cxl/mem: Fix devm_cxl_memdev_edac_release() confusion

A device release method is only for undoing allocations on the path to
preparing the device for device_add(). In contrast, devm allocations are
post device_add(), are acquired during / after ->probe() and are released
synchronous with ->remove().

So, a "devm" helper in a "release" method is a clear anti-pattern.

Move this devm release action where it belongs, an action created at edac
object creation time. Otherwise, this leaks resources until
cxl_memdev_release() time which may be long after these xarray and error
record caches have gone idle.

Note, this also fixes up the type of @cxlmd->err_rec_array which needlessly
dropped type-safety.

Fixes: 0b5ccb0 ("cxl/edac: Support for finding memory operation attributes from the current boot")
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Shiju Jose <shiju.jose@huawei.com>
Cc: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Ben Cheatham <benjamin.cheatham@amd.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Tested-by: Shiju Jose <shiju.jose@huawei.com>
Reviewed-by: Shiju Jose <shiju.jose@huawei.com>
Tested-by: Alejandro Lucero <alucerop@amd.com>
Link: https://patch.msgid.link/20251216005616.3090129-2-dan.j.williams@intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>

Author: djbw

drivers/cxl/core/edac.c

@@ -1988,6 +1988,40 @@ static int cxl_memdev_soft_ppr_init(struct cxl_memdev *cxlmd,
 	return 0;
 }
 
+static void err_rec_free(void *_cxlmd)
+{
+	struct cxl_memdev *cxlmd = _cxlmd;
+	struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array;
+	struct cxl_event_gen_media *rec_gen_media;
+	struct cxl_event_dram *rec_dram;
+	unsigned long index;
+
+	cxlmd->err_rec_array = NULL;
+	xa_for_each(&array_rec->rec_dram, index, rec_dram)
+		kfree(rec_dram);
+	xa_destroy(&array_rec->rec_dram);
+
+	xa_for_each(&array_rec->rec_gen_media, index, rec_gen_media)
+		kfree(rec_gen_media);
+	xa_destroy(&array_rec->rec_gen_media);
+	kfree(array_rec);
+}
+
+static int devm_cxl_memdev_setup_err_rec(struct cxl_memdev *cxlmd)
+{
+	struct cxl_mem_err_rec *array_rec =
+		kzalloc(sizeof(*array_rec), GFP_KERNEL);
+
+	if (!array_rec)
+		return -ENOMEM;
+
+	xa_init(&array_rec->rec_gen_media);
+	xa_init(&array_rec->rec_dram);
+	cxlmd->err_rec_array = array_rec;
+
+	return devm_add_action_or_reset(&cxlmd->dev, err_rec_free, cxlmd);
+}
+
 int devm_cxl_memdev_edac_register(struct cxl_memdev *cxlmd)
 {
 	struct edac_dev_feature ras_features[CXL_NR_EDAC_DEV_FEATURES];
@@ -2038,15 +2072,9 @@ int devm_cxl_memdev_edac_register(struct cxl_memdev *cxlmd)
 		}
 
 		if (repair_inst) {
-			struct cxl_mem_err_rec *array_rec =
-				devm_kzalloc(&cxlmd->dev, sizeof(*array_rec),
-					     GFP_KERNEL);
-			if (!array_rec)
-				return -ENOMEM;
-
-			xa_init(&array_rec->rec_gen_media);
-			xa_init(&array_rec->rec_dram);
-			cxlmd->err_rec_array = array_rec;
+			rc = devm_cxl_memdev_setup_err_rec(cxlmd);
+			if (rc)
+				return rc;
 		}
 	}
 
@@ -2088,22 +2116,4 @@ int devm_cxl_region_edac_register(struct cxl_region *cxlr)
 }
 EXPORT_SYMBOL_NS_GPL(devm_cxl_region_edac_register, "CXL");
 
-void devm_cxl_memdev_edac_release(struct cxl_memdev *cxlmd)
-{
-	struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array;
-	struct cxl_event_gen_media *rec_gen_media;
-	struct cxl_event_dram *rec_dram;
-	unsigned long index;
-
-	if (!IS_ENABLED(CONFIG_CXL_EDAC_MEM_REPAIR) || !array_rec)
-		return;
-
-	xa_for_each(&array_rec->rec_dram, index, rec_dram)
-		kfree(rec_dram);
-	xa_destroy(&array_rec->rec_dram);
 
-	xa_for_each(&array_rec->rec_gen_media, index, rec_gen_media)
-		kfree(rec_gen_media);
-	xa_destroy(&array_rec->rec_gen_media);
-}
-EXPORT_SYMBOL_NS_GPL(devm_cxl_memdev_edac_release, "CXL");

drivers/cxl/core/memdev.c

@@ -27,7 +27,6 @@ static void cxl_memdev_release(struct device *dev)
 	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
 
 	ida_free(&cxl_memdev_ida, cxlmd->id);
-	devm_cxl_memdev_edac_release(cxlmd);
 	kfree(cxlmd);
 }
 

drivers/cxl/cxlmem.h

@@ -63,7 +63,7 @@ struct cxl_memdev {
 	int depth;
 	u8 scrub_cycle;
 	int scrub_region_id;
-	void *err_rec_array;
+	struct cxl_mem_err_rec *err_rec_array;
 };
 
 static inline struct cxl_memdev *to_cxl_memdev(struct device *dev)
@@ -877,7 +877,6 @@ int devm_cxl_memdev_edac_register(struct cxl_memdev *cxlmd);
 int devm_cxl_region_edac_register(struct cxl_region *cxlr);
 int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, union cxl_event *evt);
 int cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt);
-void devm_cxl_memdev_edac_release(struct cxl_memdev *cxlmd);
 #else
 static inline int devm_cxl_memdev_edac_register(struct cxl_memdev *cxlmd)
 { return 0; }
@@ -889,8 +888,6 @@ static inline int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd,
 static inline int cxl_store_rec_dram(struct cxl_memdev *cxlmd,
 				     union cxl_event *evt)
 { return 0; }
-static inline void devm_cxl_memdev_edac_release(struct cxl_memdev *cxlmd)
-{ return; }
 #endif
 
 #ifdef CONFIG_CXL_SUSPEND