dax/hmem: Move hmem device registration to dax_hmem.ko

In preparation for the CXL region driver to take over the responsibility
of registering device-dax instances for CXL regions, move the
registration of "hmem" devices to dax_hmem.ko.

Previously the builtin component of this enabling
(drivers/dax/hmem/device.o) would register platform devices for each
address range and trigger the dax_hmem.ko module to load and attach
device-dax instances to those devices. Now, the ranges are collected
from the HMAT and EFI memory map walking, but the device creation is
deferred. A new "hmem_platform" device is created which triggers
dax_hmem.ko to load and register the platform devices.

Tested-by: Fan Ni <[email protected]>
Reviewed-by: Dave Jiang <[email protected]>
Reviewed-by: Jonathan Cameron <[email protected]>
Link: https://lore.kernel.org/r/167602002771.1924368.5653558226424530127.stgit@dwillia2-xfh.jf.intel.com
Signed-off-by: Dan Williams <[email protected]>

Author: djbw

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);
 	}
 }
 

drivers/dax/Kconfig

@@ -46,7 +46,7 @@ config DEV_DAX_HMEM
 	  Say M if unsure.
 
 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

drivers/dax/hmem/device.c

@@ -8,78 +8,75 @@
 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,
 	.end = -1,
 	.flags = IORESOURCE_MEM,
 };
 
-void hmem_register_device(int target_nid, struct resource *res)
+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)
 {
 	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,
-		.range = {
-			.start = res->start,
-			.end = res->end,
-		},
-	};
-	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;
+		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;
 }

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;
@@ -43,8 +44,110 @@ static struct platform_driver dax_hmem_driver = {
 	},
 };
 
-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;
+
+	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);
 
 MODULE_ALIAS("platform:hmem*");
+MODULE_ALIAS("platform:hmem_platform*");
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Intel Corporation");

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