xref: /kernel/linux/linux-5.10/arch/x86/kvm/svm/avic.c (revision 8c2ecf20)
1// SPDX-License-Identifier: GPL-2.0-only
2/*
3 * Kernel-based Virtual Machine driver for Linux
4 *
5 * AMD SVM support
6 *
7 * Copyright (C) 2006 Qumranet, Inc.
8 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
9 *
10 * Authors:
11 *   Yaniv Kamay  <yaniv@qumranet.com>
12 *   Avi Kivity   <avi@qumranet.com>
13 */
14
15#define pr_fmt(fmt) "SVM: " fmt
16
17#include <linux/kvm_types.h>
18#include <linux/hashtable.h>
19#include <linux/amd-iommu.h>
20#include <linux/kvm_host.h>
21
22#include <asm/irq_remapping.h>
23
24#include "trace.h"
25#include "lapic.h"
26#include "x86.h"
27#include "irq.h"
28#include "svm.h"
29
30/* enable / disable AVIC */
31int avic;
32#ifdef CONFIG_X86_LOCAL_APIC
33module_param(avic, int, S_IRUGO);
34#endif
35
36#define SVM_AVIC_DOORBELL	0xc001011b
37
38#define AVIC_HPA_MASK	~((0xFFFULL << 52) | 0xFFF)
39
40/*
41 * 0xff is broadcast, so the max index allowed for physical APIC ID
42 * table is 0xfe.  APIC IDs above 0xff are reserved.
43 */
44#define AVIC_MAX_PHYSICAL_ID_COUNT	255
45
46#define AVIC_UNACCEL_ACCESS_WRITE_MASK		1
47#define AVIC_UNACCEL_ACCESS_OFFSET_MASK		0xFF0
48#define AVIC_UNACCEL_ACCESS_VECTOR_MASK		0xFFFFFFFF
49
50/* AVIC GATAG is encoded using VM and VCPU IDs */
51#define AVIC_VCPU_ID_BITS		8
52#define AVIC_VCPU_ID_MASK		((1 << AVIC_VCPU_ID_BITS) - 1)
53
54#define AVIC_VM_ID_BITS			24
55#define AVIC_VM_ID_NR			(1 << AVIC_VM_ID_BITS)
56#define AVIC_VM_ID_MASK			((1 << AVIC_VM_ID_BITS) - 1)
57
58#define AVIC_GATAG(x, y)		(((x & AVIC_VM_ID_MASK) << AVIC_VCPU_ID_BITS) | \
59						(y & AVIC_VCPU_ID_MASK))
60#define AVIC_GATAG_TO_VMID(x)		((x >> AVIC_VCPU_ID_BITS) & AVIC_VM_ID_MASK)
61#define AVIC_GATAG_TO_VCPUID(x)		(x & AVIC_VCPU_ID_MASK)
62
63/* Note:
64 * This hash table is used to map VM_ID to a struct kvm_svm,
65 * when handling AMD IOMMU GALOG notification to schedule in
66 * a particular vCPU.
67 */
68#define SVM_VM_DATA_HASH_BITS	8
69static DEFINE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS);
70static u32 next_vm_id = 0;
71static bool next_vm_id_wrapped = 0;
72static DEFINE_SPINLOCK(svm_vm_data_hash_lock);
73
74/*
75 * This is a wrapper of struct amd_iommu_ir_data.
76 */
77struct amd_svm_iommu_ir {
78	struct list_head node;	/* Used by SVM for per-vcpu ir_list */
79	void *data;		/* Storing pointer to struct amd_ir_data */
80};
81
82enum avic_ipi_failure_cause {
83	AVIC_IPI_FAILURE_INVALID_INT_TYPE,
84	AVIC_IPI_FAILURE_TARGET_NOT_RUNNING,
85	AVIC_IPI_FAILURE_INVALID_TARGET,
86	AVIC_IPI_FAILURE_INVALID_BACKING_PAGE,
87};
88
89/* Note:
90 * This function is called from IOMMU driver to notify
91 * SVM to schedule in a particular vCPU of a particular VM.
92 */
93int avic_ga_log_notifier(u32 ga_tag)
94{
95	unsigned long flags;
96	struct kvm_svm *kvm_svm;
97	struct kvm_vcpu *vcpu = NULL;
98	u32 vm_id = AVIC_GATAG_TO_VMID(ga_tag);
99	u32 vcpu_id = AVIC_GATAG_TO_VCPUID(ga_tag);
100
101	pr_debug("SVM: %s: vm_id=%#x, vcpu_id=%#x\n", __func__, vm_id, vcpu_id);
102	trace_kvm_avic_ga_log(vm_id, vcpu_id);
103
104	spin_lock_irqsave(&svm_vm_data_hash_lock, flags);
105	hash_for_each_possible(svm_vm_data_hash, kvm_svm, hnode, vm_id) {
106		if (kvm_svm->avic_vm_id != vm_id)
107			continue;
108		vcpu = kvm_get_vcpu_by_id(&kvm_svm->kvm, vcpu_id);
109		break;
110	}
111	spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags);
112
113	/* Note:
114	 * At this point, the IOMMU should have already set the pending
115	 * bit in the vAPIC backing page. So, we just need to schedule
116	 * in the vcpu.
117	 */
118	if (vcpu)
119		kvm_vcpu_wake_up(vcpu);
120
121	return 0;
122}
123
124void avic_vm_destroy(struct kvm *kvm)
125{
126	unsigned long flags;
127	struct kvm_svm *kvm_svm = to_kvm_svm(kvm);
128
129	if (!avic)
130		return;
131
132	if (kvm_svm->avic_logical_id_table_page)
133		__free_page(kvm_svm->avic_logical_id_table_page);
134	if (kvm_svm->avic_physical_id_table_page)
135		__free_page(kvm_svm->avic_physical_id_table_page);
136
137	spin_lock_irqsave(&svm_vm_data_hash_lock, flags);
138	hash_del(&kvm_svm->hnode);
139	spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags);
140}
141
142int avic_vm_init(struct kvm *kvm)
143{
144	unsigned long flags;
145	int err = -ENOMEM;
146	struct kvm_svm *kvm_svm = to_kvm_svm(kvm);
147	struct kvm_svm *k2;
148	struct page *p_page;
149	struct page *l_page;
150	u32 vm_id;
151
152	if (!avic)
153		return 0;
154
155	/* Allocating physical APIC ID table (4KB) */
156	p_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
157	if (!p_page)
158		goto free_avic;
159
160	kvm_svm->avic_physical_id_table_page = p_page;
161
162	/* Allocating logical APIC ID table (4KB) */
163	l_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
164	if (!l_page)
165		goto free_avic;
166
167	kvm_svm->avic_logical_id_table_page = l_page;
168
169	spin_lock_irqsave(&svm_vm_data_hash_lock, flags);
170 again:
171	vm_id = next_vm_id = (next_vm_id + 1) & AVIC_VM_ID_MASK;
172	if (vm_id == 0) { /* id is 1-based, zero is not okay */
173		next_vm_id_wrapped = 1;
174		goto again;
175	}
176	/* Is it still in use? Only possible if wrapped at least once */
177	if (next_vm_id_wrapped) {
178		hash_for_each_possible(svm_vm_data_hash, k2, hnode, vm_id) {
179			if (k2->avic_vm_id == vm_id)
180				goto again;
181		}
182	}
183	kvm_svm->avic_vm_id = vm_id;
184	hash_add(svm_vm_data_hash, &kvm_svm->hnode, kvm_svm->avic_vm_id);
185	spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags);
186
187	return 0;
188
189free_avic:
190	avic_vm_destroy(kvm);
191	return err;
192}
193
194void avic_init_vmcb(struct vcpu_svm *svm)
195{
196	struct vmcb *vmcb = svm->vmcb;
197	struct kvm_svm *kvm_svm = to_kvm_svm(svm->vcpu.kvm);
198	phys_addr_t bpa = __sme_set(page_to_phys(svm->avic_backing_page));
199	phys_addr_t lpa = __sme_set(page_to_phys(kvm_svm->avic_logical_id_table_page));
200	phys_addr_t ppa = __sme_set(page_to_phys(kvm_svm->avic_physical_id_table_page));
201
202	vmcb->control.avic_backing_page = bpa & AVIC_HPA_MASK;
203	vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK;
204	vmcb->control.avic_physical_id = ppa & AVIC_HPA_MASK;
205	vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID_COUNT;
206	if (kvm_apicv_activated(svm->vcpu.kvm))
207		vmcb->control.int_ctl |= AVIC_ENABLE_MASK;
208	else
209		vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK;
210}
211
212static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu,
213				       unsigned int index)
214{
215	u64 *avic_physical_id_table;
216	struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
217
218	if (index >= AVIC_MAX_PHYSICAL_ID_COUNT)
219		return NULL;
220
221	avic_physical_id_table = page_address(kvm_svm->avic_physical_id_table_page);
222
223	return &avic_physical_id_table[index];
224}
225
226/**
227 * Note:
228 * AVIC hardware walks the nested page table to check permissions,
229 * but does not use the SPA address specified in the leaf page
230 * table entry since it uses  address in the AVIC_BACKING_PAGE pointer
231 * field of the VMCB. Therefore, we set up the
232 * APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (4KB) here.
233 */
234static int avic_update_access_page(struct kvm *kvm, bool activate)
235{
236	int ret = 0;
237
238	mutex_lock(&kvm->slots_lock);
239	/*
240	 * During kvm_destroy_vm(), kvm_pit_set_reinject() could trigger
241	 * APICv mode change, which update APIC_ACCESS_PAGE_PRIVATE_MEMSLOT
242	 * memory region. So, we need to ensure that kvm->mm == current->mm.
243	 */
244	if ((kvm->arch.apic_access_page_done == activate) ||
245	    (kvm->mm != current->mm))
246		goto out;
247
248	ret = __x86_set_memory_region(kvm,
249				      APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
250				      APIC_DEFAULT_PHYS_BASE,
251				      activate ? PAGE_SIZE : 0);
252	if (ret)
253		goto out;
254
255	kvm->arch.apic_access_page_done = activate;
256out:
257	mutex_unlock(&kvm->slots_lock);
258	return ret;
259}
260
261static int avic_init_backing_page(struct kvm_vcpu *vcpu)
262{
263	u64 *entry, new_entry;
264	int id = vcpu->vcpu_id;
265	struct vcpu_svm *svm = to_svm(vcpu);
266
267	if (id >= AVIC_MAX_PHYSICAL_ID_COUNT)
268		return -EINVAL;
269
270	if (!svm->vcpu.arch.apic->regs)
271		return -EINVAL;
272
273	if (kvm_apicv_activated(vcpu->kvm)) {
274		int ret;
275
276		ret = avic_update_access_page(vcpu->kvm, true);
277		if (ret)
278			return ret;
279	}
280
281	svm->avic_backing_page = virt_to_page(svm->vcpu.arch.apic->regs);
282
283	/* Setting AVIC backing page address in the phy APIC ID table */
284	entry = avic_get_physical_id_entry(vcpu, id);
285	if (!entry)
286		return -EINVAL;
287
288	new_entry = __sme_set((page_to_phys(svm->avic_backing_page) &
289			      AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) |
290			      AVIC_PHYSICAL_ID_ENTRY_VALID_MASK);
291	WRITE_ONCE(*entry, new_entry);
292
293	svm->avic_physical_id_cache = entry;
294
295	return 0;
296}
297
298int avic_incomplete_ipi_interception(struct vcpu_svm *svm)
299{
300	u32 icrh = svm->vmcb->control.exit_info_1 >> 32;
301	u32 icrl = svm->vmcb->control.exit_info_1;
302	u32 id = svm->vmcb->control.exit_info_2 >> 32;
303	u32 index = svm->vmcb->control.exit_info_2 & 0xFF;
304	struct kvm_lapic *apic = svm->vcpu.arch.apic;
305
306	trace_kvm_avic_incomplete_ipi(svm->vcpu.vcpu_id, icrh, icrl, id, index);
307
308	switch (id) {
309	case AVIC_IPI_FAILURE_INVALID_INT_TYPE:
310		/*
311		 * AVIC hardware handles the generation of
312		 * IPIs when the specified Message Type is Fixed
313		 * (also known as fixed delivery mode) and
314		 * the Trigger Mode is edge-triggered. The hardware
315		 * also supports self and broadcast delivery modes
316		 * specified via the Destination Shorthand(DSH)
317		 * field of the ICRL. Logical and physical APIC ID
318		 * formats are supported. All other IPI types cause
319		 * a #VMEXIT, which needs to emulated.
320		 */
321		kvm_lapic_reg_write(apic, APIC_ICR2, icrh);
322		kvm_lapic_reg_write(apic, APIC_ICR, icrl);
323		break;
324	case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: {
325		int i;
326		struct kvm_vcpu *vcpu;
327		struct kvm *kvm = svm->vcpu.kvm;
328		struct kvm_lapic *apic = svm->vcpu.arch.apic;
329
330		/*
331		 * At this point, we expect that the AVIC HW has already
332		 * set the appropriate IRR bits on the valid target
333		 * vcpus. So, we just need to kick the appropriate vcpu.
334		 */
335		kvm_for_each_vcpu(i, vcpu, kvm) {
336			bool m = kvm_apic_match_dest(vcpu, apic,
337						     icrl & APIC_SHORT_MASK,
338						     GET_APIC_DEST_FIELD(icrh),
339						     icrl & APIC_DEST_MASK);
340
341			if (m && !avic_vcpu_is_running(vcpu))
342				kvm_vcpu_wake_up(vcpu);
343		}
344		break;
345	}
346	case AVIC_IPI_FAILURE_INVALID_TARGET:
347		break;
348	case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE:
349		WARN_ONCE(1, "Invalid backing page\n");
350		break;
351	default:
352		pr_err("Unknown IPI interception\n");
353	}
354
355	return 1;
356}
357
358static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat)
359{
360	struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
361	int index;
362	u32 *logical_apic_id_table;
363	int dlid = GET_APIC_LOGICAL_ID(ldr);
364
365	if (!dlid)
366		return NULL;
367
368	if (flat) { /* flat */
369		index = ffs(dlid) - 1;
370		if (index > 7)
371			return NULL;
372	} else { /* cluster */
373		int cluster = (dlid & 0xf0) >> 4;
374		int apic = ffs(dlid & 0x0f) - 1;
375
376		if ((apic < 0) || (apic > 7) ||
377		    (cluster >= 0xf))
378			return NULL;
379		index = (cluster << 2) + apic;
380	}
381
382	logical_apic_id_table = (u32 *) page_address(kvm_svm->avic_logical_id_table_page);
383
384	return &logical_apic_id_table[index];
385}
386
387static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr)
388{
389	bool flat;
390	u32 *entry, new_entry;
391
392	flat = kvm_lapic_get_reg(vcpu->arch.apic, APIC_DFR) == APIC_DFR_FLAT;
393	entry = avic_get_logical_id_entry(vcpu, ldr, flat);
394	if (!entry)
395		return -EINVAL;
396
397	new_entry = READ_ONCE(*entry);
398	new_entry &= ~AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK;
399	new_entry |= (g_physical_id & AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK);
400	new_entry |= AVIC_LOGICAL_ID_ENTRY_VALID_MASK;
401	WRITE_ONCE(*entry, new_entry);
402
403	return 0;
404}
405
406static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu)
407{
408	struct vcpu_svm *svm = to_svm(vcpu);
409	bool flat = svm->dfr_reg == APIC_DFR_FLAT;
410	u32 *entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat);
411
412	if (entry)
413		clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry);
414}
415
416static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
417{
418	int ret = 0;
419	struct vcpu_svm *svm = to_svm(vcpu);
420	u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR);
421	u32 id = kvm_xapic_id(vcpu->arch.apic);
422
423	if (ldr == svm->ldr_reg)
424		return 0;
425
426	avic_invalidate_logical_id_entry(vcpu);
427
428	if (ldr)
429		ret = avic_ldr_write(vcpu, id, ldr);
430
431	if (!ret)
432		svm->ldr_reg = ldr;
433
434	return ret;
435}
436
437static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu)
438{
439	u64 *old, *new;
440	struct vcpu_svm *svm = to_svm(vcpu);
441	u32 id = kvm_xapic_id(vcpu->arch.apic);
442
443	if (vcpu->vcpu_id == id)
444		return 0;
445
446	old = avic_get_physical_id_entry(vcpu, vcpu->vcpu_id);
447	new = avic_get_physical_id_entry(vcpu, id);
448	if (!new || !old)
449		return 1;
450
451	/* We need to move physical_id_entry to new offset */
452	*new = *old;
453	*old = 0ULL;
454	to_svm(vcpu)->avic_physical_id_cache = new;
455
456	/*
457	 * Also update the guest physical APIC ID in the logical
458	 * APIC ID table entry if already setup the LDR.
459	 */
460	if (svm->ldr_reg)
461		avic_handle_ldr_update(vcpu);
462
463	return 0;
464}
465
466static void avic_handle_dfr_update(struct kvm_vcpu *vcpu)
467{
468	struct vcpu_svm *svm = to_svm(vcpu);
469	u32 dfr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_DFR);
470
471	if (svm->dfr_reg == dfr)
472		return;
473
474	avic_invalidate_logical_id_entry(vcpu);
475	svm->dfr_reg = dfr;
476}
477
478static int avic_unaccel_trap_write(struct vcpu_svm *svm)
479{
480	struct kvm_lapic *apic = svm->vcpu.arch.apic;
481	u32 offset = svm->vmcb->control.exit_info_1 &
482				AVIC_UNACCEL_ACCESS_OFFSET_MASK;
483
484	switch (offset) {
485	case APIC_ID:
486		if (avic_handle_apic_id_update(&svm->vcpu))
487			return 0;
488		break;
489	case APIC_LDR:
490		if (avic_handle_ldr_update(&svm->vcpu))
491			return 0;
492		break;
493	case APIC_DFR:
494		avic_handle_dfr_update(&svm->vcpu);
495		break;
496	default:
497		break;
498	}
499
500	kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset));
501
502	return 1;
503}
504
505static bool is_avic_unaccelerated_access_trap(u32 offset)
506{
507	bool ret = false;
508
509	switch (offset) {
510	case APIC_ID:
511	case APIC_EOI:
512	case APIC_RRR:
513	case APIC_LDR:
514	case APIC_DFR:
515	case APIC_SPIV:
516	case APIC_ESR:
517	case APIC_ICR:
518	case APIC_LVTT:
519	case APIC_LVTTHMR:
520	case APIC_LVTPC:
521	case APIC_LVT0:
522	case APIC_LVT1:
523	case APIC_LVTERR:
524	case APIC_TMICT:
525	case APIC_TDCR:
526		ret = true;
527		break;
528	default:
529		break;
530	}
531	return ret;
532}
533
534int avic_unaccelerated_access_interception(struct vcpu_svm *svm)
535{
536	int ret = 0;
537	u32 offset = svm->vmcb->control.exit_info_1 &
538		     AVIC_UNACCEL_ACCESS_OFFSET_MASK;
539	u32 vector = svm->vmcb->control.exit_info_2 &
540		     AVIC_UNACCEL_ACCESS_VECTOR_MASK;
541	bool write = (svm->vmcb->control.exit_info_1 >> 32) &
542		     AVIC_UNACCEL_ACCESS_WRITE_MASK;
543	bool trap = is_avic_unaccelerated_access_trap(offset);
544
545	trace_kvm_avic_unaccelerated_access(svm->vcpu.vcpu_id, offset,
546					    trap, write, vector);
547	if (trap) {
548		/* Handling Trap */
549		WARN_ONCE(!write, "svm: Handling trap read.\n");
550		ret = avic_unaccel_trap_write(svm);
551	} else {
552		/* Handling Fault */
553		ret = kvm_emulate_instruction(&svm->vcpu, 0);
554	}
555
556	return ret;
557}
558
559int avic_init_vcpu(struct vcpu_svm *svm)
560{
561	int ret;
562	struct kvm_vcpu *vcpu = &svm->vcpu;
563
564	if (!avic || !irqchip_in_kernel(vcpu->kvm))
565		return 0;
566
567	ret = avic_init_backing_page(&svm->vcpu);
568	if (ret)
569		return ret;
570
571	INIT_LIST_HEAD(&svm->ir_list);
572	spin_lock_init(&svm->ir_list_lock);
573	svm->dfr_reg = APIC_DFR_FLAT;
574
575	return ret;
576}
577
578void avic_post_state_restore(struct kvm_vcpu *vcpu)
579{
580	if (avic_handle_apic_id_update(vcpu) != 0)
581		return;
582	avic_handle_dfr_update(vcpu);
583	avic_handle_ldr_update(vcpu);
584}
585
586void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate)
587{
588	if (!avic || !lapic_in_kernel(vcpu))
589		return;
590
591	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
592	kvm_request_apicv_update(vcpu->kvm, activate,
593				 APICV_INHIBIT_REASON_IRQWIN);
594	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
595}
596
597void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
598{
599	return;
600}
601
602void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
603{
604}
605
606void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
607{
608}
609
610static int svm_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
611{
612	int ret = 0;
613	unsigned long flags;
614	struct amd_svm_iommu_ir *ir;
615	struct vcpu_svm *svm = to_svm(vcpu);
616
617	if (!kvm_arch_has_assigned_device(vcpu->kvm))
618		return 0;
619
620	/*
621	 * Here, we go through the per-vcpu ir_list to update all existing
622	 * interrupt remapping table entry targeting this vcpu.
623	 */
624	spin_lock_irqsave(&svm->ir_list_lock, flags);
625
626	if (list_empty(&svm->ir_list))
627		goto out;
628
629	list_for_each_entry(ir, &svm->ir_list, node) {
630		if (activate)
631			ret = amd_iommu_activate_guest_mode(ir->data);
632		else
633			ret = amd_iommu_deactivate_guest_mode(ir->data);
634		if (ret)
635			break;
636	}
637out:
638	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
639	return ret;
640}
641
642void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
643{
644	struct vcpu_svm *svm = to_svm(vcpu);
645	struct vmcb *vmcb = svm->vmcb;
646	bool activated = kvm_vcpu_apicv_active(vcpu);
647
648	if (!avic)
649		return;
650
651	if (activated) {
652		/**
653		 * During AVIC temporary deactivation, guest could update
654		 * APIC ID, DFR and LDR registers, which would not be trapped
655		 * by avic_unaccelerated_access_interception(). In this case,
656		 * we need to check and update the AVIC logical APIC ID table
657		 * accordingly before re-activating.
658		 */
659		avic_post_state_restore(vcpu);
660		vmcb->control.int_ctl |= AVIC_ENABLE_MASK;
661	} else {
662		vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK;
663	}
664	vmcb_mark_dirty(vmcb, VMCB_AVIC);
665
666	svm_set_pi_irte_mode(vcpu, activated);
667}
668
669void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
670{
671	return;
672}
673
674int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
675{
676	if (!vcpu->arch.apicv_active)
677		return -1;
678
679	kvm_lapic_set_irr(vec, vcpu->arch.apic);
680	smp_mb__after_atomic();
681
682	if (avic_vcpu_is_running(vcpu)) {
683		int cpuid = vcpu->cpu;
684
685		if (cpuid != get_cpu())
686			wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpuid));
687		put_cpu();
688	} else
689		kvm_vcpu_wake_up(vcpu);
690
691	return 0;
692}
693
694bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
695{
696	return false;
697}
698
699static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
700{
701	unsigned long flags;
702	struct amd_svm_iommu_ir *cur;
703
704	spin_lock_irqsave(&svm->ir_list_lock, flags);
705	list_for_each_entry(cur, &svm->ir_list, node) {
706		if (cur->data != pi->ir_data)
707			continue;
708		list_del(&cur->node);
709		kfree(cur);
710		break;
711	}
712	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
713}
714
715static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
716{
717	int ret = 0;
718	unsigned long flags;
719	struct amd_svm_iommu_ir *ir;
720
721	/**
722	 * In some cases, the existing irte is updaed and re-set,
723	 * so we need to check here if it's already been * added
724	 * to the ir_list.
725	 */
726	if (pi->ir_data && (pi->prev_ga_tag != 0)) {
727		struct kvm *kvm = svm->vcpu.kvm;
728		u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag);
729		struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
730		struct vcpu_svm *prev_svm;
731
732		if (!prev_vcpu) {
733			ret = -EINVAL;
734			goto out;
735		}
736
737		prev_svm = to_svm(prev_vcpu);
738		svm_ir_list_del(prev_svm, pi);
739	}
740
741	/**
742	 * Allocating new amd_iommu_pi_data, which will get
743	 * add to the per-vcpu ir_list.
744	 */
745	ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL_ACCOUNT);
746	if (!ir) {
747		ret = -ENOMEM;
748		goto out;
749	}
750	ir->data = pi->ir_data;
751
752	spin_lock_irqsave(&svm->ir_list_lock, flags);
753	list_add(&ir->node, &svm->ir_list);
754	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
755out:
756	return ret;
757}
758
759/**
760 * Note:
761 * The HW cannot support posting multicast/broadcast
762 * interrupts to a vCPU. So, we still use legacy interrupt
763 * remapping for these kind of interrupts.
764 *
765 * For lowest-priority interrupts, we only support
766 * those with single CPU as the destination, e.g. user
767 * configures the interrupts via /proc/irq or uses
768 * irqbalance to make the interrupts single-CPU.
769 */
770static int
771get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
772		 struct vcpu_data *vcpu_info, struct vcpu_svm **svm)
773{
774	struct kvm_lapic_irq irq;
775	struct kvm_vcpu *vcpu = NULL;
776
777	kvm_set_msi_irq(kvm, e, &irq);
778
779	if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
780	    !kvm_irq_is_postable(&irq)) {
781		pr_debug("SVM: %s: use legacy intr remap mode for irq %u\n",
782			 __func__, irq.vector);
783		return -1;
784	}
785
786	pr_debug("SVM: %s: use GA mode for irq %u\n", __func__,
787		 irq.vector);
788	*svm = to_svm(vcpu);
789	vcpu_info->pi_desc_addr = __sme_set(page_to_phys((*svm)->avic_backing_page));
790	vcpu_info->vector = irq.vector;
791
792	return 0;
793}
794
795/*
796 * svm_update_pi_irte - set IRTE for Posted-Interrupts
797 *
798 * @kvm: kvm
799 * @host_irq: host irq of the interrupt
800 * @guest_irq: gsi of the interrupt
801 * @set: set or unset PI
802 * returns 0 on success, < 0 on failure
803 */
804int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
805		       uint32_t guest_irq, bool set)
806{
807	struct kvm_kernel_irq_routing_entry *e;
808	struct kvm_irq_routing_table *irq_rt;
809	int idx, ret = 0;
810
811	if (!kvm_arch_has_assigned_device(kvm) ||
812	    !irq_remapping_cap(IRQ_POSTING_CAP))
813		return 0;
814
815	pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n",
816		 __func__, host_irq, guest_irq, set);
817
818	idx = srcu_read_lock(&kvm->irq_srcu);
819	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
820
821	if (guest_irq >= irq_rt->nr_rt_entries ||
822		hlist_empty(&irq_rt->map[guest_irq])) {
823		pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
824			     guest_irq, irq_rt->nr_rt_entries);
825		goto out;
826	}
827
828	hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
829		struct vcpu_data vcpu_info;
830		struct vcpu_svm *svm = NULL;
831
832		if (e->type != KVM_IRQ_ROUTING_MSI)
833			continue;
834
835		/**
836		 * Here, we setup with legacy mode in the following cases:
837		 * 1. When cannot target interrupt to a specific vcpu.
838		 * 2. Unsetting posted interrupt.
839		 * 3. APIC virtialization is disabled for the vcpu.
840		 * 4. IRQ has incompatible delivery mode (SMI, INIT, etc)
841		 */
842		if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set &&
843		    kvm_vcpu_apicv_active(&svm->vcpu)) {
844			struct amd_iommu_pi_data pi;
845
846			/* Try to enable guest_mode in IRTE */
847			pi.base = __sme_set(page_to_phys(svm->avic_backing_page) &
848					    AVIC_HPA_MASK);
849			pi.ga_tag = AVIC_GATAG(to_kvm_svm(kvm)->avic_vm_id,
850						     svm->vcpu.vcpu_id);
851			pi.is_guest_mode = true;
852			pi.vcpu_data = &vcpu_info;
853			ret = irq_set_vcpu_affinity(host_irq, &pi);
854
855			/**
856			 * Here, we successfully setting up vcpu affinity in
857			 * IOMMU guest mode. Now, we need to store the posted
858			 * interrupt information in a per-vcpu ir_list so that
859			 * we can reference to them directly when we update vcpu
860			 * scheduling information in IOMMU irte.
861			 */
862			if (!ret && pi.is_guest_mode)
863				svm_ir_list_add(svm, &pi);
864		} else {
865			/* Use legacy mode in IRTE */
866			struct amd_iommu_pi_data pi;
867
868			/**
869			 * Here, pi is used to:
870			 * - Tell IOMMU to use legacy mode for this interrupt.
871			 * - Retrieve ga_tag of prior interrupt remapping data.
872			 */
873			pi.prev_ga_tag = 0;
874			pi.is_guest_mode = false;
875			ret = irq_set_vcpu_affinity(host_irq, &pi);
876
877			/**
878			 * Check if the posted interrupt was previously
879			 * setup with the guest_mode by checking if the ga_tag
880			 * was cached. If so, we need to clean up the per-vcpu
881			 * ir_list.
882			 */
883			if (!ret && pi.prev_ga_tag) {
884				int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
885				struct kvm_vcpu *vcpu;
886
887				vcpu = kvm_get_vcpu_by_id(kvm, id);
888				if (vcpu)
889					svm_ir_list_del(to_svm(vcpu), &pi);
890			}
891		}
892
893		if (!ret && svm) {
894			trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id,
895						 e->gsi, vcpu_info.vector,
896						 vcpu_info.pi_desc_addr, set);
897		}
898
899		if (ret < 0) {
900			pr_err("%s: failed to update PI IRTE\n", __func__);
901			goto out;
902		}
903	}
904
905	ret = 0;
906out:
907	srcu_read_unlock(&kvm->irq_srcu, idx);
908	return ret;
909}
910
911bool svm_check_apicv_inhibit_reasons(ulong bit)
912{
913	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
914			  BIT(APICV_INHIBIT_REASON_HYPERV) |
915			  BIT(APICV_INHIBIT_REASON_NESTED) |
916			  BIT(APICV_INHIBIT_REASON_IRQWIN) |
917			  BIT(APICV_INHIBIT_REASON_PIT_REINJ) |
918			  BIT(APICV_INHIBIT_REASON_X2APIC);
919
920	return supported & BIT(bit);
921}
922
923void svm_pre_update_apicv_exec_ctrl(struct kvm *kvm, bool activate)
924{
925	avic_update_access_page(kvm, activate);
926}
927
928static inline int
929avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
930{
931	int ret = 0;
932	unsigned long flags;
933	struct amd_svm_iommu_ir *ir;
934	struct vcpu_svm *svm = to_svm(vcpu);
935
936	if (!kvm_arch_has_assigned_device(vcpu->kvm))
937		return 0;
938
939	/*
940	 * Here, we go through the per-vcpu ir_list to update all existing
941	 * interrupt remapping table entry targeting this vcpu.
942	 */
943	spin_lock_irqsave(&svm->ir_list_lock, flags);
944
945	if (list_empty(&svm->ir_list))
946		goto out;
947
948	list_for_each_entry(ir, &svm->ir_list, node) {
949		ret = amd_iommu_update_ga(cpu, r, ir->data);
950		if (ret)
951			break;
952	}
953out:
954	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
955	return ret;
956}
957
958void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
959{
960	u64 entry;
961	/* ID = 0xff (broadcast), ID > 0xff (reserved) */
962	int h_physical_id = kvm_cpu_get_apicid(cpu);
963	struct vcpu_svm *svm = to_svm(vcpu);
964
965	if (!kvm_vcpu_apicv_active(vcpu))
966		return;
967
968	/*
969	 * Since the host physical APIC id is 8 bits,
970	 * we can support host APIC ID upto 255.
971	 */
972	if (WARN_ON(h_physical_id > AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK))
973		return;
974
975	entry = READ_ONCE(*(svm->avic_physical_id_cache));
976	WARN_ON(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK);
977
978	entry &= ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK;
979	entry |= (h_physical_id & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK);
980
981	entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
982	if (svm->avic_is_running)
983		entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
984
985	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
986	avic_update_iommu_vcpu_affinity(vcpu, h_physical_id,
987					svm->avic_is_running);
988}
989
990void avic_vcpu_put(struct kvm_vcpu *vcpu)
991{
992	u64 entry;
993	struct vcpu_svm *svm = to_svm(vcpu);
994
995	if (!kvm_vcpu_apicv_active(vcpu))
996		return;
997
998	entry = READ_ONCE(*(svm->avic_physical_id_cache));
999	if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
1000		avic_update_iommu_vcpu_affinity(vcpu, -1, 0);
1001
1002	entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
1003	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
1004}
1005
1006/**
1007 * This function is called during VCPU halt/unhalt.
1008 */
1009static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
1010{
1011	struct vcpu_svm *svm = to_svm(vcpu);
1012
1013	svm->avic_is_running = is_run;
1014	if (is_run)
1015		avic_vcpu_load(vcpu, vcpu->cpu);
1016	else
1017		avic_vcpu_put(vcpu);
1018}
1019
1020void svm_vcpu_blocking(struct kvm_vcpu *vcpu)
1021{
1022	avic_set_running(vcpu, false);
1023}
1024
1025void svm_vcpu_unblocking(struct kvm_vcpu *vcpu)
1026{
1027	if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu))
1028		kvm_vcpu_update_apicv(vcpu);
1029	avic_set_running(vcpu, true);
1030}
1031