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
|
/*
* Copyright (C) 2015, 2016 ARM Ltd.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include "vgic.h"
#define CREATE_TRACE_POINTS
#include "../trace.h"
#ifdef CONFIG_DEBUG_SPINLOCK
#define DEBUG_SPINLOCK_BUG_ON(p) BUG_ON(p)
#else
#define DEBUG_SPINLOCK_BUG_ON(p)
#endif
struct vgic_global __section(.hyp.text) kvm_vgic_global_state;
/*
* Locking order is always:
* vgic_cpu->ap_list_lock
* vgic_irq->irq_lock
*
* (that is, always take the ap_list_lock before the struct vgic_irq lock).
*
* When taking more than one ap_list_lock at the same time, always take the
* lowest numbered VCPU's ap_list_lock first, so:
* vcpuX->vcpu_id < vcpuY->vcpu_id:
* spin_lock(vcpuX->arch.vgic_cpu.ap_list_lock);
* spin_lock(vcpuY->arch.vgic_cpu.ap_list_lock);
*/
struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
u32 intid)
{
/* SGIs and PPIs */
if (intid <= VGIC_MAX_PRIVATE)
return &vcpu->arch.vgic_cpu.private_irqs[intid];
/* SPIs */
if (intid <= VGIC_MAX_SPI)
return &kvm->arch.vgic.spis[intid - VGIC_NR_PRIVATE_IRQS];
/* LPIs are not yet covered */
if (intid >= VGIC_MIN_LPI)
return NULL;
WARN(1, "Looking up struct vgic_irq for reserved INTID");
return NULL;
}
/**
* kvm_vgic_target_oracle - compute the target vcpu for an irq
*
* @irq: The irq to route. Must be already locked.
*
* Based on the current state of the interrupt (enabled, pending,
* active, vcpu and target_vcpu), compute the next vcpu this should be
* given to. Return NULL if this shouldn't be injected at all.
*
* Requires the IRQ lock to be held.
*/
static struct kvm_vcpu *vgic_target_oracle(struct vgic_irq *irq)
{
DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&irq->irq_lock));
/* If the interrupt is active, it must stay on the current vcpu */
if (irq->active)
return irq->vcpu ? : irq->target_vcpu;
/*
* If the IRQ is not active but enabled and pending, we should direct
* it to its configured target VCPU.
* If the distributor is disabled, pending interrupts shouldn't be
* forwarded.
*/
if (irq->enabled && irq->pending) {
if (unlikely(irq->target_vcpu &&
!irq->target_vcpu->kvm->arch.vgic.enabled))
return NULL;
return irq->target_vcpu;
}
/* If neither active nor pending and enabled, then this IRQ should not
* be queued to any VCPU.
*/
return NULL;
}
/*
* Only valid injection if changing level for level-triggered IRQs or for a
* rising edge.
*/
static bool vgic_validate_injection(struct vgic_irq *irq, bool level)
{
switch (irq->config) {
case VGIC_CONFIG_LEVEL:
return irq->line_level != level;
case VGIC_CONFIG_EDGE:
return level;
}
return false;
}
/*
* Check whether an IRQ needs to (and can) be queued to a VCPU's ap list.
* Do the queuing if necessary, taking the right locks in the right order.
* Returns true when the IRQ was queued, false otherwise.
*
* Needs to be entered with the IRQ lock already held, but will return
* with all locks dropped.
*/
bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq)
{
struct kvm_vcpu *vcpu;
DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&irq->irq_lock));
retry:
vcpu = vgic_target_oracle(irq);
if (irq->vcpu || !vcpu) {
/*
* If this IRQ is already on a VCPU's ap_list, then it
* cannot be moved or modified and there is no more work for
* us to do.
*
* Otherwise, if the irq is not pending and enabled, it does
* not need to be inserted into an ap_list and there is also
* no more work for us to do.
*/
spin_unlock(&irq->irq_lock);
return false;
}
/*
* We must unlock the irq lock to take the ap_list_lock where
* we are going to insert this new pending interrupt.
*/
spin_unlock(&irq->irq_lock);
/* someone can do stuff here, which we re-check below */
spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock);
spin_lock(&irq->irq_lock);
/*
* Did something change behind our backs?
*
* There are two cases:
* 1) The irq lost its pending state or was disabled behind our
* backs and/or it was queued to another VCPU's ap_list.
* 2) Someone changed the affinity on this irq behind our
* backs and we are now holding the wrong ap_list_lock.
*
* In both cases, drop the locks and retry.
*/
if (unlikely(irq->vcpu || vcpu != vgic_target_oracle(irq))) {
spin_unlock(&irq->irq_lock);
spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock);
spin_lock(&irq->irq_lock);
goto retry;
}
list_add_tail(&irq->ap_list, &vcpu->arch.vgic_cpu.ap_list_head);
irq->vcpu = vcpu;
spin_unlock(&irq->irq_lock);
spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock);
kvm_vcpu_kick(vcpu);
return true;
}
static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
unsigned int intid, bool level,
bool mapped_irq)
{
struct kvm_vcpu *vcpu;
struct vgic_irq *irq;
int ret;
trace_vgic_update_irq_pending(cpuid, intid, level);
vcpu = kvm_get_vcpu(kvm, cpuid);
if (!vcpu && intid < VGIC_NR_PRIVATE_IRQS)
return -EINVAL;
irq = vgic_get_irq(kvm, vcpu, intid);
if (!irq)
return -EINVAL;
if (irq->hw != mapped_irq)
return -EINVAL;
spin_lock(&irq->irq_lock);
if (!vgic_validate_injection(irq, level)) {
/* Nothing to see here, move along... */
spin_unlock(&irq->irq_lock);
return 0;
}
if (irq->config == VGIC_CONFIG_LEVEL) {
irq->line_level = level;
irq->pending = level || irq->soft_pending;
} else {
irq->pending = true;
}
vgic_queue_irq_unlock(kvm, irq);
return 0;
}
/**
* kvm_vgic_inject_irq - Inject an IRQ from a device to the vgic
* @kvm: The VM structure pointer
* @cpuid: The CPU for PPIs
* @intid: The INTID to inject a new state to.
* @level: Edge-triggered: true: to trigger the interrupt
* false: to ignore the call
* Level-sensitive true: raise the input signal
* false: lower the input signal
*
* The VGIC is not concerned with devices being active-LOW or active-HIGH for
* level-sensitive interrupts. You can think of the level parameter as 1
* being HIGH and 0 being LOW and all devices being active-HIGH.
*/
int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
bool level)
{
return vgic_update_irq_pending(kvm, cpuid, intid, level, false);
}
|