smp.c 10.3 KB
Newer Older
C
Catalin Marinas 已提交
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
/*
 * SMP initialisation and IPI support
 * Based on arch/arm/kernel/smp.c
 *
 * Copyright (C) 2012 ARM Ltd.
 *
 * 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.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#include <linux/delay.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/sched.h>
#include <linux/interrupt.h>
#include <linux/cache.h>
#include <linux/profile.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/err.h>
#include <linux/cpu.h>
#include <linux/smp.h>
#include <linux/seq_file.h>
#include <linux/irq.h>
#include <linux/percpu.h>
#include <linux/clockchips.h>
#include <linux/completion.h>
#include <linux/of.h>

#include <asm/atomic.h>
#include <asm/cacheflush.h>
#include <asm/cputype.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/processor.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
#include <asm/ptrace.h>

/*
 * as from 2.5, kernels no longer have an init_tasks structure
 * so we need some other way of telling a new secondary core
 * where to place its SVC stack
 */
struct secondary_data secondary_data;
volatile unsigned long secondary_holding_pen_release = -1;

enum ipi_msg_type {
	IPI_RESCHEDULE,
	IPI_CALL_FUNC,
	IPI_CALL_FUNC_SINGLE,
	IPI_CPU_STOP,
};

static DEFINE_RAW_SPINLOCK(boot_lock);

/*
 * Write secondary_holding_pen_release in a way that is guaranteed to be
 * visible to all observers, irrespective of whether they're taking part
 * in coherency or not.  This is necessary for the hotplug code to work
 * reliably.
 */
static void __cpuinit write_pen_release(int val)
{
	void *start = (void *)&secondary_holding_pen_release;
	unsigned long size = sizeof(secondary_holding_pen_release);

	secondary_holding_pen_release = val;
	__flush_dcache_area(start, size);
}

/*
 * Boot a secondary CPU, and assign it the specified idle task.
 * This also gives us the initial stack to use for this CPU.
 */
static int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
{
	unsigned long timeout;

	/*
	 * Set synchronisation state between this boot processor
	 * and the secondary one
	 */
	raw_spin_lock(&boot_lock);

	/*
	 * Update the pen release flag.
	 */
	write_pen_release(cpu);

	/*
	 * Send an event, causing the secondaries to read pen_release.
	 */
	sev();

	timeout = jiffies + (1 * HZ);
	while (time_before(jiffies, timeout)) {
		if (secondary_holding_pen_release == -1UL)
			break;
		udelay(10);
	}

	/*
	 * Now the secondary core is starting up let it run its
	 * calibrations, then wait for it to finish
	 */
	raw_spin_unlock(&boot_lock);

	return secondary_holding_pen_release != -1 ? -ENOSYS : 0;
}

static DECLARE_COMPLETION(cpu_running);

int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *idle)
{
	int ret;

	/*
	 * We need to tell the secondary core where to find its stack and the
	 * page tables.
	 */
	secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;
	__flush_dcache_area(&secondary_data, sizeof(secondary_data));

	/*
	 * Now bring the CPU into our world.
	 */
	ret = boot_secondary(cpu, idle);
	if (ret == 0) {
		/*
		 * CPU was successfully started, wait for it to come online or
		 * time out.
		 */
		wait_for_completion_timeout(&cpu_running,
					    msecs_to_jiffies(1000));

		if (!cpu_online(cpu)) {
			pr_crit("CPU%u: failed to come online\n", cpu);
			ret = -EIO;
		}
	} else {
		pr_err("CPU%u: failed to boot: %d\n", cpu, ret);
	}

	secondary_data.stack = NULL;

	return ret;
}

/*
 * This is the secondary CPU boot entry.  We're using this CPUs
 * idle thread stack, but a set of temporary page tables.
 */
asmlinkage void __cpuinit secondary_start_kernel(void)
{
	struct mm_struct *mm = &init_mm;
	unsigned int cpu = smp_processor_id();

	printk("CPU%u: Booted secondary processor\n", cpu);

	/*
	 * All kernel threads share the same mm context; grab a
	 * reference and switch to it.
	 */
	atomic_inc(&mm->mm_count);
	current->active_mm = mm;
	cpumask_set_cpu(cpu, mm_cpumask(mm));

	/*
	 * TTBR0 is only used for the identity mapping at this stage. Make it
	 * point to zero page to avoid speculatively fetching new entries.
	 */
	cpu_set_reserved_ttbr0();
	flush_tlb_all();

	preempt_disable();
	trace_hardirqs_off();

	/*
	 * Let the primary processor know we're out of the
	 * pen, then head off into the C entry point
	 */
	write_pen_release(-1);

	/*
	 * Synchronise with the boot thread.
	 */
	raw_spin_lock(&boot_lock);
	raw_spin_unlock(&boot_lock);

	/*
	 * Enable local interrupts.
	 */
	notify_cpu_starting(cpu);
	local_irq_enable();
	local_fiq_enable();

	/*
	 * OK, now it's safe to let the boot CPU continue.  Wait for
	 * the CPU migration code to notice that the CPU is online
	 * before we continue.
	 */
	set_cpu_online(cpu, true);
214
	complete(&cpu_running);
C
Catalin Marinas 已提交
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

	/*
	 * OK, it's off to the idle thread for us
	 */
	cpu_idle();
}

void __init smp_cpus_done(unsigned int max_cpus)
{
	unsigned long bogosum = loops_per_jiffy * num_online_cpus();

	pr_info("SMP: Total of %d processors activated (%lu.%02lu BogoMIPS).\n",
		num_online_cpus(), bogosum / (500000/HZ),
		(bogosum / (5000/HZ)) % 100);
}

void __init smp_prepare_boot_cpu(void)
{
}

static void (*smp_cross_call)(const struct cpumask *, unsigned int);
static phys_addr_t cpu_release_addr[NR_CPUS];

/*
 * Enumerate the possible CPU set from the device tree.
 */
void __init smp_init_cpus(void)
{
	const char *enable_method;
	struct device_node *dn = NULL;
	int cpu = 0;

	while ((dn = of_find_node_by_type(dn, "cpu"))) {
		if (cpu >= NR_CPUS)
			goto next;

		/*
		 * We currently support only the "spin-table" enable-method.
		 */
		enable_method = of_get_property(dn, "enable-method", NULL);
		if (!enable_method || strcmp(enable_method, "spin-table")) {
			pr_err("CPU %d: missing or invalid enable-method property: %s\n",
			       cpu, enable_method);
			goto next;
		}

		/*
		 * Determine the address from which the CPU is polling.
		 */
		if (of_property_read_u64(dn, "cpu-release-addr",
					 &cpu_release_addr[cpu])) {
			pr_err("CPU %d: missing or invalid cpu-release-addr property\n",
			       cpu);
			goto next;
		}

		set_cpu_possible(cpu, true);
next:
		cpu++;
	}

	/* sanity check */
	if (cpu > NR_CPUS)
		pr_warning("no. of cores (%d) greater than configured maximum of %d - clipping\n",
			   cpu, NR_CPUS);
}

void __init smp_prepare_cpus(unsigned int max_cpus)
{
	int cpu;
	void **release_addr;
	unsigned int ncores = num_possible_cpus();

	/*
	 * are we trying to boot more cores than exist?
	 */
	if (max_cpus > ncores)
		max_cpus = ncores;

	/*
	 * Initialise the present map (which describes the set of CPUs
	 * actually populated at the present time) and release the
	 * secondaries from the bootloader.
	 */
	for_each_possible_cpu(cpu) {
		if (max_cpus == 0)
			break;

		if (!cpu_release_addr[cpu])
			continue;

		release_addr = __va(cpu_release_addr[cpu]);
		release_addr[0] = (void *)__pa(secondary_holding_pen);
		__flush_dcache_area(release_addr, sizeof(release_addr[0]));

		set_cpu_present(cpu, true);
		max_cpus--;
	}

	/*
	 * Send an event to wake up the secondaries.
	 */
	sev();
}


void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int))
{
	smp_cross_call = fn;
}

void arch_send_call_function_ipi_mask(const struct cpumask *mask)
{
	smp_cross_call(mask, IPI_CALL_FUNC);
}

void arch_send_call_function_single_ipi(int cpu)
{
	smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
}

static const char *ipi_types[NR_IPI] = {
#define S(x,s)	[x - IPI_RESCHEDULE] = s
	S(IPI_RESCHEDULE, "Rescheduling interrupts"),
	S(IPI_CALL_FUNC, "Function call interrupts"),
	S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
	S(IPI_CPU_STOP, "CPU stop interrupts"),
};

void show_ipi_list(struct seq_file *p, int prec)
{
	unsigned int cpu, i;

	for (i = 0; i < NR_IPI; i++) {
		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i + IPI_RESCHEDULE,
			   prec >= 4 ? " " : "");
		for_each_present_cpu(cpu)
			seq_printf(p, "%10u ",
				   __get_irq_stat(cpu, ipi_irqs[i]));
		seq_printf(p, "      %s\n", ipi_types[i]);
	}
}

u64 smp_irq_stat_cpu(unsigned int cpu)
{
	u64 sum = 0;
	int i;

	for (i = 0; i < NR_IPI; i++)
		sum += __get_irq_stat(cpu, ipi_irqs[i]);

	return sum;
}

static DEFINE_RAW_SPINLOCK(stop_lock);

/*
 * ipi_cpu_stop - handle IPI from smp_send_stop()
 */
static void ipi_cpu_stop(unsigned int cpu)
{
	if (system_state == SYSTEM_BOOTING ||
	    system_state == SYSTEM_RUNNING) {
		raw_spin_lock(&stop_lock);
		pr_crit("CPU%u: stopping\n", cpu);
		dump_stack();
		raw_spin_unlock(&stop_lock);
	}

	set_cpu_online(cpu, false);

	local_fiq_disable();
	local_irq_disable();

	while (1)
		cpu_relax();
}

/*
 * Main handler for inter-processor interrupts
 */
void handle_IPI(int ipinr, struct pt_regs *regs)
{
	unsigned int cpu = smp_processor_id();
	struct pt_regs *old_regs = set_irq_regs(regs);

	if (ipinr >= IPI_RESCHEDULE && ipinr < IPI_RESCHEDULE + NR_IPI)
		__inc_irq_stat(cpu, ipi_irqs[ipinr - IPI_RESCHEDULE]);

	switch (ipinr) {
	case IPI_RESCHEDULE:
		scheduler_ipi();
		break;

	case IPI_CALL_FUNC:
		irq_enter();
		generic_smp_call_function_interrupt();
		irq_exit();
		break;

	case IPI_CALL_FUNC_SINGLE:
		irq_enter();
		generic_smp_call_function_single_interrupt();
		irq_exit();
		break;

	case IPI_CPU_STOP:
		irq_enter();
		ipi_cpu_stop(cpu);
		irq_exit();
		break;

	default:
		pr_crit("CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr);
		break;
	}
	set_irq_regs(old_regs);
}

void smp_send_reschedule(int cpu)
{
	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
}

void smp_send_stop(void)
{
	unsigned long timeout;

	if (num_online_cpus() > 1) {
		cpumask_t mask;

		cpumask_copy(&mask, cpu_online_mask);
		cpu_clear(smp_processor_id(), mask);

		smp_cross_call(&mask, IPI_CPU_STOP);
	}

	/* Wait up to one second for other CPUs to stop */
	timeout = USEC_PER_SEC;
	while (num_online_cpus() > 1 && timeout--)
		udelay(1);

	if (num_online_cpus() > 1)
		pr_warning("SMP: failed to stop secondary CPUs\n");
}

/*
 * not supported here
 */
int setup_profiling_timer(unsigned int multiplier)
{
	return -EINVAL;
}