diff options
Diffstat (limited to 'drivers/edac/edac_mc.c')
| -rw-r--r-- | drivers/edac/edac_mc.c | 589 |
1 files changed, 303 insertions, 286 deletions
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 0499782db7c7..3a7cfe88b169 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -53,16 +53,17 @@ static int log_ce = 1; static int panic_on_ue; static int poll_msec = 1000; -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); - /* 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); + /* Structure of the whitelist and blacklist arrays */ struct edac_pci_device_list { unsigned int vendor; /* Vendor ID */ @@ -79,6 +80,12 @@ static int pci_blacklist_count; static struct edac_pci_device_list pci_whitelist[MAX_LISTED_PCI_DEVICES]; static int pci_whitelist_count ; +#ifndef DISABLE_EDAC_SYSFS +static struct kobject edac_pci_kobj; /* /sys/devices/system/edac/pci */ +static struct completion edac_pci_kobj_complete; +#endif /* DISABLE_EDAC_SYSFS */ +#endif /* CONFIG_PCI */ + /* START sysfs data and methods */ #ifndef DISABLE_EDAC_SYSFS @@ -126,18 +133,15 @@ static struct sysdev_class edac_class = { set_kset_name("edac"), }; -/* sysfs objects: +/* sysfs object: * /sys/devices/system/edac/mc - * /sys/devices/system/edac/pci */ static struct kobject edac_memctrl_kobj; -static struct kobject edac_pci_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; -static struct completion edac_pci_kobj_complete; /* * /sys/devices/system/edac/mc; @@ -323,6 +327,8 @@ static void edac_sysfs_memctrl_teardown(void) #endif /* DISABLE_EDAC_SYSFS */ } +#ifdef CONFIG_PCI + #ifndef DISABLE_EDAC_SYSFS /* @@ -623,6 +629,252 @@ static void edac_sysfs_pci_teardown(void) #endif } + +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); + } + } + } +} + +/* + * check_dev_on_list: Scan for a PCI device on a white/black list + * @list: an EDAC &edac_pci_device_list white/black list pointer + * @free_index: index of next free entry on the list + * @pci_dev: PCI Device pointer + * + * see if list contains the device. + * + * Returns: 0 not found + * 1 found on list + */ +static int check_dev_on_list(struct edac_pci_device_list *list, + int free_index, struct pci_dev *dev) +{ + int i; + int rc = 0; /* Assume not found */ + unsigned short vendor=dev->vendor; + unsigned short device=dev->device; + + /* Scan the list, looking for a vendor/device match */ + for (i = 0; i < free_index; i++, list++ ) { + if ((list->vendor == vendor ) && (list->device == device )) { + rc = 1; + break; + } + } + + return rc; +} + +/* + * 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) { + /* if whitelist exists then it has priority, so only scan + * those devices on the whitelist + */ + if (pci_whitelist_count > 0 ) { + if (check_dev_on_list(pci_whitelist, + pci_whitelist_count, dev)) + fn(dev); + } else { + /* + * if no whitelist, then check if this devices is + * blacklisted + */ + if (!check_dev_on_list(pci_blacklist, + pci_blacklist_count, dev)) + 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 */ + +static inline void do_pci_parity_check(void) +{ + /* no-op */ +} + +static inline void clear_pci_parity_errors(void) +{ + /* no-op */ +} + +static void edac_sysfs_pci_teardown(void) +{ +} + +static int edac_sysfs_pci_setup(void) +{ + return 0; +} +#endif /* CONFIG_PCI */ + #ifndef DISABLE_EDAC_SYSFS /* EDAC sysfs CSROW data structures and methods */ @@ -1131,7 +1383,7 @@ static int edac_create_sysfs_mci_device(struct mem_ctl_info *mci) return err; /* create a symlink for the device */ - err = sysfs_create_link(edac_mci_kobj, &mci->pdev->dev.kobj, + err = sysfs_create_link(edac_mci_kobj, &mci->dev->kobj, EDAC_DEVICE_SYMLINK); if (err) @@ -1237,7 +1489,7 @@ void edac_mc_dump_mci(struct mem_ctl_info *mci) debugf4("\tmci->edac_check = %p\n", mci->edac_check); debugf3("\tmci->nr_csrows = %d, csrows = %p\n", mci->nr_csrows, mci->csrows); - debugf3("\tpdev = %p\n", mci->pdev); + debugf3("\tdev = %p\n", mci->dev); debugf3("\tmod_name:ctl_name = %s:%s\n", mci->mod_name, mci->ctl_name); debugf3("\tpvt_info = %p\n\n", mci->pvt_info); @@ -1362,7 +1614,7 @@ void edac_mc_free(struct mem_ctl_info *mci) } EXPORT_SYMBOL_GPL(edac_mc_free); -static struct mem_ctl_info *find_mci_by_pdev(struct pci_dev *pdev) +static struct mem_ctl_info *find_mci_by_dev(struct device *dev) { struct mem_ctl_info *mci; struct list_head *item; @@ -1372,54 +1624,53 @@ static struct mem_ctl_info *find_mci_by_pdev(struct pci_dev *pdev) list_for_each(item, &mc_devices) { mci = list_entry(item, struct mem_ctl_info, link); - if (mci->pdev == pdev) + if (mci->dev == dev) return mci; } return NULL; } -static int add_mc_to_global_list(struct mem_ctl_info *mci) +/* Return 0 on success, 1 on failure. + * Before calling this function, caller must + * assign a unique value to mci->mc_idx. + */ +static int add_mc_to_global_list (struct mem_ctl_info *mci) { struct list_head *item, *insert_before; struct mem_ctl_info *p; - int i; - if (list_empty(&mc_devices)) { - mci->mc_idx = 0; - insert_before = &mc_devices; - } else { - if (find_mci_by_pdev(mci->pdev)) { - edac_printk(KERN_WARNING, EDAC_MC, - "%s (%s) %s %s already assigned %d\n", - mci->pdev->dev.bus_id, - pci_name(mci->pdev), mci->mod_name, - mci->ctl_name, mci->mc_idx); - return 1; - } + insert_before = &mc_devices; - insert_before = NULL; - i = 0; + if (unlikely((p = find_mci_by_dev(mci->dev)) != NULL)) + goto fail0; - list_for_each(item, &mc_devices) { - p = list_entry(item, struct mem_ctl_info, link); + list_for_each(item, &mc_devices) { + p = list_entry(item, struct mem_ctl_info, link); - if (p->mc_idx != i) { - insert_before = item; - break; - } + if (p->mc_idx >= mci->mc_idx) { + if (unlikely(p->mc_idx == mci->mc_idx)) + goto fail1; - i++; + insert_before = item; + break; } - - mci->mc_idx = i; - - if (insert_before == NULL) - insert_before = &mc_devices; } list_add_tail_rcu(&mci->link, insert_before); return 0; + +fail0: + edac_printk(KERN_WARNING, EDAC_MC, + "%s (%s) %s %s already assigned %d\n", p->dev->bus_id, + dev_name(p->dev), p->mod_name, p->ctl_name, p->mc_idx); + return 1; + +fail1: + edac_printk(KERN_WARNING, EDAC_MC, + "bug in low-level driver: attempt to assign\n" + " duplicate mc_idx %d in %s()\n", p->mc_idx, __func__); + return 1; } static void complete_mc_list_del(struct rcu_head *head) @@ -1443,6 +1694,7 @@ static void del_mc_from_global_list(struct mem_ctl_info *mci) * edac_mc_add_mc: Insert the 'mci' structure into the mci global list and * create sysfs entries associated with mci structure * @mci: pointer to the mci structure to be added to the list + * @mc_idx: A unique numeric identifier to be assigned to the 'mci' structure. * * Return: * 0 Success @@ -1450,9 +1702,10 @@ static void del_mc_from_global_list(struct mem_ctl_info *mci) */ /* FIXME - should a warning be printed if no error detection? correction? */ -int edac_mc_add_mc(struct mem_ctl_info *mci) +int edac_mc_add_mc(struct mem_ctl_info *mci, int mc_idx) { debugf0("%s()\n", __func__); + mci->mc_idx = mc_idx; #ifdef CONFIG_EDAC_DEBUG if (edac_debug_level >= 3) edac_mc_dump_mci(mci); @@ -1485,8 +1738,8 @@ int edac_mc_add_mc(struct mem_ctl_info *mci) } /* Report action taken */ - edac_mc_printk(mci, KERN_INFO, "Giving out device to %s %s: PCI %s\n", - mci->mod_name, mci->ctl_name, pci_name(mci->pdev)); + edac_mc_printk(mci, KERN_INFO, "Giving out device to %s %s: DEV %s\n", + mci->mod_name, mci->ctl_name, dev_name(mci->dev)); up(&mem_ctls_mutex); return 0; @@ -1503,18 +1756,18 @@ EXPORT_SYMBOL_GPL(edac_mc_add_mc); /** * edac_mc_del_mc: Remove sysfs entries for specified mci structure and * remove mci structure from global list - * @pdev: Pointer to 'struct pci_dev' representing mci structure to remove. + * @pdev: Pointer to 'struct device' representing mci structure to remove. * * Return pointer to removed mci structure, or NULL if device not found. */ -struct mem_ctl_info * edac_mc_del_mc(struct pci_dev *pdev) +struct mem_ctl_info * edac_mc_del_mc(struct device *dev) { struct mem_ctl_info *mci; debugf0("MC: %s()\n", __func__); down(&mem_ctls_mutex); - if ((mci = find_mci_by_pdev(pdev)) == NULL) { + if ((mci = find_mci_by_dev(dev)) == NULL) { up(&mem_ctls_mutex); return NULL; } @@ -1523,8 +1776,8 @@ struct mem_ctl_info * edac_mc_del_mc(struct pci_dev *pdev) del_mc_from_global_list(mci); up(&mem_ctls_mutex); edac_printk(KERN_INFO, EDAC_MC, - "Removed device %d for %s %s: PCI %s\n", mci->mc_idx, - mci->mod_name, mci->ctl_name, pci_name(mci->pdev)); + "Removed device %d for %s %s: DEV %s\n", mci->mc_idx, + mci->mod_name, mci->ctl_name, dev_name(mci->dev)); return mci; } EXPORT_SYMBOL_GPL(edac_mc_del_mc); @@ -1738,244 +1991,6 @@ void edac_mc_handle_ue_no_info(struct mem_ctl_info *mci, const char *msg) } EXPORT_SYMBOL_GPL(edac_mc_handle_ue_no_info); -#ifdef CONFIG_PCI - -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); - } - } - } -} - -/* - * check_dev_on_list: Scan for a PCI device on a white/black list - * @list: an EDAC &edac_pci_device_list white/black list pointer - * @free_index: index of next free entry on the list - * @pci_dev: PCI Device pointer - * - * see if list contains the device. - * - * Returns: 0 not found - * 1 found on list - */ -static int check_dev_on_list(struct edac_pci_device_list *list, - int free_index, struct pci_dev *dev) -{ - int i; - int rc = 0; /* Assume not found */ - unsigned short vendor=dev->vendor; - unsigned short device=dev->device; - - /* Scan the list, looking for a vendor/device match */ - for (i = 0; i < free_index; i++, list++ ) { - if ((list->vendor == vendor ) && (list->device == device )) { - rc = 1; - break; - } - } - - return rc; -} - -/* - * 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) { - /* if whitelist exists then it has priority, so only scan - * those devices on the whitelist - */ - if (pci_whitelist_count > 0 ) { - if (check_dev_on_list(pci_whitelist, - pci_whitelist_count, dev)) - fn(dev); - } else { - /* - * if no whitelist, then check if this devices is - * blacklisted - */ - if (!check_dev_on_list(pci_blacklist, - pci_blacklist_count, dev)) - 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 */ - -static inline void do_pci_parity_check(void) -{ - /* no-op */ -} - -static inline void clear_pci_parity_errors(void) -{ - /* no-op */ -} - -#endif /* CONFIG_PCI */ /* * Iterate over all MC instances and check for ECC, et al, errors @@ -2095,10 +2110,12 @@ 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); |