smp.c 9.2 KB
Newer Older
J
Jeremy Fitzhardinge 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
/*
 * Xen SMP support
 *
 * This file implements the Xen versions of smp_ops.  SMP under Xen is
 * very straightforward.  Bringing a CPU up is simply a matter of
 * loading its initial context and setting it running.
 *
 * IPIs are handled through the Xen event mechanism.
 *
 * Because virtual CPUs can be scheduled onto any real CPU, there's no
 * useful topology information for the kernel to make use of.  As a
 * result, all CPUs are treated as if they're single-core and
 * single-threaded.
 *
 * This does not handle HOTPLUG_CPU yet.
 */
#include <linux/sched.h>
#include <linux/err.h>
#include <linux/smp.h>

#include <asm/paravirt.h>
#include <asm/desc.h>
#include <asm/pgtable.h>
#include <asm/cpu.h>

#include <xen/interface/xen.h>
#include <xen/interface/vcpu.h>

#include <asm/xen/interface.h>
#include <asm/xen/hypercall.h>

#include <xen/page.h>
#include <xen/events.h>

#include "xen-ops.h"
#include "mmu.h"

static cpumask_t cpu_initialized_map;
static DEFINE_PER_CPU(int, resched_irq);
static DEFINE_PER_CPU(int, callfunc_irq);

/*
 * Structure and data for smp_call_function(). This is designed to minimise
 * static memory requirements. It also looks cleaner.
 */
static DEFINE_SPINLOCK(call_lock);

struct call_data_struct {
	void (*func) (void *info);
	void *info;
	atomic_t started;
	atomic_t finished;
	int wait;
};

static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id);

static struct call_data_struct *call_data;

/*
 * Reschedule call back. Nothing to do,
 * all the work is done automatically when
 * we return from the interrupt.
 */
static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
{
	return IRQ_HANDLED;
}

static __cpuinit void cpu_bringup_and_idle(void)
{
	int cpu = smp_processor_id();

	cpu_init();

	preempt_disable();
	per_cpu(cpu_state, cpu) = CPU_ONLINE;

	xen_setup_cpu_clockevents();

	/* We can take interrupts now: we're officially "up". */
	local_irq_enable();

	wmb();			/* make sure everything is out */
	cpu_idle();
}

static int xen_smp_intr_init(unsigned int cpu)
{
	int rc;
	const char *resched_name, *callfunc_name;

	per_cpu(resched_irq, cpu) = per_cpu(callfunc_irq, cpu) = -1;

	resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu);
	rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR,
				    cpu,
				    xen_reschedule_interrupt,
				    IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
				    resched_name,
				    NULL);
	if (rc < 0)
		goto fail;
	per_cpu(resched_irq, cpu) = rc;

	callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu);
	rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR,
				    cpu,
				    xen_call_function_interrupt,
				    IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
				    callfunc_name,
				    NULL);
	if (rc < 0)
		goto fail;
	per_cpu(callfunc_irq, cpu) = rc;

	return 0;

 fail:
	if (per_cpu(resched_irq, cpu) >= 0)
		unbind_from_irqhandler(per_cpu(resched_irq, cpu), NULL);
	if (per_cpu(callfunc_irq, cpu) >= 0)
		unbind_from_irqhandler(per_cpu(callfunc_irq, cpu), NULL);
	return rc;
}

void __init xen_fill_possible_map(void)
{
	int i, rc;

	for (i = 0; i < NR_CPUS; i++) {
		rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
		if (rc >= 0)
			cpu_set(i, cpu_possible_map);
	}
}

void __init xen_smp_prepare_boot_cpu(void)
{
	int cpu;

	BUG_ON(smp_processor_id() != 0);
	native_smp_prepare_boot_cpu();

	/* We've switched to the "real" per-cpu gdt, so make sure the
	   old memory can be recycled */
	make_lowmem_page_readwrite(&per_cpu__gdt_page);

149
	for_each_possible_cpu(cpu) {
150
		cpus_clear(per_cpu(cpu_sibling_map, cpu));
151 152 153 154 155 156
		/*
		 * cpu_core_map lives in a per cpu area that is cleared
		 * when the per cpu array is allocated.
		 *
		 * cpus_clear(per_cpu(cpu_core_map, cpu));
		 */
J
Jeremy Fitzhardinge 已提交
157
	}
158 159

	xen_setup_vcpu_info_placement();
J
Jeremy Fitzhardinge 已提交
160 161 162 163 164 165
}

void __init xen_smp_prepare_cpus(unsigned int max_cpus)
{
	unsigned cpu;

166
	for_each_possible_cpu(cpu) {
167
		cpus_clear(per_cpu(cpu_sibling_map, cpu));
168 169 170 171 172 173
		/*
		 * cpu_core_ map will be zeroed when the per
		 * cpu area is allocated.
		 *
		 * cpus_clear(per_cpu(cpu_core_map, cpu));
		 */
J
Jeremy Fitzhardinge 已提交
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
	}

	smp_store_cpu_info(0);
	set_cpu_sibling_map(0);

	if (xen_smp_intr_init(0))
		BUG();

	cpu_initialized_map = cpumask_of_cpu(0);

	/* Restrict the possible_map according to max_cpus. */
	while ((num_possible_cpus() > 1) && (num_possible_cpus() > max_cpus)) {
		for (cpu = NR_CPUS-1; !cpu_isset(cpu, cpu_possible_map); cpu--)
			continue;
		cpu_clear(cpu, cpu_possible_map);
	}

	for_each_possible_cpu (cpu) {
		struct task_struct *idle;

		if (cpu == 0)
			continue;

		idle = fork_idle(cpu);
		if (IS_ERR(idle))
			panic("failed fork for CPU %d", cpu);

		cpu_set(cpu, cpu_present_map);
	}

	//init_xenbus_allowed_cpumask();
}

static __cpuinit int
cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
{
	struct vcpu_guest_context *ctxt;
	struct gdt_page *gdt = &per_cpu(gdt_page, cpu);

	if (cpu_test_and_set(cpu, cpu_initialized_map))
		return 0;

	ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL);
	if (ctxt == NULL)
		return -ENOMEM;

	ctxt->flags = VGCF_IN_KERNEL;
	ctxt->user_regs.ds = __USER_DS;
	ctxt->user_regs.es = __USER_DS;
	ctxt->user_regs.fs = __KERNEL_PERCPU;
	ctxt->user_regs.gs = 0;
	ctxt->user_regs.ss = __KERNEL_DS;
	ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
	ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */

	memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));

	xen_copy_trap_info(ctxt->trap_ctxt);

	ctxt->ldt_ents = 0;

	BUG_ON((unsigned long)gdt->gdt & ~PAGE_MASK);
	make_lowmem_page_readonly(gdt->gdt);

	ctxt->gdt_frames[0] = virt_to_mfn(gdt->gdt);
	ctxt->gdt_ents      = ARRAY_SIZE(gdt->gdt);

	ctxt->user_regs.cs = __KERNEL_CS;
	ctxt->user_regs.esp = idle->thread.esp0 - sizeof(struct pt_regs);

	ctxt->kernel_ss = __KERNEL_DS;
	ctxt->kernel_sp = idle->thread.esp0;

	ctxt->event_callback_cs     = __KERNEL_CS;
	ctxt->event_callback_eip    = (unsigned long)xen_hypervisor_callback;
	ctxt->failsafe_callback_cs  = __KERNEL_CS;
	ctxt->failsafe_callback_eip = (unsigned long)xen_failsafe_callback;

	per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
	ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_mfn(swapper_pg_dir));

	if (HYPERVISOR_vcpu_op(VCPUOP_initialise, cpu, ctxt))
		BUG();

	kfree(ctxt);
	return 0;
}

int __cpuinit xen_cpu_up(unsigned int cpu)
{
	struct task_struct *idle = idle_task(cpu);
	int rc;

#if 0
	rc = cpu_up_check(cpu);
	if (rc)
		return rc;
#endif

	init_gdt(cpu);
	per_cpu(current_task, cpu) = idle;
	irq_ctx_init(cpu);
	xen_setup_timer(cpu);

	/* make sure interrupts start blocked */
	per_cpu(xen_vcpu, cpu)->evtchn_upcall_mask = 1;

	rc = cpu_initialize_context(cpu, idle);
	if (rc)
		return rc;

	if (num_online_cpus() == 1)
		alternatives_smp_switch(1);

	rc = xen_smp_intr_init(cpu);
	if (rc)
		return rc;

	smp_store_cpu_info(cpu);
	set_cpu_sibling_map(cpu);
	/* This must be done before setting cpu_online_map */
	wmb();

	cpu_set(cpu, cpu_online_map);

	rc = HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL);
	BUG_ON(rc);

	return 0;
}

void xen_smp_cpus_done(unsigned int max_cpus)
{
}

static void stop_self(void *v)
{
	int cpu = smp_processor_id();

	/* make sure we're not pinning something down */
	load_cr3(swapper_pg_dir);
	/* should set up a minimal gdt */

	HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL);
	BUG();
}

void xen_smp_send_stop(void)
{
J
Jeremy Fitzhardinge 已提交
323
	smp_call_function(stop_self, NULL, 0, 0);
J
Jeremy Fitzhardinge 已提交
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
}

void xen_smp_send_reschedule(int cpu)
{
	xen_send_IPI_one(cpu, XEN_RESCHEDULE_VECTOR);
}


static void xen_send_IPI_mask(cpumask_t mask, enum ipi_vector vector)
{
	unsigned cpu;

	cpus_and(mask, mask, cpu_online_map);

	for_each_cpu_mask(cpu, mask)
		xen_send_IPI_one(cpu, vector);
}

static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id)
{
	void (*func) (void *info) = call_data->func;
	void *info = call_data->info;
	int wait = call_data->wait;

	/*
	 * Notify initiating CPU that I've grabbed the data and am
	 * about to execute the function
	 */
	mb();
	atomic_inc(&call_data->started);
	/*
	 * At this point the info structure may be out of scope unless wait==1
	 */
	irq_enter();
	(*func)(info);
359
	__get_cpu_var(irq_stat).irq_call_count++;
J
Jeremy Fitzhardinge 已提交
360 361 362 363 364 365 366 367 368 369 370 371 372 373
	irq_exit();

	if (wait) {
		mb();		/* commit everything before setting finished */
		atomic_inc(&call_data->finished);
	}

	return IRQ_HANDLED;
}

int xen_smp_call_function_mask(cpumask_t mask, void (*func)(void *),
			       void *info, int wait)
{
	struct call_data_struct data;
374 375
	int cpus, cpu;
	bool yield;
J
Jeremy Fitzhardinge 已提交
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

	/* Holding any lock stops cpus from going down. */
	spin_lock(&call_lock);

	cpu_clear(smp_processor_id(), mask);

	cpus = cpus_weight(mask);
	if (!cpus) {
		spin_unlock(&call_lock);
		return 0;
	}

	/* Can deadlock when called with interrupts disabled */
	WARN_ON(irqs_disabled());

	data.func = func;
	data.info = info;
	atomic_set(&data.started, 0);
	data.wait = wait;
	if (wait)
		atomic_set(&data.finished, 0);

	call_data = &data;
	mb();			/* write everything before IPI */

	/* Send a message to other CPUs and wait for them to respond */
	xen_send_IPI_mask(mask, XEN_CALL_FUNCTION_VECTOR);

404 405 406 407 408 409 410 411
	/* Make sure other vcpus get a chance to run if they need to. */
	yield = false;
	for_each_cpu_mask(cpu, mask)
		if (xen_vcpu_stolen(cpu))
			yield = true;

	if (yield)
		HYPERVISOR_sched_op(SCHEDOP_yield, 0);
J
Jeremy Fitzhardinge 已提交
412 413 414 415 416 417 418 419 420 421

	/* Wait for response */
	while (atomic_read(&data.started) != cpus ||
	       (wait && atomic_read(&data.finished) != cpus))
		cpu_relax();

	spin_unlock(&call_lock);

	return 0;
}