cxl/dax: Create dax devices for CXL RAM regions

While platform firmware takes some responsibility for mapping the RAM
capacity of CXL devices present at boot, the OS is responsible for
mapping the remainder and hot-added devices. Platform firmware is also
responsible for identifying the platform general purpose memory pool,
typically DDR attached DRAM, and arranging for the remainder to be 'Soft
Reserved'. That reservation allows the CXL subsystem to route the memory
to core-mm via memory-hotplug (dax_kmem), or leave it for dedicated
access (device-dax).

The new 'struct cxl_dax_region' object allows for a CXL memory resource
(region) to be published, but also allow for udev and module policy to
act on that event. It also prevents cxl_core.ko from having a module
loading dependency on any drivers/dax/ modules.

Tested-by: Fan Ni <fan.ni@samsung.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/167602003896.1924368.10335442077318970468.stgit@dwillia2-xfh.jf.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

5 files changed, 126 insertions, 4 deletions

diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index ad0849af42d7..8ebb9a74790d 100644
--- a/drivers/cxl/acpi.c
+++ b/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);
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 479f01da6d35..cde475e13216 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -15,12 +15,14 @@ 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
@@ -38,6 +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;
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index b45d2796ef35..0bb7a5ff724b 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -46,6 +46,8 @@ static int cxl_device_id(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;
@@ -2015,6 +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");
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 8c29204279e9..91bb9ac881ff 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -2278,6 +2278,75 @@ out:
 	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;
@@ -2362,6 +2431,42 @@ err_bridge:
 	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;
@@ -2624,8 +2729,7 @@ out:
 					p->res->start, p->res->end, cxlr,
 					is_system_ram) > 0)
 			return 0;
-		dev_dbg(dev, "TODO: hookup devdax\n");
-		return 0;
+		return devm_cxl_add_dax_region(cxlr);
 	default:
 		dev_dbg(&cxlr->dev, "unsupported region mode: %d\n",
 			cxlr->mode);
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 2ac344235235..b1395c46baec 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -513,6 +513,12 @@ 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
@@ -707,6 +713,7 @@ 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"
@@ -725,6 +732,7 @@ 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)
 {
@@ -739,6 +747,10 @@ static inline int cxl_add_to_region(struct cxl_port *root,
 {
 	return 0;
 }
+static inline struct cxl_dax_region *to_cxl_dax_region(struct device *dev)
+{
+	return NULL;
+}
 #endif
 
 /*