diff options
author | Benjamin Herrenschmidt <benh@kernel.crashing.org> | 2012-03-13 10:15:35 +1100 |
---|---|---|
committer | Benjamin Herrenschmidt <benh@kernel.crashing.org> | 2012-03-13 10:15:35 +1100 |
commit | aba0eb84c87928992c021d33ef3ea59c931086b9 (patch) | |
tree | bdc323efc6773d0dcce4406ca275e9192eabb9b2 | |
parent | 7230c5644188cd9e3fb380cc97dde00c464a3ba7 (diff) | |
parent | 3780444c4fcec28c96ab7002858bb051215a5fc1 (diff) |
Merge branch 'eeh' into next
-rw-r--r-- | arch/powerpc/include/asm/device.h | 3 | ||||
-rw-r--r-- | arch/powerpc/include/asm/eeh.h | 134 | ||||
-rw-r--r-- | arch/powerpc/include/asm/eeh_event.h | 33 | ||||
-rw-r--r-- | arch/powerpc/include/asm/ppc-pci.h | 89 | ||||
-rw-r--r-- | arch/powerpc/kernel/of_platform.c | 6 | ||||
-rw-r--r-- | arch/powerpc/kernel/rtas_pci.c | 3 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/Makefile | 3 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/eeh.c | 1044 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/eeh_cache.c | 44 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/eeh_dev.c | 102 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/eeh_driver.c | 213 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/eeh_event.c | 55 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/eeh_pseries.c | 565 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/eeh_sysfs.c | 25 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/msi.c | 2 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/pci_dlpar.c | 3 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/setup.c | 7 | ||||
-rw-r--r-- | include/linux/of.h | 10 | ||||
-rw-r--r-- | include/linux/pci.h | 7 |
19 files changed, 1479 insertions, 869 deletions
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h index d57c08acedf..63d5ca49cec 100644 --- a/arch/powerpc/include/asm/device.h +++ b/arch/powerpc/include/asm/device.h @@ -31,6 +31,9 @@ struct dev_archdata { #ifdef CONFIG_SWIOTLB dma_addr_t max_direct_dma_addr; #endif +#ifdef CONFIG_EEH + struct eeh_dev *edev; +#endif }; struct pdev_archdata { diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 66ea9b8b95c..d60f99814ff 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -1,6 +1,6 @@ /* - * eeh.h * Copyright (C) 2001 Dave Engebretsen & Todd Inglett IBM Corporation. + * Copyright 2001-2012 IBM Corporation. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -31,44 +31,105 @@ struct device_node; #ifdef CONFIG_EEH -extern int eeh_subsystem_enabled; +/* + * The struct is used to trace EEH state for the associated + * PCI device node or PCI device. In future, it might + * represent PE as well so that the EEH device to form + * another tree except the currently existing tree of PCI + * buses and PCI devices + */ +#define EEH_MODE_SUPPORTED (1<<0) /* EEH supported on the device */ +#define EEH_MODE_NOCHECK (1<<1) /* EEH check should be skipped */ +#define EEH_MODE_ISOLATED (1<<2) /* The device has been isolated */ +#define EEH_MODE_RECOVERING (1<<3) /* Recovering the device */ +#define EEH_MODE_IRQ_DISABLED (1<<4) /* Interrupt disabled */ + +struct eeh_dev { + int mode; /* EEH mode */ + int class_code; /* Class code of the device */ + int config_addr; /* Config address */ + int pe_config_addr; /* PE config address */ + int check_count; /* Times of ignored error */ + int freeze_count; /* Times of froze up */ + int false_positives; /* Times of reported #ff's */ + u32 config_space[16]; /* Saved PCI config space */ + struct pci_controller *phb; /* Associated PHB */ + struct device_node *dn; /* Associated device node */ + struct pci_dev *pdev; /* Associated PCI device */ +}; + +static inline struct device_node *eeh_dev_to_of_node(struct eeh_dev *edev) +{ + return edev->dn; +} + +static inline struct pci_dev *eeh_dev_to_pci_dev(struct eeh_dev *edev) +{ + return edev->pdev; +} -/* Values for eeh_mode bits in device_node */ -#define EEH_MODE_SUPPORTED (1<<0) -#define EEH_MODE_NOCHECK (1<<1) -#define EEH_MODE_ISOLATED (1<<2) -#define EEH_MODE_RECOVERING (1<<3) -#define EEH_MODE_IRQ_DISABLED (1<<4) +/* + * The struct is used to trace the registered EEH operation + * callback functions. Actually, those operation callback + * functions are heavily platform dependent. That means the + * platform should register its own EEH operation callback + * functions before any EEH further operations. + */ +#define EEH_OPT_DISABLE 0 /* EEH disable */ +#define EEH_OPT_ENABLE 1 /* EEH enable */ +#define EEH_OPT_THAW_MMIO 2 /* MMIO enable */ +#define EEH_OPT_THAW_DMA 3 /* DMA enable */ +#define EEH_STATE_UNAVAILABLE (1 << 0) /* State unavailable */ +#define EEH_STATE_NOT_SUPPORT (1 << 1) /* EEH not supported */ +#define EEH_STATE_RESET_ACTIVE (1 << 2) /* Active reset */ +#define EEH_STATE_MMIO_ACTIVE (1 << 3) /* Active MMIO */ +#define EEH_STATE_DMA_ACTIVE (1 << 4) /* Active DMA */ +#define EEH_STATE_MMIO_ENABLED (1 << 5) /* MMIO enabled */ +#define EEH_STATE_DMA_ENABLED (1 << 6) /* DMA enabled */ +#define EEH_RESET_DEACTIVATE 0 /* Deactivate the PE reset */ +#define EEH_RESET_HOT 1 /* Hot reset */ +#define EEH_RESET_FUNDAMENTAL 3 /* Fundamental reset */ +#define EEH_LOG_TEMP 1 /* EEH temporary error log */ +#define EEH_LOG_PERM 2 /* EEH permanent error log */ + +struct eeh_ops { + char *name; + int (*init)(void); + int (*set_option)(struct device_node *dn, int option); + int (*get_pe_addr)(struct device_node *dn); + int (*get_state)(struct device_node *dn, int *state); + int (*reset)(struct device_node *dn, int option); + int (*wait_state)(struct device_node *dn, int max_wait); + int (*get_log)(struct device_node *dn, int severity, char *drv_log, unsigned long len); + int (*configure_bridge)(struct device_node *dn); + int (*read_config)(struct device_node *dn, int where, int size, u32 *val); + int (*write_config)(struct device_node *dn, int where, int size, u32 val); +}; + +extern struct eeh_ops *eeh_ops; +extern int eeh_subsystem_enabled; -/* Max number of EEH freezes allowed before we consider the device - * to be permanently disabled. */ +/* + * Max number of EEH freezes allowed before we consider the device + * to be permanently disabled. + */ #define EEH_MAX_ALLOWED_FREEZES 5 +void * __devinit eeh_dev_init(struct device_node *dn, void *data); +void __devinit eeh_dev_phb_init_dynamic(struct pci_controller *phb); +void __init eeh_dev_phb_init(void); void __init eeh_init(void); +#ifdef CONFIG_PPC_PSERIES +int __init eeh_pseries_init(void); +#endif +int __init eeh_ops_register(struct eeh_ops *ops); +int __exit eeh_ops_unregister(const char *name); unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val); int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev); void __init pci_addr_cache_build(void); - -/** - * eeh_add_device_early - * eeh_add_device_late - * - * Perform eeh initialization for devices added after boot. - * Call eeh_add_device_early before doing any i/o to the - * device (including config space i/o). Call eeh_add_device_late - * to finish the eeh setup for this device. - */ void eeh_add_device_tree_early(struct device_node *); void eeh_add_device_tree_late(struct pci_bus *); - -/** - * eeh_remove_device_recursive - undo EEH for device & children. - * @dev: pci device to be removed - * - * As above, this removes the device; it also removes child - * pci devices as well. - */ void eeh_remove_bus_device(struct pci_dev *); /** @@ -87,8 +148,25 @@ void eeh_remove_bus_device(struct pci_dev *); #define EEH_IO_ERROR_VALUE(size) (~0U >> ((4 - (size)) * 8)) #else /* !CONFIG_EEH */ + +static inline void *eeh_dev_init(struct device_node *dn, void *data) +{ + return NULL; +} + +static inline void eeh_dev_phb_init_dynamic(struct pci_controller *phb) { } + +static inline void eeh_dev_phb_init(void) { } + static inline void eeh_init(void) { } +#ifdef CONFIG_PPC_PSERIES +static inline int eeh_pseries_init(void) +{ + return 0; +} +#endif /* CONFIG_PPC_PSERIES */ + static inline unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val) { return val; diff --git a/arch/powerpc/include/asm/eeh_event.h b/arch/powerpc/include/asm/eeh_event.h index cc3cb04539a..c68b012b779 100644 --- a/arch/powerpc/include/asm/eeh_event.h +++ b/arch/powerpc/include/asm/eeh_event.h @@ -1,6 +1,4 @@ /* - * eeh_event.h - * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or @@ -22,32 +20,19 @@ #define ASM_POWERPC_EEH_EVENT_H #ifdef __KERNEL__ -/** EEH event -- structure holding pci controller data that describes - * a change in the isolation status of a PCI slot. A pointer - * to this struct is passed as the data pointer in a notify callback. +/* + * structure holding pci controller data that describes a + * change in the isolation status of a PCI slot. A pointer + * to this struct is passed as the data pointer in a notify + * callback. */ struct eeh_event { - struct list_head list; - struct device_node *dn; /* struct device node */ - struct pci_dev *dev; /* affected device */ + struct list_head list; /* to form event queue */ + struct eeh_dev *edev; /* EEH device */ }; -/** - * eeh_send_failure_event - generate a PCI error event - * @dev pci device - * - * This routine builds a PCI error event which will be delivered - * to all listeners on the eeh_notifier_chain. - * - * This routine can be called within an interrupt context; - * the actual event will be delivered in a normal context - * (from a workqueue). - */ -int eeh_send_failure_event (struct device_node *dn, - struct pci_dev *dev); - -/* Main recovery function */ -struct pci_dn * handle_eeh_events (struct eeh_event *); +int eeh_send_failure_event(struct eeh_dev *edev); +struct eeh_dev *handle_eeh_events(struct eeh_event *); #endif /* __KERNEL__ */ #endif /* ASM_POWERPC_EEH_EVENT_H */ diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index 6d422979eba..e660b37aa7d 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -47,92 +47,21 @@ extern int rtas_setup_phb(struct pci_controller *phb); extern unsigned long pci_probe_only; -/* ---- EEH internal-use-only related routines ---- */ #ifdef CONFIG_EEH +void pci_addr_cache_build(void); void pci_addr_cache_insert_device(struct pci_dev *dev); void pci_addr_cache_remove_device(struct pci_dev *dev); -void pci_addr_cache_build(void); -struct pci_dev *pci_get_device_by_addr(unsigned long addr); - -/** - * eeh_slot_error_detail -- record and EEH error condition to the log - * @pdn: pci device node - * @severity: EEH_LOG_TEMP_FAILURE or EEH_LOG_PERM_FAILURE - * - * Obtains the EEH error details from the RTAS subsystem, - * and then logs these details with the RTAS error log system. - */ -#define EEH_LOG_TEMP_FAILURE 1 -#define EEH_LOG_PERM_FAILURE 2 -void eeh_slot_error_detail (struct pci_dn *pdn, int severity); - -/** - * rtas_pci_enable - enable IO transfers for this slot - * @pdn: pci device node - * @function: either EEH_THAW_MMIO or EEH_THAW_DMA - * - * Enable I/O transfers to this slot - */ -#define EEH_THAW_MMIO 2 -#define EEH_THAW_DMA 3 -int rtas_pci_enable(struct pci_dn *pdn, int function); - -/** - * rtas_set_slot_reset -- unfreeze a frozen slot - * @pdn: pci device node - * - * Clear the EEH-frozen condition on a slot. This routine - * does this by asserting the PCI #RST line for 1/8th of - * a second; this routine will sleep while the adapter is - * being reset. - * - * Returns a non-zero value if the reset failed. - */ -int rtas_set_slot_reset (struct pci_dn *); -int eeh_wait_for_slot_status(struct pci_dn *pdn, int max_wait_msecs); - -/** - * eeh_restore_bars - Restore device configuration info. - * @pdn: pci device node - * - * A reset of a PCI device will clear out its config space. - * This routines will restore the config space for this - * device, and is children, to values previously obtained - * from the firmware. - */ -void eeh_restore_bars(struct pci_dn *); - -/** - * rtas_configure_bridge -- firmware initialization of pci bridge - * @pdn: pci device node - * - * Ask the firmware to configure all PCI bridges devices - * located behind the indicated node. Required after a - * pci device reset. Does essentially the same hing as - * eeh_restore_bars, but for brdges, and lets firmware - * do the work. - */ -void rtas_configure_bridge(struct pci_dn *); - +struct pci_dev *pci_addr_cache_get_device(unsigned long addr); +void eeh_slot_error_detail(struct eeh_dev *edev, int severity); +int eeh_pci_enable(struct eeh_dev *edev, int function); +int eeh_reset_pe(struct eeh_dev *); +void eeh_restore_bars(struct eeh_dev *); int rtas_write_config(struct pci_dn *, int where, int size, u32 val); int rtas_read_config(struct pci_dn *, int where, int size, u32 *val); - -/** - * eeh_mark_slot -- set mode flags for pertition endpoint - * @pdn: pci device node - * - * mark and clear slots: find "partition endpoint" PE and set or - * clear the flags for each subnode of the PE. - */ -void eeh_mark_slot (struct device_node *dn, int mode_flag); -void eeh_clear_slot (struct device_node *dn, int mode_flag); - -/** - * find_device_pe -- Find the associated "Partiationable Endpoint" PE - * @pdn: pci device node - */ -struct device_node * find_device_pe(struct device_node *dn); +void eeh_mark_slot(struct device_node *dn, int mode_flag); +void eeh_clear_slot(struct device_node *dn, int mode_flag); +struct device_node *eeh_find_device_pe(struct device_node *dn); void eeh_sysfs_add_device(struct pci_dev *pdev); void eeh_sysfs_remove_device(struct pci_dev *pdev); diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c index e1612dfb4a9..2049f2d00ff 100644 --- a/arch/powerpc/kernel/of_platform.c +++ b/arch/powerpc/kernel/of_platform.c @@ -21,12 +21,13 @@ #include <linux/of.h> #include <linux/of_device.h> #include <linux/of_platform.h> +#include <linux/atomic.h> #include <asm/errno.h> #include <asm/topology.h> #include <asm/pci-bridge.h> #include <asm/ppc-pci.h> -#include <linux/atomic.h> +#include <asm/eeh.h> #ifdef CONFIG_PPC_OF_PLATFORM_PCI @@ -66,6 +67,9 @@ static int __devinit of_pci_phb_probe(struct platform_device *dev) /* Init pci_dn data structures */ pci_devs_phb_init_dynamic(phb); + /* Create EEH devices for the PHB */ + eeh_dev_phb_init_dynamic(phb); + /* Register devices with EEH */ #ifdef CONFIG_EEH if (dev->dev.of_node->child) diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 6cd8f0196b6..517bd86bc3f 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -275,6 +275,9 @@ void __init find_and_init_phbs(void) of_node_put(root); pci_devs_phb_init(); + /* Create EEH devices for all PHBs */ + eeh_dev_phb_init(); + /* * pci_probe_only and pci_assign_all_buses can be set via properties * in chosen. diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 67b3e6e0cf3..c222189f5bb 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -6,7 +6,8 @@ obj-y := lpar.o hvCall.o nvram.o reconfig.o \ firmware.o power.o dlpar.o mobility.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_SCANLOG) += scanlog.o -obj-$(CONFIG_EEH) += eeh.o eeh_cache.o eeh_driver.o eeh_event.o eeh_sysfs.o +obj-$(CONFIG_EEH) += eeh.o eeh_dev.o eeh_cache.o eeh_driver.o \ + eeh_event.o eeh_sysfs.o eeh_pseries.o obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_PCI) += pci.o pci_dlpar.o obj-$(CONFIG_PSERIES_MSI) += msi.o diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c index c0b40af4ce4..8011088392d 100644 --- a/arch/powerpc/platforms/pseries/eeh.c +++ b/arch/powerpc/platforms/pseries/eeh.c @@ -1,8 +1,8 @@ /* - * eeh.c * Copyright IBM Corporation 2001, 2005, 2006 * Copyright Dave Engebretsen & Todd Inglett 2001 * Copyright Linas Vepstas 2005, 2006 + * Copyright 2001-2012 IBM Corporation. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -22,7 +22,7 @@ */ #include <linux/delay.h> -#include <linux/sched.h> /* for init_mm */ +#include <linux/sched.h> #include <linux/init.h> #include <linux/list.h> #include <linux/pci.h> @@ -86,16 +86,8 @@ /* Time to wait for a PCI slot to report status, in milliseconds */ #define PCI_BUS_RESET_WAIT_MSEC (60*1000) -/* RTAS tokens */ -static int ibm_set_eeh_option; -static int ibm_set_slot_reset; -static int ibm_read_slot_reset_state; -static int ibm_read_slot_reset_state2; -static int ibm_slot_error_detail; -static int ibm_get_config_addr_info; -static int ibm_get_config_addr_info2; -static int ibm_configure_bridge; -static int ibm_configure_pe; +/* Platform dependent EEH operations */ +struct eeh_ops *eeh_ops = NULL; int eeh_subsystem_enabled; EXPORT_SYMBOL(eeh_subsystem_enabled); @@ -103,14 +95,6 @@ EXPORT_SYMBOL(eeh_subsystem_enabled); /* Lock to avoid races due to multiple reports of an error */ static DEFINE_RAW_SPINLOCK(confirm_error_lock); -/* Buffer for reporting slot-error-detail rtas calls. Its here - * in BSS, and not dynamically alloced, so that it ends up in - * RMO where RTAS can access it. - */ -static unsigned char slot_errbuf[RTAS_ERROR_LOG_MAX]; -static DEFINE_SPINLOCK(slot_errbuf_lock); -static int eeh_error_buf_size; - /* Buffer for reporting pci register dumps. Its here in BSS, and * not dynamically alloced, so that it ends up in RMO where RTAS * can access it. @@ -118,74 +102,50 @@ static int eeh_error_buf_size; #define EEH_PCI_REGS_LOG_LEN 4096 static unsigned char pci_regs_buf[EEH_PCI_REGS_LOG_LEN]; -/* System monitoring statistics */ -static unsigned long no_device; -static unsigned long no_dn; -static unsigned long no_cfg_addr; -static unsigned long ignored_check; -static unsigned long total_mmio_ffs; -static unsigned long false_positives; -static unsigned long slot_resets; - -#define IS_BRIDGE(class_code) (((class_code)<<16) == PCI_BASE_CLASS_BRIDGE) - -/* --------------------------------------------------------------- */ -/* Below lies the EEH event infrastructure */ +/* + * The struct is used to maintain the EEH global statistic + * information. Besides, the EEH global statistics will be + * exported to user space through procfs + */ +struct eeh_stats { + u64 no_device; /* PCI device not found */ + u64 no_dn; /* OF node not found */ + u64 no_cfg_addr; /* Config address not found */ + u64 ignored_check; /* EEH check skipped */ + u64 total_mmio_ffs; /* Total EEH checks */ + u64 false_positives; /* Unnecessary EEH checks */ + u64 slot_resets; /* PE reset */ +}; -static void rtas_slot_error_detail(struct pci_dn *pdn, int severity, - char *driver_log, size_t loglen) -{ - int config_addr; - unsigned long flags; - int rc; +static struct eeh_stats eeh_stats; - /* Log the error with the rtas logger */ - spin_lock_irqsave(&slot_errbuf_lock, flags); - memset(slot_errbuf, 0, eeh_error_buf_size); - - /* Use PE configuration address, if present */ - config_addr = pdn->eeh_config_addr; - if (pdn->eeh_pe_config_addr) - config_addr = pdn->eeh_pe_config_addr; - - rc = rtas_call(ibm_slot_error_detail, - 8, 1, NULL, config_addr, - BUID_HI(pdn->phb->buid), - BUID_LO(pdn->phb->buid), - virt_to_phys(driver_log), loglen, - virt_to_phys(slot_errbuf), - eeh_error_buf_size, - severity); - - if (rc == 0) - log_error(slot_errbuf, ERR_TYPE_RTAS_LOG, 0); - spin_unlock_irqrestore(&slot_errbuf_lock, flags); -} +#define IS_BRIDGE(class_code) (((class_code)<<16) == PCI_BASE_CLASS_BRIDGE) /** - * gather_pci_data - copy assorted PCI config space registers to buff - * @pdn: device to report data for + * eeh_gather_pci_data - Copy assorted PCI config space registers to buff + * @edev: device to report data for * @buf: point to buffer in which to log * @len: amount of room in buffer * * This routine captures assorted PCI configuration space data, * and puts them into a buffer for RTAS error logging. */ -static size_t gather_pci_data(struct pci_dn *pdn, char * buf, size_t len) +static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len) { - struct pci_dev *dev = pdn->pcidev; + struct device_node *dn = eeh_dev_to_of_node(edev); + struct pci_dev *dev = eeh_dev_to_pci_dev(edev); u32 cfg; int cap, i; int n = 0; - n += scnprintf(buf+n, len-n, "%s\n", pdn->node->full_name); - printk(KERN_WARNING "EEH: of node=%s\n", pdn->node->full_name); + n += scnprintf(buf+n, len-n, "%s\n", dn->full_name); + printk(KERN_WARNING "EEH: of node=%s\n", dn->full_name); - rtas_read_config(pdn, PCI_VENDOR_ID, 4, &cfg); + eeh_ops->read_config(dn, PCI_VENDOR_ID, 4, &cfg); n += scnprintf(buf+n, len-n, "dev/vend:%08x\n", cfg); printk(KERN_WARNING "EEH: PCI device/vendor: %08x\n", cfg); - rtas_read_config(pdn, PCI_COMMAND, 4, &cfg); + eeh_ops->read_config(dn, PCI_COMMAND, 4, &cfg); n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg); printk(KERN_WARNING "EEH: PCI cmd/status register: %08x\n", cfg); @@ -196,11 +156,11 @@ static size_t gather_pci_data(struct pci_dn *pdn, char * buf, size_t len) /* Gather bridge-specific registers */ if (dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) { - rtas_read_config(pdn, PCI_SEC_STATUS, 2, &cfg); + eeh_ops->read_config(dn, PCI_SEC_STATUS, 2, &cfg); n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg); printk(KERN_WARNING "EEH: Bridge secondary status: %04x\n", cfg); - rtas_read_config(pdn, PCI_BRIDGE_CONTROL, 2, &cfg); + eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &cfg); n += scnprintf(buf+n, len-n, "brdg ctl:%x\n", cfg); printk(KERN_WARNING "EEH: Bridge control: %04x\n", cfg); } @@ -208,11 +168,11 @@ static size_t gather_pci_data(struct pci_dn *pdn, char * buf, size_t len) /* Dump out the PCI-X command and status regs */ cap = pci_find_capability(dev, PCI_CAP_ID_PCIX); if (cap) { - rtas_read_config(pdn, cap, 4, &cfg); + eeh_ops->read_config(dn, cap, 4, &cfg); n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg); printk(KERN_WARNING "EEH: PCI-X cmd: %08x\n", cfg); - rtas_read_config(pdn, cap+4, 4, &cfg); + eeh_ops->read_config(dn, cap+4, 4, &cfg); n += scnprintf(buf+n, len-n, "pcix-stat:%x\n", cfg); printk(KERN_WARNING "EEH: PCI-X status: %08x\n", cfg); } @@ -225,7 +185,7 @@ static size_t gather_pci_data(struct pci_dn *pdn, char * buf, size_t len) "EEH: PCI-E capabilities and status follow:\n"); for (i=0; i<=8; i++) { - rtas_read_config(pdn, cap+4*i, 4, &cfg); + eeh_ops->read_config(dn, cap+4*i, 4, &cfg); n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); printk(KERN_WARNING "EEH: PCI-E %02x: %08x\n", i, cfg); } @@ -237,7 +197,7 @@ static size_t gather_pci_data(struct pci_dn *pdn, char * buf, size_t len) "EEH: PCI-E AER capability register set follows:\n"); for (i=0; i<14; i++) { - rtas_read_config(pdn, cap+4*i, 4, &cfg); + eeh_ops->read_config(dn, cap+4*i, 4, &cfg); n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); printk(KERN_WARNING "EEH: PCI-E AER %02x: %08x\n", i, cfg); } @@ -246,111 +206,46 @@ static size_t gather_pci_data(struct pci_dn *pdn, char * buf, size_t len) /* Gather status on devices under the bridge */ if (dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) { - struct device_node *dn; + struct device_node *child; - for_each_child_of_node(pdn->node, dn) { - pdn = PCI_DN(dn); - if (pdn) - n += gather_pci_data(pdn, buf+n, len-n); + for_each_child_of_node(dn, child) { + if (of_node_to_eeh_dev(child)) + n += eeh_gather_pci_data(of_node_to_eeh_dev(child), buf+n, len-n); } } return n; } -void eeh_slot_error_detail(struct pci_dn *pdn, int severity) -{ - size_t loglen = 0; - pci_regs_buf[0] = 0; - - rtas_pci_enable(pdn, EEH_THAW_MMIO); - rtas_configure_bridge(pdn); - eeh_restore_bars(pdn); - loglen = gather_pci_data(pdn, pci_regs_buf, EEH_PCI_REGS_LOG_LEN); - - rtas_slot_error_detail(pdn, severity, pci_regs_buf, loglen); -} - /** - * read_slot_reset_state - Read the reset state of a device node's slot - * @dn: device node to read - * @rets: array to return results in - */ -static int read_slot_reset_state(struct pci_dn *pdn, int rets[]) -{ - int token, outputs; - int config_addr; - - if (ibm_read_slot_reset_state2 != RTAS_UNKNOWN_SERVICE) { - token = ibm_read_slot_reset_state2; - outputs = 4; - } else { - token = ibm_read_slot_reset_state; - rets[2] = 0; /* fake PE Unavailable info */ - outputs = 3; - } - - /* Use PE configuration address, if present */ - config_addr = pdn->eeh_config_addr; - if (pdn->eeh_pe_config_addr) - config_addr = pdn->eeh_pe_config_addr; - - return rtas_call(token, 3, outputs, rets, config_addr, - BUID_HI(pdn->phb->buid), BUID_LO(pdn->phb->buid)); -} - -/** - * eeh_wait_for_slot_status - returns error status of slot - * @pdn pci device node - * @max_wait_msecs maximum number to millisecs to wait - * - * Return negative value if a permanent error, else return - * Partition Endpoint (PE) status value. + * eeh_slot_error_detail - Generate combined log including driver log and error log + * @edev: device to report error log for + * @severity: temporary or permanent error log * - * If @max_wait_msecs is positive, then this routine will - * sleep until a valid status can be obtained, or until - * the max allowed wait time is exceeded, in which case - * a -2 is returned. + * This routine should be called to generate the combined log, which + * is comprised of driver log and error log. The driver log is figured + * out from the config space of the corresponding PCI device, while + * the error log is fetched through platform dependent function call. */ -int -eeh_wait_for_slot_status(struct pci_dn *pdn, int max_wait_msecs) +void eeh_slot_error_detail(struct eeh_dev *edev, int severity) { - int rc; - int rets[3]; - int mwait; - - while (1) { - rc = read_slot_reset_state(pdn, rets); - if (rc) return rc; - if (rets[1] == 0) return -1; /* EEH is not supported */ - - if (rets[0] != 5) return rets[0]; /* return actual status */ - - if (rets[2] == 0) return -1; /* permanently unavailable */ + size_t loglen = 0; + pci_regs_buf[0] = 0; - if (max_wait_msecs <= 0) break; + eeh_pci_enable(edev, EEH_OPT_THAW_MMIO); + eeh_ops->configure_bridge(eeh_dev_to_of_node(edev)); + eeh_restore_bars(edev); + loglen = eeh_gather_pci_data(edev, pci_regs_buf, EEH_PCI_REGS_LOG_LEN); - mwait = rets[2]; - if (mwait <= 0) { - printk (KERN_WARNING - "EEH: Firmware returned bad wait value=%d\n", mwait); - mwait = 1000; - } else if (mwait > 300*1000) { - printk (KERN_WARNING - "EEH: Firmware is taking too long, time=%d\n", mwait); - mwait = 300*1000; - } - max_wait_msecs -= mwait; - msleep (mwait); - } - - printk(KERN_WARNING "EEH: Timed out waiting for slot status\n"); - return -2; + eeh_ops->get_log(eeh_dev_to_of_node(edev), severity, pci_regs_buf, loglen); } /** - * eeh_token_to_phys - convert EEH address token to phys address - * @token i/o token, should be address in the form 0xA.... + * eeh_token_to_phys - Convert EEH address token to phys address + * @token: I/O token, should be address in the form 0xA.... + * + * This routine should be called to convert virtual I/O address + * to physical one. */ static inline unsigned long eeh_token_to_phys(unsigned long token) { @@ -365,36 +260,43 @@ static inline unsigned long eeh_token_to_phys(unsigned long token) return pa | (token & (PAGE_SIZE-1)); } -/** - * Return the "partitionable endpoint" (pe) under which this device lies +/** + * eeh_find_device_pe - Retrieve the PE for the given device + * @dn: device node + * + * Return the PE under which this device lies */ -struct device_node * find_device_pe(struct device_node *dn) +struct device_node *eeh_find_device_pe(struct device_node *dn) { - while ((dn->parent) && PCI_DN(dn->parent) && - (PCI_DN(dn->parent)->eeh_mode & EEH_MODE_SUPPORTED)) { + while (dn->parent && of_node_to_eeh_dev(dn->parent) && + (of_node_to_eeh_dev(dn->parent)->mode & EEH_MODE_SUPPORTED)) { dn = dn->parent; } return dn; } -/** Mark all devices that are children of this device as failed. - * Mark the device driver too, so that it can see the failure - * immediately; this is critical, since some drivers poll - * status registers in interrupts ... If a driver is polling, - * and the slot is frozen, then the driver can deadlock in - * an interrupt context, which is bad. +/** + * __eeh_mark_slot - Mark all child devices as failed + * @parent: parent device + * @mode_flag: failure flag + * + * Mark all devices that are children of this device as failed. + * Mark the device driver too, so that it can see the failure + * immediately; this is critical, since some drivers poll + * status registers in interrupts ... If a driver is polling, + * and the slot is frozen, then the driver can deadlock in + * an interrupt context, which is bad. */ - static void __eeh_mark_slot(struct device_node *parent, int mode_flag) { struct device_node *dn; for_each_child_of_node(parent, dn) { - if (PCI_DN(dn)) { + if (of_node_to_eeh_dev(dn)) { /* Mark the pci device driver too */ - struct pci_dev *dev = PCI_DN(dn)->pcidev; + struct pci_dev *dev = of_node_to_eeh_dev(dn)->pdev; - PCI_DN(dn)->eeh_mode |= mode_flag; + of_node_to_eeh_dev(dn)->mode |= mode_flag; if (dev && dev->driver) dev->error_state = pci_channel_io_frozen; @@ -404,92 +306,81 @@ static void __eeh_mark_slot(struct device_node *parent, int mode_flag) } } -void eeh_mark_slot (struct device_node *dn, int mode_flag) +/** + * eeh_mark_slot - Mark the indicated device and its children as failed + * @dn: parent device + * @mode_flag: failure flag + * + * Mark the indicated device and its child devices as failed. + * The device drivers are marked as failed as well. + */ +void eeh_mark_slot(struct device_node *dn, int mode_flag) { struct pci_dev *dev; - dn = find_device_pe (dn); + dn = eeh_find_device_pe(dn); /* Back up one, since config addrs might be shared */ - if (!pcibios_find_pci_bus(dn) && PCI_DN(dn->parent)) + if (!pcibios_find_pci_bus(dn) && of_node_to_eeh_dev(dn->parent)) dn = dn->parent; - PCI_DN(dn)->eeh_mode |= mode_flag; + of_node_to_eeh_dev(dn)->mode |= mode_flag; /* Mark the pci device too */ - dev = PCI_DN(dn)->pcidev; + dev = of_node_to_eeh_dev(dn)->pdev; if (dev) dev->error_state = pci_channel_io_frozen; __eeh_mark_slot(dn, mode_flag); } +/** + * __eeh_clear_slot - Clear failure flag for the child devices + * @parent: parent device + * @mode_flag: flag to be cleared + * + * Clear failure flag for the child devices. + */ static void __eeh_clear_slot(struct device_node *parent, int mode_flag) { struct device_node *dn; for_each_child_of_node(parent, dn) { - if (PCI_DN(dn)) { - PCI_DN(dn)->eeh_mode &= ~mode_flag; - PCI_DN(dn)->eeh_check_count = 0; + if (of_node_to_eeh_dev(dn)) { + of_node_to_eeh_dev(dn)->mode &= ~mode_flag; + of_node_to_eeh_dev(dn)->check_count = 0; __eeh_clear_slot(dn, mode_flag); } } } -void eeh_clear_slot (struct device_node *dn, int mode_flag) +/** + * eeh_clear_slot - Clear failure flag for the indicated device and its children + * @dn: parent de |