#include "qmp-commands.h"
#include "trace.h"
#include "qemu/bitops.h"
+#include "qemu/iov.h"
+#include "block/snapshot.h"
+#include "block/qapi.h"
#define SELF_ANNOUNCE_ROUNDS 5
/* savevm/loadvm support */
#define IO_BUF_SIZE 32768
+#define MAX_IOV_SIZE MIN(IOV_MAX, 64)
struct QEMUFile {
const QEMUFileOps *ops;
void *opaque;
- int is_write;
+
+ int64_t bytes_xfer;
+ int64_t xfer_limit;
int64_t pos; /* start of buffer when writing, end of buffer
when reading */
int buf_size; /* 0 when writing */
uint8_t buf[IO_BUF_SIZE];
+ struct iovec iov[MAX_IOV_SIZE];
+ unsigned int iovcnt;
+
int last_error;
};
qemu_coroutine_yield();
}
+static ssize_t socket_writev_buffer(void *opaque, struct iovec *iov, int iovcnt,
+ int64_t pos)
+{
+ QEMUFileSocket *s = opaque;
+ ssize_t len;
+ ssize_t size = iov_size(iov, iovcnt);
+
+ len = iov_send(s->fd, iov, iovcnt, 0, size);
+ if (len < size) {
+ len = -socket_error();
+ }
+ return len;
+}
+
static int socket_get_fd(void *opaque)
{
QEMUFileSocket *s = opaque;
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;
QEMUFileStdio *s = opaque;
int ret = 0;
- if (s->file->ops->put_buffer) {
+ if (s->file->ops->put_buffer || s->file->ops->writev_buffer) {
int fd = fileno(s->stdio_file);
struct stat st;
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;
}
.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') ||
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 = {
static const QEMUFileOps socket_write_ops = {
.get_fd = socket_get_fd,
- .put_buffer = socket_put_buffer,
+ .writev_buffer = socket_writev_buffer,
.close = socket_close
};
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);
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)
{
};
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)
f->opaque = opaque;
f->ops = ops;
- f->is_write = 0;
-
return f;
}
}
}
-/** Flushes QEMUFile buffer
+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)
{
- int ret = 0;
+ ssize_t ret = 0;
- if (!f->ops->put_buffer) {
+ if (!qemu_file_is_writable(f)) {
return;
}
- if (f->is_write && f->buf_index > 0) {
- ret = f->ops->put_buffer(f->opaque, f->buf, f->pos, f->buf_index);
- if (ret >= 0) {
- f->pos += f->buf_index;
+
+ if (f->ops->writev_buffer) {
+ if (f->iovcnt > 0) {
+ ret = f->ops->writev_buffer(f->opaque, f->iov, f->iovcnt, f->pos);
+ }
+ } else {
+ if (f->buf_index > 0) {
+ ret = f->ops->put_buffer(f->opaque, f->buf, f->pos, f->buf_index);
}
- f->buf_index = 0;
}
+ if (ret >= 0) {
+ f->pos += ret;
+ }
+ f->buf_index = 0;
+ f->iovcnt = 0;
if (ret < 0) {
qemu_file_set_error(f, ret);
}
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) {
return ret;
}
-void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, int size)
+static void add_to_iovec(QEMUFile *f, const uint8_t *buf, int size)
{
- int l;
+ /* check for adjacent buffer and coalesce them */
+ if (f->iovcnt > 0 && buf == f->iov[f->iovcnt - 1].iov_base +
+ f->iov[f->iovcnt - 1].iov_len) {
+ f->iov[f->iovcnt - 1].iov_len += size;
+ } else {
+ 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->ops->writev_buffer) {
+ qemu_put_buffer(f, buf, size);
+ return;
+ }
if (f->last_error) {
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->bytes_xfer += size;
+ add_to_iovec(f, buf, size);
+}
+
+void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, int size)
+{
+ int l;
+
+ if (f->last_error) {
+ return;
}
while (size > 0) {
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;
- buf += l;
- size -= l;
- if (f->buf_index >= IO_BUF_SIZE) {
+ if (f->buf_index == IO_BUF_SIZE) {
qemu_fflush(f);
- if (qemu_file_get_error(f)) {
- break;
- }
}
+ if (qemu_file_get_error(f)) {
+ break;
+ }
+ buf += l;
+ size -= l;
}
}
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->bytes_xfer++;
+ if (f->ops->writev_buffer) {
+ add_to_iovec(f, f->buf + f->buf_index, 1);
}
-
- f->buf[f->buf_index++] = v;
- f->is_write = 1;
- if (f->buf_index >= IO_BUF_SIZE) {
+ f->buf_index++;
+ if (f->buf_index == IO_BUF_SIZE) {
qemu_fflush(f);
}
}
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;
{
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);
int qemu_file_rate_limit(QEMUFile *f)
{
- if (f->ops->rate_limit)
- return f->ops->rate_limit(f->opaque);
-
+ if (qemu_file_get_error(f)) {
+ return 1;
+ }
+ if (f->xfer_limit > 0 && f->bytes_xfer > f->xfer_limit) {
+ return 1;
+ }
return 0;
}
int64_t qemu_file_get_rate_limit(QEMUFile *f)
{
- if (f->ops->get_rate_limit)
- return f->ops->get_rate_limit(f->opaque);
-
- return 0;
+ return f->xfer_limit;
}
-int64_t qemu_file_set_rate_limit(QEMUFile *f, int64_t new_rate)
+void qemu_file_set_rate_limit(QEMUFile *f, int64_t limit)
{
- /* any failed or completed migration keeps its state to allow probing of
- * migration data, but has no associated file anymore */
- if (f && f->ops->set_rate_limit)
- return f->ops->set_rate_limit(f->opaque, new_rate);
+ f->xfer_limit = limit;
+}
- return 0;
+void qemu_file_reset_rate_limit(QEMUFile *f)
+{
+ f->bytes_xfer = 0;
}
void qemu_put_be16(QEMUFile *f, unsigned int v)
.put = put_uint64,
};
+/* 64 bit unsigned int. See that the received value is the same than the one
+ in the field */
+
+static int get_uint64_equal(QEMUFile *f, void *pv, size_t size)
+{
+ uint64_t *v = pv;
+ uint64_t v2;
+ qemu_get_be64s(f, &v2);
+
+ if (*v == v2) {
+ return 0;
+ }
+ return -EINVAL;
+}
+
+const VMStateInfo vmstate_info_uint64_equal = {
+ .name = "int64 equal",
+ .get = get_uint64_equal,
+ .put = put_uint64,
+};
+
/* 8 bit int. See that the received value is the same than the one
in the field */
.put = put_uint16,
};
+/* floating point */
+
+static int get_float64(QEMUFile *f, void *pv, size_t size)
+{
+ float64 *v = pv;
+
+ *v = make_float64(qemu_get_be64(f));
+ return 0;
+}
+
+static void put_float64(QEMUFile *f, void *pv, size_t size)
+{
+ uint64_t *v = pv;
+
+ qemu_put_be64(f, float64_val(*v));
+}
+
+const VMStateInfo vmstate_info_float64 = {
+ .name = "float64",
+ .get = get_float64,
+ .put = put_float64,
+};
+
/* timers */
static int get_timer(QEMUFile *f, void *pv, size_t size)
return 0;
}
-int vmstate_register(DeviceState *dev, int instance_id,
- const VMStateDescription *vmsd, void *opaque)
-{
- return vmstate_register_with_alias_id(dev, instance_id, vmsd,
- opaque, -1, 0);
-}
-
void vmstate_unregister(DeviceState *dev, const VMStateDescription *vmsd,
void *opaque)
{
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;
}
/*
}
}
- bs = bdrv_snapshots();
+ bs = find_vmstate_bs();
if (!bs) {
monitor_printf(mon, "No block device can accept snapshots\n");
return;
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;
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;
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;
}
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");