| blob | 678189280bb409f2590d962aba784b4768eee003 |
3 PCI Bus EEH Error Recovery
4 --------------------------
5 Linas Vepstas
6 <linas@austin.ibm.com>
7 12 January 2005
10 Overview:
11 ---------
12 The IBM POWER-based pSeries and iSeries computers include PCI bus
13 controller chips that have extended capabilities for detecting and
14 reporting a large variety of PCI bus error conditions. These features
15 go under the name of "EEH", for "Enhanced Error Handling". The EEH
16 hardware features allow PCI bus errors to be cleared and a PCI
17 card to be "rebooted", without also having to reboot the operating
18 system.
20 This is in contrast to traditional PCI error handling, where the
21 PCI chip is wired directly to the CPU, and an error would cause
22 a CPU machine-check/check-stop condition, halting the CPU entirely.
23 Another "traditional" technique is to ignore such errors, which
24 can lead to data corruption, both of user data or of kernel data,
25 hung/unresponsive adapters, or system crashes/lockups. Thus,
26 the idea behind EEH is that the operating system can become more
27 reliable and robust by protecting it from PCI errors, and giving
28 the OS the ability to "reboot"/recover individual PCI devices.
30 Future systems from other vendors, based on the PCI-E specification,
31 may contain similar features.
34 Causes of EEH Errors
35 --------------------
36 EEH was originally designed to guard against hardware failure, such
37 as PCI cards dying from heat, humidity, dust, vibration and bad
38 electrical connections. The vast majority of EEH errors seen in
39 "real life" are due to either poorly seated PCI cards, or,
40 unfortunately quite commonly, due to device driver bugs, device firmware
41 bugs, and sometimes PCI card hardware bugs.
43 The most common software bug, is one that causes the device to
44 attempt to DMA to a location in system memory that has not been
45 reserved for DMA access for that card. This is a powerful feature,
46 as it prevents what; otherwise, would have been silent memory
47 corruption caused by the bad DMA. A number of device driver
48 bugs have been found and fixed in this way over the past few
49 years. Other possible causes of EEH errors include data or
50 address line parity errors (for example, due to poor electrical
51 connectivity due to a poorly seated card), and PCI-X split-completion
52 errors (due to software, device firmware, or device PCI hardware bugs).
53 The vast majority of "true hardware failures" can be cured by
54 physically removing and re-seating the PCI card.
57 Detection and Recovery
58 ----------------------
59 In the following discussion, a generic overview of how to detect
60 and recover from EEH errors will be presented. This is followed
61 by an overview of how the current implementation in the Linux
62 kernel does it. The actual implementation is subject to change,
63 and some of the finer points are still being debated. These
64 may in turn be swayed if or when other architectures implement
65 similar functionality.
67 When a PCI Host Bridge (PHB, the bus controller connecting the
68 PCI bus to the system CPU electronics complex) detects a PCI error
69 condition, it will "isolate" the affected PCI card. Isolation
70 will block all writes (either to the card from the system, or
71 from the card to the system), and it will cause all reads to
72 return all-ff's (0xff, 0xffff, 0xffffffff for 8/16/32-bit reads).
73 This value was chosen because it is the same value you would
74 get if the device was physically unplugged from the slot.
75 This includes access to PCI memory, I/O space, and PCI config
76 space. Interrupts; however, will continued to be delivered.
78 Detection and recovery are performed with the aid of ppc64
79 firmware. The programming interfaces in the Linux kernel
80 into the firmware are referred to as RTAS (Run-Time Abstraction
81 Services). The Linux kernel does not (should not) access
82 the EEH function in the PCI chipsets directly, primarily because
83 there are a number of different chipsets out there, each with
84 different interfaces and quirks. The firmware provides a
85 uniform abstraction layer that will work with all pSeries
86 and iSeries hardware (and be forwards-compatible).
88 If the OS or device driver suspects that a PCI slot has been
89 EEH-isolated, there is a firmware call it can make to determine if
90 this is the case. If so, then the device driver should put itself
91 into a consistent state (given that it won't be able to complete any
92 pending work) and start recovery of the card. Recovery normally
93 would consist of resetting the PCI device (holding the PCI #RST
94 line high for two seconds), followed by setting up the device
95 config space (the base address registers (BAR's), latency timer,
96 cache line size, interrupt line, and so on). This is followed by a
97 reinitialization of the device driver. In a worst-case scenario,
98 the power to the card can be toggled, at least on hot-plug-capable
99 slots. In principle, layers far above the device driver probably
100 do not need to know that the PCI card has been "rebooted" in this
101 way; ideally, there should be at most a pause in Ethernet/disk/USB
102 I/O while the card is being reset.
104 If the card cannot be recovered after three or four resets, the
105 kernel/device driver should assume the worst-case scenario, that the
106 card has died completely, and report this error to the sysadmin.
107 In addition, error messages are reported through RTAS and also through
108 syslogd (/var/log/messages) to alert the sysadmin of PCI resets.
109 The correct way to deal with failed adapters is to use the standard
110 PCI hotplug tools to remove and replace the dead card.
113 Current PPC64 Linux EEH Implementation
114 --------------------------------------
115 At this time, a generic EEH recovery mechanism has been implemented,
116 so that individual device drivers do not need to be modified to support
117 EEH recovery. This generic mechanism piggy-backs on the PCI hotplug
118 infrastructure, and percolates events up through the userspace/udev
119 infrastructure. Following is a detailed description of how this is
120 accomplished.
122 EEH must be enabled in the PHB's very early during the boot process,
123 and if a PCI slot is hot-plugged. The former is performed by
124 eeh_init() in arch/powerpc/platforms/pseries/eeh.c, and the later by
125 drivers/pci/hotplug/pSeries_pci.c calling in to the eeh.c code.
126 EEH must be enabled before a PCI scan of the device can proceed.
127 Current Power5 hardware will not work unless EEH is enabled;
128 although older Power4 can run with it disabled. Effectively,
129 EEH can no longer be turned off. PCI devices *must* be
130 registered with the EEH code; the EEH code needs to know about
131 the I/O address ranges of the PCI device in order to detect an
132 error. Given an arbitrary address, the routine
133 pci_get_device_by_addr() will find the pci device associated
134 with that address (if any).
136 The default arch/powerpc/include/asm/io.h macros readb(), inb(), insb(),
137 etc. include a check to see if the i/o read returned all-0xff's.
138 If so, these make a call to eeh_dn_check_failure(), which in turn
139 asks the firmware if the all-ff's value is the sign of a true EEH
140 error. If it is not, processing continues as normal. The grand
141 total number of these false alarms or "false positives" can be
142 seen in /proc/ppc64/eeh (subject to change). Normally, almost
143 all of these occur during boot, when the PCI bus is scanned, where
144 a large number of 0xff reads are part of the bus scan procedure.
146 If a frozen slot is detected, code in
147 arch/powerpc/platforms/pseries/eeh.c will print a stack trace to
148 syslog (/var/log/messages). This stack trace has proven to be very
149 useful to device-driver authors for finding out at what point the EEH
150 error was detected, as the error itself usually occurs slightly
151 beforehand.
153 Next, it uses the Linux kernel notifier chain/work queue mechanism to
154 allow any interested parties to find out about the failure. Device
155 drivers, or other parts of the kernel, can use
156 eeh_register_notifier(struct notifier_block *) to find out about EEH
157 events. The event will include a pointer to the pci device, the
158 device node and some state info. Receivers of the event can "do as
159 they wish"; the default handler will be described further in this
160 section.
162 To assist in the recovery of the device, eeh.c exports the
163 following functions:
165 rtas_set_slot_reset() -- assert the PCI #RST line for 1/8th of a second
166 rtas_configure_bridge() -- ask firmware to configure any PCI bridges
167 located topologically under the pci slot.
168 eeh_save_bars() and eeh_restore_bars(): save and restore the PCI
169 config-space info for a device and any devices under it.
172 A handler for the EEH notifier_block events is implemented in
173 drivers/pci/hotplug/pSeries_pci.c, called handle_eeh_events().
174 It saves the device BAR's and then calls rpaphp_unconfig_pci_adapter().
175 This last call causes the device driver for the card to be stopped,
176 which causes uevents to go out to user space. This triggers
177 user-space scripts that might issue commands such as "ifdown eth0"
178 for ethernet cards, and so on. This handler then sleeps for 5 seconds,
179 hoping to give the user-space scripts enough time to complete.
180 It then resets the PCI card, reconfigures the device BAR's, and
181 any bridges underneath. It then calls rpaphp_enable_pci_slot(),
182 which restarts the device driver and triggers more user-space
183 events (for example, calling "ifup eth0" for ethernet cards).
186 Device Shutdown and User-Space Events
187 -------------------------------------
188 This section documents what happens when a pci slot is unconfigured,
189 focusing on how the device driver gets shut down, and on how the
190 events get delivered to user-space scripts.
192 Following is an example sequence of events that cause a device driver
193 close function to be called during the first phase of an EEH reset.
194 The following sequence is an example of the pcnet32 device driver.
196 rpa_php_unconfig_pci_adapter (struct slot *) // in rpaphp_pci.c
197 {
198 calls
199 pci_remove_bus_device (struct pci_dev *) // in /drivers/pci/remove.c
200 {
201 calls
202 pci_destroy_dev (struct pci_dev *)
203 {
204 calls
205 device_unregister (&dev->dev) // in /drivers/base/core.c
206 {
207 calls
208 device_del (struct device *)
209 {
210 calls
211 bus_remove_device() // in /drivers/base/bus.c
212 {
213 calls
214 device_release_driver()
215 {
216 calls
217 struct device_driver->remove() which is just
218 pci_device_remove() // in /drivers/pci/pci_driver.c
219 {
220 calls
221 struct pci_driver->remove() which is just
222 pcnet32_remove_one() // in /drivers/net/pcnet32.c
223 {
224 calls
225 unregister_netdev() // in /net/core/dev.c
226 {
227 calls
228 dev_close() // in /net/core/dev.c
229 {
230 calls dev->stop();
231 which is just pcnet32_close() // in pcnet32.c
232 {
233 which does what you wanted
234 to stop the device
235 }
236 }
237 }
238 which
239 frees pcnet32 device driver memory
240 }
241 }}}}}}
244 in drivers/pci/pci_driver.c,
245 struct device_driver->remove() is just pci_device_remove()
246 which calls struct pci_driver->remove() which is pcnet32_remove_one()
247 which calls unregister_netdev() (in net/core/dev.c)
248 which calls dev_close() (in net/core/dev.c)
249 which calls dev->stop() which is pcnet32_close()
250 which then does the appropriate shutdown.
252 ---
253 Following is the analogous stack trace for events sent to user-space
254 when the pci device is unconfigured.
256 rpa_php_unconfig_pci_adapter() { // in rpaphp_pci.c
257 calls
258 pci_remove_bus_device (struct pci_dev *) { // in /drivers/pci/remove.c
259 calls
260 pci_destroy_dev (struct pci_dev *) {
261 calls
262 device_unregister (&dev->dev) { // in /drivers/base/core.c
263 calls
264 device_del(struct device * dev) { // in /drivers/base/core.c
265 calls
266 kobject_del() { //in /libs/kobject.c
267 calls
268 kobject_uevent() { // in /libs/kobject.c
269 calls
270 kset_uevent() { // in /lib/kobject.c
271 calls
272 kset->uevent_ops->uevent() // which is really just
273 a call to
274 dev_uevent() { // in /drivers/base/core.c
275 calls
276 dev->bus->uevent() which is really just a call to
277 pci_uevent () { // in drivers/pci/hotplug.c
278 which prints device name, etc....
279 }
280 }
281 then kobject_uevent() sends a netlink uevent to userspace
282 --> userspace uevent
283 (during early boot, nobody listens to netlink events and
284 kobject_uevent() executes uevent_helper[], which runs the
285 event process /sbin/hotplug)
286 }
287 }
288 kobject_del() then calls sysfs_remove_dir(), which would
289 trigger any user-space daemon that was watching /sysfs,
290 and notice the delete event.
293 Pro's and Con's of the Current Design
294 -------------------------------------
295 There are several issues with the current EEH software recovery design,
296 which may be addressed in future revisions. But first, note that the
297 big plus of the current design is that no changes need to be made to
298 individual device drivers, so that the current design throws a wide net.
299 The biggest negative of the design is that it potentially disturbs
300 network daemons and file systems that didn't need to be disturbed.
302 -- A minor complaint is that resetting the network card causes
303 user-space back-to-back ifdown/ifup burps that potentially disturb
304 network daemons, that didn't need to even know that the pci
305 card was being rebooted.
307 -- A more serious concern is that the same reset, for SCSI devices,
308 causes havoc to mounted file systems. Scripts cannot post-facto
309 unmount a file system without flushing pending buffers, but this
310 is impossible, because I/O has already been stopped. Thus,
311 ideally, the reset should happen at or below the block layer,
312 so that the file systems are not disturbed.
314 Reiserfs does not tolerate errors returned from the block device.
315 Ext3fs seems to be tolerant, retrying reads/writes until it does
316 succeed. Both have been only lightly tested in this scenario.
318 The SCSI-generic subsystem already has built-in code for performing
319 SCSI device resets, SCSI bus resets, and SCSI host-bus-adapter
320 (HBA) resets. These are cascaded into a chain of attempted
321 resets if a SCSI command fails. These are completely hidden
322 from the block layer. It would be very natural to add an EEH
323 reset into this chain of events.
325 -- If a SCSI error occurs for the root device, all is lost unless
326 the sysadmin had the foresight to run /bin, /sbin, /etc, /var
327 and so on, out of ramdisk/tmpfs.
330 Conclusions
331 -----------
332 There's forward progress ...