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
|
/*
* Handle extern requests for shutdown, reboot and sysrq
*/
#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/reboot.h>
#include <linux/sysrq.h>
#include <linux/stop_machine.h>
#include <linux/freezer.h>
#include <linux/syscore_ops.h>
#include <linux/export.h>
#include <xen/xen.h>
#include <xen/xenbus.h>
#include <xen/grant_table.h>
#include <xen/events.h>
#include <xen/hvc-console.h>
#include <xen/page.h>
#include <xen/xen-ops.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
enum shutdown_state {
SHUTDOWN_INVALID = -1,
SHUTDOWN_POWEROFF = 0,
SHUTDOWN_SUSPEND = 2,
/* Code 3 is SHUTDOWN_CRASH, which we don't use because the domain can only
report a crash, not be instructed to crash!
HALT is the same as POWEROFF, as far as we're concerned. The tools use
the distinction when we return the reason code to them. */
SHUTDOWN_HALT = 4,
};
/* Ignore multiple shutdown requests. */
static enum shutdown_state shutting_down = SHUTDOWN_INVALID;
struct suspend_info {
int cancelled;
};
static RAW_NOTIFIER_HEAD(xen_resume_notifier);
void xen_resume_notifier_register(struct notifier_block *nb)
{
raw_notifier_chain_register(&xen_resume_notifier, nb);
}
EXPORT_SYMBOL_GPL(xen_resume_notifier_register);
void xen_resume_notifier_unregister(struct notifier_block *nb)
{
raw_notifier_chain_unregister(&xen_resume_notifier, nb);
}
EXPORT_SYMBOL_GPL(xen_resume_notifier_unregister);
#ifdef CONFIG_HIBERNATE_CALLBACKS
static int xen_suspend(void *data)
{
struct suspend_info *si = data;
int err;
BUG_ON(!irqs_disabled());
err = syscore_suspend();
if (err) {
pr_err("%s: system core suspend failed: %d\n", __func__, err);
return err;
}
gnttab_suspend();
xen_arch_pre_suspend();
/*
* This hypercall returns 1 if suspend was cancelled
* or the domain was merely checkpointed, and 0 if it
* is resuming in a new domain.
*/
si->cancelled = HYPERVISOR_suspend(xen_pv_domain()
? virt_to_gfn(xen_start_info)
: 0);
xen_arch_post_suspend(si->cancelled);
gnttab_resume();
if (!si->cancelled) {
xen_irq_resume();
xen_timer_resume();
}
syscore_resume();
return 0;
}
static void do_suspend(void)
{
int err;
struct suspend_info si;
shutting_down = SHUTDOWN_SUSPEND;
err = freeze_processes();
if (err) {
pr_err("%s: freeze processes failed %d\n", __func__, err);
goto out;
}
err = freeze_kernel_threads();
if (err) {
pr_err("%s: freeze kernel threads failed %d\n", __func__, err);
goto out_thaw;
}
err = dpm_suspend_start(PMSG_FREEZE);
if (err) {
pr_err("%s: dpm_suspend_start %d\n", __func__, err);
goto out_thaw;
}
printk(KERN_DEBUG "suspending xenstore...\n");
xs_suspend();
err = dpm_suspend_end(PMSG_FREEZE);
if (err) {
pr_err("dpm_suspend_end failed: %d\n", err);
si.cancelled = 0;
goto out_resume;
}
xen_arch_suspend();
si.cancelled = 1;
err = stop_machine(xen_suspend, &si, cpumask_of(0));
/* Resume console as early as possible. */
if (!si.cancelled)
xen_console_resume();
raw_notifier_call_chain(&xen_resume_notifier, 0, NULL);
dpm_resume_start(si.cancelled ? PMSG_THAW : PMSG_RESTORE);
if (err) {
pr_err("failed to start xen_suspend: %d\n", err);
si.cancelled = 1;
}
xen_arch_resume();
out_resume:
if (!si.cancelled)
xs_resume();
else
xs_suspend_cancel();
dpm_resume_end(si.cancelled ? PMSG_THAW : PMSG_RESTORE);
out_thaw:
thaw_processes();
out:
shutting_down = SHUTDOWN_INVALID;
}
#endif /* CONFIG_HIBERNATE_CALLBACKS */
struct shutdown_handler {
#define SHUTDOWN_CMD_SIZE 11
const char command[SHUTDOWN_CMD_SIZE];
bool flag;
void (*cb)(void);
};
static int poweroff_nb(struct notifier_block *cb, unsigned long code, void *unused)
{
switch (code) {
case SYS_DOWN:
case SYS_HALT:
case SYS_POWER_OFF:
shutting_down = SHUTDOWN_POWEROFF;
default:
break;
}
return NOTIFY_DONE;
}
static void do_poweroff(void)
{
switch (system_state) {
case SYSTEM_BOOTING:
orderly_poweroff(true);
break;
case SYSTEM_RUNNING:
orderly_poweroff(false);
break;
default:
/* Don't do it when we are halting/rebooting. */
pr_info("Ignoring Xen toolstack shutdown.\n");
break;
}
}
static void do_reboot(void)
{
shutting_down = SHUTDOWN_POWEROFF; /* ? */
ctrl_alt_del();
}
static struct shutdown_handler shutdown_handlers[] = {
{ "poweroff", true, do_poweroff },
{ "halt", false, do_poweroff },
{ "reboot", true, do_reboot },
#ifdef CONFIG_HIBERNATE_CALLBACKS
{ "suspend", true, do_suspend },
#endif
};
static void shutdown_handler(struct xenbus_watch *watch,
const char **vec, unsigned int len)
{
char *str;
struct xenbus_transaction xbt;
int err;
int idx;
if (shutting_down != SHUTDOWN_INVALID)
return;
again:
err = xenbus_transaction_start(&xbt);
if (err)
return;
str = (char *)xenbus_read(xbt, "control", "shutdown", NULL);
/* Ignore read errors and empty reads. */
if (XENBUS_IS_ERR_READ(str)) {
xenbus_transaction_end(xbt, 1);
return;
}
for (idx = 0; idx < ARRAY_SIZE(shutdown_handlers); idx++) {
if (strcmp(str, shutdown_handlers[idx].command) == 0)
break;
}
/* Only acknowledge commands which we are prepared to handle. */
if (idx < ARRAY_SIZE(shutdown_handlers))
xenbus_write(xbt, "control", "shutdown", "");
err = xenbus_transaction_end(xbt, 0);
if (err == -EAGAIN) {
kfree(str);
goto again;
}
if (idx < ARRAY_SIZE(shutdown_handlers)) {
shutdown_handlers[idx].cb();
} else {
pr_info("Ignoring shutdown request: %s\n", str);
shutting_down = SHUTDOWN_INVALID;
}
kfree(str);
}
#ifdef CONFIG_MAGIC_SYSRQ
static void sysrq_handler(struct xenbus_watch *watch, const char **vec,
unsigned int len)
{
char sysrq_key = '\0';
struct xenbus_transaction xbt;
int err;
again:
err = xenbus_transaction_start(&xbt);
if (err)
return;
err = xenbus_scanf(xbt, "control", "sysrq", "%c", &sysrq_key);
if (err < 0) {
/*
* The Xenstore watch fires directly after registering it and
* after a suspend/resume cycle. So ENOENT is no error but
* might happen in those cases. ERANGE is observed when we get
* an empty value (''), this happens when we acknowledge the
* request by writing '\0' below.
*/
if (err != -ENOENT && err != -ERANGE)
pr_err("Error %d reading sysrq code in control/sysrq\n",
err);
xenbus_transaction_end(xbt, 1);
return;
}
if (sysrq_key != '\0') {
err = xenbus_printf(xbt, "control", "sysrq", "%c", '\0');
if (err) {
pr_err("%s: Error %d writing sysrq in control/sysrq\n",
__func__, err);
xenbus_transaction_end(xbt, 1);
return;
}
}
err = xenbus_transaction_end(xbt, 0);
if (err == -EAGAIN)
goto again;
if (sysrq_key != '\0')
handle_sysrq(sysrq_key);
}
static struct xenbus_watch sysrq_watch = {
.node = "control/sysrq",
.callback = sysrq_handler
};
#endif
static struct xenbus_watch shutdown_watch = {
.node = "control/shutdown",
.callback = shutdown_handler
};
static struct notifier_block xen_reboot_nb = {
.notifier_call = poweroff_nb,
};
static int setup_shutdown_watcher(void)
{
int err;
int idx;
#define FEATURE_PATH_SIZE (SHUTDOWN_CMD_SIZE + sizeof("feature-"))
char node[FEATURE_PATH_SIZE];
err = register_xenbus_watch(&shutdown_watch);
if (err) {
pr_err("Failed to set shutdown watcher\n");
return err;
}
#ifdef CONFIG_MAGIC_SYSRQ
err = register_xenbus_watch(&sysrq_watch);
if (err) {
pr_err("Failed to set sysrq watcher\n");
return err;
}
#endif
for (idx = 0; idx < ARRAY_SIZE(shutdown_handlers); idx++) {
if (!shutdown_handlers[idx].flag)
continue;
snprintf(node, FEATURE_PATH_SIZE, "feature-%s",
shutdown_handlers[idx].command);
err = xenbus_printf(XBT_NIL, "control", node, "%u", 1);
if (err) {
pr_err("%s: Error %d writing %s\n", __func__,
err, node);
return err;
}
}
return 0;
}
static int shutdown_event(struct notifier_block *notifier,
unsigned long event,
void *data)
{
setup_shutdown_watcher();
return NOTIFY_DONE;
}
int xen_setup_shutdown_event(void)
{
static struct notifier_block xenstore_notifier = {
.notifier_call = shutdown_event
};
if (!xen_domain())
return -ENODEV;
register_xenstore_notifier(&xenstore_notifier);
register_reboot_notifier(&xen_reboot_nb);
return 0;
}
EXPORT_SYMBOL_GPL(xen_setup_shutdown_event);
subsys_initcall(xen_setup_shutdown_event);
|