tests/migration/guestperf: Add --iter argument to batch runs

Allow batch runs to be executed multiple times. This is useful for
collecting averages.

Signed-off-by: Fabiano Rosas <farosas@suse.de>

docs/devel/migration.rst

@@ -39,6 +39,8 @@ over any transport.
 - exec migration: do the migration using the stdin/stdout through a process.
 - fd migration: do the migration using a file descriptor that is
   passed to QEMU.  QEMU doesn't care how this file descriptor is opened.
+- file migration: do the migration using a file that is passed by name
+  to QEMU.
 
 In addition, support is included for migration using RDMA, which
 transports the page data using ``RDMA``, where the hardware takes care of
@@ -566,6 +568,20 @@ Others (especially either older devices or system devices which for
 some reason don't have a bus concept) make use of the ``instance id``
 for otherwise identically named devices.
 
+Fixed-ram format
+----------------
+
+When the ``fixed-ram`` capability is enabled, a slightly different
+stream format is used for the RAM section. Instead of having a
+sequential stream of pages that follow the RAMBlock headers, the dirty
+pages for a RAMBlock follow its header. This ensures that each RAM
+page has a fixed offset in the resulting migration stream.
+
+The ``fixed-ram`` capaility can be enabled in both source and
+destination with:
+
+    ``migrate_set_capability fixed-ram on``
+
 Return path
 -----------
 

include/exec/ramblock.h

@@ -44,6 +44,14 @@ struct RAMBlock {
     size_t page_size;
     /* dirty bitmap used during migration */
     unsigned long *bmap;
+    /* shadow dirty bitmap used when migrating to a file */
+    unsigned long *shadow_bmap;
+    /*
+     * offset in the file pages belonging to this ramblock are saved,
+     * used only during migration to a file.
+     */
+    off_t bitmap_offset;
+    uint64_t pages_offset;
     /* bitmap of already received pages in postcopy */
     unsigned long *receivedmap;
 

include/io/channel-file.h

@@ -22,6 +22,7 @@
 #define QIO_CHANNEL_FILE_H
 
 #include "io/channel.h"
+#include "io/task.h"
 #include "qom/object.h"
 
 #define TYPE_QIO_CHANNEL_FILE "qio-channel-file"

include/io/channel.h

@@ -33,8 +33,10 @@ OBJECT_DECLARE_TYPE(QIOChannel, QIOChannelClass,
 #define QIO_CHANNEL_ERR_BLOCK -2
 
 #define QIO_CHANNEL_WRITE_FLAG_ZERO_COPY 0x1
+#define QIO_CHANNEL_WRITE_FLAG_WITH_OFFSET 0x2
 
 #define QIO_CHANNEL_READ_FLAG_MSG_PEEK 0x1
+#define QIO_CHANNEL_READ_FLAG_WITH_OFFSET 0x2
 
 typedef enum QIOChannelFeature QIOChannelFeature;
 
@@ -44,6 +46,7 @@ enum QIOChannelFeature {
     QIO_CHANNEL_FEATURE_LISTEN,
     QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY,
     QIO_CHANNEL_FEATURE_READ_MSG_PEEK,
+    QIO_CHANNEL_FEATURE_SEEKABLE,
 };
 
 
@@ -128,6 +131,16 @@ struct QIOChannelClass {
                            Error **errp);
 
     /* Optional callbacks */
+    ssize_t (*io_pwritev)(QIOChannel *ioc,
+                          const struct iovec *iov,
+                          size_t niov,
+                          off_t offset,
+                          Error **errp);
+    ssize_t (*io_preadv)(QIOChannel *ioc,
+                         const struct iovec *iov,
+                         size_t niov,
+                         off_t offset,
+                         Error **errp);
     int (*io_shutdown)(QIOChannel *ioc,
                        QIOChannelShutdown how,
                        Error **errp);
@@ -510,6 +523,126 @@ int qio_channel_set_blocking(QIOChannel *ioc,
 int qio_channel_close(QIOChannel *ioc,
                       Error **errp);
 
+/**
+ * qio_channel_pwritev_full
+ * @ioc: the channel object
+ * @iov: the array of memory regions to write data from
+ * @niov: the length of the @iov array
+ * @offset: offset in the channel where writes should begin
+ * @errp: pointer to a NULL-initialized error object
+ *
+ * Not all implementations will support this facility, so may report
+ * an error. To avoid errors, the caller may check for the feature
+ * flag QIO_CHANNEL_FEATURE_SEEKABLE prior to calling this method.
+ *
+ * Behaves as qio_channel_writev_full, apart from not supporting
+ * sending of file handles as well as beginning the write at the
+ * passed @offset
+ *
+ */
+ssize_t qio_channel_pwritev_full(QIOChannel *ioc, const struct iovec *iov,
+                                 size_t niov, off_t offset, Error **errp);
+
+/**
+ * qio_channel_write_full_all:
+ * @ioc: the channel object
+ * @iov: the array of memory regions to write data from
+ * @niov: the length of the @iov array
+ * @offset: the iovec offset in the file where to write the data
+ * @fds: an array of file handles to send
+ * @nfds: number of file handles in @fds
+ * @flags: write flags (QIO_CHANNEL_WRITE_FLAG_*)
+ * @errp: pointer to a NULL-initialized error object
+ *
+ *
+ * Selects between a writev or pwritev channel writer function.
+ *
+ * If QIO_CHANNEL_WRITE_FLAG_OFFSET is passed in flags, pwritev is
+ * used and @offset is expected to be a meaningful value, @fds and
+ * @nfds are ignored; otherwise uses writev and @offset is ignored.
+ *
+ * Returns: 0 if all bytes were written, or -1 on error
+ */
+int qio_channel_write_full_all(QIOChannel *ioc, const struct iovec *iov,
+                               size_t niov, off_t offset, int *fds, size_t nfds,
+                               int flags, Error **errp);
+
+/**
+ * qio_channel_pwritev
+ * @ioc: the channel object
+ * @buf: the memory region to write data into
+ * @buflen: the number of bytes to @buf
+ * @offset: offset in the channel where writes should begin
+ * @errp: pointer to a NULL-initialized error object
+ *
+ * Not all implementations will support this facility, so may report
+ * an error. To avoid errors, the caller may check for the feature
+ * flag QIO_CHANNEL_FEATURE_SEEKABLE prior to calling this method.
+ *
+ */
+ssize_t qio_channel_pwritev(QIOChannel *ioc, char *buf, size_t buflen,
+                            off_t offset, Error **errp);
+
+/**
+ * qio_channel_preadv_full
+ * @ioc: the channel object
+ * @iov: the array of memory regions to read data into
+ * @niov: the length of the @iov array
+ * @offset: offset in the channel where writes should begin
+ * @errp: pointer to a NULL-initialized error object
+ *
+ * Not all implementations will support this facility, so may report
+ * an error.  To avoid errors, the caller may check for the feature
+ * flag QIO_CHANNEL_FEATURE_SEEKABLE prior to calling this method.
+ *
+ * Behaves as qio_channel_readv_full, apart from not supporting
+ * receiving of file handles as well as beginning the read at the
+ * passed @offset
+ *
+ */
+ssize_t qio_channel_preadv_full(QIOChannel *ioc, const struct iovec *iov,
+                                size_t niov, off_t offset, Error **errp);
+
+/**
+ * qio_channel_read_full_all:
+ * @ioc: the channel object
+ * @iov: the array of memory regions to read data to
+ * @niov: the length of the @iov array
+ * @offset: the iovec offset in the file from where to read the data
+ * @fds: an array of file handles to send
+ * @nfds: number of file handles in @fds
+ * @flags: read flags (QIO_CHANNEL_READ_FLAG_*)
+ * @errp: pointer to a NULL-initialized error object
+ *
+ *
+ * Selects between a readv or preadv channel reader function.
+ *
+ * If QIO_CHANNEL_READ_FLAG_OFFSET is passed in flags, preadv is
+ * used and @offset is expected to be a meaningful value, @fds and
+ * @nfds are ignored; otherwise uses readv and @offset is ignored.
+ *
+ * Returns: 0 if all bytes were read, or -1 on error
+ */
+int qio_channel_read_full_all(QIOChannel *ioc, const struct iovec *iov,
+                              size_t niov, off_t offset,
+                              int flags, Error **errp);
+
+/**
+ * qio_channel_preadv
+ * @ioc: the channel object
+ * @buf: the memory region to write data into
+ * @buflen: the number of bytes to @buf
+ * @offset: offset in the channel where writes should begin
+ * @errp: pointer to a NULL-initialized error object
+ *
+ * Not all implementations will support this facility, so may report
+ * an error.  To avoid errors, the caller may check for the feature
+ * flag QIO_CHANNEL_FEATURE_SEEKABLE prior to calling this method.
+ *
+ */
+ssize_t qio_channel_preadv(QIOChannel *ioc, char *buf, size_t buflen,
+                           off_t offset, Error **errp);
+
 /**
  * qio_channel_shutdown:
  * @ioc: the channel object

include/migration/qemu-file-types.h

@@ -50,6 +50,8 @@ unsigned int qemu_get_be16(QEMUFile *f);
 unsigned int qemu_get_be32(QEMUFile *f);
 uint64_t qemu_get_be64(QEMUFile *f);
 
+bool qemu_file_is_seekable(QEMUFile *f);
+
 static inline void qemu_put_be64s(QEMUFile *f, const uint64_t *pv)
 {
     qemu_put_be64(f, *pv);

include/qemu/osdep.h

@@ -570,6 +570,8 @@ int qemu_lock_fd_test(int fd, int64_t start, int64_t len, bool exclusive);
 bool qemu_has_ofd_lock(void);
 #endif
 
+bool qemu_has_direct_io(void);
+
 #if defined(__HAIKU__) && defined(__i386__)
 #define FMT_pid "%ld"
 #elif defined(WIN64)

io/channel-file.c

@@ -35,6 +35,10 @@ qio_channel_file_new_fd(int fd)
 
     ioc->fd = fd;
 
+    if (lseek(fd, 0, SEEK_CUR) != (off_t)-1) {
+        qio_channel_set_feature(QIO_CHANNEL(ioc), QIO_CHANNEL_FEATURE_SEEKABLE);
+    }
+
     trace_qio_channel_file_new_fd(ioc, fd);
 
     return ioc;
@@ -59,6 +63,10 @@ qio_channel_file_new_path(const char *path,
         return NULL;
     }
 
+    if (lseek(ioc->fd, 0, SEEK_CUR) != (off_t)-1) {
+        qio_channel_set_feature(QIO_CHANNEL(ioc), QIO_CHANNEL_FEATURE_SEEKABLE);
+    }
+
     trace_qio_channel_file_new_path(ioc, path, flags, mode, ioc->fd);
 
     return ioc;
@@ -137,6 +145,56 @@ static ssize_t qio_channel_file_writev(QIOChannel *ioc,
     return ret;
 }
 
+static ssize_t qio_channel_file_preadv(QIOChannel *ioc,
+                                       const struct iovec *iov,
+                                       size_t niov,
+                                       off_t offset,
+                                       Error **errp)
+{
+    QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc);
+    ssize_t ret;
+
+ retry:
+    ret = preadv(fioc->fd, iov, niov, offset);
+    if (ret < 0) {
+        if (errno == EAGAIN) {
+            return QIO_CHANNEL_ERR_BLOCK;
+        }
+        if (errno == EINTR) {
+            goto retry;
+        }
+
+        error_setg_errno(errp, errno, "Unable to read from file");
+        return -1;
+    }
+
+    return ret;
+}
+
+static ssize_t qio_channel_file_pwritev(QIOChannel *ioc,
+                                        const struct iovec *iov,
+                                        size_t niov,
+                                        off_t offset,
+                                        Error **errp)
+{
+    QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc);
+    ssize_t ret;
+
+ retry:
+    ret = pwritev(fioc->fd, iov, niov, offset);
+    if (ret <= 0) {
+        if (errno == EAGAIN) {
+            return QIO_CHANNEL_ERR_BLOCK;
+        }
+        if (errno == EINTR) {
+            goto retry;
+        }
+        error_setg_errno(errp, errno, "Unable to write to file");
+        return -1;
+    }
+    return ret;
+}
+
 static int qio_channel_file_set_blocking(QIOChannel *ioc,
                                          bool enabled,
                                          Error **errp)
@@ -218,6 +276,8 @@ static void qio_channel_file_class_init(ObjectClass *klass,
     ioc_klass->io_writev = qio_channel_file_writev;
     ioc_klass->io_readv = qio_channel_file_readv;
     ioc_klass->io_set_blocking = qio_channel_file_set_blocking;
+    ioc_klass->io_pwritev = qio_channel_file_pwritev;
+    ioc_klass->io_preadv = qio_channel_file_preadv;
     ioc_klass->io_seek = qio_channel_file_seek;
     ioc_klass->io_close = qio_channel_file_close;
     ioc_klass->io_create_watch = qio_channel_file_create_watch;

io/channel.c

@@ -446,6 +446,146 @@ GSource *qio_channel_add_watch_source(QIOChannel *ioc,
 }
 
 
+ssize_t qio_channel_pwritev_full(QIOChannel *ioc, const struct iovec *iov,
+                                 size_t niov, off_t offset, Error **errp)
+{
+    QIOChannelClass *klass = QIO_CHANNEL_GET_CLASS(ioc);
+
+    if (!klass->io_pwritev) {
+        error_setg(errp, "Channel does not support pwritev");
+        return -1;
+    }
+
+    if (!qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_SEEKABLE)) {
+        error_setg_errno(errp, EINVAL, "Requested channel is not seekable");
+        return -1;
+    }
+
+    return klass->io_pwritev(ioc, iov, niov, offset, errp);
+}
+
+static int qio_channel_preadv_pwritev_contiguous(QIOChannel *ioc,
+                                                 const struct iovec *iov,
+                                                 size_t niov, off_t offset,
+                                                 bool is_write, Error **errp)
+{
+    ssize_t ret;
+    int i, slice_idx, slice_num;
+    uint64_t base, next, file_offset;
+    size_t len;
+
+    slice_idx = 0;
+    slice_num = 1;
+
+    /*
+     * If the iov array doesn't have contiguous elements, we need to
+     * split it in slices because we only have one (file) 'offset' for
+     * the whole iov. Do this here so callers don't need to break the
+     * iov array themselves.
+     */
+    for (i = 0; i < niov; i++, slice_num++) {
+        base = (uint64_t) iov[i].iov_base;
+
+        if (i != niov - 1) {
+            len = iov[i].iov_len;
+            next = (uint64_t) iov[i + 1].iov_base;
+
+            if (base + len == next) {
+                continue;
+            }
+        }
+
+        /*
+         * Use the offset of the first element of the segment that
+         * we're sending.
+         */
+        file_offset = offset + (uint64_t) iov[slice_idx].iov_base;
+
+        if (is_write) {
+            ret = qio_channel_pwritev_full(ioc, &iov[slice_idx], slice_num,
+                                           file_offset, errp);
+        } else {
+            ret = qio_channel_preadv_full(ioc, &iov[slice_idx], slice_num,
+                                          file_offset, errp);
+        }
+
+        if (ret < 0) {
+            break;
+        }
+
+        slice_idx += slice_num;
+        slice_num = 0;
+    }
+
+    return (ret < 0) ? -1 : 0;
+}
+
+int qio_channel_write_full_all(QIOChannel *ioc,
+                                const struct iovec *iov,
+                                size_t niov, off_t offset,
+                                int *fds, size_t nfds,
+                                int flags, Error **errp)
+{
+    if (flags & QIO_CHANNEL_WRITE_FLAG_WITH_OFFSET) {
+        return qio_channel_preadv_pwritev_contiguous(ioc, iov, niov,
+                                                     offset, true, errp);
+    }
+
+    return qio_channel_writev_full_all(ioc, iov, niov, NULL, 0, flags, errp);
+}
+
+ssize_t qio_channel_pwritev(QIOChannel *ioc, char *buf, size_t buflen,
+                            off_t offset, Error **errp)
+{
+    struct iovec iov = {
+        .iov_base = buf,
+        .iov_len = buflen
+    };
+
+    return qio_channel_pwritev_full(ioc, &iov, 1, offset, errp);
+}
+
+ssize_t qio_channel_preadv_full(QIOChannel *ioc, const struct iovec *iov,
+                                size_t niov, off_t offset, Error **errp)
+{
+    QIOChannelClass *klass = QIO_CHANNEL_GET_CLASS(ioc);
+
+    if (!klass->io_preadv) {
+        error_setg(errp, "Channel does not support preadv");
+        return -1;
+    }
+
+    if (!qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_SEEKABLE)) {
+        error_setg_errno(errp, EINVAL, "Requested channel is not seekable");
+        return -1;
+    }
+
+    return klass->io_preadv(ioc, iov, niov, offset, errp);
+}
+
+int qio_channel_read_full_all(QIOChannel *ioc, const struct iovec *iov,
+                              size_t niov, off_t offset,
+                              int flags, Error **errp)
+{
+    if (flags & QIO_CHANNEL_READ_FLAG_WITH_OFFSET) {
+        return qio_channel_preadv_pwritev_contiguous(ioc, iov, niov,
+                                                     offset, false, errp);
+    }
+
+    return qio_channel_readv_full_all(ioc, iov, niov, NULL, NULL, errp);
+}
+
+ssize_t qio_channel_preadv(QIOChannel *ioc, char *buf, size_t buflen,
+                           off_t offset, Error **errp)
+{
+    struct iovec iov = {
+        .iov_base = buf,
+        .iov_len = buflen
+    };
+
+    return qio_channel_preadv_full(ioc, &iov, 1, offset, errp);
+}
+
 int qio_channel_shutdown(QIOChannel *ioc,
                          QIOChannelShutdown how,
                          Error **errp)

migration/file.c

@@ -0,0 +1,131 @@
+#include "qemu/osdep.h"
+#include "io/channel-file.h"
+#include "file.h"
+#include "qemu/error-report.h"
+#include "migration.h"
+#include "options.h"
+
+static struct FileOutgoingArgs {
+    char *fname;
+    int flags;
+    int mode;
+} outgoing_args;
+
+static void qio_channel_file_connect_worker(QIOTask *task, gpointer opaque)
+{
+    /* noop */
+}
+
+static void file_migration_cancel(Error *errp)
+{
+    MigrationState *s;
+
+    s = migrate_get_current();
+
+    migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
+                      MIGRATION_STATUS_FAILED);
+    migration_cancel(errp);
+}
+
+int file_send_channel_destroy(QIOChannel *ioc)
+{
+    if (ioc) {
+        qio_channel_close(ioc, NULL);
+        object_unref(OBJECT(ioc));
+    }
+    g_free(outgoing_args.fname);
+    outgoing_args.fname = NULL;
+
+    return 0;
+}
+
+void file_send_channel_create(QIOTaskFunc f, void *data)
+{
+    QIOChannelFile *ioc;
+    QIOTask *task;
+    Error *errp = NULL;
+    int flags = outgoing_args.flags;
+
+    if (migrate_direct_io() && qemu_has_direct_io()) {
+        /*
+         * Enable O_DIRECT for the secondary channels. These are used
+         * for sending ram pages and writes should be guaranteed to be
+         * aligned to at least page size.
+         */
+        flags |= O_DIRECT;
+    }
+
+    ioc = qio_channel_file_new_path(outgoing_args.fname, flags,
+                                    outgoing_args.mode, &errp);
+    if (!ioc) {
+        file_migration_cancel(errp);
+        return;
+    }
+
+    task = qio_task_new(OBJECT(ioc), f, (gpointer)data, NULL);
+    qio_task_run_in_thread(task, qio_channel_file_connect_worker,
+                           (gpointer)data, NULL, NULL);
+}
+
+void file_start_outgoing_migration(MigrationState *s, const char *fname, Error **errp)
+{
+    QIOChannelFile *ioc;
+    int flags = O_CREAT | O_TRUNC | O_WRONLY;
+    mode_t mode = 0660;
+
+    ioc = qio_channel_file_new_path(fname, flags, mode, errp);
+    if (!ioc) {
+        error_report("Error creating migration outgoing channel");
+        return;
+    }
+
+    outgoing_args.fname = g_strdup(fname);
+    outgoing_args.flags = flags;
+    outgoing_args.mode = mode;
+
+    qio_channel_set_name(QIO_CHANNEL(ioc), "migration-file-outgoing");
+    migration_channel_connect(s, QIO_CHANNEL(ioc), NULL, NULL);
+    object_unref(OBJECT(ioc));
+}
+
+static void file_process_migration_incoming(QIOTask *task, gpointer opaque)
+{
+    QIOChannelFile *ioc = opaque;
+
+    migration_channel_process_incoming(QIO_CHANNEL(ioc));
+    object_unref(OBJECT(ioc));
+}
+
+void file_start_incoming_migration(const char *fname, Error **errp)
+{
+    QIOChannelFile *ioc;
+    QIOTask *task;
+    int channels = 1;
+    int i = 0, fd;
+
+    ioc = qio_channel_file_new_path(fname, O_RDONLY, 0, errp);
+    if (!ioc) {
+        goto out;
+    }
+
+    if (migrate_multifd()) {
+        channels += migrate_multifd_channels();
+    }
+
+    fd = ioc->fd;
+
+    do {
+        qio_channel_set_name(QIO_CHANNEL(ioc), "migration-file-incoming");
+        task = qio_task_new(OBJECT(ioc), file_process_migration_incoming,
+                            (gpointer)ioc, NULL);
+
+        qio_task_run_in_thread(task, qio_channel_file_connect_worker,
+                               (gpointer)ioc, NULL, NULL);
+    } while (++i < channels && (ioc = qio_channel_file_new_fd(fd)));
+
+out:
+    if (!ioc) {
+        error_report("Error creating migration incoming channel");
+        return;
+    }
+}

migration/file.h

@@ -0,0 +1,14 @@
+#ifndef QEMU_MIGRATION_FILE_H
+#define QEMU_MIGRATION_FILE_H
+
+#include "io/task.h"
+#include "channel.h"
+
+void file_start_outgoing_migration(MigrationState *s,
+                                   const char *filename,
+                                   Error **errp);
+
+void file_start_incoming_migration(const char *fname, Error **errp);
+void file_send_channel_create(QIOTaskFunc f, void *data);
+int file_send_channel_destroy(QIOChannel *ioc);
+#endif

migration/meson.build

@@ -16,6 +16,7 @@ softmmu_ss.add(files(
   'dirtyrate.c',
   'exec.c',
   'fd.c',
+  'file.c',
   'global_state.c',
   'migration-hmp-cmds.c',
   'migration.c',

migration/migration-hmp-cmds.c

@@ -364,6 +364,11 @@ void hmp_info_migrate_parameters(Monitor *mon, const QDict *qdict)
                 }
             }
         }
+        if (params->has_direct_io) {
+            monitor_printf(mon, "%s: %s\n",
+                           MigrationParameter_str(MIGRATION_PARAMETER_DIRECT_IO),
+                           params->direct_io ? "on" : "off");
+        }
     }
 
     qapi_free_MigrationParameters(params);
@@ -620,6 +625,10 @@ void hmp_migrate_set_parameter(Monitor *mon, const QDict *qdict)
         error_setg(&err, "The block-bitmap-mapping parameter can only be set "
                    "through QMP");
         break;
+    case MIGRATION_PARAMETER_DIRECT_IO:
+        p->has_direct_io = true;
+        visit_type_bool(v, param, &p->direct_io, &err);
+        break;
     default:
         assert(0);
     }

migration/migration.c

@@ -20,6 +20,7 @@
 #include "migration/blocker.h"
 #include "exec.h"
 #include "fd.h"
+#include "file.h"
 #include "socket.h"
 #include "sysemu/runstate.h"
 #include "sysemu/sysemu.h"
@@ -105,7 +106,7 @@ static bool migration_needs_multiple_sockets(void)
 static bool uri_supports_multi_channels(const char *uri)
 {
     return strstart(uri, "tcp:", NULL) || strstart(uri, "unix:", NULL) ||
-           strstart(uri, "vsock:", NULL);
+           strstart(uri, "vsock:", NULL) || strstart(uri, "file:", NULL);
 }
 
 static bool
@@ -442,6 +443,8 @@ static void qemu_start_incoming_migration(const char *uri, Error **errp)
         exec_start_incoming_migration(p, errp);
     } else if (strstart(uri, "fd:", &p)) {
         fd_start_incoming_migration(p, errp);
+    } else if (strstart(uri, "file:", &p)) {
+        file_start_incoming_migration(p, errp);
     } else {
         error_setg(errp, "unknown migration protocol: %s", uri);
     }
@@ -491,6 +494,10 @@ static void process_incoming_migration_bh(void *opaque)
     } else if (migration_incoming_colo_enabled()) {
         migration_incoming_disable_colo();
         vm_start();
+    } else if (global_state_received() &&
+               global_state_get_runstate() == RUN_STATE_PAUSED &&
+               (autostart || migrate_suspend())) {
+        vm_start();
     } else {
         runstate_set(global_state_get_runstate());
     }
@@ -695,6 +702,8 @@ void migration_ioc_process_incoming(QIOChannel *ioc, Error **errp)
         }
 
         default_channel = (channel_magic == cpu_to_be32(QEMU_VM_FILE_MAGIC));
+    } else if (migrate_multifd() && migrate_fixed_ram()) {
+        default_channel = multifd_recv_first_channel();
     } else {
         default_channel = !mis->from_src_file;
     }
@@ -1397,6 +1406,7 @@ void migrate_init(MigrationState *s)
     error_free(s->error);
     s->error = NULL;
     s->hostname = NULL;
+    s->vmdesc = NULL;
 
     migrate_set_state(&s->state, MIGRATION_STATUS_NONE, MIGRATION_STATUS_SETUP);
 
@@ -1662,6 +1672,8 @@ void qmp_migrate(const char *uri, bool has_blk, bool blk,
         exec_start_outgoing_migration(s, p, &local_err);
     } else if (strstart(uri, "fd:", &p)) {
         fd_start_outgoing_migration(s, p, &local_err);
+    } else if (strstart(uri, "file:", &p)) {
+        file_start_outgoing_migration(s, p, &local_err);
     } else {
         if (!(has_resume && resume)) {
             yank_unregister_instance(MIGRATION_YANK_INSTANCE);
@@ -2625,7 +2637,7 @@ static MigThrError migration_detect_error(MigrationState *s)
     }
 }
 
-static void migration_calculate_complete(MigrationState *s)
+void migration_calculate_complete(MigrationState *s)
 {
     uint64_t bytes = migration_transferred_bytes(s->to_dst_file);
     int64_t end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
@@ -2657,8 +2669,7 @@ static void update_iteration_initial_status(MigrationState *s)
     s->iteration_initial_pages = ram_get_total_transferred_pages();
 }
 
-static void migration_update_counters(MigrationState *s,
-                                      int64_t current_time)
+void migration_update_counters(MigrationState *s, int64_t current_time)
 {
     uint64_t transferred, transferred_pages, time_spent;
     uint64_t current_bytes; /* bytes transferred since the beginning */
@@ -2757,6 +2768,7 @@ static void migration_iteration_finish(MigrationState *s)
     case MIGRATION_STATUS_COMPLETED:
         migration_calculate_complete(s);
         runstate_set(RUN_STATE_POSTMIGRATE);
+        trace_migration_status((int)s->mbps / 8, (int)s->pages_per_second, s->total_time);
         break;
     case MIGRATION_STATUS_COLO:
         assert(migrate_colo());
@@ -3165,6 +3177,33 @@ fail:
     return NULL;
 }
 
+static int fixed_ram_save_setup(MigrationState *s, Error **errp)
+{
+    if (!migrate_fixed_ram()) {
+        return 0;
+    }
+
+    if (!qemu_file_is_seekable(s->to_dst_file)) {
+        error_setg(errp, "Directly mapped memory requires a seekable transport");
+        return -1;
+    }
+
+    /*
+     * Fixed-ram migration is currently only used to address "vm
+     * suspend" scenarios, so the VM would always be stopped at the
+     * end of migration. Check if we can stop it now and use the
+     * knowledge that the VM is stopped to implement optimizations
+     * down the line.
+     */
+    if (migrate_suspend()) {
+        if (vm_stop_force_state(RUN_STATE_PAUSED)) {
+            return -1;
+        }
+    }
+
+    return 0;
+}
+
 void migrate_fd_connect(MigrationState *s, Error *error_in)
 {
     Error *local_err = NULL;
@@ -3247,6 +3286,12 @@ void migrate_fd_connect(MigrationState *s, Error *error_in)
         return;
     }
 
+    if (fixed_ram_save_setup(s, &local_err) < 0) {
+        migrate_fd_cleanup(s);
+        migrate_fd_error(s, local_err);
+        return;
+    }
+
     if (multifd_save_setup(&local_err) != 0) {
         error_report_err(local_err);
         migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,

migration/migration.h

@@ -440,7 +440,9 @@ struct MigrationState {
 };
 
 void migrate_set_state(int *state, int old_state, int new_state);
-
+void migration_calculate_complete(MigrationState *s);
+void migration_update_counters(MigrationState *s,
+                               int64_t current_time);
 void migration_fd_process_incoming(QEMUFile *f, Error **errp);
 void migration_ioc_process_incoming(QIOChannel *ioc, Error **errp);
 void migration_incoming_process(void);

migration/multifd.c

@@ -17,6 +17,7 @@
 #include "exec/ramblock.h"
 #include "qemu/error-report.h"
 #include "qapi/error.h"
+#include "file.h"
 #include "ram.h"
 #include "migration.h"
 #include "migration-stats.h"
@@ -28,6 +29,7 @@
 #include "threadinfo.h"
 #include "options.h"
 #include "qemu/yank.h"
+#include "io/channel-file.h"
 #include "io/channel-socket.h"
 #include "yank_functions.h"
 
@@ -140,6 +142,7 @@ static void nocomp_recv_cleanup(MultiFDRecvParams *p)
 static int nocomp_recv_pages(MultiFDRecvParams *p, Error **errp)
 {
     uint32_t flags = p->flags & MULTIFD_FLAG_COMPRESSION_MASK;
+    uint64_t read_base = 0;
 
     if (flags != MULTIFD_FLAG_NOCOMP) {
         error_setg(errp, "multifd %u: flags received %x flags expected %x",
@@ -150,7 +153,13 @@ static int nocomp_recv_pages(MultiFDRecvParams *p, Error **errp)
         p->iov[i].iov_base = p->host + p->normal[i];
         p->iov[i].iov_len = p->page_size;
     }
-    return qio_channel_readv_all(p->c, p->iov, p->normal_num, errp);
+
+    if (migrate_fixed_ram()) {
+        read_base = p->pages->block->pages_offset - (uint64_t) p->host;
+    }
+
+    return qio_channel_read_full_all(p->c, p->iov, p->normal_num, read_base,
+                                     p->read_flags, errp);
 }
 
 static MultiFDMethods multifd_nocomp_ops = {
@@ -258,6 +267,19 @@ static void multifd_pages_clear(MultiFDPages_t *pages)
     g_free(pages);
 }
 
+static void multifd_set_file_bitmap(MultiFDSendParams *p, bool set)
+{
+    MultiFDPages_t *pages = p->pages;
+
+    if (!pages->block) {
+        return;
+    }
+
+    for (int i = 0; i < p->normal_num; i++) {
+        ramblock_set_shadow_bmap(pages->block, pages->offset[i], set);
+    }
+}
+
 static void multifd_send_fill_packet(MultiFDSendParams *p)
 {
     MultiFDPacket_t *packet = p->packet;
@@ -510,6 +532,15 @@ static void multifd_send_terminate_threads(Error *err)
     }
 }
 
+static int multifd_send_channel_destroy(QIOChannel *send)
+{
+    if (migrate_to_file()) {
+        return file_send_channel_destroy(send);
+    } else {
+        return socket_send_channel_destroy(send);
+    }
+}
+
 void multifd_save_cleanup(void)
 {
     int i;
@@ -532,7 +563,7 @@ void multifd_save_cleanup(void)
         if (p->registered_yank) {
             migration_ioc_unregister_yank(p->c);
         }
-        socket_send_channel_destroy(p->c);
+        multifd_send_channel_destroy(p->c);
         p->c = NULL;
         qemu_mutex_destroy(&p->mutex);
         qemu_sem_destroy(&p->sem);
@@ -595,6 +626,10 @@ int multifd_send_sync_main(QEMUFile *f)
         }
     }
 
+    if (!migrate_multifd_packets()) {
+        return 0;
+    }
+
     /*
      * When using zero-copy, it's necessary to flush the pages before any of
      * the pages can be sent again, so we'll make sure the new version of the
@@ -650,18 +685,22 @@ static void *multifd_send_thread(void *opaque)
     Error *local_err = NULL;
     int ret = 0;
     bool use_zero_copy_send = migrate_zero_copy_send();
+    bool use_packets = migrate_multifd_packets();
 
     thread = MigrationThreadAdd(p->name, qemu_get_thread_id());
 
     trace_multifd_send_thread_start(p->id);
     rcu_register_thread();
 
-    if (multifd_send_initial_packet(p, &local_err) < 0) {
-        ret = -1;
-        goto out;
+    if (use_packets) {
+        if (multifd_send_initial_packet(p, &local_err) < 0) {
+            ret = -1;
+            goto out;
+        }
+
+        /* initial packet */
+        p->num_packets = 1;
     }
-    /* initial packet */
-    p->num_packets = 1;
 
     while (true) {
         qemu_sem_post(&multifd_send_state->channels_ready);
@@ -673,11 +712,12 @@ static void *multifd_send_thread(void *opaque)
         qemu_mutex_lock(&p->mutex);
 
         if (p->pending_job) {
-            uint64_t packet_num = p->packet_num;
             uint32_t flags;
+            uint64_t write_base;
+
             p->normal_num = 0;
 
-            if (use_zero_copy_send) {
+            if (!use_packets || use_zero_copy_send) {
                 p->iovs_num = 0;
             } else {
                 p->iovs_num = 1;
@@ -695,16 +735,30 @@ static void *multifd_send_thread(void *opaque)
                     break;
                 }
             }
-            multifd_send_fill_packet(p);
+
+            if (use_packets) {
+                multifd_send_fill_packet(p);
+                p->num_packets++;
+                write_base = 0;
+            } else {
+                multifd_set_file_bitmap(p, true);
+
+                /*
+                 * If we subtract the host page now, we don't need to
+                 * pass it into qio_channel_write_full_all() below.
+                 */
+                write_base = p->pages->block->pages_offset -
+                    (uint64_t)p->pages->block->host;
+            }
+
             flags = p->flags;
             p->flags = 0;
-            p->num_packets++;
             p->total_normal_pages += p->normal_num;
             p->pages->num = 0;
             p->pages->block = NULL;
             qemu_mutex_unlock(&p->mutex);
 
-            trace_multifd_send(p->id, packet_num, p->normal_num, flags,
+            trace_multifd_send(p->id, p->packet_num, p->normal_num, flags,
                                p->next_packet_size);
 
             if (use_zero_copy_send) {
@@ -716,14 +770,15 @@ static void *multifd_send_thread(void *opaque)
                 }
                 stat64_add(&mig_stats.multifd_bytes, p->packet_len);
                 stat64_add(&mig_stats.transferred, p->packet_len);
-            } else {
+            } else if (use_packets) {
                 /* Send header using the same writev call */
                 p->iov[0].iov_len = p->packet_len;
                 p->iov[0].iov_base = p->packet;
             }
 
-            ret = qio_channel_writev_full_all(p->c, p->iov, p->iovs_num, NULL,
-                                              0, p->write_flags, &local_err);
+            ret = qio_channel_write_full_all(p->c, p->iov, p->iovs_num,
+                                             write_base, NULL, 0,
+                                             p->write_flags, &local_err);
             if (ret != 0) {
                 break;
             }
@@ -740,6 +795,13 @@ static void *multifd_send_thread(void *opaque)
         } else if (p->quit) {
             qemu_mutex_unlock(&p->mutex);
             break;
+        } else if (!use_packets) {
+            /*
+             * When migrating to a file there's not need for a SYNC
+             * packet, the channels are ready right away.
+             */
+            qemu_sem_post(&multifd_send_state->channels_ready);
+            qemu_mutex_unlock(&p->mutex);
         } else {
             qemu_mutex_unlock(&p->mutex);
             /* sometimes there are spurious wakeups */
@@ -749,6 +811,7 @@ static void *multifd_send_thread(void *opaque)
 out:
     if (local_err) {
         trace_multifd_send_error(p->id);
+        multifd_set_file_bitmap(p, false);
         multifd_send_terminate_threads(local_err);
         error_free(local_err);
     }
@@ -889,26 +952,36 @@ static void multifd_new_send_channel_cleanup(MultiFDSendParams *p,
 static void multifd_new_send_channel_async(QIOTask *task, gpointer opaque)
 {
     MultiFDSendParams *p = opaque;
-    QIOChannel *sioc = QIO_CHANNEL(qio_task_get_source(task));
+    QIOChannel *ioc = QIO_CHANNEL(qio_task_get_source(task));
     Error *local_err = NULL;
 
     trace_multifd_new_send_channel_async(p->id);
     if (!qio_task_propagate_error(task, &local_err)) {
-        p->c = QIO_CHANNEL(sioc);
+        p->c = QIO_CHANNEL(ioc);
         qio_channel_set_delay(p->c, false);
         p->running = true;
-        if (multifd_channel_connect(p, sioc, local_err)) {
+        if (multifd_channel_connect(p, ioc, local_err)) {
             return;
         }
     }
 
-    multifd_new_send_channel_cleanup(p, sioc, local_err);
+    multifd_new_send_channel_cleanup(p, ioc, local_err);
+}
+
+static void multifd_new_send_channel_create(gpointer opaque)
+{
+    if (migrate_to_file()) {
+        file_send_channel_create(multifd_new_send_channel_async, opaque);
+    } else {
+        socket_send_channel_create(multifd_new_send_channel_async, opaque);
+    }
 }
 
 int multifd_save_setup(Error **errp)
 {
     int thread_count;
     uint32_t page_count = MULTIFD_PACKET_SIZE / qemu_target_page_size();
+    bool use_packets = migrate_multifd_packets();
     uint8_t i;
 
     if (!migrate_multifd()) {
@@ -933,25 +1006,33 @@ int multifd_save_setup(Error **errp)
         p->pending_job = 0;
         p->id = i;
         p->pages = multifd_pages_init(page_count);
-        p->packet_len = sizeof(MultiFDPacket_t)
-                      + sizeof(uint64_t) * page_count;
-        p->packet = g_malloc0(p->packet_len);
-        p->packet->magic = cpu_to_be32(MULTIFD_MAGIC);
-        p->packet->version = cpu_to_be32(MULTIFD_VERSION);
+
+        if (use_packets) {
+            p->packet_len = sizeof(MultiFDPacket_t)
+                          + sizeof(uint64_t) * page_count;
+            p->packet = g_malloc0(p->packet_len);
+            p->packet->magic = cpu_to_be32(MULTIFD_MAGIC);
+            p->packet->version = cpu_to_be32(MULTIFD_VERSION);
+
+            /* We need one extra place for the packet header */
+            p->iov = g_new0(struct iovec, page_count + 1);
+        } else {
+            p->iov = g_new0(struct iovec, page_count);
+        }
         p->name = g_strdup_printf("multifdsend_%d", i);
-        /* We need one extra place for the packet header */
-        p->iov = g_new0(struct iovec, page_count + 1);
         p->normal = g_new0(ram_addr_t, page_count);
         p->page_size = qemu_target_page_size();
         p->page_count = page_count;
 
         if (migrate_zero_copy_send()) {
             p->write_flags = QIO_CHANNEL_WRITE_FLAG_ZERO_COPY;
+        } else if (!use_packets) {
+            p->write_flags |= QIO_CHANNEL_WRITE_FLAG_WITH_OFFSET;
         } else {
             p->write_flags = 0;
         }
 
-        socket_send_channel_create(multifd_new_send_channel_async, p);
+        multifd_new_send_channel_create(p);
     }
 
     for (i = 0; i < thread_count; i++) {
@@ -970,6 +1051,8 @@ int multifd_save_setup(Error **errp)
 
 struct {
     MultiFDRecvParams *params;
+    /* array of pages to receive */
+    MultiFDPages_t *pages;
     /* number of created threads */
     int count;
     /* syncs main thread and channels */
@@ -980,6 +1063,66 @@ struct {
     MultiFDMethods *ops;
 } *multifd_recv_state;
 
+static int multifd_recv_pages(QEMUFile *f)
+{
+    int i;
+    static int next_recv_channel;
+    MultiFDRecvParams *p = NULL;
+    MultiFDPages_t *pages = multifd_recv_state->pages;
+
+    /*
+     * next_channel can remain from a previous migration that was
+     * using more channels, so ensure it doesn't overflow if the
+     * limit is lower now.
+     */
+    next_recv_channel %= migrate_multifd_channels();
+    for (i = next_recv_channel;; i = (i + 1) % migrate_multifd_channels()) {
+        p = &multifd_recv_state->params[i];
+
+        qemu_mutex_lock(&p->mutex);
+        if (p->quit) {
+            error_report("%s: channel %d has already quit!", __func__, i);
+            qemu_mutex_unlock(&p->mutex);
+            return -1;
+        }
+        if (!p->pending_job) {
+            p->pending_job++;
+            next_recv_channel = (i + 1) % migrate_multifd_channels();
+            break;
+        }
+        qemu_mutex_unlock(&p->mutex);
+    }
+
+    multifd_recv_state->pages = p->pages;
+    p->pages = pages;
+    qemu_mutex_unlock(&p->mutex);
+    qemu_sem_post(&p->sem);
+
+    return 1;
+}
+
+int multifd_recv_queue_page(QEMUFile *f, RAMBlock *block, ram_addr_t offset)
+{
+    MultiFDPages_t *pages = multifd_recv_state->pages;
+
+    if (!pages->block) {
+        pages->block = block;
+    }
+
+    pages->offset[pages->num] = offset;
+    pages->num++;
+
+    if (pages->num < pages->allocated) {
+        return 1;
+    }
+
+    if (multifd_recv_pages(f) < 0) {
+        return -1;
+    }
+
+    return 1;
+}
+
 static void multifd_recv_terminate_threads(Error *err)
 {
     int i;
@@ -1001,6 +1144,7 @@ static void multifd_recv_terminate_threads(Error *err)
 
         qemu_mutex_lock(&p->mutex);
         p->quit = true;
+        qemu_sem_post(&p->sem);
         /*
          * We could arrive here for two reasons:
          *  - normal quit, i.e. everything went fine, just finished
@@ -1049,9 +1193,12 @@ void multifd_load_cleanup(void)
         object_unref(OBJECT(p->c));
         p->c = NULL;
         qemu_mutex_destroy(&p->mutex);
+        qemu_sem_destroy(&p->sem);
         qemu_sem_destroy(&p->sem_sync);
         g_free(p->name);
         p->name = NULL;
+        multifd_pages_clear(p->pages);
+        p->pages = NULL;
         p->packet_len = 0;
         g_free(p->packet);
         p->packet = NULL;
@@ -1064,6 +1211,8 @@ void multifd_load_cleanup(void)
     qemu_sem_destroy(&multifd_recv_state->sem_sync);
     g_free(multifd_recv_state->params);
     multifd_recv_state->params = NULL;
+    multifd_pages_clear(multifd_recv_state->pages);
+    multifd_recv_state->pages = NULL;
     g_free(multifd_recv_state);
     multifd_recv_state = NULL;
 }
@@ -1072,9 +1221,10 @@ void multifd_recv_sync_main(void)
 {
     int i;
 
-    if (!migrate_multifd()) {
+    if (!migrate_multifd() || !migrate_multifd_packets()) {
         return;
     }
+
     for (i = 0; i < migrate_multifd_channels(); i++) {
         MultiFDRecvParams *p = &multifd_recv_state->params[i];
 
@@ -1099,6 +1249,7 @@ static void *multifd_recv_thread(void *opaque)
 {
     MultiFDRecvParams *p = opaque;
     Error *local_err = NULL;
+    bool use_packets = migrate_multifd_packets();
     int ret;
 
     trace_multifd_recv_thread_start(p->id);
@@ -1106,22 +1257,45 @@ static void *multifd_recv_thread(void *opaque)
 
     while (true) {
         uint32_t flags;
+        p->normal_num = 0;
 
         if (p->quit) {
             break;
         }
 
-        ret = qio_channel_read_all_eof(p->c, (void *)p->packet,
-                                       p->packet_len, &local_err);
-        if (ret == 0 || ret == -1) {   /* 0: EOF  -1: Error */
-            break;
-        }
+        if (use_packets) {
+            ret = qio_channel_read_all_eof(p->c, (void *)p->packet,
+                                           p->packet_len, &local_err);
+            if (ret == 0 || ret == -1) {   /* 0: EOF  -1: Error */
+                break;
+            }
 
-        qemu_mutex_lock(&p->mutex);
-        ret = multifd_recv_unfill_packet(p, &local_err);
-        if (ret) {
-            qemu_mutex_unlock(&p->mutex);
-            break;
+            qemu_mutex_lock(&p->mutex);
+            ret = multifd_recv_unfill_packet(p, &local_err);
+            if (ret) {
+                qemu_mutex_unlock(&p->mutex);
+                break;
+            }
+            p->num_packets++;
+        } else {
+            /*
+             * No packets, so we need to wait for the vmstate code to
+             * queue pages.
+             */
+            qemu_sem_wait(&p->sem);
+            qemu_mutex_lock(&p->mutex);
+            if (!p->pending_job) {
+                qemu_mutex_unlock(&p->mutex);
+                break;
+            }
+
+            for (int i = 0; i < p->pages->num; i++) {
+                p->normal[p->normal_num] = p->pages->offset[i];
+                p->normal_num++;
+            }
+
+            p->pages->num = 0;
+            p->host = p->pages->block->host;
         }
 
         flags = p->flags;
@@ -1129,7 +1303,7 @@ static void *multifd_recv_thread(void *opaque)
         p->flags &= ~MULTIFD_FLAG_SYNC;
         trace_multifd_recv(p->id, p->packet_num, p->normal_num, flags,
                            p->next_packet_size);
-        p->num_packets++;
+
         p->total_normal_pages += p->normal_num;
         qemu_mutex_unlock(&p->mutex);
 
@@ -1144,6 +1318,13 @@ static void *multifd_recv_thread(void *opaque)
             qemu_sem_post(&multifd_recv_state->sem_sync);
             qemu_sem_wait(&p->sem_sync);
         }
+
+        if (!use_packets) {
+            qemu_mutex_lock(&p->mutex);
+            p->pending_job--;
+            p->pages->block = NULL;
+            qemu_mutex_unlock(&p->mutex);
+        }
     }
 
     if (local_err) {
@@ -1164,6 +1345,7 @@ int multifd_load_setup(Error **errp)
 {
     int thread_count;
     uint32_t page_count = MULTIFD_PACKET_SIZE / qemu_target_page_size();
+    bool use_packets = migrate_multifd_packets();
     uint8_t i;
 
     /*
@@ -1177,6 +1359,7 @@ int multifd_load_setup(Error **errp)
     thread_count = migrate_multifd_channels();
     multifd_recv_state = g_malloc0(sizeof(*multifd_recv_state));
     multifd_recv_state->params = g_new0(MultiFDRecvParams, thread_count);
+    multifd_recv_state->pages = multifd_pages_init(page_count);
     qatomic_set(&multifd_recv_state->count, 0);
     qemu_sem_init(&multifd_recv_state->sem_sync, 0);
     multifd_recv_state->ops = multifd_ops[migrate_multifd_compression()];
@@ -1185,12 +1368,20 @@ int multifd_load_setup(Error **errp)
         MultiFDRecvParams *p = &multifd_recv_state->params[i];
 
         qemu_mutex_init(&p->mutex);
+        qemu_sem_init(&p->sem, 0);
         qemu_sem_init(&p->sem_sync, 0);
         p->quit = false;
+        p->pending_job = 0;
         p->id = i;
-        p->packet_len = sizeof(MultiFDPacket_t)
-                      + sizeof(uint64_t) * page_count;
-        p->packet = g_malloc0(p->packet_len);
+        p->pages = multifd_pages_init(page_count);
+
+        if (use_packets) {
+            p->packet_len = sizeof(MultiFDPacket_t)
+                + sizeof(uint64_t) * page_count;
+            p->packet = g_malloc0(p->packet_len);
+        } else {
+            p->read_flags |= QIO_CHANNEL_READ_FLAG_WITH_OFFSET;
+        }
         p->name = g_strdup_printf("multifdrecv_%d", i);
         p->iov = g_new0(struct iovec, page_count);
         p->normal = g_new0(ram_addr_t, page_count);
@@ -1212,6 +1403,11 @@ int multifd_load_setup(Error **errp)
     return 0;
 }
 
+bool multifd_recv_first_channel(void)
+{
+    return !multifd_recv_state;
+}
+
 bool multifd_recv_all_channels_created(void)
 {
     int thread_count = migrate_multifd_channels();
@@ -1236,18 +1432,26 @@ void multifd_recv_new_channel(QIOChannel *ioc, Error **errp)
 {
     MultiFDRecvParams *p;
     Error *local_err = NULL;
-    int id;
+    bool use_packets = migrate_multifd_packets();
+    int id, num_packets = 0;
 
-    id = multifd_recv_initial_packet(ioc, &local_err);
-    if (id < 0) {
-        multifd_recv_terminate_threads(local_err);
-        error_propagate_prepend(errp, local_err,
-                                "failed to receive packet"
-                                " via multifd channel %d: ",
-                                qatomic_read(&multifd_recv_state->count));
-        return;
+    if (use_packets) {
+        id = multifd_recv_initial_packet(ioc, &local_err);
+        if (id < 0) {
+            multifd_recv_terminate_threads(local_err);
+            error_propagate_prepend(errp, local_err,
+                                    "failed to receive packet"
+                                    " via multifd channel %d: ",
+                                    qatomic_read(&multifd_recv_state->count));
+            return;
+        }
+        trace_multifd_recv_new_channel(id);
+
+        /* initial packet */
+        num_packets = 1;
+    } else {
+        id = qatomic_read(&multifd_recv_state->count);
     }
-    trace_multifd_recv_new_channel(id);
 
     p = &multifd_recv_state->params[id];
     if (p->c != NULL) {
@@ -1258,9 +1462,8 @@ void multifd_recv_new_channel(QIOChannel *ioc, Error **errp)
         return;
     }
     p->c = ioc;
+    p->num_packets = num_packets;
     object_ref(OBJECT(ioc));
-    /* initial packet */
-    p->num_packets = 1;
 
     p->running = true;
     qemu_thread_create(&p->thread, p->name, multifd_recv_thread, p,

migration/multifd.h

@@ -18,11 +18,13 @@ void multifd_save_cleanup(void);
 int multifd_load_setup(Error **errp);
 void multifd_load_cleanup(void);
 void multifd_load_shutdown(void);
+bool multifd_recv_first_channel(void);
 bool multifd_recv_all_channels_created(void);
 void multifd_recv_new_channel(QIOChannel *ioc, Error **errp);
 void multifd_recv_sync_main(void);
 int multifd_send_sync_main(QEMUFile *f);
 int multifd_queue_page(QEMUFile *f, RAMBlock *block, ram_addr_t offset);
+int multifd_recv_queue_page(QEMUFile *f, RAMBlock *block, ram_addr_t offset);
 
 /* Multifd Compression flags */
 #define MULTIFD_FLAG_SYNC (1 << 0)
@@ -152,7 +154,11 @@ typedef struct {
     uint32_t page_size;
     /* number of pages in a full packet */
     uint32_t page_count;
+    /* multifd flags for receiving ram */
+    int read_flags;
 
+    /* sem where to wait for more work */
+    QemuSemaphore sem;
     /* syncs main thread and channels */
     QemuSemaphore sem_sync;
 
@@ -166,6 +172,13 @@ typedef struct {
     uint32_t flags;
     /* global number of generated multifd packets */
     uint64_t packet_num;
+    int pending_job;
+    /* array of pages to sent.
+     * The owner of 'pages' depends of 'pending_job' value:
+     * pending_job == 0 -> migration_thread can use it.
+     * pending_job != 0 -> multifd_channel can use it.
+     */
+    MultiFDPages_t *pages;
 
     /* thread local variables. No locking required */
 

migration/options.c

@@ -185,6 +185,8 @@ Property migration_properties[] = {
     DEFINE_PROP_MIG_CAP("x-zero-copy-send",
             MIGRATION_CAPABILITY_ZERO_COPY_SEND),
 #endif
+    DEFINE_PROP_MIG_CAP("x-suspend", MIGRATION_CAPABILITY_SUSPEND),
+    DEFINE_PROP_MIG_CAP("x-fixed-ram", MIGRATION_CAPABILITY_FIXED_RAM),
 
     DEFINE_PROP_END_OF_LIST(),
 };
@@ -238,6 +240,13 @@ bool migrate_events(void)
     return s->capabilities[MIGRATION_CAPABILITY_EVENTS];
 }
 
+bool migrate_fixed_ram(void)
+{
+    MigrationState *s = migrate_get_current();
+
+    return s->capabilities[MIGRATION_CAPABILITY_FIXED_RAM];
+}
+
 bool migrate_ignore_shared(void)
 {
     MigrationState *s = migrate_get_current();
@@ -308,6 +317,13 @@ bool migrate_return_path(void)
     return s->capabilities[MIGRATION_CAPABILITY_RETURN_PATH];
 }
 
+bool migrate_suspend(void)
+{
+    MigrationState *s = migrate_get_current();
+
+    return s->capabilities[MIGRATION_CAPABILITY_SUSPEND];
+}
+
 bool migrate_validate_uuid(void)
 {
     MigrationState *s = migrate_get_current();
@@ -345,6 +361,16 @@ bool migrate_multifd_flush_after_each_section(void)
     return s->multifd_flush_after_each_section;
 }
 
+bool migrate_live(void)
+{
+    return !migrate_suspend();
+}
+
+bool migrate_multifd_packets(void)
+{
+    return !migrate_fixed_ram();
+}
+
 bool migrate_postcopy(void)
 {
     return migrate_postcopy_ram() || migrate_dirty_bitmaps();
@@ -357,6 +383,13 @@ bool migrate_tls(void)
     return s->parameters.tls_creds && *s->parameters.tls_creds;
 }
 
+bool migrate_to_file(void)
+{
+    MigrationState *s = migrate_get_current();
+
+    return qemu_file_is_seekable(s->to_dst_file);
+}
+
 typedef enum WriteTrackingSupport {
     WT_SUPPORT_UNKNOWN = 0,
     WT_SUPPORT_ABSENT,
@@ -413,7 +446,9 @@ INITIALIZE_MIGRATE_CAPS_SET(check_caps_background_snapshot,
     MIGRATION_CAPABILITY_XBZRLE,
     MIGRATION_CAPABILITY_X_COLO,
     MIGRATION_CAPABILITY_VALIDATE_UUID,
-    MIGRATION_CAPABILITY_ZERO_COPY_SEND);
+    MIGRATION_CAPABILITY_ZERO_COPY_SEND,
+    MIGRATION_CAPABILITY_SUSPEND,
+    MIGRATION_CAPABILITY_FIXED_RAM);
 
 /**
  * @migration_caps_check - check capability compatibility
@@ -547,6 +582,26 @@ bool migrate_caps_check(bool *old_caps, bool *new_caps, Error **errp)
         }
     }
 
+    if (new_caps[MIGRATION_CAPABILITY_FIXED_RAM]) {
+        if (new_caps[MIGRATION_CAPABILITY_XBZRLE]) {
+            error_setg(errp,
+                       "Fixed-ram migration is incompatible with xbzrle");
+            return false;
+        }
+
+        if (new_caps[MIGRATION_CAPABILITY_COMPRESS]) {
+            error_setg(errp,
+                       "Fixed-ram migration is incompatible with compression");
+            return false;
+        }
+
+        if (new_caps[MIGRATION_CAPABILITY_POSTCOPY_RAM]) {
+            error_setg(errp,
+                       "Fixed-ram migration is incompatible with postcopy ram");
+            return false;
+        }
+    }
+
     return true;
 }
 
@@ -697,6 +752,22 @@ int migrate_decompress_threads(void)
     return s->parameters.decompress_threads;
 }
 
+bool migrate_direct_io(void)
+{
+    MigrationState *s = migrate_get_current();
+
+    /* For now O_DIRECT is only supported with fixed-ram */
+    if (!s->capabilities[MIGRATION_CAPABILITY_FIXED_RAM]) {
+        return false;
+    }
+
+    if (s->parameters.has_direct_io) {
+        return s->parameters.direct_io;
+    }
+
+    return false;
+}
+
 uint64_t migrate_downtime_limit(void)
 {
     MigrationState *s = migrate_get_current();
@@ -891,6 +962,11 @@ MigrationParameters *qmp_query_migrate_parameters(Error **errp)
                        s->parameters.block_bitmap_mapping);
     }
 
+    if (s->parameters.has_direct_io) {
+        params->has_direct_io = true;
+        params->direct_io = s->parameters.direct_io;
+    }
+
     return params;
 }
 
@@ -923,6 +999,7 @@ void migrate_params_init(MigrationParameters *params)
     params->has_announce_max = true;
     params->has_announce_rounds = true;
     params->has_announce_step = true;
+    params->has_direct_io = qemu_has_direct_io();
 }
 
 /*
@@ -1182,6 +1259,10 @@ static void migrate_params_test_apply(MigrateSetParameters *params,
         dest->has_block_bitmap_mapping = true;
         dest->block_bitmap_mapping = params->block_bitmap_mapping;
     }
+
+    if (params->has_direct_io) {
+        dest->direct_io = params->direct_io;
+    }
 }
 
 static void migrate_params_apply(MigrateSetParameters *params, Error **errp)
@@ -1300,6 +1381,10 @@ static void migrate_params_apply(MigrateSetParameters *params, Error **errp)
             QAPI_CLONE(BitmapMigrationNodeAliasList,
                        params->block_bitmap_mapping);
     }
+
+    if (params->has_direct_io) {
+        s->parameters.direct_io = params->direct_io;
+    }
 }
 
 void qmp_migrate_set_parameters(MigrateSetParameters *params, Error **errp)

migration/options.h

@@ -30,6 +30,7 @@ bool migrate_colo(void);
 bool migrate_compress(void);
 bool migrate_dirty_bitmaps(void);
 bool migrate_events(void);
+bool migrate_fixed_ram(void);
 bool migrate_ignore_shared(void);
 bool migrate_late_block_activate(void);
 bool migrate_multifd(void);
@@ -40,6 +41,7 @@ bool migrate_postcopy_ram(void);
 bool migrate_rdma_pin_all(void);
 bool migrate_release_ram(void);
 bool migrate_return_path(void);
+bool migrate_suspend(void);
 bool migrate_validate_uuid(void);
 bool migrate_xbzrle(void);
 bool migrate_zero_blocks(void);
@@ -53,8 +55,11 @@ bool migrate_zero_copy_send(void);
  */
 
 bool migrate_multifd_flush_after_each_section(void);
+bool migrate_live(void);
+bool migrate_multifd_packets(void);
 bool migrate_postcopy(void);
 bool migrate_tls(void);
+bool migrate_to_file(void);
 
 /* capabilities helpers */
 
@@ -75,6 +80,7 @@ uint8_t migrate_cpu_throttle_increment(void);
 uint8_t migrate_cpu_throttle_initial(void);
 bool migrate_cpu_throttle_tailslow(void);
 int migrate_decompress_threads(void);
+bool migrate_direct_io(void);
 uint64_t migrate_downtime_limit(void);
 uint8_t migrate_max_cpu_throttle(void);
 uint64_t migrate_max_bandwidth(void);

migration/qemu-file.c

@@ -32,6 +32,7 @@
 #include "trace.h"
 #include "options.h"
 #include "qapi/error.h"
+#include "io/channel-file.h"
 
 #define IO_BUF_SIZE 32768
 #define MAX_IOV_SIZE MIN_CONST(IOV_MAX, 64)
@@ -268,6 +269,10 @@ static void qemu_iovec_release_ram(QEMUFile *f)
     memset(f->may_free, 0, sizeof(f->may_free));
 }
 
+bool qemu_file_is_seekable(QEMUFile *f)
+{
+    return qio_channel_has_feature(f->ioc, QIO_CHANNEL_FEATURE_SEEKABLE);
+}
 
 /**
  * Flushes QEMUFile buffer
@@ -532,6 +537,81 @@ void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, size_t size)
     }
 }
 
+void qemu_put_buffer_at(QEMUFile *f, const uint8_t *buf, size_t buflen, off_t pos)
+{
+    Error *err = NULL;
+
+    if (f->last_error) {
+        return;
+    }
+
+    qemu_fflush(f);
+    qio_channel_pwritev(f->ioc, (char *)buf, buflen, pos, &err);
+
+    if (err) {
+        qemu_file_set_error_obj(f, -EIO, err);
+    } else {
+        f->total_transferred += buflen;
+    }
+
+    return;
+}
+
+
+size_t qemu_get_buffer_at(QEMUFile *f, const uint8_t *buf, size_t buflen, off_t pos)
+{
+    Error *err = NULL;
+    ssize_t ret;
+
+    if (f->last_error) {
+        return 0;
+    }
+
+    ret = qio_channel_preadv(f->ioc, (char *)buf, buflen, pos, &err);
+    if (ret == -1 || err) {
+        goto error;
+    }
+
+    return (size_t)ret;
+
+ error:
+    qemu_file_set_error_obj(f, -EIO, err);
+    return 0;
+}
+
+void qemu_set_offset(QEMUFile *f, off_t off, int whence)
+{
+    Error *err = NULL;
+    off_t ret;
+
+    qemu_fflush(f);
+
+    if (!qemu_file_is_writable(f)) {
+        f->buf_index = 0;
+        f->buf_size = 0;
+    }
+
+    ret = qio_channel_io_seek(f->ioc, off, whence, &err);
+    if (ret == (off_t)-1) {
+        qemu_file_set_error_obj(f, -EIO, err);
+    }
+}
+
+off_t qemu_get_offset(QEMUFile *f)
+{
+    Error *err = NULL;
+    off_t ret;
+
+    qemu_fflush(f);
+
+    ret = qio_channel_io_seek(f->ioc, 0, SEEK_CUR, &err);
+    if (ret == (off_t)-1) {
+        qemu_file_set_error_obj(f, -EIO, err);
+    }
+    return ret;
+}
+
+
 void qemu_put_byte(QEMUFile *f, int v)
 {
     if (f->last_error) {

migration/qemu-file.h

@@ -139,6 +139,10 @@ QEMUFile *qemu_file_get_return_path(QEMUFile *f);
 void qemu_fflush(QEMUFile *f);
 void qemu_file_set_blocking(QEMUFile *f, bool block);
 int qemu_file_get_to_fd(QEMUFile *f, int fd, size_t size);
+void qemu_set_offset(QEMUFile *f, off_t off, int whence);
+off_t qemu_get_offset(QEMUFile *f);
+void qemu_put_buffer_at(QEMUFile *f, const uint8_t *buf, size_t buflen, off_t pos);
+size_t qemu_get_buffer_at(QEMUFile *f, const uint8_t *buf, size_t buflen, off_t pos);
 
 void ram_control_before_iterate(QEMUFile *f, uint64_t flags);
 void ram_control_after_iterate(QEMUFile *f, uint64_t flags);

migration/ram.c

@@ -1104,9 +1104,15 @@ static int save_zero_page_to_file(PageSearchStatus *pss, QEMUFile *file,
     int len = 0;
 
     if (buffer_is_zero(p, TARGET_PAGE_SIZE)) {
-        len += save_page_header(pss, file, block, offset | RAM_SAVE_FLAG_ZERO);
-        qemu_put_byte(file, 0);
-        len += 1;
+        if (migrate_fixed_ram()) {
+            /* for zero pages we don't need to do anything */
+            len = 1;
+        } else {
+            len += save_page_header(pss, file, block,
+                                    offset | RAM_SAVE_FLAG_ZERO);
+            qemu_put_byte(file, 0);
+            len += 1;
+        }
         ram_release_page(block->idstr, offset);
     }
     return len;
@@ -1188,14 +1194,20 @@ static int save_normal_page(PageSearchStatus *pss, RAMBlock *block,
 {
     QEMUFile *file = pss->pss_channel;
 
-    ram_transferred_add(save_page_header(pss, pss->pss_channel, block,
-                                         offset | RAM_SAVE_FLAG_PAGE));
-    if (async) {
-        qemu_put_buffer_async(file, buf, TARGET_PAGE_SIZE,
-                              migrate_release_ram() &&
-                              migration_in_postcopy());
+    if (migrate_fixed_ram()) {
+        qemu_put_buffer_at(file, buf, TARGET_PAGE_SIZE,
+                           block->pages_offset + offset);
+        set_bit(offset >> TARGET_PAGE_BITS, block->shadow_bmap);
     } else {
-        qemu_put_buffer(file, buf, TARGET_PAGE_SIZE);
+        ram_transferred_add(save_page_header(pss, pss->pss_channel, block,
+                                             offset | RAM_SAVE_FLAG_PAGE));
+        if (async) {
+            qemu_put_buffer_async(file, buf, TARGET_PAGE_SIZE,
+                                  migrate_release_ram() &&
+                                  migration_in_postcopy());
+        } else {
+            qemu_put_buffer(file, buf, TARGET_PAGE_SIZE);
+        }
     }
     ram_transferred_add(TARGET_PAGE_SIZE);
     stat64_add(&mig_stats.normal_pages, 1);
@@ -1357,14 +1369,16 @@ static int find_dirty_block(RAMState *rs, PageSearchStatus *pss)
         pss->page = 0;
         pss->block = QLIST_NEXT_RCU(pss->block, next);
         if (!pss->block) {
-            if (!migrate_multifd_flush_after_each_section()) {
-                QEMUFile *f = rs->pss[RAM_CHANNEL_PRECOPY].pss_channel;
-                int ret = multifd_send_sync_main(f);
-                if (ret < 0) {
-                    return ret;
+            if (!migrate_fixed_ram()) {
+                if (!migrate_multifd_flush_after_each_section()) {
+                    QEMUFile *f = rs->pss[RAM_CHANNEL_PRECOPY].pss_channel;
+                    int ret = multifd_send_sync_main(f);
+                    if (ret < 0) {
+                        return ret;
+                    }
+                    qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH);
+                    qemu_fflush(f);
                 }
-                qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH);
-                qemu_fflush(f);
             }
             /*
              * If memory migration starts over, we will meet a dirtied page
@@ -2465,6 +2479,8 @@ static void ram_save_cleanup(void *opaque)
         block->clear_bmap = NULL;
         g_free(block->bmap);
         block->bmap = NULL;
+        g_free(block->shadow_bmap);
+        block->shadow_bmap = NULL;
     }
 
     xbzrle_cleanup();
@@ -2832,6 +2848,7 @@ static void ram_list_init_bitmaps(void)
              */
             block->bmap = bitmap_new(pages);
             bitmap_set(block->bmap, 0, pages);
+            block->shadow_bmap = bitmap_new(block->used_length >> TARGET_PAGE_BITS);
             block->clear_bmap_shift = shift;
             block->clear_bmap = bitmap_new(clear_bmap_size(pages, shift));
         }
@@ -2972,6 +2989,70 @@ void qemu_guest_free_page_hint(void *addr, size_t len)
     }
 }
 
+#define FIXED_RAM_HDR_VERSION 1
+struct FixedRamHeader {
+    uint32_t version;
+    uint64_t page_size;
+    uint64_t bitmap_offset;
+    uint64_t pages_offset;
+    /* end of v1 */
+} QEMU_PACKED;
+
+static void fixed_ram_insert_header(QEMUFile *file, RAMBlock *block)
+{
+    g_autofree struct FixedRamHeader *header;
+    size_t header_size, bitmap_size;
+    long num_pages;
+
+    header = g_new0(struct FixedRamHeader, 1);
+    header_size = sizeof(struct FixedRamHeader);
+
+    num_pages = block->used_length >> TARGET_PAGE_BITS;
+    bitmap_size = BITS_TO_LONGS(num_pages) * sizeof(unsigned long);
+
+    /*
+     * Save the file offsets of where the bitmap and the pages should
+     * go as they are written at the end of migration and during the
+     * iterative phase, respectively.
+     */
+    block->bitmap_offset = qemu_get_offset(file) + header_size;
+    block->pages_offset = ROUND_UP(block->bitmap_offset +
+                                   bitmap_size, 0x100000);
+
+    header->version = cpu_to_be32(FIXED_RAM_HDR_VERSION);
+    header->page_size = cpu_to_be64(TARGET_PAGE_SIZE);
+    header->bitmap_offset = cpu_to_be64(block->bitmap_offset);
+    header->pages_offset = cpu_to_be64(block->pages_offset);
+
+    qemu_put_buffer(file, (uint8_t *) header, header_size);
+}
+
+static int fixed_ram_read_header(QEMUFile *file, struct FixedRamHeader *header)
+{
+    size_t ret, header_size = sizeof(struct FixedRamHeader);
+
+    ret = qemu_get_buffer(file, (uint8_t *)header, header_size);
+    if (ret != header_size) {
+        return -1;
+    }
+
+    /* migration stream is big-endian */
+    be32_to_cpus(&header->version);
+
+    if (header->version > FIXED_RAM_HDR_VERSION) {
+        error_report("Migration fixed-ram capability version mismatch (expected %d, got %d)",
+                     FIXED_RAM_HDR_VERSION, header->version);
+        return -1;
+    }
+
+    be64_to_cpus(&header->page_size);
+    be64_to_cpus(&header->bitmap_offset);
+    be64_to_cpus(&header->pages_offset);
+
+
+    return 0;
+}
+
 /*
  * Each of ram_save_setup, ram_save_iterate and ram_save_complete has
  * long-running RCU critical section.  When rcu-reclaims in the code
@@ -3021,6 +3102,12 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
             if (migrate_ignore_shared()) {
                 qemu_put_be64(f, block->mr->addr);
             }
+
+            if (migrate_fixed_ram()) {
+                fixed_ram_insert_header(f, block);
+                /* prepare offset for next ramblock */
+                qemu_set_offset(f, block->pages_offset + block->used_length, SEEK_SET);
+            }
         }
     }
 
@@ -3044,6 +3131,27 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
     return 0;
 }
 
+static void ram_save_shadow_bmap(QEMUFile *f)
+{
+    RAMBlock *block;
+
+    RAMBLOCK_FOREACH_MIGRATABLE(block) {
+        long num_pages = block->used_length >> TARGET_PAGE_BITS;
+        long bitmap_size = BITS_TO_LONGS(num_pages) * sizeof(unsigned long);
+        qemu_put_buffer_at(f, (uint8_t *)block->shadow_bmap, bitmap_size,
+                           block->bitmap_offset);
+    }
+}
+
+void ramblock_set_shadow_bmap(RAMBlock *block, ram_addr_t offset, bool set)
+{
+    if (set) {
+        set_bit(offset >> TARGET_PAGE_BITS, block->shadow_bmap);
+    } else {
+        clear_bit(offset >> TARGET_PAGE_BITS, block->shadow_bmap);
+    }
+}
+
 /**
  * ram_save_iterate: iterative stage for migration
  *
@@ -3156,7 +3264,6 @@ out:
         qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
         qemu_fflush(f);
         ram_transferred_add(8);
-
         ret = qemu_file_get_error(f);
     }
     if (ret < 0) {
@@ -3201,6 +3308,9 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
             pages = ram_find_and_save_block(rs);
             /* no more blocks to sent */
             if (pages == 0) {
+                if (migrate_fixed_ram()) {
+                    ram_save_shadow_bmap(f);
+                }
                 break;
             }
             if (pages < 0) {
@@ -3227,6 +3337,7 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
         qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH);
     }
     qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
+
     qemu_fflush(f);
 
     return 0;
@@ -3825,6 +3936,154 @@ void colo_flush_ram_cache(void)
     trace_colo_flush_ram_cache_end();
 }
 
+static void read_ramblock_fixed_ram(QEMUFile *f, RAMBlock *block,
+                                    long num_pages, unsigned long *bitmap)
+{
+    unsigned long set_bit_idx, clear_bit_idx;
+    unsigned long len;
+    ram_addr_t offset;
+    void *host;
+    size_t read, completed, read_len;
+
+    for (set_bit_idx = find_first_bit(bitmap, num_pages);
+         set_bit_idx < num_pages;
+         set_bit_idx = find_next_bit(bitmap, num_pages, clear_bit_idx + 1)) {
+
+        clear_bit_idx = find_next_zero_bit(bitmap, num_pages, set_bit_idx + 1);
+
+        len = TARGET_PAGE_SIZE * (clear_bit_idx - set_bit_idx);
+        offset = set_bit_idx << TARGET_PAGE_BITS;
+
+        for (read = 0, completed = 0; completed < len; offset += read) {
+            host = host_from_ram_block_offset(block, offset);
+            read_len = MIN(len, TARGET_PAGE_SIZE);
+
+            if (migrate_multifd()) {
+                multifd_recv_queue_page(f, block, offset);
+                read = read_len;
+            } else {
+                read = qemu_get_buffer_at(f, host, read_len,
+                                          block->pages_offset + offset);
+            }
+            completed += read;
+        }
+    }
+}
+
+static int parse_ramblock_fixed_ram(QEMUFile *f, RAMBlock *block, ram_addr_t length)
+{
+    g_autofree unsigned long *dirty_bitmap = NULL;
+    struct FixedRamHeader header;
+    size_t bitmap_size;
+    long num_pages;
+    int ret = 0;
+
+    ret = fixed_ram_read_header(f, &header);
+    if (ret < 0) {
+        error_report("Error reading fixed-ram header");
+        return -EINVAL;
+    }
+
+    block->pages_offset = header.pages_offset;
+    num_pages = length / header.page_size;
+    bitmap_size = BITS_TO_LONGS(num_pages) * sizeof(unsigned long);
+
+    dirty_bitmap = g_malloc0(bitmap_size);
+    if (qemu_get_buffer_at(f, (uint8_t *)dirty_bitmap, bitmap_size,
+                           header.bitmap_offset) != bitmap_size) {
+        error_report("Error parsing dirty bitmap");
+        return -EINVAL;
+    }
+
+    read_ramblock_fixed_ram(f, block, num_pages, dirty_bitmap);
+
+    /* Skip pages array */
+    qemu_set_offset(f, block->pages_offset + length, SEEK_SET);
+
+    return ret;
+}
+
+static int parse_ramblock(QEMUFile *f, RAMBlock *block, ram_addr_t length)
+{
+    int ret = 0;
+    /* ADVISE is earlier, it shows the source has the postcopy capability on */
+    bool postcopy_advised = migration_incoming_postcopy_advised();
+
+    assert(block);
+
+    if (migrate_fixed_ram()) {
+        return parse_ramblock_fixed_ram(f, block, length);
+    }
+
+    if (!qemu_ram_is_migratable(block)) {
+        error_report("block %s should not be migrated !", block->idstr);
+        ret = -EINVAL;
+    }
+
+    if (length != block->used_length) {
+        Error *local_err = NULL;
+
+        ret = qemu_ram_resize(block, length, &local_err);
+        if (local_err) {
+            error_report_err(local_err);
+        }
+    }
+    /* For postcopy we need to check hugepage sizes match */
+    if (postcopy_advised && migrate_postcopy_ram() &&
+        block->page_size != qemu_host_page_size) {
+        uint64_t remote_page_size = qemu_get_be64(f);
+        if (remote_page_size != block->page_size) {
+            error_report("Mismatched RAM page size %s "
+                         "(local) %zd != %" PRId64, block->idstr,
+                         block->page_size, remote_page_size);
+            ret = -EINVAL;
+        }
+    }
+    if (migrate_ignore_shared()) {
+        hwaddr addr = qemu_get_be64(f);
+        if (ramblock_is_ignored(block) &&
+            block->mr->addr != addr) {
+            error_report("Mismatched GPAs for block %s "
+                         "%" PRId64 "!= %" PRId64, block->idstr,
+                         (uint64_t)addr,
+                         (uint64_t)block->mr->addr);
+            ret = -EINVAL;
+        }
+    }
+    ram_control_load_hook(f, RAM_CONTROL_BLOCK_REG, block->idstr);
+
+    return ret;
+}
+
+static int parse_ramblocks(QEMUFile *f, ram_addr_t total_ram_bytes)
+{
+    int ret = 0;
+
+    /* Synchronize RAM block list */
+    while (!ret && total_ram_bytes) {
+        char id[256];
+        RAMBlock *block;
+        ram_addr_t length;
+        int len = qemu_get_byte(f);
+
+        qemu_get_buffer(f, (uint8_t *)id, len);
+        id[len] = 0;
+        length = qemu_get_be64(f);
+
+        block = qemu_ram_block_by_name(id);
+        if (block) {
+            ret = parse_ramblock(f, block, length);
+        } else {
+            error_report("Unknown ramblock \"%s\", cannot accept "
+                         "migration", id);
+            ret = -EINVAL;
+        }
+        total_ram_bytes -= length;
+    }
+
+    return ret;
+}
+
 /**
  * ram_load_precopy: load pages in precopy case
  *
@@ -3839,14 +4098,13 @@ static int ram_load_precopy(QEMUFile *f)
 {
     MigrationIncomingState *mis = migration_incoming_get_current();
     int flags = 0, ret = 0, invalid_flags = 0, len = 0, i = 0;
-    /* ADVISE is earlier, it shows the source has the postcopy capability on */
-    bool postcopy_advised = migration_incoming_postcopy_advised();
+
     if (!migrate_compress()) {
         invalid_flags |= RAM_SAVE_FLAG_COMPRESS_PAGE;
     }
 
     while (!ret && !(flags & RAM_SAVE_FLAG_EOS)) {
-        ram_addr_t addr, total_ram_bytes;
+        ram_addr_t addr;
         void *host = NULL, *host_bak = NULL;
         uint8_t ch;
 
@@ -3917,65 +4175,7 @@ static int ram_load_precopy(QEMUFile *f)
 
         switch (flags & ~RAM_SAVE_FLAG_CONTINUE) {
         case RAM_SAVE_FLAG_MEM_SIZE:
-            /* Synchronize RAM block list */
-            total_ram_bytes = addr;
-            while (!ret && total_ram_bytes) {
-                RAMBlock *block;
-                char id[256];
-                ram_addr_t length;
-
-                len = qemu_get_byte(f);
-                qemu_get_buffer(f, (uint8_t *)id, len);
-                id[len] = 0;
-                length = qemu_get_be64(f);
-
-                block = qemu_ram_block_by_name(id);
-                if (block && !qemu_ram_is_migratable(block)) {
-                    error_report("block %s should not be migrated !", id);
-                    ret = -EINVAL;
-                } else if (block) {
-                    if (length != block->used_length) {
-                        Error *local_err = NULL;
-
-                        ret = qemu_ram_resize(block, length,
-                                              &local_err);
-                        if (local_err) {
-                            error_report_err(local_err);
-                        }
-                    }
-                    /* For postcopy we need to check hugepage sizes match */
-                    if (postcopy_advised && migrate_postcopy_ram() &&
-                        block->page_size != qemu_host_page_size) {
-                        uint64_t remote_page_size = qemu_get_be64(f);
-                        if (remote_page_size != block->page_size) {
-                            error_report("Mismatched RAM page size %s "
-                                         "(local) %zd != %" PRId64,
-                                         id, block->page_size,
-                                         remote_page_size);
-                            ret = -EINVAL;
-                        }
-                    }
-                    if (migrate_ignore_shared()) {
-                        hwaddr addr = qemu_get_be64(f);
-                        if (ramblock_is_ignored(block) &&
-                            block->mr->addr != addr) {
-                            error_report("Mismatched GPAs for block %s "
-                                         "%" PRId64 "!= %" PRId64,
-                                         id, (uint64_t)addr,
-                                         (uint64_t)block->mr->addr);
-                            ret = -EINVAL;
-                        }
-                    }
-                    ram_control_load_hook(f, RAM_CONTROL_BLOCK_REG,
-                                          block->idstr);
-                } else {
-                    error_report("Unknown ramblock \"%s\", cannot "
-                                 "accept migration", id);
-                    ret = -EINVAL;
-                }
-
-                total_ram_bytes -= length;
-            }
+            ret = parse_ramblocks(f, addr);
             break;
 
         case RAM_SAVE_FLAG_ZERO:

migration/ram.h

@@ -76,6 +76,7 @@ int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *rb);
 bool ramblock_page_is_discarded(RAMBlock *rb, ram_addr_t start);
 void postcopy_preempt_shutdown_file(MigrationState *s);
 void *postcopy_preempt_thread(void *opaque);
+void ramblock_set_shadow_bmap(RAMBlock *block, ram_addr_t offset, bool set);
 
 /* ram cache */
 int colo_init_ram_cache(void);

migration/savevm.c

@@ -243,6 +243,7 @@ static bool should_validate_capability(int capability)
     /* Validate only new capabilities to keep compatibility. */
     switch (capability) {
     case MIGRATION_CAPABILITY_X_IGNORE_SHARED:
+    case MIGRATION_CAPABILITY_FIXED_RAM:
         return true;
     default:
         return false;
@@ -1209,13 +1210,25 @@ void qemu_savevm_non_migratable_list(strList **reasons)
 
 void qemu_savevm_state_header(QEMUFile *f)
 {
+    MigrationState *s = migrate_get_current();
+
+    s->vmdesc = json_writer_new(false);
+
     trace_savevm_state_header();
     qemu_put_be32(f, QEMU_VM_FILE_MAGIC);
     qemu_put_be32(f, QEMU_VM_FILE_VERSION);
 
-    if (migrate_get_current()->send_configuration) {
+    if (s->send_configuration) {
         qemu_put_byte(f, QEMU_VM_CONFIGURATION);
-        vmstate_save_state(f, &vmstate_configuration, &savevm_state, 0);
+        /*
+         * This starts the main json object and is paired with the
+         * json_writer_end_object in
+         * qemu_savevm_state_complete_precopy_non_iterable
+         */
+        json_writer_start_object(s->vmdesc, NULL);
+        json_writer_start_object(s->vmdesc, "configuration");
+        vmstate_save_state(f, &vmstate_configuration, &savevm_state, s->vmdesc);
+        json_writer_end_object(s->vmdesc);
     }
 }
 
@@ -1240,8 +1253,6 @@ void qemu_savevm_state_setup(QEMUFile *f)
     Error *local_err = NULL;
     int ret;
 
-    ms->vmdesc = json_writer_new(false);
-    json_writer_start_object(ms->vmdesc, NULL);
     json_writer_int64(ms->vmdesc, "page_size", qemu_target_page_size());
     json_writer_start_array(ms->vmdesc, "devices");
 
@@ -1630,6 +1641,7 @@ static int qemu_savevm_state(QEMUFile *f, Error **errp)
     qemu_mutex_lock_iothread();
 
     while (qemu_file_get_error(f) == 0) {
+        migration_update_counters(ms, qemu_clock_get_ms(QEMU_CLOCK_REALTIME));
         if (qemu_savevm_state_iterate(f, false) > 0) {
             break;
         }
@@ -1652,6 +1664,9 @@ static int qemu_savevm_state(QEMUFile *f, Error **errp)
     }
     migrate_set_state(&ms->state, MIGRATION_STATUS_SETUP, status);
 
+    migration_calculate_complete(ms);
+    trace_migration_status((int)ms->mbps / 8, (int)ms->pages_per_second, ms->total_time);
+
     /* f is outer parameter, it should not stay in global migration state after
      * this function finished */
     ms->to_dst_file = NULL;

migration/trace-events

@@ -165,6 +165,7 @@ migration_return_path_end_after(int rp_error) "%d"
 migration_thread_after_loop(void) ""
 migration_thread_file_err(void) ""
 migration_thread_setup_complete(void) ""
+migration_status(int mpbs, int pages_per_second, int64_t total_time) "%d MB/s, %d pages/s, %ld ms"
 open_return_path_on_source(void) ""
 open_return_path_on_source_continue(void) ""
 postcopy_start(void) ""

qapi/migration.json

@@ -487,6 +487,12 @@
 #     and should not affect the correctness of postcopy migration.
 #     (since 7.1)
 #
+# @suspend: If enabled, a non-live migration will be performed,
+#           i.e. the VM will be stopped before migration. (since 8.1)
+#
+# @fixed-ram: Migrate using fixed offsets for each RAM page. Requires
+#             a seekable transport such as a file.  (since 8.1)
+#
 # Features:
 #
 # @unstable: Members @x-colo and @x-ignore-shared are experimental.
@@ -502,7 +508,7 @@
            'dirty-bitmaps', 'postcopy-blocktime', 'late-block-activate',
            { 'name': 'x-ignore-shared', 'features': [ 'unstable' ] },
            'validate-uuid', 'background-snapshot',
-           'zero-copy-send', 'postcopy-preempt'] }
+           'zero-copy-send', 'postcopy-preempt', 'suspend', 'fixed-ram'] }
 
 ##
 # @MigrationCapabilityStatus:
@@ -779,6 +785,9 @@
 #     Nodes are mapped to their block device name if there is one, and
 #     to their node name otherwise.  (Since 5.2)
 #
+# @direct-io: Open migration files with O_DIRECT when possible. Not
+#             all migration transports support this. (since 8.1)
+#
 # Features:
 #
 # @unstable: Member @x-checkpoint-delay is experimental.
@@ -800,7 +809,7 @@
            'xbzrle-cache-size', 'max-postcopy-bandwidth',
            'max-cpu-throttle', 'multifd-compression',
            'multifd-zlib-level' ,'multifd-zstd-level',
-           'block-bitmap-mapping' ] }
+           'block-bitmap-mapping', 'direct-io' ] }
 
 ##
 # @MigrateSetParameters:
@@ -935,6 +944,9 @@
 #     Nodes are mapped to their block device name if there is one, and
 #     to their node name otherwise.  (Since 5.2)
 #
+# @direct-io: Open migration files with O_DIRECT when possible. Not
+#             all migration transports support this. (since 8.1)
+#
 # Features:
 #
 # @unstable: Member @x-checkpoint-delay is experimental.
@@ -972,7 +984,8 @@
             '*multifd-compression': 'MultiFDCompression',
             '*multifd-zlib-level': 'uint8',
             '*multifd-zstd-level': 'uint8',
-            '*block-bitmap-mapping': [ 'BitmapMigrationNodeAlias' ] } }
+            '*block-bitmap-mapping': [ 'BitmapMigrationNodeAlias' ],
+            '*direct-io': 'bool' } }
 
 ##
 # @migrate-set-parameters:
@@ -1127,6 +1140,9 @@
 #     Nodes are mapped to their block device name if there is one, and
 #     to their node name otherwise.  (Since 5.2)
 #
+# @direct-io: Open migration files with O_DIRECT when possible. Not
+#             all migration transports support this. (since 8.1)
+#
 # Features:
 #
 # @unstable: Member @x-checkpoint-delay is experimental.
@@ -1161,7 +1177,8 @@
             '*multifd-compression': 'MultiFDCompression',
             '*multifd-zlib-level': 'uint8',
             '*multifd-zstd-level': 'uint8',
-            '*block-bitmap-mapping': [ 'BitmapMigrationNodeAlias' ] } }
+            '*block-bitmap-mapping': [ 'BitmapMigrationNodeAlias' ],
+            '*direct-io': 'bool' } }
 
 ##
 # @query-migrate-parameters:

scripts/analyze-migration.py

@@ -23,7 +23,7 @@ import argparse
 import collections
 import struct
 import sys
-
+import math
 
 def mkdir_p(path):
     try:
@@ -119,11 +119,16 @@ class RamSection(object):
         self.file = file
         self.section_key = section_key
         self.TARGET_PAGE_SIZE = ramargs['page_size']
+        self.TARGET_PAGE_BITS = math.log2(self.TARGET_PAGE_SIZE)
         self.dump_memory = ramargs['dump_memory']
         self.write_memory = ramargs['write_memory']
+        self.fixed_ram = ramargs['fixed-ram']
         self.sizeinfo = collections.OrderedDict()
+        self.bitmap_offset = collections.OrderedDict()
+        self.pages_offset = collections.OrderedDict()
         self.data = collections.OrderedDict()
         self.data['section sizes'] = self.sizeinfo
+        self.ram_read = False
         self.name = ''
         if self.write_memory:
             self.files = { }
@@ -140,7 +145,13 @@ class RamSection(object):
     def getDict(self):
         return self.data
 
+    def write_or_dump_fixed_ram(self):
+        pass
+
     def read(self):
+        if self.fixed_ram and self.ram_read:
+            return
+
         # Read all RAM sections
         while True:
             addr = self.file.read64()
@@ -167,7 +178,26 @@ class RamSection(object):
                         f.truncate(0)
                         f.truncate(len)
                         self.files[self.name] = f
+
+                    if self.fixed_ram:
+                        bitmap_len = self.file.read32()
+                        # skip the pages_offset which we don't need
+                        offset = self.file.tell() + 8
+                        self.bitmap_offset[self.name] = offset
+                        offset = ((offset + bitmap_len + self.TARGET_PAGE_SIZE - 1) //
+                                  self.TARGET_PAGE_SIZE) * self.TARGET_PAGE_SIZE
+                        self.pages_offset[self.name] = offset
+                        self.file.file.seek(offset + len)
+
                 flags &= ~self.RAM_SAVE_FLAG_MEM_SIZE
+                if self.fixed_ram:
+                    self.ram_read = True
+                # now we should rewind to the ram page offset of the first
+                # ram section
+                if self.fixed_ram:
+                    if self.write_memory or self.dump_memory:
+                        self.write_or_dump_fixed_ram()
+                        return
 
             if flags & self.RAM_SAVE_FLAG_COMPRESS:
                 if flags & self.RAM_SAVE_FLAG_CONTINUE:
@@ -208,7 +238,7 @@ class RamSection(object):
 
             # End of RAM section
             if flags & self.RAM_SAVE_FLAG_EOS:
-                break
+                return
 
             if flags != 0:
                 raise Exception("Unknown RAM flags: %x" % flags)
@@ -521,6 +551,7 @@ class MigrationDump(object):
         ramargs['page_size'] = self.vmsd_desc['page_size']
         ramargs['dump_memory'] = dump_memory
         ramargs['write_memory'] = write_memory
+        ramargs['fixed-ram'] = False
         self.section_classes[('ram',0)][1] = ramargs
 
         while True:
@@ -528,8 +559,20 @@ class MigrationDump(object):
             if section_type == self.QEMU_VM_EOF:
                 break
             elif section_type == self.QEMU_VM_CONFIGURATION:
-                section = ConfigurationSection(file)
-                section.read()
+                config_desc = self.vmsd_desc.get('configuration')
+                if config_desc is not None:
+                    config = VMSDSection(file, 1, config_desc, 'configuration')
+                    config.read()
+                    caps = config.data.get("configuration/capabilities")
+                    if caps is not None:
+                        caps = caps.data["capabilities"]
+                        if type(caps) != list:
+                            caps = [caps]
+                        for i in caps:
+                            # chomp out string length
+                            cap = i.data[1:].decode("utf8")
+                            if cap == "fixed-ram":
+                                ramargs['fixed-ram'] = True
             elif section_type == self.QEMU_VM_SECTION_START or section_type == self.QEMU_VM_SECTION_FULL:
                 section_id = file.read32()
                 name = file.readstr()

tests/migration/guestperf/comparison.py

@@ -135,4 +135,39 @@ COMPARISONS = [
         Scenario("compr-multifd-channels-64",
                  multifd=True, multifd_channels=64),
     ]),
+
+    # Looking at the effect of fixed-ram + multifd with varying
+    # numbers of channels
+    Comparison("fixed-ram", scenarios = [
+        Scenario("multifd-channels-4",
+                 multifd=True, multifd_channels=4,
+                 fixed_ram=True, bandwidth=0, suspend=True),
+        Scenario("multifd-channels-8",
+                 multifd=True, multifd_channels=8,
+                 fixed_ram=True, bandwidth=0, suspend=True),
+        Scenario("multifd-channels-32",
+                 multifd=True, multifd_channels=32,
+                 fixed_ram=True, bandwidth=0, suspend=True),
+        Scenario("multifd-channels-64",
+                 multifd=True, multifd_channels=64,
+                 fixed_ram=True, bandwidth=0, suspend=True),
+
+        # with O_DIRECT
+        Scenario("dio-multifd-channels-4",
+                 multifd=True, multifd_channels=4,
+                 fixed_ram=True, bandwidth=0, suspend=True,
+                 direct_io=True),
+        Scenario("dio-multifd-channels-8",
+                 multifd=True, multifd_channels=8,
+                 fixed_ram=True, bandwidth=0, suspend=True,
+                 direct_io=True),
+        Scenario("dio-multifd-channels-32",
+                 multifd=True, multifd_channels=32,
+                 fixed_ram=True, bandwidth=0, suspend=True,
+                 direct_io=True),
+        Scenario("dio-multifd-channels-64",
+                 multifd=True, multifd_channels=64,
+                 fixed_ram=True, bandwidth=0, suspend=True,
+                 direct_io=True),
+    ]),
 ]

tests/migration/guestperf/engine.py

@@ -35,10 +35,11 @@ from qemu.machine import QEMUMachine
 class Engine(object):
 
     def __init__(self, binary, dst_host, kernel, initrd, transport="tcp",
-                 sleep=15, verbose=False, debug=False):
+                 sleep=15, verbose=False, debug=False, dst_file="/tmp/migfile"):
 
         self._binary = binary # Path to QEMU binary
         self._dst_host = dst_host # Hostname of target host
+        self._dst_file = dst_file # Path to file (for file transport)
         self._kernel = kernel # Path to kernel image
         self._initrd = initrd # Path to stress initrd
         self._transport = transport # 'unix' or 'tcp' or 'rdma'
@@ -203,6 +204,34 @@ class Engine(object):
             resp = dst.command("migrate-set-parameters",
                                multifd_channels=scenario._multifd_channels)
 
+        if scenario._fixed_ram:
+            resp = src.command("migrate-set-capabilities",
+                               capabilities = [
+                                   { "capability": "fixed-ram",
+                                     "state": True }
+                               ])
+            resp = dst.command("migrate-set-capabilities",
+                               capabilities = [
+                                   { "capability": "fixed-ram",
+                                     "state": True }
+                               ])
+
+        if scenario._direct_io:
+            resp = src.command("migrate-set-parameters",
+                               direct_io=scenario._direct_io)
+
+        if scenario._suspend:
+            resp = src.command("migrate-set-capabilities",
+                               capabilities = [
+                                   { "capability": "suspend",
+                                     "state": True }
+                               ])
+            resp = dst.command("migrate-set-capabilities",
+                               capabilities = [
+                                   { "capability": "suspend",
+                                     "state": True }
+                               ])
+
         resp = src.command("migrate", uri=connect_uri)
 
         post_copy = False
@@ -233,14 +262,31 @@ class Engine(object):
                     progress_history.append(progress)
 
                 if progress._status == "completed":
-                    if self._verbose:
-                        print("Sleeping %d seconds for final guest workload run" % self._sleep)
-                    sleep_secs = self._sleep
-                    while sleep_secs > 1:
-                        time.sleep(1)
-                        src_qemu_time.append(self._cpu_timing(src_pid))
-                        src_vcpu_time.extend(self._vcpu_timing(src_pid, src_threads))
-                        sleep_secs -= 1
+                    print("Transferred %5dMB of non-zero pages (total %5dMB @%5dMB/s in %4dms)" % (
+                        progress._ram._normal_bytes / (1024 * 1024),
+                        progress._ram._total_bytes / (1024 * 1024),
+                        progress._ram._transfer_rate_mbs / 8,
+                        progress._duration,
+                    ))
+
+                    if connect_uri[0:5] == "file:":
+                        if self._verbose:
+                            print("Migrating incoming")
+                        dst.command("migrate-incoming", uri=connect_uri)
+
+                        while True:
+                            progress = self._migrate_progress(dst)
+                            if progress._status in ("completed", "failed", "cancelled"):
+                                break;
+                    else:
+                        if self._verbose:
+                            print("Sleeping %d seconds for final guest workload run" % self._sleep)
+                        sleep_secs = self._sleep
+                        while sleep_secs > 1:
+                            time.sleep(1)
+                            src_qemu_time.append(self._cpu_timing(src_pid))
+                            src_vcpu_time.extend(self._vcpu_timing(src_pid, src_threads))
+                            sleep_secs -= 1
 
                 return [progress_history, src_qemu_time, src_vcpu_time]
 
@@ -357,7 +403,11 @@ class Engine(object):
         if self._dst_host != "localhost":
             tunnelled = True
         argv = self._get_common_args(hardware, tunnelled)
-        return argv + ["-incoming", uri]
+
+        incoming = ["-incoming", uri]
+        if uri[0:5] == "file:":
+            incoming = ["-incoming", "defer"]
+        return argv + incoming
 
     @staticmethod
     def _get_common_wrapper(cpu_bind, mem_bind):
@@ -417,6 +467,10 @@ class Engine(object):
                 os.remove(monaddr)
             except:
                 pass
+        elif self._transport == "file":
+            if self._dst_host != "localhost":
+                raise Exception("Use unix migration transport for non-local host")
+            uri = "file:%s" % self._dst_file
 
         if self._dst_host != "localhost":
             dstmonaddr = ("localhost", 9001)
@@ -453,6 +507,9 @@ class Engine(object):
             if self._dst_host == "localhost" and os.path.exists(dstmonaddr):
                 os.remove(dstmonaddr)
 
+            if uri[0:5] == "file:" and os.path.exists(uri[5:]):
+                os.remove(uri[5:])
+
             if self._verbose:
                 print("Finished migration")
 

tests/migration/guestperf/scenario.py

@@ -30,7 +30,8 @@ class Scenario(object):
                  auto_converge=False, auto_converge_step=10,
                  compression_mt=False, compression_mt_threads=1,
                  compression_xbzrle=False, compression_xbzrle_cache=10,
-                 multifd=False, multifd_channels=2):
+                 multifd=False, multifd_channels=2,
+                 fixed_ram=False, direct_io=False, suspend=False):
 
         self._name = name
 
@@ -60,6 +61,12 @@ class Scenario(object):
         self._multifd = multifd
         self._multifd_channels = multifd_channels
 
+        self._fixed_ram = fixed_ram
+
+        self._direct_io = direct_io
+
+        self._suspend = suspend
+
     def serialize(self):
         return {
             "name": self._name,
@@ -79,6 +86,9 @@ class Scenario(object):
             "compression_xbzrle_cache": self._compression_xbzrle_cache,
             "multifd": self._multifd,
             "multifd_channels": self._multifd_channels,
+            "fixed_ram": self._fixed_ram,
+            "direct_io": self._direct_io,
+            "suspend": self._suspend,
         }
 
     @classmethod
@@ -100,4 +110,7 @@ class Scenario(object):
             data["compression_xbzrle"],
             data["compression_xbzrle_cache"],
             data["multifd"],
-            data["multifd_channels"])
+            data["multifd_channels"],
+            data["fixed_ram"],
+            data["direct_io"],
+            data["suspend"])

tests/migration/guestperf/shell.py

@@ -48,6 +48,7 @@ class BaseShell(object):
         parser.add_argument("--kernel", dest="kernel", default="/boot/vmlinuz-%s" % platform.release())
         parser.add_argument("--initrd", dest="initrd", default="tests/migration/initrd-stress.img")
         parser.add_argument("--transport", dest="transport", default="unix")
+        parser.add_argument("--dst-file", dest="dst_file")
 
 
         # Hardware args
@@ -71,7 +72,8 @@ class BaseShell(object):
                       transport=args.transport,
                       sleep=args.sleep,
                       debug=args.debug,
-                      verbose=args.verbose)
+                      verbose=args.verbose,
+                      dst_file=args.dst_file)
 
     def get_hardware(self, args):
         def split_map(value):
@@ -127,6 +129,15 @@ class Shell(BaseShell):
         parser.add_argument("--multifd-channels", dest="multifd_channels",
                             default=2, type=int)
 
+        parser.add_argument("--fixed-ram", dest="fixed_ram", default=False,
+                            action="store_true")
+
+        parser.add_argument("--direct-io", dest="direct_io", default=False,
+                            action="store_true")
+
+        parser.add_argument("--suspend", dest="suspend", default=False,
+                            action="store_true")
+
     def get_scenario(self, args):
         return Scenario(name="perfreport",
                         downtime=args.downtime,
@@ -150,7 +161,14 @@ class Shell(BaseShell):
                         compression_xbzrle_cache=args.compression_xbzrle_cache,
 
                         multifd=args.multifd,
-                        multifd_channels=args.multifd_channels)
+                        multifd_channels=args.multifd_channels,
+
+                        fixed_ram=args.fixed_ram,
+
+                        direct_io=args.direct_io,
+
+                        suspend=args.suspend)
+
 
     def run(self, argv):
         args = self._parser.parse_args(argv)
@@ -187,6 +205,7 @@ class BatchShell(BaseShell):
 
         parser.add_argument("--filter", dest="filter", default="*")
         parser.add_argument("--output", dest="output", default=os.getcwd())
+        parser.add_argument("--iters", dest="iters", default=1, type=int)
 
     def run(self, argv):
         args = self._parser.parse_args(argv)
@@ -202,22 +221,23 @@ class BatchShell(BaseShell):
             for comparison in COMPARISONS:
                 compdir = os.path.join(args.output, comparison._name)
                 for scenario in comparison._scenarios:
-                    name = os.path.join(comparison._name, scenario._name)
-                    if not fnmatch.fnmatch(name, args.filter):
+                    for n in range(args.iters):
+                        name = os.path.join(comparison._name, scenario._name)
+                        if not fnmatch.fnmatch(name, args.filter):
+                            if args.verbose:
+                                print("Skipping %s" % name)
+                            continue
+
                         if args.verbose:
-                            print("Skipping %s" % name)
-                        continue
+                            print("Running %s i=%d" % (name,n))
 
-                    if args.verbose:
-                        print("Running %s" % name)
-
-                    dirname = os.path.join(args.output, comparison._name)
-                    filename = os.path.join(dirname, scenario._name + ".json")
-                    if not os.path.exists(dirname):
-                        os.makedirs(dirname)
-                    report = engine.run(hardware, scenario)
-                    with open(filename, "w") as fh:
-                        print(report.to_json(), file=fh)
+                        dirname = os.path.join(args.output, comparison._name)
+                        filename = os.path.join(dirname, scenario._name + ".json")
+                        if not os.path.exists(dirname):
+                            os.makedirs(dirname)
+                        report = engine.run(hardware, scenario)
+                        with open(filename, "w") as fh:
+                            print(report.to_json(), file=fh)
         except Exception as e:
             print("Error: %s" % str(e), file=sys.stderr)
             if args.debug:

tests/qtest/migration-helpers.c

@@ -130,6 +130,25 @@ void migrate_qmp(QTestState *who, const char *uri, const char *fmt, ...)
     qobject_unref(rsp);
 }
 
+
+void migrate_incoming_qmp(QTestState *who, const char *uri, const char *fmt, ...)
+{
+    va_list ap;
+    QDict *args, *rsp;
+
+    va_start(ap, fmt);
+    args = qdict_from_vjsonf_nofail(fmt, ap);
+    va_end(ap);
+
+    g_assert(!qdict_haskey(args, "uri"));
+    qdict_put_str(args, "uri", uri);
+
+    rsp = qtest_qmp(who, "{ 'execute': 'migrate-incoming', 'arguments': %p}", args);
+
+    g_assert(qdict_haskey(rsp, "return"));
+    qobject_unref(rsp);
+}
+
 /*
  * Note: caller is responsible to free the returned object via
  * qobject_unref() after use

tests/qtest/migration-helpers.h

@@ -31,6 +31,10 @@ QDict *qmp_command(QTestState *who, const char *command, ...);
 G_GNUC_PRINTF(3, 4)
 void migrate_qmp(QTestState *who, const char *uri, const char *fmt, ...);
 
+G_GNUC_PRINTF(3, 4)
+void migrate_incoming_qmp(QTestState *who, const char *uri,
+                          const char *fmt, ...);
+
 QDict *migrate_query(QTestState *who);
 QDict *migrate_query_not_failed(QTestState *who);
 

tests/qtest/migration-test.c

@@ -780,6 +780,7 @@ static void test_migrate_end(QTestState *from, QTestState *to, bool test_dest)
     cleanup("migsocket");
     cleanup("src_serial");
     cleanup("dest_serial");
+    cleanup("migfile");
 }
 
 #ifdef CONFIG_GNUTLS
@@ -1452,6 +1453,14 @@ static void test_precopy_common(MigrateCommon *args)
          * hanging forever if migration didn't converge */
         wait_for_migration_complete(from);
 
+        /*
+         * For file based migration the target must begin its migration after
+         * the source has finished
+         */
+        if (args->connect_uri && strstr(args->connect_uri, "file:")) {
+            migrate_incoming_qmp(to, args->connect_uri, "{}");
+        }
+
         if (!got_stop) {
             qtest_qmp_eventwait(from, "STOP");
         }
@@ -1639,6 +1648,137 @@ static void test_precopy_unix_compress_nowait(void)
     test_precopy_common(&args);
 }
 
+static void test_precopy_file_stream_ram(void)
+{
+    g_autofree char *uri = g_strdup_printf("file:%s/migfile", tmpfs);
+    MigrateCommon args = {
+        .connect_uri = uri,
+        .listen_uri = "defer",
+    };
+
+    test_precopy_common(&args);
+}
+
+static void *migrate_fixed_ram_start_live(QTestState *from, QTestState *to)
+{
+    migrate_set_capability(from, "fixed-ram", true);
+    migrate_set_capability(to, "fixed-ram", true);
+
+    return NULL;
+}
+
+static void *migrate_fixed_ram_start_nonlive(QTestState *from, QTestState *to)
+{
+    migrate_fixed_ram_start_live(from, to);
+
+    migrate_set_capability(from, "suspend", true);
+    migrate_set_capability(to, "suspend", true);
+
+    return NULL;
+}
+
+static void test_precopy_file_fixed_ram_live(void)
+{
+    g_autofree char *uri = g_strdup_printf("file:%s/migfile", tmpfs);
+    MigrateCommon args = {
+        .connect_uri = uri,
+        .listen_uri = "defer",
+        .start_hook = migrate_fixed_ram_start_live,
+    };
+
+    test_precopy_common(&args);
+}
+
+static void test_precopy_file_fixed_ram_nonlive(void)
+{
+    g_autofree char *uri = g_strdup_printf("file:%s/migfile", tmpfs);
+    MigrateCommon args = {
+        .connect_uri = uri,
+        .listen_uri = "defer",
+        .start_hook = migrate_fixed_ram_start_nonlive,
+    };
+
+    test_precopy_common(&args);
+}
+
+static void *migrate_multifd_fixed_ram_start_live(QTestState *from, QTestState *to)
+{
+    migrate_fixed_ram_start_live(from, to);
+
+    migrate_set_parameter_int(from, "multifd-channels", 4);
+    migrate_set_parameter_int(to, "multifd-channels", 4);
+
+    migrate_set_capability(from, "multifd", true);
+    migrate_set_capability(to, "multifd", true);
+
+    return NULL;
+}
+
+static void *migrate_multifd_fixed_ram_start_nonlive(QTestState *from, QTestState *to)
+{
+    migrate_fixed_ram_start_nonlive(from, to);
+
+    migrate_set_parameter_int(from, "multifd-channels", 4);
+    migrate_set_parameter_int(to, "multifd-channels", 4);
+
+    migrate_set_capability(from, "multifd", true);
+    migrate_set_capability(to, "multifd", true);
+
+    return NULL;
+}
+
+static void *migrate_multifd_fixed_ram_dio_start_nonlive(QTestState *from, QTestState *to)
+{
+    migrate_fixed_ram_start_nonlive(from, to);
+
+    migrate_set_parameter_int(from, "multifd-channels", 4);
+    migrate_set_parameter_int(to, "multifd-channels", 4);
+
+    migrate_set_capability(from, "multifd", true);
+    migrate_set_capability(to, "multifd", true);
+
+    migrate_set_parameter_bool(from, "direct-io", true);
+    migrate_set_parameter_bool(to, "direct-io", true);
+
+    return NULL;
+}
+
+static void test_multifd_file_fixed_ram_live(void)
+{
+    g_autofree char *uri = g_strdup_printf("file:%s/migfile", tmpfs);
+    MigrateCommon args = {
+        .connect_uri = uri,
+        .listen_uri = "defer",
+        .start_hook = migrate_multifd_fixed_ram_start_live,
+    };
+
+    test_precopy_common(&args);
+}
+
+static void test_multifd_file_fixed_ram_nonlive(void)
+{
+    g_autofree char *uri = g_strdup_printf("file:%s/migfile", tmpfs);
+    MigrateCommon args = {
+        .connect_uri = uri,
+        .listen_uri = "defer",
+        .start_hook = migrate_multifd_fixed_ram_start_nonlive,
+    };
+
+    test_precopy_common(&args);
+}
+
+static void test_multifd_file_fixed_ram_dio_nonlive(void)
+{
+    g_autofree char *uri = g_strdup_printf("file:%s/migfile", tmpfs);
+    MigrateCommon args = {
+        .connect_uri = uri,
+        .listen_uri = "defer",
+        .start_hook = migrate_multifd_fixed_ram_dio_start_nonlive,
+    };
+
+    test_precopy_common(&args);
+}
+
 static void test_precopy_tcp_plain(void)
 {
     MigrateCommon args = {
@@ -2668,6 +2808,23 @@ int main(int argc, char **argv)
         qtest_add_func("/migration/precopy/unix/compress/nowait",
                        test_precopy_unix_compress_nowait);
     }
+
+    qtest_add_func("/migration/precopy/file/stream-ram",
+                   test_precopy_file_stream_ram);
+
+    qtest_add_func("/migration/precopy/file/fixed-ram/nonlive",
+                   test_precopy_file_fixed_ram_nonlive);
+    qtest_add_func("/migration/precopy/file/fixed-ram/live",
+                   test_precopy_file_fixed_ram_live);
+
+    qtest_add_func("/migration/multifd/file/fixed-ram/nonlive",
+                   test_multifd_file_fixed_ram_nonlive);
+    qtest_add_func("/migration/multifd/file/fixed-ram/live",
+                   test_multifd_file_fixed_ram_live);
+
+    qtest_add_func("/migration/multifd/file/fixed-ram/dio/nonlive",
+                   test_multifd_file_fixed_ram_dio_nonlive);
+
 #ifdef CONFIG_GNUTLS
     qtest_add_func("/migration/precopy/unix/tls/psk",
                    test_precopy_unix_tls_psk);

util/osdep.c

@@ -277,6 +277,15 @@ int qemu_lock_fd_test(int fd, int64_t start, int64_t len, bool exclusive)
 }
 #endif
 
+bool qemu_has_direct_io(void)
+{
+#ifdef O_DIRECT
+    return true;
+#else
+    return false;
+#endif
+}
+
 static int qemu_open_cloexec(const char *name, int flags, mode_t mode)
 {
     int ret;