summaryrefslogtreecommitdiffstats
path: root/arch/arm/mach-vexpress/tc2_pm.c
blob: 7aeb5d60e484642d08ed119ecfd083b3c4074a46 (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
/*
 * arch/arm/mach-vexpress/tc2_pm.c - TC2 power management support
 *
 * Created by:	Nicolas Pitre, October 2012
 * Copyright:	(C) 2012-2013  Linaro Limited
 *
 * Some portions of this file were originally written by Achin Gupta
 * Copyright:   (C) 2012  ARM Limited
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#include <linux/init.h>
#include <linux/io.h>
#include <linux/kernel.h>
#include <linux/of_address.h>
#include <linux/spinlock.h>
#include <linux/errno.h>
#include <linux/irqchip/arm-gic.h>

#include <asm/mcpm.h>
#include <asm/proc-fns.h>
#include <asm/cacheflush.h>
#include <asm/cputype.h>
#include <asm/cp15.h>

#include <linux/arm-cci.h>

#include "spc.h"

/* SCC conf registers */
#define A15_CONF		0x400
#define A7_CONF			0x500
#define SYS_INFO		0x700
#define SPC_BASE		0xb00

/*
 * We can't use regular spinlocks. In the switcher case, it is possible
 * for an outbound CPU to call power_down() after its inbound counterpart
 * is already live using the same logical CPU number which trips lockdep
 * debugging.
 */
static arch_spinlock_t tc2_pm_lock = __ARCH_SPIN_LOCK_UNLOCKED;

#define TC2_CLUSTERS			2
#define TC2_MAX_CPUS_PER_CLUSTER	3

static unsigned int tc2_nr_cpus[TC2_CLUSTERS];

/* Keep per-cpu usage count to cope with unordered up/down requests */
static int tc2_pm_use_count[TC2_MAX_CPUS_PER_CLUSTER][TC2_CLUSTERS];

#define tc2_cluster_unused(cluster) \
	(!tc2_pm_use_count[0][cluster] && \
	 !tc2_pm_use_count[1][cluster] && \
	 !tc2_pm_use_count[2][cluster])

static int tc2_pm_power_up(unsigned int cpu, unsigned int cluster)
{
	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
	if (cluster >= TC2_CLUSTERS || cpu >= tc2_nr_cpus[cluster])
		return -EINVAL;

	/*
	 * Since this is called with IRQs enabled, and no arch_spin_lock_irq
	 * variant exists, we need to disable IRQs manually here.
	 */
	local_irq_disable();
	arch_spin_lock(&tc2_pm_lock);

	if (tc2_cluster_unused(cluster))
		ve_spc_powerdown(cluster, false);

	tc2_pm_use_count[cpu][cluster]++;
	if (tc2_pm_use_count[cpu][cluster] == 1) {
		ve_spc_set_resume_addr(cluster, cpu,
				       virt_to_phys(mcpm_entry_point));
		ve_spc_cpu_wakeup_irq(cluster, cpu, true);
	} else if (tc2_pm_use_count[cpu][cluster] != 2) {
		/*
		 * The only possible values are:
		 * 0 = CPU down
		 * 1 = CPU (still) up
		 * 2 = CPU requested to be up before it had a chance
		 *     to actually make itself down.
		 * Any other value is a bug.
		 */
		BUG();
	}

	arch_spin_unlock(&tc2_pm_lock);
	local_irq_enable();

	return 0;
}

static void tc2_pm_down(u64 residency)
{
	unsigned int mpidr, cpu, cluster;
	bool last_man = false, skip_wfi = false;

	mpidr = read_cpuid_mpidr();
	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);

	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
	BUG_ON(cluster >= TC2_CLUSTERS || cpu >= TC2_MAX_CPUS_PER_CLUSTER);

	__mcpm_cpu_going_down(cpu, cluster);

	arch_spin_lock(&tc2_pm_lock);
	BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
	tc2_pm_use_count[cpu][cluster]--;
	if (tc2_pm_use_count[cpu][cluster] == 0) {
		ve_spc_cpu_wakeup_irq(cluster, cpu, true);
		if (tc2_cluster_unused(cluster)) {
			ve_spc_powerdown(cluster, true);
			ve_spc_global_wakeup_irq(true);
			last_man = true;
		}
	} else if (tc2_pm_use_count[cpu][cluster] == 1) {
		/*
		 * A power_up request went ahead of us.
		 * Even if we do not want to shut this CPU down,
		 * the caller expects a certain state as if the WFI
		 * was aborted.  So let's continue with cache cleaning.
		 */
		skip_wfi = true;
	} else
		BUG();

	if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
		arch_spin_unlock(&tc2_pm_lock);

		if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A15) {
			/*
			 * On the Cortex-A15 we need to disable
			 * L2 prefetching before flushing the cache.
			 */
			asm volatile(
			"mcr	p15, 1, %0, c15, c0, 3 \n\t"
			"isb	\n\t"
			"dsb	"
			: : "r" (0x400) );
		}

		/*
		 * We need to disable and flush the whole (L1 and L2) cache.
		 * Let's do it in the safest possible way i.e. with
		 * no memory access within the following sequence
		 * including the stack.
		 *
		 * Note: fp is preserved to the stack explicitly prior doing
		 * this since adding it to the clobber list is incompatible
		 * with having CONFIG_FRAME_POINTER=y.
		 */
		asm volatile(
		"str	fp, [sp, #-4]! \n\t"
		"mrc	p15, 0, r0, c1, c0, 0	@ get CR \n\t"
		"bic	r0, r0, #"__stringify(CR_C)" \n\t"
		"mcr	p15, 0, r0, c1, c0, 0	@ set CR \n\t"
		"isb	\n\t"
		"bl	v7_flush_dcache_all \n\t"
		"clrex	\n\t"
		"mrc	p15, 0, r0, c1, c0, 1	@ get AUXCR \n\t"
		"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t"
		"mcr	p15, 0, r0, c1, c0, 1	@ set AUXCR \n\t"
		"isb	\n\t"
		"dsb	\n\t"
		"ldr	fp, [sp], #4"
		: : : "r0","r1","r2","r3","r4","r5","r6","r7",
		      "r9","r10","lr","memory");

		cci_disable_port_by_cpu(mpidr);

		__mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
	} else {
		/*
		 * If last man then undo any setup done previously.
		 */
		if (last_man) {
			ve_spc_powerdown(cluster, false);
			ve_spc_global_wakeup_irq(false);
		}

		arch_spin_unlock(&tc2_pm_lock);

		/*
		 * We need to disable and flush only the L1 cache.
		 * Let's do it in the safest possible way as above.
		 */
		asm volatile(
		"str	fp, [sp, #-4]! \n\t"
		"mrc	p15, 0, r0, c1, c0, 0	@ get CR \n\t"
		"bic	r0, r0, #"__stringify(CR_C)" \n\t"
		"mcr	p15, 0, r0, c1, c0, 0	@ set CR \n\t"
		"isb	\n\t"
		"bl	v7_flush_dcache_louis \n\t"
		"clrex	\n\t"
		"mrc	p15, 0, r0, c1, c0, 1	@ get AUXCR \n\t"
		"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t"
		"mcr	p15, 0, r0, c1, c0, 1	@ set AUXCR \n\t"
		"isb	\n\t"
		"dsb	\n\t"
		"ldr	fp, [sp], #4"
		: : : "r0","r1","r2","r3","r4","r5","r6","r7",
		      "r9","r10","lr","memory");
	}

	__mcpm_cpu_down(cpu, cluster);

	/* Now we are prepared for power-down, do it: */
	if (!skip_wfi)
		wfi();

	/* Not dead at this point?  Let our caller cope. */
}

static void tc2_pm_power_down(void)
{
	tc2_pm_down(0);
}

static void tc2_pm_suspend(u64 residency)
{
	unsigned int mpidr, cpu, cluster;

	mpidr = read_cpuid_mpidr();
	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
	ve_spc_set_resume_addr(cluster, cpu, virt_to_phys(mcpm_entry_point));
	gic_cpu_if_down();
	tc2_pm_down(residency);
}

static void tc2_pm_powered_up(void)
{
	unsigned int mpidr, cpu, cluster;
	unsigned long flags;

	mpidr = read_cpuid_mpidr();
	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);

	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
	BUG_ON(cluster >= TC2_CLUSTERS || cpu >= TC2_MAX_CPUS_PER_CLUSTER);

	local_irq_save(flags);
	arch_spin_lock(&tc2_pm_lock);

	if (tc2_cluster_unused(cluster)) {
		ve_spc_powerdown(cluster, false);
		ve_spc_global_wakeup_irq(false);
	}

	if (!tc2_pm_use_count[cpu][cluster])
		tc2_pm_use_count[cpu][cluster] = 1;

	ve_spc_cpu_wakeup_irq(cluster, cpu, false);
	ve_spc_set_resume_addr(cluster, cpu, 0);

	arch_spin_unlock(&tc2_pm_lock);
	local_irq_restore(flags);
}

static const struct mcpm_platform_ops tc2_pm_power_ops = {
	.power_up	= tc2_pm_power_up,
	.power_down	= tc2_pm_power_down,
	.suspend	= tc2_pm_suspend,
	.powered_up	= tc2_pm_powered_up,
};

static bool __init tc2_pm_usage_count_init(void)
{
	unsigned int mpidr, cpu, cluster;

	mpidr = read_cpuid_mpidr();
	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);

	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
	if (cluster >= TC2_CLUSTERS || cpu >= tc2_nr_cpus[cluster]) {
		pr_err("%s: boot CPU is out of bound!\n", __func__);
		return false;
	}
	tc2_pm_use_count[cpu][cluster] = 1;
	return true;
}

/*
 * Enable cluster-level coherency, in preparation for turning on the MMU.
 */
static void __naked tc2_pm_power_up_setup(unsigned int affinity_level)
{
	asm volatile (" \n"
"	cmp	r0, #1 \n"
"	bxne	lr \n"
"	b	cci_enable_port_for_self ");
}

static int __init tc2_pm_init(void)
{
	int ret;
	void __iomem *scc;
	u32 a15_cluster_id, a7_cluster_id, sys_info;
	struct device_node *np;

	/*
	 * The power management-related features are hidden behind
	 * SCC registers. We need to extract runtime information like
	 * cluster ids and number of CPUs really available in clusters.
	 */
	np = of_find_compatible_node(NULL, NULL,
			"arm,vexpress-scc,v2p-ca15_a7");
	scc = of_iomap(np, 0);
	if (!scc)
		return -ENODEV;

	a15_cluster_id = readl_relaxed(scc + A15_CONF) & 0xf;
	a7_cluster_id = readl_relaxed(scc + A7_CONF) & 0xf;
	if (a15_cluster_id >= TC2_CLUSTERS || a7_cluster_id >= TC2_CLUSTERS)
		return -EINVAL;

	sys_info = readl_relaxed(scc + SYS_INFO);
	tc2_nr_cpus[a15_cluster_id] = (sys_info >> 16) & 0xf;
	tc2_nr_cpus[a7_cluster_id] = (sys_info >> 20) & 0xf;

	/*
	 * A subset of the SCC registers is also used to communicate
	 * with the SPC (power controller). We need to be able to
	 * drive it very early in the boot process to power up
	 * processors, so we initialize the SPC driver here.
	 */
	ret = ve_spc_init(scc + SPC_BASE, a15_cluster_id);
	if (ret)
		return ret;

	if (!cci_probed())
		return -ENODEV;

	if (!tc2_pm_usage_count_init())
		return -EINVAL;

	ret = mcpm_platform_register(&tc2_pm_power_ops);
	if (!ret) {
		mcpm_sync_init(tc2_pm_power_up_setup);
		pr_info("TC2 power management initialized\n");
	}
	return ret;
}

early_initcall(tc2_pm_init);