aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/platforms/powernv/eeh-powernv.c
blob: 1d19e7917d7fc5e59cb2e4945c30a90be8e9e50a (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
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
/*
 * The file intends to implement the platform dependent EEH operations on
 * powernv platform. Actually, the powernv was created in order to fully
 * hypervisor support.
 *
 * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2013.
 *
 * 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.
 */

#include <linux/atomic.h>
#include <linux/delay.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/msi.h>
#include <linux/of.h>
#include <linux/pci.h>
#include <linux/proc_fs.h>
#include <linux/rbtree.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/spinlock.h>

#include <asm/eeh.h>
#include <asm/eeh_event.h>
#include <asm/firmware.h>
#include <asm/io.h>
#include <asm/iommu.h>
#include <asm/machdep.h>
#include <asm/msi_bitmap.h>
#include <asm/opal.h>
#include <asm/ppc-pci.h>

#include "powernv.h"
#include "pci.h"

/**
 * powernv_eeh_init - EEH platform dependent initialization
 *
 * EEH platform dependent initialization on powernv
 */
static int powernv_eeh_init(void)
{
	struct pci_controller *hose;
	struct pnv_phb *phb;

	/* We require OPALv3 */
	if (!firmware_has_feature(FW_FEATURE_OPALv3)) {
		pr_warn("%s: OPALv3 is required !\n",
			__func__);
		return -EINVAL;
	}

	/* Set probe mode */
	eeh_add_flag(EEH_PROBE_MODE_DEV);

	/*
	 * P7IOC blocks PCI config access to frozen PE, but PHB3
	 * doesn't do that. So we have to selectively enable I/O
	 * prior to collecting error log.
	 */
	list_for_each_entry(hose, &hose_list, list_node) {
		phb = hose->private_data;

		if (phb->model == PNV_PHB_MODEL_P7IOC)
			eeh_add_flag(EEH_ENABLE_IO_FOR_LOG);
		break;
	}

	return 0;
}

/**
 * powernv_eeh_post_init - EEH platform dependent post initialization
 *
 * EEH platform dependent post initialization on powernv. When
 * the function is called, the EEH PEs and devices should have
 * been built. If the I/O cache staff has been built, EEH is
 * ready to supply service.
 */
static int powernv_eeh_post_init(void)
{
	struct pci_controller *hose;
	struct pnv_phb *phb;
	int ret = 0;

	list_for_each_entry(hose, &hose_list, list_node) {
		phb = hose->private_data;

		if (phb->eeh_ops && phb->eeh_ops->post_init) {
			ret = phb->eeh_ops->post_init(hose);
			if (ret)
				break;
		}
	}

	return ret;
}

/**
 * powernv_eeh_dev_probe - Do probe on PCI device
 * @dev: PCI device
 * @flag: unused
 *
 * When EEH module is installed during system boot, all PCI devices
 * are checked one by one to see if it supports EEH. The function
 * is introduced for the purpose. By default, EEH has been enabled
 * on all PCI devices. That's to say, we only need do necessary
 * initialization on the corresponding eeh device and create PE
 * accordingly.
 *
 * It's notable that's unsafe to retrieve the EEH device through
 * the corresponding PCI device. During the PCI device hotplug, which
 * was possiblly triggered by EEH core, the binding between EEH device
 * and the PCI device isn't built yet.
 */
static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
{
	struct pci_controller *hose = pci_bus_to_host(dev->bus);
	struct pnv_phb *phb = hose->private_data;
	struct device_node *dn = pci_device_to_OF_node(dev);
	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
	int ret;

	/*
	 * When probing the root bridge, which doesn't have any
	 * subordinate PCI devices. We don't have OF node for
	 * the root bridge. So it's not reasonable to continue
	 * the probing.
	 */
	if (!dn || !edev || edev->pe)
		return 0;

	/* Skip for PCI-ISA bridge */
	if ((dev->class >> 8) == PCI_CLASS_BRIDGE_ISA)
		return 0;

	/* Initialize eeh device */
	edev->class_code = dev->class;
	edev->mode	&= 0xFFFFFF00;
	if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
		edev->mode |= EEH_DEV_BRIDGE;
	edev->pcix_cap = pci_find_capability(dev, PCI_CAP_ID_PCIX);
	if (pci_is_pcie(dev)) {
		edev->pcie_cap = pci_pcie_cap(dev);

		if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT)
			edev->mode |= EEH_DEV_ROOT_PORT;
		else if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM)
			edev->mode |= EEH_DEV_DS_PORT;

		edev->aer_cap = pci_find_ext_capability(dev,
							PCI_EXT_CAP_ID_ERR);
	}

	edev->config_addr	= ((dev->bus->number << 8) | dev->devfn);
	edev->pe_config_addr	= phb->bdfn_to_pe(phb, dev->bus, dev->devfn & 0xff);

	/* Create PE */
	ret = eeh_add_to_parent_pe(edev);
	if (ret) {
		pr_warn("%s: Can't add PCI dev %s to parent PE (%d)\n",
			__func__, pci_name(dev), ret);
		return ret;
	}

	/*
	 * If the PE contains any one of following adapters, the
	 * PCI config space can't be accessed when dumping EEH log.
	 * Otherwise, we will run into fenced PHB caused by shortage
	 * of outbound credits in the adapter. The PCI config access
	 * should be blocked until PE reset. MMIO access is dropped
	 * by hardware certainly. In order to drop PCI config requests,
	 * one more flag (EEH_PE_CFG_RESTRICTED) is introduced, which
	 * will be checked in the backend for PE state retrival. If
	 * the PE becomes frozen for the first time and the flag has
	 * been set for the PE, we will set EEH_PE_CFG_BLOCKED for
	 * that PE to block its config space.
	 *
	 * Broadcom Austin 4-ports NICs (14e4:1657)
	 * Broadcom Shiner 2-ports 10G NICs (14e4:168e)
	 */
	if ((dev->vendor == PCI_VENDOR_ID_BROADCOM && dev->device == 0x1657) ||
	    (dev->vendor == PCI_VENDOR_ID_BROADCOM && dev->device == 0x168e))
		edev->pe->state |= EEH_PE_CFG_RESTRICTED;

	/*
	 * Cache the PE primary bus, which can't be fetched when
	 * full hotplug is in progress. In that case, all child
	 * PCI devices of the PE are expected to be removed prior
	 * to PE reset.
	 */
	if (!edev->pe->bus)
		edev->pe->bus = dev->bus;

	/*
	 * Enable EEH explicitly so that we will do EEH check
	 * while accessing I/O stuff
	 */
	eeh_add_flag(EEH_ENABLED);

	/* Save memory bars */
	eeh_save_bars(edev);

	return 0;
}

/**
 * powernv_eeh_set_option - Initialize EEH or MMIO/DMA reenable
 * @pe: EEH PE
 * @option: operation to be issued
 *
 * The function is used to control the EEH functionality globally.
 * Currently, following options are support according to PAPR:
 * Enable EEH, Disable EEH, Enable MMIO and Enable DMA
 */
static int powernv_eeh_set_option(struct eeh_pe *pe, int option)
{
	struct pci_controller *hose = pe->phb;
	struct pnv_phb *phb = hose->private_data;
	int ret = -EEXIST;

	/*
	 * What we need do is pass it down for hardware
	 * implementation to handle it.
	 */
	if (phb->eeh_ops && phb->eeh_ops->set_option)
		ret = phb->eeh_ops->set_option(pe, option);

	return ret;
}

/**
 * powernv_eeh_get_pe_addr - Retrieve PE address
 * @pe: EEH PE
 *
 * Retrieve the PE address according to the given tranditional
 * PCI BDF (Bus/Device/Function) address.
 */
static int powernv_eeh_get_pe_addr(struct eeh_pe *pe)
{
	return pe->addr;
}

/**
 * powernv_eeh_get_state - Retrieve PE state
 * @pe: EEH PE
 * @delay: delay while PE state is temporarily unavailable
 *
 * Retrieve the state of the specified PE. For IODA-compitable
 * platform, it should be retrieved from IODA table. Therefore,
 * we prefer passing down to hardware implementation to handle
 * it.
 */
static int powernv_eeh_get_state(struct eeh_pe *pe, int *delay)
{
	struct pci_controller *hose = pe->phb;
	struct pnv_phb *phb = hose->private_data;
	int ret = EEH_STATE_NOT_SUPPORT;

	if (phb->eeh_ops && phb->eeh_ops->get_state) {
		ret = phb->eeh_ops->get_state(pe);

		/*
		 * If the PE state is temporarily unavailable,
		 * to inform the EEH core delay for default
		 * period (1 second)
		 */
		if (delay) {
			*delay = 0;
			if (ret & EEH_STATE_UNAVAILABLE)
				*delay = 1000;
		}
	}

	return ret;
}

/**
 * powernv_eeh_reset - Reset the specified PE
 * @pe: EEH PE
 * @option: reset option
 *
 * Reset the specified PE
 */
static int powernv_eeh_reset(struct eeh_pe *pe, int option)
{
	struct pci_controller *hose = pe->phb;
	struct pnv_phb *phb = hose->private_data;
	int ret = -EEXIST;

	if (phb->eeh_ops && phb->eeh_ops->reset)
		ret = phb->eeh_ops->reset(pe, option);

	return ret;
}

/**
 * powernv_eeh_wait_state - Wait for PE state
 * @pe: EEH PE
 * @max_wait: maximal period in microsecond
 *
 * Wait for the state of associated PE. It might take some time
 * to retrieve the PE's state.
 */
static int powernv_eeh_wait_state(struct eeh_pe *pe, int max_wait)
{
	int ret;
	int mwait;

	while (1) {
		ret = powernv_eeh_get_state(pe, &mwait);

		/*
		 * If the PE's state is temporarily unavailable,
		 * we have to wait for the specified time. Otherwise,
		 * the PE's state will be returned immediately.
		 */
		if (ret != EEH_STATE_UNAVAILABLE)
			return ret;

		max_wait -= mwait;
		if (max_wait <= 0) {
			pr_warn("%s: Timeout getting PE#%x's state (%d)\n",
				__func__, pe->addr, max_wait);
			return EEH_STATE_NOT_SUPPORT;
		}

		msleep(mwait);
	}

	return EEH_STATE_NOT_SUPPORT;
}

/**
 * powernv_eeh_get_log - Retrieve error log
 * @pe: EEH PE
 * @severity: temporary or permanent error log
 * @drv_log: driver log to be combined with retrieved error log
 * @len: length of driver log
 *
 * Retrieve the temporary or permanent error from the PE.
 */
static int powernv_eeh_get_log(struct eeh_pe *pe, int severity,
			       char *drv_log, unsigned long len)
{
	struct pci_controller *hose = pe->phb;
	struct pnv_phb *phb = hose->private_data;
	int ret = -EEXIST;

	if (phb->eeh_ops && phb->eeh_ops->get_log)
		ret = phb->eeh_ops->get_log(pe, severity, drv_log, len);

	return ret;
}

/**
 * powernv_eeh_configure_bridge - Configure PCI bridges in the indicated PE
 * @pe: EEH PE
 *
 * The function will be called to reconfigure the bridges included
 * in the specified PE so that the mulfunctional PE would be recovered
 * again.
 */
static int powernv_eeh_configure_bridge(struct eeh_pe *pe)
{
	struct pci_controller *hose = pe->phb;
	struct pnv_phb *phb = hose->private_data;
	int ret = 0;

	if (phb->eeh_ops && phb->eeh_ops->configure_bridge)
		ret = phb->eeh_ops->configure_bridge(pe);

	return ret;
}

/**
 * powernv_pe_err_inject - Inject specified error to the indicated PE
 * @pe: the indicated PE
 * @type: error type
 * @func: specific error type
 * @addr: address
 * @mask: address mask
 *
 * The routine is called to inject specified error, which is
 * determined by @type and @func, to the indicated PE for
 * testing purpose.
 */
static int powernv_eeh_err_inject(struct eeh_pe *pe, int type, int func,
				  unsigned long addr, unsigned long mask)
{
	struct pci_controller *hose = pe->phb;
	struct pnv_phb *phb = hose->private_data;
	int ret = -EEXIST;

	if (phb->eeh_ops && phb->eeh_ops->err_inject)
		ret = phb->eeh_ops->err_inject(pe, type, func, addr, mask);

	return ret;
}

static inline bool powernv_eeh_cfg_blocked(struct device_node *dn)
{
	struct eeh_dev *edev = of_node_to_eeh_dev(dn);

	if (!edev || !edev->pe)
		return false;

	if (edev->pe->state & EEH_PE_CFG_BLOCKED)
		return true;

	return false;
}

static int powernv_eeh_read_config(struct device_node *dn,
				   int where, int size, u32 *val)
{
	if (powernv_eeh_cfg_blocked(dn)) {
		*val = 0xFFFFFFFF;
		return PCIBIOS_SET_FAILED;
	}

	return pnv_pci_cfg_read(dn, where, size, val);
}

static int powernv_eeh_write_config(struct device_node *dn,
				    int where, int size, u32 val)
{
	if (powernv_eeh_cfg_blocked(dn))
		return PCIBIOS_SET_FAILED;

	return pnv_pci_cfg_write(dn, where, size, val);
}

/**
 * powernv_eeh_next_error - Retrieve next EEH error to handle
 * @pe: Affected PE
 *
 * Using OPAL API, to retrieve next EEH error for EEH core to handle
 */
static int powernv_eeh_next_error(struct eeh_pe **pe)
{
	struct pci_controller *hose;
	struct pnv_phb *phb = NULL;

	list_for_each_entry(hose, &hose_list, list_node) {
		phb = hose->private_data;
		break;
	}

	if (phb && phb->eeh_ops->next_error)
		return phb->eeh_ops->next_error(pe);

	return -EEXIST;
}

static int powernv_eeh_restore_config(struct device_node *dn)
{
	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
	struct pnv_phb *phb;
	s64 ret;

	if (!edev)
		return -EEXIST;

	phb = edev->phb->private_data;
	ret = opal_pci_reinit(phb->opal_id,
			      OPAL_REINIT_PCI_DEV, edev->config_addr);
	if (ret) {
		pr_warn("%s: Can't reinit PCI dev 0x%x (%lld)\n",
			__func__, edev->config_addr, ret);
		return -EIO;
	}

	return 0;
}

static struct eeh_ops powernv_eeh_ops = {
	.name                   = "powernv",
	.init                   = powernv_eeh_init,
	.post_init              = powernv_eeh_post_init,
	.of_probe               = NULL,
	.dev_probe              = powernv_eeh_dev_probe,
	.set_option             = powernv_eeh_set_option,
	.get_pe_addr            = powernv_eeh_get_pe_addr,
	.get_state              = powernv_eeh_get_state,
	.reset                  = powernv_eeh_reset,
	.wait_state             = powernv_eeh_wait_state,
	.get_log                = powernv_eeh_get_log,
	.configure_bridge       = powernv_eeh_configure_bridge,
	.err_inject		= powernv_eeh_err_inject,
	.read_config            = powernv_eeh_read_config,
	.write_config           = powernv_eeh_write_config,
	.next_error		= powernv_eeh_next_error,
	.restore_config		= powernv_eeh_restore_config
};

/**
 * eeh_powernv_init - Register platform dependent EEH operations
 *
 * EEH initialization on powernv platform. This function should be
 * called before any EEH related functions.
 */
static int __init eeh_powernv_init(void)
{
	int ret = -EINVAL;

	eeh_set_pe_aux_size(PNV_PCI_DIAG_BUF_SIZE);
	ret = eeh_ops_register(&powernv_eeh_ops);
	if (!ret)
		pr_info("EEH: PowerNV platform initialized\n");
	else
		pr_info("EEH: Failed to initialize PowerNV platform (%d)\n", ret);

	return ret;
}
machine_early_initcall(powernv, eeh_powernv_init);