3 files changed, 177 insertions, 76 deletions

diff --git a/drivers/dax/hmem/Makefile b/drivers/dax/hmem/Makefile
index 57377b4c3d47..d4c4cd6bccd7 100644
--- a/drivers/dax/hmem/Makefile
+++ b/drivers/dax/hmem/Makefile
@@ -1,6 +1,7 @@
 # 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
diff --git a/drivers/dax/hmem/device.c b/drivers/dax/hmem/device.c
index 903325aac991..f9e1a76a04a9 100644
--- a/drivers/dax/hmem/device.c
+++ b/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;
+}
 
-	return;
+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);
diff --git a/drivers/dax/hmem/hmem.c b/drivers/dax/hmem/hmem.c
index 1bf040dbc834..e5fe8b39fb94 100644
--- a/drivers/dax/hmem/hmem.c
+++ b/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)
-{
-	/* devm handles teardown */
-	return 0;
-}
-
 static struct platform_driver dax_hmem_driver = {
 	.probe = dax_hmem_probe,
-	.remove = dax_hmem_remove,
 	.driver = {
 		.name = "hmem",
 	},
 };
 
-module_platform_driver(dax_hmem_driver);
+static void release_memregion(void *data)
+{
+	memregion_free((long) data);
+}
+
+static void release_hmem(void *pdev)
+{
+	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 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_platform",
+	},
+};
+
+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");