EDAC: Add a Error Check Scrub control feature

Add an Error Check Scrub (ECS) control to manage a memory device's ECS
feature.

The ECS is a feature defined in JEDEC DDR5 SDRAM Specification (JESD79-5) and
allows the DRAM to internally read, correct single-bit errors, and write back
corrected data bits to the DRAM array while providing transparency to error
counts.

The DDR5 device contains a number of memory media Field Replaceable Units
(FRU) per device. The DDR5 ECS feature and thus the ECS control driver
supports configuring the ECS parameters per FRU.

Memory devices support the ECS feature register with the EDAC device driver,
which retrieves the ECS descriptor from the EDAC ECS driver.  This driver
exposes sysfs ECS control attributes to userspace via

  /sys/bus/edac/devices/<dev-name>/ecs_fruX/.

The common sysfs ECS control interface abstracts the control of an arbitrary
ECS functionality to a common set of functions.

Support for the ECS feature is added separately because the control attributes
of the DDR5 ECS feature differ from those of the scrub feature.

The sysfs ECS attribute nodes are only present if the client driver has
implemented the corresponding attribute callback function and passed the
necessary operations to the EDAC RAS feature driver during registration.

  [ bp: Massage, fixup edac_dev_register() retvals. ]

Co-developed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Fan Ni <fan.ni@samsung.com>
Tested-by: Fan Ni <fan.ni@samsung.com>
Link: https://lore.kernel.org/r/20250212143654.1893-4-shiju.jose@huawei.com

1 files changed, 46 insertions, 2 deletions

diff --git a/include/linux/edac.h b/include/linux/edac.h
index 1cbab08720df..f8346014c14e 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -667,6 +667,7 @@ static inline struct dimm_info *edac_get_dimm(struct mem_ctl_info *mci,
 /* RAS feature type */
 enum edac_dev_feat {
 	RAS_FEAT_SCRUB,
+	RAS_FEAT_ECS,
 	RAS_FEAT_MAX
 };
 
@@ -707,9 +708,47 @@ static inline int edac_scrub_get_desc(struct device *scrub_dev,
 { return -EOPNOTSUPP; }
 #endif /* CONFIG_EDAC_SCRUB */
 
+/**
+ * struct edac_ecs_ops - ECS device operations (all elements optional)
+ * @get_log_entry_type: read the log entry type value.
+ * @set_log_entry_type: set the log entry type value.
+ * @get_mode: read the mode value.
+ * @set_mode: set the mode value.
+ * @reset: reset the ECS counter.
+ * @get_threshold: read the threshold count per gigabits of memory cells.
+ * @set_threshold: set the threshold count per gigabits of memory cells.
+ */
+struct edac_ecs_ops {
+	int (*get_log_entry_type)(struct device *dev, void *drv_data, int fru_id, u32 *val);
+	int (*set_log_entry_type)(struct device *dev, void *drv_data, int fru_id, u32 val);
+	int (*get_mode)(struct device *dev, void *drv_data, int fru_id, u32 *val);
+	int (*set_mode)(struct device *dev, void *drv_data, int fru_id, u32 val);
+	int (*reset)(struct device *dev, void *drv_data, int fru_id, u32 val);
+	int (*get_threshold)(struct device *dev, void *drv_data, int fru_id, u32 *threshold);
+	int (*set_threshold)(struct device *dev, void *drv_data, int fru_id, u32 threshold);
+};
+
+struct edac_ecs_ex_info {
+	u16 num_media_frus;
+};
+
+#if IS_ENABLED(CONFIG_EDAC_ECS)
+int edac_ecs_get_desc(struct device *ecs_dev,
+		      const struct attribute_group **attr_groups,
+		      u16 num_media_frus);
+#else
+static inline int edac_ecs_get_desc(struct device *ecs_dev,
+				    const struct attribute_group **attr_groups,
+				    u16 num_media_frus)
+{ return -EOPNOTSUPP; }
+#endif /* CONFIG_EDAC_ECS */
+
 /* EDAC device feature information structure */
 struct edac_dev_data {
-	const struct edac_scrub_ops *scrub_ops;
+	union {
+		const struct edac_scrub_ops *scrub_ops;
+		const struct edac_ecs_ops *ecs_ops;
+	};
 	u8 instance;
 	void *private;
 };
@@ -718,13 +757,18 @@ struct edac_dev_feat_ctx {
 	struct device dev;
 	void *private;
 	struct edac_dev_data *scrub;
+	struct edac_dev_data ecs;
 };
 
 struct edac_dev_feature {
 	enum edac_dev_feat ft_type;
 	u8 instance;
-	const struct edac_scrub_ops *scrub_ops;
+	union {
+		const struct edac_scrub_ops *scrub_ops;
+		const struct edac_ecs_ops *ecs_ops;
+	};
 	void *ctx;
+	struct edac_ecs_ex_info ecs_info;
 };
 
 int edac_dev_register(struct device *parent, char *dev_name,