X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=savevm.c;h=03fc4d93bf38b6d56b348e7907843d7fdb22e9f8;hb=b142d79328cd0a0556634b0eeb891a15bfd5a00c;hp=406caa90e5b7878fae900cf5a972e19b5dbdcf3f;hpb=6181ec245529e0d40ac669fe3044eef3a9e19610;p=mirror_qemu.git diff --git a/savevm.c b/savevm.c index 406caa90e5..03fc4d93bf 100644 --- a/savevm.c +++ b/savevm.c @@ -40,6 +40,8 @@ #include "trace.h" #include "qemu/bitops.h" #include "qemu/iov.h" +#include "block/snapshot.h" +#include "block/qapi.h" #define SELF_ANNOUNCE_ROUNDS 5 @@ -119,7 +121,6 @@ void qemu_announce_self(void) struct QEMUFile { const QEMUFileOps *ops; void *opaque; - int is_write; int64_t bytes_xfer; int64_t xfer_limit; @@ -148,35 +149,8 @@ typedef struct QEMUFileSocket QEMUFile *file; } QEMUFileSocket; -typedef struct { - Coroutine *co; - int fd; -} FDYieldUntilData; - -static void fd_coroutine_enter(void *opaque) -{ - FDYieldUntilData *data = opaque; - qemu_set_fd_handler(data->fd, NULL, NULL, NULL); - qemu_coroutine_enter(data->co, NULL); -} - -/** - * Yield until a file descriptor becomes readable - * - * Note that this function clobbers the handlers for the file descriptor. - */ -static void coroutine_fn yield_until_fd_readable(int fd) -{ - FDYieldUntilData data; - - assert(qemu_in_coroutine()); - data.co = qemu_coroutine_self(); - data.fd = fd; - qemu_set_fd_handler(fd, fd_coroutine_enter, NULL, &data); - qemu_coroutine_yield(); -} - -static ssize_t socket_writev_buffer(void *opaque, struct iovec *iov, int iovcnt) +static ssize_t socket_writev_buffer(void *opaque, struct iovec *iov, int iovcnt, + int64_t pos) { QEMUFileSocket *s = opaque; ssize_t len; @@ -219,18 +193,6 @@ static int socket_get_buffer(void *opaque, uint8_t *buf, int64_t pos, int size) return len; } -static int socket_put_buffer(void *opaque, const uint8_t *buf, int64_t pos, int size) -{ - QEMUFileSocket *s = opaque; - ssize_t len; - - len = qemu_send_full(s->fd, buf, size, 0); - if (len < size) { - len = -socket_error(); - } - return len; -} - static int socket_close(void *opaque) { QEMUFileSocket *s = opaque; @@ -334,13 +296,13 @@ QEMUFile *qemu_popen_cmd(const char *command, const char *mode) FILE *stdio_file; QEMUFileStdio *s; - stdio_file = popen(command, mode); - if (stdio_file == NULL) { + if (mode == NULL || (mode[0] != 'r' && mode[0] != 'w') || mode[1] != 0) { + fprintf(stderr, "qemu_popen: Argument validity check failed\n"); return NULL; } - if (mode == NULL || (mode[0] != 'r' && mode[0] != 'w') || mode[1] != 0) { - fprintf(stderr, "qemu_popen: Argument validity check failed\n"); + stdio_file = popen(command, mode); + if (stdio_file == NULL) { return NULL; } @@ -368,9 +330,94 @@ static const QEMUFileOps stdio_file_write_ops = { .close = stdio_fclose }; +static ssize_t unix_writev_buffer(void *opaque, struct iovec *iov, int iovcnt, + int64_t pos) +{ + QEMUFileSocket *s = opaque; + ssize_t len, offset; + ssize_t size = iov_size(iov, iovcnt); + ssize_t total = 0; + + assert(iovcnt > 0); + offset = 0; + while (size > 0) { + /* Find the next start position; skip all full-sized vector elements */ + while (offset >= iov[0].iov_len) { + offset -= iov[0].iov_len; + iov++, iovcnt--; + } + + /* skip `offset' bytes from the (now) first element, undo it on exit */ + assert(iovcnt > 0); + iov[0].iov_base += offset; + iov[0].iov_len -= offset; + + do { + len = writev(s->fd, iov, iovcnt); + } while (len == -1 && errno == EINTR); + if (len == -1) { + return -errno; + } + + /* Undo the changes above */ + iov[0].iov_base -= offset; + iov[0].iov_len += offset; + + /* Prepare for the next iteration */ + offset += len; + total += len; + size -= len; + } + + return total; +} + +static int unix_get_buffer(void *opaque, uint8_t *buf, int64_t pos, int size) +{ + QEMUFileSocket *s = opaque; + ssize_t len; + + for (;;) { + len = read(s->fd, buf, size); + if (len != -1) { + break; + } + if (errno == EAGAIN) { + yield_until_fd_readable(s->fd); + } else if (errno != EINTR) { + break; + } + } + + if (len == -1) { + len = -errno; + } + return len; +} + +static int unix_close(void *opaque) +{ + QEMUFileSocket *s = opaque; + close(s->fd); + g_free(s); + return 0; +} + +static const QEMUFileOps unix_read_ops = { + .get_fd = socket_get_fd, + .get_buffer = unix_get_buffer, + .close = unix_close +}; + +static const QEMUFileOps unix_write_ops = { + .get_fd = socket_get_fd, + .writev_buffer = unix_writev_buffer, + .close = unix_close +}; + QEMUFile *qemu_fdopen(int fd, const char *mode) { - QEMUFileStdio *s; + QEMUFileSocket *s; if (mode == NULL || (mode[0] != 'r' && mode[0] != 'w') || @@ -379,21 +426,15 @@ QEMUFile *qemu_fdopen(int fd, const char *mode) return NULL; } - s = g_malloc0(sizeof(QEMUFileStdio)); - s->stdio_file = fdopen(fd, mode); - if (!s->stdio_file) - goto fail; + s = g_malloc0(sizeof(QEMUFileSocket)); + s->fd = fd; if(mode[0] == 'r') { - s->file = qemu_fopen_ops(s, &stdio_file_read_ops); + s->file = qemu_fopen_ops(s, &unix_read_ops); } else { - s->file = qemu_fopen_ops(s, &stdio_file_write_ops); + s->file = qemu_fopen_ops(s, &unix_write_ops); } return s->file; - -fail: - g_free(s); - return NULL; } static const QEMUFileOps socket_read_ops = { @@ -404,25 +445,34 @@ static const QEMUFileOps socket_read_ops = { static const QEMUFileOps socket_write_ops = { .get_fd = socket_get_fd, - .put_buffer = socket_put_buffer, .writev_buffer = socket_writev_buffer, .close = socket_close }; -QEMUFile *qemu_fopen_socket(int fd, const char *mode) +bool qemu_file_mode_is_not_valid(const char *mode) { - QEMUFileSocket *s = g_malloc0(sizeof(QEMUFileSocket)); - if (mode == NULL || (mode[0] != 'r' && mode[0] != 'w') || mode[1] != 'b' || mode[2] != 0) { fprintf(stderr, "qemu_fopen: Argument validity check failed\n"); + return true; + } + + return false; +} + +QEMUFile *qemu_fopen_socket(int fd, const char *mode) +{ + QEMUFileSocket *s; + + if (qemu_file_mode_is_not_valid(mode)) { return NULL; } + s = g_malloc0(sizeof(QEMUFileSocket)); s->fd = fd; if (mode[0] == 'w') { - socket_set_block(s->fd); + qemu_set_block(s->fd); s->file = qemu_fopen_ops(s, &socket_write_ops); } else { s->file = qemu_fopen_ops(s, &socket_read_ops); @@ -434,10 +484,7 @@ QEMUFile *qemu_fopen(const char *filename, const char *mode) { QEMUFileStdio *s; - if (mode == NULL || - (mode[0] != 'r' && mode[0] != 'w') || - mode[1] != 'b' || mode[2] != 0) { - fprintf(stderr, "qemu_fopen: Argument validity check failed\n"); + if (qemu_file_mode_is_not_valid(mode)) { return NULL; } @@ -458,6 +505,21 @@ fail: return NULL; } +static ssize_t block_writev_buffer(void *opaque, struct iovec *iov, int iovcnt, + int64_t pos) +{ + int ret; + QEMUIOVector qiov; + + qemu_iovec_init_external(&qiov, iov, iovcnt); + ret = bdrv_writev_vmstate(opaque, &qiov, pos); + if (ret < 0) { + return ret; + } + + return qiov.size; +} + static int block_put_buffer(void *opaque, const uint8_t *buf, int64_t pos, int size) { @@ -481,8 +543,9 @@ static const QEMUFileOps bdrv_read_ops = { }; static const QEMUFileOps bdrv_write_ops = { - .put_buffer = block_put_buffer, - .close = bdrv_fclose + .put_buffer = block_put_buffer, + .writev_buffer = block_writev_buffer, + .close = bdrv_fclose }; static QEMUFile *qemu_fopen_bdrv(BlockDriverState *bs, int is_writable) @@ -500,7 +563,6 @@ QEMUFile *qemu_fopen_ops(void *opaque, const QEMUFileOps *ops) f->opaque = opaque; f->ops = ops; - f->is_write = 0; return f; } @@ -516,54 +578,109 @@ static void qemu_file_set_error(QEMUFile *f, int ret) } } +static inline bool qemu_file_is_writable(QEMUFile *f) +{ + return f->ops->writev_buffer || f->ops->put_buffer; +} + /** * Flushes QEMUFile buffer * * If there is writev_buffer QEMUFileOps it uses it otherwise uses * put_buffer ops. */ -static void qemu_fflush(QEMUFile *f) +void qemu_fflush(QEMUFile *f) { ssize_t ret = 0; - int i = 0; - if (!f->ops->writev_buffer && !f->ops->put_buffer) { + if (!qemu_file_is_writable(f)) { return; } - if (f->is_write && f->iovcnt > 0) { - if (f->ops->writev_buffer) { - ret = f->ops->writev_buffer(f->opaque, f->iov, f->iovcnt); - if (ret >= 0) { - f->pos += ret; - } - } else { - for (i = 0; i < f->iovcnt && ret >= 0; i++) { - ret = f->ops->put_buffer(f->opaque, f->iov[i].iov_base, f->pos, - f->iov[i].iov_len); - if (ret >= 0) { - f->pos += ret; - } - } + if (f->ops->writev_buffer) { + if (f->iovcnt > 0) { + ret = f->ops->writev_buffer(f->opaque, f->iov, f->iovcnt, f->pos); } - f->buf_index = 0; - f->iovcnt = 0; + } else { + if (f->buf_index > 0) { + ret = f->ops->put_buffer(f->opaque, f->buf, f->pos, f->buf_index); + } + } + if (ret >= 0) { + f->pos += ret; } + f->buf_index = 0; + f->iovcnt = 0; if (ret < 0) { qemu_file_set_error(f, ret); } } +void ram_control_before_iterate(QEMUFile *f, uint64_t flags) +{ + int ret = 0; + + if (f->ops->before_ram_iterate) { + ret = f->ops->before_ram_iterate(f, f->opaque, flags); + if (ret < 0) { + qemu_file_set_error(f, ret); + } + } +} + +void ram_control_after_iterate(QEMUFile *f, uint64_t flags) +{ + int ret = 0; + + if (f->ops->after_ram_iterate) { + ret = f->ops->after_ram_iterate(f, f->opaque, flags); + if (ret < 0) { + qemu_file_set_error(f, ret); + } + } +} + +void ram_control_load_hook(QEMUFile *f, uint64_t flags) +{ + int ret = 0; + + if (f->ops->hook_ram_load) { + ret = f->ops->hook_ram_load(f, f->opaque, flags); + if (ret < 0) { + qemu_file_set_error(f, ret); + } + } else { + qemu_file_set_error(f, ret); + } +} + +size_t ram_control_save_page(QEMUFile *f, ram_addr_t block_offset, + ram_addr_t offset, size_t size, int *bytes_sent) +{ + if (f->ops->save_page) { + int ret = f->ops->save_page(f, f->opaque, block_offset, + offset, size, bytes_sent); + + if (ret != RAM_SAVE_CONTROL_DELAYED) { + if (bytes_sent && *bytes_sent > 0) { + qemu_update_position(f, *bytes_sent); + } else if (ret < 0) { + qemu_file_set_error(f, ret); + } + } + + return ret; + } + + return RAM_SAVE_CONTROL_NOT_SUPP; +} + static void qemu_fill_buffer(QEMUFile *f) { int len; int pending; - if (!f->ops->get_buffer) - return; - - if (f->is_write) - abort(); + assert(!qemu_file_is_writable(f)); pending = f->buf_size - f->buf_index; if (pending > 0) { @@ -591,6 +708,11 @@ int qemu_get_fd(QEMUFile *f) return -1; } +void qemu_update_position(QEMUFile *f, size_t size) +{ + f->pos += size; +} + /** Closes the file * * Returns negative error value if any error happened on previous operations or @@ -631,28 +753,25 @@ static void add_to_iovec(QEMUFile *f, const uint8_t *buf, int size) f->iov[f->iovcnt].iov_base = (uint8_t *)buf; f->iov[f->iovcnt++].iov_len = size; } + + if (f->iovcnt >= MAX_IOV_SIZE) { + qemu_fflush(f); + } } void qemu_put_buffer_async(QEMUFile *f, const uint8_t *buf, int size) { - if (f->last_error) { + if (!f->ops->writev_buffer) { + qemu_put_buffer(f, buf, size); return; } - if (f->is_write == 0 && f->buf_index > 0) { - fprintf(stderr, - "Attempted to write to buffer while read buffer is not empty\n"); - abort(); + if (f->last_error) { + return; } - add_to_iovec(f, buf, size); - - f->is_write = 1; f->bytes_xfer += size; - - if (f->buf_index >= IO_BUF_SIZE || f->iovcnt >= MAX_IOV_SIZE) { - qemu_fflush(f); - } + add_to_iovec(f, buf, size); } void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, int size) @@ -663,20 +782,19 @@ void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, int size) return; } - if (f->is_write == 0 && f->buf_index > 0) { - fprintf(stderr, - "Attempted to write to buffer while read buffer is not empty\n"); - abort(); - } - while (size > 0) { l = IO_BUF_SIZE - f->buf_index; if (l > size) l = size; memcpy(f->buf + f->buf_index, buf, l); - f->is_write = 1; + f->bytes_xfer += size; + if (f->ops->writev_buffer) { + add_to_iovec(f, f->buf + f->buf_index, l); + } f->buf_index += l; - qemu_put_buffer_async(f, f->buf + (f->buf_index - l), l); + if (f->buf_index == IO_BUF_SIZE) { + qemu_fflush(f); + } if (qemu_file_get_error(f)) { break; } @@ -691,19 +809,13 @@ void qemu_put_byte(QEMUFile *f, int v) return; } - if (f->is_write == 0 && f->buf_index > 0) { - fprintf(stderr, - "Attempted to write to buffer while read buffer is not empty\n"); - abort(); - } - - f->buf[f->buf_index++] = v; - f->is_write = 1; + f->buf[f->buf_index] = v; f->bytes_xfer++; - - add_to_iovec(f, f->buf + (f->buf_index - 1), 1); - - if (f->buf_index >= IO_BUF_SIZE || f->iovcnt >= MAX_IOV_SIZE) { + if (f->ops->writev_buffer) { + add_to_iovec(f, f->buf + f->buf_index, 1); + } + f->buf_index++; + if (f->buf_index == IO_BUF_SIZE) { qemu_fflush(f); } } @@ -720,9 +832,7 @@ static int qemu_peek_buffer(QEMUFile *f, uint8_t *buf, int size, size_t offset) int pending; int index; - if (f->is_write) { - abort(); - } + assert(!qemu_file_is_writable(f)); index = f->buf_index + offset; pending = f->buf_size - index; @@ -767,9 +877,7 @@ static int qemu_peek_byte(QEMUFile *f, int offset) { int index = f->buf_index + offset; - if (f->is_write) { - abort(); - } + assert(!qemu_file_is_writable(f)); if (index >= f->buf_size) { qemu_fill_buffer(f); @@ -2199,26 +2307,15 @@ out: return ret; } -static int bdrv_snapshot_find(BlockDriverState *bs, QEMUSnapshotInfo *sn_info, - const char *name) +static BlockDriverState *find_vmstate_bs(void) { - QEMUSnapshotInfo *sn_tab, *sn; - int nb_sns, i, ret; - - ret = -ENOENT; - nb_sns = bdrv_snapshot_list(bs, &sn_tab); - if (nb_sns < 0) - return ret; - for(i = 0; i < nb_sns; i++) { - sn = &sn_tab[i]; - if (!strcmp(sn->id_str, name) || !strcmp(sn->name, name)) { - *sn_info = *sn; - ret = 0; - break; + BlockDriverState *bs = NULL; + while ((bs = bdrv_next(bs))) { + if (bdrv_can_snapshot(bs)) { + return bs; } } - g_free(sn_tab); - return ret; + return NULL; } /* @@ -2275,7 +2372,7 @@ void do_savevm(Monitor *mon, const QDict *qdict) } } - bs = bdrv_snapshots(); + bs = find_vmstate_bs(); if (!bs) { monitor_printf(mon, "No block device can accept snapshots\n"); return; @@ -2356,7 +2453,7 @@ void qmp_xen_save_devices_state(const char *filename, Error **errp) f = qemu_fopen(filename, "wb"); if (!f) { - error_set(errp, QERR_OPEN_FILE_FAILED, filename); + error_setg_file_open(errp, errno, filename); goto the_end; } ret = qemu_save_device_state(f); @@ -2377,7 +2474,7 @@ int load_vmstate(const char *name) QEMUFile *f; int ret; - bs_vm_state = bdrv_snapshots(); + bs_vm_state = find_vmstate_bs(); if (!bs_vm_state) { error_report("No block device supports snapshots"); return -ENOTSUP; @@ -2456,7 +2553,7 @@ void do_delvm(Monitor *mon, const QDict *qdict) int ret; const char *name = qdict_get_str(qdict, "name"); - bs = bdrv_snapshots(); + bs = find_vmstate_bs(); if (!bs) { monitor_printf(mon, "No block device supports snapshots\n"); return; @@ -2486,9 +2583,8 @@ void do_info_snapshots(Monitor *mon, const QDict *qdict) int nb_sns, i, ret, available; int total; int *available_snapshots; - char buf[256]; - bs = bdrv_snapshots(); + bs = find_vmstate_bs(); if (!bs) { monitor_printf(mon, "No available block device supports snapshots\n"); return; @@ -2529,10 +2625,12 @@ void do_info_snapshots(Monitor *mon, const QDict *qdict) } if (total > 0) { - monitor_printf(mon, "%s\n", bdrv_snapshot_dump(buf, sizeof(buf), NULL)); + bdrv_snapshot_dump((fprintf_function)monitor_printf, mon, NULL); + monitor_printf(mon, "\n"); for (i = 0; i < total; i++) { sn = &sn_tab[available_snapshots[i]]; - monitor_printf(mon, "%s\n", bdrv_snapshot_dump(buf, sizeof(buf), sn)); + bdrv_snapshot_dump((fprintf_function)monitor_printf, mon, sn); + monitor_printf(mon, "\n"); } } else { monitor_printf(mon, "There is no suitable snapshot available\n");