/* * Delay for PE reset, all in ms * * PCI specification has reset hold time of 100 milliseconds. * We have 250 milliseconds here. The PCI bus settlement time * is specified as 1.5 seconds and we have 1.8 seconds.
*/ #define EEH_PE_RST_HOLD_TIME 250 #define EEH_PE_RST_SETTLE_TIME 1800
/* * The struct is used to trace PE related EEH functionality. * In theory, there will have one instance of the struct to * be created against particular PE. In nature, PEs correlate * to each other. the struct has to reflect that hierarchy in * order to easily pick up those affected PEs when one particular * PE has EEH errors. * * Also, one particular PE might be composed of PCI device, PCI * bus and its subordinate components. The struct also need ship * the information. Further more, one particular PE is only meaingful * in the corresponding PHB. Therefore, the root PEs should be created * against existing PHBs in on-to-one fashion.
*/ #define EEH_PE_INVALID (1 << 0) /* Invalid */ #define EEH_PE_PHB (1 << 1) /* PHB PE */ #define EEH_PE_DEVICE (1 << 2) /* Device PE */ #define EEH_PE_BUS (1 << 3) /* Bus PE */ #define EEH_PE_VF (1 << 4) /* VF PE */
#define EEH_PE_ISOLATED (1 << 0) /* Isolated PE */ #define EEH_PE_RECOVERING (1 << 1) /* Recovering PE */ #define EEH_PE_CFG_BLOCKED (1 << 2) /* Block config access */ #define EEH_PE_RESET (1 << 3) /* PE reset in progress */
struct eeh_pe { int type; /* PE type: PHB/Bus/Device */ int state; /* PE EEH dependent mode */ int addr; /* PE configuration address */ struct pci_controller *phb; /* Associated PHB */ struct pci_bus *bus; /* Top PCI bus for bus PE */ int check_count; /* Times of ignored error */ int freeze_count; /* Times of froze up */
time64_t tstamp; /* Time on first-time freeze */ int false_positives; /* Times of reported #ff's */
atomic_t pass_dev_cnt; /* Count of passed through devs */ struct eeh_pe *parent; /* Parent PE */ void *data; /* PE auxiliary data */ struct list_head child_list; /* List of PEs below this PE */ struct list_head child; /* Memb. child_list/eeh_phb_pe */ struct list_head edevs; /* List of eeh_dev in this PE */
#ifdef CONFIG_STACKTRACE /* * Saved stack trace. When we find a PE freeze in eeh_dev_check_failure * the stack trace is saved here so we can print it in the recovery * thread if it turns out to due to a real problem rather than * a hot-remove. * * A max of 64 entries might be overkill, but it also might not be.
*/ unsignedlong stack_trace[64]; int trace_entries; #endif/* CONFIG_STACKTRACE */
};
/* * 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_DEV_BRIDGE (1 << 0) /* PCI bridge */ #define EEH_DEV_ROOT_PORT (1 << 1) /* PCIe root port */ #define EEH_DEV_DS_PORT (1 << 2) /* Downstream port */ #define EEH_DEV_IRQ_DISABLED (1 << 3) /* Interrupt disabled */ #define EEH_DEV_DISCONNECTED (1 << 4) /* Removing from PE */
/* * 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_OPT_FREEZE_PE 4 /* Freeze PE */ #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; struct eeh_dev *(*probe)(struct pci_dev *pdev); int (*set_option)(struct eeh_pe *pe, int option); int (*get_state)(struct eeh_pe *pe, int *delay); int (*reset)(struct eeh_pe *pe, int option); int (*get_log)(struct eeh_pe *pe, int severity, char *drv_log, unsignedlong len); int (*configure_bridge)(struct eeh_pe *pe); int (*err_inject)(struct eeh_pe *pe, int type, int func, unsignedlong addr, unsignedlong mask); int (*read_config)(struct eeh_dev *edev, int where, int size, u32 *val); int (*write_config)(struct eeh_dev *edev, int where, int size, u32 val); int (*next_error)(struct eeh_pe **pe); int (*restore_config)(struct eeh_dev *edev); int (*notify_resume)(struct eeh_dev *edev);
};
void eeh_show_enabled(void); int __init eeh_init(struct eeh_ops *ops); int eeh_check_failure(constvolatilevoid __iomem *token); int eeh_dev_check_failure(struct eeh_dev *edev); void eeh_addr_cache_init(void); void eeh_probe_device(struct pci_dev *pdev); void eeh_remove_device(struct pci_dev *); int eeh_unfreeze_pe(struct eeh_pe *pe); int eeh_pe_reset_and_recover(struct eeh_pe *pe); int eeh_dev_open(struct pci_dev *pdev); void eeh_dev_release(struct pci_dev *pdev); struct eeh_pe *eeh_iommu_group_to_pe(struct iommu_group *group); int eeh_pe_set_option(struct eeh_pe *pe, int option); int eeh_pe_get_state(struct eeh_pe *pe); int eeh_pe_reset(struct eeh_pe *pe, int option, bool include_passed); int eeh_pe_configure(struct eeh_pe *pe); int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func, unsignedlong addr, unsignedlong mask); int eeh_pe_inject_mmio_error(struct pci_dev *pdev);
/** * EEH_POSSIBLE_ERROR() -- test for possible MMIO failure. * * If this macro yields TRUE, the caller relays to eeh_check_failure() * which does further tests out of line.
*/ #define EEH_POSSIBLE_ERROR(val, type) ((val) == (type)~0 && eeh_enabled())
/* * Reads from a device which has been isolated by EEH will return * all 1s. This macro gives an all-1s value of the given size (in * bytes: 1, 2, or 4) for comparing with the result of a read.
*/ #define EEH_IO_ERROR_VALUE(size) (~0U >> ((4 - (size)) * 8))
/* Look for ffff's here at dest[n]. Assume that at least 4 bytes * were copied. Check all four bytes.
*/ if (n >= 4 && EEH_POSSIBLE_ERROR(*((u32 *)(dest + n - 4)), u32))
eeh_check_failure(src);
}
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.