diff options
Diffstat (limited to 'drivers/pci/pcie/aer')
| -rw-r--r-- | drivers/pci/pcie/aer/aer_inject.c | 56 | ||||
| -rw-r--r-- | drivers/pci/pcie/aer/aerdrv.c | 194 | ||||
| -rw-r--r-- | drivers/pci/pcie/aer/aerdrv.h | 49 | ||||
| -rw-r--r-- | drivers/pci/pcie/aer/aerdrv_acpi.c | 144 | ||||
| -rw-r--r-- | drivers/pci/pcie/aer/aerdrv_core.c | 678 | ||||
| -rw-r--r-- | drivers/pci/pcie/aer/aerdrv_errprint.c | 229 |
6 files changed, 756 insertions, 594 deletions
diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c index 223052b7356..182224acedb 100644 --- a/drivers/pci/pcie/aer/aer_inject.c +++ b/drivers/pci/pcie/aer/aer_inject.c @@ -21,11 +21,16 @@ #include <linux/init.h> #include <linux/miscdevice.h> #include <linux/pci.h> +#include <linux/slab.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <linux/stddef.h> #include "aerdrv.h" +/* Override the existing corrected and uncorrected error masks */ +static bool aer_mask_override; +module_param(aer_mask_override, bool, 0); + struct aer_error_inj { u8 bus; u8 dev; @@ -167,7 +172,7 @@ static u32 *find_pci_config_dword(struct aer_error *err, int where, target = &err->root_status; rw1cs = 1; break; - case PCI_ERR_ROOT_COR_SRC: + case PCI_ERR_ROOT_ERR_SRC: target = &err->source_id; break; } @@ -207,8 +212,8 @@ out: return ops->read(bus, devfn, where, size, val); } -int pci_write_aer(struct pci_bus *bus, unsigned int devfn, int where, int size, - u32 val) +static int pci_write_aer(struct pci_bus *bus, unsigned int devfn, int where, + int size, u32 val) { u32 *sim; struct aer_error *err; @@ -283,7 +288,7 @@ static struct pci_dev *pcie_find_root_port(struct pci_dev *dev) while (1) { if (!pci_is_pcie(dev)) break; - if (dev->pcie_type == PCI_EXP_TYPE_ROOT_PORT) + if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) return dev; if (!dev->bus->self) break; @@ -321,7 +326,7 @@ static int aer_inject(struct aer_error_inj *einj) unsigned long flags; unsigned int devfn = PCI_DEVFN(einj->dev, einj->fn); int pos_cap_err, rp_pos_cap_err; - u32 sever, cor_mask, uncor_mask; + u32 sever, cor_mask, uncor_mask, cor_mask_orig = 0, uncor_mask_orig = 0; int ret = 0; dev = pci_get_domain_bus_and_slot((int)einj->domain, einj->bus, devfn); @@ -329,13 +334,13 @@ static int aer_inject(struct aer_error_inj *einj) return -ENODEV; rpdev = pcie_find_root_port(dev); if (!rpdev) { - ret = -ENOTTY; + ret = -ENODEV; goto out_put; } pos_cap_err = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); if (!pos_cap_err) { - ret = -ENOTTY; + ret = -EPERM; goto out_put; } pci_read_config_dword(dev, pos_cap_err + PCI_ERR_UNCOR_SEVER, &sever); @@ -345,7 +350,7 @@ static int aer_inject(struct aer_error_inj *einj) rp_pos_cap_err = pci_find_ext_capability(rpdev, PCI_EXT_CAP_ID_ERR); if (!rp_pos_cap_err) { - ret = -ENOTTY; + ret = -EPERM; goto out_put; } @@ -360,6 +365,18 @@ static int aer_inject(struct aer_error_inj *einj) goto out_put; } + if (aer_mask_override) { + cor_mask_orig = cor_mask; + cor_mask &= !(einj->cor_status); + pci_write_config_dword(dev, pos_cap_err + PCI_ERR_COR_MASK, + cor_mask); + + uncor_mask_orig = uncor_mask; + uncor_mask &= !(einj->uncor_status); + pci_write_config_dword(dev, pos_cap_err + PCI_ERR_UNCOR_MASK, + uncor_mask); + } + spin_lock_irqsave(&inject_lock, flags); err = __find_aer_error_by_dev(dev); @@ -377,17 +394,17 @@ static int aer_inject(struct aer_error_inj *einj) err->header_log2 = einj->header_log2; err->header_log3 = einj->header_log3; - if (einj->cor_status && !(einj->cor_status & ~cor_mask)) { + if (!aer_mask_override && einj->cor_status && + !(einj->cor_status & ~cor_mask)) { ret = -EINVAL; - printk(KERN_WARNING "The correctable error(s) is masked " - "by device\n"); + printk(KERN_WARNING "The correctable error(s) is masked by device\n"); spin_unlock_irqrestore(&inject_lock, flags); goto out_put; } - if (einj->uncor_status && !(einj->uncor_status & ~uncor_mask)) { + if (!aer_mask_override && einj->uncor_status && + !(einj->uncor_status & ~uncor_mask)) { ret = -EINVAL; - printk(KERN_WARNING "The uncorrectable error(s) is masked " - "by device\n"); + printk(KERN_WARNING "The uncorrectable error(s) is masked by device\n"); spin_unlock_irqrestore(&inject_lock, flags); goto out_put; } @@ -424,6 +441,13 @@ static int aer_inject(struct aer_error_inj *einj) } spin_unlock_irqrestore(&inject_lock, flags); + if (aer_mask_override) { + pci_write_config_dword(dev, pos_cap_err + PCI_ERR_COR_MASK, + cor_mask_orig); + pci_write_config_dword(dev, pos_cap_err + PCI_ERR_UNCOR_MASK, + uncor_mask_orig); + } + ret = pci_bus_set_aer_ops(dev->bus); if (ret) goto out_put; @@ -438,8 +462,7 @@ static int aer_inject(struct aer_error_inj *einj) goto out_put; } aer_irq(-1, edev); - } - else + } else ret = -EINVAL; out_put: kfree(err_alloc); @@ -471,6 +494,7 @@ static ssize_t aer_inject_write(struct file *filp, const char __user *ubuf, static const struct file_operations aer_inject_fops = { .write = aer_inject_write, .owner = THIS_MODULE, + .llseek = noop_llseek, }; static struct miscdevice aer_inject_device = { diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c index 21f215f4daa..0bf82a20a0f 100644 --- a/drivers/pci/pcie/aer/aerdrv.c +++ b/drivers/pci/pcie/aer/aerdrv.c @@ -17,6 +17,7 @@ #include <linux/module.h> #include <linux/pci.h> +#include <linux/pci-acpi.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/errno.h> @@ -25,6 +26,7 @@ #include <linux/interrupt.h> #include <linux/delay.h> #include <linux/pcieport_if.h> +#include <linux/slab.h> #include "aerdrv.h" #include "../../pci.h" @@ -39,14 +41,14 @@ MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); -static int __devinit aer_probe(struct pcie_device *dev); +static int aer_probe(struct pcie_device *dev); static void aer_remove(struct pcie_device *dev); static pci_ers_result_t aer_error_detected(struct pci_dev *dev, enum pci_channel_state error); static void aer_error_resume(struct pci_dev *dev); static pci_ers_result_t aer_root_reset(struct pci_dev *dev); -static struct pci_error_handlers aer_error_handlers = { +static const struct pci_error_handlers aer_error_handlers = { .error_detected = aer_error_detected, .resume = aer_error_resume, }; @@ -71,13 +73,124 @@ void pci_no_aer(void) pcie_aer_disable = 1; /* has priority over 'forceload' */ } +bool pci_aer_available(void) +{ + return !pcie_aer_disable && pci_msi_enabled(); +} + +static int set_device_error_reporting(struct pci_dev *dev, void *data) +{ + bool enable = *((bool *)data); + int type = pci_pcie_type(dev); + + if ((type == PCI_EXP_TYPE_ROOT_PORT) || + (type == PCI_EXP_TYPE_UPSTREAM) || + (type == PCI_EXP_TYPE_DOWNSTREAM)) { + if (enable) + pci_enable_pcie_error_reporting(dev); + else + pci_disable_pcie_error_reporting(dev); + } + + if (enable) + pcie_set_ecrc_checking(dev); + + return 0; +} + +/** + * set_downstream_devices_error_reporting - enable/disable the error reporting bits on the root port and its downstream ports. + * @dev: pointer to root port's pci_dev data structure + * @enable: true = enable error reporting, false = disable error reporting. + */ +static void set_downstream_devices_error_reporting(struct pci_dev *dev, + bool enable) +{ + set_device_error_reporting(dev, &enable); + + if (!dev->subordinate) + return; + pci_walk_bus(dev->subordinate, set_device_error_reporting, &enable); +} + +/** + * aer_enable_rootport - enable Root Port's interrupts when receiving messages + * @rpc: pointer to a Root Port data structure + * + * Invoked when PCIe bus loads AER service driver. + */ +static void aer_enable_rootport(struct aer_rpc *rpc) +{ + struct pci_dev *pdev = rpc->rpd->port; + int aer_pos; + u16 reg16; + u32 reg32; + + /* Clear PCIe Capability's Device Status */ + pcie_capability_read_word(pdev, PCI_EXP_DEVSTA, ®16); + pcie_capability_write_word(pdev, PCI_EXP_DEVSTA, reg16); + + /* Disable system error generation in response to error messages */ + pcie_capability_clear_word(pdev, PCI_EXP_RTCTL, + SYSTEM_ERROR_INTR_ON_MESG_MASK); + + aer_pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR); + /* Clear error status */ + pci_read_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, ®32); + pci_write_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, reg32); + pci_read_config_dword(pdev, aer_pos + PCI_ERR_COR_STATUS, ®32); + pci_write_config_dword(pdev, aer_pos + PCI_ERR_COR_STATUS, reg32); + pci_read_config_dword(pdev, aer_pos + PCI_ERR_UNCOR_STATUS, ®32); + pci_write_config_dword(pdev, aer_pos + PCI_ERR_UNCOR_STATUS, reg32); + + /* + * Enable error reporting for the root port device and downstream port + * devices. + */ + set_downstream_devices_error_reporting(pdev, true); + + /* Enable Root Port's interrupt in response to error messages */ + pci_read_config_dword(pdev, aer_pos + PCI_ERR_ROOT_COMMAND, ®32); + reg32 |= ROOT_PORT_INTR_ON_MESG_MASK; + pci_write_config_dword(pdev, aer_pos + PCI_ERR_ROOT_COMMAND, reg32); +} + +/** + * aer_disable_rootport - disable Root Port's interrupts when receiving messages + * @rpc: pointer to a Root Port data structure + * + * Invoked when PCIe bus unloads AER service driver. + */ +static void aer_disable_rootport(struct aer_rpc *rpc) +{ + struct pci_dev *pdev = rpc->rpd->port; + u32 reg32; + int pos; + + /* + * Disable error reporting for the root port device and downstream port + * devices. + */ + set_downstream_devices_error_reporting(pdev, false); + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR); + /* Disable Root's interrupt in response to error messages */ + pci_read_config_dword(pdev, pos + PCI_ERR_ROOT_COMMAND, ®32); + reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK; + pci_write_config_dword(pdev, pos + PCI_ERR_ROOT_COMMAND, reg32); + + /* Clear Root's error status reg */ + pci_read_config_dword(pdev, pos + PCI_ERR_ROOT_STATUS, ®32); + pci_write_config_dword(pdev, pos + PCI_ERR_ROOT_STATUS, reg32); +} + /** * aer_irq - Root Port's ISR * @irq: IRQ assigned to Root Port * @context: pointer to Root Port data structure * * Invoked when Root Port detects AER messages. - **/ + */ irqreturn_t aer_irq(int irq, void *context) { unsigned int status, id; @@ -96,13 +209,13 @@ irqreturn_t aer_irq(int irq, void *context) /* Read error status */ pci_read_config_dword(pdev->port, pos + PCI_ERR_ROOT_STATUS, &status); - if (!(status & ROOT_ERR_STATUS_MASKS)) { + if (!(status & (PCI_ERR_ROOT_UNCOR_RCV|PCI_ERR_ROOT_COR_RCV))) { spin_unlock_irqrestore(&rpc->e_lock, flags); return IRQ_NONE; } /* Read error source and clear error status */ - pci_read_config_dword(pdev->port, pos + PCI_ERR_ROOT_COR_SRC, &id); + pci_read_config_dword(pdev->port, pos + PCI_ERR_ROOT_ERR_SRC, &id); pci_write_config_dword(pdev->port, pos + PCI_ERR_ROOT_STATUS, status); /* Store error source for later DPC handler */ @@ -134,7 +247,7 @@ EXPORT_SYMBOL_GPL(aer_irq); * @dev: pointer to the pcie_dev data structure * * Invoked when Root Port's AER service is loaded. - **/ + */ static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev) { struct aer_rpc *rpc; @@ -143,15 +256,11 @@ static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev) if (!rpc) return NULL; - /* - * Initialize Root lock access, e_lock, to Root Error Status Reg, - * Root Error ID Reg, and Root error producer/consumer index. - */ + /* Initialize Root lock access, e_lock, to Root Error Status Reg */ spin_lock_init(&rpc->e_lock); rpc->rpd = dev; INIT_WORK(&rpc->dpc_handler, aer_isr); - rpc->prod_idx = rpc->cons_idx = 0; mutex_init(&rpc->rpc_mutex); init_waitqueue_head(&rpc->wait_release); @@ -166,7 +275,7 @@ static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev) * @dev: pointer to the pcie_dev data structure * * Invoked when PCI Express bus unloads or AER probe fails. - **/ + */ static void aer_remove(struct pcie_device *dev) { struct aer_rpc *rpc = get_service_data(dev); @@ -178,7 +287,8 @@ static void aer_remove(struct pcie_device *dev) wait_event(rpc->wait_release, rpc->prod_idx == rpc->cons_idx); - aer_delete_rootport(rpc); + aer_disable_rootport(rpc); + kfree(rpc); set_service_data(dev, NULL); } } @@ -189,8 +299,8 @@ static void aer_remove(struct pcie_device *dev) * @id: pointer to the service id data structure * * Invoked when PCI Express bus loads AER service driver. - **/ -static int __devinit aer_probe(struct pcie_device *dev) + */ +static int aer_probe(struct pcie_device *dev) { int status; struct aer_rpc *rpc; @@ -229,41 +339,30 @@ static int __devinit aer_probe(struct pcie_device *dev) * @dev: pointer to Root Port's pci_dev data structure * * Invoked by Port Bus driver when performing link reset at Root Port. - **/ + */ static pci_ers_result_t aer_root_reset(struct pci_dev *dev) { - u16 p2p_ctrl; - u32 status; + u32 reg32; int pos; pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); /* Disable Root's interrupt in response to error messages */ - pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, 0); - - /* Assert Secondary Bus Reset */ - pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &p2p_ctrl); - p2p_ctrl |= PCI_CB_BRIDGE_CTL_CB_RESET; - pci_write_config_word(dev, PCI_BRIDGE_CONTROL, p2p_ctrl); + pci_read_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, ®32); + reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK; + pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32); - /* De-assert Secondary Bus Reset */ - p2p_ctrl &= ~PCI_CB_BRIDGE_CTL_CB_RESET; - pci_write_config_word(dev, PCI_BRIDGE_CONTROL, p2p_ctrl); - - /* - * System software must wait for at least 100ms from the end - * of a reset of one or more device before it is permitted - * to issue Configuration Requests to those devices. - */ - msleep(200); + pci_reset_bridge_secondary_bus(dev); dev_printk(KERN_DEBUG, &dev->dev, "Root Port link has been reset\n"); + /* Clear Root Error Status */ + pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, ®32); + pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, reg32); + /* Enable Root Port's interrupt in response to error messages */ - pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &status); - pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, status); - pci_write_config_dword(dev, - pos + PCI_ERR_ROOT_COMMAND, - ROOT_PORT_INTR_ON_MESG_MASK); + pci_read_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, ®32); + reg32 |= ROOT_PORT_INTR_ON_MESG_MASK; + pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32); return PCI_ERS_RESULT_RECOVERED; } @@ -274,7 +373,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev) * @error: error severity being notified by port bus * * Invoked by Port Bus driver during error recovery. - **/ + */ static pci_ers_result_t aer_error_detected(struct pci_dev *dev, enum pci_channel_state error) { @@ -287,7 +386,7 @@ static pci_ers_result_t aer_error_detected(struct pci_dev *dev, * @dev: pointer to Root Port's pci_dev data structure * * Invoked by Port Bus driver during nonfatal recovery. - **/ + */ static void aer_error_resume(struct pci_dev *dev) { int pos; @@ -295,9 +394,8 @@ static void aer_error_resume(struct pci_dev *dev) u16 reg16; /* Clean up Root device status */ - pos = pci_pcie_cap(dev); - pci_read_config_word(dev, pos + PCI_EXP_DEVSTA, ®16); - pci_write_config_word(dev, pos + PCI_EXP_DEVSTA, reg16); + pcie_capability_read_word(dev, PCI_EXP_DEVSTA, ®16); + pcie_capability_write_word(dev, PCI_EXP_DEVSTA, reg16); /* Clean AER Root Error Status */ pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); @@ -314,12 +412,10 @@ static void aer_error_resume(struct pci_dev *dev) * aer_service_init - register AER root service driver * * Invoked when AER root service driver is loaded. - **/ + */ static int __init aer_service_init(void) { - if (pcie_aer_disable) - return -ENXIO; - if (!pci_msi_enabled()) + if (!pci_aer_available() || aer_acpi_firmware_first()) return -ENXIO; return pcie_port_service_register(&aerdriver); } @@ -328,7 +424,7 @@ static int __init aer_service_init(void) * aer_service_exit - unregister AER root service driver * * Invoked when AER root service driver is unloaded. - **/ + */ static void __exit aer_service_exit(void) { pcie_port_service_unregister(&aerdriver); diff --git a/drivers/pci/pcie/aer/aerdrv.h b/drivers/pci/pcie/aer/aerdrv.h index bd833ea3ba4..84420b7c945 100644 --- a/drivers/pci/pcie/aer/aerdrv.h +++ b/drivers/pci/pcie/aer/aerdrv.h @@ -13,13 +13,6 @@ #include <linux/aer.h> #include <linux/interrupt.h> -#define AER_NONFATAL 0 -#define AER_FATAL 1 -#define AER_CORRECTABLE 2 - -/* Root Error Status Register Bits */ -#define ROOT_ERR_STATUS_MASKS 0x0f - #define SYSTEM_ERROR_INTR_ON_MESG_MASK (PCI_EXP_RTCTL_SECEE| \ PCI_EXP_RTCTL_SENFEE| \ PCI_EXP_RTCTL_SEFEE) @@ -38,13 +31,6 @@ PCI_ERR_UNC_UNX_COMP| \ PCI_ERR_UNC_MALF_TLP) -struct header_log_regs { - unsigned int dw0; - unsigned int dw1; - unsigned int dw2; - unsigned int dw3; -}; - #define AER_MAX_MULTI_ERR_DEVICES 5 /* Not likely to have more */ struct aer_err_info { struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES]; @@ -62,7 +48,7 @@ struct aer_err_info { unsigned int status; /* COR/UNCOR Error Status */ unsigned int mask; /* COR/UNCOR Error Mask */ - struct header_log_regs tlp; /* TLP Header */ + struct aer_header_log_regs tlp; /* TLP Header */ }; struct aer_err_source { @@ -97,6 +83,9 @@ struct aer_broadcast_data { 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; @@ -107,7 +96,7 @@ static inline pci_ers_result_t merge_result(enum pci_ers_result orig, break; case PCI_ERS_RESULT_DISCONNECT: if (new == PCI_ERS_RESULT_NEED_RESET) - orig = new; + orig = PCI_ERS_RESULT_NEED_RESET; break; default: break; @@ -117,21 +106,27 @@ static inline pci_ers_result_t merge_result(enum pci_ers_result orig, } extern struct bus_type pcie_port_bus_type; -extern void aer_enable_rootport(struct aer_rpc *rpc); -extern void aer_delete_rootport(struct aer_rpc *rpc); -extern int aer_init(struct pcie_device *dev); -extern void aer_isr(struct work_struct *work); -extern void aer_print_error(struct pci_dev *dev, struct aer_err_info *info); -extern void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info); -extern irqreturn_t aer_irq(int irq, void *context); - -#ifdef CONFIG_ACPI -extern int aer_osc_setup(struct pcie_device *pciedev); +int aer_init(struct pcie_device *dev); +void aer_isr(struct work_struct *work); +void aer_print_error(struct pci_dev *dev, struct aer_err_info *info); +void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info); +irqreturn_t aer_irq(int irq, void *context); + +#ifdef CONFIG_ACPI_APEI +int pcie_aer_get_firmware_first(struct pci_dev *pci_dev); #else -static inline int aer_osc_setup(struct pcie_device *pciedev) +static inline int pcie_aer_get_firmware_first(struct pci_dev *pci_dev) { + if (pci_dev->__aer_firmware_first_valid) + return pci_dev->__aer_firmware_first; return 0; } #endif +static inline void pcie_aer_force_firmware_first(struct pci_dev *pci_dev, + int enable) +{ + pci_dev->__aer_firmware_first = !!enable; + pci_dev->__aer_firmware_first_valid = 1; +} #endif /* _AERDRV_H_ */ diff --git a/drivers/pci/pcie/aer/aerdrv_acpi.c b/drivers/pci/pcie/aer/aerdrv_acpi.c index 04814087658..01906576ab9 100644 --- a/drivers/pci/pcie/aer/aerdrv_acpi.c +++ b/drivers/pci/pcie/aer/aerdrv_acpi.c @@ -16,40 +16,126 @@ #include <linux/acpi.h> #include <linux/pci-acpi.h> #include <linux/delay.h> +#include <acpi/apei.h> #include "aerdrv.h" -/** - * aer_osc_setup - run ACPI _OSC method - * @pciedev: pcie_device which AER is being enabled on - * - * @return: Zero on success. Nonzero otherwise. - * - * Invoked when PCIe bus loads AER service driver. To avoid conflict with - * BIOS AER support requires BIOS to yield AER control to OS native driver. - **/ -int aer_osc_setup(struct pcie_device *pciedev) +#ifdef CONFIG_ACPI_APEI +static inline int hest_match_pci(struct acpi_hest_aer_common *p, + struct pci_dev *pci) { - acpi_status status = AE_NOT_FOUND; - struct pci_dev *pdev = pciedev->port; - acpi_handle handle = NULL; - - if (acpi_pci_disabled) - return -1; - - handle = acpi_find_root_bridge_handle(pdev); - if (handle) { - status = acpi_pci_osc_control_set(handle, - OSC_PCI_EXPRESS_AER_CONTROL | - OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL); - } + return ACPI_HEST_SEGMENT(p->bus) == pci_domain_nr(pci->bus) && + ACPI_HEST_BUS(p->bus) == pci->bus->number && + p->device == PCI_SLOT(pci->devfn) && + p->function == PCI_FUNC(pci->devfn); +} + +static inline bool hest_match_type(struct acpi_hest_header *hest_hdr, + struct pci_dev *dev) +{ + u16 hest_type = hest_hdr->type; + u8 pcie_type = pci_pcie_type(dev); + + if ((hest_type == ACPI_HEST_TYPE_AER_ROOT_PORT && + pcie_type == PCI_EXP_TYPE_ROOT_PORT) || + (hest_type == ACPI_HEST_TYPE_AER_ENDPOINT && + pcie_type == PCI_EXP_TYPE_ENDPOINT) || + (hest_type == ACPI_HEST_TYPE_AER_BRIDGE && + (dev->class >> 16) == PCI_BASE_CLASS_BRIDGE)) + return true; + return false; +} + +struct aer_hest_parse_info { + struct pci_dev *pci_dev; + int firmware_first; +}; + +static int hest_source_is_pcie_aer(struct acpi_hest_header *hest_hdr) +{ + if (hest_hdr->type == ACPI_HEST_TYPE_AER_ROOT_PORT || + hest_hdr->type == ACPI_HEST_TYPE_AER_ENDPOINT || + hest_hdr->type == ACPI_HEST_TYPE_AER_BRIDGE) + return 1; + return 0; +} + +static int aer_hest_parse(struct acpi_hest_header *hest_hdr, void *data) +{ + struct aer_hest_parse_info *info = data; + struct acpi_hest_aer_common *p; + int ff; + + if (!hest_source_is_pcie_aer(hest_hdr)) + return 0; + + p = (struct acpi_hest_aer_common *)(hest_hdr + 1); + ff = !!(p->flags & ACPI_HEST_FIRMWARE_FIRST); - if (ACPI_FAILURE(status)) { - dev_printk(KERN_DEBUG, &pciedev->device, "AER service couldn't " - "init device: %s\n", - (status == AE_SUPPORT || status == AE_NOT_FOUND) ? - "no _OSC support" : "_OSC failed"); - return -1; + /* + * If no specific device is supplied, determine whether + * FIRMWARE_FIRST is set for *any* PCIe device. + */ + if (!info->pci_dev) { + info->firmware_first |= ff; + return 0; } + /* Otherwise, check the specific device */ + if (p->flags & ACPI_HEST_GLOBAL) { + if (hest_match_type(hest_hdr, info->pci_dev)) + info->firmware_first = ff; + } else + if (hest_match_pci(p, info->pci_dev)) + info->firmware_first = ff; + return 0; } + +static void aer_set_firmware_first(struct pci_dev *pci_dev) +{ + int rc; + struct aer_hest_parse_info info = { + .pci_dev = pci_dev, + .firmware_first = 0, + }; + + rc = apei_hest_parse(aer_hest_parse, &info); + + if (rc) + pci_dev->__aer_firmware_first = 0; + else + pci_dev->__aer_firmware_first = info.firmware_first; + pci_dev->__aer_firmware_first_valid = 1; +} + +int pcie_aer_get_firmware_first(struct pci_dev *dev) +{ + if (!pci_is_pcie(dev)) + return 0; + + if (!dev->__aer_firmware_first_valid) + aer_set_firmware_first(dev); + return dev->__aer_firmware_first; +} + +static bool aer_firmware_first; + +/** + * aer_acpi_firmware_first - Check if APEI should control AER. + */ +bool aer_acpi_firmware_first(void) +{ + static bool parsed = false; + struct aer_hest_parse_info info = { + .pci_dev = NULL, /* Check all PCIe devices */ + .firmware_first = 0, + }; + + if (!parsed) { + apei_hest_parse(aer_hest_parse, &info); + aer_firmware_first = info.firmware_first; + parsed = true; + } + return aer_firmware_first; +} +#endif diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c index c843a799814..5653ea94547 100644 --- a/drivers/pci/pcie/aer/aerdrv_core.c +++ b/drivers/pci/pcie/aer/aerdrv_core.c @@ -23,61 +23,37 @@ #include <linux/pm.h> #include <linux/suspend.h> #include <linux/delay.h> +#include <linux/slab.h> +#include <linux/kfifo.h> #include "aerdrv.h" -static int forceload; -static int nosourceid; +static bool forceload; +static bool nosourceid; module_param(forceload, bool, 0); module_param(nosourceid, bool, 0); +#define PCI_EXP_AER_FLAGS (PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE | \ + PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE) + int pci_enable_pcie_error_reporting(struct pci_dev *dev) { - u16 reg16 = 0; - int pos; - - if (dev->aer_firmware_first) - return -EIO; - - pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); - if (!pos) + if (pcie_aer_get_firmware_first(dev)) return -EIO; - pos = pci_pcie_cap(dev); - if (!pos) + if (!pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR)) return -EIO; - pci_read_config_word(dev, pos+PCI_EXP_DEVCTL, ®16); - reg16 = reg16 | - PCI_EXP_DEVCTL_CERE | - PCI_EXP_DEVCTL_NFERE | - PCI_EXP_DEVCTL_FERE | - PCI_EXP_DEVCTL_URRE; - pci_write_config_word(dev, pos+PCI_EXP_DEVCTL, reg16); - - return 0; + return pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_AER_FLAGS); } EXPORT_SYMBOL_GPL(pci_enable_pcie_error_reporting); int pci_disable_pcie_error_reporting(struct pci_dev *dev) { - u16 reg16 = 0; - int pos; - - if (dev->aer_firmware_first) - return -EIO; - - pos = pci_pcie_cap(dev); - if (!pos) + if (pcie_aer_get_firmware_first(dev)) return -EIO; - pci_read_config_word(dev, pos+PCI_EXP_DEVCTL, ®16); - reg16 = reg16 & ~(PCI_EXP_DEVCTL_CERE | - PCI_EXP_DEVCTL_NFERE | - PCI_EXP_DEVCTL_FERE | - PCI_EXP_DEVCTL_URRE); - pci_write_config_word(dev, pos+PCI_EXP_DEVCTL, reg16); - - return 0; + return pcie_capability_clear_word(dev, PCI_EXP_DEVCTL, + PCI_EXP_AER_FLAGS); } EXPORT_SYMBOL_GPL(pci_disable_pcie_error_reporting); @@ -98,99 +74,44 @@ int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status); -static int set_device_error_reporting(struct pci_dev *dev, void *data) -{ - bool enable = *((bool *)data); - - if ((dev->pcie_type == PCI_EXP_TYPE_ROOT_PORT) || - (dev->pcie_type == PCI_EXP_TYPE_UPSTREAM) || - (dev->pcie_type == PCI_EXP_TYPE_DOWNSTREAM)) { - if (enable) - pci_enable_pcie_error_reporting(dev); - else - pci_disable_pcie_error_reporting(dev); - } - - if (enable) - pcie_set_ecrc_checking(dev); - - return 0; -} - /** - * set_downstream_devices_error_reporting - enable/disable the error reporting bits on the root port and its downstream ports. - * @dev: pointer to root port's pci_dev data structure - * @enable: true = enable error reporting, false = disable error reporting. + * add_error_device - list device to be handled + * @e_info: pointer to error info + * @dev: pointer to pci_dev to be added */ -static void set_downstream_devices_error_reporting(struct pci_dev *dev, - bool enable) -{ - set_device_error_reporting(dev, &enable); - - if (!dev->subordinate) - return; - pci_walk_bus(dev->subordinate, set_device_error_reporting, &enable); -} - -static inline int compare_device_id(struct pci_dev *dev, - struct aer_err_info *e_info) -{ - if (e_info->id == ((dev->bus->number << 8) | dev->devfn)) { - /* - * Device ID match - */ - return 1; - } - - return 0; -} - static int add_error_device(struct aer_err_info *e_info, struct pci_dev *dev) { if (e_info->error_dev_num < AER_MAX_MULTI_ERR_DEVICES) { e_info->dev[e_info->error_dev_num] = dev; e_info->error_dev_num++; - return 1; + return 0; } - - return 0; + return -ENOSPC; } - -#define PCI_BUS(x) (((x) >> 8) & 0xff) - -static int find_device_iter(struct pci_dev *dev, void *data) +/** + * is_error_source - check whether the device is source of reported error + * @dev: pointer to pci_dev to be checked + * @e_info: pointer to reported error info + */ +static bool is_error_source(struct pci_dev *dev, struct aer_err_info *e_info) { int pos; - u32 status; - u32 mask; + u32 status, mask; u16 reg16; - int result; - struct aer_err_info *e_info = (struct aer_err_info *)data; /* * When bus id is equal to 0, it might be a bad id * reported by root port. */ - if (!nosourceid && (PCI_BUS(e_info->id) != 0)) { - result = compare_device_id(dev, e_info); - if (result) - add_error_device(e_info, dev); + if (!nosourceid && (PCI_BUS_NUM(e_info->id) != 0)) { + /* Device ID match? */ + if (e_info->id == ((dev->bus->number << 8) | dev->devfn)) + return true; - /* - * If there is no multiple error, we stop - * or continue based on the id comparing. - */ + /* Continue id comparing if there is no multiple error */ if (!e_info->multi_error_valid) - return result; - - /* - * If there are multiple errors and id does match, - * We need continue to search other devices under - * the root port. Return 0 means that. - */ - if (result) - return 0; + return false; } /* @@ -199,80 +120,98 @@ static int find_device_iter(struct pci_dev *dev, void *data) * 2) bus id is equal to 0. Some ports might lose the bus * id of error source id; * 3) There are multiple errors and prior id comparing fails; - * We check AER status registers to find the initial reporter. + * We check AER status registers to find possible reporter. */ if (atomic_read(&dev->enable_cnt) == 0) - return 0; - pos = pci_pcie_cap(dev); - if (!pos) - return 0; + return false; + /* Check if AER is enabled */ - pci_read_config_word(dev, pos+PCI_EXP_DEVCTL, ®16); - if (!(reg16 & ( - PCI_EXP_DEVCTL_CERE | - PCI_EXP_DEVCTL_NFERE | - PCI_EXP_DEVCTL_FERE | - PCI_EXP_DEVCTL_URRE))) - return 0; + pcie_capability_read_word(dev, PCI_EXP_DEVCTL, ®16); + if (!(reg16 & PCI_EXP_AER_FLAGS)) + return false; + pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); if (!pos) - return 0; + return false; - status = 0; - mask = 0; + /* Check if error is recorded */ if (e_info->severity == AER_CORRECTABLE) { pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS, &status); pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, &mask); - if (status & ~mask) { - add_error_device(e_info, dev); - goto added; - } } else { pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status); pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, &mask); - if (status & ~mask) { - add_error_device(e_info, dev); - goto added; - } } + if (status & ~mask) + return true; - return 0; + return false; +} -added: - if (e_info->multi_error_valid) - return 0; - else - return 1; +static int find_device_iter(struct pci_dev *dev, void *data) +{ + struct aer_err_info *e_info = (struct aer_err_info *)data; + + if (is_error_source(dev, e_info)) { + /* List this device */ + if (add_error_device(e_info, dev)) { + /* We cannot handle more... Stop iteration */ + /* TODO: Should print error message here? */ + return 1; + } + + /* If there is only a single error, stop iteration */ + if (!e_info->multi_error_valid) + return 1; + } + return 0; } /** * find_source_device - search through device hierarchy for source device * @parent: pointer to Root Port pci_dev data structure - * @err_info: including detailed error information such like id + * @e_info: including detailed error information such like id + * + * Return true if found. * - * Invoked when error is detected at the Root Port. + * Invoked by DPC when error is detected at the Root Port. + * Caller of this function must set id, severity, and multi_error_valid of + * struct aer_err_info pointed by @e_info properly. This function must fill + * e_info->error_dev_num and e_info->dev[], based on the given information. */ -static void find_source_device(struct pci_dev *parent, +static bool find_source_device(struct pci_dev *parent, struct aer_err_info *e_info) { struct pci_dev *dev = parent; int result; + /* Must reset in this function */ + e_info->error_dev_num = 0; + /* Is Root Port an agent that sends error message? */ result = find_device_iter(dev, e_info); if (result) - return; + return true; pci_walk_bus(parent->subordinate, find_device_iter, e_info); + + if (!e_info->error_dev_num) { + dev_printk(KERN_DEBUG, &parent->dev, + "can't find device of ID%04x\n", + e_info->id); + return false; + } + return true; } static int report_error_detected(struct pci_dev *dev, void *data) { pci_ers_result_t vote; - struct pci_error_handlers *err_handler; + 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 || @@ -291,64 +230,89 @@ static int report_error_detected(struct pci_dev *dev, void *data) dev->driver ? "no AER-aware driver" : "no driver"); } - return 0; + + /* + * 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); } - err_handler = dev->driver->err_handler; - vote = err_handler->error_detected(dev, result_data->state); 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; - struct pci_error_handlers *err_handler; + 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) - return 0; + 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; - struct pci_error_handlers *err_handler; + 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) - return 0; + 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) { - struct pci_error_handlers *err_handler; + 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) - return 0; + goto out; err_handler = dev->driver->err_handler; err_handler->resume(dev); +out: + device_unlock(&dev->dev); return 0; } @@ -402,82 +366,79 @@ static pci_ers_result_t broadcast_error_message(struct pci_dev *dev, return result_data.result; } -struct find_aer_service_data { - struct pcie_port_service_driver *aer_driver; - int is_downstream; -}; +/** + * 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); + dev_printk(KERN_DEBUG, &dev->dev, "downstream link has been reset\n"); + return PCI_ERS_RESULT_RECOVERED; +} static int find_aer_service_iter(struct device *device, void *data) { - struct device_driver *driver; - struct pcie_port_service_driver *service_driver; - struct find_aer_service_data *result; - - result = (struct find_aer_service_data *) data; - - if (device->bus == &pcie_port_bus_type) { - struct pcie_device *pcie = to_pcie_device(device); + struct pcie_port_service_driver *service_driver, **drv; - if (pcie->port->pcie_type == PCI_EXP_TYPE_DOWNSTREAM) - result->is_downstream = 1; + drv = (struct pcie_port_service_driver **) data; - driver = device->driver; - if (driver) { - service_driver = to_service_driver(driver); - if (service_driver->service == PCIE_PORT_SERVICE_AER) { - result->aer_driver = service_driver; - return 1; - } + 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 void find_aer_service(struct pci_dev *dev, - struct find_aer_service_data *data) +static struct pcie_port_service_driver *find_aer_service(struct pci_dev *dev) { - int retval; - retval = device_for_each_child(&dev->dev, data, find_aer_service_iter); + 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 pcie_device *aerdev, - struct pci_dev *dev) +static pci_ers_result_t reset_link(struct pci_dev *dev) { struct pci_dev *udev; pci_ers_result_t status; - struct find_aer_service_data data; + struct pcie_port_service_driver *driver; - if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE) + if (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE) { + /* Reset this port for all subordinates */ udev = dev; - else + } else { + /* Reset the upstream component (likely downstream port) */ udev = dev->bus->self; + } - data.is_downstream = 0; - data.aer_driver = NULL; - find_aer_service(udev, &data); + /* Use the aer driver of the component firstly */ + driver = find_aer_service(udev); - /* - * Use the aer driver of the error agent firstly. - * If it hasn't the aer driver, use the root port's - */ - if (!data.aer_driver || !data.aer_driver->reset_link) { - if (data.is_downstream && - aerdev->device.driver && - to_service_driver(aerdev->device.driver)->reset_link) { - data.aer_driver = - to_service_driver(aerdev->device.driver); - } else { - dev_printk(KERN_DEBUG, &dev->dev, "no link-reset " - "support\n"); - return PCI_ERS_RESULT_DISCONNECT; - } + if (driver && driver->reset_link) { + status = driver->reset_link(udev); + } else if (pci_pcie_type(udev) == PCI_EXP_TYPE_DOWNSTREAM || + pci_pcie_type(udev) == PCI_EXP_TYPE_ROOT_PORT) { + status = default_reset_link(udev); + } else { + dev_printk(KERN_DEBUG, &dev->dev, + "no link-reset support at upstream device %s\n", + pci_name(udev)); + return PCI_ERS_RESULT_DISCONNECT; } - status = data.aer_driver->reset_link(udev); if (status != PCI_ERS_RESULT_RECOVERED) { - dev_printk(KERN_DEBUG, &dev->dev, "link reset at upstream " - "device %s failed\n", pci_name(udev)); + dev_printk(KERN_DEBUG, &dev->dev, + "link reset at upstream device %s failed\n", + pci_name(udev)); return PCI_ERS_RESULT_DISCONNECT; } @@ -486,7 +447,6 @@ static pci_ers_result_t reset_link(struct pcie_device *aerdev, /** * do_recovery - handle nonfatal/fatal error recovery process - * @aerdev: pointer to a pcie_device data structure of root port * @dev: pointer to a pci_dev data structure of agent detecting an error * @severity: error severity type * @@ -494,9 +454,7 @@ static pci_ers_result_t reset_link(struct pcie_device *aerdev, * error detected message to all downstream drivers within a hierarchy in * question and return the returned code. */ -static pci_ers_result_t do_recovery(struct pcie_device *aerdev, - struct pci_dev *dev, - int severity) +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; @@ -512,11 +470,9 @@ static pci_ers_result_t do_recovery(struct pcie_device *aerdev, report_error_detected); if (severity == AER_FATAL) { - result = reset_link(aerdev, dev); - if (result != PCI_ERS_RESULT_RECOVERED) { - /* TODO: Should panic here? */ - return result; - } + result = reset_link(dev); + if (result != PCI_ERS_RESULT_RECOVERED) + goto failed; } if (status == PCI_ERS_RESULT_CAN_RECOVER) @@ -537,13 +493,20 @@ static pci_ers_result_t do_recovery(struct pcie_device *aerdev, report_slot_reset); } - if (status == PCI_ERS_RESULT_RECOVERED) - broadcast_error_message(dev, + if (status != PCI_ERS_RESULT_RECOVERED) + goto failed; + + broadcast_error_message(dev, state, "resume", report_resume); - return status; + dev_info(&dev->dev, "AER: Device recovery successful\n"); + return; + +failed: + /* TODO: Should kernel panic here? */ + dev_info(&dev->dev, "AER: Device recovery failed\n"); } /** @@ -558,127 +521,87 @@ static void handle_error_source(struct pcie_device *aerdev, struct pci_dev *dev, struct aer_err_info *info) { - pci_ers_result_t status = 0; int pos; if (info->severity == AER_CORRECTABLE) { /* - * Correctable error does not need software intevention. + * Correctable error does not need software intervention. * No need to go through error recovery process. */ pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); if (pos) pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS, info->status); - } else { - status = do_recovery(aerdev, dev, info->severity); - if (status == PCI_ERS_RESULT_RECOVERED) { - dev_printk(KERN_DEBUG, &dev->dev, "AER driver " - "successfully recovered\n"); - } else { - /* TODO: Should kernel panic here? */ - dev_printk(KERN_DEBUG, &dev->dev, "AER driver didn't " - "recover\n"); - } - } + } else + do_recovery(dev, info->severity); } -/** - * aer_enable_rootport - enable Root Port's interrupts when receiving messages - * @rpc: pointer to a Root Port data structure - * - * Invoked when PCIe bus loads AER service driver. - */ -void aer_enable_rootport(struct aer_rpc *rpc) -{ - struct pci_dev *pdev = rpc->rpd->port; - int pos, aer_pos; - u16 reg16; - u32 reg32; - - pos = pci_pcie_cap(pdev); - /* Clear PCIe Capability's Device Status */ - pci_read_config_word(pdev, pos+PCI_EXP_DEVSTA, ®16); - pci_write_config_word(pdev, pos+PCI_EXP_DEVSTA, reg16); - - /* Disable system error generation in response to error messages */ - pci_read_config_word(pdev, pos + PCI_EXP_RTCTL, ®16); - reg16 &= ~(SYSTEM_ERROR_INTR_ON_MESG_MASK); - pci_write_config_word(pdev, pos + PCI_EXP_RTCTL, reg16); - - aer_pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR); - /* Clear error status */ - pci_read_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, ®32); - pci_write_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, reg32); - pci_read_config_dword(pdev, aer_pos + PCI_ERR_COR_STATUS, ®32); - pci_write_config_dword(pdev, aer_pos + PCI_ERR_COR_STATUS, reg32); - pci_read_config_dword(pdev, aer_pos + PCI_ERR_UNCOR_STATUS, ®32); - pci_write_config_dword(pdev, aer_pos + PCI_ERR_UNCOR_STATUS, reg32); +#ifdef CONFIG_ACPI_APEI_PCIEAER +static void aer_recover_work_func(struct work_struct *work); - /* - * Enable error reporting for the root port device and downstream port - * devices. - */ - set_downstream_devices_error_reporting(pdev, true); +#define AER_RECOVER_RING_ORDER 4 +#define AER_RECOVER_RING_SIZE (1 << AER_RECOVER_RING_ORDER) - /* Enable Root Port's interrupt in response to error messages */ - pci_write_config_dword(pdev, - aer_pos + PCI_ERR_ROOT_COMMAND, - ROOT_PORT_INTR_ON_MESG_MASK); -} +struct aer_recover_entry { + u8 bus; + u8 devfn; + u16 domain; + int severity; + struct aer_capability_regs *regs; +}; -/** - * disable_root_aer - disable Root Port's interrupts when receiving messages - * @rpc: pointer to a Root Port data structure - * - * Invoked when PCIe bus unloads AER service driver. +static DEFINE_KFIFO(aer_recover_ring, struct aer_recover_entry, + AER_RECOVER_RING_SIZE); +/* + * 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 + * between reader and writer. */ -static void disable_root_aer(struct aer_rpc *rpc) -{ - struct pci_dev *pdev = rpc->rpd->port; - u32 reg32; - int pos; +static DEFINE_SPINLOCK(aer_recover_ring_lock); +static DECLARE_WORK(aer_recover_work, aer_recover_work_func); - /* - * Disable error reporting for the root port device and downstream port - * devices. - */ - set_downstream_devices_error_reporting(pdev, false); - - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR); - /* Disable Root's interrupt in response to error messages */ - pci_write_config_dword(pdev, pos + PCI_ERR_ROOT_COMMAND, 0); - - /* Clear Root's error status reg */ - pci_read_config_dword(pdev, pos + PCI_ERR_ROOT_STATUS, ®32); - pci_write_config_dword(pdev, pos + PCI_ERR_ROOT_STATUS, reg32); -} - -/** - * get_e_source - retrieve an error source - * @rpc: pointer to the root port which holds an error - * - * Invoked by DPC handler to consume an error. - */ -static struct aer_err_source *get_e_source(struct aer_rpc *rpc) +void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn, + int severity, struct aer_capability_regs *aer_regs) { - struct aer_err_source *e_source; unsigned long flags; + struct aer_recover_entry entry = { + .bus = bus, + .devfn = devfn, + .domain = domain, + .severity = severity, + .regs = aer_regs, + }; + + spin_lock_irqsave(&aer_recover_ring_lock, flags); + if (kfifo_put(&aer_recover_ring, entry)) + schedule_work(&aer_recover_work); + else + pr_err("AER recover: Buffer overflow when recovering AER for %04x:%02x:%02x:%x\n", + domain, bus, PCI_SLOT(devfn), PCI_FUNC(devfn)); + spin_unlock_irqrestore(&aer_recover_ring_lock, flags); +} +EXPORT_SYMBOL_GPL(aer_recover_queue); - /* Lock access to Root error producer/consumer index */ - spin_lock_irqsave(&rpc->e_lock, flags); - if (rpc->prod_idx == rpc->cons_idx) { - spin_unlock_irqrestore(&rpc->e_lock, flags); - return NULL; +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); + do_recovery(pdev, entry.severity); + pci_dev_put(pdev); } - e_source = &rpc->e_sources[rpc->cons_idx]; - rpc->cons_idx++; - if (rpc->cons_idx == AER_ERROR_SOURCES_MAX) - rpc->cons_idx = 0; - spin_unlock_irqrestore(&rpc->e_lock, flags); - - return e_source; } +#endif /** * get_device_error_info - read error status from dev and store it to info @@ -686,11 +609,14 @@ static struct aer_err_source *get_e_source(struct aer_rpc *rpc) * @info: pointer to structure to store the error record * * Return 1 on success, 0 on error. + * + * Note that @info is reused among all error devices. Clear fields properly. */ static int get_device_error_info(struct pci_dev *dev, struct aer_err_info *info) { int pos, temp; + /* Must reset in this function */ info->status = 0; info->tlp_header_valid = 0; @@ -743,12 +669,6 @@ static inline void aer_process_err_devices(struct pcie_device *p_device, { int i; - if (!e_info->dev[0]) { - dev_printk(KERN_DEBUG, &p_device->port->dev, - "can't find device of ID%04x\n", - e_info->id); - } - /* Report all before handle them, not to lost records by reset etc. */ 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)) @@ -769,11 +689,10 @@ static void aer_isr_one_error(struct pcie_device *p_device, struct aer_err_source *e_src) { struct aer_err_info *e_info; - int i; /* struct aer_err_info might be big, so we allocate it with slab */ e_info = kmalloc(sizeof(struct aer_err_info), GFP_KERNEL); - if (e_info == NULL) { + if (!e_info) { dev_printk(KERN_DEBUG, &p_device->port->dev, "Can't allocate mem when processing AER errors\n"); return; @@ -783,37 +702,73 @@ static void aer_isr_one_error(struct pcie_device *p_device, * There is a possibility that both correctable error and * uncorrectable error being logged. Report correctable error first. */ - for (i = 1; i & ROOT_ERR_STATUS_MASKS ; i <<= 2) { - if (i > 4) - break; - if (!(e_src->status & i)) - continue; + if (e_src->status & PCI_ERR_ROOT_COR_RCV) { + e_info->id = ERR_COR_ID(e_src->id); + e_info->severity = AER_CORRECTABLE; - memset(e_info, 0, sizeof(struct aer_err_info)); + if (e_src->status & PCI_ERR_ROOT_MULTI_COR_RCV) + e_info->multi_error_valid = 1; + else + e_info->multi_error_valid = 0; - /* Init comprehensive error information */ - if (i & PCI_ERR_ROOT_COR_RCV) { - e_info->id = ERR_COR_ID(e_src->id); - e_info->severity = AER_CORRECTABLE; - } else { - e_info->id = ERR_UNCOR_ID(e_src->id); - e_info->severity = ((e_src->status >> 6) & 1); - } - if (e_src->status & - (PCI_ERR_ROOT_MULTI_COR_RCV | - PCI_ERR_ROOT_MULTI_UNCOR_RCV)) + 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 (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) { + e_info->id = ERR_UNCOR_ID(e_src->id); + + if (e_src->status & PCI_ERR_ROOT_FATAL_RCV) + e_info->severity = AER_FATAL; + else + e_info->severity = AER_NONFATAL; + + if (e_src->status & PCI_ERR_ROOT_MULTI_UNCOR_RCV) e_info->multi_error_valid = 1; + else + e_info->multi_error_valid = 0; aer_print_port_info(p_device->port, e_info); - find_source_device(p_device->port, e_info); - aer_process_err_devices(p_device, e_info); + if (find_source_device(p_device->port, e_info)) + aer_process_err_devices(p_device, e_info); } kfree(e_info); } /** + * get_e_source - retrieve an error source + * @rpc: pointer to the root port which holds an error + * @e_src: pointer to store retrieved error source + * + * Return 1 if an error source is retrieved, otherwise 0. + * + * Invoked by DPC handler to consume an error. + */ +static int get_e_source(struct aer_rpc *rpc, struct aer_err_source *e_src) +{ + unsigned long flags; + + /* Lock access to Root error producer/consumer index */ + spin_lock_irqsave(&rpc->e_lock, flags); + if (rpc->prod_idx == rpc->cons_idx) { + spin_unlock_irqrestore(&rpc->e_lock, flags); + return 0; + } + + *e_src = rpc->e_sources[rpc->cons_idx]; + rpc->cons_idx++; + if (rpc->cons_idx == AER_ERROR_SOURCES_MAX) + rpc->cons_idx = 0; + spin_unlock_irqrestore(&rpc->e_lock, flags); + + return 1; +} + +/** * aer_isr - consume errors detected by root port * @work: definition of this work item * @@ -823,34 +778,17 @@ 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 *e_src; + struct aer_err_source uninitialized_var(e_src); mutex_lock(&rpc->rpc_mutex); - e_src = get_e_source(rpc); - while (e_src) { - aer_isr_one_error(p_device, e_src); - e_src = get_e_source(rpc); - } + while (get_e_source(rpc, &e_src)) + aer_isr_one_error(p_device, &e_src); mutex_unlock(&rpc->rpc_mutex); wake_up(&rpc->wait_release); } /** - * aer_delete_rootport - disable root port aer and delete service data - * @rpc: pointer to a root port device being deleted - * - * Invoked when AER service unloaded on a specific Root Port - */ -void aer_delete_rootport(struct aer_rpc *rpc) -{ - /* Disable root port AER itself */ - disable_root_aer(rpc); - - kfree(rpc); -} - -/** * aer_init - provide AER initialization * @dev: pointer to AER pcie device * @@ -858,22 +796,10 @@ void aer_delete_rootport(struct aer_rpc *rpc) */ int aer_init(struct pcie_device *dev) { - if (dev->port->aer_firmware_first) { - dev_printk(KERN_DEBUG, &dev->device, - "PCIe errors handled by platform firmware.\n"); - goto out; - } - - if (aer_osc_setup(dev)) - goto out; - - return 0; -out: if (forceload) { dev_printk(KERN_DEBUG, &dev->device, "aerdrv forceload requested.\n"); - dev->port->aer_firmware_first = 0; - return 0; + pcie_aer_force_firmware_first(dev->port, 0); } - return -ENXIO; + return 0; } diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c index 9d3e4c8d018..36ed31b5219 100644 --- a/drivers/pci/pcie/aer/aerdrv_errprint.c +++ b/drivers/pci/pcie/aer/aerdrv_errprint.c @@ -19,9 +19,13 @@ #include <linux/errno.h> #include <linux/pm.h> #include <linux/suspend.h> +#include <linux/cper.h> #include "aerdrv.h" +#define CREATE_TRACE_POINTS +#include <trace/events/ras.h> + #define AER_AGENT_RECEIVER 0 #define AER_AGENT_REQUESTER 1 #define AER_AGENT_COMPLETER 2 @@ -57,86 +61,44 @@ (e & AER_DATA_LINK_LAYER_ERROR_MASK(t)) ? AER_DATA_LINK_LAYER_ERROR : \ AER_TRANSACTION_LAYER_ERROR) -#define AER_PR(info, pdev, fmt, args...) \ - printk("%s%s %s: " fmt, (info->severity == AER_CORRECTABLE) ? \ - KERN_WARNING : KERN_ERR, dev_driver_string(&pdev->dev), \ - dev_name(&pdev->dev), ## args) - /* * AER error strings */ -static char *aer_error_severity_string[] = { +static const char *aer_error_severity_string[] = { "Uncorrected (Non-Fatal)", "Uncorrected (Fatal)", "Corrected" }; -static char *aer_error_layer[] = { +static const char *aer_error_layer[] = { "Physical Layer", "Data Link Layer", "Transaction Layer" }; -static char *aer_correctable_error_string[] = { - "Receiver Error ", /* Bit Position 0 */ - NULL, - NULL, - NULL, - NULL, - NULL, - "Bad TLP ", /* Bit Position 6 */ - "Bad DLLP ", /* Bit Position 7 */ - "RELAY_NUM Rollover ", /* Bit Position 8 */ - NULL, - NULL, - NULL, - "Replay Timer Timeout ", /* Bit Position 12 */ - "Advisory Non-Fatal ", /* Bit Position 13 */ - NULL, - NULL, - NULL, - NULL, - NULL, - NULL, - NULL, - NULL, - NULL, - NULL, + +static const char *aer_correctable_error_string[] = { + "Receiver Error", /* Bit Position 0 */ NULL, NULL, NULL, NULL, NULL, + "Bad TLP", /* Bit Position 6 */ + "Bad DLLP", /* Bit Position 7 */ + "RELAY_NUM Rollover", /* Bit Position 8 */ NULL, NULL, NULL, + "Replay Timer Timeout", /* Bit Position 12 */ + "Advisory Non-Fatal", /* Bit Position 13 */ }; -static char *aer_uncorrectable_error_string[] = { - NULL, - NULL, - NULL, - NULL, - "Data Link Protocol ", /* Bit Position 4 */ - NULL, - NULL, - NULL, - NULL, - NULL, - NULL, - NULL, - "Poisoned TLP ", /* Bit Position 12 */ - "Flow Control Protocol ", /* Bit Position 13 */ - "Completion Timeout ", /* Bit Position 14 */ - "Completer Abort ", /* Bit Position 15 */ - "Unexpected Completion ", /* Bit Position 16 */ - "Receiver Overflow ", /* Bit Position 17 */ - "Malformed TLP ", /* Bit Position 18 */ - "ECRC ", /* Bit Position 19 */ - "Unsupported Request ", /* Bit Position 20 */ +static const char *aer_uncorrectable_error_string[] = { NULL, NULL, NULL, NULL, + "Data Link Protocol", /* Bit Position 4 */ NULL, NULL, NULL, @@ -144,20 +106,44 @@ static char *aer_uncorrectable_error_string[] = { NULL, NULL, NULL, + "Poisoned TLP", /* Bit Position 12 */ + "Flow Control Protocol", /* Bit Position 13 */ + "Completion Timeout", /* Bit Position 14 */ + "Completer Abort", /* Bit Position 15 */ + "Unexpected Completion", /* Bit Position 16 */ + "Receiver Overflow", /* Bit Position 17 */ + "Malformed TLP", /* Bit Position 18 */ + "ECRC", /* Bit Position 19 */ + "Unsupported Request", /* Bit Position 20 */ }; -static char *aer_agent_string[] = { +static const char *aer_agent_string[] = { "Receiver ID", "Requester ID", "Completer ID", "Transmitter ID" }; -static void __aer_print_error(struct aer_err_info *info, struct pci_dev *dev) +static void __print_tlp_header(struct pci_dev *dev, + struct aer_header_log_regs *t) { - int i, status; - char *errmsg = NULL; + unsigned char *tlp = (unsigned char *)&t; + + dev_err(&dev->dev, " TLP Header:" + " %02x%02x%02x%02x %02x%02x%02x%02x" + " %02x%02x%02x%02x %02x%02x%02x%02x\n", + *(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp, + *(tlp + 7), *(tlp + 6), *(tlp + 5), *(tlp + 4), + *(tlp + 11), *(tlp + 10), *(tlp + 9), + *(tlp + 8), *(tlp + 15), *(tlp + 14), + *(tlp + 13), *(tlp + 12)); +} +static void __aer_print_error(struct pci_dev *dev, + struct aer_err_info *info) +{ + int i, status; + const char *errmsg = NULL; status = (info->status & ~info->mask); for (i = 0; i < 32; i++) { @@ -165,61 +151,54 @@ static void __aer_print_error(struct aer_err_info *info, struct pci_dev *dev) continue; if (info->severity == AER_CORRECTABLE) - errmsg = aer_correctable_error_string[i]; + errmsg = i < ARRAY_SIZE(aer_correctable_error_string) ? + aer_correctable_error_string[i] : NULL; else - errmsg = aer_uncorrectable_error_string[i]; + errmsg = i < ARRAY_SIZE(aer_uncorrectable_error_string) ? + aer_uncorrectable_error_string[i] : NULL; if (errmsg) - AER_PR(info, dev, " [%2d] %s%s\n", i, errmsg, + dev_err(&dev->dev, " [%2d] %-22s%s\n", i, errmsg, info->first_error == i ? " (First)" : ""); else - AER_PR(info, dev, " [%2d] Unknown Error Bit%s\n", i, - info->first_error == i ? " (First)" : ""); + dev_err(&dev->dev, " [%2d] Unknown Error Bit%s\n", + i, info->first_error == i ? " (First)" : ""); } } void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) { + int layer, agent; int id = ((dev->bus->number << 8) | dev->devfn); - if (info->status == 0) { - AER_PR(info, dev, - "PCIe Bus Error: severity=%s, type=Unaccessible, " - "id=%04x(Unregistered Agent ID)\n", + if (!info->status) { + dev_err(&dev->dev, "PCIe Bus Error: severity=%s, type=Unaccessible, id=%04x(Unregistered Agent ID)\n", aer_error_severity_string[info->severity], id); - } else { - int layer, agent; - - layer = AER_GET_LAYER_ERROR(info->severity, info->status); - agent = AER_GET_AGENT(info->severity, info->status); - - AER_PR(info, dev, - "PCIe Bus Error: severity=%s, type=%s, id=%04x(%s)\n", - aer_error_severity_string[info->severity], - aer_error_layer[layer], id, aer_agent_string[agent]); - - AER_PR(info, dev, - " device [%04x:%04x] error status/mask=%08x/%08x\n", - dev->vendor, dev->device, info->status, info->mask); - - __aer_print_error(info, dev); - - if (info->tlp_header_valid) { - unsigned char *tlp = (unsigned char *) &info->tlp; - AER_PR(info, dev, " TLP Header:" - " %02x%02x%02x%02x %02x%02x%02x%02x" - " %02x%02x%02x%02x %02x%02x%02x%02x\n", - *(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp, - *(tlp + 7), *(tlp + 6), *(tlp + 5), *(tlp + 4), - *(tlp + 11), *(tlp + 10), *(tlp + 9), - *(tlp + 8), *(tlp + 15), *(tlp + 14), - *(tlp + 13), *(tlp + 12)); - } + goto out; } + layer = AER_GET_LAYER_ERROR(info->severity, info->status); + agent = AER_GET_AGENT(info->severity, info->status); + + dev_err(&dev->dev, "PCIe Bus Error: severity=%s, type=%s, id=%04x(%s)\n", + aer_error_severity_string[info->severity], + aer_error_layer[layer], id, aer_agent_string[agent]); + + dev_err(&dev->dev, " device [%04x:%04x] error status/mask=%08x/%08x\n", + dev->vendor, dev->device, + info->status, info->mask); + + __aer_print_error(dev, info); + + if (info->tlp_header_valid) + __print_tlp_header(dev, &info->tlp); + +out: if (info->id && info->error_dev_num > 1 && info->id == id) - AER_PR(info, dev, - " Error of this Agent(%04x) is reported first\n", id); + dev_err(&dev->dev, " Error of this Agent(%04x) is reported first\n", id); + + trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask), + info->severity); } void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info) @@ -228,3 +207,59 @@ void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info) info->multi_error_valid ? "Multiple " : "", aer_error_severity_string[info->severity], info->id); } + +#ifdef CONFIG_ACPI_APEI_PCIEAER +int cper_severity_to_aer(int cper_severity) +{ + switch (cper_severity) { + case CPER_SEV_RECOVERABLE: + return AER_NONFATAL; + case CPER_SEV_FATAL: + return AER_FATAL; + default: + return AER_CORRECTABLE; + } +} +EXPORT_SYMBOL_GPL(cper_severity_to_aer); + +void cper_print_aer(struct pci_dev *dev, int cper_severity, + struct aer_capability_regs *aer) +{ + int aer_severity, layer, agent, status_strs_size, tlp_header_valid = 0; + u32 status, mask; + const char **status_strs; + + aer_severity = cper_severity_to_aer(cper_severity); + + 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); + + dev_err(&dev->dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n", status, mask); + cper_print_bits("", status, status_strs, status_strs_size); + dev_err(&dev->dev, "aer_layer=%s, aer_agent=%s\n", + aer_error_layer[layer], aer_agent_string[agent]); + + if (aer_severity != AER_CORRECTABLE) + dev_err(&dev->dev, "aer_uncor_severity: 0x%08x\n", + aer->uncor_severity); + + if (tlp_header_valid) + __print_tlp_header(dev, &aer->header_log); + + trace_aer_event(dev_name(&dev->dev), (status & ~mask), + aer_severity); +} +#endif |