Update version for 2.9.1 release

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>

MAINTAINERS

@@ -1395,6 +1395,7 @@ S: Supported
 F: qobject/
 F: include/qapi/qmp/
 X: include/qapi/qmp/dispatch.h
+F: scripts/coccinelle/qobject.cocci
 F: tests/check-qdict.c
 F: tests/check-qfloat.c
 F: tests/check-qint.c

VERSION

@@ -1 +1 @@
-2.8.92
+2.9.1

audio/audio.c

@@ -2028,6 +2028,8 @@ void AUD_del_capture (CaptureVoiceOut *cap, void *cb_opaque)
                     sw = sw1;
                 }
                 QLIST_REMOVE (cap, entries);
+                g_free (cap->hw.mix_buf);
+                g_free (cap->buf);
                 g_free (cap);
             }
             return;

block.c

@@ -937,16 +937,14 @@ static void update_flags_from_options(int *flags, QemuOpts *opts)
 static void update_options_from_flags(QDict *options, int flags)
 {
     if (!qdict_haskey(options, BDRV_OPT_CACHE_DIRECT)) {
-        qdict_put(options, BDRV_OPT_CACHE_DIRECT,
-                  qbool_from_bool(flags & BDRV_O_NOCACHE));
+        qdict_put_bool(options, BDRV_OPT_CACHE_DIRECT, flags & BDRV_O_NOCACHE);
     }
     if (!qdict_haskey(options, BDRV_OPT_CACHE_NO_FLUSH)) {
-        qdict_put(options, BDRV_OPT_CACHE_NO_FLUSH,
-                  qbool_from_bool(flags & BDRV_O_NO_FLUSH));
+        qdict_put_bool(options, BDRV_OPT_CACHE_NO_FLUSH,
+                       flags & BDRV_O_NO_FLUSH);
     }
     if (!qdict_haskey(options, BDRV_OPT_READ_ONLY)) {
-        qdict_put(options, BDRV_OPT_READ_ONLY,
-                  qbool_from_bool(!(flags & BDRV_O_RDWR)));
+        qdict_put_bool(options, BDRV_OPT_READ_ONLY, !(flags & BDRV_O_RDWR));
     }
 }
 
@@ -1157,10 +1155,17 @@ static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file,
     if (file != NULL) {
         filename = blk_bs(file)->filename;
     } else {
+        /*
+         * Caution: while qdict_get_try_str() is fine, getting
+         * non-string types would require more care.  When @options
+         * come from -blockdev or blockdev_add, its members are typed
+         * according to the QAPI schema, but when they come from
+         * -drive, they're all QString.
+         */
         filename = qdict_get_try_str(options, "filename");
     }
 
-    if (drv->bdrv_needs_filename && !filename) {
+    if (drv->bdrv_needs_filename && (!filename || !filename[0])) {
         error_setg(errp, "The '%s' block driver requires a file name",
                    drv->format_name);
         ret = -EINVAL;
@@ -1324,6 +1329,13 @@ static int bdrv_fill_options(QDict **options, const char *filename,
     BlockDriver *drv = NULL;
     Error *local_err = NULL;
 
+    /*
+     * Caution: while qdict_get_try_str() is fine, getting non-string
+     * types would require more care.  When @options come from
+     * -blockdev or blockdev_add, its members are typed according to
+     * the QAPI schema, but when they come from -drive, they're all
+     * QString.
+     */
     drvname = qdict_get_try_str(*options, "driver");
     if (drvname) {
         drv = bdrv_find_format(drvname);
@@ -1348,7 +1360,7 @@ static int bdrv_fill_options(QDict **options, const char *filename,
     /* Fetch the file name from the options QDict if necessary */
     if (protocol && filename) {
         if (!qdict_haskey(*options, "filename")) {
-            qdict_put(*options, "filename", qstring_from_str(filename));
+            qdict_put_str(*options, "filename", filename);
             parse_filename = true;
         } else {
             error_setg(errp, "Can't specify 'file' and 'filename' options at "
@@ -1358,6 +1370,7 @@ static int bdrv_fill_options(QDict **options, const char *filename,
     }
 
     /* Find the right block driver */
+    /* See cautionary note on accessing @options above */
     filename = qdict_get_try_str(*options, "filename");
 
     if (!drvname && protocol) {
@@ -1368,7 +1381,7 @@ static int bdrv_fill_options(QDict **options, const char *filename,
             }
 
             drvname = drv->format_name;
-            qdict_put(*options, "driver", qstring_from_str(drvname));
+            qdict_put_str(*options, "driver", drvname);
         } else {
             error_setg(errp, "Must specify either driver or file");
             return -EINVAL;
@@ -1737,6 +1750,9 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
 {
     BlockDriverState *old_bs = child->bs;
 
+    if (old_bs && new_bs) {
+        assert(bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs));
+    }
     if (old_bs) {
         if (old_bs->quiesce_counter && child->role->drained_end) {
             child->role->drained_end(child);
@@ -1837,6 +1853,7 @@ BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs,
     bdrv_get_cumulative_perm(parent_bs, &perm, &shared_perm);
 
     assert(parent_bs->drv);
+    assert(bdrv_get_aio_context(parent_bs) == bdrv_get_aio_context(child_bs));
     parent_bs->drv->bdrv_child_perm(parent_bs, NULL, child_role,
                                     perm, shared_perm, &perm, &shared_perm);
 
@@ -1987,6 +2004,13 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
     qdict_extract_subqdict(parent_options, &options, bdref_key_dot);
     g_free(bdref_key_dot);
 
+    /*
+     * Caution: while qdict_get_try_str() is fine, getting non-string
+     * types would require more care.  When @parent_options come from
+     * -blockdev or blockdev_add, its members are typed according to
+     * the QAPI schema, but when they come from -drive, they're all
+     * QString.
+     */
     reference = qdict_get_try_str(parent_options, bdref_key);
     if (reference || qdict_haskey(options, "file.filename")) {
         backing_filename[0] = '\0';
@@ -2012,7 +2036,7 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
     }
 
     if (bs->backing_format[0] != '\0' && !qdict_haskey(options, "driver")) {
-        qdict_put(options, "driver", qstring_from_str(bs->backing_format));
+        qdict_put_str(options, "driver", bs->backing_format);
     }
 
     backing_hd = bdrv_open_inherit(*backing_filename ? backing_filename : NULL,
@@ -2059,6 +2083,13 @@ bdrv_open_child_bs(const char *filename, QDict *options, const char *bdref_key,
     qdict_extract_subqdict(options, &image_options, bdref_key_dot);
     g_free(bdref_key_dot);
 
+    /*
+     * Caution: while qdict_get_try_str() is fine, getting non-string
+     * types would require more care.  When @options come from
+     * -blockdev or blockdev_add, its members are typed according to
+     * the QAPI schema, but when they come from -drive, they're all
+     * QString.
+     */
     reference = qdict_get_try_str(options, bdref_key);
     if (!filename && !reference && !qdict_size(image_options)) {
         if (!allow_none) {
@@ -2160,12 +2191,9 @@ static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs,
     }
 
     /* Prepare options QDict for the temporary file */
-    qdict_put(snapshot_options, "file.driver",
-              qstring_from_str("file"));
-    qdict_put(snapshot_options, "file.filename",
-              qstring_from_str(tmp_filename));
-    qdict_put(snapshot_options, "driver",
-              qstring_from_str("qcow2"));
+    qdict_put_str(snapshot_options, "file.driver", "file");
+    qdict_put_str(snapshot_options, "file.filename", tmp_filename);
+    qdict_put_str(snapshot_options, "driver", "qcow2");
 
     bs_snapshot = bdrv_open(NULL, NULL, snapshot_options, flags, errp);
     snapshot_options = NULL;
@@ -2274,9 +2302,13 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
         goto fail;
     }
 
-    /* Set the BDRV_O_RDWR and BDRV_O_ALLOW_RDWR flags.
-     * FIXME: we're parsing the QDict to avoid having to create a
-     * QemuOpts just for this, but neither option is optimal. */
+    /*
+     * Set the BDRV_O_RDWR and BDRV_O_ALLOW_RDWR flags.
+     * Caution: getting a boolean member of @options requires care.
+     * When @options come from -blockdev or blockdev_add, members are
+     * typed according to the QAPI schema, but when they come from
+     * -drive, they're all QString.
+     */
     if (g_strcmp0(qdict_get_try_str(options, BDRV_OPT_READ_ONLY), "on") &&
         !qdict_get_try_bool(options, BDRV_OPT_READ_ONLY, false)) {
         flags |= (BDRV_O_RDWR | BDRV_O_ALLOW_RDWR);
@@ -2298,6 +2330,7 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
     options = qdict_clone_shallow(options);
 
     /* Find the right image format driver */
+    /* See cautionary note on accessing @options above */
     drvname = qdict_get_try_str(options, "driver");
     if (drvname) {
         drv = bdrv_find_format(drvname);
@@ -2309,6 +2342,7 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
 
     assert(drvname || !(flags & BDRV_O_PROTOCOL));
 
+    /* See cautionary note on accessing @options above */
     backing = qdict_get_try_str(options, "backing");
     if (backing && *backing == '\0') {
         flags |= BDRV_O_NO_BACKING;
@@ -2334,8 +2368,7 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
                 goto fail;
             }
 
-            qdict_put(options, "file",
-                      qstring_from_str(bdrv_get_node_name(file_bs)));
+            qdict_put_str(options, "file", bdrv_get_node_name(file_bs));
         }
     }
 
@@ -2357,8 +2390,8 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
          * sure to update both bs->options (which has the full effective
          * options for bs) and options (which has file.* already removed).
          */
-        qdict_put(bs->options, "driver", qstring_from_str(drv->format_name));
-        qdict_put(options, "driver", qstring_from_str(drv->format_name));
+        qdict_put_str(bs->options, "driver", drv->format_name);
+        qdict_put_str(options, "driver", drv->format_name);
     } else if (!drv) {
         error_setg(errp, "Must specify either driver or file");
         goto fail;
@@ -2733,12 +2766,12 @@ int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue,
      * that they are checked at the end of this function. */
     value = qemu_opt_get(opts, "node-name");
     if (value) {
-        qdict_put(reopen_state->options, "node-name", qstring_from_str(value));
+        qdict_put_str(reopen_state->options, "node-name", value);
     }
 
     value = qemu_opt_get(opts, "driver");
     if (value) {
-        qdict_put(reopen_state->options, "driver", qstring_from_str(value));
+        qdict_put_str(reopen_state->options, "driver", value);
     }
 
     /* if we are to stay read-only, do not allow permission change
@@ -2787,6 +2820,13 @@ int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue,
         do {
             QString *new_obj = qobject_to_qstring(entry->value);
             const char *new = qstring_get_str(new_obj);
+            /*
+             * Caution: while qdict_get_try_str() is fine, getting
+             * non-string types would require more care.  When
+             * bs->options come from -blockdev or blockdev_add, its
+             * members are typed according to the QAPI schema, but
+             * when they come from -drive, they're all QString.
+             */
             const char *old = qdict_get_try_str(reopen_state->bs->options,
                                                 entry->key);
 
@@ -3222,20 +3262,30 @@ exit:
 /**
  * Truncate file to 'offset' bytes (needed only for file protocols)
  */
-int bdrv_truncate(BdrvChild *child, int64_t offset)
+int bdrv_truncate(BdrvChild *child, int64_t offset, Error **errp)
 {
     BlockDriverState *bs = child->bs;
     BlockDriver *drv = bs->drv;
     int ret;
 
-    assert(child->perm & BLK_PERM_RESIZE);
+    /* FIXME: Some format block drivers use this function instead of implicitly
+     *        growing their file by writing beyond its end.
+     *        See bdrv_aligned_pwritev() for an explanation why we currently
+     *        cannot assert this permission in that case. */
+    // assert(child->perm & BLK_PERM_RESIZE);
 
-    if (!drv)
+    if (!drv) {
+        error_setg(errp, "No medium inserted");
         return -ENOMEDIUM;
-    if (!drv->bdrv_truncate)
+    }
+    if (!drv->bdrv_truncate) {
+        error_setg(errp, "Image format driver does not support resize");
         return -ENOTSUP;
-    if (bs->read_only)
+    }
+    if (bs->read_only) {
+        error_setg(errp, "Image is read-only");
         return -EACCES;
+    }
 
     ret = drv->bdrv_truncate(bs, offset);
     if (ret == 0) {
@@ -3243,6 +3293,8 @@ int bdrv_truncate(BdrvChild *child, int64_t offset)
         bdrv_dirty_bitmap_truncate(bs);
         bdrv_parent_cb_resize(bs);
         ++bs->write_gen;
+    } else {
+        error_setg_errno(errp, -ret, "Failed to resize image");
     }
     return ret;
 }
@@ -3811,19 +3863,6 @@ BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
     return retval;
 }
 
-int bdrv_get_backing_file_depth(BlockDriverState *bs)
-{
-    if (!bs->drv) {
-        return 0;
-    }
-
-    if (!bs->backing) {
-        return 0;
-    }
-
-    return 1 + bdrv_get_backing_file_depth(bs->backing->bs);
-}
-
 void bdrv_init(void)
 {
     module_call_init(MODULE_INIT_BLOCK);
@@ -4218,8 +4257,7 @@ void bdrv_img_create(const char *filename, const char *fmt,
 
             if (backing_fmt) {
                 backing_options = qdict_new();
-                qdict_put(backing_options, "driver",
-                          qstring_from_str(backing_fmt));
+                qdict_put_str(backing_options, "driver", backing_fmt);
             }
 
             bs = bdrv_open(full_backing, NULL, backing_options, back_flags,
@@ -4278,6 +4316,11 @@ AioContext *bdrv_get_aio_context(BlockDriverState *bs)
     return bs->aio_context;
 }
 
+void bdrv_coroutine_enter(BlockDriverState *bs, Coroutine *co)
+{
+    aio_co_enter(bdrv_get_aio_context(bs), co);
+}
+
 static void bdrv_do_remove_aio_context_notifier(BdrvAioNotifier *ban)
 {
     QLIST_REMOVE(ban, list);
@@ -4350,11 +4393,12 @@ void bdrv_attach_aio_context(BlockDriverState *bs,
 
 void bdrv_set_aio_context(BlockDriverState *bs, AioContext *new_context)
 {
-    AioContext *ctx;
+    AioContext *ctx = bdrv_get_aio_context(bs);
 
+    aio_disable_external(ctx);
+    bdrv_parent_drained_begin(bs);
     bdrv_drain(bs); /* ensure there are no in-flight requests */
 
-    ctx = bdrv_get_aio_context(bs);
     while (aio_poll(ctx, false)) {
         /* wait for all bottom halves to execute */
     }
@@ -4366,6 +4410,8 @@ void bdrv_set_aio_context(BlockDriverState *bs, AioContext *new_context)
      */
     aio_context_acquire(new_context);
     bdrv_attach_aio_context(bs, new_context);
+    bdrv_parent_drained_end(bs);
+    aio_enable_external(ctx);
     aio_context_release(new_context);
 }
 
@@ -4616,11 +4662,9 @@ void bdrv_refresh_filename(BlockDriverState *bs)
          * contain a representation of the filename, therefore the following
          * suffices without querying the (exact_)filename of this BDS. */
         if (bs->file->bs->full_open_options) {
-            qdict_put_obj(opts, "driver",
-                          QOBJECT(qstring_from_str(drv->format_name)));
+            qdict_put_str(opts, "driver", drv->format_name);
             QINCREF(bs->file->bs->full_open_options);
-            qdict_put_obj(opts, "file",
-                          QOBJECT(bs->file->bs->full_open_options));
+            qdict_put(opts, "file", bs->file->bs->full_open_options);
 
             bs->full_open_options = opts;
         } else {
@@ -4636,8 +4680,7 @@ void bdrv_refresh_filename(BlockDriverState *bs)
 
         opts = qdict_new();
         append_open_options(opts, bs);
-        qdict_put_obj(opts, "driver",
-                      QOBJECT(qstring_from_str(drv->format_name)));
+        qdict_put_str(opts, "driver", drv->format_name);
 
         if (bs->exact_filename[0]) {
             /* This may not work for all block protocol drivers (some may
@@ -4647,8 +4690,7 @@ void bdrv_refresh_filename(BlockDriverState *bs)
              * needs some special format of the options QDict, it needs to
              * implement the driver-specific bdrv_refresh_filename() function.
              */
-            qdict_put_obj(opts, "filename",
-                          QOBJECT(qstring_from_str(bs->exact_filename)));
+            qdict_put_str(opts, "filename", bs->exact_filename);
         }
 
         bs->full_open_options = opts;

block/blkdebug.c

@@ -1,6 +1,7 @@
 /*
  * Block protocol for I/O error injection
  *
+ * Copyright (C) 2016-2017 Red Hat, Inc.
  * Copyright (c) 2010 Kevin Wolf <kwolf@redhat.com>
  *
  * Permission is hereby granted, free of charge, to any person obtaining a copy
@@ -37,7 +38,12 @@
 typedef struct BDRVBlkdebugState {
     int state;
     int new_state;
-    int align;
+    uint64_t align;
+    uint64_t max_transfer;
+    uint64_t opt_write_zero;
+    uint64_t max_write_zero;
+    uint64_t opt_discard;
+    uint64_t max_discard;
 
     /* For blkdebug_refresh_filename() */
     char *config_file;
@@ -301,7 +307,7 @@ static void blkdebug_parse_filename(const char *filename, QDict *options,
     if (!strstart(filename, "blkdebug:", &filename)) {
         /* There was no prefix; therefore, all options have to be already
            present in the QDict (except for the filename) */
-        qdict_put(options, "x-image", qstring_from_str(filename));
+        qdict_put_str(options, "x-image", filename);
         return;
     }
 
@@ -320,7 +326,7 @@ static void blkdebug_parse_filename(const char *filename, QDict *options,
 
     /* TODO Allow multi-level nesting and set file.filename here */
     filename = c + 1;
-    qdict_put(options, "x-image", qstring_from_str(filename));
+    qdict_put_str(options, "x-image", filename);
 }
 
 static QemuOptsList runtime_opts = {
@@ -342,6 +348,31 @@ static QemuOptsList runtime_opts = {
             .type = QEMU_OPT_SIZE,
             .help = "Required alignment in bytes",
         },
+        {
+            .name = "max-transfer",
+            .type = QEMU_OPT_SIZE,
+            .help = "Maximum transfer size in bytes",
+        },
+        {
+            .name = "opt-write-zero",
+            .type = QEMU_OPT_SIZE,
+            .help = "Optimum write zero alignment in bytes",
+        },
+        {
+            .name = "max-write-zero",
+            .type = QEMU_OPT_SIZE,
+            .help = "Maximum write zero size in bytes",
+        },
+        {
+            .name = "opt-discard",
+            .type = QEMU_OPT_SIZE,
+            .help = "Optimum discard alignment in bytes",
+        },
+        {
+            .name = "max-discard",
+            .type = QEMU_OPT_SIZE,
+            .help = "Maximum discard size in bytes",
+        },
         { /* end of list */ }
     },
 };
@@ -352,8 +383,8 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
     BDRVBlkdebugState *s = bs->opaque;
     QemuOpts *opts;
     Error *local_err = NULL;
-    uint64_t align;
     int ret;
+    uint64_t align;
 
     opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
@@ -382,21 +413,69 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
         goto out;
     }
 
-    /* Set request alignment */
-    align = qemu_opt_get_size(opts, "align", 0);
-    if (align < INT_MAX && is_power_of_2(align)) {
-        s->align = align;
-    } else if (align) {
-        error_setg(errp, "Invalid alignment");
-        ret = -EINVAL;
-        goto fail_unref;
+    bs->supported_write_flags = BDRV_REQ_FUA &
+        bs->file->bs->supported_write_flags;
+    bs->supported_zero_flags = (BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP) &
+        bs->file->bs->supported_zero_flags;
+    ret = -EINVAL;
+
+    /* Set alignment overrides */
+    s->align = qemu_opt_get_size(opts, "align", 0);
+    if (s->align && (s->align >= INT_MAX || !is_power_of_2(s->align))) {
+        error_setg(errp, "Cannot meet constraints with align %" PRIu64,
+                   s->align);
+        goto out;
+    }
+    align = MAX(s->align, bs->file->bs->bl.request_alignment);
+
+    s->max_transfer = qemu_opt_get_size(opts, "max-transfer", 0);
+    if (s->max_transfer &&
+        (s->max_transfer >= INT_MAX ||
+         !QEMU_IS_ALIGNED(s->max_transfer, align))) {
+        error_setg(errp, "Cannot meet constraints with max-transfer %" PRIu64,
+                   s->max_transfer);
+        goto out;
+    }
+
+    s->opt_write_zero = qemu_opt_get_size(opts, "opt-write-zero", 0);
+    if (s->opt_write_zero &&
+        (s->opt_write_zero >= INT_MAX ||
+         !QEMU_IS_ALIGNED(s->opt_write_zero, align))) {
+        error_setg(errp, "Cannot meet constraints with opt-write-zero %" PRIu64,
+                   s->opt_write_zero);
+        goto out;
+    }
+
+    s->max_write_zero = qemu_opt_get_size(opts, "max-write-zero", 0);
+    if (s->max_write_zero &&
+        (s->max_write_zero >= INT_MAX ||
+         !QEMU_IS_ALIGNED(s->max_write_zero,
+                          MAX(s->opt_write_zero, align)))) {
+        error_setg(errp, "Cannot meet constraints with max-write-zero %" PRIu64,
+                   s->max_write_zero);
+        goto out;
+    }
+
+    s->opt_discard = qemu_opt_get_size(opts, "opt-discard", 0);
+    if (s->opt_discard &&
+        (s->opt_discard >= INT_MAX ||
+         !QEMU_IS_ALIGNED(s->opt_discard, align))) {
+        error_setg(errp, "Cannot meet constraints with opt-discard %" PRIu64,
+                   s->opt_discard);
+        goto out;
+    }
+
+    s->max_discard = qemu_opt_get_size(opts, "max-discard", 0);
+    if (s->max_discard &&
+        (s->max_discard >= INT_MAX ||
+         !QEMU_IS_ALIGNED(s->max_discard,
+                          MAX(s->opt_discard, align)))) {
+        error_setg(errp, "Cannot meet constraints with max-discard %" PRIu64,
+                   s->max_discard);
+        goto out;
     }
 
     ret = 0;
-    goto out;
-
-fail_unref:
-    bdrv_unref_child(bs, bs->file);
 out:
     if (ret < 0) {
         g_free(s->config_file);
@@ -405,11 +484,30 @@ out:
     return ret;
 }
 
-static int inject_error(BlockDriverState *bs, BlkdebugRule *rule)
+static int rule_check(BlockDriverState *bs, uint64_t offset, uint64_t bytes)
 {
     BDRVBlkdebugState *s = bs->opaque;
-    int error = rule->options.inject.error;
-    bool immediately = rule->options.inject.immediately;
+    BlkdebugRule *rule = NULL;
+    int error;
+    bool immediately;
+
+    QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
+        uint64_t inject_offset = rule->options.inject.offset;
+
+        if (inject_offset == -1 ||
+            (bytes && inject_offset >= offset &&
+             inject_offset < offset + bytes))
+        {
+            break;
+        }
+    }
+
+    if (!rule || !rule->options.inject.error) {
+        return 0;
+    }
+
+    immediately = rule->options.inject.immediately;
+    error = rule->options.inject.error;
 
     if (rule->options.inject.once) {
         QSIMPLEQ_REMOVE(&s->active_rules, rule, BlkdebugRule, active_next);
@@ -428,21 +526,18 @@ static int coroutine_fn
 blkdebug_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
                    QEMUIOVector *qiov, int flags)
 {
-    BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugRule *rule = NULL;
+    int err;
 
-    QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
-        uint64_t inject_offset = rule->options.inject.offset;
-
-        if (inject_offset == -1 ||
-            (inject_offset >= offset && inject_offset < offset + bytes))
-        {
-            break;
-        }
+    /* Sanity check block layer guarantees */
+    assert(QEMU_IS_ALIGNED(offset, bs->bl.request_alignment));
+    assert(QEMU_IS_ALIGNED(bytes, bs->bl.request_alignment));
+    if (bs->bl.max_transfer) {
+        assert(bytes <= bs->bl.max_transfer);
     }
 
-    if (rule && rule->options.inject.error) {
-        return inject_error(bs, rule);
+    err = rule_check(bs, offset, bytes);
+    if (err) {
+        return err;
     }
 
     return bdrv_co_preadv(bs->file, offset, bytes, qiov, flags);
@@ -452,21 +547,18 @@ static int coroutine_fn
 blkdebug_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
                     QEMUIOVector *qiov, int flags)
 {
-    BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugRule *rule = NULL;
+    int err;
 
-    QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
-        uint64_t inject_offset = rule->options.inject.offset;
-
-        if (inject_offset == -1 ||
-            (inject_offset >= offset && inject_offset < offset + bytes))
-        {
-            break;
-        }
+    /* Sanity check block layer guarantees */
+    assert(QEMU_IS_ALIGNED(offset, bs->bl.request_alignment));
+    assert(QEMU_IS_ALIGNED(bytes, bs->bl.request_alignment));
+    if (bs->bl.max_transfer) {
+        assert(bytes <= bs->bl.max_transfer);
     }
 
-    if (rule && rule->options.inject.error) {
-        return inject_error(bs, rule);
+    err = rule_check(bs, offset, bytes);
+    if (err) {
+        return err;
     }
 
     return bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags);
@@ -474,22 +566,81 @@ blkdebug_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
 
 static int blkdebug_co_flush(BlockDriverState *bs)
 {
-    BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugRule *rule = NULL;
+    int err = rule_check(bs, 0, 0);
 
-    QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
-        if (rule->options.inject.offset == -1) {
-            break;
-        }
-    }
-
-    if (rule && rule->options.inject.error) {
-        return inject_error(bs, rule);
+    if (err) {
+        return err;
     }
 
     return bdrv_co_flush(bs->file->bs);
 }
 
+static int coroutine_fn blkdebug_co_pwrite_zeroes(BlockDriverState *bs,
+                                                  int64_t offset, int count,
+                                                  BdrvRequestFlags flags)
+{
+    uint32_t align = MAX(bs->bl.request_alignment,
+                         bs->bl.pwrite_zeroes_alignment);
+    int err;
+
+    /* Only pass through requests that are larger than requested
+     * preferred alignment (so that we test the fallback to writes on
+     * unaligned portions), and check that the block layer never hands
+     * us anything unaligned that crosses an alignment boundary.  */
+    if (count < align) {
+        assert(QEMU_IS_ALIGNED(offset, align) ||
+               QEMU_IS_ALIGNED(offset + count, align) ||
+               DIV_ROUND_UP(offset, align) ==
+               DIV_ROUND_UP(offset + count, align));
+        return -ENOTSUP;
+    }
+    assert(QEMU_IS_ALIGNED(offset, align));
+    assert(QEMU_IS_ALIGNED(count, align));
+    if (bs->bl.max_pwrite_zeroes) {
+        assert(count <= bs->bl.max_pwrite_zeroes);
+    }
+
+    err = rule_check(bs, offset, count);
+    if (err) {
+        return err;
+    }
+
+    return bdrv_co_pwrite_zeroes(bs->file, offset, count, flags);
+}
+
+static int coroutine_fn blkdebug_co_pdiscard(BlockDriverState *bs,
+                                             int64_t offset, int count)
+{
+    uint32_t align = bs->bl.pdiscard_alignment;
+    int err;
+
+    /* Only pass through requests that are larger than requested
+     * minimum alignment, and ensure that unaligned requests do not
+     * cross optimum discard boundaries. */
+    if (count < bs->bl.request_alignment) {
+        assert(QEMU_IS_ALIGNED(offset, align) ||
+               QEMU_IS_ALIGNED(offset + count, align) ||
+               DIV_ROUND_UP(offset, align) ==
+               DIV_ROUND_UP(offset + count, align));
+        return -ENOTSUP;
+    }
+    assert(QEMU_IS_ALIGNED(offset, bs->bl.request_alignment));
+    assert(QEMU_IS_ALIGNED(count, bs->bl.request_alignment));
+    if (align && count >= align) {
+        assert(QEMU_IS_ALIGNED(offset, align));
+        assert(QEMU_IS_ALIGNED(count, align));
+    }
+    if (bs->bl.max_pdiscard) {
+        assert(count <= bs->bl.max_pdiscard);
+    }
+
+    err = rule_check(bs, offset, count);
+    if (err) {
+        return err;
+    }
+
+    return bdrv_co_pdiscard(bs->file->bs, offset, count);
+}
 
 static void blkdebug_close(BlockDriverState *bs)
 {
@@ -663,7 +814,7 @@ static int64_t blkdebug_getlength(BlockDriverState *bs)
 
 static int blkdebug_truncate(BlockDriverState *bs, int64_t offset)
 {
-    return bdrv_truncate(bs->file, offset);
+    return bdrv_truncate(bs->file, offset, NULL);
 }
 
 static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options)
@@ -689,16 +840,20 @@ static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options)
     }
 
     if (!force_json && bs->file->bs->exact_filename[0]) {
-        snprintf(bs->exact_filename, sizeof(bs->exact_filename),
-                 "blkdebug:%s:%s", s->config_file ?: "",
-                 bs->file->bs->exact_filename);
+        int ret = snprintf(bs->exact_filename, sizeof(bs->exact_filename),
+                           "blkdebug:%s:%s", s->config_file ?: "",
+                           bs->file->bs->exact_filename);
+        if (ret >= sizeof(bs->exact_filename)) {
+            /* An overflow makes the filename unusable, so do not report any */
+            bs->exact_filename[0] = 0;
+        }
     }
 
     opts = qdict_new();
-    qdict_put_obj(opts, "driver", QOBJECT(qstring_from_str("blkdebug")));
+    qdict_put_str(opts, "driver", "blkdebug");
 
     QINCREF(bs->file->bs->full_open_options);
-    qdict_put_obj(opts, "image", QOBJECT(bs->file->bs->full_open_options));
+    qdict_put(opts, "image", bs->file->bs->full_open_options);
 
     for (e = qdict_first(options); e; e = qdict_next(options, e)) {
         if (strcmp(qdict_entry_key(e), "x-image")) {
@@ -717,6 +872,21 @@ static void blkdebug_refresh_limits(BlockDriverState *bs, Error **errp)
     if (s->align) {
         bs->bl.request_alignment = s->align;
     }
+    if (s->max_transfer) {
+        bs->bl.max_transfer = s->max_transfer;
+    }
+    if (s->opt_write_zero) {
+        bs->bl.pwrite_zeroes_alignment = s->opt_write_zero;
+    }
+    if (s->max_write_zero) {
+        bs->bl.max_pwrite_zeroes = s->max_write_zero;
+    }
+    if (s->opt_discard) {
+        bs->bl.pdiscard_alignment = s->opt_discard;
+    }
+    if (s->max_discard) {
+        bs->bl.max_pdiscard = s->max_discard;
+    }
 }
 
 static int blkdebug_reopen_prepare(BDRVReopenState *reopen_state,
@@ -744,6 +914,8 @@ static BlockDriver bdrv_blkdebug = {
     .bdrv_co_preadv         = blkdebug_co_preadv,
     .bdrv_co_pwritev        = blkdebug_co_pwritev,
     .bdrv_co_flush_to_disk  = blkdebug_co_flush,
+    .bdrv_co_pwrite_zeroes  = blkdebug_co_pwrite_zeroes,
+    .bdrv_co_pdiscard       = blkdebug_co_pdiscard,
 
     .bdrv_debug_event           = blkdebug_debug_event,
     .bdrv_debug_breakpoint      = blkdebug_debug_breakpoint,

block/blkreplay.c

@@ -37,9 +37,6 @@ static int blkreplay_open(BlockDriverState *bs, QDict *options, int flags,
 
     ret = 0;
 fail:
-    if (ret < 0) {
-        bdrv_unref_child(bs, bs->file);
-    }
     return ret;
 }
 

block/blkverify.c

@@ -67,7 +67,7 @@ static void blkverify_parse_filename(const char *filename, QDict *options,
     if (!strstart(filename, "blkverify:", &filename)) {
         /* There was no prefix; therefore, all options have to be already
            present in the QDict (except for the filename) */
-        qdict_put(options, "x-image", qstring_from_str(filename));
+        qdict_put_str(options, "x-image", filename);
         return;
     }
 
@@ -84,7 +84,7 @@ static void blkverify_parse_filename(const char *filename, QDict *options,
 
     /* TODO Allow multi-level nesting and set file.filename here */
     filename = c + 1;
-    qdict_put(options, "x-image", qstring_from_str(filename));
+    qdict_put_str(options, "x-image", filename);
 }
 
 static QemuOptsList runtime_opts = {
@@ -142,9 +142,6 @@ static int blkverify_open(BlockDriverState *bs, QDict *options, int flags,
 
     ret = 0;
 fail:
-    if (ret < 0) {
-        bdrv_unref_child(bs, bs->file);
-    }
     qemu_opts_del(opts);
     return ret;
 }
@@ -291,13 +288,12 @@ static void blkverify_refresh_filename(BlockDriverState *bs, QDict *options)
         && s->test_file->bs->full_open_options)
     {
         QDict *opts = qdict_new();
-        qdict_put_obj(opts, "driver", QOBJECT(qstring_from_str("blkverify")));
+        qdict_put_str(opts, "driver", "blkverify");
 
         QINCREF(bs->file->bs->full_open_options);
-        qdict_put_obj(opts, "raw", QOBJECT(bs->file->bs->full_open_options));
+        qdict_put(opts, "raw", bs->file->bs->full_open_options);
         QINCREF(s->test_file->bs->full_open_options);
-        qdict_put_obj(opts, "test",
-                      QOBJECT(s->test_file->bs->full_open_options));
+        qdict_put(opts, "test", s->test_file->bs->full_open_options);
 
         bs->full_open_options = opts;
     }
@@ -305,10 +301,14 @@ static void blkverify_refresh_filename(BlockDriverState *bs, QDict *options)
     if (bs->file->bs->exact_filename[0]
         && s->test_file->bs->exact_filename[0])
     {
-        snprintf(bs->exact_filename, sizeof(bs->exact_filename),
-                 "blkverify:%s:%s",
-                 bs->file->bs->exact_filename,
-                 s->test_file->bs->exact_filename);
+        int ret = snprintf(bs->exact_filename, sizeof(bs->exact_filename),
+                           "blkverify:%s:%s",
+                           bs->file->bs->exact_filename,
+                           s->test_file->bs->exact_filename);
+        if (ret >= sizeof(bs->exact_filename)) {
+            /* An overflow makes the filename unusable, so do not report any */
+            bs->exact_filename[0] = 0;
+        }
     }
 }
 

block/block-backend.c

@@ -61,6 +61,7 @@ struct BlockBackend {
 
     uint64_t perm;
     uint64_t shared_perm;
+    bool disable_perm;
 
     bool allow_write_beyond_eof;
 
@@ -230,6 +231,9 @@ static void blk_delete(BlockBackend *blk)
     assert(!blk->refcnt);
     assert(!blk->name);
     assert(!blk->dev);
+    if (blk->public.throttle_state) {
+        blk_io_limits_disable(blk);
+    }
     if (blk->root) {
         blk_remove_bs(blk);
     }
@@ -578,7 +582,7 @@ int blk_set_perm(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
 {
     int ret;
 
-    if (blk->root) {
+    if (blk->root && !blk->disable_perm) {
         ret = bdrv_child_try_set_perm(blk->root, perm, shared_perm, errp);
         if (ret < 0) {
             return ret;
@@ -597,15 +601,52 @@ void blk_get_perm(BlockBackend *blk, uint64_t *perm, uint64_t *shared_perm)
     *shared_perm = blk->shared_perm;
 }
 
+/*
+ * Notifies the user of all BlockBackends that migration has completed. qdev
+ * devices can tighten their permissions in response (specifically revoke
+ * shared write permissions that we needed for storage migration).
+ *
+ * If an error is returned, the VM cannot be allowed to be resumed.
+ */
+void blk_resume_after_migration(Error **errp)
+{
+    BlockBackend *blk;
+    Error *local_err = NULL;
+
+    for (blk = blk_all_next(NULL); blk; blk = blk_all_next(blk)) {
+        if (!blk->disable_perm) {
+            continue;
+        }
+
+        blk->disable_perm = false;
+
+        blk_set_perm(blk, blk->perm, blk->shared_perm, &local_err);
+        if (local_err) {
+            error_propagate(errp, local_err);
+            blk->disable_perm = true;
+            return;
+        }
+    }
+}
+
 static int blk_do_attach_dev(BlockBackend *blk, void *dev)
 {
     if (blk->dev) {
         return -EBUSY;
     }
+
+    /* While migration is still incoming, we don't need to apply the
+     * permissions of guest device BlockBackends. We might still have a block
+     * job or NBD server writing to the image for storage migration. */
+    if (runstate_check(RUN_STATE_INMIGRATE)) {
+        blk->disable_perm = true;
+    }
+
     blk_ref(blk);
     blk->dev = dev;
     blk->legacy_dev = false;
     blk_iostatus_reset(blk);
+
     return 0;
 }
 
@@ -1007,7 +1048,7 @@ static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf,
         co_entry(&rwco);
     } else {
         Coroutine *co = qemu_coroutine_create(co_entry, &rwco);
-        qemu_coroutine_enter(co);
+        bdrv_coroutine_enter(blk_bs(blk), co);
         BDRV_POLL_WHILE(blk_bs(blk), rwco.ret == NOT_DONE);
     }
 
@@ -1114,7 +1155,7 @@ static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset, int bytes,
     acb->has_returned = false;
 
     co = qemu_coroutine_create(co_entry, acb);
-    qemu_coroutine_enter(co);
+    bdrv_coroutine_enter(blk_bs(blk), co);
 
     acb->has_returned = true;
     if (acb->rwco.ret != NOT_DONE) {
@@ -1705,13 +1746,14 @@ int blk_pwrite_compressed(BlockBackend *blk, int64_t offset, const void *buf,
                    BDRV_REQ_WRITE_COMPRESSED);
 }
 
-int blk_truncate(BlockBackend *blk, int64_t offset)
+int blk_truncate(BlockBackend *blk, int64_t offset, Error **errp)
 {
     if (!blk_is_available(blk)) {
+        error_setg(errp, "No medium inserted");
         return -ENOMEDIUM;
     }
 
-    return bdrv_truncate(blk->root, offset);
+    return bdrv_truncate(blk->root, offset, errp);
 }
 
 static void blk_pdiscard_entry(void *opaque)

block/commit.c

@@ -89,6 +89,12 @@ static void commit_complete(BlockJob *job, void *opaque)
     int ret = data->ret;
     bool remove_commit_top_bs = false;
 
+    /* Make sure overlay_bs and top stay around until bdrv_set_backing_hd() */
+    bdrv_ref(top);
+    if (overlay_bs) {
+        bdrv_ref(overlay_bs);
+    }
+
     /* Remove base node parent that still uses BLK_PERM_WRITE/RESIZE before
      * the normal backing chain can be restored. */
     blk_unref(s->base);
@@ -115,6 +121,13 @@ static void commit_complete(BlockJob *job, void *opaque)
     }
     g_free(s->backing_file_str);
     blk_unref(s->top);
+
+    /* If there is more than one reference to the job (e.g. if called from
+     * block_job_finish_sync()), block_job_completed() won't free it and
+     * therefore the blockers on the intermediate nodes remain. This would
+     * cause bdrv_set_backing_hd() to fail. */
+    block_job_remove_all_bdrv(job);
+
     block_job_completed(&s->common, ret);
     g_free(data);
 
@@ -124,6 +137,9 @@ static void commit_complete(BlockJob *job, void *opaque)
     if (remove_commit_top_bs) {
         bdrv_set_backing_hd(overlay_bs, top, &error_abort);
     }
+
+    bdrv_unref(overlay_bs);
+    bdrv_unref(top);
 }
 
 static void coroutine_fn commit_run(void *opaque)
@@ -151,7 +167,7 @@ static void coroutine_fn commit_run(void *opaque)
     }
 
     if (base_len < s->common.len) {
-        ret = blk_truncate(s->base, s->common.len);
+        ret = blk_truncate(s->base, s->common.len, NULL);
         if (ret) {
             goto out;
         }
@@ -335,6 +351,11 @@ void commit_start(const char *job_id, BlockDriverState *bs,
     if (commit_top_bs == NULL) {
         goto fail;
     }
+    if (!filter_node_name) {
+        commit_top_bs->implicit = true;
+    }
+    commit_top_bs->total_sectors = top->total_sectors;
+    bdrv_set_aio_context(commit_top_bs, bdrv_get_aio_context(top));
 
     bdrv_set_backing_hd(commit_top_bs, top, &local_err);
     if (local_err) {
@@ -482,6 +503,7 @@ int bdrv_commit(BlockDriverState *bs)
         error_report_err(local_err);
         goto ro_cleanup;
     }
+    bdrv_set_aio_context(commit_top_bs, bdrv_get_aio_context(backing_file_bs));
 
     bdrv_set_backing_hd(commit_top_bs, backing_file_bs, &error_abort);
     bdrv_set_backing_hd(bs, commit_top_bs, &error_abort);
@@ -508,8 +530,9 @@ int bdrv_commit(BlockDriverState *bs)
      * grow the backing file image if possible.  If not possible,
      * we must return an error */
     if (length > backing_length) {
-        ret = blk_truncate(backing, length);
+        ret = blk_truncate(backing, length, &local_err);
         if (ret < 0) {
+            error_report_err(local_err);
             goto ro_cleanup;
         }
     }

block/crypto.c

@@ -389,7 +389,7 @@ static int block_crypto_truncate(BlockDriverState *bs, int64_t offset)
 
     offset += payload_offset;
 
-    return bdrv_truncate(bs->file, offset);
+    return bdrv_truncate(bs->file, offset, NULL);
 }
 
 static void block_crypto_close(BlockDriverState *bs)

block/curl.c

@@ -147,6 +147,7 @@ static void curl_multi_do(void *arg);
 static void curl_multi_read(void *arg);
 
 #ifdef NEED_CURL_TIMER_CALLBACK
+/* Called from curl_multi_do_locked, with s->mutex held.  */
 static int curl_timer_cb(CURLM *multi, long timeout_ms, void *opaque)
 {
     BDRVCURLState *s = opaque;
@@ -163,6 +164,7 @@ static int curl_timer_cb(CURLM *multi, long timeout_ms, void *opaque)
 }
 #endif
 
+/* Called from curl_multi_do_locked, with s->mutex held.  */
 static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
                         void *userp, void *sp)
 {
@@ -212,6 +214,7 @@ static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
     return 0;
 }
 
+/* Called from curl_multi_do_locked, with s->mutex held.  */
 static size_t curl_header_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
 {
     BDRVCURLState *s = opaque;
@@ -226,6 +229,7 @@ static size_t curl_header_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
     return realsize;
 }
 
+/* Called from curl_multi_do_locked, with s->mutex held.  */
 static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
 {
     CURLState *s = ((CURLState*)opaque);
@@ -264,7 +268,9 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
                                   request_length - offset);
             }
 
+            qemu_mutex_unlock(&s->s->mutex);
             acb->common.cb(acb->common.opaque, 0);
+            qemu_mutex_lock(&s->s->mutex);
             qemu_aio_unref(acb);
             s->acb[i] = NULL;
         }
@@ -275,6 +281,7 @@ read_end:
     return size * nmemb;
 }
 
+/* Called with s->mutex held.  */
 static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
                          CURLAIOCB *acb)
 {
@@ -305,8 +312,6 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
             if (clamped_len < len) {
                 qemu_iovec_memset(acb->qiov, clamped_len, 0, len - clamped_len);
             }
-            acb->common.cb(acb->common.opaque, 0);
-
             return FIND_RET_OK;
         }
 
@@ -449,6 +454,7 @@ static void curl_multi_timeout_do(void *arg)
 #endif
 }
 
+/* Called with s->mutex held.  */
 static CURLState *curl_init_state(BlockDriverState *bs, BDRVCURLState *s)
 {
     CURLState *state = NULL;
@@ -467,7 +473,9 @@ static CURLState *curl_init_state(BlockDriverState *bs, BDRVCURLState *s)
             break;
         }
         if (!state) {
+            qemu_mutex_unlock(&s->mutex);
             aio_poll(bdrv_get_aio_context(bs), true);
+            qemu_mutex_lock(&s->mutex);
         }
     } while(!state);
 
@@ -530,8 +538,14 @@ static CURLState *curl_init_state(BlockDriverState *bs, BDRVCURLState *s)
     return state;
 }
 
+/* Called with s->mutex held.  */
 static void curl_clean_state(CURLState *s)
 {
+    int j;
+    for (j = 0; j < CURL_NUM_ACB; j++) {
+        assert(!s->acb[j]);
+    }
+
     if (s->s->multi)
         curl_multi_remove_handle(s->s->multi, s->curl);
 
@@ -548,7 +562,7 @@ static void curl_clean_state(CURLState *s)
 static void curl_parse_filename(const char *filename, QDict *options,
                                 Error **errp)
 {
-    qdict_put(options, CURL_BLOCK_OPT_URL, qstring_from_str(filename));
+    qdict_put_str(options, CURL_BLOCK_OPT_URL, filename);
 }
 
 static void curl_detach_aio_context(BlockDriverState *bs)
@@ -556,6 +570,7 @@ static void curl_detach_aio_context(BlockDriverState *bs)
     BDRVCURLState *s = bs->opaque;
     int i;
 
+    qemu_mutex_lock(&s->mutex);
     for (i = 0; i < CURL_NUM_STATES; i++) {
         if (s->states[i].in_use) {
             curl_clean_state(&s->states[i]);
@@ -571,6 +586,7 @@ static void curl_detach_aio_context(BlockDriverState *bs)
         curl_multi_cleanup(s->multi);
         s->multi = NULL;
     }
+    qemu_mutex_unlock(&s->mutex);
 
     timer_del(&s->timer);
 }
@@ -659,6 +675,7 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
     const char *cookie;
     double d;
     const char *secretid;
+    const char *protocol_delimiter;
 
     static int inited = 0;
 
@@ -667,6 +684,7 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
         return -EROFS;
     }
 
+    qemu_mutex_init(&s->mutex);
     opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (local_err) {
@@ -700,6 +718,15 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
         goto out_noclean;
     }
 
+    if (!strstart(file, bs->drv->protocol_name, &protocol_delimiter) ||
+        !strstart(protocol_delimiter, "://", NULL))
+    {
+        error_setg(errp, "%s curl driver cannot handle the URL '%s' (does not "
+                   "start with '%s://')", bs->drv->protocol_name, file,
+                   bs->drv->protocol_name);
+        goto out_noclean;
+    }
+
     s->username = g_strdup(qemu_opt_get(opts, CURL_BLOCK_OPT_USERNAME));
     secretid = qemu_opt_get(opts, CURL_BLOCK_OPT_PASSWORD_SECRET);
 
@@ -728,7 +755,9 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
     DPRINTF("CURL: Opening %s\n", file);
     s->aio_context = bdrv_get_aio_context(bs);
     s->url = g_strdup(file);
+    qemu_mutex_lock(&s->mutex);
     state = curl_init_state(bs, s);
+    qemu_mutex_unlock(&s->mutex);
     if (!state)
         goto out_noclean;
 
@@ -772,11 +801,12 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
     }
     DPRINTF("CURL: Size = %zd\n", s->len);
 
+    qemu_mutex_lock(&s->mutex);
     curl_clean_state(state);
+    qemu_mutex_unlock(&s->mutex);
     curl_easy_cleanup(state->curl);
     state->curl = NULL;
 
-    qemu_mutex_init(&s->mutex);
     curl_attach_aio_context(bs, bdrv_get_aio_context(bs));
 
     qemu_opts_del(opts);
@@ -787,6 +817,7 @@ out:
     curl_easy_cleanup(state->curl);
     state->curl = NULL;
 out_noclean:
+    qemu_mutex_destroy(&s->mutex);
     g_free(s->cookie);
     g_free(s->url);
     qemu_opts_del(opts);
@@ -817,8 +848,8 @@ static void curl_readv_bh_cb(void *p)
     // we can just call the callback and be done.
     switch (curl_find_buf(s, start, acb->nb_sectors * BDRV_SECTOR_SIZE, acb)) {
         case FIND_RET_OK:
-            qemu_aio_unref(acb);
-            // fall through
+            ret = 0;
+            goto out;
         case FIND_RET_WAIT:
             goto out;
         default:

block/dirty-bitmap.c

@@ -345,7 +345,7 @@ BlockDirtyInfoList *bdrv_query_dirty_bitmaps(BlockDriverState *bs)
     QLIST_FOREACH(bm, &bs->dirty_bitmaps, list) {
         BlockDirtyInfo *info = g_new0(BlockDirtyInfo, 1);
         BlockDirtyInfoList *entry = g_new0(BlockDirtyInfoList, 1);
-        info->count = bdrv_get_dirty_count(bm);
+        info->count = bdrv_get_dirty_count(bm) << BDRV_SECTOR_BITS;
         info->granularity = bdrv_dirty_bitmap_granularity(bm);
         info->has_name = !!bm->name;
         info->name = g_strdup(bm->name);

block/file-posix.c

@@ -377,7 +377,7 @@ static void raw_parse_filename(const char *filename, QDict *options,
      * function call can be ignored. */
     strstart(filename, "file:", &filename);
 
-    qdict_put_obj(options, "filename", QOBJECT(qstring_from_str(filename)));
+    qdict_put_str(options, "filename", filename);
 }
 
 static QemuOptsList raw_runtime_opts = {
@@ -2150,7 +2150,7 @@ static void hdev_parse_filename(const char *filename, QDict *options,
     /* The prefix is optional, just as for "file". */
     strstart(filename, "host_device:", &filename);
 
-    qdict_put_obj(options, "filename", QOBJECT(qstring_from_str(filename)));
+    qdict_put_str(options, "filename", filename);
 }
 
 static bool hdev_is_sg(BlockDriverState *bs)
@@ -2193,6 +2193,12 @@ static int hdev_open(BlockDriverState *bs, QDict *options, int flags,
     int ret;
 
 #if defined(__APPLE__) && defined(__MACH__)
+    /*
+     * Caution: while qdict_get_str() is fine, getting non-string types
+     * would require more care.  When @options come from -blockdev or
+     * blockdev_add, its members are typed according to the QAPI
+     * schema, but when they come from -drive, they're all QString.
+     */
     const char *filename = qdict_get_str(options, "filename");
     char bsd_path[MAXPATHLEN] = "";
     bool error_occurred = false;
@@ -2233,7 +2239,7 @@ static int hdev_open(BlockDriverState *bs, QDict *options, int flags,
             goto hdev_open_Mac_error;
         }
 
-        qdict_put(options, "filename", qstring_from_str(bsd_path));
+        qdict_put_str(options, "filename", bsd_path);
 
 hdev_open_Mac_error:
         g_free(mediaType);
@@ -2443,7 +2449,7 @@ static void cdrom_parse_filename(const char *filename, QDict *options,
     /* The prefix is optional, just as for "file". */
     strstart(filename, "host_cdrom:", &filename);
 
-    qdict_put_obj(options, "filename", QOBJECT(qstring_from_str(filename)));
+    qdict_put_str(options, "filename", filename);
 }
 #endif
 

block/file-win32.c

@@ -282,7 +282,7 @@ static void raw_parse_filename(const char *filename, QDict *options,
      * function call can be ignored. */
     strstart(filename, "file:", &filename);
 
-    qdict_put_obj(options, "filename", QOBJECT(qstring_from_str(filename)));
+    qdict_put_str(options, "filename", filename);
 }
 
 static QemuOptsList raw_runtime_opts = {
@@ -669,7 +669,7 @@ static void hdev_parse_filename(const char *filename, QDict *options,
     /* The prefix is optional, just as for "file". */
     strstart(filename, "host_device:", &filename);
 
-    qdict_put_obj(options, "filename", QOBJECT(qstring_from_str(filename)));
+    qdict_put_str(options, "filename", filename);
 }
 
 static int hdev_open(BlockDriverState *bs, QDict *options, int flags,

block/gluster.c

@@ -412,10 +412,12 @@ static struct glfs *qemu_gluster_glfs_init(BlockdevOptionsGluster *gconf,
     glfs_set_preopened(gconf->volume, glfs);
 
     for (server = gconf->server; server; server = server->next) {
-        if (server->value->type  == SOCKET_ADDRESS_FLAT_TYPE_UNIX) {
+        switch (server->value->type) {
+        case SOCKET_ADDRESS_FLAT_TYPE_UNIX:
             ret = glfs_set_volfile_server(glfs, "unix",
                                    server->value->u.q_unix.path, 0);
-        } else {
+            break;
+        case SOCKET_ADDRESS_FLAT_TYPE_INET:
             if (parse_uint_full(server->value->u.inet.port, &port, 10) < 0 ||
                 port > 65535) {
                 error_setg(errp, "'%s' is not a valid port number",
@@ -426,6 +428,11 @@ static struct glfs *qemu_gluster_glfs_init(BlockdevOptionsGluster *gconf,
             ret = glfs_set_volfile_server(glfs, "tcp",
                                    server->value->u.inet.host,
                                    (int)port);
+            break;
+        case SOCKET_ADDRESS_FLAT_TYPE_VSOCK:
+        case SOCKET_ADDRESS_FLAT_TYPE_FD:
+        default:
+            abort();
         }
 
         if (ret < 0) {
@@ -487,7 +494,7 @@ static int qemu_gluster_parse_json(BlockdevOptionsGluster *gconf,
     char *str = NULL;
     const char *ptr;
     size_t num_servers;
-    int i;
+    int i, type;
 
     /* create opts info from runtime_json_opts list */
     opts = qemu_opts_create(&runtime_json_opts, NULL, 0, &error_abort);
@@ -539,16 +546,17 @@ static int qemu_gluster_parse_json(BlockdevOptionsGluster *gconf,
         if (!strcmp(ptr, "tcp")) {
             ptr = "inet";       /* accept legacy "tcp" */
         }
-        gsconf->type = qapi_enum_parse(SocketAddressFlatType_lookup, ptr,
-                                       SOCKET_ADDRESS_FLAT_TYPE__MAX, -1,
-                                       &local_err);
-        if (local_err) {
-            error_append_hint(&local_err,
-                              "Parameter '%s' may be 'inet' or 'unix'\n",
-                              GLUSTER_OPT_TYPE);
+        type = qapi_enum_parse(SocketAddressFlatType_lookup, ptr,
+                               SOCKET_ADDRESS_FLAT_TYPE__MAX, -1, NULL);
+        if (type != SOCKET_ADDRESS_FLAT_TYPE_INET
+            && type != SOCKET_ADDRESS_FLAT_TYPE_UNIX) {
+            error_setg(&local_err,
+                       "Parameter '%s' may be 'inet' or 'unix'",
+                       GLUSTER_OPT_TYPE);
             error_append_hint(&local_err, GERR_INDEX_HINT, i);
             goto out;
         }
+        gsconf->type = type;
         qemu_opts_del(opts);
 
         if (gsconf->type == SOCKET_ADDRESS_FLAT_TYPE_INET) {

block/io.c

@@ -44,7 +44,7 @@ static void coroutine_fn bdrv_co_do_rw(void *opaque);
 static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
     int64_t offset, int count, BdrvRequestFlags flags);
 
-static void bdrv_parent_drained_begin(BlockDriverState *bs)
+void bdrv_parent_drained_begin(BlockDriverState *bs)
 {
     BdrvChild *c;
 
@@ -55,7 +55,7 @@ static void bdrv_parent_drained_begin(BlockDriverState *bs)
     }
 }
 
-static void bdrv_parent_drained_end(BlockDriverState *bs)
+void bdrv_parent_drained_end(BlockDriverState *bs)
 {
     BdrvChild *c;
 
@@ -158,7 +158,7 @@ bool bdrv_requests_pending(BlockDriverState *bs)
 
 static bool bdrv_drain_recurse(BlockDriverState *bs)
 {
-    BdrvChild *child;
+    BdrvChild *child, *tmp;
     bool waited;
 
     waited = BDRV_POLL_WHILE(bs, atomic_read(&bs->in_flight) > 0);
@@ -167,8 +167,25 @@ static bool bdrv_drain_recurse(BlockDriverState *bs)
         bs->drv->bdrv_drain(bs);
     }
 
-    QLIST_FOREACH(child, &bs->children, next) {
-        waited |= bdrv_drain_recurse(child->bs);
+    QLIST_FOREACH_SAFE(child, &bs->children, next, tmp) {
+        BlockDriverState *bs = child->bs;
+        bool in_main_loop =
+            qemu_get_current_aio_context() == qemu_get_aio_context();
+        assert(bs->refcnt > 0);
+        if (in_main_loop) {
+            /* In case the recursive bdrv_drain_recurse processes a
+             * block_job_defer_to_main_loop BH and modifies the graph,
+             * let's hold a reference to bs until we are done.
+             *
+             * IOThread doesn't have such a BH, and it is not safe to call
+             * bdrv_unref without BQL, so skip doing it there.
+             */
+            bdrv_ref(bs);
+        }
+        waited |= bdrv_drain_recurse(bs);
+        if (in_main_loop) {
+            bdrv_unref(bs);
+        }
     }
 
     return waited;
@@ -616,7 +633,7 @@ static int bdrv_prwv_co(BdrvChild *child, int64_t offset,
         bdrv_rw_co_entry(&rwco);
     } else {
         co = qemu_coroutine_create(bdrv_rw_co_entry, &rwco);
-        qemu_coroutine_enter(co);
+        bdrv_coroutine_enter(child->bs, co);
         BDRV_POLL_WHILE(child->bs, rwco.ret == NOT_DONE);
     }
     return rwco.ret;
@@ -945,7 +962,14 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child,
     size_t skip_bytes;
     int ret;
 
-    assert(child->perm & (BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE));
+    /* FIXME We cannot require callers to have write permissions when all they
+     * are doing is a read request. If we did things right, write permissions
+     * would be obtained anyway, but internally by the copy-on-read code. As
+     * long as it is implemented here rather than in a separat filter driver,
+     * the copy-on-read code doesn't have its own BdrvChild, however, for which
+     * it could request permissions. Therefore we have to bypass the permission
+     * system for the moment. */
+    // assert(child->perm & (BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE));
 
     /* Cover entire cluster so no additional backing file I/O is required when
      * allocating cluster in the image file.
@@ -1338,8 +1362,16 @@ static int coroutine_fn bdrv_aligned_pwritev(BdrvChild *child,
     assert(!waited || !req->serialising);
     assert(req->overlap_offset <= offset);
     assert(offset + bytes <= req->overlap_offset + req->overlap_bytes);
-    assert(child->perm & BLK_PERM_WRITE);
-    assert(end_sector <= bs->total_sectors || child->perm & BLK_PERM_RESIZE);
+    /* FIXME: Block migration uses the BlockBackend of the guest device at a
+     *        point when it has not yet taken write permissions. This will be
+     *        fixed by a future patch, but for now we have to bypass this
+     *        assertion for block migration to work. */
+    // assert(child->perm & BLK_PERM_WRITE);
+    /* FIXME: Because of the above, we also cannot guarantee that all format
+     *        BDS take the BLK_PERM_RESIZE permission on their file BDS, since
+     *        they are not obligated to do so if they do not have any parent
+     *        that has taken the permission to write to them. */
+    // assert(end_sector <= bs->total_sectors || child->perm & BLK_PERM_RESIZE);
 
     ret = notifier_with_return_list_notify(&bs->before_write_notifiers, req);
 
@@ -1725,6 +1757,7 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs,
     int64_t n;
     int64_t ret, ret2;
 
+    *file = NULL;
     total_sectors = bdrv_nb_sectors(bs);
     if (total_sectors < 0) {
         return total_sectors;
@@ -1745,11 +1778,11 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs,
         ret = BDRV_BLOCK_DATA | BDRV_BLOCK_ALLOCATED;
         if (bs->drv->protocol_name) {
             ret |= BDRV_BLOCK_OFFSET_VALID | (sector_num * BDRV_SECTOR_SIZE);
+            *file = bs;
         }
         return ret;
     }
 
-    *file = NULL;
     bdrv_inc_in_flight(bs);
     ret = bs->drv->bdrv_co_get_block_status(bs, sector_num, nb_sectors, pnum,
                                             file);
@@ -1759,9 +1792,9 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs,
     }
 
     if (ret & BDRV_BLOCK_RAW) {
-        assert(ret & BDRV_BLOCK_OFFSET_VALID);
-        ret = bdrv_get_block_status(*file, ret >> BDRV_SECTOR_BITS,
-                                    *pnum, pnum, file);
+        assert(ret & BDRV_BLOCK_OFFSET_VALID && *file);
+        ret = bdrv_co_get_block_status(*file, ret >> BDRV_SECTOR_BITS,
+                                       *pnum, pnum, file);
         goto out;
     }
 
@@ -1873,7 +1906,7 @@ int64_t bdrv_get_block_status_above(BlockDriverState *bs,
     } else {
         co = qemu_coroutine_create(bdrv_get_block_status_above_co_entry,
                                    &data);
-        qemu_coroutine_enter(co);
+        bdrv_coroutine_enter(bs, co);
         BDRV_POLL_WHILE(bs, !data.done);
     }
     return data.ret;
@@ -1999,7 +2032,7 @@ bdrv_rw_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos,
         };
         Coroutine *co = qemu_coroutine_create(bdrv_co_rw_vmstate_entry, &data);
 
-        qemu_coroutine_enter(co);
+        bdrv_coroutine_enter(bs, co);
         while (data.ret == -EINPROGRESS) {
             aio_poll(bdrv_get_aio_context(bs), true);
         }
@@ -2216,7 +2249,7 @@ static BlockAIOCB *bdrv_co_aio_prw_vector(BdrvChild *child,
     acb->is_write = is_write;
 
     co = qemu_coroutine_create(bdrv_co_do_rw, acb);
-    qemu_coroutine_enter(co);
+    bdrv_coroutine_enter(child->bs, co);
 
     bdrv_co_maybe_schedule_bh(acb);
     return &acb->common;
@@ -2247,7 +2280,7 @@ BlockAIOCB *bdrv_aio_flush(BlockDriverState *bs,
     acb->req.error = -EINPROGRESS;
 
     co = qemu_coroutine_create(bdrv_aio_flush_co_entry, acb);
-    qemu_coroutine_enter(co);
+    bdrv_coroutine_enter(bs, co);
 
     bdrv_co_maybe_schedule_bh(acb);
     return &acb->common;
@@ -2271,16 +2304,17 @@ static void coroutine_fn bdrv_flush_co_entry(void *opaque)
 
 int coroutine_fn bdrv_co_flush(BlockDriverState *bs)
 {
-    int ret;
-
-    if (!bs || !bdrv_is_inserted(bs) || bdrv_is_read_only(bs) ||
-        bdrv_is_sg(bs)) {
-        return 0;
-    }
+    int current_gen;
+    int ret = 0;
 
     bdrv_inc_in_flight(bs);
 
-    int current_gen = bs->write_gen;
+    if (!bs || !bdrv_is_inserted(bs) || bdrv_is_read_only(bs) ||
+        bdrv_is_sg(bs)) {
+        goto early_exit;
+    }
+
+    current_gen = bs->write_gen;
 
     /* Wait until any previous flushes are completed */
     while (bs->active_flush_req) {
@@ -2363,6 +2397,7 @@ out:
     /* Return value is ignored - it's ok if wait queue is empty */
     qemu_co_queue_next(&bs->flush_queue);
 
+early_exit:
     bdrv_dec_in_flight(bs);
     return ret;
 }
@@ -2380,7 +2415,7 @@ int bdrv_flush(BlockDriverState *bs)
         bdrv_flush_co_entry(&flush_co);
     } else {
         co = qemu_coroutine_create(bdrv_flush_co_entry, &flush_co);
-        qemu_coroutine_enter(co);
+        bdrv_coroutine_enter(bs, co);
         BDRV_POLL_WHILE(bs, flush_co.ret == NOT_DONE);
     }
 
@@ -2527,7 +2562,7 @@ int bdrv_pdiscard(BlockDriverState *bs, int64_t offset, int count)
         bdrv_pdiscard_co_entry(&rwco);
     } else {
         co = qemu_coroutine_create(bdrv_pdiscard_co_entry, &rwco);
-        qemu_coroutine_enter(co);
+        bdrv_coroutine_enter(bs, co);
         BDRV_POLL_WHILE(bs, rwco.ret == NOT_DONE);
     }
 

block/iscsi.c

@@ -103,7 +103,6 @@ typedef struct IscsiTask {
 
 typedef struct IscsiAIOCB {
     BlockAIOCB common;
-    QEMUIOVector *qiov;
     QEMUBH *bh;
     IscsiLun *iscsilun;
     struct scsi_task *task;
@@ -2093,6 +2092,7 @@ static int iscsi_create(const char *filename, QemuOpts *opts, Error **errp)
     BlockDriverState *bs;
     IscsiLun *iscsilun = NULL;
     QDict *bs_options;
+    Error *local_err = NULL;
 
     bs = bdrv_new();
 
@@ -2103,8 +2103,13 @@ static int iscsi_create(const char *filename, QemuOpts *opts, Error **errp)
     iscsilun = bs->opaque;
 
     bs_options = qdict_new();
-    qdict_put(bs_options, "filename", qstring_from_str(filename));
-    ret = iscsi_open(bs, bs_options, 0, NULL);
+    iscsi_parse_filename(filename, bs_options, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
+    } else {
+        ret = iscsi_open(bs, bs_options, 0, NULL);
+    }
     QDECREF(bs_options);
 
     if (ret != 0) {

block/mirror.c

@@ -514,7 +514,12 @@ static void mirror_exit(BlockJob *job, void *opaque)
 
     /* Remove target parent that still uses BLK_PERM_WRITE/RESIZE before
      * inserting target_bs at s->to_replace, where we might not be able to get
-     * these permissions. */
+     * these permissions.
+     *
+     * Note that blk_unref() alone doesn't necessarily drop permissions because
+     * we might be running nested inside mirror_drain(), which takes an extra
+     * reference, so use an explicit blk_set_perm() first. */
+    blk_set_perm(s->target, 0, BLK_PERM_ALL, &error_abort);
     blk_unref(s->target);
     s->target = NULL;
 
@@ -724,7 +729,7 @@ static void coroutine_fn mirror_run(void *opaque)
         }
 
         if (s->bdev_length > base_length) {
-            ret = blk_truncate(s->target, s->bdev_length);
+            ret = blk_truncate(s->target, s->bdev_length, NULL);
             if (ret < 0) {
                 goto immediate_exit;
             }
@@ -1147,10 +1152,14 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs,
     if (mirror_top_bs == NULL) {
         return;
     }
+    if (!filter_node_name) {
+        mirror_top_bs->implicit = true;
+    }
     mirror_top_bs->total_sectors = bs->total_sectors;
+    bdrv_set_aio_context(mirror_top_bs, bdrv_get_aio_context(bs));
 
     /* bdrv_append takes ownership of the mirror_top_bs reference, need to keep
-     * it alive until block_job_create() even if bs has no parent. */
+     * it alive until block_job_create() succeeds even if bs has no parent. */
     bdrv_ref(mirror_top_bs);
     bdrv_drained_begin(bs);
     bdrv_append(mirror_top_bs, bs, &local_err);
@@ -1168,10 +1177,12 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs,
                          BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
                          BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD, speed,
                          creation_flags, cb, opaque, errp);
-    bdrv_unref(mirror_top_bs);
     if (!s) {
         goto fail;
     }
+    /* The block job now has a reference to this node */
+    bdrv_unref(mirror_top_bs);
+
     s->source = bs;
     s->mirror_top_bs = mirror_top_bs;
 
@@ -1242,6 +1253,10 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs,
 
 fail:
     if (s) {
+        /* Make sure this BDS does not go away until we have completed the graph
+         * changes below */
+        bdrv_ref(mirror_top_bs);
+
         g_free(s->replaces);
         blk_unref(s->target);
         block_job_unref(&s->common);
@@ -1250,6 +1265,8 @@ fail:
     bdrv_child_try_set_perm(mirror_top_bs->backing, 0, BLK_PERM_ALL,
                             &error_abort);
     bdrv_replace_node(mirror_top_bs, backing_bs(mirror_top_bs), &error_abort);
+
+    bdrv_unref(mirror_top_bs);
 }
 
 void mirror_start(const char *job_id, BlockDriverState *bs,

block/nbd-client.c

@@ -352,14 +352,14 @@ int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int count)
 void nbd_client_detach_aio_context(BlockDriverState *bs)
 {
     NBDClientSession *client = nbd_get_client_session(bs);
-    qio_channel_detach_aio_context(QIO_CHANNEL(client->sioc));
+    qio_channel_detach_aio_context(QIO_CHANNEL(client->ioc));
 }
 
 void nbd_client_attach_aio_context(BlockDriverState *bs,
                                    AioContext *new_context)
 {
     NBDClientSession *client = nbd_get_client_session(bs);
-    qio_channel_attach_aio_context(QIO_CHANNEL(client->sioc), new_context);
+    qio_channel_attach_aio_context(QIO_CHANNEL(client->ioc), new_context);
     aio_co_schedule(new_context, client->read_reply_co);
 }
 

block/nbd.c

@@ -47,7 +47,7 @@ typedef struct BDRVNBDState {
     NBDClientSession client;
 
     /* For nbd_refresh_filename() */
-    SocketAddress *saddr;
+    SocketAddressFlat *saddr;
     char *export, *tlscredsid;
 } BDRVNBDState;
 
@@ -65,11 +65,11 @@ static int nbd_parse_uri(const char *filename, QDict *options)
     }
 
     /* transport */
-    if (!strcmp(uri->scheme, "nbd")) {
+    if (!g_strcmp0(uri->scheme, "nbd")) {
         is_unix = false;
-    } else if (!strcmp(uri->scheme, "nbd+tcp")) {
+    } else if (!g_strcmp0(uri->scheme, "nbd+tcp")) {
         is_unix = false;
-    } else if (!strcmp(uri->scheme, "nbd+unix")) {
+    } else if (!g_strcmp0(uri->scheme, "nbd+unix")) {
         is_unix = true;
     } else {
         ret = -EINVAL;
@@ -79,7 +79,7 @@ static int nbd_parse_uri(const char *filename, QDict *options)
     p = uri->path ? uri->path : "/";
     p += strspn(p, "/");
     if (p[0]) {
-        qdict_put(options, "export", qstring_from_str(p));
+        qdict_put_str(options, "export", p);
     }
 
     qp = query_params_parse(uri->query);
@@ -94,9 +94,8 @@ static int nbd_parse_uri(const char *filename, QDict *options)
             ret = -EINVAL;
             goto out;
         }
-        qdict_put(options, "server.type", qstring_from_str("unix"));
-        qdict_put(options, "server.data.path",
-                  qstring_from_str(qp->p[0].value));
+        qdict_put_str(options, "server.type", "unix");
+        qdict_put_str(options, "server.path", qp->p[0].value);
     } else {
         QString *host;
         char *port_str;
@@ -115,11 +114,11 @@ static int nbd_parse_uri(const char *filename, QDict *options)
             host = qstring_from_str(uri->server);
         }
 
-        qdict_put(options, "server.type", qstring_from_str("inet"));
-        qdict_put(options, "server.data.host", host);
+        qdict_put_str(options, "server.type", "inet");
+        qdict_put(options, "server.host", host);
 
         port_str = g_strdup_printf("%d", uri->port ?: NBD_DEFAULT_PORT);
-        qdict_put(options, "server.data.port", qstring_from_str(port_str));
+        qdict_put_str(options, "server.port", port_str);
         g_free(port_str);
     }
 
@@ -181,7 +180,7 @@ static void nbd_parse_filename(const char *filename, QDict *options,
         export_name[0] = 0; /* truncate 'file' */
         export_name += strlen(EN_OPTSTR);
 
-        qdict_put(options, "export", qstring_from_str(export_name));
+        qdict_put_str(options, "export", export_name);
     }
 
     /* extract the host_spec - fail if it's not nbd:... */
@@ -196,8 +195,8 @@ static void nbd_parse_filename(const char *filename, QDict *options,
 
     /* are we a UNIX or TCP socket? */
     if (strstart(host_spec, "unix:", &unixpath)) {
-        qdict_put(options, "server.type", qstring_from_str("unix"));
-        qdict_put(options, "server.data.path", qstring_from_str(unixpath));
+        qdict_put_str(options, "server.type", "unix");
+        qdict_put_str(options, "server.path", unixpath);
     } else {
         InetSocketAddress *addr = NULL;
 
@@ -206,9 +205,9 @@ static void nbd_parse_filename(const char *filename, QDict *options,
             goto out;
         }
 
-        qdict_put(options, "server.type", qstring_from_str("inet"));
-        qdict_put(options, "server.data.host", qstring_from_str(addr->host));
-        qdict_put(options, "server.data.port", qstring_from_str(addr->port));
+        qdict_put_str(options, "server.type", "inet");
+        qdict_put_str(options, "server.host", addr->host);
+        qdict_put_str(options, "server.port", addr->port);
         qapi_free_InetSocketAddress(addr);
     }
 
@@ -247,21 +246,22 @@ static bool nbd_process_legacy_socket_options(QDict *output_options,
             return false;
         }
 
-        qdict_put(output_options, "server.type", qstring_from_str("unix"));
-        qdict_put(output_options, "server.data.path", qstring_from_str(path));
+        qdict_put_str(output_options, "server.type", "unix");
+        qdict_put_str(output_options, "server.path", path);
     } else if (host) {
-        qdict_put(output_options, "server.type", qstring_from_str("inet"));
-        qdict_put(output_options, "server.data.host", qstring_from_str(host));
-        qdict_put(output_options, "server.data.port",
-                  qstring_from_str(port ?: stringify(NBD_DEFAULT_PORT)));
+        qdict_put_str(output_options, "server.type", "inet");
+        qdict_put_str(output_options, "server.host", host);
+        qdict_put_str(output_options, "server.port",
+                      port ?: stringify(NBD_DEFAULT_PORT));
     }
 
     return true;
 }
 
-static SocketAddress *nbd_config(BDRVNBDState *s, QDict *options, Error **errp)
+static SocketAddressFlat *nbd_config(BDRVNBDState *s, QDict *options,
+                                     Error **errp)
 {
-    SocketAddress *saddr = NULL;
+    SocketAddressFlat *saddr = NULL;
     QDict *addr = NULL;
     QObject *crumpled_addr = NULL;
     Visitor *iv = NULL;
@@ -278,8 +278,16 @@ static SocketAddress *nbd_config(BDRVNBDState *s, QDict *options, Error **errp)
         goto done;
     }
 
+    /*
+     * FIXME .numeric, .to, .ipv4 or .ipv6 don't work with -drive
+     * server.type=inet.  .to doesn't matter, it's ignored anyway.
+     * That's because when @options come from -blockdev or
+     * blockdev_add, members are typed according to the QAPI schema,
+     * but when they come from -drive, they're all QString.  The
+     * visitor expects the former.
+     */
     iv = qobject_input_visitor_new(crumpled_addr);
-    visit_type_SocketAddress(iv, NULL, &saddr, &local_err);
+    visit_type_SocketAddressFlat(iv, NULL, &saddr, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         goto done;
@@ -298,9 +306,10 @@ NBDClientSession *nbd_get_client_session(BlockDriverState *bs)
     return &s->client;
 }
 
-static QIOChannelSocket *nbd_establish_connection(SocketAddress *saddr,
+static QIOChannelSocket *nbd_establish_connection(SocketAddressFlat *saddr_flat,
                                                   Error **errp)
 {
+    SocketAddress *saddr = socket_address_crumple(saddr_flat);
     QIOChannelSocket *sioc;
     Error *local_err = NULL;
 
@@ -310,7 +319,9 @@ static QIOChannelSocket *nbd_establish_connection(SocketAddress *saddr,
     qio_channel_socket_connect_sync(sioc,
                                     saddr,
                                     &local_err);
+    qapi_free_SocketAddress(saddr);
     if (local_err) {
+        object_unref(OBJECT(sioc));
         error_propagate(errp, local_err);
         return NULL;
     }
@@ -401,7 +412,7 @@ static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
         goto error;
     }
 
-    /* Translate @host, @port, and @path to a SocketAddress */
+    /* Translate @host, @port, and @path to a SocketAddressFlat */
     if (!nbd_process_legacy_socket_options(options, opts, errp)) {
         goto error;
     }
@@ -421,11 +432,12 @@ static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
             goto error;
         }
 
-        if (s->saddr->type != SOCKET_ADDRESS_KIND_INET) {
+        /* TODO SOCKET_ADDRESS_KIND_FD where fd has AF_INET or AF_INET6 */
+        if (s->saddr->type != SOCKET_ADDRESS_FLAT_TYPE_INET) {
             error_setg(errp, "TLS only supported over IP sockets");
             goto error;
         }
-        hostname = s->saddr->u.inet.data->host;
+        hostname = s->saddr->u.inet.host;
     }
 
     /* establish TCP connection, return error if it fails
@@ -448,7 +460,7 @@ static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
         object_unref(OBJECT(tlscreds));
     }
     if (ret < 0) {
-        qapi_free_SocketAddress(s->saddr);
+        qapi_free_SocketAddressFlat(s->saddr);
         g_free(s->export);
         g_free(s->tlscredsid);
     }
@@ -474,7 +486,7 @@ static void nbd_close(BlockDriverState *bs)
 
     nbd_client_close(bs);
 
-    qapi_free_SocketAddress(s->saddr);
+    qapi_free_SocketAddressFlat(s->saddr);
     g_free(s->export);
     g_free(s->tlscredsid);
 }
@@ -505,17 +517,17 @@ static void nbd_refresh_filename(BlockDriverState *bs, QDict *options)
     Visitor *ov;
     const char *host = NULL, *port = NULL, *path = NULL;
 
-    if (s->saddr->type == SOCKET_ADDRESS_KIND_INET) {
-        const InetSocketAddress *inet = s->saddr->u.inet.data;
+    if (s->saddr->type == SOCKET_ADDRESS_FLAT_TYPE_INET) {
+        const InetSocketAddress *inet = &s->saddr->u.inet;
         if (!inet->has_ipv4 && !inet->has_ipv6 && !inet->has_to) {
             host = inet->host;
             port = inet->port;
         }
-    } else if (s->saddr->type == SOCKET_ADDRESS_KIND_UNIX) {
-        path = s->saddr->u.q_unix.data->path;
-    }
+    } else if (s->saddr->type == SOCKET_ADDRESS_FLAT_TYPE_UNIX) {
+        path = s->saddr->u.q_unix.path;
+    } /* else can't represent as pseudo-filename */
 
-    qdict_put(opts, "driver", qstring_from_str("nbd"));
+    qdict_put_str(opts, "driver", "nbd");
 
     if (path && s->export) {
         snprintf(bs->exact_filename, sizeof(bs->exact_filename),
@@ -532,16 +544,16 @@ static void nbd_refresh_filename(BlockDriverState *bs, QDict *options)
     }
 
     ov = qobject_output_visitor_new(&saddr_qdict);
-    visit_type_SocketAddress(ov, NULL, &s->saddr, &error_abort);
+    visit_type_SocketAddressFlat(ov, NULL, &s->saddr, &error_abort);
     visit_complete(ov, &saddr_qdict);
     visit_free(ov);
     qdict_put_obj(opts, "server", saddr_qdict);
 
     if (s->export) {
-        qdict_put(opts, "export", qstring_from_str(s->export));
+        qdict_put_str(opts, "export", s->export);
     }
     if (s->tlscredsid) {
-        qdict_put(opts, "tls-creds", qstring_from_str(s->tlscredsid));
+        qdict_put_str(opts, "tls-creds", s->tlscredsid);
     }
 
     qdict_flatten(opts);

block/nfs.c

@@ -83,7 +83,7 @@ static int nfs_parse_uri(const char *filename, QDict *options, Error **errp)
         error_setg(errp, "Invalid URI specified");
         goto out;
     }
-    if (strcmp(uri->scheme, "nfs") != 0) {
+    if (g_strcmp0(uri->scheme, "nfs") != 0) {
         error_setg(errp, "URI scheme must be 'nfs'");
         goto out;
     }
@@ -104,9 +104,9 @@ static int nfs_parse_uri(const char *filename, QDict *options, Error **errp)
         goto out;
     }
 
-    qdict_put(options, "server.host", qstring_from_str(uri->server));
-    qdict_put(options, "server.type", qstring_from_str("inet"));
-    qdict_put(options, "path", qstring_from_str(uri->path));
+    qdict_put_str(options, "server.host", uri->server);
+    qdict_put_str(options, "server.type", "inet");
+    qdict_put_str(options, "path", uri->path);
 
     for (i = 0; i < qp->n; i++) {
         unsigned long long val;
@@ -121,23 +121,17 @@ static int nfs_parse_uri(const char *filename, QDict *options, Error **errp)
             goto out;
         }
         if (!strcmp(qp->p[i].name, "uid")) {
-            qdict_put(options, "user",
-                      qstring_from_str(qp->p[i].value));
+            qdict_put_str(options, "user", qp->p[i].value);
         } else if (!strcmp(qp->p[i].name, "gid")) {
-            qdict_put(options, "group",
-                      qstring_from_str(qp->p[i].value));
+            qdict_put_str(options, "group", qp->p[i].value);
         } else if (!strcmp(qp->p[i].name, "tcp-syncnt")) {
-            qdict_put(options, "tcp-syn-count",
-                      qstring_from_str(qp->p[i].value));
+            qdict_put_str(options, "tcp-syn-count", qp->p[i].value);
         } else if (!strcmp(qp->p[i].name, "readahead")) {
-            qdict_put(options, "readahead-size",
-                      qstring_from_str(qp->p[i].value));
+            qdict_put_str(options, "readahead-size", qp->p[i].value);
         } else if (!strcmp(qp->p[i].name, "pagecache")) {
-            qdict_put(options, "page-cache-size",
-                      qstring_from_str(qp->p[i].value));
+            qdict_put_str(options, "page-cache-size", qp->p[i].value);
         } else if (!strcmp(qp->p[i].name, "debug")) {
-            qdict_put(options, "debug",
-                      qstring_from_str(qp->p[i].value));
+            qdict_put_str(options, "debug", qp->p[i].value);
         } else {
             error_setg(errp, "Unknown NFS parameter name: %s",
                        qp->p[i].name);
@@ -440,19 +434,23 @@ static void nfs_client_close(NFSClient *client)
     if (client->context) {
         if (client->fh) {
             nfs_close(client->context, client->fh);
+            client->fh = NULL;
         }
         aio_set_fd_handler(client->aio_context, nfs_get_fd(client->context),
                            false, NULL, NULL, NULL, NULL);
         nfs_destroy_context(client->context);
+        client->context = NULL;
     }
-    memset(client, 0, sizeof(NFSClient));
+    g_free(client->path);
+    qemu_mutex_destroy(&client->mutex);
+    qapi_free_NFSServer(client->server);
+    client->server = NULL;
 }
 
 static void nfs_file_close(BlockDriverState *bs)
 {
     NFSClient *client = bs->opaque;
     nfs_client_close(client);
-    qemu_mutex_destroy(&client->mutex);
 }
 
 static NFSServer *nfs_config(QDict *options, Error **errp)
@@ -474,6 +472,13 @@ static NFSServer *nfs_config(QDict *options, Error **errp)
         goto out;
     }
 
+    /*
+     * Caution: this works only because all scalar members of
+     * NFSServer are QString in @crumpled_addr.  The visitor expects
+     * @crumpled_addr to be typed according to the QAPI schema.  It
+     * is when @options come from -blockdev or blockdev_add.  But when
+     * they come from -drive, they're all QString.
+     */
     iv = qobject_input_visitor_new(crumpled_addr);
     visit_type_NFSServer(iv, NULL, &server, &local_error);
     if (local_error) {
@@ -498,6 +503,7 @@ static int64_t nfs_client_open(NFSClient *client, QDict *options,
     struct stat st;
     char *file = NULL, *strp = NULL;
 
+    qemu_mutex_init(&client->mutex);
     opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (local_err) {
@@ -660,7 +666,7 @@ static int nfs_file_open(BlockDriverState *bs, QDict *options, int flags,
     if (ret < 0) {
         return ret;
     }
-    qemu_mutex_init(&client->mutex);
+
     bs->total_sectors = ret;
     ret = 0;
     return ret;
@@ -804,7 +810,7 @@ static void nfs_refresh_filename(BlockDriverState *bs, QDict *options)
     QObject *server_qdict;
     Visitor *ov;
 
-    qdict_put(opts, "driver", qstring_from_str("nfs"));
+    qdict_put_str(opts, "driver", "nfs");
 
     if (client->uid && !client->gid) {
         snprintf(bs->exact_filename, sizeof(bs->exact_filename),
@@ -827,28 +833,25 @@ static void nfs_refresh_filename(BlockDriverState *bs, QDict *options)
     visit_type_NFSServer(ov, NULL, &client->server, &error_abort);
     visit_complete(ov, &server_qdict);
     qdict_put_obj(opts, "server", server_qdict);
-    qdict_put(opts, "path", qstring_from_str(client->path));
+    qdict_put_str(opts, "path", client->path);
 
     if (client->uid) {
-        qdict_put(opts, "user", qint_from_int(client->uid));
+        qdict_put_int(opts, "user", client->uid);
     }
     if (client->gid) {
-        qdict_put(opts, "group", qint_from_int(client->gid));
+        qdict_put_int(opts, "group", client->gid);
     }
     if (client->tcp_syncnt) {
-        qdict_put(opts, "tcp-syn-cnt",
-                  qint_from_int(client->tcp_syncnt));
+        qdict_put_int(opts, "tcp-syn-cnt", client->tcp_syncnt);
     }
     if (client->readahead) {
-        qdict_put(opts, "readahead-size",
-                  qint_from_int(client->readahead));
+        qdict_put_int(opts, "readahead-size", client->readahead);
     }
     if (client->pagecache) {
-        qdict_put(opts, "page-cache-size",
-                  qint_from_int(client->pagecache));
+        qdict_put_int(opts, "page-cache-size", client->pagecache);
     }
     if (client->debug) {
-        qdict_put(opts, "debug", qint_from_int(client->debug));
+        qdict_put_int(opts, "debug", client->debug);
     }
 
     visit_free(ov);

block/null.c

@@ -232,7 +232,7 @@ static void null_refresh_filename(BlockDriverState *bs, QDict *opts)
                  bs->drv->format_name);
     }
 
-    qdict_put(opts, "driver", qstring_from_str(bs->drv->format_name));
+    qdict_put_str(opts, "driver", bs->drv->format_name);
     bs->full_open_options = opts;
 }
 

block/parallels.c

@@ -192,8 +192,7 @@ static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num,
                                  int nb_sectors, int *pnum)
 {
     BDRVParallelsState *s = bs->opaque;
-    uint32_t idx, to_allocate, i;
-    int64_t pos, space;
+    int64_t pos, space, idx, to_allocate, i;
 
     pos = block_status(s, sector_num, nb_sectors, pnum);
     if (pos > 0) {
@@ -201,11 +200,19 @@ static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num,
     }
 
     idx = sector_num / s->tracks;
-    if (idx >= s->bat_size) {
-        return -EINVAL;
-    }
-
     to_allocate = DIV_ROUND_UP(sector_num + *pnum, s->tracks) - idx;
+
+    /* This function is called only by parallels_co_writev(), which will never
+     * pass a sector_num at or beyond the end of the image (because the block
+     * layer never passes such a sector_num to that function). Therefore, idx
+     * is always below s->bat_size.
+     * block_status() will limit *pnum so that sector_num + *pnum will not
+     * exceed the image end. Therefore, idx + to_allocate cannot exceed
+     * s->bat_size.
+     * Note that s->bat_size is an unsigned int, therefore idx + to_allocate
+     * will always fit into a uint32_t. */
+    assert(idx < s->bat_size && idx + to_allocate <= s->bat_size);
+
     space = to_allocate * s->tracks;
     if (s->data_end + space > bdrv_getlength(bs->file->bs) >> BDRV_SECTOR_BITS) {
         int ret;
@@ -216,7 +223,8 @@ static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num,
                                      space << BDRV_SECTOR_BITS, 0);
         } else {
             ret = bdrv_truncate(bs->file,
-                                (s->data_end + space) << BDRV_SECTOR_BITS);
+                                (s->data_end + space) << BDRV_SECTOR_BITS,
+                                NULL);
         }
         if (ret < 0) {
             return ret;
@@ -449,8 +457,10 @@ static int parallels_check(BlockDriverState *bs, BdrvCheckResult *res,
                 size - res->image_end_offset);
         res->leaks += count;
         if (fix & BDRV_FIX_LEAKS) {
-            ret = bdrv_truncate(bs->file, res->image_end_offset);
+            Error *local_err = NULL;
+            ret = bdrv_truncate(bs->file, res->image_end_offset, &local_err);
             if (ret < 0) {
+                error_report_err(local_err);
                 res->check_errors++;
                 return ret;
             }
@@ -497,7 +507,7 @@ static int parallels_create(const char *filename, QemuOpts *opts, Error **errp)
 
     blk_set_allow_write_beyond_eof(file, true);
 
-    ret = blk_truncate(file, 0);
+    ret = blk_truncate(file, 0, errp);
     if (ret < 0) {
         goto exit;
     }
@@ -689,7 +699,7 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     if (!(flags & BDRV_O_RESIZE) || !bdrv_has_zero_init(bs->file->bs) ||
-            bdrv_truncate(bs->file, bdrv_getlength(bs->file->bs)) != 0) {
+            bdrv_truncate(bs->file, bdrv_getlength(bs->file->bs), NULL) != 0) {
         s->prealloc_mode = PRL_PREALLOC_MODE_FALLOCATE;
     }
 
@@ -732,7 +742,7 @@ static void parallels_close(BlockDriverState *bs)
     }
 
     if (bs->open_flags & BDRV_O_RDWR) {
-        bdrv_truncate(bs->file, s->data_end << BDRV_SECTOR_BITS);
+        bdrv_truncate(bs->file, s->data_end << BDRV_SECTOR_BITS, NULL);
     }
 
     g_free(s->bat_dirty_bmap);

block/qapi.c

@@ -64,7 +64,6 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
         info->backing_file = g_strdup(bs->backing_file);
     }
 
-    info->backing_file_depth = bdrv_get_backing_file_depth(bs);
     info->detect_zeroes = bs->detect_zeroes;
 
     if (blk && blk_get_public(blk)->throttle_state) {
@@ -125,6 +124,7 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
 
     bs0 = bs;
     p_image_info = &info->image;
+    info->backing_file_depth = 0;
     while (1) {
         Error *local_err = NULL;
         bdrv_query_image_info(bs0, p_image_info, &local_err);
@@ -133,13 +133,21 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
             qapi_free_BlockDeviceInfo(info);
             return NULL;
         }
+
         if (bs0->drv && bs0->backing) {
+            info->backing_file_depth++;
             bs0 = bs0->backing->bs;
             (*p_image_info)->has_backing_image = true;
             p_image_info = &((*p_image_info)->backing_image);
         } else {
             break;
         }
+
+        /* Skip automatically inserted nodes that the user isn't aware of for
+         * query-block (blk != NULL), but not for query-named-block-nodes */
+        while (blk && bs0 && bs0->drv && bs0->implicit) {
+            bs0 = backing_bs(bs0);
+        }
     }
 
     return info;
@@ -322,6 +330,12 @@ static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
 {
     BlockInfo *info = g_malloc0(sizeof(*info));
     BlockDriverState *bs = blk_bs(blk);
+
+    /* Skip automatically inserted nodes that the user isn't aware of */
+    while (bs && bs->drv && bs->implicit) {
+        bs = backing_bs(bs);
+    }
+
     info->device = g_strdup(blk_name(blk));
     info->type = g_strdup("unknown");
     info->locked = blk_dev_is_medium_locked(blk);
@@ -424,8 +438,8 @@ static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk)
     }
 }
 
-static BlockStats *bdrv_query_bds_stats(const BlockDriverState *bs,
-                                 bool query_backing)
+static BlockStats *bdrv_query_bds_stats(BlockDriverState *bs,
+                                        bool blk_level)
 {
     BlockStats *s = NULL;
 
@@ -436,6 +450,14 @@ static BlockStats *bdrv_query_bds_stats(const BlockDriverState *bs,
         return s;
     }
 
+    /* Skip automatically inserted nodes that the user isn't aware of in
+     * a BlockBackend-level command. Stay at the exact node for a node-level
+     * command. */
+    while (blk_level && bs->drv && bs->implicit) {
+        bs = backing_bs(bs);
+        assert(bs);
+    }
+
     if (bdrv_get_node_name(bs)[0]) {
         s->has_node_name = true;
         s->node_name = g_strdup(bdrv_get_node_name(bs));
@@ -445,12 +467,12 @@ static BlockStats *bdrv_query_bds_stats(const BlockDriverState *bs,
 
     if (bs->file) {
         s->has_parent = true;
-        s->parent = bdrv_query_bds_stats(bs->file->bs, query_backing);
+        s->parent = bdrv_query_bds_stats(bs->file->bs, blk_level);
     }
 
-    if (query_backing && bs->backing) {
+    if (blk_level && bs->backing) {
         s->has_backing = true;
-        s->backing = bdrv_query_bds_stats(bs->backing->bs, query_backing);
+        s->backing = bdrv_query_bds_stats(bs->backing->bs, blk_level);
     }
 
     return s;

block/qcow.c

@@ -473,7 +473,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
                 /* round to cluster size */
                 cluster_offset = (cluster_offset + s->cluster_size - 1) &
                     ~(s->cluster_size - 1);
-                bdrv_truncate(bs->file, cluster_offset + s->cluster_size);
+                bdrv_truncate(bs->file, cluster_offset + s->cluster_size, NULL);
                 /* if encrypted, we must initialize the cluster
                    content which won't be written */
                 if (bs->encrypted &&
@@ -833,7 +833,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
 
     blk_set_allow_write_beyond_eof(qcow_blk, true);
 
-    ret = blk_truncate(qcow_blk, 0);
+    ret = blk_truncate(qcow_blk, 0, errp);
     if (ret < 0) {
         goto exit;
     }
@@ -916,7 +916,7 @@ static int qcow_make_empty(BlockDriverState *bs)
     if (bdrv_pwrite_sync(bs->file, s->l1_table_offset, s->l1_table,
             l1_length) < 0)
         return -1;
-    ret = bdrv_truncate(bs->file, s->l1_table_offset + l1_length);
+    ret = bdrv_truncate(bs->file, s->l1_table_offset + l1_length, NULL);
     if (ret < 0)
         return ret;
 

block/qcow2-cluster.c

@@ -1519,12 +1519,10 @@ int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
 
     end_offset = offset + (nb_sectors << BDRV_SECTOR_BITS);
 
-    /* Round start up and end down */
-    offset = align_offset(offset, s->cluster_size);
-    end_offset = start_of_cluster(s, end_offset);
-
-    if (offset > end_offset) {
-        return 0;
+    /* The caller must cluster-align start; round end down except at EOF */
+    assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
+    if (end_offset != bs->total_sectors * BDRV_SECTOR_SIZE) {
+        end_offset = start_of_cluster(s, end_offset);
     }
 
     nb_clusters = size_to_clusters(s, end_offset - offset);

block/qcow2-refcount.c

@@ -1728,14 +1728,17 @@ static int check_refblocks(BlockDriverState *bs, BdrvCheckResult *res,
 
             if (fix & BDRV_FIX_ERRORS) {
                 int64_t new_nb_clusters;
+                Error *local_err = NULL;
 
                 if (offset > INT64_MAX - s->cluster_size) {
                     ret = -EINVAL;
                     goto resize_fail;
                 }
 
-                ret = bdrv_truncate(bs->file, offset + s->cluster_size);
+                ret = bdrv_truncate(bs->file, offset + s->cluster_size,
+                                    &local_err);
                 if (ret < 0) {
+                    error_report_err(local_err);
                     goto resize_fail;
                 }
                 size = bdrv_getlength(bs->file->bs);

block/qcow2.c

@@ -2265,7 +2265,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
      * table)
      */
     options = qdict_new();
-    qdict_put(options, "driver", qstring_from_str("qcow2"));
+    qdict_put_str(options, "driver", "qcow2");
     blk = blk_new_open(filename, NULL, options,
                        BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_NO_FLUSH,
                        &local_err);
@@ -2294,9 +2294,9 @@ static int qcow2_create2(const char *filename, int64_t total_size,
     }
 
     /* Okay, now that we have a valid image, let's give it the right size */
-    ret = blk_truncate(blk, total_size);
+    ret = blk_truncate(blk, total_size, errp);
     if (ret < 0) {
-        error_setg_errno(errp, -ret, "Could not resize image");
+        error_prepend(errp, "Could not resize image: ");
         goto out;
     }
 
@@ -2327,7 +2327,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
 
     /* Reopen the image without BDRV_O_NO_FLUSH to flush it before returning */
     options = qdict_new();
-    qdict_put(options, "driver", qstring_from_str("qcow2"));
+    qdict_put_str(options, "driver", "qcow2");
     blk = blk_new_open(filename, NULL, options,
                        BDRV_O_RDWR | BDRV_O_NO_BACKING, &local_err);
     if (blk == NULL) {
@@ -2584,7 +2584,7 @@ qcow2_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset,
         /* align end of file to a sector boundary to ease reading with
            sector based I/Os */
         cluster_offset = bdrv_getlength(bs->file->bs);
-        return bdrv_truncate(bs->file, cluster_offset);
+        return bdrv_truncate(bs->file, cluster_offset, NULL);
     }
 
     buf = qemu_blockalign(bs, s->cluster_size);
@@ -2674,6 +2674,7 @@ fail:
 static int make_completely_empty(BlockDriverState *bs)
 {
     BDRVQcow2State *s = bs->opaque;
+    Error *local_err = NULL;
     int ret, l1_clusters;
     int64_t offset;
     uint64_t *new_reftable = NULL;
@@ -2798,8 +2799,10 @@ static int make_completely_empty(BlockDriverState *bs)
         goto fail;
     }
 
-    ret = bdrv_truncate(bs->file, (3 + l1_clusters) * s->cluster_size);
+    ret = bdrv_truncate(bs->file, (3 + l1_clusters) * s->cluster_size,
+                        &local_err);
     if (ret < 0) {
+        error_report_err(local_err);
         goto fail;
     }
 
@@ -3273,9 +3276,10 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
             return ret;
         }
 
-        ret = blk_truncate(blk, new_size);
+        ret = blk_truncate(blk, new_size, &local_err);
         blk_unref(blk);
         if (ret < 0) {
+            error_report_err(local_err);
             return ret;
         }
     }

block/qed.c

@@ -635,7 +635,7 @@ static int qed_create(const char *filename, uint32_t cluster_size,
     blk_set_allow_write_beyond_eof(blk, true);
 
     /* File must start empty and grow, check truncate is supported */
-    ret = blk_truncate(blk, 0);
+    ret = blk_truncate(blk, 0, errp);
     if (ret < 0) {
         goto out;
     }

block/quorum.c

@@ -1096,19 +1096,15 @@ static void quorum_refresh_filename(BlockDriverState *bs, QDict *options)
     children = qlist_new();
     for (i = 0; i < s->num_children; i++) {
         QINCREF(s->children[i]->bs->full_open_options);
-        qlist_append_obj(children,
-                         QOBJECT(s->children[i]->bs->full_open_options));
+        qlist_append(children, s->children[i]->bs->full_open_options);
     }
 
     opts = qdict_new();
-    qdict_put_obj(opts, "driver", QOBJECT(qstring_from_str("quorum")));
-    qdict_put_obj(opts, QUORUM_OPT_VOTE_THRESHOLD,
-                  QOBJECT(qint_from_int(s->threshold)));
-    qdict_put_obj(opts, QUORUM_OPT_BLKVERIFY,
-                  QOBJECT(qbool_from_bool(s->is_blkverify)));
-    qdict_put_obj(opts, QUORUM_OPT_REWRITE,
-                  QOBJECT(qbool_from_bool(s->rewrite_corrupted)));
-    qdict_put_obj(opts, "children", QOBJECT(children));
+    qdict_put_str(opts, "driver", "quorum");
+    qdict_put_int(opts, QUORUM_OPT_VOTE_THRESHOLD, s->threshold);
+    qdict_put_bool(opts, QUORUM_OPT_BLKVERIFY, s->is_blkverify);
+    qdict_put_bool(opts, QUORUM_OPT_REWRITE, s->rewrite_corrupted);
+    qdict_put(opts, "children", children);
 
     bs->full_open_options = opts;
 }

block/raw-format.c

@@ -341,7 +341,7 @@ static int raw_truncate(BlockDriverState *bs, int64_t offset)
 
     s->size = offset;
     offset += s->offset;
-    return bdrv_truncate(bs->file, offset);
+    return bdrv_truncate(bs->file, offset, NULL);
 }
 
 static int raw_media_changed(BlockDriverState *bs)

block/rbd.c

@@ -20,6 +20,7 @@
 #include "crypto/secret.h"
 #include "qemu/cutils.h"
 #include "qapi/qmp/qstring.h"
+#include "qapi/qmp/qjson.h"
 
 /*
  * When specifying the image filename use:
@@ -135,18 +136,16 @@ static void qemu_rbd_parse_filename(const char *filename, QDict *options,
                                     Error **errp)
 {
     const char *start;
-    char *p, *buf, *keypairs;
+    char *p, *buf;
+    QList *keypairs = NULL;
     char *found_str;
-    size_t max_keypair_size;
 
     if (!strstart(filename, "rbd:", &start)) {
         error_setg(errp, "File name must start with 'rbd:'");
         return;
     }
 
-    max_keypair_size = strlen(start) + 1;
     buf = g_strdup(start);
-    keypairs = g_malloc0(max_keypair_size);
     p = buf;
 
     found_str = qemu_rbd_next_tok(p, '/', &p);
@@ -155,20 +154,20 @@ static void qemu_rbd_parse_filename(const char *filename, QDict *options,
         goto done;
     }
     qemu_rbd_unescape(found_str);
-    qdict_put(options, "pool", qstring_from_str(found_str));
+    qdict_put_str(options, "pool", found_str);
 
     if (strchr(p, '@')) {
         found_str = qemu_rbd_next_tok(p, '@', &p);
         qemu_rbd_unescape(found_str);
-        qdict_put(options, "image", qstring_from_str(found_str));
+        qdict_put_str(options, "image", found_str);
 
         found_str = qemu_rbd_next_tok(p, ':', &p);
         qemu_rbd_unescape(found_str);
-        qdict_put(options, "snapshot", qstring_from_str(found_str));
+        qdict_put_str(options, "snapshot", found_str);
     } else {
         found_str = qemu_rbd_next_tok(p, ':', &p);
         qemu_rbd_unescape(found_str);
-        qdict_put(options, "image", qstring_from_str(found_str));
+        qdict_put_str(options, "image", found_str);
     }
     if (!p) {
         goto done;
@@ -190,37 +189,34 @@ static void qemu_rbd_parse_filename(const char *filename, QDict *options,
         qemu_rbd_unescape(value);
 
         if (!strcmp(name, "conf")) {
-            qdict_put(options, "conf", qstring_from_str(value));
+            qdict_put_str(options, "conf", value);
         } else if (!strcmp(name, "id")) {
-            qdict_put(options, "user" , qstring_from_str(value));
+            qdict_put_str(options, "user", value);
         } else {
-            /* FIXME: This is pretty ugly, and not the right way to do this.
-             *        These should be contained in a structure, and then
-             *        passed explicitly as individual key/value pairs to
-             *        rados.  Consider this legacy code that needs to be
-             *        updated. */
-            char *tmp = g_malloc0(max_keypair_size);
-            /* only use a delimiter if it is not the first keypair found */
-            /* These are sets of unknown key/value pairs we'll pass along
-             * to ceph */
-            if (keypairs[0]) {
-                snprintf(tmp, max_keypair_size, ":%s=%s", name, value);
-                pstrcat(keypairs, max_keypair_size, tmp);
-            } else {
-                snprintf(keypairs, max_keypair_size, "%s=%s", name, value);
+            /*
+             * We pass these internally to qemu_rbd_set_keypairs(), so
+             * we can get away with the simpler list of [ "key1",
+             * "value1", "key2", "value2" ] rather than a raw dict
+             * { "key1": "value1", "key2": "value2" } where we can't
+             * guarantee order, or even a more correct but complex
+             * [ { "key1": "value1" }, { "key2": "value2" } ]
+             */
+            if (!keypairs) {
+                keypairs = qlist_new();
             }
-            g_free(tmp);
+            qlist_append_str(keypairs, name);
+            qlist_append_str(keypairs, value);
         }
     }
 
-    if (keypairs[0]) {
-        qdict_put(options, "=keyvalue-pairs", qstring_from_str(keypairs));
+    if (keypairs) {
+        qdict_put(options, "=keyvalue-pairs",
+                  qobject_to_json(QOBJECT(keypairs)));
     }
 
-
 done:
     g_free(buf);
-    g_free(keypairs);
+    QDECREF(keypairs);
     return;
 }
 
@@ -244,36 +240,41 @@ static int qemu_rbd_set_auth(rados_t cluster, const char *secretid,
     return 0;
 }
 
-static int qemu_rbd_set_keypairs(rados_t cluster, const char *keypairs,
+static int qemu_rbd_set_keypairs(rados_t cluster, const char *keypairs_json,
                                  Error **errp)
 {
-    char *p, *buf;
-    char *name;
-    char *value;
+    QList *keypairs;
+    QString *name;
+    QString *value;
+    const char *key;
+    size_t remaining;
     int ret = 0;
 
-    buf = g_strdup(keypairs);
-    p = buf;
+    if (!keypairs_json) {
+        return ret;
+    }
+    keypairs = qobject_to_qlist(qobject_from_json(keypairs_json,
+                                                  &error_abort));
+    remaining = qlist_size(keypairs) / 2;
+    assert(remaining);
 
-    while (p) {
-        name = qemu_rbd_next_tok(p, '=', &p);
-        if (!p) {
-            error_setg(errp, "conf option %s has no value", name);
-            ret = -EINVAL;
-            break;
-        }
+    while (remaining--) {
+        name = qobject_to_qstring(qlist_pop(keypairs));
+        value = qobject_to_qstring(qlist_pop(keypairs));
+        assert(name && value);
+        key = qstring_get_str(name);
 
-        value = qemu_rbd_next_tok(p, ':', &p);
-
-        ret = rados_conf_set(cluster, name, value);
+        ret = rados_conf_set(cluster, key, qstring_get_str(value));
+        QDECREF(name);
+        QDECREF(value);
         if (ret < 0) {
-            error_setg_errno(errp, -ret, "invalid conf option %s", name);
+            error_setg_errno(errp, -ret, "invalid conf option %s", key);
             ret = -EINVAL;
             break;
         }
     }
 
-    g_free(buf);
+    QDECREF(keypairs);
     return ret;
 }
 
@@ -384,6 +385,12 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
         goto exit;
     }
 
+    /*
+     * Caution: while qdict_get_try_str() is fine, getting non-string
+     * types would require more care.  When @options come from -blockdev
+     * or blockdev_add, its members are typed according to the QAPI
+     * schema, but when they come from -drive, they're all QString.
+     */
     pool       = qdict_get_try_str(options, "pool");
     conf       = qdict_get_try_str(options, "conf");
     clientname = qdict_get_try_str(options, "user");

block/sheepdog.c

@@ -13,9 +13,11 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi-visit.h"
 #include "qapi/error.h"
 #include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qint.h"
+#include "qapi/qobject-input-visitor.h"
 #include "qemu/uri.h"
 #include "qemu/error-report.h"
 #include "qemu/sockets.h"
@@ -547,6 +549,47 @@ static SocketAddress *sd_socket_address(const char *path,
     return addr;
 }
 
+static SocketAddress *sd_server_config(QDict *options, Error **errp)
+{
+    QDict *server = NULL;
+    QObject *crumpled_server = NULL;
+    Visitor *iv = NULL;
+    SocketAddressFlat *saddr_flat = NULL;
+    SocketAddress *saddr = NULL;
+    Error *local_err = NULL;
+
+    qdict_extract_subqdict(options, &server, "server.");
+
+    crumpled_server = qdict_crumple(server, errp);
+    if (!crumpled_server) {
+        goto done;
+    }
+
+    /*
+     * FIXME .numeric, .to, .ipv4 or .ipv6 don't work with -drive
+     * server.type=inet.  .to doesn't matter, it's ignored anyway.
+     * That's because when @options come from -blockdev or
+     * blockdev_add, members are typed according to the QAPI schema,
+     * but when they come from -drive, they're all QString.  The
+     * visitor expects the former.
+     */
+    iv = qobject_input_visitor_new(crumpled_server);
+    visit_type_SocketAddressFlat(iv, NULL, &saddr_flat, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        goto done;
+    }
+
+    saddr = socket_address_crumple(saddr_flat);
+
+done:
+    qapi_free_SocketAddressFlat(saddr_flat);
+    visit_free(iv);
+    qobject_decref(crumpled_server);
+    QDECREF(server);
+    return saddr;
+}
+
 /* Return -EIO in case of error, file descriptor on success */
 static int connect_to_sdog(BDRVSheepdogState *s, Error **errp)
 {
@@ -693,7 +736,7 @@ static int do_req(int sockfd, BlockDriverState *bs, SheepdogReq *hdr,
     } else {
         co = qemu_coroutine_create(do_co_req, &srco);
         if (bs) {
-            qemu_coroutine_enter(co);
+            bdrv_coroutine_enter(bs, co);
             BDRV_POLL_WHILE(bs, !srco.finished);
         } else {
             qemu_coroutine_enter(co);
@@ -899,7 +942,7 @@ static void co_read_response(void *opaque)
         s->co_recv = qemu_coroutine_create(aio_read_response, opaque);
     }
 
-    aio_co_wake(s->co_recv);
+    aio_co_enter(s->aio_context, s->co_recv);
 }
 
 static void co_write_request(void *opaque)
@@ -1009,11 +1052,11 @@ static void sd_parse_uri(SheepdogConfig *cfg, const char *filename,
     }
 
     /* transport */
-    if (!strcmp(uri->scheme, "sheepdog")) {
+    if (!g_strcmp0(uri->scheme, "sheepdog")) {
         is_unix = false;
-    } else if (!strcmp(uri->scheme, "sheepdog+tcp")) {
+    } else if (!g_strcmp0(uri->scheme, "sheepdog+tcp")) {
         is_unix = false;
-    } else if (!strcmp(uri->scheme, "sheepdog+unix")) {
+    } else if (!g_strcmp0(uri->scheme, "sheepdog+unix")) {
         is_unix = true;
     } else {
         error_setg(&err, "URI scheme must be 'sheepdog', 'sheepdog+tcp',"
@@ -1174,15 +1217,15 @@ static void sd_parse_filename(const char *filename, QDict *options,
         return;
     }
 
-    if (cfg.host) {
-        qdict_set_default_str(options, "host", cfg.host);
-    }
-    if (cfg.port) {
-        snprintf(buf, sizeof(buf), "%d", cfg.port);
-        qdict_set_default_str(options, "port", buf);
-    }
     if (cfg.path) {
-        qdict_set_default_str(options, "path", cfg.path);
+        qdict_set_default_str(options, "server.path", cfg.path);
+        qdict_set_default_str(options, "server.type", "unix");
+    } else {
+        qdict_set_default_str(options, "server.type", "inet");
+        qdict_set_default_str(options, "server.host",
+                              cfg.host ?: SD_DEFAULT_ADDR);
+        snprintf(buf, sizeof(buf), "%d", cfg.port ?: SD_DEFAULT_PORT);
+        qdict_set_default_str(options, "server.port", buf);
     }
     qdict_set_default_str(options, "vdi", cfg.vdi);
     qdict_set_default_str(options, "tag", cfg.tag);
@@ -1509,18 +1552,6 @@ static QemuOptsList runtime_opts = {
     .name = "sheepdog",
     .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
     .desc = {
-        {
-            .name = "host",
-            .type = QEMU_OPT_STRING,
-        },
-        {
-            .name = "port",
-            .type = QEMU_OPT_STRING,
-        },
-        {
-            .name = "path",
-            .type = QEMU_OPT_STRING,
-        },
         {
             .name = "vdi",
             .type = QEMU_OPT_STRING,
@@ -1543,7 +1574,7 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags,
     int ret, fd;
     uint32_t vid = 0;
     BDRVSheepdogState *s = bs->opaque;
-    const char *host, *port, *path, *vdi, *snap_id_str, *tag;
+    const char *vdi, *snap_id_str, *tag;
     uint64_t snap_id;
     char *buf = NULL;
     QemuOpts *opts;
@@ -1560,20 +1591,17 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags,
         goto err_no_fd;
     }
 
-    host = qemu_opt_get(opts, "host");
-    port = qemu_opt_get(opts, "port");
-    path = qemu_opt_get(opts, "path");
+    s->addr = sd_server_config(options, errp);
+    if (!s->addr) {
+        ret = -EINVAL;
+        goto err_no_fd;
+    }
+
     vdi = qemu_opt_get(opts, "vdi");
     snap_id_str = qemu_opt_get(opts, "snap-id");
     snap_id = qemu_opt_get_number(opts, "snap-id", CURRENT_VDI_ID);
     tag = qemu_opt_get(opts, "tag");
 
-    if ((host || port) && path) {
-        error_setg(errp, "can't use 'path' together with 'host' or 'port'");
-        ret = -EINVAL;
-        goto err_no_fd;
-    }
-
     if (!vdi) {
         error_setg(errp, "parameter 'vdi' is missing");
         ret = -EINVAL;
@@ -1604,8 +1632,6 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags,
         goto err_no_fd;
     }
 
-    s->addr = sd_socket_address(path, host, port);
-
     QLIST_INIT(&s->inflight_aio_head);
     QLIST_INIT(&s->failed_aio_head);
     QLIST_INIT(&s->inflight_aiocb_head);

block/snapshot.c

@@ -27,6 +27,7 @@
 #include "block/block_int.h"
 #include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
+#include "qapi/qmp/qstring.h"
 
 QemuOptsList internal_snapshot_opts = {
     .name = "snapshot",
@@ -189,14 +190,33 @@ int bdrv_snapshot_goto(BlockDriverState *bs,
     }
 
     if (bs->file) {
+        BlockDriverState *file;
+        QDict *options = qdict_clone_shallow(bs->options);
+        QDict *file_options;
+
+        file = bs->file->bs;
+        /* Prevent it from getting deleted when detached from bs */
+        bdrv_ref(file);
+
+        qdict_extract_subqdict(options, &file_options, "file.");
+        QDECREF(file_options);
+        qdict_put_str(options, "file", bdrv_get_node_name(file));
+
         drv->bdrv_close(bs);
-        ret = bdrv_snapshot_goto(bs->file->bs, snapshot_id);
-        open_ret = drv->bdrv_open(bs, NULL, bs->open_flags, NULL);
+        bdrv_unref_child(bs, bs->file);
+        bs->file = NULL;
+
+        ret = bdrv_snapshot_goto(file, snapshot_id);
+        open_ret = drv->bdrv_open(bs, options, bs->open_flags, NULL);
+        QDECREF(options);
         if (open_ret < 0) {
-            bdrv_unref(bs->file->bs);
+            bdrv_unref(file);
             bs->drv = NULL;
             return open_ret;
         }
+
+        assert(bs->file->bs == file);
+        bdrv_unref(file);
         return ret;
     }
 

block/ssh.c

@@ -205,7 +205,7 @@ static int parse_uri(const char *filename, QDict *options, Error **errp)
         return -EINVAL;
     }
 
-    if (strcmp(uri->scheme, "ssh") != 0) {
+    if (g_strcmp0(uri->scheme, "ssh") != 0) {
         error_setg(errp, "URI scheme must be 'ssh'");
         goto err;
     }
@@ -227,24 +227,23 @@ static int parse_uri(const char *filename, QDict *options, Error **errp)
     }
 
     if(uri->user && strcmp(uri->user, "") != 0) {
-        qdict_put(options, "user", qstring_from_str(uri->user));
+        qdict_put_str(options, "user", uri->user);
     }
 
-    qdict_put(options, "server.host", qstring_from_str(uri->server));
+    qdict_put_str(options, "server.host", uri->server);
 
     port_str = g_strdup_printf("%d", uri->port ?: 22);
-    qdict_put(options, "server.port", qstring_from_str(port_str));
+    qdict_put_str(options, "server.port", port_str);
     g_free(port_str);
 
-    qdict_put(options, "path", qstring_from_str(uri->path));
+    qdict_put_str(options, "path", uri->path);
 
     /* Pick out any query parameters that we understand, and ignore
      * the rest.
      */
     for (i = 0; i < qp->n; ++i) {
         if (strcmp(qp->p[i].name, "host_key_check") == 0) {
-            qdict_put(options, "host_key_check",
-                      qstring_from_str(qp->p[i].value));
+            qdict_put_str(options, "host_key_check", qp->p[i].value);
         }
     }
 
@@ -574,9 +573,8 @@ static bool ssh_process_legacy_socket_options(QDict *output_opts,
     }
 
     if (host) {
-        qdict_put(output_opts, "server.host", qstring_from_str(host));
-        qdict_put(output_opts, "server.port",
-                  qstring_from_str(port ?: stringify(22)));
+        qdict_put_str(output_opts, "server.host", host);
+        qdict_put_str(output_opts, "server.port", port ?: stringify(22));
     }
 
     return true;
@@ -601,6 +599,14 @@ static InetSocketAddress *ssh_config(QDict *options, Error **errp)
         goto out;
     }
 
+    /*
+     * FIXME .numeric, .to, .ipv4 or .ipv6 don't work with -drive.
+     * .to doesn't matter, it's ignored anyway.
+     * That's because when @options come from -blockdev or
+     * blockdev_add, members are typed according to the QAPI schema,
+     * but when they come from -drive, they're all QString.  The
+     * visitor expects the former.
+     */
     iv = qobject_input_visitor_new(crumpled_addr);
     visit_type_InetSocketAddress(iv, NULL, &inet, &local_error);
     if (local_error) {

block/stream.c

@@ -280,6 +280,6 @@ void stream_start(const char *job_id, BlockDriverState *bs,
 
 fail:
     if (orig_bs_flags != bdrv_get_flags(bs)) {
-        bdrv_reopen(bs, s->bs_flags, NULL);
+        bdrv_reopen(bs, orig_bs_flags, NULL);
     }
 }

block/vdi.c

@@ -832,9 +832,9 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     if (image_type == VDI_TYPE_STATIC) {
-        ret = blk_truncate(blk, offset + blocks * block_size);
+        ret = blk_truncate(blk, offset + blocks * block_size, errp);
         if (ret < 0) {
-            error_setg(errp, "Failed to statically allocate %s", filename);
+            error_prepend(errp, "Failed to statically allocate %s", filename);
             goto exit;
         }
     }

block/vhdx-log.c

@@ -548,7 +548,7 @@ static int vhdx_log_flush(BlockDriverState *bs, BDRVVHDXState *s,
             if (new_file_size % (1024*1024)) {
                 /* round up to nearest 1MB boundary */
                 new_file_size = ((new_file_size >> 20) + 1) << 20;
-                bdrv_truncate(bs->file, new_file_size);
+                bdrv_truncate(bs->file, new_file_size, NULL);
             }
         }
         qemu_vfree(desc_entries);

block/vhdx.c

@@ -1171,7 +1171,7 @@ static int vhdx_allocate_block(BlockDriverState *bs, BDRVVHDXState *s,
     /* per the spec, the address for a block is in units of 1MB */
     *new_offset = ROUND_UP(*new_offset, 1024 * 1024);
 
-    return bdrv_truncate(bs->file, *new_offset + s->block_size);
+    return bdrv_truncate(bs->file, *new_offset + s->block_size, NULL);
 }
 
 /*
@@ -1586,7 +1586,7 @@ exit:
 static int vhdx_create_bat(BlockBackend *blk, BDRVVHDXState *s,
                            uint64_t image_size, VHDXImageType type,
                            bool use_zero_blocks, uint64_t file_offset,
-                           uint32_t length)
+                           uint32_t length, Error **errp)
 {
     int ret = 0;
     uint64_t data_file_offset;
@@ -1607,16 +1607,21 @@ static int vhdx_create_bat(BlockBackend *blk, BDRVVHDXState *s,
     if (type == VHDX_TYPE_DYNAMIC) {
         /* All zeroes, so we can just extend the file - the end of the BAT
          * is the furthest thing we have written yet */
-        ret = blk_truncate(blk, data_file_offset);
+        ret = blk_truncate(blk, data_file_offset, errp);
         if (ret < 0) {
+            error_setg_errno(errp, -ret,
+                            "Failed to resize the underlying file");
             goto exit;
         }
     } else if (type == VHDX_TYPE_FIXED) {
-        ret = blk_truncate(blk, data_file_offset + image_size);
+        ret = blk_truncate(blk, data_file_offset + image_size, errp);
         if (ret < 0) {
+            error_setg_errno(errp, -ret,
+                            "Failed to resize the underlying file");
             goto exit;
         }
     } else {
+        error_setg(errp, "Unsupported image type");
         ret = -ENOTSUP;
         goto exit;
     }
@@ -1627,6 +1632,7 @@ static int vhdx_create_bat(BlockBackend *blk, BDRVVHDXState *s,
         /* for a fixed file, the default BAT entry is not zero */
         s->bat = g_try_malloc0(length);
         if (length && s->bat == NULL) {
+            error_setg(errp, "Failed to allocate memory for the BAT");
             ret = -ENOMEM;
             goto exit;
         }
@@ -1646,6 +1652,7 @@ static int vhdx_create_bat(BlockBackend *blk, BDRVVHDXState *s,
         }
         ret = blk_pwrite(blk, file_offset, s->bat, length, 0);
         if (ret < 0) {
+            error_setg_errno(errp, -ret, "Failed to write the BAT");
             goto exit;
         }
     }
@@ -1671,7 +1678,8 @@ static int vhdx_create_new_region_table(BlockBackend *blk,
                                         uint32_t log_size,
                                         bool use_zero_blocks,
                                         VHDXImageType type,
-                                        uint64_t *metadata_offset)
+                                        uint64_t *metadata_offset,
+                                        Error **errp)
 {
     int ret = 0;
     uint32_t offset = 0;
@@ -1740,7 +1748,7 @@ static int vhdx_create_new_region_table(BlockBackend *blk,
     /* The region table gives us the data we need to create the BAT,
      * so do that now */
     ret = vhdx_create_bat(blk, s, image_size, type, use_zero_blocks,
-                          bat_file_offset, bat_length);
+                          bat_file_offset, bat_length, errp);
     if (ret < 0) {
         goto exit;
     }
@@ -1749,12 +1757,14 @@ static int vhdx_create_new_region_table(BlockBackend *blk,
     ret = blk_pwrite(blk, VHDX_REGION_TABLE_OFFSET, buffer,
                      VHDX_HEADER_BLOCK_SIZE, 0);
     if (ret < 0) {
+        error_setg_errno(errp, -ret, "Failed to write first region table");
         goto exit;
     }
 
     ret = blk_pwrite(blk, VHDX_REGION_TABLE2_OFFSET, buffer,
                      VHDX_HEADER_BLOCK_SIZE, 0);
     if (ret < 0) {
+        error_setg_errno(errp, -ret, "Failed to write second region table");
         goto exit;
     }
 
@@ -1825,6 +1835,7 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
         ret = -ENOTSUP;
         goto exit;
     } else {
+        error_setg(errp, "Invalid subformat '%s'", type);
         ret = -EINVAL;
         goto exit;
     }
@@ -1879,12 +1890,14 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
     ret = blk_pwrite(blk, VHDX_FILE_ID_OFFSET, &signature, sizeof(signature),
                      0);
     if (ret < 0) {
+        error_setg_errno(errp, -ret, "Failed to write file signature");
         goto delete_and_exit;
     }
     if (creator) {
         ret = blk_pwrite(blk, VHDX_FILE_ID_OFFSET + sizeof(signature),
                          creator, creator_items * sizeof(gunichar2), 0);
         if (ret < 0) {
+            error_setg_errno(errp, -ret, "Failed to write creator field");
             goto delete_and_exit;
         }
     }
@@ -1893,13 +1906,14 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
     /* Creates (B),(C) */
     ret = vhdx_create_new_headers(blk, image_size, log_size);
     if (ret < 0) {
+        error_setg_errno(errp, -ret, "Failed to write image headers");
         goto delete_and_exit;
     }
 
     /* Creates (D),(E),(G) explicitly. (F) created as by-product */
     ret = vhdx_create_new_region_table(blk, image_size, block_size, 512,
                                        log_size, use_zero_blocks, image_type,
-                                       &metadata_offset);
+                                       &metadata_offset, errp);
     if (ret < 0) {
         goto delete_and_exit;
     }
@@ -1908,6 +1922,7 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
     ret = vhdx_create_new_metadata(blk, image_size, block_size, 512,
                                    metadata_offset, image_type);
     if (ret < 0) {
+        error_setg_errno(errp, -ret, "Failed to initialize metadata");
         goto delete_and_exit;
     }
 

block/vmdk.c

@@ -1714,10 +1714,7 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
     blk_set_allow_write_beyond_eof(blk, true);
 
     if (flat) {
-        ret = blk_truncate(blk, filesize);
-        if (ret < 0) {
-            error_setg_errno(errp, -ret, "Could not truncate file");
-        }
+        ret = blk_truncate(blk, filesize, errp);
         goto exit;
     }
     magic = cpu_to_be32(VMDK4_MAGIC);
@@ -1780,9 +1777,8 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
         goto exit;
     }
 
-    ret = blk_truncate(blk, le64_to_cpu(header.grain_offset) << 9);
+    ret = blk_truncate(blk, le64_to_cpu(header.grain_offset) << 9, errp);
     if (ret < 0) {
-        error_setg_errno(errp, -ret, "Could not truncate file");
         goto exit;
     }
 
@@ -2090,10 +2086,7 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
     /* bdrv_pwrite write padding zeros to align to sector, we don't need that
      * for description file */
     if (desc_offset == 0) {
-        ret = blk_truncate(new_blk, desc_len);
-        if (ret < 0) {
-            error_setg_errno(errp, -ret, "Could not truncate file");
-        }
+        ret = blk_truncate(new_blk, desc_len, errp);
     }
 exit:
     if (new_blk) {

block/vpc.c

@@ -851,20 +851,21 @@ static int create_dynamic_disk(BlockBackend *blk, uint8_t *buf,
 }
 
 static int create_fixed_disk(BlockBackend *blk, uint8_t *buf,
-                             int64_t total_size)
+                             int64_t total_size, Error **errp)
 {
     int ret;
 
     /* Add footer to total size */
     total_size += HEADER_SIZE;
 
-    ret = blk_truncate(blk, total_size);
+    ret = blk_truncate(blk, total_size, errp);
     if (ret < 0) {
         return ret;
     }
 
     ret = blk_pwrite(blk, total_size - HEADER_SIZE, buf, HEADER_SIZE, 0);
     if (ret < 0) {
+        error_setg_errno(errp, -ret, "Unable to write VHD header");
         return ret;
     }
 
@@ -996,11 +997,11 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
 
     if (disk_type == VHD_DYNAMIC) {
         ret = create_dynamic_disk(blk, buf, total_sectors);
+        if (ret < 0) {
+            error_setg(errp, "Unable to create or write VHD header");
+        }
     } else {
-        ret = create_fixed_disk(blk, buf, total_size);
-    }
-    if (ret < 0) {
-        error_setg(errp, "Unable to create or write VHD header");
+        ret = create_fixed_disk(blk, buf, total_size, errp);
     }
 
 out:

block/vvfat.c

@@ -1057,10 +1057,10 @@ static void vvfat_parse_filename(const char *filename, QDict *options,
     }
 
     /* Fill in the options QDict */
-    qdict_put(options, "dir", qstring_from_str(filename));
-    qdict_put(options, "fat-type", qint_from_int(fat_type));
-    qdict_put(options, "floppy", qbool_from_bool(floppy));
-    qdict_put(options, "rw", qbool_from_bool(rw));
+    qdict_put_str(options, "dir", filename);
+    qdict_put_int(options, "fat-type", fat_type);
+    qdict_put_bool(options, "floppy", floppy);
+    qdict_put_bool(options, "rw", rw);
 }
 
 static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
@@ -2958,8 +2958,7 @@ vvfat_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
 static int64_t coroutine_fn vvfat_co_get_block_status(BlockDriverState *bs,
 	int64_t sector_num, int nb_sectors, int *n, BlockDriverState **file)
 {
-    BDRVVVFATState* s = bs->opaque;
-    *n = s->sector_count - sector_num;
+    *n = bs->total_sectors - sector_num;
     if (*n > nb_sectors) {
         *n = nb_sectors;
     } else if (*n < 0) {
@@ -3040,7 +3039,7 @@ static int enable_write_target(BlockDriverState *bs, Error **errp)
     }
 
     options = qdict_new();
-    qdict_put(options, "write-target.driver", qstring_from_str("qcow"));
+    qdict_put_str(options, "write-target.driver", "qcow");
     s->qcow = bdrv_open_child(s->qcow_filename, options, "write-target", bs,
                               &child_vvfat_qcow, false, errp);
     QDECREF(options);

blockdev-nbd.c

@@ -27,6 +27,10 @@ typedef struct NBDServerData {
 
 static NBDServerData *nbd_server;
 
+static void nbd_blockdev_client_closed(NBDClient *client, bool ignored)
+{
+    nbd_client_put(client);
+}
 
 static gboolean nbd_accept(QIOChannel *ioc, GIOCondition condition,
                            gpointer opaque)
@@ -46,7 +50,7 @@ static gboolean nbd_accept(QIOChannel *ioc, GIOCondition condition,
     qio_channel_set_name(QIO_CHANNEL(cioc), "nbd-server");
     nbd_client_new(NULL, cioc,
                    nbd_server->tlscreds, NULL,
-                   nbd_client_put);
+                   nbd_blockdev_client_closed);
     object_unref(OBJECT(cioc));
     return TRUE;
 }
@@ -124,6 +128,7 @@ void qmp_nbd_server_start(SocketAddress *addr,
             goto error;
         }
 
+        /* TODO SOCKET_ADDRESS_KIND_FD where fd has AF_INET or AF_INET6 */
         if (addr->type != SOCKET_ADDRESS_KIND_INET) {
             error_setg(errp, "TLS is only supported with IPv4/IPv6");
             goto error;

blockdev.c

@@ -527,7 +527,7 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
             error_setg(errp, "Cannot specify both 'driver' and 'format'");
             goto early_err;
         }
-        qdict_put(bs_opts, "driver", qstring_from_str(buf));
+        qdict_put_str(bs_opts, "driver", buf);
     }
 
     on_write_error = BLOCKDEV_ON_ERROR_ENOSPC;
@@ -903,10 +903,8 @@ DriveInfo *drive_new(QemuOpts *all_opts, BlockInterfaceType block_default_type)
         copy_on_read = false;
     }
 
-    qdict_put(bs_opts, BDRV_OPT_READ_ONLY,
-              qstring_from_str(read_only ? "on" : "off"));
-    qdict_put(bs_opts, "copy-on-read",
-              qstring_from_str(copy_on_read ? "on" :"off"));
+    qdict_put_str(bs_opts, BDRV_OPT_READ_ONLY, read_only ? "on" : "off");
+    qdict_put_str(bs_opts, "copy-on-read", copy_on_read ? "on" : "off");
 
     /* Controller type */
     value = qemu_opt_get(legacy_opts, "if");
@@ -1030,7 +1028,7 @@ DriveInfo *drive_new(QemuOpts *all_opts, BlockInterfaceType block_default_type)
             new_id = g_strdup_printf("%s%s%i", if_name[type],
                                      mediastr, unit_id);
         }
-        qdict_put(bs_opts, "id", qstring_from_str(new_id));
+        qdict_put_str(bs_opts, "id", new_id);
         g_free(new_id);
     }
 
@@ -1067,7 +1065,7 @@ DriveInfo *drive_new(QemuOpts *all_opts, BlockInterfaceType block_default_type)
             error_report("werror is not supported by this bus type");
             goto fail;
         }
-        qdict_put(bs_opts, "werror", qstring_from_str(werror));
+        qdict_put_str(bs_opts, "werror", werror);
     }
 
     rerror = qemu_opt_get(legacy_opts, "rerror");
@@ -1077,7 +1075,7 @@ DriveInfo *drive_new(QemuOpts *all_opts, BlockInterfaceType block_default_type)
             error_report("rerror is not supported by this bus type");
             goto fail;
         }
-        qdict_put(bs_opts, "rerror", qstring_from_str(rerror));
+        qdict_put_str(bs_opts, "rerror", rerror);
     }
 
     /* Actual block device init: Functionality shared with blockdev-add */
@@ -1737,10 +1735,9 @@ static void external_snapshot_prepare(BlkActionState *common,
 
         options = qdict_new();
         if (s->has_snapshot_node_name) {
-            qdict_put(options, "node-name",
-                      qstring_from_str(snapshot_node_name));
+            qdict_put_str(options, "node-name", snapshot_node_name);
         }
-        qdict_put(options, "driver", qstring_from_str(format));
+        qdict_put_str(options, "driver", format);
 
         flags |= BDRV_O_NO_BACKING;
     }
@@ -1772,6 +1769,8 @@ static void external_snapshot_prepare(BlkActionState *common,
         return;
     }
 
+    bdrv_set_aio_context(state->new_bs, state->aio_context);
+
     /* This removes our old bs and adds the new bs. This is an operation that
      * can fail, so we need to do it in .prepare; undoing it for abort is
      * always possible. */
@@ -1789,8 +1788,6 @@ static void external_snapshot_commit(BlkActionState *common)
     ExternalSnapshotState *state =
                              DO_UPCAST(ExternalSnapshotState, common, common);
 
-    bdrv_set_aio_context(state->new_bs, state->aio_context);
-
     /* We don't need (or want) to use the transactional
      * bdrv_reopen_multiple() across all the entries at once, because we
      * don't want to abort all of them if one of them fails the reopen */
@@ -2579,11 +2576,10 @@ void qmp_blockdev_change_medium(bool has_device, const char *device,
 
     options = qdict_new();
     detect_zeroes = blk_get_detect_zeroes_from_root_state(blk);
-    qdict_put(options, "detect-zeroes",
-              qstring_from_str(detect_zeroes ? "on" : "off"));
+    qdict_put_str(options, "detect-zeroes", detect_zeroes ? "on" : "off");
 
     if (has_format) {
-        qdict_put(options, "driver", qstring_from_str(format));
+        qdict_put_str(options, "driver", format);
     }
 
     medium_bs = bdrv_open(filename, NULL, options, bdrv_flags, errp);
@@ -2927,29 +2923,9 @@ void qmp_block_resize(bool has_device, const char *device,
         goto out;
     }
 
-    /* complete all in-flight operations before resizing the device */
-    bdrv_drain_all();
-
-    ret = blk_truncate(blk, size);
-    switch (ret) {
-    case 0:
-        break;
-    case -ENOMEDIUM:
-        error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM, device);
-        break;
-    case -ENOTSUP:
-        error_setg(errp, QERR_UNSUPPORTED);
-        break;
-    case -EACCES:
-        error_setg(errp, "Device '%s' is read only", device);
-        break;
-    case -EBUSY:
-        error_setg(errp, QERR_DEVICE_IN_USE, device);
-        break;
-    default:
-        error_setg_errno(errp, -ret, "Could not resize");
-        break;
-    }
+    bdrv_drained_begin(bs);
+    ret = blk_truncate(blk, size, errp);
+    bdrv_drained_end(bs);
 
 out:
     blk_unref(blk);
@@ -3174,6 +3150,7 @@ static BlockJob *do_drive_backup(DriveBackup *backup, BlockJobTxn *txn,
     Error *local_err = NULL;
     int flags;
     int64_t size;
+    bool set_backing_hd = false;
 
     if (!backup->has_speed) {
         backup->speed = 0;
@@ -3224,6 +3201,8 @@ static BlockJob *do_drive_backup(DriveBackup *backup, BlockJobTxn *txn,
     }
     if (backup->sync == MIRROR_SYNC_MODE_NONE) {
         source = bs;
+        flags |= BDRV_O_NO_BACKING;
+        set_backing_hd = true;
     }
 
     size = bdrv_getlength(bs);
@@ -3250,8 +3229,10 @@ static BlockJob *do_drive_backup(DriveBackup *backup, BlockJobTxn *txn,
     }
 
     if (backup->format) {
-        options = qdict_new();
-        qdict_put(options, "driver", qstring_from_str(backup->format));
+        if (!options) {
+            options = qdict_new();
+        }
+        qdict_put_str(options, "driver", backup->format);
     }
 
     target_bs = bdrv_open(backup->target, NULL, options, flags, errp);
@@ -3261,6 +3242,14 @@ static BlockJob *do_drive_backup(DriveBackup *backup, BlockJobTxn *txn,
 
     bdrv_set_aio_context(target_bs, aio_context);
 
+    if (set_backing_hd) {
+        bdrv_set_backing_hd(target_bs, source, &local_err);
+        if (local_err) {
+            bdrv_unref(target_bs);
+            goto out;
+        }
+    }
+
     if (backup->has_bitmap) {
         bmap = bdrv_find_dirty_bitmap(bs, backup->bitmap);
         if (!bmap) {
@@ -3555,10 +3544,10 @@ void qmp_drive_mirror(DriveMirror *arg, Error **errp)
 
     options = qdict_new();
     if (arg->has_node_name) {
-        qdict_put(options, "node-name", qstring_from_str(arg->node_name));
+        qdict_put_str(options, "node-name", arg->node_name);
     }
     if (format) {
-        qdict_put(options, "driver", qstring_from_str(format));
+        qdict_put_str(options, "driver", format);
     }
 
     /* Mirroring takes care of copy-on-write using the source's backing

blockjob.c

@@ -290,7 +290,7 @@ void block_job_start(BlockJob *job)
     job->pause_count--;
     job->busy = true;
     job->paused = false;
-    qemu_coroutine_enter(job->co);
+    bdrv_coroutine_enter(blk_bs(job->blk), job->co);
 }
 
 void block_job_ref(BlockJob *job)
@@ -532,7 +532,7 @@ void block_job_user_resume(BlockJob *job)
 void block_job_enter(BlockJob *job)
 {
     if (job->co && !job->busy) {
-        qemu_coroutine_enter(job->co);
+        bdrv_coroutine_enter(blk_bs(job->blk), job->co);
     }
 }
 

chardev/char-socket.c

@@ -47,7 +47,6 @@ typedef struct {
     int max_size;
     int do_telnetopt;
     int do_nodelay;
-    int is_unix;
     int *read_msgfds;
     size_t read_msgfds_num;
     int *write_msgfds;
@@ -358,6 +357,10 @@ static char *SocketAddress_to_str(const char *prefix, SocketAddress *addr,
         return g_strdup_printf("%sfd:%s%s", prefix, addr->u.fd.data->str,
                                is_listen ? ",server" : "");
         break;
+    case SOCKET_ADDRESS_KIND_VSOCK:
+        return g_strdup_printf("%svsock:%s:%s", prefix,
+                               addr->u.vsock.data->cid,
+                               addr->u.vsock.data->port);
     default:
         abort();
     }
@@ -825,7 +828,6 @@ static void qmp_chardev_open_socket(Chardev *chr,
     int64_t reconnect   = sock->has_reconnect ? sock->reconnect : 0;
     QIOChannelSocket *sioc = NULL;
 
-    s->is_unix = addr->type == SOCKET_ADDRESS_KIND_UNIX;
     s->is_listen = is_listen;
     s->is_telnet = is_telnet;
     s->do_nodelay = do_nodelay;
@@ -865,7 +867,8 @@ static void qmp_chardev_open_socket(Chardev *chr,
     s->addr = QAPI_CLONE(SocketAddress, sock->addr);
 
     qemu_chr_set_feature(chr, QEMU_CHAR_FEATURE_RECONNECTABLE);
-    if (s->is_unix) {
+    /* TODO SOCKET_ADDRESS_FD where fd has AF_UNIX */
+    if (addr->type == SOCKET_ADDRESS_KIND_UNIX) {
         qemu_chr_set_feature(chr, QEMU_CHAR_FEATURE_FD_PASS);
     }
 

configure

@@ -323,6 +323,7 @@ replication="yes"
 
 supported_cpu="no"
 supported_os="no"
+bogus_os="no"
 
 # parse CC options first
 for opt do
@@ -520,11 +521,11 @@ ARCH=
 # Normalise host CPU name and set ARCH.
 # Note that this case should only have supported host CPUs, not guests.
 case "$cpu" in
-  ppc|ppc64|s390|s390x|x32)
+  ppc|ppc64|s390|s390x|sparc64|x32)
     cpu="$cpu"
     supported_cpu="yes"
   ;;
-  ia64|sparc64)
+  ia64)
     cpu="$cpu"
   ;;
   i386|i486|i586|i686|i86pc|BePC)
@@ -549,6 +550,7 @@ case "$cpu" in
   ;;
   sparc|sun4[cdmuv])
     cpu="sparc"
+    supported_cpu="yes"
   ;;
   *)
     # This will result in either an error or falling back to TCI later
@@ -694,7 +696,10 @@ Linux)
   supported_os="yes"
 ;;
 *)
-  error_exit "Unsupported host OS $targetos"
+  # This is a fatal error, but don't report it yet, because we
+  # might be going to just print the --help text, or it might
+  # be the result of a missing compiler.
+  bogus_os="yes"
 ;;
 esac
 
@@ -1460,6 +1465,14 @@ if ! compile_prog ; then
     error_exit "\"$cc\" cannot build an executable (is your linker broken?)"
 fi
 
+if test "$bogus_os" = "yes"; then
+    # Now that we know that we're not printing the help and that
+    # the compiler works (so the results of the check_defines we used
+    # to identify the OS are reliable), if we didn't recognize the
+    # host OS we should stop now.
+    error_exit "Unrecognized host OS $targetos"
+fi
+
 # Check that the C++ compiler exists and works with the C compiler
 if has $cxx; then
     cat > $TMPC <<EOF
@@ -3060,12 +3073,23 @@ fi
 ##########################################
 # glib support probe
 
-glib_req_ver=2.22
+if test "$mingw32" = yes; then
+    glib_req_ver=2.30
+else
+    glib_req_ver=2.22
+fi
 glib_modules=gthread-2.0
 if test "$modules" = yes; then
     glib_modules="$glib_modules gmodule-2.0"
 fi
 
+# This workaround is required due to a bug in pkg-config file for glib as it
+# doesn't define GLIB_STATIC_COMPILATION for pkg-config --static
+
+if test "$static" = yes -a "$mingw32" = yes; then
+    QEMU_CFLAGS="-DGLIB_STATIC_COMPILATION $QEMU_CFLAGS"
+fi
+
 for i in $glib_modules; do
     if $pkg_config --atleast-version=$glib_req_ver $i; then
         glib_cflags=$($pkg_config --cflags $i)

cpu-exec.c

@@ -600,13 +600,13 @@ static inline void cpu_loop_exec_tb(CPUState *cpu, TranslationBlock *tb,
     /* Instruction counter expired.  */
     assert(use_icount);
 #ifndef CONFIG_USER_ONLY
-    if (cpu->icount_extra) {
-        /* Refill decrementer and continue execution.  */
-        cpu->icount_extra += insns_left;
-        insns_left = MIN(0xffff, cpu->icount_extra);
-        cpu->icount_extra -= insns_left;
-        cpu->icount_decr.u16.low = insns_left;
-    } else {
+    /* Ensure global icount has gone forward */
+    cpu_update_icount(cpu);
+    /* Refill decrementer and continue execution.  */
+    insns_left = MIN(0xffff, cpu->icount_budget);
+    cpu->icount_decr.u16.low = insns_left;
+    cpu->icount_extra = cpu->icount_budget - insns_left;
+    if (!cpu->icount_extra) {
         /* Execute any remaining instructions, then let the main loop
          * handle the next event.
          */

cpus.c

@@ -202,7 +202,7 @@ void qemu_tcg_configure(QemuOpts *opts, Error **errp)
             } else if (use_icount) {
                 error_setg(errp, "No MTTCG when icount is enabled");
             } else {
-#ifndef TARGET_SUPPORT_MTTCG
+#ifndef TARGET_SUPPORTS_MTTCG
                 error_report("Guest not yet converted to MTTCG - "
                              "you may get unexpected results");
 #endif
@@ -223,20 +223,51 @@ void qemu_tcg_configure(QemuOpts *opts, Error **errp)
     }
 }
 
+/* The current number of executed instructions is based on what we
+ * originally budgeted minus the current state of the decrementing
+ * icount counters in extra/u16.low.
+ */
+static int64_t cpu_get_icount_executed(CPUState *cpu)
+{
+    return cpu->icount_budget - (cpu->icount_decr.u16.low + cpu->icount_extra);
+}
+
+/*
+ * Update the global shared timer_state.qemu_icount to take into
+ * account executed instructions. This is done by the TCG vCPU
+ * thread so the main-loop can see time has moved forward.
+ */
+void cpu_update_icount(CPUState *cpu)
+{
+    int64_t executed = cpu_get_icount_executed(cpu);
+    cpu->icount_budget -= executed;
+
+#ifdef CONFIG_ATOMIC64
+    atomic_set__nocheck(&timers_state.qemu_icount,
+                        atomic_read__nocheck(&timers_state.qemu_icount) +
+                        executed);
+#else /* FIXME: we need 64bit atomics to do this safely */
+    timers_state.qemu_icount += executed;
+#endif
+}
+
 int64_t cpu_get_icount_raw(void)
 {
-    int64_t icount;
     CPUState *cpu = current_cpu;
 
-    icount = timers_state.qemu_icount;
-    if (cpu) {
+    if (cpu && cpu->running) {
         if (!cpu->can_do_io) {
             fprintf(stderr, "Bad icount read\n");
             exit(1);
         }
-        icount -= (cpu->icount_decr.u16.low + cpu->icount_extra);
+        /* Take into account what has run */
+        cpu_update_icount(cpu);
     }
-    return icount;
+#ifdef CONFIG_ATOMIC64
+    return atomic_read__nocheck(&timers_state.qemu_icount);
+#else /* FIXME: we need 64bit atomics to do this safely */
+    return timers_state.qemu_icount;
+#endif
 }
 
 /* Return the virtual CPU time, based on the instruction counter.  */
@@ -1179,6 +1210,41 @@ static void handle_icount_deadline(void)
     }
 }
 
+static void prepare_icount_for_run(CPUState *cpu)
+{
+    if (use_icount) {
+        int insns_left;
+
+        /* These should always be cleared by process_icount_data after
+         * each vCPU execution. However u16.high can be raised
+         * asynchronously by cpu_exit/cpu_interrupt/tcg_handle_interrupt
+         */
+        g_assert(cpu->icount_decr.u16.low == 0);
+        g_assert(cpu->icount_extra == 0);
+
+        cpu->icount_budget = tcg_get_icount_limit();
+        insns_left = MIN(0xffff, cpu->icount_budget);
+        cpu->icount_decr.u16.low = insns_left;
+        cpu->icount_extra = cpu->icount_budget - insns_left;
+    }
+}
+
+static void process_icount_data(CPUState *cpu)
+{
+    if (use_icount) {
+        /* Account for executed instructions */
+        cpu_update_icount(cpu);
+
+        /* Reset the counters */
+        cpu->icount_decr.u16.low = 0;
+        cpu->icount_extra = 0;
+        cpu->icount_budget = 0;
+
+        replay_account_executed_instructions();
+    }
+}
+
+
 static int tcg_cpu_exec(CPUState *cpu)
 {
     int ret;
@@ -1189,20 +1255,6 @@ static int tcg_cpu_exec(CPUState *cpu)
 #ifdef CONFIG_PROFILER
     ti = profile_getclock();
 #endif
-    if (use_icount) {
-        int64_t count;
-        int decr;
-        timers_state.qemu_icount -= (cpu->icount_decr.u16.low
-                                    + cpu->icount_extra);
-        cpu->icount_decr.u16.low = 0;
-        cpu->icount_extra = 0;
-        count = tcg_get_icount_limit();
-        timers_state.qemu_icount += count;
-        decr = (count > 0xffff) ? 0xffff : count;
-        count -= decr;
-        cpu->icount_decr.u16.low = decr;
-        cpu->icount_extra = count;
-    }
     qemu_mutex_unlock_iothread();
     cpu_exec_start(cpu);
     ret = cpu_exec(cpu);
@@ -1211,15 +1263,6 @@ static int tcg_cpu_exec(CPUState *cpu)
 #ifdef CONFIG_PROFILER
     tcg_time += profile_getclock() - ti;
 #endif
-    if (use_icount) {
-        /* Fold pending instructions back into the
-           instruction counter, and clear the interrupt flag.  */
-        timers_state.qemu_icount -= (cpu->icount_decr.u16.low
-                        + cpu->icount_extra);
-        cpu->icount_decr.u32 = 0;
-        cpu->icount_extra = 0;
-        replay_account_executed_instructions();
-    }
     return ret;
 }
 
@@ -1306,7 +1349,13 @@ static void *qemu_tcg_rr_cpu_thread_fn(void *arg)
 
             if (cpu_can_run(cpu)) {
                 int r;
+
+                prepare_icount_for_run(cpu);
+
                 r = tcg_cpu_exec(cpu);
+
+                process_icount_data(cpu);
+
                 if (r == EXCP_DEBUG) {
                     cpu_handle_guest_debug(cpu);
                     break;
@@ -1392,6 +1441,8 @@ static void *qemu_tcg_cpu_thread_fn(void *arg)
 {
     CPUState *cpu = arg;
 
+    g_assert(!use_icount);
+
     rcu_register_thread();
 
     qemu_mutex_lock_iothread();
@@ -1434,8 +1485,6 @@ static void *qemu_tcg_cpu_thread_fn(void *arg)
             }
         }
 
-        handle_icount_deadline();
-
         atomic_mb_set(&cpu->exit_request, 0);
         qemu_tcg_wait_io_event(cpu);
     }

disas/cris.c

@@ -2048,7 +2048,7 @@ print_with_operands (const struct cris_opcode *opcodep,
 	  {
 	    /* We're looking at [pc+], i.e. we need to output an immediate
 	       number, where the size can depend on different things.  */
-	    long number;
+	    int32_t number;
 	    int signedp
 	      = ((*cs == 'z' && (insn & 0x20))
 		 || opcodep->match == BDAP_QUICK_OPCODE);
@@ -2290,7 +2290,7 @@ print_with_operands (const struct cris_opcode *opcodep,
 
 		    if ((prefix_insn & 0x400) && (prefix_insn & 15) == 15)
 		      {
-			long number;
+			int32_t number;
 			unsigned int nbytes;
 
 			/* It's a value.  Get its size.  */

exec.c

@@ -2010,10 +2010,10 @@ void *qemu_map_ram_ptr(RAMBlock *ram_block, ram_addr_t addr)
          * In that case just map until the end of the page.
          */
         if (block->offset == 0) {
-            return xen_map_cache(addr, 0, 0);
+            return xen_map_cache(addr, 0, 0, false);
         }
 
-        block->host = xen_map_cache(block->offset, block->max_length, 1);
+        block->host = xen_map_cache(block->offset, block->max_length, 1, false);
     }
     return ramblock_ptr(block, addr);
 }
@@ -2024,7 +2024,7 @@ void *qemu_map_ram_ptr(RAMBlock *ram_block, ram_addr_t addr)
  * Called within RCU critical section.
  */
 static void *qemu_ram_ptr_length(RAMBlock *ram_block, ram_addr_t addr,
-                                 hwaddr *size)
+                                 hwaddr *size, bool lock)
 {
     RAMBlock *block = ram_block;
     if (*size == 0) {
@@ -2043,10 +2043,10 @@ static void *qemu_ram_ptr_length(RAMBlock *ram_block, ram_addr_t addr,
          * In that case just map the requested area.
          */
         if (block->offset == 0) {
-            return xen_map_cache(addr, *size, 1);
+            return xen_map_cache(addr, *size, lock, lock);
         }
 
-        block->host = xen_map_cache(block->offset, block->max_length, 1);
+        block->host = xen_map_cache(block->offset, block->max_length, 1, lock);
     }
 
     return ramblock_ptr(block, addr);
@@ -2765,7 +2765,7 @@ static MemTxResult address_space_write_continue(AddressSpace *as, hwaddr addr,
             }
         } else {
             /* RAM case */
-            ptr = qemu_map_ram_ptr(mr->ram_block, addr1);
+            ptr = qemu_ram_ptr_length(mr->ram_block, addr1, &l, false);
             memcpy(ptr, buf, l);
             invalidate_and_set_dirty(mr, addr1, l);
         }
@@ -2856,7 +2856,7 @@ MemTxResult address_space_read_continue(AddressSpace *as, hwaddr addr,
             }
         } else {
             /* RAM case */
-            ptr = qemu_map_ram_ptr(mr->ram_block, addr1);
+            ptr = qemu_ram_ptr_length(mr->ram_block, addr1, &l, false);
             memcpy(buf, ptr, l);
         }
 
@@ -3167,7 +3167,7 @@ void *address_space_map(AddressSpace *as,
 
     memory_region_ref(mr);
     *plen = address_space_extend_translation(as, addr, len, mr, xlat, l, is_write);
-    ptr = qemu_ram_ptr_length(mr->ram_block, xlat, plen);
+    ptr = qemu_ram_ptr_length(mr->ram_block, xlat, plen, true);
     rcu_read_unlock();
 
     return ptr;
@@ -3236,75 +3236,33 @@ int64_t address_space_cache_init(MemoryRegionCache *cache,
                                  hwaddr len,
                                  bool is_write)
 {
-    hwaddr l, xlat;
-    MemoryRegion *mr;
-    void *ptr;
-
-    assert(len > 0);
-
-    l = len;
-    mr = address_space_translate(as, addr, &xlat, &l, is_write);
-    if (!memory_access_is_direct(mr, is_write)) {
-        return -EINVAL;
-    }
-
-    l = address_space_extend_translation(as, addr, len, mr, xlat, l, is_write);
-    ptr = qemu_ram_ptr_length(mr->ram_block, xlat, &l);
-
-    cache->xlat = xlat;
-    cache->is_write = is_write;
-    cache->mr = mr;
-    cache->ptr = ptr;
-    cache->len = l;
-    memory_region_ref(cache->mr);
-
-    return l;
+    cache->len = len;
+    cache->as = as;
+    cache->xlat = addr;
+    return len;
 }
 
 void address_space_cache_invalidate(MemoryRegionCache *cache,
                                     hwaddr addr,
                                     hwaddr access_len)
 {
-    assert(cache->is_write);
-    invalidate_and_set_dirty(cache->mr, addr + cache->xlat, access_len);
 }
 
 void address_space_cache_destroy(MemoryRegionCache *cache)
 {
-    if (!cache->mr) {
-        return;
-    }
-
-    if (xen_enabled()) {
-        xen_invalidate_map_cache_entry(cache->ptr);
-    }
-    memory_region_unref(cache->mr);
-    cache->mr = NULL;
-}
-
-/* Called from RCU critical section.  This function has the same
- * semantics as address_space_translate, but it only works on a
- * predefined range of a MemoryRegion that was mapped with
- * address_space_cache_init.
- */
-static inline MemoryRegion *address_space_translate_cached(
-    MemoryRegionCache *cache, hwaddr addr, hwaddr *xlat,
-    hwaddr *plen, bool is_write)
-{
-    assert(addr < cache->len && *plen <= cache->len - addr);
-    *xlat = addr + cache->xlat;
-    return cache->mr;
+    cache->as = NULL;
 }
 
 #define ARG1_DECL                MemoryRegionCache *cache
 #define ARG1                     cache
 #define SUFFIX                   _cached
-#define TRANSLATE(...)           address_space_translate_cached(cache, __VA_ARGS__)
+#define TRANSLATE(addr, ...)     \
+    address_space_translate(cache->as, cache->xlat + (addr), __VA_ARGS__)
 #define IS_DIRECT(mr, is_write)  true
-#define MAP_RAM(mr, ofs)         (cache->ptr + (ofs - cache->xlat))
-#define INVALIDATE(mr, ofs, len) ((void)0)
-#define RCU_READ_LOCK()          ((void)0)
-#define RCU_READ_UNLOCK()        ((void)0)
+#define MAP_RAM(mr, ofs)         qemu_map_ram_ptr((mr)->ram_block, ofs)
+#define INVALIDATE(mr, ofs, len) invalidate_and_set_dirty(mr, ofs, len)
+#define RCU_READ_LOCK()          rcu_read_lock()
+#define RCU_READ_UNLOCK()        rcu_read_unlock()
 #include "memory_ldst.inc.c"
 
 /* virtual memory access for debug (includes writing to ROM) */

hw/9pfs/9p-local.c

@@ -278,17 +278,27 @@ update_map_file:
 
 static int fchmodat_nofollow(int dirfd, const char *name, mode_t mode)
 {
+    struct stat stbuf;
     int fd, ret;
 
     /* FIXME: this should be handled with fchmodat(AT_SYMLINK_NOFOLLOW).
-     * Unfortunately, the linux kernel doesn't implement it yet. As an
-     * alternative, let's open the file and use fchmod() instead. This
-     * may fail depending on the permissions of the file, but it is the
-     * best we can do to avoid TOCTTOU. We first try to open read-only
-     * in case name points to a directory. If that fails, we try write-only
-     * in case name doesn't point to a directory.
+     * Unfortunately, the linux kernel doesn't implement it yet.
      */
-    fd = openat_file(dirfd, name, O_RDONLY, 0);
+
+     /* First, we clear non-racing symlinks out of the way. */
+    if (fstatat(dirfd, name, &stbuf, AT_SYMLINK_NOFOLLOW)) {
+        return -1;
+    }
+    if (S_ISLNK(stbuf.st_mode)) {
+        errno = ELOOP;
+        return -1;
+    }
+
+    /* Access modes are ignored when O_PATH is supported. We try O_RDONLY and
+     * O_WRONLY for old-systems that don't support O_PATH.
+     */
+    fd = openat_file(dirfd, name, O_RDONLY | O_PATH_9P_UTIL, 0);
+#if O_PATH_9P_UTIL == 0
     if (fd == -1) {
         /* In case the file is writable-only and isn't a directory. */
         if (errno == EACCES) {
@@ -302,6 +312,24 @@ static int fchmodat_nofollow(int dirfd, const char *name, mode_t mode)
         return -1;
     }
     ret = fchmod(fd, mode);
+#else
+    if (fd == -1) {
+        return -1;
+    }
+
+    /* Now we handle racing symlinks. */
+    ret = fstat(fd, &stbuf);
+    if (!ret) {
+        if (S_ISLNK(stbuf.st_mode)) {
+            errno = ELOOP;
+            ret = -1;
+        } else {
+            char *proc_path = g_strdup_printf("/proc/self/fd/%d", fd);
+            ret = chmod(proc_path, mode);
+            g_free(proc_path);
+        }
+    }
+#endif
     close_preserve_errno(fd);
     return ret;
 }
@@ -452,6 +480,11 @@ static off_t local_telldir(FsContext *ctx, V9fsFidOpenState *fs)
     return telldir(fs->dir.stream);
 }
 
+static bool local_is_mapped_file_metadata(FsContext *fs_ctx, const char *name)
+{
+    return !strcmp(name, VIRTFS_META_DIR);
+}
+
 static struct dirent *local_readdir(FsContext *ctx, V9fsFidOpenState *fs)
 {
     struct dirent *entry;
@@ -465,8 +498,8 @@ again:
     if (ctx->export_flags & V9FS_SM_MAPPED) {
         entry->d_type = DT_UNKNOWN;
     } else if (ctx->export_flags & V9FS_SM_MAPPED_FILE) {
-        if (!strcmp(entry->d_name, VIRTFS_META_DIR)) {
-            /* skp the meta data directory */
+        if (local_is_mapped_file_metadata(ctx, entry->d_name)) {
+            /* skip the meta data directory */
             goto again;
         }
         entry->d_type = DT_UNKNOWN;
@@ -559,6 +592,12 @@ static int local_mknod(FsContext *fs_ctx, V9fsPath *dir_path,
     int err = -1;
     int dirfd;
 
+    if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE &&
+        local_is_mapped_file_metadata(fs_ctx, name)) {
+        errno = EINVAL;
+        return -1;
+    }
+
     dirfd = local_opendir_nofollow(fs_ctx, dir_path->data);
     if (dirfd == -1) {
         return -1;
@@ -605,6 +644,12 @@ static int local_mkdir(FsContext *fs_ctx, V9fsPath *dir_path,
     int err = -1;
     int dirfd;
 
+    if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE &&
+        local_is_mapped_file_metadata(fs_ctx, name)) {
+        errno = EINVAL;
+        return -1;
+    }
+
     dirfd = local_opendir_nofollow(fs_ctx, dir_path->data);
     if (dirfd == -1) {
         return -1;
@@ -694,6 +739,12 @@ static int local_open2(FsContext *fs_ctx, V9fsPath *dir_path, const char *name,
     int err = -1;
     int dirfd;
 
+    if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE &&
+        local_is_mapped_file_metadata(fs_ctx, name)) {
+        errno = EINVAL;
+        return -1;
+    }
+
     /*
      * Mark all the open to not follow symlinks
      */
@@ -752,6 +803,12 @@ static int local_symlink(FsContext *fs_ctx, const char *oldpath,
     int err = -1;
     int dirfd;
 
+    if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE &&
+        local_is_mapped_file_metadata(fs_ctx, name)) {
+        errno = EINVAL;
+        return -1;
+    }
+
     dirfd = local_opendir_nofollow(fs_ctx, dir_path->data);
     if (dirfd == -1) {
         return -1;
@@ -826,6 +883,12 @@ static int local_link(FsContext *ctx, V9fsPath *oldpath,
     int ret = -1;
     int odirfd, ndirfd;
 
+    if (ctx->export_flags & V9FS_SM_MAPPED_FILE &&
+        local_is_mapped_file_metadata(ctx, name)) {
+        errno = EINVAL;
+        return -1;
+    }
+
     odirfd = local_opendir_nofollow(ctx, odirpath);
     if (odirfd == -1) {
         goto out;
@@ -957,6 +1020,14 @@ static int local_unlinkat_common(FsContext *ctx, int dirfd, const char *name,
     if (ctx->export_flags & V9FS_SM_MAPPED_FILE) {
         int map_dirfd;
 
+        /* We need to remove the metadata as well:
+         * - the metadata directory if we're removing a directory
+         * - the metadata file in the parent's metadata directory
+         *
+         * If any of these are missing (ie, ENOENT) then we're probably
+         * trying to remove something that wasn't created in mapped-file
+         * mode. We just ignore the error.
+         */
         if (flags == AT_REMOVEDIR) {
             int fd;
 
@@ -964,32 +1035,20 @@ static int local_unlinkat_common(FsContext *ctx, int dirfd, const char *name,
             if (fd == -1) {
                 goto err_out;
             }
-            /*
-             * If directory remove .virtfs_metadata contained in the
-             * directory
-             */
             ret = unlinkat(fd, VIRTFS_META_DIR, AT_REMOVEDIR);
             close_preserve_errno(fd);
             if (ret < 0 && errno != ENOENT) {
-                /*
-                 * We didn't had the .virtfs_metadata file. May be file created
-                 * in non-mapped mode ?. Ignore ENOENT.
-                 */
                 goto err_out;
             }
         }
-        /*
-         * Now remove the name from parent directory
-         * .virtfs_metadata directory.
-         */
         map_dirfd = openat_dir(dirfd, VIRTFS_META_DIR);
-        ret = unlinkat(map_dirfd, name, 0);
-        close_preserve_errno(map_dirfd);
-        if (ret < 0 && errno != ENOENT) {
-            /*
-             * We didn't had the .virtfs_metadata file. May be file created
-             * in non-mapped mode ?. Ignore ENOENT.
-             */
+        if (map_dirfd != -1) {
+            ret = unlinkat(map_dirfd, name, 0);
+            close_preserve_errno(map_dirfd);
+            if (ret < 0 && errno != ENOENT) {
+                goto err_out;
+            }
+        } else if (errno != ENOENT) {
             goto err_out;
         }
     }
@@ -1013,7 +1072,7 @@ static int local_remove(FsContext *ctx, const char *path)
         goto out;
     }
 
-    if (fstatat(dirfd, path, &stbuf, AT_SYMLINK_NOFOLLOW) < 0) {
+    if (fstatat(dirfd, name, &stbuf, AT_SYMLINK_NOFOLLOW) < 0) {
         goto err_out;
     }
 
@@ -1096,10 +1155,21 @@ static int local_lremovexattr(FsContext *ctx, V9fsPath *fs_path,
 static int local_name_to_path(FsContext *ctx, V9fsPath *dir_path,
                               const char *name, V9fsPath *target)
 {
+    if (ctx->export_flags & V9FS_SM_MAPPED_FILE &&
+        local_is_mapped_file_metadata(ctx, name)) {
+        errno = EINVAL;
+        return -1;
+    }
+
     if (dir_path) {
         v9fs_path_sprintf(target, "%s/%s", dir_path->data, name);
-    } else {
+    } else if (strcmp(name, "/")) {
         v9fs_path_sprintf(target, "%s", name);
+    } else {
+        /* We want the path of the export root to be relative, otherwise
+         * "*at()" syscalls would treat it as "/" in the host.
+         */
+        v9fs_path_sprintf(target, "%s", ".");
     }
     return 0;
 }
@@ -1111,6 +1181,13 @@ static int local_renameat(FsContext *ctx, V9fsPath *olddir,
     int ret;
     int odirfd, ndirfd;
 
+    if (ctx->export_flags & V9FS_SM_MAPPED_FILE &&
+        (local_is_mapped_file_metadata(ctx, old_name) ||
+         local_is_mapped_file_metadata(ctx, new_name))) {
+        errno = EINVAL;
+        return -1;
+    }
+
     odirfd = local_opendir_nofollow(ctx, olddir->data);
     if (odirfd == -1) {
         return -1;
@@ -1201,6 +1278,12 @@ static int local_unlinkat(FsContext *ctx, V9fsPath *dir,
     int ret;
     int dirfd;
 
+    if (ctx->export_flags & V9FS_SM_MAPPED_FILE &&
+        local_is_mapped_file_metadata(ctx, name)) {
+        errno = EINVAL;
+        return -1;
+    }
+
     dirfd = local_opendir_nofollow(ctx, dir->data);
     if (dirfd == -1) {
         return -1;

hw/9pfs/9p-util.h

@@ -13,6 +13,12 @@
 #ifndef QEMU_9P_UTIL_H
 #define QEMU_9P_UTIL_H
 
+#ifdef O_PATH
+#define O_PATH_9P_UTIL O_PATH
+#else
+#define O_PATH_9P_UTIL 0
+#endif
+
 static inline void close_preserve_errno(int fd)
 {
     int serrno = errno;
@@ -22,13 +28,8 @@ static inline void close_preserve_errno(int fd)
 
 static inline int openat_dir(int dirfd, const char *name)
 {
-#ifdef O_PATH
-#define OPENAT_DIR_O_PATH O_PATH
-#else
-#define OPENAT_DIR_O_PATH 0
-#endif
     return openat(dirfd, name,
-                  O_DIRECTORY | O_RDONLY | O_NOFOLLOW | OPENAT_DIR_O_PATH);
+                  O_DIRECTORY | O_RDONLY | O_NOFOLLOW | O_PATH_9P_UTIL);
 }
 
 static inline int openat_file(int dirfd, const char *name, int flags,
@@ -43,9 +44,14 @@ static inline int openat_file(int dirfd, const char *name, int flags,
     }
 
     serrno = errno;
-    /* O_NONBLOCK was only needed to open the file. Let's drop it. */
-    ret = fcntl(fd, F_SETFL, flags);
-    assert(!ret);
+    /* O_NONBLOCK was only needed to open the file. Let's drop it. We don't
+     * do that with O_PATH since fcntl(F_SETFL) isn't supported, and openat()
+     * ignored it anyway.
+     */
+    if (!(flags & O_PATH_9P_UTIL)) {
+        ret = fcntl(fd, F_SETFL, flags);
+        assert(!ret);
+    }
     errno = serrno;
     return fd;
 }

hw/9pfs/9p-xattr.c

@@ -108,6 +108,7 @@ ssize_t v9fs_list_xattr(FsContext *ctx, const char *path,
     g_free(name);
     close_preserve_errno(dirfd);
     if (xattr_len < 0) {
+        g_free(orig_value);
         return -1;
     }
 

hw/9pfs/9p.c

@@ -539,14 +539,15 @@ static void coroutine_fn virtfs_reset(V9fsPDU *pdu)
 
     /* Free all fids */
     while (s->fid_list) {
+        /* Get fid */
         fidp = s->fid_list;
-        s->fid_list = fidp->next;
+        fidp->ref++;
 
-        if (fidp->ref) {
-            fidp->clunked = 1;
-        } else {
-            free_fid(pdu, fidp);
-        }
+        /* Clunk fid */
+        s->fid_list = fidp->next;
+        fidp->clunked = 1;
+
+        put_fid(pdu, fidp);
     }
 }
 
@@ -2387,8 +2388,10 @@ static void coroutine_fn v9fs_flush(void *opaque)
          * Wait for pdu to complete.
          */
         qemu_co_queue_wait(&cancel_pdu->complete, NULL);
-        cancel_pdu->cancelled = 0;
-        pdu_free(cancel_pdu);
+        if (!qemu_co_queue_next(&cancel_pdu->complete)) {
+            cancel_pdu->cancelled = 0;
+            pdu_free(cancel_pdu);
+        }
     }
     pdu_complete(pdu, 7);
 }

hw/acpi/piix4.c

@@ -385,7 +385,10 @@ static void piix4_device_plug_cb(HotplugHandler *hotplug_dev,
                                 dev, errp);
         }
     } else if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) {
-        acpi_pcihp_device_plug_cb(hotplug_dev, &s->acpi_pci_hotplug, dev, errp);
+        if (!xen_enabled()) {
+            acpi_pcihp_device_plug_cb(hotplug_dev, &s->acpi_pci_hotplug, dev,
+                                      errp);
+        }
     } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) {
         if (s->cpu_hotplug_legacy) {
             legacy_acpi_cpu_plug_cb(hotplug_dev, &s->gpe_cpu, dev, errp);
@@ -408,8 +411,10 @@ static void piix4_device_unplug_request_cb(HotplugHandler *hotplug_dev,
         acpi_memory_unplug_request_cb(hotplug_dev, &s->acpi_memory_hotplug,
                                       dev, errp);
     } else if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) {
-        acpi_pcihp_device_unplug_cb(hotplug_dev, &s->acpi_pci_hotplug, dev,
-                                    errp);
+        if (!xen_enabled()) {
+            acpi_pcihp_device_unplug_cb(hotplug_dev, &s->acpi_pci_hotplug, dev,
+                                        errp);
+        }
     } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU) &&
                !s->cpu_hotplug_legacy) {
         acpi_cpu_unplug_request_cb(hotplug_dev, &s->cpuhp_state, dev, errp);
@@ -700,7 +705,7 @@ static void piix4_pm_class_init(ObjectClass *klass, void *data)
      * Reason: part of PIIX4 southbridge, needs to be wired up,
      * e.g. by mips_malta_init()
      */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
     dc->hotpluggable = false;
     hc->plug = piix4_device_plug_cb;
     hc->unplug_request = piix4_device_unplug_request_cb;

hw/acpi/tco.c

@@ -75,8 +75,6 @@ static void tco_timer_expired(void *opaque)
 
     if (pm->smi_en & ICH9_PMIO_SMI_EN_TCO_EN) {
         ich9_generate_smi();
-    } else {
-        ich9_generate_nmi();
     }
     tr->tco.rld = tr->tco.tmr;
     tco_timer_reload(tr);

hw/arm/spitz.c

@@ -1076,7 +1076,7 @@ static void sl_nand_class_init(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_sl_nand_info;
     dc->props = sl_nand_properties;
     /* Reason: init() method uses drive_get() */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo sl_nand_info = {

hw/audio/marvell_88w8618.c

@@ -292,7 +292,7 @@ static void mv88w8618_audio_class_init(ObjectClass *klass, void *data)
     dc->vmsd = &mv88w8618_audio_vmsd;
     dc->props = mv88w8618_audio_properties;
     /* Reason: pointer property "wm8750" */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo mv88w8618_audio_info = {

hw/audio/pcspk.c

@@ -223,7 +223,7 @@ static void pcspk_class_initfn(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_spk;
     dc->props = pcspk_properties;
     /* Reason: realize sets global pcspk_state */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo pcspk_info = {

hw/block/xen_disk.c

@@ -1082,7 +1082,7 @@ static int blk_connect(struct XenDevice *xendev)
 
         if (strcmp(blkdev->fileproto, "<unset>")) {
             options = qdict_new();
-            qdict_put(options, "driver", qstring_from_str(blkdev->fileproto));
+            qdict_put_str(options, "driver", blkdev->fileproto);
         }
 
         /* setup via xenbus -> create new block driver instance */

hw/char/virtio-serial-bus.c

@@ -1121,6 +1121,9 @@ static void virtio_serial_device_unrealize(DeviceState *dev, Error **errp)
         timer_free(vser->post_load->timer);
         g_free(vser->post_load);
     }
+
+    qbus_set_hotplug_handler(BUS(&vser->bus), NULL, errp);
+
     virtio_cleanup(vdev);
 }
 

hw/core/or-irq.c

@@ -91,7 +91,7 @@ static void or_irq_class_init(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_or_irq;
 
     /* Reason: Needs to be wired up to work, e.g. see stm32f205_soc.c */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo or_irq_type_info = {

hw/core/qdev-properties-system.c

@@ -124,8 +124,12 @@ static void release_drive(Object *obj, const char *name, void *opaque)
     BlockBackend **ptr = qdev_get_prop_ptr(dev, prop);
 
     if (*ptr) {
+        AioContext *ctx = blk_get_aio_context(*ptr);
+
+        aio_context_acquire(ctx);
         blockdev_auto_del(*ptr);
         blk_detach_dev(*ptr, dev);
+        aio_context_release(ctx);
     }
 }
 

hw/core/qdev.c

@@ -1159,6 +1159,7 @@ static void device_class_init(ObjectClass *class, void *data)
      * should override it in their class_init()
      */
     dc->hotpluggable = true;
+    dc->user_creatable = true;
 }
 
 void device_reset(DeviceState *dev)

hw/core/register.c

@@ -288,7 +288,7 @@ static void register_class_init(ObjectClass *oc, void *data)
     DeviceClass *dc = DEVICE_CLASS(oc);
 
     /* Reason: needs to be wired up to work */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo register_info = {

hw/cpu/core.c

@@ -33,6 +33,11 @@ static void core_prop_set_core_id(Object *obj, Visitor *v, const char *name,
         return;
     }
 
+    if (value < 0) {
+        error_setg(errp, "Invalid core id %"PRId64, value);
+        return;
+    }
+
     core->core_id = value;
 }
 

hw/display/qxl.c

@@ -26,6 +26,7 @@
 #include "qemu/queue.h"
 #include "qemu/atomic.h"
 #include "sysemu/sysemu.h"
+#include "migration/migration.h"
 #include "trace.h"
 
 #include "qxl.h"
@@ -639,6 +640,30 @@ static int interface_get_command(QXLInstance *sin, struct QXLCommandExt *ext)
         qxl->guest_primary.commands++;
         qxl_track_command(qxl, ext);
         qxl_log_command(qxl, "cmd", ext);
+        {
+            /*
+             * Windows 8 drivers place qxl commands in the vram
+             * (instead of the ram) bar.  We can't live migrate such a
+             * guest, so add a migration blocker in case we detect
+             * this, to avoid triggering the assert in pre_save().
+             *
+             * https://cgit.freedesktop.org/spice/win32/qxl-wddm-dod/commit/?id=f6e099db39e7d0787f294d5fd0dce328b5210faa
+             */
+            void *msg = qxl_phys2virt(qxl, ext->cmd.data, ext->group_id);
+            if (msg != NULL && (
+                    msg < (void *)qxl->vga.vram_ptr ||
+                    msg > ((void *)qxl->vga.vram_ptr + qxl->vga.vram_size))) {
+                if (!qxl->migration_blocker) {
+                    Error *local_err = NULL;
+                    error_setg(&qxl->migration_blocker,
+                               "qxl: guest bug: command not in ram bar");
+                    migrate_add_blocker(qxl->migration_blocker, &local_err);
+                    if (local_err) {
+                        error_report_err(local_err);
+                    }
+                }
+            }
+        }
         trace_qxl_ring_command_get(qxl->id, qxl_mode_to_string(qxl->mode));
         return true;
     default:
@@ -1146,6 +1171,7 @@ static void qxl_enter_vga_mode(PCIQXLDevice *d)
     update_displaychangelistener(&d->ssd.dcl, GUI_REFRESH_INTERVAL_DEFAULT);
     qemu_spice_create_host_primary(&d->ssd);
     d->mode = QXL_MODE_VGA;
+    qemu_spice_display_switch(&d->ssd, d->ssd.ds);
     vga_dirty_log_start(&d->vga);
     graphic_hw_update(d->vga.con);
 }
@@ -1235,6 +1261,12 @@ static void qxl_hard_reset(PCIQXLDevice *d, int loadvm)
     qemu_spice_create_host_memslot(&d->ssd);
     qxl_soft_reset(d);
 
+    if (d->migration_blocker) {
+        migrate_del_blocker(d->migration_blocker);
+        error_free(d->migration_blocker);
+        d->migration_blocker = NULL;
+    }
+
     if (startstop) {
         qemu_spice_display_start();
     }

hw/display/qxl.h

@@ -40,6 +40,7 @@ typedef struct PCIQXLDevice {
     uint32_t           cmdlog;
 
     uint32_t           guest_bug;
+    Error              *migration_blocker;
 
     enum qxl_mode      mode;
     uint32_t           cmdflags;

hw/dma/i8257.c

@@ -601,7 +601,7 @@ static void i8257_class_init(ObjectClass *klass, void *data)
     idc->schedule = i8257_dma_schedule;
     idc->register_channel = i8257_dma_register_channel;
     /* Reason: needs to be wired up by isa_bus_dma() to work */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo i8257_info = {

hw/dma/sparc32_dma.c

@@ -305,7 +305,7 @@ static void sparc32_dma_class_init(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_dma;
     dc->props = sparc32_dma_properties;
     /* Reason: pointer property "iommu_opaque" */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo sparc32_dma_info = {

hw/gpio/omap_gpio.c

@@ -773,7 +773,7 @@ static void omap_gpio_class_init(ObjectClass *klass, void *data)
     dc->reset = omap_gpif_reset;
     dc->props = omap_gpio_properties;
     /* Reason: pointer property "clk" */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo omap_gpio_info = {
@@ -804,7 +804,7 @@ static void omap2_gpio_class_init(ObjectClass *klass, void *data)
     dc->reset = omap2_gpif_reset;
     dc->props = omap2_gpio_properties;
     /* Reason: pointer properties "iclk", "fclk0", ..., "fclk5" */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo omap2_gpio_info = {

hw/i2c/omap_i2c.c

@@ -491,7 +491,7 @@ static void omap_i2c_class_init(ObjectClass *klass, void *data)
     dc->props = omap_i2c_properties;
     dc->reset = omap_i2c_reset;
     /* Reason: pointer properties "iclk", "fclk" */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
     dc->realize = omap_i2c_realize;
 }
 

hw/i2c/smbus_eeprom.c

@@ -123,7 +123,7 @@ static void smbus_eeprom_class_initfn(ObjectClass *klass, void *data)
     sc->read_data = eeprom_read_data;
     dc->props = smbus_eeprom_properties;
     /* Reason: pointer property "data" */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo smbus_eeprom_info = {

hw/i2c/smbus_ich9.c

@@ -103,7 +103,7 @@ static void ich9_smb_class_init(ObjectClass *klass, void *data)
      * Reason: part of ICH9 southbridge, needs to be wired up by
      * pc_q35_init()
      */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 I2CBus *ich9_smb_init(PCIBus *bus, int devfn, uint32_t smb_io_base)

hw/i386/acpi-build.c

@@ -1818,9 +1818,9 @@ static Aml *build_q35_osc_method(void)
 
     /*
      * Always allow native PME, AER (no dependencies)
-     * Never allow SHPC (no SHPC controller in this system)
+     * Allow SHPC (PCI bridges can have SHPC controller)
      */
-    aml_append(if_ctx, aml_and(a_ctrl, aml_int(0x1D), a_ctrl));
+    aml_append(if_ctx, aml_and(a_ctrl, aml_int(0x1F), a_ctrl));
 
     if_ctx2 = aml_if(aml_lnot(aml_equal(aml_arg(1), aml_int(1))));
     /* Unknown revision */

hw/i386/pc.c

@@ -597,7 +597,7 @@ static void port92_class_initfn(ObjectClass *klass, void *data)
      * wiring: its A20 output line needs to be wired up by
      * port92_init().
      */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo port92_info = {

hw/input/hid.c

@@ -483,6 +483,7 @@ void hid_reset(HIDState *hs)
         memset(hs->kbd.keycodes, 0, sizeof(hs->kbd.keycodes));
         memset(hs->kbd.key, 0, sizeof(hs->kbd.key));
         hs->kbd.keys = 0;
+        hs->kbd.modifiers = 0;
         break;
     case HID_MOUSE:
     case HID_TABLET:

hw/input/vmmouse.c

@@ -286,7 +286,7 @@ static void vmmouse_class_initfn(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_vmmouse;
     dc->props = vmmouse_properties;
     /* Reason: pointer property "ps2_mouse" */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo vmmouse_info = {

hw/intc/apic_common.c

@@ -501,7 +501,7 @@ static void apic_common_class_init(ObjectClass *klass, void *data)
      * Reason: APIC and CPU need to be wired up by
      * x86_cpu_apic_create()
      */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo apic_common_type = {

hw/intc/arm_gicv3_kvm.c

@@ -614,12 +614,6 @@ static void arm_gicv3_icc_reset(CPUARMState *env, const ARMCPRegInfo *ri)
     s = c->gic;
     cpu = ARM_CPU(c->cpu);
 
-    /* Initialize to actual HW supported configuration */
-    kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS,
-                      KVM_VGIC_ATTR(ICC_CTLR_EL1, cpu->mp_affinity),
-                      &c->icc_ctlr_el1[GICV3_NS], false);
-
-    c->icc_ctlr_el1[GICV3_S] = c->icc_ctlr_el1[GICV3_NS];
     c->icc_pmr_el1 = 0;
     c->icc_bpr[GICV3_G0] = GIC_MIN_BPR;
     c->icc_bpr[GICV3_G1] = GIC_MIN_BPR;
@@ -628,6 +622,17 @@ static void arm_gicv3_icc_reset(CPUARMState *env, const ARMCPRegInfo *ri)
     c->icc_sre_el1 = 0x7;
     memset(c->icc_apr, 0, sizeof(c->icc_apr));
     memset(c->icc_igrpen, 0, sizeof(c->icc_igrpen));
+
+    if (s->migration_blocker) {
+        return;
+    }
+
+    /* Initialize to actual HW supported configuration */
+    kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS,
+                      KVM_VGIC_ATTR(ICC_CTLR_EL1, cpu->mp_affinity),
+                      &c->icc_ctlr_el1[GICV3_NS], false);
+
+    c->icc_ctlr_el1[GICV3_S] = c->icc_ctlr_el1[GICV3_NS];
 }
 
 static void kvm_arm_gicv3_reset(DeviceState *dev)

hw/intc/etraxfs_pic.c

@@ -173,7 +173,7 @@ static void etraxfs_pic_class_init(ObjectClass *klass, void *data)
     dc->props = etraxfs_pic_properties;
     /*
      * Note: pointer property "interrupt_vector" may remain null, thus
-     * no need for dc->cannot_instantiate_with_device_add_yet = true;
+     * no need for dc->user_creatable = false;
      */
 }
 

hw/intc/grlib_irqmp.c

@@ -360,7 +360,7 @@ static void grlib_irqmp_class_init(ObjectClass *klass, void *data)
     dc->reset = grlib_irqmp_reset;
     dc->props = grlib_irqmp_properties;
     /* Reason: pointer properties "set_pil_in", "set_pil_in_opaque" */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
     dc->realize = grlib_irqmp_realize;
 }
 

hw/intc/i8259_common.c

@@ -144,7 +144,7 @@ static void pic_common_class_init(ObjectClass *klass, void *data)
      * wiring of the slave to the master is hard-coded in device model
      * code.
      */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo pic_common_type = {

hw/intc/nios2_iic.c

@@ -80,7 +80,7 @@ static void altera_iic_class_init(ObjectClass *klass, void *data)
     DeviceClass *dc = DEVICE_CLASS(klass);
 
     /* Reason: needs to be wired up, e.g. by nios2_10m50_ghrd_init() */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
     dc->realize = altera_iic_realize;
 }
 

hw/intc/omap_intc.c

@@ -401,7 +401,7 @@ static void omap_intc_class_init(ObjectClass *klass, void *data)
     dc->reset = omap_inth_reset;
     dc->props = omap_intc_properties;
     /* Reason: pointer property "clk" */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
     dc->realize = omap_intc_realize;
 }
 
@@ -656,7 +656,7 @@ static void omap2_intc_class_init(ObjectClass *klass, void *data)
     dc->reset = omap_inth_reset;
     dc->props = omap2_intc_properties;
     /* Reason: pointer property "iclk", "fclk" */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
     dc->realize = omap2_intc_realize;
 }
 

hw/ipmi/isa_ipmi_bt.c

@@ -37,40 +37,30 @@
 #define IPMI_BT_HBUSY_BIT          6
 #define IPMI_BT_BBUSY_BIT          7
 
-#define IPMI_BT_CLR_WR_MASK        (1 << IPMI_BT_CLR_WR_BIT)
 #define IPMI_BT_GET_CLR_WR(d)      (((d) >> IPMI_BT_CLR_WR_BIT) & 0x1)
-#define IPMI_BT_SET_CLR_WR(d, v)   (d) = (((d) & ~IPMI_BT_CLR_WR_MASK) | \
-                                       (((v & 1) << IPMI_BT_CLR_WR_BIT)))
 
-#define IPMI_BT_CLR_RD_MASK        (1 << IPMI_BT_CLR_RD_BIT)
 #define IPMI_BT_GET_CLR_RD(d)      (((d) >> IPMI_BT_CLR_RD_BIT) & 0x1)
-#define IPMI_BT_SET_CLR_RD(d, v)   (d) = (((d) & ~IPMI_BT_CLR_RD_MASK) | \
-                                       (((v & 1) << IPMI_BT_CLR_RD_BIT)))
 
-#define IPMI_BT_H2B_ATN_MASK       (1 << IPMI_BT_H2B_ATN_BIT)
 #define IPMI_BT_GET_H2B_ATN(d)     (((d) >> IPMI_BT_H2B_ATN_BIT) & 0x1)
-#define IPMI_BT_SET_H2B_ATN(d, v)  (d) = (((d) & ~IPMI_BT_H2B_ATN_MASK) | \
-                                        (((v & 1) << IPMI_BT_H2B_ATN_BIT)))
 
 #define IPMI_BT_B2H_ATN_MASK       (1 << IPMI_BT_B2H_ATN_BIT)
 #define IPMI_BT_GET_B2H_ATN(d)     (((d) >> IPMI_BT_B2H_ATN_BIT) & 0x1)
-#define IPMI_BT_SET_B2H_ATN(d, v)  (d) = (((d) & ~IPMI_BT_B2H_ATN_MASK) | \
-                                        (((v & 1) << IPMI_BT_B2H_ATN_BIT)))
+#define IPMI_BT_SET_B2H_ATN(d, v)  ((d) = (((d) & ~IPMI_BT_B2H_ATN_MASK) | \
+                                        (((v) & 1) << IPMI_BT_B2H_ATN_BIT)))
 
 #define IPMI_BT_SMS_ATN_MASK       (1 << IPMI_BT_SMS_ATN_BIT)
 #define IPMI_BT_GET_SMS_ATN(d)     (((d) >> IPMI_BT_SMS_ATN_BIT) & 0x1)
-#define IPMI_BT_SET_SMS_ATN(d, v)  (d) = (((d) & ~IPMI_BT_SMS_ATN_MASK) | \
-                                        (((v & 1) << IPMI_BT_SMS_ATN_BIT)))
+#define IPMI_BT_SET_SMS_ATN(d, v)  ((d) = (((d) & ~IPMI_BT_SMS_ATN_MASK) | \
+                                        (((v) & 1) << IPMI_BT_SMS_ATN_BIT)))
 
 #define IPMI_BT_HBUSY_MASK         (1 << IPMI_BT_HBUSY_BIT)
 #define IPMI_BT_GET_HBUSY(d)       (((d) >> IPMI_BT_HBUSY_BIT) & 0x1)
-#define IPMI_BT_SET_HBUSY(d, v)    (d) = (((d) & ~IPMI_BT_HBUSY_MASK) | \
-                                       (((v & 1) << IPMI_BT_HBUSY_BIT)))
+#define IPMI_BT_SET_HBUSY(d, v)    ((d) = (((d) & ~IPMI_BT_HBUSY_MASK) | \
+                                       (((v) & 1) << IPMI_BT_HBUSY_BIT)))
 
 #define IPMI_BT_BBUSY_MASK         (1 << IPMI_BT_BBUSY_BIT)
-#define IPMI_BT_GET_BBUSY(d)       (((d) >> IPMI_BT_BBUSY_BIT) & 0x1)
-#define IPMI_BT_SET_BBUSY(d, v)    (d) = (((d) & ~IPMI_BT_BBUSY_MASK) | \
-                                       (((v & 1) << IPMI_BT_BBUSY_BIT)))
+#define IPMI_BT_SET_BBUSY(d, v)    ((d) = (((d) & ~IPMI_BT_BBUSY_MASK) | \
+                                       (((v) & 1) << IPMI_BT_BBUSY_BIT)))
 
 
 /* Mask register */
@@ -79,13 +69,13 @@
 
 #define IPMI_BT_B2H_IRQ_EN_MASK      (1 << IPMI_BT_B2H_IRQ_EN_BIT)
 #define IPMI_BT_GET_B2H_IRQ_EN(d)    (((d) >> IPMI_BT_B2H_IRQ_EN_BIT) & 0x1)
-#define IPMI_BT_SET_B2H_IRQ_EN(d, v) (d) = (((d) & ~IPMI_BT_B2H_IRQ_EN_MASK) | \
-                                        (((v & 1) << IPMI_BT_B2H_IRQ_EN_BIT)))
+#define IPMI_BT_SET_B2H_IRQ_EN(d, v) ((d) = (((d) & ~IPMI_BT_B2H_IRQ_EN_MASK) |\
+                                        (((v) & 1) << IPMI_BT_B2H_IRQ_EN_BIT)))
 
 #define IPMI_BT_B2H_IRQ_MASK         (1 << IPMI_BT_B2H_IRQ_BIT)
 #define IPMI_BT_GET_B2H_IRQ(d)       (((d) >> IPMI_BT_B2H_IRQ_BIT) & 0x1)
-#define IPMI_BT_SET_B2H_IRQ(d, v)    (d) = (((d) & ~IPMI_BT_B2H_IRQ_MASK) | \
-                                        (((v & 1) << IPMI_BT_B2H_IRQ_BIT)))
+#define IPMI_BT_SET_B2H_IRQ(d, v)    ((d) = (((d) & ~IPMI_BT_B2H_IRQ_MASK) | \
+                                        (((v) & 1) << IPMI_BT_B2H_IRQ_BIT)))
 
 typedef struct IPMIBT {
     IPMIBmc *bmc;

hw/isa/lpc_ich9.c

@@ -312,11 +312,6 @@ void ich9_generate_smi(void)
     cpu_interrupt(first_cpu, CPU_INTERRUPT_SMI);
 }
 
-void ich9_generate_nmi(void)
-{
-    cpu_interrupt(first_cpu, CPU_INTERRUPT_NMI);
-}
-
 static int ich9_lpc_sci_irq(ICH9LPCState *lpc)
 {
     switch (lpc->d.config[ICH9_LPC_ACPI_CTRL] &
@@ -810,7 +805,7 @@ static void ich9_lpc_class_init(ObjectClass *klass, void *data)
      * Reason: part of ICH9 southbridge, needs to be wired up by
      * pc_q35_init()
      */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
     hc->plug = ich9_pm_device_plug_cb;
     hc->unplug_request = ich9_pm_device_unplug_request_cb;
     hc->unplug = ich9_pm_device_unplug_cb;

hw/isa/piix4.c

@@ -123,7 +123,7 @@ static void piix4_class_init(ObjectClass *klass, void *data)
      * Reason: part of PIIX4 southbridge, needs to be wired up,
      * e.g. by mips_malta_init()
      */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
     dc->hotpluggable = false;
 }
 

hw/isa/vt82c686.c

@@ -494,7 +494,7 @@ static void via_class_init(ObjectClass *klass, void *data)
      * Reason: part of VIA VT82C686 southbridge, needs to be wired up,
      * e.g. by mips_fulong2e_init()
      */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo via_info = {

hw/mips/gt64xxx_pci.c

@@ -1224,7 +1224,7 @@ static void gt64120_pci_class_init(ObjectClass *klass, void *data)
      * PCI-facing part of the host bridge, not usable without the
      * host-facing part, which can't be device_add'ed, yet.
      */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo gt64120_pci_info = {

hw/misc/vmport.c

@@ -163,7 +163,7 @@ static void vmport_class_initfn(ObjectClass *klass, void *data)
 
     dc->realize = vmport_realizefn;
     /* Reason: realize sets global port_state */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo vmport_info = {

hw/net/dp8393x.c

@@ -934,7 +934,7 @@ static void dp8393x_class_init(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_dp8393x;
     dc->props = dp8393x_properties;
     /* Reason: dma_mr property can't be set */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo dp8393x_info = {

hw/net/e1000.c

@@ -40,7 +40,7 @@
 
 static const uint8_t bcast[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
 
-#define E1000_DEBUG
+/* #define E1000_DEBUG */
 
 #ifdef E1000_DEBUG
 enum {

hw/net/e1000e_core.c

@@ -2454,14 +2454,20 @@ e1000e_set_ics(E1000ECore *core, int index, uint32_t val)
 static void
 e1000e_set_icr(E1000ECore *core, int index, uint32_t val)
 {
+    uint32_t icr = 0;
     if ((core->mac[ICR] & E1000_ICR_ASSERTED) &&
         (core->mac[CTRL_EXT] & E1000_CTRL_EXT_IAME)) {
         trace_e1000e_irq_icr_process_iame();
         e1000e_clear_ims_bits(core, core->mac[IAM]);
     }
 
-    trace_e1000e_irq_icr_write(val, core->mac[ICR], core->mac[ICR] & ~val);
-    core->mac[ICR] &= ~val;
+    icr = core->mac[ICR] & ~val;
+    /* Windows driver expects that the "receive overrun" bit and other
+     * ones to be cleared when the "Other" bit (#24) is cleared.
+     */
+    icr = (val & E1000_ICR_OTHER) ? (icr & ~E1000_ICR_OTHER_CAUSES) : icr;
+    trace_e1000e_irq_icr_write(val, core->mac[ICR], icr);
+    core->mac[ICR] = icr;
     e1000e_update_interrupt_state(core);
 }
 

hw/net/etraxfs_eth.c

@@ -630,7 +630,7 @@ static void etraxfs_eth_class_init(ObjectClass *klass, void *data)
     k->init = fs_eth_init;
     dc->props = etraxfs_eth_properties;
     /* Reason: pointer properties "dma_out", "dma_in" */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo etraxfs_eth_info = {

hw/net/lance.c

@@ -165,7 +165,7 @@ static void lance_class_init(ObjectClass *klass, void *data)
     dc->vmsd = &vmstate_lance;
     dc->props = lance_properties;
     /* Reason: pointer property "dma" */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo lance_info = {

hw/net/virtio-net.c

@@ -510,6 +510,10 @@ static int peer_attach(VirtIONet *n, int index)
         return 0;
     }
 
+    if (n->max_queues == 1) {
+        return 0;
+    }
+
     return tap_enable(nc->peer);
 }
 
@@ -719,6 +723,8 @@ static int virtio_net_handle_offloads(VirtIONet *n, uint8_t cmd,
     if (cmd == VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET) {
         uint64_t supported_offloads;
 
+        offloads = virtio_ldq_p(vdev, &offloads);
+
         if (!n->has_vnet_hdr) {
             return VIRTIO_NET_ERR;
         }
@@ -1518,9 +1524,12 @@ static void virtio_net_del_queue(VirtIONet *n, int index)
     if (q->tx_timer) {
         timer_del(q->tx_timer);
         timer_free(q->tx_timer);
+        q->tx_timer = NULL;
     } else {
         qemu_bh_delete(q->tx_bh);
+        q->tx_bh = NULL;
     }
+    q->tx_waiting = 0;
     virtio_del_queue(vdev, index * 2 + 1);
 }
 

hw/pci-bridge/dec.c

@@ -128,7 +128,7 @@ static void dec_21154_pci_host_class_init(ObjectClass *klass, void *data)
      * PCI-facing part of the host bridge, not usable without the
      * host-facing part, which can't be device_add'ed, yet.
      */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
 }
 
 static const TypeInfo dec_21154_pci_host_info = {

hw/pci-bridge/pci_expander_bridge.c

@@ -150,7 +150,7 @@ static void pxb_host_class_init(ObjectClass *class, void *data)
 
     dc->fw_name = "pci";
     /* Reason: Internal part of the pxb/pxb-pcie device, not usable by itself */
-    dc->cannot_instantiate_with_device_add_yet = true;
+    dc->user_creatable = false;
     sbc->explicit_ofw_unit_address = pxb_host_ofw_unit_address;
     hc->root_bus_path = pxb_host_root_bus_path;
 }