summaryrefslogtreecommitdiff
path: root/drivers/hv/hv_common.c
blob: ae68298c0dcac59add8948c0510499b6958ea434 (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
// 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/panic_notifier.h>
#include <linux/ptrace.h>
#include <linux/slab.h>
#include <linux/dma-map-ops.h>
#include <asm/hyperv-tlfs.h>
#include <asm/mshyperv.h>

/*
 * hv_root_partition and ms_hyperv 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 two 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);

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);

/*
 * 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)
{
	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;
}

int __init hv_common_init(void)
{
	int i;

	/*
	 * 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) {
		crash_kexec_post_notifiers = true;
		pr_info("Hyper-V: enabling crash_kexec_post_notifiers\n");
	}

	/*
	 * 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;

	/* 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);
	*inputarg = kmalloc(pgcount * HV_HYP_PAGE_SIZE, flags);
	if (!(*inputarg))
		return -ENOMEM;

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

	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)
{
	unsigned long flags;
	void **inputarg, **outputarg;
	void *mem;

	local_irq_save(flags);

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

	if (hv_root_partition) {
		outputarg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg);
		*outputarg = NULL;
	}

	local_irq_restore(flags);

	kfree(mem);

	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);

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);

void __weak *hv_map_memory(void *addr, unsigned long size)
{
	return NULL;
}
EXPORT_SYMBOL_GPL(hv_map_memory);

void __weak hv_unmap_memory(void *addr)
{
}
EXPORT_SYMBOL_GPL(hv_unmap_memory);