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
|
/*
* irq_comm.c: Common API for in kernel interrupt controller
* Copyright (c) 2007, Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope 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, write to the Free Software Foundation, Inc., 59 Temple
* Place - Suite 330, Boston, MA 02111-1307 USA.
* Authors:
* Yaozu (Eddie) Dong <Eddie.dong@intel.com>
*
* Copyright 2010 Red Hat, Inc. and/or its affiliates.
*/
#include <linux/kvm_host.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <trace/events/kvm.h>
#include <asm/msidef.h>
#include "irq.h"
#include "ioapic.h"
#include "lapic.h"
static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
struct kvm *kvm, int irq_source_id, int level,
bool line_status)
{
struct kvm_pic *pic = pic_irqchip(kvm);
return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level);
}
static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
struct kvm *kvm, int irq_source_id, int level,
bool line_status)
{
struct kvm_ioapic *ioapic = kvm->arch.vioapic;
return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level,
line_status);
}
int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
struct kvm_lapic_irq *irq, unsigned long *dest_map)
{
int i, r = -1;
struct kvm_vcpu *vcpu, *lowest = NULL;
if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
kvm_lowest_prio_delivery(irq)) {
printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
irq->delivery_mode = APIC_DM_FIXED;
}
if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map))
return r;
kvm_for_each_vcpu(i, vcpu, kvm) {
if (!kvm_apic_present(vcpu))
continue;
if (!kvm_apic_match_dest(vcpu, src, irq->shorthand,
irq->dest_id, irq->dest_mode))
continue;
if (!kvm_lowest_prio_delivery(irq)) {
if (r < 0)
r = 0;
r += kvm_apic_set_irq(vcpu, irq, dest_map);
} else if (kvm_lapic_enabled(vcpu)) {
if (!lowest)
lowest = vcpu;
else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
lowest = vcpu;
}
}
if (lowest)
r = kvm_apic_set_irq(lowest, irq, dest_map);
return r;
}
static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
struct kvm_lapic_irq *irq)
{
trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
irq->dest_id = (e->msi.address_lo &
MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
irq->vector = (e->msi.data &
MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
irq->delivery_mode = e->msi.data & 0x700;
irq->msi_redir_hint = ((e->msi.address_lo
& MSI_ADDR_REDIRECTION_LOWPRI) > 0);
irq->level = 1;
irq->shorthand = 0;
}
int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
struct kvm *kvm, int irq_source_id, int level, bool line_status)
{
struct kvm_lapic_irq irq;
if (!level)
return -1;
kvm_set_msi_irq(e, &irq);
return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL);
}
static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e,
struct kvm *kvm)
{
struct kvm_lapic_irq irq;
int r;
kvm_set_msi_irq(e, &irq);
if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
return r;
else
return -EWOULDBLOCK;
}
/*
* Deliver an IRQ in an atomic context if we can, or return a failure,
* user can retry in a process context.
* Return value:
* -EWOULDBLOCK - Can't deliver in atomic context: retry in a process context.
* Other values - No need to retry.
*/
int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
{
struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS];
struct kvm_kernel_irq_routing_entry *e;
int ret = -EINVAL;
int idx;
trace_kvm_set_irq(irq, level, irq_source_id);
/*
* Injection into either PIC or IOAPIC might need to scan all CPUs,
* which would need to be retried from thread context; when same GSI
* is connected to both PIC and IOAPIC, we'd have to report a
* partial failure here.
* Since there's no easy way to do this, we only support injecting MSI
* which is limited to 1:1 GSI mapping.
*/
idx = srcu_read_lock(&kvm->irq_srcu);
if (kvm_irq_map_gsi(kvm, entries, irq) > 0) {
e = &entries[0];
if (likely(e->type == KVM_IRQ_ROUTING_MSI))
ret = kvm_set_msi_inatomic(e, kvm);
else
ret = -EWOULDBLOCK;
}
srcu_read_unlock(&kvm->irq_srcu, idx);
return ret;
}
int kvm_request_irq_source_id(struct kvm *kvm)
{
unsigned long *bitmap = &kvm->arch.irq_sources_bitmap;
int irq_source_id;
mutex_lock(&kvm->irq_lock);
irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG);
if (irq_source_id >= BITS_PER_LONG) {
printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n");
irq_source_id = -EFAULT;
goto unlock;
}
ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
set_bit(irq_source_id, bitmap);
unlock:
mutex_unlock(&kvm->irq_lock);
return irq_source_id;
}
void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
{
ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
mutex_lock(&kvm->irq_lock);
if (irq_source_id < 0 ||
irq_source_id >= BITS_PER_LONG) {
printk(KERN_ERR "kvm: IRQ source ID out of range!\n");
goto unlock;
}
clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
if (!irqchip_in_kernel(kvm))
goto unlock;
kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id);
kvm_pic_clear_all(pic_irqchip(kvm), irq_source_id);
unlock:
mutex_unlock(&kvm->irq_lock);
}
void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
struct kvm_irq_mask_notifier *kimn)
{
mutex_lock(&kvm->irq_lock);
kimn->irq = irq;
hlist_add_head_rcu(&kimn->link, &kvm->arch.mask_notifier_list);
mutex_unlock(&kvm->irq_lock);
}
void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
struct kvm_irq_mask_notifier *kimn)
{
mutex_lock(&kvm->irq_lock);
hlist_del_rcu(&kimn->link);
mutex_unlock(&kvm->irq_lock);
synchronize_srcu(&kvm->irq_srcu);
}
void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
bool mask)
{
struct kvm_irq_mask_notifier *kimn;
int idx, gsi;
idx = srcu_read_lock(&kvm->irq_srcu);
gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
if (gsi != -1)
hlist_for_each_entry_rcu(kimn, &kvm->arch.mask_notifier_list, link)
if (kimn->irq == gsi)
kimn->func(kimn, mask);
srcu_read_unlock(&kvm->irq_srcu, idx);
}
int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
const struct kvm_irq_routing_entry *ue)
{
int r = -EINVAL;
int delta;
unsigned max_pin;
switch (ue->type) {
case KVM_IRQ_ROUTING_IRQCHIP:
delta = 0;
switch (ue
|