summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/platforms/85xx/smp.c
blob: 8631ac5f0e579c35ffa4ac2153e237be908a8817 (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
/*
 * Author: Andy Fleming <afleming@freescale.com>
 * 	   Kumar Gala <galak@kernel.crashing.org>
 *
 * Copyright 2006-2008, 2011-2012 Freescale Semiconductor Inc.
 *
 * 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.
 */

#include <linux/stddef.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/kexec.h>
#include <linux/highmem.h>
#include <linux/cpu.h>

#include <asm/machdep.h>
#include <asm/pgtable.h>
#include <asm/page.h>
#include <asm/mpic.h>
#include <asm/cacheflush.h>
#include <asm/dbell.h>
#include <asm/fsl_guts.h>
#include <asm/code-patching.h>
#include <asm/cputhreads.h>

#include <sysdev/fsl_soc.h>
#include <sysdev/mpic.h>
#include "smp.h"

struct epapr_spin_table {
	u32	addr_h;
	u32	addr_l;
	u32	r3_h;
	u32	r3_l;
	u32	reserved;
	u32	pir;
};

static struct ccsr_guts __iomem *guts;
static u64 timebase;
static int tb_req;
static int tb_valid;

static void mpc85xx_timebase_freeze(int freeze)
{
	uint32_t mask;

	mask = CCSR_GUTS_DEVDISR_TB0 | CCSR_GUTS_DEVDISR_TB1;
	if (freeze)
		setbits32(&guts->devdisr, mask);
	else
		clrbits32(&guts->devdisr, mask);

	in_be32(&guts->devdisr);
}

static void mpc85xx_give_timebase(void)
{
	unsigned long flags;

	local_irq_save(flags);

	while (!tb_req)
		barrier();
	tb_req = 0;

	mpc85xx_timebase_freeze(1);
#ifdef CONFIG_PPC64
	/*
	 * e5500/e6500 have a workaround for erratum A-006958 in place
	 * that will reread the timebase until TBL is non-zero.
	 * That would be a bad thing when the timebase is frozen.
	 *
	 * Thus, we read it manually, and instead of checking that
	 * TBL is non-zero, we ensure that TB does not change.  We don't
	 * do that for the main mftb implementation, because it requires
	 * a scratch register
	 */
	{
		u64 prev;

		asm volatile("mfspr %0, %1" : "=r" (timebase) :
			     "i" (SPRN_TBRL));

		do {
			prev = timebase;
			asm volatile("mfspr %0, %1" : "=r" (timebase) :
				     "i" (SPRN_TBRL));
		} while (prev != timebase);
	}
#else
	timebase = get_tb();
#endif
	mb();
	tb_valid = 1;

	while (tb_valid)
		barrier();

	mpc85xx_timebase_freeze(0);

	local_irq_restore(flags);
}

static void mpc85xx_take_timebase(void)
{
	unsigned long flags;

	local_irq_save(flags);

	tb_req = 1;
	while (!tb_valid)
		barrier();

	set_tb(timebase >> 32, timebase & 0xffffffff);
	isync();
	tb_valid = 0;

	local_irq_restore(flags);
}

#ifdef CONFIG_HOTPLUG_CPU
static void smp_85xx_mach_cpu_die(void)
{
	unsigned int cpu = smp_processor_id();
	u32 tmp;

	local_irq_disable();
	idle_task_exit();
	generic_set_cpu_dead(cpu);
	mb();

	mtspr(SPRN_TCR, 0);

	__flush_disable_L1();
	tmp = (mfspr(SPRN_HID0) & ~(HID0_DOZE|HID0_SLEEP)) | HID0_NAP;
	mtspr(SPRN_HID0, tmp);
	isync();

	/* Enter NAP mode. */
	tmp = mfmsr();
	tmp |= MSR_WE;
	mb();
	mtmsr(tmp);
	isync();

	while (1)
		;
}
#endif

static inline void flush_spin_table(void *spin_table)
{
	flush_dcache_range((ulong)spin_table,
		(ulong)spin_table + sizeof(struct epapr_spin_table));
}

static inline u32 read_spin_table_addr_l(void *spin_table)
{
	flush_dcache_range((ulong)spin_table,
		(ulong)spin_table + sizeof(struct epapr_spin_table));
	return in_be32(&((struct epapr_spin_table *)spin_table)->addr_l);
}

#ifdef CONFIG_PPC64
static void wake_hw_thread(void *info)
{
	void fsl_secondary_thread_init(void);
	unsigned long imsr1, inia1;
	int nr = *(const int *)info;

	imsr1 = MSR_KERNEL;
	inia1 = *(unsigned long *)fsl_secondary_thread_init;

	mttmr(TMRN_IMSR1, imsr1);
	mttmr(TMRN_INIA1, inia1);
	mtspr(SPRN_TENS, TEN_THREAD(1));

	smp_generic_kick_cpu(nr);
}
#endif

static int smp_85xx_kick_cpu(int nr)
{
	unsigned long flags;
	const u64 *cpu_rel_addr;
	__iomem struct epapr_spin_table *spin_table;
	struct device_node *np;
	int hw_cpu = get_hard_smp_processor_id(nr);
	int ioremappable;
	int ret = 0;

	WARN_ON(nr < 0 || nr >= NR_CPUS);
	WARN_ON(hw_cpu < 0 || hw_cpu >= NR_CPUS);

	pr_debug("smp_85xx_kick_cpu: kick CPU #%d\n", nr);

#ifdef CONFIG_PPC64
	/* Threads don't use the spin table */
	if (cpu_thread_in_core(nr) != 0) {
		int primary = cpu_first_thread_sibling(nr);

		if (WARN_ON_ONCE(!cpu_has_feature(CPU_FTR_SMT)))
			return -ENOENT;

		if (cpu_thread_in_core(nr) != 1) {
			pr_err("%s: cpu %d: invalid hw thread %d\n",
			       __func__, nr, cpu_thread_in_core(nr));
			return -ENOENT;
		}

		if (!cpu_online(primary)) {
			pr_err("%s: cpu %d: primary %d not online\n",
			       __func__, nr, primary);
			return -ENOENT;
		}

		smp_call_function_single(primary, wake_hw_thread, &nr, 0);
		return 0;
	}
#endif

	np = of_get_cpu_node(nr, NULL);
	cpu_rel_addr = of_get_property(np, "cpu-release-addr", NULL);

	if (cpu_rel_addr == NULL) {
		printk(KERN_ERR "No cpu-release-addr for cpu %d\n", nr);
		return -ENOENT;
	}

	/*
	 * A secondary core could be in a spinloop in the bootpage
	 * (0xfffff000), somewhere in highmem, or somewhere in lowmem.
	 * The bootpage and highmem can be accessed via ioremap(), but
	 * we need to directly access the spinloop if its in lowmem.
	 */
	ioremappable = *cpu_rel_addr > virt_to_phys(high_memory);

	/* Map the spin table */
	if (ioremappable)
		spin_table = ioremap_prot(*cpu_rel_addr,
			sizeof(struct epapr_spin_table), _PAGE_COHERENT);
	else
		spin_table = phys_to_virt(*cpu_rel_addr);

	local_irq_save(flags);
#ifdef CONFIG_PPC32
#ifdef CONFIG_HOTPLUG_CPU
	/* Corresponding to generic_set_cpu_dead() */
	generic_set_cpu_up(nr);

	if (system_state == SYSTEM_RUNNING) {
		/*
		 * To keep it compatible with old boot program which uses
		 * cache-inhibit spin table, we need to flush the cache
		 * before accessing spin table to invalidate any staled data.
		 * We also need to flush the cache after writing to spin
		 * table to push data out.
		 */
		flush_spin_table(spin_table);
		out_be32(&spin_table->addr_l, 0);
		flush_spin_table(spin_table);

		/*
		 * We don't set the BPTR register here since it already points
		 * to the boot page properly.
		 */
		mpic_reset_core(nr);

		/*
		 * wait until core is ready...
		 * We need to invalidate the stale data, in case the boot
		 * loader uses a cache-inhibited spin table.
		 */
		if (!spin_event_timeout(
				read_spin_table_addr_l(spin_table) == 1,
				10000, 100)) {
			pr_err("%s: timeout waiting for core %d to reset\n",
							__func__, hw_cpu);
			ret = -ENOENT;
			goto out;
		}

		/*  clear the acknowledge status */
		__secondary_hold_acknowledge = -1;
	}
#endif
	flush_spin_table(spin_table);
	out_be32(&spin_table->pir, hw_cpu);
	out_be32(&spin_table->addr_l, __pa(__early_start));
	flush_spin_table(spin_table);

	/* Wait a bit for the CPU to ack. */
	if (!spin_event_timeout(__secondary_hold_acknowledge == hw_cpu,
					10000, 100)) {
		pr_err("%s: timeout waiting for core %d to ack\n",
						__func__, hw_cpu);
		ret = -ENOENT;
		goto out;
	}
out:
#else
	smp_generic_kick_cpu(nr);

	flush_spin_table(spin_table);
	out_be32(&spin_table->pir, hw_cpu);
	out_be64((u64 *)(&spin_table->addr_h),
		__pa(ppc_function_entry(generic_secondary_smp_init)));
	flush_spin_table(spin_table);
#endif

	local_irq_restore(flags);

	if (ioremappable)
		iounmap(spin_table);

	return ret;
}

struct smp_ops_t smp_85xx_ops = {
	.kick_cpu = smp_85xx_kick_cpu,
	.cpu_bootable = smp_generic_cpu_bootable,
#ifdef CONFIG_HOTPLUG_CPU
	.cpu_disable	= generic_cpu_disable,
	.cpu_die	= generic_cpu_die,
#endif
#ifdef CONFIG_KEXEC
	.give_timebase	= smp_generic_give_timebase,
	.take_timebase	= smp_generic_take_timebase,
#endif
};

#ifdef CONFIG_KEXEC
atomic_t kexec_down_cpus = ATOMIC_INIT(0);

void mpc85xx_smp_kexec_cpu_down(int crash_shutdown, int secondary)
{
	local_irq_disable();

	if (secondary) {
		atomic_inc(&kexec_down_cpus);
		/* loop forever */
		while (1);
	}
}

static void mpc85xx_smp_kexec_down(void *arg)
{
	if (ppc_md.kexec_cpu_down)
		ppc_md.kexec_cpu_down(0,1);
}

static void map_and_flush(unsigned long paddr)
{
	struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
	unsigned long kaddr  = (unsigned long)kmap_atomic(page);

	flush_dcache_range(kaddr, kaddr + PAGE_SIZE);
	kunmap_atomic((void *)kaddr);
}

/**
 * Before we reset the other cores, we need to flush relevant cache
 * out to memory so we don't get anything corrupted, some of these flushes
 * are performed out of an overabundance of caution as interrupts are not
 * disabled yet and we can switch cores
 */
static void mpc85xx_smp_flush_dcache_kexec(struct kimage *image)
{
	kimage_entry_t *ptr, entry;
	unsigned long paddr;
	int i;

	if (image->type == KEXEC_TYPE_DEFAULT) {
		/* normal kexec images are stored in temporary pages */
		for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE);
		     ptr = (entry & IND_INDIRECTION) ?
				phys_to_virt(entry & PAGE_MASK) : ptr + 1) {
			if (!(entry & IND_DESTINATION)) {
				map_and_flush(entry);
			}
		}
		/* flush out last IND_DONE page */
		map_and_flush(entry);
	} else {
		/* crash type kexec images are copied to the crash region */
		for (i = 0; i < image->nr_segments; i++) {
			struct kexec_segment *seg = &image->segment[i];
			for (paddr = seg->mem; paddr < seg->mem + seg->memsz;
			     paddr += PAGE_SIZE) {
				map_and_flush(paddr);
			}
		}
	}

	/* also flush the kimage struct to be passed in as well */
	flush_dcache_range((unsigned long)image,
			   (unsigned long)image + sizeof(*image));
}

static void mpc85xx_smp_machine_kexec(struct kimage *image)
{
	int timeout = INT_MAX;
	int i, num_cpus = num_present_cpus();

	mpc85xx_smp_flush_dcache_kexec(image);

	if (image->type == KEXEC_TYPE_DEFAULT)
		smp_call_function(mpc85xx_smp_kexec_down, NULL, 0);

	while ( (atomic_read(&kexec_down_cpus) != (num_cpus - 1)) &&
		( timeout > 0 ) )
	{
		timeout--;
	}

	if ( !timeout )
		printk(KERN_ERR "Unable to bring down secondary cpu(s)");

	for_each_online_cpu(i)
	{
		if ( i == smp_processor_id() ) continue;
		mpic_reset_core(i);
	}

	default_machine_kexec(image);
}
#endif /* CONFIG_KEXEC */

static void smp_85xx_basic_setup(int cpu_nr)
{
	if (cpu_has_feature(CPU_FTR_DBELL))
		doorbell_setup_this_cpu();
}

static void smp_85xx_setup_cpu(int cpu_nr)
{
	mpic_setup_this_cpu();
	smp_85xx_basic_setup(cpu_nr);
}

static const struct of_device_id mpc85xx_smp_guts_ids[] = {
	{ .compatible = "fsl,mpc8572-guts", },
	{ .compatible = "fsl,p1020-guts", },
	{ .compatible = "fsl,p1021-guts", },
	{ .compatible = "fsl,p1022-guts", },
	{ .compatible = "fsl,p1023-guts", },
	{ .compatible = "fsl,p2020-guts", },
	{},
};

void __init mpc85xx_smp_init(void)
{
	struct device_node *np;


	np = of_find_node_by_type(NULL, "open-pic");
	if (np) {
		smp_85xx_ops.probe = smp_mpic_probe;
		smp_85xx_ops.setup_cpu = smp_85xx_setup_cpu;
		smp_85xx_ops.message_pass = smp_mpic_message_pass;
	} else
		smp_85xx_ops.setup_cpu = smp_85xx_basic_setup;

	if (cpu_has_feature(CPU_FTR_DBELL)) {
		/*
		 * If left NULL, .message_pass defaults to
		 * smp_muxed_ipi_message_pass
		 */
		smp_85xx_ops.message_pass = NULL;
		smp_85xx_ops.cause_ipi = doorbell_cause_ipi;
		smp_85xx_ops.probe = NULL;
	}

	np = of_find_matching_node(NULL, mpc85xx_smp_guts_ids);
	if (np) {
		guts = of_iomap(np, 0);
		of_node_put(np);
		if (!guts) {
			pr_err("%s: Could not map guts node address\n",
								__func__);
			return;
		}
		smp_85xx_ops.give_timebase = mpc85xx_give_timebase;
		smp_85xx_ops.take_timebase = mpc85xx_take_timebase;
#ifdef CONFIG_HOTPLUG_CPU
		ppc_md.cpu_die = smp_85xx_mach_cpu_die;
#endif
	}

	smp_ops = &smp_85xx_ops;

#ifdef CONFIG_KEXEC
	ppc_md.kexec_cpu_down = mpc85xx_smp_kexec_cpu_down;
	ppc_md.machine_kexec = mpc85xx_smp_machine_kexec;
#endif
}