tests/qtest/migration: Print migration incoming errors

We're currently just asserting when incoming migration fails. Let's
print the error message from QMP as well.

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

docs/devel/migration.rst

@@ -41,6 +41,28 @@ over any transport.
 - exec migration: do the migration using the stdin/stdout through a process.
 - fd migration: do the migration using a file descriptor that is
   passed to QEMU.  QEMU doesn't care how this file descriptor is opened.
+- file migration: do the migration using a file that is passed to QEMU
+  by path. A file offset option is supported to allow a management
+  application to add its own metadata to the start of the file without
+  QEMU interference.
+
+  The file migration also supports using a file that has already been
+  opened. A set of file descriptors is passed to QEMU via an "fdset"
+  (see add-fd QMP command documentation). This method allows a
+  management application to have control over the migration file
+  opening operation. There are, however, strict requirements to this
+  interface:
+
+  On the migration source side:
+    - the fdset must contain two file descriptors that are not
+      duplicates between themselves;
+    - if the direct-io capability is to be used, exactly one of the
+      file descriptors must have the O_DIRECT flag set;
+    - the file must be opened with WRONLY both times.
+
+  On the migration destination side:
+    - the fdset must contain one file descriptor;
+    - the file must be opened with RDONLY.
 
 In addition, support is included for migration using RDMA, which
 transports the page data using ``RDMA``, where the hardware takes care of
@@ -572,6 +594,27 @@ 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 file.
+
+The ``fixed-ram`` capability must be enabled in both source and
+destination with:
+
+    ``migrate_set_capability fixed-ram on``
+
+Since pages are written to their relative offsets and out of order
+(due to the memory dirtying patterns), streaming channels such as
+sockets are not supported. A seekable channel such as a file is
+required. This can be verified in the QIOChannel by the presence of
+the QIO_CHANNEL_FEATURE_SEEKABLE. In more practical terms, this
+migration format requires the ``file:`` URI when migrating.
+
 Return path
 -----------
 

include/exec/ramblock.h

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

include/io/channel-file.h

@@ -89,4 +89,11 @@ qio_channel_file_new_path(const char *path,
                           mode_t mode,
                           Error **errp);
 
+/**
+ * qio_channel_file_set_direct_io:
+ * @ioc: the QIOChannel object
+ * @enabled: the desired state of the O_DIRECT flag
+ * @errp: pointer to initialized error object
+ */
+void qio_channel_file_set_direct_io(QIOChannel *ioc, bool enable, Error **errp);
 #endif /* QIO_CHANNEL_FILE_H */

include/io/channel.h

@@ -44,6 +44,7 @@ enum QIOChannelFeature {
     QIO_CHANNEL_FEATURE_LISTEN,
     QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY,
     QIO_CHANNEL_FEATURE_READ_MSG_PEEK,
+    QIO_CHANNEL_FEATURE_SEEKABLE,
 };
 
 
@@ -130,6 +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);
@@ -528,6 +539,104 @@ void qio_channel_set_follow_coroutine_ctx(QIOChannel *ioc, bool enabled);
 int qio_channel_close(QIOChannel *ioc,
                       Error **errp);
 
+/**
+ * qio_channel_pwritev
+ * @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(QIOChannel *ioc, const struct iovec *iov,
+                            size_t niov, off_t offset, Error **errp);
+
+/**
+ * qio_channel_pwritev_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
+ * @errp: pointer to a NULL-initialized error object
+ *
+ * Returns: 0 if all bytes were written, or -1 on error
+ */
+int qio_channel_pwritev_all(QIOChannel *ioc, const struct iovec *iov,
+                            size_t niov, off_t offset, Error **errp);
+
+/**
+ * qio_channel_pwrite
+ * @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_pwrite(QIOChannel *ioc, char *buf, size_t buflen,
+                           off_t offset, Error **errp);
+
+/**
+ * qio_channel_preadv
+ * @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(QIOChannel *ioc, const struct iovec *iov,
+                           size_t niov, off_t offset, Error **errp);
+
+/**
+ * qio_channel_preadv_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
+ * @errp: pointer to a NULL-initialized error object
+ *
+ * Returns: 0 if all bytes were read, or -1 on error
+ */
+int qio_channel_preadv_all(QIOChannel *ioc, const struct iovec *iov,
+                           size_t niov, off_t offset, Error **errp);
+
+/**
+ * qio_channel_pread
+ * @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_pread(QIOChannel *ioc, char *buf, size_t buflen,
+                          off_t offset, Error **errp);
+
 /**
  * qio_channel_shutdown:
  * @ioc: the channel object

include/migration/qemu-file-types.h

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

include/qemu/bitops.h

@@ -67,6 +67,19 @@ static inline void clear_bit(long nr, unsigned long *addr)
     *p &= ~mask;
 }
 
+/**
+ * clear_bit_atomic - Clears a bit in memory atomically
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ */
+static inline void clear_bit_atomic(long nr, unsigned long *addr)
+{
+    unsigned long mask = BIT_MASK(nr);
+    unsigned long *p = addr + BIT_WORD(nr);
+
+    return qatomic_and(p, ~mask);
+}
+
 /**
  * change_bit - Toggle a bit in memory
  * @nr: Bit to change

include/qemu/osdep.h

@@ -597,6 +597,8 @@ 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

@@ -36,6 +36,10 @@ 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;
@@ -60,6 +64,10 @@ 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;
@@ -138,6 +146,58 @@ static ssize_t qio_channel_file_writev(QIOChannel *ioc,
     return ret;
 }
 
+#ifdef CONFIG_PREADV
+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;
+}
+#endif /* CONFIG_PREADV */
+
 static int qio_channel_file_set_blocking(QIOChannel *ioc,
                                          bool enabled,
                                          Error **errp)
@@ -157,6 +217,31 @@ static int qio_channel_file_set_blocking(QIOChannel *ioc,
 #endif
 }
 
+void qio_channel_file_set_direct_io(QIOChannel *ioc, bool enabled, Error **errp)
+{
+#ifdef O_DIRECT
+    QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc);
+    int flags = fcntl(fioc->fd, F_GETFL);
+
+    if (flags == -1) {
+        error_setg_errno(errp, errno, "Unable to read file descriptor flags");
+        return;
+    }
+
+    if (enabled) {
+        flags |= O_DIRECT;
+    } else {
+        flags &= ~O_DIRECT;
+    }
+
+    if (fcntl(fioc->fd, F_SETFL, flags | O_DIRECT) == -1) {
+        error_setg_errno(errp, errno, "Unable to set file descriptor flags");
+        return;
+    }
+#else
+    error_setg(&errp, "System does not support O_DIRECT");
+#endif
+}
 
 static off_t qio_channel_file_seek(QIOChannel *ioc,
                                    off_t offset,
@@ -182,6 +267,11 @@ static int qio_channel_file_close(QIOChannel *ioc,
 {
     QIOChannelFile *fioc = QIO_CHANNEL_FILE(ioc);
 
+    if (qemu_fdatasync(fioc->fd) < 0) {
+        error_setg_errno(errp, errno,
+                         "Unable to synchronize file data with storage device");
+        return -1;
+    }
     if (qemu_close(fioc->fd) < 0) {
         error_setg_errno(errp, errno,
                          "Unable to close file");
@@ -223,6 +313,10 @@ 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;
+#ifdef CONFIG_PREADV
+    ioc_klass->io_pwritev = qio_channel_file_pwritev;
+    ioc_klass->io_preadv = qio_channel_file_preadv;
+#endif
     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

@@ -454,6 +454,134 @@ GSource *qio_channel_add_watch_source(QIOChannel *ioc,
 }
 
 
+ssize_t qio_channel_pwritev(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 = -1;
+    int i, slice_idx, slice_num;
+    uintptr_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 = (uintptr_t) iov[i].iov_base;
+
+        if (i != niov - 1) {
+            len = iov[i].iov_len;
+            next = (uintptr_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 + (uintptr_t) iov[slice_idx].iov_base;
+
+        if (is_write) {
+            ret = qio_channel_pwritev(ioc, &iov[slice_idx], slice_num,
+                                      file_offset, errp);
+        } else {
+            ret = qio_channel_preadv(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_pwritev_all(QIOChannel *ioc, const struct iovec *iov,
+                            size_t niov, off_t offset, Error **errp)
+{
+    return qio_channel_preadv_pwritev_contiguous(ioc, iov, niov,
+                                                 offset, true, errp);
+}
+
+ssize_t qio_channel_pwrite(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(ioc, &iov, 1, offset, errp);
+}
+
+ssize_t qio_channel_preadv(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_preadv_all(QIOChannel *ioc, const struct iovec *iov,
+                           size_t niov, off_t offset, Error **errp)
+{
+    return qio_channel_preadv_pwritev_contiguous(ioc, iov, niov,
+                                                 offset, false, errp);
+}
+
+ssize_t qio_channel_pread(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(ioc, &iov, 1, offset, errp);
+}
+
 int qio_channel_shutdown(QIOChannel *ioc,
                          QIOChannelShutdown how,
                          Error **errp)

migration/fd.c

@@ -19,14 +19,28 @@
 #include "fd.h"
 #include "migration.h"
 #include "monitor/monitor.h"
+#include "io/channel-file.h"
 #include "io/channel-util.h"
+#include "options.h"
 #include "trace.h"
 
 
+static struct FdOutgoingArgs {
+    int fd;
+} outgoing_args;
+
+int fd_args_get_fd(void)
+{
+    return outgoing_args.fd;
+}
+
 void fd_start_outgoing_migration(MigrationState *s, const char *fdname, Error **errp)
 {
     QIOChannel *ioc;
     int fd = monitor_get_fd(monitor_cur(), fdname, errp);
+
+    outgoing_args.fd = -1;
+
     if (fd == -1) {
         return;
     }
@@ -38,6 +52,8 @@ void fd_start_outgoing_migration(MigrationState *s, const char *fdname, Error **
         return;
     }
 
+    outgoing_args.fd = fd;
+
     qio_channel_set_name(ioc, "migration-fd-outgoing");
     migration_channel_connect(s, ioc, NULL, NULL);
     object_unref(OBJECT(ioc));
@@ -73,4 +89,18 @@ void fd_start_incoming_migration(const char *fdname, Error **errp)
                                fd_accept_incoming_migration,
                                NULL, NULL,
                                g_main_context_get_thread_default());
+
+    if (migrate_multifd()) {
+        int channels = migrate_multifd_channels();
+
+        while (channels--) {
+            ioc = QIO_CHANNEL(qio_channel_file_new_fd(fd));
+
+            qio_channel_set_name(ioc, "migration-fd-incoming");
+            qio_channel_add_watch_full(ioc, G_IO_IN,
+                                       fd_accept_incoming_migration,
+                                       NULL, NULL,
+                                       g_main_context_get_thread_default());
+        }
+    }
 }

migration/fd.h

@@ -20,4 +20,5 @@ void fd_start_incoming_migration(const char *fdname, Error **errp);
 
 void fd_start_outgoing_migration(MigrationState *s, const char *fdname,
                                  Error **errp);
+int fd_args_get_fd(void);
 #endif

migration/file.c

@@ -7,16 +7,26 @@
 
 #include "qemu/osdep.h"
 #include "qemu/cutils.h"
+#include "qemu/error-report.h"
 #include "qapi/error.h"
+#include "qapi/qapi-commands-misc.h"
 #include "channel.h"
+#include "fd.h"
 #include "file.h"
 #include "migration.h"
 #include "io/channel-file.h"
 #include "io/channel-util.h"
+#include "monitor/monitor.h"
+#include "options.h"
 #include "trace.h"
 
 #define OFFSET_OPTION ",offset="
 
+static struct FileOutgoingArgs {
+    char *fname;
+    int64_t fdset_id;
+} outgoing_args;
+
 /* Remove the offset option from @filespec and return it in @offsetp. */
 
 int file_parse_offset(char *filespec, uint64_t *offsetp, Error **errp)
@@ -36,6 +46,145 @@ int file_parse_offset(char *filespec, uint64_t *offsetp, Error **errp)
     return 0;
 }
 
+/*
+ * If the open flags and file status flags from the file descriptors
+ * in the fdset don't match what QEMU expects, errno gets set to
+ * EACCES. Let's provide a more user-friendly message.
+ */
+static void file_fdset_error(int flags, Error **errp)
+{
+    ERRP_GUARD();
+
+    if (errno == EACCES) {
+        /* ditch the previous error */
+        error_free(*errp);
+        *errp = NULL;
+
+        error_setg(errp, "Fdset is missing a file descriptor with flags: 0x%x",
+                   flags);
+    }
+}
+
+static void file_remove_fdset(void)
+{
+    if (outgoing_args.fdset_id != -1) {
+        qmp_remove_fd(outgoing_args.fdset_id, false, -1, NULL);
+        outgoing_args.fdset_id = -1;
+    }
+}
+
+/*
+ * Due to the behavior of the dup() system call, we need the fdset to
+ * have two non-duplicate fds so we can enable direct IO in the
+ * secondary channels without affecting the main channel.
+ */
+static bool file_parse_fdset(const char *filename, int64_t *fdset_id,
+                             Error **errp)
+{
+    FdsetInfoList *fds_info;
+    FdsetFdInfoList *fd_info;
+    const char *fdset_id_str;
+    int nfds = 0;
+
+    *fdset_id = -1;
+
+    if (!strstart(filename, "/dev/fdset/", &fdset_id_str)) {
+        return true;
+    }
+
+    if (!migrate_multifd()) {
+        error_setg(errp, "fdset is only supported with multifd");
+        return false;
+    }
+
+    *fdset_id = qemu_parse_fd(fdset_id_str);
+
+    for (fds_info = qmp_query_fdsets(NULL); fds_info;
+         fds_info = fds_info->next) {
+
+        if (*fdset_id != fds_info->value->fdset_id) {
+            continue;
+        }
+
+        for (fd_info = fds_info->value->fds; fd_info; fd_info = fd_info->next) {
+            if (nfds++ > 2) {
+                break;
+            }
+        }
+    }
+
+    if (nfds != 2) {
+        error_setg(errp, "Outgoing migration needs two fds in the fdset, "
+                   "got %d", nfds);
+        qmp_remove_fd(*fdset_id, false, -1, NULL);
+        *fdset_id = -1;
+        return false;
+    }
+
+    return true;
+}
+
+static void qio_channel_file_connect_worker(QIOTask *task, gpointer opaque)
+{
+    /* noop */
+}
+
+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;
+
+    file_remove_fdset();
+    return 0;
+}
+
+void file_send_channel_create(QIOTaskFunc f, void *data)
+{
+    QIOChannelFile *ioc = NULL;
+    QIOTask *task;
+    Error *err = NULL;
+    int flags = O_WRONLY;
+    int fd = fd_args_get_fd();
+
+    if (migrate_direct_io()) {
+#ifdef O_DIRECT
+        /*
+         * 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;
+#else
+        error_setg(&err, "System does not support O_DIRECT");
+        error_append_hint(&err,
+                          "Try disabling direct-io migration capability\n");
+        /* errors are propagated through the qio_task below */
+#endif
+    }
+
+    if (!err) {
+        if (fd && fd != -1) {
+            ioc = qio_channel_file_new_fd(fd);
+        } else {
+            ioc = qio_channel_file_new_path(outgoing_args.fname, flags, 0, &err);
+        }
+    }
+
+    task = qio_task_new(OBJECT(ioc), f, (gpointer)data, NULL);
+    if (!ioc) {
+        file_fdset_error(flags, &err);
+        qio_task_set_error(task, err);
+        return;
+    }
+
+    qio_task_run_in_thread(task, qio_channel_file_connect_worker,
+                           (gpointer)data, NULL, NULL);
+}
+
 void file_start_outgoing_migration(MigrationState *s,
                                    FileMigrationArgs *file_args, Error **errp)
 {
@@ -43,12 +192,20 @@ void file_start_outgoing_migration(MigrationState *s,
     g_autofree char *filename = g_strdup(file_args->filename);
     uint64_t offset = file_args->offset;
     QIOChannel *ioc;
+    int flags = O_CREAT | O_TRUNC | O_WRONLY;
+    mode_t mode = 0660;
 
     trace_migration_file_outgoing(filename);
 
-    fioc = qio_channel_file_new_path(filename, O_CREAT | O_WRONLY | O_TRUNC,
-                                     0600, errp);
+    if (!file_parse_fdset(filename, &outgoing_args.fdset_id, errp)) {
+        return;
+    }
+
+    outgoing_args.fname = g_strdup(filename);
+
+    fioc = qio_channel_file_new_path(filename, flags, mode, errp);
     if (!fioc) {
+        file_fdset_error(flags, errp);
         return;
     }
 
@@ -74,22 +231,40 @@ void file_start_incoming_migration(FileMigrationArgs *file_args, Error **errp)
     g_autofree char *filename = g_strdup(file_args->filename);
     QIOChannelFile *fioc = NULL;
     uint64_t offset = file_args->offset;
-    QIOChannel *ioc;
+    int channels = 1;
+    int i = 0, fd, flags = O_RDONLY;
 
     trace_migration_file_incoming(filename);
 
-    fioc = qio_channel_file_new_path(filename, O_RDONLY, 0, errp);
+    fioc = qio_channel_file_new_path(filename, flags, 0, errp);
     if (!fioc) {
+        file_fdset_error(flags, errp);
         return;
     }
 
-    ioc = QIO_CHANNEL(fioc);
-    if (offset && qio_channel_io_seek(ioc, offset, SEEK_SET, errp) < 0) {
+    if (offset &&
+        qio_channel_io_seek(QIO_CHANNEL(fioc), offset, SEEK_SET, errp) < 0) {
+        return;
+    }
+
+    if (migrate_multifd()) {
+        channels += migrate_multifd_channels();
+    }
+
+    fd = fioc->fd;
+
+    do {
+        QIOChannel *ioc = QIO_CHANNEL(fioc);
+
+        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)));
+
+    if (!fioc) {
+        error_setg(errp, "Error creating migration incoming channel");
         return;
     }
-    qio_channel_set_name(QIO_CHANNEL(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());
 }

migration/file.h

@@ -9,10 +9,15 @@
 #define QEMU_MIGRATION_FILE_H
 
 #include "qapi/qapi-types-migration.h"
+#include "io/task.h"
+#include "channel.h"
 
 void file_start_incoming_migration(FileMigrationArgs *file_args, Error **errp);
 
 void file_start_outgoing_migration(MigrationState *s,
                                    FileMigrationArgs *file_args, Error **errp);
 int file_parse_offset(char *filespec, uint64_t *offsetp, Error **errp);
+
+void file_send_channel_create(QIOTaskFunc f, void *data);
+int file_send_channel_destroy(QIOChannel *ioc);
 #endif

migration/migration-hmp-cmds.c

@@ -392,6 +392,13 @@ void hmp_info_migrate_parameters(Monitor *mon, const QDict *qdict)
         monitor_printf(mon, "%s: %s\n",
             MigrationParameter_str(MIGRATION_PARAMETER_MODE),
             qapi_enum_lookup(&MigMode_lookup, params->mode));
+
+        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);
@@ -679,6 +686,10 @@ void hmp_migrate_set_parameter(Monitor *mon, const QDict *qdict)
         p->has_mode = true;
         visit_type_MigMode(v, param, &p->mode, &err);
         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

@@ -128,24 +128,88 @@ static bool migration_needs_multiple_sockets(void)
     return migrate_multifd() || migrate_postcopy_preempt();
 }
 
-static bool transport_supports_multi_channels(SocketAddress *saddr)
+static bool transport_supports_multi_channels(MigrationAddress *addr)
 {
-    return saddr->type == SOCKET_ADDRESS_TYPE_INET ||
-           saddr->type == SOCKET_ADDRESS_TYPE_UNIX ||
-           saddr->type == SOCKET_ADDRESS_TYPE_VSOCK;
+    if (addr->transport == MIGRATION_ADDRESS_TYPE_SOCKET) {
+        SocketAddress *saddr = &addr->u.socket;
+
+        if (saddr->type == SOCKET_ADDRESS_TYPE_FD) {
+            return migrate_fixed_ram();
+        }
+
+        return (saddr->type == SOCKET_ADDRESS_TYPE_INET ||
+                saddr->type == SOCKET_ADDRESS_TYPE_UNIX ||
+                saddr->type == SOCKET_ADDRESS_TYPE_VSOCK);
+    } else if (addr->transport == MIGRATION_ADDRESS_TYPE_FILE) {
+        return migrate_fixed_ram();
+    } else {
+        return false;
+    }
+}
+
+static bool migration_needs_seekable_channel(void)
+{
+    return migrate_fixed_ram();
+}
+
+static bool migration_needs_multiple_fds(void)
+{
+    /*
+     * When doing direct-io, multifd requires two different,
+     * non-duplicated file descriptors so we can use one of them for
+     * unaligned IO.
+     */
+    return migrate_multifd() && migrate_direct_io();
+}
+
+static bool transport_supports_seeking(MigrationAddress *addr)
+{
+    if (addr->transport == MIGRATION_ADDRESS_TYPE_FILE) {
+        return true;
+    }
+
+    /*
+     * At this point, the user might not yet have passed the file
+     * descriptor to QEMU, so we cannot know for sure whether it
+     * refers to a plain file or a socket. Let it through anyway.
+     */
+    if (addr->transport == MIGRATION_ADDRESS_TYPE_SOCKET) {
+        return addr->u.socket.type == SOCKET_ADDRESS_TYPE_FD;
+    }
+
+    return false;
+}
+
+static bool transport_supports_multiple_fds(MigrationAddress *addr)
+{
+    /* file: works because QEMU can open it multiple times */
+    return addr->transport == MIGRATION_ADDRESS_TYPE_FILE;
 }
 
 static bool
 migration_channels_and_transport_compatible(MigrationAddress *addr,
                                             Error **errp)
 {
+    if (migration_needs_seekable_channel() &&
+        !transport_supports_seeking(addr)) {
+        error_setg(errp, "Migration requires seekable transport (e.g. file)");
+        return false;
+    }
+
     if (migration_needs_multiple_sockets() &&
-        (addr->transport == MIGRATION_ADDRESS_TYPE_SOCKET) &&
-        !transport_supports_multi_channels(&addr->u.socket)) {
+        !transport_supports_multi_channels(addr)) {
         error_setg(errp, "Migration requires multi-channel URIs (e.g. tcp)");
         return false;
     }
 
+    if (migration_needs_multiple_fds() &&
+        !transport_supports_multiple_fds(addr)) {
+        error_setg(errp,
+                   "Migration with direct-io is incompatible with the fd: URI,"
+                   " use file: instead");
+        return false;
+    }
+
     return true;
 }
 
@@ -314,6 +378,46 @@ static void migrate_generate_event(int new_state)
     }
 }
 
+void migration_direct_io_start(QEMUFile *file, off_t align)
+{
+    off_t base;
+
+    if (!migrate_direct_io() || migrate_multifd()) {
+        return;
+    }
+
+    base = qemu_get_offset(file);
+    if (base < 0 || qemu_file_get_error(file)) {
+        goto err_align;
+    }
+
+    qemu_set_offset(file, ROUND_UP(base, align), SEEK_SET);
+
+    if (qemu_file_get_error(file)) {
+        goto err_align;
+    }
+
+    if (!qemu_file_set_direct_io(file, true)) {
+        error_report("Failed to enable direct-io");
+    }
+
+    return;
+
+err_align:
+    error_report("Failed to align stream for direct-io");
+}
+
+void migration_direct_io_finish(QEMUFile *file)
+{
+    if (!migrate_direct_io() || migrate_multifd()) {
+        return;
+    }
+
+    if (!qemu_file_set_direct_io(file, false)) {
+        error_report("Failed to disable direct-io");
+    }
+}
+
 /*
  * Send a message on the return channel back to the source
  * of the migration.
@@ -822,7 +926,8 @@ void migration_ioc_process_incoming(QIOChannel *ioc, Error **errp)
     uint32_t channel_magic = 0;
     int ret = 0;
 
-    if (migrate_multifd() && !migrate_postcopy_ram() &&
+    if (migrate_multifd() && migrate_multifd_packets() &&
+        !migrate_postcopy_ram() &&
         qio_channel_has_feature(ioc, QIO_CHANNEL_FEATURE_READ_MSG_PEEK)) {
         /*
          * With multiple channels, it is possible that we receive channels

migration/migration.h

@@ -550,4 +550,7 @@ void migration_rp_kick(MigrationState *s);
 
 int migration_stop_vm(RunState state);
 
+void migration_direct_io_start(QEMUFile *file, off_t align);
+void migration_direct_io_finish(QEMUFile *file);
+
 #endif

migration/multifd-zlib.c

@@ -69,7 +69,7 @@ static int zlib_send_setup(MultiFDSendParams *p, Error **errp)
         err_msg = "out of memory for buf";
         goto err_free_zbuff;
     }
-    p->data = z;
+    p->compress_data = z;
     return 0;
 
 err_free_zbuff:
@@ -92,15 +92,15 @@ err_free_z:
  */
 static void zlib_send_cleanup(MultiFDSendParams *p, Error **errp)
 {
-    struct zlib_data *z = p->data;
+    struct zlib_data *z = p->compress_data;
 
     deflateEnd(&z->zs);
     g_free(z->zbuff);
     z->zbuff = NULL;
     g_free(z->buf);
     z->buf = NULL;
-    g_free(p->data);
-    p->data = NULL;
+    g_free(p->compress_data);
+    p->compress_data = NULL;
 }
 
 /**
@@ -116,7 +116,7 @@ static void zlib_send_cleanup(MultiFDSendParams *p, Error **errp)
  */
 static int zlib_send_prepare(MultiFDSendParams *p, Error **errp)
 {
-    struct zlib_data *z = p->data;
+    struct zlib_data *z = p->compress_data;
     z_stream *zs = &z->zs;
     uint32_t out_size = 0;
     int ret;
@@ -189,7 +189,7 @@ static int zlib_recv_setup(MultiFDRecvParams *p, Error **errp)
     struct zlib_data *z = g_new0(struct zlib_data, 1);
     z_stream *zs = &z->zs;
 
-    p->data = z;
+    p->compress_data = z;
     zs->zalloc = Z_NULL;
     zs->zfree = Z_NULL;
     zs->opaque = Z_NULL;
@@ -219,13 +219,13 @@ static int zlib_recv_setup(MultiFDRecvParams *p, Error **errp)
  */
 static void zlib_recv_cleanup(MultiFDRecvParams *p)
 {
-    struct zlib_data *z = p->data;
+    struct zlib_data *z = p->compress_data;
 
     inflateEnd(&z->zs);
     g_free(z->zbuff);
     z->zbuff = NULL;
-    g_free(p->data);
-    p->data = NULL;
+    g_free(p->compress_data);
+    p->compress_data = NULL;
 }
 
 /**
@@ -241,7 +241,7 @@ static void zlib_recv_cleanup(MultiFDRecvParams *p)
  */
 static int zlib_recv_pages(MultiFDRecvParams *p, Error **errp)
 {
-    struct zlib_data *z = p->data;
+    struct zlib_data *z = p->compress_data;
     z_stream *zs = &z->zs;
     uint32_t in_size = p->next_packet_size;
     /* we measure the change of total_out */
@@ -314,7 +314,7 @@ static MultiFDMethods multifd_zlib_ops = {
     .send_prepare = zlib_send_prepare,
     .recv_setup = zlib_recv_setup,
     .recv_cleanup = zlib_recv_cleanup,
-    .recv_pages = zlib_recv_pages
+    .recv_data = zlib_recv_pages
 };
 
 static void multifd_zlib_register(void)

migration/multifd-zstd.c

@@ -52,7 +52,7 @@ static int zstd_send_setup(MultiFDSendParams *p, Error **errp)
     struct zstd_data *z = g_new0(struct zstd_data, 1);
     int res;
 
-    p->data = z;
+    p->compress_data = z;
     z->zcs = ZSTD_createCStream();
     if (!z->zcs) {
         g_free(z);
@@ -90,14 +90,14 @@ static int zstd_send_setup(MultiFDSendParams *p, Error **errp)
  */
 static void zstd_send_cleanup(MultiFDSendParams *p, Error **errp)
 {
-    struct zstd_data *z = p->data;
+    struct zstd_data *z = p->compress_data;
 
     ZSTD_freeCStream(z->zcs);
     z->zcs = NULL;
     g_free(z->zbuff);
     z->zbuff = NULL;
-    g_free(p->data);
-    p->data = NULL;
+    g_free(p->compress_data);
+    p->compress_data = NULL;
 }
 
 /**
@@ -113,7 +113,7 @@ static void zstd_send_cleanup(MultiFDSendParams *p, Error **errp)
  */
 static int zstd_send_prepare(MultiFDSendParams *p, Error **errp)
 {
-    struct zstd_data *z = p->data;
+    struct zstd_data *z = p->compress_data;
     int ret;
     uint32_t i;
 
@@ -178,7 +178,7 @@ static int zstd_recv_setup(MultiFDRecvParams *p, Error **errp)
     struct zstd_data *z = g_new0(struct zstd_data, 1);
     int ret;
 
-    p->data = z;
+    p->compress_data = z;
     z->zds = ZSTD_createDStream();
     if (!z->zds) {
         g_free(z);
@@ -216,14 +216,14 @@ static int zstd_recv_setup(MultiFDRecvParams *p, Error **errp)
  */
 static void zstd_recv_cleanup(MultiFDRecvParams *p)
 {
-    struct zstd_data *z = p->data;
+    struct zstd_data *z = p->compress_data;
 
     ZSTD_freeDStream(z->zds);
     z->zds = NULL;
     g_free(z->zbuff);
     z->zbuff = NULL;
-    g_free(p->data);
-    p->data = NULL;
+    g_free(p->compress_data);
+    p->compress_data = NULL;
 }
 
 /**
@@ -243,7 +243,7 @@ static int zstd_recv_pages(MultiFDRecvParams *p, Error **errp)
     uint32_t out_size = 0;
     uint32_t expected_size = p->normal_num * p->page_size;
     uint32_t flags = p->flags & MULTIFD_FLAG_COMPRESSION_MASK;
-    struct zstd_data *z = p->data;
+    struct zstd_data *z = p->compress_data;
     int ret;
     int i;
 
@@ -305,7 +305,7 @@ static MultiFDMethods multifd_zstd_ops = {
     .send_prepare = zstd_send_prepare,
     .recv_setup = zstd_recv_setup,
     .recv_cleanup = zstd_recv_cleanup,
-    .recv_pages = zstd_recv_pages
+    .recv_data = zstd_recv_pages
 };
 
 static void multifd_zstd_register(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"
 
@@ -128,7 +130,7 @@ static void nocomp_recv_cleanup(MultiFDRecvParams *p)
 }
 
 /**
- * nocomp_recv_pages: read the data from the channel into actual pages
+ * nocomp_recv_data: read the data from the channel
  *
  * For no compression we just need to read things into the correct place.
  *
@@ -137,20 +139,39 @@ static void nocomp_recv_cleanup(MultiFDRecvParams *p)
  * @p: Params for the channel that we are using
  * @errp: pointer to an error
  */
-static int nocomp_recv_pages(MultiFDRecvParams *p, Error **errp)
+static int nocomp_recv_data(MultiFDRecvParams *p, Error **errp)
 {
     uint32_t flags = p->flags & MULTIFD_FLAG_COMPRESSION_MASK;
+    ERRP_GUARD();
 
     if (flags != MULTIFD_FLAG_NOCOMP) {
         error_setg(errp, "multifd %u: flags received %x flags expected %x",
                    p->id, flags, MULTIFD_FLAG_NOCOMP);
         return -1;
     }
-    for (int i = 0; i < p->normal_num; i++) {
-        p->iov[i].iov_base = p->host + p->normal[i];
-        p->iov[i].iov_len = p->page_size;
+
+    if (!migrate_multifd_packets()) {
+        MultiFDRecvData *data = p->data;
+        size_t ret;
+
+        ret = qio_channel_pread(p->c, (char *) data->opaque,
+                                data->size, data->file_offset, errp);
+        if (ret != data->size) {
+            error_prepend(errp,
+                          "multifd recv (%u): read 0x%zx, expected 0x%zx",
+                          p->id, ret, data->size);
+            return -1;
+        }
+
+        return 0;
+    } else {
+        for (int i = 0; i < p->normal_num; i++) {
+            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);
     }
-    return qio_channel_readv_all(p->c, p->iov, p->normal_num, errp);
 }
 
 static MultiFDMethods multifd_nocomp_ops = {
@@ -159,7 +180,7 @@ static MultiFDMethods multifd_nocomp_ops = {
     .send_prepare = nocomp_send_prepare,
     .recv_setup = nocomp_recv_setup,
     .recv_cleanup = nocomp_recv_cleanup,
-    .recv_pages = nocomp_recv_pages
+    .recv_data = nocomp_recv_data
 };
 
 static MultiFDMethods *multifd_ops[MULTIFD_COMPRESSION__MAX] = {
@@ -257,6 +278,17 @@ static void multifd_pages_clear(MultiFDPages_t *pages)
     g_free(pages);
 }
 
+static void multifd_set_file_bitmap(MultiFDSendParams *p)
+{
+    MultiFDPages_t *pages = p->pages;
+
+    assert(pages->block);
+
+    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;
@@ -511,7 +543,11 @@ static void multifd_send_terminate_threads(Error *err)
 
 static int multifd_send_channel_destroy(QIOChannel *send)
 {
-    return socket_send_channel_destroy(send);
+    if (migrate_to_file()) {
+        return file_send_channel_destroy(send);
+    } else {
+        return socket_send_channel_destroy(send);
+    }
 }
 
 void multifd_save_cleanup(void)
@@ -599,6 +635,34 @@ int multifd_send_sync_main(QEMUFile *f)
         }
     }
 
+    if (!migrate_multifd_packets()) {
+        /*
+         * There's no sync packet to send. Just make sure the sending
+         * above has finished.
+         */
+        for (i = 0; i < migrate_multifd_channels(); i++) {
+            qemu_sem_wait(&multifd_send_state->channels_ready);
+        }
+
+        /* sanity check and release the channels */
+        for (i = 0; i < migrate_multifd_channels(); i++) {
+            MultiFDSendParams *p = &multifd_send_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;
+            }
+            assert(!p->pending_job);
+            qemu_mutex_unlock(&p->mutex);
+
+            qemu_sem_post(&p->sem);
+        }
+
+        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
@@ -654,18 +718,22 @@ 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 = 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);
@@ -677,11 +745,12 @@ 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;
+            uintptr_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;
@@ -699,33 +768,53 @@ static void *multifd_send_thread(void *opaque)
                     break;
                 }
             }
-            multifd_send_fill_packet(p);
+
+            if (use_packets) {
+                multifd_send_fill_packet(p);
+                p->num_packets++;
+            } else {
+                multifd_set_file_bitmap(p);
+
+                /*
+                 * If we subtract the host page now, we don't need to
+                 * pass it into qio_channel_pwritev_all() below.
+                 */
+                write_base = p->pages->block->pages_offset -
+                    (uintptr_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) {
-                /* Send header first, without zerocopy */
-                ret = qio_channel_write_all(p->c, (void *)p->packet,
-                                            p->packet_len, &local_err);
-                if (ret != 0) {
-                    break;
+            if (use_packets) {
+                if (use_zero_copy_send) {
+                    /* Send header first, without zerocopy */
+                    ret = qio_channel_write_all(p->c, (void *)p->packet,
+                                                p->packet_len, &local_err);
+                    if (ret != 0) {
+                        break;
+                    }
+                } else {
+                    /* 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);
             } else {
-                /* 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_pwritev_all(p->c, p->iov, p->iovs_num,
+                                              write_base, &local_err);
             }
 
-            ret = qio_channel_writev_full_all(p->c, p->iov, p->iovs_num, NULL,
-                                              0, p->write_flags, &local_err);
             if (ret != 0) {
                 break;
             }
@@ -858,8 +947,7 @@ static bool multifd_channel_connect(MultiFDSendParams *p,
     return true;
 }
 
-static void multifd_new_send_channel_cleanup(MultiFDSendParams *p,
-                                             QIOChannel *ioc, Error *err)
+static void multifd_new_send_channel_cleanup(MultiFDSendParams *p, Error *err)
 {
      migrate_set_error(migrate_get_current(), err);
      /* Error happen, we need to tell who pay attention to me */
@@ -871,20 +959,20 @@ static void multifd_new_send_channel_cleanup(MultiFDSendParams *p,
       * its status.
       */
      p->quit = true;
-     object_unref(OBJECT(ioc));
      error_free(err);
 }
 
 static void multifd_new_send_channel_async(QIOTask *task, gpointer opaque)
 {
     MultiFDSendParams *p = opaque;
-    QIOChannel *ioc = QIO_CHANNEL(qio_task_get_source(task));
+    Object *obj = 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 = ioc;
-        qio_channel_set_delay(p->c, false);
+        QIOChannel *ioc = QIO_CHANNEL(obj);
+
+        qio_channel_set_delay(ioc, false);
         p->running = true;
         if (multifd_channel_connect(p, ioc, &local_err)) {
             return;
@@ -892,18 +980,24 @@ static void multifd_new_send_channel_async(QIOTask *task, gpointer opaque)
     }
 
     trace_multifd_new_send_channel_async_error(p->id, local_err);
-    multifd_new_send_channel_cleanup(p, ioc, local_err);
+    multifd_new_send_channel_cleanup(p, local_err);
+    object_unref(obj);
 }
 
 static void multifd_new_send_channel_create(gpointer opaque)
 {
-    socket_send_channel_create(multifd_new_send_channel_async, 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()) {
@@ -928,14 +1022,20 @@ 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;
@@ -965,6 +1065,7 @@ int multifd_save_setup(Error **errp)
 
 struct {
     MultiFDRecvParams *params;
+    MultiFDRecvData *data;
     /* number of created threads */
     int count;
     /* syncs main thread and channels */
@@ -975,6 +1076,49 @@ struct {
     MultiFDMethods *ops;
 } *multifd_recv_state;
 
+int multifd_recv(void)
+{
+    int i;
+    static int next_recv_channel;
+    MultiFDRecvParams *p = NULL;
+    MultiFDRecvData *data = multifd_recv_state->data;
+
+    /*
+     * 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);
+    }
+    assert(p->data->size == 0);
+    multifd_recv_state->data = p->data;
+    p->data = data;
+    qemu_mutex_unlock(&p->mutex);
+    qemu_sem_post(&p->sem);
+
+    return 1;
+}
+
+MultiFDRecvData *multifd_get_recv_data(void)
+{
+    return multifd_recv_state->data;
+}
+
 static void multifd_recv_terminate_threads(Error *err)
 {
     int i;
@@ -996,6 +1140,7 @@ 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
@@ -1045,6 +1190,7 @@ void multifd_load_cleanup(void)
         p->c = NULL;
         qemu_mutex_destroy(&p->mutex);
         qemu_sem_destroy(&p->sem_sync);
+        qemu_sem_destroy(&p->sem);
         g_free(p->name);
         p->name = NULL;
         p->packet_len = 0;
@@ -1059,6 +1205,8 @@ void multifd_load_cleanup(void)
     qemu_sem_destroy(&multifd_recv_state->sem_sync);
     g_free(multifd_recv_state->params);
     multifd_recv_state->params = NULL;
+    g_free(multifd_recv_state->data);
+    multifd_recv_state->data = NULL;
     g_free(multifd_recv_state);
     multifd_recv_state = NULL;
 }
@@ -1067,9 +1215,24 @@ void multifd_recv_sync_main(void)
 {
     int i;
 
-    if (!migrate_multifd()) {
+    if (!migrate_multifd() || !migrate_multifd_packets()) {
         return;
     }
+
+    if (!migrate_multifd_packets()) {
+        for (i = 0; i < migrate_multifd_channels(); i++) {
+            MultiFDRecvParams *p = &multifd_recv_state->params[i];
+
+            qemu_sem_post(&p->sem);
+            qemu_sem_wait(&p->sem_sync);
+
+            qemu_mutex_lock(&p->mutex);
+            assert(!p->pending_job || p->quit);
+            qemu_mutex_unlock(&p->mutex);
+        }
+        return;
+    }
+
     for (i = 0; i < migrate_multifd_channels(); i++) {
         MultiFDRecvParams *p = &multifd_recv_state->params[i];
 
@@ -1094,51 +1257,82 @@ 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);
     rcu_register_thread();
 
     while (true) {
-        uint32_t flags;
+        uint32_t flags = 0;
+        bool has_data = false;
+        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;
+            }
+            p->num_packets++;
+
+            flags = p->flags;
+            /* recv methods don't know how to handle the SYNC flag */
+            p->flags &= ~MULTIFD_FLAG_SYNC;
+            trace_multifd_recv(p->id, p->packet_num, p->normal_num, flags,
+                               p->next_packet_size);
+
+            p->total_normal_pages += p->normal_num;
+            has_data = !!p->normal_num;
+        } else {
+            /*
+             * No packets, so we need to wait for the vmstate code to
+             * give us work.
+             */
+            qemu_sem_wait(&p->sem);
+            qemu_mutex_lock(&p->mutex);
+            if (!p->pending_job) {
+                qemu_mutex_unlock(&p->mutex);
+                break;
+            }
+            has_data = !!p->data->size;
         }
 
-        qemu_mutex_lock(&p->mutex);
-        ret = multifd_recv_unfill_packet(p, &local_err);
-        if (ret) {
-            qemu_mutex_unlock(&p->mutex);
-            break;
-        }
-
-        flags = p->flags;
-        /* recv methods don't know how to handle the SYNC flag */
-        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);
 
-        if (p->normal_num) {
-            ret = multifd_recv_state->ops->recv_pages(p, &local_err);
+        if (has_data) {
+            ret = multifd_recv_state->ops->recv_data(p, &local_err);
             if (ret != 0) {
                 break;
             }
         }
 
-        if (flags & MULTIFD_FLAG_SYNC) {
+        if (use_packets && (flags & MULTIFD_FLAG_SYNC)) {
             qemu_sem_post(&multifd_recv_state->sem_sync);
             qemu_sem_wait(&p->sem_sync);
         }
+
+        if (!use_packets) {
+            qemu_mutex_lock(&p->mutex);
+            p->data->size = 0;
+            p->pending_job--;
+            qemu_mutex_unlock(&p->mutex);
+        }
+    }
+
+    if (!use_packets) {
+        qemu_sem_post(&p->sem_sync);
     }
 
     if (local_err) {
@@ -1159,6 +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;
 
     /*
@@ -1172,6 +1367,10 @@ 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->data = g_new0(MultiFDRecvData, 1);
+    multifd_recv_state->data->size = 0;
+
     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()];
@@ -1181,11 +1380,19 @@ int multifd_load_setup(Error **errp)
 
         qemu_mutex_init(&p->mutex);
         qemu_sem_init(&p->sem_sync, 0);
+        qemu_sem_init(&p->sem, 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->data = g_new0(MultiFDRecvData, 1);
+        p->data->size = 0;
+
+        if (use_packets) {
+            p->packet_len = sizeof(MultiFDPacket_t)
+                + sizeof(uint64_t) * page_count;
+            p->packet = g_malloc0(p->packet_len);
+        }
         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);
@@ -1231,18 +1438,26 @@ 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) {
@@ -1253,9 +1468,8 @@ 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

@@ -13,16 +13,21 @@
 #ifndef QEMU_MIGRATION_MULTIFD_H
 #define QEMU_MIGRATION_MULTIFD_H
 
+typedef struct MultiFDRecvData MultiFDRecvData;
+
 int multifd_save_setup(Error **errp);
 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(void);
+MultiFDRecvData *multifd_get_recv_data(void);
 
 /* Multifd Compression flags */
 #define MULTIFD_FLAG_SYNC (1 << 0)
@@ -65,6 +70,13 @@ typedef struct {
     RAMBlock *block;
 } MultiFDPages_t;
 
+struct MultiFDRecvData {
+    void *opaque;
+    size_t size;
+    /* for preadv */
+    off_t file_offset;
+};
+
 typedef struct {
     /* Fields are only written at creating/deletion time */
     /* No lock required for them, they are read only */
@@ -131,7 +143,7 @@ typedef struct {
     /* num of non zero pages */
     uint32_t normal_num;
     /* used for compression methods */
-    void *data;
+    void *compress_data;
 }  MultiFDSendParams;
 
 typedef struct {
@@ -155,6 +167,8 @@ typedef struct {
 
     /* syncs main thread and channels */
     QemuSemaphore sem_sync;
+    /* sem where to wait for more work */
+    QemuSemaphore sem;
 
     /* this mutex protects the following parameters */
     QemuMutex mutex;
@@ -166,6 +180,13 @@ typedef struct {
     uint32_t flags;
     /* global number of generated multifd packets */
     uint64_t packet_num;
+    int pending_job;
+    /*
+     * The owner of 'data' depends of 'pending_job' value:
+     * pending_job == 0 -> migration_thread can use it.
+     * pending_job != 0 -> multifd_channel can use it.
+     */
+    MultiFDRecvData *data;
 
     /* thread local variables. No locking required */
 
@@ -188,7 +209,7 @@ typedef struct {
     /* num of non zero pages */
     uint32_t normal_num;
     /* used for de-compression methods */
-    void *data;
+    void *compress_data;
 } MultiFDRecvParams;
 
 typedef struct {
@@ -202,11 +223,10 @@ typedef struct {
     int (*recv_setup)(MultiFDRecvParams *p, Error **errp);
     /* Cleanup for receiving side */
     void (*recv_cleanup)(MultiFDRecvParams *p);
-    /* Read all pages */
-    int (*recv_pages)(MultiFDRecvParams *p, Error **errp);
+    /* Read all data */
+    int (*recv_data)(MultiFDRecvParams *p, Error **errp);
 } MultiFDMethods;
 
 void multifd_register_ops(int method, MultiFDMethods *ops);
 
 #endif
-

migration/options.c

@@ -204,6 +204,7 @@ Property migration_properties[] = {
     DEFINE_PROP_MIG_CAP("x-switchover-ack",
                         MIGRATION_CAPABILITY_SWITCHOVER_ACK),
     DEFINE_PROP_MIG_CAP("x-dirty-limit", MIGRATION_CAPABILITY_DIRTY_LIMIT),
+    DEFINE_PROP_MIG_CAP("x-fixed-ram", MIGRATION_CAPABILITY_FIXED_RAM),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -263,6 +264,13 @@ 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();
@@ -377,6 +385,11 @@ 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();
@@ -396,6 +409,13 @@ 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,
@@ -645,6 +665,26 @@ 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;
 }
 
@@ -795,6 +835,22 @@ 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();
@@ -1012,6 +1068,11 @@ MigrationParameters *qmp_query_migrate_parameters(Error **errp)
     params->has_mode = true;
     params->mode = s->parameters.mode;
 
+    if (s->parameters.has_direct_io) {
+        params->has_direct_io = true;
+        params->direct_io = s->parameters.direct_io;
+    }
+
     return params;
 }
 
@@ -1047,6 +1108,7 @@ void migrate_params_init(MigrationParameters *params)
     params->has_x_vcpu_dirty_limit_period = true;
     params->has_vcpu_dirty_limit = true;
     params->has_mode = true;
+    params->has_direct_io = qemu_has_direct_io();
 }
 
 /*
@@ -1348,6 +1410,10 @@ static void migrate_params_test_apply(MigrateSetParameters *params,
     if (params->has_mode) {
         dest->mode = params->mode;
     }
+
+    if (params->has_direct_io) {
+        dest->direct_io = params->direct_io;
+    }
 }
 
 static void migrate_params_apply(MigrateSetParameters *params, Error **errp)
@@ -1492,6 +1558,10 @@ static void migrate_params_apply(MigrateSetParameters *params, Error **errp)
     if (params->has_mode) {
         s->parameters.mode = params->mode;
     }
+
+    if (params->has_direct_io) {
+        s->parameters.direct_io = params->direct_io;
+    }
 }
 
 void qmp_migrate_set_parameters(MigrateSetParameters *params, Error **errp)

migration/options.h

@@ -31,6 +31,7 @@ bool migrate_compress(void);
 bool migrate_dirty_bitmaps(void);
 bool migrate_dirty_limit(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);
@@ -55,9 +56,11 @@ 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_rdma(void);
 bool migrate_tls(void);
+bool migrate_to_file(void);
 
 /* capabilities helpers */
 
@@ -78,6 +81,7 @@ 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

@@ -33,6 +33,7 @@
 #include "options.h"
 #include "qapi/error.h"
 #include "rdma.h"
+#include "io/channel-file.h"
 
 #define IO_BUF_SIZE 32768
 #define MAX_IOV_SIZE MIN_CONST(IOV_MAX, 64)
@@ -255,6 +256,10 @@ 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
@@ -447,6 +452,83 @@ 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_pwrite(f->ioc, (char *)buf, buflen, pos, &err);
+
+    if (err) {
+        qemu_file_set_error_obj(f, -EIO, err);
+    } else {
+        stat64_add(&mig_stats.qemu_file_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_pread(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) {
@@ -834,3 +916,15 @@ int qemu_file_get_to_fd(QEMUFile *f, int fd, size_t size)
 
     return 0;
 }
+
+bool qemu_file_set_direct_io(QEMUFile *f, bool enabled)
+{
+    Error *local_err = NULL;
+
+    qio_channel_file_set_direct_io(f->ioc, enabled, &local_err);
+    if (local_err) {
+        qemu_file_set_error_obj(f, -EINVAL, local_err);
+        return false;
+    }
+    return true;
+}

migration/qemu-file.h

@@ -75,7 +75,13 @@ QEMUFile *qemu_file_get_return_path(QEMUFile *f);
 int 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);
 
 QIOChannel *qemu_file_get_ioc(QEMUFile *file);
-
+bool qemu_file_set_direct_io(QEMUFile *f, bool enabled);
 #endif

migration/ram.c

@@ -94,6 +94,25 @@
 #define RAM_SAVE_FLAG_MULTIFD_FLUSH    0x200
 /* We can't use any flag that is bigger than 0x200 */
 
+/*
+ * fixed-ram migration supports O_DIRECT, so we need to make sure the
+ * userspace buffer, the IO operation size and the file offset are
+ * aligned according to the underlying device's block size. The first
+ * two are already aligned to page size, but we need to add padding to
+ * the file to align the offset.  We cannot read the block size
+ * dynamically because the migration file can be moved between
+ * different systems, so use 1M to cover most block sizes and to keep
+ * the file offset aligned at page size as well.
+ */
+#define FIXED_RAM_FILE_OFFSET_ALIGNMENT 0x100000
+
+/*
+ * When doing fixed-ram migration, this is the amount we read from the
+ * pages region in the migration file at a time.
+ */
+#define FIXED_RAM_LOAD_BUF_SIZE 0x100000
+#define FIXED_RAM_MULTIFD_LOAD_BUF_SIZE 0x100000
+
 XBZRLECacheStats xbzrle_counters;
 
 /* used by the search for pages to send */
@@ -1127,12 +1146,18 @@ static int save_zero_page(RAMState *rs, PageSearchStatus *pss,
         return 0;
     }
 
+    stat64_add(&mig_stats.zero_pages, 1);
+
+    if (migrate_fixed_ram()) {
+        /* zero pages are not transferred with fixed-ram */
+        clear_bit_atomic(offset >> TARGET_PAGE_BITS, pss->block->shadow_bmap);
+        return 1;
+    }
+
     len += save_page_header(pss, file, pss->block, offset | RAM_SAVE_FLAG_ZERO);
     qemu_put_byte(file, 0);
     len += 1;
     ram_release_page(pss->block->idstr, offset);
-
-    stat64_add(&mig_stats.zero_pages, 1);
     ram_transferred_add(len);
 
     /*
@@ -1190,14 +1215,20 @@ 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);
@@ -1333,7 +1364,7 @@ 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() &&
+            if (migrate_multifd() && !migrate_fixed_ram() &&
                 !migrate_multifd_flush_after_each_section()) {
                 QEMUFile *f = rs->pss[RAM_CHANNEL_PRECOPY].pss_channel;
                 int ret = multifd_send_sync_main(f);
@@ -2215,6 +2246,9 @@ static int ram_save_host_page(RAMState *rs, PageSearchStatus *pss)
     /* Update host page boundary information */
     pss_host_page_prepare(pss);
 
+    migration_direct_io_start(pss->pss_channel,
+                              FIXED_RAM_FILE_OFFSET_ALIGNMENT);
+
     do {
         page_dirty = migration_bitmap_clear_dirty(rs, pss->block, pss->page);
 
@@ -2248,6 +2282,7 @@ static int ram_save_host_page(RAMState *rs, PageSearchStatus *pss)
 
         if (tmppages < 0) {
             pss_host_page_finish(pss);
+            migration_direct_io_finish(pss->pss_channel);
             return tmppages;
         }
 
@@ -2255,6 +2290,7 @@ static int ram_save_host_page(RAMState *rs, PageSearchStatus *pss)
     } while (pss_within_range(pss));
 
     pss_host_page_finish(pss);
+    migration_direct_io_finish(pss->pss_channel);
 
     res = ram_save_release_protection(rs, pss, start_page);
     return (res < 0 ? res : pages);
@@ -2780,6 +2816,7 @@ static void ram_list_init_bitmaps(void)
              */
             block->bmap = bitmap_new(pages);
             bitmap_set(block->bmap, 0, pages);
+            block->shadow_bmap = bitmap_new(pages);
             block->clear_bmap_shift = shift;
             block->clear_bmap = bitmap_new(clear_bmap_size(pages, shift));
         }
@@ -2917,6 +2954,87 @@ void qemu_guest_free_page_hint(void *addr, size_t len)
     }
 }
 
+#define FIXED_RAM_HDR_VERSION 1
+struct FixedRamHeader {
+    uint32_t version;
+    /*
+     * The target's page size, so we know how many pages are in the
+     * bitmap.
+     */
+    uint64_t page_size;
+    /*
+     * The offset in the migration file where the pages bitmap is
+     * found.
+     */
+    uint64_t bitmap_offset;
+    /*
+     * The offset in the migration file where the actual pages (data)
+     * are found.
+     */
+    uint64_t pages_offset;
+    /* end of v1 */
+} QEMU_PACKED;
+typedef struct FixedRamHeader FixedRamHeader;
+
+static void fixed_ram_insert_header(QEMUFile *file, RAMBlock *block)
+{
+    g_autofree FixedRamHeader *header;
+    size_t header_size, bitmap_size;
+    long num_pages;
+
+    header = g_new0(FixedRamHeader, 1);
+    header_size = sizeof(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,
+                                   FIXED_RAM_FILE_OFFSET_ALIGNMENT);
+
+    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 bool fixed_ram_read_header(QEMUFile *file, FixedRamHeader *header,
+                                  Error **errp)
+{
+    size_t ret, header_size = sizeof(FixedRamHeader);
+
+    ret = qemu_get_buffer(file, (uint8_t *)header, header_size);
+    if (ret != header_size) {
+        error_setg(errp, "Could not read whole fixed-ram migration header "
+                   "(expected %zd, got %zd bytes)", header_size, ret);
+        return false;
+    }
+
+    /* migration stream is big-endian */
+    header->version = be32_to_cpu(header->version);
+
+    if (header->version > FIXED_RAM_HDR_VERSION) {
+        error_setg(errp, "Migration fixed-ram capability version mismatch "
+                   "(expected %d, got %d)", FIXED_RAM_HDR_VERSION,
+                   header->version);
+        return false;
+    }
+
+    header->page_size = be64_to_cpu(header->page_size);
+    header->bitmap_offset = be64_to_cpu(header->bitmap_offset);
+    header->pages_offset = be64_to_cpu(header->pages_offset);
+
+    return true;
+}
+
 /*
  * Each of ram_save_setup, ram_save_iterate and ram_save_complete has
  * long-running RCU critical section.  When rcu-reclaims in the code
@@ -2966,6 +3084,13 @@ 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);
+            }
         }
     }
 
@@ -2991,7 +3116,8 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
         return ret;
     }
 
-    if (migrate_multifd() && !migrate_multifd_flush_after_each_section()) {
+    if (migrate_multifd() && !migrate_multifd_flush_after_each_section()
+        && !migrate_fixed_ram()) {
         qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH);
     }
 
@@ -2999,6 +3125,32 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
     return qemu_fflush(f);
 }
 
+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);
+        ram_transferred_add(bitmap_size);
+
+        /*
+         * Free the bitmap here to catch any synchronization issues
+         * with multifd channels. No channels should be sending pages
+         * after we've written the bitmap to file.
+         */
+        g_free(block->shadow_bmap);
+        block->shadow_bmap = NULL;
+    }
+}
+
+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
  *
@@ -3108,8 +3260,11 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
 out:
     if (ret >= 0
         && migration_is_setup_or_active(migrate_get_current()->state)) {
-        if (migrate_multifd() && migrate_multifd_flush_after_each_section()) {
-            ret = multifd_send_sync_main(rs->pss[RAM_CHANNEL_PRECOPY].pss_channel);
+        if (migrate_multifd() &&
+            (migrate_multifd_flush_after_each_section() ||
+             migrate_fixed_ram())) {
+            ret = multifd_send_sync_main(
+                rs->pss[RAM_CHANNEL_PRECOPY].pss_channel);
             if (ret < 0) {
                 return ret;
             }
@@ -3188,6 +3343,10 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
         return ret;
     }
 
+    if (migrate_fixed_ram()) {
+        ram_save_shadow_bmap(f);
+    }
+
     if (migrate_multifd() && !migrate_multifd_flush_after_each_section()) {
         qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH);
     }
@@ -3789,6 +3948,107 @@ void colo_flush_ram_cache(void)
     trace_colo_flush_ram_cache_end();
 }
 
+static size_t ram_load_multifd_pages(RAMBlock *block, ram_addr_t start_offset,
+                                     size_t size)
+{
+    MultiFDRecvData *data = multifd_get_recv_data();
+
+    /*
+     * Pointing the opaque directly to the host buffer, no
+     * preprocessing needed.
+     */
+    data->opaque = block->host + start_offset;
+
+    data->file_offset = block->pages_offset + start_offset;
+    data->size = size;
+
+    if (multifd_recv() < 0) {
+        return -1;
+    }
+
+    return size;
+}
+
+static void read_ramblock_fixed_ram(QEMUFile *f, RAMBlock *block,
+                                    long num_pages, unsigned long *bitmap)
+{
+    unsigned long set_bit_idx, clear_bit_idx;
+    ram_addr_t offset;
+    void *host;
+    size_t read, unread, size;
+    size_t buf_size = (migrate_multifd() ? FIXED_RAM_MULTIFD_LOAD_BUF_SIZE :
+                       FIXED_RAM_LOAD_BUF_SIZE);
+
+    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);
+
+        unread = TARGET_PAGE_SIZE * (clear_bit_idx - set_bit_idx);
+        offset = set_bit_idx << TARGET_PAGE_BITS;
+
+        while (unread > 0) {
+            host = host_from_ram_block_offset(block, offset);
+            size = MIN(unread, buf_size);
+
+            if (migrate_multifd()) {
+                read = ram_load_multifd_pages(block, offset, size);
+            } else {
+                read = qemu_get_buffer_at(f, host, size,
+                                          block->pages_offset + offset);
+            }
+            offset += read;
+            unread -= read;
+        }
+    }
+}
+
+static int parse_ramblock_fixed_ram(QEMUFile *f, RAMBlock *block,
+                                    ram_addr_t length, Error **errp)
+{
+    g_autofree unsigned long *bitmap = NULL;
+    FixedRamHeader header;
+    size_t bitmap_size;
+    long num_pages;
+
+    if (!fixed_ram_read_header(f, &header, errp)) {
+        return -EINVAL;
+    }
+
+    block->pages_offset = header.pages_offset;
+
+    /*
+     * Check the alignment of the file region that contains pages. We
+     * don't enforce FIXED_RAM_FILE_OFFSET_ALIGNMENT to allow that
+     * value to change in the future. Do only a sanity check with page
+     * size alignment.
+     */
+    if (!QEMU_IS_ALIGNED(block->pages_offset, TARGET_PAGE_SIZE)) {
+        error_setg(errp,
+                   "Error reading ramblock %s pages, region has bad alignment",
+                   block->idstr);
+        return -EINVAL;
+    }
+
+    num_pages = length / header.page_size;
+    bitmap_size = BITS_TO_LONGS(num_pages) * sizeof(unsigned long);
+
+    bitmap = g_malloc0(bitmap_size);
+    if (qemu_get_buffer_at(f, (uint8_t *)bitmap, bitmap_size,
+                           header.bitmap_offset) != bitmap_size) {
+        error_setg(errp, "Error reading dirty bitmap");
+        return -EINVAL;
+    }
+
+    read_ramblock_fixed_ram(f, block, num_pages, bitmap);
+
+    /* Skip pages array */
+    qemu_set_offset(f, block->pages_offset + length, SEEK_SET);
+
+    return 0;
+}
+
 static int parse_ramblock(QEMUFile *f, RAMBlock *block, ram_addr_t length)
 {
     int ret = 0;
@@ -3797,6 +4057,16 @@ static int parse_ramblock(QEMUFile *f, RAMBlock *block, ram_addr_t length)
 
     assert(block);
 
+    if (migrate_fixed_ram()) {
+        Error *local_err = NULL;
+
+        ret = parse_ramblock_fixed_ram(f, block, length, &local_err);
+        if (local_err) {
+            error_report_err(local_err);
+        }
+        return ret;
+    }
+
     if (!qemu_ram_is_migratable(block)) {
         error_report("block %s should not be migrated !", block->idstr);
         return -EINVAL;

migration/ram.h

@@ -75,6 +75,7 @@ bool ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *rb, Error **errp);
 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

@@ -245,6 +245,7 @@ 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;

monitor/fds.c

@@ -173,9 +173,9 @@ static void monitor_fdset_cleanup(MonFdset *mon_fdset)
     MonFdsetFd *mon_fdset_fd_next;
 
     QLIST_FOREACH_SAFE(mon_fdset_fd, &mon_fdset->fds, next, mon_fdset_fd_next) {
-        if ((mon_fdset_fd->removed ||
-                (QLIST_EMPTY(&mon_fdset->dup_fds) && mon_refcount == 0)) &&
-                runstate_is_running()) {
+        if (mon_fdset_fd->removed ||
+            (QLIST_EMPTY(&mon_fdset->dup_fds) && mon_refcount == 0 &&
+             runstate_is_running())) {
             close(mon_fdset_fd->fd);
             g_free(mon_fdset_fd->opaque);
             QLIST_REMOVE(mon_fdset_fd, next);
@@ -406,6 +406,25 @@ AddfdInfo *monitor_fdset_add_fd(int fd, bool has_fdset_id, int64_t fdset_id,
     return fdinfo;
 }
 
+#ifndef _WIN32
+static bool monitor_fdset_flags_match(int flags, int fd_flags)
+{
+    bool match = false;
+
+    if ((flags & O_ACCMODE) == (fd_flags & O_ACCMODE)) {
+        match = true;
+
+#ifdef O_DIRECT
+        if ((flags & O_DIRECT) != (fd_flags & O_DIRECT)) {
+            match = false;
+        }
+#endif
+    }
+
+    return match;
+}
+#endif
+
 int monitor_fdset_dup_fd_add(int64_t fdset_id, int flags)
 {
 #ifdef _WIN32
@@ -431,7 +450,7 @@ int monitor_fdset_dup_fd_add(int64_t fdset_id, int flags)
                 return -1;
             }
 
-            if ((flags & O_ACCMODE) == (mon_fd_flags & O_ACCMODE)) {
+            if (monitor_fdset_flags_match(flags, mon_fd_flags)) {
                 fd = mon_fdset_fd->fd;
                 break;
             }

qapi/migration.json

@@ -531,6 +531,10 @@
 #     and can result in more stable read performance.  Requires KVM
 #     with accelerator property "dirty-ring-size" set.  (Since 8.1)
 #
+# @fixed-ram: Migrate using fixed offsets for each RAM page.  Requires
+#     a migration URI that supports seeking, such as a file.  (since
+#     8.2)
+#
 # Features:
 #
 # @deprecated: Member @block is deprecated.  Use blockdev-mirror with
@@ -555,7 +559,7 @@
            { 'name': 'x-ignore-shared', 'features': [ 'unstable' ] },
            'validate-uuid', 'background-snapshot',
            'zero-copy-send', 'postcopy-preempt', 'switchover-ack',
-           'dirty-limit'] }
+           'dirty-limit', 'fixed-ram'] }
 
 ##
 # @MigrationCapabilityStatus:
@@ -874,6 +878,9 @@
 # @mode: Migration mode. See description in @MigMode. Default is 'normal'.
 #        (Since 8.2)
 #
+# @direct-io: Open migration files with O_DIRECT when possible. This
+#     requires that the 'fixed-ram' capability is enabled. (since 9.0)
+#
 # Features:
 #
 # @deprecated: Member @block-incremental is deprecated.  Use
@@ -907,7 +914,8 @@
            'block-bitmap-mapping',
            { 'name': 'x-vcpu-dirty-limit-period', 'features': ['unstable'] },
            'vcpu-dirty-limit',
-           'mode'] }
+           'mode',
+           'direct-io'] }
 
 ##
 # @MigrateSetParameters:
@@ -1062,6 +1070,9 @@
 # @mode: Migration mode. See description in @MigMode. Default is 'normal'.
 #        (Since 8.2)
 #
+# @direct-io: Open migration files with O_DIRECT when possible. This
+#     requires that the 'fixed-ram' capability is enabled. (since 9.0)
+#
 # Features:
 #
 # @deprecated: Member @block-incremental is deprecated.  Use
@@ -1115,7 +1126,8 @@
             '*x-vcpu-dirty-limit-period': { 'type': 'uint64',
                                             'features': [ 'unstable' ] },
             '*vcpu-dirty-limit': 'uint64',
-            '*mode': 'MigMode'} }
+            '*mode': 'MigMode',
+            '*direct-io': 'bool' } }
 
 ##
 # @migrate-set-parameters:
@@ -1290,6 +1302,9 @@
 # @mode: Migration mode. See description in @MigMode. Default is 'normal'.
 #        (Since 8.2)
 #
+# @direct-io: Open migration files with O_DIRECT when possible. This
+#     requires that the 'fixed-ram' capability is enabled. (since 9.0)
+#
 # Features:
 #
 # @deprecated: Member @block-incremental is deprecated.  Use
@@ -1340,7 +1355,8 @@
             '*x-vcpu-dirty-limit-period': { 'type': 'uint64',
                                             'features': [ 'unstable' ] },
             '*vcpu-dirty-limit': 'uint64',
-            '*mode': 'MigMode'} }
+            '*mode': 'MigMode',
+            '*direct-io': 'bool' } }
 
 ##
 # @query-migrate-parameters:

tests/qtest/migration-helpers.c

@@ -118,6 +118,12 @@ void migrate_incoming_qmp(QTestState *to, const char *uri, const char *fmt, ...)
 
     rsp = qtest_qmp(to, "{ 'execute': 'migrate-incoming', 'arguments': %p}",
                     args);
+
+    if (!qdict_haskey(rsp, "return")) {
+        g_autoptr(GString) s = qobject_to_json_pretty(QOBJECT(rsp), true);
+        g_test_message("%s", s->str);
+    }
+
     g_assert(qdict_haskey(rsp, "return"));
     qobject_unref(rsp);
 
@@ -292,3 +298,45 @@ char *resolve_machine_version(const char *alias, const char *var1,
 
     return find_common_machine_version(machine_name, var1, var2);
 }
+
+#ifdef O_DIRECT
+/*
+ * Probe for O_DIRECT support on the filesystem. Since this is used
+ * for tests, be conservative, if anything fails, assume it's
+ * unsupported.
+ */
+bool probe_o_direct_support(const char *tmpfs)
+{
+    g_autofree char *filename = g_strdup_printf("%s/probe-o-direct", tmpfs);
+    int fd, flags = O_CREAT | O_RDWR | O_TRUNC | O_DIRECT;
+    void *buf;
+    ssize_t ret, len;
+    uint64_t offset;
+
+    fd = open(filename, flags, 0660);
+    if (fd < 0) {
+        unlink(filename);
+        return false;
+    }
+
+    /*
+     * Assuming 4k should be enough to satisfy O_DIRECT alignment
+     * requirements. The migration code uses 1M to be conservative.
+     */
+    len = 0x100000;
+    offset = 0x100000;
+
+    buf = aligned_alloc(len, len);
+    g_assert(buf);
+
+    ret = pwrite(fd, buf, len, offset);
+    unlink(filename);
+    g_free(buf);
+
+    if (ret < 0) {
+        return false;
+    }
+
+    return true;
+}
+#endif

tests/qtest/migration-helpers.h

@@ -47,4 +47,5 @@ char *find_common_machine_version(const char *mtype, const char *var1,
                                   const char *var2);
 char *resolve_machine_version(const char *alias, const char *var1,
                               const char *var2);
+bool probe_o_direct_support(const char *tmpfs);
 #endif /* MIGRATION_HELPERS_H */

tests/qtest/migration-test.c

@@ -2135,6 +2135,14 @@ static void *test_mode_reboot_start(QTestState *from, QTestState *to)
     return NULL;
 }
 
+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_mode_reboot(void)
 {
     g_autofree char *uri = g_strdup_printf("file:%s/%s", tmpfs,
@@ -2149,6 +2157,202 @@ static void test_mode_reboot(void)
     test_file_common(&args, true);
 }
 
+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);
+}
+
+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, 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 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);
+}
+
+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, true);
+}
+
+#ifdef O_DIRECT
+static void *migrate_fixed_ram_dio_start(QTestState *from,
+                                                 QTestState *to)
+{
+    migrate_set_parameter_bool(from, "direct-io", true);
+    migrate_set_parameter_bool(to, "direct-io", true);
+
+    return NULL;
+}
+
+static void *migrate_multifd_fixed_ram_dio_start(QTestState *from,
+                                                 QTestState *to)
+{
+    migrate_multifd_fixed_ram_start(from, to);
+    return migrate_fixed_ram_dio_start(from, to);
+}
+
+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,
+    };
+
+    if (!probe_o_direct_support(tmpfs)) {
+        g_test_skip("Filesystem does not support O_DIRECT");
+        return;
+    }
+
+    test_file_common(&args, true);
+}
+
+static void test_precopy_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_fixed_ram_dio_start,
+    };
+
+    test_file_common(&args, true);
+}
+
+static void migrate_multifd_fixed_ram_fdset_dio_end(QTestState *from,
+                                                    QTestState *to,
+                                                    void *opaque)
+{
+    QDict *resp;
+    QList *fdsets;
+
+    /*
+     * Check that we removed the fdsets after migration, otherwise a
+     * second migration would fail due to too many fdsets.
+     */
+
+    resp = qtest_qmp(from, "{'execute': 'query-fdsets', "
+                     "'arguments': {}}");
+    g_assert(qdict_haskey(resp, "return"));
+    fdsets = qdict_get_qlist(resp, "return");
+    g_assert(fdsets && qlist_empty(fdsets));
+}
+#endif /* O_DIRECT */
+
+#ifndef _WIN32
+static void *migrate_multifd_fixed_ram_fdset(QTestState *from, QTestState *to)
+{
+    g_autofree char *file = g_strdup_printf("%s/%s", tmpfs, FILE_TEST_FILENAME);
+    int fds[3];
+    int src_flags = O_CREAT | O_WRONLY;
+    int dst_flags = O_CREAT | O_RDONLY;
+
+    /* main outgoing channel: no O_DIRECT */
+    fds[0] = open(file, src_flags, 0660);
+    assert(fds[0] != -1);
+
+#ifdef O_DIRECT
+    src_flags |= O_DIRECT;
+#endif
+
+    /* secondary outgoing channels */
+    fds[1] = open(file, src_flags, 0660);
+    assert(fds[1] != -1);
+
+    qtest_qmp_fds_assert_success(from, &fds[0], 1, "{'execute': 'add-fd', "
+                                 "'arguments': {'fdset-id': 1}}");
+
+    qtest_qmp_fds_assert_success(from, &fds[1], 1, "{'execute': 'add-fd', "
+                                 "'arguments': {'fdset-id': 1}}");
+
+    /* incoming channel */
+    fds[2] = open(file, dst_flags, 0660);
+    assert(fds[2] != -1);
+
+    qtest_qmp_fds_assert_success(to, &fds[2], 1, "{'execute': 'add-fd', "
+                                 "'arguments': {'fdset-id': 1}}");
+
+#ifdef O_DIRECT
+        migrate_multifd_fixed_ram_dio_start(from, to);
+#else
+        migrate_multifd_fixed_ram_start(from, to);
+#endif
+
+    return NULL;
+}
+
+static void test_multifd_file_fixed_ram_fdset(void)
+{
+    g_autofree char *uri = g_strdup_printf("file:/dev/fdset/1,offset=0x100");
+    MigrateCommon args = {
+        .connect_uri = uri,
+        .listen_uri = "defer",
+        .start_hook = migrate_multifd_fixed_ram_fdset,
+#ifdef O_DIRECT
+        .finish_hook = migrate_multifd_fixed_ram_fdset_dio_end,
+#endif
+    };
+
+    if (!probe_o_direct_support(tmpfs)) {
+        g_test_skip("Filesystem does not support O_DIRECT");
+        return;
+    }
+
+    test_file_common(&args, true);
+}
+#endif /* _WIN32 */
+
 static void test_precopy_tcp_plain(void)
 {
     MigrateCommon args = {
@@ -2358,7 +2562,7 @@ static void test_migrate_fd_finish_hook(QTestState *from,
     qobject_unref(rsp);
 }
 
-static void test_migrate_fd_proto(void)
+static void test_migrate_precopy_fd_socket(void)
 {
     MigrateCommon args = {
         .listen_uri = "defer",
@@ -2368,6 +2572,82 @@ static void test_migrate_fd_proto(void)
     };
     test_precopy_common(&args);
 }
+
+static void *migrate_precopy_fd_file_start(QTestState *from, QTestState *to)
+{
+    g_autofree char *file = g_strdup_printf("%s/%s", tmpfs, FILE_TEST_FILENAME);
+    int src_flags = O_CREAT | O_RDWR;
+    int dst_flags = O_CREAT | O_RDWR;
+    int fds[2];
+
+    fds[0] = open(file, src_flags, 0660);
+    assert(fds[0] != -1);
+
+    fds[1] = open(file, dst_flags, 0660);
+    assert(fds[1] != -1);
+
+
+    qtest_qmp_fds_assert_success(to, &fds[0], 1,
+                                 "{ 'execute': 'getfd',"
+                                 "  'arguments': { 'fdname': 'fd-mig' }}");
+
+    qtest_qmp_fds_assert_success(from, &fds[1], 1,
+                                 "{ 'execute': 'getfd',"
+                                 "  'arguments': { 'fdname': 'fd-mig' }}");
+
+    close(fds[0]);
+    close(fds[1]);
+
+    return NULL;
+}
+
+static void *migrate_fd_file_fixed_ram_start(QTestState *from, QTestState *to)
+{
+    migrate_fixed_ram_start(from, to);
+
+    return migrate_precopy_fd_file_start(from, to);
+}
+
+static void test_migrate_precopy_fd_file(void)
+{
+    MigrateCommon args = {
+        .listen_uri = "defer",
+        .connect_uri = "fd:fd-mig",
+        .start_hook = migrate_precopy_fd_file_start,
+        .finish_hook = test_migrate_fd_finish_hook
+    };
+    test_file_common(&args, true);
+}
+
+static void test_migrate_precopy_fd_file_fixed_ram(void)
+{
+    MigrateCommon args = {
+        .listen_uri = "defer",
+        .connect_uri = "fd:fd-mig",
+        .start_hook = migrate_fd_file_fixed_ram_start,
+        .finish_hook = test_migrate_fd_finish_hook
+    };
+    test_file_common(&args, true);
+}
+
+static void *migrate_multifd_fd_fixed_ram_start(QTestState *from,
+                                                QTestState *to)
+{
+    migrate_multifd_fixed_ram_start(from, to);
+    return migrate_precopy_fd_file_start(from, to);
+}
+
+static void test_multifd_fd_fixed_ram(void)
+{
+    MigrateCommon args = {
+        .connect_uri = "fd:fd-mig",
+        .listen_uri = "defer",
+        .start_hook = migrate_multifd_fd_fixed_ram_start,
+        .finish_hook = test_migrate_fd_finish_hook
+    };
+
+    test_file_common(&args, true);
+}
 #endif /* _WIN32 */
 
 static void do_test_validate_uuid(MigrateStart *args, bool should_fail)
@@ -3392,6 +3672,32 @@ int main(int argc, char **argv)
         qtest_add_func("/migration/mode/reboot", test_mode_reboot);
     }
 
+    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);
+#ifndef _WIN32
+    qtest_add_func("/migration/multifd/fd/fixed-ram",
+                   test_multifd_fd_fixed_ram);
+#endif
+
+#ifdef O_DIRECT
+    qtest_add_func("/migration/precopy/file/fixed-ram/dio",
+                   test_precopy_file_fixed_ram_dio);
+    qtest_add_func("/migration/multifd/file/fixed-ram/dio",
+                   test_multifd_file_fixed_ram_dio);
+#endif
+
+#ifndef _WIN32
+    qtest_add_func("/migration/multifd/file/fixed-ram/fdset",
+                   test_multifd_file_fixed_ram_fdset);
+#endif
+
 #ifdef CONFIG_GNUTLS
     qtest_add_func("/migration/precopy/unix/tls/psk",
                    test_precopy_unix_tls_psk);
@@ -3448,7 +3754,10 @@ int main(int argc, char **argv)
 
     /* qtest_add_func("/migration/ignore_shared", test_ignore_shared); */
 #ifndef _WIN32
-    qtest_add_func("/migration/fd_proto", test_migrate_fd_proto);
+    qtest_add_func("/migration/precopy/fd/tcp", test_migrate_precopy_fd_socket);
+    qtest_add_func("/migration/precopy/fd/file", test_migrate_precopy_fd_file);
+    qtest_add_func("/migration/precopy/fd/file/fixed-ram",
+                   test_migrate_precopy_fd_file_fixed_ram);
 #endif
     qtest_add_func("/migration/validate_uuid", test_validate_uuid);
     qtest_add_func("/migration/validate_uuid_error", test_validate_uuid_error);

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;