summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/sysdev/cpm1.c
blob: 5e6ff38ea69f197a873e9f47923d9f3434107221 (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
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
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
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
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
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
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
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
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
/*
 * General Purpose functions for the global management of the
 * Communication Processor Module.
 * Copyright (c) 1997 Dan error_act (dmalek@jlc.net)
 *
 * In addition to the individual control of the communication
 * channels, there are a few functions that globally affect the
 * communication processor.
 *
 * Buffer descriptors must be allocated from the dual ported memory
 * space.  The allocator for that is here.  When the communication
 * process is reset, we reclaim the memory available.  There is
 * currently no deallocator for this memory.
 * The amount of space available is platform dependent.  On the
 * MBX, the EPPC software loads additional microcode into the
 * communication processor, and uses some of the DP ram for this
 * purpose.  Current, the first 512 bytes and the last 256 bytes of
 * memory are used.  Right now I am conservative and only use the
 * memory that can never be used for microcode.  If there are
 * applications that require more DP ram, we can expand the boundaries
 * but then we have to be careful of any downloaded microcode.
 */
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/dma-mapping.h>
#include <linux/param.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/8xx_immap.h>
#include <asm/cpm1.h>
#include <asm/io.h>
#include <asm/tlbflush.h>
#include <asm/rheap.h>
#include <asm/prom.h>
#include <asm/cpm.h>

#include <asm/fs_pd.h>

#ifdef CONFIG_8xx_GPIO
#include <linux/of_gpio.h>
#endif

#define CPM_MAP_SIZE    (0x4000)

cpm8xx_t __iomem *cpmp;  /* Pointer to comm processor space */
immap_t __iomem *mpc8xx_immr;
static cpic8xx_t __iomem *cpic_reg;

static struct irq_domain *cpm_pic_host;

static void cpm_mask_irq(struct irq_data *d)
{
	unsigned int cpm_vec = (unsigned int)irqd_to_hwirq(d);

	clrbits32(&cpic_reg->cpic_cimr, (1 << cpm_vec));
}

static void cpm_unmask_irq(struct irq_data *d)
{
	unsigned int cpm_vec = (unsigned int)irqd_to_hwirq(d);

	setbits32(&cpic_reg->cpic_cimr, (1 << cpm_vec));
}

static void cpm_end_irq(struct irq_data *d)
{
	unsigned int cpm_vec = (unsigned int)irqd_to_hwirq(d);

	out_be32(&cpic_reg->cpic_cisr, (1 << cpm_vec));
}

static struct irq_chip cpm_pic = {
	.name = "CPM PIC",
	.irq_mask = cpm_mask_irq,
	.irq_unmask = cpm_unmask_irq,
	.irq_eoi = cpm_end_irq,
};

int cpm_get_irq(void)
{
	int cpm_vec;

	/* Get the vector by setting the ACK bit and then reading
	 * the register.
	 */
	out_be16(&cpic_reg->cpic_civr, 1);
	cpm_vec = in_be16(&cpic_reg->cpic_civr);
	cpm_vec >>= 11;

	return irq_linear_revmap(cpm_pic_host, cpm_vec);
}

static int cpm_pic_host_map(struct irq_domain *h, unsigned int virq,
			  irq_hw_number_t hw)
{
	pr_debug("cpm_pic_host_map(%d, 0x%lx)\n", virq, hw);

	irq_set_status_flags(virq, IRQ_LEVEL);
	irq_set_chip_and_handler(virq, &cpm_pic, handle_fasteoi_irq);
	return 0;
}

/* The CPM can generate the error interrupt when there is a race condition
 * between generating and masking interrupts.  All we have to do is ACK it
 * and return.  This is a no-op function so we don't need any special
 * tests in the interrupt handler.
 */
static irqreturn_t cpm_error_interrupt(int irq, void *dev)
{
	return IRQ_HANDLED;
}

static struct irqaction cpm_error_irqaction = {
	.handler = cpm_error_interrupt,
	.flags = IRQF_NO_THREAD,
	.name = "error",
};

static const struct irq_domain_ops cpm_pic_host_ops = {
	.map = cpm_pic_host_map,
};

unsigned int cpm_pic_init(void)
{
	struct device_node *np = NULL;
	struct resource res;
	unsigned int sirq = NO_IRQ, hwirq, eirq;
	int ret;

	pr_debug("cpm_pic_init\n");

	np = of_find_compatible_node(NULL, NULL, "fsl,cpm1-pic");
	if (np == NULL)
		np = of_find_compatible_node(NULL, "cpm-pic", "CPM");
	if (np == NULL) {
		printk(KERN_ERR "CPM PIC init: can not find cpm-pic node\n");
		return sirq;
	}

	ret = of_address_to_resource(np, 0, &res);
	if (ret)
		goto end;

	cpic_reg = ioremap(res.start, resource_size(&res));
	if (cpic_reg == NULL)
		goto end;

	sirq = irq_of_parse_and_map(np, 0);
	if (sirq == NO_IRQ)
		goto end;

	/* Initialize the CPM interrupt controller. */
	hwirq = (unsigned int)virq_to_hw(sirq);
	out_be32(&cpic_reg->cpic_cicr,
	    (CICR_SCD_SCC4 | CICR_SCC_SCC3 | CICR_SCB_SCC2 | CICR_SCA_SCC1) |
		((hwirq/2) << 13) | CICR_HP_MASK);

	out_be32(&cpic_reg->cpic_cimr, 0);

	cpm_pic_host = irq_domain_add_linear(np, 64, &cpm_pic_host_ops, NULL);
	if (cpm_pic_host == NULL) {
		printk(KERN_ERR "CPM2 PIC: failed to allocate irq host!\n");
		sirq = NO_IRQ;
		goto end;
	}

	/* Install our own error handler. */
	np = of_find_compatible_node(NULL, NULL, "fsl,cpm1");
	if (np == NULL)
		np = of_find_node_by_type(NULL, "cpm");
	if (np == NULL) {
		printk(KERN_ERR "CPM PIC init: can not find cpm node\n");
		goto end;
	}

	eirq = irq_of_parse_and_map(np, 0);
	if (eirq == NO_IRQ)
		goto end;

	if (setup_irq(eirq, &cpm_error_irqaction))
		printk(KERN_ERR "Could not allocate CPM error IRQ!");

	setbits32(&cpic_reg->cpic_cicr, CICR_IEN);

end:
	of_node_put(np);
	return sirq;
}

void __init cpm_reset(void)
{
	sysconf8xx_t __iomem *siu_conf;

	mpc8xx_immr = ioremap(get_immrbase(), 0x4000);
	if (!mpc8xx_immr) {
		printk(KERN_CRIT "Could not map IMMR\n");
		return;
	}

	cpmp = &mpc8xx_immr->im_cpm;

#ifndef CONFIG_PPC_EARLY_DEBUG_CPM
	/* Perform a reset.
	*/
	out_be16(&cpmp->cp_cpcr, CPM_CR_RST | CPM_CR_FLG);

	/* Wait for it.
	*/
	while (in_be16(&cpmp->cp_cpcr) & CPM_CR_FLG);
#endif

#ifdef CONFIG_UCODE_PATCH
	cpm_load_patch(cpmp);
#endif

	/* Set SDMA Bus Request priority 5.
	 * On 860T, this also enables FEC priority 6.  I am not sure
	 * this is what we really want for some applications, but the
	 * manual recommends it.
	 * Bit 25, FAM can also be set to use FEC aggressive mode (860T).
	 */
	siu_conf = immr_map(im_siu_conf);
	out_be32(&siu_conf->sc_sdcr, 1);
	immr_unmap(siu_conf);

	cpm_muram_init();
}

static DEFINE_SPINLOCK(cmd_lock);

#define MAX_CR_CMD_LOOPS        10000

int cpm_command(u32 command, u8 opcode)
{
	int i, ret;
	unsigned long flags;

	if (command & 0xffffff0f)
		return -EINVAL;

	spin_lock_irqsave(&cmd_lock, flags);

	ret = 0;
	out_be16(&cpmp->cp_cpcr, command | CPM_CR_FLG | (opcode << 8));
	for (i = 0; i < MAX_CR_CMD_LOOPS; i++)
		if ((in_be16(&cpmp->cp_cpcr) & CPM_CR_FLG) == 0)
			goto out;

	printk(KERN_ERR "%s(): Not able to issue CPM command\n", __func__);
	ret = -EIO;
out:
	spin_unlock_irqrestore(&cmd_lock, flags);
	return ret;
}
EXPORT_SYMBOL(cpm_command);

/* Set a baud rate generator.  This needs lots of work.  There are
 * four BRGs, any of which can be wired to any channel.
 * The internal baud rate clock is the system clock divided by 16.
 * This assumes the baudrate is 16x oversampled by the uart.
 */
#define BRG_INT_CLK		(get_brgfreq())
#define BRG_UART_CLK		(BRG_INT_CLK/16)
#define BRG_UART_CLK_DIV16	(BRG_UART_CLK/16)

void
cpm_setbrg(uint brg, uint rate)
{
	u32 __iomem *bp;

	/* This is good enough to get SMCs running.....
	*/
	bp = &cpmp->cp_brgc1;
	bp += brg;
	/* The BRG has a 12-bit counter.  For really slow baud rates (or
	 * really fast processors), we may have to further divide by 16.
	 */
	if (((BRG_UART_CLK / rate) - 1) < 4096)
		out_be32(bp, (((BRG_UART_CLK / rate) - 1) << 1) | CPM_BRG_EN);
	else
		out_be32(bp, (((BRG_UART_CLK_DIV16 / rate) - 1) << 1) |
			      CPM_BRG_EN | CPM_BRG_DIV16);
}

struct cpm_ioport16 {
	__be16 dir, par, odr_sor, dat, intr;
	__be16 res[3];
};

struct cpm_ioport32b {
	__be32 dir, par, odr, dat;
};

struct cpm_ioport32e {
	__be32 dir, par, sor, odr, dat;
};

static void cpm1_set_pin32(int port, int pin, int flags)
{
	struct cpm_ioport32e __iomem *iop;
	pin = 1 << (31 - pin);

	if (port == CPM_PORTB)
		iop = (struct cpm_ioport32e __iomem *)
		      &mpc8xx_immr->im_cpm.cp_pbdir;
	else
		iop = (struct cpm_ioport32e __iomem *)
		      &mpc8xx_immr->im_cpm.cp_pedir;

	if (flags & CPM_PIN_OUTPUT)
		setbits32(&iop->dir, pin);
	else
		clrbits32(&iop->dir, pin);

	if (!(flags & CPM_PIN_GPIO))
		setbits32(&iop->par, pin);
	else
		clrbits32(&iop->par, pin);

	if (port == CPM_PORTB) {
		if (flags & CPM_PIN_OPENDRAIN)
			setbits16(&mpc8xx_immr->im_cpm.cp_pbodr, pin);
		else
			clrbits16(&mpc8xx_immr->im_cpm.cp_pbodr, pin);
	}

	if (port == CPM_PORTE) {
		if (flags & CPM_PIN_SECONDARY)
			setbits32(&iop->sor, pin);
		else
			clrbits32(&iop->sor, pin);

		if (flags & CPM_PIN_OPENDRAIN)
			setbits32(&mpc8xx_immr->im_cpm.cp_peodr, pin);
		else
			clrbits32(&mpc8xx_immr->im_cpm.cp_peodr, pin);
	}
}

static void cpm1_set_pin16(int port, int pin, int flags)
{
	struct cpm_ioport16 __iomem *iop =
		(struct cpm_ioport16 __iomem *)&mpc8xx_immr->im_ioport;

	pin = 1 << (15 - pin);

	if (port != 0)
		iop += port - 1;

	if (flags & CPM_PIN_OUTPUT)
		setbits16(&iop->dir, pin);
	else
		clrbits16(&iop->dir, pin);

	if (!(flags & CPM_PIN_GPIO))
		setbits16(&iop->par, pin);
	else
		clrbits16(&iop->par, pin);

	if (port == CPM_PORTA) {
		if (flags & CPM_PIN_OPENDRAIN)
			setbits16(&iop->odr_sor, pin);
		else
			clrbits16(&iop->odr_sor, pin);
	}
	if (port == CPM_PORTC) {
		if (flags & CPM_PIN_SECONDARY)
			setbits16(&iop->odr_sor, pin);
		else
			clrbits16(&iop->odr_sor, pin);
	}
}

void cpm1_set_pin(enum cpm_port port, int pin, int flags)
{
	if (port == CPM_PORTB || port == CPM_PORTE)
		cpm1_set_pin32(port, pin, flags);
	else
		cpm1_set_pin16(port, pin, flags);
}

int cpm1_clk_setup(enum cpm_clk_target target, int clock, int mode)
{
	int shift;
	int i, bits = 0;
	u32 __iomem *reg;
	u32 mask = 7;

	u8 clk_map[][3] = {
		{CPM_CLK_SCC1, CPM_BRG1, 0},
		{CPM_CLK_SCC1, CPM_BRG2, 1},
		{CPM_CLK_SCC1, CPM_BRG3, 2},
		{CPM_CLK_SCC1, CPM_BRG4, 3},
		{CPM_CLK_SCC1, CPM_CLK1, 4},
		{CPM_CLK_SCC1, CPM_CLK2, 5},
		{CPM_CLK_SCC1, CPM_CLK3, 6},
		{CPM_CLK_SCC1, CPM_CLK4, 7},

		{CPM_CLK_SCC2, CPM_BRG1, 0},
		{CPM_CLK_SCC2, CPM_BRG2, 1},
		{CPM_CLK_SCC2, CPM_BRG3, 2},
		{CPM_CLK_SCC2, CPM_BRG4, 3},
		{CPM_CLK_SCC2, CPM_CLK1, 4},
		{CPM_CLK_SCC2, CPM_CLK2, 5},
		{CPM_CLK_SCC2, CPM_CLK3, 6},
		{CPM_CLK_SCC2, CPM_CLK4, 7},

		{CPM_CLK_SCC3, CPM_BRG1, 0},
		{CPM_CLK_SCC3, CPM_BRG2, 1},
		{CPM_CLK_SCC3, CPM_BRG3, 2},
		{CPM_CLK_SCC3, CPM_BRG4, 3},
		{CPM_CLK_SCC3, CPM_CLK5, 4},
		{CPM_CLK_SCC3, CPM_CLK6, 5},
		{CPM_CLK_SCC3, CPM_CLK7, 6},
		{CPM_CLK_SCC3, CPM_CLK8, 7},

		{CPM_CLK_SCC4, CPM_BRG1, 0},
		{CPM_CLK_SCC4, CPM_BRG2, 1},
		{CPM_CLK_SCC4, CPM_BRG3, 2},
		{CPM_CLK_SCC4, CPM_BRG4, 3},
		{CPM_CLK_SCC4, CPM_CLK5, 4},
		{CPM_CLK_SCC4, CPM_CLK6, 5},
		{CPM_CLK_SCC4, CPM_CLK7, 6},
		{CPM_CLK_SCC4, CPM_CLK8, 7},

		{CPM_CLK_SMC1, CPM_BRG1, 0},
		{CPM_CLK_SMC1, CPM_BRG2, 1},
		{CPM_CLK_SMC1, CPM_BRG3, 2},
		{CPM_CLK_SMC1, CPM_BRG4, 3},
		{CPM_CLK_SMC1, CPM_CLK1, 4},
		{CPM_CLK_SMC1, CPM_CLK2, 5},
		{CPM_CLK_SMC1, CPM_CLK3, 6},
		{CPM_CLK_SMC1, CPM_CLK4, 7},

		{CPM_CLK_SMC2, CPM_BRG1, 0},
		{CPM_CLK_SMC2, CPM_BRG2, 1},
		{CPM_CLK_SMC2, CPM_BRG3, 2},
		{CPM_CLK_SMC2, CPM_BRG4, 3},
		{CPM_CLK_SMC2, CPM_CLK5, 4},
		{CPM_CLK_SMC2, CPM_CLK6, 5},
		{CPM_CLK_SMC2, CPM_CLK7, 6},
		{CPM_CLK_SMC2, CPM_CLK8, 7},
	};

	switch (target) {
	case CPM_CLK_SCC1:
		reg = &mpc8xx_immr->im_cpm.cp_sicr;
		shift = 0;
		break;

	case CPM_CLK_SCC2:
		reg = &mpc8xx_immr->im_cpm.cp_sicr;
		shift = 8;
		break;

	case CPM_CLK_SCC3:
		reg = &mpc8xx_immr->im_cpm.cp_sicr;
		shift = 16;
		break;

	case CPM_CLK_SCC4:
		reg = &mpc8xx_immr->im_cpm.cp_sicr;
		shift = 24;
		break;

	case CPM_CLK_SMC1:
		reg = &mpc8xx_immr->im_cpm.cp_simode;
		shift = 12;
		break;

	case CPM_CLK_SMC2:
		reg = &mpc8xx_immr->im_cpm.cp_simode;
		shift = 28;
		break;

	default:
		printk(KERN_ERR "cpm1_clock_setup: invalid clock target\n");
		return -EINVAL;
	}

	for (i = 0; i < ARRAY_SIZE(clk_map); i++) {
		if (clk_map[i][0] == target && clk_map[i][1] == clock) {
			bits = clk_map[i][2];
			break;
		}
	}

	if (i == ARRAY_SIZE(clk_map)) {
		printk(KERN_ERR "cpm1_clock_setup: invalid clock combination\n");
		return -EINVAL;
	}

	bits <<= shift;
	mask <<= shift;

	if (reg == &mpc8xx_immr->im_cpm.cp_sicr) {
		if (mode == CPM_CLK_RTX) {
			bits |= bits << 3;
			mask |= mask << 3;
		} else if (mode == CPM_CLK_RX) {
			bits <<= 3;
			mask <<= 3;
		}
	}

	out_be32(reg, (in_be32(reg) & ~mask) | bits);

	return 0;
}

/*
 * GPIO LIB API implementation
 */
#ifdef CONFIG_8xx_GPIO

struct cpm1_gpio16_chip {
	struct of_mm_gpio_chip mm_gc;
	spinlock_t lock;

	/* shadowed data register to clear/set bits safely */
	u16 cpdata;
};

static inline struct cpm1_gpio16_chip *
to_cpm1_gpio16_chip(struct of_mm_gpio_chip *mm_gc)
{
	return container_of(mm_gc, struct cpm1_gpio16_chip, mm_gc);
}

static void cpm1_gpio16_save_regs(struct of_mm_gpio_chip *mm_gc)
{
	struct cpm1_gpio16_chip *cpm1_gc = to_cpm1_gpio16_chip(mm_gc);
	struct cpm_ioport16 __iomem *iop = mm_gc->regs;

	cpm1_gc->cpdata = in_be16(&iop->dat);
}

static int cpm1_gpio16_get(struct gpio_chip *gc, unsigned int gpio)
{
	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
	struct cpm_ioport16 __iomem *iop = mm_gc->regs;
	u16 pin_mask;

	pin_mask = 1 << (15 - gpio);

	return !!(in_be16(&iop->dat) & pin_mask);
}

static void __cpm1_gpio16_set(struct of_mm_gpio_chip *mm_gc, u16 pin_mask,
	int value)
{
	struct cpm1_gpio16_chip *cpm1_gc = to_cpm1_gpio16_chip(mm_gc);
	struct cpm_ioport16 __iomem *iop = mm_gc->regs;

	if (value)
		cpm1_gc->cpdata |= pin_mask;
	else
		cpm1_gc->cpdata &= ~pin_mask;

	out_be16(&iop->dat, cpm1_gc->cpdata);
}

static void cpm1_gpio16_set(struct gpio_chip *gc, unsigned int gpio, int value)
{
	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
	struct cpm1_gpio16_chip *cpm1_gc = to_cpm1_gpio16_chip(mm_gc);
	unsigned long flags;
	u16 pin_mask = 1 << (15 - gpio);

	spin_lock_irqsave(&cpm1_gc->lock, flags);

	__cpm1_gpio16_set(mm_gc, pin_mask, value);

	spin_unlock_irqrestore(&cpm1_gc->lock, flags);
}

static int cpm1_gpio16_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
{
	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
	struct cpm1_gpio16_chip *cpm1_gc = to_cpm1_gpio16_chip(mm_gc);
	struct cpm_ioport16 __iomem *iop = mm_gc->regs;
	unsigned long flags;
	u16 pin_mask = 1 << (15 - gpio);

	spin_lock_irqsave(&cpm1_gc->lock, flags);

	setbits16(&iop->dir, pin_mask);
	__cpm1_gpio16_set(mm_gc, pin_mask, val);

	spin_unlock_irqrestore(&cpm1_gc->lock, flags);

	return 0;
}

static int cpm1_gpio16_dir_in(struct gpio_chip *gc, unsigned int gpio)
{
	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
	struct cpm1_gpio16_chip *cpm1_gc = to_cpm1_gpio16_chip(mm_gc);
	struct cpm_ioport16 __iomem *iop = mm_gc->regs;
	unsigned long flags;
	u16 pin_mask = 1 << (15 - gpio);

	spin_lock_irqsave(&cpm1_gc->lock, flags);

	clrbits16(&iop->dir, pin_mask);

	spin_unlock_irqrestore(&cpm1_gc->lock, flags);

	return 0;
}

int cpm1_gpiochip_add16(struct device_node *np)
{
	struct cpm1_gpio16_chip *cpm1_gc;
	struct of_mm_gpio_chip *mm_gc;
	struct gpio_chip *gc;

	cpm1_gc = kzalloc(sizeof(*cpm1_gc), GFP_KERNEL);
	if (!cpm1_gc)
		return -ENOMEM;

	spin_lock_init(&cpm1_gc->lock);

	mm_gc = &cpm1_gc->mm_gc;
	gc = &mm_gc->gc;

	mm_gc->save_regs = cpm1_gpio16_save_regs;
	gc->ngpio = 16;
	gc->direction_input = cpm1_gpio16_dir_in;
	gc->direction_output = cpm1_gpio16_dir_out;
	gc->get = cpm1_gpio16_get;
	gc->set = cpm1_gpio16_set;

	return of_mm_gpiochip_add(np, mm_gc);
}

struct cpm1_gpio32_chip {
	struct of_mm_gpio_chip mm_gc;
	spinlock_t lock;

	/* shadowed data register to clear/set bits safely */
	u32 cpdata;
};

static inline struct cpm1_gpio32_chip *
to_cpm1_gpio32_chip(struct of_mm_gpio_chip *mm_gc)
{
	return container_of(mm_gc, struct cpm1_gpio32_chip, mm_gc);
}

static void cpm1_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc)
{
	struct cpm1_gpio32_chip *cpm1_gc = to_cpm1_gpio32_chip(mm_gc);
	struct cpm_ioport32b __iomem *iop = mm_gc->regs;

	cpm1_gc->cpdata = in_be32(&iop->dat);
}

static int cpm1_gpio32_get(struct gpio_chip *gc, unsigned int gpio)
{
	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
	struct cpm_ioport32b __iomem *iop = mm_gc->regs;
	u32 pin_mask;

	pin_mask = 1 << (31 - gpio);

	return !!(in_be32(&iop->dat) & pin_mask);
}

static void __cpm1_gpio32_set(struct of_mm_gpio_chip *mm_gc, u32 pin_mask,
	int value)
{
	struct cpm1_gpio32_chip *cpm1_gc = to_cpm1_gpio32_chip(mm_gc);
	struct cpm_ioport32b __iomem *iop = mm_gc->regs;

	if (value)
		cpm1_gc->cpdata |= pin_mask;
	else
		cpm1_gc->cpdata &= ~pin_mask;

	out_be32(&iop->dat, cpm1_gc->cpdata);
}

static void cpm1_gpio32_set(struct gpio_chip *gc, unsigned int gpio, int value)
{
	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
	struct cpm1_gpio32_chip *cpm1_gc = to_cpm1_gpio32_chip(mm_gc);
	unsigned long flags;
	u32 pin_mask = 1 << (31 - gpio);

	spin_lock_irqsave(&cpm1_gc->lock, flags);

	__cpm1_gpio32_set(mm_gc, pin_mask, value);

	spin_unlock_irqrestore(&cpm1_gc->lock, flags);
}

static int cpm1_gpio32_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
{
	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
	struct cpm1_gpio32_chip *cpm1_gc = to_cpm1_gpio32_chip(mm_gc);
	struct cpm_ioport32b __iomem *iop = mm_gc->regs;
	unsigned long flags;
	u32 pin_mask = 1 << (31 - gpio);

	spin_lock_irqsave(&cpm1_gc->lock, flags);

	setbits32(&iop->dir, pin_mask);
	__cpm1_gpio32_set(mm_gc, pin_mask, val);

	spin_unlock_irqrestore(&cpm1_gc->lock, flags);

	return 0;
}

static int cpm1_gpio32_dir_in(struct gpio_chip *gc, unsigned int gpio)
{
	struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc);
	struct cpm1_gpio32_chip *cpm1_gc = to_cpm1_gpio32_chip(mm_gc);
	struct cpm_ioport32b __iomem *iop = mm_gc->regs;
	unsigned long flags;
	u32 pin_mask = 1 << (31 - gpio);

	spin_lock_irqsave(&cpm1_gc->lock, flags);

	clrbits32(&iop->dir, pin_mask);

	spin_unlock_irqrestore(&cpm1_gc->lock, flags);

	return 0;
}

int cpm1_gpiochip_add32(struct device_node *np)
{
	struct cpm1_gpio32_chip *cpm1_gc;
	struct of_mm_gpio_chip *mm_gc;
	struct gpio_chip *gc;

	cpm1_gc = kzalloc(sizeof(*cpm1_gc), GFP_KERNEL);
	if (!cpm1_gc)
		return -ENOMEM;

	spin_lock_init(&cpm1_gc->lock);

	mm_gc = &cpm1_gc->mm_gc;
	gc = &mm_gc->gc;

	mm_gc->save_regs = cpm1_gpio32_save_regs;
	gc->ngpio = 32;
	gc->direction_input = cpm1_gpio32_dir_in;
	gc->direction_output = cpm1_gpio32_dir_out;
	gc->get = cpm1_gpio32_get;
	gc->set = cpm1_gpio32_set;

	return of_mm_gpiochip_add(np, mm_gc);
}

static int cpm_init_par_io(void)
{
	struct device_node *np;

	for_each_compatible_node(np, NULL, "fsl,cpm1-pario-bank-a")
		cpm1_gpiochip_add16(np);

	for_each_compatible_node(np, NULL, "fsl,cpm1-pario-bank-b")
		cpm1_gpiochip_add32(np);

	for_each_compatible_node(np, NULL, "fsl,cpm1-pario-bank-c")
		cpm1_gpiochip_add16(np);

	for_each_compatible_node(np, NULL, "fsl,cpm1-pario-bank-d")
		cpm1_gpiochip_add16(np);

	/* Port E uses CPM2 layout */
	for_each_compatible_node(np, NULL, "fsl,cpm1-pario-bank-e")
		cpm2_gpiochip_add32(np);
	return 0;
}
arch_initcall(cpm_init_par_io);

#endif /* CONFIG_8xx_GPIO */