【PCIe】AER linux 驱动浅析

AER及linux内核驱动简介：https://blog.csdn.net/u010443710/article/details/104649179

下面是PCIe设备端错误记录和报告的详细流程图。

1. AER 中断

首先AER驱动作为错误上报和处理的机制，必须有一个错误上报的入口。

这个入口就是AER中断。linux的AER驱动只针对RC，也就是说软件需要处理RC的AER中断请求。

并在中断处理函数中通过AER 寄存器来判断错误类型并作出相应处理。

1.1 AER中断产生

在PCIe spec中定义了2种AER中断产生方式，类似于ep设备，可以选择legacy的INTx或者MSI/MSIx的方式来产生中断。

但对于RC而言，无论是INTx还是MSI/MSIx，都不需要像ep那样真的来触发INTx边带信号或发送MSI tlp来告知RC。

因为RC作为根节点，内部的中断就是报给自己，可以直接在chip内部处理，不需要在PCIe协议上走一圈。

这就涉及RC内部中断上报的机制，由于RC内部中断不仅限于AER中断，所以这部分单独开一篇进行阐述。

1.2 如何使能AER中断?

AER Capability -> Root Error Command Register (Offset 2Ch)

打开相应的报告使能bit位，当错误发生后，就会有中断产生。

2. AER驱动

AER驱动与PME、pciehp、pcie-dpc一样是作为pcie port的可选service。

service挂载在pcie port驱动上，由portdrv_core进行管理，service通过pcie_port_service_register进行注册。

具体来说，service的数据结构如下：

struct pcie_port_service_driver {const char *name;int (*probe) (struct pcie_device *dev);void (*remove) (struct pcie_device *dev);int (*suspend) (struct pcie_device *dev);int (*resume) (struct pcie_device *dev);/* Service Error Recovery Handler */const struct pci_error_handlers *err_handler;/* Link Reset Capability - AER service driver specific */pci_ers_result_t (*reset_link) (struct pci_dev *dev);int port_type;  /* Type of the port this driver can handle */u32 service;    /* Port service this device represents */struct device_driver driver;
};

 以下是AER的service结构

static struct pcie_port_service_driver aerdriver = {.name		= "aer",.port_type	= PCI_EXP_TYPE_ROOT_PORT,.service	= PCIE_PORT_SERVICE_AER,.probe		= aer_probe,.remove		= aer_remove,.err_handler	= &aer_error_handlers,.reset_link	= aer_root_reset,
};

2.1 初始化（aer_probe）

AER初始化主要完成2件事情：

1. 为错误处理入口aer_irq，申请中断；request_irq(dev->irq, aer_irq, IRQF_SHARED, "aerdrv", dev);
2. 配置AER功能相关的cap寄存器，打开AER能使，中断上报使能等；aer_enable_rootport(rpc);

/*** aer_probe - initialize resources* @dev: pointer to the pcie_dev data structure** Invoked when PCI Express bus loads AER service driver.*/
static int aer_probe(struct pcie_device *dev)
{int status;struct aer_rpc *rpc;struct device *device = &dev->device;/* Alloc rpc data structure */rpc = aer_alloc_rpc(dev);if (!rpc) {dev_printk(KERN_DEBUG, device, "alloc rpc failed\n");aer_remove(dev);return -ENOMEM;}/* Request IRQ ISR */status = request_irq(dev->irq, aer_irq, IRQF_SHARED, "aerdrv", dev);if (status) {dev_printk(KERN_DEBUG, device, "request IRQ failed\n");aer_remove(dev);return status;}rpc->isr = 1;aer_enable_rootport(rpc);return status;
}

这里的中断向量dev->irq，是pcie port驱动初始化时已经申请好了可能是lagecy的或者是MSI/MSIx，AER只需要再注册一个share中断上去。

看一下aer_enable_rootport，先清楚了所有device的状态位，再把上下游设备的错误上报全部使能。

/*** 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, &reg16);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 = pdev->aer_cap;/* Clear error status */pci_read_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, &reg32);pci_write_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, reg32);pci_read_config_dword(pdev, aer_pos + PCI_ERR_COR_STATUS, &reg32);pci_write_config_dword(pdev, aer_pos + PCI_ERR_COR_STATUS, reg32);pci_read_config_dword(pdev, aer_pos + PCI_ERR_UNCOR_STATUS, &reg32);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, &reg32);reg32 |= ROOT_PORT_INTR_ON_MESG_MASK;pci_write_config_dword(pdev, aer_pos + PCI_ERR_ROOT_COMMAND, reg32);
}

2.2 中断处理

AER中断分为上下半部，上半部aer_irq：

irqreturn_t aer_irq(int irq, void *context)
{unsigned int status, id;struct pcie_device *pdev = (struct pcie_device *)context;struct aer_rpc *rpc = get_service_data(pdev);int next_prod_idx;unsigned long flags;int pos;pos = pdev->port->aer_cap;/** Must lock access to Root Error Status Reg, Root Error ID Reg,* and Root error producer/consumer index*/spin_lock_irqsave(&rpc->e_lock, flags);/* Read error status */pci_read_config_dword(pdev->port, pos + PCI_ERR_ROOT_STATUS, &status);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_ERR_SRC, &id);pci_write_config_dword(pdev->port, pos + PCI_ERR_ROOT_STATUS, status);/* Store error source for later DPC handler */next_prod_idx = rpc->prod_idx + 1;if (next_prod_idx == AER_ERROR_SOURCES_MAX)next_prod_idx = 0;if (next_prod_idx == rpc->cons_idx) {/** Error Storm Condition - possibly the same error occurred.* Drop the error.*/spin_unlock_irqrestore(&rpc->e_lock, flags);return IRQ_HANDLED;}rpc->e_sources[rpc->prod_idx].status =  status;rpc->e_sources[rpc->prod_idx].id = id;rpc->prod_idx = next_prod_idx;spin_unlock_irqrestore(&rpc->e_lock, flags);/*  Invoke DPC handler */schedule_work(&rpc->dpc_handler);return IRQ_HANDLED;
}

irq中首先读取 Root Error Status Register，看看是不是有错误产生了。（PCI_ERR_ROOT_STATUS）

获取错误源ID，Error Source Identification Register，PCI_ERR_ROOT_ERR_SRC

并保存在rpc->e_sources数组里面。

中断处理下半部 ：aer_isr，这是一个worker

/*** aer_isr - consume errors detected by root port* @work: definition of this work item** Invoked, as DPC, when root port records new detected error*/
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);mutex_unlock(&rpc->rpc_mutex);
}

把刚才上半部保存在rpc->e_sources里面的错误源取出来，一个一个调用aer_isr_one_error进行处理

/*** aer_isr_one_error - consume an error detected by root port* @p_device: pointer to error root port service device* @e_src: pointer to an error source*/
static void aer_isr_one_error(struct pcie_device *p_device,struct aer_err_source *e_src)
{struct aer_rpc *rpc = get_service_data(p_device);struct aer_err_info *e_info = &rpc->e_info;/** There is a possibility that both correctable error and* uncorrectable error being logged. Report correctable error first.*/if (e_src->status & PCI_ERR_ROOT_COR_RCV) {e_info->id = ERR_COR_ID(e_src->id);e_info->severity = AER_CORRECTABLE;if (e_src->status & PCI_ERR_ROOT_MULTI_COR_RCV)e_info->multi_error_valid = 1;elsee_info->multi_error_valid = 0;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;elsee_info->severity = AER_NONFATAL;if (e_src->status & PCI_ERR_ROOT_MULTI_UNCOR_RCV)e_info->multi_error_valid = 1;elsee_info->multi_error_valid = 0;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);}
}

aer_isr_one_error就是处理错误的具体实现了，这里按照AER的不同类型进行错误报告或者恢复处理。