summaryrefslogtreecommitdiffstats
path: root/arch/x86/xen/smp_pv.c
blob: 1ea598e5f03025ef509aaafca17623f7d8cbed5f (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
/*
 * 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.
 */
#include <linux/sched.h>
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/smp.h>
#include <linux/irq_work.h>
#include <linux/tick.h>
#include <linux/nmi.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 <xen/interface/xenpmu.h>

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

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

#include <xen/hvc-console.h>
#include "xen-ops.h"
#include "mmu.h"
#include "smp.h"
#include "pmu.h"

cpumask_var_t xen_cpu_initialized_map;

static DEFINE_PER_CPU(struct xen_common_irq, xen_irq_work) = { .irq = -1 };
static DEFINE_PER_CPU(struct xen_common_irq, xen_pmu_irq) = { .irq = -1 };

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

static void cpu_bringup(void)
{
	int cpu;

	cpu_init();
	touch_softlockup_watchdog();
	preempt_disable();

	/* PVH runs in ring 0 and allows us to do native syscalls. Yay! */
	if (!xen_feature(XENFEAT_supervisor_mode_kernel)) {
		xen_enable_sysenter();
		xen_enable_syscall();
	}
	cpu = smp_processor_id();
	smp_store_cpu_info(cpu);
	cpu_data(cpu).x86_max_cores = 1;
	set_cpu_sibling_map(cpu);

	xen_setup_cpu_clockevents();

	notify_cpu_starting(cpu);

	set_cpu_online(cpu, true);

	cpu_set_state_online(cpu);  /* Implies full memory barrier. */

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

asmlinkage __visible void cpu_bringup_and_idle(void)
{
	cpu_bringup();
	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}

void xen_smp_intr_free_pv(unsigned int cpu)
{
	if (per_cpu(xen_irq_work, cpu).irq >= 0) {
		unbind_from_irqhandler(per_cpu(xen_irq_work, cpu).irq, NULL);
		per_cpu(xen_irq_work, cpu).irq = -1;
		kfree(per_cpu(xen_irq_work, cpu).name);
		per_cpu(xen_irq_work, cpu).name = NULL;
	}

	if (per_cpu(xen_pmu_irq, cpu).irq >= 0) {
		unbind_from_irqhandler(per_cpu(xen_pmu_irq, cpu).irq, NULL);
		per_cpu(xen_pmu_irq, cpu).irq = -1;
		kfree(per_cpu(xen_pmu_irq, cpu).name);
		per_cpu(xen_pmu_irq, cpu).name = NULL;
	}
}

int xen_smp_intr_init_pv(unsigned int cpu)
{
	int rc;
	char *callfunc_name, *pmu_name;

	callfunc_name = kasprintf(GFP_KERNEL, "irqwork%d", cpu);
	rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR,
				    cpu,
				    xen_irq_work_interrupt,
				    IRQF_PERCPU|IRQF_NOBALANCING,
				    callfunc_name,
				    NULL);
	if (rc < 0)
		goto fail;
	per_cpu(xen_irq_work, cpu).irq = rc;
	per_cpu(xen_irq_work, cpu).name = callfunc_name;

	if (is_xen_pmu(cpu)) {
		pmu_name = kasprintf(GFP_KERNEL, "pmu%d", cpu);
		rc = bind_virq_to_irqhandler(VIRQ_XENPMU, cpu,
					     xen_pmu_irq_handler,
					     IRQF_PERCPU|IRQF_NOBALANCING,
					     pmu_name, NULL);
		if (rc < 0)
			goto fail;
		per_cpu(xen_pmu_irq, cpu).irq = rc;
		per_cpu(xen_pmu_irq, cpu).name = pmu_name;
	}

	return 0;

 fail:
	xen_smp_intr_free_pv(cpu);
	return rc;
}

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

	if (xen_initial_domain())
		return;

	for (i = 0; i < nr_cpu_ids; i++) {
		rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
		if (rc >= 0) {
			num_processors++;
			set_cpu_possible(i, true);
		}
	}
}

static void __init xen_filter_cpu_maps(void)
{
	int i, rc;
	unsigned int subtract = 0;

	if (!xen_initial_domain())
		return;

	num_processors = 0;
	disabled_cpus = 0;
	for (i = 0; i < nr_cpu_ids; i++) {
		rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
		if (rc >= 0) {
			num_processors++;
			set_cpu_possible(i, true);
		} else {
			set_cpu_possible(i, false);
			set_cpu_present(i, false);
			subtract++;
		}
	}
#ifdef CONFIG_HOTPLUG_CPU
	/* This is akin to using 'nr_cpus' on the Linux command line.
	 * Which is OK as when we use 'dom0_max_vcpus=X' we can only
	 * have up to X, while nr_cpu_ids is greater than X. This
	 * normally is not a problem, except when CPU hotplugging
	 * is involved and then there might be more than X CPUs
	 * in the guest - which will not work as there is no
	 * hypercall to expand the max number of VCPUs an already
	 * running guest has. So cap it up to X. */
	if (subtract)
		nr_cpu_ids = nr_cpu_ids - subtract;
#endif

}

static void __init xen_pv_smp_prepare_boot_cpu(void)
{
	BUG_ON(smp_processor_id() != 0);
	native_smp_prepare_boot_cpu();

	if (!xen_feature(XENFEAT_writable_page_tables))
		/* We've switched to the "real" per-cpu gdt, so make
		 * sure the old memory can be recycled. */
		make_lowmem_page_readwrite(xen_initial_gdt);

#ifdef CONFIG_X86_32
	/*
	 * Xen starts us with XEN_FLAT_RING1_DS, but linux code
	 * expects __USER_DS
	 */
	loadsegment(ds, __USER_DS);
	loadsegment(es, __USER_DS);
#endif

	xen_filter_cpu_maps();
	xen_setup_vcpu_info_placement();

	/*
	 * The alternative logic (which patches the unlock/lock) runs before
	 * the smp bootup up code is activated. Hence we need to set this up
	 * the core kernel is being patched. Otherwise we will have only
	 * modules patched but not core code.
	 */
	xen_init_spinlocks();
}

static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus)
{
	unsigned cpu;
	unsigned int i;

	if (skip_ioapic_setup) {
		char *m = (max_cpus == 0) ?
			"The nosmp parameter is incompatible with Xen; " \
			"use Xen dom0_max_vcpus=1 parameter" :
			"The noapic parameter is incompatible with Xen";

		xen_raw_printk(m);
		panic(m);
	}
	xen_init_lock_cpu(0);

	smp_store_boot_cpu_info();
	cpu_data(0).x86_max_cores = 1;

	for_each_possible_cpu(i) {
		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
	}
	set_cpu_sibling_map(0);

	xen_pmu_init(0);

	if (xen_smp_intr_init(0) || xen_smp_intr_init_pv(0))
		BUG();

	if (!alloc_cpumask_var(&xen_cpu_initialized_map, GFP_KERNEL))
		panic("could not allocate xen_cpu_initialized_map\n");

	cpumask_copy(xen_cpu_initialized_map, cpumask_of(0));

	/* Restrict the possible_map according to max_cpus. */
	while ((num_possible_cpus() > 1) && (num_possible_cpus() > max_cpus)) {
		for (cpu = nr_cpu_ids - 1; !cpu_possible(cpu); cpu--)
			continue;
		set_cpu_possible(cpu, false);
	}

	for_each_possible_cpu(cpu)
		set_cpu_present(cpu, true);
}

static int
cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
{
	struct vcpu_guest_context *ctxt;
	struct desc_struct *gdt;
	unsigned long gdt_mfn;

	/* used to tell cpu_init() that it can proceed with initialization */
	cpumask_set_cpu(cpu, cpu_callout_mask);
	if (cpumask_test_and_set_cpu(cpu, xen_cpu_initialized_map))
		return 0;

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

	gdt = get_cpu_gdt_rw(cpu);

#ifdef CONFIG_X86_32
	ctxt->user_regs.fs = __KERNEL_PERCPU;
	ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
#endif
	memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));

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

	xen_copy_trap_info(ctxt->trap_ctxt);

	ctxt->ldt_ents = 0;

	BUG_ON((unsigned long)gdt & ~PAGE_MASK);

	gdt_mfn = arbitrary_virt_to_mfn(gdt);
	make_lowmem_page_readonly(gdt);
	make_lowmem_page_readonly(mfn_to_virt(gdt_mfn));

	ctxt->gdt_frames[0] = gdt_mfn;
	ctxt->gdt_ents      = GDT_ENTRIES;

	ctxt->kernel_ss = __KERNEL_DS;
	ctxt->kernel_sp = idle->thread.sp0;

#ifdef CONFIG_X86_32
	ctxt->event_callback_cs     = __KERNEL_CS;
	ctxt->failsafe_callback_cs  = __KERNEL_CS;
#else
	ctxt->gs_base_kernel = per_cpu_offset(cpu);
#endif
	ctxt->event_callback_eip    =
		(unsigned long)xen_hypervisor_callback;
	ctxt->failsafe_callback_eip =
		(unsigned long)xen_failsafe_callback;
	ctxt->user_regs.cs = __KERNEL_CS;
	per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);

	ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
	ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_gfn(swapper_pg_dir));
	if (HYPERVISOR_vcpu_op(VCPUOP_initialise, xen_vcpu_nr(cpu), ctxt))
		BUG();

	kfree(ctxt);
	return 0;
}

static int xen_pv_cpu_up(unsigned int cpu, struct task_struct *idle)
{
	int rc;

	common_cpu_up(cpu, idle);

	xen_setup_runstate_info(cpu);

	/*
	 * PV VCPUs are always successfully taken down (see 'while' loop
	 * in xen_cpu_die()), so -EBUSY is an error.
	 */
	rc = cpu_check_up_prepare(cpu);
	if (rc)
		return rc;

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

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

	xen_pmu_init(cpu);

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

	while (cpu_report_state(cpu) != CPU_ONLINE)
		HYPERVISOR_sched_op(SCHEDOP_yield, NULL);

	return 0;
}

#ifdef CONFIG_HOTPLUG_CPU
static int xen_pv_cpu_disable(void)
{
	unsigned int cpu = smp_processor_id();
	if (cpu == 0)
		return -EBUSY;

	cpu_disable_common();

	load_cr3(swapper_pg_dir);
	return 0;
}

static void xen_pv_cpu_die(unsigned int cpu)
{
	while (HYPERVISOR_vcpu_op(VCPUOP_is_up,
				  xen_vcpu_nr(cpu), NULL)) {
		__set_current_state(TASK_UNINTERRUPTIBLE);
		schedule_timeout(HZ/10);
	}

	if (common_cpu_die(cpu) == 0) {
		xen_smp_intr_free(cpu);
		xen_uninit_lock_cpu(cpu);
		xen_teardown_timer(cpu);
		xen_pmu_finish(cpu);
	}
}

static void xen_pv_play_dead(void) /* used only with HOTPLUG_CPU */
{
	play_dead_common();
	HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(smp_processor_id()), NULL);
	cpu_bringup();
	/*
	 * commit 4b0c0f294 (tick: Cleanup NOHZ per cpu data on cpu down)
	 * clears certain data that the cpu_idle loop (which called us
	 * and that we return from) expects. The only way to get that
	 * data back is to call:
	 */
	tick_nohz_idle_enter();

	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}

#else /* !CONFIG_HOTPLUG_CPU */
static int xen_pv_cpu_disable(void)
{
	return -ENOSYS;
}

static void xen_pv_cpu_die(unsigned int cpu)
{
	BUG();
}

static void xen_pv_play_dead(void)
{
	BUG();
}

#endif
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 */

	set_cpu_online(cpu, false);

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

static void xen_pv_stop_other_cpus(int wait)
{
	smp_call_function(stop_self, NULL, wait);
}

static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id)
{
	irq_enter();
	irq_work_run();
	inc_irq_stat(apic_irq_work_irqs);
	irq_exit();

	return IRQ_HANDLED;
}

static const struct smp_ops xen_smp_ops __initconst = {
	.smp_prepare_boot_cpu = xen_pv_smp_prepare_boot_cpu,
	.smp_prepare_cpus = xen_pv_smp_prepare_cpus,
	.smp_cpus_done = xen_smp_cpus_done,

	.cpu_up = xen_pv_cpu_up,
	.cpu_die = xen_pv_cpu_die,
	.cpu_disable = xen_pv_cpu_disable,
	.play_dead = xen_pv_play_dead,

	.stop_other_cpus = xen_pv_stop_other_cpus,
	.smp_send_reschedule = xen_smp_send_reschedule,

	.send_call_func_ipi = xen_smp_send_call_function_ipi,
	.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi,
};

void __init xen_smp_init(void)
{
	smp_ops = xen_smp_ops;
	xen_fill_possible_map();
}