diff options
Diffstat (limited to 'arch/powerpc/platforms/pseries')
| -rw-r--r-- | arch/powerpc/platforms/pseries/eeh.c | 19 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/eeh_dev.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/io_event_irq.c | 68 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/iommu.c | 29 | ||||
| -rw-r--r-- | arch/powerpc/platforms/pseries/ras.c | 195 |
5 files changed, 149 insertions, 164 deletions
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c index 8011088392d3..309d38ef7322 100644 --- a/arch/powerpc/platforms/pseries/eeh.c +++ b/arch/powerpc/platforms/pseries/eeh.c @@ -984,7 +984,8 @@ int __exit eeh_ops_unregister(const char *name) */ void __init eeh_init(void) { - struct device_node *phb, *np; + struct pci_controller *hose, *tmp; + struct device_node *phb; int ret; /* call platform initialization function */ @@ -1000,19 +1001,9 @@ void __init eeh_init(void) raw_spin_lock_init(&confirm_error_lock); - np = of_find_node_by_path("/rtas"); - if (np == NULL) - return; - - /* Enable EEH for all adapters. Note that eeh requires buid's */ - for (phb = of_find_node_by_name(NULL, "pci"); phb; - phb = of_find_node_by_name(phb, "pci")) { - unsigned long buid; - - buid = get_phb_buid(phb); - if (buid == 0 || !of_node_to_eeh_dev(phb)) - continue; - + /* Enable EEH for all adapters */ + list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { + phb = hose->dn; traverse_pci_devices(phb, eeh_early_enable, NULL); } diff --git a/arch/powerpc/platforms/pseries/eeh_dev.c b/arch/powerpc/platforms/pseries/eeh_dev.c index f3aed7dcae95..c4507d095900 100644 --- a/arch/powerpc/platforms/pseries/eeh_dev.c +++ b/arch/powerpc/platforms/pseries/eeh_dev.c @@ -62,7 +62,7 @@ void * __devinit eeh_dev_init(struct device_node *dn, void *data) } /* Associate EEH device with OF node */ - dn->edev = edev; + PCI_DN(dn)->edev = edev; edev->dn = dn; edev->phb = phb; diff --git a/arch/powerpc/platforms/pseries/io_event_irq.c b/arch/powerpc/platforms/pseries/io_event_irq.c index 1a709bc48ce1..ef9d9d84c7d5 100644 --- a/arch/powerpc/platforms/pseries/io_event_irq.c +++ b/arch/powerpc/platforms/pseries/io_event_irq.c @@ -63,73 +63,9 @@ EXPORT_SYMBOL_GPL(pseries_ioei_notifier_list); static int ioei_check_exception_token; -/* pSeries event log format */ - -/* Two bytes ASCII section IDs */ -#define PSERIES_ELOG_SECT_ID_PRIV_HDR (('P' << 8) | 'H') -#define PSERIES_ELOG_SECT_ID_USER_HDR (('U' << 8) | 'H') -#define PSERIES_ELOG_SECT_ID_PRIMARY_SRC (('P' << 8) | 'S') -#define PSERIES_ELOG_SECT_ID_EXTENDED_UH (('E' << 8) | 'H') -#define PSERIES_ELOG_SECT_ID_FAILING_MTMS (('M' << 8) | 'T') -#define PSERIES_ELOG_SECT_ID_SECONDARY_SRC (('S' << 8) | 'S') -#define PSERIES_ELOG_SECT_ID_DUMP_LOCATOR (('D' << 8) | 'H') -#define PSERIES_ELOG_SECT_ID_FW_ERROR (('S' << 8) | 'W') -#define PSERIES_ELOG_SECT_ID_IMPACT_PART_ID (('L' << 8) | 'P') -#define PSERIES_ELOG_SECT_ID_LOGIC_RESOURCE_ID (('L' << 8) | 'R') -#define PSERIES_ELOG_SECT_ID_HMC_ID (('H' << 8) | 'M') -#define PSERIES_ELOG_SECT_ID_EPOW (('E' << 8) | 'P') -#define PSERIES_ELOG_SECT_ID_IO_EVENT (('I' << 8) | 'E') -#define PSERIES_ELOG_SECT_ID_MANUFACT_INFO (('M' << 8) | 'I') -#define PSERIES_ELOG_SECT_ID_CALL_HOME (('C' << 8) | 'H') -#define PSERIES_ELOG_SECT_ID_USER_DEF (('U' << 8) | 'D') - -/* Vendor specific Platform Event Log Format, Version 6, section header */ -struct pseries_elog_section { - uint16_t id; /* 0x00 2-byte ASCII section ID */ - uint16_t length; /* 0x02 Section length in bytes */ - uint8_t version; /* 0x04 Section version */ - uint8_t subtype; /* 0x05 Section subtype */ - uint16_t creator_component; /* 0x06 Creator component ID */ - uint8_t data[]; /* 0x08 Start of section data */ -}; - static char ioei_rtas_buf[RTAS_DATA_BUF_SIZE] __cacheline_aligned; /** - * Find data portion of a specific section in RTAS extended event log. - * @elog: RTAS error/event log. - * @sect_id: secsion ID. - * - * Return: - * pointer to the section data of the specified section - * NULL if not found - */ -static struct pseries_elog_section *find_xelog_section(struct rtas_error_log *elog, - uint16_t sect_id) -{ - struct rtas_ext_event_log_v6 *xelog = - (struct rtas_ext_event_log_v6 *) elog->buffer; - struct pseries_elog_section *sect; - unsigned char *p, *log_end; - - /* Check that we understand the format */ - if (elog->extended_log_length < sizeof(struct rtas_ext_event_log_v6) || - xelog->log_format != RTAS_V6EXT_LOG_FORMAT_EVENT_LOG || - xelog->company_id != RTAS_V6EXT_COMPANY_ID_IBM) - return NULL; - - log_end = elog->buffer + elog->extended_log_length; - p = xelog->vendor_log; - while (p < log_end) { - sect = (struct pseries_elog_section *)p; - if (sect->id == sect_id) - return sect; - p += sect->length; - } - return NULL; -} - -/** * Find the data portion of an IO Event section from event log. * @elog: RTAS error/event log. * @@ -138,7 +74,7 @@ static struct pseries_elog_section *find_xelog_section(struct rtas_error_log *el */ static struct pseries_io_event * ioei_find_event(struct rtas_error_log *elog) { - struct pseries_elog_section *sect; + struct pseries_errorlog *sect; /* We should only ever get called for io-event interrupts, but if * we do get called for another type then something went wrong so @@ -152,7 +88,7 @@ static struct pseries_io_event * ioei_find_event(struct rtas_error_log *elog) return NULL; } - sect = find_xelog_section(elog, PSERIES_ELOG_SECT_ID_IO_EVENT); + sect = get_pseries_errorlog(elog, PSERIES_ELOG_SECT_ID_IO_EVENT); if (unlikely(!sect)) { printk_once(KERN_WARNING "io_event_irq: RTAS extended event " "log does not contain an IO Event section. " diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index c442f2b1980f..0915b1ad66ce 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -809,8 +809,7 @@ machine_arch_initcall(pseries, find_existing_ddw_windows); static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, struct ddw_query_response *query) { - struct device_node *dn; - struct pci_dn *pcidn; + struct eeh_dev *edev; u32 cfg_addr; u64 buid; int ret; @@ -821,12 +820,12 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, * Retrieve them from the pci device, not the node with the * dma-window property */ - dn = pci_device_to_OF_node(dev); - pcidn = PCI_DN(dn); - cfg_addr = pcidn->eeh_config_addr; - if (pcidn->eeh_pe_config_addr) - cfg_addr = pcidn->eeh_pe_config_addr; - buid = pcidn->phb->buid; + edev = pci_dev_to_eeh_dev(dev); + cfg_addr = edev->config_addr; + if (edev->pe_config_addr) + cfg_addr = edev->pe_config_addr; + buid = edev->phb->buid; + ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query, cfg_addr, BUID_HI(buid), BUID_LO(buid)); dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x" @@ -839,8 +838,7 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, struct ddw_create_response *create, int page_shift, int window_shift) { - struct device_node *dn; - struct pci_dn *pcidn; + struct eeh_dev *edev; u32 cfg_addr; u64 buid; int ret; @@ -851,12 +849,11 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, * Retrieve them from the pci device, not the node with the * dma-window property */ - dn = pci_device_to_OF_node(dev); - pcidn = PCI_DN(dn); - cfg_addr = pcidn->eeh_config_addr; - if (pcidn->eeh_pe_config_addr) - cfg_addr = pcidn->eeh_pe_config_addr; - buid = pcidn->phb->buid; + edev = pci_dev_to_eeh_dev(dev); + cfg_addr = edev->config_addr; + if (edev->pe_config_addr) + cfg_addr = edev->pe_config_addr; + buid = edev->phb->buid; do { /* extra outputs are LIOBN and dma-addr (hi, lo) */ diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 086d2ae4e06a..c4dfccd3a3d9 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -16,37 +16,15 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -/* Change Activity: - * 2001/09/21 : engebret : Created with minimal EPOW and HW exception support. - * End Change Activity - */ - -#include <linux/errno.h> -#include <linux/threads.h> -#include <linux/kernel_stat.h> -#include <linux/signal.h> #include <linux/sched.h> -#include <linux/ioport.h> #include <linux/interrupt.h> -#include <linux/timex.h> -#include <linux/init.h> -#include <linux/delay.h> #include <linux/irq.h> -#include <linux/random.h> -#include <linux/sysrq.h> -#include <linux/bitops.h> - -#include <asm/uaccess.h> -#include <asm/system.h> -#include <asm/io.h> -#include <asm/pgtable.h> -#include <asm/irq.h> -#include <asm/cache.h> -#include <asm/prom.h> -#include <asm/ptrace.h> +#include <linux/of.h> +#include <linux/fs.h> +#include <linux/reboot.h> + #include <asm/machdep.h> #include <asm/rtas.h> -#include <asm/udbg.h> #include <asm/firmware.h> #include "pseries.h" @@ -57,7 +35,6 @@ static DEFINE_SPINLOCK(ras_log_buf_lock); static char global_mce_data_buf[RTAS_ERROR_LOG_MAX]; static DEFINE_PER_CPU(__u64, mce_data_buf); -static int ras_get_sensor_state_token; static int ras_check_exception_token; #define EPOW_SENSOR_TOKEN 9 @@ -75,7 +52,6 @@ static int __init init_ras_IRQ(void) { struct device_node *np; - ras_get_sensor_state_token = rtas_token("get-sensor-state"); ras_check_exception_token = rtas_token("check-exception"); /* Internal Errors */ @@ -95,26 +71,126 @@ static int __init init_ras_IRQ(void) return 0; } -__initcall(init_ras_IRQ); +subsys_initcall(init_ras_IRQ); -/* - * Handle power subsystem events (EPOW). - * - * Presently we just log the event has occurred. This should be fixed - * to examine the type of power failure and take appropriate action where - * the time horizon permits something useful to be done. - */ +#define EPOW_SHUTDOWN_NORMAL 1 +#define EPOW_SHUTDOWN_ON_UPS 2 +#define EPOW_SHUTDOWN_LOSS_OF_CRITICAL_FUNCTIONS 3 +#define EPOW_SHUTDOWN_AMBIENT_TEMPERATURE_TOO_HIGH 4 + +static void handle_system_shutdown(char event_modifier) +{ + switch (event_modifier) { + case EPOW_SHUTDOWN_NORMAL: + pr_emerg("Firmware initiated power off"); + orderly_poweroff(1); + break; + + case EPOW_SHUTDOWN_ON_UPS: + pr_emerg("Loss of power reported by firmware, system is " + "running on UPS/battery"); + break; + + case EPOW_SHUTDOWN_LOSS_OF_CRITICAL_FUNCTIONS: + pr_emerg("Loss of system critical functions reported by " + "firmware"); + pr_emerg("Check RTAS error log for details"); + orderly_poweroff(1); + break; + + case EPOW_SHUTDOWN_AMBIENT_TEMPERATURE_TOO_HIGH: + pr_emerg("Ambient temperature too high reported by firmware"); + pr_emerg("Check RTAS error log for details"); + orderly_poweroff(1); + break; + + default: + pr_err("Unknown power/cooling shutdown event (modifier %d)", + event_modifier); + } +} + +struct epow_errorlog { + unsigned char sensor_value; + unsigned char event_modifier; + unsigned char extended_modifier; + unsigned char reserved; + unsigned char platform_reason; +}; + +#define EPOW_RESET 0 +#define EPOW_WARN_COOLING 1 +#define EPOW_WARN_POWER 2 +#define EPOW_SYSTEM_SHUTDOWN 3 +#define EPOW_SYSTEM_HALT 4 +#define EPOW_MAIN_ENCLOSURE 5 +#define EPOW_POWER_OFF 7 + +void rtas_parse_epow_errlog(struct rtas_error_log *log) +{ + struct pseries_errorlog *pseries_log; + struct epow_errorlog *epow_log; + char action_code; + char modifier; + + pseries_log = get_pseries_errorlog(log, PSERIES_ELOG_SECT_ID_EPOW); + if (pseries_log == NULL) + return; + + epow_log = (struct epow_errorlog *)pseries_log->data; + action_code = epow_log->sensor_value & 0xF; /* bottom 4 bits */ + modifier = epow_log->event_modifier & 0xF; /* bottom 4 bits */ + + switch (action_code) { + case EPOW_RESET: + pr_err("Non critical power or cooling issue cleared"); + break; + + case EPOW_WARN_COOLING: + pr_err("Non critical cooling issue reported by firmware"); + pr_err("Check RTAS error log for details"); + break; + + case EPOW_WARN_POWER: + pr_err("Non critical power issue reported by firmware"); + pr_err("Check RTAS error log for details"); + break; + + case EPOW_SYSTEM_SHUTDOWN: + handle_system_shutdown(epow_log->event_modifier); + break; + + case EPOW_SYSTEM_HALT: + pr_emerg("Firmware initiated power off"); + orderly_poweroff(1); + break; + + case EPOW_MAIN_ENCLOSURE: + case EPOW_POWER_OFF: + pr_emerg("Critical power/cooling issue reported by firmware"); + pr_emerg("Check RTAS error log for details"); + pr_emerg("Immediate power off"); + emergency_sync(); + kernel_power_off(); + break; + + default: + pr_err("Unknown power/cooling event (action code %d)", + action_code); + } +} + +/* Handle environmental and power warning (EPOW) interrupts. */ static irqreturn_t ras_epow_interrupt(int irq, void *dev_id) { - int status = 0xdeadbeef; - int state = 0; + int status; + int state; int critical; - status = rtas_call(ras_get_sensor_state_token, 2, 2, &state, - EPOW_SENSOR_TOKEN, EPOW_SENSOR_INDEX); + status = rtas_get_sensor(EPOW_SENSOR_TOKEN, EPOW_SENSOR_INDEX, &state); if (state > 3) - critical = 1; /* Time Critical */ + critical = 1; /* Time Critical */ else critical = 0; @@ -123,18 +199,14 @@ static irqreturn_t ras_epow_interrupt(int irq, void *dev_id) status = rtas_call(ras_check_exception_token, 6, 1, NULL, RTAS_VECTOR_EXTERNAL_INTERRUPT, virq_to_hw(irq), - RTAS_EPOW_WARNING | RTAS_POWERMGM_EVENTS, + RTAS_EPOW_WARNING, critical, __pa(&ras_log_buf), rtas_get_error_log_max()); - udbg_printf("EPOW <0x%lx 0x%x 0x%x>\n", - *((unsigned long *)&ras_log_buf), status, state); - printk(KERN_WARNING "EPOW <0x%lx 0x%x 0x%x>\n", - *((unsigned long *)&ras_log_buf), status, state); - - /* format and print the extended information */ log_error(ras_log_buf, ERR_TYPE_RTAS_LOG, 0); + rtas_parse_epow_errlog((struct rtas_error_log *)ras_log_buf); + spin_unlock(&ras_log_buf_lock); return IRQ_HANDLED; } @@ -150,7 +222,7 @@ static irqreturn_t ras_epow_interrupt(int irq, void *dev_id) static irqreturn_t ras_error_interrupt(int irq, void *dev_id) { struct rtas_error_log *rtas_elog; - int status = 0xdeadbeef; + int status; int fatal; spin_lock(&ras_log_buf_lock); @@ -158,7 +230,7 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) status = rtas_call(ras_check_exception_token, 6, 1, NULL, RTAS_VECTOR_EXTERNAL_INTERRUPT, virq_to_hw(irq), - RTAS_INTERNAL_ERROR, 1 /*Time Critical */, + RTAS_INTERNAL_ERROR, 1 /* Time Critical */, __pa(&ras_log_buf), rtas_get_error_log_max()); @@ -173,24 +245,13 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) log_error(ras_log_buf, ERR_TYPE_RTAS_LOG, fatal); if (fatal) { - udbg_printf("Fatal HW Error <0x%lx 0x%x>\n", - *((unsigned long *)&ras_log_buf), status); - printk(KERN_EMERG "Error: Fatal hardware error <0x%lx 0x%x>\n", - *((unsigned long *)&ras_log_buf), status); - -#ifndef DEBUG_RTAS_POWER_OFF - /* Don't actually power off when debugging so we can test - * without actually failing while injecting errors. - * Error data will not be logged to syslog. - */ - ppc_md.power_off(); -#endif + pr_emerg("Fatal hardware error reported by firmware"); + pr_emerg("Check RTAS error log for details"); + pr_emerg("Immediate power off"); + emergency_sync(); + kernel_power_off(); } else { - udbg_printf("Recoverable HW Error <0x%lx 0x%x>\n", - *((unsigned long *)&ras_log_buf), status); - printk(KERN_WARNING - "Warning: Recoverable hardware error <0x%lx 0x%x>\n", - *((unsigned long *)&ras_log_buf), status); + pr_err("Recoverable hardware error reported by firmware"); } spin_unlock(&ras_log_buf_lock); |