diff options
author | Douglas Thompson <dougthompson@xmission.com> | 2007-07-19 01:49:33 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@woody.linux-foundation.org> | 2007-07-19 10:04:53 -0700 |
commit | 7c9281d76c1c0b130f79d5fc021084e9749959d4 (patch) | |
tree | 8e54412e8dc529e8bf755633ebe71e35183353d0 /drivers | |
parent | d56933e018b14fc7cad322f413eecc6cb6edf12e (diff) |
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: Douglas Thompson <dougthompson@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'drivers')
-rw-r--r-- | drivers/edac/Makefile | 7 | ||||
-rw-r--r-- | drivers/edac/edac_core.h | 478 | ||||
-rw-r--r-- | drivers/edac/edac_mc.c | 1317 | ||||
-rw-r--r-- | drivers/edac/edac_mc.h | 471 | ||||
-rw-r--r-- | drivers/edac/edac_mc_sysfs.c | 889 | ||||
-rw-r--r-- | drivers/edac/edac_module.c | 130 | ||||
-rw-r--r-- | drivers/edac/edac_module.h | 55 | ||||
-rw-r--r-- | drivers/edac/edac_pci_sysfs.c | 361 |
8 files changed, 1932 insertions, 1776 deletions
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile index 93137fdab4b..51f59aa84d3 100644 --- a/drivers/edac/Makefile +++ b/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 diff --git a/drivers/edac/edac_core.h b/drivers/edac/edac_core.h new file mode 100644 index 00000000000..397f144791e --- /dev/null +++ b/drivers/edac/edac_core.h @@ -0,0 +1,478 @@ +/* + * 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_ */ diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 88bee33e7ec..3be5b7fe79c 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -27,1197 +27,17 @@ #include <linux/list.h> #include <linux/sysdev.h> #include <linux/ctype.h> -#include <linux/kthread.h> -#include <linux/freezer.h> #include <asm/uaccess.h> #include <asm/page.h> #include <asm/edac.h> #include "edac_mc.h" +#include "edac_module.h" -#define EDAC_MC_VERSION "Ver: 2.0.1 " __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 - -/* EDAC Controls, setable by module parameter, and sysfs */ -static int log_ue = 1; -static int log_ce = 1; -static int panic_on_ue; -static int poll_msec = 1000; /* lock to memory controller's control array */ static DECLARE_MUTEX(mem_ctls_mutex); static struct list_head mc_devices = LIST_HEAD_INIT(mc_devices); -static struct task_struct *edac_thread; - -#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; -#endif /* CONFIG_PCI */ - -/* START sysfs data and methods */ - - -static const char *mem_types[] = { - [MEM_EMPTY] = "Empty", - [MEM_RESERVED] = "Reserved", - [MEM_UNKNOWN] = "Unknown", - [MEM_FPM] = "FPM", - [MEM_EDO] = "EDO", - [MEM_BEDO] = "BEDO", - [MEM_SDR] = "Unbuffered-SDR", - [MEM_RDR] = "Registered-SDR", - [MEM_DDR] = "Unbuffered-DDR", - [MEM_RDDR] = "Registered-DDR", - [MEM_RMBS] = "RMBS" -}; - -static const char *dev_types[] = { - [DEV_UNKNOWN] = "Unknown", - [DEV_X1] = "x1", - [DEV_X2] = "x2", - [DEV_X4] = "x4", - [DEV_X8] = "x8", - [DEV_X16] = "x16", - [DEV_X32] = "x32", - [DEV_X64] = "x64" -}; - -static const char *edac_caps[] = { - [EDAC_UNKNOWN] = "Unknown", - [EDAC_NONE] = "None", - [EDAC_RESERVED] = "Reserved", - [EDAC_PARITY] = "PARITY", - [EDAC_EC] = "EC", - [EDAC_SECDED] = "SECDED", - [EDAC_S2ECD2ED] = "S2ECD2ED", - [EDAC_S4ECD4ED] = "S4ECD4ED", - [EDAC_S8ECD8ED] = "S8ECD8ED", - [EDAC_S16ECD16ED] = "S16ECD16ED" -}; - -/* sysfs object: /sys/devices/system/edac */ -static struct sysdev_class edac_class = { - set_kset_name("edac"), -}; - -/* sysfs object: - * /sys/devices/system/edac/mc - */ -static struct kobject edac_memctrl_kobj; - -/* We use these to wait for the reference counts on edac_memctrl_kobj and - * edac_pci_kobj to reach 0. - */ -static struct completion edac_memctrl_kobj_complete; - -/* - * /sys/devices/system/edac/mc; - * data structures and methods - */ -static ssize_t memctrl_int_show(void *ptr, char *buffer) -{ - int *value = (int*) ptr; - return sprintf(buffer, "%u\n", *value); -} - -static ssize_t memctrl_int_store(void *ptr, const char *buffer, size_t count) -{ - int *value = (int*) ptr; - - if (isdigit(*buffer)) - *value = simple_strtoul(buffer, NULL, 0); - - return count; -} - -struct memctrl_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 memory control object */ -static ssize_t memctrl_dev_show(struct kobject *kobj, - struct attribute *attr, char *buffer) -{ - struct memctrl_dev_attribute *memctrl_dev; - memctrl_dev = (struct memctrl_dev_attribute*)attr; - - if (memctrl_dev->show) - return memctrl_dev->show(memctrl_dev->value, buffer); - - return -EIO; -} - -static ssize_t memctrl_dev_store(struct kobject *kobj, struct attribute *attr, - const char *buffer, size_t count) -{ - struct memctrl_dev_attribute *memctrl_dev; - memctrl_dev = (struct memctrl_dev_attribute*)attr; - - if (memctrl_dev->store) - return memctrl_dev->store(memctrl_dev->value, buffer, count); - - return -EIO; -} - -static struct sysfs_ops memctrlfs_ops = { - .show = memctrl_dev_show, - .store = memctrl_dev_store -}; - -#define MEMCTRL_ATTR(_name,_mode,_show,_store) \ -static struct memctrl_dev_attribute attr_##_name = { \ - .attr = {.name = __stringify(_name), .mode = _mode }, \ - .value = &_name, \ - .show = _show, \ - .store = _store, \ -}; - -#define MEMCTRL_STRING_ATTR(_name,_data,_mode,_show,_store) \ -static struct memctrl_dev_attribute attr_##_name = { \ - .attr = {.name = __stringify(_name), .mode = _mode }, \ - .value = _data, \ - .show = _show, \ - .store = _store, \ -}; - -/* csrow<id> control files */ -MEMCTRL_ATTR(panic_on_ue,S_IRUGO|S_IWUSR,memctrl_int_show,memctrl_int_store); -MEMCTRL_ATTR(log_ue,S_IRUGO|S_IWUSR,memctrl_int_show,memctrl_int_store); -MEMCTRL_ATTR(log_ce,S_IRUGO|S_IWUSR,memctrl_int_show,memctrl_int_store); -MEMCTRL_ATTR(poll_msec,S_IRUGO|S_IWUSR,memctrl_int_show,memctrl_int_store); - -/* Base Attributes of the memory ECC object */ -static struct memctrl_dev_attribute *memctrl_attr[] = { - &attr_panic_on_ue, - &attr_log_ue, - &attr_log_ce, - &attr_poll_msec, - NULL, -}; - -/* Main MC kobject release() function */ -static void edac_memctrl_master_release(struct kobject *kobj) -{ - debugf1("%s()\n", __func__); - complete(&edac_memctrl_kobj_complete); -} - -static struct kobj_type ktype_memctrl = { - .release = edac_memctrl_master_release, - .sysfs_ops = &memctrlfs_ops, - .default_attrs = (struct attribute **) memctrl_attr, -}; - -/* Initialize the main sysfs entries for edac: - * /sys/devices/system/edac - * - * and children - * - * Return: 0 SUCCESS - * !0 FAILURE - */ -static int edac_sysfs_memctrl_setup(void) -{ - int err = 0; - - debugf1("%s()\n", __func__); - - /* create the /sys/devices/system/edac directory */ - err = sysdev_class_register(&edac_class); - - if (err) { - debugf1("%s() error=%d\n", __func__, err); - return err; - } - - /* Init the MC's kobject */ - memset(&edac_memctrl_kobj, 0, sizeof (edac_memctrl_kobj)); - edac_memctrl_kobj.parent = &edac_class.kset.kobj; - edac_memctrl_kobj.ktype = &ktype_memctrl; - - /* generate sysfs "..../edac/mc" */ - err = kobject_set_name(&edac_memctrl_kobj,"mc"); - - if (err) - goto fail; - - /* FIXME: maybe new sysdev_create_subdir() */ - err = kobject_register(&edac_memctrl_kobj); - - if (err) { - debugf1("Failed to register '.../edac/mc'\n"); - goto fail; - } - - debugf1("Registered '.../edac/mc' kobject\n"); - - return 0; - -fail: - sysdev_class_unregister(&edac_class); - return err; -} - -/* - * MC teardown: - * the '..../edac/mc' kobject followed by '..../edac' itself - */ -static void edac_sysfs_memctrl_teardown(void) -{ - debugf0("MC: " __FILE__ ": %s()\n", __func__); - - /* Unregister the MC's kobject and wait for reference count to reach - * 0. - */ - init_completion(&edac_memctrl_kobj_complete); - kobject_unregister(&edac_memctrl_kobj); - wait_for_completion(&edac_memctrl_kobj_complete); - - /* Unregister the 'edac' object */ - sysdev_class_unregister(&edac_class); -} - -#ifdef CONFIG_PCI -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() - * - */ -static int edac_sysfs_pci_setup(void) -{ - int err; - - debugf1("%s()\n", __func__); - - 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 csrow 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; -} - -static 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); - } -} - -static void do_pci_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"); - } -} - -static inline void clear_pci_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); -} - -#else /* CONFIG_PCI */ - -/* pre-process these away */ -#define do_pci_parity_check() -#define clear_pci_parity_errors() -#define edac_sysfs_pci_teardown() -#define edac_sysfs_pci_setup() (0) - -#endif /* CONFIG_PCI */ - -/* EDAC sysfs CSROW data structures and methods - */ - -/* Set of more default csrow<id> attribute show/store functions */ -static ssize_t csrow_ue_count_show(struct csrow_info *csrow, char *data, int private) -{ - return sprintf(data,"%u\n", csrow->ue_count); -} - -static ssize_t csrow_ce_count_show(struct csrow_info *csrow, char *data, int private) -{ - return sprintf(data,"%u\n", csrow->ce_count); -} - -static ssize_t csrow_size_show(struct csrow_info *csrow, char *data, int private) -{ - return sprintf(data,"%u\n", PAGES_TO_MiB(csrow->nr_pages)); -} - -static ssize_t csrow_mem_type_show(struct csrow_info *csrow, char *data, int private) -{ - return sprintf(data,"%s\n", mem_types[csrow->mtype]); -} - -static ssize_t csrow_dev_type_show(struct csrow_info *csrow, char *data, int private) -{ - return sprintf(data,"%s\n", dev_types[csrow->dtype]); -} - -static ssize_t csrow_edac_mode_show(struct csrow_info *csrow, char *data, int private) -{ - return sprintf(data,"%s\n", edac_caps[csrow->edac_mode]); -} - -/* show/store functions for DIMM Label attributes */ -static ssize_t channel_dimm_label_show(struct csrow_info *csrow, - char *data, int channel) -{ - return snprintf(data, EDAC_MC_LABEL_LEN,"%s", - csrow->channels[channel].label); -} - -static ssize_t channel_dimm_label_store(struct csrow_info *csrow, - const char *data, - size_t count, - int channel) -{ - ssize_t max_size = 0; - - max_size = min((ssize_t)count,(ssize_t)EDAC_MC_LABEL_LEN-1); - strncpy(csrow->channels[channel].label, data, max_size); - csrow->channels[channel].label[max_size] = '\0'; - - return max_size; -} - -/* show function for dynamic chX_ce_count attribute */ -static ssize_t channel_ce_count_show(struct csrow_info *csrow, - char *data, - int channel) -{ - return sprintf(data, "%u\n", csrow->channels[channel].ce_count); -} - -/* csrow specific attribute structure */ -struct csrowdev_attribute { - struct attribute attr; - ssize_t (*show)(struct csrow_info *,char *,int); - ssize_t (*store)(struct csrow_info *, const char *,size_t,int); - int private; -}; - -#define to_csrow(k) container_of(k, struct csrow_info, kobj) -#define to_csrowdev_attr(a) container_of(a, struct csrowdev_attribute, attr) - -/* Set of show/store higher level functions for default csrow attributes */ -static ssize_t csrowdev_show(struct kobject *kobj, - struct attribute *attr, - char *buffer) -{ - struct csrow_info *csrow = to_csrow(kobj); - struct csrowdev_attribute *csrowdev_attr = to_csrowdev_attr(attr); - - if (csrowdev_attr->show) - return csrowdev_attr->show(csrow, - buffer, - csrowdev_attr->private); - return -EIO; -} - -static ssize_t csrowdev_store(struct kobject *kobj, struct attribute *attr, - const char *buffer, size_t count) -{ - struct csrow_info *csrow = to_csrow(kobj); - struct csrowdev_attribute * csrowdev_attr = to_csrowdev_attr(attr); - - if (csrowdev_attr->store) - return csrowdev_attr->store(csrow, - buffer, - count, - csrowdev_attr->private); - return -EIO; -} - -static struct sysfs_ops csrowfs_ops = { - .show = csrowdev_show, - .store = csrowdev_store -}; - -#define CSROWDEV_ATTR(_name,_mode,_show,_store,_private) \ -static struct csrowdev_attribute attr_##_name = { \ - .attr = {.name = __stringify(_name), .mode = _mode }, \ - .show = _show, \ - .store = _store, \ - .private = _private, \ -}; - -/* default cwrow<id>/attribute files */ -CSROWDEV_ATTR(size_mb,S_IRUGO,csrow_size_show,NULL,0); -CSROWDEV_ATTR(dev_type,S_IRUGO,csrow_dev_type_show,NULL,0); -CSROWDEV_ATTR(mem_type,S_IRUGO,csrow_mem_type_show,NULL,0); -CSROWDEV_ATTR(edac_mode,S_IRUGO,csrow_edac_mode_show,NULL,0); -CSROWDEV_ATTR(ue_count,S_IRUGO,csrow_ue_count_show,NULL,0); -CSROWDEV_ATTR(ce_count,S_IRUGO,csrow_ce_count_show,NULL,0); - -/* default attributes of the CSROW<id> object */ -static struct csrowdev_attribute *default_csrow_attr[] = { - &attr_dev_type, - &attr_mem_type, - &attr_edac_mode, - &attr_size_mb, - &attr_ue_count, - &attr_ce_count, - NULL, -}; - - -/* possible dynamic channel DIMM Label attribute files */ -CSROWDEV_ATTR(ch0_dimm_label,S_IRUGO|S_IWUSR, - channel_dimm_label_show, - channel_dimm_label_store, - 0 ); -CSROWDEV_ATTR(ch1_dimm_label,S_IRUGO|S_IWUSR, - channel_dimm_label_show, - channel_dimm_label_store, - 1 ); -CSROWDEV_ATTR(ch2_dimm_label,S_IRUGO|S_IWUSR, - channel_dimm_label_show, - channel_dimm_label_store, - 2 ); -CSROWDEV_ATTR(ch3_dimm_label,S_IRUGO|S_IWUSR, - channel_dimm_label_show, - channel_dimm_label_store, - 3 ); -CSROWDEV_ATTR(ch4_dimm_label,S_IRUGO|S_IWUSR, - channel_dimm_label_show, - channel_dimm_label_store, - 4 ); -CSROWDEV_ATTR(ch5_dimm_label,S_IRUGO|S_IWUSR, - channel_dimm_label_show, - channel_dimm_label_store, - 5 ); - -/* Total possible dynamic DIMM Label attribute file table */ -static struct csrowdev_attribute *dynamic_csrow_dimm_attr[] = { - &attr_ch0_dimm_label, - &attr_ch1_dimm_label, - &attr_ch2_dimm_label, - &attr_ch3_dimm_label, - &attr_ch4_dimm_label, - &attr_ch5_dimm_label -}; - -/* possible dynamic channel ce_count attribute files */ -CSROWDEV_ATTR(ch0_ce_count,S_IRUGO|S_IWUSR, - channel_ce_count_show, - NULL, - 0 ); -CSROWDEV_ATTR(ch1_ce_count,S_IRUGO|S_IWUSR, - channel_ce_count_show, - NULL, - 1 ); -CSROWDEV_ATTR(ch2_ce_count,S_IRUGO|S_IWUSR, - channel_ce_count_show, - NULL, - 2 ); -CSROWDEV_ATTR(ch3_ce_count,S_IRUGO|S_IWUSR, - channel_ce_count_show, - NULL, - 3 ); -CSROWDEV_ATTR(ch4_ce_count,S_IRUGO|S_IWUSR, - channel_ce_count_show, - NULL, - 4 ); -CSROWDEV_ATTR(ch5_ce_count,S_IRUGO|S_IWUSR, - channel_ce_count_show, - NULL, - 5 ); - -/* Total possible dynamic ce_count attribute file table */ -static struct csrowdev_attribute *dynamic_csrow_ce_count_attr[] = { - &attr_ch0_ce_count, - &attr_ch1_ce_count, - &attr_ch2_ce_count, - &attr_ch3_ce_count, - &attr_ch4_ce_count, - &attr_ch5_ce_count -}; - - -#define EDAC_NR_CHANNELS 6 - -/* Create dynamic CHANNEL files, indexed by 'chan', under specifed CSROW */ -static int edac_create_channel_files(struct kobject *kobj, int chan) -{ - int err=-ENODEV; - - if (chan >= EDAC_NR_CHANNELS) - return err; - - /* create the DIMM label attribute file */ - err = sysfs_create_file(kobj, - (struct attribute *) dynamic_csrow_dimm_attr[chan]); - - if (!err) { - /* create the CE Count attribute file */ - err = sysfs_create_file(kobj, - (struct attribute *) dynamic_csrow_ce_count_attr[chan]); - } else { - debugf1("%s() dimm labels and ce_count files created", __func__); - } - - return err; -} - -/* No memory to release for this kobj */ -static void edac_csrow_instance_release(struct kobject *kobj) -{ - struct csrow_info *cs; - - cs = container_of(kobj, struct csrow_info, kobj); - complete(&cs->kobj_complete); -} - -/* the kobj_type instance for a CSROW */ -static struct kobj_type ktype_csrow = { - .release = edac_csrow_instance_release, - .sysfs_ops = &csrowfs_ops, - .default_attrs = (struct attribute **) default_csrow_attr, -}; - -/* Create a CSROW object under specifed edac_mc_device */ -static int edac_create_csrow_object( - struct kobject *edac_mci_kobj, - struct csrow_info *csrow, - int index) -{ - int err = 0; - int chan; - - memset(&csrow->kobj, 0, sizeof(csrow->kobj)); - - /* generate ..../edac/mc/mc<id>/csrow<index> */ - - csrow->kobj.parent = edac_mci_kobj; - csrow->kobj.ktype = &ktype_csrow; - - /* name this instance of csrow<id> */ - err = kobject_set_name(&csrow->kobj,"csrow%d",index); - if (err) - goto error_exit; - - /* Instanstiate the csrow object */ - err = kobject_register(&csrow->kobj); - if (!err) { - /* Create the dyanmic attribute files on this csrow, - * namely, the DIMM labels and the channel ce_count - */ - for (chan = 0; chan < csrow->nr_channels; chan++) { - err = edac_create_channel_files(&csrow->kobj,chan); - if (err) - break; - } - } - -error_exit: - return err; -} - -/* default sysfs methods and data structures for the main MCI kobject */ - -static ssize_t mci_reset_counters_store(struct mem_ctl_info *mci, - const char *data, size_t count) -{ - int row, chan; - - mci->ue_noinfo_count = 0; - mci->ce_noinfo_count = 0; - mci->ue_count = 0; - mci->ce_count = 0; - - for (row = 0; row < mci->nr_csrows; row++) { - struct csrow_info *ri = &mci->csrows[row]; - - ri->ue_count = 0; - ri->ce_count = 0; - - for (chan = 0; chan < ri->nr_channels; chan++) - ri->channels[chan].ce_count = 0; - } - - mci->start_time = jiffies; - return count; -} - -/* memory scrubbing */ -static ssize_t mci_sdram_scrub_rate_store(struct mem_ctl_info *mci, - const char *data, size_t count) -{ - u32 bandwidth = -1; - - if (mci->set_sdram_scrub_rate) { - - memctrl_int_store(&bandwidth, data, count); - - if (!(*mci->set_sdram_scrub_rate)(mci, &bandwidth)) { - edac_printk(KERN_DEBUG, EDAC_MC, - "Scrub rate set successfully, applied: %d\n", - bandwidth); - } else { - /* FIXME: error codes maybe? */ - edac_printk(KERN_DEBUG, EDAC_MC, - "Scrub rate set FAILED, could not apply: %d\n", - bandwidth); - } - } else { - /* FIXME: produce "not implemented" ERROR for user-side. */ - edac_printk(KERN_WARNING, EDAC_MC, - "Memory scrubbing 'set'control is not implemented!\n"); - } - return count; -} - -static ssize_t mci_sdram_scrub_rate_show(struct mem_ctl_info *mci, char *data) -{ - u32 bandwidth = -1; - - if (mci->get_sdram_scrub_rate) { - if (!(*mci->get_sdram_scrub_rate)(mci, &bandwidth)) { - edac_printk(KERN_DEBUG, EDAC_MC, - "Scrub rate successfully, fetched: %d\n", - bandwidth); - } else { - /* FIXME: error codes maybe? */ - edac_printk(KERN_DEBUG, EDAC_MC, - "Scrub rate fetch FAILED, got: %d\n", - bandwidth); - } - } else { - /* FIXME: produce "not implemented" ERROR for user-side. */ - edac_printk(KERN_WARNING, EDAC_MC, - "Memory scrubbing 'get' control is not implemented!\n"); - } - return sprintf(data, "%d\n", bandwidth); -} - -/* default attribute files for the MCI object */ -static ssize_t mci_ue_count_show(struct mem_ctl_info *mci, char *data) -{ - return sprintf(data,"%d\n", mci->ue_count); -} - -static ssize_t mci_ce_count_show(struct mem_ctl_info *mci, char *data) -{ - return sprintf(data,"%d\n", mci->ce_count); -} - -static ssize_t mci_ce_noinfo_show(struct mem_ctl_info *mci, char *data) -{ - return sprintf(data,"%d\n", mci->ce_noinfo_count); -} - -static ssize_t mci_ue_noinfo_show(struct mem_ctl_info *mci, char *data) -{ - return sprintf(data,"%d\n", mci->ue_noinfo_count); -} - -static ssize_t mci_seconds_show(struct mem_ctl_info *mci, char *data) -{ - return sprintf(data,"%ld\n", (jiffies - mci->start_time) / HZ); -} - -static ssize_t mci_ctl_name_show(struct mem_ctl_info *mci, char *data) -{ - return sprintf(data,"%s\n", mci->ctl_name); -} - -static ssize_t mci_size_mb_show(struct mem_ctl_info *mci, char *data) -{ - int total_pages, csrow_idx; - - for (total_pages = csrow_idx = 0; csrow_idx < mci->nr_csrows; - csrow_idx++) { - struct csrow_info *csrow = &mci->csrows[csrow_idx]; - - if (!csrow->nr_pages) - continue; - - total_pages += csrow->nr_pages; - } - - return sprintf(data,"%u\n", PAGES_TO_MiB(total_pages)); -} - -struct mcidev_attribute { - struct attribute attr; - ssize_t (*show)(struct mem_ctl_info *,char *); - ssize_t (*store)(struct mem_ctl_info *, const char *,size_t); -}; - -#define to_mci(k) container_of(k, struct mem_ctl_info, edac_mci_kobj) -#define to_mcidev_attr(a) container_of(a, struct mcidev_attribute, attr) - -/* MCI show/store functions for top most object */ -static ssize_t mcidev_show(struct kobject *kobj, struct attribute *attr, - char *buffer) -{ - struct mem_ctl_info *mem_ctl_info = to_mci(kobj); - struct mcidev_attribute * mcidev_attr = to_mcidev_attr(attr); - - if (mcidev_attr->show) - return mcidev_attr->show(mem_ctl_info, buffer); - - return -EIO; -} - -static ssize_t mcidev_store(struct kobject *kobj, struct attribute *attr, - const char *buffer, size_t count) -{ - struct mem_ctl_info *mem_ctl_info = to_mci(kobj); - struct mcidev_attribute * mcidev_attr = to_mcidev_attr(attr); - - if (mcidev_attr->store) - return mcidev_attr->store(mem_ctl_info, buffer, count); - - return -EIO; -} - -static struct sysfs_ops mci_ops = { - .show = mcidev_show, - .store = mcidev_store -}; - -#define MCIDEV_ATTR(_name,_mode,_show,_store) \ -static struct mcidev_attribute mci_attr_##_name = { \ - .attr = {.name = __stringify(_name), .mode = _mode }, \ - .show = _show, \ - .store = _store, \ -}; - -/* default Control file */ -MCIDEV_ATTR(reset_counters,S_IWUSR,NULL,mci_reset_counters_store); - -/* default Attribute files */ -MCIDEV_ATTR(mc_name,S_IRUGO,mci_ctl_name_show,NULL); -MCIDEV_ATTR(size_mb,S_IRUGO,mci_size_mb_show,NULL); -MCIDEV_ATTR(seconds_since_reset,S_IRUGO,mci_seconds_show,NULL); -MCIDEV_ATTR(ue_noinfo_count,S_IRUGO,mci_ue_noinfo_show,NULL); -MCIDEV_ATTR(ce_noinfo_count,S_IRUGO,mci_ce_noinfo_show,NULL); -MCIDEV_ATTR(ue_count,S_IRUGO,mci_ue_count_show,NULL); -MCIDEV_ATTR(ce_count,S_IRUGO,mci_ce_count_show,NULL); - -/* memory scrubber attribute file */ -MCIDEV_ATTR(sdram_scrub_rate,S_IRUGO|S_IWUSR,mci_sdram_scrub_rate_show,mci_sdram_scrub_rate_store); - -static struct mcidev_attribute *mci_attr[] = { - &mci_attr_reset_counters, - &mci_attr_mc_name, - &mci_attr_size_mb, - &mci_attr_seconds_since_reset, - &mci_attr_ue_noinfo_count, - &mci_attr_ce_noinfo_count, - &mci_attr_ue_count, - &mci_attr_ce_count, - &mci_attr_sdram_scrub_rate, - NULL -}; - -/* - * Release of a MC controlling instance - */ -static void edac_mci_instance_release(struct kobject *kobj) -{ - struct mem_ctl_info *mci; - - mci = to_mci(kobj); - debugf0("%s() idx=%d\n", __func__, mci->mc_idx); - complete(&mci->kobj_complete); -} - -static struct kobj_type ktype_mci = { - .release = edac_mci_instance_release, - .sysfs_ops = &mci_ops, - .default_attrs = (struct attribute **) mci_attr, -}; - - -#define EDAC_DEVICE_SYMLINK "device" - -/* - * Create a new Memory Controller kobject instance, - * mc<id> under the 'mc' directory - * - * Return: - * 0 Success - * !0 Failure - */ -static int edac_create_sysfs_mci_device(struct mem_ctl_info *mci) -{ - int i; - int err; - struct csrow_info *csrow; - struct kobject *edac_mci_kobj=&mci->edac_mci_kobj; - - debugf0("%s() idx=%d\n", __func__, mci->mc_idx); - memset(edac_mci_kobj, 0, sizeof(*edac_mci_kobj)); - - /* set the name of the mc<id> object */ - err = kobject_set_name(edac_mci_kobj,"mc%d",mci->mc_idx); - if (err) - return err; - - /* link to our parent the '..../edac/mc' object */ - edac_mci_kobj->parent = &edac_memctrl_kobj; - edac_mci_kobj->ktype = &ktype_mci; - - /* register the mc<id> kobject */ - err = kobject_register(edac_mci_kobj); - if (err) - return err; - - /* create a symlink for the device */ - err = sysfs_create_link(edac_mci_kobj, &mci->dev->kobj, - EDAC_DEVICE_SYMLINK); - if (err) - goto fail0; - - /* Make directories for each CSROW object - * under the mc<id> kobject - */ - for (i = 0; i < mci->nr_csrows; i++) { - csrow = &mci->csrows[i]; - - /* Only expose populated CSROWs */ - if (csrow->nr_pages > 0) { - err = edac_create_csrow_object(edac_mci_kobj,csrow,i); - if (err) - goto fail1; - } - } - - return 0; - - /* CSROW error: backout what has already been registered, */ -fail1: - for ( i--; i >= 0; i--) { - if (csrow->nr_pages > 0) { - init_completion(&csrow->kobj_complete); - kobject_unregister(&mci->csrows[i].kobj); - wait_for_completion(&csrow->kobj_complete); - } - } - -fail0: - init_completion(&mci->kobj_complete); - kobject_unregister(edac_mci_kobj); - wait_for_completion(&mci->kobj_complete); - return err; -} - -/* - * remove a Memory Controller instance - */ -static void edac_remove_sysfs_mci_device(struct mem_ctl_info *mci) -{ - int i; - - debugf0("%s()\n", __func__); - - /* remove all csrow kobjects */ - for (i = 0; i < mci->nr_csrows; i++) { - if (mci->csrows[i].nr_pages > 0) { - init_completion(&mci->csrows[i].kobj_complete); - kobject_unregister(&mci->csrows[i].kobj); - wait_for_completion(&mci->csrows[i].kobj_complete); - } - } - - sysfs_remove_link(&mci->edac_mci_kobj, EDAC_DEVICE_SYMLINK); - init_completion(&mci->kobj_complete); - kobject_unregister(&mci->edac_mci_kobj); - wait_for_completion(&mci->kobj_complete); -} - -/* END OF sysfs data and methods */ - #ifdef CONFIG_EDAC_DEBUG static void edac_mc_dump_channel(struct channel_info *chan) @@ -1672,7 +492,7 @@ void edac_mc_handle_ce(struct mem_ctl_info *mci, return; } - if (log_ce) + if (edac_get_log_ce()) /* FIXME - put in DIMM location */ edac_mc_printk(mci, KERN_WARNING, "CE page 0x%lx, offset 0x%lx, grain %d, syndrome " @@ -1707,7 +527,7 @@ EXPORT_SYMBOL_GPL(edac_mc_handle_ce); void edac_mc_handle_ce_no_info(struct mem_ctl_info *mci, const char *msg) { - if (log_ce) + if (edac_get_log_ce()) edac_mc_printk(mci, KERN_WARNING, "CE - no information available: %s\n", msg); @@ -1751,14 +571,14 @@ void edac_mc_handle_ue(struct mem_ctl_info *mci, pos += chars; } - if (log_ue) + if (edac_get_log_ue()) edac_mc_printk(mci, KERN_EMERG, "UE page 0x%lx, offset 0x%lx, grain %d, row %d, " "labels \"%s\": %s\n", page_frame_number, offset_in_page, mci->csrows[row].grain, row, labels, msg); - if (panic_on_ue) + if (edac_get_panic_on_ue()) panic("EDAC MC%d: UE page 0x%lx, offset 0x%lx, grain %d, " "row %d, labels \"%s\": %s\n", mci->mc_idx, page_frame_number, offset_in_page, @@ -1771,10 +591,10 @@ EXPORT_SYMBOL_GPL(edac_mc_handle_ue); void edac_mc_handle_ue_no_info(struct mem_ctl_info *mci, const char *msg) { - if (panic_on_ue) + if (edac_get_panic_on_ue()) panic("EDAC MC%d: Uncorrected Error", mci->mc_idx); - if (log_ue) + if (edac_get_log_ue()) edac_mc_printk(mci, KERN_WARNING, "UE - no information available: %s\n", msg); mci->ue_noinfo_count++; @@ -1837,13 +657,13 @@ void edac_mc_handle_fbd_ue(struct mem_ctl_info *mci, chars = snprintf(pos, len + 1, "-%s", mci->csrows[csrow].channels[channelb].label); - if (log_ue) + if (edac_get_log_ue()) edac_mc_printk(mci, KERN_EMERG, "UE row %d, channel-a= %d channel-b= %d " "labels \"%s\": %s\n", csrow, channela, channelb, labels, msg); - if (panic_on_ue) + if (edac_get_panic_on_ue()) panic("UE row %d, channel-a= %d channel-b= %d " "labels \"%s\": %s\n", csrow, channela, channelb, labels, msg); @@ -1878,7 +698,7 @@ void edac_mc_handle_fbd_ce(struct mem_ctl_info *mci, return; } - if (log_ce) + if (edac_get_log_ce()) /* FIXME - put in DIMM location */ edac_mc_printk(mci, KERN_WARNING, "CE row %d, channel %d, label \"%s\": %s\n", @@ -1896,7 +716,7 @@ EXPORT_SYMBOL(edac_mc_handle_fbd_ce); /* * Iterate over all MC instances and check for ECC, et al, errors */ -static inline void check_mc_devices(void) +void edac_check_mc_devices(void) { struct list_head *item; struct mem_ctl_info *mci; @@ -1913,118 +733,3 @@ static inline void check_mc_devices(void) up(&mem_ctls_mutex); } - -/* - * Check MC status every poll_msec. - * Check PCI status every 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__); - check_mc_devices(); - do_pci_parity_check(); -} - -static int edac_kernel_thread(void *arg) -{ - set_freezable(); - while (!kthread_should_stop()) { - do_edac_check(); - - /* goto sleep for the interval */ - schedule_timeout_interruptible((HZ * poll_msec) / 1000); - try_to_freeze(); - } - - return 0; -} - -/* - * edac_mc_init - * module initialization entry point - */ -static int __init edac_mc_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. - */ - clear_pci_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, - "EDAC 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_mc_exit() - * module exit/termination functioni - */ -static void __exit edac_mc_exit(void) -{ - debugf0("%s()\n", __func__); - kthread_stop(edac_thread); - - /* tear down the sysfs device */ - edac_sysfs_memctrl_teardown(); - edac_sysfs_pci_teardown(); -} - -module_init(edac_mc_init); -module_exit(edac_mc_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Linux Networx (http://lnxi.com) Thayne Harbaugh et al\n" - "Based on work by Dan Hollis et al"); -MODULE_DESCRIPTION("Core library routines for MC reporting"); - -module_param(panic_on_ue, int, 0644); -MODULE_PARM_DESC(panic_on_ue, "Panic on uncorrected error: 0=off 1=on"); -#ifdef CONFIG_PCI -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 -module_param(log_ue, int, 0644); -MODULE_PARM_DESC(log_ue, "Log uncorrectable error to console: 0=off 1=on"); -module_param(log_ce, int, 0644); -MODULE_PARM_DESC(log_ce, "Log correctable error to console: 0=off 1=on"); -module_param(poll_msec, int, 0644); -MODULE_PARM_DESC(poll_msec, "Polling period in milliseconds"); -#ifdef CONFIG_EDAC_DEBUG -module_param(edac_debug_level, int, 0644); -MODULE_PARM_DESC(edac_debug_level, "Debug level"); -#endif diff --git a/drivers/edac/edac_mc.h b/drivers/edac/edac_mc.h index fdc811d8967..b92d2720a4d 100644 --- a/drivers/edac/edac_mc.h +++ b/drivers/edac/edac_mc.h @@ -1,476 +1,9 @@ -/* - * 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_ */ diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c new file mode 100644 index 00000000000..4a5e335f61d --- /dev/null +++ b/drivers/edac/edac_mc_sysfs.c @@ -0,0 +1,889 @@ +/* + * 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" + +/* MC EDAC Controls, setable by module parameter, and sysfs */ +static int log_ue = 1; +static int log_ce = 1; +static int panic_on_ue; +static int poll_msec = 1000; + +/* Getter functions for above */ +int edac_get_log_ue() +{ + return log_ue; +} + +int edac_get_log_ce() +{ + return log_ce; +} + +int edac_get_panic_on_ue() +{ + return panic_on_ue; +} + +int edac_get_poll_msec() +{ + return poll_msec; +} + +/* Parameter declarations for above */ +module_param(panic_on_ue, int, 0644); +MODULE_PARM_DESC(panic_on_ue, "Panic on uncorrected error: 0=off 1=on"); +module_param(log_ue, int, 0644); +MODULE_PARM_DESC(log_ue, "Log uncorrectable error to console: 0=off 1=on"); +module_param(log_ce, int, 0644); +MODULE_PARM_DESC(log_ce, "Log correctable error to console: 0=off 1=on"); +module_param(poll_msec, int, 0644); +MODULE_PARM_DESC(poll_msec, "Polling period in milliseconds"); + + +/* + * various constants for Memory Controllers + */ +static const char *mem_types[] = { + [MEM_EMPTY] = "Empty", + [MEM_RESERVED] = "Reserved", + [MEM_UNKNOWN] = "Unknown", + [MEM_FPM] = "FPM", + [MEM_EDO] = "EDO", + [MEM_BEDO] = "BEDO", + [MEM_SDR] = "Unbuffered-SDR", + [MEM_RDR] = "Registered-SDR", + [MEM_DDR] = "Unbuffered-DDR", + [MEM_RDDR] = "Registered-DDR", + [MEM_RMBS] = "RMBS" +}; + +static const char *dev_types[] = { + [DEV_UNKNOWN] = "Unknown", + [DEV_X1] = "x1", + [DEV_X2] = "x2", + [DEV_X4] = "x4", + [DEV_X8] = "x8", + [DEV_X16] = "x16", + [DEV_X32] = "x32", + [DEV_X64] = "x64" +}; + +static const char *edac_caps[] = { + [EDAC_UNKNOWN] = "Unknown", + [EDAC_NONE] = "None", + [EDAC_RESERVED] = "Reserved", + [EDAC_PARITY] = "PARITY", + [EDAC_EC] = "EC", + [EDAC_SECDED] = "SECDED", + [EDAC_S2ECD2ED] = "S2ECD2ED", + [EDAC_S4ECD4ED] = "S4ECD4ED", + [EDAC_S8ECD8ED] = "S8ECD8ED", + [EDAC_S16ECD16ED] = "S16ECD16ED" +}; + +/* + * sysfs object: /sys/devices/system/edac + * need to export to other files in this modules + */ +struct sysdev_class edac_class = { + set_kset_name("edac"), +}; + +/* sysfs object: + * /sys/devices/system/edac/mc + */ +static struct kobject edac_memctrl_kobj; + +/* We use these to wait for the reference counts on edac_memctrl_kobj and + * edac_pci_kobj to reach 0. + */ +static struct completion edac_memctrl_kobj_complete; + +/* + * /sys/devices/system/edac/mc; + * data structures and methods + */ +static ssize_t memctrl_int_show(void *ptr, char *buffer) +{ + int *value = (int*) ptr; + return sprintf(buffer, "%u\n", *value); +} + +static ssize_t memctrl_int_store(void *ptr, const char *buffer, size_t count) +{ + int *value = (int*) ptr; + + if (isdigit(*buffer)) + *value = simple_strtoul(buffer, NULL, 0); + + return count; +} + +struct memctrl_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 memory control object */ +static ssize_t memctrl_dev_show(struct kobject *kobj, + struct attribute *attr, char *buffer) +{ + struct memctrl_dev_attribute *memctrl_dev; + memctrl_dev = (struct memctrl_dev_attribute*)attr; + + if (memctrl_dev->show) + return memctrl_dev->show(memctrl_dev->value, buffer); + + return -EIO; +} + +static ssize_t memctrl_dev_store(struct kobject *kobj, struct attribute *attr, + const char *buffer, size_t count) +{ + struct memctrl_dev_attribute *memctrl_dev; + memctrl_dev = (struct memctrl_dev_attribute*)attr; + + if (memctrl_dev->store) + return memctrl_dev->store(memctrl_dev->value, buffer, count); + + return -EIO; +} + +static struct sysfs_ops memctrlfs_ops = { + .show = memctrl_dev_show, + .store = memctrl_dev_store +}; + +#define MEMCTRL_ATTR(_name,_mode,_show,_store) \ +static struct memctrl_dev_attribute attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = _mode }, \ + .value = &_name, \ + .show = _show, \ + .store = _store, \ +}; + +#define MEMCTRL_STRING_ATTR(_name,_data,_mode,_show,_store) \ +static struct memctrl_dev_attribute attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = _mode }, \ + .value = _data, \ + .show = _show, \ + .store = _store, \ +}; + +/* csrow<id> control files */ +MEMCTRL_ATTR(panic_on_ue,S_IRUGO|S_IWUSR,memctrl_int_show,memctrl_int_store); +MEMCTRL_ATTR(log_ue,S_IRUGO|S_IWUSR,memctrl_int_show,memctrl_int_store); +MEMCTRL_ATTR(log_ce,S_IRUGO|S_IWUSR,memctrl_int_show,memctrl_int_store); +MEMCTRL_ATTR(poll_msec,S_IRUGO|S_IWUSR,memctrl_int_show,memctrl_int_store); + +/* Base Attributes of the memory ECC object */ +static struct memctrl_dev_attribute *memctrl_attr[] = { + &attr_panic_on_ue, + &attr_log_ue, + &attr_log_ce, + &attr_poll_msec, + NULL, +}; + +/* Main MC kobject release() function */ +static void edac_memctrl_master_release(struct kobject *kobj) +{ + debugf1("%s()\n", __func__); + complete(&edac_memctrl_kobj_complete); +} + +static struct kobj_type ktype_memctrl = { + .release = edac_memctrl_master_release, + .sysfs_ops = &memctrlfs_ops, + .default_attrs = (struct attribute **) memctrl_attr, +}; + +/* Initialize the main sysfs entries for edac: + * /sys/devices/system/edac + * + * and children + * + * Return: 0 SUCCESS + * !0 FAILURE + */ +int edac_sysfs_memctrl_setup(void) +{ + int err = 0; + + debugf1("%s()\n", __func__); + + /* create the /sys/devices/system/edac directory */ + err = sysdev_class_register(&edac_class); + + if (err) { + debugf1("%s() error=%d\n", __func__, err); + return err; + } + + /* Init the MC's kobject */ + memset(&edac_memctrl_kobj, 0, sizeof (edac_memctrl_kobj)); + edac_memctrl_kobj.parent = &edac_class.kset.kobj; + edac_memctrl_kobj.ktype = &ktype_memctrl; + + /* generate sysfs "..../edac/mc" */ + err = kobject_set_name(&edac_memctrl_kobj,"mc"); + + if (err) + goto fail; + + /* FIXME: maybe new sysdev_create_subdir() */ + err = kobject_register(&edac_memctrl_kobj); + + if (err) { + debugf1("Failed to register '.../edac/mc'\n"); + goto fail; + } + + debugf1("Registered '.../edac/mc' kobject\n"); + + return 0; + +fail: + sysdev_class_unregister(&edac_class); + return err; +} + +/* + * MC teardown: + * the '..../edac/mc' kobject followed by '..../edac' itself + */ +void edac_sysfs_memctrl_teardown(void) +{ + debugf0("MC: " __FILE__ ": %s()\n", __func__); + + /* Unregister the MC's kobject and wait for reference count to reach 0. + */ + init_completion(&edac_memctrl_kobj_complete); + kobject_unregister(&edac_memctrl_kobj); + wait_for_completion(&edac_memctrl_kobj_complete); + + /* Unregister the 'edac' object */ + sysdev_class_unregister(&edac_class); +} + + +/* EDAC sysfs CSROW data structures and methods + */ + +/* Set of more default csrow<id> attribute show/store functions */ +static ssize_t csrow_ue_count_show(struct csrow_info *csrow, char *data, int private) +{ + return sprintf(data,"%u\n", csrow->ue_count); +} + +static ssize_t csrow_ce_count_show(struct csrow_info *csrow, char *data, int private) +{ + return sprintf(data,"%u\n", csrow->ce_count); +} + +static ssize_t csrow_size_show(struct csrow_info *csrow, char *data, int private) +{ + return sprintf(data,"%u\n", PAGES_TO_MiB(csrow->nr_pages)); +} + +static ssize_t csrow_mem_type_show(struct csrow_info *csrow, char *data, int private) +{ + return sprintf(data,"%s\n", mem_types[csrow->mtype]); +} + +static ssize_t csrow_dev_type_show(struct csrow_info *csrow, char *data, int private) +{ + return sprintf(data,"%s\n", dev_types[csrow->dtype]); +} + +static ssize_t csrow_edac_mode_show(struct csrow_info *csrow, char *data, int private) +{ + return sprintf(data,"%s\n", edac_caps[csrow->edac_mode]); +} + +/* show/store functions for DIMM Label attributes */ +static ssize_t channel_dimm_label_show(struct csrow_info *csrow, + char *data, int channel) +{ + return snprintf(data, EDAC_MC_LABEL_LEN,"%s", + csrow->channels[channel].label); +} + +static ssize_t channel_dimm_label_store(struct csrow_info *csrow, + const char *data, + size_t count, + int channel) +{ + ssize_t max_size = 0; + + max_size = min((ssize_t)count,(ssize_t)EDAC_MC_LABEL_LEN-1); + strncpy(csrow->channels[channel].label, data, max_size); + csrow->channels[channel].label[max_size] = '\0'; + + return max_size; +} + +/* show function for dynamic chX_ce_count attribute */ +static ssize_t channel_ce_count_show(struct csrow_info *csrow, + char *data, + int channel) +{ + return sprintf(data, "%u\n", csrow->channels[channel].ce_count); +} + +/* csrow specific attribute structure */ +struct csrowdev_attribute { + struct attribute attr; + ssize_t (*show)(struct csrow_info *,char *,int); + ssize_t (*store)(struct csrow_info *, const char *,size_t,int); + int private; +}; + +#define to_csrow(k) container_of(k, struct csrow_info, kobj) +#define to_csrowdev_attr(a) container_of(a, struct csrowdev_attribute, attr) + +/* Set of show/store higher level functions for default csrow attributes */ +static ssize_t csrowdev_show(struct kobject *kobj, + struct attribute *attr, + char *buffer) +{ + struct csrow_info *csrow = to_csrow(kobj); + struct csrowdev_attribute *csrowdev_attr = to_csrowdev_attr(attr); + + if (csrowdev_attr->show) + return csrowdev_attr->show(csrow, + buffer, + csrowdev_attr->private); + return -EIO; +} + +static ssize_t csrowdev_store(struct kobject *kobj, struct attribute *attr, + const char *buffer, size_t count) +{ + struct csrow_info *csrow = to_csrow(kobj); + struct csrowdev_attribute * csrowdev_attr = to_csrowdev_attr(attr); + + if (csrowdev_attr->store) + return csrowdev_attr->store(csrow, + buffer, + count, + csrowdev_attr->private); + return -EIO; +} + +static struct sysfs_ops csrowfs_ops = { + .show = csrowdev_show, + .store = csrowdev_store +}; + +#define CSROWDEV_ATTR(_name,_mode,_show,_store,_private) \ +static struct csrowdev_attribute attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = _mode }, \ + .show = _show, \ + .store = _store, \ + .private = _private, \ +}; + +/* default cwrow<id>/attribute files */ +CSROWDEV_ATTR(size_mb,S_IRUGO,csrow_size_show,NULL,0); +CSROWDEV_ATTR(dev_type,S_IRUGO,csrow_dev_type_show,NULL,0); +CSROWDEV_ATTR(mem_type,S_IRUGO,csrow_mem_type_show,NULL,0); +CSROWDEV_ATTR(edac_mode,S_IRUGO,csrow_edac_mode_show,NULL,0); +CSROWDEV_ATTR(ue_count,S_IRUGO,csrow_ue_count_show,NULL,0); +CSROWDEV_ATTR(ce_count,S_IRUGO,csrow_ce_count_show,NULL,0); + +/* default attributes of the CSROW<id> object */ +static struct csrowdev_attribute *default_csrow_attr[] = { + &attr_dev_type, + &attr_mem_type, + &attr_edac_mode, + &attr_size_mb, + &attr_ue_count, + &attr_ce_count, + NULL, +}; + + +/* possible dynamic channel DIMM Label attribute files */ +CSROWDEV_ATTR(ch0_dimm_label,S_IRUGO|S_IWUSR, + channel_dimm_label_show, + channel_dimm_label_store, + 0 ); +CSROWDEV_ATTR(ch1_dimm_label,S_IRUGO|S_IWUSR, + channel_dimm_label_show, + channel_dimm_label_store, + 1 ); +CSROWDEV_ATTR(ch2_dimm_label,S_IRUGO|S_IWUSR, + channel_dimm_label_show, + channel_dimm_label_store, + 2 ); +CSROWDEV_ATTR(ch3_dimm_label,S_IRUGO|S_IWUSR, + channel_dimm_label_show, + channel_dimm_label_store, + 3 ); +CSROWDEV_ATTR(ch4_dimm_label,S_IRUGO|S_IWUSR, + channel_dimm_label_show, + channel_dimm_label_store, + 4 ); +CSROWDEV_ATTR(ch5_dimm_label,S_IRUGO|S_IWUSR, + channel_dimm_label_show, + channel_dimm_label_store, + 5 ); + +/* Total possible dynamic DIMM Label attribute file table */ +static struct csrowdev_attribute *dynamic_csrow_dimm_attr[] = { + &attr_ch0_dimm_label, + &attr_ch1_dimm_label, + &attr_ch2_dimm_label, + &attr_ch3_dimm_label, + &attr_ch4_dimm_label, + &attr_ch5_dimm_label +}; + +/* possible dynamic channel ce_count attribute files */ +CSROWDEV_ATTR(ch0_ce_count,S_IRUGO|S_IWUSR, + channel_ce_count_show, + NULL, + 0 ); +CSROWDEV_ATTR(ch1_ce_count,S_IRUGO|S_IWUSR, + channel_ce_count_show, + NULL, + 1 ); +CSROWDEV_ATTR(ch2_ce_count,S_IRUGO|S_IWUSR, + channel_ce_count_show, + NULL, + 2 ); +CSROWDEV_ATTR(ch3_ce_count,S_IRUGO|S_IWUSR, + channel_ce_count_show, + NULL, + 3 ); +CSROWDEV_ATTR(ch4_ce_count,S_IRUGO|S_IWUSR, + channel_ce_count_show, + NULL, + 4 ); +CSROWDEV_ATTR(ch5_ce_count,S_IRUGO|S_IWUSR, + channel_ce_count_show, + NULL, + 5 ); + +/* Total possible dynamic ce_count attribute file table */ +static struct csrowdev_attribute *dynamic_csrow_ce_count_attr[] = { + &attr_ch0_ce_count, + &attr_ch1_ce_count, + &attr_ch2_ce_count, + &attr_ch3_ce_count, + &attr_ch4_ce_count, + &attr_ch5_ce_count +}; + + +#define EDAC_NR_CHANNELS 6 + +/* Create dynamic CHANNEL files, indexed by 'chan', under specifed CSROW */ +static int edac_create_channel_files(struct kobject *kobj, int chan) +{ + int err=-ENODEV; + + if (chan >= EDAC_NR_CHANNELS) + return err; + + /* create the DIMM label attribute file */ + err = sysfs_create_file(kobj, + (struct attribute *) dynamic_csrow_dimm_attr[chan]); + + if (!err) { + /* create the CE Count attribute file */ + err = sysfs_create_file(kobj, + (struct attribute *) dynamic_csrow_ce_count_attr[chan]); + } else { + debugf1("%s() dimm labels and ce_count files created", __func__); + } + + return err; +} + +/* No memory to release for this kobj */ +static void edac_csrow_instance_release(struct kobject *kobj) +{ + struct csrow_info *cs; + + cs = container_of(kobj, struct csrow_info, kobj); + complete(&cs->kobj_complete); +} + +/* the kobj_type instance for a CSROW */ +static struct kobj_type ktype_csrow = { + .release = edac_csrow_instance_release, + .sysfs_ops = &csrowfs_ops, + .default_attrs = (struct attribute **) default_csrow_attr, +}; + +/* Create a CSROW object under specifed edac_mc_device */ +static int edac_create_csrow_object( + struct kobject *edac_mci_kobj, + struct csrow_info *csrow, + int index) +{ + int err = 0; + int chan; + + memset(&csrow->kobj, 0, sizeof(csrow->kobj)); + + /* generate ..../edac/mc/mc<id>/csrow<index> */ + + csrow->kobj.parent = edac_mci_kobj; + csrow->kobj.ktype = &ktype_csrow; + + /* name this instance of csrow<id> */ + err = kobject_set_name(&csrow->kobj,"csrow%d",index); + if (err) + goto error_exit; + + /* Instanstiate the csrow object */ + err = kobject_register(&csrow->kobj); + if (!err) { + /* Create the dyanmic attribute files on this csrow, + * namely, the DIMM labels and the channel ce_count + */ + for (chan = 0; chan < csrow->nr_channels; chan++) { + err = edac_create_channel_files(&csrow->kobj,chan); + if (err) + break; + } + } + +error_exit: + return err; +} + +/* default sysfs methods and data structures for the main MCI kobject */ + +static ssize_t mci_reset_counters_store(struct mem_ctl_info *mci, + const char *data, size_t count) +{ + int row, chan; + + mci->ue_noinfo_count = 0; + mci->ce_noinfo_count = 0; + mci->ue_count = 0; + mci->ce_count = 0; + + for (row = 0; row < mci->nr_csrows; row++) { + struct csrow_info *ri = &mci->csrows[row]; + + ri->ue_count = 0; + ri->ce_count = 0; + + for (chan = 0; chan < ri->nr_channels; chan++) + ri->channels[chan].ce_count = 0; + } + + mci->start_time = jiffies; + return count; +} + +/* memory scrubbing */ +static ssize_t mci_sdram_scrub_rate_store(struct mem_ctl_info *mci, + const char *data, size_t count) +{ + u32 bandwidth = -1; + + if (mci->set_sdram_scrub_rate) { + + memctrl_int_store(&bandwidth, data, count); + + if (!(*mci->set_sdram_scrub_rate)(mci, &bandwidth)) { + edac_printk(KERN_DEBUG, EDAC_MC, + "Scrub rate set successfully, applied: %d\n", + bandwidth); + } else { + /* FIXME: error codes maybe? */ + edac_printk(KERN_DEBUG, EDAC_MC, + "Scrub rate set FAILED, could not apply: %d\n", + bandwidth); + } + } else { + /* FIXME: produce "not implemented" ERROR for user-side. */ + edac_printk(KERN_WARNING, EDAC_MC, + "Memory scrubbing 'set'control is not implemented!\n"); + } + return count; +} + +static ssize_t mci_sdram_scrub_rate_show(struct mem_ctl_info *mci, char *data) +{ + u32 bandwidth = -1; + + if (mci->get_sdram_scrub_rate) { + if (!(*mci->get_sdram_scrub_rate)(mci, &bandwidth)) { + edac_printk(KERN_DEBUG, EDAC_MC, + "Scrub rate successfully, fetched: %d\n", + bandwidth); + } else { + /* FIXME: error codes maybe? */ + edac_printk(KERN_DEBUG, EDAC_MC, + "Scrub rate fetch FAILED, got: %d\n", + bandwidth); + } + } else { + /* FIXME: produce "not implemented" ERROR for user-side. */ + edac_printk(KERN_WARNING, EDAC_MC, + "Memory scrubbing 'get' control is not implemented!\n"); + } + return sprintf(data, "%d\n", bandwidth); +} + +/* default attribute files for the MCI object */ +static ssize_t mci_ue_count_show(struct mem_ctl_info *mci, char *data) +{ + return sprintf(data,"%d\n", mci->ue_count); +} + +static ssize_t mci_ce_count_show(struct mem_ctl_info *mci, char *data) +{ + return sprintf(data,"%d\n", mci->ce_count); +} + +static ssize_t mci_ce_noinfo_show(struct mem_ctl_info *mci, char *data) +{ + return sprintf(data,"%d\n", mci->ce_noinfo_count); +} + +static ssize_t mci_ue_noinfo_show(struct mem_ctl_info *mci, char *data) +{ + return sprintf(data,"%d\n", mci->ue_noinfo_count); +} + +static ssize_t mci_seconds_show(struct mem_ctl_info *mci, char *data) +{ + return sprintf(data,"%ld\n", (jiffies - mci->start_time) / HZ); +} + +static ssize_t mci_ctl_name_show(struct mem_ctl_info *mci, char *data) +{ + return sprintf(data,"%s\n", mci->ctl_name); +} + +static ssize_t mci_size_mb_show(struct mem_ctl_info *mci, char *data) +{ + int total_pages, csrow_idx; + + for (total_pages = csrow_idx = 0; csrow_idx < mci->nr_csrows; + csrow_idx++) { + struct csrow_info *csrow = &mci->csrows[csrow_idx]; + + if (!csrow->nr_pages) + continue; + + total_pages += csrow->nr_pages; + } + + return sprintf(data,"%u\n", PAGES_TO_MiB(total_pages)); +} + +struct mcidev_attribute { + struct attribute attr; + ssize_t (*show)(struct mem_ctl_info *,char *); + ssize_t (*store)(struct mem_ctl_info *, const char *,size_t); +}; + +#define to_mci(k) container_of(k, struct mem_ctl_info, edac_mci_kobj) +#define to_mcidev_attr(a) container_of(a, struct mcidev_attribute, attr) + +/* MCI show/store functions for top most object */ +static ssize_t mcidev_show(struct kobject *kobj, struct attribute *attr, + char *buffer) +{ + struct mem_ctl_info *mem_ctl_info = to_mci(kobj); + struct mcidev_attribute * mcidev_attr = to_mcidev_attr(attr); + + if (mcidev_attr->show) + return mcidev_attr->show(mem_ctl_info, buffer); + + return -EIO; +} + +static ssize_t mcidev_store(struct kobject *kobj, struct attribute *attr, + const char *buffer, size_t count) +{ + struct mem_ctl_info *mem_ctl_info = to_mci(kobj); + struct mcidev_attribute * mcidev_attr = to_mcidev_attr(attr); + + if (mcidev_attr->store) + return mcidev_attr->store(mem_ctl_info, buffer, count); + + return -EIO; +} + +static struct sysfs_ops mci_ops = { + .show = mcidev_show, + .store = mcidev_store +}; + +#define MCIDEV_ATTR(_name,_mode,_show,_store) \ +static struct mcidev_attribute mci_attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = _mode }, \ + .show = _show, \ + .store = _store, \ +}; + +/* default Control file */ +MCIDEV_ATTR(reset_counters,S_IWUSR,NULL,mci_reset_counters_store); + +/* default Attribute files */ +MCIDEV_ATTR(mc_name,S_IRUGO,mci_ctl_name_show,NULL); +MCIDEV_ATTR(size_mb,S_IRUGO,mci_size_mb_show,NULL); +MCIDEV_ATTR(seconds_since_reset,S_IRUGO,mci_seconds_show,NULL); +MCIDEV_ATTR(ue_noinfo_count,S_IRUGO,mci_ue_noinfo_show,NULL); +MCIDEV_ATTR(ce_noinfo_count,S_IRUGO,mci_ce_noinfo_show,NULL); +MCIDEV_ATTR(ue_count,S_IRUGO,mci_ue_count_show,NULL); +MCIDEV_ATTR(ce_count,S_IRUGO,mci_ce_count_show,NULL); + +/* memory scrubber attribute file */ +MCIDEV_ATTR(sdram_scrub_rate,S_IRUGO|S_IWUSR,mci_sdram_scrub_rate_show,mci_sdram_scrub_rate_store); + +static struct mcidev_attribute *mci_attr[] = { + &mci_attr_reset_counters, + &mci_attr_mc_name, + &mci_attr_size_mb, + &mci_attr_seconds_since_reset, + &mci_attr_ue_noinfo_count, + &mci_attr_ce_noinfo_count, + &mci_attr_ue_count, + &mci_attr_ce_count, + &mci_attr_sdram_scrub_rate, + NULL +}; + +/* + * Release of a MC controlling instance + */ +static void edac_mci_instance_release(struct kobject *kobj) +{ + struct mem_ctl_info *mci; + + mci = to_mci(kobj); + debugf0("%s() idx=%d\n", __func__, mci->mc_idx); + complete(&mci->kobj_complete); +} + +static struct kobj_type ktype_mci = { + .release = edac_mci_instance_release, + .sysfs_ops = &mci_ops, + .default_attrs = (struct attribute **) mci_attr, +}; + + +#define EDAC_DEVICE_SYMLINK "device" + +/* + * Create a new Memory Controller kobject instance, + * mc<id> under the 'mc' directory + * + * Return: + * 0 Success + * !0 Failure + */ +int edac_create_sysfs_mci_device(struct mem_ctl_info *mci) +{ + int i; + int err; + struct csrow_info *csrow; + struct kobject *edac_mci_kobj=&mci->edac_mci_kobj; + + debugf0("%s() idx=%d\n", __func__, mci->mc_idx); + memset(edac_mci_kobj, 0, sizeof(*edac_mci_kobj)); + + /* set the name of the mc<id> object */ + err = kobject_set_name(edac_mci_kobj,"mc%d",mci->mc_idx); + if (err) + return err; + + /* link to our parent the '..../edac/mc' object */ + edac_mci_kobj->parent = &edac_memctrl_kobj; + edac_mci_kobj->ktype = &ktype_mci; + + /* register the mc<id> kobject */ + err = kobject_register(edac_mci_kobj); + if (err) + return err; + + /* create a symlink for the device */ + err = sysfs_create_link(edac_mci_kobj, &mci->dev->kobj, + EDAC_DEVICE_SYMLINK); + if (err) + goto fail0; + + /* Make directories for each CSROW object + * under the mc<id> kobject + */ + for (i = 0; i < mci->nr_csrows; i++) { + csrow = &mci->csrows[i]; + + /* Only expose populated CSROWs */ + if (csrow->nr_pages > 0) { + err = edac_create_csrow_object(edac_mci_kobj,csrow,i); + if (err) + goto fail1; + } + } + + return 0; + + /* CSROW error: backout what has already been registered, */ +fail1: + for ( i--; i >= 0; i--) { + if (csrow->nr_pages > 0) { + init_completion(&csrow->kobj_complete); + kobject_unregister(&mci->csrows[i].kobj); + wait_for_completion(&csrow->kobj_complete); + } + } + +fail0: + init_completion(&mci->kobj_complete); + kobject_unregister(edac_mci_kobj); + wait_for_completion(&mci->kobj_complete); + return err; +} + +/* + * remove a Memory Controller instance + */ +void edac_remove_sysfs_mci_device(struct mem_ctl_info *mci) +{ + int i; + + debugf0("%s()\n", __func__); + + /* remove all csrow kobjects */ + for (i = 0; i < mci->nr_csrows; i++) { + if (mci->csrows[i].nr_pages > 0) { + init_completion(&mci->csrows[i].kobj_complete); + kobject_unregister(&mci->csrows[i].kobj); + wait_for_completion(&mci->csrows[i].kobj_complete); + } + } + + sysfs_remove_link(&mci->edac_mci_kobj, EDAC_DEVICE_SYMLINK); + init_completion(&mci->kobj_complete); + kobject_unregister(&mci->edac_mci_kobj); + wait_for_completion(&mci->kobj_complete); +} + + diff --git a/drivers/edac/edac_module.c b/drivers/edac/edac_module.c new file mode 100644 index 00000000000..8db0471a947 --- /dev/null +++ b/drivers/edac/edac_module.c @@ -0,0 +1,130 @@ + +#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 + diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h new file mode 100644 index 00000000000..69c77f85bcd --- /dev/null +++ b/drivers/edac/edac_module.h @@ -0,0 +1,55 @@ + +/* + * 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__ */ + diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c new file mode 100644 index 00000000000..db23fec522e --- /dev/null +++ b/drivers/edac/edac_pci_sysfs.c @@ -0,0 +1,361 @@ +/* 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 */ |