aboutsummaryrefslogtreecommitdiff
path: root/arch/arm/common/bL_switcher.c
blob: c2d9c7da0a2c9588cd627aaea372aa62f391718c (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
/*
 * arch/arm/common/bL_switcher.c -- big.LITTLE cluster switcher core driver
 *
 * Created by:	Nicolas Pitre, March 2012
 * Copyright:	(C) 2012  Linaro 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/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/interrupt.h>
#include <linux/cpu_pm.h>
#include <linux/cpumask.h>
#include <linux/workqueue.h>
#include <linux/clockchips.h>
#include <linux/hrtimer.h>
#include <linux/tick.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/irqchip/arm-gic.h>

#include <asm/smp_plat.h>
#include <asm/cacheflush.h>
#include <asm/suspend.h>
#include <asm/mcpm.h>
#include <asm/bL_switcher.h>


/*
 * Use our own MPIDR accessors as the generic ones in asm/cputype.h have
 * __attribute_const__ and we don't want the compiler to assume any
 * constness here as the value _does_ change along some code paths.
 */

static int read_mpidr(void)
{
	unsigned int id;
	asm volatile ("mrc\tp15, 0, %0, c0, c0, 5" : "=r" (id));
	return id & MPIDR_HWID_BITMASK;
}

/*
 * bL switcher core code.
 */

static void bL_do_switch(void *_unused)
{
	unsigned mpidr, cpuid, clusterid, ob_cluster, ib_cluster;

	/*
	 * We now have a piece of stack borrowed from the init task's.
	 * Let's also switch to init_mm right away to match it.
	 */
	cpu_switch_mm(init_mm.pgd, &init_mm);

	pr_debug("%s\n", __func__);

	mpidr = read_mpidr();
	cpuid = MPIDR_AFFINITY_LEVEL(mpidr, 0);
	clusterid = MPIDR_AFFINITY_LEVEL(mpidr, 1);
	ob_cluster = clusterid;
	ib_cluster = clusterid ^ 1;

	/*
	 * Our state has been saved at this point.  Let's release our
	 * inbound CPU.
	 */
	mcpm_set_entry_vector(cpuid, ib_cluster, cpu_resume);
	sev();

	/*
	 * From this point, we must assume that our counterpart CPU might
	 * have taken over in its parallel world already, as if execution
	 * just returned from cpu_suspend().  It is therefore important to
	 * be very careful not to make any change the other guy is not
	 * expecting.  This is why we need stack isolation.
	 *
	 * Fancy under cover tasks could be performed here.  For now
	 * we have none.
	 */

	/* Let's put ourself down. */
	mcpm_cpu_power_down();

	/* should never get here */
	BUG();
}

/*
 * Stack isolation.  To ensure 'current' remains valid, we just borrow
 * a slice of the init/idle task which should be fairly lightly used.
 * The borrowed area starts just above the thread_info structure located
 * at the very bottom of the stack, aligned to a cache line.
 */
#define STACK_SIZE 256
extern void call_with_stack(void (*fn)(void *), void *arg, void *sp);
static int bL_switchpoint(unsigned long _arg)
{
	unsigned int mpidr = read_mpidr();
	unsigned int cpuid = MPIDR_AFFINITY_LEVEL(mpidr, 0);
	unsigned int clusterid = MPIDR_AFFINITY_LEVEL(mpidr, 1);
	unsigned int cpu_index = cpuid + clusterid * MAX_CPUS_PER_CLUSTER;
	void *stack = &init_thread_info + 1;
	stack = PTR_ALIGN(stack, L1_CACHE_BYTES);
	stack += cpu_index * STACK_SIZE + STACK_SIZE;
	call_with_stack(bL_do_switch, (void *)_arg, stack);
	BUG();
}

/*
 * Generic switcher interface
 */

/*
 * bL_switch_to - Switch to a specific cluster for the current CPU
 * @new_cluster_id: the ID of the cluster to switch to.
 *
 * This function must be called on the CPU to be switched.
 * Returns 0 on success, else a negative status code.
 */
static int bL_switch_to(unsigned int new_cluster_id)
{
	unsigned int mpidr, cpuid, clusterid, ob_cluster, ib_cluster, this_cpu;
	struct tick_device *tdev;
	enum clock_event_mode tdev_mode;
	int ret;

	mpidr = read_mpidr();
	cpuid = MPIDR_AFFINITY_LEVEL(mpidr, 0);
	clusterid = MPIDR_AFFINITY_LEVEL(mpidr, 1);
	ob_cluster = clusterid;
	ib_cluster = clusterid ^ 1;

	if (new_cluster_id == clusterid)
		return 0;

	pr_debug("before switch: CPU %d in cluster %d\n", cpuid, clusterid);

	/* Close the gate for our entry vectors */
	mcpm_set_entry_vector(cpuid, ob_cluster, NULL);
	mcpm_set_entry_vector(cpuid, ib_cluster, NULL);

	/*
	 * Let's wake up the inbound CPU now in case it requires some delay
	 * to come online, but leave it gated in our entry vector code.
	 */
	ret = mcpm_cpu_power_up(cpuid, ib_cluster);
	if (ret) {
		pr_err("%s: mcpm_cpu_power_up() returned %d\n", __func__, ret);
		return ret;
	}

	/*
	 * From this point we are entering the switch critical zone
	 * and can't sleep/schedule anymore.
	 */
	local_irq_disable();
	local_fiq_disable();

	this_cpu = smp_processor_id();

	/* redirect GIC's SGIs to our counterpart */
	gic_migrate_target(cpuid + ib_cluster*4);

	/*
	 * Raise a SGI on the inbound CPU to make sure it doesn't stall
	 * in a possible WFI, such as in mcpm_power_down().
	 */
	arch_send_wakeup_ipi_mask(cpumask_of(this_cpu));

	tdev = tick_get_device(this_cpu);
	if (tdev && !cpumask_equal(tdev->evtdev->cpumask, cpumask_of(this_cpu)))
		tdev = NULL;
	if (tdev) {
		tdev_mode = tdev->evtdev->mode;
		clockevents_set_mode(tdev->evtdev, CLOCK_EVT_MODE_SHUTDOWN);
	}

	ret = cpu_pm_enter();

	/* we can not tolerate errors at this point */
	if (ret)
		panic("%s: cpu_pm_enter() returned %d\n", __func__, ret);

	/*
	 * Flip the cluster in the CPU logical map for this CPU.
	 * This must be flushed to RAM as the resume code
	 * needs to access it while the caches are still disabled.
	 */
	cpu_logical_map(this_cpu) ^= (1 << 8);
	__cpuc_flush_dcache_area(&cpu_logical_map(this_cpu),
				 sizeof(cpu_logical_map(this_cpu)));

	/* Let's do the actual CPU switch. */
	ret = cpu_suspend(0, bL_switchpoint);
	if (ret > 0)
		panic("%s: cpu_suspend() returned %d\n", __func__, ret);

	/* We are executing on the inbound CPU at this point */
	mpidr = read_mpidr();
	cpuid = MPIDR_AFFINITY_LEVEL(mpidr, 0);
	clusterid = MPIDR_AFFINITY_LEVEL(mpidr, 1);
	pr_debug("after switch: CPU %d in cluster %d\n", cpuid, clusterid);
	BUG_ON(clusterid != ib_cluster);

	mcpm_cpu_powered_up();

	ret = cpu_pm_exit();

	if (tdev) {
		clockevents_set_mode(tdev->evtdev, tdev_mode);
		clockevents_program_event(tdev->evtdev,
					  tdev->evtdev->next_event, 1);
	}

	local_fiq_enable();
	local_irq_enable();

	if (ret)
		pr_err("%s exiting with error %d\n", __func__, ret);
	return ret;
}

struct switch_args {
	unsigned int cluster;
	struct work_struct work;
};

static void __bL_switch_to(struct work_struct *work)
{
	struct switch_args *args = container_of(work, struct switch_args, work);
	bL_switch_to(args->cluster);
}

/*
 * bL_switch_request - Switch to a specific cluster for the given CPU
 *
 * @cpu: the CPU to switch
 * @new_cluster_id: the ID of the cluster to switch to.
 *
 * This function causes a cluster switch on the given CPU.  If the given
 * CPU is the same as the calling CPU then the switch happens right away.
 * Otherwise the request is put on a work queue to be scheduled on the
 * remote CPU.
 */
void bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
{
	unsigned int this_cpu = get_cpu();
	struct switch_args args;

	if (cpu == this_cpu) {
		bL_switch_to(new_cluster_id);
		put_cpu();
		return;
	}
	put_cpu();

	args.cluster = new_cluster_id;
	INIT_WORK_ONSTACK(&args.work, __bL_switch_to);
	schedule_work_on(cpu, &args.work);
	flush_work(&args.work);
}

EXPORT_SYMBOL_GPL(bL_switch_request);