EDAC: Update memory repair control interface for memory sparing feature

shijujose4 · bp3tk0v · commit 81e42fc1d303 · 2025-02-26T11:14:40.000+01:00
Update memory repair control interface for memory sparing feature. CXL memory devices can support soft and hard memory sparing at cacheline, row, bank and rank granularities. Memory sparing is defined as a repair function that replaces a portion of memory with a portion of functional memory at that same granularity. When a CXL device detects an error in memory, it will report to the host that there's need for a repair maintenance operation by using an event record where the "maintenance needed" flag is set. The event records contain the device physical address (DPA) and other attributes of the memory to repair such as bank group, bank, rank, row, column, channel etc. The kernel will report the corresponding CXL general media or DRAM trace event to userspace, and userspace tools (e.g. rasdaemon) will initiate a repair operation in response to the device request via the sysfs repair control. [ bp: Massage. ] Signed-off-by: Shiju Jose <shiju.jose@huawei.com> Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de> Link: https://lore.kernel.org/r/20250212143654.1893-15-shiju.jose@huawei.com
diff --git a/Documentation/ABI/testing/sysfs-edac-memory-repair b/Documentation/ABI/testing/sysfs-edac-memory-repair
@@ -42,6 +42,14 @@ Description:
 
 		- ppr - Post package repair.
 
+		- cacheline-sparing
+
+		- row-sparing
+
+		- bank-sparing
+
+		- rank-sparing
+
 		- All other values are reserved.
 
 What:		/sys/bus/edac/devices/<dev-name>/mem_repairX/persist_mode
@@ -134,6 +142,55 @@ Description:
 		related error records and trace events, for eg. CXL DRAM
 		and CXL general media error records in CXL memory devices.
 
+What:		/sys/bus/edac/devices/<dev-name>/mem_repairX/bank_group
+What:		/sys/bus/edac/devices/<dev-name>/mem_repairX/bank
+What:		/sys/bus/edac/devices/<dev-name>/mem_repairX/rank
+What:		/sys/bus/edac/devices/<dev-name>/mem_repairX/row
+What:		/sys/bus/edac/devices/<dev-name>/mem_repairX/column
+What:		/sys/bus/edac/devices/<dev-name>/mem_repairX/channel
+What:		/sys/bus/edac/devices/<dev-name>/mem_repairX/sub_channel
+Date:		March 2025
+KernelVersion:	6.15
+Contact:	linux-edac@vger.kernel.org
+Description:
+		(RW) The control attributes for the memory to be repaired.
+		The specific value of attributes to use depends on the
+		portion of memory to repair and will be reported to the host
+		in related error records and be available to userspace
+		in trace events, such as CXL DRAM and CXL general media
+		error records of CXL memory devices.
+
+		When readng back these attributes, it returns the current
+		value of memory requested to be repaired.
+
+		bank_group - The bank group of the memory to repair.
+
+		bank - The bank number of the memory to repair.
+
+		rank - The rank of the memory to repair. Rank is defined as a
+		set of memory devices on a channel that together execute a
+		transaction.
+
+		row - The row number of the memory to repair.
+
+		column - The column number of the memory to repair.
+
+		channel - The channel of the memory to repair. Channel is
+		defined as an interface that can be independently accessed
+		for a transaction.
+
+		sub_channel - The subchannel of the memory to repair.
+
+		The requirement to set these attributes varies based on the
+		repair function. The attributes in sysfs are not present
+		unless required for a repair function.
+
+		For example, CXL spec ver 3.1, Section 8.2.9.7.1.2 Table 8-103
+		soft PPR and Section 8.2.9.7.1.3 Table 8-104 hard PPR operations,
+		these attributes are not required to set. CXL spec ver 3.1,
+		Section 8.2.9.7.1.4 Table 8-105 memory sparing, these attributes
+		are required to set based on memory sparing granularity.
+
 What:		/sys/bus/edac/devices/<dev-name>/mem_repairX/repair
 Date:		March 2025
 KernelVersion:	6.15
diff --git a/drivers/edac/mem_repair.c b/drivers/edac/mem_repair.c
@@ -22,6 +22,13 @@ enum edac_mem_repair_attributes {
 	MR_MIN_DPA,
 	MR_MAX_DPA,
 	MR_NIBBLE_MASK,
+	MR_BANK_GROUP,
+	MR_BANK,
+	MR_RANK,
+	MR_ROW,
+	MR_COLUMN,
+	MR_CHANNEL,
+	MR_SUB_CHANNEL,
 	MEM_DO_REPAIR,
 	MR_MAX_ATTRS
 };
@@ -70,6 +77,13 @@ MR_ATTR_SHOW(dpa, get_dpa, u64, "0x%llx\n")
 MR_ATTR_SHOW(min_dpa, get_min_dpa, u64, "0x%llx\n")
 MR_ATTR_SHOW(max_dpa, get_max_dpa, u64, "0x%llx\n")
 MR_ATTR_SHOW(nibble_mask, get_nibble_mask, u32, "0x%x\n")
+MR_ATTR_SHOW(bank_group, get_bank_group, u32, "%u\n")
+MR_ATTR_SHOW(bank, get_bank, u32, "%u\n")
+MR_ATTR_SHOW(rank, get_rank, u32, "%u\n")
+MR_ATTR_SHOW(row, get_row, u32, "0x%x\n")
+MR_ATTR_SHOW(column, get_column, u32, "%u\n")
+MR_ATTR_SHOW(channel, get_channel, u32, "%u\n")
+MR_ATTR_SHOW(sub_channel, get_sub_channel, u32, "%u\n")
 
 #define MR_ATTR_STORE(attrib, cb, type, conv_func)			\
 static ssize_t attrib##_store(struct device *ras_feat_dev,			\
@@ -99,6 +113,13 @@ MR_ATTR_STORE(persist_mode, set_persist_mode, unsigned long, kstrtoul)
 MR_ATTR_STORE(hpa, set_hpa, u64, kstrtou64)
 MR_ATTR_STORE(dpa, set_dpa, u64, kstrtou64)
 MR_ATTR_STORE(nibble_mask, set_nibble_mask, unsigned long, kstrtoul)
+MR_ATTR_STORE(bank_group, set_bank_group, unsigned long, kstrtoul)
+MR_ATTR_STORE(bank, set_bank, unsigned long, kstrtoul)
+MR_ATTR_STORE(rank, set_rank, unsigned long, kstrtoul)
+MR_ATTR_STORE(row, set_row, unsigned long, kstrtoul)
+MR_ATTR_STORE(column, set_column, unsigned long, kstrtoul)
+MR_ATTR_STORE(channel, set_channel, unsigned long, kstrtoul)
+MR_ATTR_STORE(sub_channel, set_sub_channel, unsigned long, kstrtoul)
 
 #define MR_DO_OP(attrib, cb)						\
 static ssize_t attrib##_store(struct device *ras_feat_dev,				\
@@ -189,6 +210,62 @@ static umode_t mem_repair_attr_visible(struct kobject *kobj, struct attribute *a
 				return 0444;
 		}
 		break;
+	case MR_BANK_GROUP:
+		if (ops->get_bank_group) {
+			if (ops->set_bank_group)
+				return a->mode;
+			else
+				return 0444;
+		}
+		break;
+	case MR_BANK:
+		if (ops->get_bank) {
+			if (ops->set_bank)
+				return a->mode;
+			else
+				return 0444;
+		}
+		break;
+	case MR_RANK:
+		if (ops->get_rank) {
+			if (ops->set_rank)
+				return a->mode;
+			else
+				return 0444;
+		}
+		break;
+	case MR_ROW:
+		if (ops->get_row) {
+			if (ops->set_row)
+				return a->mode;
+			else
+				return 0444;
+		}
+		break;
+	case MR_COLUMN:
+		if (ops->get_column) {
+			if (ops->set_column)
+				return a->mode;
+			else
+				return 0444;
+		}
+		break;
+	case MR_CHANNEL:
+		if (ops->get_channel) {
+			if (ops->set_channel)
+				return a->mode;
+			else
+				return 0444;
+		}
+		break;
+	case MR_SUB_CHANNEL:
+		if (ops->get_sub_channel) {
+			if (ops->set_sub_channel)
+				return a->mode;
+			else
+				return 0444;
+		}
+		break;
 	case MEM_DO_REPAIR:
 		if (ops->do_repair)
 			return a->mode;
@@ -230,6 +307,13 @@ static int mem_repair_create_desc(struct device *dev,
 		[MR_MIN_DPA]	  = MR_ATTR_RO(min_dpa, instance),
 		[MR_MAX_DPA]	  = MR_ATTR_RO(max_dpa, instance),
 		[MR_NIBBLE_MASK]  = MR_ATTR_RW(nibble_mask, instance),
+		[MR_BANK_GROUP]   = MR_ATTR_RW(bank_group, instance),
+		[MR_BANK]	  = MR_ATTR_RW(bank, instance),
+		[MR_RANK]	  = MR_ATTR_RW(rank, instance),
+		[MR_ROW]	  = MR_ATTR_RW(row, instance),
+		[MR_COLUMN]	  = MR_ATTR_RW(column, instance),
+		[MR_CHANNEL]	  = MR_ATTR_RW(channel, instance),
+		[MR_SUB_CHANNEL]  = MR_ATTR_RW(sub_channel, instance),
 		[MEM_DO_REPAIR]	  = MR_ATTR_WO(repair, instance)
 	};
 
diff --git a/include/linux/edac.h b/include/linux/edac.h
@@ -780,6 +780,20 @@ enum edac_mem_repair_cmd {
  * @get_max_dpa: get the maximum supported device physical address (DPA).
  * @get_nibble_mask: get current nibble mask of memory to repair.
  * @set_nibble_mask: set nibble mask of memory to repair.
+ * @get_bank_group: get current bank group of memory to repair.
+ * @set_bank_group: set bank group of memory to repair.
+ * @get_bank: get current bank of memory to repair.
+ * @set_bank: set bank of memory to repair.
+ * @get_rank: get current rank of memory to repair.
+ * @set_rank: set rank of memory to repair.
+ * @get_row: get current row of memory to repair.
+ * @set_row: set row of memory to repair.
+ * @get_column: get current column of memory to repair.
+ * @set_column: set column of memory to repair.
+ * @get_channel: get current channel of memory to repair.
+ * @set_channel: set channel of memory to repair.
+ * @get_sub_channel: get current subchannel of memory to repair.
+ * @set_sub_channel: set subchannel of memory to repair.
  * @do_repair: Issue memory repair operation for the HPA/DPA and
  *	       other control attributes set for the memory to repair.
  *
@@ -800,6 +814,20 @@ struct edac_mem_repair_ops {
 	int (*get_max_dpa)(struct device *dev, void *drv_data, u64 *dpa);
 	int (*get_nibble_mask)(struct device *dev, void *drv_data, u32 *val);
 	int (*set_nibble_mask)(struct device *dev, void *drv_data, u32 val);
+	int (*get_bank_group)(struct device *dev, void *drv_data, u32 *val);
+	int (*set_bank_group)(struct device *dev, void *drv_data, u32 val);
+	int (*get_bank)(struct device *dev, void *drv_data, u32 *val);
+	int (*set_bank)(struct device *dev, void *drv_data, u32 val);
+	int (*get_rank)(struct device *dev, void *drv_data, u32 *val);
+	int (*set_rank)(struct device *dev, void *drv_data, u32 val);
+	int (*get_row)(struct device *dev, void *drv_data, u32 *val);
+	int (*set_row)(struct device *dev, void *drv_data, u32 val);
+	int (*get_column)(struct device *dev, void *drv_data, u32 *val);
+	int (*set_column)(struct device *dev, void *drv_data, u32 val);
+	int (*get_channel)(struct device *dev, void *drv_data, u32 *val);
+	int (*set_channel)(struct device *dev, void *drv_data, u32 val);
+	int (*get_sub_channel)(struct device *dev, void *drv_data, u32 *val);
+	int (*set_sub_channel)(struct device *dev, void *drv_data, u32 val);
 	int (*do_repair)(struct device *dev, void *drv_data, u32 val);
 };
 
