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
|
/*
* Virtio Balloon Device
*
* Copyright IBM, Corp. 2008
* Copyright (C) 2011 Red Hat, Inc.
* Copyright (C) 2011 Amit Shah <amit.shah@redhat.com>
*
* Authors:
* Anthony Liguori <aliguori@us.ibm.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
*/
#include "qemu/iov.h"
#include "qemu-common.h"
#include "virtio.h"
#include "pc.h"
#include "cpu.h"
#include "sysemu/balloon.h"
#include "virtio-balloon.h"
#include "sysemu/kvm.h"
#include "exec/address-spaces.h"
#if defined(__linux__)
#include <sys/mman.h>
#endif
typedef struct VirtIOBalloon
{
VirtIODevice vdev;
VirtQueue *ivq, *dvq, *svq;
uint32_t num_pages;
uint32_t actual;
uint64_t stats[VIRTIO_BALLOON_S_NR];
VirtQueueElement stats_vq_elem;
size_t stats_vq_offset;
DeviceState *qdev;
} VirtIOBalloon;
static VirtIOBalloon *to_virtio_balloon(VirtIODevice *vdev)
{
return (VirtIOBalloon *)vdev;
}
static void balloon_page(void *addr, int deflate)
{
#if defined(__linux__)
if (!kvm_enabled() || kvm_has_sync_mmu())
qemu_madvise(addr, TARGET_PAGE_SIZE,
deflate ? QEMU_MADV_WILLNEED : QEMU_MADV_DONTNEED);
#endif
}
/*
* reset_stats - Mark all items in the stats array as unset
*
* This function needs to be called at device intialization and before
* before updating to a set of newly-generated stats. This will ensure that no
* stale values stick around in case the guest reports a subset of the supported
* statistics.
*/
static inline void reset_stats(VirtIOBalloon *dev)
{
int i;
for (i = 0; i < VIRTIO_BALLOON_S_NR; dev->stats[i++] = -1);
}
static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIOBalloon *s = to_virtio_balloon(vdev);
VirtQueueElement elem;
MemoryRegionSection section;
while (virtqueue_pop(vq, &elem)) {
size_t offset = 0;
uint32_t pfn;
while (iov_to_buf(elem.out_sg, elem.out_num, offset, &pfn, 4) == 4) {
ram_addr_t pa;
ram_addr_t addr;
pa = (ram_addr_t)ldl_p(&pfn) << VIRTIO_BALLOON_PFN_SHIFT;
offset += 4;
/* FIXME: remove get_system_memory(), but how? */
section = memory_region_find(get_system_memory(), pa, 1);
if (!section.size || !memory_region_is_ram(section.mr))
continue;
/* Using memory_region_get_ram_ptr is bending the rules a bit, but
should be OK because we only want a single page. */
addr = section.offset_within_region;
balloon_page(memory_region_get_ram_ptr(section.mr) + addr,
!!(vq == s->dvq));
}
virtqueue_push(vq, &elem, offset);
virtio_notify(vdev, vq);
}
}
static void virtio_balloon_receive_stats(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIOBalloon *s = DO_UPCAST(VirtIOBalloon, vdev, vdev);
VirtQueueElement *elem = &s->stats_vq_elem;
VirtIOBalloonStat stat;
size_t offset = 0;
if (!virtqueue_pop(vq, elem)) {
return;
}
/* Initialize the stats to get rid of any stale values. This is only
* needed to handle the case where a guest supports fewer stats than it
* used to (ie. it has booted into an old kernel).
*/
reset_stats(s);
while (iov_to_buf(elem->out_sg, elem->out_num, offset, &stat, sizeof(stat))
== sizeof(stat)) {
uint16_t tag = tswap16(stat.tag);
uint64_t val = tswap64(stat.val);
offset += sizeof(stat);
if (tag < VIRTIO_BALLOON_S_NR)
s->stats[tag] = val;
}
s->stats_vq_offset = offset;
}
static void virtio_balloon_get_config(VirtIODevice *vdev, uint8_t *config_data)
{
VirtIOBalloon *dev = to_virtio_balloon(vdev);
struct virtio_balloon_config config;
config.num_pages = cpu_to_le32(dev->num_pages);
config.actual = cpu_to_le32(dev->actual);
memcpy(config_data, &config, 8);
}
static void virtio_balloon_set_config(VirtIODevice *vdev,
const uint8_t *config_data)
{
VirtIOBalloon *dev = to_virtio_balloon(vdev);
struct virtio_balloon_config config;
uint32_t oldactual = dev->actual;
memcpy(&config, config_data, 8);
dev->actual = le32_to_cpu(config.actual);
if (dev->actual != oldactual) {
qemu_balloon_changed(ram_size -
(dev->actual << VIRTIO_BALLOON_PFN_SHIFT));
}
}
static uint32_t virtio_balloon_get_features(VirtIODevice *vdev, uint32_t f)
{
f |= (1 << VIRTIO_BALLOON_F_STATS_VQ);
return f;
}
static void virtio_balloon_stat(void *opaque, BalloonInfo *info)
{
VirtIOBalloon *dev = opaque;
#if 0
/* Disable guest-provided stats for now. For more details please check:
* https://bugzilla.redhat.com/show_bug.cgi?id=623903
*
* If you do enable it (which is probably not going to happen as we
* need a new command for it), remember that you also need to fill the
* appropriate members of the BalloonInfo structure so that the stats
* are returned to the client.
*/
if (dev->vdev.guest_features & (1 << VIRTIO_BALLOON_F_STATS_VQ)) {
virtqueue_push(dev->svq, &dev->stats_vq_elem, dev->stats_vq_offset);
virtio_notify(&dev->vdev, dev->svq);
return;
}
#endif
/* Stats are not supported. Clear out any stale values that might
* have been set by a more featureful guest kernel.
*/
reset_stats(dev);
info->actual = ram_size - ((uint64_t) dev->actual <<
VIRTIO_BALLOON_PFN_SHIFT);
}
static void virtio_balloon_to_target(void *opaque, ram_addr_t target)
{
VirtIOBalloon *dev = opaque;
if (target > ram_size) {
target = ram_size;
}
if (target) {
dev->num_pages = (ram_size - target) >> VIRTIO_BALLOON_PFN_SHIFT;
virtio_notify_config(&dev->vdev);
}
}
static void virtio_balloon_save(QEMUFile *f, void *opaque)
{
VirtIOBalloon *s = opaque;
virtio_save(&s->vdev, f);
qemu_put_be32(f, s->num_pages);
qemu_put_be32(f, s->actual);
}
static int virtio_balloon_load(QEMUFile *f, void *opaque, int version_id)
{
VirtIOBalloon *s = opaque;
int ret;
if (version_id != 1)
return -EINVAL;
ret = virtio_load(&s->vdev, f);
if (ret) {
return ret;
}
s->num_pages = qemu_get_be32(f);
s->actual = qemu_get_be32(f);
return 0;
}
VirtIODevice *virtio_balloon_init(DeviceState *dev)
{
VirtIOBalloon *s;
int ret;
s = (VirtIOBalloon *)virtio_common_init("virtio-balloon",
VIRTIO_ID_BALLOON,
8, sizeof(VirtIOBalloon));
s->vdev.get_config = virtio_balloon_get_config;
s->vdev.set_config = virtio_balloon_set_config;
s->vdev.get_features = virtio_balloon_get_features;
ret = qemu_add_balloon_handler(virtio_balloon_to_target,
virtio_balloon_stat, s);
if (ret < 0) {
virtio_cleanup(&s->vdev);
return NULL;
}
s->ivq = virtio_add_queue(&s->vdev, 128, virtio_balloon_handle_output);
s->dvq = virtio_add_queue(&s->vdev, 128, virtio_balloon_handle_output);
s->svq = virtio_add_queue(&s->vdev, 128, virtio_balloon_receive_stats);
reset_stats(s);
s->qdev = dev;
register_savevm(dev, "virtio-balloon", -1, 1,
virtio_balloon_save, virtio_balloon_load, s);
return &s->vdev;
}
void virtio_balloon_exit(VirtIODevice *vdev)
{
VirtIOBalloon *s = DO_UPCAST(VirtIOBalloon, vdev, vdev);
qemu_remove_balloon_handler(s);
unregister_savevm(s->qdev, "virtio-balloon", s);
virtio_cleanup(vdev);
}
|