
  cxl/pci: Break out range register decoding from cxl_hdm_decode_init()
  cxl: add RAS status unmasking for CXL
  cxl: remove unnecessary calling of pci_enable_pcie_error_reporting()
  dax/hmem: build hmem device support as module if possible
  dax: cxl: add CXL_REGION dependency
  cxl: avoid returning uninitialized error code
  cxl/pmem: Fix nvdimm registration races
  cxl/mem: Fix UAPI command comment
  cxl/uapi: Tag commands from cxl_query_cmd()
  ...

Documentation/ABI/testing/sysfs-bus-cxl

@@ -90,6 +90,21 @@ Description:
 		capability.
 
 
+What:		/sys/bus/cxl/devices/{port,endpoint}X/parent_dport
+Date:		January, 2023
+KernelVersion:	v6.3
+Contact:	linux-cxl@vger.kernel.org
+Description:
+		(RO) CXL port objects are instantiated for each upstream port in
+		a CXL/PCIe switch, and for each endpoint to map the
+		corresponding memory device into the CXL port hierarchy. When a
+		descendant CXL port (switch or endpoint) is enumerated it is
+		useful to know which 'dport' object in the parent CXL port
+		routes to this descendant. The 'parent_dport' symlink points to
+		the device representing the downstream port of a CXL switch that
+		routes to {port,endpoint}X.
+
+
 What:		/sys/bus/cxl/devices/portX/dportY
 Date:		June, 2021
 KernelVersion:	v5.14
@@ -183,7 +198,7 @@ Description:
 
 What:		/sys/bus/cxl/devices/endpointX/CDAT
 Date:		July, 2022
-KernelVersion:	v5.20
+KernelVersion:	v6.0
 Contact:	linux-cxl@vger.kernel.org
 Description:
 		(RO) If this sysfs entry is not present no DOE mailbox was
@@ -194,7 +209,7 @@ Description:
 
 What:		/sys/bus/cxl/devices/decoderX.Y/mode
 Date:		May, 2022
-KernelVersion:	v5.20
+KernelVersion:	v6.0
 Contact:	linux-cxl@vger.kernel.org
 Description:
 		(RW) When a CXL decoder is of devtype "cxl_decoder_endpoint" it
@@ -214,7 +229,7 @@ Description:
 
 What:		/sys/bus/cxl/devices/decoderX.Y/dpa_resource
 Date:		May, 2022
-KernelVersion:	v5.20
+KernelVersion:	v6.0
 Contact:	linux-cxl@vger.kernel.org
 Description:
 		(RO) When a CXL decoder is of devtype "cxl_decoder_endpoint",
@@ -225,7 +240,7 @@ Description:
 
 What:		/sys/bus/cxl/devices/decoderX.Y/dpa_size
 Date:		May, 2022
-KernelVersion:	v5.20
+KernelVersion:	v6.0
 Contact:	linux-cxl@vger.kernel.org
 Description:
 		(RW) When a CXL decoder is of devtype "cxl_decoder_endpoint" it
@@ -245,7 +260,7 @@ Description:
 
 What:		/sys/bus/cxl/devices/decoderX.Y/interleave_ways
 Date:		May, 2022
-KernelVersion:	v5.20
+KernelVersion:	v6.0
 Contact:	linux-cxl@vger.kernel.org
 Description:
 		(RO) The number of targets across which this decoder's host
@@ -260,7 +275,7 @@ Description:
 
 What:		/sys/bus/cxl/devices/decoderX.Y/interleave_granularity
 Date:		May, 2022
-KernelVersion:	v5.20
+KernelVersion:	v6.0
 Contact:	linux-cxl@vger.kernel.org
 Description:
 		(RO) The number of consecutive bytes of host physical address
@@ -270,25 +285,25 @@ Description:
 		interleave_granularity).
 
 
-What:		/sys/bus/cxl/devices/decoderX.Y/create_pmem_region
-Date:		May, 2022
-KernelVersion:	v5.20
+What:		/sys/bus/cxl/devices/decoderX.Y/create_{pmem,ram}_region
+Date:		May, 2022, January, 2023
+KernelVersion:	v6.0 (pmem), v6.3 (ram)
 Contact:	linux-cxl@vger.kernel.org
 Description:
 		(RW) Write a string in the form 'regionZ' to start the process
-		of defining a new persistent memory region (interleave-set)
-		within the decode range bounded by root decoder 'decoderX.Y'.
-		The value written must match the current value returned from
-		reading this attribute. An atomic compare exchange operation is
-		done on write to assign the requested id to a region and
-		allocate the region-id for the next creation attempt. EBUSY is
-		returned if the region name written does not match the current
-		cached value.
+		of defining a new persistent, or volatile memory region
+		(interleave-set) within the decode range bounded by root decoder
+		'decoderX.Y'. The value written must match the current value
+		returned from reading this attribute. An atomic compare exchange
+		operation is done on write to assign the requested id to a
+		region and allocate the region-id for the next creation attempt.
+		EBUSY is returned if the region name written does not match the
+		current cached value.
 
 
 What:		/sys/bus/cxl/devices/decoderX.Y/delete_region
 Date:		May, 2022
-KernelVersion:	v5.20
+KernelVersion:	v6.0
 Contact:	linux-cxl@vger.kernel.org
 Description:
 		(WO) Write a string in the form 'regionZ' to delete that region,
@@ -297,17 +312,18 @@ Description:
 
 What:		/sys/bus/cxl/devices/regionZ/uuid
 Date:		May, 2022
-KernelVersion:	v5.20
+KernelVersion:	v6.0
 Contact:	linux-cxl@vger.kernel.org
 Description:
 		(RW) Write a unique identifier for the region. This field must
 		be set for persistent regions and it must not conflict with the
-		UUID of another region.
+		UUID of another region. For volatile ram regions this
+		attribute is a read-only empty string.
 
 
 What:		/sys/bus/cxl/devices/regionZ/interleave_granularity
 Date:		May, 2022
-KernelVersion:	v5.20
+KernelVersion:	v6.0
 Contact:	linux-cxl@vger.kernel.org
 Description:
 		(RW) Set the number of consecutive bytes each device in the
@@ -318,7 +334,7 @@ Description:
 
 What:		/sys/bus/cxl/devices/regionZ/interleave_ways
 Date:		May, 2022
-KernelVersion:	v5.20
+KernelVersion:	v6.0
 Contact:	linux-cxl@vger.kernel.org
 Description:
 		(RW) Configures the number of devices participating in the
@@ -328,7 +344,7 @@ Description:
 
 What:		/sys/bus/cxl/devices/regionZ/size
 Date:		May, 2022
-KernelVersion:	v5.20
+KernelVersion:	v6.0
 Contact:	linux-cxl@vger.kernel.org
 Description:
 		(RW) System physical address space to be consumed by the region.
@@ -343,9 +359,20 @@ Description:
 		results in the same address being allocated.
 
 
+What:		/sys/bus/cxl/devices/regionZ/mode
+Date:		January, 2023
+KernelVersion:	v6.3
+Contact:	linux-cxl@vger.kernel.org
+Description:
+		(RO) The mode of a region is established at region creation time
+		and dictates the mode of the endpoint decoder that comprise the
+		region. For more details on the possible modes see
+		/sys/bus/cxl/devices/decoderX.Y/mode
+
+
 What:		/sys/bus/cxl/devices/regionZ/resource
 Date:		May, 2022
-KernelVersion:	v5.20
+KernelVersion:	v6.0
 Contact:	linux-cxl@vger.kernel.org
 Description:
 		(RO) A region is a contiguous partition of a CXL root decoder
@@ -357,7 +384,7 @@ Description:
 
 What:		/sys/bus/cxl/devices/regionZ/target[0..N]
 Date:		May, 2022
-KernelVersion:	v5.20
+KernelVersion:	v6.0
 Contact:	linux-cxl@vger.kernel.org
 Description:
 		(RW) Write an endpoint decoder object name to 'targetX' where X
@@ -376,7 +403,7 @@ Description:
 
 What:		/sys/bus/cxl/devices/regionZ/commit
 Date:		May, 2022
-KernelVersion:	v5.20
+KernelVersion:	v6.0
 Contact:	linux-cxl@vger.kernel.org
 Description:
 		(RW) Write a boolean 'true' string value to this attribute to

MAINTAINERS

@@ -5912,6 +5912,7 @@ M:	Dan Williams <dan.j.williams@intel.com>
 M:	Vishal Verma <vishal.l.verma@intel.com>
 M:	Dave Jiang <dave.jiang@intel.com>
 L:	nvdimm@lists.linux.dev
+L:	linux-cxl@vger.kernel.org
 S:	Supported
 F:	drivers/dax/
 

drivers/Makefile

@@ -71,7 +71,7 @@ obj-$(CONFIG_FB_INTEL)          += video/fbdev/intelfb/
 obj-$(CONFIG_PARPORT)		+= parport/
 obj-y				+= base/ block/ misc/ mfd/ nfc/
 obj-$(CONFIG_LIBNVDIMM)		+= nvdimm/
-obj-$(CONFIG_DAX)		+= dax/
+obj-y				+= dax/
 obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/
 obj-$(CONFIG_NUBUS)		+= nubus/
 obj-y				+= cxl/

drivers/acpi/numa/hmat.c

@@ -718,7 +718,7 @@ static void hmat_register_target_devices(struct memory_target *target)
 	for (res = target->memregions.child; res; res = res->sibling) {
 		int target_nid = pxm_to_node(target->memory_pxm);
 
-		hmem_register_device(target_nid, res);
+		hmem_register_resource(target_nid, res);
 	}
 }
 
@@ -869,4 +869,4 @@ static __init int hmat_init(void)
 	acpi_put_table(tbl);
 	return 0;
 }
-device_initcall(hmat_init);
+subsys_initcall(hmat_init);

drivers/acpi/pci_root.c

@@ -1047,6 +1047,9 @@ struct pci_bus *acpi_pci_root_create(struct acpi_pci_root *root,
 	if (!(root->osc_control_set & OSC_PCI_EXPRESS_DPC_CONTROL))
 		host_bridge->native_dpc = 0;
 
+	if (!(root->osc_ext_control_set & OSC_CXL_ERROR_REPORTING_CONTROL))
+		host_bridge->native_cxl_error = 0;
+
 	/*
 	 * Evaluate the "PCI Boot Configuration" _DSM Function.  If it
 	 * exists and returns 0, we must preserve any PCI resource

drivers/cxl/Kconfig

@@ -104,19 +104,29 @@ config CXL_SUSPEND
 	depends on SUSPEND && CXL_MEM
 
 config CXL_REGION
-	bool
+	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 notifiying those caches to
+	  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

drivers/cxl/acpi.c

@@ -19,7 +19,7 @@ struct cxl_cxims_data {
 
 /*
  * Find a targets entry (n) in the host bridge interleave list.
- * CXL Specfication 3.0 Table 9-22
+ * CXL Specification 3.0 Table 9-22
  */
 static int cxl_xor_calc_n(u64 hpa, struct cxl_cxims_data *cximsd, int iw,
 			  int ig)
@@ -731,7 +731,8 @@ static void __exit cxl_acpi_exit(void)
 	cxl_bus_drain();
 }
 
-module_init(cxl_acpi_init);
+/* load before dax_hmem sees 'Soft Reserved' CXL ranges */
+subsys_initcall(cxl_acpi_init);
 module_exit(cxl_acpi_exit);
 MODULE_LICENSE("GPL v2");
 MODULE_IMPORT_NS(CXL);

drivers/cxl/core/Makefile

@@ -3,6 +3,8 @@ 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
@@ -10,4 +12,5 @@ cxl_core-y += memdev.o
 cxl_core-y += mbox.o
 cxl_core-y += pci.o
 cxl_core-y += hdm.o
+cxl_core-$(CONFIG_TRACING) += trace.o
 cxl_core-$(CONFIG_CXL_REGION) += region.o

drivers/cxl/core/core.h

@@ -11,15 +11,18 @@ extern struct attribute_group cxl_base_attribute_group;
 
 #ifdef CONFIG_CXL_REGION
 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;
 void cxl_decoder_kill_region(struct cxl_endpoint_decoder *cxled);
 #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);
 #else
@@ -37,6 +40,7 @@ static inline void cxl_region_exit(void)
 #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;
@@ -56,9 +60,6 @@ resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled);
 resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled);
 extern struct rw_semaphore cxl_dpa_rwsem;
 
-bool is_switch_decoder(struct device *dev);
-struct cxl_switch_decoder *to_cxl_switch_decoder(struct device *dev);
-
 int cxl_memdev_init(void);
 void cxl_memdev_exit(void);
 void cxl_mbox_init(void);

drivers/cxl/core/hdm.c

@@ -101,11 +101,34 @@ static int map_hdm_decoder_regs(struct cxl_port *port, void __iomem *crb,
 				      BIT(CXL_CM_CAP_CAP_ID_HDM));
 }
 
+static struct cxl_hdm *devm_cxl_setup_emulated_hdm(struct cxl_port *port,
+						   struct cxl_endpoint_dvsec_info *info)
+{
+	struct device *dev = &port->dev;
+	struct cxl_hdm *cxlhdm;
+
+	if (!info->mem_enabled)
+		return ERR_PTR(-ENODEV);
+
+	cxlhdm = devm_kzalloc(dev, sizeof(*cxlhdm), GFP_KERNEL);
+	if (!cxlhdm)
+		return ERR_PTR(-ENOMEM);
+
+	cxlhdm->port = port;
+	cxlhdm->decoder_count = info->ranges;
+	cxlhdm->target_count = info->ranges;
+	dev_set_drvdata(&port->dev, cxlhdm);
+
+	return cxlhdm;
+}
+
 /**
  * devm_cxl_setup_hdm - map HDM decoder component registers
  * @port: cxl_port to map
+ * @info: cached DVSEC range register info
  */
-struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port)
+struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port,
+				   struct cxl_endpoint_dvsec_info *info)
 {
 	struct device *dev = &port->dev;
 	struct cxl_hdm *cxlhdm;
@@ -119,6 +142,9 @@ struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port)
 	cxlhdm->port = port;
 	crb = ioremap(port->component_reg_phys, CXL_COMPONENT_REG_BLOCK_SIZE);
 	if (!crb) {
+		if (info && info->mem_enabled)
+			return devm_cxl_setup_emulated_hdm(port, info);
+
 		dev_err(dev, "No component registers mapped\n");
 		return ERR_PTR(-ENXIO);
 	}
@@ -279,7 +305,7 @@ static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 	return 0;
 }
 
-static int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
+int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 				resource_size_t base, resource_size_t len,
 				resource_size_t skipped)
 {
@@ -295,6 +321,7 @@ static int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 
 	return devm_add_action_or_reset(&port->dev, cxl_dpa_release, cxled);
 }
+EXPORT_SYMBOL_NS_GPL(devm_cxl_dpa_reserve, CXL);
 
 resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled)
 {
@@ -676,12 +703,71 @@ static int cxl_decoder_reset(struct cxl_decoder *cxld)
 	port->commit_end--;
 	cxld->flags &= ~CXL_DECODER_F_ENABLE;
 
+	/* Userspace is now responsible for reconfiguring this decoder */
+	if (is_endpoint_decoder(&cxld->dev)) {
+		struct cxl_endpoint_decoder *cxled;
+
+		cxled = to_cxl_endpoint_decoder(&cxld->dev);
+		cxled->state = CXL_DECODER_STATE_MANUAL;
+	}
+
+	return 0;
+}
+
+static int cxl_setup_hdm_decoder_from_dvsec(struct cxl_port *port,
+					    struct cxl_decoder *cxld, int which,
+					    struct cxl_endpoint_dvsec_info *info)
+{
+	if (!is_cxl_endpoint(port))
+		return -EOPNOTSUPP;
+
+	if (!range_len(&info->dvsec_range[which]))
+		return -ENOENT;
+
+	cxld->target_type = CXL_DECODER_EXPANDER;
+	cxld->commit = NULL;
+	cxld->reset = NULL;
+	cxld->hpa_range = info->dvsec_range[which];
+
+	/*
+	 * Set the emulated decoder as locked pending additional support to
+	 * change the range registers at run time.
+	 */
+	cxld->flags |= CXL_DECODER_F_ENABLE | CXL_DECODER_F_LOCK;
+	port->commit_end = cxld->id;
+
 	return 0;
 }
 
+static bool should_emulate_decoders(struct cxl_port *port)
+{
+	struct cxl_hdm *cxlhdm = dev_get_drvdata(&port->dev);
+	void __iomem *hdm = cxlhdm->regs.hdm_decoder;
+	u32 ctrl;
+	int i;
+
+	if (!is_cxl_endpoint(cxlhdm->port))
+		return false;
+
+	if (!hdm)
+		return true;
+
+	/*
+	 * If any decoders are committed already, there should not be any
+	 * emulated DVSEC decoders.
+	 */
+	for (i = 0; i < cxlhdm->decoder_count; i++) {
+		ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(i));
+		if (FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl))
+			return false;
+	}
+
+	return true;
+}
+
 static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 			    int *target_map, void __iomem *hdm, int which,
-			    u64 *dpa_base)
+			    u64 *dpa_base, struct cxl_endpoint_dvsec_info *info)
 {
 	struct cxl_endpoint_decoder *cxled = NULL;
 	u64 size, base, skip, dpa_size;
@@ -694,6 +780,9 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 		unsigned char target_id[8];
 	} target_list;
 
+	if (should_emulate_decoders(port))
+		return cxl_setup_hdm_decoder_from_dvsec(port, cxld, which, info);
+
 	if (is_endpoint_decoder(&cxld->dev))
 		cxled = to_cxl_endpoint_decoder(&cxld->dev);
 
@@ -717,6 +806,9 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 		.end = base + size - 1,
 	};
 
+	if (cxled && !committed && range_len(&info->dvsec_range[which]))
+		return cxl_setup_hdm_decoder_from_dvsec(port, cxld, which, info);
+
 	/* decoders are enabled if committed */
 	if (committed) {
 		cxld->flags |= CXL_DECODER_F_ENABLE;
@@ -783,21 +875,21 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 		return rc;
 	}
 	*dpa_base += dpa_size + skip;
+
+	cxled->state = CXL_DECODER_STATE_AUTO;
+
 	return 0;
 }
 
-/**
- * devm_cxl_enumerate_decoders - add decoder objects per HDM register set
- * @cxlhdm: Structure to populate with HDM capabilities
- */
-int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm)
+static void cxl_settle_decoders(struct cxl_hdm *cxlhdm)
 {
 	void __iomem *hdm = cxlhdm->regs.hdm_decoder;
-	struct cxl_port *port = cxlhdm->port;
-	int i, committed;
-	u64 dpa_base = 0;
+	int committed, i;
 	u32 ctrl;
 
+	if (!hdm)
+		return;
+
 	/*
 	 * Since the register resource was recently claimed via request_region()
 	 * be careful about trusting the "not-committed" status until the commit
@@ -814,6 +906,22 @@ int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm)
 	/* ensure that future checks of committed can be trusted */
 	if (committed != cxlhdm->decoder_count)
 		msleep(20);
+}
+
+/**
+ * devm_cxl_enumerate_decoders - add decoder objects per HDM register set
+ * @cxlhdm: Structure to populate with HDM capabilities
+ * @info: cached DVSEC range register info
+ */
+int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
+				struct cxl_endpoint_dvsec_info *info)
+{
+	void __iomem *hdm = cxlhdm->regs.hdm_decoder;
+	struct cxl_port *port = cxlhdm->port;
+	int i;
+	u64 dpa_base = 0;
+
+	cxl_settle_decoders(cxlhdm);
 
 	for (i = 0; i < cxlhdm->decoder_count; i++) {
 		int target_map[CXL_DECODER_MAX_INTERLEAVE] = { 0 };
@@ -826,7 +934,8 @@ int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm)
 			cxled = cxl_endpoint_decoder_alloc(port);
 			if (IS_ERR(cxled)) {
 				dev_warn(&port->dev,
-					 "Failed to allocate the decoder\n");
+					 "Failed to allocate decoder%d.%d\n",
+					 port->id, i);
 				return PTR_ERR(cxled);
 			}
 			cxld = &cxled->cxld;
@@ -836,21 +945,26 @@ int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm)
 			cxlsd = cxl_switch_decoder_alloc(port, target_count);
 			if (IS_ERR(cxlsd)) {
 				dev_warn(&port->dev,
-					 "Failed to allocate the decoder\n");
+					 "Failed to allocate decoder%d.%d\n",
+					 port->id, i);
 				return PTR_ERR(cxlsd);
 			}
 			cxld = &cxlsd->cxld;
 		}
 
-		rc = init_hdm_decoder(port, cxld, target_map, hdm, i, &dpa_base);
+		rc = init_hdm_decoder(port, cxld, target_map, hdm, i,
+				      &dpa_base, info);
 		if (rc) {
+			dev_warn(&port->dev,
+				 "Failed to initialize decoder%d.%d\n",
+				 port->id, i);
 			put_device(&cxld->dev);
 			return rc;
 		}
 		rc = add_hdm_decoder(port, cxld, target_map);
 		if (rc) {
 			dev_warn(&port->dev,
-				 "Failed to add decoder to port\n");
+				 "Failed to add decoder%d.%d\n", port->id, i);
 			return rc;
 		}
 	}

drivers/cxl/core/mbox.c

@@ -3,11 +3,13 @@
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/security.h>
 #include <linux/debugfs.h>
+#include <linux/ktime.h>
 #include <linux/mutex.h>
 #include <cxlmem.h>
 #include <cxl.h>
 
 #include "core.h"
+#include "trace.h"
 
 static bool cxl_raw_allow_all;
 
@@ -170,6 +172,12 @@ int cxl_internal_send_cmd(struct cxl_dev_state *cxlds,
 	out_size = mbox_cmd->size_out;
 	min_out = mbox_cmd->min_out;
 	rc = cxlds->mbox_send(cxlds, mbox_cmd);
+	/*
+	 * EIO is reserved for a payload size mismatch and mbox_send()
+	 * may not return this error.
+	 */
+	if (WARN_ONCE(rc == -EIO, "Bad return code: -EIO"))
+		return -ENXIO;
 	if (rc)
 		return rc;
 
@@ -445,9 +453,14 @@ int cxl_query_cmd(struct cxl_memdev *cxlmd,
 	 * structures.
 	 */
 	cxl_for_each_cmd(cmd) {
-		const struct cxl_command_info *info = &cmd->info;
+		struct cxl_command_info info = cmd->info;
 
-		if (copy_to_user(&q->commands[j++], info, sizeof(*info)))
+		if (test_bit(info.id, cxlmd->cxlds->enabled_cmds))
+			info.flags |= CXL_MEM_COMMAND_FLAG_ENABLED;
+		if (test_bit(info.id, cxlmd->cxlds->exclusive_cmds))
+			info.flags |= CXL_MEM_COMMAND_FLAG_EXCLUSIVE;
+
+		if (copy_to_user(&q->commands[j++], &info, sizeof(info)))
 			return -EFAULT;
 
 		if (j == n_commands)
@@ -550,9 +563,9 @@ int cxl_send_cmd(struct cxl_memdev *cxlmd, struct cxl_send_command __user *s)
 	return 0;
 }
 
-static int cxl_xfer_log(struct cxl_dev_state *cxlds, uuid_t *uuid, u32 size, u8 *out)
+static int cxl_xfer_log(struct cxl_dev_state *cxlds, uuid_t *uuid, u32 *size, u8 *out)
 {
-	u32 remaining = size;
+	u32 remaining = *size;
 	u32 offset = 0;
 
 	while (remaining) {
@@ -576,6 +589,17 @@ static int cxl_xfer_log(struct cxl_dev_state *cxlds, uuid_t *uuid, u32 size, u8
 		};
 
 		rc = cxl_internal_send_cmd(cxlds, &mbox_cmd);
+
+		/*
+		 * The output payload length that indicates the number
+		 * of valid bytes can be smaller than the Log buffer
+		 * size.
+		 */
+		if (rc == -EIO && mbox_cmd.size_out < xfer_size) {
+			offset += mbox_cmd.size_out;
+			break;
+		}
+
 		if (rc < 0)
 			return rc;
 
@@ -584,6 +608,8 @@ static int cxl_xfer_log(struct cxl_dev_state *cxlds, uuid_t *uuid, u32 size, u8
 		offset += xfer_size;
 	}
 
+	*size = offset;
+
 	return 0;
 }
 
@@ -610,11 +636,12 @@ static void cxl_walk_cel(struct cxl_dev_state *cxlds, size_t size, u8 *cel)
 
 		if (!cmd) {
 			dev_dbg(cxlds->dev,
-				"Opcode 0x%04x unsupported by driver", opcode);
+				"Opcode 0x%04x unsupported by driver\n", opcode);
 			continue;
 		}
 
 		set_bit(cmd->info.id, cxlds->enabled_cmds);
+		dev_dbg(cxlds->dev, "Opcode 0x%04x enabled\n", opcode);
 	}
 }
 
@@ -694,7 +721,7 @@ int cxl_enumerate_cmds(struct cxl_dev_state *cxlds)
 			goto out;
 		}
 
-		rc = cxl_xfer_log(cxlds, &uuid, size, log);
+		rc = cxl_xfer_log(cxlds, &uuid, &size, log);
 		if (rc) {
 			kvfree(log);
 			goto out;
@@ -717,6 +744,203 @@ int cxl_enumerate_cmds(struct cxl_dev_state *cxlds)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_enumerate_cmds, CXL);
 
+/*
+ * General Media Event Record
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+static const uuid_t gen_media_event_uuid =
+	UUID_INIT(0xfbcd0a77, 0xc260, 0x417f,
+		  0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6);
+
+/*
+ * DRAM Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ */
+static const uuid_t dram_event_uuid =
+	UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,
+		  0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24);
+
+/*
+ * Memory Module Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+static const uuid_t mem_mod_event_uuid =
+	UUID_INIT(0xfe927475, 0xdd59, 0x4339,
+		  0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74);
+
+static void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
+				   enum cxl_event_log_type type,
+				   struct cxl_event_record_raw *record)
+{
+	uuid_t *id = &record->hdr.id;
+
+	if (uuid_equal(id, &gen_media_event_uuid)) {
+		struct cxl_event_gen_media *rec =
+				(struct cxl_event_gen_media *)record;
+
+		trace_cxl_general_media(cxlmd, type, rec);
+	} else if (uuid_equal(id, &dram_event_uuid)) {
+		struct cxl_event_dram *rec = (struct cxl_event_dram *)record;
+
+		trace_cxl_dram(cxlmd, type, rec);
+	} else if (uuid_equal(id, &mem_mod_event_uuid)) {
+		struct cxl_event_mem_module *rec =
+				(struct cxl_event_mem_module *)record;
+
+		trace_cxl_memory_module(cxlmd, type, rec);
+	} else {
+		/* For unknown record types print just the header */
+		trace_cxl_generic_event(cxlmd, type, record);
+	}
+}
+
+static int cxl_clear_event_record(struct cxl_dev_state *cxlds,
+				  enum cxl_event_log_type log,
+				  struct cxl_get_event_payload *get_pl)
+{
+	struct cxl_mbox_clear_event_payload *payload;
+	u16 total = le16_to_cpu(get_pl->record_count);
+	u8 max_handles = CXL_CLEAR_EVENT_MAX_HANDLES;
+	size_t pl_size = struct_size(payload, handles, max_handles);
+	struct cxl_mbox_cmd mbox_cmd;
+	u16 cnt;
+	int rc = 0;
+	int i;
+
+	/* Payload size may limit the max handles */
+	if (pl_size > cxlds->payload_size) {
+		max_handles = (cxlds->payload_size - sizeof(*payload)) /
+				sizeof(__le16);
+		pl_size = struct_size(payload, handles, max_handles);
+	}
+
+	payload = kvzalloc(pl_size, GFP_KERNEL);
+	if (!payload)
+		return -ENOMEM;
+
+	*payload = (struct cxl_mbox_clear_event_payload) {
+		.event_log = log,
+	};
+
+	mbox_cmd = (struct cxl_mbox_cmd) {
+		.opcode = CXL_MBOX_OP_CLEAR_EVENT_RECORD,
+		.payload_in = payload,
+		.size_in = pl_size,
+	};
+
+	/*
+	 * Clear Event Records uses u8 for the handle cnt while Get Event
+	 * Record can return up to 0xffff records.
+	 */
+	i = 0;
+	for (cnt = 0; cnt < total; cnt++) {
+		payload->handles[i++] = get_pl->records[cnt].hdr.handle;
+		dev_dbg(cxlds->dev, "Event log '%d': Clearing %u\n",
+			log, le16_to_cpu(payload->handles[i]));
+
+		if (i == max_handles) {
+			payload->nr_recs = i;
+			rc = cxl_internal_send_cmd(cxlds, &mbox_cmd);
+			if (rc)
+				goto free_pl;
+			i = 0;
+		}
+	}
+
+	/* Clear what is left if any */
+	if (i) {
+		payload->nr_recs = i;
+		mbox_cmd.size_in = struct_size(payload, handles, i);
+		rc = cxl_internal_send_cmd(cxlds, &mbox_cmd);
+		if (rc)
+			goto free_pl;
+	}
+
+free_pl:
+	kvfree(payload);
+	return rc;
+}
+
+static void cxl_mem_get_records_log(struct cxl_dev_state *cxlds,
+				    enum cxl_event_log_type type)
+{
+	struct cxl_get_event_payload *payload;
+	struct cxl_mbox_cmd mbox_cmd;
+	u8 log_type = type;
+	u16 nr_rec;
+
+	mutex_lock(&cxlds->event.log_lock);
+	payload = cxlds->event.buf;
+
+	mbox_cmd = (struct cxl_mbox_cmd) {
+		.opcode = CXL_MBOX_OP_GET_EVENT_RECORD,
+		.payload_in = &log_type,
+		.size_in = sizeof(log_type),
+		.payload_out = payload,
+		.size_out = cxlds->payload_size,
+		.min_out = struct_size(payload, records, 0),
+	};
+
+	do {
+		int rc, i;
+
+		rc = cxl_internal_send_cmd(cxlds, &mbox_cmd);
+		if (rc) {
+			dev_err_ratelimited(cxlds->dev,
+				"Event log '%d': Failed to query event records : %d",
+				type, rc);
+			break;
+		}
+
+		nr_rec = le16_to_cpu(payload->record_count);
+		if (!nr_rec)
+			break;
+
+		for (i = 0; i < nr_rec; i++)
+			cxl_event_trace_record(cxlds->cxlmd, type,
+					       &payload->records[i]);
+
+		if (payload->flags & CXL_GET_EVENT_FLAG_OVERFLOW)
+			trace_cxl_overflow(cxlds->cxlmd, type, payload);
+
+		rc = cxl_clear_event_record(cxlds, type, payload);
+		if (rc) {
+			dev_err_ratelimited(cxlds->dev,
+				"Event log '%d': Failed to clear events : %d",
+				type, rc);
+			break;
+		}
+	} while (nr_rec);
+
+	mutex_unlock(&cxlds->event.log_lock);
+}
+
+/**
+ * cxl_mem_get_event_records - Get Event Records from the device
+ * @cxlds: The device data for the operation
+ * @status: Event Status register value identifying which events are available.
+ *
+ * Retrieve all event records available on the device, report them as trace
+ * events, and clear them.
+ *
+ * See CXL rev 3.0 @8.2.9.2.2 Get Event Records
+ * See CXL rev 3.0 @8.2.9.2.3 Clear Event Records
+ */
+void cxl_mem_get_event_records(struct cxl_dev_state *cxlds, u32 status)
+{
+	dev_dbg(cxlds->dev, "Reading event logs: %x\n", status);
+
+	if (status & CXLDEV_EVENT_STATUS_FATAL)
+		cxl_mem_get_records_log(cxlds, CXL_EVENT_TYPE_FATAL);
+	if (status & CXLDEV_EVENT_STATUS_FAIL)
+		cxl_mem_get_records_log(cxlds, CXL_EVENT_TYPE_FAIL);
+	if (status & CXLDEV_EVENT_STATUS_WARN)
+		cxl_mem_get_records_log(cxlds, CXL_EVENT_TYPE_WARN);
+	if (status & CXLDEV_EVENT_STATUS_INFO)
+		cxl_mem_get_records_log(cxlds, CXL_EVENT_TYPE_INFO);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_mem_get_event_records, CXL);
+
 /**
  * cxl_mem_get_partition_info - Get partition info
  * @cxlds: The device data for the operation
@@ -857,6 +1081,32 @@ int cxl_mem_create_range_info(struct cxl_dev_state *cxlds)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_mem_create_range_info, CXL);
 
+int cxl_set_timestamp(struct cxl_dev_state *cxlds)
+{
+	struct cxl_mbox_cmd mbox_cmd;
+	struct cxl_mbox_set_timestamp_in pi;
+	int rc;
+
+	pi.timestamp = cpu_to_le64(ktime_get_real_ns());
+	mbox_cmd = (struct cxl_mbox_cmd) {
+		.opcode = CXL_MBOX_OP_SET_TIMESTAMP,
+		.size_in = sizeof(pi),
+		.payload_in = &pi,
+	};
+
+	rc = cxl_internal_send_cmd(cxlds, &mbox_cmd);
+	/*
+	 * Command is optional. Devices may have another way of providing
+	 * a timestamp, or may return all 0s in timestamp fields.
+	 * Don't report an error if this command isn't supported
+	 */
+	if (rc && (mbox_cmd.return_code != CXL_MBOX_CMD_RC_UNSUPPORTED))
+		return rc;
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_set_timestamp, CXL);
+
 struct cxl_dev_state *cxl_dev_state_create(struct device *dev)
 {
 	struct cxl_dev_state *cxlds;
@@ -868,6 +1118,7 @@ struct cxl_dev_state *cxl_dev_state_create(struct device *dev)
 	}
 
 	mutex_init(&cxlds->mbox_mutex);
+	mutex_init(&cxlds->event.log_lock);
 	cxlds->dev = dev;
 
 	return cxlds;

drivers/cxl/core/memdev.c

@@ -242,10 +242,11 @@ static struct cxl_memdev *cxl_memdev_alloc(struct cxl_dev_state *cxlds,
 	if (!cxlmd)
 		return ERR_PTR(-ENOMEM);
 
-	rc = ida_alloc_range(&cxl_memdev_ida, 0, CXL_MEM_MAX_DEVS, GFP_KERNEL);
+	rc = ida_alloc_max(&cxl_memdev_ida, CXL_MEM_MAX_DEVS - 1, GFP_KERNEL);
 	if (rc < 0)
 		goto err;
 	cxlmd->id = rc;
+	cxlmd->depth = -1;
 
 	dev = &cxlmd->dev;
 	device_initialize(dev);

drivers/cxl/core/pci.c

@@ -9,6 +9,7 @@
 #include <cxlmem.h>
 #include <cxl.h>
 #include "core.h"
+#include "trace.h"
 
 /**
  * DOC: cxl core pci
@@ -141,11 +142,10 @@ int cxl_await_media_ready(struct cxl_dev_state *cxlds)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_await_media_ready, CXL);
 
-static int wait_for_valid(struct cxl_dev_state *cxlds)
+static int wait_for_valid(struct pci_dev *pdev, int d)
 {
-	struct pci_dev *pdev = to_pci_dev(cxlds->dev);
-	int d = cxlds->cxl_dvsec, rc;
 	u32 val;
+	int rc;
 
 	/*
 	 * Memory_Info_Valid: When set, indicates that the CXL Range 1 Size high
@@ -213,11 +213,6 @@ static int devm_cxl_enable_mem(struct device *host, struct cxl_dev_state *cxlds)
 	return devm_add_action_or_reset(host, clear_mem_enable, cxlds);
 }
 
-static bool range_contains(struct range *r1, struct range *r2)
-{
-	return r1->start <= r2->start && r1->end >= r2->end;
-}
-
 /* require dvsec ranges to be covered by a locked platform window */
 static int dvsec_range_allowed(struct device *dev, void *arg)
 {
@@ -229,8 +224,6 @@ static int dvsec_range_allowed(struct device *dev, void *arg)
 
 	cxld = to_cxl_decoder(dev);
 
-	if (!(cxld->flags & CXL_DECODER_F_LOCK))
-		return 0;
 	if (!(cxld->flags & CXL_DECODER_F_RAM))
 		return 0;
 
@@ -260,94 +253,11 @@ static int devm_cxl_enable_hdm(struct device *host, struct cxl_hdm *cxlhdm)
 	return devm_add_action_or_reset(host, disable_hdm, cxlhdm);
 }
 
-static bool __cxl_hdm_decode_init(struct cxl_dev_state *cxlds,
-				  struct cxl_hdm *cxlhdm,
+int cxl_dvsec_rr_decode(struct device *dev, int d,
 			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;
-
-	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) {
-		rc = devm_cxl_enable_mem(&port->dev, cxlds);
-		if (rc)
-			return false;
-		return true;
-	}
-
-	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 false;
-	}
-
-	for (i = 0, allowed = 0; info->mem_enabled && 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) {
-		cxl_set_mem_enable(cxlds, 0);
-		info->mem_enabled = 0;
-	}
-
-	/*
-	 * 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. If at least one DVSEC range is enabled and allowed, skip HDM
-	 * Decoder Capability Enable.
-	 */
-	if (info->mem_enabled)
-		return false;
-
-	rc = devm_cxl_enable_hdm(&port->dev, cxlhdm);
-	if (rc)
-		return false;
-
-	rc = devm_cxl_enable_mem(&port->dev, cxlds);
-	if (rc)
-		return false;
-
-	return true;
-}
-
-/**
- * cxl_hdm_decode_init() - Setup HDM decoding for the endpoint
- * @cxlds: Device state
- * @cxlhdm: Mapped HDM decoder Capability
- *
- * Try to enable the endpoint's HDM Decoder Capability
- */
-int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm)
-{
-	struct pci_dev *pdev = to_pci_dev(cxlds->dev);
-	struct cxl_endpoint_dvsec_info info = { 0 };
+	struct pci_dev *pdev = to_pci_dev(dev);
 	int hdm_count, rc, i, ranges = 0;
-	struct device *dev = &pdev->dev;
-	int d = cxlds->cxl_dvsec;
 	u16 cap, ctrl;
 
 	if (!d) {
@@ -378,7 +288,7 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm)
 	if (!hdm_count || hdm_count > 2)
 		return -EINVAL;
 
-	rc = wait_for_valid(cxlds);
+	rc = wait_for_valid(pdev, d);
 	if (rc) {
 		dev_dbg(dev, "Failure awaiting MEM_INFO_VALID (%d)\n", rc);
 		return rc;
@@ -389,9 +299,9 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm)
 	 * disabled, and they will remain moot after the HDM Decoder
 	 * capability is enabled.
 	 */
-	info.mem_enabled = FIELD_GET(CXL_DVSEC_MEM_ENABLE, ctrl);
-	if (!info.mem_enabled)
-		goto hdm_init;
+	info->mem_enabled = FIELD_GET(CXL_DVSEC_MEM_ENABLE, ctrl);
+	if (!info->mem_enabled)
+		return 0;
 
 	for (i = 0; i < hdm_count; i++) {
 		u64 base, size;
@@ -410,6 +320,13 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm)
 			return rc;
 
 		size |= temp & CXL_DVSEC_MEM_SIZE_LOW_MASK;
+		if (!size) {
+			info->dvsec_range[i] = (struct range) {
+				.start = 0,
+				.end = CXL_RESOURCE_NONE,
+			};
+			continue;
+		}
 
 		rc = pci_read_config_dword(
 			pdev, d + CXL_DVSEC_RANGE_BASE_HIGH(i), &temp);
@@ -425,29 +342,94 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm)
 
 		base |= temp & CXL_DVSEC_MEM_BASE_LOW_MASK;
 
-		info.dvsec_range[i] = (struct range) {
+		info->dvsec_range[i] = (struct range) {
 			.start = base,
 			.end = base + size - 1
 		};
 
-		if (size)
 		ranges++;
 	}
 
-	info.ranges = ranges;
+	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 DVSEC ranges are being used instead of HDM decoder registers there
-	 * is no use in trying to manage those.
+	 * If the HDM Decoder Capability is already enabled then assume
+	 * that some other agent like platform firmware set it up.
 	 */
-hdm_init:
-	if (!__cxl_hdm_decode_init(cxlds, cxlhdm, &info)) {
-		dev_err(dev,
-			"Legacy range registers configuration prevents HDM operation.\n");
-		return -EBUSY;
+	if (global_ctrl & CXL_HDM_DECODER_ENABLE || (!hdm && info->mem_enabled))
+		return devm_cxl_enable_mem(&port->dev, cxlds);
+	else if (!hdm)
+		return -ENODEV;
+
+	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; info->mem_enabled && 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) {
+		cxl_set_mem_enable(cxlds, 0);
+		info->mem_enabled = 0;
+	}
+
+	/*
+	 * 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. If at least one DVSEC range is enabled and allowed, skip HDM
+	 * Decoder Capability Enable.
+	 */
+	if (info->mem_enabled)
 		return 0;
+
+	rc = devm_cxl_enable_hdm(&port->dev, cxlhdm);
+	if (rc)
+		return rc;
+
+	return devm_cxl_enable_mem(&port->dev, cxlds);
 }
 EXPORT_SYMBOL_NS_GPL(cxl_hdm_decode_init, CXL);
 
@@ -622,3 +604,113 @@ void read_cdat_data(struct cxl_port *port)
 	}
 }
 EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL);
+
+void cxl_cor_error_detected(struct pci_dev *pdev)
+{
+	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
+	void __iomem *addr;
+	u32 status;
+
+	if (!cxlds->regs.ras)
+		return;
+
+	addr = cxlds->regs.ras + 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(cxlds->cxlmd, status);
+	}
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cor_error_detected, CXL);
+
+/* CXL spec rev3.0 8.2.4.16.1 */
+static void header_log_copy(struct cxl_dev_state *cxlds, u32 *log)
+{
+	void __iomem *addr;
+	u32 *log_addr;
+	int i, log_u32_size = CXL_HEADERLOG_SIZE / sizeof(u32);
+
+	addr = cxlds->regs.ras + CXL_RAS_HEADER_LOG_OFFSET;
+	log_addr = log;
+
+	for (i = 0; i < log_u32_size; 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.
+ */
+static bool cxl_report_and_clear(struct cxl_dev_state *cxlds)
+{
+	u32 hl[CXL_HEADERLOG_SIZE_U32];
+	void __iomem *addr;
+	u32 status;
+	u32 fe;
+
+	if (!cxlds->regs.ras)
+		return false;
+
+	addr = cxlds->regs.ras + 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 =
+			cxlds->regs.ras + CXL_RAS_CAP_CONTROL_OFFSET;
+
+		fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
+				   readl(rcc_addr)));
+	} else {
+		fe = status;
+	}
+
+	header_log_copy(cxlds, hl);
+	trace_cxl_aer_uncorrectable_error(cxlds->cxlmd, status, fe, hl);
+	writel(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK, addr);
+
+	return true;
+}
+
+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;
+
+	/*
+	 * 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_report_and_clear(cxlds);
+
+	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);

drivers/cxl/core/port.c

@@ -46,6 +46,8 @@ static int cxl_device_id(const struct device *dev)
 		return CXL_DEVICE_NVDIMM;
 	if (dev->type == CXL_PMEM_REGION_TYPE())
 		return CXL_DEVICE_PMEM_REGION;
+	if (dev->type == CXL_DAX_REGION_TYPE())
+		return CXL_DEVICE_DAX_REGION;
 	if (is_cxl_port(dev)) {
 		if (is_cxl_root(to_cxl_port(dev)))
 			return CXL_DEVICE_ROOT;
@@ -180,17 +182,7 @@ static ssize_t mode_show(struct device *dev, struct device_attribute *attr,
 {
 	struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev);
 
-	switch (cxled->mode) {
-	case CXL_DECODER_RAM:
-		return sysfs_emit(buf, "ram\n");
-	case CXL_DECODER_PMEM:
-		return sysfs_emit(buf, "pmem\n");
-	case CXL_DECODER_NONE:
-		return sysfs_emit(buf, "none\n");
-	case CXL_DECODER_MIXED:
-	default:
-		return sysfs_emit(buf, "mixed\n");
-	}
+	return sysfs_emit(buf, "%s\n", cxl_decoder_mode_name(cxled->mode));
 }
 
 static ssize_t mode_store(struct device *dev, struct device_attribute *attr,
@@ -304,6 +296,7 @@ static struct attribute *cxl_decoder_root_attrs[] = {
 	&dev_attr_cap_type3.attr,
 	&dev_attr_target_list.attr,
 	SET_CXL_REGION_ATTR(create_pmem_region)
+	SET_CXL_REGION_ATTR(create_ram_region)
 	SET_CXL_REGION_ATTR(delete_region)
 	NULL,
 };
@@ -315,6 +308,13 @@ static bool can_create_pmem(struct cxl_root_decoder *cxlrd)
 	return (cxlrd->cxlsd.cxld.flags & flags) == flags;
 }
 
+static bool can_create_ram(struct cxl_root_decoder *cxlrd)
+{
+	unsigned long flags = CXL_DECODER_F_TYPE3 | CXL_DECODER_F_RAM;
+
+	return (cxlrd->cxlsd.cxld.flags & flags) == flags;
+}
+
 static umode_t cxl_root_decoder_visible(struct kobject *kobj, struct attribute *a, int n)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -323,7 +323,11 @@ static umode_t cxl_root_decoder_visible(struct kobject *kobj, struct attribute *
 	if (a == CXL_REGION_ATTR(create_pmem_region) && !can_create_pmem(cxlrd))
 		return 0;
 
-	if (a == CXL_REGION_ATTR(delete_region) && !can_create_pmem(cxlrd))
+	if (a == CXL_REGION_ATTR(create_ram_region) && !can_create_ram(cxlrd))
+		return 0;
+
+	if (a == CXL_REGION_ATTR(delete_region) &&
+	    !(can_create_pmem(cxlrd) || can_create_ram(cxlrd)))
 		return 0;
 
 	return a->mode;
@@ -444,6 +448,7 @@ bool is_endpoint_decoder(struct device *dev)
 {
 	return dev->type == &cxl_decoder_endpoint_type;
 }
+EXPORT_SYMBOL_NS_GPL(is_endpoint_decoder, CXL);
 
 bool is_root_decoder(struct device *dev)
 {
@@ -455,6 +460,7 @@ bool is_switch_decoder(struct device *dev)
 {
 	return is_root_decoder(dev) || dev->type == &cxl_decoder_switch_type;
 }
+EXPORT_SYMBOL_NS_GPL(is_switch_decoder, CXL);
 
 struct cxl_decoder *to_cxl_decoder(struct device *dev)
 {
@@ -482,6 +488,7 @@ struct cxl_switch_decoder *to_cxl_switch_decoder(struct device *dev)
 		return NULL;
 	return container_of(dev, struct cxl_switch_decoder, cxld.dev);
 }
+EXPORT_SYMBOL_NS_GPL(to_cxl_switch_decoder, CXL);
 
 static void cxl_ep_release(struct cxl_ep *ep)
 {
@@ -583,6 +590,29 @@ static int devm_cxl_link_uport(struct device *host, struct cxl_port *port)
 	return devm_add_action_or_reset(host, cxl_unlink_uport, port);
 }
 
+static void cxl_unlink_parent_dport(void *_port)
+{
+	struct cxl_port *port = _port;
+
+	sysfs_remove_link(&port->dev.kobj, "parent_dport");
+}
+
+static int devm_cxl_link_parent_dport(struct device *host,
+				      struct cxl_port *port,
+				      struct cxl_dport *parent_dport)
+{
+	int rc;
+
+	if (!parent_dport)
+		return 0;
+
+	rc = sysfs_create_link(&port->dev.kobj, &parent_dport->dport->kobj,
+			       "parent_dport");
+	if (rc)
+		return rc;
+	return devm_add_action_or_reset(host, cxl_unlink_parent_dport, port);
+}
+
 static struct lock_class_key cxl_port_key;
 
 static struct cxl_port *cxl_port_alloc(struct device *uport,
@@ -692,6 +722,10 @@ static struct cxl_port *__devm_cxl_add_port(struct device *host,
 	if (rc)
 		return ERR_PTR(rc);
 
+	rc = devm_cxl_link_parent_dport(host, port, parent_dport);
+	if (rc)
+		return ERR_PTR(rc);
+
 	return port;
 
 err:
@@ -1137,7 +1171,7 @@ static struct cxl_port *find_cxl_port_at(struct cxl_port *parent_port,
 }
 
 /*
- * All users of grandparent() are using it to walk PCIe-like swich port
+ * All users of grandparent() are using it to walk PCIe-like switch port
  * hierarchy. A PCIe switch is comprised of a bridge device representing the
  * upstream switch port and N bridges representing downstream switch ports. When
  * bridges stack the grand-parent of a downstream switch port is another
@@ -1164,6 +1198,7 @@ static void delete_endpoint(void *data)
 
 	device_lock(parent);
 	if (parent->driver && !endpoint->dead) {
+		devm_release_action(parent, cxl_unlink_parent_dport, endpoint);
 		devm_release_action(parent, cxl_unlink_uport, endpoint);
 		devm_release_action(parent, unregister_port, endpoint);
 	}
@@ -1179,6 +1214,7 @@ int cxl_endpoint_autoremove(struct cxl_memdev *cxlmd, struct cxl_port *endpoint)
 
 	get_device(&endpoint->dev);
 	dev_set_drvdata(dev, endpoint);
+	cxlmd->depth = endpoint->depth;
 	return devm_add_action_or_reset(dev, delete_endpoint, cxlmd);
 }
 EXPORT_SYMBOL_NS_GPL(cxl_endpoint_autoremove, CXL);
@@ -1194,6 +1230,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_endpoint_autoremove, CXL);
  */
 static void delete_switch_port(struct cxl_port *port)
 {
+	devm_release_action(port->dev.parent, cxl_unlink_parent_dport, port);
 	devm_release_action(port->dev.parent, cxl_unlink_uport, port);
 	devm_release_action(port->dev.parent, unregister_port, port);
 }
@@ -1212,50 +1249,55 @@ static void reap_dports(struct cxl_port *port)
 	}
 }
 
+struct detach_ctx {
+	struct cxl_memdev *cxlmd;
+	int depth;
+};
+
+static int port_has_memdev(struct device *dev, const void *data)
+{
+	const struct detach_ctx *ctx = data;
+	struct cxl_port *port;
+
+	if (!is_cxl_port(dev))
+		return 0;
+
+	port = to_cxl_port(dev);
+	if (port->depth != ctx->depth)
+		return 0;
+
+	return !!cxl_ep_load(port, ctx->cxlmd);
+}
+
 static void cxl_detach_ep(void *data)
 {
 	struct cxl_memdev *cxlmd = data;
-	struct device *iter;
 
-	for (iter = &cxlmd->dev; iter; iter = grandparent(iter)) {
-		struct device *dport_dev = grandparent(iter);
+	for (int i = cxlmd->depth - 1; i >= 1; i--) {
 		struct cxl_port *port, *parent_port;
+		struct detach_ctx ctx = {
+			.cxlmd = cxlmd,
+			.depth = i,
+		};
+		struct device *dev;
 		struct cxl_ep *ep;
 		bool died = false;
 
-		if (!dport_dev)
-			break;
-
-		port = find_cxl_port(dport_dev, NULL);
-		if (!port)
-			continue;
-
-		if (is_cxl_root(port)) {
-			put_device(&port->dev);
+		dev = bus_find_device(&cxl_bus_type, NULL, &ctx,
+				      port_has_memdev);
+		if (!dev)
 			continue;
-		}
+		port = to_cxl_port(dev);
 
 		parent_port = to_cxl_port(port->dev.parent);
 		device_lock(&parent_port->dev);
-		if (!parent_port->dev.driver) {
-			/*
-			 * The bottom-up race to delete the port lost to a
-			 * top-down port disable, give up here, because the
-			 * parent_port ->remove() will have cleaned up all
-			 * descendants.
-			 */
-			device_unlock(&parent_port->dev);
-			put_device(&port->dev);
-			continue;
-		}
-
 		device_lock(&port->dev);
 		ep = cxl_ep_load(port, cxlmd);
 		dev_dbg(&cxlmd->dev, "disconnect %s from %s\n",
 			ep ? dev_name(ep->ep) : "", dev_name(&port->dev));
 		cxl_ep_remove(port, ep);
 		if (ep && !port->dead && xa_empty(&port->endpoints) &&
-		    !is_cxl_root(parent_port)) {
+		    !is_cxl_root(parent_port) && parent_port->dev.driver) {
 			/*
 			 * This was the last ep attached to a dynamically
 			 * enumerated port. Block new cxl_add_ep() and garbage
@@ -1591,6 +1633,7 @@ struct cxl_root_decoder *cxl_root_decoder_alloc(struct cxl_port *port,
 	}
 
 	cxlrd->calc_hb = calc_hb;
+	mutex_init(&cxlrd->range_lock);
 
 	cxld = &cxlsd->cxld;
 	cxld->dev.type = &cxl_decoder_root_type;
@@ -1974,6 +2017,6 @@ static void cxl_core_exit(void)
 	debugfs_remove_recursive(cxl_debugfs);
 }
 
-module_init(cxl_core_init);
+subsys_initcall(cxl_core_init);
 module_exit(cxl_core_exit);
 MODULE_LICENSE("GPL v2");

drivers/cxl/core/region.c

@@ -6,6 +6,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/uuid.h>
+#include <linux/sort.h>
 #include <linux/idr.h>
 #include <cxlmem.h>
 #include <cxl.h>
@@ -45,6 +46,9 @@ static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
 	rc = down_read_interruptible(&cxl_region_rwsem);
 	if (rc)
 		return rc;
+	if (cxlr->mode != CXL_DECODER_PMEM)
+		rc = sysfs_emit(buf, "\n");
+	else
 		rc = sysfs_emit(buf, "%pUb\n", &p->uuid);
 	up_read(&cxl_region_rwsem);
 
@@ -157,6 +161,22 @@ static int cxl_region_decode_reset(struct cxl_region *cxlr, int count)
 	return 0;
 }
 
+static int commit_decoder(struct cxl_decoder *cxld)
+{
+	struct cxl_switch_decoder *cxlsd = NULL;
+
+	if (cxld->commit)
+		return cxld->commit(cxld);
+
+	if (is_switch_decoder(&cxld->dev))
+		cxlsd = to_cxl_switch_decoder(&cxld->dev);
+
+	if (dev_WARN_ONCE(&cxld->dev, !cxlsd || cxlsd->nr_targets > 1,
+			  "->commit() is required\n"))
+		return -ENXIO;
+	return 0;
+}
+
 static int cxl_region_decode_commit(struct cxl_region *cxlr)
 {
 	struct cxl_region_params *p = &cxlr->params;
@@ -175,8 +195,7 @@ static int cxl_region_decode_commit(struct cxl_region *cxlr)
 		     iter = to_cxl_port(iter->dev.parent)) {
 			cxl_rr = cxl_rr_load(iter, cxlr);
 			cxld = cxl_rr->decoder;
-			if (cxld->commit)
-				rc = cxld->commit(cxld);
+			rc = commit_decoder(cxld);
 			if (rc)
 				break;
 		}
@@ -287,8 +306,12 @@ static umode_t cxl_region_visible(struct kobject *kobj, struct attribute *a,
 	struct device *dev = kobj_to_dev(kobj);
 	struct cxl_region *cxlr = to_cxl_region(dev);
 
+	/*
+	 * Support tooling that expects to find a 'uuid' attribute for all
+	 * regions regardless of mode.
+	 */
 	if (a == &dev_attr_uuid.attr && cxlr->mode != CXL_DECODER_PMEM)
-		return 0;
+		return 0444;
 	return a->mode;
 }
 
@@ -401,7 +424,7 @@ static ssize_t interleave_granularity_store(struct device *dev,
 	 * When the host-bridge is interleaved, disallow region granularity !=
 	 * root granularity. Regions with a granularity less than the root
 	 * interleave result in needing multiple endpoints to support a single
-	 * slot in the interleave (possible to suport in the future). Regions
+	 * slot in the interleave (possible to support in the future). Regions
 	 * with a granularity greater than the root interleave result in invalid
 	 * DPA translations (invalid to support).
 	 */
@@ -445,6 +468,15 @@ static ssize_t resource_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(resource);
 
+static ssize_t mode_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct cxl_region *cxlr = to_cxl_region(dev);
+
+	return sysfs_emit(buf, "%s\n", cxl_decoder_mode_name(cxlr->mode));
+}
+static DEVICE_ATTR_RO(mode);
+
 static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size)
 {
 	struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent);
@@ -495,6 +527,11 @@ static void cxl_region_iomem_release(struct cxl_region *cxlr)
 	if (device_is_registered(&cxlr->dev))
 		lockdep_assert_held_write(&cxl_region_rwsem);
 	if (p->res) {
+		/*
+		 * Autodiscovered regions may not have been able to insert their
+		 * resource.
+		 */
+		if (p->res->parent)
 			remove_resource(p->res);
 		kfree(p->res);
 		p->res = NULL;
@@ -572,6 +609,7 @@ static struct attribute *cxl_region_attrs[] = {
 	&dev_attr_interleave_granularity.attr,
 	&dev_attr_resource.attr,
 	&dev_attr_size.attr,
+	&dev_attr_mode.attr,
 	NULL,
 };
 
@@ -1075,12 +1113,35 @@ static int cxl_port_setup_targets(struct cxl_port *port,
 		return rc;
 	}
 
+	if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) {
+		if (cxld->interleave_ways != iw ||
+		    cxld->interleave_granularity != ig ||
+		    cxld->hpa_range.start != p->res->start ||
+		    cxld->hpa_range.end != p->res->end ||
+		    ((cxld->flags & CXL_DECODER_F_ENABLE) == 0)) {
+			dev_err(&cxlr->dev,
+				"%s:%s %s expected iw: %d ig: %d %pr\n",
+				dev_name(port->uport), dev_name(&port->dev),
+				__func__, iw, ig, p->res);
+			dev_err(&cxlr->dev,
+				"%s:%s %s got iw: %d ig: %d state: %s %#llx:%#llx\n",
+				dev_name(port->uport), dev_name(&port->dev),
+				__func__, cxld->interleave_ways,
+				cxld->interleave_granularity,
+				(cxld->flags & CXL_DECODER_F_ENABLE) ?
+					"enabled" :
+					"disabled",
+				cxld->hpa_range.start, cxld->hpa_range.end);
+			return -ENXIO;
+		}
+	} else {
 		cxld->interleave_ways = iw;
 		cxld->interleave_granularity = ig;
 		cxld->hpa_range = (struct range) {
 			.start = p->res->start,
 			.end = p->res->end,
 		};
+	}
 	dev_dbg(&cxlr->dev, "%s:%s iw: %d ig: %d\n", dev_name(port->uport),
 		dev_name(&port->dev), iw, ig);
 add_target:
@@ -1091,6 +1152,16 @@ static int cxl_port_setup_targets(struct cxl_port *port,
 			dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev), pos);
 		return -ENXIO;
 	}
+	if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) {
+		if (cxlsd->target[cxl_rr->nr_targets_set] != ep->dport) {
+			dev_dbg(&cxlr->dev, "%s:%s: %s expected %s at %d\n",
+				dev_name(port->uport), dev_name(&port->dev),
+				dev_name(&cxlsd->cxld.dev),
+				dev_name(ep->dport->dport),
+				cxl_rr->nr_targets_set);
+			return -ENXIO;
+		}
+	} else
 		cxlsd->target[cxl_rr->nr_targets_set] = ep->dport;
 	inc = 1;
 out_target_set:
@@ -1133,6 +1204,13 @@ static void cxl_region_teardown_targets(struct cxl_region *cxlr)
 	struct cxl_ep *ep;
 	int i;
 
+	/*
+	 * In the auto-discovery case skip automatic teardown since the
+	 * address space is already active
+	 */
+	if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags))
+		return;
+
 	for (i = 0; i < p->nr_targets; i++) {
 		cxled = p->targets[i];
 		cxlmd = cxled_to_memdev(cxled);
@@ -1165,8 +1243,8 @@ static int cxl_region_setup_targets(struct cxl_region *cxlr)
 			iter = to_cxl_port(iter->dev.parent);
 
 		/*
-		 * Descend the topology tree programming targets while
-		 * looking for conflicts.
+		 * Descend the topology tree programming / validating
+		 * targets while looking for conflicts.
 		 */
 		for (ep = cxl_ep_load(iter, cxlmd); iter;
 		     iter = ep->next, ep = cxl_ep_load(iter, cxlmd)) {
@@ -1181,29 +1259,13 @@ static int cxl_region_setup_targets(struct cxl_region *cxlr)
 	return 0;
 }
 
-static int cxl_region_attach(struct cxl_region *cxlr,
-			     struct cxl_endpoint_decoder *cxled, int pos)
+static int cxl_region_validate_position(struct cxl_region *cxlr,
+					struct cxl_endpoint_decoder *cxled,
+					int pos)
 {
-	struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent);
 	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
-	struct cxl_port *ep_port, *root_port, *iter;
 	struct cxl_region_params *p = &cxlr->params;
-	struct cxl_dport *dport;
-	int i, rc = -ENXIO;
-
-	if (cxled->mode == CXL_DECODER_DEAD) {
-		dev_dbg(&cxlr->dev, "%s dead\n", dev_name(&cxled->cxld.dev));
-		return -ENODEV;
-	}
-
-	/* all full of members, or interleave config not established? */
-	if (p->state > CXL_CONFIG_INTERLEAVE_ACTIVE) {
-		dev_dbg(&cxlr->dev, "region already active\n");
-		return -EBUSY;
-	} else if (p->state < CXL_CONFIG_INTERLEAVE_ACTIVE) {
-		dev_dbg(&cxlr->dev, "interleave config missing\n");
-		return -ENXIO;
-	}
+	int i;
 
 	if (pos < 0 || pos >= p->interleave_ways) {
 		dev_dbg(&cxlr->dev, "position %d out of range %d\n", pos,
@@ -1242,6 +1304,256 @@ static int cxl_region_attach(struct cxl_region *cxlr,
 		}
 	}
 
+	return 0;
+}
+
+static int cxl_region_attach_position(struct cxl_region *cxlr,
+				      struct cxl_root_decoder *cxlrd,
+				      struct cxl_endpoint_decoder *cxled,
+				      const struct cxl_dport *dport, int pos)
+{
+	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
+	struct cxl_port *iter;
+	int rc;
+
+	if (cxlrd->calc_hb(cxlrd, pos) != dport) {
+		dev_dbg(&cxlr->dev, "%s:%s invalid target position for %s\n",
+			dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev),
+			dev_name(&cxlrd->cxlsd.cxld.dev));
+		return -ENXIO;
+	}
+
+	for (iter = cxled_to_port(cxled); !is_cxl_root(iter);
+	     iter = to_cxl_port(iter->dev.parent)) {
+		rc = cxl_port_attach_region(iter, cxlr, cxled, pos);
+		if (rc)
+			goto err;
+	}
+
+	return 0;
+
+err:
+	for (iter = cxled_to_port(cxled); !is_cxl_root(iter);
+	     iter = to_cxl_port(iter->dev.parent))
+		cxl_port_detach_region(iter, cxlr, cxled);
+	return rc;
+}
+
+static int cxl_region_attach_auto(struct cxl_region *cxlr,
+				  struct cxl_endpoint_decoder *cxled, int pos)
+{
+	struct cxl_region_params *p = &cxlr->params;
+
+	if (cxled->state != CXL_DECODER_STATE_AUTO) {
+		dev_err(&cxlr->dev,
+			"%s: unable to add decoder to autodetected region\n",
+			dev_name(&cxled->cxld.dev));
+		return -EINVAL;
+	}
+
+	if (pos >= 0) {
+		dev_dbg(&cxlr->dev, "%s: expected auto position, not %d\n",
+			dev_name(&cxled->cxld.dev), pos);
+		return -EINVAL;
+	}
+
+	if (p->nr_targets >= p->interleave_ways) {
+		dev_err(&cxlr->dev, "%s: no more target slots available\n",
+			dev_name(&cxled->cxld.dev));
+		return -ENXIO;
+	}
+
+	/*
+	 * Temporarily record the endpoint decoder into the target array. Yes,
+	 * this means that userspace can view devices in the wrong position
+	 * before the region activates, and must be careful to understand when
+	 * it might be racing region autodiscovery.
+	 */
+	pos = p->nr_targets;
+	p->targets[pos] = cxled;
+	cxled->pos = pos;
+	p->nr_targets++;
+
+	return 0;
+}
+
+static struct cxl_port *next_port(struct cxl_port *port)
+{
+	if (!port->parent_dport)
+		return NULL;
+	return port->parent_dport->port;
+}
+
+static int decoder_match_range(struct device *dev, void *data)
+{
+	struct cxl_endpoint_decoder *cxled = data;
+	struct cxl_switch_decoder *cxlsd;
+
+	if (!is_switch_decoder(dev))
+		return 0;
+
+	cxlsd = to_cxl_switch_decoder(dev);
+	return range_contains(&cxlsd->cxld.hpa_range, &cxled->cxld.hpa_range);
+}
+
+static void find_positions(const struct cxl_switch_decoder *cxlsd,
+			   const struct cxl_port *iter_a,
+			   const struct cxl_port *iter_b, int *a_pos,
+			   int *b_pos)
+{
+	int i;
+
+	for (i = 0, *a_pos = -1, *b_pos = -1; i < cxlsd->nr_targets; i++) {
+		if (cxlsd->target[i] == iter_a->parent_dport)
+			*a_pos = i;
+		else if (cxlsd->target[i] == iter_b->parent_dport)
+			*b_pos = i;
+		if (*a_pos >= 0 && *b_pos >= 0)
+			break;
+	}
+}
+
+static int cmp_decode_pos(const void *a, const void *b)
+{
+	struct cxl_endpoint_decoder *cxled_a = *(typeof(cxled_a) *)a;
+	struct cxl_endpoint_decoder *cxled_b = *(typeof(cxled_b) *)b;
+	struct cxl_memdev *cxlmd_a = cxled_to_memdev(cxled_a);
+	struct cxl_memdev *cxlmd_b = cxled_to_memdev(cxled_b);
+	struct cxl_port *port_a = cxled_to_port(cxled_a);
+	struct cxl_port *port_b = cxled_to_port(cxled_b);
+	struct cxl_port *iter_a, *iter_b, *port = NULL;
+	struct cxl_switch_decoder *cxlsd;
+	struct device *dev;
+	int a_pos, b_pos;
+	unsigned int seq;
+
+	/* Exit early if any prior sorting failed */
+	if (cxled_a->pos < 0 || cxled_b->pos < 0)
+		return 0;
+
+	/*
+	 * Walk up the hierarchy to find a shared port, find the decoder that
+	 * maps the range, compare the relative position of those dport
+	 * mappings.
+	 */
+	for (iter_a = port_a; iter_a; iter_a = next_port(iter_a)) {
+		struct cxl_port *next_a, *next_b;
+
+		next_a = next_port(iter_a);
+		if (!next_a)
+			break;
+
+		for (iter_b = port_b; iter_b; iter_b = next_port(iter_b)) {
+			next_b = next_port(iter_b);
+			if (next_a != next_b)
+				continue;
+			port = next_a;
+			break;
+		}
+
+		if (port)
+			break;
+	}
+
+	if (!port) {
+		dev_err(cxlmd_a->dev.parent,
+			"failed to find shared port with %s\n",
+			dev_name(cxlmd_b->dev.parent));
+		goto err;
+	}
+
+	dev = device_find_child(&port->dev, cxled_a, decoder_match_range);
+	if (!dev) {
+		struct range *range = &cxled_a->cxld.hpa_range;
+
+		dev_err(port->uport,
+			"failed to find decoder that maps %#llx-%#llx\n",
+			range->start, range->end);
+		goto err;
+	}
+
+	cxlsd = to_cxl_switch_decoder(dev);
+	do {
+		seq = read_seqbegin(&cxlsd->target_lock);
+		find_positions(cxlsd, iter_a, iter_b, &a_pos, &b_pos);
+	} while (read_seqretry(&cxlsd->target_lock, seq));
+
+	put_device(dev);
+
+	if (a_pos < 0 || b_pos < 0) {
+		dev_err(port->uport,
+			"failed to find shared decoder for %s and %s\n",
+			dev_name(cxlmd_a->dev.parent),
+			dev_name(cxlmd_b->dev.parent));
+		goto err;
+	}
+
+	dev_dbg(port->uport, "%s comes %s %s\n", dev_name(cxlmd_a->dev.parent),
+		a_pos - b_pos < 0 ? "before" : "after",
+		dev_name(cxlmd_b->dev.parent));
+
+	return a_pos - b_pos;
+err:
+	cxled_a->pos = -1;
+	return 0;
+}
+
+static int cxl_region_sort_targets(struct cxl_region *cxlr)
+{
+	struct cxl_region_params *p = &cxlr->params;
+	int i, rc = 0;
+
+	sort(p->targets, p->nr_targets, sizeof(p->targets[0]), cmp_decode_pos,
+	     NULL);
+
+	for (i = 0; i < p->nr_targets; i++) {
+		struct cxl_endpoint_decoder *cxled = p->targets[i];
+
+		/*
+		 * Record that sorting failed, but still continue to restore
+		 * cxled->pos with its ->targets[] position so that follow-on
+		 * code paths can reliably do p->targets[cxled->pos] to
+		 * self-reference their entry.
+		 */
+		if (cxled->pos < 0)
+			rc = -ENXIO;
+		cxled->pos = i;
+	}
+
+	dev_dbg(&cxlr->dev, "region sort %s\n", rc ? "failed" : "successful");
+	return rc;
+}
+
+static int cxl_region_attach(struct cxl_region *cxlr,
+			     struct cxl_endpoint_decoder *cxled, int pos)
+{
+	struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent);
+	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
+	struct cxl_region_params *p = &cxlr->params;
+	struct cxl_port *ep_port, *root_port;
+	struct cxl_dport *dport;
+	int rc = -ENXIO;
+
+	if (cxled->mode != cxlr->mode) {
+		dev_dbg(&cxlr->dev, "%s region mode: %d mismatch: %d\n",
+			dev_name(&cxled->cxld.dev), cxlr->mode, cxled->mode);
+		return -EINVAL;
+	}
+
+	if (cxled->mode == CXL_DECODER_DEAD) {
+		dev_dbg(&cxlr->dev, "%s dead\n", dev_name(&cxled->cxld.dev));
+		return -ENODEV;
+	}
+
+	/* all full of members, or interleave config not established? */
+	if (p->state > CXL_CONFIG_INTERLEAVE_ACTIVE) {
+		dev_dbg(&cxlr->dev, "region already active\n");
+		return -EBUSY;
+	} else if (p->state < CXL_CONFIG_INTERLEAVE_ACTIVE) {
+		dev_dbg(&cxlr->dev, "interleave config missing\n");
+		return -ENXIO;
+	}
+
 	ep_port = cxled_to_port(cxled);
 	root_port = cxlrd_to_port(cxlrd);
 	dport = cxl_find_dport_by_dev(root_port, ep_port->host_bridge);
@@ -1252,13 +1564,6 @@ static int cxl_region_attach(struct cxl_region *cxlr,
 		return -ENXIO;
 	}
 
-	if (cxlrd->calc_hb(cxlrd, pos) != dport) {
-		dev_dbg(&cxlr->dev, "%s:%s invalid target position for %s\n",
-			dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev),
-			dev_name(&cxlrd->cxlsd.cxld.dev));
-		return -ENXIO;
-	}
-
 	if (cxled->cxld.target_type != cxlr->type) {
 		dev_dbg(&cxlr->dev, "%s:%s type mismatch: %d vs %d\n",
 			dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev),
@@ -1282,13 +1587,58 @@ static int cxl_region_attach(struct cxl_region *cxlr,
 		return -EINVAL;
 	}
 
-	for (iter = ep_port; !is_cxl_root(iter);
-	     iter = to_cxl_port(iter->dev.parent)) {
-		rc = cxl_port_attach_region(iter, cxlr, cxled, pos);
+	if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) {
+		int i;
+
+		rc = cxl_region_attach_auto(cxlr, cxled, pos);
 		if (rc)
-			goto err;
+			return rc;
+
+		/* await more targets to arrive... */
+		if (p->nr_targets < p->interleave_ways)
+			return 0;
+
+		/*
+		 * All targets are here, which implies all PCI enumeration that
+		 * affects this region has been completed. Walk the topology to
+		 * sort the devices into their relative region decode position.
+		 */
+		rc = cxl_region_sort_targets(cxlr);
+		if (rc)
+			return rc;
+
+		for (i = 0; i < p->nr_targets; i++) {
+			cxled = p->targets[i];
+			ep_port = cxled_to_port(cxled);
+			dport = cxl_find_dport_by_dev(root_port,
+						      ep_port->host_bridge);
+			rc = cxl_region_attach_position(cxlr, cxlrd, cxled,
+							dport, i);
+			if (rc)
+				return rc;
+		}
+
+		rc = cxl_region_setup_targets(cxlr);
+		if (rc)
+			return rc;
+
+		/*
+		 * If target setup succeeds in the autodiscovery case
+		 * then the region is already committed.
+		 */
+		p->state = CXL_CONFIG_COMMIT;
+
+		return 0;
 	}
 
+	rc = cxl_region_validate_position(cxlr, cxled, pos);
+	if (rc)
+		return rc;
+
+	rc = cxl_region_attach_position(cxlr, cxlrd, cxled, dport, pos);
+	if (rc)
+		return rc;
+
 	p->targets[pos] = cxled;
 	cxled->pos = pos;
 	p->nr_targets++;
@@ -1311,10 +1661,8 @@ static int cxl_region_attach(struct cxl_region *cxlr,
 
 err_decrement:
 	p->nr_targets--;
-err:
-	for (iter = ep_port; !is_cxl_root(iter);
-	     iter = to_cxl_port(iter->dev.parent))
-		cxl_port_detach_region(iter, cxlr, cxled);
+	cxled->pos = -1;
+	p->targets[pos] = NULL;
 	return rc;
 }
 
@@ -1386,31 +1734,25 @@ void cxl_decoder_kill_region(struct cxl_endpoint_decoder *cxled)
 	up_write(&cxl_region_rwsem);
 }
 
-static int attach_target(struct cxl_region *cxlr, const char *decoder, int pos)
+static int attach_target(struct cxl_region *cxlr,
+			 struct cxl_endpoint_decoder *cxled, int pos,
+			 unsigned int state)
 {
-	struct device *dev;
-	int rc;
-
-	dev = bus_find_device_by_name(&cxl_bus_type, NULL, decoder);
-	if (!dev)
-		return -ENODEV;
-
-	if (!is_endpoint_decoder(dev)) {
-		put_device(dev);
-		return -EINVAL;
-	}
+	int rc = 0;
 
+	if (state == TASK_INTERRUPTIBLE)
 		rc = down_write_killable(&cxl_region_rwsem);
+	else
+		down_write(&cxl_region_rwsem);
 	if (rc)
-		goto out;
+		return rc;
+
 	down_read(&cxl_dpa_rwsem);
-	rc = cxl_region_attach(cxlr, to_cxl_endpoint_decoder(dev), pos);
+	rc = cxl_region_attach(cxlr, cxled, pos);
 	if (rc == 0)
 		set_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags);
 	up_read(&cxl_dpa_rwsem);
 	up_write(&cxl_region_rwsem);
-out:
-	put_device(dev);
 	return rc;
 }
 
@@ -1448,8 +1790,23 @@ static size_t store_targetN(struct cxl_region *cxlr, const char *buf, int pos,
 
 	if (sysfs_streq(buf, "\n"))
 		rc = detach_target(cxlr, pos);
-	else
-		rc = attach_target(cxlr, buf, pos);
+	else {
+		struct device *dev;
+
+		dev = bus_find_device_by_name(&cxl_bus_type, NULL, buf);
+		if (!dev)
+			return -ENODEV;
+
+		if (!is_endpoint_decoder(dev)) {
+			rc = -EINVAL;
+			goto out;
+		}
+
+		rc = attach_target(cxlr, to_cxl_endpoint_decoder(dev), pos,
+				   TASK_INTERRUPTIBLE);
+out:
+		put_device(dev);
+	}
 
 	if (rc < 0)
 		return rc;
@@ -1653,6 +2010,15 @@ static struct cxl_region *devm_cxl_add_region(struct cxl_root_decoder *cxlrd,
 	struct device *dev;
 	int rc;
 
+	switch (mode) {
+	case CXL_DECODER_RAM:
+	case CXL_DECODER_PMEM:
+		break;
+	default:
+		dev_err(&cxlrd->cxlsd.cxld.dev, "unsupported mode %d\n", mode);
+		return ERR_PTR(-EINVAL);
+	}
+
 	cxlr = cxl_region_alloc(cxlrd, id);
 	if (IS_ERR(cxlr))
 		return cxlr;
@@ -1681,12 +2047,38 @@ static struct cxl_region *devm_cxl_add_region(struct cxl_root_decoder *cxlrd,
 	return ERR_PTR(rc);
 }
 
+static ssize_t __create_region_show(struct cxl_root_decoder *cxlrd, char *buf)
+{
+	return sysfs_emit(buf, "region%u\n", atomic_read(&cxlrd->region_id));
+}
+
 static ssize_t create_pmem_region_show(struct device *dev,
 				       struct device_attribute *attr, char *buf)
 {
-	struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(dev);
+	return __create_region_show(to_cxl_root_decoder(dev), buf);
+}
 
-	return sysfs_emit(buf, "region%u\n", atomic_read(&cxlrd->region_id));
+static ssize_t create_ram_region_show(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	return __create_region_show(to_cxl_root_decoder(dev), buf);
+}
+
+static struct cxl_region *__create_region(struct cxl_root_decoder *cxlrd,
+					  enum cxl_decoder_mode mode, int id)
+{
+	int rc;
+
+	rc = memregion_alloc(GFP_KERNEL);
+	if (rc < 0)
+		return ERR_PTR(rc);
+
+	if (atomic_cmpxchg(&cxlrd->region_id, id, rc) != id) {
+		memregion_free(rc);
+		return ERR_PTR(-EBUSY);
+	}
+
+	return devm_cxl_add_region(cxlrd, id, mode, CXL_DECODER_EXPANDER);
 }
 
 static ssize_t create_pmem_region_store(struct device *dev,
@@ -1695,29 +2087,39 @@ static ssize_t create_pmem_region_store(struct device *dev,
 {
 	struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(dev);
 	struct cxl_region *cxlr;
-	int id, rc;
+	int rc, id;
 
 	rc = sscanf(buf, "region%d\n", &id);
 	if (rc != 1)
 		return -EINVAL;
 
-	rc = memregion_alloc(GFP_KERNEL);
-	if (rc < 0)
-		return rc;
+	cxlr = __create_region(cxlrd, CXL_DECODER_PMEM, id);
+	if (IS_ERR(cxlr))
+		return PTR_ERR(cxlr);
 
-	if (atomic_cmpxchg(&cxlrd->region_id, id, rc) != id) {
-		memregion_free(rc);
-		return -EBUSY;
-	}
+	return len;
+}
+DEVICE_ATTR_RW(create_pmem_region);
+
+static ssize_t create_ram_region_store(struct device *dev,
+				       struct device_attribute *attr,
+				       const char *buf, size_t len)
+{
+	struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(dev);
+	struct cxl_region *cxlr;
+	int rc, id;
+
+	rc = sscanf(buf, "region%d\n", &id);
+	if (rc != 1)
+		return -EINVAL;
 
-	cxlr = devm_cxl_add_region(cxlrd, id, CXL_DECODER_PMEM,
-				   CXL_DECODER_EXPANDER);
+	cxlr = __create_region(cxlrd, CXL_DECODER_RAM, id);
 	if (IS_ERR(cxlr))
 		return PTR_ERR(cxlr);
 
 	return len;
 }
-DEVICE_ATTR_RW(create_pmem_region);
+DEVICE_ATTR_RW(create_ram_region);
 
 static ssize_t region_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
@@ -1878,6 +2280,75 @@ static struct cxl_pmem_region *cxl_pmem_region_alloc(struct cxl_region *cxlr)
 	return cxlr_pmem;
 }
 
+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;
+
+	down_read(&cxl_region_rwsem);
+	if (p->state != CXL_CONFIG_COMMIT) {
+		cxlr_dax = ERR_PTR(-ENXIO);
+		goto out;
+	}
+
+	cxlr_dax = kzalloc(sizeof(*cxlr_dax), GFP_KERNEL);
+	if (!cxlr_dax) {
+		cxlr_dax = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	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;
+out:
+	up_read(&cxl_region_rwsem);
+
+	return cxlr_dax;
+}
+
 static void cxlr_pmem_unregister(void *_cxlr_pmem)
 {
 	struct cxl_pmem_region *cxlr_pmem = _cxlr_pmem;
@@ -1962,6 +2433,227 @@ static int devm_cxl_add_pmem_region(struct cxl_region *cxlr)
 	return rc;
 }
 
+static void cxlr_dax_unregister(void *_cxlr_dax)
+{
+	struct cxl_dax_region *cxlr_dax = _cxlr_dax;
+
+	device_unregister(&cxlr_dax->dev);
+}
+
+static int devm_cxl_add_dax_region(struct cxl_region *cxlr)
+{
+	struct cxl_dax_region *cxlr_dax;
+	struct device *dev;
+	int rc;
+
+	cxlr_dax = 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)
+		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));
+
+	return devm_add_action_or_reset(&cxlr->dev, cxlr_dax_unregister,
+					cxlr_dax);
+err:
+	put_device(dev);
+	return rc;
+}
+
+static int match_decoder_by_range(struct device *dev, void *data)
+{
+	struct range *r1, *r2 = data;
+	struct cxl_root_decoder *cxlrd;
+
+	if (!is_root_decoder(dev))
+		return 0;
+
+	cxlrd = to_cxl_root_decoder(dev);
+	r1 = &cxlrd->cxlsd.cxld.hpa_range;
+	return range_contains(r1, r2);
+}
+
+static int match_region_by_range(struct device *dev, void *data)
+{
+	struct cxl_region_params *p;
+	struct cxl_region *cxlr;
+	struct range *r = data;
+	int rc = 0;
+
+	if (!is_cxl_region(dev))
+		return 0;
+
+	cxlr = to_cxl_region(dev);
+	p = &cxlr->params;
+
+	down_read(&cxl_region_rwsem);
+	if (p->res && p->res->start == r->start && p->res->end == r->end)
+		rc = 1;
+	up_read(&cxl_region_rwsem);
+
+	return rc;
+}
+
+/* Establish an empty region covering the given HPA range */
+static struct cxl_region *construct_region(struct cxl_root_decoder *cxlrd,
+					   struct cxl_endpoint_decoder *cxled)
+{
+	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
+	struct cxl_port *port = cxlrd_to_port(cxlrd);
+	struct range *hpa = &cxled->cxld.hpa_range;
+	struct cxl_region_params *p;
+	struct cxl_region *cxlr;
+	struct resource *res;
+	int rc;
+
+	do {
+		cxlr = __create_region(cxlrd, cxled->mode,
+				       atomic_read(&cxlrd->region_id));
+	} while (IS_ERR(cxlr) && PTR_ERR(cxlr) == -EBUSY);
+
+	if (IS_ERR(cxlr)) {
+		dev_err(cxlmd->dev.parent,
+			"%s:%s: %s failed assign region: %ld\n",
+			dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev),
+			__func__, PTR_ERR(cxlr));
+		return cxlr;
+	}
+
+	down_write(&cxl_region_rwsem);
+	p = &cxlr->params;
+	if (p->state >= CXL_CONFIG_INTERLEAVE_ACTIVE) {
+		dev_err(cxlmd->dev.parent,
+			"%s:%s: %s autodiscovery interrupted\n",
+			dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev),
+			__func__);
+		rc = -EBUSY;
+		goto err;
+	}
+
+	set_bit(CXL_REGION_F_AUTO, &cxlr->flags);
+
+	res = kmalloc(sizeof(*res), GFP_KERNEL);
+	if (!res) {
+		rc = -ENOMEM;
+		goto err;
+	}
+
+	*res = DEFINE_RES_MEM_NAMED(hpa->start, range_len(hpa),
+				    dev_name(&cxlr->dev));
+	rc = insert_resource(cxlrd->res, res);
+	if (rc) {
+		/*
+		 * Platform-firmware may not have split resources like "System
+		 * RAM" on CXL window boundaries see cxl_region_iomem_release()
+		 */
+		dev_warn(cxlmd->dev.parent,
+			 "%s:%s: %s %s cannot insert resource\n",
+			 dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev),
+			 __func__, dev_name(&cxlr->dev));
+	}
+
+	p->res = res;
+	p->interleave_ways = cxled->cxld.interleave_ways;
+	p->interleave_granularity = cxled->cxld.interleave_granularity;
+	p->state = CXL_CONFIG_INTERLEAVE_ACTIVE;
+
+	rc = sysfs_update_group(&cxlr->dev.kobj, get_cxl_region_target_group());
+	if (rc)
+		goto err;
+
+	dev_dbg(cxlmd->dev.parent, "%s:%s: %s %s res: %pr iw: %d ig: %d\n",
+		dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev), __func__,
+		dev_name(&cxlr->dev), p->res, p->interleave_ways,
+		p->interleave_granularity);
+
+	/* ...to match put_device() in cxl_add_to_region() */
+	get_device(&cxlr->dev);
+	up_write(&cxl_region_rwsem);
+
+	return cxlr;
+
+err:
+	up_write(&cxl_region_rwsem);
+	devm_release_action(port->uport, unregister_region, cxlr);
+	return ERR_PTR(rc);
+}
+
+int cxl_add_to_region(struct cxl_port *root, struct cxl_endpoint_decoder *cxled)
+{
+	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
+	struct range *hpa = &cxled->cxld.hpa_range;
+	struct cxl_decoder *cxld = &cxled->cxld;
+	struct device *cxlrd_dev, *region_dev;
+	struct cxl_root_decoder *cxlrd;
+	struct cxl_region_params *p;
+	struct cxl_region *cxlr;
+	bool attach = false;
+	int rc;
+
+	cxlrd_dev = device_find_child(&root->dev, &cxld->hpa_range,
+				      match_decoder_by_range);
+	if (!cxlrd_dev) {
+		dev_err(cxlmd->dev.parent,
+			"%s:%s no CXL window for range %#llx:%#llx\n",
+			dev_name(&cxlmd->dev), dev_name(&cxld->dev),
+			cxld->hpa_range.start, cxld->hpa_range.end);
+		return -ENXIO;
+	}
+
+	cxlrd = to_cxl_root_decoder(cxlrd_dev);
+
+	/*
+	 * Ensure that if multiple threads race to construct_region() for @hpa
+	 * one does the construction and the others add to that.
+	 */
+	mutex_lock(&cxlrd->range_lock);
+	region_dev = device_find_child(&cxlrd->cxlsd.cxld.dev, hpa,
+				       match_region_by_range);
+	if (!region_dev) {
+		cxlr = construct_region(cxlrd, cxled);
+		region_dev = &cxlr->dev;
+	} else
+		cxlr = to_cxl_region(region_dev);
+	mutex_unlock(&cxlrd->range_lock);
+
+	rc = PTR_ERR_OR_ZERO(cxlr);
+	if (rc)
+		goto out;
+
+	attach_target(cxlr, cxled, -1, TASK_UNINTERRUPTIBLE);
+
+	down_read(&cxl_region_rwsem);
+	p = &cxlr->params;
+	attach = p->state == CXL_CONFIG_COMMIT;
+	up_read(&cxl_region_rwsem);
+
+	if (attach) {
+		/*
+		 * If device_attach() fails the range may still be active via
+		 * the platform-firmware memory map, otherwise the driver for
+		 * regions is local to this file, so driver matching can't fail.
+		 */
+		if (device_attach(&cxlr->dev) < 0)
+			dev_err(&cxlr->dev, "failed to enable, range: %pr\n",
+				p->res);
+	}
+
+	put_device(region_dev);
+out:
+	put_device(cxlrd_dev);
+	return rc;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_add_to_region, CXL);
+
 static int cxl_region_invalidate_memregion(struct cxl_region *cxlr)
 {
 	if (!test_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags))
@@ -1969,7 +2661,7 @@ static int cxl_region_invalidate_memregion(struct cxl_region *cxlr)
 
 	if (!cpu_cache_has_invalidate_memregion()) {
 		if (IS_ENABLED(CONFIG_CXL_REGION_INVALIDATION_TEST)) {
-			dev_warn(
+			dev_warn_once(
 				&cxlr->dev,
 				"Bypassing cpu_cache_invalidate_memregion() for testing!\n");
 			clear_bit(CXL_REGION_F_INCOHERENT, &cxlr->flags);
@@ -1986,6 +2678,15 @@ static int cxl_region_invalidate_memregion(struct cxl_region *cxlr)
 	return 0;
 }
 
+static int is_system_ram(struct resource *res, void *arg)
+{
+	struct cxl_region *cxlr = arg;
+	struct cxl_region_params *p = &cxlr->params;
+
+	dev_dbg(&cxlr->dev, "%pr has System RAM: %pr\n", p->res, res);
+	return 1;
+}
+
 static int cxl_region_probe(struct device *dev)
 {
 	struct cxl_region *cxlr = to_cxl_region(dev);
@@ -2019,6 +2720,17 @@ static int cxl_region_probe(struct device *dev)
 	switch (cxlr->mode) {
 	case CXL_DECODER_PMEM:
 		return devm_cxl_add_pmem_region(cxlr);
+	case CXL_DECODER_RAM:
+		/*
+		 * The region can not be manged by CXL if any portion of
+		 * it is already online as 'System RAM'
+		 */
+		if (walk_iomem_res_desc(IORES_DESC_NONE,
+					IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
+					p->res->start, p->res->end, cxlr,
+					is_system_ram) > 0)
+			return 0;
+		return devm_cxl_add_dax_region(cxlr);
 	default:
 		dev_dbg(&cxlr->dev, "unsupported region mode: %d\n",
 			cxlr->mode);

drivers/cxl/core/trace.c

+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"

drivers/cxl/core/trace.h

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM cxl
+
+#if !defined(_CXL_EVENTS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _CXL_EVENTS_H
+
+#include <linux/tracepoint.h>
+#include <asm-generic/unaligned.h>
+
+#include <cxl.h>
+#include <cxlmem.h>
+
+#define CXL_RAS_UC_CACHE_DATA_PARITY	BIT(0)
+#define CXL_RAS_UC_CACHE_ADDR_PARITY	BIT(1)
+#define CXL_RAS_UC_CACHE_BE_PARITY	BIT(2)
+#define CXL_RAS_UC_CACHE_DATA_ECC	BIT(3)
+#define CXL_RAS_UC_MEM_DATA_PARITY	BIT(4)
+#define CXL_RAS_UC_MEM_ADDR_PARITY	BIT(5)
+#define CXL_RAS_UC_MEM_BE_PARITY	BIT(6)
+#define CXL_RAS_UC_MEM_DATA_ECC		BIT(7)
+#define CXL_RAS_UC_REINIT_THRESH	BIT(8)
+#define CXL_RAS_UC_RSVD_ENCODE		BIT(9)
+#define CXL_RAS_UC_POISON		BIT(10)
+#define CXL_RAS_UC_RECV_OVERFLOW	BIT(11)
+#define CXL_RAS_UC_INTERNAL_ERR		BIT(14)
+#define CXL_RAS_UC_IDE_TX_ERR		BIT(15)
+#define CXL_RAS_UC_IDE_RX_ERR		BIT(16)
+
+#define show_uc_errs(status)	__print_flags(status, " | ",		  \
+	{ CXL_RAS_UC_CACHE_DATA_PARITY, "Cache Data Parity Error" },	  \
+	{ CXL_RAS_UC_CACHE_ADDR_PARITY, "Cache Address Parity Error" },	  \
+	{ CXL_RAS_UC_CACHE_BE_PARITY, "Cache Byte Enable Parity Error" }, \
+	{ CXL_RAS_UC_CACHE_DATA_ECC, "Cache Data ECC Error" },		  \
+	{ CXL_RAS_UC_MEM_DATA_PARITY, "Memory Data Parity Error" },	  \
+	{ CXL_RAS_UC_MEM_ADDR_PARITY, "Memory Address Parity Error" },	  \
+	{ CXL_RAS_UC_MEM_BE_PARITY, "Memory Byte Enable Parity Error" },  \
+	{ CXL_RAS_UC_MEM_DATA_ECC, "Memory Data ECC Error" },		  \
+	{ CXL_RAS_UC_REINIT_THRESH, "REINIT Threshold Hit" },		  \
+	{ CXL_RAS_UC_RSVD_ENCODE, "Received Unrecognized Encoding" },	  \
+	{ CXL_RAS_UC_POISON, "Received Poison From Peer" },		  \
+	{ CXL_RAS_UC_RECV_OVERFLOW, "Receiver Overflow" },		  \
+	{ CXL_RAS_UC_INTERNAL_ERR, "Component Specific Error" },	  \
+	{ CXL_RAS_UC_IDE_TX_ERR, "IDE Tx Error" },			  \
+	{ CXL_RAS_UC_IDE_RX_ERR, "IDE Rx Error" }			  \
+)
+
+TRACE_EVENT(cxl_aer_uncorrectable_error,
+	TP_PROTO(const struct cxl_memdev *cxlmd, u32 status, u32 fe, u32 *hl),
+	TP_ARGS(cxlmd, status, fe, hl),
+	TP_STRUCT__entry(
+		__string(memdev, dev_name(&cxlmd->dev))
+		__string(host, dev_name(cxlmd->dev.parent))
+		__field(u64, serial)
+		__field(u32, status)
+		__field(u32, first_error)
+		__array(u32, header_log, CXL_HEADERLOG_SIZE_U32)
+	),
+	TP_fast_assign(
+		__assign_str(memdev, dev_name(&cxlmd->dev));
+		__assign_str(host, dev_name(cxlmd->dev.parent));
+		__entry->serial = cxlmd->cxlds->serial;
+		__entry->status = status;
+		__entry->first_error = fe;
+		/*
+		 * Embed the 512B headerlog data for user app retrieval and
+		 * parsing, but no need to print this in the trace buffer.
+		 */
+		memcpy(__entry->header_log, hl, CXL_HEADERLOG_SIZE);
+	),
+	TP_printk("memdev=%s host=%s serial=%lld: status: '%s' first_error: '%s'",
+		  __get_str(memdev), __get_str(host), __entry->serial,
+		  show_uc_errs(__entry->status),
+		  show_uc_errs(__entry->first_error)
+	)
+);
+
+#define CXL_RAS_CE_CACHE_DATA_ECC	BIT(0)
+#define CXL_RAS_CE_MEM_DATA_ECC		BIT(1)
+#define CXL_RAS_CE_CRC_THRESH		BIT(2)
+#define CLX_RAS_CE_RETRY_THRESH		BIT(3)
+#define CXL_RAS_CE_CACHE_POISON		BIT(4)
+#define CXL_RAS_CE_MEM_POISON		BIT(5)
+#define CXL_RAS_CE_PHYS_LAYER_ERR	BIT(6)
+
+#define show_ce_errs(status)	__print_flags(status, " | ",			\
+	{ CXL_RAS_CE_CACHE_DATA_ECC, "Cache Data ECC Error" },			\
+	{ CXL_RAS_CE_MEM_DATA_ECC, "Memory Data ECC Error" },			\
+	{ CXL_RAS_CE_CRC_THRESH, "CRC Threshold Hit" },				\
+	{ CLX_RAS_CE_RETRY_THRESH, "Retry Threshold" },				\
+	{ CXL_RAS_CE_CACHE_POISON, "Received Cache Poison From Peer" },		\
+	{ CXL_RAS_CE_MEM_POISON, "Received Memory Poison From Peer" },		\
+	{ CXL_RAS_CE_PHYS_LAYER_ERR, "Received Error From Physical Layer" }	\
+)
+
+TRACE_EVENT(cxl_aer_correctable_error,
+	TP_PROTO(const struct cxl_memdev *cxlmd, u32 status),
+	TP_ARGS(cxlmd, status),
+	TP_STRUCT__entry(
+		__string(memdev, dev_name(&cxlmd->dev))
+		__string(host, dev_name(cxlmd->dev.parent))
+		__field(u64, serial)
+		__field(u32, status)
+	),
+	TP_fast_assign(
+		__assign_str(memdev, dev_name(&cxlmd->dev));
+		__assign_str(host, dev_name(cxlmd->dev.parent));
+		__entry->serial = cxlmd->cxlds->serial;
+		__entry->status = status;
+	),
+	TP_printk("memdev=%s host=%s serial=%lld: status: '%s'",
+		  __get_str(memdev), __get_str(host), __entry->serial,
+		  show_ce_errs(__entry->status)
+	)
+);
+
+#define cxl_event_log_type_str(type)				\
+	__print_symbolic(type,					\
+		{ CXL_EVENT_TYPE_INFO, "Informational" },	\
+		{ CXL_EVENT_TYPE_WARN, "Warning" },		\
+		{ CXL_EVENT_TYPE_FAIL, "Failure" },		\
+		{ CXL_EVENT_TYPE_FATAL, "Fatal" })
+
+TRACE_EVENT(cxl_overflow,
+
+	TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
+		 struct cxl_get_event_payload *payload),
+
+	TP_ARGS(cxlmd, log, payload),
+
+	TP_STRUCT__entry(
+		__string(memdev, dev_name(&cxlmd->dev))
+		__string(host, dev_name(cxlmd->dev.parent))
+		__field(int, log)
+		__field(u64, serial)
+		__field(u64, first_ts)
+		__field(u64, last_ts)
+		__field(u16, count)
+	),
+
+	TP_fast_assign(
+		__assign_str(memdev, dev_name(&cxlmd->dev));
+		__assign_str(host, dev_name(cxlmd->dev.parent));
+		__entry->serial = cxlmd->cxlds->serial;
+		__entry->log = log;
+		__entry->count = le16_to_cpu(payload->overflow_err_count);
+		__entry->first_ts = le64_to_cpu(payload->first_overflow_timestamp);
+		__entry->last_ts = le64_to_cpu(payload->last_overflow_timestamp);
+	),
+
+	TP_printk("memdev=%s host=%s serial=%lld: log=%s : %u records from %llu to %llu",
+		__get_str(memdev), __get_str(host), __entry->serial,
+		cxl_event_log_type_str(__entry->log), __entry->count,
+		__entry->first_ts, __entry->last_ts)
+
+);
+
+/*
+ * Common Event Record Format
+ * CXL 3.0 section 8.2.9.2.1; Table 8-42
+ */
+#define CXL_EVENT_RECORD_FLAG_PERMANENT		BIT(2)
+#define CXL_EVENT_RECORD_FLAG_MAINT_NEEDED	BIT(3)
+#define CXL_EVENT_RECORD_FLAG_PERF_DEGRADED	BIT(4)
+#define CXL_EVENT_RECORD_FLAG_HW_REPLACE	BIT(5)
+#define show_hdr_flags(flags)	__print_flags(flags, " | ",			   \
+	{ CXL_EVENT_RECORD_FLAG_PERMANENT,	"PERMANENT_CONDITION"		}, \
+	{ CXL_EVENT_RECORD_FLAG_MAINT_NEEDED,	"MAINTENANCE_NEEDED"		}, \
+	{ CXL_EVENT_RECORD_FLAG_PERF_DEGRADED,	"PERFORMANCE_DEGRADED"		}, \
+	{ CXL_EVENT_RECORD_FLAG_HW_REPLACE,	"HARDWARE_REPLACEMENT_NEEDED"	}  \
+)
+
+/*
+ * Define macros for the common header of each CXL event.
+ *
+ * Tracepoints using these macros must do 3 things:
+ *
+ *	1) Add CXL_EVT_TP_entry to TP_STRUCT__entry
+ *	2) Use CXL_EVT_TP_fast_assign within TP_fast_assign;
+ *	   pass the dev, log, and CXL event header
+ *	3) Use CXL_EVT_TP_printk() instead of TP_printk()
+ *
+ * See the generic_event tracepoint as an example.
+ */
+#define CXL_EVT_TP_entry					\
+	__string(memdev, dev_name(&cxlmd->dev))			\
+	__string(host, dev_name(cxlmd->dev.parent))		\
+	__field(int, log)					\
+	__field_struct(uuid_t, hdr_uuid)			\
+	__field(u64, serial)					\
+	__field(u32, hdr_flags)					\
+	__field(u16, hdr_handle)				\
+	__field(u16, hdr_related_handle)			\
+	__field(u64, hdr_timestamp)				\
+	__field(u8, hdr_length)					\
+	__field(u8, hdr_maint_op_class)
+
+#define CXL_EVT_TP_fast_assign(cxlmd, l, hdr)					\
+	__assign_str(memdev, dev_name(&(cxlmd)->dev));				\
+	__assign_str(host, dev_name((cxlmd)->dev.parent));			\
+	__entry->log = (l);							\
+	__entry->serial = (cxlmd)->cxlds->serial;				\
+	memcpy(&__entry->hdr_uuid, &(hdr).id, sizeof(uuid_t));			\
+	__entry->hdr_length = (hdr).length;					\
+	__entry->hdr_flags = get_unaligned_le24((hdr).flags);			\
+	__entry->hdr_handle = le16_to_cpu((hdr).handle);			\
+	__entry->hdr_related_handle = le16_to_cpu((hdr).related_handle);	\
+	__entry->hdr_timestamp = le64_to_cpu((hdr).timestamp);			\
+	__entry->hdr_maint_op_class = (hdr).maint_op_class
+
+#define CXL_EVT_TP_printk(fmt, ...) \
+	TP_printk("memdev=%s host=%s serial=%lld log=%s : time=%llu uuid=%pUb "	\
+		"len=%d flags='%s' handle=%x related_handle=%x "		\
+		"maint_op_class=%u : " fmt,					\
+		__get_str(memdev), __get_str(host), __entry->serial,		\
+		cxl_event_log_type_str(__entry->log),				\
+		__entry->hdr_timestamp, &__entry->hdr_uuid, __entry->hdr_length,\
+		show_hdr_flags(__entry->hdr_flags), __entry->hdr_handle,	\
+		__entry->hdr_related_handle, __entry->hdr_maint_op_class,	\
+		##__VA_ARGS__)
+
+TRACE_EVENT(cxl_generic_event,
+
+	TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
+		 struct cxl_event_record_raw *rec),
+
+	TP_ARGS(cxlmd, log, rec),
+
+	TP_STRUCT__entry(
+		CXL_EVT_TP_entry
+		__array(u8, data, CXL_EVENT_RECORD_DATA_LENGTH)
+	),
+
+	TP_fast_assign(
+		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		memcpy(__entry->data, &rec->data, CXL_EVENT_RECORD_DATA_LENGTH);
+	),
+
+	CXL_EVT_TP_printk("%s",
+		__print_hex(__entry->data, CXL_EVENT_RECORD_DATA_LENGTH))
+);
+
+/*
+ * Physical Address field masks
+ *
+ * General Media Event Record
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ *
+ * DRAM Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ */
+#define CXL_DPA_FLAGS_MASK			0x3F
+#define CXL_DPA_MASK				(~CXL_DPA_FLAGS_MASK)
+
+#define CXL_DPA_VOLATILE			BIT(0)
+#define CXL_DPA_NOT_REPAIRABLE			BIT(1)
+#define show_dpa_flags(flags)	__print_flags(flags, "|",		   \
+	{ CXL_DPA_VOLATILE,			"VOLATILE"		}, \
+	{ CXL_DPA_NOT_REPAIRABLE,		"NOT_REPAIRABLE"	}  \
+)
+
+/*
+ * General Media Event Record - GMER
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+#define CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT		BIT(0)
+#define CXL_GMER_EVT_DESC_THRESHOLD_EVENT		BIT(1)
+#define CXL_GMER_EVT_DESC_POISON_LIST_OVERFLOW		BIT(2)
+#define show_event_desc_flags(flags)	__print_flags(flags, "|",		   \
+	{ CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT,		"UNCORRECTABLE_EVENT"	}, \
+	{ CXL_GMER_EVT_DESC_THRESHOLD_EVENT,		"THRESHOLD_EVENT"	}, \
+	{ CXL_GMER_EVT_DESC_POISON_LIST_OVERFLOW,	"POISON_LIST_OVERFLOW"	}  \
+)
+
+#define CXL_GMER_MEM_EVT_TYPE_ECC_ERROR			0x00
+#define CXL_GMER_MEM_EVT_TYPE_INV_ADDR			0x01
+#define CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR		0x02
+#define show_mem_event_type(type)	__print_symbolic(type,			\
+	{ CXL_GMER_MEM_EVT_TYPE_ECC_ERROR,		"ECC Error" },		\
+	{ CXL_GMER_MEM_EVT_TYPE_INV_ADDR,		"Invalid Address" },	\
+	{ CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR,	"Data Path Error" }	\
+)
+
+#define CXL_GMER_TRANS_UNKNOWN				0x00
+#define CXL_GMER_TRANS_HOST_READ			0x01
+#define CXL_GMER_TRANS_HOST_WRITE			0x02
+#define CXL_GMER_TRANS_HOST_SCAN_MEDIA			0x03
+#define CXL_GMER_TRANS_HOST_INJECT_POISON		0x04
+#define CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB		0x05
+#define CXL_GMER_TRANS_INTERNAL_MEDIA_MANAGEMENT	0x06
+#define show_trans_type(type)	__print_symbolic(type,					\
+	{ CXL_GMER_TRANS_UNKNOWN,			"Unknown" },			\
+	{ CXL_GMER_TRANS_HOST_READ,			"Host Read" },			\
+	{ CXL_GMER_TRANS_HOST_WRITE,			"Host Write" },			\
+	{ CXL_GMER_TRANS_HOST_SCAN_MEDIA,		"Host Scan Media" },		\
+	{ CXL_GMER_TRANS_HOST_INJECT_POISON,		"Host Inject Poison" },		\
+	{ CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB,		"Internal Media Scrub" },	\
+	{ CXL_GMER_TRANS_INTERNAL_MEDIA_MANAGEMENT,	"Internal Media Management" }	\
+)
+
+#define CXL_GMER_VALID_CHANNEL				BIT(0)
+#define CXL_GMER_VALID_RANK				BIT(1)
+#define CXL_GMER_VALID_DEVICE				BIT(2)
+#define CXL_GMER_VALID_COMPONENT			BIT(3)
+#define show_valid_flags(flags)	__print_flags(flags, "|",		   \
+	{ CXL_GMER_VALID_CHANNEL,			"CHANNEL"	}, \
+	{ CXL_GMER_VALID_RANK,				"RANK"		}, \
+	{ CXL_GMER_VALID_DEVICE,			"DEVICE"	}, \
+	{ CXL_GMER_VALID_COMPONENT,			"COMPONENT"	}  \
+)
+
+TRACE_EVENT(cxl_general_media,
+
+	TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
+		 struct cxl_event_gen_media *rec),
+
+	TP_ARGS(cxlmd, log, rec),
+
+	TP_STRUCT__entry(
+		CXL_EVT_TP_entry
+		/* General Media */
+		__field(u64, dpa)
+		__field(u8, descriptor)
+		__field(u8, type)
+		__field(u8, transaction_type)
+		__field(u8, channel)
+		__field(u32, device)
+		__array(u8, comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE)
+		__field(u16, validity_flags)
+		/* Following are out of order to pack trace record */
+		__field(u8, rank)
+		__field(u8, dpa_flags)
+	),
+
+	TP_fast_assign(
+		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+
+		/* General Media */
+		__entry->dpa = le64_to_cpu(rec->phys_addr);
+		__entry->dpa_flags = __entry->dpa & CXL_DPA_FLAGS_MASK;
+		/* Mask after flags have been parsed */
+		__entry->dpa &= CXL_DPA_MASK;
+		__entry->descriptor = rec->descriptor;
+		__entry->type = rec->type;
+		__entry->transaction_type = rec->transaction_type;
+		__entry->channel = rec->channel;
+		__entry->rank = rec->rank;
+		__entry->device = get_unaligned_le24(rec->device);
+		memcpy(__entry->comp_id, &rec->component_id,
+			CXL_EVENT_GEN_MED_COMP_ID_SIZE);
+		__entry->validity_flags = get_unaligned_le16(&rec->validity_flags);
+	),
+
+	CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' " \
+		"descriptor='%s' type='%s' transaction_type='%s' channel=%u rank=%u " \
+		"device=%x comp_id=%s validity_flags='%s'",
+		__entry->dpa, show_dpa_flags(__entry->dpa_flags),
+		show_event_desc_flags(__entry->descriptor),
+		show_mem_event_type(__entry->type),
+		show_trans_type(__entry->transaction_type),
+		__entry->channel, __entry->rank, __entry->device,
+		__print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE),
+		show_valid_flags(__entry->validity_flags)
+	)
+);
+
+/*
+ * DRAM Event Record - DER
+ *
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ */
+/*
+ * DRAM Event Record defines many fields the same as the General Media Event
+ * Record.  Reuse those definitions as appropriate.
+ */
+#define CXL_DER_VALID_CHANNEL				BIT(0)
+#define CXL_DER_VALID_RANK				BIT(1)
+#define CXL_DER_VALID_NIBBLE				BIT(2)
+#define CXL_DER_VALID_BANK_GROUP			BIT(3)
+#define CXL_DER_VALID_BANK				BIT(4)
+#define CXL_DER_VALID_ROW				BIT(5)
+#define CXL_DER_VALID_COLUMN				BIT(6)
+#define CXL_DER_VALID_CORRECTION_MASK			BIT(7)
+#define show_dram_valid_flags(flags)	__print_flags(flags, "|",			   \
+	{ CXL_DER_VALID_CHANNEL,			"CHANNEL"		}, \
+	{ CXL_DER_VALID_RANK,				"RANK"			}, \
+	{ CXL_DER_VALID_NIBBLE,				"NIBBLE"		}, \
+	{ CXL_DER_VALID_BANK_GROUP,			"BANK GROUP"		}, \
+	{ CXL_DER_VALID_BANK,				"BANK"			}, \
+	{ CXL_DER_VALID_ROW,				"ROW"			}, \
+	{ CXL_DER_VALID_COLUMN,				"COLUMN"		}, \
+	{ CXL_DER_VALID_CORRECTION_MASK,		"CORRECTION MASK"	}  \
+)
+
+TRACE_EVENT(cxl_dram,
+
+	TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
+		 struct cxl_event_dram *rec),
+
+	TP_ARGS(cxlmd, log, rec),
+
+	TP_STRUCT__entry(
+		CXL_EVT_TP_entry
+		/* DRAM */
+		__field(u64, dpa)
+		__field(u8, descriptor)
+		__field(u8, type)
+		__field(u8, transaction_type)
+		__field(u8, channel)
+		__field(u16, validity_flags)
+		__field(u16, column)	/* Out of order to pack trace record */
+		__field(u32, nibble_mask)
+		__field(u32, row)
+		__array(u8, cor_mask, CXL_EVENT_DER_CORRECTION_MASK_SIZE)
+		__field(u8, rank)	/* Out of order to pack trace record */
+		__field(u8, bank_group)	/* Out of order to pack trace record */
+		__field(u8, bank)	/* Out of order to pack trace record */
+		__field(u8, dpa_flags)	/* Out of order to pack trace record */
+	),
+
+	TP_fast_assign(
+		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+
+		/* DRAM */
+		__entry->dpa = le64_to_cpu(rec->phys_addr);
+		__entry->dpa_flags = __entry->dpa & CXL_DPA_FLAGS_MASK;
+		__entry->dpa &= CXL_DPA_MASK;
+		__entry->descriptor = rec->descriptor;
+		__entry->type = rec->type;
+		__entry->transaction_type = rec->transaction_type;
+		__entry->validity_flags = get_unaligned_le16(rec->validity_flags);
+		__entry->channel = rec->channel;
+		__entry->rank = rec->rank;
+		__entry->nibble_mask = get_unaligned_le24(rec->nibble_mask);
+		__entry->bank_group = rec->bank_group;
+		__entry->bank = rec->bank;
+		__entry->row = get_unaligned_le24(rec->row);
+		__entry->column = get_unaligned_le16(rec->column);
+		memcpy(__entry->cor_mask, &rec->correction_mask,
+			CXL_EVENT_DER_CORRECTION_MASK_SIZE);
+	),
+
+	CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' descriptor='%s' type='%s' " \
+		"transaction_type='%s' channel=%u rank=%u nibble_mask=%x " \
+		"bank_group=%u bank=%u row=%u column=%u cor_mask=%s " \
+		"validity_flags='%s'",
+		__entry->dpa, show_dpa_flags(__entry->dpa_flags),
+		show_event_desc_flags(__entry->descriptor),
+		show_mem_event_type(__entry->type),
+		show_trans_type(__entry->transaction_type),
+		__entry->channel, __entry->rank, __entry->nibble_mask,
+		__entry->bank_group, __entry->bank,
+		__entry->row, __entry->column,
+		__print_hex(__entry->cor_mask, CXL_EVENT_DER_CORRECTION_MASK_SIZE),
+		show_dram_valid_flags(__entry->validity_flags)
+	)
+);
+
+/*
+ * Memory Module Event Record - MMER
+ *
+ * CXL res 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+#define CXL_MMER_HEALTH_STATUS_CHANGE		0x00
+#define CXL_MMER_MEDIA_STATUS_CHANGE		0x01
+#define CXL_MMER_LIFE_USED_CHANGE		0x02
+#define CXL_MMER_TEMP_CHANGE			0x03
+#define CXL_MMER_DATA_PATH_ERROR		0x04
+#define CXL_MMER_LSA_ERROR			0x05
+#define show_dev_evt_type(type)	__print_symbolic(type,			   \
+	{ CXL_MMER_HEALTH_STATUS_CHANGE,	"Health Status Change"	}, \
+	{ CXL_MMER_MEDIA_STATUS_CHANGE,		"Media Status Change"	}, \
+	{ CXL_MMER_LIFE_USED_CHANGE,		"Life Used Change"	}, \
+	{ CXL_MMER_TEMP_CHANGE,			"Temperature Change"	}, \
+	{ CXL_MMER_DATA_PATH_ERROR,		"Data Path Error"	}, \
+	{ CXL_MMER_LSA_ERROR,			"LSA Error"		}  \
+)
+
+/*
+ * Device Health Information - DHI
+ *
+ * CXL res 3.0 section 8.2.9.8.3.1; Table 8-100
+ */
+#define CXL_DHI_HS_MAINTENANCE_NEEDED				BIT(0)
+#define CXL_DHI_HS_PERFORMANCE_DEGRADED				BIT(1)
+#define CXL_DHI_HS_HW_REPLACEMENT_NEEDED			BIT(2)
+#define show_health_status_flags(flags)	__print_flags(flags, "|",	   \
+	{ CXL_DHI_HS_MAINTENANCE_NEEDED,	"MAINTENANCE_NEEDED"	}, \
+	{ CXL_DHI_HS_PERFORMANCE_DEGRADED,	"PERFORMANCE_DEGRADED"	}, \
+	{ CXL_DHI_HS_HW_REPLACEMENT_NEEDED,	"REPLACEMENT_NEEDED"	}  \
+)
+
+#define CXL_DHI_MS_NORMAL							0x00
+#define CXL_DHI_MS_NOT_READY							0x01
+#define CXL_DHI_MS_WRITE_PERSISTENCY_LOST					0x02
+#define CXL_DHI_MS_ALL_DATA_LOST						0x03
+#define CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_EVENT_POWER_LOSS			0x04
+#define CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_EVENT_SHUTDOWN			0x05
+#define CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_IMMINENT				0x06
+#define CXL_DHI_MS_WRITE_ALL_DATA_LOSS_EVENT_POWER_LOSS				0x07
+#define CXL_DHI_MS_WRITE_ALL_DATA_LOSS_EVENT_SHUTDOWN				0x08
+#define CXL_DHI_MS_WRITE_ALL_DATA_LOSS_IMMINENT					0x09
+#define show_media_status(ms)	__print_symbolic(ms,			   \
+	{ CXL_DHI_MS_NORMAL,						   \
+		"Normal"						}, \
+	{ CXL_DHI_MS_NOT_READY,						   \
+		"Not Ready"						}, \
+	{ CXL_DHI_MS_WRITE_PERSISTENCY_LOST,				   \
+		"Write Persistency Lost"				}, \
+	{ CXL_DHI_MS_ALL_DATA_LOST,					   \
+		"All Data Lost"						}, \
+	{ CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_EVENT_POWER_LOSS,		   \
+		"Write Persistency Loss in the Event of Power Loss"	}, \
+	{ CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_EVENT_SHUTDOWN,		   \
+		"Write Persistency Loss in Event of Shutdown"		}, \
+	{ CXL_DHI_MS_WRITE_PERSISTENCY_LOSS_IMMINENT,			   \
+		"Write Persistency Loss Imminent"			}, \
+	{ CXL_DHI_MS_WRITE_ALL_DATA_LOSS_EVENT_POWER_LOSS,		   \
+		"All Data Loss in Event of Power Loss"			}, \
+	{ CXL_DHI_MS_WRITE_ALL_DATA_LOSS_EVENT_SHUTDOWN,		   \
+		"All Data loss in the Event of Shutdown"		}, \
+	{ CXL_DHI_MS_WRITE_ALL_DATA_LOSS_IMMINENT,			   \
+		"All Data Loss Imminent"				}  \
+)
+
+#define CXL_DHI_AS_NORMAL		0x0
+#define CXL_DHI_AS_WARNING		0x1
+#define CXL_DHI_AS_CRITICAL		0x2
+#define show_two_bit_status(as) __print_symbolic(as,	   \
+	{ CXL_DHI_AS_NORMAL,		"Normal"	}, \
+	{ CXL_DHI_AS_WARNING,		"Warning"	}, \
+	{ CXL_DHI_AS_CRITICAL,		"Critical"	}  \
+)
+#define show_one_bit_status(as) __print_symbolic(as,	   \
+	{ CXL_DHI_AS_NORMAL,		"Normal"	}, \
+	{ CXL_DHI_AS_WARNING,		"Warning"	}  \
+)
+
+#define CXL_DHI_AS_LIFE_USED(as)			(as & 0x3)
+#define CXL_DHI_AS_DEV_TEMP(as)				((as & 0xC) >> 2)
+#define CXL_DHI_AS_COR_VOL_ERR_CNT(as)			((as & 0x10) >> 4)
+#define CXL_DHI_AS_COR_PER_ERR_CNT(as)			((as & 0x20) >> 5)
+
+TRACE_EVENT(cxl_memory_module,
+
+	TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
+		 struct cxl_event_mem_module *rec),
+
+	TP_ARGS(cxlmd, log, rec),
+
+	TP_STRUCT__entry(
+		CXL_EVT_TP_entry
+
+		/* Memory Module Event */
+		__field(u8, event_type)
+
+		/* Device Health Info */
+		__field(u8, health_status)
+		__field(u8, media_status)
+		__field(u8, life_used)
+		__field(u32, dirty_shutdown_cnt)
+		__field(u32, cor_vol_err_cnt)
+		__field(u32, cor_per_err_cnt)
+		__field(s16, device_temp)
+		__field(u8, add_status)
+	),
+
+	TP_fast_assign(
+		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+
+		/* Memory Module Event */
+		__entry->event_type = rec->event_type;
+
+		/* Device Health Info */
+		__entry->health_status = rec->info.health_status;
+		__entry->media_status = rec->info.media_status;
+		__entry->life_used = rec->info.life_used;
+		__entry->dirty_shutdown_cnt = get_unaligned_le32(rec->info.dirty_shutdown_cnt);
+		__entry->cor_vol_err_cnt = get_unaligned_le32(rec->info.cor_vol_err_cnt);
+		__entry->cor_per_err_cnt = get_unaligned_le32(rec->info.cor_per_err_cnt);
+		__entry->device_temp = get_unaligned_le16(rec->info.device_temp);
+		__entry->add_status = rec->info.add_status;
+	),
+
+	CXL_EVT_TP_printk("event_type='%s' health_status='%s' media_status='%s' " \
+		"as_life_used=%s as_dev_temp=%s as_cor_vol_err_cnt=%s " \
+		"as_cor_per_err_cnt=%s life_used=%u device_temp=%d " \
+		"dirty_shutdown_cnt=%u cor_vol_err_cnt=%u cor_per_err_cnt=%u",
+		show_dev_evt_type(__entry->event_type),
+		show_health_status_flags(__entry->health_status),
+		show_media_status(__entry->media_status),
+		show_two_bit_status(CXL_DHI_AS_LIFE_USED(__entry->add_status)),
+		show_two_bit_status(CXL_DHI_AS_DEV_TEMP(__entry->add_status)),
+		show_one_bit_status(CXL_DHI_AS_COR_VOL_ERR_CNT(__entry->add_status)),
+		show_one_bit_status(CXL_DHI_AS_COR_PER_ERR_CNT(__entry->add_status)),
+		__entry->life_used, __entry->device_temp,
+		__entry->dirty_shutdown_cnt, __entry->cor_vol_err_cnt,
+		__entry->cor_per_err_cnt
+	)
+);
+
+#endif /* _CXL_EVENTS_H */
+
+#define TRACE_INCLUDE_FILE trace
+#include <trace/define_trace.h>

drivers/cxl/cxl.h

@@ -130,6 +130,7 @@ static inline int ways_to_eiw(unsigned int ways, u8 *eiw)
 #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
@@ -140,6 +141,8 @@ static inline int ways_to_eiw(unsigned int ways, u8 *eiw)
 #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_512
+#define CXL_HEADERLOG_SIZE_U32 SZ_512 / sizeof(u32)
 
 /* CXL 2.0 8.2.8.1 Device Capabilities Array Register */
 #define CXLDEV_CAP_ARRAY_OFFSET 0x0
@@ -154,6 +157,22 @@ static inline int ways_to_eiw(unsigned int ways, u8 *eiw)
 #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)
@@ -259,6 +278,8 @@ resource_size_t cxl_rcrb_to_component(struct device *dev,
  * 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)
@@ -318,12 +339,36 @@ enum cxl_decoder_mode {
 	CXL_DECODER_DEAD,
 };
 
+static inline const char *cxl_decoder_mode_name(enum cxl_decoder_mode mode)
+{
+	static const char * const names[] = {
+		[CXL_DECODER_NONE] = "none",
+		[CXL_DECODER_RAM] = "ram",
+		[CXL_DECODER_PMEM] = "pmem",
+		[CXL_DECODER_MIXED] = "mixed",
+	};
+
+	if (mode >= CXL_DECODER_NONE && mode <= CXL_DECODER_MIXED)
+		return names[mode];
+	return "mixed";
+}
+
+/*
+ * Track whether this decoder is reserved for region autodiscovery, or
+ * free for userspace provisioning.
+ */
+enum cxl_decoder_state {
+	CXL_DECODER_STATE_MANUAL,
+	CXL_DECODER_STATE_AUTO,
+};
+
 /**
  * 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
  * @mode: which memory type / access-mode-partition this decoder targets
+ * @state: autodiscovery state
  * @pos: interleave position in @cxld.region
  */
 struct cxl_endpoint_decoder {
@@ -331,6 +376,7 @@ struct cxl_endpoint_decoder {
 	struct resource *dpa_res;
 	resource_size_t skip;
 	enum cxl_decoder_mode mode;
+	enum cxl_decoder_state state;
 	int pos;
 };
 
@@ -364,6 +410,7 @@ typedef struct cxl_dport *(*cxl_calc_hb_fn)(struct cxl_root_decoder *cxlrd,
  * @region_id: region id for next region provisioning event
  * @calc_hb: which host bridge covers the n'th position by granularity
  * @platform_data: platform specific configuration data
+ * @range_lock: sync region autodiscovery by address range
  * @cxlsd: base cxl switch decoder
  */
 struct cxl_root_decoder {
@@ -371,6 +418,7 @@ struct cxl_root_decoder {
 	atomic_t region_id;
 	cxl_calc_hb_fn calc_hb;
 	void *platform_data;
+	struct mutex range_lock;
 	struct cxl_switch_decoder cxlsd;
 };
 
@@ -420,6 +468,13 @@ struct cxl_region_params {
  */
 #define CXL_REGION_F_INCOHERENT 0
 
+/*
+ * 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 1
+
 /**
  * struct cxl_region - CXL region
  * @dev: This region's device
@@ -475,6 +530,12 @@ struct cxl_pmem_region {
 	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
@@ -615,8 +676,10 @@ struct cxl_dport *devm_cxl_add_rch_dport(struct cxl_port *port,
 
 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,
@@ -630,10 +693,26 @@ int cxl_decoder_add_locked(struct cxl_decoder *cxld, int *target_map);
 int cxl_decoder_autoremove(struct device *host, struct cxl_decoder *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, PCIE_DEVICE
+ * @ranges: Number of active HDM ranges this device uses.
+ * @dvsec_range: cached attributes of the ranges in the DVSEC, PCIE_DEVICE
+ */
+struct cxl_endpoint_dvsec_info {
+	bool mem_enabled;
+	int ranges;
+	struct range dvsec_range[2];
+};
+
 struct cxl_hdm;
-struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port);
-int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm);
+struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port,
+				   struct cxl_endpoint_dvsec_info *info);
+int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
+				struct cxl_endpoint_dvsec_info *info);
 int devm_cxl_add_passthrough_decoder(struct cxl_port *port);
+int cxl_dvsec_rr_decode(struct device *dev, int dvsec,
+			struct cxl_endpoint_dvsec_info *info);
 
 bool is_cxl_region(struct device *dev);
 
@@ -667,6 +746,7 @@ void cxl_driver_unregister(struct cxl_driver *cxl_drv);
 #define CXL_DEVICE_MEMORY_EXPANDER	5
 #define CXL_DEVICE_REGION		6
 #define CXL_DEVICE_PMEM_REGION		7
+#define CXL_DEVICE_DAX_REGION		8
 
 #define MODULE_ALIAS_CXL(type) MODULE_ALIAS("cxl:t" __stringify(type) "*")
 #define CXL_MODALIAS_FMT "cxl:t%d"
@@ -683,6 +763,9 @@ struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct device *dev);
 #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_port *root,
+		      struct cxl_endpoint_decoder *cxled);
+struct cxl_dax_region *to_cxl_dax_region(struct device *dev);
 #else
 static inline bool is_cxl_pmem_region(struct device *dev)
 {
@@ -692,6 +775,15 @@ static inline struct cxl_pmem_region *to_cxl_pmem_region(struct device *dev)
 {
 	return NULL;
 }
+static inline int cxl_add_to_region(struct cxl_port *root,
+				    struct cxl_endpoint_decoder *cxled)
+{
+	return 0;
+}
+static inline struct cxl_dax_region *to_cxl_dax_region(struct device *dev)
+{
+	return NULL;
+}
 #endif
 
 /*

drivers/cxl/cxlmem.h

@@ -4,6 +4,7 @@
 #define __CXL_MEM_H__
 #include <uapi/linux/cxl_mem.h>
 #include <linux/cdev.h>
+#include <linux/uuid.h>
 #include "cxl.h"
 
 /* CXL 2.0 8.2.8.5.1.1 Memory Device Status Register */
@@ -38,6 +39,7 @@
  * @cxl_nvb: coordinate removal of @cxl_nvd if present
  * @cxl_nvd: optional bridge to an nvdimm if the device supports pmem
  * @id: id number of this memdev instance.
+ * @depth: endpoint port depth
  */
 struct cxl_memdev {
 	struct device dev;
@@ -47,6 +49,7 @@ struct cxl_memdev {
 	struct cxl_nvdimm_bridge *cxl_nvb;
 	struct cxl_nvdimm *cxl_nvd;
 	int id;
+	int depth;
 };
 
 static inline struct cxl_memdev *to_cxl_memdev(struct device *dev)
@@ -79,6 +82,9 @@ static inline bool is_cxl_endpoint(struct cxl_port *port)
 }
 
 struct cxl_memdev *devm_cxl_add_memdev(struct cxl_dev_state *cxlds);
+int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
+			 resource_size_t base, resource_size_t len,
+			 resource_size_t skipped);
 
 static inline struct cxl_ep *cxl_ep_load(struct cxl_port *port,
 					 struct cxl_memdev *cxlmd)
@@ -182,15 +188,31 @@ static inline int cxl_mbox_cmd_rc2errno(struct cxl_mbox_cmd *mbox_cmd)
 #define CXL_CAPACITY_MULTIPLIER SZ_256M
 
 /**
- * struct cxl_endpoint_dvsec_info - Cached DVSEC info
- * @mem_enabled: cached value of mem_enabled in the DVSEC, PCIE_DEVICE
- * @ranges: Number of active HDM ranges this device uses.
- * @dvsec_range: cached attributes of the ranges in the DVSEC, PCIE_DEVICE
+ * 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
+ *
+ * @event_buf: Buffer to receive event data
+ * @event_log_lock: Serialize event_buf and log use
  */
-struct cxl_endpoint_dvsec_info {
-	bool mem_enabled;
-	int ranges;
-	struct range dvsec_range[2];
+struct cxl_event_state {
+	struct cxl_get_event_payload *buf;
+	struct mutex log_lock;
 };
 
 /**
@@ -228,6 +250,7 @@ struct cxl_endpoint_dvsec_info {
  * @info: Cached DVSEC information about the device.
  * @serial: PCIe Device Serial Number
  * @doe_mbs: PCI DOE mailbox array
+ * @event: event log driver state
  * @mbox_send: @dev specific transport for transmitting mailbox commands
  *
  * See section 8.2.9.5.2 Capacity Configuration and Label Storage for
@@ -266,14 +289,21 @@ struct cxl_dev_state {
 
 	struct xarray doe_mbs;
 
+	struct cxl_event_state event;
+
 	int (*mbox_send)(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd);
 };
 
 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_ACTIVATE_FW		= 0x0202,
+	CXL_MBOX_OP_SET_TIMESTAMP	= 0x0301,
 	CXL_MBOX_OP_GET_SUPPORTED_LOGS	= 0x0400,
 	CXL_MBOX_OP_GET_LOG		= 0x0401,
 	CXL_MBOX_OP_IDENTIFY		= 0x4000,
@@ -347,6 +377,136 @@ struct cxl_mbox_identify {
 	u8 qos_telemetry_caps;
 } __packed;
 
+/*
+ * Common Event Record Format
+ * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
+ */
+struct cxl_event_record_hdr {
+	uuid_t id;
+	u8 length;
+	u8 flags[3];
+	__le16 handle;
+	__le16 related_handle;
+	__le64 timestamp;
+	u8 maint_op_class;
+	u8 reserved[15];
+} __packed;
+
+#define CXL_EVENT_RECORD_DATA_LENGTH 0x50
+struct cxl_event_record_raw {
+	struct cxl_event_record_hdr hdr;
+	u8 data[CXL_EVENT_RECORD_DATA_LENGTH];
+} __packed;
+
+/*
+ * 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
+
+/*
+ * General Media Event Record
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+#define CXL_EVENT_GEN_MED_COMP_ID_SIZE	0x10
+struct cxl_event_gen_media {
+	struct cxl_event_record_hdr hdr;
+	__le64 phys_addr;
+	u8 descriptor;
+	u8 type;
+	u8 transaction_type;
+	u8 validity_flags[2];
+	u8 channel;
+	u8 rank;
+	u8 device[3];
+	u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
+	u8 reserved[46];
+} __packed;
+
+/*
+ * DRAM Event Record - DER
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44
+ */
+#define CXL_EVENT_DER_CORRECTION_MASK_SIZE	0x20
+struct cxl_event_dram {
+	struct cxl_event_record_hdr hdr;
+	__le64 phys_addr;
+	u8 descriptor;
+	u8 type;
+	u8 transaction_type;
+	u8 validity_flags[2];
+	u8 channel;
+	u8 rank;
+	u8 nibble_mask[3];
+	u8 bank_group;
+	u8 bank;
+	u8 row[3];
+	u8 column[2];
+	u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE];
+	u8 reserved[0x17];
+} __packed;
+
+/*
+ * Get Health Info Record
+ * CXL rev 3.0 section 8.2.9.8.3.1; Table 8-100
+ */
+struct cxl_get_health_info {
+	u8 health_status;
+	u8 media_status;
+	u8 add_status;
+	u8 life_used;
+	u8 device_temp[2];
+	u8 dirty_shutdown_cnt[4];
+	u8 cor_vol_err_cnt[4];
+	u8 cor_per_err_cnt[4];
+} __packed;
+
+/*
+ * Memory Module Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+struct cxl_event_mem_module {
+	struct cxl_event_record_hdr hdr;
+	u8 event_type;
+	struct cxl_get_health_info info;
+	u8 reserved[0x3d];
+} __packed;
+
 struct cxl_mbox_get_partition_info {
 	__le64 active_volatile_cap;
 	__le64 active_persistent_cap;
@@ -372,6 +532,12 @@ struct cxl_mbox_set_partition_info {
 
 #define  CXL_SET_PARTITION_IMMEDIATE_FLAG	BIT(0)
 
+/* Set Timestamp CXL 3.0 Spec 8.2.9.4.2 */
+struct cxl_mbox_set_timestamp_in {
+	__le64 timestamp;
+
+} __packed;
+
 /**
  * struct cxl_mem_command - Driver representation of a memory device command
  * @info: Command information as it exists for the UAPI
@@ -393,7 +559,6 @@ struct cxl_mem_command {
 	struct cxl_command_info info;
 	enum cxl_opcode opcode;
 	u32 flags;
-#define CXL_CMD_FLAG_NONE 0
 #define CXL_CMD_FLAG_FORCE_ENABLE BIT(0)
 };
 
@@ -441,6 +606,9 @@ int cxl_mem_create_range_info(struct cxl_dev_state *cxlds);
 struct cxl_dev_state *cxl_dev_state_create(struct device *dev);
 void set_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cmds);
 void clear_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cmds);
+void cxl_mem_get_event_records(struct cxl_dev_state *cxlds, u32 status);
+int cxl_set_timestamp(struct cxl_dev_state *cxlds);
+
 #ifdef CONFIG_CXL_SUSPEND
 void cxl_mem_active_inc(void);
 void cxl_mem_active_dec(void);

drivers/cxl/cxlpci.h

@@ -53,6 +53,12 @@
 #define	    CXL_DVSEC_REG_LOCATOR_BLOCK_ID_MASK			GENMASK(15, 8)
 #define     CXL_DVSEC_REG_LOCATOR_BLOCK_OFF_LOW_MASK		GENMASK(31, 16)
 
+/*
+ * 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,
@@ -64,6 +70,10 @@ enum cxl_regloc_type {
 
 int devm_cxl_port_enumerate_dports(struct cxl_port *port);
 struct cxl_dev_state;
-int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm);
+int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm,
+			struct cxl_endpoint_dvsec_info *info);
 void read_cdat_data(struct cxl_port *port);
+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);
 #endif /* __CXL_PCI_H__ */

drivers/cxl/pci.c

@@ -14,8 +14,6 @@
 #include "cxlmem.h"
 #include "cxlpci.h"
 #include "cxl.h"
-#define CREATE_TRACE_POINTS
-#include <trace/events/cxl.h>
 
 /**
  * DOC: cxl pci
@@ -162,7 +160,7 @@ static int __cxl_pci_mbox_send_cmd(struct cxl_dev_state *cxlds,
 	writeq(cmd_reg, cxlds->regs.mbox + CXLDEV_MBOX_CMD_OFFSET);
 
 	/* #4 */
-	dev_dbg(dev, "Sending command\n");
+	dev_dbg(dev, "Sending command: 0x%04x\n", mbox_cmd->opcode);
 	writel(CXLDEV_MBOX_CTRL_DOORBELL,
 	       cxlds->regs.mbox + CXLDEV_MBOX_CTRL_OFFSET);
 
@@ -414,13 +412,295 @@ static bool is_cxl_restricted(struct pci_dev *pdev)
 	return pci_pcie_type(pdev) == PCI_EXP_TYPE_RC_END;
 }
 
-static void disable_aer(void *pdev)
+/*
+ * 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 bool cxl_pci_flit_256(struct pci_dev *pdev)
 {
-	pci_disable_pcie_error_reporting(pdev);
+	u16 lnksta2;
+
+	pcie_capability_read_word(pdev, PCI_EXP_LNKSTA2, &lnksta2);
+	return lnksta2 & PCI_EXP_LNKSTA2_FLIT;
+}
+
+static int cxl_pci_ras_unmask(struct pci_dev *pdev)
+{
+	struct pci_host_bridge *host_bridge = pci_find_host_bridge(pdev->bus);
+	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
+	void __iomem *addr;
+	u32 orig_val, val, mask;
+	u16 cap;
+	int rc;
+
+	if (!cxlds->regs.ras) {
+		dev_dbg(&pdev->dev, "No RAS registers.\n");
+		return 0;
+	}
+
+	/* BIOS has CXL error control */
+	if (!host_bridge->native_cxl_error)
+		return -ENXIO;
+
+	rc = pcie_capability_read_word(pdev, PCI_EXP_DEVCTL, &cap);
+	if (rc)
+		return rc;
+
+	if (cap & PCI_EXP_DEVCTL_URRE) {
+		addr = cxlds->regs.ras + CXL_RAS_UNCORRECTABLE_MASK_OFFSET;
+		orig_val = readl(addr);
+
+		mask = CXL_RAS_UNCORRECTABLE_MASK_MASK;
+		if (!cxl_pci_flit_256(pdev))
+			mask &= ~CXL_RAS_UNCORRECTABLE_MASK_F256B_MASK;
+		val = orig_val & ~mask;
+		writel(val, addr);
+		dev_dbg(&pdev->dev,
+			"Uncorrectable RAS Errors Mask: %#x -> %#x\n",
+			orig_val, val);
+	}
+
+	if (cap & PCI_EXP_DEVCTL_CERE) {
+		addr = cxlds->regs.ras + CXL_RAS_CORRECTABLE_MASK_OFFSET;
+		orig_val = readl(addr);
+		val = orig_val & ~CXL_RAS_CORRECTABLE_MASK_MASK;
+		writel(val, addr);
+		dev_dbg(&pdev->dev, "Correctable RAS Errors Mask: %#x -> %#x\n",
+			orig_val, val);
+	}
+
+	return 0;
+}
+
+static void free_event_buf(void *buf)
+{
+	kvfree(buf);
+}
+
+/*
+ * There is a single buffer for reading event logs from the mailbox.  All logs
+ * share this buffer protected by the cxlds->event_log_lock.
+ */
+static int cxl_mem_alloc_event_buf(struct cxl_dev_state *cxlds)
+{
+	struct cxl_get_event_payload *buf;
+
+	buf = kvmalloc(cxlds->payload_size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+	cxlds->event.buf = buf;
+
+	return devm_add_action_or_reset(cxlds->dev, free_event_buf, buf);
+}
+
+static int cxl_alloc_irq_vectors(struct pci_dev *pdev)
+{
+	int nvecs;
+
+	/*
+	 * Per CXL 3.0 3.1.1 CXL.io Endpoint a function on a CXL device must
+	 * not generate INTx messages if that function participates in
+	 * CXL.cache or CXL.mem.
+	 *
+	 * Additionally pci_alloc_irq_vectors() handles calling
+	 * pci_free_irq_vectors() automatically despite not being called
+	 * pcim_*.  See pci_setup_msi_context().
+	 */
+	nvecs = pci_alloc_irq_vectors(pdev, 1, CXL_PCI_DEFAULT_MAX_VECTORS,
+				      PCI_IRQ_MSIX | PCI_IRQ_MSI);
+	if (nvecs < 1) {
+		dev_dbg(&pdev->dev, "Failed to alloc irq vectors: %d\n", nvecs);
+		return -ENXIO;
+	}
+	return 0;
+}
+
+struct cxl_dev_id {
+	struct cxl_dev_state *cxlds;
+};
+
+static irqreturn_t cxl_event_thread(int irq, void *id)
+{
+	struct cxl_dev_id *dev_id = id;
+	struct cxl_dev_state *cxlds = dev_id->cxlds;
+	u32 status;
+
+	do {
+		/*
+		 * CXL 3.0 8.2.8.3.1: The lower 32 bits are the status;
+		 * ignore the reserved upper 32 bits
+		 */
+		status = readl(cxlds->regs.status + CXLDEV_DEV_EVENT_STATUS_OFFSET);
+		/* Ignore logs unknown to the driver */
+		status &= CXLDEV_EVENT_STATUS_ALL;
+		if (!status)
+			break;
+		cxl_mem_get_event_records(cxlds, status);
+		cond_resched();
+	} while (status);
+
+	return IRQ_HANDLED;
+}
+
+static int cxl_event_req_irq(struct cxl_dev_state *cxlds, u8 setting)
+{
+	struct device *dev = cxlds->dev;
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct cxl_dev_id *dev_id;
+	int irq;
+
+	if (FIELD_GET(CXLDEV_EVENT_INT_MODE_MASK, setting) != CXL_INT_MSI_MSIX)
+		return -ENXIO;
+
+	/* dev_id must be globally unique and must contain the cxlds */
+	dev_id = devm_kzalloc(dev, sizeof(*dev_id), GFP_KERNEL);
+	if (!dev_id)
+		return -ENOMEM;
+	dev_id->cxlds = cxlds;
+
+	irq =  pci_irq_vector(pdev,
+			      FIELD_GET(CXLDEV_EVENT_INT_MSGNUM_MASK, setting));
+	if (irq < 0)
+		return irq;
+
+	return devm_request_threaded_irq(dev, irq, NULL, cxl_event_thread,
+					 IRQF_SHARED | IRQF_ONESHOT, NULL,
+					 dev_id);
+}
+
+static int cxl_event_get_int_policy(struct cxl_dev_state *cxlds,
+				    struct cxl_event_interrupt_policy *policy)
+{
+	struct cxl_mbox_cmd mbox_cmd = {
+		.opcode = CXL_MBOX_OP_GET_EVT_INT_POLICY,
+		.payload_out = policy,
+		.size_out = sizeof(*policy),
+	};
+	int rc;
+
+	rc = cxl_internal_send_cmd(cxlds, &mbox_cmd);
+	if (rc < 0)
+		dev_err(cxlds->dev, "Failed to get event interrupt policy : %d",
+			rc);
+
+	return rc;
+}
+
+static int cxl_event_config_msgnums(struct cxl_dev_state *cxlds,
+				    struct cxl_event_interrupt_policy *policy)
+{
+	struct cxl_mbox_cmd mbox_cmd;
+	int rc;
+
+	*policy = (struct cxl_event_interrupt_policy) {
+		.info_settings = CXL_INT_MSI_MSIX,
+		.warn_settings = CXL_INT_MSI_MSIX,
+		.failure_settings = CXL_INT_MSI_MSIX,
+		.fatal_settings = CXL_INT_MSI_MSIX,
+	};
+
+	mbox_cmd = (struct cxl_mbox_cmd) {
+		.opcode = CXL_MBOX_OP_SET_EVT_INT_POLICY,
+		.payload_in = policy,
+		.size_in = sizeof(*policy),
+	};
+
+	rc = cxl_internal_send_cmd(cxlds, &mbox_cmd);
+	if (rc < 0) {
+		dev_err(cxlds->dev, "Failed to set event interrupt policy : %d",
+			rc);
+		return rc;
+	}
+
+	/* Retrieve final interrupt settings */
+	return cxl_event_get_int_policy(cxlds, policy);
+}
+
+static int cxl_event_irqsetup(struct cxl_dev_state *cxlds)
+{
+	struct cxl_event_interrupt_policy policy;
+	int rc;
+
+	rc = cxl_event_config_msgnums(cxlds, &policy);
+	if (rc)
+		return rc;
+
+	rc = cxl_event_req_irq(cxlds, policy.info_settings);
+	if (rc) {
+		dev_err(cxlds->dev, "Failed to get interrupt for event Info log\n");
+		return rc;
+	}
+
+	rc = cxl_event_req_irq(cxlds, policy.warn_settings);
+	if (rc) {
+		dev_err(cxlds->dev, "Failed to get interrupt for event Warn log\n");
+		return rc;
+	}
+
+	rc = cxl_event_req_irq(cxlds, policy.failure_settings);
+	if (rc) {
+		dev_err(cxlds->dev, "Failed to get interrupt for event Failure log\n");
+		return rc;
+	}
+
+	rc = cxl_event_req_irq(cxlds, policy.fatal_settings);
+	if (rc) {
+		dev_err(cxlds->dev, "Failed to get interrupt for event Fatal log\n");
+		return rc;
+	}
+
+	return 0;
+}
+
+static bool cxl_event_int_is_fw(u8 setting)
+{
+	u8 mode = FIELD_GET(CXLDEV_EVENT_INT_MODE_MASK, setting);
+
+	return mode == CXL_INT_FW;
+}
+
+static int cxl_event_config(struct pci_host_bridge *host_bridge,
+			    struct cxl_dev_state *cxlds)
+{
+	struct cxl_event_interrupt_policy policy;
+	int rc;
+
+	/*
+	 * When BIOS maintains CXL error reporting control, it will process
+	 * event records.  Only one agent can do so.
+	 */
+	if (!host_bridge->native_cxl_error)
+		return 0;
+
+	rc = cxl_mem_alloc_event_buf(cxlds);
+	if (rc)
+		return rc;
+
+	rc = cxl_event_get_int_policy(cxlds, &policy);
+	if (rc)
+		return rc;
+
+	if (cxl_event_int_is_fw(policy.info_settings) ||
+	    cxl_event_int_is_fw(policy.warn_settings) ||
+	    cxl_event_int_is_fw(policy.failure_settings) ||
+	    cxl_event_int_is_fw(policy.fatal_settings)) {
+		dev_err(cxlds->dev, "FW still in control of Event Logs despite _OSC settings\n");
+		return -EBUSY;
+	}
+
+	rc = cxl_event_irqsetup(cxlds);
+	if (rc)
+		return rc;
+
+	cxl_mem_get_event_records(cxlds, CXLDEV_EVENT_STATUS_ALL);
+
+	return 0;
 }
 
 static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
+	struct pci_host_bridge *host_bridge = pci_find_host_bridge(pdev->bus);
 	struct cxl_register_map map;
 	struct cxl_memdev *cxlmd;
 	struct cxl_dev_state *cxlds;
@@ -436,6 +716,7 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	rc = pcim_enable_device(pdev);
 	if (rc)
 		return rc;
+	pci_set_master(pdev);
 
 	cxlds = cxl_dev_state_create(&pdev->dev);
 	if (IS_ERR(cxlds))
@@ -484,6 +765,10 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (rc)
 		return rc;
 
+	rc = cxl_set_timestamp(cxlds);
+	if (rc)
+		return rc;
+
 	rc = cxl_dev_state_identify(cxlds);
 	if (rc)
 		return rc;
@@ -492,16 +777,22 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (rc)
 		return rc;
 
+	rc = cxl_alloc_irq_vectors(pdev);
+	if (rc)
+		return rc;
+
 	cxlmd = devm_cxl_add_memdev(cxlds);
 	if (IS_ERR(cxlmd))
 		return PTR_ERR(cxlmd);
 
-	if (cxlds->regs.ras) {
-		pci_enable_pcie_error_reporting(pdev);
-		rc = devm_add_action_or_reset(&pdev->dev, disable_aer, pdev);
+	rc = cxl_event_config(host_bridge, cxlds);
 	if (rc)
 		return rc;
-	}
+
+	rc = cxl_pci_ras_unmask(pdev);
+	if (rc)
+		dev_dbg(&pdev->dev, "No RAS reporting unmasked\n");
+
 	pci_save_state(pdev);
 
 	return rc;
@@ -514,99 +805,6 @@ static const struct pci_device_id cxl_mem_pci_tbl[] = {
 };
 MODULE_DEVICE_TABLE(pci, cxl_mem_pci_tbl);
 
-/* CXL spec rev3.0 8.2.4.16.1 */
-static void header_log_copy(struct cxl_dev_state *cxlds, u32 *log)
-{
-	void __iomem *addr;
-	u32 *log_addr;
-	int i, log_u32_size = CXL_HEADERLOG_SIZE / sizeof(u32);
-
-	addr = cxlds->regs.ras + CXL_RAS_HEADER_LOG_OFFSET;
-	log_addr = log;
-
-	for (i = 0; i < log_u32_size; 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.
- */
-static bool cxl_report_and_clear(struct cxl_dev_state *cxlds)
-{
-	struct cxl_memdev *cxlmd = cxlds->cxlmd;
-	struct device *dev = &cxlmd->dev;
-	u32 hl[CXL_HEADERLOG_SIZE_U32];
-	void __iomem *addr;
-	u32 status;
-	u32 fe;
-
-	if (!cxlds->regs.ras)
-		return false;
-
-	addr = cxlds->regs.ras + 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 =
-			cxlds->regs.ras + CXL_RAS_CAP_CONTROL_OFFSET;
-
-		fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
-				   readl(rcc_addr)));
-	} else {
-		fe = status;
-	}
-
-	header_log_copy(cxlds, hl);
-	trace_cxl_aer_uncorrectable_error(dev, status, fe, hl);
-	writel(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK, addr);
-
-	return true;
-}
-
-static 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;
-
-	/*
-	 * 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_report_and_clear(cxlds);
-
-	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;
-}
-
 static pci_ers_result_t cxl_slot_reset(struct pci_dev *pdev)
 {
 	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
@@ -631,25 +829,6 @@ static void cxl_error_resume(struct pci_dev *pdev)
 		 dev->driver ? "successful" : "failed");
 }
 
-static 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 = &cxlmd->dev;
-	void __iomem *addr;
-	u32 status;
-
-	if (!cxlds->regs.ras)
-		return;
-
-	addr = cxlds->regs.ras + 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(dev, status);
-	}
-}
-
 static const struct pci_error_handlers cxl_error_handlers = {
 	.error_detected	= cxl_error_detected,
 	.slot_reset	= cxl_slot_reset,

drivers/cxl/pmem.c

@@ -76,6 +76,7 @@ static int cxl_nvdimm_probe(struct device *dev)
 		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);

drivers/cxl/port.c

@@ -30,57 +30,116 @@ static void schedule_detach(void *cxlmd)
 	schedule_cxl_memdev_detach(cxlmd);
 }
 
-static int cxl_port_probe(struct device *dev)
+static int discover_region(struct device *dev, void *root)
 {
-	struct cxl_port *port = to_cxl_port(dev);
-	struct cxl_hdm *cxlhdm;
+	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(root, 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)
+{
+	struct cxl_hdm *cxlhdm;
+	int rc;
 
-	if (!is_cxl_endpoint(port)) {
 	rc = devm_cxl_port_enumerate_dports(port);
 	if (rc < 0)
 		return rc;
+
 	if (rc == 1)
 		return devm_cxl_add_passthrough_decoder(port);
-	}
 
-	cxlhdm = devm_cxl_setup_hdm(port);
+	cxlhdm = devm_cxl_setup_hdm(port, NULL);
 	if (IS_ERR(cxlhdm))
 		return PTR_ERR(cxlhdm);
 
-	if (is_cxl_endpoint(port)) {
+	return devm_cxl_enumerate_decoders(cxlhdm, NULL);
+}
+
+static int cxl_endpoint_port_probe(struct cxl_port *port)
+{
 	struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport);
+	struct cxl_endpoint_dvsec_info info = { 0 };
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_hdm *cxlhdm;
+	struct cxl_port *root;
+	int rc;
+
+	rc = cxl_dvsec_rr_decode(cxlds->dev, cxlds->cxl_dvsec, &info);
+	if (rc < 0)
+		return rc;
+
+	cxlhdm = devm_cxl_setup_hdm(port, &info);
+	if (IS_ERR(cxlhdm))
+		return PTR_ERR(cxlhdm);
 
 	/* Cache the data early to ensure is_visible() works */
 	read_cdat_data(port);
 
 	get_device(&cxlmd->dev);
-		rc = devm_add_action_or_reset(dev, schedule_detach, cxlmd);
+	rc = devm_add_action_or_reset(&port->dev, schedule_detach, cxlmd);
 	if (rc)
 		return rc;
 
-		rc = cxl_hdm_decode_init(cxlds, cxlhdm);
+	rc = cxl_hdm_decode_init(cxlds, cxlhdm, &info);
 	if (rc)
 		return rc;
 
 	rc = cxl_await_media_ready(cxlds);
 	if (rc) {
-			dev_err(dev, "Media not active (%d)\n", rc);
+		dev_err(&port->dev, "Media not active (%d)\n", rc);
 		return rc;
 	}
-	}
 
-	rc = devm_cxl_enumerate_decoders(cxlhdm);
-	if (rc) {
-		dev_err(dev, "Couldn't enumerate decoders (%d)\n", rc);
+	rc = devm_cxl_enumerate_decoders(cxlhdm, &info);
+	if (rc)
 		return rc;
-	}
+
+	/*
+	 * This can't fail in practice as CXL root exit unregisters all
+	 * descendant ports and that in turn synchronizes with cxl_port_probe()
+	 */
+	root = find_cxl_root(&cxlmd->dev);
+
+	/*
+	 * Now that all endpoint decoders are successfully enumerated, try to
+	 * assemble regions from committed decoders
+	 */
+	device_for_each_child(&port->dev, root, discover_region);
+	put_device(&root->dev);
 
 	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,
 			 struct bin_attribute *bin_attr, char *buf,
 			 loff_t offset, size_t count)

drivers/dax/Kconfig

@@ -44,12 +44,25 @@ config DEV_DAX_HMEM
 
 	  Say M if unsure.
 
+config DEV_DAX_CXL
+	tristate "CXL DAX: direct access to CXL RAM regions"
+	depends on CXL_BUS && CXL_REGION && DEV_DAX
+	default CXL_REGION && DEV_DAX
+	help
+	  CXL RAM regions are either mapped by platform-firmware
+	  and published in the initial system-memory map as "System RAM", mapped
+	  by platform-firmware as "Soft Reserved", or dynamically provisioned
+	  after boot by the CXL driver. In the latter two cases a device-dax
+	  instance is created to access that unmapped-by-default address range.
+	  Per usual it can remain as dedicated access via a device interface, or
+	  converted to "System RAM" via the dax_kmem facility.
+
 config DEV_DAX_HMEM_DEVICES
-	depends on DEV_DAX_HMEM && DAX=y
+	depends on DEV_DAX_HMEM && DAX
 	def_bool y
 
 config DEV_DAX_KMEM
-	tristate "KMEM DAX: volatile-use of persistent memory"
+	tristate "KMEM DAX: map dax-devices as System-RAM"
 	default DEV_DAX
 	depends on DEV_DAX
 	depends on MEMORY_HOTPLUG # for add_memory() and friends

drivers/dax/Makefile

@@ -3,10 +3,12 @@ obj-$(CONFIG_DAX) += dax.o
 obj-$(CONFIG_DEV_DAX) += device_dax.o
 obj-$(CONFIG_DEV_DAX_KMEM) += kmem.o
 obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o
+obj-$(CONFIG_DEV_DAX_CXL) += dax_cxl.o
 
 dax-y := super.o
 dax-y += bus.o
 device_dax-y := device.o
 dax_pmem-y := pmem.o
+dax_cxl-y := cxl.o
 
 obj-y += hmem/

drivers/dax/bus.c

@@ -56,6 +56,25 @@ static int dax_match_id(struct dax_device_driver *dax_drv, struct device *dev)
 	return match;
 }
 
+static int dax_match_type(struct dax_device_driver *dax_drv, struct device *dev)
+{
+	enum dax_driver_type type = DAXDRV_DEVICE_TYPE;
+	struct dev_dax *dev_dax = to_dev_dax(dev);
+
+	if (dev_dax->region->res.flags & IORESOURCE_DAX_KMEM)
+		type = DAXDRV_KMEM_TYPE;
+
+	if (dax_drv->type == type)
+		return 1;
+
+	/* default to device mode if dax_kmem is disabled */
+	if (dax_drv->type == DAXDRV_DEVICE_TYPE &&
+	    !IS_ENABLED(CONFIG_DEV_DAX_KMEM))
+		return 1;
+
+	return 0;
+}
+
 enum id_action {
 	ID_REMOVE,
 	ID_ADD,
@@ -216,14 +235,9 @@ static int dax_bus_match(struct device *dev, struct device_driver *drv)
 {
 	struct dax_device_driver *dax_drv = to_dax_drv(drv);
 
-	/*
-	 * All but the 'device-dax' driver, which has 'match_always'
-	 * set, requires an exact id match.
-	 */
-	if (dax_drv->match_always)
+	if (dax_match_id(dax_drv, dev))
 		return 1;
-
-	return dax_match_id(dax_drv, dev);
+	return dax_match_type(dax_drv, dev);
 }
 
 /*
@@ -427,8 +441,8 @@ static void unregister_dev_dax(void *dev)
 	dev_dbg(dev, "%s\n", __func__);
 
 	kill_dev_dax(dev_dax);
-	free_dev_dax_ranges(dev_dax);
 	device_del(dev);
+	free_dev_dax_ranges(dev_dax);
 	put_device(dev);
 }
 
@@ -1413,13 +1427,10 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
 }
 EXPORT_SYMBOL_GPL(devm_create_dev_dax);
 
-static int match_always_count;
-
 int __dax_driver_register(struct dax_device_driver *dax_drv,
 		struct module *module, const char *mod_name)
 {
 	struct device_driver *drv = &dax_drv->drv;
-	int rc = 0;
 
 	/*
 	 * dax_bus_probe() calls dax_drv->probe() unconditionally.
@@ -1434,26 +1445,7 @@ int __dax_driver_register(struct dax_device_driver *dax_drv,
 	drv->mod_name = mod_name;
 	drv->bus = &dax_bus_type;
 
-	/* there can only be one default driver */
-	mutex_lock(&dax_bus_lock);
-	match_always_count += dax_drv->match_always;
-	if (match_always_count > 1) {
-		match_always_count--;
-		WARN_ON(1);
-		rc = -EINVAL;
-	}
-	mutex_unlock(&dax_bus_lock);
-	if (rc)
-		return rc;
-
-	rc = driver_register(drv);
-	if (rc && dax_drv->match_always) {
-		mutex_lock(&dax_bus_lock);
-		match_always_count -= dax_drv->match_always;
-		mutex_unlock(&dax_bus_lock);
-	}
-
-	return rc;
+	return driver_register(drv);
 }
 EXPORT_SYMBOL_GPL(__dax_driver_register);
 
@@ -1463,7 +1455,6 @@ void dax_driver_unregister(struct dax_device_driver *dax_drv)
 	struct dax_id *dax_id, *_id;
 
 	mutex_lock(&dax_bus_lock);
-	match_always_count -= dax_drv->match_always;
 	list_for_each_entry_safe(dax_id, _id, &dax_drv->ids, list) {
 		list_del(&dax_id->list);
 		kfree(dax_id);

drivers/dax/bus.h

@@ -11,7 +11,10 @@ struct dax_device;
 struct dax_region;
 void dax_region_put(struct dax_region *dax_region);
 
-#define IORESOURCE_DAX_STATIC (1UL << 0)
+/* dax bus specific ioresource flags */
+#define IORESOURCE_DAX_STATIC BIT(0)
+#define IORESOURCE_DAX_KMEM BIT(1)
+
 struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 		struct range *range, int target_node, unsigned int align,
 		unsigned long flags);
@@ -25,10 +28,15 @@ struct dev_dax_data {
 
 struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data);
 
+enum dax_driver_type {
+	DAXDRV_KMEM_TYPE,
+	DAXDRV_DEVICE_TYPE,
+};
+
 struct dax_device_driver {
 	struct device_driver drv;
 	struct list_head ids;
-	int match_always;
+	enum dax_driver_type type;
 	int (*probe)(struct dev_dax *dev);
 	void (*remove)(struct dev_dax *dev);
 };

drivers/dax/cxl.c

+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2023 Intel Corporation. All rights reserved. */
+#include <linux/module.h>
+#include <linux/dax.h>
+
+#include "../cxl/cxl.h"
+#include "bus.h"
+
+static int cxl_dax_region_probe(struct device *dev)
+{
+	struct cxl_dax_region *cxlr_dax = to_cxl_dax_region(dev);
+	int nid = phys_to_target_node(cxlr_dax->hpa_range.start);
+	struct cxl_region *cxlr = cxlr_dax->cxlr;
+	struct dax_region *dax_region;
+	struct dev_dax_data data;
+	struct dev_dax *dev_dax;
+
+	if (nid == NUMA_NO_NODE)
+		nid = memory_add_physaddr_to_nid(cxlr_dax->hpa_range.start);
+
+	dax_region = alloc_dax_region(dev, cxlr->id, &cxlr_dax->hpa_range, nid,
+				      PMD_SIZE, IORESOURCE_DAX_KMEM);
+	if (!dax_region)
+		return -ENOMEM;
+
+	data = (struct dev_dax_data) {
+		.dax_region = dax_region,
+		.id = -1,
+		.size = range_len(&cxlr_dax->hpa_range),
+	};
+	dev_dax = devm_create_dev_dax(&data);
+	if (IS_ERR(dev_dax))
+		return PTR_ERR(dev_dax);
+
+	/* child dev_dax instances now own the lifetime of the dax_region */
+	dax_region_put(dax_region);
+	return 0;
+}
+
+static struct cxl_driver cxl_dax_region_driver = {
+	.name = "cxl_dax_region",
+	.probe = cxl_dax_region_probe,
+	.id = CXL_DEVICE_DAX_REGION,
+	.drv = {
+		.suppress_bind_attrs = true,
+	},
+};
+
+module_cxl_driver(cxl_dax_region_driver);
+MODULE_ALIAS_CXL(CXL_DEVICE_DAX_REGION);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Intel Corporation");
+MODULE_IMPORT_NS(CXL);

drivers/dax/device.c

@@ -475,8 +475,7 @@ EXPORT_SYMBOL_GPL(dev_dax_probe);
 
 static struct dax_device_driver device_dax_driver = {
 	.probe = dev_dax_probe,
-	/* all probe actions are unwound by devm, so .remove isn't necessary */
-	.match_always = 1,
+	.type = DAXDRV_DEVICE_TYPE,
 };
 
 static int __init dax_init(void)

drivers/dax/hmem/Makefile

 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_DEV_DAX_HMEM) += dax_hmem.o
+# device_hmem.o deliberately precedes dax_hmem.o for initcall ordering
 obj-$(CONFIG_DEV_DAX_HMEM_DEVICES) += device_hmem.o
+obj-$(CONFIG_DEV_DAX_HMEM) += dax_hmem.o
 
 device_hmem-y := device.o
 dax_hmem-y := hmem.o

drivers/dax/hmem/device.c

@@ -8,6 +8,8 @@
 static bool nohmem;
 module_param_named(disable, nohmem, bool, 0444);
 
+static bool platform_initialized;
+static DEFINE_MUTEX(hmem_resource_lock);
 static struct resource hmem_active = {
 	.name = "HMEM devices",
 	.start = 0,
@@ -15,80 +17,66 @@ static struct resource hmem_active = {
 	.flags = IORESOURCE_MEM,
 };
 
-void hmem_register_device(int target_nid, struct resource *r)
+int walk_hmem_resources(struct device *host, walk_hmem_fn fn)
+{
+	struct resource *res;
+	int rc = 0;
+
+	mutex_lock(&hmem_resource_lock);
+	for (res = hmem_active.child; res; res = res->sibling) {
+		rc = fn(host, (int) res->desc, res);
+		if (rc)
+			break;
+	}
+	mutex_unlock(&hmem_resource_lock);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(walk_hmem_resources);
+
+static void __hmem_register_resource(int target_nid, struct resource *res)
 {
-	/* define a clean / non-busy resource for the platform device */
-	struct resource res = {
-		.start = r->start,
-		.end = r->end,
-		.flags = IORESOURCE_MEM,
-		.desc = IORES_DESC_SOFT_RESERVED,
-	};
 	struct platform_device *pdev;
-	struct memregion_info info;
-	int rc, id;
+	struct resource *new;
+	int rc;
 
-	if (nohmem)
+	new = __request_region(&hmem_active, res->start, resource_size(res), "",
+			       0);
+	if (!new) {
+		pr_debug("hmem range %pr already active\n", res);
 		return;
+	}
 
-	rc = region_intersects(res.start, resource_size(&res), IORESOURCE_MEM,
-			IORES_DESC_SOFT_RESERVED);
-	if (rc != REGION_INTERSECTS)
-		return;
+	new->desc = target_nid;
 
-	id = memregion_alloc(GFP_KERNEL);
-	if (id < 0) {
-		pr_err("memregion allocation failure for %pr\n", &res);
+	if (platform_initialized)
 		return;
-	}
 
-	pdev = platform_device_alloc("hmem", id);
+	pdev = platform_device_alloc("hmem_platform", 0);
 	if (!pdev) {
-		pr_err("hmem device allocation failure for %pr\n", &res);
-		goto out_pdev;
-	}
-
-	if (!__request_region(&hmem_active, res.start, resource_size(&res),
-			      dev_name(&pdev->dev), 0)) {
-		dev_dbg(&pdev->dev, "hmem range %pr already active\n", &res);
-		goto out_active;
-	}
-
-	pdev->dev.numa_node = numa_map_to_online_node(target_nid);
-	info = (struct memregion_info) {
-		.target_node = target_nid,
-	};
-	rc = platform_device_add_data(pdev, &info, sizeof(info));
-	if (rc < 0) {
-		pr_err("hmem memregion_info allocation failure for %pr\n", &res);
-		goto out_resource;
-	}
-
-	rc = platform_device_add_resources(pdev, &res, 1);
-	if (rc < 0) {
-		pr_err("hmem resource allocation failure for %pr\n", &res);
-		goto out_resource;
+		pr_err_once("failed to register device-dax hmem_platform device\n");
+		return;
 	}
 
 	rc = platform_device_add(pdev);
-	if (rc < 0) {
-		dev_err(&pdev->dev, "device add failed for %pr\n", &res);
-		goto out_resource;
-	}
+	if (rc)
+		platform_device_put(pdev);
+	else
+		platform_initialized = true;
+}
 
+void hmem_register_resource(int target_nid, struct resource *res)
+{
+	if (nohmem)
 		return;
 
-out_resource:
-	__release_region(&hmem_active, res.start, resource_size(&res));
-out_active:
-	platform_device_put(pdev);
-out_pdev:
-	memregion_free(id);
+	mutex_lock(&hmem_resource_lock);
+	__hmem_register_resource(target_nid, res);
+	mutex_unlock(&hmem_resource_lock);
 }
 
 static __init int hmem_register_one(struct resource *res, void *data)
 {
-	hmem_register_device(phys_to_target_node(res->start), res);
+	hmem_register_resource(phys_to_target_node(res->start), res);
 
 	return 0;
 }
@@ -104,4 +92,4 @@ static __init int hmem_init(void)
  * As this is a fallback for address ranges unclaimed by the ACPI HMAT
  * parsing it must be at an initcall level greater than hmat_init().
  */
-late_initcall(hmem_init);
+device_initcall(hmem_init);

drivers/dax/hmem/hmem.c

@@ -3,6 +3,7 @@
 #include <linux/memregion.h>
 #include <linux/module.h>
 #include <linux/pfn_t.h>
+#include <linux/dax.h>
 #include "../bus.h"
 
 static bool region_idle;
@@ -10,30 +11,32 @@ module_param_named(region_idle, region_idle, bool, 0644);
 
 static int dax_hmem_probe(struct platform_device *pdev)
 {
+	unsigned long flags = IORESOURCE_DAX_KMEM;
 	struct device *dev = &pdev->dev;
 	struct dax_region *dax_region;
 	struct memregion_info *mri;
 	struct dev_dax_data data;
 	struct dev_dax *dev_dax;
-	struct resource *res;
-	struct range range;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -ENOMEM;
+	/*
+	 * @region_idle == true indicates that an administrative agent
+	 * wants to manipulate the range partitioning before the devices
+	 * are created, so do not send them to the dax_kmem driver by
+	 * default.
+	 */
+	if (region_idle)
+		flags = 0;
 
 	mri = dev->platform_data;
-	range.start = res->start;
-	range.end = res->end;
-	dax_region = alloc_dax_region(dev, pdev->id, &range, mri->target_node,
-			PMD_SIZE, 0);
+	dax_region = alloc_dax_region(dev, pdev->id, &mri->range,
+				      mri->target_node, PMD_SIZE, flags);
 	if (!dax_region)
 		return -ENOMEM;
 
 	data = (struct dev_dax_data) {
 		.dax_region = dax_region,
 		.id = -1,
-		.size = region_idle ? 0 : resource_size(res),
+		.size = region_idle ? 0 : range_len(&mri->range),
 	};
 	dev_dax = devm_create_dev_dax(&data);
 	if (IS_ERR(dev_dax))
@@ -44,22 +47,131 @@ static int dax_hmem_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int dax_hmem_remove(struct platform_device *pdev)
+static struct platform_driver dax_hmem_driver = {
+	.probe = dax_hmem_probe,
+	.driver = {
+		.name = "hmem",
+	},
+};
+
+static void release_memregion(void *data)
+{
+	memregion_free((long) data);
+}
+
+static void release_hmem(void *pdev)
 {
-	/* devm handles teardown */
+	platform_device_unregister(pdev);
+}
+
+static int hmem_register_device(struct device *host, int target_nid,
+				const struct resource *res)
+{
+	struct platform_device *pdev;
+	struct memregion_info info;
+	long id;
+	int rc;
+
+	if (IS_ENABLED(CONFIG_CXL_REGION) &&
+	    region_intersects(res->start, resource_size(res), IORESOURCE_MEM,
+			      IORES_DESC_CXL) != REGION_DISJOINT) {
+		dev_dbg(host, "deferring range to CXL: %pr\n", res);
+		return 0;
+	}
+
+	rc = region_intersects(res->start, resource_size(res), IORESOURCE_MEM,
+			       IORES_DESC_SOFT_RESERVED);
+	if (rc != REGION_INTERSECTS)
 		return 0;
+
+	id = memregion_alloc(GFP_KERNEL);
+	if (id < 0) {
+		dev_err(host, "memregion allocation failure for %pr\n", res);
+		return -ENOMEM;
+	}
+	rc = devm_add_action_or_reset(host, release_memregion, (void *) id);
+	if (rc)
+		return rc;
+
+	pdev = platform_device_alloc("hmem", id);
+	if (!pdev) {
+		dev_err(host, "device allocation failure for %pr\n", res);
+		return -ENOMEM;
+	}
+
+	pdev->dev.numa_node = numa_map_to_online_node(target_nid);
+	info = (struct memregion_info) {
+		.target_node = target_nid,
+		.range = {
+			.start = res->start,
+			.end = res->end,
+		},
+	};
+	rc = platform_device_add_data(pdev, &info, sizeof(info));
+	if (rc < 0) {
+		dev_err(host, "memregion_info allocation failure for %pr\n",
+		       res);
+		goto out_put;
+	}
+
+	rc = platform_device_add(pdev);
+	if (rc < 0) {
+		dev_err(host, "%s add failed for %pr\n", dev_name(&pdev->dev),
+			res);
+		goto out_put;
+	}
+
+	return devm_add_action_or_reset(host, release_hmem, pdev);
+
+out_put:
+	platform_device_put(pdev);
+	return rc;
 }
 
-static struct platform_driver dax_hmem_driver = {
-	.probe = dax_hmem_probe,
-	.remove = dax_hmem_remove,
+static int dax_hmem_platform_probe(struct platform_device *pdev)
+{
+	return walk_hmem_resources(&pdev->dev, hmem_register_device);
+}
+
+static struct platform_driver dax_hmem_platform_driver = {
+	.probe = dax_hmem_platform_probe,
 	.driver = {
-		.name = "hmem",
+		.name = "hmem_platform",
 	},
 };
 
-module_platform_driver(dax_hmem_driver);
+static __init int dax_hmem_init(void)
+{
+	int rc;
+
+	rc = platform_driver_register(&dax_hmem_platform_driver);
+	if (rc)
+		return rc;
+
+	rc = platform_driver_register(&dax_hmem_driver);
+	if (rc)
+		platform_driver_unregister(&dax_hmem_platform_driver);
+
+	return rc;
+}
+
+static __exit void dax_hmem_exit(void)
+{
+	platform_driver_unregister(&dax_hmem_driver);
+	platform_driver_unregister(&dax_hmem_platform_driver);
+}
+
+module_init(dax_hmem_init);
+module_exit(dax_hmem_exit);
+
+/* Allow for CXL to define its own dax regions */
+#if IS_ENABLED(CONFIG_CXL_REGION)
+#if IS_MODULE(CONFIG_CXL_ACPI)
+MODULE_SOFTDEP("pre: cxl_acpi");
+#endif
+#endif
 
 MODULE_ALIAS("platform:hmem*");
+MODULE_ALIAS("platform:hmem_platform*");
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Intel Corporation");

drivers/dax/kmem.c

@@ -146,7 +146,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 		if (rc) {
 			dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n",
 					i, range.start, range.end);
-			release_resource(res);
+			remove_resource(res);
 			kfree(res);
 			data->res[i] = NULL;
 			if (mapped)
@@ -195,7 +195,7 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
 
 		rc = remove_memory(range.start, range_len(&range));
 		if (rc == 0) {
-			release_resource(data->res[i]);
+			remove_resource(data->res[i]);
 			kfree(data->res[i]);
 			data->res[i] = NULL;
 			success++;
@@ -239,6 +239,7 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
 static struct dax_device_driver device_dax_kmem_driver = {
 	.probe = dev_dax_kmem_probe,
 	.remove = dev_dax_kmem_remove,
+	.type = DAXDRV_KMEM_TYPE,
 };
 
 static int __init dax_kmem_init(void)

drivers/nvdimm/bus.c

@@ -508,7 +508,7 @@ static void nd_async_device_unregister(void *d, async_cookie_t cookie)
 	put_device(dev);
 }
 
-void nd_device_register(struct device *dev)
+static void __nd_device_register(struct device *dev, bool sync)
 {
 	if (!dev)
 		return;
@@ -531,11 +531,24 @@ void nd_device_register(struct device *dev)
 	}
 	get_device(dev);
 
+	if (sync)
+		nd_async_device_register(dev, 0);
+	else
 		async_schedule_dev_domain(nd_async_device_register, dev,
 					  &nd_async_domain);
 }
+
+void nd_device_register(struct device *dev)
+{
+	__nd_device_register(dev, false);
+}
 EXPORT_SYMBOL(nd_device_register);
 
+void nd_device_register_sync(struct device *dev)
+{
+	__nd_device_register(dev, true);
+}
+
 void nd_device_unregister(struct device *dev, enum nd_async_mode mode)
 {
 	bool killed;

drivers/nvdimm/dimm_devs.c

@@ -624,6 +624,9 @@ struct nvdimm *__nvdimm_create(struct nvdimm_bus *nvdimm_bus,
 	nvdimm->sec.ext_flags = nvdimm_security_flags(nvdimm, NVDIMM_MASTER);
 	device_initialize(dev);
 	lockdep_set_class(&dev->mutex, &nvdimm_key);
+	if (test_bit(NDD_REGISTER_SYNC, &flags))
+		nd_device_register_sync(dev);
+	else
 		nd_device_register(dev);
 
 	return nvdimm;

drivers/nvdimm/nd-core.h

@@ -107,6 +107,7 @@ int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus);
 void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus);
 void nd_synchronize(void);
 void nd_device_register(struct device *dev);
+void nd_device_register_sync(struct device *dev);
 struct nd_label_id;
 char *nd_label_gen_id(struct nd_label_id *label_id, const uuid_t *uuid,
 		      u32 flags);

drivers/pci/probe.c

@@ -596,6 +596,7 @@ static void pci_init_host_bridge(struct pci_host_bridge *bridge)
 	bridge->native_ltr = 1;
 	bridge->native_dpc = 1;
 	bridge->domain_nr = PCI_DOMAIN_NR_NOT_SET;
+	bridge->native_cxl_error = 1;
 
 	device_initialize(&bridge->dev);
 }

include/linux/dax.h

@@ -262,11 +262,14 @@ static inline bool dax_mapping(struct address_space *mapping)
 }
 
 #ifdef CONFIG_DEV_DAX_HMEM_DEVICES
-void hmem_register_device(int target_nid, struct resource *r);
+void hmem_register_resource(int target_nid, struct resource *r);
 #else
-static inline void hmem_register_device(int target_nid, struct resource *r)
+static inline void hmem_register_resource(int target_nid, struct resource *r)
 {
 }
 #endif
 
+typedef int (*walk_hmem_fn)(struct device *dev, int target_nid,
+			    const struct resource *res);
+int walk_hmem_resources(struct device *dev, walk_hmem_fn fn);
 #endif

include/linux/libnvdimm.h

@@ -41,6 +41,9 @@ enum {
 	 */
 	NDD_INCOHERENT = 7,
 
+	/* dimm provider wants synchronous registration by __nvdimm_create() */
+	NDD_REGISTER_SYNC = 8,
+
 	/* need to set a limit somewhere, but yes, this is likely overkill */
 	ND_IOCTL_MAX_BUFLEN = SZ_4M,
 	ND_CMD_MAX_ELEM = 5,

include/linux/memregion.h

@@ -3,10 +3,12 @@
 #define _MEMREGION_H_
 #include <linux/types.h>
 #include <linux/errno.h>
+#include <linux/range.h>
 #include <linux/bug.h>
 
 struct memregion_info {
 	int target_node;
+	struct range range;
 };
 
 #ifdef CONFIG_MEMREGION

include/linux/pci.h

@@ -579,6 +579,7 @@ struct pci_host_bridge {
 	unsigned int	native_pme:1;		/* OS may use PCIe PME */
 	unsigned int	native_ltr:1;		/* OS may use PCIe LTR */
 	unsigned int	native_dpc:1;		/* OS may use PCIe DPC */
+	unsigned int	native_cxl_error:1;	/* OS may use CXL RAS/Events */
 	unsigned int	preserve_config:1;	/* Preserve FW resource setup */
 	unsigned int	size_windows:1;		/* Enable root bus sizing */
 	unsigned int	msi_domain:1;		/* Bridge wants MSI domain */

include/linux/range.h

@@ -13,6 +13,11 @@ static inline u64 range_len(const struct range *range)
 	return range->end - range->start + 1;
 }
 
+static inline bool range_contains(struct range *r1, struct range *r2)
+{
+	return r1->start <= r2->start && r1->end >= r2->end;
+}
+
 int add_range(struct range *range, int az, int nr_range,
 		u64 start, u64 end);
 

include/trace/events/cxl.h

-/* SPDX-License-Identifier: GPL-2.0 */
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM cxl
-
-#if !defined(_CXL_EVENTS_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _CXL_EVENTS_H
-
-#include <linux/tracepoint.h>
-
-#define CXL_HEADERLOG_SIZE		SZ_512
-#define CXL_HEADERLOG_SIZE_U32		SZ_512 / sizeof(u32)
-
-#define CXL_RAS_UC_CACHE_DATA_PARITY	BIT(0)
-#define CXL_RAS_UC_CACHE_ADDR_PARITY	BIT(1)
-#define CXL_RAS_UC_CACHE_BE_PARITY	BIT(2)
-#define CXL_RAS_UC_CACHE_DATA_ECC	BIT(3)
-#define CXL_RAS_UC_MEM_DATA_PARITY	BIT(4)
-#define CXL_RAS_UC_MEM_ADDR_PARITY	BIT(5)
-#define CXL_RAS_UC_MEM_BE_PARITY	BIT(6)
-#define CXL_RAS_UC_MEM_DATA_ECC		BIT(7)
-#define CXL_RAS_UC_REINIT_THRESH	BIT(8)
-#define CXL_RAS_UC_RSVD_ENCODE		BIT(9)
-#define CXL_RAS_UC_POISON		BIT(10)
-#define CXL_RAS_UC_RECV_OVERFLOW	BIT(11)
-#define CXL_RAS_UC_INTERNAL_ERR		BIT(14)
-#define CXL_RAS_UC_IDE_TX_ERR		BIT(15)
-#define CXL_RAS_UC_IDE_RX_ERR		BIT(16)
-
-#define show_uc_errs(status)	__print_flags(status, " | ",		  \
-	{ CXL_RAS_UC_CACHE_DATA_PARITY, "Cache Data Parity Error" },	  \
-	{ CXL_RAS_UC_CACHE_ADDR_PARITY, "Cache Address Parity Error" },	  \
-	{ CXL_RAS_UC_CACHE_BE_PARITY, "Cache Byte Enable Parity Error" }, \
-	{ CXL_RAS_UC_CACHE_DATA_ECC, "Cache Data ECC Error" },		  \
-	{ CXL_RAS_UC_MEM_DATA_PARITY, "Memory Data Parity Error" },	  \
-	{ CXL_RAS_UC_MEM_ADDR_PARITY, "Memory Address Parity Error" },	  \
-	{ CXL_RAS_UC_MEM_BE_PARITY, "Memory Byte Enable Parity Error" },  \
-	{ CXL_RAS_UC_MEM_DATA_ECC, "Memory Data ECC Error" },		  \
-	{ CXL_RAS_UC_REINIT_THRESH, "REINIT Threshold Hit" },		  \
-	{ CXL_RAS_UC_RSVD_ENCODE, "Received Unrecognized Encoding" },	  \
-	{ CXL_RAS_UC_POISON, "Received Poison From Peer" },		  \
-	{ CXL_RAS_UC_RECV_OVERFLOW, "Receiver Overflow" },		  \
-	{ CXL_RAS_UC_INTERNAL_ERR, "Component Specific Error" },	  \
-	{ CXL_RAS_UC_IDE_TX_ERR, "IDE Tx Error" },			  \
-	{ CXL_RAS_UC_IDE_RX_ERR, "IDE Rx Error" }			  \
-)
-
-TRACE_EVENT(cxl_aer_uncorrectable_error,
-	TP_PROTO(const struct device *dev, u32 status, u32 fe, u32 *hl),
-	TP_ARGS(dev, status, fe, hl),
-	TP_STRUCT__entry(
-		__string(dev_name, dev_name(dev))
-		__field(u32, status)
-		__field(u32, first_error)
-		__array(u32, header_log, CXL_HEADERLOG_SIZE_U32)
-	),
-	TP_fast_assign(
-		__assign_str(dev_name, dev_name(dev));
-		__entry->status = status;
-		__entry->first_error = fe;
-		/*
-		 * Embed the 512B headerlog data for user app retrieval and
-		 * parsing, but no need to print this in the trace buffer.
-		 */
-		memcpy(__entry->header_log, hl, CXL_HEADERLOG_SIZE);
-	),
-	TP_printk("%s: status: '%s' first_error: '%s'",
-		  __get_str(dev_name),
-		  show_uc_errs(__entry->status),
-		  show_uc_errs(__entry->first_error)
-	)
-);
-
-#define CXL_RAS_CE_CACHE_DATA_ECC	BIT(0)
-#define CXL_RAS_CE_MEM_DATA_ECC		BIT(1)
-#define CXL_RAS_CE_CRC_THRESH		BIT(2)
-#define CLX_RAS_CE_RETRY_THRESH		BIT(3)
-#define CXL_RAS_CE_CACHE_POISON		BIT(4)
-#define CXL_RAS_CE_MEM_POISON		BIT(5)
-#define CXL_RAS_CE_PHYS_LAYER_ERR	BIT(6)
-
-#define show_ce_errs(status)	__print_flags(status, " | ",			\
-	{ CXL_RAS_CE_CACHE_DATA_ECC, "Cache Data ECC Error" },			\
-	{ CXL_RAS_CE_MEM_DATA_ECC, "Memory Data ECC Error" },			\
-	{ CXL_RAS_CE_CRC_THRESH, "CRC Threshold Hit" },				\
-	{ CLX_RAS_CE_RETRY_THRESH, "Retry Threshold" },				\
-	{ CXL_RAS_CE_CACHE_POISON, "Received Cache Poison From Peer" },		\
-	{ CXL_RAS_CE_MEM_POISON, "Received Memory Poison From Peer" },		\
-	{ CXL_RAS_CE_PHYS_LAYER_ERR, "Received Error From Physical Layer" }	\
-)
-
-TRACE_EVENT(cxl_aer_correctable_error,
-	TP_PROTO(const struct device *dev, u32 status),
-	TP_ARGS(dev, status),
-	TP_STRUCT__entry(
-		__string(dev_name, dev_name(dev))
-		__field(u32, status)
-	),
-	TP_fast_assign(
-		__assign_str(dev_name, dev_name(dev));
-		__entry->status = status;
-	),
-	TP_printk("%s: status: '%s'",
-		  __get_str(dev_name), show_ce_errs(__entry->status)
-	)
-);
-
-#endif /* _CXL_EVENTS_H */
-
-/* This part must be outside protection */
-#undef TRACE_INCLUDE_FILE
-#define TRACE_INCLUDE_FILE cxl
-#include <trace/define_trace.h>

include/uapi/linux/cxl_mem.h

@@ -11,14 +11,19 @@
 /**
  * DOC: UAPI
  *
- * Not all of all commands that the driver supports are always available for use
- * by userspace. Userspace must check the results from the QUERY command in
- * order to determine the live set of commands.
+ * Not all of the commands that the driver supports are available for use by
+ * userspace at all times.  Userspace can check the result of the QUERY command
+ * to determine the live set of commands.  Alternatively, it can issue the
+ * command and check for failure.
  */
 
 #define CXL_MEM_QUERY_COMMANDS _IOR(0xCE, 1, struct cxl_mem_query_commands)
 #define CXL_MEM_SEND_COMMAND _IOWR(0xCE, 2, struct cxl_send_command)
 
+/*
+ * NOTE: New defines must be added to the end of the list to preserve
+ * compatibility because this enum is exported to user space.
+ */
 #define CXL_CMDS                                                          \
 	___C(INVALID, "Invalid Command"),                                 \
 	___C(IDENTIFY, "Identify Command"),                               \
@@ -68,6 +73,19 @@ static const struct {
  * struct cxl_command_info - Command information returned from a query.
  * @id: ID number for the command.
  * @flags: Flags that specify command behavior.
+ *
+ *         CXL_MEM_COMMAND_FLAG_USER_ENABLED
+ *
+ *         The given command id is supported by the driver and is supported by
+ *         a related opcode on the device.
+ *
+ *         CXL_MEM_COMMAND_FLAG_EXCLUSIVE
+ *
+ *         Requests with the given command id will terminate with EBUSY as the
+ *         kernel actively owns management of the given resource. For example,
+ *         the label-storage-area can not be written while the kernel is
+ *         actively managing that space.
+ *
  * @size_in: Expected input size, or ~0 if variable length.
  * @size_out: Expected output size, or ~0 if variable length.
  *
@@ -77,7 +95,7 @@ static const struct {
  * bytes of output.
  *
  *  - @id = 10
- *  - @flags = 0
+ *  - @flags = CXL_MEM_COMMAND_FLAG_ENABLED
  *  - @size_in = ~0
  *  - @size_out = 0
  *
@@ -87,7 +105,9 @@ struct cxl_command_info {
 	__u32 id;
 
 	__u32 flags;
-#define CXL_MEM_COMMAND_FLAG_MASK GENMASK(0, 0)
+#define CXL_MEM_COMMAND_FLAG_MASK		GENMASK(1, 0)
+#define CXL_MEM_COMMAND_FLAG_ENABLED		BIT(0)
+#define CXL_MEM_COMMAND_FLAG_EXCLUSIVE		BIT(1)
 
 	__u32 size_in;
 	__u32 size_out;

include/uapi/linux/pci_regs.h

@@ -693,6 +693,7 @@
 #define  PCI_EXP_LNKCTL2_TX_MARGIN	0x0380 /* Transmit Margin */
 #define  PCI_EXP_LNKCTL2_HASD		0x0020 /* HW Autonomous Speed Disable */
 #define PCI_EXP_LNKSTA2		0x32	/* Link Status 2 */
+#define  PCI_EXP_LNKSTA2_FLIT		0x0400 /* Flit Mode Status */
 #define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2	0x32	/* end of v2 EPs w/ link */
 #define PCI_EXP_SLTCAP2		0x34	/* Slot Capabilities 2 */
 #define  PCI_EXP_SLTCAP2_IBPD	0x00000001 /* In-band PD Disable Supported */

kernel/resource.c

@@ -1343,20 +1343,6 @@ void release_mem_region_adjustable(resource_size_t start, resource_size_t size)
 			continue;
 		}
 
-		/*
-		 * All memory regions added from memory-hotplug path have the
-		 * flag IORESOURCE_SYSTEM_RAM. If the resource does not have
-		 * this flag, we know that we are dealing with a resource coming
-		 * from HMM/devm. HMM/devm use another mechanism to add/release
-		 * a resource. This goes via devm_request_mem_region and
-		 * devm_release_mem_region.
-		 * HMM/devm take care to release their resources when they want,
-		 * so if we are dealing with them, let us just back off here.
-		 */
-		if (!(res->flags & IORESOURCE_SYSRAM)) {
-			break;
-		}
-
 		if (!(res->flags & IORESOURCE_MEM))
 			break;
 

lib/stackinit_kunit.c

@@ -31,7 +31,7 @@ static volatile u8 forced_mask = 0xff;
 static void *fill_start, *target_start;
 static size_t fill_size, target_size;
 
-static bool range_contains(char *haystack_start, size_t haystack_size,
+static bool stackinit_range_contains(char *haystack_start, size_t haystack_size,
 				     char *needle_start, size_t needle_size)
 {
 	if (needle_start >= haystack_start &&
@@ -175,7 +175,7 @@ static noinline void test_ ## name (struct kunit *test)		\
 								\
 	/* Validate that compiler lined up fill and target. */	\
 	KUNIT_ASSERT_TRUE_MSG(test,				\
-		range_contains(fill_start, fill_size,		\
+		stackinit_range_contains(fill_start, fill_size,	\
 			    target_start, target_size),		\
 		"stack fill missed target!? "			\
 		"(fill %zu wide, target offset by %d)\n",	\

tools/testing/cxl/Kbuild

@@ -10,6 +10,7 @@ ldflags-y += --wrap=devm_cxl_add_passthrough_decoder
 ldflags-y += --wrap=devm_cxl_enumerate_decoders
 ldflags-y += --wrap=cxl_await_media_ready
 ldflags-y += --wrap=cxl_hdm_decode_init
+ldflags-y += --wrap=cxl_dvsec_rr_decode
 ldflags-y += --wrap=cxl_rcrb_to_component
 
 DRIVERS := ../../../drivers
@@ -17,28 +18,34 @@ CXL_SRC := $(DRIVERS)/cxl
 CXL_CORE_SRC := $(DRIVERS)/cxl/core
 ccflags-y := -I$(srctree)/drivers/cxl/
 ccflags-y += -D__mock=__weak
+ccflags-y += -DTRACE_INCLUDE_PATH=$(CXL_CORE_SRC) -I$(srctree)/drivers/cxl/core/
 
 obj-m += cxl_acpi.o
 
 cxl_acpi-y := $(CXL_SRC)/acpi.o
 cxl_acpi-y += mock_acpi.o
 cxl_acpi-y += config_check.o
+cxl_acpi-y += cxl_acpi_test.o
 
 obj-m += cxl_pmem.o
 
 cxl_pmem-y := $(CXL_SRC)/pmem.o
 cxl_pmem-y += $(CXL_SRC)/security.o
 cxl_pmem-y += config_check.o
+cxl_pmem-y += cxl_pmem_test.o
 
 obj-m += cxl_port.o
 
 cxl_port-y := $(CXL_SRC)/port.o
 cxl_port-y += config_check.o
+cxl_port-y += cxl_port_test.o
+
 
 obj-m += cxl_mem.o
 
 cxl_mem-y := $(CXL_SRC)/mem.o
 cxl_mem-y += config_check.o
+cxl_mem-y += cxl_mem_test.o
 
 obj-m += cxl_core.o
 
@@ -49,7 +56,9 @@ cxl_core-y += $(CXL_CORE_SRC)/memdev.o
 cxl_core-y += $(CXL_CORE_SRC)/mbox.o
 cxl_core-y += $(CXL_CORE_SRC)/pci.o
 cxl_core-y += $(CXL_CORE_SRC)/hdm.o
+cxl_core-$(CONFIG_TRACING) += $(CXL_CORE_SRC)/trace.o
 cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o
 cxl_core-y += config_check.o
+cxl_core-y += cxl_core_test.o
 
 obj-m += test/

tools/testing/cxl/config_check.c

@@ -7,6 +7,7 @@ void check(void)
 	 * These kconfig symbols must be set to "m" for cxl_test to load
 	 * and operate.
 	 */
+	BUILD_BUG_ON(!IS_ENABLED(CONFIG_64BIT));
 	BUILD_BUG_ON(!IS_MODULE(CONFIG_CXL_BUS));
 	BUILD_BUG_ON(!IS_MODULE(CONFIG_CXL_ACPI));
 	BUILD_BUG_ON(!IS_MODULE(CONFIG_CXL_PMEM));

tools/testing/cxl/cxl_acpi_test.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+
+#include "watermark.h"
+
+cxl_test_watermark(cxl_acpi);

tools/testing/cxl/cxl_core_test.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+
+#include "watermark.h"
+
+cxl_test_watermark(cxl_core);

tools/testing/cxl/cxl_mem_test.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+
+#include "watermark.h"
+
+cxl_test_watermark(cxl_mem);

tools/testing/cxl/cxl_pmem_test.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+
+#include "watermark.h"
+
+cxl_test_watermark(cxl_pmem);

tools/testing/cxl/cxl_port_test.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+
+#include "watermark.h"
+
+cxl_test_watermark(cxl_port);

tools/testing/cxl/test/Kbuild

 # SPDX-License-Identifier: GPL-2.0
-ccflags-y := -I$(srctree)/drivers/cxl/
+ccflags-y := -I$(srctree)/drivers/cxl/ -I$(srctree)/drivers/cxl/core
 
 obj-m += cxl_test.o
 obj-m += cxl_mock.o

tools/testing/cxl/test/cxl.c

@@ -9,6 +9,8 @@
 #include <linux/pci.h>
 #include <linux/mm.h>
 #include <cxlmem.h>
+
+#include "../watermark.h"
 #include "mock.h"
 
 static int interleave_arithmetic;
@@ -618,7 +620,8 @@ static struct acpi_pci_root *mock_acpi_pci_find_root(acpi_handle handle)
 	return &mock_pci_root[host_bridge_index(adev)];
 }
 
-static struct cxl_hdm *mock_cxl_setup_hdm(struct cxl_port *port)
+static struct cxl_hdm *mock_cxl_setup_hdm(struct cxl_port *port,
+					  struct cxl_endpoint_dvsec_info *info)
 {
 	struct cxl_hdm *cxlhdm = devm_kzalloc(&port->dev, sizeof(*cxlhdm), GFP_KERNEL);
 
@@ -701,7 +704,144 @@ static int mock_decoder_reset(struct cxl_decoder *cxld)
 	return 0;
 }
 
-static int mock_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm)
+static void default_mock_decoder(struct cxl_decoder *cxld)
+{
+	cxld->hpa_range = (struct range){
+		.start = 0,
+		.end = -1,
+	};
+
+	cxld->interleave_ways = 1;
+	cxld->interleave_granularity = 256;
+	cxld->target_type = CXL_DECODER_EXPANDER;
+	cxld->commit = mock_decoder_commit;
+	cxld->reset = mock_decoder_reset;
+}
+
+static int first_decoder(struct device *dev, void *data)
+{
+	struct cxl_decoder *cxld;
+
+	if (!is_switch_decoder(dev))
+		return 0;
+	cxld = to_cxl_decoder(dev);
+	if (cxld->id == 0)
+		return 1;
+	return 0;
+}
+
+static void mock_init_hdm_decoder(struct cxl_decoder *cxld)
+{
+	struct acpi_cedt_cfmws *window = mock_cfmws[0];
+	struct platform_device *pdev = NULL;
+	struct cxl_endpoint_decoder *cxled;
+	struct cxl_switch_decoder *cxlsd;
+	struct cxl_port *port, *iter;
+	const int size = SZ_512M;
+	struct cxl_memdev *cxlmd;
+	struct cxl_dport *dport;
+	struct device *dev;
+	bool hb0 = false;
+	u64 base;
+	int i;
+
+	if (is_endpoint_decoder(&cxld->dev)) {
+		cxled = to_cxl_endpoint_decoder(&cxld->dev);
+		cxlmd = cxled_to_memdev(cxled);
+		WARN_ON(!dev_is_platform(cxlmd->dev.parent));
+		pdev = to_platform_device(cxlmd->dev.parent);
+
+		/* check is endpoint is attach to host-bridge0 */
+		port = cxled_to_port(cxled);
+		do {
+			if (port->uport == &cxl_host_bridge[0]->dev) {
+				hb0 = true;
+				break;
+			}
+			if (is_cxl_port(port->dev.parent))
+				port = to_cxl_port(port->dev.parent);
+			else
+				port = NULL;
+		} while (port);
+		port = cxled_to_port(cxled);
+	}
+
+	/*
+	 * The first decoder on the first 2 devices on the first switch
+	 * attached to host-bridge0 mock a fake / static RAM region. All
+	 * other decoders are default disabled. Given the round robin
+	 * assignment those devices are named cxl_mem.0, and cxl_mem.4.
+	 *
+	 * See 'cxl list -BMPu -m cxl_mem.0,cxl_mem.4'
+	 */
+	if (!hb0 || pdev->id % 4 || pdev->id > 4 || cxld->id > 0) {
+		default_mock_decoder(cxld);
+		return;
+	}
+
+	base = window->base_hpa;
+	cxld->hpa_range = (struct range) {
+		.start = base,
+		.end = base + size - 1,
+	};
+
+	cxld->interleave_ways = 2;
+	eig_to_granularity(window->granularity, &cxld->interleave_granularity);
+	cxld->target_type = CXL_DECODER_EXPANDER;
+	cxld->flags = CXL_DECODER_F_ENABLE;
+	cxled->state = CXL_DECODER_STATE_AUTO;
+	port->commit_end = cxld->id;
+	devm_cxl_dpa_reserve(cxled, 0, size / cxld->interleave_ways, 0);
+	cxld->commit = mock_decoder_commit;
+	cxld->reset = mock_decoder_reset;
+
+	/*
+	 * Now that endpoint decoder is set up, walk up the hierarchy
+	 * and setup the switch and root port decoders targeting @cxlmd.
+	 */
+	iter = port;
+	for (i = 0; i < 2; i++) {
+		dport = iter->parent_dport;
+		iter = dport->port;
+		dev = device_find_child(&iter->dev, NULL, first_decoder);
+		/*
+		 * Ancestor ports are guaranteed to be enumerated before
+		 * @port, and all ports have at least one decoder.
+		 */
+		if (WARN_ON(!dev))
+			continue;
+		cxlsd = to_cxl_switch_decoder(dev);
+		if (i == 0) {
+			/* put cxl_mem.4 second in the decode order */
+			if (pdev->id == 4)
+				cxlsd->target[1] = dport;
+			else
+				cxlsd->target[0] = dport;
+		} else
+			cxlsd->target[0] = dport;
+		cxld = &cxlsd->cxld;
+		cxld->target_type = CXL_DECODER_EXPANDER;
+		cxld->flags = CXL_DECODER_F_ENABLE;
+		iter->commit_end = 0;
+		/*
+		 * Switch targets 2 endpoints, while host bridge targets
+		 * one root port
+		 */
+		if (i == 0)
+			cxld->interleave_ways = 2;
+		else
+			cxld->interleave_ways = 1;
+		cxld->interleave_granularity = 256;
+		cxld->hpa_range = (struct range) {
+			.start = base,
+			.end = base + size - 1,
+		};
+		put_device(dev);
+	}
+}
+
+static int mock_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
+				       struct cxl_endpoint_dvsec_info *info)
 {
 	struct cxl_port *port = cxlhdm->port;
 	struct cxl_port *parent_port = to_cxl_port(port->dev.parent);
@@ -746,16 +886,7 @@ static int mock_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm)
 			cxld = &cxled->cxld;
 		}
 
-		cxld->hpa_range = (struct range) {
-			.start = 0,
-			.end = -1,
-		};
-
-		cxld->interleave_ways = min_not_zero(target_count, 1);
-		cxld->interleave_granularity = SZ_4K;
-		cxld->target_type = CXL_DECODER_EXPANDER;
-		cxld->commit = mock_decoder_commit;
-		cxld->reset = mock_decoder_reset;
+		mock_init_hdm_decoder(cxld);
 
 		if (target_count) {
 			rc = device_for_each_child(port->uport, &ctx,
@@ -1119,6 +1250,12 @@ static __init int cxl_test_init(void)
 {
 	int rc, i;
 
+	cxl_acpi_test();
+	cxl_core_test();
+	cxl_mem_test();
+	cxl_pmem_test();
+	cxl_port_test();
+
 	register_cxl_mock_ops(&cxl_mock_ops);
 
 	cxl_mock_pool = gen_pool_create(ilog2(SZ_2M), NUMA_NO_NODE);
@@ -1135,11 +1272,9 @@ static __init int cxl_test_init(void)
 	if (interleave_arithmetic == 1) {
 		cfmws_start = CFMWS_XOR_ARRAY_START;
 		cfmws_end = CFMWS_XOR_ARRAY_END;
-		dev_dbg(NULL, "cxl_test loading xor math option\n");
 	} else {
 		cfmws_start = CFMWS_MOD_ARRAY_START;
 		cfmws_end = CFMWS_MOD_ARRAY_END;
-		dev_dbg(NULL, "cxl_test loading modulo math option\n");
 	}
 
 	rc = populate_cedt();
@@ -1326,7 +1461,7 @@ static __exit void cxl_test_exit(void)
 	unregister_cxl_mock_ops(&cxl_mock_ops);
 }
 
-module_param(interleave_arithmetic, int, 0000);
+module_param(interleave_arithmetic, int, 0444);
 MODULE_PARM_DESC(interleave_arithmetic, "Modulo:0, XOR:1");
 module_init(cxl_test_init);
 module_exit(cxl_test_exit);

tools/testing/cxl/test/mem.c

@@ -9,6 +9,8 @@
 #include <linux/bits.h>
 #include <cxlmem.h>
 
+#include "trace.h"
+
 #define LSA_SIZE SZ_128K
 #define DEV_SIZE SZ_2G
 #define EFFECT(x) (1U << x)
@@ -67,6 +69,26 @@ static struct {
 
 #define PASS_TRY_LIMIT 3
 
+#define CXL_TEST_EVENT_CNT_MAX 15
+
+/* Set a number of events to return at a time for simulation.  */
+#define CXL_TEST_EVENT_CNT 3
+
+struct mock_event_log {
+	u16 clear_idx;
+	u16 cur_idx;
+	u16 nr_events;
+	u16 nr_overflow;
+	u16 overflow_reset;
+	struct cxl_event_record_raw *events[CXL_TEST_EVENT_CNT_MAX];
+};
+
+struct mock_event_store {
+	struct cxl_dev_state *cxlds;
+	struct mock_event_log mock_logs[CXL_EVENT_TYPE_MAX];
+	u32 ev_status;
+};
+
 struct cxl_mockmem_data {
 	void *lsa;
 	u32 security_state;
@@ -74,9 +96,317 @@ struct cxl_mockmem_data {
 	u8 master_pass[NVDIMM_PASSPHRASE_LEN];
 	int user_limit;
 	int master_limit;
+	struct mock_event_store mes;
+	u8 event_buf[SZ_4K];
+};
+
+static struct mock_event_log *event_find_log(struct device *dev, int log_type)
+{
+	struct cxl_mockmem_data *mdata = dev_get_drvdata(dev);
+
+	if (log_type >= CXL_EVENT_TYPE_MAX)
+		return NULL;
+	return &mdata->mes.mock_logs[log_type];
+}
+
+static struct cxl_event_record_raw *event_get_current(struct mock_event_log *log)
+{
+	return log->events[log->cur_idx];
+}
+
+static void event_reset_log(struct mock_event_log *log)
+{
+	log->cur_idx = 0;
+	log->clear_idx = 0;
+	log->nr_overflow = log->overflow_reset;
+}
+
+/* Handle can never be 0 use 1 based indexing for handle */
+static u16 event_get_clear_handle(struct mock_event_log *log)
+{
+	return log->clear_idx + 1;
+}
+
+/* Handle can never be 0 use 1 based indexing for handle */
+static __le16 event_get_cur_event_handle(struct mock_event_log *log)
+{
+	u16 cur_handle = log->cur_idx + 1;
+
+	return cpu_to_le16(cur_handle);
+}
+
+static bool event_log_empty(struct mock_event_log *log)
+{
+	return log->cur_idx == log->nr_events;
+}
+
+static void mes_add_event(struct mock_event_store *mes,
+			  enum cxl_event_log_type log_type,
+			  struct cxl_event_record_raw *event)
+{
+	struct mock_event_log *log;
+
+	if (WARN_ON(log_type >= CXL_EVENT_TYPE_MAX))
+		return;
+
+	log = &mes->mock_logs[log_type];
+
+	if ((log->nr_events + 1) > CXL_TEST_EVENT_CNT_MAX) {
+		log->nr_overflow++;
+		log->overflow_reset = log->nr_overflow;
+		return;
+	}
+
+	log->events[log->nr_events] = event;
+	log->nr_events++;
+}
+
+static int mock_get_event(struct cxl_dev_state *cxlds,
+			  struct cxl_mbox_cmd *cmd)
+{
+	struct cxl_get_event_payload *pl;
+	struct mock_event_log *log;
+	u16 nr_overflow;
+	u8 log_type;
+	int i;
+
+	if (cmd->size_in != sizeof(log_type))
+		return -EINVAL;
+
+	if (cmd->size_out < struct_size(pl, records, CXL_TEST_EVENT_CNT))
+		return -EINVAL;
+
+	log_type = *((u8 *)cmd->payload_in);
+	if (log_type >= CXL_EVENT_TYPE_MAX)
+		return -EINVAL;
+
+	memset(cmd->payload_out, 0, cmd->size_out);
+
+	log = event_find_log(cxlds->dev, log_type);
+	if (!log || event_log_empty(log))
+		return 0;
+
+	pl = cmd->payload_out;
+
+	for (i = 0; i < CXL_TEST_EVENT_CNT && !event_log_empty(log); i++) {
+		memcpy(&pl->records[i], event_get_current(log),
+		       sizeof(pl->records[i]));
+		pl->records[i].hdr.handle = event_get_cur_event_handle(log);
+		log->cur_idx++;
+	}
+
+	pl->record_count = cpu_to_le16(i);
+	if (!event_log_empty(log))
+		pl->flags |= CXL_GET_EVENT_FLAG_MORE_RECORDS;
+
+	if (log->nr_overflow) {
+		u64 ns;
+
+		pl->flags |= CXL_GET_EVENT_FLAG_OVERFLOW;
+		pl->overflow_err_count = cpu_to_le16(nr_overflow);
+		ns = ktime_get_real_ns();
+		ns -= 5000000000; /* 5s ago */
+		pl->first_overflow_timestamp = cpu_to_le64(ns);
+		ns = ktime_get_real_ns();
+		ns -= 1000000000; /* 1s ago */
+		pl->last_overflow_timestamp = cpu_to_le64(ns);
+	}
 
+	return 0;
+}
+
+static int mock_clear_event(struct cxl_dev_state *cxlds,
+			    struct cxl_mbox_cmd *cmd)
+{
+	struct cxl_mbox_clear_event_payload *pl = cmd->payload_in;
+	struct mock_event_log *log;
+	u8 log_type = pl->event_log;
+	u16 handle;
+	int nr;
+
+	if (log_type >= CXL_EVENT_TYPE_MAX)
+		return -EINVAL;
+
+	log = event_find_log(cxlds->dev, log_type);
+	if (!log)
+		return 0; /* No mock data in this log */
+
+	/*
+	 * This check is technically not invalid per the specification AFAICS.
+	 * (The host could 'guess' handles and clear them in order).
+	 * However, this is not good behavior for the host so test it.
+	 */
+	if (log->clear_idx + pl->nr_recs > log->cur_idx) {
+		dev_err(cxlds->dev,
+			"Attempting to clear more events than returned!\n");
+		return -EINVAL;
+	}
+
+	/* Check handle order prior to clearing events */
+	for (nr = 0, handle = event_get_clear_handle(log);
+	     nr < pl->nr_recs;
+	     nr++, handle++) {
+		if (handle != le16_to_cpu(pl->handles[nr])) {
+			dev_err(cxlds->dev, "Clearing events out of order\n");
+			return -EINVAL;
+		}
+	}
+
+	if (log->nr_overflow)
+		log->nr_overflow = 0;
+
+	/* Clear events */
+	log->clear_idx += pl->nr_recs;
+	return 0;
+}
+
+static void cxl_mock_event_trigger(struct device *dev)
+{
+	struct cxl_mockmem_data *mdata = dev_get_drvdata(dev);
+	struct mock_event_store *mes = &mdata->mes;
+	int i;
+
+	for (i = CXL_EVENT_TYPE_INFO; i < CXL_EVENT_TYPE_MAX; i++) {
+		struct mock_event_log *log;
+
+		log = event_find_log(dev, i);
+		if (log)
+			event_reset_log(log);
+	}
+
+	cxl_mem_get_event_records(mes->cxlds, mes->ev_status);
+}
+
+struct cxl_event_record_raw maint_needed = {
+	.hdr = {
+		.id = UUID_INIT(0xBA5EBA11, 0xABCD, 0xEFEB,
+				0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
+		.length = sizeof(struct cxl_event_record_raw),
+		.flags[0] = CXL_EVENT_RECORD_FLAG_MAINT_NEEDED,
+		/* .handle = Set dynamically */
+		.related_handle = cpu_to_le16(0xa5b6),
+	},
+	.data = { 0xDE, 0xAD, 0xBE, 0xEF },
+};
+
+struct cxl_event_record_raw hardware_replace = {
+	.hdr = {
+		.id = UUID_INIT(0xABCDEFEB, 0xBA11, 0xBA5E,
+				0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
+		.length = sizeof(struct cxl_event_record_raw),
+		.flags[0] = CXL_EVENT_RECORD_FLAG_HW_REPLACE,
+		/* .handle = Set dynamically */
+		.related_handle = cpu_to_le16(0xb6a5),
+	},
+	.data = { 0xDE, 0xAD, 0xBE, 0xEF },
+};
+
+struct cxl_event_gen_media gen_media = {
+	.hdr = {
+		.id = UUID_INIT(0xfbcd0a77, 0xc260, 0x417f,
+				0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6),
+		.length = sizeof(struct cxl_event_gen_media),
+		.flags[0] = CXL_EVENT_RECORD_FLAG_PERMANENT,
+		/* .handle = Set dynamically */
+		.related_handle = cpu_to_le16(0),
+	},
+	.phys_addr = cpu_to_le64(0x2000),
+	.descriptor = CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT,
+	.type = CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR,
+	.transaction_type = CXL_GMER_TRANS_HOST_WRITE,
+	/* .validity_flags = <set below> */
+	.channel = 1,
+	.rank = 30
+};
+
+struct cxl_event_dram dram = {
+	.hdr = {
+		.id = UUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,
+				0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24),
+		.length = sizeof(struct cxl_event_dram),
+		.flags[0] = CXL_EVENT_RECORD_FLAG_PERF_DEGRADED,
+		/* .handle = Set dynamically */
+		.related_handle = cpu_to_le16(0),
+	},
+	.phys_addr = cpu_to_le64(0x8000),
+	.descriptor = CXL_GMER_EVT_DESC_THRESHOLD_EVENT,
+	.type = CXL_GMER_MEM_EVT_TYPE_INV_ADDR,
+	.transaction_type = CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB,
+	/* .validity_flags = <set below> */
+	.channel = 1,
+	.bank_group = 5,
+	.bank = 2,
+	.column = {0xDE, 0xAD},
+};
+
+struct cxl_event_mem_module mem_module = {
+	.hdr = {
+		.id = UUID_INIT(0xfe927475, 0xdd59, 0x4339,
+				0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74),
+		.length = sizeof(struct cxl_event_mem_module),
+		/* .handle = Set dynamically */
+		.related_handle = cpu_to_le16(0),
+	},
+	.event_type = CXL_MMER_TEMP_CHANGE,
+	.info = {
+		.health_status = CXL_DHI_HS_PERFORMANCE_DEGRADED,
+		.media_status = CXL_DHI_MS_ALL_DATA_LOST,
+		.add_status = (CXL_DHI_AS_CRITICAL << 2) |
+			      (CXL_DHI_AS_WARNING << 4) |
+			      (CXL_DHI_AS_WARNING << 5),
+		.device_temp = { 0xDE, 0xAD},
+		.dirty_shutdown_cnt = { 0xde, 0xad, 0xbe, 0xef },
+		.cor_vol_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
+		.cor_per_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
+	}
 };
 
+static void cxl_mock_add_event_logs(struct mock_event_store *mes)
+{
+	put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK,
+			   &gen_media.validity_flags);
+
+	put_unaligned_le16(CXL_DER_VALID_CHANNEL | CXL_DER_VALID_BANK_GROUP |
+			   CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN,
+			   &dram.validity_flags);
+
+	mes_add_event(mes, CXL_EVENT_TYPE_INFO, &maint_needed);
+	mes_add_event(mes, CXL_EVENT_TYPE_INFO,
+		      (struct cxl_event_record_raw *)&gen_media);
+	mes_add_event(mes, CXL_EVENT_TYPE_INFO,
+		      (struct cxl_event_record_raw *)&mem_module);
+	mes->ev_status |= CXLDEV_EVENT_STATUS_INFO;
+
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &maint_needed);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL,
+		      (struct cxl_event_record_raw *)&dram);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL,
+		      (struct cxl_event_record_raw *)&gen_media);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL,
+		      (struct cxl_event_record_raw *)&mem_module);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL,
+		      (struct cxl_event_record_raw *)&dram);
+	/* Overflow this log */
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FAIL, &hardware_replace);
+	mes->ev_status |= CXLDEV_EVENT_STATUS_FAIL;
+
+	mes_add_event(mes, CXL_EVENT_TYPE_FATAL, &hardware_replace);
+	mes_add_event(mes, CXL_EVENT_TYPE_FATAL,
+		      (struct cxl_event_record_raw *)&dram);
+	mes->ev_status |= CXLDEV_EVENT_STATUS_FATAL;
+}
+
 static int mock_gsl(struct cxl_mbox_cmd *cmd)
 {
 	if (cmd->size_out < sizeof(mock_gsl_payload))
@@ -582,6 +912,12 @@ static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *
 	case CXL_MBOX_OP_GET_PARTITION_INFO:
 		rc = mock_partition_info(cxlds, cmd);
 		break;
+	case CXL_MBOX_OP_GET_EVENT_RECORD:
+		rc = mock_get_event(cxlds, cmd);
+		break;
+	case CXL_MBOX_OP_CLEAR_EVENT_RECORD:
+		rc = mock_clear_event(cxlds, cmd);
+		break;
 	case CXL_MBOX_OP_SET_LSA:
 		rc = mock_set_lsa(cxlds, cmd);
 		break;
@@ -628,6 +964,15 @@ static bool is_rcd(struct platform_device *pdev)
 	return !!id->driver_data;
 }
 
+static ssize_t event_trigger_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t count)
+{
+	cxl_mock_event_trigger(dev);
+	return count;
+}
+static DEVICE_ATTR_WO(event_trigger);
+
 static int cxl_mock_mem_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -655,6 +1000,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
 	cxlds->serial = pdev->id;
 	cxlds->mbox_send = cxl_mock_mbox_send;
 	cxlds->payload_size = SZ_4K;
+	cxlds->event.buf = (struct cxl_get_event_payload *) mdata->event_buf;
 	if (is_rcd(pdev)) {
 		cxlds->rcd = true;
 		cxlds->component_reg_phys = CXL_RESOURCE_NONE;
@@ -672,10 +1018,15 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
 	if (rc)
 		return rc;
 
+	mdata->mes.cxlds = cxlds;
+	cxl_mock_add_event_logs(&mdata->mes);
+
 	cxlmd = devm_cxl_add_memdev(cxlds);
 	if (IS_ERR(cxlmd))
 		return PTR_ERR(cxlmd);
 
+	cxl_mem_get_event_records(cxlds, CXLDEV_EVENT_STATUS_ALL);
+
 	return 0;
 }
 
@@ -714,6 +1065,7 @@ static DEVICE_ATTR_RW(security_lock);
 
 static struct attribute *cxl_mock_mem_attrs[] = {
 	&dev_attr_security_lock.attr,
+	&dev_attr_event_trigger.attr,
 	NULL
 };
 ATTRIBUTE_GROUPS(cxl_mock_mem);

tools/testing/cxl/test/mock.c

@@ -131,16 +131,18 @@ __wrap_nvdimm_bus_register(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(__wrap_nvdimm_bus_register);
 
-struct cxl_hdm *__wrap_devm_cxl_setup_hdm(struct cxl_port *port)
+struct cxl_hdm *__wrap_devm_cxl_setup_hdm(struct cxl_port *port,
+					  struct cxl_endpoint_dvsec_info *info)
+
 {
 	int index;
 	struct cxl_hdm *cxlhdm;
 	struct cxl_mock_ops *ops = get_cxl_mock_ops(&index);
 
 	if (ops && ops->is_mock_port(port->uport))
-		cxlhdm = ops->devm_cxl_setup_hdm(port);
+		cxlhdm = ops->devm_cxl_setup_hdm(port, info);
 	else
-		cxlhdm = devm_cxl_setup_hdm(port);
+		cxlhdm = devm_cxl_setup_hdm(port, info);
 	put_cxl_mock_ops(index);
 
 	return cxlhdm;
@@ -162,16 +164,17 @@ int __wrap_devm_cxl_add_passthrough_decoder(struct cxl_port *port)
 }
 EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_add_passthrough_decoder, CXL);
 
-int __wrap_devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm)
+int __wrap_devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
+				       struct cxl_endpoint_dvsec_info *info)
 {
 	int rc, index;
 	struct cxl_port *port = cxlhdm->port;
 	struct cxl_mock_ops *ops = get_cxl_mock_ops(&index);
 
 	if (ops && ops->is_mock_port(port->uport))
-		rc = ops->devm_cxl_enumerate_decoders(cxlhdm);
+		rc = ops->devm_cxl_enumerate_decoders(cxlhdm, info);
 	else
-		rc = devm_cxl_enumerate_decoders(cxlhdm);
+		rc = devm_cxl_enumerate_decoders(cxlhdm, info);
 	put_cxl_mock_ops(index);
 
 	return rc;
@@ -209,7 +212,8 @@ int __wrap_cxl_await_media_ready(struct cxl_dev_state *cxlds)
 EXPORT_SYMBOL_NS_GPL(__wrap_cxl_await_media_ready, CXL);
 
 int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds,
-			       struct cxl_hdm *cxlhdm)
+			       struct cxl_hdm *cxlhdm,
+			       struct cxl_endpoint_dvsec_info *info)
 {
 	int rc = 0, index;
 	struct cxl_mock_ops *ops = get_cxl_mock_ops(&index);
@@ -217,13 +221,29 @@ int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds,
 	if (ops && ops->is_mock_dev(cxlds->dev))
 		rc = 0;
 	else
-		rc = cxl_hdm_decode_init(cxlds, cxlhdm);
+		rc = cxl_hdm_decode_init(cxlds, cxlhdm, info);
 	put_cxl_mock_ops(index);
 
 	return rc;
 }
 EXPORT_SYMBOL_NS_GPL(__wrap_cxl_hdm_decode_init, CXL);
 
+int __wrap_cxl_dvsec_rr_decode(struct device *dev, int dvsec,
+			       struct cxl_endpoint_dvsec_info *info)
+{
+	int rc = 0, index;
+	struct cxl_mock_ops *ops = get_cxl_mock_ops(&index);
+
+	if (ops && ops->is_mock_dev(dev))
+		rc = 0;
+	else
+		rc = cxl_dvsec_rr_decode(dev, dvsec, info);
+	put_cxl_mock_ops(index);
+
+	return rc;
+}
+EXPORT_SYMBOL_NS_GPL(__wrap_cxl_dvsec_rr_decode, CXL);
+
 resource_size_t __wrap_cxl_rcrb_to_component(struct device *dev,
 					     resource_size_t rcrb,
 					     enum cxl_rcrb which)

tools/testing/cxl/test/mock.h

@@ -23,9 +23,11 @@ struct cxl_mock_ops {
 	bool (*is_mock_port)(struct device *dev);
 	bool (*is_mock_dev)(struct device *dev);
 	int (*devm_cxl_port_enumerate_dports)(struct cxl_port *port);
-	struct cxl_hdm *(*devm_cxl_setup_hdm)(struct cxl_port *port);
+	struct cxl_hdm *(*devm_cxl_setup_hdm)(
+		struct cxl_port *port, struct cxl_endpoint_dvsec_info *info);
 	int (*devm_cxl_add_passthrough_decoder)(struct cxl_port *port);
-	int (*devm_cxl_enumerate_decoders)(struct cxl_hdm *hdm);
+	int (*devm_cxl_enumerate_decoders)(
+		struct cxl_hdm *hdm, struct cxl_endpoint_dvsec_info *info);
 };
 
 void register_cxl_mock_ops(struct cxl_mock_ops *ops);

tools/testing/cxl/watermark.h

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+#ifndef _TEST_CXL_WATERMARK_H_
+#define _TEST_CXL_WATERMARK_H_
+#include <linux/module.h>
+#include <linux/printk.h>
+
+int cxl_acpi_test(void);
+int cxl_core_test(void);
+int cxl_mem_test(void);
+int cxl_pmem_test(void);
+int cxl_port_test(void);
+
+/*
+ * dummy routine for cxl_test to validate it is linking to the properly
+ * mocked module and not the standard one from the base tree.
+ */
+#define cxl_test_watermark(x)				\
+int x##_test(void)					\
+{							\
+	pr_debug("%s for cxl_test\n", KBUILD_MODNAME);	\
+	return 0;					\
+}							\
+EXPORT_SYMBOL(x##_test)
+#endif /* _TEST_CXL_WATERMARK_H_ */