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
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
|
/*
* os-posix-lib.c
*
* Copyright (c) 2003-2008 Fabrice Bellard
* Copyright (c) 2010 Red Hat, Inc.
*
* QEMU library functions on POSIX which are shared between QEMU and
* the QEMU tools.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include <termios.h>
#include <glib/gprintf.h>
#include "sysemu/sysemu.h"
#include "trace.h"
#include "qapi/error.h"
#include "qemu/sockets.h"
#include <libgen.h>
#include <sys/signal.h>
#include "qemu/cutils.h"
#ifdef CONFIG_LINUX
#include <sys/syscall.h>
#endif
#ifdef __FreeBSD__
#include <sys/sysctl.h>
#include <sys/user.h>
#include <libutil.h>
#endif
#ifdef __NetBSD__
#include <sys/sysctl.h>
#endif
#include "qemu/mmap-alloc.h"
#ifdef CONFIG_DEBUG_STACK_USAGE
#include "qemu/error-report.h"
#endif
#define MAX_MEM_PREALLOC_THREAD_COUNT 16
struct MemsetThread {
char *addr;
size_t numpages;
size_t hpagesize;
QemuThread pgthread;
sigjmp_buf env;
};
typedef struct MemsetThread MemsetThread;
static MemsetThread *memset_thread;
static int memset_num_threads;
static bool memset_thread_failed;
int qemu_get_thread_id(void)
{
#if defined(__linux__)
return syscall(SYS_gettid);
#else
return getpid();
#endif
}
int qemu_daemon(int nochdir, int noclose)
{
return daemon(nochdir, noclose);
}
bool qemu_write_pidfile(const char *path, Error **errp)
{
int fd;
char pidstr[32];
while (1) {
struct stat a, b;
struct flock lock = {
.l_type = F_WRLCK,
.l_whence = SEEK_SET,
.l_len = 0,
};
fd = qemu_open(path, O_CREAT | O_WRONLY, S_IRUSR | S_IWUSR);
if (fd == -1) {
error_setg_errno(errp, errno, "Cannot open pid file");
return false;
}
if (fstat(fd, &b) < 0) {
error_setg_errno(errp, errno, "Cannot stat file");
goto fail_close;
}
if (fcntl(fd, F_SETLK, &lock)) {
error_setg_errno(errp, errno, "Cannot lock pid file");
goto fail_close;
}
/*
* Now make sure the path we locked is the same one that now
* exists on the filesystem.
*/
if (stat(path, &a) < 0) {
/*
* PID file disappeared, someone else must be racing with
* us, so try again.
*/
close(fd);
continue;
}
if (a.st_ino == b.st_ino) {
break;
}
/*
* PID file was recreated, someone else must be racing with
* us, so try again.
*/
close(fd);
}
if (ftruncate(fd, 0) < 0) {
error_setg_errno(errp, errno, "Failed to truncate pid file");
goto fail_unlink;
}
snprintf(pidstr, sizeof(pidstr), FMT_pid "\n", getpid());
if (write(fd, pidstr, strlen(pidstr)) != strlen(pidstr)) {
error_setg(errp, "Failed to write pid file");
goto fail_unlink;
}
return true;
fail_unlink:
unlink(path);
fail_close:
close(fd);
return false;
}
void *qemu_oom_check(void *ptr)
{
if (ptr == NULL) {
fprintf(stderr, "Failed to allocate memory: %s\n", strerror(errno));
abort();
}
return ptr;
}
void *qemu_try_memalign(size_t alignment, size_t size)
{
void *ptr;
if (alignment < sizeof(void*)) {
alignment = sizeof(void*);
}
#if defined(CONFIG_POSIX_MEMALIGN)
int ret;
ret = posix_memalign(&ptr, alignment, size);
if (ret != 0) {
errno = ret;
ptr = NULL;
}
#elif defined(CONFIG_BSD)
ptr = valloc(size);
#else
ptr = memalign(alignment, size);
#endif
trace_qemu_memalign(alignment, size, ptr);
return ptr;
}
void *qemu_memalign(size_t alignment, size_t size)
{
return qemu_oom_check(qemu_try_memalign(alignment, size));
}
/* alloc shared memory pages */
void *qemu_anon_ram_alloc(size_t size, uint64_t *alignment, bool shared)
{
size_t align = QEMU_VMALLOC_ALIGN;
void *ptr = qemu_ram_mmap(-1, size, align, shared);
if (ptr == MAP_FAILED) {
return NULL;
}
if (alignment) {
*alignment = align;
}
trace_qemu_anon_ram_alloc(size, ptr);
return ptr;
}
void qemu_vfree(void *ptr)
{
trace_qemu_vfree(ptr);
free(ptr);
}
void qemu_anon_ram_free(void *ptr, size_t size)
{
trace_qemu_anon_ram_free(ptr, size);
qemu_ram_munmap(ptr, size);
}
void qemu_set_block(int fd)
{
int f;
f = fcntl(fd, F_GETFL);
fcntl(fd, F_SETFL, f & ~O_NONBLOCK);
}
void qemu_set_nonblock(int fd)
{
int f;
f = fcntl(fd, F_GETFL);
fcntl(fd, F_SETFL, f | O_NONBLOCK);
}
int socket_set_fast_reuse(int fd)
{
int val = 1, ret;
ret = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR,
(const char *)&val, sizeof(val));
assert(ret == 0);
return ret;
}
void qemu_set_cloexec(int fd)
{
int f;
f = fcntl(fd, F_GETFD);
assert(f != -1);
f = fcntl(fd, F_SETFD, f | FD_CLOEXEC);
assert(f != -1);
}
/*
* Creates a pipe with FD_CLOEXEC set on both file descriptors
*/
int qemu_pipe(int pipefd[2])
{
int ret;
#ifdef CONFIG_PIPE2
ret = pipe2(pipefd, O_CLOEXEC);
if (ret != -1 || errno != ENOSYS) {
return ret;
}
#endif
ret = pipe(pipefd);
if (ret == 0) {
qemu_set_cloexec(pipefd[0]);
qemu_set_cloexec(pipefd[1]);
}
return ret;
}
char *
qemu_get_local_state_pathname(const char *relative_pathname)
{
return g_strdup_printf("%s/%s", CONFIG_QEMU_LOCALSTATEDIR,
relative_pathname);
}
void qemu_set_tty_echo(int fd, bool echo)
{
struct termios tty;
tcgetattr(fd, &tty);
if (echo) {
tty.c_lflag |= ECHO | ECHONL | ICANON | IEXTEN;
} else {
tty.c_lflag &= ~(ECHO | ECHONL | ICANON | IEXTEN);
}
tcsetattr(fd, TCSANOW, &tty);
}
static char exec_dir[PATH_MAX];
void qemu_init_exec_dir(const char *argv0)
{
char *dir;
char *p = NULL;
char buf[PATH_MAX];
assert(!exec_dir[0]);
#if defined(__linux__)
{
int len;
len = readlink("/proc/self/exe", buf, sizeof(buf) - 1);
if (len > 0) {
buf[len] = 0;
p = buf;
}
}
#elif defined(__FreeBSD__) \
|| (defined(__NetBSD__) && defined(KERN_PROC_PATHNAME))
{
#if defined(__FreeBSD__)
static int mib[4] = {CTL_KERN, KERN_PROC, KERN_PROC_PATHNAME, -1};
#else
static int mib[4] = {CTL_KERN, KERN_PROC_ARGS, -1, KERN_PROC_PATHNAME};
#endif
size_t len = sizeof(buf) - 1;
*buf = '\0';
if (!sysctl(mib, ARRAY_SIZE(mib), buf, &len, NULL, 0) &&
*buf) {
buf[sizeof(buf) - 1] = '\0';
p = buf;
}
}
#endif
/* If we don't have any way of figuring out the actual executable
location then try argv[0]. */
if (!p) {
if (!argv0) {
return;
}
p = realpath(argv0, buf);
if (!p) {
return;
}
}
dir = g_path_get_dirname(p);
pstrcpy(exec_dir, sizeof(exec_dir), dir);
g_free(dir);
}
char *qemu_get_exec_dir(void)
{
return g_strdup(exec_dir);
}
static void sigbus_handler(int signal)
{
int i;
if (memset_thread) {
for (i = 0; i < memset_num_threads; i++) {
if (qemu_thread_is_self(&memset_thread[i].pgthread)) {
siglongjmp(memset_thread[i].env, 1);
}
}
}
}
static void *do_touch_pages(void *arg)
{
MemsetThread *memset_args = (MemsetThread *)arg;
sigset_t set, oldset;
/* unblock SIGBUS */
sigemptyset(&set);
sigaddset(&set, SIGBUS);
pthread_sigmask(SIG_UNBLOCK, &set, &oldset);
if (sigsetjmp(memset_args->env, 1)) {
memset_thread_failed = true;
} else {
char *addr = memset_args->addr;
size_t numpages = memset_args->numpages;
size_t hpagesize = memset_args->hpagesize;
size_t i;
for (i = 0; i < numpages; i++) {
/*
* Read & write back the same value, so we don't
* corrupt existing user/app data that might be
* stored.
*
* 'volatile' to stop compiler optimizing this away
* to a no-op
*
* TODO: get a better solution from kernel so we
* don't need to write at all so we don't cause
* wear on the storage backing the region...
*/
*(volatile char *)addr = *addr;
addr += hpagesize;
}
}
pthread_sigmask(SIG_SETMASK, &oldset, NULL);
return NULL;
}
static inline int get_memset_num_threads(int smp_cpus)
{
long host_procs = sysconf(_SC_NPROCESSORS_ONLN);
int ret = 1;
if (host_procs > 0) {
ret = MIN(MIN(host_procs, MAX_MEM_PREALLOC_THREAD_COUNT), smp_cpus);
}
/* In case sysconf() fails, we fall back to single threaded */
return ret;
}
static bool touch_all_pages(char *area, size_t hpagesize, size_t numpages,
int smp_cpus)
{
size_t numpages_per_thread;
size_t size_per_thread;
char *addr = area;
int i = 0;
memset_thread_failed = false;
memset_num_threads = get_memset_num_threads(smp_cpus);
memset_thread = g_new0(MemsetThread, memset_num_threads);
numpages_per_thread = (numpages / memset_num_threads);
size_per_thread = (hpagesize * numpages_per_thread);
for (i = 0; i < memset_num_threads; i++) {
memset_thread[i].addr = addr;
memset_thread[i].numpages = (i == (memset_num_threads - 1)) ?
numpages : numpages_per_thread;
memset_thread[i].hpagesize = hpagesize;
qemu_thread_create(&memset_thread[i].pgthread, "touch_pages",
do_touch_pages, &memset_thread[i],
QEMU_THREAD_JOINABLE);
addr += size_per_thread;
numpages -= numpages_per_thread;
}
for (i = 0; i < memset_num_threads; i++) {
qemu_thread_join(&memset_thread[i].pgthread);
}
g_free(memset_thread);
memset_thread = NULL;
return memset_thread_failed;
}
void os_mem_prealloc(int fd, char *area, size_t memory, int smp_cpus,
Error **errp)
{
int ret;
struct sigaction act, oldact;
size_t hpagesize = qemu_fd_getpagesize(fd);
size_t numpages = DIV_ROUND_UP(memory, hpagesize);
memset(&act, 0, sizeof(act));
act.sa_handler = &sigbus_handler;
act.sa_flags = 0;
ret = sigaction(SIGBUS, &act, &oldact);
if (ret) {
error_setg_errno(errp, errno,
"os_mem_prealloc: failed to install signal handler");
return;
}
/* touch pages simultaneously */
if (touch_all_pages(area, hpagesize, numpages, smp_cpus)) {
error_setg(errp, "os_mem_prealloc: Insufficient free host memory "
"pages available to allocate guest RAM");
}
ret = sigaction(SIGBUS, &oldact, NULL);
if (ret) {
/* Terminate QEMU since it can't recover from error */
perror("os_mem_prealloc: failed to reinstall signal handler");
exit(1);
}
}
char *qemu_get_pid_name(pid_t pid)
{
char *name = NULL;
#if defined(__FreeBSD__)
/* BSDs don't have /proc, but they provide a nice substitute */
struct kinfo_proc *proc = kinfo_getproc(pid);
if (proc) {
name = g_strdup(proc->ki_comm);
free(proc);
}
#else
/* Assume a system with reasonable procfs */
char *pid_path;
size_t len;
pid_path = g_strdup_printf("/proc/%d/cmdline", pid);
g_file_get_contents(pid_path, &name, &len, NULL);
g_free(pid_path);
#endif
return name;
}
pid_t qemu_fork(Error **errp)
{
sigset_t oldmask, newmask;
struct sigaction sig_action;
int saved_errno;
pid_t pid;
/*
* Need to block signals now, so that child process can safely
* kill off caller's signal handlers without a race.
*/
sigfillset(&newmask);
if (pthread_sigmask(SIG_SETMASK, &newmask, &oldmask) != 0) {
error_setg_errno(errp, errno,
"cannot block signals");
return -1;
}
pid = fork();
saved_errno = errno;
if (pid < 0) {
/* attempt to restore signal mask, but ignore failure, to
* avoid obscuring the fork failure */
(void)pthread_sigmask(SIG_SETMASK, &oldmask, NULL);
error_setg_errno(errp, saved_errno,
"cannot fork child process");
errno = saved_errno;
return -1;
} else if (pid) {
/* parent process */
/* Restore our original signal mask now that the child is
* safely running. Only documented failures are EFAULT (not
* possible, since we are using just-grabbed mask) or EINVAL
* (not possible, since we are using correct arguments). */
(void)pthread_sigmask(SIG_SETMASK, &oldmask, NULL);
} else {
/* child process */
size_t i;
/* Clear out all signal handlers from parent so nothing
* unexpected can happen in our child once we unblock
* signals */
sig_action.sa_handler = SIG_DFL;
sig_action.sa_flags = 0;
sigemptyset(&sig_action.sa_mask);
for (i = 1; i < NSIG; i++) {
/* Only possible errors are EFAULT or EINVAL The former
* won't happen, the latter we expect, so no need to check
* return value */
(void)sigaction(i, &sig_action, NULL);
}
/* Unmask all signals in child, since we've no idea what the
* caller's done with their signal mask and don't want to
* propagate that to children */
sigemptyset(&newmask);
if (pthread_sigmask(SIG_SETMASK, &newmask, NULL) != 0) {
Error *local_err = NULL;
error_setg_errno(&local_err, errno,
"cannot unblock signals");
error_report_err(local_err);
_exit(1);
}
}
return pid;
}
void *qemu_alloc_stack(size_t *sz)
{
void *ptr, *guardpage;
int flags;
#ifdef CONFIG_DEBUG_STACK_USAGE
void *ptr2;
#endif
size_t pagesz = getpagesize();
#ifdef _SC_THREAD_STACK_MIN
/* avoid stacks smaller than _SC_THREAD_STACK_MIN */
long min_stack_sz = sysconf(_SC_THREAD_STACK_MIN);
*sz = MAX(MAX(min_stack_sz, 0), *sz);
#endif
/* adjust stack size to a multiple of the page size */
*sz = ROUND_UP(*sz, pagesz);
/* allocate one extra page for the guard page */
*sz += pagesz;
flags = MAP_PRIVATE | MAP_ANONYMOUS;
#if defined(MAP_STACK) && defined(__OpenBSD__)
/* Only enable MAP_STACK on OpenBSD. Other OS's such as
* Linux/FreeBSD/NetBSD have a flag with the same name
* but have differing functionality. OpenBSD will SEGV
* if it spots execution with a stack pointer pointing
* at memory that was not allocated with MAP_STACK.
*/
flags |= MAP_STACK;
#endif
ptr = mmap(NULL, *sz, PROT_READ | PROT_WRITE, flags, -1, 0);
if (ptr == MAP_FAILED) {
perror("failed to allocate memory for stack");
abort();
}
#if defined(HOST_IA64)
/* separate register stack */
guardpage = ptr + (((*sz - pagesz) / 2) & ~pagesz);
#elif defined(HOST_HPPA)
/* stack grows up */
guardpage = ptr + *sz - pagesz;
#else
/* stack grows down */
guardpage = ptr;
#endif
if (mprotect(guardpage, pagesz, PROT_NONE) != 0) {
perror("failed to set up stack guard page");
abort();
}
#ifdef CONFIG_DEBUG_STACK_USAGE
for (ptr2 = ptr + pagesz; ptr2 < ptr + *sz; ptr2 += sizeof(uint32_t)) {
*(uint32_t *)ptr2 = 0xdeadbeaf;
}
#endif
return ptr;
}
#ifdef CONFIG_DEBUG_STACK_USAGE
static __thread unsigned int max_stack_usage;
#endif
void qemu_free_stack(void *stack, size_t sz)
{
#ifdef CONFIG_DEBUG_STACK_USAGE
unsigned int usage;
void *ptr;
for (ptr = stack + getpagesize(); ptr < stack + sz;
ptr += sizeof(uint32_t)) {
if (*(uint32_t *)ptr != 0xdeadbeaf) {
break;
}
}
usage = sz - (uintptr_t) (ptr - stack);
if (usage > max_stack_usage) {
error_report("thread %d max stack usage increased from %u to %u",
qemu_get_thread_id(), max_stack_usage, usage);
max_stack_usage = usage;
}
#endif
munmap(stack, sz);
}
void sigaction_invoke(struct sigaction *action,
struct qemu_signalfd_siginfo *info)
{
siginfo_t si = {};
si.si_signo = info->ssi_signo;
si.si_errno = info->ssi_errno;
si.si_code = info->ssi_code;
/* Convert the minimal set of fields defined by POSIX.
* Positive si_code values are reserved for kernel-generated
* signals, where the valid siginfo fields are determined by
* the signal number. But according to POSIX, it is unspecified
* whether SI_USER and SI_QUEUE have values less than or equal to
* zero.
*/
if (info->ssi_code == SI_USER || info->ssi_code == SI_QUEUE ||
info->ssi_code <= 0) {
/* SIGTERM, etc. */
si.si_pid = info->ssi_pid;
si.si_uid = info->ssi_uid;
} else if (info->ssi_signo == SIGILL || info->ssi_signo == SIGFPE ||
info->ssi_signo == SIGSEGV || info->ssi_signo == SIGBUS) {
si.si_addr = (void *)(uintptr_t)info->ssi_addr;
} else if (info->ssi_signo == SIGCHLD) {
si.si_pid = info->ssi_pid;
si.si_status = info->ssi_status;
si.si_uid = info->ssi_uid;
}
action->sa_sigaction(info->ssi_signo, &si, NULL);
}
|