events/hw_event: Create a Hardware Anomaly Report Mechanism (HARM)

index 3d96534..ef0738b 100644
@@ -34,11 +34,10 @@
 #include <linux/platform_device.h>
 #include <linux/sysdev.h>
 #include <linux/workqueue.h>
+#include <linux/edac.h>
 
-#define EDAC_MC_LABEL_LEN	31
 #define EDAC_DEVICE_NAME_LEN	31
 #define EDAC_ATTRIB_VALUE_LEN	15
-#define MC_PROC_NAME_MAX_LEN	7
 
 #if PAGE_SHIFT < 20
 #define PAGES_TO_MiB(pages)	((pages) >> (20 - PAGE_SHIFT))

@@ -101,357 +100,6 @@ extern int edac_debug_level;
 
 #define edac_dev_name(dev) (dev)->dev_name
 
-/* memory devices */
-enum dev_type {
-	DEV_UNKNOWN = 0,
-	DEV_X1,
-	DEV_X2,
-	DEV_X4,
-	DEV_X8,
-	DEV_X16,
-	DEV_X32,		/* Do these parts exist? */
-	DEV_X64			/* Do these parts exist? */
-};
-
-#define DEV_FLAG_UNKNOWN	BIT(DEV_UNKNOWN)
-#define DEV_FLAG_X1		BIT(DEV_X1)
-#define DEV_FLAG_X2		BIT(DEV_X2)
-#define DEV_FLAG_X4		BIT(DEV_X4)
-#define DEV_FLAG_X8		BIT(DEV_X8)
-#define DEV_FLAG_X16		BIT(DEV_X16)
-#define DEV_FLAG_X32		BIT(DEV_X32)
-#define DEV_FLAG_X64		BIT(DEV_X64)
-
-/* memory types */
-enum mem_type {
-	MEM_EMPTY = 0,		/* Empty csrow */
-	MEM_RESERVED,		/* Reserved csrow type */
-	MEM_UNKNOWN,		/* Unknown csrow type */
-	MEM_FPM,		/* Fast page mode */
-	MEM_EDO,		/* Extended data out */
-	MEM_BEDO,		/* Burst Extended data out */
-	MEM_SDR,		/* Single data rate SDRAM */
-	MEM_RDR,		/* Registered single data rate SDRAM */
-	MEM_DDR,		/* Double data rate SDRAM */
-	MEM_RDDR,		/* Registered Double data rate SDRAM */
-	MEM_RMBS,		/* Rambus DRAM */
-	MEM_DDR2,		/* DDR2 RAM */
-	MEM_FB_DDR2,		/* fully buffered DDR2 */
-	MEM_RDDR2,		/* Registered DDR2 RAM */
-	MEM_XDR,		/* Rambus XDR */
-	MEM_DDR3,		/* DDR3 RAM */
-	MEM_RDDR3,		/* Registered DDR3 RAM */
-};
-
-#define MEM_FLAG_EMPTY		BIT(MEM_EMPTY)
-#define MEM_FLAG_RESERVED	BIT(MEM_RESERVED)
-#define MEM_FLAG_UNKNOWN	BIT(MEM_UNKNOWN)
-#define MEM_FLAG_FPM		BIT(MEM_FPM)
-#define MEM_FLAG_EDO		BIT(MEM_EDO)
-#define MEM_FLAG_BEDO		BIT(MEM_BEDO)
-#define MEM_FLAG_SDR		BIT(MEM_SDR)
-#define MEM_FLAG_RDR		BIT(MEM_RDR)
-#define MEM_FLAG_DDR		BIT(MEM_DDR)
-#define MEM_FLAG_RDDR		BIT(MEM_RDDR)
-#define MEM_FLAG_RMBS		BIT(MEM_RMBS)
-#define MEM_FLAG_DDR2           BIT(MEM_DDR2)
-#define MEM_FLAG_FB_DDR2        BIT(MEM_FB_DDR2)
-#define MEM_FLAG_RDDR2          BIT(MEM_RDDR2)
-#define MEM_FLAG_XDR            BIT(MEM_XDR)
-#define MEM_FLAG_DDR3		 BIT(MEM_DDR3)
-#define MEM_FLAG_RDDR3		 BIT(MEM_RDDR3)
-
-/* chipset Error Detection and Correction capabilities and mode */
-enum edac_type {
-	EDAC_UNKNOWN = 0,	/* Unknown if ECC is available */
-	EDAC_NONE,		/* Doesnt support ECC */
-	EDAC_RESERVED,		/* Reserved ECC type */
-	EDAC_PARITY,		/* Detects parity errors */
-	EDAC_EC,		/* Error Checking - no correction */
-	EDAC_SECDED,		/* Single bit error correction, Double detection */
-	EDAC_S2ECD2ED,		/* Chipkill x2 devices - do these exist? */
-	EDAC_S4ECD4ED,		/* Chipkill x4 devices */
-	EDAC_S8ECD8ED,		/* Chipkill x8 devices */
-	EDAC_S16ECD16ED,	/* Chipkill x16 devices */
-};
-
-#define EDAC_FLAG_UNKNOWN	BIT(EDAC_UNKNOWN)
-#define EDAC_FLAG_NONE		BIT(EDAC_NONE)
-#define EDAC_FLAG_PARITY	BIT(EDAC_PARITY)
-#define EDAC_FLAG_EC		BIT(EDAC_EC)
-#define EDAC_FLAG_SECDED	BIT(EDAC_SECDED)
-#define EDAC_FLAG_S2ECD2ED	BIT(EDAC_S2ECD2ED)
-#define EDAC_FLAG_S4ECD4ED	BIT(EDAC_S4ECD4ED)
-#define EDAC_FLAG_S8ECD8ED	BIT(EDAC_S8ECD8ED)
-#define EDAC_FLAG_S16ECD16ED	BIT(EDAC_S16ECD16ED)
-
-/* scrubbing capabilities */
-enum scrub_type {
-	SCRUB_UNKNOWN = 0,	/* Unknown if scrubber is available */
-	SCRUB_NONE,		/* No scrubber */
-	SCRUB_SW_PROG,		/* SW progressive (sequential) scrubbing */
-	SCRUB_SW_SRC,		/* Software scrub only errors */
-	SCRUB_SW_PROG_SRC,	/* Progressive software scrub from an error */
-	SCRUB_SW_TUNABLE,	/* Software scrub frequency is tunable */
-	SCRUB_HW_PROG,		/* HW progressive (sequential) scrubbing */
-	SCRUB_HW_SRC,		/* Hardware scrub only errors */
-	SCRUB_HW_PROG_SRC,	/* Progressive hardware scrub from an error */
-	SCRUB_HW_TUNABLE	/* Hardware scrub frequency is tunable */
-};
-
-#define SCRUB_FLAG_SW_PROG	BIT(SCRUB_SW_PROG)
-#define SCRUB_FLAG_SW_SRC	BIT(SCRUB_SW_SRC)
-#define SCRUB_FLAG_SW_PROG_SRC	BIT(SCRUB_SW_PROG_SRC)
-#define SCRUB_FLAG_SW_TUN	BIT(SCRUB_SW_SCRUB_TUNABLE)
-#define SCRUB_FLAG_HW_PROG	BIT(SCRUB_HW_PROG)
-#define SCRUB_FLAG_HW_SRC	BIT(SCRUB_HW_SRC)
-#define SCRUB_FLAG_HW_PROG_SRC	BIT(SCRUB_HW_PROG_SRC)
-#define SCRUB_FLAG_HW_TUN	BIT(SCRUB_HW_TUNABLE)
-
-/* FIXME - should have notify capabilities: NMI, LOG, PROC, etc */
-
-/* EDAC internal operation states */
-#define	OP_ALLOC		0x100
-#define OP_RUNNING_POLL		0x201
-#define OP_RUNNING_INTERRUPT	0x202
-#define OP_RUNNING_POLL_INTR	0x203
-#define OP_OFFLINE		0x300
-
-/*
- * There are several things to be aware of that aren't at all obvious:
- *
- *
- * SOCKETS, SOCKET SETS, BANKS, ROWS, CHIP-SELECT ROWS, CHANNELS, etc..
- *
- * These are some of the many terms that are thrown about that don't always
- * mean what people think they mean (Inconceivable!).  In the interest of
- * creating a common ground for discussion, terms and their definitions
- * will be established.
- *
- * Memory devices:	The individual chip on a memory stick.  These devices
- *			commonly output 4 and 8 bits each.  Grouping several
- *			of these in parallel provides 64 bits which is common
- *			for a memory stick.
- *
- * Memory Stick:	A printed circuit board that agregates multiple
- *			memory devices in parallel.  This is the atomic
- *			memory component that is purchaseable by Joe consumer
- *			and loaded into a memory socket.
- *
- * Socket:		A physical connector on the motherboard that accepts
- *			a single memory stick.
- *
- * Channel:		Set of memory devices on a memory stick that must be
- *			grouped in parallel with one or more additional
- *			channels from other memory sticks.  This parallel
- *			grouping of the output from multiple channels are
- *			necessary for the smallest granularity of memory access.
- *			Some memory controllers are capable of single channel -
- *			which means that memory sticks can be loaded
- *			individually.  Other memory controllers are only
- *			capable of dual channel - which means that memory
- *			sticks must be loaded as pairs (see "socket set").
- *
- * Chip-select row:	All of the memory devices that are selected together.
- *			for a single, minimum grain of memory access.
- *			This selects all of the parallel memory devices across
- *			all of the parallel channels.  Common chip-select rows
- *			for single channel are 64 bits, for dual channel 128
- *			bits.
- *
- * Single-Ranked stick:	A Single-ranked stick has 1 chip-select row of memory.
- *			Motherboards commonly drive two chip-select pins to
- *			a memory stick. A single-ranked stick, will occupy
- *			only one of those rows. The other will be unused.
- *
- * Double-Ranked stick:	A double-ranked stick has two chip-select rows which
- *			access different sets of memory devices.  The two
- *			rows cannot be accessed concurrently.
- *
- * Double-sided stick:	DEPRECATED TERM, see Double-Ranked stick.
- *			A double-sided stick has two chip-select rows which
- *			access different sets of memory devices.  The two
- *			rows cannot be accessed concurrently.  "Double-sided"
- *			is irrespective of the memory devices being mounted
- *			on both sides of the memory stick.
- *
- * Socket set:		All of the memory sticks that are required for
- *			a single memory access or all of the memory sticks
- *			spanned by a chip-select row.  A single socket set
- *			has two chip-select rows and if double-sided sticks
- *			are used these will occupy those chip-select rows.
- *
- * Bank:		This term is avoided because it is unclear when
- *			needing to distinguish between chip-select rows and
- *			socket sets.
- *
- * Controller pages:
- *
- * Physical pages:
- *
- * Virtual pages:
- *
- *
- * STRUCTURE ORGANIZATION AND CHOICES
- *
- *
- *
- * PS - I enjoyed writing all that about as much as you enjoyed reading it.
- */
-
-struct channel_info {
-	int chan_idx;		/* channel index */
-	u32 ce_count;		/* Correctable Errors for this CHANNEL */
-	char label[EDAC_MC_LABEL_LEN + 1];	/* DIMM label on motherboard */
-	struct csrow_info *csrow;	/* the parent */
-};
-
-struct csrow_info {
-	unsigned long first_page;	/* first page number in dimm */
-	unsigned long last_page;	/* last page number in dimm */
-	unsigned long page_mask;	/* used for interleaving -
-					 * 0UL for non intlv
-					 */
-	u32 nr_pages;		/* number of pages in csrow */
-	u32 grain;		/* granularity of reported error in bytes */
-	int csrow_idx;		/* the chip-select row */
-	enum dev_type dtype;	/* memory device type */
-	u32 ue_count;		/* Uncorrectable Errors for this csrow */
-	u32 ce_count;		/* Correctable Errors for this csrow */
-	enum mem_type mtype;	/* memory csrow type */
-	enum edac_type edac_mode;	/* EDAC mode for this csrow */
-	struct mem_ctl_info *mci;	/* the parent */
-
-	struct kobject kobj;	/* sysfs kobject for this csrow */
-
-	/* channel information for this csrow */
-	u32 nr_channels;
-	struct channel_info *channels;
-};
-
-struct mcidev_sysfs_group {
-	const char *name;				/* group name */
-	const struct mcidev_sysfs_attribute *mcidev_attr; /* group attributes */
-};
-
-struct mcidev_sysfs_group_kobj {
-	struct list_head list;		/* list for all instances within a mc */
-
-	struct kobject kobj;		/* kobj for the group */
-
-	const struct mcidev_sysfs_group *grp;	/* group description table */
-	struct mem_ctl_info *mci;	/* the parent */
-};
-
-/* mcidev_sysfs_attribute structure
- *	used for driver sysfs attributes and in mem_ctl_info
- * 	sysfs top level entries
- */
-struct mcidev_sysfs_attribute {
-	/* It should use either attr or grp */
-	struct attribute attr;
-	const struct mcidev_sysfs_group *grp;	/* Points to a group of attributes */
-
-	/* Ops for show/store values at the attribute - not used on group */
-        ssize_t (*show)(struct mem_ctl_info *,char *);
-        ssize_t (*store)(struct mem_ctl_info *, const char *,size_t);
-};
-
-/* MEMORY controller information structure
- */
-struct mem_ctl_info {
-	struct list_head link;	/* for global list of mem_ctl_info structs */
-
-	struct module *owner;	/* Module owner of this control struct */
-
-	unsigned long mtype_cap;	/* memory types supported by mc */
-	unsigned long edac_ctl_cap;	/* Mem controller EDAC capabilities */
-	unsigned long edac_cap;	/* configuration capabilities - this is
-				 * closely related to edac_ctl_cap.  The
-				 * difference is that the controller may be
-				 * capable of s4ecd4ed which would be listed
-				 * in edac_ctl_cap, but if channels aren't
-				 * capable of s4ecd4ed then the edac_cap would
-				 * not have that capability.
-				 */
-	unsigned long scrub_cap;	/* chipset scrub capabilities */
-	enum scrub_type scrub_mode;	/* current scrub mode */
-
-	/* Translates sdram memory scrub rate given in bytes/sec to the
-	   internal representation and configures whatever else needs
-	   to be configured.
-	 */
-	int (*set_sdram_scrub_rate) (struct mem_ctl_info * mci, u32 bw);
-
-	/* Get the current sdram memory scrub rate from the internal
-	   representation and converts it to the closest matching
-	   bandwith in bytes/sec.
-	 */
-	int (*get_sdram_scrub_rate) (struct mem_ctl_info * mci);
-
-
-	/* pointer to edac checking routine */
-	void (*edac_check) (struct mem_ctl_info * mci);
-
-	/*
-	 * Remaps memory pages: controller pages to physical pages.
-	 * For most MC's, this will be NULL.
-	 */
-	/* FIXME - why not send the phys page to begin with? */
-	unsigned long (*ctl_page_to_phys) (struct mem_ctl_info * mci,
-					   unsigned long page);
-	int mc_idx;
-	int nr_csrows;
-	struct csrow_info *csrows;
-	/*
-	 * FIXME - what about controllers on other busses? - IDs must be
-	 * unique.  dev pointer should be sufficiently unique, but
-	 * BUS:SLOT.FUNC numbers may not be unique.
-	 */
-	struct device *dev;
-	const char *mod_name;
-	const char *mod_ver;
-	const char *ctl_name;
-	const char *dev_name;
-	char proc_name[MC_PROC_NAME_MAX_LEN + 1];
-	void *pvt_info;
-	u32 ue_noinfo_count;	/* Uncorrectable Errors w/o info */
-	u32 ce_noinfo_count;	/* Correctable Errors w/o info */
-	u32 ue_count;		/* Total Uncorrectable Errors for this MC */
-	u32 ce_count;		/* Total Correctable Errors for this MC */
-	unsigned long start_time;	/* mci load start time (in jiffies) */
-
-	/* this stuff is for safe removal of mc devices from global list while
-	 * NMI handlers may be traversing list
-	 */
-	struct rcu_head rcu;
-	struct completion complete;
-
-	/* edac sysfs device control */
-	struct kobject edac_mci_kobj;
-
-	/* list for all grp instances within a mc */
-	struct list_head grp_kobj_list;
-
-	/* Additional top controller level attributes, but specified
-	 * by the low level driver.
-	 *
-	 * Set by the low level driver to provide attributes at the
-	 * controller level, same level as 'ue_count' and 'ce_count' above.
-	 * An array of structures, NULL terminated
-	 *
-	 * If attributes are desired, then set to array of attributes
-	 * If no attributes are desired, leave NULL
-	 */
-	const struct mcidev_sysfs_attribute *mc_driver_sysfs_attributes;
-
-	/* work struct for this MC */
-	struct delayed_work work;
-
-	/* the internal state of this controller instance */
-	int op_state;
-};
-
 /*
  * The following are the structures to provide for a generic
  * or abstract 'edac_device'. This set of structures and the

358 lines not on this page · raw message

index 3d96534..ef0738b 100644
@@ -34,11 +34,10 @@
 #include <linux/platform_device.h>
 #include <linux/sysdev.h>
 #include <linux/workqueue.h>
+#include <linux/edac.h>
 
-#define EDAC_MC_LABEL_LEN	31
 #define EDAC_DEVICE_NAME_LEN	31
 #define EDAC_ATTRIB_VALUE_LEN	15
-#define MC_PROC_NAME_MAX_LEN	7
 
 #if PAGE_SHIFT < 20
 #define PAGES_TO_MiB(pages)	((pages) >> (20 - PAGE_SHIFT))

@@ -101,357 +100,6 @@ extern int edac_debug_level;
 
 #define edac_dev_name(dev) (dev)->dev_name
 
-/* memory devices */
-enum dev_type {
-	DEV_UNKNOWN = 0,
-	DEV_X1,
-	DEV_X2,
-	DEV_X4,
-	DEV_X8,
-	DEV_X16,
-	DEV_X32,		/* Do these parts exist? */
-	DEV_X64			/* Do these parts exist? */
-};
-
-#define DEV_FLAG_UNKNOWN	BIT(DEV_UNKNOWN)
-#define DEV_FLAG_X1		BIT(DEV_X1)
-#define DEV_FLAG_X2		BIT(DEV_X2)
-#define DEV_FLAG_X4		BIT(DEV_X4)
-#define DEV_FLAG_X8		BIT(DEV_X8)
-#define DEV_FLAG_X16		BIT(DEV_X16)
-#define DEV_FLAG_X32		BIT(DEV_X32)
-#define DEV_FLAG_X64		BIT(DEV_X64)
-
-/* memory types */
-enum mem_type {
-	MEM_EMPTY = 0,		/* Empty csrow */
-	MEM_RESERVED,		/* Reserved csrow type */
-	MEM_UNKNOWN,		/* Unknown csrow type */
-	MEM_FPM,		/* Fast page mode */
-	MEM_EDO,		/* Extended data out */
-	MEM_BEDO,		/* Burst Extended data out */
-	MEM_SDR,		/* Single data rate SDRAM */
-	MEM_RDR,		/* Registered single data rate SDRAM */
-	MEM_DDR,		/* Double data rate SDRAM */
-	MEM_RDDR,		/* Registered Double data rate SDRAM */
-	MEM_RMBS,		/* Rambus DRAM */
-	MEM_DDR2,		/* DDR2 RAM */
-	MEM_FB_DDR2,		/* fully buffered DDR2 */
-	MEM_RDDR2,		/* Registered DDR2 RAM */
-	MEM_XDR,		/* Rambus XDR */
-	MEM_DDR3,		/* DDR3 RAM */
-	MEM_RDDR3,		/* Registered DDR3 RAM */
-};
-
-#define MEM_FLAG_EMPTY		BIT(MEM_EMPTY)
-#define MEM_FLAG_RESERVED	BIT(MEM_RESERVED)
-#define MEM_FLAG_UNKNOWN	BIT(MEM_UNKNOWN)
-#define MEM_FLAG_FPM		BIT(MEM_FPM)
-#define MEM_FLAG_EDO		BIT(MEM_EDO)
-#define MEM_FLAG_BEDO		BIT(MEM_BEDO)
-#define MEM_FLAG_SDR		BIT(MEM_SDR)
-#define MEM_FLAG_RDR		BIT(MEM_RDR)
-#define MEM_FLAG_DDR		BIT(MEM_DDR)
-#define MEM_FLAG_RDDR		BIT(MEM_RDDR)
-#define MEM_FLAG_RMBS		BIT(MEM_RMBS)
-#define MEM_FLAG_DDR2           BIT(MEM_DDR2)
-#define MEM_FLAG_FB_DDR2        BIT(MEM_FB_DDR2)
-#define MEM_FLAG_RDDR2          BIT(MEM_RDDR2)
-#define MEM_FLAG_XDR            BIT(MEM_XDR)
-#define MEM_FLAG_DDR3		 BIT(MEM_DDR3)
-#define MEM_FLAG_RDDR3		 BIT(MEM_RDDR3)
-
-/* chipset Error Detection and Correction capabilities and mode */
-enum edac_type {
-	EDAC_UNKNOWN = 0,	/* Unknown if ECC is available */
-	EDAC_NONE,		/* Doesnt support ECC */
-	EDAC_RESERVED,		/* Reserved ECC type */
-	EDAC_PARITY,		/* Detects parity errors */
-	EDAC_EC,		/* Error Checking - no correction */
-	EDAC_SECDED,		/* Single bit error correction, Double detection */
-	EDAC_S2ECD2ED,		/* Chipkill x2 devices - do these exist? */
-	EDAC_S4ECD4ED,		/* Chipkill x4 devices */
-	EDAC_S8ECD8ED,		/* Chipkill x8 devices */
-	EDAC_S16ECD16ED,	/* Chipkill x16 devices */
-};
-
-#define EDAC_FLAG_UNKNOWN	BIT(EDAC_UNKNOWN)
-#define EDAC_FLAG_NONE		BIT(EDAC_NONE)
-#define EDAC_FLAG_PARITY	BIT(EDAC_PARITY)
-#define EDAC_FLAG_EC		BIT(EDAC_EC)
-#define EDAC_FLAG_SECDED	BIT(EDAC_SECDED)
-#define EDAC_FLAG_S2ECD2ED	BIT(EDAC_S2ECD2ED)
-#define EDAC_FLAG_S4ECD4ED	BIT(EDAC_S4ECD4ED)
-#define EDAC_FLAG_S8ECD8ED	BIT(EDAC_S8ECD8ED)
-#define EDAC_FLAG_S16ECD16ED	BIT(EDAC_S16ECD16ED)
-
-/* scrubbing capabilities */
-enum scrub_type {
-	SCRUB_UNKNOWN = 0,	/* Unknown if scrubber is available */
-	SCRUB_NONE,		/* No scrubber */
-	SCRUB_SW_PROG,		/* SW progressive (sequential) scrubbing */
-	SCRUB_SW_SRC,		/* Software scrub only errors */
-	SCRUB_SW_PROG_SRC,	/* Progressive software scrub from an error */
-	SCRUB_SW_TUNABLE,	/* Software scrub frequency is tunable */
-	SCRUB_HW_PROG,		/* HW progressive (sequential) scrubbing */
-	SCRUB_HW_SRC,		/* Hardware scrub only errors */
-	SCRUB_HW_PROG_SRC,	/* Progressive hardware scrub from an error */
-	SCRUB_HW_TUNABLE	/* Hardware scrub frequency is tunable */
-};
-
-#define SCRUB_FLAG_SW_PROG	BIT(SCRUB_SW_PROG)
-#define SCRUB_FLAG_SW_SRC	BIT(SCRUB_SW_SRC)
-#define SCRUB_FLAG_SW_PROG_SRC	BIT(SCRUB_SW_PROG_SRC)
-#define SCRUB_FLAG_SW_TUN	BIT(SCRUB_SW_SCRUB_TUNABLE)
-#define SCRUB_FLAG_HW_PROG	BIT(SCRUB_HW_PROG)
-#define SCRUB_FLAG_HW_SRC	BIT(SCRUB_HW_SRC)
-#define SCRUB_FLAG_HW_PROG_SRC	BIT(SCRUB_HW_PROG_SRC)
-#define SCRUB_FLAG_HW_TUN	BIT(SCRUB_HW_TUNABLE)
-
-/* FIXME - should have notify capabilities: NMI, LOG, PROC, etc */
-
-/* EDAC internal operation states */
-#define	OP_ALLOC		0x100
-#define OP_RUNNING_POLL		0x201
-#define OP_RUNNING_INTERRUPT	0x202
-#define OP_RUNNING_POLL_INTR	0x203
-#define OP_OFFLINE		0x300
-
-/*
- * There are several things to be aware of that aren't at all obvious:
- *
- *
- * SOCKETS, SOCKET SETS, BANKS, ROWS, CHIP-SELECT ROWS, CHANNELS, etc..
- *
- * These are some of the many terms that are thrown about that don't always
- * mean what people think they mean (Inconceivable!).  In the interest of
- * creating a common ground for discussion, terms and their definitions
- * will be established.
- *
- * Memory devices:	The individual chip on a memory stick.  These devices
- *			commonly output 4 and 8 bits each.  Grouping several
- *			of these in parallel provides 64 bits which is common
- *			for a memory stick.
- *
- * Memory Stick:	A printed circuit board that agregates multiple
- *			memory devices in parallel.  This is the atomic
- *			memory component that is purchaseable by Joe consumer
- *			and loaded into a memory socket.
- *
- * Socket:		A physical connector on the motherboard that accepts
- *			a single memory stick.
- *
- * Channel:		Set of memory devices on a memory stick that must be
- *			grouped in parallel with one or more additional
- *			channels from other memory sticks.  This parallel
- *			grouping of the output from multiple channels are
- *			necessary for the smallest granularity of memory access.
- *			Some memory controllers are capable of single channel -
- *			which means that memory sticks can be loaded
- *			individually.  Other memory controllers are only
- *			capable of dual channel - which means that memory
- *			sticks must be loaded as pairs (see "socket set").
- *
- * Chip-select row:	All of the memory devices that are selected together.
- *			for a single, minimum grain of memory access.
- *			This selects all of the parallel memory devices across
- *			all of the parallel channels.  Common chip-select rows
- *			for single channel are 64 bits, for dual channel 128
- *			bits.
- *
- * Single-Ranked stick:	A Single-ranked stick has 1 chip-select row of memory.
- *			Motherboards commonly drive two chip-select pins to
- *			a memory stick. A single-ranked stick, will occupy
- *			only one of those rows. The other will be unused.
- *
- * Double-Ranked stick:	A double-ranked stick has two chip-select rows which
- *			access different sets of memory devices.  The two
- *			rows cannot be accessed concurrently.
- *
- * Double-sided stick:	DEPRECATED TERM, see Double-Ranked stick.
- *			A double-sided stick has two chip-select rows which
- *			access different sets of memory devices.  The two
- *			rows cannot be accessed concurrently.  "Double-sided"
- *			is irrespective of the memory devices being mounted
- *			on both sides of the memory stick.
- *
- * Socket set:		All of the memory sticks that are required for
- *			a single memory access or all of the memory sticks
- *			spanned by a chip-select row.  A single socket set
- *			has two chip-select rows and if double-sided sticks
- *			are used these will occupy those chip-select rows.
- *
- * Bank:		This term is avoided because it is unclear when
- *			needing to distinguish between chip-select rows and
- *			socket sets.
- *
- * Controller pages:
- *
- * Physical pages:
- *
- * Virtual pages:
- *
- *
- * STRUCTURE ORGANIZATION AND CHOICES
- *
- *
- *
- * PS - I enjoyed writing all that about as much as you enjoyed reading it.
- */
-
-struct channel_info {
-	int chan_idx;		/* channel index */
-	u32 ce_count;		/* Correctable Errors for this CHANNEL */
-	char label[EDAC_MC_LABEL_LEN + 1];	/* DIMM label on motherboard */
-	struct csrow_info *csrow;	/* the parent */
-};
-
-struct csrow_info {
-	unsigned long first_page;	/* first page number in dimm */
-	unsigned long last_page;	/* last page number in dimm */
-	unsigned long page_mask;	/* used for interleaving -
-					 * 0UL for non intlv
-					 */
-	u32 nr_pages;		/* number of pages in csrow */
-	u32 grain;		/* granularity of reported error in bytes */
-	int csrow_idx;		/* the chip-select row */
-	enum dev_type dtype;	/* memory device type */
-	u32 ue_count;		/* Uncorrectable Errors for this csrow */
-	u32 ce_count;		/* Correctable Errors for this csrow */
-	enum mem_type mtype;	/* memory csrow type */
-	enum edac_type edac_mode;	/* EDAC mode for this csrow */
-	struct mem_ctl_info *mci;	/* the parent */
-
-	struct kobject kobj;	/* sysfs kobject for this csrow */
-
-	/* channel information for this csrow */
-	u32 nr_channels;
-	struct channel_info *channels;
-};
-
-struct mcidev_sysfs_group {
-	const char *name;				/* group name */
-	const struct mcidev_sysfs_attribute *mcidev_attr; /* group attributes */
-};
-
-struct mcidev_sysfs_group_kobj {
-	struct list_head list;		/* list for all instances within a mc */
-
-	struct kobject kobj;		/* kobj for the group */
-
-	const struct mcidev_sysfs_group *grp;	/* group description table */
-	struct mem_ctl_info *mci;	/* the parent */
-};
-
-/* mcidev_sysfs_attribute structure
- *	used for driver sysfs attributes and in mem_ctl_info
- * 	sysfs top level entries
- */
-struct mcidev_sysfs_attribute {
-	/* It should use either attr or grp */
-	struct attribute attr;
-	const struct mcidev_sysfs_group *grp;	/* Points to a group of attributes */
-
-	/* Ops for show/store values at the attribute - not used on group */
-        ssize_t (*show)(struct mem_ctl_info *,char *);
-        ssize_t (*store)(struct mem_ctl_info *, const char *,size_t);
-};
-
-/* MEMORY controller information structure
- */
-struct mem_ctl_info {
-	struct list_head link;	/* for global list of mem_ctl_info structs */
-
-	struct module *owner;	/* Module owner of this control struct */
-
-	unsigned long mtype_cap;	/* memory types supported by mc */
-	unsigned long edac_ctl_cap;	/* Mem controller EDAC capabilities */
-	unsigned long edac_cap;	/* configuration capabilities - this is
-				 * closely related to edac_ctl_cap.  The
-				 * difference is that the controller may be
-				 * capable of s4ecd4ed which would be listed
-				 * in edac_ctl_cap, but if channels aren't
-				 * capable of s4ecd4ed then the edac_cap would
-				 * not have that capability.
-				 */
-	unsigned long scrub_cap;	/* chipset scrub capabilities */
-	enum scrub_type scrub_mode;	/* current scrub mode */
-
-	/* Translates sdram memory scrub rate given in bytes/sec to the
-	   internal representation and configures whatever else needs
-	   to be configured.
-	 */
-	int (*set_sdram_scrub_rate) (struct mem_ctl_info * mci, u32 bw);
-
-	/* Get the current sdram memory scrub rate from the internal
-	   representation and converts it to the closest matching
-	   bandwith in bytes/sec.
-	 */
-	int (*get_sdram_scrub_rate) (struct mem_ctl_info * mci);
-
-
-	/* pointer to edac checking routine */
-	void (*edac_check) (struct mem_ctl_info * mci);
-
-	/*
-	 * Remaps memory pages: controller pages to physical pages.
-	 * For most MC's, this will be NULL.
-	 */
-	/* FIXME - why not send the phys page to begin with? */
-	unsigned long (*ctl_page_to_phys) (struct mem_ctl_info * mci,
-					   unsigned long page);
-	int mc_idx;
-	int nr_csrows;
-	struct csrow_info *csrows;
-	/*
-	 * FIXME - what about controllers on other busses? - IDs must be
-	 * unique.  dev pointer should be sufficiently unique, but
-	 * BUS:SLOT.FUNC numbers may not be unique.
-	 */
-	struct device *dev;
-	const char *mod_name;
-	const char *mod_ver;
-	const char *ctl_name;
-	const char *dev_name;
-	char proc_name[MC_PROC_NAME_MAX_LEN + 1];
-	void *pvt_info;
-	u32 ue_noinfo_count;	/* Uncorrectable Errors w/o info */
-	u32 ce_noinfo_count;	/* Correctable Errors w/o info */
-	u32 ue_count;		/* Total Uncorrectable Errors for this MC */
-	u32 ce_count;		/* Total Correctable Errors for this MC */
-	unsigned long start_time;	/* mci load start time (in jiffies) */
-
-	/* this stuff is for safe removal of mc devices from global list while
-	 * NMI handlers may be traversing list
-	 */
-	struct rcu_head rcu;
-	struct completion complete;
-
-	/* edac sysfs device control */
-	struct kobject edac_mci_kobj;
-
-	/* list for all grp instances within a mc */
-	struct list_head grp_kobj_list;
-
-	/* Additional top controller level attributes, but specified
-	 * by the low level driver.
-	 *
-	 * Set by the low level driver to provide attributes at the
-	 * controller level, same level as 'ue_count' and 'ce_count' above.
-	 * An array of structures, NULL terminated
-	 *
-	 * If attributes are desired, then set to array of attributes
-	 * If no attributes are desired, leave NULL
-	 */
-	const struct mcidev_sysfs_attribute *mc_driver_sysfs_attributes;
-
-	/* work struct for this MC */
-	struct delayed_work work;
-
-	/* the internal state of this controller instance */
-	int op_state;
-};
-
 /*
  * The following are the structures to provide for a generic
  * or abstract 'edac_device'. This set of structures and the

358 lines not on this page · raw message

index a4e9db2..12821ef 100644
@@ -34,6 +34,9 @@
 #include "edac_core.h"
 #include "edac_module.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/hw_event.h>
+
 /* lock to memory controller's control array */
 static DEFINE_MUTEX(mem_ctls_mutex);
 static LIST_HEAD(mc_devices);

@@ -224,6 +227,9 @@ struct mem_ctl_info *edac_mc_alloc(unsigned sz_pvt, unsigned nr_csrows,
 	 * which will perform kobj unregistration and the actual free
 	 * will occur during the kobject callback operation
 	 */
+
+	trace_hw_event_init("mce", (unsigned)edac_index);
+
 	return mci;
 }
 EXPORT_SYMBOL_GPL(edac_mc_alloc);

@@ -689,6 +695,7 @@ void edac_mc_handle_ce(struct mem_ctl_info *mci,
 	/* FIXME - maybe make panic on INTERNAL ERROR an option */
 	if (row >= mci->nr_csrows || row < 0) {
 		/* something is wrong */
+		trace_mc_out_of_range(mci, "CE", "row", row, 0, mci->nr_csrows);
 		edac_mc_printk(mci, KERN_ERR,
 			"INTERNAL ERROR: row out of range "
 			"(%d >= %d)\n", row, mci->nr_csrows);

@@ -698,6 +705,8 @@ void edac_mc_handle_ce(struct mem_ctl_info *mci,
 
 	if (channel >= mci->csrows[row].nr_channels || channel < 0) {
 		/* something is wrong */
+		trace_mc_out_of_range(mci, "CE", "channel", channel,
+				      0, mci->csrows[row].nr_channels);
 		edac_mc_printk(mci, KERN_ERR,
 			"INTERNAL ERROR: channel out of range "
 			"(%d >= %d)\n", channel,

@@ -706,6 +715,9 @@ void edac_mc_handle_ce(struct mem_ctl_info *mci,
 		return;
 	}
 
+	trace_mc_corrected_error(mci, page_frame_number, offset_in_page,
+				syndrome, row, channel, msg);
+
 	if (edac_mc_get_log_ce())
 		/* FIXME - put in DIMM location */
 		edac_mc_printk(mci, KERN_WARNING,

@@ -741,6 +753,7 @@ EXPORT_SYMBOL_GPL(edac_mc_handle_ce);
 
 void edac_mc_handle_ce_no_info(struct mem_ctl_info *mci, const char *msg)
 {
+	trace_mc_corrected_error_no_info(mci, msg);
 	if (edac_mc_get_log_ce())
 		edac_mc_printk(mci, KERN_WARNING,
 			"CE - no information available: %s\n", msg);

@@ -765,6 +778,8 @@ void edac_mc_handle_ue(struct mem_ctl_info *mci,
 	/* FIXME - maybe make panic on INTERNAL ERROR an option */
 	if (row >= mci->nr_csrows || row < 0) {
 		/* something is wrong */
+		trace_mc_out_of_range(mci, "UE", "row", row,
+				      0, mci->nr_csrows);
 		edac_mc_printk(mci, KERN_ERR,
 			"INTERNAL ERROR: row out of range "
 			"(%d >= %d)\n", row, mci->nr_csrows);

@@ -785,6 +800,8 @@ void edac_mc_handle_ue(struct mem_ctl_info *mci,
 		pos += chars;
 	}
 
+	trace_mc_uncorrected_error(mci, page_frame_number, offset_in_page,
+				row, msg, labels);
 	if (edac_mc_get_log_ue())
 		edac_mc_printk(mci, KERN_EMERG,
 			"UE page 0x%lx, offset 0x%lx, grain %d, row %d, "

@@ -805,6 +822,7 @@ EXPORT_SYMBOL_GPL(edac_mc_handle_ue);
 
 void edac_mc_handle_ue_no_info(struct mem_ctl_info *mci, const char *msg)
 {
+	trace_mc_uncorrected_error_no_info(mci, msg);
 	if (edac_mc_get_panic_on_ue())
 		panic("EDAC MC%d: Uncorrected Error", mci->mc_idx);
 

@@ -832,6 +850,9 @@ void edac_mc_handle_fbd_ue(struct mem_ctl_info *mci,
 
 	if (csrow >= mci->nr_csrows) {
 		/* something is wrong */
+
+		trace_mc_out_of_range(mci, "UE FBDIMM", "row", csrow,
+				      0, mci->nr_csrows);
 		edac_mc_printk(mci, KERN_ERR,
 			"INTERNAL ERROR: row out of range (%d >= %d)\n",
 			csrow, mci->nr_csrows);

@@ -841,6 +862,8 @@ void edac_mc_handle_fbd_ue(struct mem_ctl_info *mci,
 
 	if (channela >= mci->csrows[csrow].nr_channels) {
 		/* something is wrong */
+		trace_mc_out_of_range(mci, "UE FBDIMM", "channel-a", channela,
+				      0, mci->csrows[csrow].nr_channels);
 		edac_mc_printk(mci, KERN_ERR,
 			"INTERNAL ERROR: channel-a out of range "
 			"(%d >= %d)\n",

@@ -851,6 +874,8 @@ void edac_mc_handle_fbd_ue(struct mem_ctl_info *mci,
 
 	if (channelb >= mci->csrows[csrow].nr_channels) {
 		/* something is wrong */
+		trace_mc_out_of_range(mci, "UE FBDIMM", "channel-b", channelb,
+				      0, mci->csrows[csrow].nr_channels);
 		edac_mc_printk(mci, KERN_ERR,
 			"INTERNAL ERROR: channel-b out of range "
 			"(%d >= %d)\n",

@@ -870,6 +895,8 @@ void edac_mc_handle_fbd_ue(struct mem_ctl_info *mci,
 	chars = snprintf(pos, len + 1, "-%s",
 			 mci->csrows[csrow].channels[channelb].label);
 
+	trace_mc_uncorrected_error_fbd(mci, csrow, channela, channelb,
+				       msg, labels);
 	if (edac_mc_get_log_ue())
 		edac_mc_printk(mci, KERN_EMERG,
 			"UE row %d, channel-a= %d channel-b= %d "

@@ -894,6 +921,8 @@ void edac_mc_handle_fbd_ce(struct mem_ctl_info *mci,
 	/* Ensure boundary values */
 	if (csrow >= mci->nr_csrows) {
 		/* something is wrong */
+		trace_mc_out_of_range(mci, "CE FBDIMM", "row", csrow,
+				      0, mci->nr_csrows);
 		edac_mc_printk(mci, KERN_ERR,
 			"INTERNAL ERROR: row out of range (%d >= %d)\n",
 			csrow, mci->nr_csrows);

@@ -902,6 +931,8 @@ void edac_mc_handle_fbd_ce(struct mem_ctl_info *mci,
 	}
 	if (channel >= mci->csrows[csrow].nr_channels) {
 		/* something is wrong */
+		trace_mc_out_of_range(mci, "UE FBDIMM", "channel", channel,
+				      0, mci->csrows[csrow].nr_channels);
 		edac_mc_printk(mci, KERN_ERR,
 			"INTERNAL ERROR: channel out of range (%d >= %d)\n",
 			channel, mci->csrows[csrow].nr_channels);

@@ -909,6 +940,7 @@ void edac_mc_handle_fbd_ce(struct mem_ctl_info *mci,
 		return;
 	}
 
+	trace_mc_corrected_error_fbd(mci, csrow, channel, msg);
 	if (edac_mc_get_log_ce())
 		/* FIXME - put in DIMM location */
 		edac_mc_printk(mci, KERN_WARNING,

322 lines not on this page · raw message

index d69144a..2b8382e 100644
@@ -34,6 +34,9 @@
 #include "edac_core.h"
 #include "edac_module.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/hw_event.h>
+
 /* lock to memory controller's control array */
 static DEFINE_MUTEX(mem_ctls_mutex);
 static LIST_HEAD(mc_devices);

@@ -224,6 +227,9 @@ struct mem_ctl_info *edac_mc_alloc(unsigned sz_pvt, unsigned nr_csrows,
 	 * which will perform kobj unregistration and the actual free
 	 * will occur during the kobject callback operation
 	 */
+
+	trace_hw_event_init("mce", (unsigned)edac_index);
+
 	return mci;
 }
 EXPORT_SYMBOL_GPL(edac_mc_alloc);

@@ -685,6 +691,7 @@ void edac_mc_handle_ce(struct mem_ctl_info *mci,
 	/* FIXME - maybe make panic on INTERNAL ERROR an option */
 	if (row >= mci->nr_csrows || row < 0) {
 		/* something is wrong */
+		trace_mc_out_of_range(mci, "CE", "row", row, 0, mci->nr_csrows);
 		edac_mc_printk(mci, KERN_ERR,
 			"INTERNAL ERROR: row out of range "
 			"(%d >= %d)\n", row, mci->nr_csrows);

@@ -694,6 +701,8 @@ void edac_mc_handle_ce(struct mem_ctl_info *mci,
 
 	if (channel >= mci->csrows[row].nr_channels || channel < 0) {
 		/* something is wrong */
+		trace_mc_out_of_range(mci, "CE", "channel", channel,
+				      0, mci->csrows[row].nr_channels);
 		edac_mc_printk(mci, KERN_ERR,
 			"INTERNAL ERROR: channel out of range "
 			"(%d >= %d)\n", channel,

@@ -702,6 +711,9 @@ void edac_mc_handle_ce(struct mem_ctl_info *mci,
 		return;
 	}
 
+	trace_mc_corrected_error(mci, page_frame_number, offset_in_page,
+				syndrome, row, channel, msg);
+
 	if (edac_mc_get_log_ce())
 		/* FIXME - put in DIMM location */
 		edac_mc_printk(mci, KERN_WARNING,

@@ -737,6 +749,7 @@ EXPORT_SYMBOL_GPL(edac_mc_handle_ce);
 
 void edac_mc_handle_ce_no_info(struct mem_ctl_info *mci, const char *msg)
 {
+	trace_mc_corrected_error_no_info(mci, msg);
 	if (edac_mc_get_log_ce())
 		edac_mc_printk(mci, KERN_WARNING,
 			"CE - no information available: %s\n", msg);

@@ -761,6 +774,8 @@ void edac_mc_handle_ue(struct mem_ctl_info *mci,
 	/* FIXME - maybe make panic on INTERNAL ERROR an option */
 	if (row >= mci->nr_csrows || row < 0) {
 		/* something is wrong */
+		trace_mc_out_of_range(mci, "UE", "row", row,
+				      0, mci->nr_csrows);
 		edac_mc_printk(mci, KERN_ERR,
 			"INTERNAL ERROR: row out of range "
 			"(%d >= %d)\n", row, mci->nr_csrows);

@@ -781,6 +796,8 @@ void edac_mc_handle_ue(struct mem_ctl_info *mci,
 		pos += chars;
 	}
 
+	trace_mc_uncorrected_error(mci, page_frame_number, offset_in_page,
+				row, msg, labels);
 	if (edac_mc_get_log_ue())
 		edac_mc_printk(mci, KERN_EMERG,
 			"UE page 0x%lx, offset 0x%lx, grain %d, row %d, "

@@ -801,6 +818,7 @@ EXPORT_SYMBOL_GPL(edac_mc_handle_ue);
 
 void edac_mc_handle_ue_no_info(struct mem_ctl_info *mci, const char *msg)
 {
+	trace_mc_uncorrected_error_no_info(mci, msg);
 	if (edac_mc_get_panic_on_ue())
 		panic("EDAC MC%d: Uncorrected Error", mci->mc_idx);
 

@@ -828,6 +846,9 @@ void edac_mc_handle_fbd_ue(struct mem_ctl_info *mci,
 
 	if (csrow >= mci->nr_csrows) {
 		/* something is wrong */
+
+		trace_mc_out_of_range(mci, "UE FBDIMM", "row", csrow,
+				      0, mci->nr_csrows);
 		edac_mc_printk(mci, KERN_ERR,
 			"INTERNAL ERROR: row out of range (%d >= %d)\n",
 			csrow, mci->nr_csrows);

@@ -837,6 +858,8 @@ void edac_mc_handle_fbd_ue(struct mem_ctl_info *mci,
 
 	if (channela >= mci->csrows[csrow].nr_channels) {
 		/* something is wrong */
+		trace_mc_out_of_range(mci, "UE FBDIMM", "channel-a", channela,
+				      0, mci->csrows[csrow].nr_channels);
 		edac_mc_printk(mci, KERN_ERR,
 			"INTERNAL ERROR: channel-a out of range "
 			"(%d >= %d)\n",

@@ -847,6 +870,8 @@ void edac_mc_handle_fbd_ue(struct mem_ctl_info *mci,
 
 	if (channelb >= mci->csrows[csrow].nr_channels) {
 		/* something is wrong */
+		trace_mc_out_of_range(mci, "UE FBDIMM", "channel-b", channelb,
+				      0, mci->csrows[csrow].nr_channels);
 		edac_mc_printk(mci, KERN_ERR,
 			"INTERNAL ERROR: channel-b out of range "
 			"(%d >= %d)\n",

@@ -866,6 +891,8 @@ void edac_mc_handle_fbd_ue(struct mem_ctl_info *mci,
 	chars = snprintf(pos, len + 1, "-%s",
 			 mci->csrows[csrow].channels[channelb].label);
 
+	trace_mc_uncorrected_error_fbd(mci, csrow, channela, channelb,
+				       msg, labels);
 	if (edac_mc_get_log_ue())
 		edac_mc_printk(mci, KERN_EMERG,
 			"UE row %d, channel-a= %d channel-b= %d "

@@ -890,6 +917,8 @@ void edac_mc_handle_fbd_ce(struct mem_ctl_info *mci,
 	/* Ensure boundary values */
 	if (csrow >= mci->nr_csrows) {
 		/* something is wrong */
+		trace_mc_out_of_range(mci, "CE FBDIMM", "row", csrow,
+				      0, mci->nr_csrows);
 		edac_mc_printk(mci, KERN_ERR,
 			"INTERNAL ERROR: row out of range (%d >= %d)\n",
 			csrow, mci->nr_csrows);

@@ -898,6 +927,8 @@ void edac_mc_handle_fbd_ce(struct mem_ctl_info *mci,
 	}
 	if (channel >= mci->csrows[csrow].nr_channels) {
 		/* something is wrong */
+		trace_mc_out_of_range(mci, "UE FBDIMM", "channel", channel,
+				      0, mci->csrows[csrow].nr_channels);
 		edac_mc_printk(mci, KERN_ERR,
 			"INTERNAL ERROR: channel out of range (%d >= %d)\n",
 			channel, mci->csrows[csrow].nr_channels);

@@ -905,6 +936,7 @@ void edac_mc_handle_fbd_ce(struct mem_ctl_info *mci,
 		return;
 	}
 
+	trace_mc_corrected_error_fbd(mci, csrow, channel, msg);
 	if (edac_mc_get_log_ce())
 		/* FIXME - put in DIMM location */
 		edac_mc_printk(mci, KERN_WARNING,

322 lines not on this page · raw message

index a46ac61..85fca0d 100644
@@ -20,17 +20,17 @@ DECLARE_EVENT_CLASS(hw_event_class,
 	TP_ARGS(type, instance),
 
 	TP_STRUCT__entry(
-		__field(	const char *,	type			)
+		__string(	type,		type			)
 		__field(	unsigned int,	instance		)
 	),
 
 	TP_fast_assign(
-		__entry->type	= type;
+		__assign_str(type, type);
 		__entry->instance = instance;
 	),
 
 	TP_printk("Initialized %s#%d\n",
-		__entry->type,
+		__get_str(type),
 		__entry->instance)
 );
 

@@ -70,8 +70,8 @@ TRACE_EVENT(mc_corrected_error,
 		__field(	unsigned long,	syndrome		)
 		__field(	int,		row			)
 		__field(	int,		channel			)
-		__field(	const char *,	label			)
-		__field(	const char *,	msg			)
+		__string(	label,		mci->csrows[row].channels[channel].label)
+		__string(	msg,		msg			)
 	),
 
 	TP_fast_assign(

@@ -82,16 +82,16 @@ TRACE_EVENT(mc_corrected_error,
 		__entry->syndrome		= syndrome;
 		__entry->row			= row;
 		__entry->channel		= channel;
-		__entry->label			= mci->csrows[row].channels[channel].label;
-		__entry->msg			= msg;
+		__assign_str(label, mci->csrows[row].channels[channel].label);
+		__assign_str(msg, msg);
 	),
 
 	TP_printk(HW_ERR "mce#%d: Corrected error %s on label \"%s\" "
 			 "(page 0x%lux, offset 0x%lux, grain %ud, "
 			 "syndrome 0x%lux, row %d, channel %d)\n",
 		__entry->mc_index,
-		__entry->msg,
-		__entry->label,
+		__get_str(msg),
+		__get_str(label),
 		__entry->page_frame_number,
 		__entry->offset_in_page,
 		__entry->grain,

@@ -116,8 +116,8 @@ TRACE_EVENT(mc_uncorrected_error,
 		__field(	unsigned long,	offset_in_page		)
 		__field(	u32,		grain			)
 		__field(	int,		row			)
-		__field(	const char *,	msg			)
-		__field(	const char *,	label			)
+		__string(	msg,		msg			)
+		__string(	label,		label			)
 	),
 
 	TP_fast_assign(

@@ -126,15 +126,15 @@ TRACE_EVENT(mc_uncorrected_error,
 		__entry->offset_in_page		= offset_in_page;
 		__entry->grain			= mci->csrows[row].grain;
 		__entry->row			= row;
-		__entry->msg			= msg;
-		__entry->label			= label;
+		__assign_str(msg, msg);
+		__assign_str(label, label);
 	),
 
 	TP_printk(HW_ERR "mce#%d: Uncorrected error %s on label \"%s\""
 			 "(page 0x%lux, offset 0x%lux, grain %ud, row %d)\n",
 		__entry->mc_index,
-		__entry->msg,
-		__entry->label,
+		__get_str(msg),
+		__get_str(label),
 		__entry->page_frame_number,
 		__entry->offset_in_page,
 		__entry->grain,

@@ -160,23 +160,23 @@ TRACE_EVENT(mc_corrected_error_fbd,
 		__field(	unsigned int,	mc_index		)
 		__field(	int,		row			)
 		__field(	int,		channel	        	)
-		__field(	const char *,	label			)
-		__field(	const char *,	msg			)
+		__string(	label,		mci->csrows[row].channels[channel].label)
+		__string(	msg,		msg			)
 	),
 
 	TP_fast_assign(
 		__entry->mc_index		= mci->mc_idx;
 		__entry->row			= row;
 		__entry->channel		= channel;
-		__entry->label			= mci->csrows[row].channels[channel].label;
-		__entry->msg			= msg;
+		__assign_str(label, mci->csrows[row].channels[channel].label);
+		__assign_str(msg, msg);
 	),
 
 	TP_printk(HW_ERR "mce#%d: Corrected Error %s on label \"%s\" "
 			 "(row %d, channel %d)\n",
 		__entry->mc_index,
-		__entry->msg,
-		__entry->label,
+		__get_str(msg),
+		__get_str(label),
 		__entry->row,
 		__entry->channel)
 );

@@ -194,8 +194,8 @@ TRACE_EVENT(mc_uncorrected_error_fbd,
 		__field(	int,		row			)
 		__field(	int,		channela		)
 		__field(	int,		channelb		)
-		__field(	const char *,	msg			)
-		__field(	const char *,	label			)
+		__string(	msg,		msg			)
+		__string(	label,		label			)
 	),
 
 	TP_fast_assign(

@@ -203,15 +203,15 @@ TRACE_EVENT(mc_uncorrected_error_fbd,
 		__entry->row			= row;
 		__entry->channela		= channela;
 		__entry->channelb		= channelb;
-		__entry->msg			= msg;
-		__entry->label			= label;
+		__assign_str(msg, msg);
+		__assign_str(label, label);
 	),
 
 	TP_printk(HW_ERR "mce#%d: Uncorrected Error %s on label \"%s\" "
 			 "(row %d, channels: %d, %d)\n",
 		__entry->mc_index,
-		__entry->msg,
-		__entry->label,
+		__get_str(msg),
+		__get_str(label),
 		__entry->row,
 		__entry->channela,
 		__entry->channelb)

@@ -236,8 +236,8 @@ TRACE_EVENT(mc_out_of_range,
 	TP_ARGS(mci, type, field, invalid_val, min, max),
 
 	TP_STRUCT__entry(
-		__field(	const char *,	type			)
-		__field(	const char *,	field			)
+		__string(	type,		type			)
+		__string(	field,		field			)
 		__field(	unsigned int,	mc_index		)
 		__field(	int,		invalid_val		)
 		__field(	int,		min			)

@@ -245,8 +245,8 @@ TRACE_EVENT(mc_out_of_range,
 	),
 
 	TP_fast_assign(
-		__entry->type			= type;
-		__entry->field			= field;
+		__assign_str(type, type);
+		__assign_str(field, field);
 		__entry->mc_index		= mci->mc_idx;
 		__entry->invalid_val		= invalid_val;
 		__entry->min			= min;

@@ -255,8 +255,8 @@ TRACE_EVENT(mc_out_of_range,
 
 	TP_printk(HW_ERR "mce#%d %s: %s=%d is not between %d and %d\n",
 		__entry->mc_index,
-		__entry->type,
-		__entry->field,
+		__get_str(type),
+		__get_str(field),
 		__entry->invalid_val,
 		__entry->min,
 		__entry->max)

@@ -274,18 +274,18 @@ TRACE_EVENT(mc_corrected_error_no_info,
 	TP_ARGS(mci, msg),
 
 	TP_STRUCT__entry(
-		__field(	const char *,	msg			)
+	__string(	msg,			msg			)
 		__field(	unsigned int,	mc_index		)
 	),
 
 	TP_fast_assign(
-		__entry->msg			= msg;
+		__assign_str(msg, msg);
 		__entry->mc_index		= mci->mc_idx;
 	),
 
 	TP_printk(HW_ERR "mce#%d: Corrected Error: %s\n",
 		__entry->mc_index,
-		__entry->msg)
+		__get_str(msg))
 );
 
 TRACE_EVENT(mc_uncorrected_error_no_info,

@@ -294,18 +294,18 @@ TRACE_EVENT(mc_uncorrected_error_no_info,
 	TP_ARGS(mci, msg),
 
 	TP_STRUCT__entry(
-		__field(	const char *,	msg			)
+		__string(	msg,		msg			)
 		__field(	unsigned int,	mc_index		)
 	),
 
 	TP_fast_assign(
-		__entry->msg			= msg;
+		__assign_str(msg, msg);
 		__entry->mc_index		= mci->mc_idx;
 	),
 
 	TP_printk(HW_ERR "mce#%d: Uncorrected Error: %s\n",
 		__entry->mc_index,
-		__entry->msg)
+		__get_str(msg))
 );
 
 

index 2b8382e..5038239 100644
@@ -685,6 +685,7 @@ void edac_mc_handle_ce(struct mem_ctl_info *mci,
 		int row, int channel, const char *msg)
 {
 	unsigned long remapped_page;
+	char detail[80];
 
 	debugf3("MC%d: %s()\n", mci->mc_idx, __func__);
 

@@ -711,8 +712,15 @@ void edac_mc_handle_ce(struct mem_ctl_info *mci,
 		return;
 	}
 
-	trace_mc_corrected_error(mci, page_frame_number, offset_in_page,
-				syndrome, row, channel, msg);
+	/* Memory type dependent details about the error */
+	snprintf(detail, sizeof(detail),
+		 " (page 0x%lx, offset 0x%lx, grain %d, "
+		 "syndrome 0x%lx, row %d, channel %d)\n",
+		 page_frame_number, offset_in_page,
+		 mci->csrows[row].grain, syndrome, row, channel);
+	trace_mc_error(HW_EVENT_ERR_CORRECTED, mci->mc_idx,
+		       mci->csrows[row].channels[channel].label,
+		       msg, detail);
 
 	if (edac_mc_get_log_ce())
 		/* FIXME - put in DIMM location */

@@ -749,7 +757,8 @@ EXPORT_SYMBOL_GPL(edac_mc_handle_ce);
 
 void edac_mc_handle_ce_no_info(struct mem_ctl_info *mci, const char *msg)
 {
-	trace_mc_corrected_error_no_info(mci, msg);
+	trace_mc_error(HW_EVENT_ERR_CORRECTED, mci->mc_idx,
+		       "unknown", msg, "");
 	if (edac_mc_get_log_ce())
 		edac_mc_printk(mci, KERN_WARNING,
 			"CE - no information available: %s\n", msg);

@@ -768,6 +777,7 @@ void edac_mc_handle_ue(struct mem_ctl_info *mci,
 	char *pos = labels;
 	int chan;
 	int chars;
+	char detail[80];
 
 	debugf3("MC%d: %s()\n", mci->mc_idx, __func__);
 

@@ -796,8 +806,15 @@ void edac_mc_handle_ue(struct mem_ctl_info *mci,
 		pos += chars;
 	}
 
-	trace_mc_uncorrected_error(mci, page_frame_number, offset_in_page,
-				row, msg, labels);
+	/* Memory type dependent details about the error */
+	snprintf(detail, sizeof(detail),
+		 "page 0x%lx, offset 0x%lx, grain %d, row %d ",
+		 page_frame_number, offset_in_page,
+	         mci->csrows[row].grain, row);
+	trace_mc_error(HW_EVENT_ERR_UNCORRECTED, mci->mc_idx,
+		       labels,
+		       msg, detail);
+
 	if (edac_mc_get_log_ue())
 		edac_mc_printk(mci, KERN_EMERG,
 			"UE page 0x%lx, offset 0x%lx, grain %d, row %d, "

@@ -818,7 +835,8 @@ EXPORT_SYMBOL_GPL(edac_mc_handle_ue);
 
 void edac_mc_handle_ue_no_info(struct mem_ctl_info *mci, const char *msg)
 {
-	trace_mc_uncorrected_error_no_info(mci, msg);
+	trace_mc_error(HW_EVENT_ERR_UNCORRECTED, mci->mc_idx,
+		       "unknown", msg, "");
 	if (edac_mc_get_panic_on_ue())
 		panic("EDAC MC%d: Uncorrected Error", mci->mc_idx);
 

@@ -843,6 +861,7 @@ void edac_mc_handle_fbd_ue(struct mem_ctl_info *mci,
 	char labels[len + 1];
 	char *pos = labels;
 	int chars;
+	char detail[80];
 
 	if (csrow >= mci->nr_csrows) {
 		/* something is wrong */

@@ -891,8 +910,13 @@ void edac_mc_handle_fbd_ue(struct mem_ctl_info *mci,
 	chars = snprintf(pos, len + 1, "-%s",
 			 mci->csrows[csrow].channels[channelb].label);
 
-	trace_mc_uncorrected_error_fbd(mci, csrow, channela, channelb,
-				       msg, labels);
+	/* Memory type dependent details about the error */
+	snprintf(detail, sizeof(detail),
+		 "row %d, channel-a= %d channel-b= %d ",
+		 csrow, channela, channelb);
+	trace_mc_error(HW_EVENT_ERR_UNCORRECTED, mci->mc_idx,
+		       labels,
+		       msg, detail);
 	if (edac_mc_get_log_ue())
 		edac_mc_printk(mci, KERN_EMERG,
 			"UE row %d, channel-a= %d channel-b= %d "

@@ -913,7 +937,7 @@ EXPORT_SYMBOL(edac_mc_handle_fbd_ue);
 void edac_mc_handle_fbd_ce(struct mem_ctl_info *mci,
 			unsigned int csrow, unsigned int channel, char *msg)
 {
-
+	char detail[80];
 	/* Ensure boundary values */
 	if (csrow >= mci->nr_csrows) {
 		/* something is wrong */

@@ -936,7 +960,14 @@ void edac_mc_handle_fbd_ce(struct mem_ctl_info *mci,
 		return;
 	}
 
-	trace_mc_corrected_error_fbd(mci, csrow, channel, msg);
+	/* Memory type dependent details about the error */
+	snprintf(detail, sizeof(detail),
+		 "(row %d, channel %d)\n",
+		 csrow, channel);
+	trace_mc_error(HW_EVENT_ERR_CORRECTED, mci->mc_idx,
+		       mci->csrows[csrow].channels[channel].label,
+		       msg, detail);
+
 	if (edac_mc_get_log_ce())
 		/* FIXME - put in DIMM location */
 		edac_mc_printk(mci, KERN_WARNING,

index 055b248..3ba99d7 100644
@@ -66,6 +66,12 @@ enum dev_type {
 #define DEV_FLAG_X32		BIT(DEV_X32)
 #define DEV_FLAG_X64		BIT(DEV_X64)
 
+enum hw_event_mc_err_type {
+	HW_EVENT_ERR_CORRECTED,
+	HW_EVENT_ERR_UNCORRECTED,
+	HW_EVENT_ERR_FATAL,
+};
+
 /* memory types */
 enum mem_type {
 	MEM_EMPTY = 0,		/* Empty csrow */

258 lines not on this page · raw message