summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kernel/pci_dn.c
blob: 61571ae23953063ee5ae4e80589922b8102a8804 (plain)
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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * pci_dn.c
 *
 * Copyright (C) 2001 Todd Inglett, IBM Corporation
 *
 * PCI manipulation via device_nodes.
 */
#include <linux/kernel.h>
#include <linux/pci.h>
#include <linux/string.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/gfp.h>

#include <asm/io.h>
#include <asm/prom.h>
#include <asm/pci-bridge.h>
#include <asm/ppc-pci.h>
#include <asm/firmware.h>
#include <asm/eeh.h>

/*
 * The function is used to find the firmware data of one
 * specific PCI device, which is attached to the indicated
 * PCI bus. For VFs, their firmware data is linked to that
 * one of PF's bridge. For other devices, their firmware
 * data is linked to that of their bridge.
 */
static struct pci_dn *pci_bus_to_pdn(struct pci_bus *bus)
{
	struct pci_bus *pbus;
	struct device_node *dn;
	struct pci_dn *pdn;

	/*
	 * We probably have virtual bus which doesn't
	 * have associated bridge.
	 */
	pbus = bus;
	while (pbus) {
		if (pci_is_root_bus(pbus) || pbus->self)
			break;

		pbus = pbus->parent;
	}

	/*
	 * Except virtual bus, all PCI buses should
	 * have device nodes.
	 */
	dn = pci_bus_to_OF_node(pbus);
	pdn = dn ? PCI_DN(dn) : NULL;

	return pdn;
}

struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus,
				    int devfn)
{
	struct device_node *dn = NULL;
	struct pci_dn *parent, *pdn;
	struct pci_dev *pdev = NULL;

	/* Fast path: fetch from PCI device */
	list_for_each_entry(pdev, &bus->devices, bus_list) {
		if (pdev->devfn == devfn) {
			if (pdev->dev.archdata.pci_data)
				return pdev->dev.archdata.pci_data;

			dn = pci_device_to_OF_node(pdev);
			break;
		}
	}

	/* Fast path: fetch from device node */
	pdn = dn ? PCI_DN(dn) : NULL;
	if (pdn)
		return pdn;

	/* Slow path: fetch from firmware data hierarchy */
	parent = pci_bus_to_pdn(bus);
	if (!parent)
		return NULL;

	list_for_each_entry(pdn, &parent->child_list, list) {
		if (pdn->busno == bus->number &&
                    pdn->devfn == devfn)
                        return pdn;
        }

	return NULL;
}

struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
{
	struct device_node *dn;
	struct pci_dn *parent, *pdn;

	/* Search device directly */
	if (pdev->dev.archdata.pci_data)
		return pdev->dev.archdata.pci_data;

	/* Check device node */
	dn = pci_device_to_OF_node(pdev);
	pdn = dn ? PCI_DN(dn) : NULL;
	if (pdn)
		return pdn;

	/*
	 * VFs don't have device nodes. We hook their
	 * firmware data to PF's bridge.
	 */
	parent = pci_bus_to_pdn(pdev->bus);
	if (!parent)
		return NULL;

	list_for_each_entry(pdn, &parent->child_list, list) {
		if (pdn->busno == pdev->bus->number &&
		    pdn->devfn == pdev->devfn)
			return pdn;
	}

	return NULL;
}

#ifdef CONFIG_EEH
static struct eeh_dev *eeh_dev_init(struct pci_dn *pdn)
{
	struct eeh_dev *edev;

	/* Allocate EEH device */
	edev = kzalloc(sizeof(*edev), GFP_KERNEL);
	if (!edev)
		return NULL;

	/* Associate EEH device with OF node */
	pdn->edev = edev;
	edev->pdn = pdn;
	edev->bdfn = (pdn->busno << 8) | pdn->devfn;
	edev->controller = pdn->phb;

	return edev;
}
#endif /* CONFIG_EEH */

#ifdef CONFIG_PCI_IOV
static struct pci_dn *add_one_sriov_vf_pdn(struct pci_dn *parent,
					   int busno, int devfn)
{
	struct pci_dn *pdn;

	/* Except PHB, we always have the parent */
	if (!parent)
		return NULL;

	pdn = kzalloc(sizeof(*pdn), GFP_KERNEL);
	if (!pdn)
		return NULL;

	pdn->phb = parent->phb;
	pdn->parent = parent;
	pdn->busno = busno;
	pdn->devfn = devfn;
	pdn->pe_number = IODA_INVALID_PE;
	INIT_LIST_HEAD(&pdn->child_list);
	INIT_LIST_HEAD(&pdn->list);
	list_add_tail(&pdn->list, &parent->child_list);

	return pdn;
}

struct pci_dn *add_sriov_vf_pdns(struct pci_dev *pdev)
{
	struct pci_dn *parent, *pdn;
	int i;

	/* Only support IOV for now */
	if (WARN_ON(!pdev->is_physfn))
		return NULL;

	/* Check if VFs have been populated */
	pdn = pci_get_pdn(pdev);
	if (!pdn || (pdn->flags & PCI_DN_FLAG_IOV_VF))
		return NULL;

	pdn->flags |= PCI_DN_FLAG_IOV_VF;
	parent = pci_bus_to_pdn(pdev->bus);
	if (!parent)
		return NULL;

	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
		struct eeh_dev *edev __maybe_unused;

		pdn = add_one_sriov_vf_pdn(parent,
					   pci_iov_virtfn_bus(pdev, i),
					   pci_iov_virtfn_devfn(pdev, i));
		if (!pdn) {
			dev_warn(&pdev->dev, "%s: Cannot create firmware data for VF#%d\n",
				 __func__, i);
			return NULL;
		}

#ifdef CONFIG_EEH
		/* Create the EEH device for the VF */
		edev = eeh_dev_init(pdn);
		BUG_ON(!edev);

		/* FIXME: these should probably be populated by the EEH probe */
		edev->physfn = pdev;
		edev->vf_index = i;
#endif /* CONFIG_EEH */
	}
	return pci_get_pdn(pdev);
}

void remove_sriov_vf_pdns(struct pci_dev *pdev)
{
	struct pci_dn *parent;
	struct pci_dn *pdn, *tmp;
	int i;

	/* Only support IOV PF for now */
	if (WARN_ON(!pdev->is_physfn))
		return;

	/* Check if VFs have been populated */
	pdn = pci_get_pdn(pdev);
	if (!pdn || !(pdn->flags & PCI_DN_FLAG_IOV_VF))
		return;

	pdn->flags &= ~PCI_DN_FLAG_IOV_VF;
	parent = pci_bus_to_pdn(pdev->bus);
	if (!parent)
		return;

	/*
	 * We might introduce flag to pci_dn in future
	 * so that we can release VF's firmware data in
	 * a batch mode.
	 */
	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
		struct eeh_dev *edev __maybe_unused;

		list_for_each_entry_safe(pdn, tmp,
			&parent->child_list, list) {
			if (pdn->busno != pci_iov_virtfn_bus(pdev, i) ||
			    pdn->devfn != pci_iov_virtfn_devfn(pdev, i))
				continue;

#ifdef CONFIG_EEH
			/*
			 * Release EEH state for this VF. The PCI core
			 * has already torn down the pci_dev for this VF, but
			 * we're responsible to removing the eeh_dev since it
			 * has the same lifetime as the pci_dn that spawned it.
			 */
			edev = pdn_to_eeh_dev(pdn);
			if (edev) {
				/*
				 * We allocate pci_dn's for the totalvfs count,
				 * but only only the vfs that were activated
				 * have a configured PE.
				 */
				if (edev->pe)
					eeh_pe_tree_remove(edev);

				pdn->edev = NULL;
				kfree(edev);
			}
#endif /* CONFIG_EEH */

			if (!list_empty(&pdn->list))
				list_del(&pdn->list);

			kfree(pdn);
		}
	}
}
#endif /* CONFIG_PCI_IOV */

struct pci_dn *pci_add_device_node_info(struct pci_controller *hose,
					struct device_node *dn)
{
	const __be32 *type = of_get_property(dn, "ibm,pci-config-space-type", NULL);
	const __be32 *regs;
	struct device_node *parent;
	struct pci_dn *pdn;
#ifdef CONFIG_EEH
	struct eeh_dev *edev;
#endif

	pdn = kzalloc(sizeof(*pdn), GFP_KERNEL);
	if (pdn == NULL)
		return NULL;
	dn->data = pdn;
	pdn->phb = hose;
	pdn->pe_number = IODA_INVALID_PE;
	regs = of_get_property(dn, "reg", NULL);
	if (regs) {
		u32 addr = of_read_number(regs, 1);

		/* First register entry is addr (00BBSS00)  */
		pdn->busno = (addr >> 16) & 0xff;
		pdn->devfn = (addr >> 8) & 0xff;
	}

	/* vendor/device IDs and class code */
	regs = of_get_property(dn, "vendor-id", NULL);
	pdn->vendor_id = regs ? of_read_number(regs, 1) : 0;
	regs = of_get_property(dn, "device-id", NULL);
	pdn->device_id = regs ? of_read_number(regs, 1) : 0;
	regs = of_get_property(dn, "class-code", NULL);
	pdn->class_code = regs ? of_read_number(regs, 1) : 0;

	/* Extended config space */
	pdn->pci_ext_config_space = (type && of_read_number(type, 1) == 1);

	/* Create EEH device */
#ifdef CONFIG_EEH
	edev = eeh_dev_init(pdn);
	if (!edev) {
		kfree(pdn);
		return NULL;
	}
#endif

	/* Attach to parent node */
	INIT_LIST_HEAD(&pdn->child_list);
	INIT_LIST_HEAD(&pdn->list);
	parent = of_get_parent(dn);
	pdn->parent = parent ? PCI_DN(parent) : NULL;
	if (pdn->parent)
		list_add_tail(&pdn->list, &pdn->parent->child_list);

	return pdn;
}
EXPORT_SYMBOL_GPL(pci_add_device_node_info);

void pci_remove_device_node_info(struct device_node *dn)
{
	struct pci_dn *pdn = dn ? PCI_DN(dn) : NULL;
	struct device_node *parent;
	struct pci_dev *pdev;
#ifdef CONFIG_EEH
	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);

	if (edev)
		edev->pdn = NULL;
#endif

	if (!pdn)
		return;

	WARN_ON(!list_empty(&pdn->child_list));
	list_del(&pdn->list);

	/* Drop the parent pci_dn's ref to our backing dt node */
	parent = of_get_parent(dn);
	if (parent)
		of_node_put(parent);

	/*
	 * At this point we *might* still have a pci_dev that was
	 * instantiated from this pci_dn. So defer free()ing it until
	 * the pci_dev's release function is called.
	 */
	pdev = pci_get_domain_bus_and_slot(pdn->phb->global_number,
			pdn->busno, pdn->devfn);
	if (pdev) {
		/* NB: pdev has a ref to dn */
		pci_dbg(pdev, "marked pdn (from %pOF) as dead\n", dn);
		pdn->flags |= PCI_DN_FLAG_DEAD;
	} else {
		dn->data = NULL;
		kfree(pdn);
	}

	pci_dev_put(pdev);
}
EXPORT_SYMBOL_GPL(pci_remove_device_node_info);

/*
 * Traverse a device tree stopping each PCI device in the tree.
 * This is done depth first.  As each node is processed, a "pre"
 * function is called and the children are processed recursively.
 *
 * The "pre" func returns a value.  If non-zero is returned from
 * the "pre" func, the traversal stops and this value is returned.
 * This return value is useful when using traverse as a method of
 * finding a device.
 *
 * NOTE: we do not run the func for devices that do not appear to
 * be PCI except for the start node which we assume (this is good
 * because the start node is often a phb which may be missing PCI
 * properties).
 * We use the class-code as an indicator. If we run into
 * one of these nodes we also assume its siblings are non-pci for
 * performance.
 */
void *pci_traverse_device_nodes(struct device_node *start,
				void *(*fn)(struct device_node *, void *),
				void *data)
{
	struct device_node *dn, *nextdn;
	void *ret;

	/* We started with a phb, iterate all childs */
	for (dn = start->child; dn; dn = nextdn) {
		const __be32 *classp;
		u32 class = 0;

		nextdn = NULL;
		classp = of_get_property(dn, "class-code", NULL);
		if (classp)
			class = of_read_number(classp, 1);

		if (fn) {
			ret = fn(dn, data);
			if (ret)
				return ret;
		}

		/* If we are a PCI bridge, go down */
		if (dn->child && ((class >> 8) == PCI_CLASS_BRIDGE_PCI ||
				  (class >> 8) == PCI_CLASS_BRIDGE_CARDBUS))
			/* Depth first...do children */
			nextdn = dn->child;
		else if (dn->sibling)
			/* ok, try next sibling instead. */
			nextdn = dn->sibling;
		if (!nextdn) {
			/* Walk up to next valid sibling. */
			do {
				dn = dn->parent;
				if (dn == start)
					return NULL;
			} while (dn->sibling == NULL);
			nextdn = dn->sibling;
		}
	}
	return NULL;
}
EXPORT_SYMBOL_GPL(pci_traverse_device_nodes);

static void *add_pdn(struct device_node *dn, void *data)
{
	struct pci_controller *hose = data;
	struct pci_dn *pdn;

	pdn = pci_add_device_node_info(hose, dn);
	if (!pdn)
		return ERR_PTR(-ENOMEM);

	return NULL;
}

/** 
 * pci_devs_phb_init_dynamic - setup pci devices under this PHB
 * phb: pci-to-host bridge (top-level bridge connecting to cpu)
 *
 * This routine is called both during boot, (before the memory
 * subsystem is set up, before kmalloc is valid) and during the 
 * dynamic lpar operation of adding a PHB to a running system.
 */
void pci_devs_phb_init_dynamic(struct pci_controller *phb)
{
	struct device_node *dn = phb->dn;
	struct pci_dn *pdn;

	/* PHB nodes themselves must not match */
	pdn = pci_add_device_node_info(phb, dn);
	if (pdn) {
		pdn->devfn = pdn->busno = -1;
		pdn->vendor_id = pdn->device_id = pdn->class_code = 0;
		pdn->phb = phb;
		phb->pci_data = pdn;
	}

	/* Update dn->phb ptrs for new phb and children devices */
	pci_traverse_device_nodes(dn, add_pdn, phb);
}

static void pci_dev_pdn_setup(struct pci_dev *pdev)
{
	struct pci_dn *pdn;

	if (pdev->dev.archdata.pci_data)
		return;

	/* Setup the fast path */
	pdn = pci_get_pdn(pdev);
	pdev->dev.archdata.pci_data = pdn;
}
DECLARE_PCI_FIXUP_EARLY(PCI_ANY_ID, PCI_ANY_ID, pci_dev_pdn_setup);