Merge branch 'for-6.3/cxl-ram-region' into cxl/next

Include the support for enumerating and provisioning ram regions for
v6.3. This also include a default policy change for ram / volatile
device-dax instances to assign them to the dax_kmem driver by default.

Author: djbw

Documentation/ABI/testing/sysfs-bus-cxl

@@ -198,7 +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
@@ -209,7 +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
@@ -229,7 +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",
@@ -240,7 +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
@@ -260,7 +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
@@ -275,7 +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
@@ -285,25 +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,
@@ -312,17 +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
@@ -333,7 +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
@@ -343,7 +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.
@@ -358,9 +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
@@ -372,7 +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
@@ -391,7 +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

@@ -6034,6 +6034,7 @@ 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/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/cxl/Kconfig

@@ -104,12 +104,22 @@ 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)"

drivers/cxl/acpi.c

@@ -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/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

@@ -279,7 +279,7 @@ 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 +295,7 @@ 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)
 {
@@ -676,6 +677,14 @@ 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;
 }
 
@@ -783,6 +792,9 @@ 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;
 }
 
@@ -826,7 +838,8 @@ 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 +849,25 @@ 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);
 		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/memdev.c

@@ -246,6 +246,7 @@ static struct cxl_memdev *cxl_memdev_alloc(struct cxl_dev_state *cxlds,
 	if (rc < 0)
 		goto err;
 	cxlmd->id = rc;
+	cxlmd->depth = -1;
 
 	dev = &cxlmd->dev;
 	device_initialize(dev);

drivers/cxl/core/pci.c

@@ -214,11 +214,6 @@ 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)
 {