summaryrefslogtreecommitdiffstats
path: root/drivers/hv/hv.c
blob: a8ad728354cb097621db497cd48251861a0f1016 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (c) 2009, Microsoft Corporation.
 *
 * Authors:
 *   Haiyang Zhang <haiyangz@microsoft.com>
 *   Hank Janssen  <hjanssen@microsoft.com>
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/io.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/hyperv.h>
#include <linux/random.h>
#include <linux/clockchips.h>
#include <linux/delay.h>
#include <linux/interrupt.h>
#include <clocksource/hyperv_timer.h>
#include <asm/mshyperv.h>
#include <linux/set_memory.h>
#include "hyperv_vmbus.h"

/* The one and only */
struct hv_context hv_context;

/*
 * hv_init - Main initialization routine.
 *
 * This routine must be called before any other routines in here are called
 */
int hv_init(void)
{
	hv_context.cpu_context = alloc_percpu(struct hv_per_cpu_context);
	if (!hv_context.cpu_context)
		return -ENOMEM;
	return 0;
}

/*
 * hv_post_message - Post a message using the hypervisor message IPC.
 *
 * This involves a hypercall.
 */
int hv_post_message(union hv_connection_id connection_id,
		  enum hv_message_type message_type,
		  void *payload, size_t payload_size)
{
	struct hv_input_post_message *aligned_msg;
	unsigned long flags;
	u64 status;

	if (payload_size > HV_MESSAGE_PAYLOAD_BYTE_COUNT)
		return -EMSGSIZE;

	local_irq_save(flags);

	/*
	 * A TDX VM with the paravisor must use the decrypted post_msg_page: see
	 * the comment in struct hv_per_cpu_context. A SNP VM with the paravisor
	 * can use the encrypted hyperv_pcpu_input_arg because it copies the
	 * input into the GHCB page, which has been decrypted by the paravisor.
	 */
	if (hv_isolation_type_tdx() && ms_hyperv.paravisor_present)
		aligned_msg = this_cpu_ptr(hv_context.cpu_context)->post_msg_page;
	else
		aligned_msg = *this_cpu_ptr(hyperv_pcpu_input_arg);

	aligned_msg->connectionid = connection_id;
	aligned_msg->reserved = 0;
	aligned_msg->message_type = message_type;
	aligned_msg->payload_size = payload_size;
	memcpy((void *)aligned_msg->payload, payload, payload_size);

	if (ms_hyperv.paravisor_present) {
		if (hv_isolation_type_tdx())
			status = hv_tdx_hypercall(HVCALL_POST_MESSAGE,
						  virt_to_phys(aligned_msg), 0);
		else if (hv_isolation_type_snp())
			status = hv_ghcb_hypercall(HVCALL_POST_MESSAGE,
						   aligned_msg, NULL,
						   sizeof(*aligned_msg));
		else
			status = HV_STATUS_INVALID_PARAMETER;
	} else {
		status = hv_do_hypercall(HVCALL_POST_MESSAGE,
				aligned_msg, NULL);
	}

	local_irq_restore(flags);

	return hv_result(status);
}

int hv_synic_alloc(void)
{
	int cpu, ret = -ENOMEM;
	struct hv_per_cpu_context *hv_cpu;

	/*
	 * First, zero all per-cpu memory areas so hv_synic_free() can
	 * detect what memory has been allocated and cleanup properly
	 * after any failures.
	 */
	for_each_present_cpu(cpu) {
		hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu);
		memset(hv_cpu, 0, sizeof(*hv_cpu));
	}

	hv_context.hv_numa_map = kcalloc(nr_node_ids, sizeof(struct cpumask),
					 GFP_KERNEL);
	if (hv_context.hv_numa_map == NULL) {
		pr_err("Unable to allocate NUMA map\n");
		goto err;
	}

	for_each_present_cpu(cpu) {
		hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu);

		tasklet_init(&hv_cpu->msg_dpc,
			     vmbus_on_msg_dpc, (unsigned long) hv_cpu);

		if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) {
			hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC);
			if (hv_cpu->post_msg_page == NULL) {
				pr_err("Unable to allocate post msg page\n");
				goto err;
			}

			ret = set_memory_decrypted((unsigned long)hv_cpu->post_msg_page, 1);
			if (ret) {
				pr_err("Failed to decrypt post msg page: %d\n", ret);
				/* Just leak the page, as it's unsafe to free the page. */
				hv_cpu->post_msg_page = NULL;
				goto err;
			}

			memset(hv_cpu->post_msg_page, 0, PAGE_SIZE);
		}

		/*
		 * Synic message and event pages are allocated by paravisor.
		 * Skip these pages allocation here.
		 */
		if (!ms_hyperv.paravisor_present && !hv_root_partition) {
			hv_cpu->synic_message_page =
				(void *)get_zeroed_page(GFP_ATOMIC);
			if (hv_cpu->synic_message_page == NULL) {
				pr_err("Unable to allocate SYNIC message page\n");
				goto err;
			}

			hv_cpu->synic_event_page =
				(void *)get_zeroed_page(GFP_ATOMIC);
			if (hv_cpu->synic_event_page == NULL) {
				pr_err("Unable to allocate SYNIC event page\n");

				free_page((unsigned long)hv_cpu->synic_message_page);
				hv_cpu->synic_message_page = NULL;
				goto err;
			}
		}

		if (!ms_hyperv.paravisor_present &&
		    (hv_isolation_type_snp() || hv_isolation_type_tdx())) {
			ret = set_memory_decrypted((unsigned long)
				hv_cpu->synic_message_page, 1);
			if (ret) {
				pr_err("Failed to decrypt SYNIC msg page: %d\n", ret);
				hv_cpu->synic_message_page = NULL;

				/*
				 * Free the event page here so that hv_synic_free()
				 * won't later try to re-encrypt it.
				 */
				free_page((unsigned long)hv_cpu->synic_event_page);
				hv_cpu->synic_event_page = NULL;
				goto err;
			}

			ret = set_memory_decrypted((unsigned long)
				hv_cpu->synic_event_page, 1);
			if (ret) {
				pr_err("Failed to decrypt SYNIC event page: %d\n", ret);
				hv_cpu->synic_event_page = NULL;
				goto err;
			}

			memset(hv_cpu->synic_message_page, 0, PAGE_SIZE);
			memset(hv_cpu->synic_event_page, 0, PAGE_SIZE);
		}
	}

	return 0;

err:
	/*
	 * Any memory allocations that succeeded will be freed when
	 * the caller cleans up by calling hv_synic_free()
	 */
	return ret;
}


void hv_synic_free(void)
{
	int cpu, ret;

	for_each_present_cpu(cpu) {
		struct hv_per_cpu_context *hv_cpu
			= per_cpu_ptr(hv_context.cpu_context, cpu);

		/* It's better to leak the page if the encryption fails. */
		if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) {
			if (hv_cpu->post_msg_page) {
				ret = set_memory_encrypted((unsigned long)
					hv_cpu->post_msg_page, 1);
				if (ret) {
					pr_err("Failed to encrypt post msg page: %d\n", ret);
					hv_cpu->post_msg_page = NULL;
				}
			}
		}

		if (!ms_hyperv.paravisor_present &&
		    (hv_isolation_type_snp() || hv_isolation_type_tdx())) {
			if (hv_cpu->synic_message_page) {
				ret = set_memory_encrypted((unsigned long)
					hv_cpu->synic_message_page, 1);
				if (ret) {
					pr_err("Failed to encrypt SYNIC msg page: %d\n", ret);
					hv_cpu->synic_message_page = NULL;
				}
			}

			if (hv_cpu->synic_event_page) {
				ret = set_memory_encrypted((unsigned long)
					hv_cpu->synic_event_page, 1);
				if (ret) {
					pr_err("Failed to encrypt SYNIC event page: %d\n", ret);
					hv_cpu->synic_event_page = NULL;
				}
			}
		}

		free_page((unsigned long)hv_cpu->post_msg_page);
		free_page((unsigned long)hv_cpu->synic_event_page);
		free_page((unsigned long)hv_cpu->synic_message_page);
	}

	kfree(hv_context.hv_numa_map);
}

/*
 * hv_synic_init - Initialize the Synthetic Interrupt Controller.
 *
 * If it is already initialized by another entity (ie x2v shim), we need to
 * retrieve the initialized message and event pages.  Otherwise, we create and
 * initialize the message and event pages.
 */
void hv_synic_enable_regs(unsigned int cpu)
{
	struct hv_per_cpu_context *hv_cpu
		= per_cpu_ptr(hv_context.cpu_context, cpu);
	union hv_synic_simp simp;
	union hv_synic_siefp siefp;
	union hv_synic_sint shared_sint;
	union hv_synic_scontrol sctrl;

	/* Setup the Synic's message page */
	simp.as_uint64 = hv_get_msr(HV_MSR_SIMP);
	simp.simp_enabled = 1;

	if (ms_hyperv.paravisor_present || hv_root_partition) {
		/* Mask out vTOM bit. ioremap_cache() maps decrypted */
		u64 base = (simp.base_simp_gpa << HV_HYP_PAGE_SHIFT) &
				~ms_hyperv.shared_gpa_boundary;
		hv_cpu->synic_message_page
			= (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE);
		if (!hv_cpu->synic_message_page)
			pr_err("Fail to map synic message page.\n");
	} else {
		simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page)
			>> HV_HYP_PAGE_SHIFT;
	}

	hv_set_msr(HV_MSR_SIMP, simp.as_uint64);

	/* Setup the Synic's event page */
	siefp.as_uint64 = hv_get_msr(HV_MSR_SIEFP);
	siefp.siefp_enabled = 1;

	if (ms_hyperv.paravisor_present || hv_root_partition) {
		/* Mask out vTOM bit. ioremap_cache() maps decrypted */
		u64 base = (siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT) &
				~ms_hyperv.shared_gpa_boundary;
		hv_cpu->synic_event_page
			= (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE);
		if (!hv_cpu->synic_event_page)
			pr_err("Fail to map synic event page.\n");
	} else {
		siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page)
			>> HV_HYP_PAGE_SHIFT;
	}

	hv_set_msr(HV_MSR_SIEFP, siefp.as_uint64);

	/* Setup the shared SINT. */
	if (vmbus_irq != -1)
		enable_percpu_irq(vmbus_irq, 0);
	shared_sint.as_uint64 = hv_get_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT);

	shared_sint.vector = vmbus_interrupt;
	shared_sint.masked = false;

	/*
	 * On architectures where Hyper-V doesn't support AEOI (e.g., ARM64),
	 * it doesn't provide a recommendation flag and AEOI must be disabled.
	 */
#ifdef HV_DEPRECATING_AEOI_RECOMMENDED
	shared_sint.auto_eoi =
			!(ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED);
#else
	shared_sint.auto_eoi = 0;
#endif
	hv_set_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64);

	/* Enable the global synic bit */
	sctrl.as_uint64 = hv_get_msr(HV_MSR_SCONTROL);
	sctrl.enable = 1;

	hv_set_msr(HV_MSR_SCONTROL, sctrl.as_uint64);
}

int hv_synic_init(unsigned int cpu)
{
	hv_synic_enable_regs(cpu);

	hv_stimer_legacy_init(cpu, VMBUS_MESSAGE_SINT);

	return 0;
}

/*
 * hv_synic_cleanup - Cleanup routine for hv_synic_init().
 */
void hv_synic_disable_regs(unsigned int cpu)
{
	struct hv_per_cpu_context *hv_cpu
		= per_cpu_ptr(hv_context.cpu_context, cpu);
	union hv_synic_sint shared_sint;
	union hv_synic_simp simp;
	union hv_synic_siefp siefp;
	union hv_synic_scontrol sctrl;

	shared_sint.as_uint64 = hv_get_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT);

	shared_sint.masked = 1;

	/* Need to correctly cleanup in the case of SMP!!! */
	/* Disable the interrupt */
	hv_set_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64);

	simp.as_uint64 = hv_get_msr(HV_MSR_SIMP);
	/*
	 * In Isolation VM, sim and sief pages are allocated by
	 * paravisor. These pages also will be used by kdump
	 * kernel. So just reset enable bit here and keep page
	 * addresses.
	 */
	simp.simp_enabled = 0;
	if (ms_hyperv.paravisor_present || hv_root_partition) {
		iounmap(hv_cpu->synic_message_page);
		hv_cpu->synic_message_page = NULL;
	} else {
		simp.base_simp_gpa = 0;
	}

	hv_set_msr(HV_MSR_SIMP, simp.as_uint64);

	siefp.as_uint64 = hv_get_msr(HV_MSR_SIEFP);
	siefp.siefp_enabled = 0;

	if (ms_hyperv.paravisor_present || hv_root_partition) {
		iounmap(hv_cpu->synic_event_page);
		hv_cpu->synic_event_page = NULL;
	} else {
		siefp.base_siefp_gpa = 0;
	}

	hv_set_msr(HV_MSR_SIEFP, siefp.as_uint64);

	/* Disable the global synic bit */
	sctrl.as_uint64 = hv_get_msr(HV_MSR_SCONTROL);
	sctrl.enable = 0;
	hv_set_msr(HV_MSR_SCONTROL, sctrl.as_uint64);

	if (vmbus_irq != -1)
		disable_percpu_irq(vmbus_irq);
}

#define HV_MAX_TRIES 3
/*
 * Scan the event flags page of 'this' CPU looking for any bit that is set.  If we find one
 * bit set, then wait for a few milliseconds.  Repeat these steps for a maximum of 3 times.
 * Return 'true', if there is still any set bit after this operation; 'false', otherwise.
 *
 * If a bit is set, that means there is a pending channel interrupt.  The expectation is
 * that the normal interrupt handling mechanism will find and process the channel interrupt
 * "very soon", and in the process clear the bit.
 */
static bool hv_synic_event_pending(void)
{
	struct hv_per_cpu_context *hv_cpu = this_cpu_ptr(hv_context.cpu_context);
	union hv_synic_event_flags *event =
		(union hv_synic_event_flags *)hv_cpu->synic_event_page + VMBUS_MESSAGE_SINT;
	unsigned long *recv_int_page = event->flags; /* assumes VMBus version >= VERSION_WIN8 */
	bool pending;
	u32 relid;
	int tries = 0;

retry:
	pending = false;
	for_each_set_bit(relid, recv_int_page, HV_EVENT_FLAGS_COUNT) {
		/* Special case - VMBus channel protocol messages */
		if (relid == 0)
			continue;
		pending = true;
		break;
	}
	if (pending && tries++ < HV_MAX_TRIES) {
		usleep_range(10000, 20000);
		goto retry;
	}
	return pending;
}

int hv_synic_cleanup(unsigned int cpu)
{
	struct vmbus_channel *channel, *sc;
	bool channel_found = false;

	if (vmbus_connection.conn_state != CONNECTED)
		goto always_cleanup;

	/*
	 * Hyper-V does not provide a way to change the connect CPU once
	 * it is set; we must prevent the connect CPU from going offline
	 * while the VM is running normally. But in the panic or kexec()
	 * path where the vmbus is already disconnected, the CPU must be
	 * allowed to shut down.
	 */
	if (cpu == VMBUS_CONNECT_CPU)
		return -EBUSY;

	/*
	 * Search for channels which are bound to the CPU we're about to
	 * cleanup.  In case we find one and vmbus is still connected, we
	 * fail; this will effectively prevent CPU offlining.
	 *
	 * TODO: Re-bind the channels to different CPUs.
	 */
	mutex_lock(&vmbus_connection.channel_mutex);
	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
		if (channel->target_cpu == cpu) {
			channel_found = true;
			break;
		}
		list_for_each_entry(sc, &channel->sc_list, sc_list) {
			if (sc->target_cpu == cpu) {
				channel_found = true;
				break;
			}
		}
		if (channel_found)
			break;
	}
	mutex_unlock(&vmbus_connection.channel_mutex);

	if (channel_found)
		return -EBUSY;

	/*
	 * channel_found == false means that any channels that were previously
	 * assigned to the CPU have been reassigned elsewhere with a call of
	 * vmbus_send_modifychannel().  Scan the event flags page looking for
	 * bits that are set and waiting with a timeout for vmbus_chan_sched()
	 * to process such bits.  If bits are still set after this operation
	 * and VMBus is connected, fail the CPU offlining operation.
	 */
	if (vmbus_proto_version >= VERSION_WIN10_V4_1 && hv_synic_event_pending())
		return -EBUSY;

always_cleanup:
	hv_stimer_legacy_cleanup(cpu);

	hv_synic_disable_regs(cpu);

	return 0;
}