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/kernel_stat.h>
26#include <linux/delay.h>
27#include <linux/init.h>
28#include <linux/spinlock.h>
29#include <linux/errno.h>
30#include <linux/hardirq.h>
31#include <linux/cpu.h>
32#include <linux/compiler.h>
33#include <linux/pgtable.h>
34
35#include <asm/ptrace.h>
36#include <linux/atomic.h>
37#include <asm/code-patching.h>
38#include <asm/irq.h>
39#include <asm/page.h>
40#include <asm/sections.h>
41#include <asm/io.h>
42#include <asm/prom.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		case PSURGE_NONE:
150			break;
151		default:
152			PSURGE_QUAD_OUT(PSURGE_QUAD_IRQ_CLR, 1 << cpu);
153		}
154	}
155}
156
157/*
158 * On powersurge (old SMP powermac architecture) we don't have
159 * separate IPIs for separate messages like openpic does.  Instead
160 * use the generic demux helpers
161 *  -- paulus.
162 */
163static irqreturn_t psurge_ipi_intr(int irq, void *d)
164{
165	psurge_clr_ipi(smp_processor_id());
166	smp_ipi_demux();
167
168	return IRQ_HANDLED;
169}
170
171static void smp_psurge_cause_ipi(int cpu)
172{
173	psurge_set_ipi(cpu);
174}
175
176static int psurge_host_map(struct irq_domain *h, unsigned int virq,
177			 irq_hw_number_t hw)
178{
179	irq_set_chip_and_handler(virq, &dummy_irq_chip, handle_percpu_irq);
180
181	return 0;
182}
183
184static const struct irq_domain_ops psurge_host_ops = {
185	.map	= psurge_host_map,
186};
187
188static int psurge_secondary_ipi_init(void)
189{
190	int rc = -ENOMEM;
191
192	psurge_host = irq_domain_add_nomap(NULL, ~0, &psurge_host_ops, NULL);
193
194	if (psurge_host)
195		psurge_secondary_virq = irq_create_direct_mapping(psurge_host);
196
197	if (psurge_secondary_virq)
198		rc = request_irq(psurge_secondary_virq, psurge_ipi_intr,
199			IRQF_PERCPU | IRQF_NO_THREAD, "IPI", NULL);
200
201	if (rc)
202		pr_err("Failed to setup secondary cpu IPI\n");
203
204	return rc;
205}
206
207/*
208 * Determine a quad card presence. We read the board ID register, we
209 * force the data bus to change to something else, and we read it again.
210 * It it's stable, then the register probably exist (ugh !)
211 */
212static int __init psurge_quad_probe(void)
213{
214	int type;
215	unsigned int i;
216
217	type = PSURGE_QUAD_IN(PSURGE_QUAD_BOARD_ID);
218	if (type < PSURGE_QUAD_OKEE || type > PSURGE_QUAD_ICEGRASS
219	    || type != PSURGE_QUAD_IN(PSURGE_QUAD_BOARD_ID))
220		return PSURGE_DUAL;
221
222	/* looks OK, try a slightly more rigorous test */
223	/* bogus is not necessarily cacheline-aligned,
224	   though I don't suppose that really matters.  -- paulus */
225	for (i = 0; i < 100; i++) {
226		volatile u32 bogus[8];
227		bogus[(0+i)%8] = 0x00000000;
228		bogus[(1+i)%8] = 0x55555555;
229		bogus[(2+i)%8] = 0xFFFFFFFF;
230		bogus[(3+i)%8] = 0xAAAAAAAA;
231		bogus[(4+i)%8] = 0x33333333;
232		bogus[(5+i)%8] = 0xCCCCCCCC;
233		bogus[(6+i)%8] = 0xCCCCCCCC;
234		bogus[(7+i)%8] = 0x33333333;
235		wmb();
236		asm volatile("dcbf 0,%0" : : "r" (bogus) : "memory");
237		mb();
238		if (type != PSURGE_QUAD_IN(PSURGE_QUAD_BOARD_ID))
239			return PSURGE_DUAL;
240	}
241	return type;
242}
243
244static void __init psurge_quad_init(void)
245{
246	int procbits;
247
248	if (ppc_md.progress) ppc_md.progress("psurge_quad_init", 0x351);
249	procbits = ~PSURGE_QUAD_IN(PSURGE_QUAD_WHICH_CPU);
250	if (psurge_type == PSURGE_QUAD_ICEGRASS)
251		PSURGE_QUAD_BIS(PSURGE_QUAD_RESET_CTL, procbits);
252	else
253		PSURGE_QUAD_BIC(PSURGE_QUAD_CKSTOP_CTL, procbits);
254	mdelay(33);
255	out_8(psurge_sec_intr, ~0);
256	PSURGE_QUAD_OUT(PSURGE_QUAD_IRQ_CLR, procbits);
257	PSURGE_QUAD_BIS(PSURGE_QUAD_RESET_CTL, procbits);
258	if (psurge_type != PSURGE_QUAD_ICEGRASS)
259		PSURGE_QUAD_BIS(PSURGE_QUAD_CKSTOP_CTL, procbits);
260	PSURGE_QUAD_BIC(PSURGE_QUAD_PRIMARY_ARB, procbits);
261	mdelay(33);
262	PSURGE_QUAD_BIC(PSURGE_QUAD_RESET_CTL, procbits);
263	mdelay(33);
264	PSURGE_QUAD_BIS(PSURGE_QUAD_PRIMARY_ARB, procbits);
265	mdelay(33);
266}
267
268static void __init smp_psurge_probe(void)
269{
270	int i, ncpus;
271	struct device_node *dn;
272
273	/*
274	 * The powersurge cpu board can be used in the generation
275	 * of powermacs that have a socket for an upgradeable cpu card,
276	 * including the 7500, 8500, 9500, 9600.
277	 * The device tree doesn't tell you if you have 2 cpus because
278	 * OF doesn't know anything about the 2nd processor.
279	 * Instead we look for magic bits in magic registers,
280	 * in the hammerhead memory controller in the case of the
281	 * dual-cpu powersurge board.  -- paulus.
282	 */
283	dn = of_find_node_by_name(NULL, "hammerhead");
284	if (dn == NULL)
285		return;
286	of_node_put(dn);
287
288	hhead_base = ioremap(HAMMERHEAD_BASE, 0x800);
289	quad_base = ioremap(PSURGE_QUAD_REG_ADDR, 1024);
290	psurge_sec_intr = hhead_base + HHEAD_SEC_INTR;
291
292	psurge_type = psurge_quad_probe();
293	if (psurge_type != PSURGE_DUAL) {
294		psurge_quad_init();
295		/* All released cards using this HW design have 4 CPUs */
296		ncpus = 4;
297		/* No sure how timebase sync works on those, let's use SW */
298		smp_ops->give_timebase = smp_generic_give_timebase;
299		smp_ops->take_timebase = smp_generic_take_timebase;
300	} else {
301		iounmap(quad_base);
302		if ((in_8(hhead_base + HHEAD_CONFIG) & 0x02) == 0) {
303			/* not a dual-cpu card */
304			iounmap(hhead_base);
305			psurge_type = PSURGE_NONE;
306			return;
307		}
308		ncpus = 2;
309	}
310
311	if (psurge_secondary_ipi_init())
312		return;
313
314	psurge_start = ioremap(PSURGE_START, 4);
315	psurge_pri_intr = ioremap(PSURGE_PRI_INTR, 4);
316
317	/* This is necessary because OF doesn't know about the
318	 * secondary cpu(s), and thus there aren't nodes in the
319	 * device tree for them, and smp_setup_cpu_maps hasn't
320	 * set their bits in cpu_present_mask.
321	 */
322	if (ncpus > NR_CPUS)
323		ncpus = NR_CPUS;
324	for (i = 1; i < ncpus ; ++i)
325		set_cpu_present(i, true);
326
327	if (ppc_md.progress) ppc_md.progress("smp_psurge_probe - done", 0x352);
328}
329
330static int __init smp_psurge_kick_cpu(int nr)
331{
332	unsigned long start = __pa(__secondary_start_pmac_0) + nr * 8;
333	unsigned long a, flags;
334	int i, j;
335
336	/* Defining this here is evil ... but I prefer hiding that
337	 * crap to avoid giving people ideas that they can do the
338	 * same.
339	 */
340	extern volatile unsigned int cpu_callin_map[NR_CPUS];
341
342	/* may need to flush here if secondary bats aren't setup */
343	for (a = KERNELBASE; a < KERNELBASE + 0x800000; a += 32)
344		asm volatile("dcbf 0,%0" : : "r" (a) : "memory");
345	asm volatile("sync");
346
347	if (ppc_md.progress) ppc_md.progress("smp_psurge_kick_cpu", 0x353);
348
349	/* This is going to freeze the timeebase, we disable interrupts */
350	local_irq_save(flags);
351
352	out_be32(psurge_start, start);
353	mb();
354
355	psurge_set_ipi(nr);
356
357	/*
358	 * We can't use udelay here because the timebase is now frozen.
359	 */
360	for (i = 0; i < 2000; ++i)
361		asm volatile("nop" : : : "memory");
362	psurge_clr_ipi(nr);
363
364	/*
365	 * Also, because the timebase is frozen, we must not return to the
366	 * caller which will try to do udelay's etc... Instead, we wait -here-
367	 * for the CPU to callin.
368	 */
369	for (i = 0; i < 100000 && !cpu_callin_map[nr]; ++i) {
370		for (j = 1; j < 10000; j++)
371			asm volatile("nop" : : : "memory");
372		asm volatile("sync" : : : "memory");
373	}
374	if (!cpu_callin_map[nr])
375		goto stuck;
376
377	/* And we do the TB sync here too for standard dual CPU cards */
378	if (psurge_type == PSURGE_DUAL) {
379		while(!tb_req)
380			barrier();
381		tb_req = 0;
382		mb();
383		timebase = get_tb();
384		mb();
385		while (timebase)
386			barrier();
387		mb();
388	}
389 stuck:
390	/* now interrupt the secondary, restarting both TBs */
391	if (psurge_type == PSURGE_DUAL)
392		psurge_set_ipi(1);
393
394	if (ppc_md.progress) ppc_md.progress("smp_psurge_kick_cpu - done", 0x354);
395
396	return 0;
397}
398
399static void __init smp_psurge_setup_cpu(int cpu_nr)
400{
401	unsigned long flags = IRQF_PERCPU | IRQF_NO_THREAD;
402	int irq;
403
404	if (cpu_nr != 0 || !psurge_start)
405		return;
406
407	/* reset the entry point so if we get another intr we won't
408	 * try to startup again */
409	out_be32(psurge_start, 0x100);
410	irq = irq_create_mapping(NULL, 30);
411	if (request_irq(irq, psurge_ipi_intr, flags, "primary IPI", NULL))
412		printk(KERN_ERR "Couldn't get primary IPI interrupt");
413}
414
415void __init smp_psurge_take_timebase(void)
416{
417	if (psurge_type != PSURGE_DUAL)
418		return;
419
420	tb_req = 1;
421	mb();
422	while (!timebase)
423		barrier();
424	mb();
425	set_tb(timebase >> 32, timebase & 0xffffffff);
426	timebase = 0;
427	mb();
428	set_dec(tb_ticks_per_jiffy/2);
429}
430
431void __init smp_psurge_give_timebase(void)
432{
433	/* Nothing to do here */
434}
435
436/* PowerSurge-style Macs */
437struct smp_ops_t psurge_smp_ops = {
438	.message_pass	= NULL,	/* Use smp_muxed_ipi_message_pass */
439	.cause_ipi	= smp_psurge_cause_ipi,
440	.cause_nmi_ipi	= NULL,
441	.probe		= smp_psurge_probe,
442	.kick_cpu	= smp_psurge_kick_cpu,
443	.setup_cpu	= smp_psurge_setup_cpu,
444	.give_timebase	= smp_psurge_give_timebase,
445	.take_timebase	= smp_psurge_take_timebase,
446};
447#endif /* CONFIG_PPC_PMAC32_PSURGE */
448
449/*
450 * Core 99 and later support
451 */
452
453
454static void smp_core99_give_timebase(void)
455{
456	unsigned long flags;
457
458	local_irq_save(flags);
459
460	while(!tb_req)
461		barrier();
462	tb_req = 0;
463	(*pmac_tb_freeze)(1);
464	mb();
465	timebase = get_tb();
466	mb();
467	while (timebase)
468		barrier();
469	mb();
470	(*pmac_tb_freeze)(0);
471	mb();
472
473	local_irq_restore(flags);
474}
475
476
477static void smp_core99_take_timebase(void)
478{
479	unsigned long flags;
480
481	local_irq_save(flags);
482
483	tb_req = 1;
484	mb();
485	while (!timebase)
486		barrier();
487	mb();
488	set_tb(timebase >> 32, timebase & 0xffffffff);
489	timebase = 0;
490	mb();
491
492	local_irq_restore(flags);
493}
494
495#ifdef CONFIG_PPC64
496/*
497 * G5s enable/disable the timebase via an i2c-connected clock chip.
498 */
499static struct pmac_i2c_bus *pmac_tb_clock_chip_host;
500static u8 pmac_tb_pulsar_addr;
501
502static void smp_core99_cypress_tb_freeze(int freeze)
503{
504	u8 data;
505	int rc;
506
507	/* Strangely, the device-tree says address is 0xd2, but darwin
508	 * accesses 0xd0 ...
509	 */
510	pmac_i2c_setmode(pmac_tb_clock_chip_host,
511			 pmac_i2c_mode_combined);
512	rc = pmac_i2c_xfer(pmac_tb_clock_chip_host,
513			   0xd0 | pmac_i2c_read,
514			   1, 0x81, &data, 1);
515	if (rc != 0)
516		goto bail;
517
518	data = (data & 0xf3) | (freeze ? 0x00 : 0x0c);
519
520       	pmac_i2c_setmode(pmac_tb_clock_chip_host, pmac_i2c_mode_stdsub);
521	rc = pmac_i2c_xfer(pmac_tb_clock_chip_host,
522			   0xd0 | pmac_i2c_write,
523			   1, 0x81, &data, 1);
524
525 bail:
526	if (rc != 0) {
527		printk("Cypress Timebase %s rc: %d\n",
528		       freeze ? "freeze" : "unfreeze", rc);
529		panic("Timebase freeze failed !\n");
530	}
531}
532
533
534static void smp_core99_pulsar_tb_freeze(int freeze)
535{
536	u8 data;
537	int rc;
538
539	pmac_i2c_setmode(pmac_tb_clock_chip_host,
540			 pmac_i2c_mode_combined);
541	rc = pmac_i2c_xfer(pmac_tb_clock_chip_host,
542			   pmac_tb_pulsar_addr | pmac_i2c_read,
543			   1, 0x2e, &data, 1);
544	if (rc != 0)
545		goto bail;
546
547	data = (data & 0x88) | (freeze ? 0x11 : 0x22);
548
549	pmac_i2c_setmode(pmac_tb_clock_chip_host, pmac_i2c_mode_stdsub);
550	rc = pmac_i2c_xfer(pmac_tb_clock_chip_host,
551			   pmac_tb_pulsar_addr | pmac_i2c_write,
552			   1, 0x2e, &data, 1);
553 bail:
554	if (rc != 0) {
555		printk(KERN_ERR "Pulsar Timebase %s rc: %d\n",
556		       freeze ? "freeze" : "unfreeze", rc);
557		panic("Timebase freeze failed !\n");
558	}
559}
560
561static void __init smp_core99_setup_i2c_hwsync(int ncpus)
562{
563	struct device_node *cc = NULL;
564	struct device_node *p;
565	const char *name = NULL;
566	const u32 *reg;
567	int ok;
568
569	/* Look for the clock chip */
570	for_each_node_by_name(cc, "i2c-hwclock") {
571		p = of_get_parent(cc);
572		ok = p && of_device_is_compatible(p, "uni-n-i2c");
573		of_node_put(p);
574		if (!ok)
575			continue;
576
577		pmac_tb_clock_chip_host = pmac_i2c_find_bus(cc);
578		if (pmac_tb_clock_chip_host == NULL)
579			continue;
580		reg = of_get_property(cc, "reg", NULL);
581		if (reg == NULL)
582			continue;
583		switch (*reg) {
584		case 0xd2:
585			if (of_device_is_compatible(cc,"pulsar-legacy-slewing")) {
586				pmac_tb_freeze = smp_core99_pulsar_tb_freeze;
587				pmac_tb_pulsar_addr = 0xd2;
588				name = "Pulsar";
589			} else if (of_device_is_compatible(cc, "cy28508")) {
590				pmac_tb_freeze = smp_core99_cypress_tb_freeze;
591				name = "Cypress";
592			}
593			break;
594		case 0xd4:
595			pmac_tb_freeze = smp_core99_pulsar_tb_freeze;
596			pmac_tb_pulsar_addr = 0xd4;
597			name = "Pulsar";
598			break;
599		}
600		if (pmac_tb_freeze != NULL)
601			break;
602	}
603	if (pmac_tb_freeze != NULL) {
604		/* Open i2c bus for synchronous access */
605		if (pmac_i2c_open(pmac_tb_clock_chip_host, 1)) {
606			printk(KERN_ERR "Failed top open i2c bus for clock"
607			       " sync, fallback to software sync !\n");
608			goto no_i2c_sync;
609		}
610		printk(KERN_INFO "Processor timebase sync using %s i2c clock\n",
611		       name);
612		return;
613	}
614 no_i2c_sync:
615	pmac_tb_freeze = NULL;
616	pmac_tb_clock_chip_host = NULL;
617}
618
619
620
621/*
622 * Newer G5s uses a platform function
623 */
624
625static void smp_core99_pfunc_tb_freeze(int freeze)
626{
627	struct device_node *cpus;
628	struct pmf_args args;
629
630	cpus = of_find_node_by_path("/cpus");
631	BUG_ON(cpus == NULL);
632	args.count = 1;
633	args.u[0].v = !freeze;
634	pmf_call_function(cpus, "cpu-timebase", &args);
635	of_node_put(cpus);
636}
637
638#else /* CONFIG_PPC64 */
639
640/*
641 * SMP G4 use a GPIO to enable/disable the timebase.
642 */
643
644static unsigned int core99_tb_gpio;	/* Timebase freeze GPIO */
645
646static void smp_core99_gpio_tb_freeze(int freeze)
647{
648	if (freeze)
649		pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, core99_tb_gpio, 4);
650	else
651		pmac_call_feature(PMAC_FTR_WRITE_GPIO, NULL, core99_tb_gpio, 0);
652	pmac_call_feature(PMAC_FTR_READ_GPIO, NULL, core99_tb_gpio, 0);
653}
654
655
656#endif /* !CONFIG_PPC64 */
657
658static void core99_init_caches(int cpu)
659{
660#ifndef CONFIG_PPC64
661	/* L2 and L3 cache settings to pass from CPU0 to CPU1 on G4 cpus */
662	static long int core99_l2_cache;
663	static long int core99_l3_cache;
664
665	if (!cpu_has_feature(CPU_FTR_L2CR))
666		return;
667
668	if (cpu == 0) {
669		core99_l2_cache = _get_L2CR();
670		printk("CPU0: L2CR is %lx\n", core99_l2_cache);
671	} else {
672		printk("CPU%d: L2CR was %lx\n", cpu, _get_L2CR());
673		_set_L2CR(0);
674		_set_L2CR(core99_l2_cache);
675		printk("CPU%d: L2CR set to %lx\n", cpu, core99_l2_cache);
676	}
677
678	if (!cpu_has_feature(CPU_FTR_L3CR))
679		return;
680
681	if (cpu == 0){
682		core99_l3_cache = _get_L3CR();
683		printk("CPU0: L3CR is %lx\n", core99_l3_cache);
684	} else {
685		printk("CPU%d: L3CR was %lx\n", cpu, _get_L3CR());
686		_set_L3CR(0);
687		_set_L3CR(core99_l3_cache);
688		printk("CPU%d: L3CR set to %lx\n", cpu, core99_l3_cache);
689	}
690#endif /* !CONFIG_PPC64 */
691}
692
693static void __init smp_core99_setup(int ncpus)
694{
695#ifdef CONFIG_PPC64
696
697	/* i2c based HW sync on some G5s */
698	if (of_machine_is_compatible("PowerMac7,2") ||
699	    of_machine_is_compatible("PowerMac7,3") ||
700	    of_machine_is_compatible("RackMac3,1"))
701		smp_core99_setup_i2c_hwsync(ncpus);
702
703	/* pfunc based HW sync on recent G5s */
704	if (pmac_tb_freeze == NULL) {
705		struct device_node *cpus =
706			of_find_node_by_path("/cpus");
707		if (cpus &&
708		    of_get_property(cpus, "platform-cpu-timebase", NULL)) {
709			pmac_tb_freeze = smp_core99_pfunc_tb_freeze;
710			printk(KERN_INFO "Processor timebase sync using"
711			       " platform function\n");
712		}
713	}
714
715#else /* CONFIG_PPC64 */
716
717	/* GPIO based HW sync on ppc32 Core99 */
718	if (pmac_tb_freeze == NULL && !of_machine_is_compatible("MacRISC4")) {
719		struct device_node *cpu;
720		const u32 *tbprop = NULL;
721
722		core99_tb_gpio = KL_GPIO_TB_ENABLE;	/* default value */
723		cpu = of_find_node_by_type(NULL, "cpu");
724		if (cpu != NULL) {
725			tbprop = of_get_property(cpu, "timebase-enable", NULL);
726			if (tbprop)
727				core99_tb_gpio = *tbprop;
728			of_node_put(cpu);
729		}
730		pmac_tb_freeze = smp_core99_gpio_tb_freeze;
731		printk(KERN_INFO "Processor timebase sync using"
732		       " GPIO 0x%02x\n", core99_tb_gpio);
733	}
734
735#endif /* CONFIG_PPC64 */
736
737	/* No timebase sync, fallback to software */
738	if (pmac_tb_freeze == NULL) {
739		smp_ops->give_timebase = smp_generic_give_timebase;
740		smp_ops->take_timebase = smp_generic_take_timebase;
741		printk(KERN_INFO "Processor timebase sync using software\n");
742	}
743
744#ifndef CONFIG_PPC64
745	{
746		int i;
747
748		/* XXX should get this from reg properties */
749		for (i = 1; i < ncpus; ++i)
750			set_hard_smp_processor_id(i, i);
751	}
752#endif
753
754	/* 32 bits SMP can't NAP */
755	if (!of_machine_is_compatible("MacRISC4"))
756		powersave_nap = 0;
757}
758
759static void __init smp_core99_probe(void)
760{
761	struct device_node *cpus;
762	int ncpus = 0;
763
764	if (ppc_md.progress) ppc_md.progress("smp_core99_probe", 0x345);
765
766	/* Count CPUs in the device-tree */
767	for_each_node_by_type(cpus, "cpu")
768		++ncpus;
769
770	printk(KERN_INFO "PowerMac SMP probe found %d cpus\n", ncpus);
771
772	/* Nothing more to do if less than 2 of them */
773	if (ncpus <= 1)
774		return;
775
776	/* We need to perform some early initialisations before we can start
777	 * setting up SMP as we are running before initcalls
778	 */
779	pmac_pfunc_base_install();
780	pmac_i2c_init();
781
782	/* Setup various bits like timebase sync method, ability to nap, ... */
783	smp_core99_setup(ncpus);
784
785	/* Install IPIs */
786	mpic_request_ipis();
787
788	/* Collect l2cr and l3cr values from CPU 0 */
789	core99_init_caches(0);
790}
791
792static int smp_core99_kick_cpu(int nr)
793{
794	unsigned int save_vector;
795	unsigned long target, flags;
796	unsigned int *vector = (unsigned int *)(PAGE_OFFSET+0x100);
797
798	if (nr < 0 || nr > 3)
799		return -ENOENT;
800
801	if (ppc_md.progress)
802		ppc_md.progress("smp_core99_kick_cpu", 0x346);
803
804	local_irq_save(flags);
805
806	/* Save reset vector */
807	save_vector = *vector;
808
809	/* Setup fake reset vector that does
810	 *   b __secondary_start_pmac_0 + nr*8
811	 */
812	target = (unsigned long) __secondary_start_pmac_0 + nr * 8;
813	patch_branch((struct ppc_inst *)vector, target, BRANCH_SET_LINK);
814
815	/* Put some life in our friend */
816	pmac_call_feature(PMAC_FTR_RESET_CPU, NULL, nr, 0);
817
818	/* FIXME: We wait a bit for the CPU to take the exception, I should
819	 * instead wait for the entry code to set something for me. Well,
820	 * ideally, all that crap will be done in prom.c and the CPU left
821	 * in a RAM-based wait loop like CHRP.
822	 */
823	mdelay(1);
824
825	/* Restore our exception vector */
826	patch_instruction((struct ppc_inst *)vector, ppc_inst(save_vector));
827
828	local_irq_restore(flags);
829	if (ppc_md.progress) ppc_md.progress("smp_core99_kick_cpu done", 0x347);
830
831	return 0;
832}
833
834static void smp_core99_setup_cpu(int cpu_nr)
835{
836	/* Setup L2/L3 */
837	if (cpu_nr != 0)
838		core99_init_caches(cpu_nr);
839
840	/* Setup openpic */
841	mpic_setup_this_cpu();
842}
843
844#ifdef CONFIG_PPC64
845#ifdef CONFIG_HOTPLUG_CPU
846static unsigned int smp_core99_host_open;
847
848static int smp_core99_cpu_prepare(unsigned int cpu)
849{
850	int rc;
851
852	/* Open i2c bus if it was used for tb sync */
853	if (pmac_tb_clock_chip_host && !smp_core99_host_open) {
854		rc = pmac_i2c_open(pmac_tb_clock_chip_host, 1);
855		if (rc) {
856			pr_err("Failed to open i2c bus for time sync\n");
857			return notifier_from_errno(rc);
858		}
859		smp_core99_host_open = 1;
860	}
861	return 0;
862}
863
864static int smp_core99_cpu_online(unsigned int cpu)
865{
866	/* Close i2c bus if it was used for tb sync */
867	if (pmac_tb_clock_chip_host && smp_core99_host_open) {
868		pmac_i2c_close(pmac_tb_clock_chip_host);
869		smp_core99_host_open = 0;
870	}
871	return 0;
872}
873#endif /* CONFIG_HOTPLUG_CPU */
874
875static void __init smp_core99_bringup_done(void)
876{
877	extern void g5_phy_disable_cpu1(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