summaryrefslogtreecommitdiff
path: root/drivers/hv/hv_common.c
blob: ccad7bca3fd3dadc4c162ba6c1b6d95e9a3a991d (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
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
// SPDX-License-Identifier: GPL-2.0

/*
 * Architecture neutral utility routines for interacting with
 * Hyper-V. This file is specifically for code that must be
 * built-in to the kernel image when CONFIG_HYPERV is set
 * (vs. being in a module) because it is called from architecture
 * specific code under arch/.
 *
 * Copyright (C) 2021, Microsoft, Inc.
 *
 * Author : Michael Kelley <mikelley@microsoft.com>
 */

#include <linux/types.h>
#include <linux/acpi.h>
#include <linux/export.h>
#include <linux/bitfield.h>
#include <linux/cpumask.h>
#include <linux/sched/task_stack.h>
#include <linux/panic_notifier.h>
#include <linux/ptrace.h>
#include <linux/kdebug.h>
#include <linux/kmsg_dump.h>
#include <linux/slab.h>
#include <linux/dma-map-ops.h>
#include <linux/set_memory.h>
#include <asm/hyperv-tlfs.h>
#include <asm/mshyperv.h>

/*
 * hv_root_partition, ms_hyperv and hv_nested are defined here with other
 * Hyper-V specific globals so they are shared across all architectures and are
 * built only when CONFIG_HYPERV is defined.  But on x86,
 * ms_hyperv_init_platform() is built even when CONFIG_HYPERV is not
 * defined, and it uses these three variables.  So mark them as __weak
 * here, allowing for an overriding definition in the module containing
 * ms_hyperv_init_platform().
 */
bool __weak hv_root_partition;
EXPORT_SYMBOL_GPL(hv_root_partition);

bool __weak hv_nested;
EXPORT_SYMBOL_GPL(hv_nested);

struct ms_hyperv_info __weak ms_hyperv;
EXPORT_SYMBOL_GPL(ms_hyperv);

u32 *hv_vp_index;
EXPORT_SYMBOL_GPL(hv_vp_index);

u32 hv_max_vp_index;
EXPORT_SYMBOL_GPL(hv_max_vp_index);

void * __percpu *hyperv_pcpu_input_arg;
EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg);

void * __percpu *hyperv_pcpu_output_arg;
EXPORT_SYMBOL_GPL(hyperv_pcpu_output_arg);

static void hv_kmsg_dump_unregister(void);

static struct ctl_table_header *hv_ctl_table_hdr;

/*
 * Hyper-V specific initialization and shutdown code that is
 * common across all architectures.  Called from architecture
 * specific initialization functions.
 */

void __init hv_common_free(void)
{
	unregister_sysctl_table(hv_ctl_table_hdr);
	hv_ctl_table_hdr = NULL;

	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE)
		hv_kmsg_dump_unregister();

	kfree(hv_vp_index);
	hv_vp_index = NULL;

	free_percpu(hyperv_pcpu_output_arg);
	hyperv_pcpu_output_arg = NULL;

	free_percpu(hyperv_pcpu_input_arg);
	hyperv_pcpu_input_arg = NULL;
}

/*
 * Functions for allocating and freeing memory with size and
 * alignment HV_HYP_PAGE_SIZE. These functions are needed because
 * the guest page size may not be the same as the Hyper-V page
 * size. We depend upon kmalloc() aligning power-of-two size
 * allocations to the allocation size boundary, so that the
 * allocated memory appears to Hyper-V as a page of the size
 * it expects.
 */

void *hv_alloc_hyperv_page(void)
{
	BUILD_BUG_ON(PAGE_SIZE <  HV_HYP_PAGE_SIZE);

	if (PAGE_SIZE == HV_HYP_PAGE_SIZE)
		return (void *)__get_free_page(GFP_KERNEL);
	else
		return kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
}
EXPORT_SYMBOL_GPL(hv_alloc_hyperv_page);

void *hv_alloc_hyperv_zeroed_page(void)
{
	if (PAGE_SIZE == HV_HYP_PAGE_SIZE)
		return (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
	else
		return kzalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
}
EXPORT_SYMBOL_GPL(hv_alloc_hyperv_zeroed_page);

void hv_free_hyperv_page(void *addr)
{
	if (PAGE_SIZE == HV_HYP_PAGE_SIZE)
		free_page((unsigned long)addr);
	else
		kfree(addr);
}
EXPORT_SYMBOL_GPL(hv_free_hyperv_page);

static void *hv_panic_page;

/*
 * Boolean to control whether to report panic messages over Hyper-V.
 *
 * It can be set via /proc/sys/kernel/hyperv_record_panic_msg
 */
static int sysctl_record_panic_msg = 1;

/*
 * sysctl option to allow the user to control whether kmsg data should be
 * reported to Hyper-V on panic.
 */
static struct ctl_table hv_ctl_table[] = {
	{
		.procname	= "hyperv_record_panic_msg",
		.data		= &sysctl_record_panic_msg,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= SYSCTL_ZERO,
		.extra2		= SYSCTL_ONE
	},
	{}
};

static int hv_die_panic_notify_crash(struct notifier_block *self,
				     unsigned long val, void *args);

static struct notifier_block hyperv_die_report_block = {
	.notifier_call = hv_die_panic_notify_crash,
};

static struct notifier_block hyperv_panic_report_block = {
	.notifier_call = hv_die_panic_notify_crash,
};

/*
 * The following callback works both as die and panic notifier; its
 * goal is to provide panic information to the hypervisor unless the
 * kmsg dumper is used [see hv_kmsg_dump()], which provides more
 * information but isn't always available.
 *
 * Notice that both the panic/die report notifiers are registered only
 * if we have the capability HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE set.
 */
static int hv_die_panic_notify_crash(struct notifier_block *self,
				     unsigned long val, void *args)
{
	struct pt_regs *regs;
	bool is_die;

	/* Don't notify Hyper-V unless we have a die oops event or panic. */
	if (self == &hyperv_panic_report_block) {
		is_die = false;
		regs = current_pt_regs();
	} else { /* die event */
		if (val != DIE_OOPS)
			return NOTIFY_DONE;

		is_die = true;
		regs = ((struct die_args *)args)->regs;
	}

	/*
	 * Hyper-V should be notified only once about a panic/die. If we will
	 * be calling hv_kmsg_dump() later with kmsg data, don't do the
	 * notification here.
	 */
	if (!sysctl_record_panic_msg || !hv_panic_page)
		hyperv_report_panic(regs, val, is_die);

	return NOTIFY_DONE;
}

/*
 * Callback from kmsg_dump. Grab as much as possible from the end of the kmsg
 * buffer and call into Hyper-V to transfer the data.
 */
static void hv_kmsg_dump(struct kmsg_dumper *dumper,
			 enum kmsg_dump_reason reason)
{
	struct kmsg_dump_iter iter;
	size_t bytes_written;

	/* We are only interested in panics. */
	if (reason != KMSG_DUMP_PANIC || !sysctl_record_panic_msg)
		return;

	/*
	 * Write dump contents to the page. No need to synchronize; panic should
	 * be single-threaded.
	 */
	kmsg_dump_rewind(&iter);
	kmsg_dump_get_buffer(&iter, false, hv_panic_page, HV_HYP_PAGE_SIZE,
			     &bytes_written);
	if (!bytes_written)
		return;
	/*
	 * P3 to contain the physical address of the panic page & P4 to
	 * contain the size of the panic data in that page. Rest of the
	 * registers are no-op when the NOTIFY_MSG flag is set.
	 */
	hv_set_register(HV_REGISTER_CRASH_P0, 0);
	hv_set_register(HV_REGISTER_CRASH_P1, 0);
	hv_set_register(HV_REGISTER_CRASH_P2, 0);
	hv_set_register(HV_REGISTER_CRASH_P3, virt_to_phys(hv_panic_page));
	hv_set_register(HV_REGISTER_CRASH_P4, bytes_written);

	/*
	 * Let Hyper-V know there is crash data available along with
	 * the panic message.
	 */
	hv_set_register(HV_REGISTER_CRASH_CTL,
			(HV_CRASH_CTL_CRASH_NOTIFY |
			 HV_CRASH_CTL_CRASH_NOTIFY_MSG));
}

static struct kmsg_dumper hv_kmsg_dumper = {
	.dump = hv_kmsg_dump,
};

static void hv_kmsg_dump_unregister(void)
{
	kmsg_dump_unregister(&hv_kmsg_dumper);
	unregister_die_notifier(&hyperv_die_report_block);
	atomic_notifier_chain_unregister(&panic_notifier_list,
					 &hyperv_panic_report_block);

	hv_free_hyperv_page(hv_panic_page);
	hv_panic_page = NULL;
}

static void hv_kmsg_dump_register(void)
{
	int ret;

	hv_panic_page = hv_alloc_hyperv_zeroed_page();
	if (!hv_panic_page) {
		pr_err("Hyper-V: panic message page memory allocation failed\n");
		return;
	}

	ret = kmsg_dump_register(&hv_kmsg_dumper);
	if (ret) {
		pr_err("Hyper-V: kmsg dump register error 0x%x\n", ret);
		hv_free_hyperv_page(hv_panic_page);
		hv_panic_page = NULL;
	}
}

int __init hv_common_init(void)
{
	int i;

	if (hv_is_isolation_supported())
		sysctl_record_panic_msg = 0;

	/*
	 * Hyper-V expects to get crash register data or kmsg when
	 * crash enlightment is available and system crashes. Set
	 * crash_kexec_post_notifiers to be true to make sure that
	 * calling crash enlightment interface before running kdump
	 * kernel.
	 */
	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
		u64 hyperv_crash_ctl;

		crash_kexec_post_notifiers = true;
		pr_info("Hyper-V: enabling crash_kexec_post_notifiers\n");

		/*
		 * Panic message recording (sysctl_record_panic_msg)
		 * is enabled by default in non-isolated guests and
		 * disabled by default in isolated guests; the panic
		 * message recording won't be available in isolated
		 * guests should the following registration fail.
		 */
		hv_ctl_table_hdr = register_sysctl("kernel", hv_ctl_table);
		if (!hv_ctl_table_hdr)
			pr_err("Hyper-V: sysctl table register error");

		/*
		 * Register for panic kmsg callback only if the right
		 * capability is supported by the hypervisor.
		 */
		hyperv_crash_ctl = hv_get_register(HV_REGISTER_CRASH_CTL);
		if (hyperv_crash_ctl & HV_CRASH_CTL_CRASH_NOTIFY_MSG)
			hv_kmsg_dump_register();

		register_die_notifier(&hyperv_die_report_block);
		atomic_notifier_chain_register(&panic_notifier_list,
					       &hyperv_panic_report_block);
	}

	/*
	 * Allocate the per-CPU state for the hypercall input arg.
	 * If this allocation fails, we will not be able to setup
	 * (per-CPU) hypercall input page and thus this failure is
	 * fatal on Hyper-V.
	 */
	hyperv_pcpu_input_arg = alloc_percpu(void  *);
	BUG_ON(!hyperv_pcpu_input_arg);

	/* Allocate the per-CPU state for output arg for root */
	if (hv_root_partition) {
		hyperv_pcpu_output_arg = alloc_percpu(void *);
		BUG_ON(!hyperv_pcpu_output_arg);
	}

	hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index),
				    GFP_KERNEL);
	if (!hv_vp_index) {
		hv_common_free();
		return -ENOMEM;
	}

	for (i = 0; i < num_possible_cpus(); i++)
		hv_vp_index[i] = VP_INVAL;

	return 0;
}

/*
 * Hyper-V specific initialization and die code for
 * individual CPUs that is common across all architectures.
 * Called by the CPU hotplug mechanism.
 */

int hv_common_cpu_init(unsigned int cpu)
{
	void **inputarg, **outputarg;
	u64 msr_vp_index;
	gfp_t flags;
	int pgcount = hv_root_partition ? 2 : 1;
	void *mem;
	int ret;

	/* hv_cpu_init() can be called with IRQs disabled from hv_resume() */
	flags = irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL;

	inputarg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);

	/*
	 * hyperv_pcpu_input_arg and hyperv_pcpu_output_arg memory is already
	 * allocated if this CPU was previously online and then taken offline
	 */
	if (!*inputarg) {
		mem = kmalloc(pgcount * HV_HYP_PAGE_SIZE, flags);
		if (!mem)
			return -ENOMEM;

		if (hv_root_partition) {
			outputarg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg);
			*outputarg = (char *)mem + HV_HYP_PAGE_SIZE;
		}

		if (!ms_hyperv.paravisor_present &&
		    (hv_isolation_type_snp() || hv_isolation_type_tdx())) {
			ret = set_memory_decrypted((unsigned long)mem, pgcount);
			if (ret) {
				/* It may be unsafe to free 'mem' */
				return ret;
			}

			memset(mem, 0x00, pgcount * HV_HYP_PAGE_SIZE);
		}

		/*
		 * In a fully enlightened TDX/SNP VM with more than 64 VPs, if
		 * hyperv_pcpu_input_arg is not NULL, set_memory_decrypted() ->
		 * ... -> cpa_flush()-> ... -> __send_ipi_mask_ex() tries to
		 * use hyperv_pcpu_input_arg as the hypercall input page, which
		 * must be a decrypted page in such a VM, but the page is still
		 * encrypted before set_memory_decrypted() returns. Fix this by
		 * setting *inputarg after the above set_memory_decrypted(): if
		 * hyperv_pcpu_input_arg is NULL, __send_ipi_mask_ex() returns
		 * HV_STATUS_INVALID_PARAMETER immediately, and the function
		 * hv_send_ipi_mask() falls back to orig_apic.send_IPI_mask(),
		 * which may be slightly slower than the hypercall, but still
		 * works correctly in such a VM.
		 */
		*inputarg = mem;
	}

	msr_vp_index = hv_get_register(HV_REGISTER_VP_INDEX);

	hv_vp_index[cpu] = msr_vp_index;

	if (msr_vp_index > hv_max_vp_index)
		hv_max_vp_index = msr_vp_index;

	return 0;
}

int hv_common_cpu_die(unsigned int cpu)
{
	/*
	 * The hyperv_pcpu_input_arg and hyperv_pcpu_output_arg memory
	 * is not freed when the CPU goes offline as the hyperv_pcpu_input_arg
	 * may be used by the Hyper-V vPCI driver in reassigning interrupts
	 * as part of the offlining process.  The interrupt reassignment
	 * happens *after* the CPUHP_AP_HYPERV_ONLINE state has run and
	 * called this function.
	 *
	 * If a previously offlined CPU is brought back online again, the
	 * originally allocated memory is reused in hv_common_cpu_init().
	 */

	return 0;
}

/* Bit mask of the extended capability to query: see HV_EXT_CAPABILITY_xxx */
bool hv_query_ext_cap(u64 cap_query)
{
	/*
	 * The address of the 'hv_extended_cap' variable will be used as an
	 * output parameter to the hypercall below and so it should be
	 * compatible with 'virt_to_phys'. Which means, it's address should be
	 * directly mapped. Use 'static' to keep it compatible; stack variables
	 * can be virtually mapped, making them incompatible with
	 * 'virt_to_phys'.
	 * Hypercall input/output addresses should also be 8-byte aligned.
	 */
	static u64 hv_extended_cap __aligned(8);
	static bool hv_extended_cap_queried;
	u64 status;

	/*
	 * Querying extended capabilities is an extended hypercall. Check if the
	 * partition supports extended hypercall, first.
	 */
	if (!(ms_hyperv.priv_high & HV_ENABLE_EXTENDED_HYPERCALLS))
		return false;

	/* Extended capabilities do not change at runtime. */
	if (hv_extended_cap_queried)
		return hv_extended_cap & cap_query;

	status = hv_do_hypercall(HV_EXT_CALL_QUERY_CAPABILITIES, NULL,
				 &hv_extended_cap);

	/*
	 * The query extended capabilities hypercall should not fail under
	 * any normal circumstances. Avoid repeatedly making the hypercall, on
	 * error.
	 */
	hv_extended_cap_queried = true;
	if (!hv_result_success(status)) {
		pr_err("Hyper-V: Extended query capabilities hypercall failed 0x%llx\n",
		       status);
		return false;
	}

	return hv_extended_cap & cap_query;
}
EXPORT_SYMBOL_GPL(hv_query_ext_cap);

void hv_setup_dma_ops(struct device *dev, bool coherent)
{
	/*
	 * Hyper-V does not offer a vIOMMU in the guest
	 * VM, so pass 0/NULL for the IOMMU settings
	 */
	arch_setup_dma_ops(dev, 0, 0, NULL, coherent);
}
EXPORT_SYMBOL_GPL(hv_setup_dma_ops);

bool hv_is_hibernation_supported(void)
{
	return !hv_root_partition && acpi_sleep_state_supported(ACPI_STATE_S4);
}
EXPORT_SYMBOL_GPL(hv_is_hibernation_supported);

/*
 * Default function to read the Hyper-V reference counter, independent
 * of whether Hyper-V enlightened clocks/timers are being used. But on
 * architectures where it is used, Hyper-V enlightenment code in
 * hyperv_timer.c may override this function.
 */
static u64 __hv_read_ref_counter(void)
{
	return hv_get_register(HV_REGISTER_TIME_REF_COUNT);
}

u64 (*hv_read_reference_counter)(void) = __hv_read_ref_counter;
EXPORT_SYMBOL_GPL(hv_read_reference_counter);

/* These __weak functions provide default "no-op" behavior and
 * may be overridden by architecture specific versions. Architectures
 * for which the default "no-op" behavior is sufficient can leave
 * them unimplemented and not be cluttered with a bunch of stub
 * functions in arch-specific code.
 */

bool __weak hv_is_isolation_supported(void)
{
	return false;
}
EXPORT_SYMBOL_GPL(hv_is_isolation_supported);

bool __weak hv_isolation_type_snp(void)
{
	return false;
}
EXPORT_SYMBOL_GPL(hv_isolation_type_snp);

bool __weak hv_isolation_type_tdx(void)
{
	return false;
}
EXPORT_SYMBOL_GPL(hv_isolation_type_tdx);

void __weak hv_setup_vmbus_handler(void (*handler)(void))
{
}
EXPORT_SYMBOL_GPL(hv_setup_vmbus_handler);

void __weak hv_remove_vmbus_handler(void)
{
}
EXPORT_SYMBOL_GPL(hv_remove_vmbus_handler);

void __weak hv_setup_kexec_handler(void (*handler)(void))
{
}
EXPORT_SYMBOL_GPL(hv_setup_kexec_handler);

void __weak hv_remove_kexec_handler(void)
{
}
EXPORT_SYMBOL_GPL(hv_remove_kexec_handler);

void __weak hv_setup_crash_handler(void (*handler)(struct pt_regs *regs))
{
}
EXPORT_SYMBOL_GPL(hv_setup_crash_handler);

void __weak hv_remove_crash_handler(void)
{
}
EXPORT_SYMBOL_GPL(hv_remove_crash_handler);

void __weak hyperv_cleanup(void)
{
}
EXPORT_SYMBOL_GPL(hyperv_cleanup);

u64 __weak hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size)
{
	return HV_STATUS_INVALID_PARAMETER;
}
EXPORT_SYMBOL_GPL(hv_ghcb_hypercall);

u64 __weak hv_tdx_hypercall(u64 control, u64 param1, u64 param2)
{
	return HV_STATUS_INVALID_PARAMETER;
}
EXPORT_SYMBOL_GPL(hv_tdx_hypercall);