1// SPDX-License-Identifier: GPL-2.0-or-later
2/*
3 * SMP support for power macintosh.
4 *
5 * We support both the old "powersurge" SMP architecture
6 * and the current Core99 (G4 PowerMac) machines.
7 *
8 * Note that we don't support the very first rev. of
9 * Apple/DayStar 2 CPUs board, the one with the funky
10 * watchdog. Hopefully, none of these should be there except
11 * maybe internally to Apple. I should probably still add some
12 * code to detect this card though and disable SMP. --BenH.
13 *
14 * Support Macintosh G4 SMP by Troy Benjegerdes (hozer@drgw.net)
15 * and Ben Herrenschmidt <benh@kernel.crashing.org>.
16 *
17 * Support for DayStar quad CPU cards
18 * Copyright (C) XLR8, Inc. 1994-2000
19 */
20#include <linux/kernel.h>
21#include <linux/sched.h>
22#include <linux/sched/hotplug.h>
23#include <linux/smp.h>
24#include <linux/interrupt.h>
25#include <linux/irqdomain.h>
26#include <linux/kernel_stat.h>
27#include <linux/delay.h>
28#include <linux/init.h>
29#include <linux/spinlock.h>
30#include <linux/errno.h>
31#include <linux/hardirq.h>
32#include <linux/cpu.h>
33#include <linux/compiler.h>
34#include <linux/pgtable.h>
35
36#include <asm/ptrace.h>
37#include <linux/atomic.h>
38#include <asm/code-patching.h>
39#include <asm/irq.h>
40#include <asm/page.h>
41#include <asm/sections.h>
42#include <asm/io.h>
43#include <asm/smp.h>
44#include <asm/machdep.h>
45#include <asm/pmac_feature.h>
46#include <asm/time.h>
47#include <asm/mpic.h>
48#include <asm/cacheflush.h>
49#include <asm/keylargo.h>
50#include <asm/pmac_low_i2c.h>
51#include <asm/pmac_pfunc.h>
52#include <asm/inst.h>
53
54#include "pmac.h"
55
56#undef DEBUG
57
58#ifdef DEBUG
59#define DBG(fmt...) udbg_printf(fmt)
60#else
61#define DBG(fmt...)
62#endif
63
64extern void __secondary_start_pmac_0(void);
65
66static void (*pmac_tb_freeze)(int freeze);
67static u64 timebase;
68static int tb_req;
69
70#ifdef CONFIG_PPC_PMAC32_PSURGE
71
72/*
73 * Powersurge (old powermac SMP) support.
74 */
75
76/* Addresses for powersurge registers */
77#define HAMMERHEAD_BASE		0xf8000000
78#define HHEAD_CONFIG		0x90
79#define HHEAD_SEC_INTR		0xc0
80
81/* register for interrupting the primary processor on the powersurge */
82/* N.B. this is actually the ethernet ROM! */
83#define PSURGE_PRI_INTR		0xf3019000
84
85/* register for storing the start address for the secondary processor */
86/* N.B. this is the PCI config space address register for the 1st bridge */
87#define PSURGE_START		0xf2800000
88
89/* Daystar/XLR8 4-CPU card */
90#define PSURGE_QUAD_REG_ADDR	0xf8800000
91
92#define PSURGE_QUAD_IRQ_SET	0
93#define PSURGE_QUAD_IRQ_CLR	1
94#define PSURGE_QUAD_IRQ_PRIMARY	2
95#define PSURGE_QUAD_CKSTOP_CTL	3
96#define PSURGE_QUAD_PRIMARY_ARB	4
97#define PSURGE_QUAD_BOARD_ID	6
98#define PSURGE_QUAD_WHICH_CPU	7
99#define PSURGE_QUAD_CKSTOP_RDBK	8
100#define PSURGE_QUAD_RESET_CTL	11
101
102#define PSURGE_QUAD_OUT(r, v)	(out_8(quad_base + ((r) << 4) + 4, (v)))
103#define PSURGE_QUAD_IN(r)	(in_8(quad_base + ((r) << 4) + 4) & 0x0f)
104#define PSURGE_QUAD_BIS(r, v)	(PSURGE_QUAD_OUT((r), PSURGE_QUAD_IN(r) | (v)))
105#define PSURGE_QUAD_BIC(r, v)	(PSURGE_QUAD_OUT((r), PSURGE_QUAD_IN(r) & ~(v)))
106
107/* virtual addresses for the above */
108static volatile u8 __iomem *hhead_base;
109static volatile u8 __iomem *quad_base;
110static volatile u32 __iomem *psurge_pri_intr;
111static volatile u8 __iomem *psurge_sec_intr;
112static volatile u32 __iomem *psurge_start;
113
114/* values for psurge_type */
115#define PSURGE_NONE		-1
116#define PSURGE_DUAL		0
117#define PSURGE_QUAD_OKEE	1
118#define PSURGE_QUAD_COTTON	2
119#define PSURGE_QUAD_ICEGRASS	3
120
121/* what sort of powersurge board we have */
122static int psurge_type = PSURGE_NONE;
123
124/* irq for secondary cpus to report */
125static struct irq_domain *psurge_host;
126int psurge_secondary_virq;
127
128/*
129 * Set and clear IPIs for powersurge.
130 */
131static inline void psurge_set_ipi(int cpu)
132{
133	if (psurge_type == PSURGE_NONE)
134		return;
135	if (cpu == 0)
136		in_be32(psurge_pri_intr);
137	else if (psurge_type == PSURGE_DUAL)
138		out_8(psurge_sec_intr, 0);
139	else
140		PSURGE_QUAD_OUT(PSURGE_QUAD_IRQ_SET, 1 << cpu);
141}
142
143static inline void psurge_clr_ipi(int cpu)
144{
145	if (cpu > 0) {
146		switch(psurge_type) {
147		case PSURGE_DUAL:
148			out_8(psurge_sec_intr, ~0);
149			break;
150		case PSURGE_NONE:
151			break;
152		default:
153			PSURGE_QUAD_OUT(PSURGE_QUAD_IRQ_CLR, 1 << cpu);
154		}
155	}
156}
157
158/*
159 * On powersurge (old SMP powermac architecture) we don't have
160 * separate IPIs for separate messages like openpic does.  Instead
161 * use the generic demux helpers
162 *  -- paulus.
163 */
164static irqreturn_t psurge_ipi_intr(int irq, void *d)
165{
166	psurge_clr_ipi(smp_processor_id());
167	smp_ipi_demux();
168
169	return IRQ_HANDLED;
170}
171
172static void smp_psurge_cause_ipi(int cpu)
173{
174	psurge_set_ipi(cpu);
175}
176
177static int psurge_host_map(struct irq_domain *h, unsigned int virq,
178			 irq_hw_number_t hw)
179{
180	irq_set_chip_and_handler(virq, &dummy_irq_chip, handle_percpu_irq);
181
182	return 0;
183}
184
185static const struct irq_domain_ops psurge_host_ops = {
186	.map	= psurge_host_map,
187};
188
189static int __init psurge_secondary_ipi_init(void)
190{
191	int rc = -ENOMEM;
192
193	psurge_host = irq_domain_add_nomap(NULL, ~0, &psurge_host_ops, NULL);
194
195	if (psurge_host)
196		psurge_secondary_virq = irq_create_direct_mapping(psurge_host);
197
198	if (psurge_secondary_virq)
199		rc = request_irq(psurge_secondary_virq, psurge_ipi_intr,
200			IRQF_PERCPU | IRQF_NO_THREAD, "IPI", NULL);
201
202	if (rc)
203		pr_err("Failed to setup secondary cpu IPI\n");
204
205	return rc;
206}
207
208/*
209 * Determine a quad card presence. We read the board ID register, we
210 * force the data bus to change to something else, and we read it again.
211 * It it's stable, then the register probably exist (ugh !)
212 */
213static int __init psurge_quad_probe(void)
214{
215	int type;
216	unsigned int i;
217
218	type = PSURGE_QUAD_IN(PSURGE_QUAD_BOARD_ID);
219	if (type < PSURGE_QUAD_OKEE || type > PSURGE_QUAD_ICEGRASS
220	    || type != PSURGE_QUAD_IN(PSURGE_QUAD_BOARD_ID))
221		return PSURGE_DUAL;
222
223	/* looks OK, try a slightly more rigorous test */
224	/* bogus is not necessarily cacheline-aligned,
225	   though I don't suppose that really matters.  -- paulus */
226	for (i = 0; i < 100; i++) {
227		volatile u32 bogus[8];
228		bogus[(0+i)%8] = 0x00000000;
229		bogus[(1+i)%8] = 0x55555555;
230		bogus[(2+i)%8] = 0xFFFFFFFF;
231		bogus[(3+i)%8] = 0xAAAAAAAA;
232		bogus[(4+i)%8] = 0x33333333;
233		bogus[(5+i)%8] = 0xCCCCCCCC;
234		bogus[(6+i)%8] = 0xCCCCCCCC;
235		bogus[(7+i)%8] = 0x33333333;
236		wmb();
237		asm volatile("dcbf 0,%0" : : "r" (bogus) : "memory");
238		mb();
239		if (type != PSURGE_QUAD_IN(PSURGE_QUAD_BOARD_ID))
240			return PSURGE_DUAL;
241	}
242	return type;
243}
244
245static void __init psurge_quad_init(void)
246{
247	int procbits;
248
249	if (ppc_md.progress) ppc_md.progress("psurge_quad_init", 0x351);
250	procbits = ~PSURGE_QUAD_IN(PSURGE_QUAD_WHICH_CPU);
251	if (psurge_type == PSURGE_QUAD_ICEGRASS)
252		PSURGE_QUAD_BIS(PSURGE_QUAD_RESET_CTL, procbits);
253	else
254		PSURGE_QUAD_BIC(PSURGE_QUAD_CKSTOP_CTL, procbits);
255	mdelay(33);
256	out_8(psurge_sec_intr, ~0);
257	PSURGE_QUAD_OUT(PSURGE_QUAD_IRQ_CLR, procbits);
258	PSURGE_QUAD_BIS(PSURGE_QUAD_RESET_CTL, procbits);
259	if (psurge_type != PSURGE_QUAD_ICEGRASS)
260		PSURGE_QUAD_BIS(PSURGE_QUAD_CKSTOP_CTL, procbits);
261	PSURGE_QUAD_BIC(PSURGE_QUAD_PRIMARY_ARB, procbits);
262	mdelay(33);
263	PSURGE_QUAD_BIC(PSURGE_QUAD_RESET_CTL, procbits);
264	mdelay(33);
265	PSURGE_QUAD_BIS(PSURGE_QUAD_PRIMARY_ARB, procbits);
266	mdelay(33);
267}
268
269static void __init smp_psurge_probe(void)
270{
271	int i, ncpus;
272	struct device_node *dn;
273
274	/*
275	 * The powersurge cpu board can be used in the generation
276	 * of powermacs that have a socket for an upgradeable cpu card,
277	 * including the 7500, 8500, 9500, 9600.
278	 * The device tree doesn't tell you if you have 2 cpus because
279	 * OF doesn't know anything about the 2nd processor.
280	 * Instead we look for magic bits in magic registers,
281	 * in the hammerhead memory controller in the case of the
282	 * dual-cpu powersurge board.  -- paulus.
283	 */
284	dn = of_find_node_by_name(NULL, "hammerhead");
285	if (dn == NULL)
286		return;
287	of_node_put(dn);
288
289	hhead_base = ioremap(HAMMERHEAD_BASE, 0x800);
290	quad_base = ioremap(PSURGE_QUAD_REG_ADDR, 1024);
291	psurge_sec_intr = hhead_base + HHEAD_SEC_INTR;
292
293	psurge_type = psurge_quad_probe();
294	if (psurge_type != PSURGE_DUAL) {
295		psurge_quad_init();
296		/* All released cards using this HW design have 4 CPUs */
297		ncpus = 4;
298		/* No sure how timebase sync works on those, let's use SW */
299		smp_ops->give_timebase = smp_generic_give_timebase;
300		smp_ops->take_timebase = smp_generic_take_timebase;
301	} else {
302		iounmap(quad_base);
303		if ((in_8(hhead_base + HHEAD_CONFIG) & 0x02) == 0) {
304			/* not a dual-cpu card */
305			iounmap(hhead_base);
306			psurge_type = PSURGE_NONE;
307			return;
308		}
309		ncpus = 2;
310	}
311
312	if (psurge_secondary_ipi_init())
313		return;
314
315	psurge_start = ioremap(PSURGE_START, 4);
316	psurge_pri_intr = ioremap(PSURGE_PRI_INTR, 4);
317
318	/* This is necessary because OF doesn't know about the
319	 * secondary cpu(s), and thus there aren't nodes in the
320	 * device tree for them, and smp_setup_cpu_maps hasn't
321	 * set their bits in cpu_present_mask.
322	 */
323	if (ncpus > NR_CPUS)
324		ncpus = NR_CPUS;
325	for (i = 1; i < ncpus ; ++i)
326		set_cpu_present(i, true);
327
328	if (ppc_md.progress) ppc_md.progress("smp_psurge_probe - done", 0x352);
329}
330
331static int __init smp_psurge_kick_cpu(int nr)
332{
333	unsigned long start = __pa(__secondary_start_pmac_0) + nr * 8;
334	unsigned long a, flags;
335	int i, j;
336
337	/* Defining this here is evil ... but I prefer hiding that
338	 * crap to avoid giving people ideas that they can do the
339	 * same.
340	 */
341	extern volatile unsigned int cpu_callin_map[NR_CPUS];
342
343	/* may need to flush here if secondary bats aren't setup */
344	for (a = KERNELBASE; a < KERNELBASE + 0x800000; a += 32)
345		asm volatile("dcbf 0,%0" : : "r" (a) : "memory");
346	asm volatile("sync");
347
348	if (ppc_md.progress) ppc_md.progress("smp_psurge_kick_cpu", 0x353);
349
350	/* This is going to freeze the timeebase, we disable interrupts */
351	local_irq_save(flags);
352
353	out_be32(psurge_start, start);
354	mb();
355
356	psurge_set_ipi(nr);
357
358	/*
359	 * We can't use udelay here because the timebase is now frozen.
360	 */
361	for (i = 0; i < 2000; ++i)
362		asm volatile("nop" : : : "memory");
363	psurge_clr_ipi(nr);
364
365	/*
366	 * Also, because the timebase is frozen, we must not return to the
367	 * caller which will try to do udelay's etc... Instead, we wait -here-
368	 * for the CPU to callin.
369	 */
370	for (i = 0; i < 100000 && !cpu_callin_map[nr]; ++i) {
371		for (j = 1; j < 10000; j++)
372			asm volatile("nop" : : : "memory");
373		asm volatile("sync" : : : "memory");
374	}
375	if (!cpu_callin_map[nr])
376		goto stuck;
377
378	/* And we do the TB sync here too for standard dual CPU cards */
379	if (psurge_type == PSURGE_DUAL) {
380		while(!tb_req)
381			barrier();
382		tb_req = 0;
383		mb();
384		timebase = get_tb();
385		mb();
386		while (timebase)
387			barrier();
388		mb();
389	}
390 stuck:
391	/* now interrupt the secondary, restarting both TBs */
392	if (psurge_type == PSURGE_DUAL)
393		psurge_set_ipi(1);
394
395	if (ppc_md.progress) ppc_md.progress("smp_psurge_kick_cpu - done", 0x354);
396
397	return 0;
398}
399
400static void __init smp_psurge_setup_cpu(int cpu_nr)
401{
402	unsigned long flags = IRQF_PERCPU | IRQF_NO_THREAD;
403	int irq;
404
405	if (cpu_nr != 0 || !psurge_start)
406		return;
407
408	/* reset the entry point so if we get another intr we won't
409	 * try to startup again */
410	out_be32(psurge_start, 0x100);
411	irq = irq_create_mapping(NULL, 30);
412	if (request_irq(irq, psurge_ipi_intr, flags, "primary IPI", NULL))
413		printk(KERN_ERR "Couldn't get primary IPI interrupt");
414}
415
416void __init smp_psurge_take_timebase(void)
417{
418	if (psurge_type != PSURGE_DUAL)
419		return;
420
421	tb_req = 1;
422	mb();
423	while (!timebase)
424		barrier();
425	mb();
426	set_tb(timebase >> 32, timebase & 0xffffffff);
427	timebase = 0;
428	mb();
429	set_dec(tb_ticks_per_jiffy/2);
430}
431
432void __init smp_psurge_give_timebase(void)
433{
434	/* Nothing to do here */
435}
436
437/* PowerSurge-style Macs */
438struct smp_ops_t psurge_smp_ops = {
439	.message_pass	= NULL,	/* Use smp_muxed_ipi_message_pass */
440	.cause_ipi	= smp_psurge_cause_ipi,
441	.cause_nmi_ipi	= NULL,
442	.probe		= smp_psurge_probe,
443	.kick_cpu	= smp_psurge_kick_cpu,
444	.setup_cpu	= smp_psurge_setup_cpu,
445	.give_timebase	= smp_psurge_give_timebase,
446	.take_timebase	= smp_psurge_take_timebase,
447};
448#endif /* CONFIG_PPC_PMAC32_PSURGE */
449
450/*
451 * Core 99 and later support
452 */
453
454
455static void smp_core99_give_timebase(void)
456{
457	unsigned long flags;
458
459	local_irq_save(flags);
460
461	while(!tb_req)
462		barrier();
463	tb_req = 0;
464	(*pmac_tb_freeze)(1);
465	mb();
466	timebase = get_tb();
467	mb();
468	while (timebase)
469		barrier();
470	mb();
471	(*pmac_tb_freeze)(0);
472	mb();
473
474	local_irq_restore(flags);
475}
476
477
478static void smp_core99_take_timebase(void)
479{
480	unsigned long flags;
481
482	local_irq_save(flags);
483
484	tb_req = 1;
485	mb();
486	while (!timebase)
487		barrier();
488	mb();
489	set_tb(timebase >> 32, timebase & 0xffffffff);
490	timebase = 0;
491	mb();
492
493	local_irq_restore(flags);
494}
495
496#ifdef CONFIG_PPC64
497/*
498 * G5s enable/disable the timebase via an i2c-connected clock chip.
499 */
500static struct pmac_i2c_bus *pmac_tb_clock_chip_host;
501static u8 pmac_tb_pulsar_addr;
502
503static void smp_core99_cypress_tb_freeze(int freeze)
504{
505	u8 data;
506	int rc;
507
508	/* Strangely, the device-tree says address is 0xd2, but darwin
509	 * accesses 0xd0 ...
510	 */
511	pmac_i2c_setmode(pmac_tb_clock_chip_host,
512			 pmac_i2c_mode_combined);
513	rc = pmac_i2c_xfer(pmac_tb_clock_chip_host,
514			   0xd0 | pmac_i2c_read,
515			   1, 0x81, &data, 1);
516	if (rc != 0)
517		goto bail;
518
519	data = (data & 0xf3) | (freeze ? 0x00 : 0x0c);
520
521       	pmac_i2c_setmode(pmac_tb_clock_chip_host, pmac_i2c_mode_stdsub);
522	rc = pmac_i2c_xfer(pmac_tb_clock_chip_host,
523			   0xd0 | pmac_i2c_write,
524			   1, 0x81, &data, 1);
525
526 bail:
527	if (rc != 0) {
528		printk("Cypress Timebase %s rc: %d\n",
529		       freeze ? "freeze" : "unfreeze", rc);
530		panic("Timebase freeze failed !\n");
531	}
532}
533
534
535static void smp_core99_pulsar_tb_freeze(int freeze)
536{
537	u8 data;
538	int rc;
539
540	pmac_i2c_setmode(pmac_tb_clock_chip_host,
541			 pmac_i2c_mode_combined);
542	rc = pmac_i2c_xfer(pmac_tb_clock_chip_host,
543			   pmac_tb_pulsar_addr | pmac_i2c_read,
544			   1, 0x2e, &data, 1);
545	if (rc != 0)
546		goto bail;
547
548	data = (data & 0x88) | (freeze ? 0x11 : 0x22);
549
550	pmac_i2c_setmode(pmac_tb_clock_chip_host, pmac_i2c_mode_stdsub);
551	rc = pmac_i2c_xfer(pmac_tb_clock_chip_host,
552			   pmac_tb_pulsar_addr | pmac_i2c_write,
553			   1, 0x2e, &data, 1);
554 bail:
555	if (rc != 0) {
556		printk(KERN_ERR "Pulsar Timebase %s rc: %d\n",
557		       freeze ? "freeze" : "unfreeze", rc);
558		panic("Timebase freeze failed !\n");
559	}
560}
561
562static void __init smp_core99_setup_i2c_hwsync(int ncpus)
563{
564	struct device_node *cc = NULL;
565	struct device_node *p;
566	const char *name = NULL;
567	const u32 *reg;
568	int ok;
569
570	/* Look for the clock chip */
571	for_each_node_by_name(cc, "i2c-hwclock") {
572		p = of_get_parent(cc);
573		ok = p && of_device_is_compatible(p, "uni-n-i2c");
574		of_node_put(p);
575		if (!ok)
576			continue;
577
578		pmac_tb_clock_chip_host = pmac_i2c_find_bus(cc);
579		if (pmac_tb_clock_chip_host == NULL)
580			continue;
581		reg = of_get_property(cc, "reg", NULL);
582		if (reg == NULL)
583			continue;
584		switch (*reg) {
585		case 0xd2:
586			if (of_device_is_compatible(cc,"pulsar-legacy-slewing")) {
587				pmac_tb_freeze = smp_core99_pulsar_tb_freeze;
588				pmac_tb_pulsar_addr = 0xd2;
589				name = "Pulsar";
590			} else if (of_device_is_compatible(cc, "cy28508")) {
591				pmac_tb_freeze = smp_core99_cypress_tb_freeze;
592				name = "Cypress";
593			}
594			break;
595		case 0xd4:
596			pmac_tb_freeze = smp_core99_pulsar_tb_freeze;
597			pmac_tb_pulsar_addr = 0xd4;
598			name = "Pulsar";
599			break;
600		}
601		if (pmac_tb_freeze != NULL)
602			break;
603	}
604	if (pmac_tb_freeze != NULL) {
605		/* Open i2c bus for synchronous access */
606		if (pmac_i2c_open(pmac_tb_clock_chip_host, 1)) {
607			printk(KERN_ERR "Failed top open i2c bus for clock"
608			       " sync, fallback to software sync !\n");
609			goto no_i2c_sync;
610		}
611		printk(KERN_INFO "Processor timebase sync using %s i2c clock\n",
612		       name);
613		return;
614	}
615 no_i2c_sync:
616	pmac_tb_freeze = NULL;
617	pmac_tb_clock_chip_host = NULL;
618}
619
620
621
622/*
623 * Newer G5s uses a platform function
624 */
625
626static void smp_core99_pfunc_tb_freeze(int freeze)
627{
628	struct device_node *cpus;
629	struct pmf_args args;
630
631	cpus = of_find_node_by_path("/cpus");
632	BUG_ON(cpus == NULL);
633	args.count = 1;
634	args.u[0].v = !freeze;
635	pmf_call_function(cpus, "cpu-timebase", &args);
636	of_node_put(cpus);
637}
638
639#else /* CONFIG_PPC64 */
640
641/*
642 * SMP G4 use a GPIO to enable/disable the timebase.
643 */
644
645static unsigned int core99_tb_gpio;	/* Timebase freeze GPIO */
646
647static void smp_core99_gpio_tb_freeze(int freeze)
648{
649	if (freeze)
650		pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, core99_tb_gpio, 4);
651	else
652		pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, core99_tb_gpio, 0);
653	pmac_call_feature(PMAC_FTR_READ_GPIO, NULL, core99_tb_gpio, 0);
654}
655
656
657#endif /* !CONFIG_PPC64 */
658
659static void core99_init_caches(int cpu)
660{
661#ifndef CONFIG_PPC64
662	/* L2 and L3 cache settings to pass from CPU0 to CPU1 on G4 cpus */
663	static long int core99_l2_cache;
664	static long int core99_l3_cache;
665
666	if (!cpu_has_feature(CPU_FTR_L2CR))
667		return;
668
669	if (cpu == 0) {
670		core99_l2_cache = _get_L2CR();
671		printk("CPU0: L2CR is %lx\n", core99_l2_cache);
672	} else {
673		printk("CPU%d: L2CR was %lx\n", cpu, _get_L2CR());
674		_set_L2CR(0);
675		_set_L2CR(core99_l2_cache);
676		printk("CPU%d: L2CR set to %lx\n", cpu, core99_l2_cache);
677	}
678
679	if (!cpu_has_feature(CPU_FTR_L3CR))
680		return;
681
682	if (cpu == 0){
683		core99_l3_cache = _get_L3CR();
684		printk("CPU0: L3CR is %lx\n", core99_l3_cache);
685	} else {
686		printk("CPU%d: L3CR was %lx\n", cpu, _get_L3CR());
687		_set_L3CR(0);
688		_set_L3CR(core99_l3_cache);
689		printk("CPU%d: L3CR set to %lx\n", cpu, core99_l3_cache);
690	}
691#endif /* !CONFIG_PPC64 */
692}
693
694static void __init smp_core99_setup(int ncpus)
695{
696#ifdef CONFIG_PPC64
697
698	/* i2c based HW sync on some G5s */
699	if (of_machine_is_compatible("PowerMac7,2") ||
700	    of_machine_is_compatible("PowerMac7,3") ||
701	    of_machine_is_compatible("RackMac3,1"))
702		smp_core99_setup_i2c_hwsync(ncpus);
703
704	/* pfunc based HW sync on recent G5s */
705	if (pmac_tb_freeze == NULL) {
706		struct device_node *cpus =
707			of_find_node_by_path("/cpus");
708		if (cpus &&
709		    of_property_read_bool(cpus, "platform-cpu-timebase")) {
710			pmac_tb_freeze = smp_core99_pfunc_tb_freeze;
711			printk(KERN_INFO "Processor timebase sync using"
712			       " platform function\n");
713		}
714		of_node_put(cpus);
715	}
716
717#else /* CONFIG_PPC64 */
718
719	/* GPIO based HW sync on ppc32 Core99 */
720	if (pmac_tb_freeze == NULL && !of_machine_is_compatible("MacRISC4")) {
721		struct device_node *cpu;
722		const u32 *tbprop = NULL;
723
724		core99_tb_gpio = KL_GPIO_TB_ENABLE;	/* default value */
725		cpu = of_find_node_by_type(NULL, "cpu");
726		if (cpu != NULL) {
727			tbprop = of_get_property(cpu, "timebase-enable", NULL);
728			if (tbprop)
729				core99_tb_gpio = *tbprop;
730			of_node_put(cpu);
731		}
732		pmac_tb_freeze = smp_core99_gpio_tb_freeze;
733		printk(KERN_INFO "Processor timebase sync using"
734		       " GPIO 0x%02x\n", core99_tb_gpio);
735	}
736
737#endif /* CONFIG_PPC64 */
738
739	/* No timebase sync, fallback to software */
740	if (pmac_tb_freeze == NULL) {
741		smp_ops->give_timebase = smp_generic_give_timebase;
742		smp_ops->take_timebase = smp_generic_take_timebase;
743		printk(KERN_INFO "Processor timebase sync using software\n");
744	}
745
746#ifndef CONFIG_PPC64
747	{
748		int i;
749
750		/* XXX should get this from reg properties */
751		for (i = 1; i < ncpus; ++i)
752			set_hard_smp_processor_id(i, i);
753	}
754#endif
755
756	/* 32 bits SMP can't NAP */
757	if (!of_machine_is_compatible("MacRISC4"))
758		powersave_nap = 0;
759}
760
761static void __init smp_core99_probe(void)
762{
763	struct device_node *cpus;
764	int ncpus = 0;
765
766	if (ppc_md.progress) ppc_md.progress("smp_core99_probe", 0x345);
767
768	/* Count CPUs in the device-tree */
769	for_each_node_by_type(cpus, "cpu")
770		++ncpus;
771
772	printk(KERN_INFO "PowerMac SMP probe found %d cpus\n", ncpus);
773
774	/* Nothing more to do if less than 2 of them */
775	if (ncpus <= 1)
776		return;
777
778	/* We need to perform some early initialisations before we can start
779	 * setting up SMP as we are running before initcalls
780	 */
781	pmac_pfunc_base_install();
782	pmac_i2c_init();
783
784	/* Setup various bits like timebase sync method, ability to nap, ... */
785	smp_core99_setup(ncpus);
786
787	/* Install IPIs */
788	mpic_request_ipis();
789
790	/* Collect l2cr and l3cr values from CPU 0 */
791	core99_init_caches(0);
792}
793
794static int smp_core99_kick_cpu(int nr)
795{
796	unsigned int save_vector;
797	unsigned long target, flags;
798	unsigned int *vector = (unsigned int *)(PAGE_OFFSET+0x100);
799
800	if (nr < 0 || nr > 3)
801		return -ENOENT;
802
803	if (ppc_md.progress)
804		ppc_md.progress("smp_core99_kick_cpu", 0x346);
805
806	local_irq_save(flags);
807
808	/* Save reset vector */
809	save_vector = *vector;
810
811	/* Setup fake reset vector that does
812	 *   b __secondary_start_pmac_0 + nr*8
813	 */
814	target = (unsigned long) __secondary_start_pmac_0 + nr * 8;
815	patch_branch(vector, target, BRANCH_SET_LINK);
816
817	/* Put some life in our friend */
818	pmac_call_feature(PMAC_FTR_RESET_CPU, NULL, nr, 0);
819
820	/* FIXME: We wait a bit for the CPU to take the exception, I should
821	 * instead wait for the entry code to set something for me. Well,
822	 * ideally, all that crap will be done in prom.c and the CPU left
823	 * in a RAM-based wait loop like CHRP.
824	 */
825	mdelay(1);
826
827	/* Restore our exception vector */
828	patch_instruction(vector, ppc_inst(save_vector));
829
830	local_irq_restore(flags);
831	if (ppc_md.progress) ppc_md.progress("smp_core99_kick_cpu done", 0x347);
832
833	return 0;
834}
835
836static void smp_core99_setup_cpu(int cpu_nr)
837{
838	/* Setup L2/L3 */
839	if (cpu_nr != 0)
840		core99_init_caches(cpu_nr);
841
842	/* Setup openpic */
843	mpic_setup_this_cpu();
844}
845
846#ifdef CONFIG_PPC64
847#ifdef CONFIG_HOTPLUG_CPU
848static unsigned int smp_core99_host_open;
849
850static int smp_core99_cpu_prepare(unsigned int cpu)
851{
852	int rc;
853
854	/* Open i2c bus if it was used for tb sync */
855	if (pmac_tb_clock_chip_host && !smp_core99_host_open) {
856		rc = pmac_i2c_open(pmac_tb_clock_chip_host, 1);
857		if (rc) {
858			pr_err("Failed to open i2c bus for time sync\n");
859			return notifier_from_errno(rc);
860		}
861		smp_core99_host_open = 1;
862	}
863	return 0;
864}
865
866static int smp_core99_cpu_online(unsigned int cpu)
867{
868	/* Close i2c bus if it was used for tb sync */
869	if (pmac_tb_clock_chip_host && smp_core99_host_open) {
870		pmac_i2c_close(pmac_tb_clock_chip_host);
871		smp_core99_host_open = 0;
872	}
873	return 0;
874}
875#endif /* CONFIG_HOTPLUG_CPU */
876
877static void __init smp_core99_bringup_done(void)
878{
879	/* Close i2c bus if it was used for tb sync */
880	if (pmac_tb_clock_chip_host)
881		pmac_i2c_close(pmac_tb_clock_chip_host);
882
883	/* If we didn't start the second CPU, we must take
884	 * it off the bus.
885	 */
886	if (of_machine_is_compatible("MacRISC4") &&
887	    num_online_cpus() < 2) {
888		set_cpu_present(1, false);
889		g5_phy_disable_cpu1();
890	}
891#ifdef CONFIG_HOTPLUG_CPU
892	cpuhp_setup_state_nocalls(CPUHP_POWERPC_PMAC_PREPARE,
893				  "powerpc/pmac:prepare", smp_core99_cpu_prepare,
894				  NULL);
895	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "powerpc/pmac:online",
896				  smp_core99_cpu_online, NULL);
897#endif
898
899	if (ppc_md.progress)
900		ppc_md.progress("smp_core99_bringup_done", 0x349);
901}
902#endif /* CONFIG_PPC64 */
903
904#ifdef CONFIG_HOTPLUG_CPU
905
906static int smp_core99_cpu_disable(void)
907{
908	int rc = generic_cpu_disable();
909	if (rc)
910		return rc;
911
912	mpic_cpu_set_priority(0xf);
913
914	cleanup_cpu_mmu_context();
915
916	return 0;
917}
918
919#ifdef CONFIG_PPC32
920
921static void pmac_cpu_offline_self(void)
922{
923	int cpu = smp_processor_id();
924
925	local_irq_disable();
926	idle_task_exit();
927	pr_debug("CPU%d offline\n", cpu);
928	generic_set_cpu_dead(cpu);
929	smp_wmb();
930	mb();
931	low_cpu_offline_self();
932}
933
934#else /* CONFIG_PPC32 */
935
936static void pmac_cpu_offline_self(void)
937{
938	int cpu = smp_processor_id();
939
940	local_irq_disable();
941	idle_task_exit();
942
943	/*
944	 * turn off as much as possible, we'll be
945	 * kicked out as this will only be invoked
946	 * on core99 platforms for now ...
947	 */
948
949	printk(KERN_INFO "CPU#%d offline\n", cpu);
950	generic_set_cpu_dead(cpu);
951	smp_wmb();
952
953	/*
954	 * Re-enable interrupts. The NAP code needs to enable them
955	 * anyways, do it now so we deal with the case where one already
956	 * happened while soft-disabled.
957	 * We shouldn't get any external interrupts, only decrementer, and the
958	 * decrementer handler is safe for use on offline CPUs
959	 */
960	local_irq_enable();
961
962	while (1) {
963		/* let's not take timer interrupts too often ... */
964		set_dec(0x7fffffff);
965
966		/* Enter NAP mode */
967		power4_idle();
968	}
969}
970
971#endif /* else CONFIG_PPC32 */
972#endif /* CONFIG_HOTPLUG_CPU */
973
974/* Core99 Macs (dual G4s and G5s) */
975static struct smp_ops_t core99_smp_ops = {
976	.message_pass	= smp_mpic_message_pass,
977	.probe		= smp_core99_probe,
978#ifdef CONFIG_PPC64
979	.bringup_done	= smp_core99_bringup_done,
980#endif
981	.kick_cpu	= smp_core99_kick_cpu,
982	.setup_cpu	= smp_core99_setup_cpu,
983	.give_timebase	= smp_core99_give_timebase,
984	.take_timebase	= smp_core99_take_timebase,
985#if defined(CONFIG_HOTPLUG_CPU)
986	.cpu_disable	= smp_core99_cpu_disable,
987	.cpu_die	= generic_cpu_die,
988#endif
989};
990
991void __init pmac_setup_smp(void)
992{
993	struct device_node *np;
994
995	/* Check for Core99 */
996	np = of_find_node_by_name(NULL, "uni-n");
997	if (!np)
998		np = of_find_node_by_name(NULL, "u3");
999	if (!np)
1000		np = of_find_node_by_name(NULL, "u4");
1001	if (np) {
1002		of_node_put(np);
1003		smp_ops = &core99_smp_ops;
1004	}
1005#ifdef CONFIG_PPC_PMAC32_PSURGE
1006	else {
1007		/* We have to set bits in cpu_possible_mask here since the
1008		 * secondary CPU(s) aren't in the device tree. Various
1009		 * things won't be initialized for CPUs not in the possible
1010		 * map, so we really need to fix it up here.
1011		 */
1012		int cpu;
1013
1014		for (cpu = 1; cpu < 4 && cpu < NR_CPUS; ++cpu)
1015			set_cpu_possible(cpu, true);
1016		smp_ops = &psurge_smp_ops;
1017	}
1018#endif /* CONFIG_PPC_PMAC32_PSURGE */
1019
1020#ifdef CONFIG_HOTPLUG_CPU
1021	smp_ops->cpu_offline_self = pmac_cpu_offline_self;
1022#endif
1023}
1024
1025
1026