diff options
| -rw-r--r-- | Documentation/PCI/pci-error-recovery.txt | 35 | ||||
| -rw-r--r-- | drivers/pci/hotplug/pciehp_hpc.c | 20 | ||||
| -rw-r--r-- | drivers/pci/pci-driver.c | 2 | ||||
| -rw-r--r-- | drivers/pci/pci.c | 29 | ||||
| -rw-r--r-- | drivers/pci/pci.h | 5 | ||||
| -rw-r--r-- | drivers/pci/pcie/Makefile | 2 | ||||
| -rw-r--r-- | drivers/pci/pcie/aer/aerdrv.c | 11 | ||||
| -rw-r--r-- | drivers/pci/pcie/aer/aerdrv.h | 32 | ||||
| -rw-r--r-- | drivers/pci/pcie/aer/aerdrv_core.c | 397 | ||||
| -rw-r--r-- | drivers/pci/pcie/aer/aerdrv_errprint.c | 38 | ||||
| -rw-r--r-- | drivers/pci/pcie/dpc.c | 69 | ||||
| -rw-r--r-- | drivers/pci/pcie/err.c | 388 | ||||
| -rw-r--r-- | drivers/pci/pcie/portdrv.h | 3 | ||||
| -rw-r--r-- | drivers/pci/pcie/portdrv_core.c | 69 | ||||
| -rw-r--r-- | include/linux/aer.h | 1 | ||||
| -rw-r--r-- | include/linux/pci.h | 2 | ||||
| -rw-r--r-- | include/ras/ras_event.h | 22 | ||||
| -rw-r--r-- | include/uapi/linux/pci_regs.h | 1 |
18 files changed, 650 insertions, 476 deletions
diff --git a/Documentation/PCI/pci-error-recovery.txt b/Documentation/PCI/pci-error-recovery.txt index 0b6bb3ef449e..688b69121e82 100644 --- a/Documentation/PCI/pci-error-recovery.txt +++ b/Documentation/PCI/pci-error-recovery.txt @@ -110,7 +110,7 @@ The actual steps taken by a platform to recover from a PCI error event will be platform-dependent, but will follow the general sequence described below. -STEP 0: Error Event +STEP 0: Error Event: ERR_NONFATAL ------------------- A PCI bus error is detected by the PCI hardware. On powerpc, the slot is isolated, in that all I/O is blocked: all reads return 0xffffffff, @@ -228,13 +228,7 @@ proceeds to either STEP3 (Link Reset) or to STEP 5 (Resume Operations). If any driver returned PCI_ERS_RESULT_NEED_RESET, then the platform proceeds to STEP 4 (Slot Reset) -STEP 3: Link Reset ------------------- -The platform resets the link. This is a PCI-Express specific step -and is done whenever a fatal error has been detected that can be -"solved" by resetting the link. - -STEP 4: Slot Reset +STEP 3: Slot Reset ------------------ In response to a return value of PCI_ERS_RESULT_NEED_RESET, the @@ -320,7 +314,7 @@ Failure). >>> However, it probably should. -STEP 5: Resume Operations +STEP 4: Resume Operations ------------------------- The platform will call the resume() callback on all affected device drivers if all drivers on the segment have returned @@ -332,7 +326,7 @@ a result code. At this point, if a new error happens, the platform will restart a new error recovery sequence. -STEP 6: Permanent Failure +STEP 5: Permanent Failure ------------------------- A "permanent failure" has occurred, and the platform cannot recover the device. The platform will call error_detected() with a @@ -355,6 +349,27 @@ errors. See the discussion in powerpc/eeh-pci-error-recovery.txt for additional detail on real-life experience of the causes of software errors. +STEP 0: Error Event: ERR_FATAL +------------------- +PCI bus error is detected by the PCI hardware. On powerpc, the slot is +isolated, in that all I/O is blocked: all reads return 0xffffffff, all +writes are ignored. + +STEP 1: Remove devices +-------------------- +Platform removes the devices depending on the error agent, it could be +this port for all subordinates or upstream component (likely downstream +port) + +STEP 2: Reset link +-------------------- +The platform resets the link. This is a PCI-Express specific step and is +done whenever a fatal error has been detected that can be "solved" by +resetting the link. + +STEP 3: Re-enumerate the devices +-------------------- +Initiates the re-enumeration. Conclusion; General Remarks --------------------------- diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 18a42f8f5dc5..e0c2b8ead6cb 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -231,25 +231,11 @@ bool pciehp_check_link_active(struct controller *ctrl) return ret; } -static void __pcie_wait_link_active(struct controller *ctrl, bool active) -{ - int timeout = 1000; - - if (pciehp_check_link_active(ctrl) == active) - return; - while (timeout > 0) { - msleep(10); - timeout -= 10; - if (pciehp_check_link_active(ctrl) == active) - return; - } - ctrl_dbg(ctrl, "Data Link Layer Link Active not %s in 1000 msec\n", - active ? "set" : "cleared"); -} - static void pcie_wait_link_active(struct controller *ctrl) { - __pcie_wait_link_active(ctrl, true); + struct pci_dev *pdev = ctrl_dev(ctrl); + + pcie_wait_for_link(pdev, true); } static bool pci_bus_check_dev(struct pci_bus *bus, int devfn) diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 6ace47099fc5..ffb956457b4a 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -1535,7 +1535,7 @@ static int pci_uevent(struct device *dev, struct kobj_uevent_env *env) return 0; } -#if defined(CONFIG_PCIEAER) || defined(CONFIG_EEH) +#if defined(CONFIG_PCIEPORTBUS) || defined(CONFIG_EEH) /** * pci_uevent_ers - emit a uevent during recovery path of PCI device * @pdev: PCI device undergoing error recovery diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e597655a5643..764bf64a097d 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4138,6 +4138,35 @@ static int pci_pm_reset(struct pci_dev *dev, int probe) return pci_dev_wait(dev, "PM D3->D0", PCIE_RESET_READY_POLL_MS); } +/** + * pcie_wait_for_link - Wait until link is active or inactive + * @pdev: Bridge device + * @active: waiting for active or inactive? + * + * Use this to wait till link becomes active or inactive. + */ +bool pcie_wait_for_link(struct pci_dev *pdev, bool active) +{ + int timeout = 1000; + bool ret; + u16 lnk_status; + + for (;;) { + pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status); + ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA); + if (ret == active) + return true; + if (timeout <= 0) + break; + msleep(10); + timeout -= 10; + } + + pci_info(pdev, "Data Link Layer Link Active not %s in 1000 msec\n", + active ? "set" : "cleared"); + + return false; +} void pci_reset_secondary_bus(struct pci_dev *dev) { diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 023f7cf25bff..6af75952cac7 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -353,6 +353,11 @@ static inline resource_size_t pci_resource_alignment(struct pci_dev *dev, void pci_enable_acs(struct pci_dev *dev); +/* PCI error reporting and recovery */ +void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service); +void pcie_do_nonfatal_recovery(struct pci_dev *dev); + +bool pcie_wait_for_link(struct pci_dev *pdev, bool active); #ifdef CONFIG_PCIEASPM void pcie_aspm_init_link_state(struct pci_dev *pdev); void pcie_aspm_exit_link_state(struct pci_dev *pdev); diff --git a/drivers/pci/pcie/Makefile b/drivers/pci/pcie/Makefile index 800e1d404a45..03f4e0b3a140 100644 --- a/drivers/pci/pcie/Makefile +++ b/drivers/pci/pcie/Makefile @@ -2,7 +2,7 @@ # # Makefile for PCI Express features and port driver -pcieportdrv-y := portdrv_core.o portdrv_pci.o +pcieportdrv-y := portdrv_core.o portdrv_pci.o err.o obj-$(CONFIG_PCIEPORTBUS) += pcieportdrv.o diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c index 779b3879b1b5..9735c19bf39c 100644 --- a/drivers/pci/pcie/aer/aerdrv.c +++ b/drivers/pci/pcie/aer/aerdrv.c @@ -94,7 +94,7 @@ static void set_downstream_devices_error_reporting(struct pci_dev *dev, */ static void aer_enable_rootport(struct aer_rpc *rpc) { - struct pci_dev *pdev = rpc->rpd->port; + struct pci_dev *pdev = rpc->rpd; int aer_pos; u16 reg16; u32 reg32; @@ -136,7 +136,7 @@ static void aer_enable_rootport(struct aer_rpc *rpc) */ static void aer_disable_rootport(struct aer_rpc *rpc) { - struct pci_dev *pdev = rpc->rpd->port; + struct pci_dev *pdev = rpc->rpd; u32 reg32; int pos; @@ -232,7 +232,7 @@ static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev) /* Initialize Root lock access, e_lock, to Root Error Status Reg */ spin_lock_init(&rpc->e_lock); - rpc->rpd = dev; + rpc->rpd = dev->port; INIT_WORK(&rpc->dpc_handler, aer_isr); mutex_init(&rpc->rpc_mutex); @@ -353,10 +353,7 @@ static void aer_error_resume(struct pci_dev *dev) pos = dev->aer_cap; pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status); pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &mask); - if (dev->error_state == pci_channel_io_normal) - status &= ~mask; /* Clear corresponding nonfatal bits */ - else - status &= mask; /* Clear corresponding fatal bits */ + status &= ~mask; /* Clear corresponding nonfatal bits */ pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status); } diff --git a/drivers/pci/pcie/aer/aerdrv.h b/drivers/pci/pcie/aer/aerdrv.h index 08b4584f62fe..6e0ad9a68fd9 100644 --- a/drivers/pci/pcie/aer/aerdrv.h +++ b/drivers/pci/pcie/aer/aerdrv.h @@ -58,7 +58,7 @@ struct aer_err_source { }; struct aer_rpc { - struct pcie_device *rpd; /* Root Port device */ + struct pci_dev *rpd; /* Root Port device */ struct work_struct dpc_handler; struct aer_err_source e_sources[AER_ERROR_SOURCES_MAX]; struct aer_err_info e_info; @@ -76,36 +76,6 @@ struct aer_rpc { */ }; -struct aer_broadcast_data { - enum pci_channel_state state; - enum pci_ers_result result; -}; - -static inline pci_ers_result_t merge_result(enum pci_ers_result orig, - enum pci_ers_result new) -{ - if (new == PCI_ERS_RESULT_NO_AER_DRIVER) - return PCI_ERS_RESULT_NO_AER_DRIVER; - - if (new == PCI_ERS_RESULT_NONE) - return orig; - - switch (orig) { - case PCI_ERS_RESULT_CAN_RECOVER: - case PCI_ERS_RESULT_RECOVERED: - orig = new; - break; - case PCI_ERS_RESULT_DISCONNECT: - if (new == PCI_ERS_RESULT_NEED_RESET) - orig = PCI_ERS_RESULT_NEED_RESET; - break; - default: - break; - } - - return orig; -} - extern struct bus_type pcie_port_bus_type; void aer_isr(struct work_struct *work); void aer_print_error(struct pci_dev *dev, struct aer_err_info *info); diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c index 0ea5acc40323..42d4f3f32282 100644 --- a/drivers/pci/pcie/aer/aerdrv_core.c +++ b/drivers/pci/pcie/aer/aerdrv_core.c @@ -20,6 +20,7 @@ #include <linux/slab.h> #include <linux/kfifo.h> #include "aerdrv.h" +#include "../../pci.h" #define PCI_EXP_AER_FLAGS (PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE | \ PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE) @@ -227,329 +228,14 @@ static bool find_source_device(struct pci_dev *parent, return true; } -static int report_error_detected(struct pci_dev *dev, void *data) -{ - pci_ers_result_t vote; - const struct pci_error_handlers *err_handler; - struct aer_broadcast_data *result_data; - result_data = (struct aer_broadcast_data *) data; - - device_lock(&dev->dev); - dev->error_state = result_data->state; - - if (!dev->driver || - !dev->driver->err_handler || - !dev->driver->err_handler->error_detected) { - if (result_data->state == pci_channel_io_frozen && - dev->hdr_type != PCI_HEADER_TYPE_BRIDGE) { - /* - * In case of fatal recovery, if one of down- - * stream device has no driver. We might be - * unable to recover because a later insmod - * of a driver for this device is unaware of - * its hw state. - */ - pci_printk(KERN_DEBUG, dev, "device has %s\n", - dev->driver ? - "no AER-aware driver" : "no driver"); - } - - /* - * If there's any device in the subtree that does not - * have an error_detected callback, returning - * PCI_ERS_RESULT_NO_AER_DRIVER prevents calling of - * the subsequent mmio_enabled/slot_reset/resume - * callbacks of "any" device in the subtree. All the - * devices in the subtree are left in the error state - * without recovery. - */ - - if (dev->hdr_type != PCI_HEADER_TYPE_BRIDGE) - vote = PCI_ERS_RESULT_NO_AER_DRIVER; - else - vote = PCI_ERS_RESULT_NONE; - } else { - err_handler = dev->driver->err_handler; - vote = err_handler->error_detected(dev, result_data->state); - pci_uevent_ers(dev, PCI_ERS_RESULT_NONE); - } - - result_data->result = merge_result(result_data->result, vote); - device_unlock(&dev->dev); - return 0; -} - -static int report_mmio_enabled(struct pci_dev *dev, void *data) -{ - pci_ers_result_t vote; - const struct pci_error_handlers *err_handler; - struct aer_broadcast_data *result_data; - result_data = (struct aer_broadcast_data *) data; - - device_lock(&dev->dev); - if (!dev->driver || - !dev->driver->err_handler || - !dev->driver->err_handler->mmio_enabled) - goto out; - - err_handler = dev->driver->err_handler; - vote = err_handler->mmio_enabled(dev); - result_data->result = merge_result(result_data->result, vote); -out: - device_unlock(&dev->dev); - return 0; -} - -static int report_slot_reset(struct pci_dev *dev, void *data) -{ - pci_ers_result_t vote; - const struct pci_error_handlers *err_handler; - struct aer_broadcast_data *result_data; - result_data = (struct aer_broadcast_data *) data; - - device_lock(&dev->dev); - if (!dev->driver || - !dev->driver->err_handler || - !dev->driver->err_handler->slot_reset) - goto out; - - err_handler = dev->driver->err_handler; - vote = err_handler->slot_reset(dev); - result_data->result = merge_result(result_data->result, vote); -out: - device_unlock(&dev->dev); - return 0; -} - -static int report_resume(struct pci_dev *dev, void *data) -{ - const struct pci_error_handlers *err_handler; - - device_lock(&dev->dev); - dev->error_state = pci_channel_io_normal; - - if (!dev->driver || - !dev->driver->err_handler || - !dev->driver->err_handler->resume) - goto out; - - err_handler = dev->driver->err_handler; - err_handler->resume(dev); - pci_uevent_ers(dev, PCI_ERS_RESULT_RECOVERED); -out: - device_unlock(&dev->dev); - return 0; -} - -/** - * broadcast_error_message - handle message broadcast to downstream drivers - * @dev: pointer to from where in a hierarchy message is broadcasted down - * @state: error state - * @error_mesg: message to print - * @cb: callback to be broadcasted - * - * Invoked during error recovery process. Once being invoked, the content - * of error severity will be broadcasted to all downstream drivers in a - * hierarchy in question. - */ -static pci_ers_result_t broadcast_error_message(struct pci_dev *dev, - enum pci_channel_state state, - char *error_mesg, - int (*cb)(struct pci_dev *, void *)) -{ - struct aer_broadcast_data result_data; - - pci_printk(KERN_DEBUG, dev, "broadcast %s message\n", error_mesg); - result_data.state = state; - if (cb == report_error_detected) - result_data.result = PCI_ERS_RESULT_CAN_RECOVER; - else - result_data.result = PCI_ERS_RESULT_RECOVERED; - - if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) { - /* - * If the error is reported by a bridge, we think this error - * is related to the downstream link of the bridge, so we - * do error recovery on all subordinates of the bridge instead - * of the bridge and clear the error status of the bridge. - */ - if (cb == report_error_detected) - dev->error_state = state; - pci_walk_bus(dev->subordinate, cb, &result_data); - if (cb == report_resume) { - pci_cleanup_aer_uncorrect_error_status(dev); - dev->error_state = pci_channel_io_normal; - } - } else { - /* - * If the error is reported by an end point, we think this - * error is related to the upstream link of the end point. - */ - if (state == pci_channel_io_normal) - /* - * the error is non fatal so the bus is ok, just invoke - * the callback for the function that logged the error. - */ - cb(dev, &result_data); - else - pci_walk_bus(dev->bus, cb, &result_data); - } - - return result_data.result; -} - -/** - * default_reset_link - default reset function - * @dev: pointer to pci_dev data structure - * - * Invoked when performing link reset on a Downstream Port or a - * Root Port with no aer driver. - */ -static pci_ers_result_t default_reset_link(struct pci_dev *dev) -{ - pci_reset_bridge_secondary_bus(dev); - pci_printk(KERN_DEBUG, dev, "downstream link has been reset\n"); - return PCI_ERS_RESULT_RECOVERED; -} - -static int find_aer_service_iter(struct device *device, void *data) -{ - struct pcie_port_service_driver *service_driver, **drv; - - drv = (struct pcie_port_service_driver **) data; - - if (device->bus == &pcie_port_bus_type && device->driver) { - service_driver = to_service_driver(device->driver); - if (service_driver->service == PCIE_PORT_SERVICE_AER) { - *drv = service_driver; - return 1; - } - } - - return 0; -} - -static struct pcie_port_service_driver *find_aer_service(struct pci_dev *dev) -{ - struct pcie_port_service_driver *drv = NULL; - - device_for_each_child(&dev->dev, &drv, find_aer_service_iter); - - return drv; -} - -static pci_ers_result_t reset_link(struct pci_dev *dev) -{ - struct pci_dev *udev; - pci_ers_result_t status; - struct pcie_port_service_driver *driver; - - if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) { - /* Reset this port for all subordinates */ - udev = dev; - } else { - /* Reset the upstream component (likely downstream port) */ - udev = dev->bus->self; - } - - /* Use the aer driver of the component firstly */ - driver = find_aer_service(udev); - - if (driver && driver->reset_link) { - status = driver->reset_link(udev); - } else if (udev->has_secondary_link) { - status = default_reset_link(udev); - } else { - pci_printk(KERN_DEBUG, dev, "no link-reset support at upstream device %s\n", - pci_name(udev)); - return PCI_ERS_RESULT_DISCONNECT; - } - - if (status != PCI_ERS_RESULT_RECOVERED) { - pci_printk(KERN_DEBUG, dev, "link reset at upstream device %s failed\n", - pci_name(udev)); - return PCI_ERS_RESULT_DISCONNECT; - } - - return status; -} - -/** - * do_recovery - handle nonfatal/fatal error recovery process - * @dev: pointer to a pci_dev data structure of agent detecting an error - * @severity: error severity type - * - * Invoked when an error is nonfatal/fatal. Once being invoked, broadcast - * error detected message to all downstream drivers within a hierarchy in - * question and return the returned code. - */ -static void do_recovery(struct pci_dev *dev, int severity) -{ - pci_ers_result_t status, result = PCI_ERS_RESULT_RECOVERED; - enum pci_channel_state state; - - if (severity == AER_FATAL) - state = pci_channel_io_frozen; - else - state = pci_channel_io_normal; - - status = broadcast_error_message(dev, - state, - "error_detected", - report_error_detected); - - if (severity == AER_FATAL) { - result = reset_link(dev); - if (result != PCI_ERS_RESULT_RECOVERED) - goto failed; - } - - if (status == PCI_ERS_RESULT_CAN_RECOVER) - status = broadcast_error_message(dev, - state, - "mmio_enabled", - report_mmio_enabled); - - if (status == PCI_ERS_RESULT_NEED_RESET) { - /* - * TODO: Should call platform-specific - * functions to reset slot before calling - * drivers' slot_reset callbacks? - */ - status = broadcast_error_message(dev, - state, - "slot_reset", - report_slot_reset); - } - - if (status != PCI_ERS_RESULT_RECOVERED) - goto failed; - - broadcast_error_message(dev, - state, - "resume", - report_resume); - - pci_info(dev, "AER: Device recovery successful\n"); - return; - -failed: - pci_uevent_ers(dev, PCI_ERS_RESULT_DISCONNECT); - /* TODO: Should kernel panic here? */ - pci_info(dev, "AER: Device recovery failed\n"); -} - /** * handle_error_source - handle logging error into an event log - * @aerdev: pointer to pcie_device data structure of the root port * @dev: pointer to pci_dev data structure of error source device * @info: comprehensive error information * * Invoked when an error being detected by Root Port. */ -static void handle_error_source(struct pcie_device *aerdev, - struct pci_dev *dev, - struct aer_err_info *info) +static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info) { int pos; @@ -562,12 +248,13 @@ static void handle_error_source(struct pcie_device *aerdev, if (pos) pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS, info->status); - } else - do_recovery(dev, info->severity); + } else if (info->severity == AER_NONFATAL) + pcie_do_nonfatal_recovery(dev); + else if (info->severity == AER_FATAL) + pcie_do_fatal_recovery(dev, PCIE_PORT_SERVICE_AER); } #ifdef CONFIG_ACPI_APEI_PCIEAER -static void aer_recover_work_func(struct work_struct *work); #define AER_RECOVER_RING_ORDER 4 #define AER_RECOVER_RING_SIZE (1 << AER_RECOVER_RING_ORDER) @@ -582,6 +269,30 @@ struct aer_recover_entry { static DEFINE_KFIFO(aer_recover_ring, struct aer_recover_entry, AER_RECOVER_RING_SIZE); + +static void aer_recover_work_func(struct work_struct *work) +{ + struct aer_recover_entry entry; + struct pci_dev *pdev; + + while (kfifo_get(&aer_recover_ring, &entry)) { + pdev = pci_get_domain_bus_and_slot(entry.domain, entry.bus, + entry.devfn); + if (!pdev) { + pr_err("AER recover: Can not find pci_dev for %04x:%02x:%02x:%x\n", + entry.domain, entry.bus, + PCI_SLOT(entry.devfn), PCI_FUNC(entry.devfn)); + continue; + } + cper_print_aer(pdev, entry.severity, entry.regs); + if (entry.severity == AER_NONFATAL) + pcie_do_nonfatal_recovery(pdev); + else if (entry.severity == AER_FATAL) + pcie_do_fatal_recovery(pdev, PCIE_PORT_SERVICE_AER); + pci_dev_put(pdev); + } +} + /* * Mutual exclusion for writers of aer_recover_ring, reader side don't * need lock, because there is only one reader and lock is not needed @@ -611,27 +322,6 @@ void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn, spin_unlock_irqrestore(&aer_recover_ring_lock, flags); } EXPORT_SYMBOL_GPL(aer_recover_queue); - -static void aer_recover_work_func(struct work_struct *work) -{ - struct aer_recover_entry entry; - struct pci_dev *pdev; - - while (kfifo_get(&aer_recover_ring, &entry)) { - pdev = pci_get_domain_bus_and_slot(entry.domain, entry.bus, - entry.devfn); - if (!pdev) { - pr_err("AER recover: Can not find pci_dev for %04x:%02x:%02x:%x\n", - entry.domain, entry.bus, - PCI_SLOT(entry.devfn), PCI_FUNC(entry.devfn)); - continue; - } - cper_print_aer(pdev, entry.severity, entry.regs); - if (entry.severity != AER_CORRECTABLE) - do_recovery(pdev, entry.severity); - pci_dev_put(pdev); - } -} #endif /** @@ -695,8 +385,7 @@ static int get_device_error_info(struct pci_dev *dev, struct aer_err_info *info) return 1; } -static inline void aer_process_err_devices(struct pcie_device *p_device, - struct aer_err_info *e_info) +static inline void aer_process_err_devices(struct aer_err_info *e_info) { int i; @@ -707,19 +396,19 @@ static inline void aer_process_err_devices(struct pcie_device *p_device, } for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) { if (get_device_error_info(e_info->dev[i], e_info)) - handle_error_source(p_device, e_info->dev[i], e_info); + handle_error_source(e_info->dev[i], e_info); } } /** * aer_isr_one_error - consume an error detected by root port - * @p_device: pointer to error root port service device + * @rpc: pointer to the root port which holds an error * @e_src: pointer to an error source */ -static void aer_isr_one_error(struct pcie_device *p_device, +static void aer_isr_one_error(struct aer_rpc *rpc, struct aer_err_source *e_src) { - struct aer_rpc *rpc = get_service_data(p_device); + struct pci_dev *pdev = rpc->rpd; struct aer_err_info *e_info = &rpc->e_info; /* @@ -734,11 +423,10 @@ static void aer_isr_one_error(struct pcie_device *p_device, e_info->multi_error_valid = 1; else e_info->multi_error_valid = 0; + aer_print_port_info(pdev, e_info); - aer_print_port_info(p_device->port, e_info); - - if (find_source_device(p_device->port, e_info)) - aer_process_err_devices(p_device, e_info); + if (find_source_device(pdev, e_info)) + aer_process_err_devices(e_info); } if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) { @@ -754,10 +442,10 @@ static void aer_isr_one_error(struct pcie_device *p_device, else e_info->multi_error_valid = 0; - aer_print_port_info(p_device->port, e_info); + aer_print_port_info(pdev, e_info); - if (find_source_device(p_device->port, e_info)) - aer_process_err_devices(p_device, e_info); + if (find_source_device(pdev, e_info)) + aer_process_err_devices(e_info); } } @@ -799,11 +487,10 @@ static int get_e_source(struct aer_rpc *rpc, struct aer_err_source *e_src) void aer_isr(struct work_struct *work) { struct aer_rpc *rpc = container_of(work, struct aer_rpc, dpc_handler); - struct pcie_device *p_device = rpc->rpd; struct aer_err_source uninitialized_var(e_src); mutex_lock(&rpc->rpc_mutex); while (get_e_source(rpc, &e_src)) - aer_isr_one_error(p_device, &e_src); + aer_isr_one_error(rpc, &e_src); mutex_unlock(&rpc->rpc_mutex); } diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c index cfc89dd57831..4985bdf64c2e 100644 --- a/drivers/pci/pcie/aer/aerdrv_errprint.c +++ b/drivers/pci/pcie/aer/aerdrv_errprint.c @@ -163,17 +163,17 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) int id = ((dev->bus->number << 8) | dev->devfn); if (!info->status) { - pci_err(dev, "PCIe Bus Error: severity=%s, type=Unaccessible, id=%04x(Unregistered Agent ID)\n", - aer_error_severity_string[info->severity], id); + pci_err(dev, "PCIe Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n", + aer_error_severity_string[info->severity]); goto out; } layer = AER_GET_LAYER_ERROR(info->severity, info->status); agent = AER_GET_AGENT(info->severity, info->status); - pci_err(dev, "PCIe Bus Error: severity=%s, type=%s, id=%04x(%s)\n", + pci_err(dev, "PCIe Bus Error: severity=%s, type=%s, (%s)\n", aer_error_severity_string[info->severity], - aer_error_layer[layer], id, aer_agent_string[agent]); + aer_error_layer[layer], aer_agent_string[agent]); pci_err(dev, " device [%04x:%04x] error status/mask=%08x/%08x\n", dev->vendor, dev->device, @@ -186,17 +186,21 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) out: if (info->id && info->error_dev_num > 1 && info->id == id) - pci_err(dev, " Error of this Agent(%04x) is reported first\n", id); + pci_err(dev, " Error of this Agent is reported first\n"); trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask), - info->severity); + info->severity, info->tlp_header_valid, &info->tlp); } void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info) { - pci_info(dev, "AER: %s%s error received: id=%04x\n", + u8 bus = info->id >> 8; + u8 devfn = info->id & 0xff; + + pci_info(dev, "AER: %s%s error received: %04x:%02x:%02x.%d\n", info->multi_error_valid ? "Multiple " : "", - aer_error_severity_string[info->severity], info->id); + aer_error_severity_string[info->severity], + pci_domain_nr(dev->bus), bus, PCI_SLOT(devfn), PCI_FUNC(devfn)); } #ifdef CONFIG_ACPI_APEI_PCIEAER @@ -216,28 +220,30 @@ EXPORT_SYMBOL_GPL(cper_severity_to_aer); void cper_print_aer(struct pci_dev *dev, int aer_severity, struct aer_capability_regs *aer) { - int layer, agent, status_strs_size, tlp_header_valid = 0; + int layer, agent, tlp_header_valid = 0; u32 status, mask; - const char **status_strs; + struct aer_err_info info; if (aer_severity == AER_CORRECTABLE) { status = aer->cor_status; mask = aer->cor_mask; - status_strs = aer_correctable_error_string; - status_strs_size = ARRAY_SIZE(aer_correctable_error_string); } else { status = aer->uncor_status; mask = aer->uncor_mask; - status_strs = aer_uncorrectable_error_string; - status_strs_size = ARRAY_SIZE(aer_uncorrectable_error_string); tlp_header_valid = status & AER_LOG_TLP_MASKS; } layer = AER_GET_LAYER_ERROR(aer_severity, status); agent = AER_GET_AGENT(aer_severity, status); + memset(&info, 0, sizeof(info)); + info.severity = aer_severity; + info.status = status; + info.mask = mask; + info.first_error = PCI_ERR_CAP_FEP(aer->cap_control); + pci_err(dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n", status, mask); - cper_print_bits("", status, status_strs, status_strs_size); + __aer_print_error(dev, &info); pci_err(dev, "aer_layer=%s, aer_agent=%s\n", aer_error_layer[layer], aer_agent_string[agent]); @@ -249,6 +255,6 @@ void cper_print_aer(struct pci_dev *dev, int aer_severity, __print_tlp_header(dev, &aer->header_log); trace_aer_event(dev_name(&dev->dev), (status & ~mask), - aer_severity); + aer_severity, tlp_header_valid, &aer->header_log); } #endif diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c index 8c57d607e603..6064041409d2 100644 --- a/drivers/pci/pcie/dpc.c +++ b/drivers/pci/pcie/dpc.c @@ -68,44 +68,35 @@ static int dpc_wait_rp_inactive(struct dpc_dev *dpc) static void dpc_wait_link_inactive(struct dpc_dev *dpc) { - unsigned long timeout = jiffies + HZ; struct pci_dev *pdev = dpc->dev->port; - struct device *dev = &dpc->dev->device; - u16 lnk_status; - pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status); - while (lnk_status & PCI_EXP_LNKSTA_DLLLA && - !time_after(jiffies, timeout)) { - msleep(10); - pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status); - } - if (lnk_status & PCI_EXP_LNKSTA_DLLLA) - dev_warn(dev, "Link state not disabled for DPC event\n"); + pcie_wait_for_link(pdev, false); } -static void dpc_work(struct work_struct *work) +static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev) { - struct dpc_dev *dpc = container_of(work, struct dpc_dev, work); - struct pci_dev *dev, *temp, *pdev = dpc->dev->port; - struct pci_bus *parent = pdev->subordinate; - u16 cap = dpc->cap_pos, ctl; - - pci_lock_rescan_remove(); - list_for_each_entry_safe_reverse(dev, temp, &parent->devices, - bus_list) { - pci_dev_get(dev); - pci_dev_set_disconnected(dev, NULL); - if (pci_has_subordinate(dev)) - pci_walk_bus(dev->subordinate, - pci_dev_set_disconnected, NULL); - pci_stop_and_remove_bus_device(dev); - pci_dev_put(dev); - } - pci_unlock_rescan_remove(); - + struct dpc_dev *dpc; + struct pcie_device *pciedev; + struct device *devdpc; + u16 cap, ctl; + + /* + * DPC disables the Link automatically in hardware, so it has + * already been reset by the time we get here. + */ + devdpc = pcie_port_find_device(pdev, PCIE_PORT_SERVICE_DPC); + pciedev = to_pcie_device(devdpc); + dpc = get_service_data(pciedev); + cap = dpc->cap_pos; + + /* + * Wait until the Link is inactive, then clear DPC Trigger Status + * to allow the Port to leave DPC. + */ dpc_wait_link_inactive(dpc); + if (dpc->rp_extensions && dpc_wait_rp_inactive(dpc)) - return; + return PCI_ERS_RESULT_DISCONNECT; if (dpc->rp_extensions && dpc->rp_pio_status) { pci_write_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_STATUS, dpc->rp_pio_status); @@ -118,6 +109,17 @@ static void dpc_work(struct work_struct *work) pci_read_config_word(pdev, cap + PCI_EXP_DPC_CTL, &ctl); pci_write_config_word(pdev, cap + PCI_EXP_DPC_CTL, ctl | PCI_EXP_DPC_CTL_INT_EN); + + return PCI_ERS_RESULT_RECOVERED; +} + +static void dpc_work(struct work_struct *work) +{ + struct dpc_dev *dpc = container_of(work, struct dpc_dev, work); + struct pci_dev *pdev = dpc->dev->port; + + /* We configure DPC so it only triggers on ERR_FATAL */ + pcie_do_fatal_recovery(pdev, PCIE_PORT_SERVICE_DPC); } static void dpc_process_rp_pio_error(struct dpc_dev *dpc) @@ -270,7 +272,7 @@ static int dpc_probe(struct pcie_device *dev) } } - ctl = (ctl & 0xfff4) | PCI_EXP_DPC_CTL_EN_NONFATAL | PCI_EXP_DPC_CTL_INT_EN; + ctl = (ctl & 0xfff4) | PCI_EXP_DPC_CTL_EN_FATAL | PCI_EXP_DPC_CTL_INT_EN; pci_write_config_word(pdev, dpc->cap_pos + PCI_EXP_DPC_CTL, ctl); dev_info(device, "DPC error containment capabilities: Int Msg #%d, RPExt%c PoisonedTLP%c SwTrigger%c RP PIO Log %d, DL_ActiveErr%c\n", @@ -288,7 +290,7 @@ static void dpc_remove(struct pcie_device *dev) u16 ctl; pci_read_config_word(pdev, dpc->cap_pos + PCI_EXP_DPC_CTL, &ctl); - ctl &= ~(PCI_EXP_DPC_CTL_EN_NONFATAL | PCI_EXP_DPC_CTL_INT_EN); + ctl &= ~(PCI_EXP_DPC_CTL_EN_FATAL | PCI_EXP_DPC_CTL_INT_EN); pci_write_config_word(pdev, dpc->cap_pos + PCI_EXP_DPC_CTL, ctl); } @@ -298,6 +300,7 @@ static struct pcie_port_service_driver dpcdriver = { .service = PCIE_PORT_SERVICE_DPC, .probe = dpc_probe, .remove = dpc_remove, + .reset_link = dpc_reset_link, }; static int __init dpc_service_init(void) diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c new file mode 100644 index 000000000000..f7ce0cb0b0b7 --- /dev/null +++ b/drivers/pci/pcie/err.c @@ -0,0 +1,388 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This file implements the error recovery as a core part of PCIe error + * reporting. When a PCIe error is delivered, an error message will be + * collected and printed to console, then, an error recovery procedure + * will be executed by following the PCI error recovery rules. + * + * Copyright (C) 2006 Intel Corp. + * Tom Long Nguyen (tom.l.nguyen@intel.com) + * Zhang Yanmin (yanmin.zhang@intel.com) + */ + +#include <linux/pci.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/aer.h> +#include "portdrv.h" +#include "../pci.h" + +struct aer_broadcast_data { + enum pci_channel_state state; + enum pci_ers_result result; +}; + +static pci_ers_result_t merge_result(enum pci_ers_result orig, + enum pci_ers_result new) +{ + if (new == PCI_ERS_RESULT_NO_AER_DRIVER) + return PCI_ERS_RESULT_NO_AER_DRIVER; + + if (new == PCI_ERS_RESULT_NONE) + return orig; + + switch (orig) { + case PCI_ERS_RESULT_CAN_RECOVER: + case PCI_ERS_RESULT_RECOVERED: + orig = new; + break; + case PCI_ERS_RESULT_DISCONNECT: + if (new == PCI_ERS_RESULT_NEED_RESET) + orig = PCI_ERS_RESULT_NEED_RESET; + break; + default: + break; + } + + return orig; +} + +static int report_error_detected(struct pci_dev *dev, void *data) +{ + pci_ers_result_t vote; + const struct pci_error_handlers *err_handler; + struct aer_broadcast_data *result_data; + + result_data = (struct aer_broadcast_data *) data; + + device_lock(&dev->dev); + dev->error_state = result_data->state; + + if (!dev->driver || + !dev->driver->err_handler || + !dev->driver->err_handler->error_detected) { + if (result_data->state == pci_channel_io_frozen && + dev->hdr_type != PCI_HEADER_TYPE_BRIDGE) { + /* + * In case of fatal recovery, if one of down- + * stream device has no driver. We might be + * unable to recover because a later insmod + * of a driver for this device is unaware of + * its hw state. + */ + pci_printk(KERN_DEBUG, dev, "device has %s\n", + dev->driver ? + "no AER-aware driver" : "no driver"); + } + + /* + * If there's any device in the subtree that does not + * have an error_detected callback, returning + * PCI_ERS_RESULT_NO_AER_DRIVER prevents calling of + * the subsequent mmio_enabled/slot_reset/resume + * callbacks of "any" device in the subtree. All the + * devices in the subtree are left in the error state + * without recovery. + */ + + if (dev->hdr_type != PCI_HEADER_TYPE_BRIDGE) + vote = PCI_ERS_RESULT_NO_AER_DRIVER; + else + vote = PCI_ERS_RESULT_NONE; + } else { + err_handler = dev->driver->err_handler; + vote = err_handler->error_detected(dev, result_data->state); + pci_uevent_ers(dev, PCI_ERS_RESULT_NONE); + } + + result_data->result = merge_result(result_data->result, vote); + device_unlock(&dev->dev); + return 0; +} + +static int report_mmio_enabled(struct pci_dev *dev, void *data) +{ + pci_ers_result_t vote; + const struct pci_error_handlers *err_handler; + struct aer_broadcast_data *result_data; + + result_data = (struct aer_broadcast_data *) data; + + device_lock(&dev->dev); + if (!dev->driver || + !dev->driver->err_handler || + !dev->driver->err_handler->mmio_enabled) + goto out; + + err_handler = dev->driver->err_handler; + vote = err_handler->mmio_enabled(dev); + result_data->result = merge_result(result_data->result, vote); +out: + device_unlock(&dev->dev); + return 0; +} + +static int report_slot_reset(struct pci_dev *dev, void *data) +{ + pci_ers_result_t vote; + const struct pci_error_handlers *err_handler; + struct aer_broadcast_data *result_data; + + result_data = (struct aer_broadcast_data *) data; + + device_lock(&dev->dev); + if (!dev->driver || + !dev->driver->err_handler || + !dev->driver->err_handler->slot_reset) + goto out; + + err_handler = dev->driver->err_handler; + vote = err_handler->slot_reset(dev); + result_data->result = merge_result(result_data->result, vote); +out: + device_unlock(&dev->dev); + return 0; +} + +static int report_resume(struct pci_dev *dev, void *data) +{ + const struct pci_error_handlers *err_handler; + + device_lock(&dev->dev); + dev->error_state = pci_channel_io_normal; + + if (!dev->driver || + !dev->driver->err_handler || + !dev->driver->err_handler->resume) + goto out; + + err_handler = dev->driver->err_handler; + err_handler->resume(dev); + pci_uevent_ers(dev, PCI_ERS_RESULT_RECOVERED); +out: + device_unlock(&dev->dev); + return 0; +} + +/** + * default_reset_link - default reset function + * @dev: pointer to pci_dev data structure + * + * Invoked when performing link reset on a Downstream Port or a + * Root Port with no aer driver. + */ +static pci_ers_result_t default_reset_link(struct pci_dev *dev) +{ + pci_reset_bridge_secondary_bus(dev); + pci_printk(KERN_DEBUG, dev, "downstream link has been reset\n"); + return PCI_ERS_RESULT_RECOVERED; +} + +static pci_ers_result_t reset_link(struct pci_dev *dev, u32 service) +{ + struct pci_dev *udev; + pci_ers_result_t status; + struct pcie_port_service_driver *driver = NULL; + + if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) { + /* Reset this port for all subordinates */ + udev = dev; + } else { + /* Reset the upstream component (likely downstream port) */ + udev = dev->bus->self; + } + + /* Use the aer driver of the component firstly */ + driver = pcie_port_find_service(udev, service); + + if (driver && driver->reset_link) { + status = driver->reset_link(udev); + } else if (udev->has_secondary_link) { + status = default_reset_link(udev); + } else { + pci_printk(KERN_DEBUG, dev, "no link-reset support at upstream device %s\n", + pci_name(udev)); + return PCI_ERS_RESULT_DISCONNECT; + } + + if (status != PCI_ERS_RESULT_RECOVERED) { + pci_printk(KERN_DEBUG, dev, "link reset at upstream device %s failed\n", + pci_name(udev)); + return PCI_ERS_RESULT_DISCONNECT; + } + + return status; +} + +/** + * broadcast_error_message - handle message broadcast to downstream drivers + * @dev: pointer to from where in a hierarchy message is broadcasted down + * @state: error state + * @error_mesg: message to print + * @cb: callback to be broadcasted + * + * Invoked during error recovery process. Once being invoked, the content + * of error severity will be broadcasted to all downstream drivers in a + * hierarchy in question. + */ +static pci_ers_result_t broadcast_error_message(struct pci_dev *dev, + enum pci_channel_state state, + char *error_mesg, + int (*cb)(struct pci_dev *, void *)) +{ + struct aer_broadcast_data result_data; + + pci_printk(KERN_DEBUG, dev, "broadcast %s message\n", error_mesg); + result_data.state = state; + if (cb == report_error_detected) + result_data.result = PCI_ERS_RESULT_CAN_RECOVER; + else + result_data.result = PCI_ERS_RESULT_RECOVERED; + + if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) { + /* + * If the error is reported by a bridge, we think this error + * is related to the downstream link of the bridge, so we + * do error recovery on all subordinates of the bridge instead + * of the bridge and clear the error status of the bridge. + */ + if (cb == report_error_detected) + dev->error_state = state; + pci_walk_bus(dev->subordinate, cb, &result_data); + if (cb == report_resume) { + pci_cleanup_aer_uncorrect_error_status(dev); + dev->error_state = pci_channel_io_normal; + } + } else { + /* + * If the error is reported by an end point, we think this + * error is related to the upstream link of the end point. + */ + if (state == pci_channel_io_normal) + /* + * the error is non fatal so the bus is ok, just invoke + * the callback for the function that logged the error. + */ + cb(dev, &result_data); + else + pci_walk_bus(dev->bus, cb, &result_data); + } + + return result_data.result; +} + +/** + * pcie_do_fatal_recovery - handle fatal error recovery process + * @dev: pointer to a pci_dev data structure of agent detecting an error + * + * Invoked when an error is fatal. Once being invoked, removes the devices + * beneath this AER agent, followed by reset link e.g. secondary bus reset + * followed by re-enumeration of devices. + */ +void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service) +{ + struct pci_dev *udev; + struct pci_bus *parent; + struct pci_dev *pdev, *temp; + pci_ers_result_t result; + + if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) + udev = dev; + else + udev = dev->bus->self; + + parent = udev->subordinate; + pci_lock_rescan_remove(); + list_for_each_entry_safe_reverse(pdev, temp, &parent->devices, + bus_list) { + pci_dev_get(pdev); + pci_dev_set_disconnected(pdev, NULL); + if (pci_has_subordinate(pdev)) + pci_walk_bus(pdev->subordinate, + pci_dev_set_disconnected, NULL); + pci_stop_and_remove_bus_device(pdev); + pci_dev_put(pdev); + } + + result = reset_link(udev, service); + + if ((service == PCIE_PORT_SERVICE_AER) && + (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)) { + /* + * If the error is reported by a bridge, we think this error + * is related to the downstream link of the bridge, so we + * do error recovery on all subordinates of the bridge instead + * of the bridge and clear the error status of the bridge. + */ + pci_cleanup_aer_uncorrect_error_status(dev); + } + + if (result == PCI_ERS_RESULT_RECOVERED) { + if (pcie_wait_for_link(udev, true)) + pci_rescan_bus(udev->bus); + pci_info(dev, "Device recovery from fatal error successful\n"); + } else { + pci_uevent_ers(dev, PCI_ERS_RESULT_DISCONNECT); + pci_info(dev, "Device recovery from fatal error failed\n"); + } + + pci_unlock_rescan_remove(); +} + +/** + * pcie_do_nonfatal_recovery - handle nonfatal error recovery process + * @dev: pointer to a pci_dev data structure of agent detecting an error + * + * Invoked when an error is nonfatal/fatal. Once being invoked, broadcast + * error detected message to all downstream drivers within a hierarchy in + * question and return the returned code. + */ +void pcie_do_nonfatal_recovery(struct pci_dev *dev) +{ + pci_ers_result_t status; + enum pci_channel_state state; + + state = pci_channel_io_normal; + + status = broadcast_error_message(dev, + state, + "error_detected", + report_error_detected); + + if (status == PCI_ERS_RESULT_CAN_RECOVER) + status = broadcast_error_message(dev, + state, + "mmio_enabled", + report_mmio_enabled); + + if (status == PCI_ERS_RESULT_NEED_RESET) { + /* + * TODO: Should call platform-specific + * functions to reset slot before calling + * drivers' slot_reset callbacks? + */ + status = broadcast_error_message(dev, + state, + "slot_reset", + report_slot_reset); + } + + if (status != PCI_ERS_RESULT_RECOVERED) + goto failed; + + broadcast_error_message(dev, + state, + "resume", + report_resume); + + pci_info(dev, "AER: Device recovery successful\n"); + return; + +failed: + pci_uevent_ers(dev, PCI_ERS_RESULT_DISCONNECT); + + /* TODO: Should kernel panic here? */ + pci_info(dev, "AER: Device recovery failed\n"); +} diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h index d0c6783dbfe3..d82401acb831 100644 --- a/drivers/pci/pcie/portdrv.h +++ b/drivers/pci/pcie/portdrv.h @@ -112,4 +112,7 @@ static inline bool pcie_pme_no_msi(void) { return false; } static inline void pcie_pme_interrupt_enable(struct pci_dev *dev, bool en) {} #endif /* !CONFIG_PCIE_PME */ +struct pcie_port_service_driver *pcie_port_find_service(struct pci_dev *dev, + u32 service); +struct device *pcie_port_find_device(struct pci_dev *dev, u32 service); #endif /* _PORTDRV_H_ */ diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c index c9c0663db282..a9c581df7a62 100644 --- a/drivers/pci/pcie/portdrv_core.c +++ b/drivers/pci/pcie/portdrv_core.c @@ -19,6 +19,12 @@ #include "../pci.h" #include "portdrv.h" +struct portdrv_service_data { + struct pcie_port_service_driver *drv; + struct device *dev; + u32 service; +}; + /** * release_pcie_device - free PCI Express port service device structure * @dev: Port service device to release @@ -398,6 +404,69 @@ static int remove_iter(struct device *dev, void *data) return 0; } +static int find_service_iter(struct device *device, void *data) +{ + struct pcie_port_service_driver *service_driver; + struct portdrv_service_data *pdrvs; + u32 service; + + pdrvs = (struct portdrv_service_data *) data; + service = pdrvs->service; + + if (device->bus == &pcie_port_bus_type && device->driver) { + service_driver = to_service_driver(device->driver); + if (service_driver->service == service) { + pdrvs->drv = service_driver; + pdrvs->dev = device; + return 1; + } + } + + return 0; +} + +/** + * pcie_port_find_service - find the service driver + * @dev: PCI Express port the service is associated with + * @service: Service to find + * + * Find PCI Express port service driver associated with given service + */ +struct pcie_port_service_driver *pcie_port_find_service(struct pci_dev *dev, + u32 service) +{ + struct pcie_port_service_driver *drv; + struct portdrv_service_data pdrvs; + + pdrvs.drv = NULL; + pdrvs.service = service; + device_for_each_child(&dev->dev, &pdrvs, find_service_iter); + + drv = pdrvs.drv; + return drv; +} + +/** + * pcie_port_find_device - find the struct device + * @dev: PCI Express port the service is associated with + * @service: For the service to find + * + * Find the struct device associated with given service on a pci_dev + */ +struct device *pcie_port_find_device(struct pci_dev *dev, + u32 service) +{ + struct device *device; + struct portdrv_service_data pdrvs; + + pdrvs.dev = NULL; + pdrvs.service = service; + device_for_each_child(&dev->dev, &pdrvs, find_service_iter); + + device = pdrvs.dev; + return device; +} + /** * pcie_port_device_remove - unregister PCI Express port service devices * @dev: PCI Express port the service devices to unregister are associated with diff --git a/include/linux/aer.h b/include/linux/aer.h index 8f87bbeceef4..514bffa11dbb 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -14,6 +14,7 @@ #define AER_NONFATAL 0 #define AER_FATAL 1 #define AER_CORRECTABLE 2 +#define DPC_FATAL 3 struct pci_dev; diff --git a/include/linux/pci.h b/include/linux/pci.h index 73178a2fcee0..4f721f757363 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2284,7 +2284,7 @@ static inline bool pci_is_thunderbolt_attached(struct pci_dev *pdev) return false; } -#if defined(CONFIG_PCIEAER) || defined(CONFIG_EEH) +#if defined(CONFIG_PCIEPORTBUS) || defined(CONFIG_EEH) void pci_uevent_ers(struct pci_dev *pdev, enum pci_ers_result err_type); #endif diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index 9c689868eb4d..a0794632fd01 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -298,30 +298,44 @@ TRACE_EVENT(non_standard_event, TRACE_EVENT(aer_event, TP_PROTO(const char *dev_name, const u32 status, - const u8 severity), + const u8 severity, + const u8 tlp_header_valid, + struct aer_header_log_regs *tlp), - TP_ARGS(dev_name, status, severity), + TP_ARGS(dev_name, status, severity, tlp_header_valid, tlp), TP_STRUCT__entry( __string( dev_name, dev_name ) __field( u32, status ) __field( u8, severity ) + __field( u8, tlp_header_valid) + __array( u32, tlp_header, 4 ) ), TP_fast_assign( __assign_str(dev_name, dev_name); __entry->status = status; __entry->severity = severity; + __entry->tlp_header_valid = tlp_header_valid; + if (tlp_header_valid) { + __entry->tlp_header[0] = tlp->dw0; + __entry->tlp_header[1] = tlp->dw1; + __entry->tlp_header[2] = tlp->dw2; + __entry->tlp_header[3] = tlp->dw3; + } ), - TP_printk("%s PCIe Bus Error: severity=%s, %s\n", + TP_printk("%s PCIe Bus Error: severity=%s, %s, TLP Header=%s\n", __get_str(dev_name), __entry->severity == AER_CORRECTABLE ? "Corrected" : __entry->severity == AER_FATAL ? "Fatal" : "Uncorrected, non-fatal", __entry->severity == AER_CORRECTABLE ? __print_flags(__entry->status, "|", aer_correctable_errors) : - __print_flags(__entry->status, "|", aer_uncorrectable_errors)) + __print_flags(__entry->status, "|", aer_uncorrectable_errors), + __entry->tlp_header_valid ? + __print_array(__entry->tlp_header, 4, 4) : + "Not available") ); /* diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 103ba797a8f3..5182e0dda083 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -981,6 +981,7 @@ #define PCI_EXP_DPC_CAP_DL_ACTIVE 0x1000 /* ERR_COR signal on DL_Active supported */ #define PCI_EXP_DPC_CTL 6 /* DPC control */ +#define PCI_EXP_DPC_CTL_EN_FATAL 0x0001 /* Enable trigger on ERR_FATAL message */ #define PCI_EXP_DPC_CTL_EN_NONFATAL 0x0002 /* Enable trigger on ERR_NONFATAL message */ #define PCI_EXP_DPC_CTL_INT_EN 0x0008 /* DPC Interrupt Enable */ |