diff options
Diffstat (limited to 'arch/powerpc/platforms/pseries/eeh.c')
| -rw-r--r-- | arch/powerpc/platforms/pseries/eeh.c | 1055 |
1 files changed, 463 insertions, 592 deletions
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c index c0b40af4ce4f..309d38ef7322 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) +/* + * 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 */ +}; -/* --------------------------------------------------------------- */ -/* Below lies the EEH event infrastructure */ +static struct eeh_stats eeh_stats; -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; - - /* 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 + * 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 * - * Return negative value if a permanent error, else return - * Partition Endpoint (PE) status value. - * - * 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 device + * @mode_flag: flag to be cleared + * + * Clear failure flag for the indicated device and its children. + */ +void eeh_clear_slot(struct device_node *dn, int mode_flag) { unsigned long flags; raw_spin_lock_irqsave(&confirm_error_lock, flags); - 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; - PCI_DN(dn)->eeh_check_count = 0; + of_node_to_eeh_dev(dn)->mode &= ~mode_flag; + of_node_to_eeh_dev(dn)->check_count = 0; __eeh_clear_slot(dn, mode_flag); raw_spin_unlock_irqrestore(&confirm_error_lock, flags); } -void __eeh_set_pe_freset(struct device_node *parent, unsigned int *freset) -{ - struct device_node *dn; - - for_each_child_of_node(parent, dn) { - if (PCI_DN(dn)) { - - struct pci_dev *dev = PCI_DN(dn)->pcidev; - - if (dev && dev->driver) - *freset |= dev->needs_freset; - - __eeh_set_pe_freset(dn, freset); - } - } -} - -void eeh_set_pe_freset(struct device_node *dn, unsigned int *freset) -{ - struct pci_dev *dev; - dn = find_device_pe(dn); - - /* Back up one, since config addrs might be shared */ - if (!pcibios_find_pci_bus(dn) && PCI_DN(dn->parent)) - dn = dn->parent; - - dev = PCI_DN(dn)->pcidev; - if (dev) - *freset |= dev->needs_freset; - - __eeh_set_pe_freset(dn, freset); -} - /** - * eeh_dn_check_failure - check if all 1's data is due to EEH slot freeze - * @dn device node - * @dev pci device, if known + * eeh_dn_check_failure - Check if all 1's data is due to EEH slot freeze + * @dn: device node + * @dev: pci device, if known * * Check for an EEH failure for the given device node. Call this * routine if the result of a read was all 0xff's and you want to @@ -504,35 +395,34 @@ void eeh_set_pe_freset(struct device_node *dn, unsigned int *freset) int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) { int ret; - int rets[3]; unsigned long flags; - struct pci_dn *pdn; + struct eeh_dev *edev; int rc = 0; const char *location; - total_mmio_ffs++; + eeh_stats.total_mmio_ffs++; if (!eeh_subsystem_enabled) return 0; if (!dn) { - no_dn++; + eeh_stats.no_dn++; return 0; } - dn = find_device_pe(dn); - pdn = PCI_DN(dn); + dn = eeh_find_device_pe(dn); + edev = of_node_to_eeh_dev(dn); /* Access to IO BARs might get this far and still not want checking. */ - if (!(pdn->eeh_mode & EEH_MODE_SUPPORTED) || - pdn->eeh_mode & EEH_MODE_NOCHECK) { - ignored_check++; + if (!(edev->mode & EEH_MODE_SUPPORTED) || + edev->mode & EEH_MODE_NOCHECK) { + eeh_stats.ignored_check++; pr_debug("EEH: Ignored check (%x) for %s %s\n", - pdn->eeh_mode, eeh_pci_name(dev), dn->full_name); + edev->mode, eeh_pci_name(dev), dn->full_name); return 0; } - if (!pdn->eeh_config_addr && !pdn->eeh_pe_config_addr) { - no_cfg_addr++; + if (!edev->config_addr && !edev->pe_config_addr) { + eeh_stats.no_cfg_addr++; return 0; } @@ -544,15 +434,15 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) */ raw_spin_lock_irqsave(&confirm_error_lock, flags); rc = 1; - if (pdn->eeh_mode & EEH_MODE_ISOLATED) { - pdn->eeh_check_count ++; - if (pdn->eeh_check_count % EEH_MAX_FAILS == 0) { + if (edev->mode & EEH_MODE_ISOLATED) { + edev->check_count++; + if (edev->check_count % EEH_MAX_FAILS == 0) { location = of_get_property(dn, "ibm,loc-code", NULL); - printk (KERN_ERR "EEH: %d reads ignored for recovering device at " + printk(KERN_ERR "EEH: %d reads ignored for recovering device at " "location=%s driver=%s pci addr=%s\n", - pdn->eeh_check_count, location, + edev->check_count, location, eeh_driver_name(dev), eeh_pci_name(dev)); - printk (KERN_ERR "EEH: Might be infinite loop in %s driver\n", + printk(KERN_ERR "EEH: Might be infinite loop in %s driver\n", eeh_driver_name(dev)); dump_stack(); } @@ -566,58 +456,39 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) * function zero of a multi-function device. * In any case they must share a common PHB. */ - ret = read_slot_reset_state(pdn, rets); - - /* If the call to firmware failed, punt */ - if (ret != 0) { - printk(KERN_WARNING "EEH: read_slot_reset_state() failed; rc=%d dn=%s\n", - ret, dn->full_name); - false_positives++; - pdn->eeh_false_positives ++; - rc = 0; - goto dn_unlock; - } + ret = eeh_ops->get_state(dn, NULL); /* Note that config-io to empty slots may fail; - * they are empty when they don't have children. */ - if ((rets[0] == 5) && (rets[2] == 0) && (dn->child == NULL)) { - false_positives++; - pdn->eeh_false_positives ++; - rc = 0; - goto dn_unlock; - } - - /* If EEH is not supported on this device, punt. */ - if (rets[1] != 1) { - printk(KERN_WARNING "EEH: event on unsupported device, rc=%d dn=%s\n", - ret, dn->full_name); - false_positives++; - pdn->eeh_false_positives ++; - rc = 0; - goto dn_unlock; - } - - /* If not the kind of error we know about, punt. */ - if (rets[0] != 1 && rets[0] != 2 && rets[0] != 4 && rets[0] != 5) { - false_positives++; - pdn->eeh_false_positives ++; + * they are empty when they don't have children. + * We will punt with the following conditions: Failure to get + * PE's state, EEH not support and Permanently unavailable + * state, PE is in good state. + */ + if ((ret < 0) || + (ret == EEH_STATE_NOT_SUPPORT) || + (ret & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) == + (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) { + eeh_stats.false_positives++; + edev->false_positives ++; rc = 0; goto dn_unlock; } - slot_resets++; + eeh_stats.slot_resets++; /* Avoid repeated reports of this failure, including problems * with other functions on this device, and functions under - * bridges. */ - eeh_mark_slot (dn, EEH_MODE_ISOLATED); + * bridges. + */ + eeh_mark_slot(dn, EEH_MODE_ISOLATED); raw_spin_unlock_irqrestore(&confirm_error_lock, flags); - eeh_send_failure_event (dn, dev); + eeh_send_failure_event(edev); /* Most EEH events are due to device driver bugs. Having * a stack trace will help the device-driver authors figure - * out what happened. So print that out. */ + * out what happened. So print that out. + */ dump_stack(); return 1; @@ -629,9 +500,9 @@ dn_unlock: EXPORT_SYMBOL_GPL(eeh_dn_check_failure); /** - * eeh_check_failure - check if all 1's data is due to EEH slot freeze - * @token i/o token, should be address in the form 0xA.... - * @val value, should be all 1's (XXX why do we need this arg??) + * eeh_check_failure - Check if all 1's data is due to EEH slot freeze + * @token: I/O token, should be address in the form 0xA.... + * @val: value, should be all 1's (XXX why do we need this arg??) * * Check for an EEH failure at the given token address. Call this * routine if the result of a read was all 0xff's and you want to @@ -648,14 +519,14 @@ unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned lon /* Finding the phys addr + pci device; this is pretty quick. */ addr = eeh_token_to_phys((unsigned long __force) token); - dev = pci_get_device_by_addr(addr); + dev = pci_addr_cache_get_device(addr); if (!dev) { - no_device++; + eeh_stats.no_device++; return val; } dn = pci_device_to_OF_node(dev); - eeh_dn_check_failure (dn, dev); + eeh_dn_check_failure(dn, dev); pci_dev_put(dev); return val; @@ -663,115 +534,54 @@ unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned lon EXPORT_SYMBOL(eeh_check_failure); -/* ------------------------------------------------------------- */ -/* The code below deals with error recovery */ /** - * rtas_pci_enable - enable MMIO or DMA transfers for this slot - * @pdn pci device node + * eeh_pci_enable - Enable MMIO or DMA transfers for this slot + * @edev: pci device node + * + * This routine should be called to reenable frozen MMIO or DMA + * so that it would work correctly again. It's useful while doing + * recovery or log collection on the indicated device. */ - -int -rtas_pci_enable(struct pci_dn *pdn, int function) +int eeh_pci_enable(struct eeh_dev *edev, int function) { - int config_addr; int rc; + struct device_node *dn = eeh_dev_to_of_node(edev); - /* 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_set_eeh_option, 4, 1, NULL, - config_addr, - BUID_HI(pdn->phb->buid), - BUID_LO(pdn->phb->buid), - function); - + rc = eeh_ops->set_option(dn, function); if (rc) printk(KERN_WARNING "EEH: Unexpected state change %d, err=%d dn=%s\n", - function, rc, pdn->node->full_name); + function, rc, dn->full_name); - rc = eeh_wait_for_slot_status (pdn, PCI_BUS_RESET_WAIT_MSEC); - if ((rc == 4) && (function == EEH_THAW_MMIO)) + rc = eeh_ops->wait_state(dn, PCI_BUS_RESET_WAIT_MSEC); + if (rc > 0 && (rc & EEH_STATE_MMIO_ENABLED) && + (function == EEH_OPT_THAW_MMIO)) return 0; return rc; } /** - * rtas_pci_slot_reset - raises/lowers the pci #RST line - * @pdn pci device node - * @state: 1/0 to raise/lower the #RST - * - * Clear the EEH-frozen condition on a slot. This routine - * asserts the PCI #RST line if the 'state' argument is '1', - * and drops the #RST line if 'state is '0'. This routine is - * safe to call in an interrupt context. - * - */ - -static void -rtas_pci_slot_reset(struct pci_dn *pdn, int state) -{ - int config_addr; - int rc; - - BUG_ON (pdn==NULL); - - if (!pdn->phb) { - printk (KERN_WARNING "EEH: in slot reset, device node %s has no phb\n", - pdn->node->full_name); - return; - } - - /* 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_set_slot_reset, 4, 1, NULL, - config_addr, - BUID_HI(pdn->phb->buid), - BUID_LO(pdn->phb->buid), - state); - - /* Fundamental-reset not supported on this PE, try hot-reset */ - if (rc == -8 && state == 3) { - rc = rtas_call(ibm_set_slot_reset, 4, 1, NULL, - config_addr, - BUID_HI(pdn->phb->buid), - BUID_LO(pdn->phb->buid), 1); - if (rc) - printk(KERN_WARNING - "EEH: Unable to reset the failed slot," - " #RST=%d dn=%s\n", - rc, pdn->node->full_name); - } -} - -/** * pcibios_set_pcie_slot_reset - Set PCI-E reset state - * @dev: pci device struct - * @state: reset state to enter + * @dev: pci device struct + * @state: reset state to enter * * Return value: * 0 if success - **/ + */ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state) { struct device_node *dn = pci_device_to_OF_node(dev); - struct pci_dn *pdn = PCI_DN(dn); switch (state) { case pcie_deassert_reset: - rtas_pci_slot_reset(pdn, 0); + eeh_ops->reset(dn, EEH_RESET_DEACTIVATE); break; case pcie_hot_reset: - rtas_pci_slot_reset(pdn, 1); + eeh_ops->reset(dn, EEH_RESET_HOT); break; case pcie_warm_reset: - rtas_pci_slot_reset(pdn, 3); + eeh_ops->reset(dn, EEH_RESET_FUNDAMENTAL); break; default: return -EINVAL; @@ -781,13 +591,66 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat } /** - * rtas_set_slot_reset -- assert the pci #RST line for 1/4 second - * @pdn: pci device node to be reset. + * __eeh_set_pe_freset - Check the required reset for child devices + * @parent: parent device + * @freset: return value + * + * Each device might have its preferred reset type: fundamental or + * hot reset. The routine is used to collect the information from + * the child devices so that they could be reset accordingly. + */ +void __eeh_set_pe_freset(struct device_node *parent, unsigned int *freset) +{ + struct device_node *dn; + + for_each_child_of_node(parent, dn) { + if (of_node_to_eeh_dev(dn)) { + struct pci_dev *dev = of_node_to_eeh_dev(dn)->pdev; + + if (dev && dev->driver) + *freset |= dev->needs_freset; + + __eeh_set_pe_freset(dn, freset); + } + } +} + +/** + * eeh_set_pe_freset - Check the required reset for the indicated device and its children + * @dn: parent device + * @freset: return value + * + * Each device might have its preferred reset type: fundamental or + * hot reset. The routine is used to collected the information for + * the indicated device and its children so that the bunch of the + * devices could be reset properly. */ +void eeh_set_pe_freset(struct device_node *dn, unsigned int *freset) +{ + struct pci_dev *dev; + dn = eeh_find_device_pe(dn); -static void __rtas_set_slot_reset(struct pci_dn *pdn) + /* Back up one, since config addrs might be shared */ + if (!pcibios_find_pci_bus(dn) && of_node_to_eeh_dev(dn->parent)) + dn = dn->parent; + + dev = of_node_to_eeh_dev(dn)->pdev; + if (dev) + *freset |= dev->needs_freset; + + __eeh_set_pe_freset(dn, freset); +} + +/** + * eeh_reset_pe_once - Assert the pci #RST line for 1/4 second + * @edev: pci device node to be reset. + * + * Assert the PCI #RST line for 1/4 second. + */ +static void eeh_reset_pe_once(struct eeh_dev *edev) { unsigned int freset = 0; + struct device_node *dn = eeh_dev_to_of_node(edev); /* Determine type of EEH reset required for * Partitionable Endpoint, a hot-reset (1) @@ -795,58 +658,68 @@ static void __rtas_set_slot_reset(struct pci_dn *pdn) * A fundamental reset required by any device under * Partitionable Endpoint trumps hot-reset. */ - eeh_set_pe_freset(pdn->node, &freset); + eeh_set_pe_freset(dn, &freset); if (freset) - rtas_pci_slot_reset(pdn, 3); + eeh_ops->reset(dn, EEH_RESET_FUNDAMENTAL); else - rtas_pci_slot_reset(pdn, 1); + eeh_ops->reset(dn, EEH_RESET_HOT); /* The PCI bus requires that the reset be held high for at least - * a 100 milliseconds. We wait a bit longer 'just in case'. */ - + * a 100 milliseconds. We wait a bit longer 'just in case'. + */ #define PCI_BUS_RST_HOLD_TIME_MSEC 250 - msleep (PCI_BUS_RST_HOLD_TIME_MSEC); + msleep(PCI_BUS_RST_HOLD_TIME_MSEC); /* We might get hit with another EEH freeze as soon as the * pci slot reset line is dropped. Make sure we don't miss - * these, and clear the flag now. */ - eeh_clear_slot (pdn->node, EEH_MODE_ISOLATED); + * these, and clear the flag now. + */ + eeh_clear_slot(dn, EEH_MODE_ISOLATED); - rtas_pci_slot_reset (pdn, 0); + eeh_ops->reset(dn, EEH_RESET_DEACTIVATE); /* After a PCI slot has been reset, the PCI Express spec requires * a 1.5 second idle time for the bus to stabilize, before starting - * up traffic. */ + * up traffic. + */ #define PCI_BUS_SETTLE_TIME_MSEC 1800 - msleep (PCI_BUS_SETTLE_TIME_MSEC); + msleep(PCI_BUS_SETTLE_TIME_MSEC); } -int rtas_set_slot_reset(struct pci_dn *pdn) +/** + * eeh_reset_pe - Reset the indicated PE + * @edev: PCI device associated EEH device + * + * This routine should be called to reset indicated device, including + * PE. A PE might include multiple PCI devices and sometimes PCI bridges + * might be involved as well. + */ +int eeh_reset_pe(struct eeh_dev *edev) { int i, rc; + struct device_node *dn = eeh_dev_to_of_node(edev); /* Take three shots at resetting the bus */ for (i=0; i<3; i++) { - __rtas_set_slot_reset(pdn); + eeh_reset_pe_once(edev); - rc = eeh_wait_for_slot_status(pdn, PCI_BUS_RESET_WAIT_MSEC); - if (rc == 0) + rc = eeh_ops->wait_state(dn, PCI_BUS_RESET_WAIT_MSEC); + if (rc == (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) return 0; if (rc < 0) { printk(KERN_ERR "EEH: unrecoverable slot failure %s\n", - pdn->node->full_name); + dn->full_name); return -1; } printk(KERN_ERR "EEH: bus reset %d failed on slot %s, rc=%d\n", - i+1, pdn->node->full_name, rc); + i+1, dn->full_name, rc); } return -1; } -/* ------------------------------------------------------- */ /** Save and restore of PCI BARs * * Although firmware will set up BARs during boot, it doesn't @@ -856,181 +729,122 @@ int rtas_set_slot_reset(struct pci_dn *pdn) */ /** - * __restore_bars - Restore the Base Address Registers - * @pdn: pci device node + * eeh_restore_one_device_bars - Restore the Base Address Registers for one device + * @edev: PCI device associated EEH device * * Loads the PCI configuration space base address registers, * the expansion ROM base address, the latency timer, and etc. * from the saved values in the device node. */ -static inline void __restore_bars (struct pci_dn *pdn) +static inline void eeh_restore_one_device_bars(struct eeh_dev *edev) { int i; u32 cmd; + struct device_node *dn = eeh_dev_to_of_node(edev); + + if (!edev->phb) + return; - if (NULL==pdn->phb) return; for (i=4; i<10; i++) { - rtas_write_config(pdn, i*4, 4, pdn->config_space[i]); + eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]); } /* 12 == Expansion ROM Address */ - rtas_write_config(pdn, 12*4, 4, pdn->config_space[12]); + eeh_ops->write_config(dn, 12*4, 4, edev->config_space[12]); #define BYTE_SWAP(OFF) (8*((OFF)/4)+3-(OFF)) -#define SAVED_BYTE(OFF) (((u8 *)(pdn->config_space))[BYTE_SWAP(OFF)]) +#define SAVED_BYTE(OFF) (((u8 *)(edev->config_space))[BYTE_SWAP(OFF)]) - rtas_write_config (pdn, PCI_CACHE_LINE_SIZE, 1, + eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1, SAVED_BYTE(PCI_CACHE_LINE_SIZE)); - rtas_write_config (pdn, PCI_LATENCY_TIMER, 1, + eeh_ops->write_config(dn, PCI_LATENCY_TIMER, 1, SAVED_BYTE(PCI_LATENCY_TIMER)); /* max latency, min grant, interrupt pin and line */ - rtas_write_config(pdn, 15*4, 4, pdn->config_space[15]); + eeh_ops->write_config(dn, 15*4, 4, edev->config_space[15]); /* Restore PERR & SERR bits, some devices require it, - don't touch the other command bits */ - rtas_read_config(pdn, PCI_COMMAND, 4, &cmd); - if (pdn->config_space[1] & PCI_COMMAND_PARITY) + * don't touch the other command bits + */ + eeh_ops->read_config(dn, PCI_COMMAND, 4, &cmd); + if (edev->config_space[1] & PCI_COMMAND_PARITY) cmd |= PCI_COMMAND_PARITY; else cmd &= ~PCI_COMMAND_PARITY; - if (pdn->config_space[1] & PCI_COMMAND_SERR) + if (edev->config_space[1] & PCI_COMMAND_SERR) cmd |= PCI_COMMAND_SERR; else cmd &= ~PCI_COMMAND_SERR; - rtas_write_config(pdn, PCI_COMMAND, 4, cmd); + eeh_ops->write_config(dn, PCI_COMMAND, 4, cmd); } /** - * eeh_restore_bars - restore the PCI config space info + * eeh_restore_bars - Restore the PCI config space info + * @edev: EEH device * * This routine performs a recursive walk to the children * of this device as well. */ -void eeh_restore_bars(struct pci_dn *pdn) +void eeh_restore_bars(struct eeh_dev *edev) { struct device_node *dn; - if (!pdn) + if (!edev) return; - if ((pdn->eeh_mode & EEH_MODE_SUPPORTED) && !IS_BRIDGE(pdn->class_code)) - __restore_bars (pdn); + if ((edev->mode & EEH_MODE_SUPPORTED) && !IS_BRIDGE(edev->class_code)) + eeh_restore_one_device_bars(edev); - for_each_child_of_node(pdn->node, dn) - eeh_restore_bars (PCI_DN(dn)); + for_each_child_of_node(eeh_dev_to_of_node(edev), dn) + eeh_restore_bars(of_node_to_eeh_dev(dn)); } /** - * eeh_save_bars - save device bars + * eeh_save_bars - Save device bars + * @edev: PCI device associated EEH device * * Save the values of the device bars. Unlike the restore * routine, this routine is *not* recursive. This is because * PCI devices are added individually; but, for the restore, * an entire slot is reset at a time. */ -static void eeh_save_bars(struct pci_dn *pdn) +static void eeh_save_bars(struct eeh_dev *edev) { int i; + struct device_node *dn; - if (!pdn ) + if (!edev) return; + dn = eeh_dev_to_of_node(edev); for (i = 0; i < 16; i++) - rtas_read_config(pdn, i * 4, 4, &pdn->config_space[i]); -} - -void -rtas_configure_bridge(struct pci_dn *pdn) -{ - int config_addr; - int rc; - int token; - - /* 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; - - /* Use new configure-pe function, if supported */ - if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) - token = ibm_configure_pe; - else - token = ibm_configure_bridge; - - rc = rtas_call(token, 3, 1, NULL, - config_addr, - BUID_HI(pdn->phb->buid), - BUID_LO(pdn->phb->buid)); - if (rc) { - printk (KERN_WARNING "EEH: Unable to configure device bridge (%d) for %s\n", - rc, pdn->node->full_name); - } + eeh_ops->read_config(dn, i * 4, 4, &edev->config_space[i]); } -/* ------------------------------------------------------------- */ -/* The code below deals with enabling EEH for devices during the - * early boot sequence. EEH must be enabled before any PCI probing - * can be done. +/** + * eeh_early_enable - Early enable EEH on the indicated device + * @dn: device node + * @data: BUID + * + * Enable EEH functionality on the specified PCI device. The function + * is expected to be called before real PCI probing is done. However, + * the PHBs have been initialized at this point. */ - -#define EEH_ENABLE 1 - -struct eeh_early_enable_info { - unsigned int buid_hi; - unsigned int buid_lo; -}; - -static int get_pe_addr (int config_addr, - struct eeh_early_enable_info *info) -{ - unsigned int rets[3]; - int ret; - - /* Use latest config-addr token on power6 */ - if (ibm_get_config_addr_info2 != RTAS_UNKNOWN_SERVICE) { - /* Make sure we have a PE in hand */ - ret = rtas_call (ibm_get_config_addr_info2, 4, 2, rets, - config_addr, info->buid_hi, info->buid_lo, 1); - if (ret || (rets[0]==0)) - return 0; - - ret = rtas_call (ibm_get_config_addr_info2, 4, 2, rets, - config_addr, info->buid_hi, info->buid_lo, 0); - if (ret) - return 0; - return rets[0]; - } - - /* Use older config-addr token on power5 */ - if (ibm_get_config_addr_info != RTAS_UNKNOWN_SERVICE) { - ret = rtas_call (ibm_get_config_addr_info, 4, 2, rets, - config_addr, info->buid_hi, info->buid_lo, 0); - if (ret) - return 0; - return rets[0]; - } - return 0; -} - -/* Enable eeh for the given device node. */ -static void *early_enable_eeh(struct device_node *dn, void *data) +static void *eeh_early_enable(struct device_node *dn, void *data) { - unsigned int rets[3]; - struct eeh_early_enable_info *info = data; int ret; const u32 *class_code = of_get_property(dn, "class-code", NULL); const u32 *vendor_id = of_get_property(dn, "vendor-id", NULL); const u32 *device_id = of_get_property(dn, "device-id", NULL); const u32 *regs; int enable; - struct pci_dn *pdn = PCI_DN(dn); + struct eeh_dev *edev = of_node_to_eeh_dev(dn); - pdn->class_code = 0; - pdn->eeh_mode = 0; - pdn->eeh_check_count = 0; - pdn->eeh_freeze_count = 0; - pdn->eeh_false_positives = 0; + edev->class_code = 0; + edev->mode = 0; + edev->check_count = 0; + edev->freeze_count = 0; + edev->false_positives = 0; if (!of_device_is_available(dn)) return NULL; @@ -1041,54 +855,56 @@ static void *early_enable_eeh(struct device_node *dn, void *data) /* There is nothing to check on PCI to ISA bridges */ if (dn->type && !strcmp(dn->type, "isa")) { - pdn->eeh_mode |= EEH_MODE_NOCHECK; + edev->mode |= EEH_MODE_NOCHECK; return NULL; } - pdn->class_code = *class_code; + edev->class_code = *class_code; /* Ok... see if this device supports EEH. Some do, some don't, - * and the only way to find out is to check each and every one. */ + * and the only way to find out is to check each and every one. + */ regs = of_get_property(dn, "reg", NULL); if (regs) { /* First register entry is addr (00BBSS00) */ /* Try to enable eeh */ - ret = rtas_call(ibm_set_eeh_option, 4, 1, NULL, - regs[0], info->buid_hi, info->buid_lo, - EEH_ENABLE); + ret = eeh_ops->set_option(dn, EEH_OPT_ENABLE); enable = 0; if (ret == 0) { - pdn->eeh_config_addr = regs[0]; + edev->config_addr = regs[0]; /* If the newer, better, ibm,get-config-addr-info is supported, - * then use that instead. */ - pdn->eeh_pe_config_addr = get_pe_addr(pdn->eeh_config_addr, info); + * then use that instead. + */ + edev->pe_config_addr = eeh_ops->get_pe_addr(dn); /* Some older systems (Power4) allow the * ibm,set-eeh-option call to succeed even on nodes * where EEH is not supported. Verify support - * explicitly. */ - ret = read_slot_reset_state(pdn, rets); - if ((ret == 0) && (rets[1] == 1)) + * explicitly. + */ + ret = eeh_ops->get_state(dn, NULL); + if (ret > 0 && ret != EEH_STATE_NOT_SUPPORT) enable = 1; } if (enable) { eeh_subsystem_enabled = 1; - pdn->eeh_mode |= EEH_MODE_SUPPORTED; + edev->mode |= EEH_MODE_SUPPORTED; pr_debug("EEH: %s: eeh enabled, config=%x pe_config=%x\n", - dn->full_name, pdn->eeh_config_addr, - pdn->eeh_pe_config_addr); + dn->full_name, edev->config_addr, + edev->pe_config_addr); } else { /* This device doesn't support EEH, but it may have an - * EEH parent, in which case we mark it as supported. */ - if (dn->parent && PCI_DN(dn->parent) - && (PCI_DN(dn->parent)->eeh_mode & EEH_MODE_SUPPORTED)) { + * EEH parent, in which case we mark it as supported. + */ + if (dn->parent && of_node_to_eeh_dev(dn->parent) && + (of_node_to_eeh_dev(dn->parent)->mode & EEH_MODE_SUPPORTED)) { /* Parent supports EEH. */ - pdn->eeh_mode |= EEH_MODE_SUPPORTED; - pdn->eeh_config_addr = PCI_DN(dn->parent)->eeh_config_addr; + edev->mode |= EEH_MODE_SUPPORTED; + edev->config_addr = of_node_to_eeh_dev(dn->parent)->config_addr; return NULL; } } @@ -1097,11 +913,63 @@ static void *early_enable_eeh(struct device_node *dn, void *data) dn->full_name); } - eeh_save_bars(pdn); + eeh_save_bars(edev); return NULL; } -/* +/** + * eeh_ops_register - Register platform dependent EEH operations + * @ops: platform dependent EEH operations + * + * Register the platform dependent EEH operation callback + * functions. The platform should call this function before + * any other EEH operations. + */ +int __init eeh_ops_register(struct eeh_ops *ops) +{ + if (!ops->name) { + pr_warning("%s: Invalid EEH ops name for %p\n", + __func__, ops); + return -EINVAL; + } + + if (eeh_ops && eeh_ops != ops) { + pr_warning("%s: EEH ops of platform %s already existing (%s)\n", + __func__, eeh_ops->name, ops->name); + return -EEXIST; + } + + eeh_ops = ops; + + return 0; +} + +/** + * eeh_ops_unregister - Unreigster platform dependent EEH operations + * @name: name of EEH platform operations + * + * Unregister the platform dependent EEH operation callback + * functions. + */ +int __exit eeh_ops_unregister(const char *name) +{ + if (!name || !strlen(name)) { + pr_warning("%s: Invalid EEH ops name\n", + __func__); + return -EINVAL; + } + + if (eeh_ops && !strcmp(eeh_ops->name, name)) { + eeh_ops = NULL; + return 0; + } + + return -EEXIST; +} + +/** + * eeh_init - EEH initialization + * * Initialize EEH by trying to enable it for all of the adapters in the system. * As a side effect we can determine here if eeh is supported at all. * Note that we leave EEH on so failed config cycles won't cause a machine @@ -1116,51 +984,27 @@ static void *early_enable_eeh(struct device_node *dn, void *data) */ void __init eeh_init(void) { - struct device_node *phb, *np; - struct eeh_early_enable_info info; - - raw_spin_lock_init(&confirm_error_lock); - spin_lock_init(&slot_errbuf_lock); + struct pci_controller *hose, *tmp; + struct device_node *phb; + int ret; - np = of_find_node_by_path("/rtas"); - if (np == NULL) + /* call platform initialization function */ + if (!eeh_ops) { + pr_warning("%s: Platform EEH operation not found\n", + __func__); return; - - ibm_set_eeh_option = rtas_token("ibm,set-eeh-option"); - ibm_set_slot_reset = rtas_token("ibm,set-slot-reset"); - ibm_read_slot_reset_state2 = rtas_token("ibm,read-slot-reset-state2"); - ibm_read_slot_reset_state = rtas_token("ibm,read-slot-reset-state"); - ibm_slot_error_detail = rtas_token("ibm,slot-error-detail"); - ibm_get_config_addr_info = rtas_token("ibm,get-config-addr-info"); - ibm_get_config_addr_info2 = rtas_token("ibm,get-config-addr-info2"); - ibm_configure_bridge = rtas_token ("ibm,configure-bridge"); - ibm_configure_pe = rtas_token("ibm,configure-pe"); - - if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE) + } else if ((ret = eeh_ops->init())) { + pr_warning("%s: Failed to call platform init function (%d)\n", + __func__, ret); return; - - eeh_error_buf_size = rtas_token("rtas-error-log-max"); - if (eeh_error_buf_size == RTAS_UNKNOWN_SERVICE) { - eeh_error_buf_size = 1024; - } - if (eeh_error_buf_size > RTAS_ERROR_LOG_MAX) { - printk(KERN_WARNING "EEH: rtas-error-log-max is bigger than allocated " - "buffer ! (%d vs %d)", eeh_error_buf_size, RTAS_ERROR_LOG_MAX); - eeh_error_buf_size = RTAS_ERROR_LOG_MAX; } - /* 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 || PCI_DN(phb) == NULL) - continue; + raw_spin_lock_init(&confirm_error_lock); - info.buid_lo = BUID_LO(buid); - info.buid_hi = BUID_HI(buid); - traverse_pci_devices(phb, early_enable_eeh, &info); + /* 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); } if (eeh_subsystem_enabled) @@ -1170,7 +1014,7 @@ void __init eeh_init(void) } /** - * eeh_add_device_early - enable EEH for the indicated device_node + * eeh_add_device_early - Enable EEH for the indicated device_node * @dn: device node for which to set up EEH * * This routine must be used to perform EEH initialization for PCI @@ -1184,21 +1028,26 @@ void __init eeh_init(void) static void eeh_add_device_early(struct device_node *dn) { struct pci_controller *phb; - struct eeh_early_enable_info info; - if (!dn || !PCI_DN(dn)) + if (!dn || !of_node_to_eeh_dev(dn)) return; - phb = PCI_DN(dn)->phb; + phb = of_node_to_eeh_dev(dn)->phb; /* USB Bus children of PCI devices will not have BUID's */ if (NULL == phb || 0 == phb->buid) return; - info.buid_hi = BUID_HI(phb->buid); - info.buid_lo = BUID_LO(phb->buid); - early_enable_eeh(dn, &info); + eeh_early_enable(dn, NULL); } +/** + * eeh_add_device_tree_early - Enable EEH for the indicated device + * @dn: device node + * + * This routine must be used to perform EEH initialization for the + * indicated PCI device that was added after system boot (e.g. + * hotplug, dlpar). + */ void eeh_add_device_tree_early(struct device_node *dn) { struct device_node *sib; @@ -1210,7 +1059,7 @@ void eeh_add_device_tree_early(struct device_node *dn) EXPORT_SYMBOL_GPL(eeh_add_device_tree_early); /** - * eeh_add_device_late - perform EEH initialization for the indicated pci device + * eeh_add_device_late - Perform EEH initialization for the indicated pci device * @dev: pci device for which to set up EEH * * This routine must be used to complete EEH initialization for PCI @@ -1219,7 +1068,7 @@ EXPORT_SYMBOL_GPL(eeh_add_device_tree_early); static void eeh_add_device_late(struct pci_dev *dev) { struct device_node *dn; - struct pci_dn *pdn; + struct eeh_dev *edev; if (!dev || !eeh_subsystem_enabled) return; @@ -1227,20 +1076,29 @@ static void eeh_add_device_late(struct pci_dev *dev) pr_debug("EEH: Adding device %s\n", pci_name(dev)); dn = pci_device_to_OF_node(dev); - pdn = PCI_DN(dn); - if (pdn->pcidev == dev) { + edev = pci_dev_to_eeh_dev(dev); + if (edev->pdev == dev) { pr_debug("EEH: Already referenced !\n"); return; } - WARN_ON(pdn->pcidev); + WARN_ON(edev->pdev); - pci_dev_get (dev); - pdn->pcidev = dev; + pci_dev_get(dev); + edev->pdev = dev; + dev->dev.archdata.edev = edev; pci_addr_cache_insert_device(dev); eeh_sysfs_add_device(dev); } +/** + * eeh_add_device_tree_late - Perform EEH initialization for the indicated PCI bus + * @bus: PCI bus + * + * This routine must be used to perform EEH initialization for PCI + * devices which are attached to the indicated PCI bus. The PCI bus + * is added after system boot through hotplug or dlpar. + */ void eeh_add_device_tree_late(struct pci_bus *bus) { struct pci_dev *dev; @@ -1257,7 +1115,7 @@ void eeh_add_device_tree_late(struct pci_bus *bus) EXPORT_SYMBOL_GPL(eeh_add_device_tree_late); /** - * eeh_remove_device - undo EEH setup for the indicated pci device + * eeh_remove_device - Undo EEH setup for the indicated pci device * @dev: pci device to be removed * * This routine should be called when a device is removed from @@ -1268,25 +1126,35 @@ EXPORT_SYMBOL_GPL(eeh_add_device_tree_late); */ static void eeh_remove_device(struct pci_dev *dev) { - struct device_node *dn; + struct eeh_dev *edev; + if (!dev || !eeh_subsystem_enabled) return; + edev = pci_dev_to_eeh_dev(dev); /* Unregister the device with the EEH/PCI address search system */ pr_debug("EEH: Removing device %s\n", pci_name(dev)); - dn = pci_device_to_OF_node(dev); - if (PCI_DN(dn)->pcidev == NULL) { + if (!edev || !edev->pdev) { pr_debug("EEH: Not referenced !\n"); return; } - PCI_DN(dn)->pcidev = NULL; - pci_dev_put (dev); + edev->pdev = NULL; + dev->dev.archdata.edev = NULL; + pci_dev_put(dev); pci_addr_cache_remove_device(dev); eeh_sysfs_remove_device(dev); } +/** + * eeh_remove_bus_device - Undo EEH setup for the indicated PCI device + * @dev: PCI device + * + * This routine must be called when a device is removed from the + * running system through hotplug or dlpar. The corresponding + * PCI address cache will be removed. + */ void eeh_remove_bus_device(struct pci_dev *dev) { struct pci_bus *bus = dev->subordinate; @@ -1305,21 +1173,24 @@ static int proc_eeh_show(struct seq_file *m, void *v) { if (0 == eeh_subsystem_enabled) { seq_printf(m, "EEH Subsystem is globally disabled\n"); - seq_printf(m, "eeh_total_mmio_ffs=%ld\n", total_mmio_ffs); + seq_printf(m, "eeh_total_mmio_ffs=%llu\n", eeh_stats.total_mmio_ffs); } else { seq_printf(m, "EEH Subsystem is enabled\n"); seq_printf(m, - "no device=%ld\n" - "no device node=%ld\n" - "no config address=%ld\n" - "check not wanted=%ld\n" - "eeh_total_mmio_ffs=%ld\n" - "eeh_false_positives=%ld\n" - "eeh_slot_resets=%ld\n", - no_device, no_dn, no_cfg_addr, - ignored_check, total_mmio_ffs, - false_positives, - slot_resets); + "no device=%llu\n" + "no device node=%llu\n" + "no config address=%llu\n" + "check not wanted=%llu\n" + "eeh_total_mmio_ffs=%llu\n" + "eeh_false_positives=%llu\n" + "eeh_slot_resets=%llu\n", + eeh_stats.no_device, + eeh_stats.no_dn, + eeh_stats.no_cfg_addr, + eeh_stats.ignored_check, + eeh_stats.total_mmio_ffs, + eeh_stats.false_positives, + eeh_stats.slot_resets); } return 0; |