1 The PCI Express Advanced Error Reporting Driver Guide HOWTO
2 T. Long Nguyen <tom.l.nguyen@intel.com>
3 Yanmin Zhang <yanmin.zhang@intel.com>
11 This guide describes the basics of the PCI Express Advanced Error
12 Reporting (AER) driver and provides information on how to use it, as
13 well as how to enable the drivers of endpoint devices to conform with
14 PCI Express AER driver.
16 1.2 Copyright (C) Intel Corporation 2006.
18 1.3 What is the PCI Express AER Driver?
20 PCI Express error signaling can occur on the PCI Express link itself
21 or on behalf of transactions initiated on the link. PCI Express
22 defines two error reporting paradigms: the baseline capability and
23 the Advanced Error Reporting capability. The baseline capability is
24 required of all PCI Express components providing a minimum defined
25 set of error reporting requirements. Advanced Error Reporting
26 capability is implemented with a PCI Express advanced error reporting
27 extended capability structure providing more robust error reporting.
29 The PCI Express AER driver provides the infrastructure to support PCI
30 Express Advanced Error Reporting capability. The PCI Express AER
31 driver provides three basic functions:
33 - Gathers the comprehensive error information if errors occurred.
34 - Reports error to the users.
35 - Performs error recovery actions.
37 AER driver only attaches root ports which support PCI-Express AER
43 2.1 Include the PCI Express AER Root Driver into the Linux Kernel
45 The PCI Express AER Root driver is a Root Port service driver attached
46 to the PCI Express Port Bus driver. If a user wants to use it, the driver
47 has to be compiled. Option CONFIG_PCIEAER supports this capability. It
48 depends on CONFIG_PCIEPORTBUS, so pls. set CONFIG_PCIEPORTBUS=y and
51 2.2 Load PCI Express AER Root Driver
53 Some systems have AER support in firmware. Enabling Linux AER support at
54 the same time the firmware handles AER may result in unpredictable
55 behavior. Therefore, Linux does not handle AER events unless the firmware
56 grants AER control to the OS via the ACPI _OSC method. See the PCI FW 3.0
57 Specification for details regarding _OSC usage.
61 When a PCIe AER error is captured, an error message will be output to
62 console. If it's a correctable error, it is output as a warning.
63 Otherwise, it is printed as an error. So users could choose different
64 log level to filter out correctable error messages.
66 Below shows an example:
67 0000:50:00.0: PCIe Bus Error: severity=Uncorrected (Fatal), type=Transaction Layer, id=0500(Requester ID)
68 0000:50:00.0: device [8086:0329] error status/mask=00100000/00000000
69 0000:50:00.0: [20] Unsupported Request (First)
70 0000:50:00.0: TLP Header: 04000001 00200a03 05010000 00050100
72 In the example, 'Requester ID' means the ID of the device who sends
73 the error message to root port. Pls. refer to pci express specs for
79 To enable AER aware support requires a software driver to configure
80 the AER capability structure within its device and to provide callbacks.
82 To support AER better, developers need understand how AER does work
85 PCI Express errors are classified into two types: correctable errors
86 and uncorrectable errors. This classification is based on the impacts
87 of those errors, which may result in degraded performance or function
90 Correctable errors pose no impacts on the functionality of the
91 interface. The PCI Express protocol can recover without any software
92 intervention or any loss of data. These errors are detected and
93 corrected by hardware. Unlike correctable errors, uncorrectable
94 errors impact functionality of the interface. Uncorrectable errors
95 can cause a particular transaction or a particular PCI Express link
96 to be unreliable. Depending on those error conditions, uncorrectable
97 errors are further classified into non-fatal errors and fatal errors.
98 Non-fatal errors cause the particular transaction to be unreliable,
99 but the PCI Express link itself is fully functional. Fatal errors, on
100 the other hand, cause the link to be unreliable.
102 When AER is enabled, a PCI Express device will automatically send an
103 error message to the PCIe root port above it when the device captures
104 an error. The Root Port, upon receiving an error reporting message,
105 internally processes and logs the error message in its PCI Express
106 capability structure. Error information being logged includes storing
107 the error reporting agent's requestor ID into the Error Source
108 Identification Registers and setting the error bits of the Root Error
109 Status Register accordingly. If AER error reporting is enabled in Root
110 Error Command Register, the Root Port generates an interrupt if an
113 Note that the errors as described above are related to the PCI Express
114 hierarchy and links. These errors do not include any device specific
115 errors because device specific errors will still get sent directly to
118 3.1 Configure the AER capability structure
120 AER aware drivers of PCI Express component need change the device
121 control registers to enable AER. They also could change AER registers,
122 including mask and severity registers. Helper function
123 pci_enable_pcie_error_reporting could be used to enable AER. See
126 3.2. Provide callbacks
128 3.2.1 callback reset_link to reset pci express link
130 This callback is used to reset the pci express physical link when a
131 fatal error happens. The root port aer service driver provides a
132 default reset_link function, but different upstream ports might
133 have different specifications to reset pci express link, so all
134 upstream ports should provide their own reset_link functions.
136 In struct pcie_port_service_driver, a new pointer, reset_link, is
139 pci_ers_result_t (*reset_link) (struct pci_dev *dev);
141 Section 3.2.2.2 provides more detailed info on when to call
144 3.2.2 PCI error-recovery callbacks
146 The PCI Express AER Root driver uses error callbacks to coordinate
147 with downstream device drivers associated with a hierarchy in question
148 when performing error recovery actions.
150 Data struct pci_driver has a pointer, err_handler, to point to
151 pci_error_handlers who consists of a couple of callback function
152 pointers. AER driver follows the rules defined in
153 pci-error-recovery.txt except pci express specific parts (e.g.
154 reset_link). Pls. refer to pci-error-recovery.txt for detailed
155 definitions of the callbacks.
157 Below sections specify when to call the error callback functions.
159 3.2.2.1 Correctable errors
161 Correctable errors pose no impacts on the functionality of
162 the interface. The PCI Express protocol can recover without any
163 software intervention or any loss of data. These errors do not
164 require any recovery actions. The AER driver clears the device's
165 correctable error status register accordingly and logs these errors.
167 3.2.2.2 Non-correctable (non-fatal and fatal) errors
169 If an error message indicates a non-fatal error, performing link reset
170 at upstream is not required. The AER driver calls error_detected(dev,
171 pci_channel_io_normal) to all drivers associated within a hierarchy in
172 question. for example,
173 EndPoint<==>DownstreamPort B<==>UpstreamPort A<==>RootPort.
174 If Upstream port A captures an AER error, the hierarchy consists of
175 Downstream port B and EndPoint.
177 A driver may return PCI_ERS_RESULT_CAN_RECOVER,
178 PCI_ERS_RESULT_DISCONNECT, or PCI_ERS_RESULT_NEED_RESET, depending on
179 whether it can recover or the AER driver calls mmio_enabled as next.
181 If an error message indicates a fatal error, kernel will broadcast
182 error_detected(dev, pci_channel_io_frozen) to all drivers within
183 a hierarchy in question. Then, performing link reset at upstream is
184 necessary. As different kinds of devices might use different approaches
185 to reset link, AER port service driver is required to provide the
186 function to reset link. Firstly, kernel looks for if the upstream
187 component has an aer driver. If it has, kernel uses the reset_link
188 callback of the aer driver. If the upstream component has no aer driver
189 and the port is downstream port, we will perform a hot reset as the
190 default by setting the Secondary Bus Reset bit of the Bridge Control
191 register associated with the downstream port. As for upstream ports,
192 they should provide their own aer service drivers with reset_link
193 function. If error_detected returns PCI_ERS_RESULT_CAN_RECOVER and
194 reset_link returns PCI_ERS_RESULT_RECOVERED, the error handling goes
199 3.3.1 int pci_enable_pcie_error_reporting(struct pci_dev *dev);
200 pci_enable_pcie_error_reporting enables the device to send error
201 messages to root port when an error is detected. Note that devices
202 don't enable the error reporting by default, so device drivers need
203 call this function to enable it.
205 3.3.2 int pci_disable_pcie_error_reporting(struct pci_dev *dev);
206 pci_disable_pcie_error_reporting disables the device to send error
207 messages to root port when an error is detected.
209 3.3.3 int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev);
210 pci_cleanup_aer_uncorrect_error_status cleanups the uncorrectable
211 error status register.
213 3.4 Frequent Asked Questions
215 Q: What happens if a PCI Express device driver does not provide an
216 error recovery handler (pci_driver->err_handler is equal to NULL)?
218 A: The devices attached with the driver won't be recovered. If the
219 error is fatal, kernel will print out warning messages. Please refer
220 to section 3 for more information.
222 Q: What happens if an upstream port service driver does not provide
225 A: Fatal error recovery will fail if the errors are reported by the
226 upstream ports who are attached by the service driver.
228 Q: How does this infrastructure deal with driver that is not PCI
231 A: This infrastructure calls the error callback functions of the
232 driver when an error happens. But if the driver is not aware of
233 PCI Express, the device might not report its own errors to root
236 Q: What modifications will that driver need to make it compatible
237 with the PCI Express AER Root driver?
239 A: It could call the helper functions to enable AER in devices and
240 cleanup uncorrectable status register. Pls. refer to section 3.3.
243 4. Software error injection
245 Debugging PCIe AER error recovery code is quite difficult because it
246 is hard to trigger real hardware errors. Software based error
247 injection can be used to fake various kinds of PCIe errors.
249 First you should enable PCIe AER software error injection in kernel
250 configuration, that is, following item should be in your .config.
252 CONFIG_PCIEAER_INJECT=y or CONFIG_PCIEAER_INJECT=m
254 After reboot with new kernel or insert the module, a device file named
255 /dev/aer_inject should be created.
257 Then, you need a user space tool named aer-inject, which can be gotten
259 http://www.kernel.org/pub/linux/utils/pci/aer-inject/
261 More information about aer-inject can be found in the document comes
262 with its source code.