pci-ioda.c 36 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
/*
 * Support PCI/PCIe on PowerNV platforms
 *
 * Copyright 2011 Benjamin Herrenschmidt, IBM Corp.
 *
 * 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.
 */

12
#undef DEBUG
13
14
15

#include <linux/kernel.h>
#include <linux/pci.h>
16
#include <linux/debugfs.h>
17
18
19
20
21
22
23
24
25
26
27
28
29
#include <linux/delay.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/irq.h>
#include <linux/io.h>
#include <linux/msi.h>

#include <asm/sections.h>
#include <asm/io.h>
#include <asm/prom.h>
#include <asm/pci-bridge.h>
#include <asm/machdep.h>
30
#include <asm/msi_bitmap.h>
31
32
33
34
#include <asm/ppc-pci.h>
#include <asm/opal.h>
#include <asm/iommu.h>
#include <asm/tce.h>
35
#include <asm/xics.h>
36
#include <asm/debug.h>
37
38
39
40
41
42
43
44
45

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

#define define_pe_printk_level(func, kern_level)		\
static int func(const struct pnv_ioda_pe *pe, const char *fmt, ...)	\
{								\
	struct va_format vaf;					\
	va_list args;						\
Gavin Shan's avatar
Gavin Shan committed
46
	char pfix[32];						\
47
48
49
50
51
52
53
	int r;							\
								\
	va_start(args, fmt);					\
								\
	vaf.fmt = fmt;						\
	vaf.va = &args;						\
								\
Gavin Shan's avatar
Gavin Shan committed
54
55
56
57
58
59
60
61
62
63
	if (pe->pdev)						\
		strlcpy(pfix, dev_name(&pe->pdev->dev),		\
			sizeof(pfix));				\
	else							\
		sprintf(pfix, "%04x:%02x     ",			\
			pci_domain_nr(pe->pbus),		\
			pe->pbus->number);			\
	r = printk(kern_level "pci %s: [PE# %.3d] %pV",		\
		   pfix, pe->pe_number, &vaf);			\
								\
64
65
66
67
68
69
70
71
72
	va_end(args);						\
								\
	return r;						\
}								\

define_pe_printk_level(pe_err, KERN_ERR);
define_pe_printk_level(pe_warn, KERN_WARNING);
define_pe_printk_level(pe_info, KERN_INFO);

73
74
75
76
77
78
79
80
81
82
/*
 * stdcix is only supposed to be used in hypervisor real mode as per
 * the architecture spec
 */
static inline void __raw_rm_writeq(u64 val, volatile void __iomem *paddr)
{
	__asm__ __volatile__("stdcix %0,0,%1"
		: : "r" (val), "r" (paddr) : "memory");
}

83
static int pnv_ioda_alloc_pe(struct pnv_phb *phb)
84
85
86
87
88
89
90
91
92
93
{
	unsigned long pe;

	do {
		pe = find_next_zero_bit(phb->ioda.pe_alloc,
					phb->ioda.total_pe, 0);
		if (pe >= phb->ioda.total_pe)
			return IODA_INVALID_PE;
	} while(test_and_set_bit(pe, phb->ioda.pe_alloc));

94
	phb->ioda.pe_array[pe].phb = phb;
95
96
97
98
	phb->ioda.pe_array[pe].pe_number = pe;
	return pe;
}

99
static void pnv_ioda_free_pe(struct pnv_phb *phb, int pe)
100
101
102
103
104
105
106
107
108
109
110
{
	WARN_ON(phb->ioda.pe_array[pe].pdev);

	memset(&phb->ioda.pe_array[pe], 0, sizeof(struct pnv_ioda_pe));
	clear_bit(pe, phb->ioda.pe_alloc);
}

/* Currently those 2 are only used when MSIs are enabled, this will change
 * but in the meantime, we need to protect them to avoid warnings
 */
#ifdef CONFIG_PCI_MSI
111
static struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev)
112
113
114
{
	struct pci_controller *hose = pci_bus_to_host(dev->bus);
	struct pnv_phb *phb = hose->private_data;
115
	struct pci_dn *pdn = pci_get_pdn(dev);
116
117
118
119
120
121
122
123
124

	if (!pdn)
		return NULL;
	if (pdn->pe_number == IODA_INVALID_PE)
		return NULL;
	return &phb->ioda.pe_array[pdn->pe_number];
}
#endif /* CONFIG_PCI_MSI */

125
static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
126
127
128
129
130
131
132
133
134
135
136
137
{
	struct pci_dev *parent;
	uint8_t bcomp, dcomp, fcomp;
	long rc, rid_end, rid;

	/* Bus validation ? */
	if (pe->pbus) {
		int count;

		dcomp = OPAL_IGNORE_RID_DEVICE_NUMBER;
		fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER;
		parent = pe->pbus->self;
138
139
140
141
142
		if (pe->flags & PNV_IODA_PE_BUS_ALL)
			count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1;
		else
			count = 1;

143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
		switch(count) {
		case  1: bcomp = OpalPciBusAll;		break;
		case  2: bcomp = OpalPciBus7Bits;	break;
		case  4: bcomp = OpalPciBus6Bits;	break;
		case  8: bcomp = OpalPciBus5Bits;	break;
		case 16: bcomp = OpalPciBus4Bits;	break;
		case 32: bcomp = OpalPciBus3Bits;	break;
		default:
			pr_err("%s: Number of subordinate busses %d"
			       " unsupported\n",
			       pci_name(pe->pbus->self), count);
			/* Do an exact match only */
			bcomp = OpalPciBusAll;
		}
		rid_end = pe->rid + (count << 8);
	} else {
		parent = pe->pdev->bus->self;
		bcomp = OpalPciBusAll;
		dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER;
		fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER;
		rid_end = pe->rid + 1;
	}

166
167
168
169
170
171
	/*
	 * Associate PE in PELT. We need add the PE into the
	 * corresponding PELT-V as well. Otherwise, the error
	 * originated from the PE might contribute to other
	 * PEs.
	 */
172
173
174
175
176
177
	rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid,
			     bcomp, dcomp, fcomp, OPAL_MAP_PE);
	if (rc) {
		pe_err(pe, "OPAL error %ld trying to setup PELT table\n", rc);
		return -ENXIO;
	}
178
179
180
181
182

	rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number,
				pe->pe_number, OPAL_ADD_PE_TO_DOMAIN);
	if (rc)
		pe_warn(pe, "OPAL error %d adding self to PELTV\n", rc);
183
184
185
186
187
	opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number,
				  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);

	/* Add to all parents PELT-V */
	while (parent) {
188
		struct pci_dn *pdn = pci_get_pdn(parent);
189
190
		if (pdn && pdn->pe_number != IODA_INVALID_PE) {
			rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number,
191
						pe->pe_number, OPAL_ADD_PE_TO_DOMAIN);
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
			/* XXX What to do in case of error ? */
		}
		parent = parent->bus->self;
	}
	/* Setup reverse map */
	for (rid = pe->rid; rid < rid_end; rid++)
		phb->ioda.pe_rmap[rid] = pe->pe_number;

	/* Setup one MVTs on IODA1 */
	if (phb->type == PNV_PHB_IODA1) {
		pe->mve_number = pe->pe_number;
		rc = opal_pci_set_mve(phb->opal_id, pe->mve_number,
				      pe->pe_number);
		if (rc) {
			pe_err(pe, "OPAL error %ld setting up MVE %d\n",
			       rc, pe->mve_number);
			pe->mve_number = -1;
		} else {
			rc = opal_pci_set_mve_enable(phb->opal_id,
211
						     pe->mve_number, OPAL_ENABLE_MVE);
212
213
214
215
216
217
218
219
220
221
222
223
			if (rc) {
				pe_err(pe, "OPAL error %ld enabling MVE %d\n",
				       rc, pe->mve_number);
				pe->mve_number = -1;
			}
		}
	} else if (phb->type == PNV_PHB_IODA2)
		pe->mve_number = 0;

	return 0;
}

224
225
static void pnv_ioda_link_pe_by_weight(struct pnv_phb *phb,
				       struct pnv_ioda_pe *pe)
226
227
228
{
	struct pnv_ioda_pe *lpe;

229
	list_for_each_entry(lpe, &phb->ioda.pe_dma_list, dma_link) {
230
		if (lpe->dma_weight < pe->dma_weight) {
231
			list_add_tail(&pe->dma_link, &lpe->dma_link);
232
233
234
			return;
		}
	}
235
	list_add_tail(&pe->dma_link, &phb->ioda.pe_dma_list);
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
}

static unsigned int pnv_ioda_dma_weight(struct pci_dev *dev)
{
	/* This is quite simplistic. The "base" weight of a device
	 * is 10. 0 means no DMA is to be accounted for it.
	 */

	/* If it's a bridge, no DMA */
	if (dev->hdr_type != PCI_HEADER_TYPE_NORMAL)
		return 0;

	/* Reduce the weight of slow USB controllers */
	if (dev->class == PCI_CLASS_SERIAL_USB_UHCI ||
	    dev->class == PCI_CLASS_SERIAL_USB_OHCI ||
	    dev->class == PCI_CLASS_SERIAL_USB_EHCI)
		return 3;

	/* Increase the weight of RAID (includes Obsidian) */
	if ((dev->class >> 8) == PCI_CLASS_STORAGE_RAID)
		return 15;

	/* Default */
	return 10;
}

262
#if 0
263
static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
264
265
266
{
	struct pci_controller *hose = pci_bus_to_host(dev->bus);
	struct pnv_phb *phb = hose->private_data;
267
	struct pci_dn *pdn = pci_get_pdn(dev);
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
	struct pnv_ioda_pe *pe;
	int pe_num;

	if (!pdn) {
		pr_err("%s: Device tree node not associated properly\n",
			   pci_name(dev));
		return NULL;
	}
	if (pdn->pe_number != IODA_INVALID_PE)
		return NULL;

	/* PE#0 has been pre-set */
	if (dev->bus->number == 0)
		pe_num = 0;
	else
		pe_num = pnv_ioda_alloc_pe(phb);
	if (pe_num == IODA_INVALID_PE) {
		pr_warning("%s: Not enough PE# available, disabling device\n",
			   pci_name(dev));
		return NULL;
	}

	/* NOTE: We get only one ref to the pci_dev for the pdn, not for the
	 * pointer in the PE data structure, both should be destroyed at the
	 * same time. However, this needs to be looked at more closely again
	 * once we actually start removing things (Hotplug, SR-IOV, ...)
	 *
	 * At some point we want to remove the PDN completely anyways
	 */
	pe = &phb->ioda.pe_array[pe_num];
	pci_dev_get(dev);
	pdn->pcidev = dev;
	pdn->pe_number = pe_num;
	pe->pdev = dev;
	pe->pbus = NULL;
	pe->tce32_seg = -1;
	pe->mve_number = -1;
	pe->rid = dev->bus->number << 8 | pdn->devfn;

	pe_info(pe, "Associated device to PE\n");

	if (pnv_ioda_configure_pe(phb, pe)) {
		/* XXX What do we do here ? */
		if (pe_num)
			pnv_ioda_free_pe(phb, pe_num);
		pdn->pe_number = IODA_INVALID_PE;
		pe->pdev = NULL;
		pci_dev_put(dev);
		return NULL;
	}

	/* Assign a DMA weight to the device */
	pe->dma_weight = pnv_ioda_dma_weight(dev);
	if (pe->dma_weight != 0) {
		phb->ioda.dma_weight += pe->dma_weight;
		phb->ioda.dma_pe_count++;
	}

	/* Link the PE */
	pnv_ioda_link_pe_by_weight(phb, pe);

	return pe;
}
331
#endif /* Useful for SRIOV case */
332
333
334
335
336
337

static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
{
	struct pci_dev *dev;

	list_for_each_entry(dev, &bus->devices, bus_list) {
338
		struct pci_dn *pdn = pci_get_pdn(dev);
339
340
341
342
343
344
345
346
347
348

		if (pdn == NULL) {
			pr_warn("%s: No device node associated with device !\n",
				pci_name(dev));
			continue;
		}
		pci_dev_get(dev);
		pdn->pcidev = dev;
		pdn->pe_number = pe->pe_number;
		pe->dma_weight += pnv_ioda_dma_weight(dev);
349
		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
350
351
352
353
			pnv_ioda_setup_same_PE(dev->subordinate, pe);
	}
}

354
355
356
357
358
359
/*
 * There're 2 types of PCI bus sensitive PEs: One that is compromised of
 * single PCI bus. Another one that contains the primary PCI bus and its
 * subordinate PCI devices and buses. The second type of PE is normally
 * orgiriated by PCIe-to-PCI bridge or PLX switch downstream ports.
 */
360
static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all)
361
{
362
	struct pci_controller *hose = pci_bus_to_host(bus);
363
364
365
366
367
368
	struct pnv_phb *phb = hose->private_data;
	struct pnv_ioda_pe *pe;
	int pe_num;

	pe_num = pnv_ioda_alloc_pe(phb);
	if (pe_num == IODA_INVALID_PE) {
369
370
		pr_warning("%s: Not enough PE# available for PCI bus %04x:%02x\n",
			__func__, pci_domain_nr(bus), bus->number);
371
372
373
374
		return;
	}

	pe = &phb->ioda.pe_array[pe_num];
375
	pe->flags = (all ? PNV_IODA_PE_BUS_ALL : PNV_IODA_PE_BUS);
376
377
378
379
	pe->pbus = bus;
	pe->pdev = NULL;
	pe->tce32_seg = -1;
	pe->mve_number = -1;
380
	pe->rid = bus->busn_res.start << 8;
381
382
	pe->dma_weight = 0;

383
384
385
386
387
388
	if (all)
		pe_info(pe, "Secondary bus %d..%d associated with PE#%d\n",
			bus->busn_res.start, bus->busn_res.end, pe_num);
	else
		pe_info(pe, "Secondary bus %d associated with PE#%d\n",
			bus->busn_res.start, pe_num);
389
390
391
392
393
394
395
396
397
398
399
400

	if (pnv_ioda_configure_pe(phb, pe)) {
		/* XXX What do we do here ? */
		if (pe_num)
			pnv_ioda_free_pe(phb, pe_num);
		pe->pbus = NULL;
		return;
	}

	/* Associate it with all child devices */
	pnv_ioda_setup_same_PE(bus, pe);

401
402
403
	/* Put PE to the list */
	list_add_tail(&pe->list, &phb->ioda.pe_list);

404
405
406
407
408
409
410
411
412
413
414
415
	/* Account for one DMA PE if at least one DMA capable device exist
	 * below the bridge
	 */
	if (pe->dma_weight != 0) {
		phb->ioda.dma_weight += pe->dma_weight;
		phb->ioda.dma_pe_count++;
	}

	/* Link the PE */
	pnv_ioda_link_pe_by_weight(phb, pe);
}

416
static void pnv_ioda_setup_PEs(struct pci_bus *bus)
417
418
{
	struct pci_dev *dev;
419
420

	pnv_ioda_setup_bus_PE(bus, 0);
421
422

	list_for_each_entry(dev, &bus->devices, bus_list) {
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
		if (dev->subordinate) {
			if (pci_pcie_type(dev) == PCI_EXP_TYPE_PCI_BRIDGE)
				pnv_ioda_setup_bus_PE(dev->subordinate, 1);
			else
				pnv_ioda_setup_PEs(dev->subordinate);
		}
	}
}

/*
 * Configure PEs so that the downstream PCI buses and devices
 * could have their associated PE#. Unfortunately, we didn't
 * figure out the way to identify the PLX bridge yet. So we
 * simply put the PCI bus and the subordinate behind the root
 * port to PE# here. The game rule here is expected to be changed
 * as soon as we can detected PLX bridge correctly.
 */
440
static void pnv_pci_ioda_setup_PEs(void)
441
442
443
444
445
{
	struct pci_controller *hose, *tmp;

	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
		pnv_ioda_setup_PEs(hose->bus);
446
447
448
	}
}

449
static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev)
450
{
451
	struct pci_dn *pdn = pci_get_pdn(pdev);
452
	struct pnv_ioda_pe *pe;
453

454
455
456
457
458
459
460
	/*
	 * The function can be called while the PE#
	 * hasn't been assigned. Do nothing for the
	 * case.
	 */
	if (!pdn || pdn->pe_number == IODA_INVALID_PE)
		return;
461

462
463
	pe = &phb->ioda.pe_array[pdn->pe_number];
	set_iommu_table_base(&pdev->dev, &pe->tce32_table);
464
465
}

466
467
468
469
470
471
472
473
474
475
476
static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
{
	struct pci_dev *dev;

	list_for_each_entry(dev, &bus->devices, bus_list) {
		set_iommu_table_base(&dev->dev, &pe->tce32_table);
		if (dev->subordinate)
			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
	}
}

477
478
static void pnv_pci_ioda1_tce_invalidate(struct pnv_ioda_pe *pe,
					 struct iommu_table *tbl,
479
					 __be64 *startp, __be64 *endp, bool rm)
480
{
481
482
483
	__be64 __iomem *invalidate = rm ?
		(__be64 __iomem *)pe->tce_inval_reg_phys :
		(__be64 __iomem *)tbl->it_index;
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
	unsigned long start, end, inc;

	start = __pa(startp);
	end = __pa(endp);

	/* BML uses this case for p6/p7/galaxy2: Shift addr and put in node */
	if (tbl->it_busno) {
		start <<= 12;
		end <<= 12;
		inc = 128 << 12;
		start |= tbl->it_busno;
		end |= tbl->it_busno;
	} else if (tbl->it_type & TCE_PCI_SWINV_PAIR) {
		/* p7ioc-style invalidation, 2 TCEs per write */
		start |= (1ull << 63);
		end |= (1ull << 63);
		inc = 16;
        } else {
		/* Default (older HW) */
                inc = 128;
	}

        end |= inc - 1;	/* round up end to be different than start */

        mb(); /* Ensure above stores are visible */
        while (start <= end) {
510
		if (rm)
511
			__raw_rm_writeq(cpu_to_be64(start), invalidate);
512
		else
513
			__raw_writeq(cpu_to_be64(start), invalidate);
514
515
516
517
518
519
520
521
522
523
524
                start += inc;
        }

	/*
	 * The iommu layer will do another mb() for us on build()
	 * and we don't care on free()
	 */
}

static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
					 struct iommu_table *tbl,
525
					 __be64 *startp, __be64 *endp, bool rm)
526
527
{
	unsigned long start, end, inc;
528
529
530
	__be64 __iomem *invalidate = rm ?
		(__be64 __iomem *)pe->tce_inval_reg_phys :
		(__be64 __iomem *)tbl->it_index;
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545

	/* We'll invalidate DMA address in PE scope */
	start = 0x2ul << 60;
	start |= (pe->pe_number & 0xFF);
	end = start;

	/* Figure out the start, end and step */
	inc = tbl->it_offset + (((u64)startp - tbl->it_base) / sizeof(u64));
	start |= (inc << 12);
	inc = tbl->it_offset + (((u64)endp - tbl->it_base) / sizeof(u64));
	end |= (inc << 12);
	inc = (0x1ul << 12);
	mb();

	while (start <= end) {
546
		if (rm)
547
			__raw_rm_writeq(cpu_to_be64(start), invalidate);
548
		else
549
			__raw_writeq(cpu_to_be64(start), invalidate);
550
551
552
553
554
		start += inc;
	}
}

void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
555
				 __be64 *startp, __be64 *endp, bool rm)
556
557
558
559
560
561
{
	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
					      tce32_table);
	struct pnv_phb *phb = pe->phb;

	if (phb->type == PNV_PHB_IODA1)
562
		pnv_pci_ioda1_tce_invalidate(pe, tbl, startp, endp, rm);
563
	else
564
		pnv_pci_ioda2_tce_invalidate(pe, tbl, startp, endp, rm);
565
566
}

567
568
569
static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
				      struct pnv_ioda_pe *pe, unsigned int base,
				      unsigned int segs)
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
{

	struct page *tce_mem = NULL;
	const __be64 *swinvp;
	struct iommu_table *tbl;
	unsigned int i;
	int64_t rc;
	void *addr;

	/* 256M DMA window, 4K TCE pages, 8 bytes TCE */
#define TCE32_TABLE_SIZE	((0x10000000 / 0x1000) * 8)

	/* XXX FIXME: Handle 64-bit only DMA devices */
	/* XXX FIXME: Provide 64-bit DMA facilities & non-4K TCE tables etc.. */
	/* XXX FIXME: Allocate multi-level tables on PHB3 */

	/* We shouldn't already have a 32-bit DMA associated */
	if (WARN_ON(pe->tce32_seg >= 0))
		return;

	/* Grab a 32-bit TCE table */
	pe->tce32_seg = base;
	pe_info(pe, " Setting up 32-bit TCE table at %08x..%08x\n",
		(base << 28), ((base + segs) << 28) - 1);

	/* XXX Currently, we allocate one big contiguous table for the
	 * TCEs. We only really need one chunk per 256M of TCE space
	 * (ie per segment) but that's an optimization for later, it
	 * requires some added smarts with our get/put_tce implementation
	 */
	tce_mem = alloc_pages_node(phb->hose->node, GFP_KERNEL,
				   get_order(TCE32_TABLE_SIZE * segs));
	if (!tce_mem) {
		pe_err(pe, " Failed to allocate a 32-bit TCE memory\n");
		goto fail;
	}
	addr = page_address(tce_mem);
	memset(addr, 0, TCE32_TABLE_SIZE * segs);

	/* Configure HW */
	for (i = 0; i < segs; i++) {
		rc = opal_pci_map_pe_dma_window(phb->opal_id,
					      pe->pe_number,
					      base + i, 1,
					      __pa(addr) + TCE32_TABLE_SIZE * i,
					      TCE32_TABLE_SIZE, 0x1000);
		if (rc) {
			pe_err(pe, " Failed to configure 32-bit TCE table,"
			       " err %ld\n", rc);
			goto fail;
		}
	}

	/* Setup linux iommu table */
	tbl = &pe->tce32_table;
	pnv_pci_setup_iommu_table(tbl, addr, TCE32_TABLE_SIZE * segs,
				  base << 28);

	/* OPAL variant of P7IOC SW invalidated TCEs */
	swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
	if (swinvp) {
		/* We need a couple more fields -- an address and a data
		 * to or.  Since the bus is only printed out on table free
		 * errors, and on the first pass the data will be a relative
		 * bus number, print that out instead.
		 */
		tbl->it_busno = 0;
637
638
639
		pe->tce_inval_reg_phys = be64_to_cpup(swinvp);
		tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys,
				8);
640
641
		tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE |
			       TCE_PCI_SWINV_PAIR;
642
643
	}
	iommu_init_table(tbl, phb->hose->node);
644
	iommu_register_group(tbl, pci_domain_nr(pe->pbus), pe->pe_number);
645

646
647
648
649
650
	if (pe->pdev)
		set_iommu_table_base(&pe->pdev->dev, tbl);
	else
		pnv_ioda_setup_bus_dma(pe, pe->pbus);

651
652
653
654
655
656
657
658
659
	return;
 fail:
	/* XXX Failure: Try to fallback to 64-bit only ? */
	if (pe->tce32_seg >= 0)
		pe->tce32_seg = -1;
	if (tce_mem)
		__free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs));
}

660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
				       struct pnv_ioda_pe *pe)
{
	struct page *tce_mem = NULL;
	void *addr;
	const __be64 *swinvp;
	struct iommu_table *tbl;
	unsigned int tce_table_size, end;
	int64_t rc;

	/* We shouldn't already have a 32-bit DMA associated */
	if (WARN_ON(pe->tce32_seg >= 0))
		return;

	/* The PE will reserve all possible 32-bits space */
	pe->tce32_seg = 0;
	end = (1 << ilog2(phb->ioda.m32_pci_base));
	tce_table_size = (end / 0x1000) * 8;
	pe_info(pe, "Setting up 32-bit TCE table at 0..%08x\n",
		end);

	/* Allocate TCE table */
	tce_mem = alloc_pages_node(phb->hose->node, GFP_KERNEL,
				   get_order(tce_table_size));
	if (!tce_mem) {
		pe_err(pe, "Failed to allocate a 32-bit TCE memory\n");
		goto fail;
	}
	addr = page_address(tce_mem);
	memset(addr, 0, tce_table_size);

	/*
	 * Map TCE table through TVT. The TVE index is the PE number
	 * shifted by 1 bit for 32-bits DMA space.
	 */
	rc = opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number,
					pe->pe_number << 1, 1, __pa(addr),
					tce_table_size, 0x1000);
	if (rc) {
		pe_err(pe, "Failed to configure 32-bit TCE table,"
		       " err %ld\n", rc);
		goto fail;
	}

	/* Setup linux iommu table */
	tbl = &pe->tce32_table;
	pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0);

	/* OPAL variant of PHB3 invalidated TCEs */
	swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
	if (swinvp) {
		/* We need a couple more fields -- an address and a data
		 * to or.  Since the bus is only printed out on table free
		 * errors, and on the first pass the data will be a relative
		 * bus number, print that out instead.
		 */
		tbl->it_busno = 0;
717
718
719
		pe->tce_inval_reg_phys = be64_to_cpup(swinvp);
		tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys,
				8);
720
721
722
723
		tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE;
	}
	iommu_init_table(tbl, phb->hose->node);

724
725
726
727
728
	if (pe->pdev)
		set_iommu_table_base(&pe->pdev->dev, tbl);
	else
		pnv_ioda_setup_bus_dma(pe, pe->pbus);

729
730
731
732
733
734
735
736
	return;
fail:
	if (pe->tce32_seg >= 0)
		pe->tce32_seg = -1;
	if (tce_mem)
		__free_pages(tce_mem, get_order(tce_table_size));
}

737
static void pnv_ioda_setup_dma(struct pnv_phb *phb)
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
{
	struct pci_controller *hose = phb->hose;
	unsigned int residual, remaining, segs, tw, base;
	struct pnv_ioda_pe *pe;

	/* If we have more PE# than segments available, hand out one
	 * per PE until we run out and let the rest fail. If not,
	 * then we assign at least one segment per PE, plus more based
	 * on the amount of devices under that PE
	 */
	if (phb->ioda.dma_pe_count > phb->ioda.tce32_count)
		residual = 0;
	else
		residual = phb->ioda.tce32_count -
			phb->ioda.dma_pe_count;

	pr_info("PCI: Domain %04x has %ld available 32-bit DMA segments\n",
		hose->global_number, phb->ioda.tce32_count);
	pr_info("PCI: %d PE# for a total weight of %d\n",
		phb->ioda.dma_pe_count, phb->ioda.dma_weight);

	/* Walk our PE list and configure their DMA segments, hand them
	 * out one base segment plus any residual segments based on
	 * weight
	 */
	remaining = phb->ioda.tce32_count;
	tw = phb->ioda.dma_weight;
	base = 0;
766
	list_for_each_entry(pe, &phb->ioda.pe_dma_list, dma_link) {
767
768
769
770
771
772
773
774
775
776
777
778
		if (!pe->dma_weight)
			continue;
		if (!remaining) {
			pe_warn(pe, "No DMA32 resources available\n");
			continue;
		}
		segs = 1;
		if (residual) {
			segs += ((pe->dma_weight * residual)  + (tw / 2)) / tw;
			if (segs > remaining)
				segs = remaining;
		}
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794

		/*
		 * For IODA2 compliant PHB3, we needn't care about the weight.
		 * The all available 32-bits DMA space will be assigned to
		 * the specific PE.
		 */
		if (phb->type == PNV_PHB_IODA1) {
			pe_info(pe, "DMA weight %d, assigned %d DMA32 segments\n",
				pe->dma_weight, segs);
			pnv_pci_ioda_setup_dma_pe(phb, pe, base, segs);
		} else {
			pe_info(pe, "Assign DMA32 space\n");
			segs = 0;
			pnv_pci_ioda2_setup_dma_pe(phb, pe);
		}

795
796
797
798
799
800
		remaining -= segs;
		base += segs;
	}
}

#ifdef CONFIG_PCI_MSI
801
802
803
804
805
806
807
808
809
810
811
812
813
814
static void pnv_ioda2_msi_eoi(struct irq_data *d)
{
	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
	struct irq_chip *chip = irq_data_get_irq_chip(d);
	struct pnv_phb *phb = container_of(chip, struct pnv_phb,
					   ioda.irq_chip);
	int64_t rc;

	rc = opal_pci_msi_eoi(phb->opal_id, hw_irq);
	WARN_ON_ONCE(rc);

	icp_native_eoi(d);
}

815
static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
816
817
				  unsigned int hwirq, unsigned int virq,
				  unsigned int is_64, struct msi_msg *msg)
818
819
{
	struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev);
820
	struct pci_dn *pdn = pci_get_pdn(dev);
821
822
	struct irq_data *idata;
	struct irq_chip *ichip;
823
	unsigned int xive_num = hwirq - phb->msi_base;
824
	__be32 data;
825
826
827
828
829
830
831
832
833
834
	int rc;

	/* No PE assigned ? bail out ... no MSI for you ! */
	if (pe == NULL)
		return -ENXIO;

	/* Check if we have an MVE */
	if (pe->mve_number < 0)
		return -ENXIO;

835
836
837
838
	/* Force 32-bit MSI on some broken devices */
	if (pdn && pdn->force_32bit_msi)
		is_64 = 0;

839
840
841
842
843
844
845
846
847
	/* Assign XIVE to PE */
	rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num);
	if (rc) {
		pr_warn("%s: OPAL error %d setting XIVE %d PE\n",
			pci_name(dev), rc, xive_num);
		return -EIO;
	}

	if (is_64) {
848
849
		__be64 addr64;

850
851
852
853
854
855
856
		rc = opal_get_msi_64(phb->opal_id, pe->mve_number, xive_num, 1,
				     &addr64, &data);
		if (rc) {
			pr_warn("%s: OPAL error %d getting 64-bit MSI data\n",
				pci_name(dev), rc);
			return -EIO;
		}
857
858
		msg->address_hi = be64_to_cpu(addr64) >> 32;
		msg->address_lo = be64_to_cpu(addr64) & 0xfffffffful;
859
	} else {
860
861
		__be32 addr32;

862
863
864
865
866
867
868
869
		rc = opal_get_msi_32(phb->opal_id, pe->mve_number, xive_num, 1,
				     &addr32, &data);
		if (rc) {
			pr_warn("%s: OPAL error %d getting 32-bit MSI data\n",
				pci_name(dev), rc);
			return -EIO;
		}
		msg->address_hi = 0;
870
		msg->address_lo = be32_to_cpu(addr32);
871
	}
872
	msg->data = be32_to_cpu(data);
873

874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
	/*
	 * Change the IRQ chip for the MSI interrupts on PHB3.
	 * The corresponding IRQ chip should be populated for
	 * the first time.
	 */
	if (phb->type == PNV_PHB_IODA2) {
		if (!phb->ioda.irq_chip_init) {
			idata = irq_get_irq_data(virq);
			ichip = irq_data_get_irq_chip(idata);
			phb->ioda.irq_chip_init = 1;
			phb->ioda.irq_chip = *ichip;
			phb->ioda.irq_chip.irq_eoi = pnv_ioda2_msi_eoi;
		}

		irq_set_chip(virq, &phb->ioda.irq_chip);
	}

891
892
893
894
895
896
897
898
899
900
	pr_devel("%s: %s-bit MSI on hwirq %x (xive #%d),"
		 " address=%x_%08x data=%x PE# %d\n",
		 pci_name(dev), is_64 ? "64" : "32", hwirq, xive_num,
		 msg->address_hi, msg->address_lo, data, pe->pe_number);

	return 0;
}

static void pnv_pci_init_ioda_msis(struct pnv_phb *phb)
{
901
	unsigned int count;
902
903
904
905
906
907
908
909
910
911
	const __be32 *prop = of_get_property(phb->hose->dn,
					     "ibm,opal-msi-ranges", NULL);
	if (!prop) {
		/* BML Fallback */
		prop = of_get_property(phb->hose->dn, "msi-ranges", NULL);
	}
	if (!prop)
		return;

	phb->msi_base = be32_to_cpup(prop);
912
913
	count = be32_to_cpup(prop + 1);
	if (msi_bitmap_alloc(&phb->msi_bmp, count, phb->hose->dn)) {
914
915
916
917
		pr_err("PCI %d: Failed to allocate MSI bitmap !\n",
		       phb->hose->global_number);
		return;
	}
918

919
920
921
	phb->msi_setup = pnv_pci_ioda_msi_setup;
	phb->msi32_support = 1;
	pr_info("  Allocated bitmap for %d MSIs (base IRQ 0x%x)\n",
922
		count, phb->msi_base);
923
924
925
926
927
}
#else
static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { }
#endif /* CONFIG_PCI_MSI */

928
929
930
931
932
/*
 * This function is supposed to be called on basis of PE from top
 * to bottom style. So the the I/O or MMIO segment assigned to
 * parent PE could be overrided by its child PEs if necessary.
 */
933
934
static void pnv_ioda_setup_pe_seg(struct pci_controller *hose,
				  struct pnv_ioda_pe *pe)
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
{
	struct pnv_phb *phb = hose->private_data;
	struct pci_bus_region region;
	struct resource *res;
	int i, index;
	int rc;

	/*
	 * NOTE: We only care PCI bus based PE for now. For PCI
	 * device based PE, for example SRIOV sensitive VF should
	 * be figured out later.
	 */
	BUG_ON(!(pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)));

	pci_bus_for_each_resource(pe->pbus, res, i) {
		if (!res || !res->flags ||
		    res->start > res->end)
			continue;

		if (res->flags & IORESOURCE_IO) {
			region.start = res->start - phb->ioda.io_pci_base;
			region.end   = res->end - phb->ioda.io_pci_base;
			index = region.start / phb->ioda.io_segsize;

			while (index < phb->ioda.total_pe &&
			       region.start <= region.end) {
				phb->ioda.io_segmap[index] = pe->pe_number;
				rc = opal_pci_map_pe_mmio_window(phb->opal_id,
					pe->pe_number, OPAL_IO_WINDOW_TYPE, 0, index);
				if (rc != OPAL_SUCCESS) {
					pr_err("%s: OPAL error %d when mapping IO "
					       "segment #%d to PE#%d\n",
					       __func__, rc, index, pe->pe_number);
					break;
				}

				region.start += phb->ioda.io_segsize;
				index++;
			}
		} else if (res->flags & IORESOURCE_MEM) {
975
976
977
			/* WARNING: Assumes M32 is mem region 0 in PHB. We need to
			 * harden that algorithm when we start supporting M64
			 */
978
			region.start = res->start -
979
				       hose->mem_offset[0] -
980
981
				       phb->ioda.m32_pci_base;
			region.end   = res->end -
982
				       hose->mem_offset[0] -
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
				       phb->ioda.m32_pci_base;
			index = region.start / phb->ioda.m32_segsize;

			while (index < phb->ioda.total_pe &&
			       region.start <= region.end) {
				phb->ioda.m32_segmap[index] = pe->pe_number;
				rc = opal_pci_map_pe_mmio_window(phb->opal_id,
					pe->pe_number, OPAL_M32_WINDOW_TYPE, 0, index);
				if (rc != OPAL_SUCCESS) {
					pr_err("%s: OPAL error %d when mapping M32 "
					       "segment#%d to PE#%d",
					       __func__, rc, index, pe->pe_number);
					break;
				}

				region.start += phb->ioda.m32_segsize;
				index++;
			}
		}
	}
}

1005
static void pnv_pci_ioda_setup_seg(void)
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
{
	struct pci_controller *tmp, *hose;
	struct pnv_phb *phb;
	struct pnv_ioda_pe *pe;

	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
		phb = hose->private_data;
		list_for_each_entry(pe, &phb->ioda.pe_list, list) {
			pnv_ioda_setup_pe_seg(hose, pe);
		}
	}
}

1019
static void pnv_pci_ioda_setup_DMA(void)
1020
1021
{
	struct pci_controller *hose, *tmp;
1022
	struct pnv_phb *phb;
1023
1024
1025

	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
		pnv_ioda_setup_dma(hose->private_data);
1026
1027
1028
1029

		/* Mark the PHB initialization done */
		phb = hose->private_data;
		phb->initialized = 1;
1030
1031
1032
	}
}

1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
static void pnv_pci_ioda_create_dbgfs(void)
{
#ifdef CONFIG_DEBUG_FS
	struct pci_controller *hose, *tmp;
	struct pnv_phb *phb;
	char name[16];

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

		sprintf(name, "PCI%04x", hose->global_number);
		phb->dbgfs = debugfs_create_dir(name, powerpc_debugfs_root);
		if (!phb->dbgfs)
			pr_warning("%s: Error on creating debugfs on PHB#%x\n",
				__func__, hose->global_number);
	}
#endif /* CONFIG_DEBUG_FS */
}

1052
static void pnv_pci_ioda_fixup(void)
1053
1054
{
	pnv_pci_ioda_setup_PEs();
1055
	pnv_pci_ioda_setup_seg();
1056
	pnv_pci_ioda_setup_DMA();
1057

1058
1059
	pnv_pci_ioda_create_dbgfs();

1060
#ifdef CONFIG_EEH
1061
	eeh_probe_mode_set(EEH_PROBE_MODE_DEV);
1062
1063
1064
	eeh_addr_cache_build();
	eeh_init();
#endif
1065
1066
}

1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
/*
 * Returns the alignment for I/O or memory windows for P2P
 * bridges. That actually depends on how PEs are segmented.
 * For now, we return I/O or M32 segment size for PE sensitive
 * P2P bridges. Otherwise, the default values (4KiB for I/O,
 * 1MiB for memory) will be returned.
 *
 * The current PCI bus might be put into one PE, which was
 * create against the parent PCI bridge. For that case, we
 * needn't enlarge the alignment so that we can save some
 * resources.
 */
static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus,
						unsigned long type)
{
	struct pci_dev *bridge;
	struct pci_controller *hose = pci_bus_to_host(bus);
	struct pnv_phb *phb = hose->private_data;
	int num_pci_bridges = 0;

	bridge = bus->self;
	while (bridge) {
		if (pci_pcie_type(bridge) == PCI_EXP_TYPE_PCI_BRIDGE) {
			num_pci_bridges++;
			if (num_pci_bridges >= 2)
				return 1;
		}

		bridge = bridge->bus->self;
	}

	/* We need support prefetchable memory window later */
	if (type & IORESOURCE_MEM)
		return phb->ioda.m32_segsize;

	return phb->ioda.io_segsize;
}

1105
1106
1107
/* Prevent enabling devices for which we couldn't properly
 * assign a PE
 */
1108
static int pnv_pci_enable_device_hook(struct pci_dev *dev)
1109
{
1110
1111
1112
	struct pci_controller *hose = pci_bus_to_host(dev->bus);
	struct pnv_phb *phb = hose->private_data;
	struct pci_dn *pdn;
1113

1114
1115
1116
1117
1118
1119
1120
1121
	/* The function is probably called while the PEs have
	 * not be created yet. For example, resource reassignment
	 * during PCI probe period. We just skip the check if
	 * PEs isn't ready.
	 */
	if (!phb->initialized)
		return 0;

1122
	pdn = pci_get_pdn(dev);
1123
1124
	if (!pdn || pdn->pe_number == IODA_INVALID_PE)
		return -EINVAL;
1125

1126
1127
1128
1129
1130
1131
1132
1133
1134
	return 0;
}

static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus,
			       u32 devfn)
{
	return phb->ioda.pe_rmap[(bus->number << 8) | devfn];
}

1135
1136
1137
1138
1139
1140
static void pnv_pci_ioda_shutdown(struct pnv_phb *phb)
{
	opal_pci_reset(phb->opal_id, OPAL_PCI_IODA_TABLE_RESET,
		       OPAL_ASSERT_RESET);
}

1141
1142
void __init pnv_pci_init_ioda_phb(struct device_node *np,
				  u64 hub_id, int ioda_type)
1143
1144
1145
1146
{
	struct pci_controller *hose;
	struct pnv_phb *phb;
	unsigned long size, m32map_off, iomap_off, pemap_off;
1147
	const __be64 *prop64;
1148
	const __be32 *prop32;
1149
	int len;
1150
1151
1152
1153
	u64 phb_id;
	void *aux;
	long rc;

1154
	pr_info("Initializing IODA%d OPAL PHB %s\n", ioda_type, np->full_name);
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164

	prop64 = of_get_property(np, "ibm,opal-phbid", NULL);
	if (!prop64) {
		pr_err("  Missing \"ibm,opal-phbid\" property !\n");
		return;
	}
	phb_id = be64_to_cpup(prop64);
	pr_debug("  PHB-ID  : 0x%016llx\n", phb_id);

	phb = alloc_bootmem(sizeof(struct pnv_phb));
1165
1166
1167
	if (!phb) {
		pr_err("  Out of memory !\n");
		return;
1168
	}
1169
1170
1171
1172
1173
1174

	/* Allocate PCI controller */
	memset(phb, 0, sizeof(struct pnv_phb));
	phb->hose = hose = pcibios_alloc_controller(np);
	if (!phb->hose) {
		pr_err("  Can't allocate PCI controller for %s\n",
1175
		       np->full_name);
1176
		free_bootmem((unsigned long)phb, sizeof(struct pnv_phb));
1177
1178
1179
1180
		return;
	}

	spin_lock_init(&phb->lock);
1181
1182
	prop32 = of_get_property(np, "bus-range", &len);
	if (prop32 && len == 8) {
1183
1184
		hose->first_busno = be32_to_cpu(prop32[0]);
		hose->last_busno = be32_to_cpu(prop32[1]);
1185
1186
1187
1188
1189
	} else {
		pr_warn("  Broken <bus-range> on %s\n", np->full_name);
		hose->first_busno = 0;
		hose->last_busno = 0xff;
	}
1190
	hose->private_data = phb;
1191
	phb->hub_id = hub_id;
1192
	phb->opal_id = phb_id;
Gavin Shan's avatar
Gavin Shan committed
1193
	phb->type = ioda_type;
1194

1195
1196
1197
	/* Detect specific models for error handling */
	if (of_device_is_compatible(np, "ibm,p7ioc-pciex"))
		phb->model = PNV_PHB_MODEL_P7IOC;
1198
	else if (of_device_is_compatible(np, "ibm,power8-pciex"))
Gavin Shan's avatar
Gavin Shan committed
1199
		phb->model = PNV_PHB_MODEL_PHB3;
1200
1201
1202
	else
		phb->model = PNV_PHB_MODEL_UNKNOWN;

Gavin Shan's avatar
Gavin Shan committed
1203
	/* Parse 32-bit and IO ranges (if any) */
1204
	pci_process_bridge_OF_ranges(hose, np, !hose->global_number);
1205

Gavin Shan's avatar
Gavin Shan committed
1206
	/* Get registers */
1207
1208
1209
1210
1211
	phb->regs = of_iomap(np, 0);
	if (phb->regs == NULL)
		pr_err("  Failed to map registers !\n");

	/* Initialize more IODA stuff */
1212
	phb->ioda.total_pe = 1;
Gavin Shan's avatar
Gavin Shan committed
1213
	prop32 = of_get_property(np, "ibm,opal-num-pes", NULL);
1214
	if (prop32)
1215
		phb->ioda.total_pe = be32_to_cpup(prop32);
1216
1217
1218
	prop32 = of_get_property(np, "ibm,opal-reserved-pe", NULL);
	if (prop32)
		phb->ioda.reserved_pe = be32_to_cpup(prop32);
1219
	phb->ioda.m32_size = resource_size(&hose->mem_resources[0]);
Gavin Shan's avatar
Gavin Shan committed
1220
	/* FW Has already off top 64k of M32 space (MSI space) */
1221
1222
1223
	phb->ioda.m32_size += 0x10000;

	phb->ioda.m32_segsize = phb->ioda.m32_size / phb->ioda.total_pe;
1224
	phb->ioda.m32_pci_base = hose->mem_resources[0].start - hose->mem_offset[0];
1225
1226
1227
1228
	phb->ioda.io_size = hose->pci_io_size;
	phb->ioda.io_segsize = phb->ioda.io_size / phb->ioda.total_pe;
	phb->ioda.io_pci_base = 0; /* XXX calculate this ? */

1229
	/* Allocate aux data & arrays. We don't have IO ports on PHB3 */
1230
1231
	size = _ALIGN_UP(phb->ioda.total_pe / 8, sizeof(unsigned long));
	m32map_off = size;
1232
	size += phb->ioda.total_pe * sizeof(phb->ioda.m32_segmap[0]);
1233
	iomap_off = size;
1234
1235
1236
1237
	if (phb->type == PNV_PHB_IODA1) {
		iomap_off = size;
		size += phb->ioda.total_pe * sizeof(phb->ioda.io_segmap[0]);
	}
1238
1239
1240
1241
1242
1243
	pemap_off = size;
	size += phb->ioda.total_pe * sizeof(struct pnv_ioda_pe);
	aux = alloc_bootmem(size);
	memset(aux, 0, size);
	phb->ioda.pe_alloc = aux;
	phb->ioda.m32_segmap = aux + m32map_off;
1244
1245
	if (phb->type == PNV_PHB_IODA1)
		phb->ioda.io_segmap = aux + iomap_off;
1246
	phb->ioda.pe_array = aux + pemap_off;
1247
	set_bit(phb->ioda.reserved_pe, phb->ioda.pe_alloc);
1248

1249
	INIT_LIST_HEAD(&phb->ioda.pe_dma_list);
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
	INIT_LIST_HEAD(&phb->ioda.pe_list);

	/* Calculate how many 32-bit TCE segments we have */
	phb->ioda.tce32_count = phb->ioda.m32_pci_base >> 28;

	/* Clear unusable m64 */
	hose->mem_resources[1].flags = 0;
	hose->mem_resources[1].start = 0;
	hose->mem_resources[1].end = 0;
	hose->mem_resources[2].flags = 0;
	hose->mem_resources[2].start = 0;
	hose->mem_resources[2].end = 0;

Gavin Shan's avatar
Gavin Shan committed
1263
#if 0 /* We should really do that ... */
1264
1265
1266
1267
1268
1269
1270
1271
	rc = opal_pci_set_phb_mem_window(opal->phb_id,
					 window_type,
					 window_num,
					 starting_real_address,
					 starting_pci_address,
					 segment_size);
#endif

1272
1273
	pr_info("  %d (%d) PE's M32: 0x%x [segment=0x%x]"
		" IO: 0x%x [segment=0x%x]\n",
1274
		phb->ioda.total_pe,
1275
		phb->ioda.reserved_pe,
1276
1277
1278
1279
		phb->ioda.m32_size, phb->ioda.m32_segsize,
		phb->ioda.io_size, phb->ioda.io_segsize);

	phb->hose->ops = &pnv_pci_ops;
1280
1281
1282
#ifdef CONFIG_EEH
	phb->eeh_ops = &ioda_eeh_ops;
#endif
1283
1284
1285
1286
1287
1288
1289

	/* Setup RID -> PE mapping function */
	phb->bdfn_to_pe = pnv_ioda_bdfn_to_pe;

	/* Setup TCEs */
	phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;

1290
1291
1292
	/* Setup shutdown function for kexec */
	phb->shutdown = pnv_pci_ioda_shutdown;

1293
1294
1295
	/* Setup MSI support */
	pnv_pci_init_ioda_msis(phb);

1296
1297
1298
1299
1300
1301
	/*
	 * We pass the PCI probe flag PCI_REASSIGN_ALL_RSRC here
	 * to let the PCI core do resource assignment. It's supposed
	 * that the PCI core will do correct I/O and MMIO alignment
	 * for the P2P bridge bars so that each PCI bus (excluding
	 * the child P2P bridges) can form individual PE.
1302
	 */
1303
	ppc_md.pcibios_fixup = pnv_pci_ioda_fixup;
1304
	ppc_md.pcibios_enable_device_hook = pnv_pci_enable_device_hook;
1305
	ppc_md.pcibios_window_alignment = pnv_pci_window_alignment;
1306
	pci_add_flags(PCI_REASSIGN_ALL_RSRC);
1307
1308

	/* Reset IODA tables to a clean state */
1309
	rc = opal_pci_reset(phb_id, OPAL_PCI_IODA_TABLE_RESET, OPAL_ASSERT_RESET);
1310
	if (rc)
1311
		pr_warning("  OPAL Error %ld performing IODA table reset !\n", rc);
Gavin Shan's avatar
Gavin Shan committed
1312
1313
}

1314
void __init pnv_pci_init_ioda2_phb(struct device_node *np)
Gavin Shan's avatar
Gavin Shan committed
1315
{
1316
	pnv_pci_init_ioda_phb(np, 0, PNV_PHB_IODA2);
1317
1318
1319
1320
1321
}

void __init pnv_pci_init_ioda_hub(struct device_node *np)
{
	struct device_node *phbn;
1322
	const __be64 *prop64;
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
	u64 hub_id;

	pr_info("Probing IODA IO-Hub %s\n", np->full_name);

	prop64 = of_get_property(np, "ibm,opal-hubid", NULL);
	if (!prop64) {
		pr_err(" Missing \"ibm,opal-hubid\" property !\n");
		return;
	}
	hub_id = be64_to_cpup(prop64);
	pr_devel(" HUB-ID : 0x%016llx\n", hub_id);

	/* Count child PHBs */
	for_each_child_of_node(np, phbn) {
		/* Look for IODA1 PHBs */
		if (of_device_is_compatible(phbn, "ibm,ioda-phb"))
1339
			pnv_pci_init_ioda_phb(phbn, hub_id, PNV_PHB_IODA1);
1340
1341
	}
}