[PATCH] EDAC: core EDAC support code

This is a subset of the bluesmoke project core code, stripped of the NMI work
which isn't ready to merge and some of the "interesting" proc functionality
that needs reworking or just has no place in kernel.  It requires no core
kernel changes except the added scrub functions already posted.

The goal is to merge further functionality only after the core code is
accepted and proven in the base kernel, and only at the point the upstream
extras are really ready to merge.

From: doug thompson <norsk5@xmission.com>

  This converts EDAC to sysfs and is the final chunk neccessary before EDAC
  has a stable user space API and can be considered for submission into the
  base kernel.
Signed-off-by: Alan Cox <alan@redhat.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Jesper Juhl <jesper.juhl@gmail.com>
Signed-off-by: doug thompson <norsk5@xmission.com>
Signed-off-by: Pavel Machek <pavel@suse.cz>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

MAINTAINERS

@@ -867,6 +867,15 @@ L:	ebtables-devel@lists.sourceforge.net
 W:	http://ebtables.sourceforge.net/
 S:	Maintained
 
+EDAC-CORE
+P:      Doug Thompson
+M:      norsk5@xmission.com, dthompson@linuxnetworx.com
+P:      Dave Peterson
+M:      dsp@llnl.gov, dave_peterson@pobox.com
+L:      bluesmoke-devel@lists.sourceforge.net
+W:      bluesmoke.sourceforge.net
+S:      Maintained
+
 EEPRO100 NETWORK DRIVER
 P:	Andrey V. Savochkin
 M:	saw@saw.sw.com.sg

arch/i386/kernel/quirks.c

@@ -25,8 +25,7 @@ static void __devinit quirk_intel_irqbalance(struct pci_dev *dev)
 
 	/* enable access to config space*/
 	pci_read_config_byte(dev, 0xf4, &config);
-	config |= 0x2;
-	pci_write_config_byte(dev, 0xf4, config);
+	pci_write_config_byte(dev, 0xf4, config|0x2);
 
 	/* read xTPR register */
 	raw_pci_ops->read(0, 0, 0x40, 0x4c, 2, &word);
@@ -42,9 +41,9 @@ static void __devinit quirk_intel_irqbalance(struct pci_dev *dev)
 #endif
 	}
 
-	config &= ~0x2;
-	/* disable access to config space*/
-	pci_write_config_byte(dev, 0xf4, config);
+	/* put back the original value for config space*/
+	if (!(config & 0x2))
+		pci_write_config_byte(dev, 0xf4, config);
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_E7320_MCH,	quirk_intel_irqbalance);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_E7525_MCH,	quirk_intel_irqbalance);

drivers/Kconfig

@@ -68,4 +68,6 @@ source "drivers/infiniband/Kconfig"
 
 source "drivers/sn/Kconfig"
 
+source "drivers/edac/Kconfig"
+
 endmenu

drivers/Makefile

@@ -63,6 +63,7 @@ obj-$(CONFIG_PHONE)		+= telephony/
 obj-$(CONFIG_MD)		+= md/
 obj-$(CONFIG_BT)		+= bluetooth/
 obj-$(CONFIG_ISDN)		+= isdn/
+obj-$(CONFIG_EDAC)		+= edac/
 obj-$(CONFIG_MCA)		+= mca/
 obj-$(CONFIG_EISA)		+= eisa/
 obj-$(CONFIG_CPU_FREQ)		+= cpufreq/

drivers/edac/Kconfig

+#
+#	EDAC Kconfig
+#	Copyright (c) 2003 Linux Networx
+#	Licensed and distributed under the GPL
+#
+# $Id: Kconfig,v 1.4.2.7 2005/07/08 22:05:38 dsp_llnl Exp $
+#
+
+menu 'EDAC - error detection and reporting (RAS)'
+
+config EDAC
+	tristate "EDAC core system error reporting"
+	depends on X86
+	default y
+	help
+	  EDAC is designed to report errors in the core system.
+	  These are low-level errors that are reported in the CPU or
+	  supporting chipset: memory errors, cache errors, PCI errors,
+	  thermal throttling, etc..  If unsure, select 'Y'.
+
+
+comment "Reporting subsystems"
+	depends on EDAC
+
+config EDAC_DEBUG
+	bool "Debugging"
+	depends on EDAC
+	help
+	  This turns on debugging information for the entire EDAC
+	  sub-system. You can insert module with "debug_level=x", current
+	  there're four debug levels (x=0,1,2,3 from low to high).
+	  Usually you should select 'N'.
+
+config EDAC_MM_EDAC
+	tristate "Main Memory EDAC (Error Detection And Correction) reporting"
+	depends on EDAC
+	default y
+	help
+	  Some systems are able to detect and correct errors in main
+	  memory.  EDAC can report statistics on memory error
+	  detection and correction (EDAC - or commonly referred to ECC
+	  errors).  EDAC will also try to decode where these errors
+	  occurred so that a particular failing memory module can be
+	  replaced.  If unsure, select 'Y'.
+
+
+config EDAC_AMD76X
+	tristate "AMD 76x (760, 762, 768)"
+	depends on EDAC_MM_EDAC  && PCI
+	help
+	  Support for error detection and correction on the AMD 76x
+	  series of chipsets used with the Athlon processor.
+
+config EDAC_E7XXX
+	tristate "Intel e7xxx (e7205, e7500, e7501, e7505)"
+	depends on EDAC_MM_EDAC && PCI
+	help
+	  Support for error detection and correction on the Intel
+	  E7205, E7500, E7501 and E7505 server chipsets.
+
+config EDAC_E752X
+	tristate "Intel e752x (e7520, e7525, e7320)"
+	depends on EDAC_MM_EDAC && PCI
+	help
+	  Support for error detection and correction on the Intel
+	  E7520, E7525, E7320 server chipsets.
+
+config EDAC_I82875P
+	tristate "Intel 82875p (D82875P, E7210)"
+	depends on EDAC_MM_EDAC && PCI
+	help
+	  Support for error detection and correction on the Intel
+	  DP82785P and E7210 server chipsets.
+
+config EDAC_I82860
+	tristate "Intel 82860"
+	depends on EDAC_MM_EDAC && PCI
+	help
+	  Support for error detection and correction on the Intel
+	  82860 chipset.
+
+config EDAC_R82600
+	tristate "Radisys 82600 embedded chipset"
+	depends on EDAC_MM_EDAC
+	help
+	  Support for error detection and correction on the Radisys
+	  82600 embedded chipset.
+
+choice
+	prompt "Error detecting method"
+	depends on EDAC
+	default EDAC_POLL
+
+config EDAC_POLL
+	bool "Poll for errors"
+	depends on EDAC
+	help
+	  Poll the chipset periodically to detect errors.
+
+endchoice
+
+endmenu

drivers/edac/Makefile

+#
+# Makefile for the Linux kernel EDAC drivers.
+#
+# Copyright 02 Jul 2003, Linux Networx (http://lnxi.com)
+# This file may be distributed under the terms of the
+# GNU General Public License.
+#
+# $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_AMD76X)		+= amd76x_edac.o
+obj-$(CONFIG_EDAC_E7XXX)		+= e7xxx_edac.o
+obj-$(CONFIG_EDAC_E752X)		+= e752x_edac.o
+obj-$(CONFIG_EDAC_I82875P)		+= i82875p_edac.o
+obj-$(CONFIG_EDAC_I82860)		+= i82860_edac.o
+obj-$(CONFIG_EDAC_R82600)		+= r82600_edac.o
+

drivers/edac/amd76x_edac.c

@@ -338,7 +338,7 @@ static struct pci_driver amd76x_driver = {
 	.id_table = amd76x_pci_tbl,
 };
 
-int __init amd76x_init(void)
+static int __init amd76x_init(void)
 {
 	return pci_register_driver(&amd76x_driver);
 }

drivers/edac/e752x_edac.c

@@ -13,7 +13,7 @@
  * 	Wang Zhenyu at intel.com
  * 	Dave Jiang at mvista.com
  *
- * $Id: bluesmoke_e752x.c,v 1.5.2.11 2005/10/05 00:43:44 dsp_llnl Exp $
+ * $Id: edac_e752x.c,v 1.5.2.11 2005/10/05 00:43:44 dsp_llnl Exp $
  *
  */
 
@@ -376,14 +376,14 @@ static inline void process_threshold_ce(struct mem_ctl_info *mci, u16 error,
 		       mci->mc_idx);
 }
 
-char *global_message[11] = {
+static char *global_message[11] = {
 	"PCI Express C1", "PCI Express C", "PCI Express B1",
 	"PCI Express B", "PCI Express A1", "PCI Express A",
 	"DMA Controler", "HUB Interface", "System Bus",
 	"DRAM Controler", "Internal Buffer"
 };
 
-char *fatal_message[2] = { "Non-Fatal ", "Fatal " };
+static char *fatal_message[2] = { "Non-Fatal ", "Fatal " };
 
 static void do_global_error(int fatal, u32 errors)
 {
@@ -405,7 +405,7 @@ static inline void global_error(int fatal, u32 errors, int *error_found,
 		do_global_error(fatal, errors);
 }
 
-char *hub_message[7] = {
+static char *hub_message[7] = {
 	"HI Address or Command Parity", "HI Illegal Access",
 	"HI Internal Parity", "Out of Range Access",
 	"HI Data Parity", "Enhanced Config Access",
@@ -432,7 +432,7 @@ static inline void hub_error(int fatal, u8 errors, int *error_found,
 		do_hub_error(fatal, errors);
 }
 
-char *membuf_message[4] = {
+static char *membuf_message[4] = {
 	"Internal PMWB to DRAM parity",
 	"Internal PMWB to System Bus Parity",
 	"Internal System Bus or IO to PMWB Parity",
@@ -458,6 +458,7 @@ static inline void membuf_error(u8 errors, int *error_found, int handle_error)
 		do_membuf_error(errors);
 }
 
+#if 0
 char *sysbus_message[10] = {
 	"Addr or Request Parity",
 	"Data Strobe Glitch",
@@ -469,6 +470,7 @@ char *sysbus_message[10] = {
 	"Memory Parity",
 	"IO Subsystem Parity"
 };
+#endif  /*  0  */
 
 static void do_sysbus_error(int fatal, u32 errors)
 {
@@ -1044,7 +1046,7 @@ static struct pci_driver e752x_driver = {
 };
 
 
-int __init e752x_init(void)
+static int __init e752x_init(void)
 {
 	int pci_rc;
 

drivers/edac/e7xxx_edac.c

@@ -537,7 +537,7 @@ static struct pci_driver e7xxx_driver = {
 };
 
 
-int __init e7xxx_init(void)
+static int __init e7xxx_init(void)
 {
 	return pci_register_driver(&e7xxx_driver);
 }

drivers/edac/i82860_edac.c

@@ -253,7 +253,7 @@ static struct pci_driver i82860_driver = {
 	.id_table = i82860_pci_tbl,
 };
 
-int __init i82860_init(void)
+static int __init i82860_init(void)
 {
 	int pci_rc;
 

drivers/edac/i82875p_edac.c

@@ -483,7 +483,7 @@ static struct pci_driver i82875p_driver = {
 };
 
 
-int __init i82875p_init(void)
+static int __init i82875p_init(void)
 {
 	int pci_rc;
 

drivers/edac/r82600_edac.c

@@ -381,7 +381,7 @@ static struct pci_driver r82600_driver = {
 };
 
 
-int __init r82600_init(void)
+static int __init r82600_init(void)
 {
 	return pci_register_driver(&r82600_driver);
 }

include/asm-i386/atomic.h

@@ -255,17 +255,5 @@ __asm__ __volatile__(LOCK "orl %0,%1" \
 #define smp_mb__before_atomic_inc()	barrier()
 #define smp_mb__after_atomic_inc()	barrier()
 
-/* ECC atomic, DMA, SMP and interrupt safe scrub function */
-
-static __inline__ void atomic_scrub(unsigned long *virt_addr, u32 size)
-{
-	u32 i;
-	for (i = 0; i < size / 4; i++, virt_addr++)
-		/* Very carefully read and write to memory atomically
-		 * so we are interrupt, DMA and SMP safe.
-		 */
-		__asm__ __volatile__("lock; addl $0, %0"::"m"(*virt_addr));
-}
-
 #include <asm-generic/atomic.h>
 #endif

include/asm-i386/edac.h

+#ifndef ASM_EDAC_H
+#define ASM_EDAC_H
+
+/* ECC atomic, DMA, SMP and interrupt safe scrub function */
+
+static __inline__ void atomic_scrub(void *va, u32 size)
+{
+	unsigned long *virt_addr = va;
+	u32 i;
+
+	for (i = 0; i < size / 4; i++, virt_addr++)
+		/* Very carefully read and write to memory atomically
+		 * so we are interrupt, DMA and SMP safe.
+		 */
+		__asm__ __volatile__("lock; addl $0, %0"::"m"(*virt_addr));
+}
+
+#endif

include/asm-x86_64/atomic.h

@@ -426,17 +426,5 @@ __asm__ __volatile__(LOCK "orl %0,%1" \
 #define smp_mb__before_atomic_inc()	barrier()
 #define smp_mb__after_atomic_inc()	barrier()
 
-/* ECC atomic, DMA, SMP and interrupt safe scrub function */
-
-static __inline__ void atomic_scrub(u32 *virt_addr, u32 size)
-{
-	u32 i;
-	for (i = 0; i < size / 4; i++, virt_addr++)
-		/* Very carefully read and write to memory atomically
-		 * so we are interrupt, DMA and SMP safe.
-		 */
-		__asm__ __volatile__("lock; addl $0, %0"::"m"(*virt_addr));
-}
-
 #include <asm-generic/atomic.h>
 #endif

include/asm-x86_64/edac.h

+#ifndef ASM_EDAC_H
+#define ASM_EDAC_H
+
+/* ECC atomic, DMA, SMP and interrupt safe scrub function */
+
+static __inline__ void atomic_scrub(void *va, u32 size)
+{
+	unsigned int *virt_addr = va;
+	u32 i;
+
+	for (i = 0; i < size / 4; i++, virt_addr++)
+		/* Very carefully read and write to memory atomically
+		 * so we are interrupt, DMA and SMP safe.
+		 */
+		__asm__ __volatile__("lock; addl $0, %0"::"m"(*virt_addr));
+}
+
+#endif