tests/qtest: Add a test for migration with direct-io and multifd

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

docs/devel/migration.rst

@@ -566,6 +566,20 @@ 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.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/global_state.h

@@ -16,7 +16,8 @@
 #include "qapi/qapi-types-run-state.h"
 
 void register_global_state(void);
-void global_state_store(void);
+RunState global_state_store(void);
+RunState global_state_store_once(void);
 void global_state_store_running(void);
 bool global_state_received(void);
 RunState global_state_get_runstate(void);

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 +1,188 @@
+/*
+ * Copyright (c) 2021-2023 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qemu/cutils.h"
+#include "qemu/error-report.h"
+#include "channel.h"
+#include "file.h"
+#include "io/channel-file.h"
+#include "io/channel-util.h"
+#include "migration.h"
+#include "options.h"
+#include "trace.h"
+
+#define OFFSET_OPTION ",offset="
+
+static struct FileOutgoingArgs {
+    char *fname;
+    int flags;
+    int mode;
+} outgoing_args;
+
+/* Remove the offset option from @filespec and return it in @offsetp. */
+
+static int file_parse_offset(const char *filespec, uint64_t *offsetp, Error **errp)
+{
+    char *option = strstr(filespec, OFFSET_OPTION);
+    int ret;
+
+    if (option) {
+        *option = 0;
+        option += sizeof(OFFSET_OPTION) - 1;
+        ret = qemu_strtosz(option, NULL, offsetp);
+        if (ret) {
+            error_setg_errno(errp, -ret, "file URI has bad offset %s", option);
+            return -1;
+        }
+    }
+    return 0;
+}
+
+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 *filename,
+                                   Error **errp)
+{
+    g_autoptr(QIOChannelFile) fioc = NULL;
+    uint64_t offset = 0;
+    QIOChannel *ioc;
+    int flags = O_CREAT | O_TRUNC | O_WRONLY;
+    mode_t mode = 0660;
+
+    trace_migration_file_outgoing(filename);
+
+    if (file_parse_offset(filename, &offset, errp)) {
+        return;
+    }
+
+    fioc = qio_channel_file_new_path(filename, flags, mode, errp);
+    if (!fioc) {
+        return;
+    }
+
+    outgoing_args.fname = g_strdup(filename);
+    outgoing_args.flags = flags;
+    outgoing_args.mode = mode;
+
+    ioc = QIO_CHANNEL(fioc);
+    if (offset && qio_channel_io_seek(ioc, offset, SEEK_SET, errp) < 0) {
+        return;
+    }
+    qio_channel_set_name(ioc, "migration-file-outgoing");
+    migration_channel_connect(s, ioc, NULL, NULL);
+}
+
+static gboolean file_accept_incoming_migration(QIOChannel *ioc,
+                                               GIOCondition condition,
+                                               gpointer opaque)
+{
+    migration_channel_process_incoming(ioc);
+    object_unref(OBJECT(ioc));
+    return G_SOURCE_REMOVE;
+}
+
+void file_start_incoming_migration(const char *filespec, Error **errp)
+{
+    g_autofree char *filename = g_strdup(filespec);
+    QIOChannelFile *fioc = NULL;
+    uint64_t offset = 0;
+    int channels = 1;
+    int i = 0, fd;
+
+    trace_migration_file_incoming(filename);
+
+    if (file_parse_offset(filename, &offset, errp)) {
+        return;
+    }
+
+    fioc = qio_channel_file_new_path(filename, O_RDONLY, 0, errp);
+    if (!fioc) {
+        goto out;
+    }
+
+    if (migrate_multifd()) {
+        channels += migrate_multifd_channels();
+    }
+
+    fd = fioc->fd;
+
+    do {
+        QIOChannel *ioc = QIO_CHANNEL(fioc);
+
+        if (offset && qio_channel_io_seek(ioc, offset, SEEK_SET, errp) < 0) {
+            return;
+        }
+
+        qio_channel_set_name(ioc, "migration-file-incoming");
+        qio_channel_add_watch_full(ioc, G_IO_IN,
+                                   file_accept_incoming_migration,
+                                   NULL, NULL,
+                                   g_main_context_get_thread_default());
+    } while (++i < channels && (fioc = qio_channel_file_new_fd(fd)));
+
+out:
+    if (!fioc) {
+        error_report("Error creating migration incoming channel");
+        return;
+    }
+}

migration/file.h

@@ -0,0 +1,20 @@
+/*
+ * Copyright (c) 2021-2023 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ * See the COPYING file in the top-level directory.
+ */
+
+#ifndef QEMU_MIGRATION_FILE_H
+#define QEMU_MIGRATION_FILE_H
+
+#include "io/task.h"
+#include "channel.h"
+
+void file_start_incoming_migration(const char *filename, Error **errp);
+
+void file_start_outgoing_migration(MigrationState *s, const char *filename,
+                                   Error **errp);
+void file_send_channel_create(QIOTaskFunc f, void *data);
+int file_send_channel_destroy(QIOChannel *ioc);
+#endif

migration/global_state.c

@@ -37,9 +37,25 @@ static void global_state_do_store(RunState state)
               state_str, '\0');
 }
 
-void global_state_store(void)
+RunState global_state_store(void)
 {
-    global_state_do_store(runstate_get());
+    RunState r = runstate_get();
+
+    global_state_do_store(r);
+    return r;
+}
+
+RunState global_state_store_once(void)
+{
+    int r;
+    char *runstate = (char *)global_state.runstate;
+
+    r = qapi_enum_parse(&RunState_lookup, runstate, -1, NULL);
+    if (r < 0) {
+        return global_state_store();
+    }
+
+    return r;
 }
 
 void global_state_store_running(void)

migration/meson.build

@@ -16,6 +16,7 @@ system_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"
@@ -103,22 +104,58 @@ static bool migration_needs_multiple_sockets(void)
     return migrate_multifd() || migrate_postcopy_preempt();
 }
 
+static bool migration_needs_seekable_channel(void)
+{
+    return migrate_fixed_ram();
+}
+
 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 uri_supports_seeking(const char *uri)
+{
+    return strstart(uri, "file:", NULL);
 }
 
 static bool
 migration_channels_and_uri_compatible(const char *uri, Error **errp)
 {
+    bool compatible = true;
+
+    if (migration_needs_seekable_channel() &&
+        !uri_supports_seeking(uri)) {
+        error_setg(errp, "Migration requires seekable transport (e.g. file)");
+        compatible = false;
+    }
+
     if (migration_needs_multiple_sockets() &&
         !uri_supports_multi_channels(uri)) {
         error_setg(errp, "Migration requires multi-channel URIs (e.g. tcp)");
+        compatible = false;
+    }
+
+    return compatible;
+}
+
+static bool migration_should_pause(const char *uri)
+{
+    if (!migrate_auto_pause()) {
         return false;
     }
 
-    return true;
+    /*
+     * Return true for migration schemes that benefit from a nonlive
+     * migration.
+     */
+
+    if (strstart(uri, "file:", NULL)) {
+        return true;
+    }
+
+    return false;
 }
 
 static gint page_request_addr_cmp(gconstpointer ap, gconstpointer bp)
@@ -424,13 +461,16 @@ void migrate_add_address(SocketAddress *address)
 static void qemu_start_incoming_migration(const char *uri, Error **errp)
 {
     const char *p = NULL;
+    MigrationIncomingState *mis = migration_incoming_get_current();
 
     /* URI is not suitable for migration? */
     if (!migration_channels_and_uri_compatible(uri, errp)) {
         return;
     }
 
-    qapi_event_send_migration(MIGRATION_STATUS_SETUP);
+    migrate_set_state(&mis->state, MIGRATION_STATUS_NONE,
+                      MIGRATION_STATUS_SETUP);
+
     if (strstart(uri, "tcp:", &p) ||
         strstart(uri, "unix:", NULL) ||
         strstart(uri, "vsock:", NULL)) {
@@ -443,6 +483,8 @@ 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);
     }
@@ -522,7 +564,7 @@ process_incoming_migration_co(void *opaque)
 
     mis->largest_page_size = qemu_ram_pagesize_largest();
     postcopy_state_set(POSTCOPY_INCOMING_NONE);
-    migrate_set_state(&mis->state, MIGRATION_STATUS_NONE,
+    migrate_set_state(&mis->state, MIGRATION_STATUS_SETUP,
                       MIGRATION_STATUS_ACTIVE);
 
     mis->loadvm_co = qemu_coroutine_self();
@@ -696,6 +738,8 @@ 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;
     }
@@ -1660,6 +1704,11 @@ void qmp_migrate(const char *uri, bool has_blk, bool blk,
         }
     }
 
+    if (migration_should_pause(uri)) {
+        global_state_store();
+        vm_stop_force_state(RUN_STATE_PAUSED);
+    }
+
     if (strstart(uri, "tcp:", &p) ||
         strstart(uri, "unix:", NULL) ||
         strstart(uri, "vsock:", NULL)) {
@@ -1672,6 +1721,8 @@ 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 (!resume_requested) {
             yank_unregister_instance(MIGRATION_YANK_INSTANCE);
@@ -2097,7 +2148,7 @@ static int postcopy_start(MigrationState *ms)
     trace_postcopy_start_set_run();
 
     qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER, NULL);
-    global_state_store();
+    global_state_store_once();
     ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
     if (ret < 0) {
         goto fail;
@@ -2304,8 +2355,7 @@ static void migration_completion(MigrationState *s)
         s->downtime_start = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
         qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER, NULL);
 
-        s->vm_old_state = runstate_get();
-        global_state_store();
+        s->vm_old_state = global_state_store_once();
 
         ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
         trace_migration_completion_vm_stop(ret);
@@ -2634,7 +2684,7 @@ 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);
@@ -2666,8 +2716,7 @@ 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 */
@@ -2781,6 +2830,7 @@ 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());
@@ -2953,7 +3003,7 @@ static void *migration_thread(void *opaque)
     MigThrError thr_error;
     bool urgent = false;
 
-    thread = MigrationThreadAdd("live_migration", qemu_get_thread_id());
+    thread = migration_threads_add("live_migration", qemu_get_thread_id());
 
     rcu_register_thread();
 
@@ -3031,7 +3081,7 @@ static void *migration_thread(void *opaque)
     migration_iteration_finish(s);
     object_unref(OBJECT(s));
     rcu_unregister_thread();
-    MigrationThreadDel(thread);
+    migration_threads_remove(thread);
     return NULL;
 }
 
@@ -3117,9 +3167,8 @@ static void *bg_migration_thread(void *opaque)
      * transition in vm_stop_force_state() we need to wakeup it up.
      */
     qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER, NULL);
-    s->vm_old_state = runstate_get();
+    s->vm_old_state = global_state_store_once();
 
-    global_state_store();
     /* Forcibly stop VM before saving state of vCPUs and devices */
     if (vm_stop_force_state(RUN_STATE_PAUSED)) {
         goto fail;

migration/migration.h

@@ -456,7 +456,9 @@ 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)
+{
+    MultiFDPages_t *pages = p->pages;
+
+    if (!pages->block) {
+        return;
+    }
+
+    for (int i = 0; i < p->normal_num; i++) {
+        ramblock_set_shadow_bmap_atomic(pages->block, pages->offset[i]);
+    }
+}
+
 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());
+    thread = migration_threads_add(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);
+
+                /*
+                 * 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 */
@@ -767,7 +829,7 @@ out:
     qemu_mutex_unlock(&p->mutex);
 
     rcu_unregister_thread();
-    MigrationThreadDel(thread);
+    migration_threads_remove(thread);
     trace_multifd_send_thread_end(p->id, p->num_packets, p->total_normal_pages);
 
     return NULL;
@@ -889,26 +951,36 @@ 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 = sioc;
+        p->c = 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 +1005,33 @@ 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 +1050,8 @@ 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 +1062,75 @@ 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;
+    bool changed = false;
+
+    if (!pages->block) {
+        pages->block = block;
+    }
+
+    if (pages->block == block) {
+        pages->offset[pages->num] = offset;
+        pages->num++;
+
+        if (pages->num < pages->allocated) {
+            return 1;
+        }
+    } else {
+        changed = true;
+    }
+
+    if (multifd_recv_pages(f) < 0) {
+        return -1;
+    }
+
+    if (changed) {
+        return multifd_recv_queue_page(f, block, offset);
+    }
+
+    return 1;
+}
+
 static void multifd_recv_terminate_threads(Error *err)
 {
     int i;
@@ -1001,6 +1152,7 @@ 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 +1201,12 @@ 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 +1219,8 @@ 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 +1229,10 @@ 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 +1257,7 @@ 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 +1265,45 @@ 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 +1311,7 @@ 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 +1326,13 @@ 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 +1353,7 @@ 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 +1367,7 @@ 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 +1376,20 @@ 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 +1411,11 @@ 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 +1440,26 @@ 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 +1470,8 @@ 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

@@ -187,6 +187,9 @@ Property migration_properties[] = {
 #endif
     DEFINE_PROP_MIG_CAP("x-switchover-ack",
                         MIGRATION_CAPABILITY_SWITCHOVER_ACK),
+    DEFINE_PROP_BOOL("x-auto-pause", MigrationState,
+                     capabilities[MIGRATION_CAPABILITY_AUTO_PAUSE], true),
+    DEFINE_PROP_MIG_CAP("x-fixed-ram", MIGRATION_CAPABILITY_FIXED_RAM),
 
     DEFINE_PROP_END_OF_LIST(),
 };
@@ -198,6 +201,13 @@ bool migrate_auto_converge(void)
     return s->capabilities[MIGRATION_CAPABILITY_AUTO_CONVERGE];
 }
 
+bool migrate_auto_pause(void)
+{
+    MigrationState *s = migrate_get_current();
+
+    return s->capabilities[MIGRATION_CAPABILITY_AUTO_PAUSE];
+}
+
 bool migrate_background_snapshot(void)
 {
     MigrationState *s = migrate_get_current();
@@ -240,6 +250,13 @@ 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();
@@ -354,6 +371,11 @@ bool migrate_multifd_flush_after_each_section(void)
     return s->multifd_flush_after_each_section;
 }
 
+bool migrate_multifd_packets(void)
+{
+    return !migrate_fixed_ram();
+}
+
 bool migrate_postcopy(void)
 {
     return migrate_postcopy_ram() || migrate_dirty_bitmaps();
@@ -366,6 +388,13 @@ 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,
@@ -564,6 +593,26 @@ 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;
 }
 
@@ -714,6 +763,22 @@ 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();
@@ -908,6 +973,11 @@ 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;
 }
 
@@ -940,6 +1010,7 @@ 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();
 }
 
 /*
@@ -1199,6 +1270,10 @@ 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)
@@ -1317,6 +1392,10 @@ 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

@@ -24,12 +24,14 @@ extern Property migration_properties[];
 /* capabilities */
 
 bool migrate_auto_converge(void);
+bool migrate_auto_pause(void);
 bool migrate_background_snapshot(void);
 bool migrate_block(void);
 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);
@@ -54,8 +56,10 @@ bool migrate_zero_copy_send(void);
  */
 
 bool migrate_multifd_flush_after_each_section(void);
+bool migrate_multifd_packets(void);
 bool migrate_postcopy(void);
 bool migrate_tls(void);
+bool migrate_to_file(void);
 
 /* capabilities helpers */
 
@@ -76,6 +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

@@ -558,7 +558,6 @@ void mig_throttle_counter_reset(void)
 /**
  * xbzrle_cache_zero_page: insert a zero page in the XBZRLE cache
  *
- * @rs: current RAM state
  * @current_addr: address for the zero page
  *
  * Update the xbzrle cache to reflect a page that's been sent as all 0.
@@ -567,7 +566,7 @@ void mig_throttle_counter_reset(void)
  * As a bonus, if the page wasn't in the cache it gets added so that
  * when a small write is made into the 0'd page it gets XBZRLE sent.
  */
-static void xbzrle_cache_zero_page(RAMState *rs, ram_addr_t current_addr)
+static void xbzrle_cache_zero_page(ram_addr_t current_addr)
 {
     /* We don't care if this fails to allocate a new cache page
      * as long as it updated an old one */
@@ -1088,51 +1087,50 @@ void ram_release_page(const char *rbname, uint64_t offset)
     ram_discard_range(rbname, offset, TARGET_PAGE_SIZE);
 }
 
-/**
- * save_zero_page_to_file: send the zero page to the file
- *
- * Returns the size of data written to the file, 0 means the page is not
- * a zero page
- *
- * @pss: current PSS channel
- * @block: block that contains the page we want to send
- * @offset: offset inside the block for the page
- */
-static int save_zero_page_to_file(PageSearchStatus *pss, QEMUFile *file,
-                                  RAMBlock *block, ram_addr_t offset)
-{
-    uint8_t *p = block->host + offset;
-    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;
-        ram_release_page(block->idstr, offset);
-    }
-    return len;
-}
-
 /**
  * save_zero_page: send the zero page to the stream
  *
  * Returns the number of pages written.
  *
+ * @rs: current RAM state
  * @pss: current PSS channel
  * @block: block that contains the page we want to send
  * @offset: offset inside the block for the page
  */
-static int save_zero_page(PageSearchStatus *pss, QEMUFile *f, RAMBlock *block,
+static int save_zero_page(RAMState *rs, PageSearchStatus *pss, RAMBlock *block,
                           ram_addr_t offset)
 {
-    int len = save_zero_page_to_file(pss, f, block, offset);
+    uint8_t *p = block->host + offset;
+    QEMUFile *file = pss->pss_channel;
+    int len = 0;
 
-    if (len) {
-        stat64_add(&mig_stats.zero_pages, 1);
-        ram_transferred_add(len);
+    if (!buffer_is_zero(p, TARGET_PAGE_SIZE)) {
+        return 0;
+    }
+
+    stat64_add(&mig_stats.zero_pages, 1);
+
+    if (migrate_fixed_ram()) {
+        /* fixed-ram does not touch zero pages, consider it handled */
         return 1;
     }
-    return -1;
+
+    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);
+    ram_transferred_add(len);
+
+    /* Must let xbzrle know, otherwise a previous (now 0'd) cached
+     * page would be stale
+     */
+    if (rs->xbzrle_started) {
+        XBZRLE_cache_lock();
+        xbzrle_cache_zero_page(block->offset + offset);
+        XBZRLE_cache_unlock();
+    }
+
+    return len;
 }
 
 /*
@@ -1189,14 +1187,20 @@ 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);
@@ -1358,14 +1362,16 @@ 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
@@ -2100,17 +2106,8 @@ static int ram_save_target_page_legacy(RAMState *rs, PageSearchStatus *pss)
         return 1;
     }
 
-    res = save_zero_page(pss, pss->pss_channel, block, offset);
-    if (res > 0) {
-        /* Must let xbzrle know, otherwise a previous (now 0'd) cached
-         * page would be stale
-         */
-        if (rs->xbzrle_started) {
-            XBZRLE_cache_lock();
-            xbzrle_cache_zero_page(rs, block->offset + offset);
-            XBZRLE_cache_unlock();
-        }
-        return res;
+    if (save_zero_page(rs, pss, block, offset)) {
+        return 1;
     }
 
     /*
@@ -2466,6 +2463,8 @@ 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();
@@ -2833,6 +2832,7 @@ 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));
         }
@@ -2973,6 +2973,70 @@ 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
@@ -3022,6 +3086,12 @@ 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);
+            }
         }
     }
 
@@ -3045,6 +3115,23 @@ 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_atomic(RAMBlock *block, ram_addr_t offset)
+{
+    set_bit_atomic(offset >> TARGET_PAGE_BITS, block->shadow_bmap);
+}
+
 /**
  * ram_save_iterate: iterative stage for migration
  *
@@ -3157,7 +3244,6 @@ 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) {
@@ -3202,6 +3288,9 @@ 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) {
@@ -3227,7 +3316,9 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
     if (!migrate_multifd_flush_after_each_section()) {
         qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH);
     }
+
     qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
+
     qemu_fflush(f);
 
     return 0;
@@ -3826,6 +3917,154 @@ 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
  *
@@ -3840,14 +4079,13 @@ 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;
 
@@ -3918,65 +4156,7 @@ 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:
@@ -4014,6 +4194,7 @@ static int ram_load_precopy(QEMUFile *f)
             if (migrate_multifd_flush_after_each_section()) {
                 multifd_recv_sync_main();
             }
+
             break;
         case RAM_SAVE_FLAG_HOOK:
             ram_control_load_hook(f, RAM_CONTROL_HOOK, NULL);

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_atomic(RAMBlock *block, ram_addr_t offset);
 
 /* 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;
@@ -1631,6 +1632,7 @@ 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;
         }
@@ -1653,6 +1655,9 @@ 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/threadinfo.c

@@ -10,23 +10,35 @@
  *  See the COPYING file in the top-level directory.
  */
 
+#include "qemu/osdep.h"
+#include "qemu/queue.h"
+#include "qemu/lockable.h"
 #include "threadinfo.h"
 
+QemuMutex migration_threads_lock;
 static QLIST_HEAD(, MigrationThread) migration_threads;
 
-MigrationThread *MigrationThreadAdd(const char *name, int thread_id)
+static void __attribute__((constructor)) migration_threads_init(void)
+{
+    qemu_mutex_init(&migration_threads_lock);
+}
+
+MigrationThread *migration_threads_add(const char *name, int thread_id)
 {
     MigrationThread *thread =  g_new0(MigrationThread, 1);
     thread->name = name;
     thread->thread_id = thread_id;
 
-    QLIST_INSERT_HEAD(&migration_threads, thread, node);
+    WITH_QEMU_LOCK_GUARD(&migration_threads_lock) {
+        QLIST_INSERT_HEAD(&migration_threads, thread, node);
+    }
 
     return thread;
 }
 
-void MigrationThreadDel(MigrationThread *thread)
+void migration_threads_remove(MigrationThread *thread)
 {
+    QEMU_LOCK_GUARD(&migration_threads_lock);
     if (thread) {
         QLIST_REMOVE(thread, node);
         g_free(thread);
@@ -39,6 +51,7 @@ MigrationThreadInfoList *qmp_query_migrationthreads(Error **errp)
     MigrationThreadInfoList **tail = &head;
     MigrationThread *thread = NULL;
 
+    QEMU_LOCK_GUARD(&migration_threads_lock);
     QLIST_FOREACH(thread, &migration_threads, node) {
         MigrationThreadInfo *info = g_new0(MigrationThreadInfo, 1);
         info->name = g_strdup(thread->name);

migration/threadinfo.h

@@ -10,8 +10,6 @@
  *  See the COPYING file in the top-level directory.
  */
 
-#include "qemu/queue.h"
-#include "qemu/osdep.h"
 #include "qapi/error.h"
 #include "qapi/qapi-commands-migration.h"
 
@@ -23,6 +21,5 @@ struct MigrationThread {
     QLIST_ENTRY(MigrationThread) node;
 };
 
-MigrationThread *MigrationThreadAdd(const char *name, int thread_id);
-
-void MigrationThreadDel(MigrationThread *info);
+MigrationThread *migration_threads_add(const char *name, int thread_id);
+void migration_threads_remove(MigrationThread *info);

migration/trace-events

@@ -167,6 +167,7 @@ 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) ""
@@ -310,6 +311,10 @@ migration_exec_incoming(const char *cmd) "cmd=%s"
 migration_fd_outgoing(int fd) "fd=%d"
 migration_fd_incoming(int fd) "fd=%d"
 
+# file.c
+migration_file_outgoing(const char *filename) "filename=%s"
+migration_file_incoming(const char *filename) "filename=%s"
+
 # socket.c
 migration_socket_incoming_accepted(void) ""
 migration_socket_outgoing_connected(const char *hostname) "hostname=%s"

qapi/migration.json

@@ -497,6 +497,13 @@
 #     are present.  'return-path' capability must be enabled to use
 #     it.  (since 8.1)
 #
+# @auto-pause: If enabled, allows QEMU to decide whether to pause the
+#     VM before migration for an optimal migration performance.
+#     Enabled by default. (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.
@@ -512,7 +519,8 @@
            'dirty-bitmaps', 'postcopy-blocktime', 'late-block-activate',
            { 'name': 'x-ignore-shared', 'features': [ 'unstable' ] },
            'validate-uuid', 'background-snapshot',
-           'zero-copy-send', 'postcopy-preempt', 'switchover-ack'] }
+           'zero-copy-send', 'postcopy-preempt', 'switchover-ack',
+           'auto-pause', 'fixed-ram'] }
 
 ##
 # @MigrationCapabilityStatus:
@@ -789,6 +797,9 @@
 #     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.
@@ -810,7 +821,7 @@
            '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:
@@ -945,6 +956,9 @@
 #     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.
@@ -982,7 +996,8 @@
             '*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:
@@ -1137,6 +1152,9 @@
 #     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.
@@ -1171,7 +1189,8 @@
             '*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:

qemu-options.hx

@@ -4629,6 +4629,7 @@ DEF("incoming", HAS_ARG, QEMU_OPTION_incoming, \
     "                prepare for incoming migration, listen on\n" \
     "                specified protocol and socket address\n" \
     "-incoming fd:fd\n" \
+    "-incoming file:filename[,offset=offset]\n" \
     "-incoming exec:cmdline\n" \
     "                accept incoming migration on given file descriptor\n" \
     "                or from given external command\n" \
@@ -4645,7 +4646,11 @@ SRST
     Prepare for incoming migration, listen on a given unix socket.
 
 ``-incoming fd:fd``
-    Accept incoming migration from a given filedescriptor.
+    Accept incoming migration from a given file descriptor.
+
+``-incoming file:filename[,offset=offset]``
+    Accept incoming migration from a given file starting at offset.
+    offset allows the common size suffixes, or a 0x prefix, but not both.
 
 ``-incoming exec:cmdline``
     Accept incoming migration as an output from specified external

tests/qtest/libqtest.c

@@ -84,6 +84,7 @@ struct QTestState
     GList *pending_events;
     QTestQMPEventCallback eventCB;
     void *eventData;
+    QTestMigrationState *migration_state;
 };
 
 static GHookList abrt_hooks;
@@ -483,6 +484,8 @@ QTestState *qtest_init_without_qmp_handshake(const char *extra_args)
         s->irq_level[i] = false;
     }
 
+    s->migration_state = g_new0(QTestMigrationState, 1);
+
     /*
      * Stopping QEMU for debugging is not supported on Windows.
      *
@@ -574,6 +577,7 @@ void qtest_quit(QTestState *s)
     close(s->fd);
     close(s->qmp_fd);
     g_string_free(s->rx, true);
+    g_free(s->migration_state);
 
     for (GList *it = s->pending_events; it != NULL; it = it->next) {
         qobject_unref((QDict *)it->data);
@@ -827,6 +831,11 @@ void qtest_qmp_set_event_callback(QTestState *s,
     s->eventData = opaque;
 }
 
+void qtest_qmp_set_migration_callback(QTestState *s, QTestQMPEventCallback cb)
+{
+    qtest_qmp_set_event_callback(s, cb, s->migration_state);
+}
+
 QDict *qtest_qmp_event_ref(QTestState *s, const char *event)
 {
     while (s->pending_events) {
@@ -1248,6 +1257,28 @@ void qtest_memset(QTestState *s, uint64_t addr, uint8_t pattern, size_t size)
     qtest_rsp(s);
 }
 
+QDict *qtest_vqmp_assert_failure_ref(QTestState *qts,
+                                     const char *fmt, va_list args)
+{
+    QDict *response;
+    QDict *ret;
+
+    response = qtest_vqmp(qts, fmt, args);
+
+    g_assert(response);
+    if (!qdict_haskey(response, "error")) {
+        g_autoptr(GString) s = qobject_to_json_pretty(QOBJECT(response), true);
+        g_test_message("%s", s->str);
+    }
+    g_assert(qdict_haskey(response, "error"));
+    g_assert(!qdict_haskey(response, "return"));
+    ret = qdict_get_qdict(response, "error");
+    qobject_ref(ret);
+    qobject_unref(response);
+
+    return ret;
+}
+
 QDict *qtest_vqmp_assert_success_ref(QTestState *qts,
                                      const char *fmt, va_list args)
 {
@@ -1310,6 +1341,17 @@ void qtest_vqmp_fds_assert_success(QTestState *qts, int *fds, size_t nfds,
 }
 #endif /* !_WIN32 */
 
+QDict *qtest_qmp_assert_failure_ref(QTestState *qts, const char *fmt, ...)
+{
+    QDict *response;
+    va_list ap;
+
+    va_start(ap, fmt);
+    response = qtest_vqmp_assert_failure_ref(qts, fmt, ap);
+    va_end(ap);
+    return response;
+}
+
 QDict *qtest_qmp_assert_success_ref(QTestState *qts, const char *fmt, ...)
 {
     QDict *response;
@@ -1794,3 +1836,8 @@ bool mkimg(const char *file, const char *fmt, unsigned size_mb)
 
     return ret && !err;
 }
+
+QTestMigrationState *qtest_migration_state(QTestState *s)
+{
+    return s->migration_state;
+}

tests/qtest/libqtest.h

@@ -23,6 +23,22 @@
 
 typedef struct QTestState QTestState;
 
+struct QTestMigrationState {
+    bool stop_seen;
+    bool resume_seen;
+    bool setup_seen;
+    bool active_seen;
+};
+typedef struct QTestMigrationState QTestMigrationState;
+
+/**
+ * qtest_migration_state:
+ * @s: #QTestState instance to operate on.
+ *
+ * Returns: #QTestMigrationState instance.
+ */
+QTestMigrationState *qtest_migration_state(QTestState *s);
+
 /**
  * qtest_initf:
  * @fmt: Format for creating other arguments to pass to QEMU, formatted
@@ -275,6 +291,15 @@ typedef bool (*QTestQMPEventCallback)(QTestState *s, const char *name,
 void qtest_qmp_set_event_callback(QTestState *s,
                                   QTestQMPEventCallback cb, void *opaque);
 
+/**
+ * qtest_qmp_set_migration_callback:
+ * @s: #QTestSTate instance to operate on
+ * @cb: callback to invoke for events
+ *
+ * Like qtest_qmp_set_event_callback, but includes migration state events
+ */
+void qtest_qmp_set_migration_callback(QTestState *s, QTestQMPEventCallback cb);
+
 /**
  * qtest_qmp_eventwait:
  * @s: #QTestState instance to operate on.
@@ -799,6 +824,34 @@ void qtest_vqmp_fds_assert_success(QTestState *qts, int *fds, size_t nfds,
     G_GNUC_PRINTF(4, 0);
 #endif /* !_WIN32 */
 
+/**
+ * qtest_qmp_assert_failure_ref:
+ * @qts: QTestState instance to operate on
+ * @fmt: QMP message to send to qemu, formatted like
+ * qobject_from_jsonf_nofail().  See parse_interpolation() for what's
+ * supported after '%'.
+ *
+ * Sends a QMP message to QEMU, asserts that an 'error' key is present in
+ * the response, and returns the response.
+ */
+QDict *qtest_qmp_assert_failure_ref(QTestState *qts, const char *fmt, ...)
+    G_GNUC_PRINTF(2, 3);
+
+/**
+ * qtest_vqmp_assert_failure_ref:
+ * @qts: QTestState instance to operate on
+ * @fmt: QMP message to send to qemu, formatted like
+ * qobject_from_jsonf_nofail().  See parse_interpolation() for what's
+ * supported after '%'.
+ * @args: variable arguments for @fmt
+ *
+ * Sends a QMP message to QEMU, asserts that an 'error' key is present in
+ * the response, and returns the response.
+ */
+QDict *qtest_vqmp_assert_failure_ref(QTestState *qts,
+                                     const char *fmt, va_list args)
+    G_GNUC_PRINTF(2, 0);
+
 /**
  * qtest_qmp_assert_success_ref:
  * @qts: QTestState instance to operate on

tests/qtest/meson.build

@@ -316,6 +316,7 @@ qtests = {
   'tpm-tis-i2c-test': [io, tpmemu_files, 'qtest_aspeed.c'],
   'tpm-tis-device-swtpm-test': [io, tpmemu_files, 'tpm-tis-util.c'],
   'tpm-tis-device-test': [io, tpmemu_files, 'tpm-tis-util.c'],
+  'virtio-net-failover': files('migration-helpers.c'),
   'vmgenid-test': files('boot-sector.c', 'acpi-utils.c'),
   'netdev-socket': files('netdev-socket.c', '../unit/socket-helpers.c'),
 }

tests/qtest/migration-helpers.c

@@ -23,30 +23,56 @@
  */
 #define MIGRATION_STATUS_WAIT_TIMEOUT 120
 
-bool migrate_watch_for_stop(QTestState *who, const char *name,
-                            QDict *event, void *opaque)
+bool migrate_watch_for_events(QTestState *who, const char *name,
+                              QDict *event, void *opaque)
 {
-    bool *seen = opaque;
+    QTestMigrationState *state = opaque;
 
     if (g_str_equal(name, "STOP")) {
-        *seen = true;
+        state->stop_seen = true;
+        return true;
+    } else if (g_str_equal(name, "RESUME")) {
+        state->resume_seen = true;
+        return true;
+    } else if (g_str_equal(name, "MIGRATION")) {
+        QDict *data;
+        g_assert(qdict_haskey(event, "data"));
+
+        data = qdict_get_qdict(event, "data");
+        g_assert(qdict_haskey(data, "status"));
+
+        if (g_str_equal(qdict_get_str(data, "status"), "setup")) {
+            state->setup_seen = true;
+        } else if (g_str_equal(qdict_get_str(data, "status"), "active")) {
+            state->active_seen = true;
+        } else {
+            return false;
+        }
+
         return true;
     }
 
     return false;
 }
 
-bool migrate_watch_for_resume(QTestState *who, const char *name,
-                              QDict *event, void *opaque)
+void migrate_qmp_fail(QTestState *who, const char *uri, const char *fmt, ...)
 {
-    bool *seen = opaque;
+    va_list ap;
+    QDict *args, *err;
 
-    if (g_str_equal(name, "RESUME")) {
-        *seen = true;
-        return true;
-    }
+    va_start(ap, fmt);
+    args = qdict_from_vjsonf_nofail(fmt, ap);
+    va_end(ap);
 
-    return false;
+    g_assert(!qdict_haskey(args, "uri"));
+    qdict_put_str(args, "uri", uri);
+
+    err = qtest_qmp_assert_failure_ref(
+        who, "{ 'execute': 'migrate', 'arguments': %p}", args);
+
+    g_assert(qdict_haskey(err, "desc"));
+
+    qobject_unref(err);
 }
 
 /*
@@ -70,6 +96,96 @@ void migrate_qmp(QTestState *who, const char *uri, const char *fmt, ...)
                              "{ 'execute': 'migrate', 'arguments': %p}", args);
 }
 
+void migrate_set_capability(QTestState *who, const char *capability,
+                            bool value)
+{
+    qtest_qmp_assert_success(who,
+                             "{ 'execute': 'migrate-set-capabilities',"
+                             "'arguments': { "
+                             "'capabilities': [ { "
+                             "'capability': %s, 'state': %i } ] } }",
+                             capability, value);
+}
+
+void wait_for_stop(QTestState *who)
+{
+    QTestMigrationState *state = qtest_migration_state(who);
+
+    if (!state->stop_seen) {
+        qtest_qmp_eventwait(who, "STOP");
+    }
+}
+
+void wait_for_resume(QTestState *who)
+{
+    QTestMigrationState *state = qtest_migration_state(who);
+
+    if (!state->resume_seen) {
+        qtest_qmp_eventwait(who, "RESUME");
+    }
+}
+
+static void wait_for_migration_state(QTestState *who, const char* state)
+{
+        QDict *rsp, *data;
+
+        for (;;) {
+            rsp = qtest_qmp_eventwait_ref(who, "MIGRATION");
+            g_assert(qdict_haskey(rsp, "data"));
+
+            data = qdict_get_qdict(rsp, "data");
+            g_assert(qdict_haskey(data, "status"));
+
+            if (g_str_equal(qdict_get_str(data, "status"), state)) {
+                break;
+            }
+            qobject_unref(rsp);
+        }
+
+        qobject_unref(rsp);
+        return;
+}
+
+void wait_for_setup(QTestState *who)
+{
+    QTestMigrationState *state = qtest_migration_state(who);
+
+    if (!state->setup_seen) {
+        wait_for_migration_state(who, "setup");
+    }
+}
+
+void wait_for_active(QTestState *who)
+{
+    QTestMigrationState *state = qtest_migration_state(who);
+
+    if (!state->active_seen) {
+        wait_for_migration_state(who, "active");
+    }
+}
+
+void migrate_incoming_qmp(QTestState *to, 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);
+
+    migrate_set_capability(to, "events", true);
+
+    rsp = qtest_qmp(to, "{ 'execute': 'migrate-incoming', 'arguments': %p}",
+                    args);
+    g_assert(qdict_haskey(rsp, "return"));
+    qobject_unref(rsp);
+
+    wait_for_setup(to);
+}
+
 /*
  * Note: caller is responsible to free the returned object via
  * qobject_unref() after use

tests/qtest/migration-helpers.h

@@ -15,14 +15,28 @@
 
 #include "libqtest.h"
 
-bool migrate_watch_for_stop(QTestState *who, const char *name,
-                            QDict *event, void *opaque);
-bool migrate_watch_for_resume(QTestState *who, const char *name,
+bool migrate_watch_for_events(QTestState *who, const char *name,
                               QDict *event, void *opaque);
 
+
+void wait_for_stop(QTestState *who);
+void wait_for_resume(QTestState *who);
+void wait_for_setup(QTestState *who);
+void wait_for_active(QTestState *who);
+
 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, ...);
+
+G_GNUC_PRINTF(3, 4)
+void migrate_qmp_fail(QTestState *who, const char *uri, const char *fmt, ...);
+
+void migrate_set_capability(QTestState *who, const char *capability,
+                            bool value);
+
 QDict *migrate_query(QTestState *who);
 QDict *migrate_query_not_failed(QTestState *who);
 

tests/qtest/migration-test.c

@@ -43,8 +43,6 @@
 unsigned start_address;
 unsigned end_address;
 static bool uffd_feature_thread_id;
-static bool got_src_stop;
-static bool got_dst_resume;
 
 /*
  * An initial 3 MB offset is used as that corresponds
@@ -66,6 +64,10 @@ static bool got_dst_resume;
  */
 #define DIRTYLIMIT_TOLERANCE_RANGE  25  /* MB/s */
 
+#define QEMU_VM_FILE_MAGIC 0x5145564d
+#define FILE_TEST_FILENAME "migfile"
+#define FILE_TEST_OFFSET 0x1000
+
 #if defined(__linux__)
 #include <sys/syscall.h>
 #include <sys/vfs.h>
@@ -235,21 +237,20 @@ static void read_blocktime(QTestState *who)
     qobject_unref(rsp_return);
 }
 
+/*
+ * Wait for two changes in the migration pass count, but bail if we stop.
+ */
 static void wait_for_migration_pass(QTestState *who)
 {
-    uint64_t initial_pass = get_migration_pass(who);
-    uint64_t pass;
+    uint64_t pass, prev_pass = 0, changes = 0;
+    QTestMigrationState *state = qtest_migration_state(who);
 
-    /* Wait for the 1st sync */
-    while (!got_src_stop && !initial_pass) {
-        usleep(1000);
-        initial_pass = get_migration_pass(who);
-    }
-
-    do {
+    while (changes < 2 && !state->stop_seen) {
         usleep(1000);
         pass = get_migration_pass(who);
-    } while (pass == initial_pass && !got_src_stop);
+        changes += (pass != prev_pass);
+        prev_pass = pass;
+    }
 }
 
 static void check_guests_ram(QTestState *who)
@@ -571,25 +572,11 @@ static void migrate_cancel(QTestState *who)
     qtest_qmp_assert_success(who, "{ 'execute': 'migrate_cancel' }");
 }
 
-static void migrate_set_capability(QTestState *who, const char *capability,
-                                   bool value)
-{
-    qtest_qmp_assert_success(who,
-                             "{ 'execute': 'migrate-set-capabilities',"
-                             "'arguments': { "
-                             "'capabilities': [ { "
-                             "'capability': %s, 'state': %i } ] } }",
-                             capability, value);
-}
-
 static void migrate_postcopy_start(QTestState *from, QTestState *to)
 {
     qtest_qmp_assert_success(from, "{ 'execute': 'migrate-start-postcopy' }");
 
-    if (!got_src_stop) {
-        qtest_qmp_eventwait(from, "STOP");
-    }
-
+    wait_for_stop(from);
     qtest_qmp_eventwait(to, "RESUME");
 }
 
@@ -674,6 +661,8 @@ typedef struct {
         MIG_TEST_FAIL,
         /* This test should fail, dest qemu should fail with abnormal status */
         MIG_TEST_FAIL_DEST_QUIT_ERR,
+        /* The QMP command for this migration should fail with an error */
+        MIG_TEST_QMP_ERROR,
     } result;
 
     /*
@@ -719,8 +708,6 @@ static int test_migrate_start(QTestState **from, QTestState **to,
         }
     }
 
-    got_src_stop = false;
-    got_dst_resume = false;
     bootpath = g_strdup_printf("%s/bootsect", tmpfs);
     if (strcmp(arch, "i386") == 0 || strcmp(arch, "x86_64") == 0) {
         /* the assembled x86 boot sector should be exactly one sector large */
@@ -806,9 +793,7 @@ static int test_migrate_start(QTestState **from, QTestState **to,
                                  ignore_stderr);
     if (!args->only_target) {
         *from = qtest_init(cmd_source);
-        qtest_qmp_set_event_callback(*from,
-                                     migrate_watch_for_stop,
-                                     &got_src_stop);
+        qtest_qmp_set_migration_callback(*from, migrate_watch_for_events);
     }
 
     cmd_target = g_strdup_printf("-accel kvm%s -accel tcg%s%s "
@@ -826,9 +811,7 @@ static int test_migrate_start(QTestState **from, QTestState **to,
                                  args->opts_target ? args->opts_target : "",
                                  ignore_stderr);
     *to = qtest_init(cmd_target);
-    qtest_qmp_set_event_callback(*to,
-                                 migrate_watch_for_resume,
-                                 &got_dst_resume);
+    qtest_qmp_set_migration_callback(*to, migrate_watch_for_events);
 
     /*
      * Remove shmem file immediately to avoid memory leak in test failed case.
@@ -873,6 +856,7 @@ static void test_migrate_end(QTestState *from, QTestState *to, bool test_dest)
     cleanup("migsocket");
     cleanup("src_serial");
     cleanup("dest_serial");
+    cleanup(FILE_TEST_FILENAME);
 }
 
 #ifdef CONFIG_GNUTLS
@@ -1494,6 +1478,7 @@ static void test_precopy_common(MigrateCommon *args)
 {
     QTestState *from, *to;
     void *data_hook = NULL;
+    g_autofree char *connect_uri = NULL;
 
     if (test_migrate_start(&from, &to, args->listen_uri, &args->start)) {
         return;
@@ -1520,21 +1505,23 @@ static void test_precopy_common(MigrateCommon *args)
          */
         if (args->result == MIG_TEST_SUCCEED) {
             qtest_qmp_assert_success(from, "{ 'execute' : 'stop'}");
-            if (!got_src_stop) {
-                qtest_qmp_eventwait(from, "STOP");
-            }
+            wait_for_stop(from);
             migrate_ensure_converge(from);
         }
     }
 
     if (!args->connect_uri) {
-        g_autofree char *local_connect_uri =
-            migrate_get_socket_address(to, "socket-address");
-        migrate_qmp(from, local_connect_uri, "{}");
+        connect_uri = migrate_get_socket_address(to, "socket-address");
     } else {
-        migrate_qmp(from, args->connect_uri, "{}");
+        connect_uri = g_strdup(args->connect_uri);
     }
 
+    if (args->result == MIG_TEST_QMP_ERROR) {
+        migrate_qmp_fail(from, connect_uri, "{}");
+        goto finish;
+    }
+
+    migrate_qmp(from, connect_uri, "{}");
 
     if (args->result != MIG_TEST_SUCCEED) {
         bool allow_active = args->result == MIG_TEST_FAIL;
@@ -1564,9 +1551,8 @@ static void test_precopy_common(MigrateCommon *args)
              */
             wait_for_migration_complete(from);
 
-            if (!got_src_stop) {
-                qtest_qmp_eventwait(from, "STOP");
-            }
+            wait_for_stop(from);
+
         } else {
             wait_for_migration_complete(from);
             /*
@@ -1579,13 +1565,100 @@ static void test_precopy_common(MigrateCommon *args)
             qtest_qmp_assert_success(to, "{ 'execute' : 'cont'}");
         }
 
-        if (!got_dst_resume) {
-            qtest_qmp_eventwait(to, "RESUME");
-        }
-
+        wait_for_resume(to);
         wait_for_serial("dest_serial");
     }
 
+finish:
+    if (args->finish_hook) {
+        args->finish_hook(from, to, data_hook);
+    }
+
+    test_migrate_end(from, to, args->result == MIG_TEST_SUCCEED);
+}
+
+static void test_file_common(MigrateCommon *args, bool stop_src, bool auto_pause)
+{
+    QTestState *from, *to;
+    void *data_hook = NULL;
+    g_autofree char *connect_uri = g_strdup(args->connect_uri);
+
+    if (test_migrate_start(&from, &to, args->listen_uri, &args->start)) {
+        return;
+    }
+
+    migrate_set_capability(from, "events", true);
+    migrate_set_capability(to, "events", true);
+
+    if (!auto_pause) {
+        migrate_set_capability(from, "auto-pause", false);
+    }
+
+    /*
+     * File migration is never live. We can stop the source before
+     * migrating, but the destination will not be running
+     * concurrently.
+     */
+    g_assert_false(args->live);
+
+    if (args->start_hook) {
+        data_hook = args->start_hook(from, to);
+    }
+
+    migrate_ensure_converge(from);
+    wait_for_serial("src_serial");
+
+    if (stop_src) {
+        qtest_qmp_assert_success(from, "{ 'execute' : 'stop'}");
+        wait_for_stop(from);
+    }
+
+    if (args->result == MIG_TEST_QMP_ERROR) {
+        migrate_qmp_fail(from, connect_uri, "{}");
+        goto finish;
+    }
+    migrate_qmp(from, connect_uri, "{}");
+
+    wait_for_setup(from);
+
+    /* auto-pause stops the VM right after setup */
+    if (auto_pause && !stop_src) {
+        wait_for_stop(from);
+    }
+
+    wait_for_active(from);
+
+    /*
+     * If the VM is not already stop by the test or auto-pause,
+     * migration completion will stop it.
+     */
+    if (!stop_src && !auto_pause) {
+        wait_for_stop(from);
+    }
+    wait_for_migration_complete(from);
+
+    /*
+     * We need to wait for the source to finish before starting the
+     * destination.
+     */
+    migrate_incoming_qmp(to, connect_uri, "{}");
+    wait_for_active(to);
+    wait_for_migration_complete(to);
+
+    if (stop_src || auto_pause) {
+        /*
+         * The VM has been paused on source by either the test or
+         * auto-pause, re-start on destination to make sure it won't
+         * crash.
+         */
+        qtest_qmp_assert_success(to, "{ 'execute' : 'cont'}");
+    }
+
+    wait_for_resume(to);
+
+    wait_for_serial("dest_serial");
+
+finish:
     if (args->finish_hook) {
         args->finish_hook(from, to, data_hook);
     }
@@ -1700,9 +1773,7 @@ static void test_ignore_shared(void)
 
     migrate_wait_for_dirty_mem(from, to);
 
-    if (!got_src_stop) {
-        qtest_qmp_eventwait(from, "STOP");
-    }
+    wait_for_stop(from);
 
     qtest_qmp_eventwait(to, "RESUME");
 
@@ -1788,6 +1859,171 @@ static void test_precopy_unix_compress_nowait(void)
     test_precopy_common(&args);
 }
 
+static void test_precopy_file(void)
+{
+    g_autofree char *uri = g_strdup_printf("file:%s/%s", tmpfs,
+                                           FILE_TEST_FILENAME);
+    MigrateCommon args = {
+        .connect_uri = uri,
+        .listen_uri = "defer",
+    };
+
+    test_file_common(&args, true, true);
+}
+
+static void file_offset_finish_hook(QTestState *from, QTestState *to, void *opaque)
+{
+#if defined(__linux__)
+    g_autofree char *path = g_strdup_printf("%s/%s", tmpfs, FILE_TEST_FILENAME);
+    size_t size = FILE_TEST_OFFSET + sizeof(QEMU_VM_FILE_MAGIC);
+    uintptr_t *addr, *p;
+    int fd;
+
+    fd = open(path, O_RDONLY);
+    g_assert(fd != -1);
+    addr = mmap(NULL, size, PROT_READ, MAP_SHARED, fd, 0);
+    g_assert(addr != MAP_FAILED);
+
+    /*
+     * Ensure the skipped offset contains zeros and the migration
+     * stream starts at the right place.
+     */
+    p = addr;
+    while (p < addr + FILE_TEST_OFFSET / sizeof(uintptr_t)) {
+        g_assert(*p == 0);
+        p++;
+    }
+    g_assert_cmpint(cpu_to_be32(*p), ==, QEMU_VM_FILE_MAGIC);
+
+    munmap(addr, size);
+    close(fd);
+#endif
+}
+
+static void test_precopy_file_offset(void)
+{
+    g_autofree char *uri = g_strdup_printf("file:%s/%s,offset=%d", tmpfs,
+                                           FILE_TEST_FILENAME,
+                                           FILE_TEST_OFFSET);
+    MigrateCommon args = {
+        .connect_uri = uri,
+        .listen_uri = "defer",
+        .finish_hook = file_offset_finish_hook,
+    };
+
+    test_file_common(&args, false, true);
+}
+
+static void test_precopy_file_offset_bad(void)
+{
+    /* using a value not supported by qemu_strtosz() */
+    g_autofree char *uri = g_strdup_printf("file:%s/%s,offset=0x20M",
+                                           tmpfs, FILE_TEST_FILENAME);
+    MigrateCommon args = {
+        .connect_uri = uri,
+        .listen_uri = "defer",
+        .result = MIG_TEST_QMP_ERROR,
+    };
+
+    test_file_common(&args, false, false);
+}
+
+static void *migrate_fixed_ram_start(QTestState *from, QTestState *to)
+{
+    migrate_set_capability(from, "fixed-ram", true);
+    migrate_set_capability(to, "fixed-ram", true);
+
+    return NULL;
+}
+
+static void test_precopy_file_fixed_ram_live(void)
+{
+    g_autofree char *uri = g_strdup_printf("file:%s/%s", tmpfs,
+                                           FILE_TEST_FILENAME);
+    MigrateCommon args = {
+        .connect_uri = uri,
+        .listen_uri = "defer",
+        .start_hook = migrate_fixed_ram_start,
+    };
+
+    test_file_common(&args, false, false);
+}
+
+static void test_precopy_file_fixed_ram(void)
+{
+    g_autofree char *uri = g_strdup_printf("file:%s/%s", tmpfs,
+                                           FILE_TEST_FILENAME);
+    MigrateCommon args = {
+        .connect_uri = uri,
+        .listen_uri = "defer",
+        .start_hook = migrate_fixed_ram_start,
+    };
+
+    test_file_common(&args, false, true);
+}
+
+static void *migrate_multifd_fixed_ram_start(QTestState *from, QTestState *to)
+{
+    migrate_fixed_ram_start(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(QTestState *from, QTestState *to)
+{
+    migrate_multifd_fixed_ram_start(from, to);
+
+    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/%s", tmpfs,
+                                           FILE_TEST_FILENAME);
+    MigrateCommon args = {
+        .connect_uri = uri,
+        .listen_uri = "defer",
+        .start_hook = migrate_multifd_fixed_ram_start,
+    };
+
+    test_file_common(&args, false, false);
+}
+
+static void test_multifd_file_fixed_ram(void)
+{
+    g_autofree char *uri = g_strdup_printf("file:%s/%s", tmpfs,
+                                           FILE_TEST_FILENAME);
+    MigrateCommon args = {
+        .connect_uri = uri,
+        .listen_uri = "defer",
+        .start_hook = migrate_multifd_fixed_ram_start,
+    };
+
+    test_file_common(&args, false, true);
+}
+
+static void test_multifd_file_fixed_ram_dio(void)
+{
+    g_autofree char *uri = g_strdup_printf("file:%s/%s", tmpfs,
+                                           FILE_TEST_FILENAME);
+    MigrateCommon args = {
+        .connect_uri = uri,
+        .listen_uri = "defer",
+        .start_hook = migrate_multifd_fixed_ram_dio_start,
+    };
+
+    test_file_common(&args, false, true);
+}
+
 static void test_precopy_tcp_plain(void)
 {
     MigrateCommon args = {
@@ -1961,8 +2197,7 @@ static void *test_migrate_fd_start_hook(QTestState *from,
     close(pair[0]);
 
     /* Start incoming migration from the 1st socket */
-    qtest_qmp_assert_success(to, "{ 'execute': 'migrate-incoming',"
-                             "  'arguments': { 'uri': 'fd:fd-mig' }}");
+    migrate_incoming_qmp(to, "fd:fd-mig", "{}");
 
     /* Send the 2nd socket to the target */
     qtest_qmp_fds_assert_success(from, &pair[1], 1,
@@ -2143,7 +2378,7 @@ static void test_migrate_auto_converge(void)
             break;
         }
         usleep(20);
-        g_assert_false(got_src_stop);
+        g_assert_false(qtest_migration_state(from)->stop_seen);
     } while (true);
     /* The first percentage of throttling should be at least init_pct */
     g_assert_cmpint(percentage, >=, init_pct);
@@ -2184,8 +2419,7 @@ test_migrate_precopy_tcp_multifd_start_common(QTestState *from,
     migrate_set_capability(to, "multifd", true);
 
     /* Start incoming migration from the 1st socket */
-    qtest_qmp_assert_success(to, "{ 'execute': 'migrate-incoming',"
-                             "  'arguments': { 'uri': 'tcp:127.0.0.1:0' }}");
+    migrate_incoming_qmp(to, "tcp:127.0.0.1:0", "{}");
 
     return NULL;
 }
@@ -2438,8 +2672,7 @@ static void test_multifd_tcp_cancel(void)
     migrate_set_capability(to, "multifd", true);
 
     /* Start incoming migration from the 1st socket */
-    qtest_qmp_assert_success(to, "{ 'execute': 'migrate-incoming',"
-                             "  'arguments': { 'uri': 'tcp:127.0.0.1:0' }}");
+    migrate_incoming_qmp(to, "tcp:127.0.0.1:0", "{}");
 
     /* Wait for the first serial output from the source */
     wait_for_serial("src_serial");
@@ -2469,8 +2702,7 @@ static void test_multifd_tcp_cancel(void)
     migrate_set_capability(to2, "multifd", true);
 
     /* Start incoming migration from the 1st socket */
-    qtest_qmp_assert_success(to2, "{ 'execute': 'migrate-incoming',"
-                             "  'arguments': { 'uri': 'tcp:127.0.0.1:0' }}");
+    migrate_incoming_qmp(to2, "tcp:127.0.0.1:0", "{}");
 
     g_free(uri);
     uri = migrate_get_socket_address(to2, "socket-address");
@@ -2481,13 +2713,11 @@ static void test_multifd_tcp_cancel(void)
 
     migrate_qmp(from, uri, "{}");
 
-    migrate_wait_for_dirty_mem(from, to);
+    migrate_wait_for_dirty_mem(from, to2);
 
     migrate_ensure_converge(from);
 
-    if (!got_src_stop) {
-        qtest_qmp_eventwait(from, "STOP");
-    }
+    wait_for_stop(from);
     qtest_qmp_eventwait(to2, "RESUME");
 
     wait_for_serial("dest_serial");
@@ -2844,6 +3074,27 @@ 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",
+                   test_precopy_file);
+    qtest_add_func("/migration/precopy/file/offset",
+                   test_precopy_file_offset);
+    qtest_add_func("/migration/precopy/file/offset/bad",
+                   test_precopy_file_offset_bad);
+
+    qtest_add_func("/migration/precopy/file/fixed-ram",
+                   test_precopy_file_fixed_ram);
+    qtest_add_func("/migration/precopy/file/fixed-ram/live",
+                   test_precopy_file_fixed_ram_live);
+
+    qtest_add_func("/migration/multifd/file/fixed-ram",
+                   test_multifd_file_fixed_ram);
+    qtest_add_func("/migration/multifd/file/fixed-ram/live",
+                   test_multifd_file_fixed_ram_live);
+
+    qtest_add_func("/migration/multifd/file/fixed-ram/dio",
+                   test_multifd_file_fixed_ram_dio);
+
 #ifdef CONFIG_GNUTLS
     qtest_add_func("/migration/precopy/unix/tls/psk",
                    test_precopy_unix_tls_psk);
@@ -2916,14 +3167,8 @@ int main(int argc, char **argv)
     }
     qtest_add_func("/migration/multifd/tcp/plain/none",
                    test_multifd_tcp_none);
-    /*
-     * This test is flaky and sometimes fails in CI and otherwise:
-     * don't run unless user opts in via environment variable.
-     */
-    if (getenv("QEMU_TEST_FLAKY_TESTS")) {
-        qtest_add_func("/migration/multifd/tcp/plain/cancel",
-                       test_multifd_tcp_cancel);
-    }
+    qtest_add_func("/migration/multifd/tcp/plain/cancel",
+                   test_multifd_tcp_cancel);
     qtest_add_func("/migration/multifd/tcp/plain/zlib",
                    test_multifd_tcp_zlib);
 #ifdef CONFIG_ZSTD

tests/qtest/virtio-net-failover.c

@@ -11,6 +11,7 @@
 #include "libqtest.h"
 #include "libqos/pci.h"
 #include "libqos/pci-pc.h"
+#include "migration-helpers.h"
 #include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qlist.h"
 #include "qapi/qmp/qjson.h"
@@ -736,26 +737,10 @@ static void test_migrate_out(gconstpointer opaque)
     machine_stop(qts);
 }
 
-static QDict *get_migration_event(QTestState *qts)
-{
-    QDict *resp;
-    QDict *data;
-
-    resp = qtest_qmp_eventwait_ref(qts, "MIGRATION");
-    g_assert(qdict_haskey(resp, "data"));
-
-    data = qdict_get_qdict(resp, "data");
-    g_assert(qdict_haskey(data, "status"));
-    qobject_ref(data);
-    qobject_unref(resp);
-
-    return data;
-}
-
 static void test_migrate_in(gconstpointer opaque)
 {
     QTestState *qts;
-    QDict *resp, *args, *ret;
+    QDict *resp, *ret;
     g_autofree gchar *uri = g_strdup_printf("exec: cat %s", (gchar *)opaque);
 
     qts = machine_start(BASE_MACHINE
@@ -787,18 +772,7 @@ static void test_migrate_in(gconstpointer opaque)
     check_one_card(qts, true, "standby0", MAC_STANDBY0);
     check_one_card(qts, false, "primary0", MAC_PRIMARY0);
 
-    args = qdict_from_jsonf_nofail("{}");
-    g_assert_nonnull(args);
-    qdict_put_str(args, "uri", uri);
-
-    resp = qtest_qmp(qts, "{ 'execute': 'migrate-incoming', 'arguments': %p}",
-                     args);
-    g_assert(qdict_haskey(resp, "return"));
-    qobject_unref(resp);
-
-    resp = get_migration_event(qts);
-    g_assert_cmpstr(qdict_get_str(resp, "status"), ==, "setup");
-    qobject_unref(resp);
+    migrate_incoming_qmp(qts, uri, "{}");
 
     resp = get_failover_negociated_event(qts);
     g_assert_cmpstr(qdict_get_str(resp, "device-id"), ==, "standby0");
@@ -888,7 +862,7 @@ static void test_off_migrate_out(gconstpointer opaque)
 static void test_off_migrate_in(gconstpointer opaque)
 {
     QTestState *qts;
-    QDict *resp, *args, *ret;
+    QDict *ret;
     g_autofree gchar *uri = g_strdup_printf("exec: cat %s", (gchar *)opaque);
 
     qts = machine_start(BASE_MACHINE
@@ -920,18 +894,7 @@ static void test_off_migrate_in(gconstpointer opaque)
     check_one_card(qts, true, "standby0", MAC_STANDBY0);
     check_one_card(qts, true, "primary0", MAC_PRIMARY0);
 
-    args = qdict_from_jsonf_nofail("{}");
-    g_assert_nonnull(args);
-    qdict_put_str(args, "uri", uri);
-
-    resp = qtest_qmp(qts, "{ 'execute': 'migrate-incoming', 'arguments': %p}",
-                     args);
-    g_assert(qdict_haskey(resp, "return"));
-    qobject_unref(resp);
-
-    resp = get_migration_event(qts);
-    g_assert_cmpstr(qdict_get_str(resp, "status"), ==, "setup");
-    qobject_unref(resp);
+    migrate_incoming_qmp(qts, uri, "{}");
 
     check_one_card(qts, true, "standby0", MAC_STANDBY0);
     check_one_card(qts, true, "primary0", MAC_PRIMARY0);
@@ -1026,7 +989,7 @@ static void test_guest_off_migrate_out(gconstpointer opaque)
 static void test_guest_off_migrate_in(gconstpointer opaque)
 {
     QTestState *qts;
-    QDict *resp, *args, *ret;
+    QDict *ret;
     g_autofree gchar *uri = g_strdup_printf("exec: cat %s", (gchar *)opaque);
 
     qts = machine_start(BASE_MACHINE
@@ -1058,18 +1021,7 @@ static void test_guest_off_migrate_in(gconstpointer opaque)
     check_one_card(qts, true, "standby0", MAC_STANDBY0);
     check_one_card(qts, false, "primary0", MAC_PRIMARY0);
 
-    args = qdict_from_jsonf_nofail("{}");
-    g_assert_nonnull(args);
-    qdict_put_str(args, "uri", uri);
-
-    resp = qtest_qmp(qts, "{ 'execute': 'migrate-incoming', 'arguments': %p}",
-                     args);
-    g_assert(qdict_haskey(resp, "return"));
-    qobject_unref(resp);
-
-    resp = get_migration_event(qts);
-    g_assert_cmpstr(qdict_get_str(resp, "status"), ==, "setup");
-    qobject_unref(resp);
+    migrate_incoming_qmp(qts, uri, "{}");
 
     check_one_card(qts, true, "standby0", MAC_STANDBY0);
     check_one_card(qts, false, "primary0", MAC_PRIMARY0);
@@ -1728,7 +1680,7 @@ static void test_multi_out(gconstpointer opaque)
 static void test_multi_in(gconstpointer opaque)
 {
     QTestState *qts;
-    QDict *resp, *args, *ret;
+    QDict *resp, *ret;
     g_autofree gchar *uri = g_strdup_printf("exec: cat %s", (gchar *)opaque);
 
     qts = machine_start(BASE_MACHINE
@@ -1794,18 +1746,7 @@ static void test_multi_in(gconstpointer opaque)
     check_one_card(qts, true, "standby1", MAC_STANDBY1);
     check_one_card(qts, false, "primary1", MAC_PRIMARY1);
 
-    args = qdict_from_jsonf_nofail("{}");
-    g_assert_nonnull(args);
-    qdict_put_str(args, "uri", uri);
-
-    resp = qtest_qmp(qts, "{ 'execute': 'migrate-incoming', 'arguments': %p}",
-                     args);
-    g_assert(qdict_haskey(resp, "return"));
-    qobject_unref(resp);
-
-    resp = get_migration_event(qts);
-    g_assert_cmpstr(qdict_get_str(resp, "status"), ==, "setup");
-    qobject_unref(resp);
+    migrate_incoming_qmp(qts, uri, "{}");
 
     resp = get_failover_negociated_event(qts);
     g_assert_cmpstr(qdict_get_str(resp, "device-id"), ==, "standby0");

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;