aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/platforms/pseries/eeh_driver.c
blob: 68ea5eee39a832ddd054b9fe36d78d301f884f67 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
/*
 * PCI Error Recovery Driver for RPA-compliant PPC64 platform.
 * Copyright IBM Corp. 2004 2005
 * Copyright Linas Vepstas <linas@linas.org> 2004, 2005
 *
 * All rights reserved.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or (at
 * your option) any later version.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
 * NON INFRINGEMENT.  See the GNU General Public License for more
 * details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 *
 * Send comments and feedback to Linas Vepstas <linas@austin.ibm.com>
 */
#include <linux/delay.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/pci.h>
#include <asm/eeh.h>
#include <asm/eeh_event.h>
#include <asm/ppc-pci.h>
#include <asm/pci-bridge.h>
#include <asm/prom.h>
#include <asm/rtas.h>


static inline const char * pcid_name (struct pci_dev *pdev)
{
	if (pdev && pdev->dev.driver)
		return pdev->dev.driver->name;
	return "";
}

#ifdef DEBUG
static void print_device_node_tree (struct pci_dn *pdn, int dent)
{
	int i;
	if (!pdn) return;
	for (i=0;i<dent; i++)
		printk(" ");
	printk("dn=%s mode=%x \tcfg_addr=%x pe_addr=%x \tfull=%s\n",
		pdn->node->name, pdn->eeh_mode, pdn->eeh_config_addr,
		pdn->eeh_pe_config_addr, pdn->node->full_name);
	dent += 3;
	struct device_node *pc = pdn->node->child;
	while (pc) {
		print_device_node_tree(PCI_DN(pc), dent);
		pc = pc->sibling;
	}
}
#endif

/** 
 * irq_in_use - return true if this irq is being used 
 */
static int irq_in_use(unsigned int irq)
{
	int rc = 0;
	unsigned long flags;
   struct irq_desc *desc = irq_desc + irq;

	spin_lock_irqsave(&desc->lock, flags);
	if (desc->action)
		rc = 1;
	spin_unlock_irqrestore(&desc->lock, flags);
	return rc;
}

/* ------------------------------------------------------- */
/**
 * eeh_report_error - report pci error to each device driver
 * 
 * Report an EEH error to each device driver, collect up and 
 * merge the device driver responses. Cumulative response 
 * passed back in "userdata".
 */

static void eeh_report_error(struct pci_dev *dev, void *userdata)
{
	enum pci_ers_result rc, *res = userdata;
	struct pci_driver *driver = dev->driver;

	dev->error_state = pci_channel_io_frozen;

	if (!driver)
		return;

	if (irq_in_use (dev->irq)) {
		struct device_node *dn = pci_device_to_OF_node(dev);
		PCI_DN(dn)->eeh_mode |= EEH_MODE_IRQ_DISABLED;
		disable_irq_nosync(dev->irq);
	}
	if (!driver->err_handler ||
	    !driver->err_handler->error_detected)
		return;

	rc = driver->err_handler->error_detected (dev, pci_channel_io_frozen);

	/* A driver that needs a reset trumps all others */
	if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
	if (*res == PCI_ERS_RESULT_NONE) *res = rc;
}

/**
 * eeh_report_mmio_enabled - tell drivers that MMIO has been enabled
 *
 * Tells each device driver that IO ports, MMIO and config space I/O
 * are now enabled. Collects up and merges the device driver responses.
 * Cumulative response passed back in "userdata".
 */

static void eeh_report_mmio_enabled(struct pci_dev *dev, void *userdata)
{
	enum pci_ers_result rc, *res = userdata;
	struct pci_driver *driver = dev->driver;

	if (!driver ||
	    !driver->err_handler ||
	    !driver->err_handler->mmio_enabled)
		return;

	rc = driver->err_handler->mmio_enabled (dev);

	/* A driver that needs a reset trumps all others */
	if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
	if (*res == PCI_ERS_RESULT_NONE) *res = rc;
}

/**
 * eeh_report_reset - tell device that slot has been reset
 */

static void eeh_report_reset(struct pci_dev *dev, void *userdata)
{
	enum pci_ers_result rc, *res = userdata;
	struct pci_driver *driver = dev->driver;
	struct device_node *dn = pci_device_to_OF_node(dev);

	if (!driver)
		return;

	if ((PCI_DN(dn)->eeh_mode) & EEH_MODE_IRQ_DISABLED) {
		PCI_DN(dn)->eeh_mode &= ~EEH_MODE_IRQ_DISABLED;
		enable_irq(dev->irq);
	}
	if (!driver->err_handler ||
	    !driver->err_handler->slot_reset)
		return;

	rc = driver->err_handler->slot_reset(dev);
	if ((*res == PCI_ERS_RESULT_NONE) ||
	    (*res == PCI_ERS_RESULT_RECOVERED)) *res = rc;
	if (*res == PCI_ERS_RESULT_DISCONNECT &&
	     rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
}

/**
 * eeh_report_resume - tell device to resume normal operations
 */

static void eeh_report_resume(struct pci_dev *dev, void *userdata)
{
	struct pci_driver *driver = dev->driver;
	struct device_node *dn = pci_device_to_OF_node(dev);

	dev->error_state = pci_channel_io_normal;

	if (!driver)
		return;

	if ((PCI_DN(dn)->eeh_mode) & EEH_MODE_IRQ_DISABLED) {
		PCI_DN(dn)->eeh_mode &= ~EEH_MODE_IRQ_DISABLED;
		enable_irq(dev->irq);
	}
	if (!driver->err_handler ||
	    !driver->err_handler->resume)
		return;

	driver->err_handler->resume(dev);
}

/**
 * eeh_report_failure - tell device driver that device is dead.
 *
 * This informs the device driver that the device is permanently
 * dead, and that no further recovery attempts will be made on it.
 */

static void eeh_report_failure(struct pci_dev *dev, void *userdata)
{
	struct pci_driver *driver = dev->driver;

	dev->error_state = pci_channel_io_perm_failure;

	if (!driver)
		return;

	if (irq_in_use (dev->irq)) {
		struct device_node *dn = pci_device_to_OF_node(dev);
		PCI_DN(dn)->eeh_mode |= EEH_MODE_IRQ_DISABLED;
		disable_irq_nosync(dev->irq);
	}
	if (!driver->err_handler)
		return;
	if (!driver->err_handler->error_detected)
		return;
	driver->err_handler->error_detected(dev, pci_channel_io_perm_failure);
}

/* ------------------------------------------------------- */
/**
 * handle_eeh_events -- reset a PCI device after hard lockup.
 *
 * pSeries systems will isolate a PCI slot if the PCI-Host
 * bridge detects address or data parity errors, DMA's
 * occurring to wild addresses (which usually happen due to
 * bugs in device drivers or in PCI adapter firmware).
 * Slot isolations also occur if #SERR, #PERR or other misc
 * PCI-related errors are detected.
 *
 * Recovery process consists of unplugging the device driver
 * (which generated hotplug events to userspace), then issuing
 * a PCI #RST to the device, then reconfiguring the PCI config
 * space for all bridges & devices under this slot, and then
 * finally restarting the device drivers (which cause a second
 * set of hotplug events to go out to userspace).
 */

/**
 * eeh_reset_device() -- perform actual reset of a pci slot
 * @bus: pointer to the pci bus structure corresponding
 *            to the isolated slot. A non-null value will
 *            cause all devices under the bus to be removed
 *            and then re-added.
 * @pe_dn: pointer to a "Partionable Endpoint" device node.
 *            This is the top-level structure on which pci
 *            bus resets can be performed.
 */

static int eeh_reset_device (struct pci_dn *pe_dn, struct pci_bus *bus)
{
	struct device_node *dn;
	int cnt, rc;

	/* pcibios will clear the counter; save the value */
	cnt = pe_dn->eeh_freeze_count;

	if (bus)
		pcibios_remove_pci_devices(bus);

	/* Reset the pci controller. (Asserts RST#; resets config space).
	 * Reconfigure bridges and devices. Don't try to bring the system
	 * up if the reset failed for some reason. */
	rc = rtas_set_slot_reset(pe_dn);
	if (rc)
		return rc;

	/* Walk over all functions on this device.  */
	dn = pe_dn->node;
	if (!pcibios_find_pci_bus(dn) && PCI_DN(dn->parent))
		dn = dn->parent->child;

	while (dn) {
		struct pci_dn *ppe = PCI_DN(dn);
		/* On Power4, always true because eeh_pe_config_addr=0 */
		if (pe_dn->eeh_pe_config_addr == ppe->eeh_pe_config_addr) {
			rtas_configure_bridge(ppe);
			eeh_restore_bars(ppe);
 		}
		dn = dn->sibling;
	}

	/* Give the system 5 seconds to finish running the user-space
	 * hotplug shutdown scripts, e.g. ifdown for ethernet.  Yes, 
	 * this is a hack, but if we don't do this, and try to bring 
	 * the device up before the scripts have taken it down, 
	 * potentially weird things happen.
	 */
	if (bus) {
		ssleep (5);
		pcibios_add_pci_devices(bus);
	}
	pe_dn->eeh_freeze_count = cnt;

	return 0;
}

/* The longest amount of time to wait for a pci device
 * to come back on line, in seconds.
 */
#define MAX_WAIT_FOR_RECOVERY 150

struct pci_dn * handle_eeh_events (struct eeh_event *event)
{
	struct device_node *frozen_dn;
	struct pci_dn *frozen_pdn;
	struct pci_bus *frozen_bus;
	int rc = 0;
	enum pci_ers_result result = PCI_ERS_RESULT_NONE;
	const char *location, *pci_str, *drv_str;

	frozen_dn = find_device_pe(event->dn);
	if (!frozen_dn) {

		location = of_get_property(event->dn, "ibm,loc-code", NULL);
		location = location ? location : "unknown";
		printk(KERN_ERR "EEH: Error: Cannot find partition endpoint "
		                "for location=%s pci addr=%s\n",
		        location, pci_name(event->dev));
		return NULL;
	}

	frozen_bus = pcibios_find_pci_bus(frozen_dn);
	location = of_get_property(frozen_dn, "ibm,loc-code", NULL);
	location = location ? location : "unknown";

	/* There are two different styles for coming up with the PE.
	 * In the old style, it was the highest EEH-capable device
	 * which was always an EADS pci bridge.  In the new style,
	 * there might not be any EADS bridges, and even when there are,
	 * the firmware marks them as "EEH incapable". So another
	 * two-step is needed to find the pci bus.. */
	if (!frozen_bus)
		frozen_bus = pcibios_find_pci_bus (frozen_dn->parent);

	if (!frozen_bus) {
		printk(KERN_ERR "EEH: Cannot find PCI bus "
		        "for location=%s dn=%s\n",
		        location, frozen_dn->full_name);
		return NULL;
	}

	frozen_pdn = PCI_DN(frozen_dn);
	frozen_pdn->eeh_freeze_count++;

	if (frozen_pdn->pcidev) {
		pci_str = pci_name (frozen_pdn->pcidev);
		drv_str = pcid_name (frozen_pdn->pcidev);
	} else {
		pci_str = pci_name (event->dev);
		drv_str = pcid_name (event->dev);
	}
	
	if (frozen_pdn->eeh_freeze_count > EEH_MAX_ALLOWED_FREEZES)
		goto excess_failures;

	printk(KERN_WARNING
	   "EEH: This PCI device has failed %d times in the last hour:\n",
		frozen_pdn->eeh_freeze_count);
	printk(KERN_WARNING
		"EEH: location=%s driver=%s pci addr=%s\n",
		location, drv_str, pci_str);

	/* Walk the various device drivers attached to this slot through
	 * a reset sequence, giving each an opportunity to do what it needs
	 * to accomplish the reset.  Each child gets a report of the
	 * status ... if any child can't handle the reset, then the entire
	 * slot is dlpar removed and added.
	 */
	pci_walk_bus(frozen_bus, eeh_report_error, &result);

	/* Get the current PCI slot state. This can take a long time,
	 * sometimes over 3 seconds for certain systems. */
	rc = eeh_wait_for_slot_status (frozen_pdn, MAX_WAIT_FOR_RECOVERY*1000);
	if (rc < 0) {
		printk(KERN_WARNING "EEH: Permanent failure\n");
		goto hard_fail;
	}

	/* Since rtas may enable MMIO when posting the error log,
	 * don't post the error log until after all dev drivers
	 * have been informed.
	 */
	eeh_slot_error_detail(frozen_pdn, EEH_LOG_TEMP_FAILURE);

	/* If all device drivers were EEH-unaware, then shut
	 * down all of the device drivers, and hope they
	 * go down willingly, without panicing the system.
	 */
	if (result == PCI_ERS_RESULT_NONE) {
		rc = eeh_reset_device(frozen_pdn, frozen_bus);
		if (rc) {
			printk(KERN_WARNING "EEH: Unable to reset, rc=%d\n", rc);
			goto hard_fail;
		}
	}

	/* If all devices reported they can proceed, then re-enable MMIO */
	if (result == PCI_ERS_RESULT_CAN_RECOVER) {
		rc = rtas_pci_enable(frozen_pdn, EEH_THAW_MMIO);

		if (rc < 0)
			goto hard_fail;
		if (rc) {
			result = PCI_ERS_RESULT_NEED_RESET;
		} else {
			result = PCI_ERS_RESULT_NONE;
			pci_walk_bus(frozen_bus, eeh_report_mmio_enabled, &result);
		}
	}

	/* If all devices reported they can proceed, then re-enable DMA */
	if (result == PCI_ERS_RESULT_CAN_RECOVER) {
		rc = rtas_pci_enable(frozen_pdn, EEH_THAW_DMA);

		if (rc < 0)
			goto hard_fail;
		if (rc)
			result = PCI_ERS_RESULT_NEED_RESET;
		else
			result = PCI_ERS_RESULT_RECOVERED;
	}

	/* If any device has a hard failure, then shut off everything. */
	if (result == PCI_ERS_RESULT_DISCONNECT) {
		printk(KERN_WARNING "EEH: Device driver gave up\n");
		goto hard_fail;
	}

	/* If any device called out for a reset, then reset the slot */
	if (result == PCI_ERS_RESULT_NEED_RESET) {
		rc = eeh_reset_device(frozen_pdn, NULL);
		if (rc) {
			printk(KERN_WARNING "EEH: Cannot reset, rc=%d\n", rc);
			goto hard_fail;
		}
		result = PCI_ERS_RESULT_NONE;
		pci_walk_bus(frozen_bus, eeh_report_reset, &result);
	}

	/* All devices should claim they have recovered by now. */
	if ((result != PCI_ERS_RESULT_RECOVERED) &&
	    (result != PCI_ERS_RESULT_NONE)) {
		printk(KERN_WARNING "EEH: Not recovered\n");
		goto hard_fail;
	}

	/* Tell all device drivers that they can resume operations */
	pci_walk_bus(frozen_bus, eeh_report_resume, NULL);

	return frozen_pdn;
	
excess_failures:
	/*
	 * About 90% of all real-life EEH failures in the field
	 * are due to poorly seated PCI cards. Only 10% or so are
	 * due to actual, failed cards.
	 */
	printk(KERN_ERR
	   "EEH: PCI device at location=%s driver=%s pci addr=%s \n"
		"has failed %d times in the last hour "
		"and has been permanently disabled. \n"
		"Please try reseating this device or replacing it.\n",
		location, drv_str, pci_str, frozen_pdn->eeh_freeze_count);
	goto perm_error;

hard_fail:
	printk(KERN_ERR
	   "EEH: Unable to recover from failure of PCI device "
	   "at location=%s driver=%s pci addr=%s \n"
	   "Please try reseating this device or replacing it.\n",
		location, drv_str, pci_str);

perm_error:
	eeh_slot_error_detail(frozen_pdn, EEH_LOG_PERM_FAILURE);

	/* Notify all devices that they're about to go down. */
	pci_walk_bus(frozen_bus, eeh_report_failure, NULL);

	/* Shut down the device drivers for good. */
	pcibios_remove_pci_devices(frozen_bus);

	return NULL;
}

/* ---------- end of file ---------- */