summaryrefslogtreecommitdiffstats
path: root/arch/x86/xen/enlighten.c
blob: 205b1176084f572e9438882bf2ee9ff13404d2cd (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
// SPDX-License-Identifier: GPL-2.0

#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
#include <linux/memblock.h>
#endif
#include <linux/cpu.h>
#include <linux/kexec.h>
#include <linux/slab.h>

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

#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
#include <asm/cpu.h>
#include <asm/e820/api.h> 

#include "xen-ops.h"
#include "smp.h"
#include "pmu.h"

EXPORT_SYMBOL_GPL(hypercall_page);

/*
 * Pointer to the xen_vcpu_info structure or
 * &HYPERVISOR_shared_info->vcpu_info[cpu]. See xen_hvm_init_shared_info
 * and xen_vcpu_setup for details. By default it points to share_info->vcpu_info
 * but if the hypervisor supports VCPUOP_register_vcpu_info then it can point
 * to xen_vcpu_info. The pointer is used in __xen_evtchn_do_upcall to
 * acknowledge pending events.
 * Also more subtly it is used by the patched version of irq enable/disable
 * e.g. xen_irq_enable_direct and xen_iret in PV mode.
 *
 * The desire to be able to do those mask/unmask operations as a single
 * instruction by using the per-cpu offset held in %gs is the real reason
 * vcpu info is in a per-cpu pointer and the original reason for this
 * hypercall.
 *
 */
DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);

/*
 * Per CPU pages used if hypervisor supports VCPUOP_register_vcpu_info
 * hypercall. This can be used both in PV and PVHVM mode. The structure
 * overrides the default per_cpu(xen_vcpu, cpu) value.
 */
DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);

/* Linux <-> Xen vCPU id mapping */
DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);

enum xen_domain_type xen_domain_type = XEN_NATIVE;
EXPORT_SYMBOL_GPL(xen_domain_type);

unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START;
EXPORT_SYMBOL(machine_to_phys_mapping);
unsigned long  machine_to_phys_nr;
EXPORT_SYMBOL(machine_to_phys_nr);

struct start_info *xen_start_info;
EXPORT_SYMBOL_GPL(xen_start_info);

struct shared_info xen_dummy_shared_info;

__read_mostly int xen_have_vector_callback;
EXPORT_SYMBOL_GPL(xen_have_vector_callback);

/*
 * NB: needs to live in .data because it's used by xen_prepare_pvh which runs
 * before clearing the bss.
 */
uint32_t xen_start_flags __attribute__((section(".data"))) = 0;
EXPORT_SYMBOL(xen_start_flags);

/*
 * Point at some empty memory to start with. We map the real shared_info
 * page as soon as fixmap is up and running.
 */
struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info;

/*
 * Flag to determine whether vcpu info placement is available on all
 * VCPUs.  We assume it is to start with, and then set it to zero on
 * the first failure.  This is because it can succeed on some VCPUs
 * and not others, since it can involve hypervisor memory allocation,
 * or because the guest failed to guarantee all the appropriate
 * constraints on all VCPUs (ie buffer can't cross a page boundary).
 *
 * Note that any particular CPU may be using a placed vcpu structure,
 * but we can only optimise if the all are.
 *
 * 0: not available, 1: available
 */
int xen_have_vcpu_info_placement = 1;

static int xen_cpu_up_online(unsigned int cpu)
{
	xen_init_lock_cpu(cpu);
	return 0;
}

int xen_cpuhp_setup(int (*cpu_up_prepare_cb)(unsigned int),
		    int (*cpu_dead_cb)(unsigned int))
{
	int rc;

	rc = cpuhp_setup_state_nocalls(CPUHP_XEN_PREPARE,
				       "x86/xen/guest:prepare",
				       cpu_up_prepare_cb, cpu_dead_cb);
	if (rc >= 0) {
		rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
					       "x86/xen/guest:online",
					       xen_cpu_up_online, NULL);
		if (rc < 0)
			cpuhp_remove_state_nocalls(CPUHP_XEN_PREPARE);
	}

	return rc >= 0 ? 0 : rc;
}

static int xen_vcpu_setup_restore(int cpu)
{
	int rc = 0;

	/* Any per_cpu(xen_vcpu) is stale, so reset it */
	xen_vcpu_info_reset(cpu);

	/*
	 * For PVH and PVHVM, setup online VCPUs only. The rest will
	 * be handled by hotplug.
	 */
	if (xen_pv_domain() ||
	    (xen_hvm_domain() && cpu_online(cpu))) {
		rc = xen_vcpu_setup(cpu);
	}

	return rc;
}

/*
 * On restore, set the vcpu placement up again.
 * If it fails, then we're in a bad state, since
 * we can't back out from using it...
 */
void xen_vcpu_restore(void)
{
	int cpu, rc;

	for_each_possible_cpu(cpu) {
		bool other_cpu = (cpu != smp_processor_id());
		bool is_up;

		if (xen_vcpu_nr(cpu) == XEN_VCPU_ID_INVALID)
			continue;

		/* Only Xen 4.5 and higher support this. */
		is_up = HYPERVISOR_vcpu_op(VCPUOP_is_up,
					   xen_vcpu_nr(cpu), NULL) > 0;

		if (other_cpu && is_up &&
		    HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(cpu), NULL))
			BUG();

		if (xen_pv_domain() || xen_feature(XENFEAT_hvm_safe_pvclock))
			xen_setup_runstate_info(cpu);

		rc = xen_vcpu_setup_restore(cpu);
		if (rc)
			pr_emerg_once("vcpu restore failed for cpu=%d err=%d. "
					"System will hang.\n", cpu, rc);
		/*
		 * In case xen_vcpu_setup_restore() fails, do not bring up the
		 * VCPU. This helps us avoid the resulting OOPS when the VCPU
		 * accesses pvclock_vcpu_time via xen_vcpu (which is NULL.)
		 * Note that this does not improve the situation much -- now the
		 * VM hangs instead of OOPSing -- with the VCPUs that did not
		 * fail, spinning in stop_machine(), waiting for the failed
		 * VCPUs to come up.
		 */
		if (other_cpu && is_up && (rc == 0) &&
		    HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL))
			BUG();
	}
}

void xen_vcpu_info_reset(int cpu)
{
	if (xen_vcpu_nr(cpu) < MAX_VIRT_CPUS) {
		per_cpu(xen_vcpu, cpu) =
			&HYPERVISOR_shared_info->vcpu_info[xen_vcpu_nr(cpu)];
	} else {
		/* Set to NULL so that if somebody accesses it we get an OOPS */
		per_cpu(xen_vcpu, cpu) = NULL;
	}
}

int xen_vcpu_setup(int cpu)
{
	struct vcpu_register_vcpu_info info;
	int err;
	struct vcpu_info *vcpup;

	BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);

	/*
	 * This path is called on PVHVM at bootup (xen_hvm_smp_prepare_boot_cpu)
	 * and at restore (xen_vcpu_restore). Also called for hotplugged
	 * VCPUs (cpu_init -> xen_hvm_cpu_prepare_hvm).
	 * However, the hypercall can only be done once (see below) so if a VCPU
	 * is offlined and comes back online then let's not redo the hypercall.
	 *
	 * For PV it is called during restore (xen_vcpu_restore) and bootup
	 * (xen_setup_vcpu_info_placement). The hotplug mechanism does not
	 * use this function.
	 */
	if (xen_hvm_domain()) {
		if (per_cpu(xen_vcpu, cpu) == &per_cpu(xen_vcpu_info, cpu))
			return 0;
	}

	if (xen_have_vcpu_info_placement) {
		vcpup = &per_cpu(xen_vcpu_info, cpu);
		info.mfn = arbitrary_virt_to_mfn(vcpup);
		info.offset = offset_in_page(vcpup);

		/*
		 * Check to see if the hypervisor will put the vcpu_info
		 * structure where we want it, which allows direct access via
		 * a percpu-variable.
		 * N.B. This hypercall can _only_ be called once per CPU.
		 * Subsequent calls will error out with -EINVAL. This is due to
		 * the fact that hypervisor has no unregister variant and this
		 * hypercall does not allow to over-write info.mfn and
		 * info.offset.
		 */
		err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info,
					 xen_vcpu_nr(cpu), &info);

		if (err) {
			pr_warn_once("register_vcpu_info failed: cpu=%d err=%d\n",
				     cpu, err);
			xen_have_vcpu_info_placement = 0;
		} else {
			/*
			 * This cpu is using the registered vcpu info, even if
			 * later ones fail to.
			 */
			per_cpu(xen_vcpu, cpu) = vcpup;
		}
	}

	if (!xen_have_vcpu_info_placement)
		xen_vcpu_info_reset(cpu);

	return ((per_cpu(xen_vcpu, cpu) == NULL) ? -ENODEV : 0);
}

void xen_reboot(int reason)
{
	struct sched_shutdown r = { .reason = reason };
	int cpu;

	for_each_online_cpu(cpu)
		xen_pmu_finish(cpu);

	if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r))
		BUG();
}

static int reboot_reason = SHUTDOWN_reboot;
static bool xen_legacy_crash;
void xen_emergency_restart(void)
{
	xen_reboot(reboot_reason);
}

static int
xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr)
{
	if (!kexec_crash_loaded()) {
		if (xen_legacy_crash)
			xen_reboot(SHUTDOWN_crash);

		reboot_reason = SHUTDOWN_crash;

		/*
		 * If panic_timeout==0 then we are supposed to wait forever.
		 * However, to preserve original dom0 behavior we have to drop
		 * into hypervisor. (domU behavior is controlled by its
		 * config file)
		 */
		if (panic_timeout == 0)
			panic_timeout = -1;
	}
	return NOTIFY_DONE;
}

static int __init parse_xen_legacy_crash(char *arg)
{
	xen_legacy_crash = true;
	return 0;
}
early_param("xen_legacy_crash", parse_xen_legacy_crash);

static struct notifier_block xen_panic_block = {
	.notifier_call = xen_panic_event,
	.priority = INT_MIN
};

int xen_panic_handler_init(void)
{
	atomic_notifier_chain_register(&panic_notifier_list, &xen_panic_block);
	return 0;
}

void xen_pin_vcpu(int cpu)
{
	static bool disable_pinning;
	struct sched_pin_override pin_override;
	int ret;

	if (disable_pinning)
		return;

	pin_override.pcpu = cpu;
	ret = HYPERVISOR_sched_op(SCHEDOP_pin_override, &pin_override);

	/* Ignore errors when removing override. */
	if (cpu < 0)
		return;

	switch (ret) {
	case -ENOSYS:
		pr_warn("Unable to pin on physical cpu %d. In case of problems consider vcpu pinning.\n",
			cpu);
		disable_pinning = true;
		break;
	case -EPERM:
		WARN(1, "Trying to pin vcpu without having privilege to do so\n");
		disable_pinning = true;
		break;
	case -EINVAL:
	case -EBUSY:
		pr_warn("Physical cpu %d not available for pinning. Check Xen cpu configuration.\n",
			cpu);
		break;
	case 0:
		break;
	default:
		WARN(1, "rc %d while trying to pin vcpu\n", ret);
		disable_pinning = true;
	}
}

#ifdef CONFIG_HOTPLUG_CPU
void xen_arch_register_cpu(int num)
{
	arch_register_cpu(num);
}
EXPORT_SYMBOL(xen_arch_register_cpu);

void xen_arch_unregister_cpu(int num)
{
	arch_unregister_cpu(num);
}
EXPORT_SYMBOL(xen_arch_unregister_cpu);
#endif