commands-posix.c 74.2 KB
Newer Older
1
/*
2
 * QEMU Guest Agent POSIX-specific command implementations
3 4 5 6 7
 *
 * Copyright IBM Corp. 2011
 *
 * Authors:
 *  Michael Roth      <mdroth@linux.vnet.ibm.com>
8
 *  Michal Privoznik  <mprivozn@redhat.com>
9 10 11 12 13
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or later.
 * See the COPYING file in the top-level directory.
 */

P
Peter Maydell 已提交
14
#include "qemu/osdep.h"
15
#include <sys/ioctl.h>
16
#include <sys/utsname.h>
17
#include <sys/wait.h>
18
#include <dirent.h>
19 20
#include "qga/guest-agent-core.h"
#include "qga-qmp-commands.h"
21
#include "qapi/qmp/qerror.h"
22 23
#include "qemu/queue.h"
#include "qemu/host-utils.h"
24
#include "qemu/sockets.h"
25
#include "qemu/base64.h"
26
#include "qemu/cutils.h"
27

28 29 30 31
#ifdef HAVE_UTMPX
#include <utmpx.h>
#endif

32
#ifndef CONFIG_HAS_ENVIRON
33 34 35 36
#ifdef __APPLE__
#include <crt_externs.h>
#define environ (*_NSGetEnviron())
#else
37 38
extern char **environ;
#endif
39
#endif
40

41
#if defined(__linux__)
42
#include <mntent.h>
43
#include <linux/fs.h>
44 45 46 47
#include <ifaddrs.h>
#include <arpa/inet.h>
#include <sys/socket.h>
#include <net/if.h>
48

49
#ifdef FIFREEZE
50 51
#define CONFIG_FSFREEZE
#endif
52 53 54
#ifdef FITRIM
#define CONFIG_FSTRIM
#endif
55 56
#endif

57
static void ga_wait_child(pid_t pid, int *status, Error **errp)
58 59 60 61 62 63 64 65 66 67
{
    pid_t rpid;

    *status = 0;

    do {
        rpid = waitpid(pid, status, 0);
    } while (rpid == -1 && errno == EINTR);

    if (rpid == -1) {
68 69
        error_setg_errno(errp, errno, "failed to wait for child (pid: %d)",
                         pid);
70 71 72 73 74 75
        return;
    }

    g_assert(rpid == pid);
}

76
void qmp_guest_shutdown(bool has_mode, const char *mode, Error **errp)
77 78
{
    const char *shutdown_flag;
79 80
    Error *local_err = NULL;
    pid_t pid;
81
    int status;
82 83 84 85 86 87 88 89 90

    slog("guest-shutdown called, mode: %s", mode);
    if (!has_mode || strcmp(mode, "powerdown") == 0) {
        shutdown_flag = "-P";
    } else if (strcmp(mode, "halt") == 0) {
        shutdown_flag = "-H";
    } else if (strcmp(mode, "reboot") == 0) {
        shutdown_flag = "-r";
    } else {
91
        error_setg(errp,
92
                   "mode is invalid (valid values are: halt|powerdown|reboot");
93 94 95
        return;
    }

96 97
    pid = fork();
    if (pid == 0) {
98 99
        /* child, start the shutdown */
        setsid();
100 101 102
        reopen_fd_to_null(0);
        reopen_fd_to_null(1);
        reopen_fd_to_null(2);
103

104
        execle("/sbin/shutdown", "shutdown", "-h", shutdown_flag, "+0",
105 106
               "hypervisor initiated shutdown", (char*)NULL, environ);
        _exit(EXIT_FAILURE);
107
    } else if (pid < 0) {
108
        error_setg_errno(errp, errno, "failed to create child process");
109
        return;
110
    }
111

112
    ga_wait_child(pid, &status, &local_err);
113
    if (local_err) {
114
        error_propagate(errp, local_err);
115 116 117 118
        return;
    }

    if (!WIFEXITED(status)) {
119
        error_setg(errp, "child process has terminated abnormally");
120 121 122 123
        return;
    }

    if (WEXITSTATUS(status)) {
124
        error_setg(errp, "child process has failed to shutdown");
125 126 127
        return;
    }

P
Peter Maydell 已提交
128
    /* succeeded */
129 130
}

L
Lei Li 已提交
131 132 133 134 135 136 137 138 139 140 141
int64_t qmp_guest_get_time(Error **errp)
{
   int ret;
   qemu_timeval tq;

   ret = qemu_gettimeofday(&tq);
   if (ret < 0) {
       error_setg_errno(errp, errno, "Failed to get time");
       return -1;
   }

142
   return tq.tv_sec * 1000000000LL + tq.tv_usec * 1000;
L
Lei Li 已提交
143 144
}

145
void qmp_guest_set_time(bool has_time, int64_t time_ns, Error **errp)
L
Lei Li 已提交
146 147 148 149 150 151 152
{
    int ret;
    int status;
    pid_t pid;
    Error *local_err = NULL;
    struct timeval tv;

153 154
    /* If user has passed a time, validate and set it. */
    if (has_time) {
155 156
        GDate date = { 0, };

157 158 159 160 161 162 163 164
        /* year-2038 will overflow in case time_t is 32bit */
        if (time_ns / 1000000000 != (time_t)(time_ns / 1000000000)) {
            error_setg(errp, "Time %" PRId64 " is too large", time_ns);
            return;
        }

        tv.tv_sec = time_ns / 1000000000;
        tv.tv_usec = (time_ns % 1000000000) / 1000;
165 166 167 168 169
        g_date_set_time_t(&date, tv.tv_sec);
        if (date.year < 1970 || date.year >= 2070) {
            error_setg_errno(errp, errno, "Invalid time");
            return;
        }
170 171 172 173 174 175

        ret = settimeofday(&tv, NULL);
        if (ret < 0) {
            error_setg_errno(errp, errno, "Failed to set time to guest");
            return;
        }
L
Lei Li 已提交
176 177
    }

178 179 180
    /* Now, if user has passed a time to set and the system time is set, we
     * just need to synchronize the hardware clock. However, if no time was
     * passed, user is requesting the opposite: set the system time from the
181
     * hardware clock (RTC). */
L
Lei Li 已提交
182 183 184 185 186 187 188
    pid = fork();
    if (pid == 0) {
        setsid();
        reopen_fd_to_null(0);
        reopen_fd_to_null(1);
        reopen_fd_to_null(2);

189 190 191 192
        /* Use '/sbin/hwclock -w' to set RTC from the system time,
         * or '/sbin/hwclock -s' to set the system time from RTC. */
        execle("/sbin/hwclock", "hwclock", has_time ? "-w" : "-s",
               NULL, environ);
L
Lei Li 已提交
193 194 195 196 197 198 199
        _exit(EXIT_FAILURE);
    } else if (pid < 0) {
        error_setg_errno(errp, errno, "failed to create child process");
        return;
    }

    ga_wait_child(pid, &status, &local_err);
200
    if (local_err) {
L
Lei Li 已提交
201 202 203 204 205 206 207 208 209 210 211 212 213 214 215
        error_propagate(errp, local_err);
        return;
    }

    if (!WIFEXITED(status)) {
        error_setg(errp, "child process has terminated abnormally");
        return;
    }

    if (WEXITSTATUS(status)) {
        error_setg(errp, "hwclock failed to set hardware clock to system time");
        return;
    }
}

216 217 218 219 220 221
typedef enum {
    RW_STATE_NEW,
    RW_STATE_READING,
    RW_STATE_WRITING,
} RwState;

222 223 224
typedef struct GuestFileHandle {
    uint64_t id;
    FILE *fh;
225
    RwState state;
226 227 228 229 230
    QTAILQ_ENTRY(GuestFileHandle) next;
} GuestFileHandle;

static struct {
    QTAILQ_HEAD(, GuestFileHandle) filehandles;
231 232 233
} guest_file_state = {
    .filehandles = QTAILQ_HEAD_INITIALIZER(guest_file_state.filehandles),
};
234

235
static int64_t guest_file_handle_add(FILE *fh, Error **errp)
236 237
{
    GuestFileHandle *gfh;
238 239 240
    int64_t handle;

    handle = ga_get_fd_handle(ga_state, errp);
241 242
    if (handle < 0) {
        return -1;
243
    }
244

245
    gfh = g_new0(GuestFileHandle, 1);
246
    gfh->id = handle;
247 248
    gfh->fh = fh;
    QTAILQ_INSERT_TAIL(&guest_file_state.filehandles, gfh, next);
249 250

    return handle;
251 252
}

253
static GuestFileHandle *guest_file_handle_find(int64_t id, Error **errp)
254 255 256 257 258 259 260 261 262 263
{
    GuestFileHandle *gfh;

    QTAILQ_FOREACH(gfh, &guest_file_state.filehandles, next)
    {
        if (gfh->id == id) {
            return gfh;
        }
    }

264
    error_setg(errp, "handle '%" PRId64 "' has not been found", id);
265 266 267
    return NULL;
}

268 269
typedef const char * const ccpc;

270 271 272 273
#ifndef O_BINARY
#define O_BINARY 0
#endif

274 275 276 277 278
/* http://pubs.opengroup.org/onlinepubs/9699919799/functions/fopen.html */
static const struct {
    ccpc *forms;
    int oflag_base;
} guest_file_open_modes[] = {
279 280 281 282 283 284 285 286 287 288 289 290
    { (ccpc[]){ "r",          NULL }, O_RDONLY                                 },
    { (ccpc[]){ "rb",         NULL }, O_RDONLY                      | O_BINARY },
    { (ccpc[]){ "w",          NULL }, O_WRONLY | O_CREAT | O_TRUNC             },
    { (ccpc[]){ "wb",         NULL }, O_WRONLY | O_CREAT | O_TRUNC  | O_BINARY },
    { (ccpc[]){ "a",          NULL }, O_WRONLY | O_CREAT | O_APPEND            },
    { (ccpc[]){ "ab",         NULL }, O_WRONLY | O_CREAT | O_APPEND | O_BINARY },
    { (ccpc[]){ "r+",         NULL }, O_RDWR                                   },
    { (ccpc[]){ "rb+", "r+b", NULL }, O_RDWR                        | O_BINARY },
    { (ccpc[]){ "w+",         NULL }, O_RDWR   | O_CREAT | O_TRUNC             },
    { (ccpc[]){ "wb+", "w+b", NULL }, O_RDWR   | O_CREAT | O_TRUNC  | O_BINARY },
    { (ccpc[]){ "a+",         NULL }, O_RDWR   | O_CREAT | O_APPEND            },
    { (ccpc[]){ "ab+", "a+b", NULL }, O_RDWR   | O_CREAT | O_APPEND | O_BINARY }
291 292 293
};

static int
294
find_open_flag(const char *mode_str, Error **errp)
295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310
{
    unsigned mode;

    for (mode = 0; mode < ARRAY_SIZE(guest_file_open_modes); ++mode) {
        ccpc *form;

        form = guest_file_open_modes[mode].forms;
        while (*form != NULL && strcmp(*form, mode_str) != 0) {
            ++form;
        }
        if (*form != NULL) {
            break;
        }
    }

    if (mode == ARRAY_SIZE(guest_file_open_modes)) {
311
        error_setg(errp, "invalid file open mode '%s'", mode_str);
312 313 314 315 316 317 318 319 320 321
        return -1;
    }
    return guest_file_open_modes[mode].oflag_base | O_NOCTTY | O_NONBLOCK;
}

#define DEFAULT_NEW_FILE_MODE (S_IRUSR | S_IWUSR | \
                               S_IRGRP | S_IWGRP | \
                               S_IROTH | S_IWOTH)

static FILE *
322
safe_open_or_create(const char *path, const char *mode, Error **errp)
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
{
    Error *local_err = NULL;
    int oflag;

    oflag = find_open_flag(mode, &local_err);
    if (local_err == NULL) {
        int fd;

        /* If the caller wants / allows creation of a new file, we implement it
         * with a two step process: open() + (open() / fchmod()).
         *
         * First we insist on creating the file exclusively as a new file. If
         * that succeeds, we're free to set any file-mode bits on it. (The
         * motivation is that we want to set those file-mode bits independently
         * of the current umask.)
         *
         * If the exclusive creation fails because the file already exists
         * (EEXIST is not possible for any other reason), we just attempt to
         * open the file, but in this case we won't be allowed to change the
         * file-mode bits on the preexistent file.
         *
         * The pathname should never disappear between the two open()s in
         * practice. If it happens, then someone very likely tried to race us.
         * In this case just go ahead and report the ENOENT from the second
         * open() to the caller.
         *
         * If the caller wants to open a preexistent file, then the first
         * open() is decisive and its third argument is ignored, and the second
         * open() and the fchmod() are never called.
         */
        fd = open(path, oflag | ((oflag & O_CREAT) ? O_EXCL : 0), 0);
        if (fd == -1 && errno == EEXIST) {
            oflag &= ~(unsigned)O_CREAT;
            fd = open(path, oflag);
        }

        if (fd == -1) {
            error_setg_errno(&local_err, errno, "failed to open file '%s' "
                             "(mode: '%s')", path, mode);
        } else {
            qemu_set_cloexec(fd);

            if ((oflag & O_CREAT) && fchmod(fd, DEFAULT_NEW_FILE_MODE) == -1) {
                error_setg_errno(&local_err, errno, "failed to set permission "
                                 "0%03o on new file '%s' (mode: '%s')",
                                 (unsigned)DEFAULT_NEW_FILE_MODE, path, mode);
            } else {
                FILE *f;

                f = fdopen(fd, mode);
                if (f == NULL) {
                    error_setg_errno(&local_err, errno, "failed to associate "
                                     "stdio stream with file descriptor %d, "
                                     "file '%s' (mode: '%s')", fd, path, mode);
                } else {
                    return f;
                }
            }

            close(fd);
383 384 385
            if (oflag & O_CREAT) {
                unlink(path);
            }
386 387 388
        }
    }

389
    error_propagate(errp, local_err);
390 391 392
    return NULL;
}

393 394
int64_t qmp_guest_file_open(const char *path, bool has_mode, const char *mode,
                            Error **errp)
395 396
{
    FILE *fh;
397
    Error *local_err = NULL;
398
    int64_t handle;
399 400 401 402 403

    if (!has_mode) {
        mode = "r";
    }
    slog("guest-file-open called, filepath: %s, mode: %s", path, mode);
404 405
    fh = safe_open_or_create(path, mode, &local_err);
    if (local_err != NULL) {
406
        error_propagate(errp, local_err);
407 408 409 410 411 412
        return -1;
    }

    /* set fd non-blocking to avoid common use cases (like reading from a
     * named pipe) from hanging the agent
     */
413
    qemu_set_nonblock(fileno(fh));
414

415
    handle = guest_file_handle_add(fh, errp);
416
    if (handle < 0) {
417 418 419 420
        fclose(fh);
        return -1;
    }

421
    slog("guest-file-open, handle: %" PRId64, handle);
422
    return handle;
423 424
}

425
void qmp_guest_file_close(int64_t handle, Error **errp)
426
{
427
    GuestFileHandle *gfh = guest_file_handle_find(handle, errp);
428 429
    int ret;

430
    slog("guest-file-close called, handle: %" PRId64, handle);
431 432 433 434 435
    if (!gfh) {
        return;
    }

    ret = fclose(gfh->fh);
436
    if (ret == EOF) {
437
        error_setg_errno(errp, errno, "failed to close handle");
438 439 440 441
        return;
    }

    QTAILQ_REMOVE(&guest_file_state.filehandles, gfh, next);
442
    g_free(gfh);
443 444 445
}

struct GuestFileRead *qmp_guest_file_read(int64_t handle, bool has_count,
446
                                          int64_t count, Error **errp)
447
{
448
    GuestFileHandle *gfh = guest_file_handle_find(handle, errp);
449 450 451 452 453 454 455 456 457 458 459 460
    GuestFileRead *read_data = NULL;
    guchar *buf;
    FILE *fh;
    size_t read_count;

    if (!gfh) {
        return NULL;
    }

    if (!has_count) {
        count = QGA_READ_COUNT_DEFAULT;
    } else if (count < 0) {
461
        error_setg(errp, "value '%" PRId64 "' is invalid for argument count",
462
                   count);
463 464 465 466
        return NULL;
    }

    fh = gfh->fh;
467 468 469 470 471 472 473 474 475 476 477

    /* explicitly flush when switching from writing to reading */
    if (gfh->state == RW_STATE_WRITING) {
        int ret = fflush(fh);
        if (ret == EOF) {
            error_setg_errno(errp, errno, "failed to flush file");
            return NULL;
        }
        gfh->state = RW_STATE_NEW;
    }

478
    buf = g_malloc0(count+1);
479 480
    read_count = fread(buf, 1, count, fh);
    if (ferror(fh)) {
481
        error_setg_errno(errp, errno, "failed to read file");
482
        slog("guest-file-read failed, handle: %" PRId64, handle);
483 484
    } else {
        buf[read_count] = 0;
485
        read_data = g_new0(GuestFileRead, 1);
486 487 488 489 490
        read_data->count = read_count;
        read_data->eof = feof(fh);
        if (read_count) {
            read_data->buf_b64 = g_base64_encode(buf, read_count);
        }
491
        gfh->state = RW_STATE_READING;
492
    }
493
    g_free(buf);
494 495 496 497 498 499
    clearerr(fh);

    return read_data;
}

GuestFileWrite *qmp_guest_file_write(int64_t handle, const char *buf_b64,
500 501
                                     bool has_count, int64_t count,
                                     Error **errp)
502 503 504 505 506
{
    GuestFileWrite *write_data = NULL;
    guchar *buf;
    gsize buf_len;
    int write_count;
507
    GuestFileHandle *gfh = guest_file_handle_find(handle, errp);
508 509 510 511 512 513 514
    FILE *fh;

    if (!gfh) {
        return NULL;
    }

    fh = gfh->fh;
515 516 517 518 519 520 521 522 523 524

    if (gfh->state == RW_STATE_READING) {
        int ret = fseek(fh, 0, SEEK_CUR);
        if (ret == -1) {
            error_setg_errno(errp, errno, "failed to seek file");
            return NULL;
        }
        gfh->state = RW_STATE_NEW;
    }

525 526 527 528
    buf = qbase64_decode(buf_b64, -1, &buf_len, errp);
    if (!buf) {
        return NULL;
    }
529 530 531 532

    if (!has_count) {
        count = buf_len;
    } else if (count < 0 || count > buf_len) {
533
        error_setg(errp, "value '%" PRId64 "' is invalid for argument count",
534
                   count);
535
        g_free(buf);
536 537 538 539 540
        return NULL;
    }

    write_count = fwrite(buf, 1, count, fh);
    if (ferror(fh)) {
541
        error_setg_errno(errp, errno, "failed to write to file");
542
        slog("guest-file-write failed, handle: %" PRId64, handle);
543
    } else {
544
        write_data = g_new0(GuestFileWrite, 1);
545 546
        write_data->count = write_count;
        write_data->eof = feof(fh);
547
        gfh->state = RW_STATE_WRITING;
548
    }
549
    g_free(buf);
550 551 552 553 554 555
    clearerr(fh);

    return write_data;
}

struct GuestFileSeek *qmp_guest_file_seek(int64_t handle, int64_t offset,
556 557
                                          GuestFileWhence *whence_code,
                                          Error **errp)
558
{
559
    GuestFileHandle *gfh = guest_file_handle_find(handle, errp);
560 561 562
    GuestFileSeek *seek_data = NULL;
    FILE *fh;
    int ret;
563
    int whence;
564
    Error *err = NULL;
565 566 567 568 569

    if (!gfh) {
        return NULL;
    }

570
    /* We stupidly exposed 'whence':'int' in our qapi */
571 572 573
    whence = ga_parse_whence(whence_code, &err);
    if (err) {
        error_propagate(errp, err);
574 575 576
        return NULL;
    }

577 578 579
    fh = gfh->fh;
    ret = fseek(fh, offset, whence);
    if (ret == -1) {
580
        error_setg_errno(errp, errno, "failed to seek file");
581 582 583 584
        if (errno == ESPIPE) {
            /* file is non-seekable, stdio shouldn't be buffering anyways */
            gfh->state = RW_STATE_NEW;
        }
585
    } else {
586
        seek_data = g_new0(GuestFileSeek, 1);
587 588
        seek_data->position = ftell(fh);
        seek_data->eof = feof(fh);
589
        gfh->state = RW_STATE_NEW;
590 591 592 593 594 595
    }
    clearerr(fh);

    return seek_data;
}

596
void qmp_guest_file_flush(int64_t handle, Error **errp)
597
{
598
    GuestFileHandle *gfh = guest_file_handle_find(handle, errp);
599 600 601 602 603 604 605 606 607 608
    FILE *fh;
    int ret;

    if (!gfh) {
        return;
    }

    fh = gfh->fh;
    ret = fflush(fh);
    if (ret == EOF) {
609
        error_setg_errno(errp, errno, "failed to flush file");
610 611
    } else {
        gfh->state = RW_STATE_NEW;
612 613 614
    }
}

615 616 617
/* linux-specific implementations. avoid this if at all possible. */
#if defined(__linux__)

618
#if defined(CONFIG_FSFREEZE) || defined(CONFIG_FSTRIM)
619
typedef struct FsMount {
620 621
    char *dirname;
    char *devtype;
622
    unsigned int devmajor, devminor;
623 624
    QTAILQ_ENTRY(FsMount) next;
} FsMount;
625

626
typedef QTAILQ_HEAD(FsMountList, FsMount) FsMountList;
627

628
static void free_fs_mount_list(FsMountList *mounts)
629
{
630
     FsMount *mount, *temp;
631 632 633 634 635 636 637 638 639 640 641 642 643

     if (!mounts) {
         return;
     }

     QTAILQ_FOREACH_SAFE(mount, mounts, next, temp) {
         QTAILQ_REMOVE(mounts, mount, next);
         g_free(mount->dirname);
         g_free(mount->devtype);
         g_free(mount);
     }
}

644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667
static int dev_major_minor(const char *devpath,
                           unsigned int *devmajor, unsigned int *devminor)
{
    struct stat st;

    *devmajor = 0;
    *devminor = 0;

    if (stat(devpath, &st) < 0) {
        slog("failed to stat device file '%s': %s", devpath, strerror(errno));
        return -1;
    }
    if (S_ISDIR(st.st_mode)) {
        /* It is bind mount */
        return -2;
    }
    if (S_ISBLK(st.st_mode)) {
        *devmajor = major(st.st_rdev);
        *devminor = minor(st.st_rdev);
        return 0;
    }
    return -1;
}

668 669 670
/*
 * Walk the mount table and build a list of local file systems
 */
671
static void build_fs_mount_list_from_mtab(FsMountList *mounts, Error **errp)
672 673
{
    struct mntent *ment;
674
    FsMount *mount;
675
    char const *mtab = "/proc/self/mounts";
676
    FILE *fp;
677
    unsigned int devmajor, devminor;
678 679 680

    fp = setmntent(mtab, "r");
    if (!fp) {
681
        error_setg(errp, "failed to open mtab file: '%s'", mtab);
682
        return;
683 684 685 686 687 688 689 690 691 692 693 694 695 696
    }

    while ((ment = getmntent(fp))) {
        /*
         * An entry which device name doesn't start with a '/' is
         * either a dummy file system or a network file system.
         * Add special handling for smbfs and cifs as is done by
         * coreutils as well.
         */
        if ((ment->mnt_fsname[0] != '/') ||
            (strcmp(ment->mnt_type, "smbfs") == 0) ||
            (strcmp(ment->mnt_type, "cifs") == 0)) {
            continue;
        }
697 698 699 700
        if (dev_major_minor(ment->mnt_fsname, &devmajor, &devminor) == -2) {
            /* Skip bind mounts */
            continue;
        }
701

702
        mount = g_new0(FsMount, 1);
703 704
        mount->dirname = g_strdup(ment->mnt_dir);
        mount->devtype = g_strdup(ment->mnt_type);
705 706
        mount->devmajor = devmajor;
        mount->devminor = devminor;
707

708
        QTAILQ_INSERT_TAIL(mounts, mount, next);
709 710 711 712
    }

    endmntent(fp);
}
713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780

static void decode_mntname(char *name, int len)
{
    int i, j = 0;
    for (i = 0; i <= len; i++) {
        if (name[i] != '\\') {
            name[j++] = name[i];
        } else if (name[i + 1] == '\\') {
            name[j++] = '\\';
            i++;
        } else if (name[i + 1] >= '0' && name[i + 1] <= '3' &&
                   name[i + 2] >= '0' && name[i + 2] <= '7' &&
                   name[i + 3] >= '0' && name[i + 3] <= '7') {
            name[j++] = (name[i + 1] - '0') * 64 +
                        (name[i + 2] - '0') * 8 +
                        (name[i + 3] - '0');
            i += 3;
        } else {
            name[j++] = name[i];
        }
    }
}

static void build_fs_mount_list(FsMountList *mounts, Error **errp)
{
    FsMount *mount;
    char const *mountinfo = "/proc/self/mountinfo";
    FILE *fp;
    char *line = NULL, *dash;
    size_t n;
    char check;
    unsigned int devmajor, devminor;
    int ret, dir_s, dir_e, type_s, type_e, dev_s, dev_e;

    fp = fopen(mountinfo, "r");
    if (!fp) {
        build_fs_mount_list_from_mtab(mounts, errp);
        return;
    }

    while (getline(&line, &n, fp) != -1) {
        ret = sscanf(line, "%*u %*u %u:%u %*s %n%*s%n%c",
                     &devmajor, &devminor, &dir_s, &dir_e, &check);
        if (ret < 3) {
            continue;
        }
        dash = strstr(line + dir_e, " - ");
        if (!dash) {
            continue;
        }
        ret = sscanf(dash, " - %n%*s%n %n%*s%n%c",
                     &type_s, &type_e, &dev_s, &dev_e, &check);
        if (ret < 1) {
            continue;
        }
        line[dir_e] = 0;
        dash[type_e] = 0;
        dash[dev_e] = 0;
        decode_mntname(line + dir_s, dir_e - dir_s);
        decode_mntname(dash + dev_s, dev_e - dev_s);
        if (devmajor == 0) {
            /* btrfs reports major number = 0 */
            if (strcmp("btrfs", dash + type_s) != 0 ||
                dev_major_minor(dash + dev_s, &devmajor, &devminor) < 0) {
                continue;
            }
        }

781
        mount = g_new0(FsMount, 1);
782 783 784 785 786 787 788 789 790 791 792
        mount->dirname = g_strdup(line + dir_s);
        mount->devtype = g_strdup(dash + type_s);
        mount->devmajor = devmajor;
        mount->devminor = devminor;

        QTAILQ_INSERT_TAIL(mounts, mount, next);
    }
    free(line);

    fclose(fp);
}
793 794 795
#endif

#if defined(CONFIG_FSFREEZE)
796

797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001
static char *get_pci_driver(char const *syspath, int pathlen, Error **errp)
{
    char *path;
    char *dpath;
    char *driver = NULL;
    char buf[PATH_MAX];
    ssize_t len;

    path = g_strndup(syspath, pathlen);
    dpath = g_strdup_printf("%s/driver", path);
    len = readlink(dpath, buf, sizeof(buf) - 1);
    if (len != -1) {
        buf[len] = 0;
        driver = g_strdup(basename(buf));
    }
    g_free(dpath);
    g_free(path);
    return driver;
}

static int compare_uint(const void *_a, const void *_b)
{
    unsigned int a = *(unsigned int *)_a;
    unsigned int b = *(unsigned int *)_b;

    return a < b ? -1 : a > b ? 1 : 0;
}

/* Walk the specified sysfs and build a sorted list of host or ata numbers */
static int build_hosts(char const *syspath, char const *host, bool ata,
                       unsigned int *hosts, int hosts_max, Error **errp)
{
    char *path;
    DIR *dir;
    struct dirent *entry;
    int i = 0;

    path = g_strndup(syspath, host - syspath);
    dir = opendir(path);
    if (!dir) {
        error_setg_errno(errp, errno, "opendir(\"%s\")", path);
        g_free(path);
        return -1;
    }

    while (i < hosts_max) {
        entry = readdir(dir);
        if (!entry) {
            break;
        }
        if (ata && sscanf(entry->d_name, "ata%d", hosts + i) == 1) {
            ++i;
        } else if (!ata && sscanf(entry->d_name, "host%d", hosts + i) == 1) {
            ++i;
        }
    }

    qsort(hosts, i, sizeof(hosts[0]), compare_uint);

    g_free(path);
    closedir(dir);
    return i;
}

/* Store disk device info specified by @sysfs into @fs */
static void build_guest_fsinfo_for_real_device(char const *syspath,
                                               GuestFilesystemInfo *fs,
                                               Error **errp)
{
    unsigned int pci[4], host, hosts[8], tgt[3];
    int i, nhosts = 0, pcilen;
    GuestDiskAddress *disk;
    GuestPCIAddress *pciaddr;
    GuestDiskAddressList *list = NULL;
    bool has_ata = false, has_host = false, has_tgt = false;
    char *p, *q, *driver = NULL;

    p = strstr(syspath, "/devices/pci");
    if (!p || sscanf(p + 12, "%*x:%*x/%x:%x:%x.%x%n",
                     pci, pci + 1, pci + 2, pci + 3, &pcilen) < 4) {
        g_debug("only pci device is supported: sysfs path \"%s\"", syspath);
        return;
    }

    driver = get_pci_driver(syspath, (p + 12 + pcilen) - syspath, errp);
    if (!driver) {
        goto cleanup;
    }

    p = strstr(syspath, "/target");
    if (p && sscanf(p + 7, "%*u:%*u:%*u/%*u:%u:%u:%u",
                    tgt, tgt + 1, tgt + 2) == 3) {
        has_tgt = true;
    }

    p = strstr(syspath, "/ata");
    if (p) {
        q = p + 4;
        has_ata = true;
    } else {
        p = strstr(syspath, "/host");
        q = p + 5;
    }
    if (p && sscanf(q, "%u", &host) == 1) {
        has_host = true;
        nhosts = build_hosts(syspath, p, has_ata, hosts,
                             sizeof(hosts) / sizeof(hosts[0]), errp);
        if (nhosts < 0) {
            goto cleanup;
        }
    }

    pciaddr = g_malloc0(sizeof(*pciaddr));
    pciaddr->domain = pci[0];
    pciaddr->bus = pci[1];
    pciaddr->slot = pci[2];
    pciaddr->function = pci[3];

    disk = g_malloc0(sizeof(*disk));
    disk->pci_controller = pciaddr;

    list = g_malloc0(sizeof(*list));
    list->value = disk;

    if (strcmp(driver, "ata_piix") == 0) {
        /* a host per ide bus, target*:0:<unit>:0 */
        if (!has_host || !has_tgt) {
            g_debug("invalid sysfs path '%s' (driver '%s')", syspath, driver);
            goto cleanup;
        }
        for (i = 0; i < nhosts; i++) {
            if (host == hosts[i]) {
                disk->bus_type = GUEST_DISK_BUS_TYPE_IDE;
                disk->bus = i;
                disk->unit = tgt[1];
                break;
            }
        }
        if (i >= nhosts) {
            g_debug("no host for '%s' (driver '%s')", syspath, driver);
            goto cleanup;
        }
    } else if (strcmp(driver, "sym53c8xx") == 0) {
        /* scsi(LSI Logic): target*:0:<unit>:0 */
        if (!has_tgt) {
            g_debug("invalid sysfs path '%s' (driver '%s')", syspath, driver);
            goto cleanup;
        }
        disk->bus_type = GUEST_DISK_BUS_TYPE_SCSI;
        disk->unit = tgt[1];
    } else if (strcmp(driver, "virtio-pci") == 0) {
        if (has_tgt) {
            /* virtio-scsi: target*:0:0:<unit> */
            disk->bus_type = GUEST_DISK_BUS_TYPE_SCSI;
            disk->unit = tgt[2];
        } else {
            /* virtio-blk: 1 disk per 1 device */
            disk->bus_type = GUEST_DISK_BUS_TYPE_VIRTIO;
        }
    } else if (strcmp(driver, "ahci") == 0) {
        /* ahci: 1 host per 1 unit */
        if (!has_host || !has_tgt) {
            g_debug("invalid sysfs path '%s' (driver '%s')", syspath, driver);
            goto cleanup;
        }
        for (i = 0; i < nhosts; i++) {
            if (host == hosts[i]) {
                disk->unit = i;
                disk->bus_type = GUEST_DISK_BUS_TYPE_SATA;
                break;
            }
        }
        if (i >= nhosts) {
            g_debug("no host for '%s' (driver '%s')", syspath, driver);
            goto cleanup;
        }
    } else {
        g_debug("unknown driver '%s' (sysfs path '%s')", driver, syspath);
        goto cleanup;
    }

    list->next = fs->disk;
    fs->disk = list;
    g_free(driver);
    return;

cleanup:
    if (list) {
        qapi_free_GuestDiskAddressList(list);
    }
    g_free(driver);
}

static void build_guest_fsinfo_for_device(char const *devpath,
                                          GuestFilesystemInfo *fs,
                                          Error **errp);

/* Store a list of slave devices of virtual volume specified by @syspath into
 * @fs */
static void build_guest_fsinfo_for_virtual_device(char const *syspath,
                                                  GuestFilesystemInfo *fs,
                                                  Error **errp)
{
    DIR *dir;
    char *dirpath;
1002
    struct dirent *entry;
1003 1004 1005 1006

    dirpath = g_strdup_printf("%s/slaves", syspath);
    dir = opendir(dirpath);
    if (!dir) {
1007 1008 1009
        if (errno != ENOENT) {
            error_setg_errno(errp, errno, "opendir(\"%s\")", dirpath);
        }
1010 1011 1012 1013 1014
        g_free(dirpath);
        return;
    }

    for (;;) {
1015 1016 1017 1018 1019 1020
        errno = 0;
        entry = readdir(dir);
        if (entry == NULL) {
            if (errno) {
                error_setg_errno(errp, errno, "readdir(\"%s\")", dirpath);
            }
1021 1022 1023
            break;
        }

1024 1025 1026 1027 1028 1029 1030
        if (entry->d_type == DT_LNK) {
            char *path;

            g_debug(" slave device '%s'", entry->d_name);
            path = g_strdup_printf("%s/slaves/%s", syspath, entry->d_name);
            build_guest_fsinfo_for_device(path, fs, errp);
            g_free(path);
1031 1032 1033 1034 1035 1036 1037

            if (*errp) {
                break;
            }
        }
    }

1038
    g_free(dirpath);
1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118
    closedir(dir);
}

/* Dispatch to functions for virtual/real device */
static void build_guest_fsinfo_for_device(char const *devpath,
                                          GuestFilesystemInfo *fs,
                                          Error **errp)
{
    char *syspath = realpath(devpath, NULL);

    if (!syspath) {
        error_setg_errno(errp, errno, "realpath(\"%s\")", devpath);
        return;
    }

    if (!fs->name) {
        fs->name = g_strdup(basename(syspath));
    }

    g_debug("  parse sysfs path '%s'", syspath);

    if (strstr(syspath, "/devices/virtual/block/")) {
        build_guest_fsinfo_for_virtual_device(syspath, fs, errp);
    } else {
        build_guest_fsinfo_for_real_device(syspath, fs, errp);
    }

    free(syspath);
}

/* Return a list of the disk device(s)' info which @mount lies on */
static GuestFilesystemInfo *build_guest_fsinfo(struct FsMount *mount,
                                               Error **errp)
{
    GuestFilesystemInfo *fs = g_malloc0(sizeof(*fs));
    char *devpath = g_strdup_printf("/sys/dev/block/%u:%u",
                                    mount->devmajor, mount->devminor);

    fs->mountpoint = g_strdup(mount->dirname);
    fs->type = g_strdup(mount->devtype);
    build_guest_fsinfo_for_device(devpath, fs, errp);

    g_free(devpath);
    return fs;
}

GuestFilesystemInfoList *qmp_guest_get_fsinfo(Error **errp)
{
    FsMountList mounts;
    struct FsMount *mount;
    GuestFilesystemInfoList *new, *ret = NULL;
    Error *local_err = NULL;

    QTAILQ_INIT(&mounts);
    build_fs_mount_list(&mounts, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        return NULL;
    }

    QTAILQ_FOREACH(mount, &mounts, next) {
        g_debug("Building guest fsinfo for '%s'", mount->dirname);

        new = g_malloc0(sizeof(*ret));
        new->value = build_guest_fsinfo(mount, &local_err);
        new->next = ret;
        ret = new;
        if (local_err) {
            error_propagate(errp, local_err);
            qapi_free_GuestFilesystemInfoList(ret);
            ret = NULL;
            break;
        }
    }

    free_fs_mount_list(&mounts);
    return ret;
}


1119 1120 1121 1122 1123
typedef enum {
    FSFREEZE_HOOK_THAW = 0,
    FSFREEZE_HOOK_FREEZE,
} FsfreezeHookArg;

1124
static const char *fsfreeze_hook_arg_string[] = {
1125 1126 1127 1128
    "thaw",
    "freeze",
};

1129
static void execute_fsfreeze_hook(FsfreezeHookArg arg, Error **errp)
1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141
{
    int status;
    pid_t pid;
    const char *hook;
    const char *arg_str = fsfreeze_hook_arg_string[arg];
    Error *local_err = NULL;

    hook = ga_fsfreeze_hook(ga_state);
    if (!hook) {
        return;
    }
    if (access(hook, X_OK) != 0) {
1142
        error_setg_errno(errp, errno, "can't access fsfreeze hook '%s'", hook);
1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156
        return;
    }

    slog("executing fsfreeze hook with arg '%s'", arg_str);
    pid = fork();
    if (pid == 0) {
        setsid();
        reopen_fd_to_null(0);
        reopen_fd_to_null(1);
        reopen_fd_to_null(2);

        execle(hook, hook, arg_str, NULL, environ);
        _exit(EXIT_FAILURE);
    } else if (pid < 0) {
1157
        error_setg_errno(errp, errno, "failed to create child process");
1158 1159 1160 1161
        return;
    }

    ga_wait_child(pid, &status, &local_err);
1162
    if (local_err) {
1163
        error_propagate(errp, local_err);
1164 1165 1166 1167
        return;
    }

    if (!WIFEXITED(status)) {
1168
        error_setg(errp, "fsfreeze hook has terminated abnormally");
1169 1170 1171 1172 1173
        return;
    }

    status = WEXITSTATUS(status);
    if (status) {
1174
        error_setg(errp, "fsfreeze hook has failed with status %d", status);
1175 1176 1177 1178
        return;
    }
}

1179 1180 1181
/*
 * Return status of freeze/thaw
 */
1182
GuestFsfreezeStatus qmp_guest_fsfreeze_status(Error **errp)
1183
{
1184 1185 1186 1187 1188
    if (ga_is_frozen(ga_state)) {
        return GUEST_FSFREEZE_STATUS_FROZEN;
    }

    return GUEST_FSFREEZE_STATUS_THAWED;
1189 1190
}

1191 1192 1193 1194 1195
int64_t qmp_guest_fsfreeze_freeze(Error **errp)
{
    return qmp_guest_fsfreeze_freeze_list(false, NULL, errp);
}

1196 1197 1198 1199
/*
 * Walk list of mounted file systems in the guest, and freeze the ones which
 * are real local file systems.
 */
1200 1201 1202
int64_t qmp_guest_fsfreeze_freeze_list(bool has_mountpoints,
                                       strList *mountpoints,
                                       Error **errp)
1203 1204
{
    int ret = 0, i = 0;
1205
    strList *list;
1206 1207
    FsMountList mounts;
    struct FsMount *mount;
1208
    Error *local_err = NULL;
1209 1210 1211 1212
    int fd;

    slog("guest-fsfreeze called");

1213
    execute_fsfreeze_hook(FSFREEZE_HOOK_FREEZE, &local_err);
1214
    if (local_err) {
1215
        error_propagate(errp, local_err);
1216 1217 1218
        return -1;
    }

1219
    QTAILQ_INIT(&mounts);
1220
    build_fs_mount_list(&mounts, &local_err);
1221
    if (local_err) {
1222
        error_propagate(errp, local_err);
1223
        return -1;
1224 1225 1226
    }

    /* cannot risk guest agent blocking itself on a write in this state */
1227
    ga_set_frozen(ga_state);
1228

1229
    QTAILQ_FOREACH_REVERSE(mount, &mounts, FsMountList, next) {
1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242
        /* To issue fsfreeze in the reverse order of mounts, check if the
         * mount is listed in the list here */
        if (has_mountpoints) {
            for (list = mountpoints; list; list = list->next) {
                if (strcmp(list->value, mount->dirname) == 0) {
                    break;
                }
            }
            if (!list) {
                continue;
            }
        }

1243 1244
        fd = qemu_open(mount->dirname, O_RDONLY);
        if (fd == -1) {
1245
            error_setg_errno(errp, errno, "failed to open %s", mount->dirname);
1246 1247 1248
            goto error;
        }

M
Michael Tokarev 已提交
1249 1250
        /* we try to cull filesystems we know won't work in advance, but other
         * filesystems may not implement fsfreeze for less obvious reasons.
1251 1252
         * these will report EOPNOTSUPP. we simply ignore these when tallying
         * the number of frozen filesystems.
1253 1254 1255
         * if a filesystem is mounted more than once (aka bind mount) a
         * consecutive attempt to freeze an already frozen filesystem will
         * return EBUSY.
1256 1257 1258 1259
         *
         * any other error means a failure to freeze a filesystem we
         * expect to be freezable, so return an error in those cases
         * and return system to thawed state.
1260 1261
         */
        ret = ioctl(fd, FIFREEZE);
1262
        if (ret == -1) {
1263
            if (errno != EOPNOTSUPP && errno != EBUSY) {
1264
                error_setg_errno(errp, errno, "failed to freeze %s",
1265
                                 mount->dirname);
1266 1267 1268 1269 1270
                close(fd);
                goto error;
            }
        } else {
            i++;
1271 1272 1273 1274
        }
        close(fd);
    }

1275
    free_fs_mount_list(&mounts);
1276 1277 1278
    return i;

error:
1279
    free_fs_mount_list(&mounts);
1280
    qmp_guest_fsfreeze_thaw(NULL);
1281 1282 1283 1284 1285 1286
    return 0;
}

/*
 * Walk list of frozen file systems in the guest, and thaw them.
 */
1287
int64_t qmp_guest_fsfreeze_thaw(Error **errp)
1288 1289
{
    int ret;
1290 1291
    FsMountList mounts;
    FsMount *mount;
1292
    int fd, i = 0, logged;
1293
    Error *local_err = NULL;
1294 1295

    QTAILQ_INIT(&mounts);
1296
    build_fs_mount_list(&mounts, &local_err);
1297
    if (local_err) {
1298
        error_propagate(errp, local_err);
1299 1300
        return 0;
    }
1301

1302 1303
    QTAILQ_FOREACH(mount, &mounts, next) {
        logged = false;
1304 1305 1306 1307
        fd = qemu_open(mount->dirname, O_RDONLY);
        if (fd == -1) {
            continue;
        }
1308 1309 1310 1311 1312
        /* we have no way of knowing whether a filesystem was actually unfrozen
         * as a result of a successful call to FITHAW, only that if an error
         * was returned the filesystem was *not* unfrozen by that particular
         * call.
         *
J
Jim Meyering 已提交
1313
         * since multiple preceding FIFREEZEs require multiple calls to FITHAW
1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330
         * to unfreeze, continuing issuing FITHAW until an error is returned,
         * in which case either the filesystem is in an unfreezable state, or,
         * more likely, it was thawed previously (and remains so afterward).
         *
         * also, since the most recent successful call is the one that did
         * the actual unfreeze, we can use this to provide an accurate count
         * of the number of filesystems unfrozen by guest-fsfreeze-thaw, which
         * may * be useful for determining whether a filesystem was unfrozen
         * during the freeze/thaw phase by a process other than qemu-ga.
         */
        do {
            ret = ioctl(fd, FITHAW);
            if (ret == 0 && !logged) {
                i++;
                logged = true;
            }
        } while (ret == 0);
1331 1332 1333
        close(fd);
    }

1334
    ga_unset_frozen(ga_state);
1335
    free_fs_mount_list(&mounts);
1336

1337
    execute_fsfreeze_hook(FSFREEZE_HOOK_THAW, errp);
1338

1339 1340 1341 1342 1343 1344 1345
    return i;
}

static void guest_fsfreeze_cleanup(void)
{
    Error *err = NULL;

1346
    if (ga_is_frozen(ga_state) == GUEST_FSFREEZE_STATUS_FROZEN) {
1347 1348 1349 1350 1351
        qmp_guest_fsfreeze_thaw(&err);
        if (err) {
            slog("failed to clean up frozen filesystems: %s",
                 error_get_pretty(err));
            error_free(err);
1352 1353 1354
        }
    }
}
1355
#endif /* CONFIG_FSFREEZE */
1356

1357 1358 1359 1360
#if defined(CONFIG_FSTRIM)
/*
 * Walk list of mounted file systems in the guest, and trim them.
 */
1361 1362
GuestFilesystemTrimResponse *
qmp_guest_fstrim(bool has_minimum, int64_t minimum, Error **errp)
1363
{
1364 1365 1366
    GuestFilesystemTrimResponse *response;
    GuestFilesystemTrimResultList *list;
    GuestFilesystemTrimResult *result;
1367 1368 1369 1370
    int ret = 0;
    FsMountList mounts;
    struct FsMount *mount;
    int fd;
1371
    Error *local_err = NULL;
1372
    struct fstrim_range r;
1373 1374 1375 1376

    slog("guest-fstrim called");

    QTAILQ_INIT(&mounts);
1377
    build_fs_mount_list(&mounts, &local_err);
1378
    if (local_err) {
1379
        error_propagate(errp, local_err);
1380
        return NULL;
1381 1382
    }

1383 1384
    response = g_malloc0(sizeof(*response));

1385
    QTAILQ_FOREACH(mount, &mounts, next) {
1386 1387 1388 1389 1390 1391 1392 1393
        result = g_malloc0(sizeof(*result));
        result->path = g_strdup(mount->dirname);

        list = g_malloc0(sizeof(*list));
        list->value = result;
        list->next = response->paths;
        response->paths = list;

1394 1395
        fd = qemu_open(mount->dirname, O_RDONLY);
        if (fd == -1) {
1396 1397 1398 1399
            result->error = g_strdup_printf("failed to open: %s",
                                            strerror(errno));
            result->has_error = true;
            continue;
1400 1401
        }

M
Michael Tokarev 已提交
1402 1403 1404 1405
        /* We try to cull filesystems we know won't work in advance, but other
         * filesystems may not implement fstrim for less obvious reasons.
         * These will report EOPNOTSUPP; while in some other cases ENOTTY
         * will be reported (e.g. CD-ROMs).
1406
         * Any other error means an unexpected error.
1407
         */
1408 1409 1410
        r.start = 0;
        r.len = -1;
        r.minlen = has_minimum ? minimum : 0;
1411 1412
        ret = ioctl(fd, FITRIM, &r);
        if (ret == -1) {
1413 1414 1415 1416 1417 1418
            result->has_error = true;
            if (errno == ENOTTY || errno == EOPNOTSUPP) {
                result->error = g_strdup("trim not supported");
            } else {
                result->error = g_strdup_printf("failed to trim: %s",
                                                strerror(errno));
1419
            }
1420 1421
            close(fd);
            continue;
1422
        }
1423 1424 1425 1426 1427

        result->has_minimum = true;
        result->minimum = r.minlen;
        result->has_trimmed = true;
        result->trimmed = r.len;
1428 1429 1430 1431
        close(fd);
    }

    free_fs_mount_list(&mounts);
1432
    return response;
1433 1434 1435 1436
}
#endif /* CONFIG_FSTRIM */


1437 1438 1439 1440 1441
#define LINUX_SYS_STATE_FILE "/sys/power/state"
#define SUSPEND_SUPPORTED 0
#define SUSPEND_NOT_SUPPORTED 1

static void bios_supports_mode(const char *pmutils_bin, const char *pmutils_arg,
1442
                               const char *sysfile_str, Error **errp)
1443
{
1444
    Error *local_err = NULL;
1445
    char *pmutils_path;
1446
    pid_t pid;
1447
    int status;
1448 1449 1450 1451 1452

    pmutils_path = g_find_program_in_path(pmutils_bin);

    pid = fork();
    if (!pid) {
1453 1454 1455
        char buf[32]; /* hopefully big enough */
        ssize_t ret;
        int fd;
1456 1457 1458 1459 1460 1461

        setsid();
        reopen_fd_to_null(0);
        reopen_fd_to_null(1);
        reopen_fd_to_null(2);

1462 1463 1464
        if (pmutils_path) {
            execle(pmutils_path, pmutils_bin, pmutils_arg, NULL, environ);
        }
1465

1466 1467 1468 1469
        /*
         * If we get here either pm-utils is not installed or execle() has
         * failed. Let's try the manual method if the caller wants it.
         */
1470

1471 1472 1473
        if (!sysfile_str) {
            _exit(SUSPEND_NOT_SUPPORTED);
        }
1474

1475 1476
        fd = open(LINUX_SYS_STATE_FILE, O_RDONLY);
        if (fd < 0) {
1477 1478 1479
            _exit(SUSPEND_NOT_SUPPORTED);
        }

1480 1481 1482
        ret = read(fd, buf, sizeof(buf)-1);
        if (ret <= 0) {
            _exit(SUSPEND_NOT_SUPPORTED);
1483
        }
1484
        buf[ret] = '\0';
1485

1486 1487
        if (strstr(buf, sysfile_str)) {
            _exit(SUSPEND_SUPPORTED);
1488 1489
        }

1490
        _exit(SUSPEND_NOT_SUPPORTED);
1491
    } else if (pid < 0) {
1492
        error_setg_errno(errp, errno, "failed to create child process");
1493
        goto out;
1494 1495
    }

1496
    ga_wait_child(pid, &status, &local_err);
1497
    if (local_err) {
1498
        error_propagate(errp, local_err);
1499 1500
        goto out;
    }
1501

1502
    if (!WIFEXITED(status)) {
1503
        error_setg(errp, "child process has terminated abnormally");
1504
        goto out;
1505 1506
    }

1507 1508 1509 1510
    switch (WEXITSTATUS(status)) {
    case SUSPEND_SUPPORTED:
        goto out;
    case SUSPEND_NOT_SUPPORTED:
1511
        error_setg(errp,
1512 1513 1514
                   "the requested suspend mode is not supported by the guest");
        goto out;
    default:
1515
        error_setg(errp,
1516 1517 1518
                   "the helper program '%s' returned an unexpected exit status"
                   " code (%d)", pmutils_path, WEXITSTATUS(status));
        goto out;
1519 1520
    }

1521 1522
out:
    g_free(pmutils_path);
1523 1524 1525
}

static void guest_suspend(const char *pmutils_bin, const char *sysfile_str,
1526
                          Error **errp)
1527
{
1528
    Error *local_err = NULL;
1529
    char *pmutils_path;
1530
    pid_t pid;
1531
    int status;
1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567

    pmutils_path = g_find_program_in_path(pmutils_bin);

    pid = fork();
    if (pid == 0) {
        /* child */
        int fd;

        setsid();
        reopen_fd_to_null(0);
        reopen_fd_to_null(1);
        reopen_fd_to_null(2);

        if (pmutils_path) {
            execle(pmutils_path, pmutils_bin, NULL, environ);
        }

        /*
         * If we get here either pm-utils is not installed or execle() has
         * failed. Let's try the manual method if the caller wants it.
         */

        if (!sysfile_str) {
            _exit(EXIT_FAILURE);
        }

        fd = open(LINUX_SYS_STATE_FILE, O_WRONLY);
        if (fd < 0) {
            _exit(EXIT_FAILURE);
        }

        if (write(fd, sysfile_str, strlen(sysfile_str)) < 0) {
            _exit(EXIT_FAILURE);
        }

        _exit(EXIT_SUCCESS);
1568
    } else if (pid < 0) {
1569
        error_setg_errno(errp, errno, "failed to create child process");
1570
        goto out;
1571 1572
    }

1573
    ga_wait_child(pid, &status, &local_err);
1574
    if (local_err) {
1575
        error_propagate(errp, local_err);
1576 1577
        goto out;
    }
1578

1579
    if (!WIFEXITED(status)) {
1580
        error_setg(errp, "child process has terminated abnormally");
1581
        goto out;
1582 1583
    }

1584
    if (WEXITSTATUS(status)) {
1585
        error_setg(errp, "child process has failed to suspend");
1586
        goto out;
1587
    }
1588

1589 1590
out:
    g_free(pmutils_path);
1591 1592
}

1593
void qmp_guest_suspend_disk(Error **errp)
1594
{
1595 1596 1597 1598 1599
    Error *local_err = NULL;

    bios_supports_mode("pm-is-supported", "--hibernate", "disk", &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
1600 1601 1602
        return;
    }

1603
    guest_suspend("pm-hibernate", "disk", errp);
1604 1605
}

1606
void qmp_guest_suspend_ram(Error **errp)
L
Luiz Capitulino 已提交
1607
{
1608 1609 1610 1611 1612
    Error *local_err = NULL;

    bios_supports_mode("pm-is-supported", "--suspend", "mem", &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
L
Luiz Capitulino 已提交
1613 1614 1615
        return;
    }

1616
    guest_suspend("pm-suspend", "mem", errp);
L
Luiz Capitulino 已提交
1617 1618
}

1619
void qmp_guest_suspend_hybrid(Error **errp)
1620
{
1621 1622 1623 1624 1625 1626
    Error *local_err = NULL;

    bios_supports_mode("pm-is-supported", "--suspend-hybrid", NULL,
                       &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
1627 1628 1629
        return;
    }

1630
    guest_suspend("pm-suspend-hybrid", NULL, errp);
1631 1632
}

1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654
static GuestNetworkInterfaceList *
guest_find_interface(GuestNetworkInterfaceList *head,
                     const char *name)
{
    for (; head; head = head->next) {
        if (strcmp(head->value->name, name) == 0) {
            break;
        }
    }

    return head;
}

/*
 * Build information about guest interfaces
 */
GuestNetworkInterfaceList *qmp_guest_network_get_interfaces(Error **errp)
{
    GuestNetworkInterfaceList *head = NULL, *cur_item = NULL;
    struct ifaddrs *ifap, *ifa;

    if (getifaddrs(&ifap) < 0) {
1655
        error_setg_errno(errp, errno, "getifaddrs failed");
1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690
        goto error;
    }

    for (ifa = ifap; ifa; ifa = ifa->ifa_next) {
        GuestNetworkInterfaceList *info;
        GuestIpAddressList **address_list = NULL, *address_item = NULL;
        char addr4[INET_ADDRSTRLEN];
        char addr6[INET6_ADDRSTRLEN];
        int sock;
        struct ifreq ifr;
        unsigned char *mac_addr;
        void *p;

        g_debug("Processing %s interface", ifa->ifa_name);

        info = guest_find_interface(head, ifa->ifa_name);

        if (!info) {
            info = g_malloc0(sizeof(*info));
            info->value = g_malloc0(sizeof(*info->value));
            info->value->name = g_strdup(ifa->ifa_name);

            if (!cur_item) {
                head = cur_item = info;
            } else {
                cur_item->next = info;
                cur_item = info;
            }
        }

        if (!info->value->has_hardware_address &&
            ifa->ifa_flags & SIOCGIFHWADDR) {
            /* we haven't obtained HW address yet */
            sock = socket(PF_INET, SOCK_STREAM, 0);
            if (sock == -1) {
1691
                error_setg_errno(errp, errno, "failed to create socket");
1692 1693 1694 1695
                goto error;
            }

            memset(&ifr, 0, sizeof(ifr));
1696
            pstrcpy(ifr.ifr_name, IF_NAMESIZE, info->value->name);
1697
            if (ioctl(sock, SIOCGIFHWADDR, &ifr) == -1) {
1698 1699 1700
                error_setg_errno(errp, errno,
                                 "failed to get MAC address of %s",
                                 ifa->ifa_name);
1701
                close(sock);
1702 1703 1704
                goto error;
            }

1705
            close(sock);
1706 1707
            mac_addr = (unsigned char *) &ifr.ifr_hwaddr.sa_data;

1708 1709 1710 1711 1712
            info->value->hardware_address =
                g_strdup_printf("%02x:%02x:%02x:%02x:%02x:%02x",
                                (int) mac_addr[0], (int) mac_addr[1],
                                (int) mac_addr[2], (int) mac_addr[3],
                                (int) mac_addr[4], (int) mac_addr[5]);
1713 1714 1715 1716 1717 1718 1719 1720 1721

            info->value->has_hardware_address = true;
        }

        if (ifa->ifa_addr &&
            ifa->ifa_addr->sa_family == AF_INET) {
            /* interface with IPv4 address */
            p = &((struct sockaddr_in *)ifa->ifa_addr)->sin_addr;
            if (!inet_ntop(AF_INET, p, addr4, sizeof(addr4))) {
1722
                error_setg_errno(errp, errno, "inet_ntop failed");
1723 1724 1725
                goto error;
            }

1726 1727
            address_item = g_malloc0(sizeof(*address_item));
            address_item->value = g_malloc0(sizeof(*address_item->value));
1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741
            address_item->value->ip_address = g_strdup(addr4);
            address_item->value->ip_address_type = GUEST_IP_ADDRESS_TYPE_IPV4;

            if (ifa->ifa_netmask) {
                /* Count the number of set bits in netmask.
                 * This is safe as '1' and '0' cannot be shuffled in netmask. */
                p = &((struct sockaddr_in *)ifa->ifa_netmask)->sin_addr;
                address_item->value->prefix = ctpop32(((uint32_t *) p)[0]);
            }
        } else if (ifa->ifa_addr &&
                   ifa->ifa_addr->sa_family == AF_INET6) {
            /* interface with IPv6 address */
            p = &((struct sockaddr_in6 *)ifa->ifa_addr)->sin6_addr;
            if (!inet_ntop(AF_INET6, p, addr6, sizeof(addr6))) {
1742
                error_setg_errno(errp, errno, "inet_ntop failed");
1743 1744 1745
                goto error;
            }

1746 1747
            address_item = g_malloc0(sizeof(*address_item));
            address_item->value = g_malloc0(sizeof(*address_item->value));
1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792
            address_item->value->ip_address = g_strdup(addr6);
            address_item->value->ip_address_type = GUEST_IP_ADDRESS_TYPE_IPV6;

            if (ifa->ifa_netmask) {
                /* Count the number of set bits in netmask.
                 * This is safe as '1' and '0' cannot be shuffled in netmask. */
                p = &((struct sockaddr_in6 *)ifa->ifa_netmask)->sin6_addr;
                address_item->value->prefix =
                    ctpop32(((uint32_t *) p)[0]) +
                    ctpop32(((uint32_t *) p)[1]) +
                    ctpop32(((uint32_t *) p)[2]) +
                    ctpop32(((uint32_t *) p)[3]);
            }
        }

        if (!address_item) {
            continue;
        }

        address_list = &info->value->ip_addresses;

        while (*address_list && (*address_list)->next) {
            address_list = &(*address_list)->next;
        }

        if (!*address_list) {
            *address_list = address_item;
        } else {
            (*address_list)->next = address_item;
        }

        info->value->has_ip_addresses = true;


    }

    freeifaddrs(ifap);
    return head;

error:
    freeifaddrs(ifap);
    qapi_free_GuestNetworkInterfaceList(head);
    return NULL;
}

1793
#define SYSCONF_EXACT(name, errp) sysconf_exact((name), #name, (errp))
1794

1795
static long sysconf_exact(int name, const char *name_str, Error **errp)
1796 1797 1798 1799 1800 1801 1802
{
    long ret;

    errno = 0;
    ret = sysconf(name);
    if (ret == -1) {
        if (errno == 0) {
1803
            error_setg(errp, "sysconf(%s): value indefinite", name_str);
1804
        } else {
1805
            error_setg_errno(errp, errno, "sysconf(%s)", name_str);
1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922
        }
    }
    return ret;
}

/* Transfer online/offline status between @vcpu and the guest system.
 *
 * On input either @errp or *@errp must be NULL.
 *
 * In system-to-@vcpu direction, the following @vcpu fields are accessed:
 * - R: vcpu->logical_id
 * - W: vcpu->online
 * - W: vcpu->can_offline
 *
 * In @vcpu-to-system direction, the following @vcpu fields are accessed:
 * - R: vcpu->logical_id
 * - R: vcpu->online
 *
 * Written members remain unmodified on error.
 */
static void transfer_vcpu(GuestLogicalProcessor *vcpu, bool sys2vcpu,
                          Error **errp)
{
    char *dirpath;
    int dirfd;

    dirpath = g_strdup_printf("/sys/devices/system/cpu/cpu%" PRId64 "/",
                              vcpu->logical_id);
    dirfd = open(dirpath, O_RDONLY | O_DIRECTORY);
    if (dirfd == -1) {
        error_setg_errno(errp, errno, "open(\"%s\")", dirpath);
    } else {
        static const char fn[] = "online";
        int fd;
        int res;

        fd = openat(dirfd, fn, sys2vcpu ? O_RDONLY : O_RDWR);
        if (fd == -1) {
            if (errno != ENOENT) {
                error_setg_errno(errp, errno, "open(\"%s/%s\")", dirpath, fn);
            } else if (sys2vcpu) {
                vcpu->online = true;
                vcpu->can_offline = false;
            } else if (!vcpu->online) {
                error_setg(errp, "logical processor #%" PRId64 " can't be "
                           "offlined", vcpu->logical_id);
            } /* otherwise pretend successful re-onlining */
        } else {
            unsigned char status;

            res = pread(fd, &status, 1, 0);
            if (res == -1) {
                error_setg_errno(errp, errno, "pread(\"%s/%s\")", dirpath, fn);
            } else if (res == 0) {
                error_setg(errp, "pread(\"%s/%s\"): unexpected EOF", dirpath,
                           fn);
            } else if (sys2vcpu) {
                vcpu->online = (status != '0');
                vcpu->can_offline = true;
            } else if (vcpu->online != (status != '0')) {
                status = '0' + vcpu->online;
                if (pwrite(fd, &status, 1, 0) == -1) {
                    error_setg_errno(errp, errno, "pwrite(\"%s/%s\")", dirpath,
                                     fn);
                }
            } /* otherwise pretend successful re-(on|off)-lining */

            res = close(fd);
            g_assert(res == 0);
        }

        res = close(dirfd);
        g_assert(res == 0);
    }

    g_free(dirpath);
}

GuestLogicalProcessorList *qmp_guest_get_vcpus(Error **errp)
{
    int64_t current;
    GuestLogicalProcessorList *head, **link;
    long sc_max;
    Error *local_err = NULL;

    current = 0;
    head = NULL;
    link = &head;
    sc_max = SYSCONF_EXACT(_SC_NPROCESSORS_CONF, &local_err);

    while (local_err == NULL && current < sc_max) {
        GuestLogicalProcessor *vcpu;
        GuestLogicalProcessorList *entry;

        vcpu = g_malloc0(sizeof *vcpu);
        vcpu->logical_id = current++;
        vcpu->has_can_offline = true; /* lolspeak ftw */
        transfer_vcpu(vcpu, true, &local_err);

        entry = g_malloc0(sizeof *entry);
        entry->value = vcpu;

        *link = entry;
        link = &entry->next;
    }

    if (local_err == NULL) {
        /* there's no guest with zero VCPUs */
        g_assert(head != NULL);
        return head;
    }

    qapi_free_GuestLogicalProcessorList(head);
    error_propagate(errp, local_err);
    return NULL;
}

1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948
int64_t qmp_guest_set_vcpus(GuestLogicalProcessorList *vcpus, Error **errp)
{
    int64_t processed;
    Error *local_err = NULL;

    processed = 0;
    while (vcpus != NULL) {
        transfer_vcpu(vcpus->value, false, &local_err);
        if (local_err != NULL) {
            break;
        }
        ++processed;
        vcpus = vcpus->next;
    }

    if (local_err != NULL) {
        if (processed == 0) {
            error_propagate(errp, local_err);
        } else {
            error_free(local_err);
        }
    }

    return processed;
}

1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963
void qmp_guest_set_user_password(const char *username,
                                 const char *password,
                                 bool crypted,
                                 Error **errp)
{
    Error *local_err = NULL;
    char *passwd_path = NULL;
    pid_t pid;
    int status;
    int datafd[2] = { -1, -1 };
    char *rawpasswddata = NULL;
    size_t rawpasswdlen;
    char *chpasswddata = NULL;
    size_t chpasswdlen;

1964 1965 1966 1967
    rawpasswddata = (char *)qbase64_decode(password, -1, &rawpasswdlen, errp);
    if (!rawpasswddata) {
        return;
    }
1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053
    rawpasswddata = g_renew(char, rawpasswddata, rawpasswdlen + 1);
    rawpasswddata[rawpasswdlen] = '\0';

    if (strchr(rawpasswddata, '\n')) {
        error_setg(errp, "forbidden characters in raw password");
        goto out;
    }

    if (strchr(username, '\n') ||
        strchr(username, ':')) {
        error_setg(errp, "forbidden characters in username");
        goto out;
    }

    chpasswddata = g_strdup_printf("%s:%s\n", username, rawpasswddata);
    chpasswdlen = strlen(chpasswddata);

    passwd_path = g_find_program_in_path("chpasswd");

    if (!passwd_path) {
        error_setg(errp, "cannot find 'passwd' program in PATH");
        goto out;
    }

    if (pipe(datafd) < 0) {
        error_setg(errp, "cannot create pipe FDs");
        goto out;
    }

    pid = fork();
    if (pid == 0) {
        close(datafd[1]);
        /* child */
        setsid();
        dup2(datafd[0], 0);
        reopen_fd_to_null(1);
        reopen_fd_to_null(2);

        if (crypted) {
            execle(passwd_path, "chpasswd", "-e", NULL, environ);
        } else {
            execle(passwd_path, "chpasswd", NULL, environ);
        }
        _exit(EXIT_FAILURE);
    } else if (pid < 0) {
        error_setg_errno(errp, errno, "failed to create child process");
        goto out;
    }
    close(datafd[0]);
    datafd[0] = -1;

    if (qemu_write_full(datafd[1], chpasswddata, chpasswdlen) != chpasswdlen) {
        error_setg_errno(errp, errno, "cannot write new account password");
        goto out;
    }
    close(datafd[1]);
    datafd[1] = -1;

    ga_wait_child(pid, &status, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        goto out;
    }

    if (!WIFEXITED(status)) {
        error_setg(errp, "child process has terminated abnormally");
        goto out;
    }

    if (WEXITSTATUS(status)) {
        error_setg(errp, "child process has failed to set user password");
        goto out;
    }

out:
    g_free(chpasswddata);
    g_free(rawpasswddata);
    g_free(passwd_path);
    if (datafd[0] != -1) {
        close(datafd[0]);
    }
    if (datafd[1] != -1) {
        close(datafd[1]);
    }
}

2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131
static void ga_read_sysfs_file(int dirfd, const char *pathname, char *buf,
                               int size, Error **errp)
{
    int fd;
    int res;

    errno = 0;
    fd = openat(dirfd, pathname, O_RDONLY);
    if (fd == -1) {
        error_setg_errno(errp, errno, "open sysfs file \"%s\"", pathname);
        return;
    }

    res = pread(fd, buf, size, 0);
    if (res == -1) {
        error_setg_errno(errp, errno, "pread sysfs file \"%s\"", pathname);
    } else if (res == 0) {
        error_setg(errp, "pread sysfs file \"%s\": unexpected EOF", pathname);
    }
    close(fd);
}

static void ga_write_sysfs_file(int dirfd, const char *pathname,
                                const char *buf, int size, Error **errp)
{
    int fd;

    errno = 0;
    fd = openat(dirfd, pathname, O_WRONLY);
    if (fd == -1) {
        error_setg_errno(errp, errno, "open sysfs file \"%s\"", pathname);
        return;
    }

    if (pwrite(fd, buf, size, 0) == -1) {
        error_setg_errno(errp, errno, "pwrite sysfs file \"%s\"", pathname);
    }

    close(fd);
}

/* Transfer online/offline status between @mem_blk and the guest system.
 *
 * On input either @errp or *@errp must be NULL.
 *
 * In system-to-@mem_blk direction, the following @mem_blk fields are accessed:
 * - R: mem_blk->phys_index
 * - W: mem_blk->online
 * - W: mem_blk->can_offline
 *
 * In @mem_blk-to-system direction, the following @mem_blk fields are accessed:
 * - R: mem_blk->phys_index
 * - R: mem_blk->online
 *-  R: mem_blk->can_offline
 * Written members remain unmodified on error.
 */
static void transfer_memory_block(GuestMemoryBlock *mem_blk, bool sys2memblk,
                                  GuestMemoryBlockResponse *result,
                                  Error **errp)
{
    char *dirpath;
    int dirfd;
    char *status;
    Error *local_err = NULL;

    if (!sys2memblk) {
        DIR *dp;

        if (!result) {
            error_setg(errp, "Internal error, 'result' should not be NULL");
            return;
        }
        errno = 0;
        dp = opendir("/sys/devices/system/memory/");
         /* if there is no 'memory' directory in sysfs,
         * we think this VM does not support online/offline memory block,
         * any other solution?
         */
2132 2133 2134 2135 2136
        if (!dp) {
            if (errno == ENOENT) {
                result->response =
                    GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_NOT_SUPPORTED;
            }
2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191
            goto out1;
        }
        closedir(dp);
    }

    dirpath = g_strdup_printf("/sys/devices/system/memory/memory%" PRId64 "/",
                              mem_blk->phys_index);
    dirfd = open(dirpath, O_RDONLY | O_DIRECTORY);
    if (dirfd == -1) {
        if (sys2memblk) {
            error_setg_errno(errp, errno, "open(\"%s\")", dirpath);
        } else {
            if (errno == ENOENT) {
                result->response = GUEST_MEMORY_BLOCK_RESPONSE_TYPE_NOT_FOUND;
            } else {
                result->response =
                    GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_FAILED;
            }
        }
        g_free(dirpath);
        goto out1;
    }
    g_free(dirpath);

    status = g_malloc0(10);
    ga_read_sysfs_file(dirfd, "state", status, 10, &local_err);
    if (local_err) {
        /* treat with sysfs file that not exist in old kernel */
        if (errno == ENOENT) {
            error_free(local_err);
            if (sys2memblk) {
                mem_blk->online = true;
                mem_blk->can_offline = false;
            } else if (!mem_blk->online) {
                result->response =
                    GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_NOT_SUPPORTED;
            }
        } else {
            if (sys2memblk) {
                error_propagate(errp, local_err);
            } else {
                result->response =
                    GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_FAILED;
            }
        }
        goto out2;
    }

    if (sys2memblk) {
        char removable = '0';

        mem_blk->online = (strncmp(status, "online", 6) == 0);

        ga_read_sysfs_file(dirfd, "removable", &removable, 1, &local_err);
        if (local_err) {
V
Veres Lajos 已提交
2192
            /* if no 'removable' file, it doesn't support offline mem blk */
2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203
            if (errno == ENOENT) {
                error_free(local_err);
                mem_blk->can_offline = false;
            } else {
                error_propagate(errp, local_err);
            }
        } else {
            mem_blk->can_offline = (removable != '0');
        }
    } else {
        if (mem_blk->online != (strncmp(status, "online", 6) == 0)) {
2204
            const char *new_state = mem_blk->online ? "online" : "offline";
2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232

            ga_write_sysfs_file(dirfd, "state", new_state, strlen(new_state),
                                &local_err);
            if (local_err) {
                error_free(local_err);
                result->response =
                    GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_FAILED;
                goto out2;
            }

            result->response = GUEST_MEMORY_BLOCK_RESPONSE_TYPE_SUCCESS;
            result->has_error_code = false;
        } /* otherwise pretend successful re-(on|off)-lining */
    }
    g_free(status);
    close(dirfd);
    return;

out2:
    g_free(status);
    close(dirfd);
out1:
    if (!sys2memblk) {
        result->has_error_code = true;
        result->error_code = errno;
    }
}

2233 2234
GuestMemoryBlockList *qmp_guest_get_memory_blocks(Error **errp)
{
2235 2236 2237 2238 2239 2240 2241 2242 2243 2244
    GuestMemoryBlockList *head, **link;
    Error *local_err = NULL;
    struct dirent *de;
    DIR *dp;

    head = NULL;
    link = &head;

    dp = opendir("/sys/devices/system/memory/");
    if (!dp) {
2245 2246 2247 2248 2249 2250
        /* it's ok if this happens to be a system that doesn't expose
         * memory blocks via sysfs, but otherwise we should report
         * an error
         */
        if (errno != ENOENT) {
            error_setg_errno(errp, errno, "Can't open directory"
2251
                             "\"/sys/devices/system/memory/\"");
2252
        }
2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293
        return NULL;
    }

    /* Note: the phys_index of memory block may be discontinuous,
     * this is because a memblk is the unit of the Sparse Memory design, which
     * allows discontinuous memory ranges (ex. NUMA), so here we should
     * traverse the memory block directory.
     */
    while ((de = readdir(dp)) != NULL) {
        GuestMemoryBlock *mem_blk;
        GuestMemoryBlockList *entry;

        if ((strncmp(de->d_name, "memory", 6) != 0) ||
            !(de->d_type & DT_DIR)) {
            continue;
        }

        mem_blk = g_malloc0(sizeof *mem_blk);
        /* The d_name is "memoryXXX",  phys_index is block id, same as XXX */
        mem_blk->phys_index = strtoul(&de->d_name[6], NULL, 10);
        mem_blk->has_can_offline = true; /* lolspeak ftw */
        transfer_memory_block(mem_blk, true, NULL, &local_err);

        entry = g_malloc0(sizeof *entry);
        entry->value = mem_blk;

        *link = entry;
        link = &entry->next;
    }

    closedir(dp);
    if (local_err == NULL) {
        /* there's no guest with zero memory blocks */
        if (head == NULL) {
            error_setg(errp, "guest reported zero memory blocks!");
        }
        return head;
    }

    qapi_free_GuestMemoryBlockList(head);
    error_propagate(errp, local_err);
2294 2295 2296 2297 2298 2299
    return NULL;
}

GuestMemoryBlockResponseList *
qmp_guest_set_memory_blocks(GuestMemoryBlockList *mem_blks, Error **errp)
{
2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328
    GuestMemoryBlockResponseList *head, **link;
    Error *local_err = NULL;

    head = NULL;
    link = &head;

    while (mem_blks != NULL) {
        GuestMemoryBlockResponse *result;
        GuestMemoryBlockResponseList *entry;
        GuestMemoryBlock *current_mem_blk = mem_blks->value;

        result = g_malloc0(sizeof(*result));
        result->phys_index = current_mem_blk->phys_index;
        transfer_memory_block(current_mem_blk, false, result, &local_err);
        if (local_err) { /* should never happen */
            goto err;
        }
        entry = g_malloc0(sizeof *entry);
        entry->value = result;

        *link = entry;
        link = &entry->next;
        mem_blks = mem_blks->next;
    }

    return head;
err:
    qapi_free_GuestMemoryBlockResponseList(head);
    error_propagate(errp, local_err);
2329 2330 2331 2332 2333
    return NULL;
}

GuestMemoryBlockInfo *qmp_guest_get_memory_block_info(Error **errp)
{
2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350
    Error *local_err = NULL;
    char *dirpath;
    int dirfd;
    char *buf;
    GuestMemoryBlockInfo *info;

    dirpath = g_strdup_printf("/sys/devices/system/memory/");
    dirfd = open(dirpath, O_RDONLY | O_DIRECTORY);
    if (dirfd == -1) {
        error_setg_errno(errp, errno, "open(\"%s\")", dirpath);
        g_free(dirpath);
        return NULL;
    }
    g_free(dirpath);

    buf = g_malloc0(20);
    ga_read_sysfs_file(dirfd, "block_size_bytes", buf, 20, &local_err);
2351
    close(dirfd);
2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363
    if (local_err) {
        g_free(buf);
        error_propagate(errp, local_err);
        return NULL;
    }

    info = g_new0(GuestMemoryBlockInfo, 1);
    info->size = strtol(buf, NULL, 16); /* the unit is bytes */

    g_free(buf);

    return info;
2364 2365
}

2366 2367
#else /* defined(__linux__) */

2368
void qmp_guest_suspend_disk(Error **errp)
2369
{
2370
    error_setg(errp, QERR_UNSUPPORTED);
2371 2372
}

2373
void qmp_guest_suspend_ram(Error **errp)
2374
{
2375
    error_setg(errp, QERR_UNSUPPORTED);
2376 2377
}

2378
void qmp_guest_suspend_hybrid(Error **errp)
2379
{
2380
    error_setg(errp, QERR_UNSUPPORTED);
2381 2382
}

2383
GuestNetworkInterfaceList *qmp_guest_network_get_interfaces(Error **errp)
2384
{
2385
    error_setg(errp, QERR_UNSUPPORTED);
2386
    return NULL;
2387 2388
}

2389 2390
GuestLogicalProcessorList *qmp_guest_get_vcpus(Error **errp)
{
2391
    error_setg(errp, QERR_UNSUPPORTED);
2392 2393 2394
    return NULL;
}

2395 2396
int64_t qmp_guest_set_vcpus(GuestLogicalProcessorList *vcpus, Error **errp)
{
2397
    error_setg(errp, QERR_UNSUPPORTED);
2398 2399 2400
    return -1;
}

2401 2402 2403 2404 2405
void qmp_guest_set_user_password(const char *username,
                                 const char *password,
                                 bool crypted,
                                 Error **errp)
{
2406
    error_setg(errp, QERR_UNSUPPORTED);
2407 2408
}

2409 2410
GuestMemoryBlockList *qmp_guest_get_memory_blocks(Error **errp)
{
2411
    error_setg(errp, QERR_UNSUPPORTED);
2412 2413 2414 2415 2416 2417
    return NULL;
}

GuestMemoryBlockResponseList *
qmp_guest_set_memory_blocks(GuestMemoryBlockList *mem_blks, Error **errp)
{
2418
    error_setg(errp, QERR_UNSUPPORTED);
2419 2420 2421 2422 2423
    return NULL;
}

GuestMemoryBlockInfo *qmp_guest_get_memory_block_info(Error **errp)
{
2424
    error_setg(errp, QERR_UNSUPPORTED);
2425 2426 2427
    return NULL;
}

2428 2429 2430 2431
#endif

#if !defined(CONFIG_FSFREEZE)

2432 2433
GuestFilesystemInfoList *qmp_guest_get_fsinfo(Error **errp)
{
2434
    error_setg(errp, QERR_UNSUPPORTED);
2435 2436 2437
    return NULL;
}

2438
GuestFsfreezeStatus qmp_guest_fsfreeze_status(Error **errp)
2439
{
2440
    error_setg(errp, QERR_UNSUPPORTED);
2441 2442

    return 0;
2443 2444
}

2445
int64_t qmp_guest_fsfreeze_freeze(Error **errp)
2446
{
2447
    error_setg(errp, QERR_UNSUPPORTED);
2448 2449

    return 0;
2450 2451
}

2452 2453 2454 2455
int64_t qmp_guest_fsfreeze_freeze_list(bool has_mountpoints,
                                       strList *mountpoints,
                                       Error **errp)
{
2456
    error_setg(errp, QERR_UNSUPPORTED);
2457 2458 2459 2460

    return 0;
}

2461
int64_t qmp_guest_fsfreeze_thaw(Error **errp)
2462
{
2463
    error_setg(errp, QERR_UNSUPPORTED);
2464 2465

    return 0;
2466
}
2467 2468 2469
#endif /* CONFIG_FSFREEZE */

#if !defined(CONFIG_FSTRIM)
2470 2471
GuestFilesystemTrimResponse *
qmp_guest_fstrim(bool has_minimum, int64_t minimum, Error **errp)
2472
{
2473
    error_setg(errp, QERR_UNSUPPORTED);
2474
    return NULL;
2475
}
2476 2477
#endif

2478 2479 2480 2481 2482 2483 2484 2485
/* add unsupported commands to the blacklist */
GList *ga_command_blacklist_init(GList *blacklist)
{
#if !defined(__linux__)
    {
        const char *list[] = {
            "guest-suspend-disk", "guest-suspend-ram",
            "guest-suspend-hybrid", "guest-network-get-interfaces",
2486 2487 2488
            "guest-get-vcpus", "guest-set-vcpus",
            "guest-get-memory-blocks", "guest-set-memory-blocks",
            "guest-get-memory-block-size", NULL};
2489 2490 2491
        char **p = (char **)list;

        while (*p) {
2492
            blacklist = g_list_append(blacklist, g_strdup(*p++));
2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505
        }
    }
#endif

#if !defined(CONFIG_FSFREEZE)
    {
        const char *list[] = {
            "guest-get-fsinfo", "guest-fsfreeze-status",
            "guest-fsfreeze-freeze", "guest-fsfreeze-freeze-list",
            "guest-fsfreeze-thaw", "guest-get-fsinfo", NULL};
        char **p = (char **)list;

        while (*p) {
2506
            blacklist = g_list_append(blacklist, g_strdup(*p++));
2507 2508 2509 2510 2511
        }
    }
#endif

#if !defined(CONFIG_FSTRIM)
2512
    blacklist = g_list_append(blacklist, g_strdup("guest-fstrim"));
2513 2514 2515 2516 2517
#endif

    return blacklist;
}

2518 2519 2520
/* register init/cleanup routines for stateful command groups */
void ga_command_state_init(GAState *s, GACommandState *cs)
{
2521
#if defined(CONFIG_FSFREEZE)
2522
    ga_command_state_add(cs, NULL, guest_fsfreeze_cleanup);
2523
#endif
2524
}
2525

2526 2527
#ifdef HAVE_UTMPX

2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585
#define QGA_MICRO_SECOND_TO_SECOND 1000000

static double ga_get_login_time(struct utmpx *user_info)
{
    double seconds = (double)user_info->ut_tv.tv_sec;
    double useconds = (double)user_info->ut_tv.tv_usec;
    useconds /= QGA_MICRO_SECOND_TO_SECOND;
    return seconds + useconds;
}

GuestUserList *qmp_guest_get_users(Error **err)
{
    GHashTable *cache = NULL;
    GuestUserList *head = NULL, *cur_item = NULL;
    struct utmpx *user_info = NULL;
    gpointer value = NULL;
    GuestUser *user = NULL;
    GuestUserList *item = NULL;
    double login_time = 0;

    cache = g_hash_table_new(g_str_hash, g_str_equal);
    setutxent();

    for (;;) {
        user_info = getutxent();
        if (user_info == NULL) {
            break;
        } else if (user_info->ut_type != USER_PROCESS) {
            continue;
        } else if (g_hash_table_contains(cache, user_info->ut_user)) {
            value = g_hash_table_lookup(cache, user_info->ut_user);
            user = (GuestUser *)value;
            login_time = ga_get_login_time(user_info);
            /* We're ensuring the earliest login time to be sent */
            if (login_time < user->login_time) {
                user->login_time = login_time;
            }
            continue;
        }

        item = g_new0(GuestUserList, 1);
        item->value = g_new0(GuestUser, 1);
        item->value->user = g_strdup(user_info->ut_user);
        item->value->login_time = ga_get_login_time(user_info);

        g_hash_table_insert(cache, item->value->user, item->value);

        if (!cur_item) {
            head = cur_item = item;
        } else {
            cur_item->next = item;
            cur_item = item;
        }
    }
    endutxent();
    g_hash_table_destroy(cache);
    return head;
}
2586 2587 2588 2589 2590 2591 2592 2593 2594 2595

#else

GuestUserList *qmp_guest_get_users(Error **errp)
{
    error_setg(errp, QERR_UNSUPPORTED);
    return NULL;
}

#endif
2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684

/* Replace escaped special characters with theire real values. The replacement
 * is done in place -- returned value is in the original string.
 */
static void ga_osrelease_replace_special(gchar *value)
{
    gchar *p, *p2, quote;

    /* Trim the string at first space or semicolon if it is not enclosed in
     * single or double quotes. */
    if ((value[0] != '"') || (value[0] == '\'')) {
        p = strchr(value, ' ');
        if (p != NULL) {
            *p = 0;
        }
        p = strchr(value, ';');
        if (p != NULL) {
            *p = 0;
        }
        return;
    }

    quote = value[0];
    p2 = value;
    p = value + 1;
    while (*p != 0) {
        if (*p == '\\') {
            p++;
            switch (*p) {
            case '$':
            case '\'':
            case '"':
            case '\\':
            case '`':
                break;
            default:
                /* Keep literal backslash followed by whatever is there */
                p--;
                break;
            }
        } else if (*p == quote) {
            *p2 = 0;
            break;
        }
        *(p2++) = *(p++);
    }
}

static GKeyFile *ga_parse_osrelease(const char *fname)
{
    gchar *content = NULL;
    gchar *content2 = NULL;
    GError *err = NULL;
    GKeyFile *keys = g_key_file_new();
    const char *group = "[os-release]\n";

    if (!g_file_get_contents(fname, &content, NULL, &err)) {
        slog("failed to read '%s', error: %s", fname, err->message);
        goto fail;
    }

    if (!g_utf8_validate(content, -1, NULL)) {
        slog("file is not utf-8 encoded: %s", fname);
        goto fail;
    }
    content2 = g_strdup_printf("%s%s", group, content);

    if (!g_key_file_load_from_data(keys, content2, -1, G_KEY_FILE_NONE,
                                   &err)) {
        slog("failed to parse file '%s', error: %s", fname, err->message);
        goto fail;
    }

    g_free(content);
    g_free(content2);
    return keys;

fail:
    g_error_free(err);
    g_free(content);
    g_free(content2);
    g_key_file_free(keys);
    return NULL;
}

GuestOSInfo *qmp_guest_get_osinfo(Error **errp)
{
    GuestOSInfo *info = NULL;
    struct utsname kinfo;
2685 2686
    GKeyFile *osrelease = NULL;
    const char *qga_os_release = g_getenv("QGA_OS_RELEASE");
2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700

    info = g_new0(GuestOSInfo, 1);

    if (uname(&kinfo) != 0) {
        error_setg_errno(errp, errno, "uname failed");
    } else {
        info->has_kernel_version = true;
        info->kernel_version = g_strdup(kinfo.version);
        info->has_kernel_release = true;
        info->kernel_release = g_strdup(kinfo.release);
        info->has_machine = true;
        info->machine = g_strdup(kinfo.machine);
    }

2701 2702 2703 2704 2705 2706 2707
    if (qga_os_release != NULL) {
        osrelease = ga_parse_osrelease(qga_os_release);
    } else {
        osrelease = ga_parse_osrelease("/etc/os-release");
        if (osrelease == NULL) {
            osrelease = ga_parse_osrelease("/usr/lib/os-release");
        }
2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734
    }

    if (osrelease != NULL) {
        char *value;

#define GET_FIELD(field, osfield) do { \
    value = g_key_file_get_value(osrelease, "os-release", osfield, NULL); \
    if (value != NULL) { \
        ga_osrelease_replace_special(value); \
        info->has_ ## field = true; \
        info->field = value; \
    } \
} while (0)
        GET_FIELD(id, "ID");
        GET_FIELD(name, "NAME");
        GET_FIELD(pretty_name, "PRETTY_NAME");
        GET_FIELD(version, "VERSION");
        GET_FIELD(version_id, "VERSION_ID");
        GET_FIELD(variant, "VARIANT");
        GET_FIELD(variant_id, "VARIANT_ID");
#undef GET_FIELD

        g_key_file_free(osrelease);
    }

    return info;
}