drivers/edac: split out functions to unique files

This is a large patch to refactor the original EDAC module in the kernel
and to break it up into better file granularity, such that each source
file contains a given subsystem of the EDAC CORE.

Originally, the EDAC 'core' was contained in one source file: edac_mc.c
with it corresponding edac_mc.h file.

Now, there are the following files:

edac_module.c	The main module init/exit function and other overhead
edac_mc.c	Code handling the edac_mc class of object
edac_mc_sysfs.c	Code handling for sysfs presentation
edac_pci_sysfs.c  Code handling for PCI sysfs presentation
edac_core.h	CORE .h include file for 'edac_mc' and 'edac_device' drivers
edac_module.h	Internal CORE .h include file

This forms a foundation upon which a later patch can create the 'edac_device'
class of object code in a new file 'edac_device.c'.
Signed-off-by: NDouglas Thompson <dougthompson@xmission.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

drivers/edac/Makefile

@@ -8,7 +8,12 @@
 # $Id: Makefile,v 1.4.2.3 2005/07/08 22:05:38 dsp_llnl Exp $
 
 
-obj-$(CONFIG_EDAC_MM_EDAC)		+= edac_mc.o
+obj-$(CONFIG_EDAC_MM_EDAC)		+= edac_core.o
+
+edac_core-objs	:= edac_mc.o edac_mc_sysfs.o edac_pci_sysfs.o
+
+edac_core-objs	+= edac_module.o
+
 obj-$(CONFIG_EDAC_AMD76X)		+= amd76x_edac.o
 obj-$(CONFIG_EDAC_E7XXX)		+= e7xxx_edac.o
 obj-$(CONFIG_EDAC_E752X)		+= e752x_edac.o

drivers/edac/edac_core.h

+/*
+ * Defines, structures, APIs for edac_core module
+ *
+ * (C) 2007 Linux Networx (http://lnxi.com)
+ * This file may be distributed under the terms of the
+ * GNU General Public License.
+ *
+ * Written by Thayne Harbaugh
+ * Based on work by Dan Hollis <goemon at anime dot net> and others.
+ *	http://www.anime.net/~goemon/linux-ecc/
+ *
+ * NMI handling support added by
+ *     Dave Peterson <dsp@llnl.gov> <dave_peterson@pobox.com>
+ *
+ * Refactored for multi-source files:
+ *	Doug Thompson <norsk5@xmission.com>
+ *
+ */
+
+#ifndef _EDAC_CORE_H_
+#define _EDAC_CORE_H_
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/pci.h>
+#include <linux/time.h>
+#include <linux/nmi.h>
+#include <linux/rcupdate.h>
+#include <linux/completion.h>
+#include <linux/kobject.h>
+#include <linux/platform_device.h>
+
+#define EDAC_MC_LABEL_LEN	31
+#define MC_PROC_NAME_MAX_LEN 7
+
+#if PAGE_SHIFT < 20
+#define PAGES_TO_MiB( pages )	( ( pages ) >> ( 20 - PAGE_SHIFT ) )
+#else				/* PAGE_SHIFT > 20 */
+#define PAGES_TO_MiB( pages )	( ( pages ) << ( PAGE_SHIFT - 20 ) )
+#endif
+
+#define edac_printk(level, prefix, fmt, arg...) \
+	printk(level "EDAC " prefix ": " fmt, ##arg)
+
+#define edac_mc_printk(mci, level, fmt, arg...) \
+	printk(level "EDAC MC%d: " fmt, mci->mc_idx, ##arg)
+
+#define edac_mc_chipset_printk(mci, level, prefix, fmt, arg...) \
+	printk(level "EDAC " prefix " MC%d: " fmt, mci->mc_idx, ##arg)
+
+/* prefixes for edac_printk() and edac_mc_printk() */
+#define EDAC_MC "MC"
+#define EDAC_PCI "PCI"
+#define EDAC_DEBUG "DEBUG"
+
+#ifdef CONFIG_EDAC_DEBUG
+extern int edac_debug_level;
+
+#define edac_debug_printk(level, fmt, arg...)                            \
+	do {                                                             \
+		if (level <= edac_debug_level)                           \
+			edac_printk(KERN_DEBUG, EDAC_DEBUG, fmt, ##arg); \
+	} while(0)
+
+#define debugf0( ... ) edac_debug_printk(0, __VA_ARGS__ )
+#define debugf1( ... ) edac_debug_printk(1, __VA_ARGS__ )
+#define debugf2( ... ) edac_debug_printk(2, __VA_ARGS__ )
+#define debugf3( ... ) edac_debug_printk(3, __VA_ARGS__ )
+#define debugf4( ... ) edac_debug_printk(4, __VA_ARGS__ )
+
+#else  /* !CONFIG_EDAC_DEBUG */
+
+#define debugf0( ... )
+#define debugf1( ... )
+#define debugf2( ... )
+#define debugf3( ... )
+#define debugf4( ... )
+
+#endif  /* !CONFIG_EDAC_DEBUG */
+
+#define BIT(x) (1 << (x))
+
+#define PCI_VEND_DEV(vend, dev) PCI_VENDOR_ID_ ## vend, \
+	PCI_DEVICE_ID_ ## vend ## _ ## dev
+
+#if defined(CONFIG_X86) && defined(CONFIG_PCI)
+#define dev_name(dev) pci_name(to_pci_dev(dev))
+#else
+#define dev_name(dev) to_platform_device(dev)->name
+#endif
+
+/* 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 */
+};
+
+#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)
+
+/* 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_CORR)
+#define SCRUB_FLAG_SW_PROG_SRC	BIT(SCRUB_SW_PROG_SRC_CORR)
+#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_CORR)
+#define SCRUB_FLAG_HW_PROG_SRC	BIT(SCRUB_HW_PROG_SRC_CORR)
+#define SCRUB_FLAG_HW_TUN	BIT(SCRUB_HW_TUNABLE)
+
+/* FIXME - should have notify capabilities: NMI, LOG, PROC, etc */
+
+/*
+ * 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 memmory.
+ *			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 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 */
+	struct completion kobj_complete;
+
+	/* FIXME the number of CHANNELs might need to become dynamic */
+	u32 nr_channels;
+	struct channel_info *channels;
+};
+
+struct mem_ctl_info {
+	struct list_head link;  /* for global list of mem_ctl_info structs */
+	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, u32 *bw);
+
+	/* 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;
+	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;
+	struct completion kobj_complete;
+};
+
+#ifdef CONFIG_PCI
+
+/* write all or some bits in a byte-register*/
+static inline void pci_write_bits8(struct pci_dev *pdev, int offset, u8 value,
+		u8 mask)
+{
+	if (mask != 0xff) {
+		u8 buf;
+
+		pci_read_config_byte(pdev, offset, &buf);
+		value &= mask;
+		buf &= ~mask;
+		value |= buf;
+	}
+
+	pci_write_config_byte(pdev, offset, value);
+}
+
+/* write all or some bits in a word-register*/
+static inline void pci_write_bits16(struct pci_dev *pdev, int offset,
+		u16 value, u16 mask)
+{
+	if (mask != 0xffff) {
+		u16 buf;
+
+		pci_read_config_word(pdev, offset, &buf);
+		value &= mask;
+		buf &= ~mask;
+		value |= buf;
+	}
+
+	pci_write_config_word(pdev, offset, value);
+}
+
+/* write all or some bits in a dword-register*/
+static inline void pci_write_bits32(struct pci_dev *pdev, int offset,
+		u32 value, u32 mask)
+{
+	if (mask != 0xffff) {
+		u32 buf;
+
+		pci_read_config_dword(pdev, offset, &buf);
+		value &= mask;
+		buf &= ~mask;
+		value |= buf;
+	}
+
+	pci_write_config_dword(pdev, offset, value);
+}
+
+#endif /* CONFIG_PCI */
+
+extern struct mem_ctl_info * edac_mc_find(int idx);
+extern int edac_mc_add_mc(struct mem_ctl_info *mci,int mc_idx);
+extern struct mem_ctl_info * edac_mc_del_mc(struct device *dev);
+extern int edac_mc_find_csrow_by_page(struct mem_ctl_info *mci,
+					unsigned long page);
+
+/*
+ * The no info errors are used when error overflows are reported.
+ * There are a limited number of error logging registers that can
+ * be exausted.  When all registers are exhausted and an additional
+ * error occurs then an error overflow register records that an
+ * error occured and the type of error, but doesn't have any
+ * further information.  The ce/ue versions make for cleaner
+ * reporting logic and function interface - reduces conditional
+ * statement clutter and extra function arguments.
+ */
+extern void edac_mc_handle_ce(struct mem_ctl_info *mci,
+		unsigned long page_frame_number, unsigned long offset_in_page,
+		unsigned long syndrome, int row, int channel,
+		const char *msg);
+extern void edac_mc_handle_ce_no_info(struct mem_ctl_info *mci,
+		const char *msg);
+extern void edac_mc_handle_ue(struct mem_ctl_info *mci,
+		unsigned long page_frame_number, unsigned long offset_in_page,
+		int row, const char *msg);
+extern void edac_mc_handle_ue_no_info(struct mem_ctl_info *mci,
+		const char *msg);
+extern void edac_mc_handle_fbd_ue(struct mem_ctl_info *mci,
+		unsigned int csrow,
+		unsigned int channel0,
+		unsigned int channel1,
+		char *msg);
+extern void edac_mc_handle_fbd_ce(struct mem_ctl_info *mci,
+		unsigned int csrow,
+		unsigned int channel,
+		char *msg);
+
+/*
+ * This kmalloc's and initializes all the structures.
+ * Can't be used if all structures don't have the same lifetime.
+ */
+extern struct mem_ctl_info *edac_mc_alloc(unsigned sz_pvt, unsigned nr_csrows,
+		unsigned nr_chans);
+
+/* Free an mc previously allocated by edac_mc_alloc() */
+extern void edac_mc_free(struct mem_ctl_info *mci);
+
+#endif				/* _EDAC_CORE_H_ */

drivers/edac/edac_mc.h

-/*
- * MC kernel module
- * (C) 2003 Linux Networx (http://lnxi.com)
- * This file may be distributed under the terms of the
- * GNU General Public License.
- *
- * Written by Thayne Harbaugh
- * Based on work by Dan Hollis <goemon at anime dot net> and others.
- *	http://www.anime.net/~goemon/linux-ecc/
- *
- * NMI handling support added by
- *     Dave Peterson <dsp@llnl.gov> <dave_peterson@pobox.com>
- *
- * $Id: edac_mc.h,v 1.4.2.10 2005/10/05 00:43:44 dsp_llnl Exp $
- *
- */
-
-#ifndef _EDAC_MC_H_
-#define _EDAC_MC_H_
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/module.h>
-#include <linux/spinlock.h>
-#include <linux/smp.h>
-#include <linux/pci.h>
-#include <linux/time.h>
-#include <linux/nmi.h>
-#include <linux/rcupdate.h>
-#include <linux/completion.h>
-#include <linux/kobject.h>
-#include <linux/platform_device.h>
-
-#define EDAC_MC_LABEL_LEN	31
-#define MC_PROC_NAME_MAX_LEN 7
-
-#if PAGE_SHIFT < 20
-#define PAGES_TO_MiB( pages )	( ( pages ) >> ( 20 - PAGE_SHIFT ) )
-#else				/* PAGE_SHIFT > 20 */
-#define PAGES_TO_MiB( pages )	( ( pages ) << ( PAGE_SHIFT - 20 ) )
-#endif
-
-#define edac_printk(level, prefix, fmt, arg...) \
-	printk(level "EDAC " prefix ": " fmt, ##arg)
-
-#define edac_mc_printk(mci, level, fmt, arg...) \
-	printk(level "EDAC MC%d: " fmt, mci->mc_idx, ##arg)
-
-#define edac_mc_chipset_printk(mci, level, prefix, fmt, arg...) \
-	printk(level "EDAC " prefix " MC%d: " fmt, mci->mc_idx, ##arg)
-
-/* prefixes for edac_printk() and edac_mc_printk() */
-#define EDAC_MC "MC"
-#define EDAC_PCI "PCI"
-#define EDAC_DEBUG "DEBUG"
-
-#ifdef CONFIG_EDAC_DEBUG
-extern int edac_debug_level;
-
-#define edac_debug_printk(level, fmt, arg...)                            \
-	do {                                                             \
-		if (level <= edac_debug_level)                           \
-			edac_printk(KERN_DEBUG, EDAC_DEBUG, fmt, ##arg); \
-	} while(0)
-
-#define debugf0( ... ) edac_debug_printk(0, __VA_ARGS__ )
-#define debugf1( ... ) edac_debug_printk(1, __VA_ARGS__ )
-#define debugf2( ... ) edac_debug_printk(2, __VA_ARGS__ )
-#define debugf3( ... ) edac_debug_printk(3, __VA_ARGS__ )
-#define debugf4( ... ) edac_debug_printk(4, __VA_ARGS__ )
-
-#else  /* !CONFIG_EDAC_DEBUG */
-
-#define debugf0( ... )
-#define debugf1( ... )
-#define debugf2( ... )
-#define debugf3( ... )
-#define debugf4( ... )
-
-#endif  /* !CONFIG_EDAC_DEBUG */
 
-#define BIT(x) (1 << (x))
-
-#define PCI_VEND_DEV(vend, dev) PCI_VENDOR_ID_ ## vend, \
-	PCI_DEVICE_ID_ ## vend ## _ ## dev
-
-#if defined(CONFIG_X86) && defined(CONFIG_PCI)
-#define dev_name(dev) pci_name(to_pci_dev(dev))
-#else
-#define dev_name(dev) to_platform_device(dev)->name
-#endif
-
-/* 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 */
-};
-
-#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)
-
-/* 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_CORR)
-#define SCRUB_FLAG_SW_PROG_SRC	BIT(SCRUB_SW_PROG_SRC_CORR)
-#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_CORR)
-#define SCRUB_FLAG_HW_PROG_SRC	BIT(SCRUB_HW_PROG_SRC_CORR)
-#define SCRUB_FLAG_HW_TUN	BIT(SCRUB_HW_TUNABLE)
-
-/* FIXME - should have notify capabilities: NMI, LOG, PROC, etc */
 
 /*
- * 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 memmory.
- *			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.
+ * Older .h file for edac, until all drivers are modified
  *
- * 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 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 */
-	struct completion kobj_complete;
-
-	/* FIXME the number of CHANNELs might need to become dynamic */
-	u32 nr_channels;
-	struct channel_info *channels;
-};
-
-struct mem_ctl_info {
-	struct list_head link;  /* for global list of mem_ctl_info structs */
-	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, u32 *bw);
-
-	/* 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;
-	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;
-	struct completion kobj_complete;
-};
-
-#ifdef CONFIG_PCI
-
-/* write all or some bits in a byte-register*/
-static inline void pci_write_bits8(struct pci_dev *pdev, int offset, u8 value,
-		u8 mask)
-{
-	if (mask != 0xff) {
-		u8 buf;
-
-		pci_read_config_byte(pdev, offset, &buf);
-		value &= mask;
-		buf &= ~mask;
-		value |= buf;
-	}
-
-	pci_write_config_byte(pdev, offset, value);
-}
-
-/* write all or some bits in a word-register*/
-static inline void pci_write_bits16(struct pci_dev *pdev, int offset,
-		u16 value, u16 mask)
-{
-	if (mask != 0xffff) {
-		u16 buf;
-
-		pci_read_config_word(pdev, offset, &buf);
-		value &= mask;
-		buf &= ~mask;
-		value |= buf;
-	}
-
-	pci_write_config_word(pdev, offset, value);
-}
-
-/* write all or some bits in a dword-register*/
-static inline void pci_write_bits32(struct pci_dev *pdev, int offset,
-		u32 value, u32 mask)
-{
-	if (mask != 0xffff) {
-		u32 buf;
-
-		pci_read_config_dword(pdev, offset, &buf);
-		value &= mask;
-		buf &= ~mask;
-		value |= buf;
-	}
-
-	pci_write_config_dword(pdev, offset, value);
-}
-
-#endif /* CONFIG_PCI */
-
-extern struct mem_ctl_info * edac_mc_find(int idx);
-extern int edac_mc_add_mc(struct mem_ctl_info *mci,int mc_idx);
-extern struct mem_ctl_info * edac_mc_del_mc(struct device *dev);
-extern int edac_mc_find_csrow_by_page(struct mem_ctl_info *mci,
-					unsigned long page);
-
-/*
- * The no info errors are used when error overflows are reported.
- * There are a limited number of error logging registers that can
- * be exausted.  When all registers are exhausted and an additional
- * error occurs then an error overflow register records that an
- * error occured and the type of error, but doesn't have any
- * further information.  The ce/ue versions make for cleaner
- * reporting logic and function interface - reduces conditional
- * statement clutter and extra function arguments.
- */
-extern void edac_mc_handle_ce(struct mem_ctl_info *mci,
-		unsigned long page_frame_number, unsigned long offset_in_page,
-		unsigned long syndrome, int row, int channel,
-		const char *msg);
-extern void edac_mc_handle_ce_no_info(struct mem_ctl_info *mci,
-		const char *msg);
-extern void edac_mc_handle_ue(struct mem_ctl_info *mci,
-		unsigned long page_frame_number, unsigned long offset_in_page,
-		int row, const char *msg);
-extern void edac_mc_handle_ue_no_info(struct mem_ctl_info *mci,
-		const char *msg);
-extern void edac_mc_handle_fbd_ue(struct mem_ctl_info *mci,
-		unsigned int csrow,
-		unsigned int channel0,
-		unsigned int channel1,
-		char *msg);
-extern void edac_mc_handle_fbd_ce(struct mem_ctl_info *mci,
-		unsigned int csrow,
-		unsigned int channel,
-		char *msg);
-
-/*
- * This kmalloc's and initializes all the structures.
- * Can't be used if all structures don't have the same lifetime.
  */
-extern struct mem_ctl_info *edac_mc_alloc(unsigned sz_pvt, unsigned nr_csrows,
-		unsigned nr_chans);
 
-/* Free an mc previously allocated by edac_mc_alloc() */
-extern void edac_mc_free(struct mem_ctl_info *mci);
+#include "edac_core.h"
 
-#endif				/* _EDAC_MC_H_ */

drivers/edac/edac_module.c

+
+#include <linux/freezer.h>
+#include <linux/kthread.h>
+
+#include "edac_mc.h"
+#include "edac_module.h"
+
+#define EDAC_MC_VERSION "Ver: 2.0.3" __DATE__
+
+#ifdef CONFIG_EDAC_DEBUG
+/* Values of 0 to 4 will generate output */
+int edac_debug_level = 1;
+EXPORT_SYMBOL_GPL(edac_debug_level);
+#endif
+
+static struct task_struct *edac_thread;
+
+/*
+ * Check MC status every edac_get_poll_msec().
+ * Check PCI status every edac_get_poll_msec() as well.
+ *
+ * This where the work gets done for edac.
+ *
+ * SMP safe, doesn't use NMI, and auto-rate-limits.
+ */
+static void do_edac_check(void)
+{
+	debugf3("%s()\n", __func__);
+
+	/* perform the poll activities */
+	edac_check_mc_devices();
+	edac_pci_do_parity_check();
+}
+
+/*
+ * Action thread for EDAC to perform the POLL operations
+ */
+static int edac_kernel_thread(void *arg)
+{
+	int msec;
+
+	while (!kthread_should_stop()) {
+
+		do_edac_check();
+
+		/* goto sleep for the interval */
+		msec = (HZ * edac_get_poll_msec()) / 1000;
+		schedule_timeout_interruptible(msec);
+		try_to_freeze();
+	}
+
+	return 0;
+}
+
+/*
+ * edac_init
+ *      module initialization entry point
+ */
+static int __init edac_init(void)
+{
+	edac_printk(KERN_INFO, EDAC_MC, EDAC_MC_VERSION "\n");
+
+	/*
+	 * Harvest and clear any boot/initialization PCI parity errors
+	 *
+	 * FIXME: This only clears errors logged by devices present at time of
+	 * 	module initialization.  We should also do an initial clear
+	 *	of each newly hotplugged device.
+	 */
+	edac_pci_clear_parity_errors();
+
+	/* Create the MC sysfs entries */
+	if (edac_sysfs_memctrl_setup()) {
+		edac_printk(KERN_ERR, EDAC_MC,
+			"Error initializing sysfs code\n");
+		return -ENODEV;
+	}
+
+	/* Create the PCI parity sysfs entries */
+	if (edac_sysfs_pci_setup()) {
+		edac_sysfs_memctrl_teardown();
+		edac_printk(KERN_ERR, EDAC_MC,
+			"PCI: Error initializing sysfs code\n");
+		return -ENODEV;
+	}
+
+	/* create our kernel thread */
+	edac_thread = kthread_run(edac_kernel_thread, NULL, "kedac");
+
+	if (IS_ERR(edac_thread)) {
+		/* remove the sysfs entries */
+		edac_sysfs_memctrl_teardown();
+		edac_sysfs_pci_teardown();
+		return PTR_ERR(edac_thread);
+	}
+
+	return 0;
+}
+
+/*
+ * edac_exit()
+ *      module exit/termination function
+ */
+static void __exit edac_exit(void)
+{
+	debugf0("%s()\n", __func__);
+	kthread_stop(edac_thread);
+
+	/* tear down the sysfs device */
+	edac_sysfs_memctrl_teardown();
+	edac_sysfs_pci_teardown();
+}
+
+/*
+ * Inform the kernel of our entry and exit points
+ */
+module_init(edac_init);
+module_exit(edac_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Doug Thompson www.softwarebitmaker.com, et al");
+MODULE_DESCRIPTION("Core library routines for EDAC reporting");
+
+/* refer to *_sysfs.c files for parameters that are exported via sysfs */
+
+#ifdef CONFIG_EDAC_DEBUG
+module_param(edac_debug_level, int, 0644);
+MODULE_PARM_DESC(edac_debug_level, "Debug level");
+#endif
+

drivers/edac/edac_module.h

+
+/*
+ * edac_module.h
+ *
+ * For defining functions/data for within the EDAC_CORE module only
+ *
+ * written by doug thompson <norsk5@xmission.h>
+ */
+
+#ifndef	__EDAC_MODULE_H__
+#define	__EDAC_MODULE_H__
+
+#include <linux/sysdev.h>
+
+#include "edac_core.h"
+
+/*
+ * INTERNAL EDAC MODULE:
+ * EDAC memory controller sysfs create/remove functions
+ * and setup/teardown functions
+ */
+extern int edac_create_sysfs_mci_device(struct mem_ctl_info *mci);
+extern void edac_remove_sysfs_mci_device(struct mem_ctl_info *mci);
+extern int edac_sysfs_memctrl_setup(void);
+extern void edac_sysfs_memctrl_teardown(void);
+extern void edac_check_mc_devices(void);
+extern int edac_get_log_ue(void);
+extern int edac_get_log_ce(void);
+extern int edac_get_panic_on_ue(void);
+extern int edac_get_poll_msec(void);
+
+extern int edac_device_create_sysfs(struct edac_device_ctl_info *edac_dev);
+extern void edac_device_remove_sysfs(struct edac_device_ctl_info *edac_dev);
+extern struct sysdev_class *edac_get_edac_class(void);
+
+
+/*
+ * EDAC PCI functions
+ */
+#ifdef	CONFIG_PCI
+extern void edac_pci_do_parity_check(void);
+extern void edac_pci_clear_parity_errors(void);
+extern int edac_sysfs_pci_setup(void);
+extern void edac_sysfs_pci_teardown(void);
+#else   /* CONFIG_PCI */
+/* pre-process these away */
+#define edac_pci_do_parity_check()
+#define edac_pci_clear_parity_errors()
+#define edac_sysfs_pci_setup()  (0)
+#define edac_sysfs_pci_teardown()
+#endif  /* CONFIG_PCI */
+
+
+#endif	/* __EDAC_MODULE_H__ */
+

drivers/edac/edac_pci_sysfs.c

+/* edac_mc kernel module
+ * (C) 2005, 2006 Linux Networx (http://lnxi.com)
+ * This file may be distributed under the terms of the
+ * GNU General Public License.
+ *
+ * Written Doug Thompson <norsk5@xmission.com>
+ *
+ */
+#include <linux/module.h>
+#include <linux/sysdev.h>
+#include <linux/ctype.h>
+
+#include "edac_mc.h"
+#include "edac_module.h"
+
+
+#ifdef CONFIG_PCI
+static int check_pci_parity = 0;	/* default YES check PCI parity */
+static int panic_on_pci_parity;		/* default no panic on PCI Parity */
+static atomic_t pci_parity_count = ATOMIC_INIT(0);
+
+static struct kobject edac_pci_kobj; /* /sys/devices/system/edac/pci */
+static struct completion edac_pci_kobj_complete;
+
+
+static ssize_t edac_pci_int_show(void *ptr, char *buffer)
+{
+	int *value = ptr;
+	return sprintf(buffer,"%d\n",*value);
+}
+
+static ssize_t edac_pci_int_store(void *ptr, const char *buffer, size_t count)
+{
+	int *value = ptr;
+
+	if (isdigit(*buffer))
+		*value = simple_strtoul(buffer,NULL,0);
+
+	return count;
+}
+
+struct edac_pci_dev_attribute {
+	struct attribute attr;
+	void *value;
+	ssize_t (*show)(void *,char *);
+	ssize_t (*store)(void *, const char *,size_t);
+};
+
+/* Set of show/store abstract level functions for PCI Parity object */
+static ssize_t edac_pci_dev_show(struct kobject *kobj, struct attribute *attr,
+		char *buffer)
+{
+	struct edac_pci_dev_attribute *edac_pci_dev;
+	edac_pci_dev= (struct edac_pci_dev_attribute*)attr;
+
+	if (edac_pci_dev->show)
+		return edac_pci_dev->show(edac_pci_dev->value, buffer);
+	return -EIO;
+}
+
+static ssize_t edac_pci_dev_store(struct kobject *kobj,
+		struct attribute *attr, const char *buffer, size_t count)
+{
+	struct edac_pci_dev_attribute *edac_pci_dev;
+	edac_pci_dev= (struct edac_pci_dev_attribute*)attr;
+
+	if (edac_pci_dev->show)
+		return edac_pci_dev->store(edac_pci_dev->value, buffer, count);
+	return -EIO;
+}
+
+static struct sysfs_ops edac_pci_sysfs_ops = {
+	.show   = edac_pci_dev_show,
+	.store  = edac_pci_dev_store
+};
+
+#define EDAC_PCI_ATTR(_name,_mode,_show,_store)			\
+static struct edac_pci_dev_attribute edac_pci_attr_##_name = {		\
+	.attr = {.name = __stringify(_name), .mode = _mode },	\
+	.value  = &_name,					\
+	.show   = _show,					\
+	.store  = _store,					\
+};
+
+#define EDAC_PCI_STRING_ATTR(_name,_data,_mode,_show,_store)	\
+static struct edac_pci_dev_attribute edac_pci_attr_##_name = {		\
+	.attr = {.name = __stringify(_name), .mode = _mode },	\
+	.value  = _data,					\
+	.show   = _show,					\
+	.store  = _store,					\
+};
+
+/* PCI Parity control files */
+EDAC_PCI_ATTR(check_pci_parity, S_IRUGO|S_IWUSR, edac_pci_int_show,
+	edac_pci_int_store);
+EDAC_PCI_ATTR(panic_on_pci_parity, S_IRUGO|S_IWUSR, edac_pci_int_show,
+	edac_pci_int_store);
+EDAC_PCI_ATTR(pci_parity_count, S_IRUGO, edac_pci_int_show, NULL);
+
+/* Base Attributes of the memory ECC object */
+static struct edac_pci_dev_attribute *edac_pci_attr[] = {
+	&edac_pci_attr_check_pci_parity,
+	&edac_pci_attr_panic_on_pci_parity,
+	&edac_pci_attr_pci_parity_count,
+	NULL,
+};
+
+/* No memory to release */
+static void edac_pci_release(struct kobject *kobj)
+{
+	debugf1("%s()\n", __func__);
+	complete(&edac_pci_kobj_complete);
+}
+
+static struct kobj_type ktype_edac_pci = {
+	.release = edac_pci_release,
+	.sysfs_ops = &edac_pci_sysfs_ops,
+	.default_attrs = (struct attribute **) edac_pci_attr,
+};
+
+/**
+ * edac_sysfs_pci_setup()
+ *
+ *	setup the sysfs for EDAC PCI attributes
+ *	assumes edac_class has already been initialized
+ */
+int edac_sysfs_pci_setup(void)
+{
+	int err;
+	struct sysdev_class *edac_class;
+
+	debugf1("%s()\n", __func__);
+
+	edac_class = edac_get_edac_class();
+
+	memset(&edac_pci_kobj, 0, sizeof(edac_pci_kobj));
+	edac_pci_kobj.parent = &edac_class->kset.kobj;
+	edac_pci_kobj.ktype = &ktype_edac_pci;
+	err = kobject_set_name(&edac_pci_kobj, "pci");
+
+	if (!err) {
+		/* Instanstiate the pci object */
+		/* FIXME: maybe new sysdev_create_subdir() */
+		err = kobject_register(&edac_pci_kobj);
+
+		if (err)
+			debugf1("Failed to register '.../edac/pci'\n");
+		else
+			debugf1("Registered '.../edac/pci' kobject\n");
+	}
+
+	return err;
+}
+
+/*
+ * edac_sysfs_pci_teardown
+ *
+ *	perform the sysfs teardown for the PCI attributes
+ */
+void edac_sysfs_pci_teardown(void)
+{
+	debugf0("%s()\n", __func__);
+	init_completion(&edac_pci_kobj_complete);
+	kobject_unregister(&edac_pci_kobj);
+	wait_for_completion(&edac_pci_kobj_complete);
+}
+
+
+static u16 get_pci_parity_status(struct pci_dev *dev, int secondary)
+{
+	int where;
+	u16 status;
+
+	where = secondary ? PCI_SEC_STATUS : PCI_STATUS;
+	pci_read_config_word(dev, where, &status);
+
+	/* If we get back 0xFFFF then we must suspect that the card has been
+	 * pulled but the Linux PCI layer has not yet finished cleaning up.
+	 * We don't want to report on such devices
+	 */
+
+	if (status == 0xFFFF) {
+		u32 sanity;
+
+		pci_read_config_dword(dev, 0, &sanity);
+
+		if (sanity == 0xFFFFFFFF)
+			return 0;
+	}
+
+	status &= PCI_STATUS_DETECTED_PARITY | PCI_STATUS_SIG_SYSTEM_ERROR |
+		PCI_STATUS_PARITY;
+
+	if (status)
+		/* reset only the bits we are interested in */
+		pci_write_config_word(dev, where, status);
+
+	return status;
+}
+
+typedef void (*pci_parity_check_fn_t) (struct pci_dev *dev);
+
+/* Clear any PCI parity errors logged by this device. */
+static void edac_pci_dev_parity_clear(struct pci_dev *dev)
+{
+	u8 header_type;
+
+	get_pci_parity_status(dev, 0);
+
+	/* read the device TYPE, looking for bridges */
+	pci_read_config_byte(dev, PCI_HEADER_TYPE, &header_type);
+
+	if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE)
+		get_pci_parity_status(dev, 1);
+}
+
+/*
+ *  PCI Parity polling
+ *
+ */
+static void edac_pci_dev_parity_test(struct pci_dev *dev)
+{
+	u16 status;
+	u8  header_type;
+
+	/* read the STATUS register on this device
+	 */
+	status = get_pci_parity_status(dev, 0);
+
+	debugf2("PCI STATUS= 0x%04x %s\n", status, dev->dev.bus_id );
+
+	/* check the status reg for errors */
+	if (status) {
+		if (status & (PCI_STATUS_SIG_SYSTEM_ERROR))
+			edac_printk(KERN_CRIT, EDAC_PCI,
+				"Signaled System Error on %s\n",
+				pci_name(dev));
+
+		if (status & (PCI_STATUS_PARITY)) {
+			edac_printk(KERN_CRIT, EDAC_PCI,
+				"Master Data Parity Error on %s\n",
+				pci_name(dev));
+
+			atomic_inc(&pci_parity_count);
+		}
+
+		if (status & (PCI_STATUS_DETECTED_PARITY)) {
+			edac_printk(KERN_CRIT, EDAC_PCI,
+				"Detected Parity Error on %s\n",
+				pci_name(dev));
+
+			atomic_inc(&pci_parity_count);
+		}
+	}
+
+	/* read the device TYPE, looking for bridges */
+	pci_read_config_byte(dev, PCI_HEADER_TYPE, &header_type);
+
+	debugf2("PCI HEADER TYPE= 0x%02x %s\n", header_type, dev->dev.bus_id );
+
+	if ((header_type & 0x7F) == PCI_HEADER_TYPE_BRIDGE) {
+		/* On bridges, need to examine secondary status register  */
+		status = get_pci_parity_status(dev, 1);
+
+		debugf2("PCI SEC_STATUS= 0x%04x %s\n",
+				status, dev->dev.bus_id );
+
+		/* check the secondary status reg for errors */
+		if (status) {
+			if (status & (PCI_STATUS_SIG_SYSTEM_ERROR))
+				edac_printk(KERN_CRIT, EDAC_PCI, "Bridge "
+					"Signaled System Error on %s\n",
+					pci_name(dev));
+
+			if (status & (PCI_STATUS_PARITY)) {
+				edac_printk(KERN_CRIT, EDAC_PCI, "Bridge "
+					"Master Data Parity Error on "
+					"%s\n", pci_name(dev));
+
+				atomic_inc(&pci_parity_count);
+			}
+
+			if (status & (PCI_STATUS_DETECTED_PARITY)) {
+				edac_printk(KERN_CRIT, EDAC_PCI, "Bridge "
+					"Detected Parity Error on %s\n",
+					pci_name(dev));
+
+				atomic_inc(&pci_parity_count);
+			}
+		}
+	}
+}
+
+/*
+ * pci_dev parity list iterator
+ *	Scan the PCI device list for one iteration, looking for SERRORs
+ *	Master Parity ERRORS or Parity ERRORs on primary or secondary devices
+ */
+static inline void edac_pci_dev_parity_iterator(pci_parity_check_fn_t fn)
+{
+	struct pci_dev *dev = NULL;
+
+	/* request for kernel access to the next PCI device, if any,
+	 * and while we are looking at it have its reference count
+	 * bumped until we are done with it
+	 */
+	while((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
+		fn(dev);
+	}
+}
+
+/*
+ * edac_pci_do_parity_check
+ *
+ *	performs the actual PCI parity check operation
+ */
+void edac_pci_do_parity_check(void)
+{
+	unsigned long flags;
+	int before_count;
+
+	debugf3("%s()\n", __func__);
+
+	if (!check_pci_parity)
+		return;
+
+	before_count = atomic_read(&pci_parity_count);
+
+	/* scan all PCI devices looking for a Parity Error on devices and
+	 * bridges
+	 */
+	local_irq_save(flags);
+	edac_pci_dev_parity_iterator(edac_pci_dev_parity_test);
+	local_irq_restore(flags);
+
+	/* Only if operator has selected panic on PCI Error */
+	if (panic_on_pci_parity) {
+		/* If the count is different 'after' from 'before' */
+		if (before_count != atomic_read(&pci_parity_count))
+			panic("EDAC: PCI Parity Error");
+	}
+}
+
+void edac_pci_clear_parity_errors(void)
+{
+	/* Clear any PCI bus parity errors that devices initially have logged
+	 * in their registers.
+	 */
+	edac_pci_dev_parity_iterator(edac_pci_dev_parity_clear);
+}
+
+
+/*
+ * Define the PCI parameter to the module
+ */
+module_param(check_pci_parity, int, 0644);
+MODULE_PARM_DESC(check_pci_parity, "Check for PCI bus parity errors: 0=off 1=on");
+module_param(panic_on_pci_parity, int, 0644);
+MODULE_PARM_DESC(panic_on_pci_parity, "Panic on PCI Bus Parity error: 0=off 1=on");
+
+#endif	/* CONFIG_PCI */