SMBIOS: Build aggregate smbios tables and entry point

Build an aggregate set of smbios tables and an entry point structure.

Insert tables and entry point into fw_cfg respectively under
"etc/smbios/smbios-tables" and "etc/smbios/smbios-anchor".

Machine types <= 2.0 will for now continue using field-by-field
overrides to SeaBIOS defaults, but for machine types 2.1 and up we
expect the BIOS to look for and use the aggregate tables generated
by this patch.

Signed-off-by: Gabriel Somlo <somlo@cmu.edu>

[ kraxel: fix 32bit build ]

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>

.gitignore

@@ -18,8 +18,8 @@
 /*-darwin-user
 /*-linux-user
 /*-bsd-user
-libdis*
+/libdis*
-libuser
+/libuser
 /linux-headers/asm
 /qga/qapi-generated
 /qapi-generated
@@ -49,19 +49,9 @@ libuser
 /qemu-monitor.texi
 /qmp-commands.txt
 /vscclient
-/test-bitops
-/test-coroutine
-/test-int128
-/test-opts-visitor
-/test-qmp-input-visitor
-/test-qmp-output-visitor
-/test-string-input-visitor
-/test-string-output-visitor
-/test-visitor-serialization
 /fsdev/virtfs-proxy-helper
 /fsdev/virtfs-proxy-helper.1
 /fsdev/virtfs-proxy-helper.pod
-/.gdbinit
 *.a
 *.aux
 *.cp
@@ -90,12 +80,8 @@ libuser
 *.pc
 .libs
 .sdk
-*.swp
-*.orig
-.pc
 *.gcda
 *.gcno
-patches
 /pc-bios/bios-pq/status
 /pc-bios/vgabios-pq/status
 /pc-bios/optionrom/linuxboot.asm

MAINTAINERS

@@ -304,7 +304,7 @@ S: Maintained
 F: hw/*/versatile*
 
 Xilinx Zynq
-M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
+M: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
 S: Maintained
 F: hw/arm/xilinx_zynq.c
 F: hw/misc/zynq_slcr.c
@@ -353,7 +353,7 @@ S: Maintained
 F: hw/microblaze/petalogix_s3adsp1800_mmu.c
 
 petalogix_ml605
-M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
+M: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
 S: Maintained
 F: hw/microblaze/petalogix_ml605_mmu.c
 
@@ -592,7 +592,7 @@ S: Orphan
 F: hw/scsi/lsi53c895a.c
 
 SSI
-M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
+M: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
 S: Maintained
 F: hw/ssi/*
 F: hw/block/m25p80.c
@@ -623,6 +623,7 @@ M: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
 S: Supported
 F: hw/9pfs/
 F: fsdev/
+F: tests/virtio-9p-test.c
 T: git git://github.com/kvaneesh/QEMU.git
 
 virtio-blk
@@ -648,9 +649,10 @@ nvme
 M: Keith Busch <keith.busch@intel.com>
 S: Supported
 F: hw/block/nvme*
+F: tests/nvme-test.c
 
 Xilinx EDK
-M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
+M: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
 M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
 S: Maintained
 F: hw/*/xilinx_*
@@ -672,6 +674,8 @@ S: Supported
 F: block*
 F: block/
 F: hw/block/
+F: qemu-img*
+F: qemu-io*
 T: git git://repo.or.cz/qemu/kevin.git block
 T: git git://github.com/stefanha/qemu.git block
 
@@ -694,7 +698,7 @@ F: include/hw/cpu/icc_bus.h
 F: hw/cpu/icc_bus.c
 
 Device Tree
-M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
+M: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
 M: Alexander Graf <agraf@suse.de>
 S: Maintained
 F: device_tree.[ch]
@@ -715,7 +719,8 @@ F: hw/display/qxl*
 
 Graphics
 M: Anthony Liguori <aliguori@amazon.com>
-S: Maintained
+M: Gerd Hoffmann <kraxel@redhat.com>
+S: Odd Fixes
 F: ui/
 
 Cocoa graphics

Makefile

@@ -133,6 +133,7 @@ dummy := $(call unnest-vars,, \
                 stub-obj-y \
                 util-obj-y \
                 qga-obj-y \
+                qga-vss-dll-obj-y \
                 block-obj-y \
                 block-obj-m \
                 common-obj-y \
@@ -376,7 +377,7 @@ endif
 ifneq ($(CONFIG_MODULES),)
 	$(INSTALL_DIR) "$(DESTDIR)$(qemu_moddir)"
 	for s in $(patsubst %.mo,%$(DSOSUF),$(modules-m)); do \
-		$(INSTALL_PROG) $(STRIP_OPT) $$s "$(DESTDIR)$(qemu_moddir)/$${s//\//-}"; \
+		$(INSTALL_PROG) $(STRIP_OPT) $$s "$(DESTDIR)$(qemu_moddir)/$$(echo $$s | tr / -)"; \
 	done
 endif
 ifneq ($(HELPERS-y),)

VERSION

@@ -1 +1 @@
-1.7.90
+2.0.50

block-migration.c

@@ -310,13 +310,28 @@ static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds)
 
 /* Called with iothread lock taken.  */
 
-static void set_dirty_tracking(void)
+static int set_dirty_tracking(void)
 {
     BlkMigDevState *bmds;
+    int ret;
 
     QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
-        bmds->dirty_bitmap = bdrv_create_dirty_bitmap(bmds->bs, BLOCK_SIZE);
+        bmds->dirty_bitmap = bdrv_create_dirty_bitmap(bmds->bs, BLOCK_SIZE,
+                                                      NULL);
+        if (!bmds->dirty_bitmap) {
+            ret = -errno;
+            goto fail;
+        }
     }
+    return 0;
+
+fail:
+    QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
+        if (bmds->dirty_bitmap) {
+            bdrv_release_dirty_bitmap(bmds->bs, bmds->dirty_bitmap);
+        }
+    }
+    return ret;
 }
 
 static void unset_dirty_tracking(void)
@@ -611,10 +626,17 @@ static int block_save_setup(QEMUFile *f, void *opaque)
             block_mig_state.submitted, block_mig_state.transferred);
 
     qemu_mutex_lock_iothread();
-    init_blk_migration(f);
 
     /* start track dirty blocks */
-    set_dirty_tracking();
+    ret = set_dirty_tracking();
+
+    if (ret) {
+        qemu_mutex_unlock_iothread();
+        return ret;
+    }
+
+    init_blk_migration(f);
+
     qemu_mutex_unlock_iothread();
 
     ret = flush_blks(f);

block.c

@@ -332,10 +332,21 @@ void bdrv_register(BlockDriver *bdrv)
 }
 
 /* create a new block device (by default it is empty) */
-BlockDriverState *bdrv_new(const char *device_name)
+BlockDriverState *bdrv_new(const char *device_name, Error **errp)
 {
     BlockDriverState *bs;
 
+    if (bdrv_find(device_name)) {
+        error_setg(errp, "Device with id '%s' already exists",
+                   device_name);
+        return NULL;
+    }
+    if (bdrv_find_node(device_name)) {
+        error_setg(errp, "Device with node-name '%s' already exists",
+                   device_name);
+        return NULL;
+    }
+
     bs = g_malloc0(sizeof(BlockDriverState));
     QLIST_INIT(&bs->dirty_bitmaps);
     pstrcpy(bs->device_name, sizeof(bs->device_name), device_name);
@@ -763,10 +774,54 @@ void bdrv_disable_copy_on_read(BlockDriverState *bs)
     bs->copy_on_read--;
 }
 
+/*
+ * Returns the flags that bs->file should get, based on the given flags for
+ * the parent BDS
+ */
+static int bdrv_inherited_flags(int flags)
+{
+    /* Enable protocol handling, disable format probing for bs->file */
+    flags |= BDRV_O_PROTOCOL;
+
+    /* Our block drivers take care to send flushes and respect unmap policy,
+     * so we can enable both unconditionally on lower layers. */
+    flags |= BDRV_O_CACHE_WB | BDRV_O_UNMAP;
+
+    /* The backing file of a temporary snapshot is read-only */
+    if (flags & BDRV_O_SNAPSHOT) {
+        flags &= ~BDRV_O_RDWR;
+    }
+
+    /* Clear flags that only apply to the top layer */
+    flags &= ~(BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING | BDRV_O_COPY_ON_READ);
+
+    return flags;
+}
+
+/*
+ * Returns the flags that bs->backing_hd should get, based on the given flags
+ * for the parent BDS
+ */
+static int bdrv_backing_flags(int flags)
+{
+    /* backing files always opened read-only */
+    flags &= ~(BDRV_O_RDWR | BDRV_O_COPY_ON_READ);
+
+    /* snapshot=on is handled on the top layer */
+    flags &= ~(BDRV_O_SNAPSHOT | BDRV_O_TEMPORARY);
+
+    return flags;
+}
+
 static int bdrv_open_flags(BlockDriverState *bs, int flags)
 {
     int open_flags = flags | BDRV_O_CACHE_WB;
 
+    /* The backing file of a temporary snapshot is read-only */
+    if (flags & BDRV_O_SNAPSHOT) {
+        open_flags &= ~BDRV_O_RDWR;
+    }
+
     /*
      * Clear flags that are internal to the block layer before opening the
      * image.
@@ -776,45 +831,43 @@ static int bdrv_open_flags(BlockDriverState *bs, int flags)
     /*
      * Snapshots should be writable.
      */
-    if (bs->is_temporary) {
+    if (flags & BDRV_O_TEMPORARY) {
         open_flags |= BDRV_O_RDWR;
     }
 
     return open_flags;
 }
 
-static int bdrv_assign_node_name(BlockDriverState *bs,
+static void bdrv_assign_node_name(BlockDriverState *bs,
-                                 const char *node_name,
+                                  const char *node_name,
-                                 Error **errp)
+                                  Error **errp)
 {
     if (!node_name) {
-        return 0;
+        return;
     }
 
     /* empty string node name is invalid */
     if (node_name[0] == '\0') {
         error_setg(errp, "Empty node name");
-        return -EINVAL;
+        return;
     }
 
     /* takes care of avoiding namespaces collisions */
     if (bdrv_find(node_name)) {
         error_setg(errp, "node-name=%s is conflicting with a device id",
                    node_name);
-        return -EINVAL;
+        return;
     }
 
     /* takes care of avoiding duplicates node names */
     if (bdrv_find_node(node_name)) {
         error_setg(errp, "Duplicate node name");
-        return -EINVAL;
+        return;
     }
 
     /* copy node name into the bs and insert it into the graph list */
     pstrcpy(bs->node_name, sizeof(bs->node_name), node_name);
     QTAILQ_INSERT_TAIL(&graph_bdrv_states, bs, node_list);
-
-    return 0;
 }
 
 /*
@@ -849,9 +902,10 @@ static int bdrv_open_common(BlockDriverState *bs, BlockDriverState *file,
     trace_bdrv_open_common(bs, filename ?: "", flags, drv->format_name);
 
     node_name = qdict_get_try_str(options, "node-name");
-    ret = bdrv_assign_node_name(bs, node_name, errp);
+    bdrv_assign_node_name(bs, node_name, &local_err);
-    if (ret < 0) {
+    if (local_err) {
-        return ret;
+        error_propagate(errp, local_err);
+        return -EINVAL;
     }
     qdict_del(options, "node-name");
 
@@ -936,13 +990,6 @@ static int bdrv_open_common(BlockDriverState *bs, BlockDriverState *file,
     bdrv_refresh_limits(bs);
     assert(bdrv_opt_mem_align(bs) != 0);
     assert((bs->request_alignment != 0) || bs->sg);
-
-#ifndef _WIN32
-    if (bs->is_temporary) {
-        assert(bs->filename[0] != '\0');
-        unlink(bs->filename);
-    }
-#endif
     return 0;
 
 free_and_fail:
@@ -968,7 +1015,7 @@ static int bdrv_file_open(BlockDriverState *bs, const char *filename,
 {
     BlockDriver *drv;
     const char *drvname;
-    bool allow_protocol_prefix = false;
+    bool parse_filename = false;
     Error *local_err = NULL;
     int ret;
 
@@ -977,7 +1024,7 @@ static int bdrv_file_open(BlockDriverState *bs, const char *filename,
         filename = qdict_get_try_str(*options, "filename");
     } else if (filename && !qdict_haskey(*options, "filename")) {
         qdict_put(*options, "filename", qstring_from_str(filename));
-        allow_protocol_prefix = true;
+        parse_filename = true;
     } else {
         error_setg(errp, "Can't specify 'file' and 'filename' options at the "
                    "same time");
@@ -994,7 +1041,7 @@ static int bdrv_file_open(BlockDriverState *bs, const char *filename,
         }
         qdict_del(*options, "driver");
     } else if (filename) {
-        drv = bdrv_find_protocol(filename, allow_protocol_prefix);
+        drv = bdrv_find_protocol(filename, parse_filename);
         if (!drv) {
             error_setg(errp, "Unknown protocol");
         }
@@ -1010,7 +1057,7 @@ static int bdrv_file_open(BlockDriverState *bs, const char *filename,
     }
 
     /* Parse the filename and open it */
-    if (drv->bdrv_parse_filename && filename) {
+    if (drv->bdrv_parse_filename && parse_filename) {
         drv->bdrv_parse_filename(filename, *options, &local_err);
         if (local_err) {
             error_propagate(errp, local_err);
@@ -1053,14 +1100,14 @@ fail:
  */
 int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
 {
-    char backing_filename[PATH_MAX];
+    char *backing_filename = g_malloc0(PATH_MAX);
-    int back_flags, ret;
+    int ret = 0;
     BlockDriver *back_drv = NULL;
     Error *local_err = NULL;
 
     if (bs->backing_hd != NULL) {
         QDECREF(options);
-        return 0;
+        goto free_exit;
     }
 
     /* NULL means an empty set of options */
@@ -1073,31 +1120,26 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
         backing_filename[0] = '\0';
     } else if (bs->backing_file[0] == '\0' && qdict_size(options) == 0) {
         QDECREF(options);
-        return 0;
+        goto free_exit;
     } else {
-        bdrv_get_full_backing_filename(bs, backing_filename,
+        bdrv_get_full_backing_filename(bs, backing_filename, PATH_MAX);
-                                       sizeof(backing_filename));
     }
 
     if (bs->backing_format[0] != '\0') {
         back_drv = bdrv_find_format(bs->backing_format);
     }
 
-    /* backing files always opened read-only */
-    back_flags = bs->open_flags & ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT |
-                                    BDRV_O_COPY_ON_READ);
-
     assert(bs->backing_hd == NULL);
     ret = bdrv_open(&bs->backing_hd,
                     *backing_filename ? backing_filename : NULL, NULL, options,
-                    back_flags, back_drv, &local_err);
+                    bdrv_backing_flags(bs->open_flags), back_drv, &local_err);
     if (ret < 0) {
         bs->backing_hd = NULL;
         bs->open_flags |= BDRV_O_NO_BACKING;
         error_setg(errp, "Could not open backing file: %s",
                    error_get_pretty(local_err));
         error_free(local_err);
-        return ret;
+        goto free_exit;
     }
 
     if (bs->backing_hd->file) {
@@ -1108,7 +1150,9 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
     /* Recalculate the BlockLimits with the backing file */
     bdrv_refresh_limits(bs);
 
-    return 0;
+free_exit:
+    g_free(backing_filename);
+    return ret;
 }
 
 /*
@@ -1162,6 +1206,75 @@ done:
     return ret;
 }
 
+void bdrv_append_temp_snapshot(BlockDriverState *bs, Error **errp)
+{
+    /* TODO: extra byte is a hack to ensure MAX_PATH space on Windows. */
+    char *tmp_filename = g_malloc0(PATH_MAX + 1);
+    int64_t total_size;
+    BlockDriver *bdrv_qcow2;
+    QEMUOptionParameter *create_options;
+    QDict *snapshot_options;
+    BlockDriverState *bs_snapshot;
+    Error *local_err;
+    int ret;
+
+    /* if snapshot, we create a temporary backing file and open it
+       instead of opening 'filename' directly */
+
+    /* Get the required size from the image */
+    total_size = bdrv_getlength(bs);
+    if (total_size < 0) {
+        error_setg_errno(errp, -total_size, "Could not get image size");
+        goto out;
+    }
+    total_size &= BDRV_SECTOR_MASK;
+
+    /* Create the temporary image */
+    ret = get_tmp_filename(tmp_filename, PATH_MAX + 1);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Could not get temporary filename");
+        goto out;
+    }
+
+    bdrv_qcow2 = bdrv_find_format("qcow2");
+    create_options = parse_option_parameters("", bdrv_qcow2->create_options,
+                                             NULL);
+
+    set_option_parameter_int(create_options, BLOCK_OPT_SIZE, total_size);
+
+    ret = bdrv_create(bdrv_qcow2, tmp_filename, create_options, &local_err);
+    free_option_parameters(create_options);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Could not create temporary overlay "
+                         "'%s': %s", tmp_filename,
+                         error_get_pretty(local_err));
+        error_free(local_err);
+        goto out;
+    }
+
+    /* Prepare a new options QDict for the temporary file */
+    snapshot_options = qdict_new();
+    qdict_put(snapshot_options, "file.driver",
+              qstring_from_str("file"));
+    qdict_put(snapshot_options, "file.filename",
+              qstring_from_str(tmp_filename));
+
+    bs_snapshot = bdrv_new("", &error_abort);
+
+    ret = bdrv_open(&bs_snapshot, NULL, NULL, snapshot_options,
+                    (bs->open_flags & ~BDRV_O_SNAPSHOT) | BDRV_O_TEMPORARY,
+                    bdrv_qcow2, &local_err);
+    if (ret < 0) {
+        error_propagate(errp, local_err);
+        goto out;
+    }
+
+    bdrv_append(bs_snapshot, bs);
+
+out:
+    g_free(tmp_filename);
+}
+
 /*
  * Opens a disk image (raw, qcow2, vmdk, ...)
  *
@@ -1182,8 +1295,6 @@ int bdrv_open(BlockDriverState **pbs, const char *filename,
               BlockDriver *drv, Error **errp)
 {
     int ret;
-    /* TODO: extra byte is a hack to ensure MAX_PATH space on Windows. */
-    char tmp_filename[PATH_MAX + 1];
     BlockDriverState *file = NULL, *bs;
     const char *drvname;
     Error *local_err = NULL;
@@ -1218,7 +1329,7 @@ int bdrv_open(BlockDriverState **pbs, const char *filename,
     if (*pbs) {
         bs = *pbs;
     } else {
-        bs = bdrv_new("");
+        bs = bdrv_new("", &error_abort);
     }
 
     /* NULL means an empty set of options */
@@ -1243,74 +1354,6 @@ int bdrv_open(BlockDriverState **pbs, const char *filename,
         }
     }
 
-    /* For snapshot=on, create a temporary qcow2 overlay */
-    if (flags & BDRV_O_SNAPSHOT) {
-        BlockDriverState *bs1;
-        int64_t total_size;
-        BlockDriver *bdrv_qcow2;
-        QEMUOptionParameter *create_options;
-        QDict *snapshot_options;
-
-        /* if snapshot, we create a temporary backing file and open it
-           instead of opening 'filename' directly */
-
-        /* Get the required size from the image */
-        QINCREF(options);
-        bs1 = NULL;
-        ret = bdrv_open(&bs1, filename, NULL, options, BDRV_O_NO_BACKING,
-                        drv, &local_err);
-        if (ret < 0) {
-            goto fail;
-        }
-        total_size = bdrv_getlength(bs1) & BDRV_SECTOR_MASK;
-
-        bdrv_unref(bs1);
-
-        /* Create the temporary image */
-        ret = get_tmp_filename(tmp_filename, sizeof(tmp_filename));
-        if (ret < 0) {
-            error_setg_errno(errp, -ret, "Could not get temporary filename");
-            goto fail;
-        }
-
-        bdrv_qcow2 = bdrv_find_format("qcow2");
-        create_options = parse_option_parameters("", bdrv_qcow2->create_options,
-                                                 NULL);
-
-        set_option_parameter_int(create_options, BLOCK_OPT_SIZE, total_size);
-
-        ret = bdrv_create(bdrv_qcow2, tmp_filename, create_options, &local_err);
-        free_option_parameters(create_options);
-        if (ret < 0) {
-            error_setg_errno(errp, -ret, "Could not create temporary overlay "
-                             "'%s': %s", tmp_filename,
-                             error_get_pretty(local_err));
-            error_free(local_err);
-            local_err = NULL;
-            goto fail;
-        }
-
-        /* Prepare a new options QDict for the temporary file, where user
-         * options refer to the backing file */
-        if (filename) {
-            qdict_put(options, "file.filename", qstring_from_str(filename));
-        }
-        if (drv) {
-            qdict_put(options, "driver", qstring_from_str(drv->format_name));
-        }
-
-        snapshot_options = qdict_new();
-        qdict_put(snapshot_options, "backing", options);
-        qdict_flatten(snapshot_options);
-
-        bs->options = snapshot_options;
-        options = qdict_clone_shallow(bs->options);
-
-        filename = tmp_filename;
-        drv = bdrv_qcow2;
-        bs->is_temporary = 1;
-    }
-
     /* Open image file without format layer */
     if (flags & BDRV_O_RDWR) {
         flags |= BDRV_O_ALLOW_RDWR;
@@ -1318,10 +1361,10 @@ int bdrv_open(BlockDriverState **pbs, const char *filename,
 
     assert(file == NULL);
     ret = bdrv_open_image(&file, filename, options, "file",
-                          bdrv_open_flags(bs, flags | BDRV_O_UNMAP) |
+                          bdrv_inherited_flags(flags),
-                          BDRV_O_PROTOCOL, true, &local_err);
+                          true, &local_err);
     if (ret < 0) {
-        goto unlink_and_fail;
+        goto fail;
     }
 
     /* Find the right image format driver */
@@ -1332,7 +1375,7 @@ int bdrv_open(BlockDriverState **pbs, const char *filename,
         if (!drv) {
             error_setg(errp, "Invalid driver: '%s'", drvname);
             ret = -EINVAL;
-            goto unlink_and_fail;
+            goto fail;
         }
     }
 
@@ -1342,18 +1385,18 @@ int bdrv_open(BlockDriverState **pbs, const char *filename,
         } else {
             error_setg(errp, "Must specify either driver or file");
             ret = -EINVAL;
-            goto unlink_and_fail;
+            goto fail;
         }
     }
 
     if (!drv) {
-        goto unlink_and_fail;
+        goto fail;
     }
 
     /* Open the image */
     ret = bdrv_open_common(bs, file, options, flags, drv, &local_err);
     if (ret < 0) {
-        goto unlink_and_fail;
+        goto fail;
     }
 
     if (file && (bs->file != file)) {
@@ -1372,6 +1415,17 @@ int bdrv_open(BlockDriverState **pbs, const char *filename,
         }
     }
 
+    /* For snapshot=on, create a temporary qcow2 overlay. bs points to the
+     * temporary snapshot afterwards. */
+    if (flags & BDRV_O_SNAPSHOT) {
+        bdrv_append_temp_snapshot(bs, &local_err);
+        if (local_err) {
+            error_propagate(errp, local_err);
+            goto close_and_fail;
+        }
+    }
+
+
 done:
     /* Check if any unknown options were used */
     if (options && (qdict_size(options) != 0)) {
@@ -1404,14 +1458,10 @@ done:
     *pbs = bs;
     return 0;
 
-unlink_and_fail:
+fail:
     if (file != NULL) {
         bdrv_unref(file);
     }
-    if (bs->is_temporary) {
-        unlink(filename);
-    }
-fail:
     QDECREF(bs->options);
     QDECREF(options);
     bs->options = NULL;
@@ -1475,8 +1525,11 @@ BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
         QSIMPLEQ_INIT(bs_queue);
     }
 
+    /* bdrv_open() masks this flag out */
+    flags &= ~BDRV_O_PROTOCOL;
+
     if (bs->file) {
-        bdrv_reopen_queue(bs_queue, bs->file, flags);
+        bdrv_reopen_queue(bs_queue, bs->file, bdrv_inherited_flags(flags));
     }
 
     bs_entry = g_new0(BlockReopenQueueEntry, 1);
@@ -1691,11 +1744,6 @@ void bdrv_close(BlockDriverState *bs)
         }
         bs->drv->bdrv_close(bs);
         g_free(bs->opaque);
-#ifdef _WIN32
-        if (bs->is_temporary) {
-            unlink(bs->filename);
-        }
-#endif
         bs->opaque = NULL;
         bs->drv = NULL;
         bs->copy_on_read = 0;
@@ -1819,7 +1867,6 @@ static void bdrv_move_feature_fields(BlockDriverState *bs_dest,
                                      BlockDriverState *bs_src)
 {
     /* move some fields that need to stay attached to the device */
-    bs_dest->open_flags         = bs_src->open_flags;
 
     /* dev info */
     bs_dest->dev_ops            = bs_src->dev_ops;
@@ -2568,6 +2615,10 @@ static int bdrv_check_byte_request(BlockDriverState *bs, int64_t offset,
 {
     int64_t len;
 
+    if (size > INT_MAX) {
+        return -EIO;
+    }
+
     if (!bdrv_is_inserted(bs))
         return -ENOMEDIUM;
 
@@ -2588,6 +2639,10 @@ static int bdrv_check_byte_request(BlockDriverState *bs, int64_t offset,
 static int bdrv_check_request(BlockDriverState *bs, int64_t sector_num,
                               int nb_sectors)
 {
+    if (nb_sectors < 0 || nb_sectors > INT_MAX / BDRV_SECTOR_SIZE) {
+        return -EIO;
+    }
+
     return bdrv_check_byte_request(bs, sector_num * BDRV_SECTOR_SIZE,
                                    nb_sectors * BDRV_SECTOR_SIZE);
 }
@@ -2669,6 +2724,10 @@ static int bdrv_rw_co(BlockDriverState *bs, int64_t sector_num, uint8_t *buf,
         .iov_len = nb_sectors * BDRV_SECTOR_SIZE,
     };
 
+    if (nb_sectors < 0 || nb_sectors > INT_MAX / BDRV_SECTOR_SIZE) {
+        return -EINVAL;
+    }
+
     qemu_iovec_init_external(&qiov, &iov, 1);
     return bdrv_prwv_co(bs, sector_num << BDRV_SECTOR_BITS,
                         &qiov, is_write, flags);
@@ -2724,10 +2783,16 @@ int bdrv_write_zeroes(BlockDriverState *bs, int64_t sector_num,
  */
 int bdrv_make_zero(BlockDriverState *bs, BdrvRequestFlags flags)
 {
-    int64_t target_size = bdrv_getlength(bs) / BDRV_SECTOR_SIZE;
+    int64_t target_size;
     int64_t ret, nb_sectors, sector_num = 0;
     int n;
 
+    target_size = bdrv_getlength(bs);
+    if (target_size < 0) {
+        return target_size;
+    }
+    target_size /= BDRV_SECTOR_SIZE;
+
     for (;;) {
         nb_sectors = target_size - sector_num;
         if (nb_sectors <= 0) {
@@ -3557,10 +3622,25 @@ void bdrv_iterate_format(void (*it)(void *opaque, const char *name),
                          void *opaque)
 {
     BlockDriver *drv;
+    int count = 0;
+    const char **formats = NULL;
 
     QLIST_FOREACH(drv, &bdrv_drivers, list) {
-        it(opaque, drv->format_name);
+        if (drv->format_name) {
+            bool found = false;
+            int i = count;
+            while (formats && i && !found) {
+                found = !strcmp(formats[--i], drv->format_name);
+            }
+
+            if (!found) {
+                formats = g_realloc(formats, (count + 1) * sizeof(char *));
+                formats[count++] = drv->format_name;
+                it(opaque, drv->format_name);
+            }
+        }
     }
+    g_free(formats);
 }
 
 /* This function is to find block backend bs */
@@ -5079,7 +5159,8 @@ bool bdrv_qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov)
     return true;
 }
 
-BdrvDirtyBitmap *bdrv_create_dirty_bitmap(BlockDriverState *bs, int granularity)
+BdrvDirtyBitmap *bdrv_create_dirty_bitmap(BlockDriverState *bs, int granularity,
+                                          Error **errp)
 {
     int64_t bitmap_size;
     BdrvDirtyBitmap *bitmap;
@@ -5088,7 +5169,13 @@ BdrvDirtyBitmap *bdrv_create_dirty_bitmap(BlockDriverState *bs, int granularity)
 
     granularity >>= BDRV_SECTOR_BITS;
     assert(granularity);
-    bitmap_size = (bdrv_getlength(bs) >> BDRV_SECTOR_BITS);
+    bitmap_size = bdrv_getlength(bs);
+    if (bitmap_size < 0) {
+        error_setg_errno(errp, -bitmap_size, "could not get length of device");
+        errno = -bitmap_size;
+        return NULL;
+    }
+    bitmap_size >>= BDRV_SECTOR_BITS;
     bitmap = g_malloc0(sizeof(BdrvDirtyBitmap));
     bitmap->bitmap = hbitmap_alloc(bitmap_size, ffs(granularity) - 1);
     QLIST_INSERT_HEAD(&bs->dirty_bitmaps, bitmap, list);

block/bochs.c

@@ -38,57 +38,42 @@
 
 // not allocated: 0xffffffff
 
-// always little-endian
-struct bochs_header_v1 {
-    char magic[32]; // "Bochs Virtual HD Image"
-    char type[16]; // "Redolog"
-    char subtype[16]; // "Undoable" / "Volatile" / "Growing"
-    uint32_t version;
-    uint32_t header; // size of header
-
-    union {
-	struct {
-	    uint32_t catalog; // num of entries
-	    uint32_t bitmap; // bitmap size
-	    uint32_t extent; // extent size
-	    uint64_t disk; // disk size
-	    char padding[HEADER_SIZE - 64 - 8 - 20];
-	} redolog;
-	char padding[HEADER_SIZE - 64 - 8];
-    } extra;
-};
-
 // always little-endian
 struct bochs_header {
-    char magic[32]; // "Bochs Virtual HD Image"
+    char magic[32];     /* "Bochs Virtual HD Image" */
-    char type[16]; // "Redolog"
+    char type[16];      /* "Redolog" */
-    char subtype[16]; // "Undoable" / "Volatile" / "Growing"
+    char subtype[16];   /* "Undoable" / "Volatile" / "Growing" */
     uint32_t version;
-    uint32_t header; // size of header
+    uint32_t header;    /* size of header */
+
+    uint32_t catalog;   /* num of entries */
+    uint32_t bitmap;    /* bitmap size */
+    uint32_t extent;    /* extent size */
 
     union {
-	struct {
+        struct {
-	    uint32_t catalog; // num of entries
+            uint32_t reserved;  /* for ??? */
-	    uint32_t bitmap; // bitmap size
+            uint64_t disk;      /* disk size */
-	    uint32_t extent; // extent size
+            char padding[HEADER_SIZE - 64 - 20 - 12];
-	    uint32_t reserved; // for ???
+        } QEMU_PACKED redolog;
-	    uint64_t disk; // disk size
+        struct {
-	    char padding[HEADER_SIZE - 64 - 8 - 24];
+            uint64_t disk;      /* disk size */
-	} redolog;
+            char padding[HEADER_SIZE - 64 - 20 - 8];
-	char padding[HEADER_SIZE - 64 - 8];
+        } QEMU_PACKED redolog_v1;
+        char padding[HEADER_SIZE - 64 - 20];
     } extra;
-};
+} QEMU_PACKED;
 
 typedef struct BDRVBochsState {
     CoMutex lock;
     uint32_t *catalog_bitmap;
-    int catalog_size;
+    uint32_t catalog_size;
 
-    int data_offset;
+    uint32_t data_offset;
 
-    int bitmap_blocks;
+    uint32_t bitmap_blocks;
-    int extent_blocks;
+    uint32_t extent_blocks;
-    int extent_size;
+    uint32_t extent_size;
 } BDRVBochsState;
 
 static int bochs_probe(const uint8_t *buf, int buf_size, const char *filename)
@@ -112,9 +97,8 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
                       Error **errp)
 {
     BDRVBochsState *s = bs->opaque;
-    int i;
+    uint32_t i;
     struct bochs_header bochs;
-    struct bochs_header_v1 header_v1;
     int ret;
 
     bs->read_only = 1; // no write support yet
@@ -134,13 +118,19 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     if (le32_to_cpu(bochs.version) == HEADER_V1) {
-      memcpy(&header_v1, &bochs, sizeof(bochs));
+        bs->total_sectors = le64_to_cpu(bochs.extra.redolog_v1.disk) / 512;
-      bs->total_sectors = le64_to_cpu(header_v1.extra.redolog.disk) / 512;
     } else {
-      bs->total_sectors = le64_to_cpu(bochs.extra.redolog.disk) / 512;
+        bs->total_sectors = le64_to_cpu(bochs.extra.redolog.disk) / 512;
+    }
+
+    /* Limit to 1M entries to avoid unbounded allocation. This is what is
+     * needed for the largest image that bximage can create (~8 TB). */
+    s->catalog_size = le32_to_cpu(bochs.catalog);
+    if (s->catalog_size > 0x100000) {
+        error_setg(errp, "Catalog size is too large");
+        return -EFBIG;
     }
 
-    s->catalog_size = le32_to_cpu(bochs.extra.redolog.catalog);
     s->catalog_bitmap = g_malloc(s->catalog_size * 4);
 
     ret = bdrv_pread(bs->file, le32_to_cpu(bochs.header), s->catalog_bitmap,
@@ -154,10 +144,34 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
 
     s->data_offset = le32_to_cpu(bochs.header) + (s->catalog_size * 4);
 
-    s->bitmap_blocks = 1 + (le32_to_cpu(bochs.extra.redolog.bitmap) - 1) / 512;
+    s->bitmap_blocks = 1 + (le32_to_cpu(bochs.bitmap) - 1) / 512;
-    s->extent_blocks = 1 + (le32_to_cpu(bochs.extra.redolog.extent) - 1) / 512;
+    s->extent_blocks = 1 + (le32_to_cpu(bochs.extent) - 1) / 512;
 
-    s->extent_size = le32_to_cpu(bochs.extra.redolog.extent);
+    s->extent_size = le32_to_cpu(bochs.extent);
+    if (s->extent_size < BDRV_SECTOR_SIZE) {
+        /* bximage actually never creates extents smaller than 4k */
+        error_setg(errp, "Extent size must be at least 512");
+        ret = -EINVAL;
+        goto fail;
+    } else if (!is_power_of_2(s->extent_size)) {
+        error_setg(errp, "Extent size %" PRIu32 " is not a power of two",
+                   s->extent_size);
+        ret = -EINVAL;
+        goto fail;
+    } else if (s->extent_size > 0x800000) {
+        error_setg(errp, "Extent size %" PRIu32 " is too large",
+                   s->extent_size);
+        ret = -EINVAL;
+        goto fail;
+    }
+
+    if (s->catalog_size < DIV_ROUND_UP(bs->total_sectors,
+                                       s->extent_size / BDRV_SECTOR_SIZE))
+    {
+        error_setg(errp, "Catalog size is too small for this disk size");
+        ret = -EINVAL;
+        goto fail;
+    }
 
     qemu_co_mutex_init(&s->lock);
     return 0;
@@ -170,29 +184,32 @@ fail:
 static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)
 {
     BDRVBochsState *s = bs->opaque;
-    int64_t offset = sector_num * 512;
+    uint64_t offset = sector_num * 512;
-    int64_t extent_index, extent_offset, bitmap_offset;
+    uint64_t extent_index, extent_offset, bitmap_offset;
     char bitmap_entry;
+    int ret;
 
     // seek to sector
     extent_index = offset / s->extent_size;
     extent_offset = (offset % s->extent_size) / 512;
 
     if (s->catalog_bitmap[extent_index] == 0xffffffff) {
-	return -1; /* not allocated */
+	return 0; /* not allocated */
     }
 
-    bitmap_offset = s->data_offset + (512 * s->catalog_bitmap[extent_index] *
+    bitmap_offset = s->data_offset +
-	(s->extent_blocks + s->bitmap_blocks));
+        (512 * (uint64_t) s->catalog_bitmap[extent_index] *
+        (s->extent_blocks + s->bitmap_blocks));
 
     /* read in bitmap for current extent */
-    if (bdrv_pread(bs->file, bitmap_offset + (extent_offset / 8),
+    ret = bdrv_pread(bs->file, bitmap_offset + (extent_offset / 8),
-                   &bitmap_entry, 1) != 1) {
+                     &bitmap_entry, 1);
-        return -1;
+    if (ret < 0) {
+        return ret;
     }
 
     if (!((bitmap_entry >> (extent_offset % 8)) & 1)) {
-	return -1; /* not allocated */
+	return 0; /* not allocated */
     }
 
     return bitmap_offset + (512 * (s->bitmap_blocks + extent_offset));
@@ -205,13 +222,16 @@ static int bochs_read(BlockDriverState *bs, int64_t sector_num,
 
     while (nb_sectors > 0) {
         int64_t block_offset = seek_to_sector(bs, sector_num);
-        if (block_offset >= 0) {
+        if (block_offset < 0) {
+            return block_offset;
+        } else if (block_offset > 0) {
             ret = bdrv_pread(bs->file, block_offset, buf, 512);
-            if (ret != 512) {
+            if (ret < 0) {
-                return -1;
+                return ret;
             }
-        } else
+        } else {
             memset(buf, 0, 512);
+        }
         nb_sectors--;
         sector_num++;
         buf += 512;

block/cloop.c

@@ -26,6 +26,9 @@
 #include "qemu/module.h"
 #include <zlib.h>
 
+/* Maximum compressed block size */
+#define MAX_BLOCK_SIZE (64 * 1024 * 1024)
+
 typedef struct BDRVCloopState {
     CoMutex lock;
     uint32_t block_size;
@@ -68,6 +71,26 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
         return ret;
     }
     s->block_size = be32_to_cpu(s->block_size);
+    if (s->block_size % 512) {
+        error_setg(errp, "block_size %" PRIu32 " must be a multiple of 512",
+                   s->block_size);
+        return -EINVAL;
+    }
+    if (s->block_size == 0) {
+        error_setg(errp, "block_size cannot be zero");
+        return -EINVAL;
+    }
+
+    /* cloop's create_compressed_fs.c warns about block sizes beyond 256 KB but
+     * we can accept more.  Prevent ridiculous values like 4 GB - 1 since we
+     * need a buffer this big.
+     */
+    if (s->block_size > MAX_BLOCK_SIZE) {
+        error_setg(errp, "block_size %" PRIu32 " must be %u MB or less",
+                   s->block_size,
+                   MAX_BLOCK_SIZE / (1024 * 1024));
+        return -EINVAL;
+    }
 
     ret = bdrv_pread(bs->file, 128 + 4, &s->n_blocks, 4);
     if (ret < 0) {
@@ -76,7 +99,23 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
     s->n_blocks = be32_to_cpu(s->n_blocks);
 
     /* read offsets */
-    offsets_size = s->n_blocks * sizeof(uint64_t);
+    if (s->n_blocks > (UINT32_MAX - 1) / sizeof(uint64_t)) {
+        /* Prevent integer overflow */
+        error_setg(errp, "n_blocks %" PRIu32 " must be %zu or less",
+                   s->n_blocks,
+                   (UINT32_MAX - 1) / sizeof(uint64_t));
+        return -EINVAL;
+    }
+    offsets_size = (s->n_blocks + 1) * sizeof(uint64_t);
+    if (offsets_size > 512 * 1024 * 1024) {
+        /* Prevent ridiculous offsets_size which causes memory allocation to
+         * fail or overflows bdrv_pread() size.  In practice the 512 MB
+         * offsets[] limit supports 16 TB images at 256 KB block size.
+         */
+        error_setg(errp, "image requires too many offsets, "
+                   "try increasing block size");
+        return -EINVAL;
+    }
     s->offsets = g_malloc(offsets_size);
 
     ret = bdrv_pread(bs->file, 128 + 4 + 4, s->offsets, offsets_size);
@@ -84,13 +123,37 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
 
-    for(i=0;i<s->n_blocks;i++) {
+    for (i = 0; i < s->n_blocks + 1; i++) {
+        uint64_t size;
+
         s->offsets[i] = be64_to_cpu(s->offsets[i]);
-        if (i > 0) {
+        if (i == 0) {
-            uint32_t size = s->offsets[i] - s->offsets[i - 1];
+            continue;
-            if (size > max_compressed_block_size) {
+        }
-                max_compressed_block_size = size;
+
-            }
+        if (s->offsets[i] < s->offsets[i - 1]) {
+            error_setg(errp, "offsets not monotonically increasing at "
+                       "index %" PRIu32 ", image file is corrupt", i);
+            ret = -EINVAL;
+            goto fail;
+        }
+
+        size = s->offsets[i] - s->offsets[i - 1];
+
+        /* Compressed blocks should be smaller than the uncompressed block size
+         * but maybe compression performed poorly so the compressed block is
+         * actually bigger.  Clamp down on unrealistic values to prevent
+         * ridiculous s->compressed_block allocation.
+         */
+        if (size > 2 * MAX_BLOCK_SIZE) {
+            error_setg(errp, "invalid compressed block size at index %" PRIu32
+                       ", image file is corrupt", i);
+            ret = -EINVAL;
+            goto fail;
+        }
+
+        if (size > max_compressed_block_size) {
+            max_compressed_block_size = size;
         }
     }
 
@@ -180,9 +243,7 @@ static coroutine_fn int cloop_co_read(BlockDriverState *bs, int64_t sector_num,
 static void cloop_close(BlockDriverState *bs)
 {
     BDRVCloopState *s = bs->opaque;
-    if (s->n_blocks > 0) {
+    g_free(s->offsets);
-        g_free(s->offsets);
-    }
     g_free(s->compressed_block);
     g_free(s->uncompressed_block);
     inflateEnd(&s->zstream);

block/commit.c

@@ -194,7 +194,7 @@ void commit_start(BlockDriverState *bs, BlockDriverState *base,
     if ((on_error == BLOCKDEV_ON_ERROR_STOP ||
          on_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
         !bdrv_iostatus_is_enabled(bs)) {
-        error_set(errp, QERR_INVALID_PARAMETER_COMBINATION);
+        error_setg(errp, "Invalid parameter combination");
         return;
     }
 

block/cow.c

@@ -82,7 +82,7 @@ static int cow_open(BlockDriverState *bs, QDict *options, int flags,
     if (be32_to_cpu(cow_header.version) != COW_VERSION) {
         char version[64];
         snprintf(version, sizeof(version),
-               "COW version %d", cow_header.version);
+               "COW version %" PRIu32, cow_header.version);
         error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
             bs->device_name, "cow", version);
         ret = -ENOTSUP;

block/curl.c

@@ -71,6 +71,7 @@ typedef struct CURLState
     struct BDRVCURLState *s;
     CURLAIOCB *acb[CURL_NUM_ACB];
     CURL *curl;
+    curl_socket_t sock_fd;
     char *orig_buf;
     size_t buf_start;
     size_t buf_off;
@@ -92,6 +93,7 @@ typedef struct BDRVCURLState {
 
 static void curl_clean_state(CURLState *s);
 static void curl_multi_do(void *arg);
+static void curl_multi_read(void *arg);
 
 #ifdef NEED_CURL_TIMER_CALLBACK
 static int curl_timer_cb(CURLM *multi, long timeout_ms, void *opaque)
@@ -113,16 +115,20 @@ static int curl_timer_cb(CURLM *multi, long timeout_ms, void *opaque)
 static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
                         void *s, void *sp)
 {
+    CURLState *state = NULL;
+    curl_easy_getinfo(curl, CURLINFO_PRIVATE, (char **)&state);
+    state->sock_fd = fd;
+
     DPRINTF("CURL (AIO): Sock action %d on fd %d\n", action, fd);
     switch (action) {
         case CURL_POLL_IN:
-            qemu_aio_set_fd_handler(fd, curl_multi_do, NULL, s);
+            qemu_aio_set_fd_handler(fd, curl_multi_read, NULL, state);
             break;
         case CURL_POLL_OUT:
-            qemu_aio_set_fd_handler(fd, NULL, curl_multi_do, s);
+            qemu_aio_set_fd_handler(fd, NULL, curl_multi_do, state);
             break;
         case CURL_POLL_INOUT:
-            qemu_aio_set_fd_handler(fd, curl_multi_do, curl_multi_do, s);
+            qemu_aio_set_fd_handler(fd, curl_multi_read, curl_multi_do, state);
             break;
         case CURL_POLL_REMOVE:
             qemu_aio_set_fd_handler(fd, NULL, NULL, NULL);
@@ -155,8 +161,13 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
     DPRINTF("CURL: Just reading %zd bytes\n", realsize);
 
     if (!s || !s->orig_buf)
-        goto read_end;
+        return 0;
 
+    if (s->buf_off >= s->buf_len) {
+        /* buffer full, read nothing */
+        return 0;
+    }
+    realsize = MIN(realsize, s->buf_len - s->buf_off);
     memcpy(s->orig_buf + s->buf_off, ptr, realsize);
     s->buf_off += realsize;
 
@@ -175,7 +186,6 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
         }
     }
 
-read_end:
     return realsize;
 }
 
@@ -210,7 +220,8 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
         }
 
         // Wait for unfinished chunks
-        if ((start >= state->buf_start) &&
+        if (state->in_use &&
+            (start >= state->buf_start) &&
             (start <= buf_fend) &&
             (end >= state->buf_start) &&
             (end <= buf_fend))
@@ -232,68 +243,69 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
     return FIND_RET_NONE;
 }
 
-static void curl_multi_read(BDRVCURLState *s)
+static void curl_multi_check_completion(BDRVCURLState *s)
 {
     int msgs_in_queue;
 
     /* Try to find done transfers, so we can free the easy
      * handle again. */
-    do {
+    for (;;) {
         CURLMsg *msg;
         msg = curl_multi_info_read(s->multi, &msgs_in_queue);
 
+        /* Quit when there are no more completions */
         if (!msg)
             break;
-        if (msg->msg == CURLMSG_NONE)
-            break;
 
-        switch (msg->msg) {
+        if (msg->msg == CURLMSG_DONE) {
-            case CURLMSG_DONE:
+            CURLState *state = NULL;
-            {
+            curl_easy_getinfo(msg->easy_handle, CURLINFO_PRIVATE,
-                CURLState *state = NULL;
+                              (char **)&state);
-                curl_easy_getinfo(msg->easy_handle, CURLINFO_PRIVATE, (char**)&state);
 
-                /* ACBs for successful messages get completed in curl_read_cb */
+            /* ACBs for successful messages get completed in curl_read_cb */
-                if (msg->data.result != CURLE_OK) {
+            if (msg->data.result != CURLE_OK) {
-                    int i;
+                int i;
-                    for (i = 0; i < CURL_NUM_ACB; i++) {
+                for (i = 0; i < CURL_NUM_ACB; i++) {
-                        CURLAIOCB *acb = state->acb[i];
+                    CURLAIOCB *acb = state->acb[i];
 
-                        if (acb == NULL) {
+                    if (acb == NULL) {
-                            continue;
+                        continue;
-                        }
-
-                        acb->common.cb(acb->common.opaque, -EIO);
-                        qemu_aio_release(acb);
-                        state->acb[i] = NULL;
                     }
-                }
 
-                curl_clean_state(state);
+                    acb->common.cb(acb->common.opaque, -EIO);
-                break;
+                    qemu_aio_release(acb);
+                    state->acb[i] = NULL;
+                }
             }
-            default:
+
-                msgs_in_queue = 0;
+            curl_clean_state(state);
-                break;
+            break;
         }
-    } while(msgs_in_queue);
+    }
 }
 
 static void curl_multi_do(void *arg)
 {
-    BDRVCURLState *s = (BDRVCURLState *)arg;
+    CURLState *s = (CURLState *)arg;
     int running;
     int r;
 
-    if (!s->multi) {
+    if (!s->s->multi) {
         return;
     }
 
     do {
-        r = curl_multi_socket_all(s->multi, &running);
+        r = curl_multi_socket_action(s->s->multi, s->sock_fd, 0, &running);
     } while(r == CURLM_CALL_MULTI_PERFORM);
 
-    curl_multi_read(s);
+}
+
+static void curl_multi_read(void *arg)
+{
+    CURLState *s = (CURLState *)arg;
+
+    curl_multi_do(arg);
+    curl_multi_check_completion(s->s);
 }
 
 static void curl_multi_timeout_do(void *arg)
@@ -308,7 +320,7 @@ static void curl_multi_timeout_do(void *arg)
 
     curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
 
-    curl_multi_read(s);
+    curl_multi_check_completion(s);
 #else
     abort();
 #endif
@@ -332,44 +344,42 @@ static CURLState *curl_init_state(BDRVCURLState *s)
             break;
         }
         if (!state) {
-            g_usleep(100);
+            qemu_aio_wait();
-            curl_multi_do(s);
         }
     } while(!state);
 
-    if (state->curl)
+    if (!state->curl) {
-        goto has_curl;
+        state->curl = curl_easy_init();
+        if (!state->curl) {
+            return NULL;
+        }
+        curl_easy_setopt(state->curl, CURLOPT_URL, s->url);
+        curl_easy_setopt(state->curl, CURLOPT_TIMEOUT, 5);
+        curl_easy_setopt(state->curl, CURLOPT_WRITEFUNCTION,
+                         (void *)curl_read_cb);
+        curl_easy_setopt(state->curl, CURLOPT_WRITEDATA, (void *)state);
+        curl_easy_setopt(state->curl, CURLOPT_PRIVATE, (void *)state);
+        curl_easy_setopt(state->curl, CURLOPT_AUTOREFERER, 1);
+        curl_easy_setopt(state->curl, CURLOPT_FOLLOWLOCATION, 1);
+        curl_easy_setopt(state->curl, CURLOPT_NOSIGNAL, 1);
+        curl_easy_setopt(state->curl, CURLOPT_ERRORBUFFER, state->errmsg);
+        curl_easy_setopt(state->curl, CURLOPT_FAILONERROR, 1);
 
-    state->curl = curl_easy_init();
+        /* Restrict supported protocols to avoid security issues in the more
-    if (!state->curl)
+         * obscure protocols.  For example, do not allow POP3/SMTP/IMAP see
-        return NULL;
+         * CVE-2013-0249.
-    curl_easy_setopt(state->curl, CURLOPT_URL, s->url);
+         *
-    curl_easy_setopt(state->curl, CURLOPT_TIMEOUT, 5);
+         * Restricting protocols is only supported from 7.19.4 upwards.
-    curl_easy_setopt(state->curl, CURLOPT_WRITEFUNCTION, (void *)curl_read_cb);
+         */
-    curl_easy_setopt(state->curl, CURLOPT_WRITEDATA, (void *)state);
-    curl_easy_setopt(state->curl, CURLOPT_PRIVATE, (void *)state);
-    curl_easy_setopt(state->curl, CURLOPT_AUTOREFERER, 1);
-    curl_easy_setopt(state->curl, CURLOPT_FOLLOWLOCATION, 1);
-    curl_easy_setopt(state->curl, CURLOPT_NOSIGNAL, 1);
-    curl_easy_setopt(state->curl, CURLOPT_ERRORBUFFER, state->errmsg);
-    curl_easy_setopt(state->curl, CURLOPT_FAILONERROR, 1);
-
-    /* Restrict supported protocols to avoid security issues in the more
-     * obscure protocols.  For example, do not allow POP3/SMTP/IMAP see
-     * CVE-2013-0249.
-     *
-     * Restricting protocols is only supported from 7.19.4 upwards.
-     */
 #if LIBCURL_VERSION_NUM >= 0x071304
-    curl_easy_setopt(state->curl, CURLOPT_PROTOCOLS, PROTOCOLS);
+        curl_easy_setopt(state->curl, CURLOPT_PROTOCOLS, PROTOCOLS);
-    curl_easy_setopt(state->curl, CURLOPT_REDIR_PROTOCOLS, PROTOCOLS);
+        curl_easy_setopt(state->curl, CURLOPT_REDIR_PROTOCOLS, PROTOCOLS);
 #endif
 
 #ifdef DEBUG_VERBOSE
-    curl_easy_setopt(state->curl, CURLOPT_VERBOSE, 1);
+        curl_easy_setopt(state->curl, CURLOPT_VERBOSE, 1);
 #endif
-
+    }
-has_curl:
 
     state->s = s;
 
@@ -526,19 +536,17 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
     // initialize the multi interface!
 
     s->multi = curl_multi_init();
-    curl_multi_setopt(s->multi, CURLMOPT_SOCKETDATA, s);
     curl_multi_setopt(s->multi, CURLMOPT_SOCKETFUNCTION, curl_sock_cb);
 #ifdef NEED_CURL_TIMER_CALLBACK
     curl_multi_setopt(s->multi, CURLMOPT_TIMERDATA, s);
     curl_multi_setopt(s->multi, CURLMOPT_TIMERFUNCTION, curl_timer_cb);
 #endif
-    curl_multi_do(s);
 
     qemu_opts_del(opts);
     return 0;
 
 out:
-    fprintf(stderr, "CURL: Error opening file: %s\n", state->errmsg);
+    error_setg(errp, "CURL: Error opening file: %s", state->errmsg);
     curl_easy_cleanup(state->curl);
     state->curl = NULL;
 out_noclean:
@@ -561,6 +569,7 @@ static const AIOCBInfo curl_aiocb_info = {
 static void curl_readv_bh_cb(void *p)
 {
     CURLState *state;
+    int running;
 
     CURLAIOCB *acb = p;
     BDRVCURLState *s = acb->common.bs->opaque;
@@ -609,8 +618,9 @@ static void curl_readv_bh_cb(void *p)
     curl_easy_setopt(state->curl, CURLOPT_RANGE, state->range);
 
     curl_multi_add_handle(s->multi, state->curl);
-    curl_multi_do(s);
 
+    /* Tell curl it needs to kick things off */
+    curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
 }
 
 static BlockDriverAIOCB *curl_aio_readv(BlockDriverState *bs,

block/dmg.c

@@ -27,6 +27,14 @@
 #include "qemu/module.h"
 #include <zlib.h>
 
+enum {
+    /* Limit chunk sizes to prevent unreasonable amounts of memory being used
+     * or truncating when converting to 32-bit types
+     */
+    DMG_LENGTHS_MAX = 64 * 1024 * 1024, /* 64 MB */
+    DMG_SECTORCOUNTS_MAX = DMG_LENGTHS_MAX / 512,
+};
+
 typedef struct BDRVDMGState {
     CoMutex lock;
     /* each chunk contains a certain number of sectors,
@@ -92,13 +100,44 @@ static int read_uint32(BlockDriverState *bs, int64_t offset, uint32_t *result)
     return 0;
 }
 
+/* Increase max chunk sizes, if necessary.  This function is used to calculate
+ * the buffer sizes needed for compressed/uncompressed chunk I/O.
+ */
+static void update_max_chunk_size(BDRVDMGState *s, uint32_t chunk,
+                                  uint32_t *max_compressed_size,
+                                  uint32_t *max_sectors_per_chunk)
+{
+    uint32_t compressed_size = 0;
+    uint32_t uncompressed_sectors = 0;
+
+    switch (s->types[chunk]) {
+    case 0x80000005: /* zlib compressed */
+        compressed_size = s->lengths[chunk];
+        uncompressed_sectors = s->sectorcounts[chunk];
+        break;
+    case 1: /* copy */
+        uncompressed_sectors = (s->lengths[chunk] + 511) / 512;
+        break;
+    case 2: /* zero */
+        uncompressed_sectors = s->sectorcounts[chunk];
+        break;
+    }
+
+    if (compressed_size > *max_compressed_size) {
+        *max_compressed_size = compressed_size;
+    }
+    if (uncompressed_sectors > *max_sectors_per_chunk) {
+        *max_sectors_per_chunk = uncompressed_sectors;
+    }
+}
+
 static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
                     Error **errp)
 {
     BDRVDMGState *s = bs->opaque;
-    uint64_t info_begin,info_end,last_in_offset,last_out_offset;
+    uint64_t info_begin, info_end, last_in_offset, last_out_offset;
     uint32_t count, tmp;
-    uint32_t max_compressed_size=1,max_sectors_per_chunk=1,i;
+    uint32_t max_compressed_size = 1, max_sectors_per_chunk = 1, i;
     int64_t offset;
     int ret;
 
@@ -160,37 +199,40 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
             goto fail;
         }
 
-	if (type == 0x6d697368 && count >= 244) {
+        if (type == 0x6d697368 && count >= 244) {
-	    int new_size, chunk_count;
+            size_t new_size;
+            uint32_t chunk_count;
 
             offset += 4;
             offset += 200;
 
-	    chunk_count = (count-204)/40;
+            chunk_count = (count - 204) / 40;
-	    new_size = sizeof(uint64_t) * (s->n_chunks + chunk_count);
+            new_size = sizeof(uint64_t) * (s->n_chunks + chunk_count);
-	    s->types = g_realloc(s->types, new_size/2);
+            s->types = g_realloc(s->types, new_size / 2);
-	    s->offsets = g_realloc(s->offsets, new_size);
+            s->offsets = g_realloc(s->offsets, new_size);
-	    s->lengths = g_realloc(s->lengths, new_size);
+            s->lengths = g_realloc(s->lengths, new_size);
-	    s->sectors = g_realloc(s->sectors, new_size);
+            s->sectors = g_realloc(s->sectors, new_size);
-	    s->sectorcounts = g_realloc(s->sectorcounts, new_size);
+            s->sectorcounts = g_realloc(s->sectorcounts, new_size);
 
             for (i = s->n_chunks; i < s->n_chunks + chunk_count; i++) {
                 ret = read_uint32(bs, offset, &s->types[i]);
                 if (ret < 0) {
                     goto fail;
                 }
-		offset += 4;
+                offset += 4;
-		if(s->types[i]!=0x80000005 && s->types[i]!=1 && s->types[i]!=2) {
+                if (s->types[i] != 0x80000005 && s->types[i] != 1 &&
-		    if(s->types[i]==0xffffffff) {
+                    s->types[i] != 2) {
-			last_in_offset = s->offsets[i-1]+s->lengths[i-1];
+                    if (s->types[i] == 0xffffffff && i > 0) {
-			last_out_offset = s->sectors[i-1]+s->sectorcounts[i-1];
+                        last_in_offset = s->offsets[i - 1] + s->lengths[i - 1];
-		    }
+                        last_out_offset = s->sectors[i - 1] +
-		    chunk_count--;
+                                          s->sectorcounts[i - 1];
-		    i--;
+                    }
-		    offset += 36;
+                    chunk_count--;
-		    continue;
+                    i--;
-		}
+                    offset += 36;
-		offset += 4;
+                    continue;
+                }
+                offset += 4;
 
                 ret = read_uint64(bs, offset, &s->sectors[i]);
                 if (ret < 0) {
@@ -205,6 +247,14 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
                 }
                 offset += 8;
 
+                if (s->sectorcounts[i] > DMG_SECTORCOUNTS_MAX) {
+                    error_report("sector count %" PRIu64 " for chunk %" PRIu32
+                                 " is larger than max (%u)",
+                                 s->sectorcounts[i], i, DMG_SECTORCOUNTS_MAX);
+                    ret = -EINVAL;
+                    goto fail;
+                }
+
                 ret = read_uint64(bs, offset, &s->offsets[i]);
                 if (ret < 0) {
                     goto fail;
@@ -218,19 +268,25 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
                 }
                 offset += 8;
 
-		if(s->lengths[i]>max_compressed_size)
+                if (s->lengths[i] > DMG_LENGTHS_MAX) {
-		    max_compressed_size = s->lengths[i];
+                    error_report("length %" PRIu64 " for chunk %" PRIu32
-		if(s->sectorcounts[i]>max_sectors_per_chunk)
+                                 " is larger than max (%u)",
-		    max_sectors_per_chunk = s->sectorcounts[i];
+                                 s->lengths[i], i, DMG_LENGTHS_MAX);
-	    }
+                    ret = -EINVAL;
-	    s->n_chunks+=chunk_count;
+                    goto fail;
-	}
+                }
+
+                update_max_chunk_size(s, i, &max_compressed_size,
+                                      &max_sectors_per_chunk);
+            }
+            s->n_chunks += chunk_count;
+        }
     }
 
     /* initialize zlib engine */
-    s->compressed_chunk = g_malloc(max_compressed_size+1);
+    s->compressed_chunk = g_malloc(max_compressed_size + 1);
-    s->uncompressed_chunk = g_malloc(512*max_sectors_per_chunk);
+    s->uncompressed_chunk = g_malloc(512 * max_sectors_per_chunk);
-    if(inflateInit(&s->zstream) != Z_OK) {
+    if (inflateInit(&s->zstream) != Z_OK) {
         ret = -EINVAL;
         goto fail;
     }
@@ -252,83 +308,82 @@ fail:
 }
 
 static inline int is_sector_in_chunk(BDRVDMGState* s,
-		uint32_t chunk_num,int sector_num)
+                uint32_t chunk_num, uint64_t sector_num)
 {
-    if(chunk_num>=s->n_chunks || s->sectors[chunk_num]>sector_num ||
+    if (chunk_num >= s->n_chunks || s->sectors[chunk_num] > sector_num ||
-	    s->sectors[chunk_num]+s->sectorcounts[chunk_num]<=sector_num)
+            s->sectors[chunk_num] + s->sectorcounts[chunk_num] <= sector_num) {
-	return 0;
+        return 0;
-    else
+    } else {
-	return -1;
+        return -1;
+    }
 }
 
-static inline uint32_t search_chunk(BDRVDMGState* s,int sector_num)
+static inline uint32_t search_chunk(BDRVDMGState *s, uint64_t sector_num)
 {
     /* binary search */
-    uint32_t chunk1=0,chunk2=s->n_chunks,chunk3;
+    uint32_t chunk1 = 0, chunk2 = s->n_chunks, chunk3;
-    while(chunk1!=chunk2) {
+    while (chunk1 != chunk2) {
-	chunk3 = (chunk1+chunk2)/2;
+        chunk3 = (chunk1 + chunk2) / 2;
-	if(s->sectors[chunk3]>sector_num)
+        if (s->sectors[chunk3] > sector_num) {
-	    chunk2 = chunk3;
+            chunk2 = chunk3;
-	else if(s->sectors[chunk3]+s->sectorcounts[chunk3]>sector_num)
+        } else if (s->sectors[chunk3] + s->sectorcounts[chunk3] > sector_num) {
-	    return chunk3;
+            return chunk3;
-	else
+        } else {
-	    chunk1 = chunk3;
+            chunk1 = chunk3;
+        }
     }
     return s->n_chunks; /* error */
 }
 
-static inline int dmg_read_chunk(BlockDriverState *bs, int sector_num)
+static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num)
 {
     BDRVDMGState *s = bs->opaque;
 
-    if(!is_sector_in_chunk(s,s->current_chunk,sector_num)) {
+    if (!is_sector_in_chunk(s, s->current_chunk, sector_num)) {
-	int ret;
+        int ret;
-	uint32_t chunk = search_chunk(s,sector_num);
+        uint32_t chunk = search_chunk(s, sector_num);
 
-	if(chunk>=s->n_chunks)
+        if (chunk >= s->n_chunks) {
-	    return -1;
+            return -1;
+        }
 
-	s->current_chunk = s->n_chunks;
+        s->current_chunk = s->n_chunks;
-	switch(s->types[chunk]) {
+        switch (s->types[chunk]) {
-	case 0x80000005: { /* zlib compressed */
+        case 0x80000005: { /* zlib compressed */
-	    int i;
+            /* we need to buffer, because only the chunk as whole can be
+             * inflated. */
+            ret = bdrv_pread(bs->file, s->offsets[chunk],
+                             s->compressed_chunk, s->lengths[chunk]);
+            if (ret != s->lengths[chunk]) {
+                return -1;
+            }
 
-	    /* we need to buffer, because only the chunk as whole can be
+            s->zstream.next_in = s->compressed_chunk;
-	     * inflated. */
+            s->zstream.avail_in = s->lengths[chunk];
-	    i=0;
+            s->zstream.next_out = s->uncompressed_chunk;
-	    do {
+            s->zstream.avail_out = 512 * s->sectorcounts[chunk];
-                ret = bdrv_pread(bs->file, s->offsets[chunk] + i,
+            ret = inflateReset(&s->zstream);
-                                 s->compressed_chunk+i, s->lengths[chunk]-i);
+            if (ret != Z_OK) {
-		if(ret<0 && errno==EINTR)
+                return -1;
-		    ret=0;
+            }
-		i+=ret;
+            ret = inflate(&s->zstream, Z_FINISH);
-	    } while(ret>=0 && ret+i<s->lengths[chunk]);
+            if (ret != Z_STREAM_END ||
-
+                s->zstream.total_out != 512 * s->sectorcounts[chunk]) {
-	    if (ret != s->lengths[chunk])
+                return -1;
-		return -1;
+            }
-
+            break; }
-	    s->zstream.next_in = s->compressed_chunk;
+        case 1: /* copy */
-	    s->zstream.avail_in = s->lengths[chunk];
+            ret = bdrv_pread(bs->file, s->offsets[chunk],
-	    s->zstream.next_out = s->uncompressed_chunk;
-	    s->zstream.avail_out = 512*s->sectorcounts[chunk];
-	    ret = inflateReset(&s->zstream);
-	    if(ret != Z_OK)
-		return -1;
-	    ret = inflate(&s->zstream, Z_FINISH);
-	    if(ret != Z_STREAM_END || s->zstream.total_out != 512*s->sectorcounts[chunk])
-		return -1;
-	    break; }
-	case 1: /* copy */
-	    ret = bdrv_pread(bs->file, s->offsets[chunk],
                              s->uncompressed_chunk, s->lengths[chunk]);
-	    if (ret != s->lengths[chunk])
+            if (ret != s->lengths[chunk]) {
-		return -1;
+                return -1;
-	    break;
+            }
-	case 2: /* zero */
+            break;
-	    memset(s->uncompressed_chunk, 0, 512*s->sectorcounts[chunk]);
+        case 2: /* zero */
-	    break;
+            memset(s->uncompressed_chunk, 0, 512 * s->sectorcounts[chunk]);
-	}
+            break;
-	s->current_chunk = chunk;
+        }
+        s->current_chunk = chunk;
     }
     return 0;
 }
@@ -339,12 +394,14 @@ static int dmg_read(BlockDriverState *bs, int64_t sector_num,
     BDRVDMGState *s = bs->opaque;
     int i;
 
-    for(i=0;i<nb_sectors;i++) {
+    for (i = 0; i < nb_sectors; i++) {
-	uint32_t sector_offset_in_chunk;
+        uint32_t sector_offset_in_chunk;
-	if(dmg_read_chunk(bs, sector_num+i) != 0)
+        if (dmg_read_chunk(bs, sector_num + i) != 0) {
-	    return -1;
+            return -1;
-	sector_offset_in_chunk = sector_num+i-s->sectors[s->current_chunk];
+        }
-	memcpy(buf+i*512,s->uncompressed_chunk+sector_offset_in_chunk*512,512);
+        sector_offset_in_chunk = sector_num + i - s->sectors[s->current_chunk];
+        memcpy(buf + i * 512,
+               s->uncompressed_chunk + sector_offset_in_chunk * 512, 512);
     }
     return 0;
 }
@@ -376,12 +433,12 @@ static void dmg_close(BlockDriverState *bs)
 }
 
 static BlockDriver bdrv_dmg = {
-    .format_name	= "dmg",
+    .format_name    = "dmg",
-    .instance_size	= sizeof(BDRVDMGState),
+    .instance_size  = sizeof(BDRVDMGState),
-    .bdrv_probe		= dmg_probe,
+    .bdrv_probe     = dmg_probe,
-    .bdrv_open		= dmg_open,
+    .bdrv_open      = dmg_open,
-    .bdrv_read          = dmg_co_read,
+    .bdrv_read      = dmg_co_read,
-    .bdrv_close		= dmg_close,
+    .bdrv_close     = dmg_close,
 };
 
 static void bdrv_dmg_init(void)

block/iscsi.c

@@ -417,6 +417,10 @@ static int coroutine_fn iscsi_co_flush(BlockDriverState *bs)
     IscsiLun *iscsilun = bs->opaque;
     struct IscsiTask iTask;
 
+    if (bs->sg) {
+        return 0;
+    }
+
     iscsi_co_init_iscsitask(iscsilun, &iTask);
 
 retry:
@@ -838,7 +842,8 @@ retry:
 
     if (iTask.status == SCSI_STATUS_CHECK_CONDITION &&
         iTask.task->sense.key == SCSI_SENSE_ILLEGAL_REQUEST &&
-        iTask.task->sense.ascq == SCSI_SENSE_ASCQ_INVALID_OPERATION_CODE) {
+        (iTask.task->sense.ascq == SCSI_SENSE_ASCQ_INVALID_OPERATION_CODE ||
+         iTask.task->sense.ascq == SCSI_SENSE_ASCQ_INVALID_FIELD_IN_CDB)) {
         /* WRITE SAME is not supported by the target */
         iscsilun->has_write_same = false;
         scsi_free_scsi_task(iTask.task);
@@ -1090,7 +1095,7 @@ static struct scsi_task *iscsi_do_inquiry(struct iscsi_context *iscsi, int lun,
     *inq = scsi_datain_unmarshall(task);
     if (*inq == NULL) {
         error_setg(errp, "iSCSI: failed to unmarshall inquiry datain blob");
-        goto fail;
+        goto fail_with_err;
     }
 
     return task;
@@ -1098,6 +1103,7 @@ static struct scsi_task *iscsi_do_inquiry(struct iscsi_context *iscsi, int lun,
 fail:
     error_setg(errp, "iSCSI: Inquiry command failed : %s",
                iscsi_get_error(iscsi));
+fail_with_err:
     if (task != NULL) {
         scsi_free_scsi_task(task);
     }
@@ -1226,6 +1232,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
     iscsi_readcapacity_sync(iscsilun, &local_err);
     if (local_err != NULL) {
         error_propagate(errp, local_err);
+        ret = -EINVAL;
         goto out;
     }
     bs->total_sectors = sector_lun2qemu(iscsilun->num_blocks, iscsilun);
@@ -1330,18 +1337,20 @@ static int iscsi_refresh_limits(BlockDriverState *bs)
 
     /* We don't actually refresh here, but just return data queried in
      * iscsi_open(): iscsi targets don't change their limits. */
-    if (iscsilun->lbp.lbpu || iscsilun->lbp.lbpws) {
+    if (iscsilun->lbp.lbpu) {
         if (iscsilun->bl.max_unmap < 0xffffffff) {
             bs->bl.max_discard = sector_lun2qemu(iscsilun->bl.max_unmap,
                                                  iscsilun);
         }
         bs->bl.discard_alignment = sector_lun2qemu(iscsilun->bl.opt_unmap_gran,
                                                    iscsilun);
+    }
 
-        if (iscsilun->bl.max_ws_len < 0xffffffff) {
+    if (iscsilun->bl.max_ws_len < 0xffffffff) {
-            bs->bl.max_write_zeroes = sector_lun2qemu(iscsilun->bl.max_ws_len,
+        bs->bl.max_write_zeroes = sector_lun2qemu(iscsilun->bl.max_ws_len,
-                                                      iscsilun);
+                                                  iscsilun);
-        }
+    }
+    if (iscsilun->lbp.lbpws) {
         bs->bl.write_zeroes_alignment = sector_lun2qemu(iscsilun->bl.opt_unmap_gran,
                                                         iscsilun);
     }
@@ -1391,7 +1400,7 @@ static int iscsi_create(const char *filename, QEMUOptionParameter *options,
     IscsiLun *iscsilun = NULL;
     QDict *bs_options;
 
-    bs = bdrv_new("");
+    bs = bdrv_new("", &error_abort);
 
     /* Read out options */
     while (options && options->name) {

block/mirror.c

@@ -325,11 +325,11 @@ static void coroutine_fn mirror_run(void *opaque)
 
     s->common.len = bdrv_getlength(bs);
     if (s->common.len <= 0) {
-        block_job_completed(&s->common, s->common.len);
+        ret = s->common.len;
-        return;
+        goto immediate_exit;
     }
 
-    length = (bdrv_getlength(bs) + s->granularity - 1) / s->granularity;
+    length = DIV_ROUND_UP(s->common.len, s->granularity);
     s->in_flight_bitmap = bitmap_new(length);
 
     /* If we have no backing file yet in the destination, we cannot let
@@ -339,7 +339,10 @@ static void coroutine_fn mirror_run(void *opaque)
     bdrv_get_backing_filename(s->target, backing_filename,
                               sizeof(backing_filename));
     if (backing_filename[0] && !s->target->backing_hd) {
-        bdrv_get_info(s->target, &bdi);
+        ret = bdrv_get_info(s->target, &bdi);
+        if (ret < 0) {
+            goto immediate_exit;
+        }
         if (s->granularity < bdi.cluster_size) {
             s->buf_size = MAX(s->buf_size, bdi.cluster_size);
             s->cow_bitmap = bitmap_new(length);
@@ -605,7 +608,10 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
     s->granularity = granularity;
     s->buf_size = MAX(buf_size, granularity);
 
-    s->dirty_bitmap = bdrv_create_dirty_bitmap(bs, granularity);
+    s->dirty_bitmap = bdrv_create_dirty_bitmap(bs, granularity, errp);
+    if (!s->dirty_bitmap) {
+        return;
+    }
     bdrv_set_enable_write_cache(s->target, true);
     bdrv_set_on_error(s->target, on_target_error, on_target_error);
     bdrv_iostatus_enable(s->target);
@@ -677,7 +683,7 @@ void commit_active_start(BlockDriverState *bs, BlockDriverState *base,
     mirror_start_job(bs, base, speed, 0, 0,
                      on_error, on_error, cb, opaque, &local_err,
                      &commit_active_job_driver, false, base);
-    if (error_is_set(&local_err)) {
+    if (local_err) {
         error_propagate(errp, local_err);
         goto error_restore_flags;
     }

block/nbd.c

@@ -175,7 +175,7 @@ static void nbd_parse_filename(const char *filename, QDict *options,
         InetSocketAddress *addr = NULL;
 
         addr = inet_parse(host_spec, errp);
-        if (error_is_set(errp)) {
+        if (!addr) {
             goto out;
         }
 

block/nfs.c

@@ -343,7 +343,7 @@ static int nfs_file_open(BlockDriverState *bs, QDict *options, int flags,
 
     opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (error_is_set(&local_err)) {
+    if (local_err) {
         error_propagate(errp, local_err);
         return -EINVAL;
     }

block/parallels.c

@@ -49,9 +49,9 @@ typedef struct BDRVParallelsState {
     CoMutex lock;
 
     uint32_t *catalog_bitmap;
-    int catalog_size;
+    unsigned int catalog_size;
 
-    int tracks;
+    unsigned int tracks;
 } BDRVParallelsState;
 
 static int parallels_probe(const uint8_t *buf, int buf_size, const char *filename)
@@ -93,8 +93,18 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
     bs->total_sectors = le32_to_cpu(ph.nb_sectors);
 
     s->tracks = le32_to_cpu(ph.tracks);
+    if (s->tracks == 0) {
+        error_setg(errp, "Invalid image: Zero sectors per track");
+        ret = -EINVAL;
+        goto fail;
+    }
 
     s->catalog_size = le32_to_cpu(ph.catalog_entries);
+    if (s->catalog_size > INT_MAX / 4) {
+        error_setg(errp, "Catalog too large");
+        ret = -EFBIG;
+        goto fail;
+    }
     s->catalog_bitmap = g_malloc(s->catalog_size * 4);
 
     ret = bdrv_pread(bs->file, 64, s->catalog_bitmap, s->catalog_size * 4);

block/qapi.c

@@ -532,12 +532,11 @@ static void dump_qdict(fprintf_function func_fprintf, void *f, int indentation,
 void bdrv_image_info_specific_dump(fprintf_function func_fprintf, void *f,
                                    ImageInfoSpecific *info_spec)
 {
-    Error *local_err = NULL;
     QmpOutputVisitor *ov = qmp_output_visitor_new();
     QObject *obj, *data;
 
     visit_type_ImageInfoSpecific(qmp_output_get_visitor(ov), &info_spec, NULL,
-                                 &local_err);
+                                 &error_abort);
     obj = qmp_output_get_qobject(ov);
     assert(qobject_type(obj) == QTYPE_QDICT);
     data = qdict_get(qobject_to_qdict(obj), "data");

block/qcow.c

@@ -119,7 +119,8 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
     }
     if (header.version != QCOW_VERSION) {
         char version[64];
-        snprintf(version, sizeof(version), "QCOW version %d", header.version);
+        snprintf(version, sizeof(version), "QCOW version %" PRIu32,
+                 header.version);
         error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
                   bs->device_name, "qcow", version);
         ret = -ENOTSUP;

block/qcow2-cluster.c

@@ -42,6 +42,13 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
     if (min_size <= s->l1_size)
         return 0;
 
+    /* Do a sanity check on min_size before trying to calculate new_l1_size
+     * (this prevents overflows during the while loop for the calculation of
+     * new_l1_size) */
+    if (min_size > INT_MAX / sizeof(uint64_t)) {
+        return -EFBIG;
+    }
+
     if (exact_size) {
         new_l1_size = min_size;
     } else {
@@ -55,7 +62,7 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
         }
     }
 
-    if (new_l1_size > INT_MAX) {
+    if (new_l1_size > INT_MAX / sizeof(uint64_t)) {
         return -EFBIG;
     }
 
@@ -359,15 +366,6 @@ static int coroutine_fn copy_sectors(BlockDriverState *bs,
     struct iovec iov;
     int n, ret;
 
-    /*
-     * If this is the last cluster and it is only partially used, we must only
-     * copy until the end of the image, or bdrv_check_request will fail for the
-     * bdrv_read/write calls below.
-     */
-    if (start_sect + n_end > bs->total_sectors) {
-        n_end = bs->total_sectors - start_sect;
-    }
-
     n = n_end - n_start;
     if (n <= 0) {
         return 0;
@@ -500,6 +498,7 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
         break;
     case QCOW2_CLUSTER_ZERO:
         if (s->qcow_version < 3) {
+            qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
             return -EIO;
         }
         c = count_contiguous_clusters(nb_clusters, s->cluster_size,
@@ -1368,9 +1367,9 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
     nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
 
     for (i = 0; i < nb_clusters; i++) {
-        uint64_t old_offset;
+        uint64_t old_l2_entry;
 
-        old_offset = be64_to_cpu(l2_table[l2_index + i]);
+        old_l2_entry = be64_to_cpu(l2_table[l2_index + i]);
 
         /*
          * Make sure that a discarded area reads back as zeroes for v3 images
@@ -1381,12 +1380,22 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
          * TODO We might want to use bdrv_get_block_status(bs) here, but we're
          * holding s->lock, so that doesn't work today.
          */
-        if (old_offset & QCOW_OFLAG_ZERO) {
+        switch (qcow2_get_cluster_type(old_l2_entry)) {
-            continue;
+            case QCOW2_CLUSTER_UNALLOCATED:
-        }
+                if (!bs->backing_hd) {
+                    continue;
+                }
+                break;
 
-        if ((old_offset & L2E_OFFSET_MASK) == 0 && !bs->backing_hd) {
+            case QCOW2_CLUSTER_ZERO:
-            continue;
+                continue;
+
+            case QCOW2_CLUSTER_NORMAL:
+            case QCOW2_CLUSTER_COMPRESSED:
+                break;
+
+            default:
+                abort();
         }
 
         /* First remove L2 entries */
@@ -1398,7 +1407,7 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
         }
 
         /* Then decrease the refcount */
-        qcow2_free_any_clusters(bs, old_offset, 1, type);
+        qcow2_free_any_clusters(bs, old_l2_entry, 1, type);
     }
 
     ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);

block/qcow2-refcount.c

@@ -28,7 +28,7 @@
 #include "qemu/range.h"
 #include "qapi/qmp/types.h"
 
-static int64_t alloc_clusters_noref(BlockDriverState *bs, int64_t size);
+static int64_t alloc_clusters_noref(BlockDriverState *bs, uint64_t size);
 static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
                             int64_t offset, int64_t length,
                             int addend, enum qcow2_discard_type type);
@@ -40,8 +40,10 @@ static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
 int qcow2_refcount_init(BlockDriverState *bs)
 {
     BDRVQcowState *s = bs->opaque;
-    int ret, refcount_table_size2, i;
+    unsigned int refcount_table_size2, i;
+    int ret;
 
+    assert(s->refcount_table_size <= INT_MAX / sizeof(uint64_t));
     refcount_table_size2 = s->refcount_table_size * sizeof(uint64_t);
     s->refcount_table = g_malloc(refcount_table_size2);
     if (s->refcount_table_size > 0) {
@@ -87,7 +89,7 @@ static int load_refcount_block(BlockDriverState *bs,
 static int get_refcount(BlockDriverState *bs, int64_t cluster_index)
 {
     BDRVQcowState *s = bs->opaque;
-    int refcount_table_index, block_index;
+    uint64_t refcount_table_index, block_index;
     int64_t refcount_block_offset;
     int ret;
     uint16_t *refcount_block;
@@ -192,10 +194,11 @@ static int alloc_refcount_block(BlockDriverState *bs,
      *   they can describe them themselves.
      *
      * - We need to consider that at this point we are inside update_refcounts
-     *   and doing the initial refcount increase. This means that some clusters
+     *   and potentially doing an initial refcount increase. This means that
-     *   have already been allocated by the caller, but their refcount isn't
+     *   some clusters have already been allocated by the caller, but their
-     *   accurate yet. free_cluster_index tells us where this allocation ends
+     *   refcount isn't accurate yet. If we allocate clusters for metadata, we
-     *   as long as we don't overwrite it by freeing clusters.
+     *   need to return -EAGAIN to signal the caller that it needs to restart
+     *   the search for free clusters.
      *
      * - alloc_clusters_noref and qcow2_free_clusters may load a different
      *   refcount block into the cache
@@ -280,7 +283,10 @@ static int alloc_refcount_block(BlockDriverState *bs,
         }
 
         s->refcount_table[refcount_table_index] = new_block;
-        return 0;
+
+        /* The new refcount block may be where the caller intended to put its
+         * data, so let it restart the search. */
+        return -EAGAIN;
     }
 
     ret = qcow2_cache_put(bs, s->refcount_block_cache, (void**) refcount_block);
@@ -303,8 +309,11 @@ static int alloc_refcount_block(BlockDriverState *bs,
 
     /* Calculate the number of refcount blocks needed so far */
     uint64_t refcount_block_clusters = 1 << (s->cluster_bits - REFCOUNT_SHIFT);
-    uint64_t blocks_used = (s->free_cluster_index +
+    uint64_t blocks_used = DIV_ROUND_UP(cluster_index, refcount_block_clusters);
-        refcount_block_clusters - 1) / refcount_block_clusters;
+
+    if (blocks_used > QCOW_MAX_REFTABLE_SIZE / sizeof(uint64_t)) {
+        return -EFBIG;
+    }
 
     /* And now we need at least one block more for the new metadata */
     uint64_t table_size = next_refcount_table_size(s, blocks_used + 1);
@@ -337,8 +346,6 @@ static int alloc_refcount_block(BlockDriverState *bs,
     uint16_t *new_blocks = g_malloc0(blocks_clusters * s->cluster_size);
     uint64_t *new_table = g_malloc0(table_size * sizeof(uint64_t));
 
-    assert(meta_offset >= (s->free_cluster_index * s->cluster_size));
-
     /* Fill the new refcount table */
     memcpy(new_table, s->refcount_table,
         s->refcount_table_size * sizeof(uint64_t));
@@ -401,18 +408,19 @@ static int alloc_refcount_block(BlockDriverState *bs,
     s->refcount_table_size = table_size;
     s->refcount_table_offset = table_offset;
 
-    /* Free old table. Remember, we must not change free_cluster_index */
+    /* Free old table. */
-    uint64_t old_free_cluster_index = s->free_cluster_index;
     qcow2_free_clusters(bs, old_table_offset, old_table_size * sizeof(uint64_t),
                         QCOW2_DISCARD_OTHER);
-    s->free_cluster_index = old_free_cluster_index;
 
     ret = load_refcount_block(bs, new_block, (void**) refcount_block);
     if (ret < 0) {
         return ret;
     }
 
-    return 0;
+    /* If we were trying to do the initial refcount update for some cluster
+     * allocation, we might have used the same clusters to store newly
+     * allocated metadata. Make the caller search some new space. */
+    return -EAGAIN;
 
 fail_table:
     g_free(new_table);
@@ -627,15 +635,16 @@ int qcow2_update_cluster_refcount(BlockDriverState *bs,
 
 
 /* return < 0 if error */
-static int64_t alloc_clusters_noref(BlockDriverState *bs, int64_t size)
+static int64_t alloc_clusters_noref(BlockDriverState *bs, uint64_t size)
 {
     BDRVQcowState *s = bs->opaque;
-    int i, nb_clusters, refcount;
+    uint64_t i, nb_clusters;
+    int refcount;
 
     nb_clusters = size_to_clusters(s, size);
 retry:
     for(i = 0; i < nb_clusters; i++) {
-        int64_t next_cluster_index = s->free_cluster_index++;
+        uint64_t next_cluster_index = s->free_cluster_index++;
         refcount = get_refcount(bs, next_cluster_index);
 
         if (refcount < 0) {
@@ -644,6 +653,13 @@ retry:
             goto retry;
         }
     }
+
+    /* Make sure that all offsets in the "allocated" range are representable
+     * in an int64_t */
+    if (s->free_cluster_index - 1 > (INT64_MAX >> s->cluster_bits)) {
+        return -EFBIG;
+    }
+
 #ifdef DEBUG_ALLOC2
     fprintf(stderr, "alloc_clusters: size=%" PRId64 " -> %" PRId64 "\n",
             size,
@@ -652,18 +668,21 @@ retry:
     return (s->free_cluster_index - nb_clusters) << s->cluster_bits;
 }
 
-int64_t qcow2_alloc_clusters(BlockDriverState *bs, int64_t size)
+int64_t qcow2_alloc_clusters(BlockDriverState *bs, uint64_t size)
 {
     int64_t offset;
     int ret;
 
     BLKDBG_EVENT(bs->file, BLKDBG_CLUSTER_ALLOC);
-    offset = alloc_clusters_noref(bs, size);
+    do {
-    if (offset < 0) {
+        offset = alloc_clusters_noref(bs, size);
-        return offset;
+        if (offset < 0) {
-    }
+            return offset;
+        }
+
+        ret = update_refcount(bs, offset, size, 1, QCOW2_DISCARD_NEVER);
+    } while (ret == -EAGAIN);
 
-    ret = update_refcount(bs, offset, size, 1, QCOW2_DISCARD_NEVER);
     if (ret < 0) {
         return ret;
     }
@@ -676,7 +695,6 @@ int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
 {
     BDRVQcowState *s = bs->opaque;
     uint64_t cluster_index;
-    uint64_t old_free_cluster_index;
     uint64_t i;
     int refcount, ret;
 
@@ -685,30 +703,28 @@ int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
         return 0;
     }
 
-    /* Check how many clusters there are free */
+    do {
-    cluster_index = offset >> s->cluster_bits;
+        /* Check how many clusters there are free */
-    for(i = 0; i < nb_clusters; i++) {
+        cluster_index = offset >> s->cluster_bits;
-        refcount = get_refcount(bs, cluster_index++);
+        for(i = 0; i < nb_clusters; i++) {
+            refcount = get_refcount(bs, cluster_index++);
 
-        if (refcount < 0) {
+            if (refcount < 0) {
-            return refcount;
+                return refcount;
-        } else if (refcount != 0) {
+            } else if (refcount != 0) {
-            break;
+                break;
+            }
         }
-    }
 
-    /* And then allocate them */
+        /* And then allocate them */
-    old_free_cluster_index = s->free_cluster_index;
+        ret = update_refcount(bs, offset, i << s->cluster_bits, 1,
-    s->free_cluster_index = cluster_index + i;
+                              QCOW2_DISCARD_NEVER);
+    } while (ret == -EAGAIN);
 
-    ret = update_refcount(bs, offset, i << s->cluster_bits, 1,
-                          QCOW2_DISCARD_NEVER);
     if (ret < 0) {
         return ret;
     }
 
-    s->free_cluster_index = old_free_cluster_index;
-
     return i;
 }
 
@@ -1011,8 +1027,7 @@ static void inc_refcounts(BlockDriverState *bs,
                           int64_t offset, int64_t size)
 {
     BDRVQcowState *s = bs->opaque;
-    int64_t start, last, cluster_offset;
+    uint64_t start, last, cluster_offset, k;
-    int k;
 
     if (size <= 0)
         return;
@@ -1022,11 +1037,7 @@ static void inc_refcounts(BlockDriverState *bs,
     for(cluster_offset = start; cluster_offset <= last;
         cluster_offset += s->cluster_size) {
         k = cluster_offset >> s->cluster_bits;
-        if (k < 0) {
+        if (k >= refcount_table_size) {
-            fprintf(stderr, "ERROR: invalid cluster offset=0x%" PRIx64 "\n",
-                cluster_offset);
-            res->corruptions++;
-        } else if (k >= refcount_table_size) {
             fprintf(stderr, "Warning: cluster offset=0x%" PRIx64 " is after "
                 "the end of the image file, can't properly check refcounts.\n",
                 cluster_offset);
@@ -1469,14 +1480,24 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
                           BdrvCheckMode fix)
 {
     BDRVQcowState *s = bs->opaque;
-    int64_t size, i, highest_cluster;
+    int64_t size, i, highest_cluster, nb_clusters;
-    int nb_clusters, refcount1, refcount2;
+    int refcount1, refcount2;
     QCowSnapshot *sn;
     uint16_t *refcount_table;
     int ret;
 
     size = bdrv_getlength(bs->file);
+    if (size < 0) {
+        res->check_errors++;
+        return size;
+    }
+
     nb_clusters = size_to_clusters(s, size);
+    if (nb_clusters > INT_MAX) {
+        res->check_errors++;
+        return -EFBIG;
+    }
+
     refcount_table = g_malloc0(nb_clusters * sizeof(uint16_t));
 
     res->bfi.total_clusters =

block/qcow2-snapshot.c

@@ -26,31 +26,6 @@
 #include "block/block_int.h"
 #include "block/qcow2.h"
 
-typedef struct QEMU_PACKED QCowSnapshotHeader {
-    /* header is 8 byte aligned */
-    uint64_t l1_table_offset;
-
-    uint32_t l1_size;
-    uint16_t id_str_size;
-    uint16_t name_size;
-
-    uint32_t date_sec;
-    uint32_t date_nsec;
-
-    uint64_t vm_clock_nsec;
-
-    uint32_t vm_state_size;
-    uint32_t extra_data_size; /* for extension */
-    /* extra data follows */
-    /* id_str follows */
-    /* name follows  */
-} QCowSnapshotHeader;
-
-typedef struct QEMU_PACKED QCowSnapshotExtraData {
-    uint64_t vm_state_size_large;
-    uint64_t disk_size;
-} QCowSnapshotExtraData;
-
 void qcow2_free_snapshots(BlockDriverState *bs)
 {
     BDRVQcowState *s = bs->opaque;
@@ -141,8 +116,14 @@ int qcow2_read_snapshots(BlockDriverState *bs)
         }
         offset += name_size;
         sn->name[name_size] = '\0';
+
+        if (offset - s->snapshots_offset > QCOW_MAX_SNAPSHOTS_SIZE) {
+            ret = -EFBIG;
+            goto fail;
+        }
     }
 
+    assert(offset - s->snapshots_offset <= INT_MAX);
     s->snapshots_size = offset - s->snapshots_offset;
     return 0;
 
@@ -163,7 +144,7 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
         uint32_t nb_snapshots;
         uint64_t snapshots_offset;
     } QEMU_PACKED header_data;
-    int64_t offset, snapshots_offset;
+    int64_t offset, snapshots_offset = 0;
     int ret;
 
     /* compute the size of the snapshots */
@@ -175,7 +156,14 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
         offset += sizeof(extra);
         offset += strlen(sn->id_str);
         offset += strlen(sn->name);
+
+        if (offset > QCOW_MAX_SNAPSHOTS_SIZE) {
+            ret = -EFBIG;
+            goto fail;
+        }
     }
+
+    assert(offset <= INT_MAX);
     snapshots_size = offset;
 
     /* Allocate space for the new snapshot list */
@@ -357,6 +345,10 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
     uint64_t *l1_table = NULL;
     int64_t l1_table_offset;
 
+    if (s->nb_snapshots >= QCOW_MAX_SNAPSHOTS) {
+        return -EFBIG;
+    }
+
     memset(sn, 0, sizeof(*sn));
 
     /* Generate an ID if it wasn't passed */
@@ -701,7 +693,11 @@ int qcow2_snapshot_load_tmp(BlockDriverState *bs,
     sn = &s->snapshots[snapshot_index];
 
     /* Allocate and read in the snapshot's L1 table */
-    new_l1_bytes = s->l1_size * sizeof(uint64_t);
+    if (sn->l1_size > QCOW_MAX_L1_SIZE) {
+        error_setg(errp, "Snapshot L1 table too large");
+        return -EFBIG;
+    }
+    new_l1_bytes = sn->l1_size * sizeof(uint64_t);
     new_l1_table = g_malloc0(align_offset(new_l1_bytes, 512));
 
     ret = bdrv_pread(bs->file, sn->l1_table_offset, new_l1_table, new_l1_bytes);

block/qcow2.c

@@ -124,8 +124,9 @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset,
 
         case QCOW2_EXT_MAGIC_BACKING_FORMAT:
             if (ext.len >= sizeof(bs->backing_format)) {
-                error_setg(errp, "ERROR: ext_backing_format: len=%u too large"
+                error_setg(errp, "ERROR: ext_backing_format: len=%" PRIu32
-                           " (>=%zu)", ext.len, sizeof(bs->backing_format));
+                           " too large (>=%zu)", ext.len,
+                           sizeof(bs->backing_format));
                 return 2;
             }
             ret = bdrv_pread(bs->file, offset, bs->backing_format, ext.len);
@@ -269,12 +270,15 @@ static int qcow2_mark_clean(BlockDriverState *bs)
     BDRVQcowState *s = bs->opaque;
 
     if (s->incompatible_features & QCOW2_INCOMPAT_DIRTY) {
-        int ret = bdrv_flush(bs);
+        int ret;
+
+        s->incompatible_features &= ~QCOW2_INCOMPAT_DIRTY;
+
+        ret = bdrv_flush(bs);
         if (ret < 0) {
             return ret;
         }
 
-        s->incompatible_features &= ~QCOW2_INCOMPAT_DIRTY;
         return qcow2_update_header(bs);
     }
     return 0;
@@ -329,6 +333,32 @@ static int qcow2_check(BlockDriverState *bs, BdrvCheckResult *result,
     return ret;
 }
 
+static int validate_table_offset(BlockDriverState *bs, uint64_t offset,
+                                 uint64_t entries, size_t entry_len)
+{
+    BDRVQcowState *s = bs->opaque;
+    uint64_t size;
+
+    /* Use signed INT64_MAX as the maximum even for uint64_t header fields,
+     * because values will be passed to qemu functions taking int64_t. */
+    if (entries > INT64_MAX / entry_len) {
+        return -EINVAL;
+    }
+
+    size = entries * entry_len;
+
+    if (INT64_MAX - size < offset) {
+        return -EINVAL;
+    }
+
+    /* Tables must be cluster aligned */
+    if (offset & (s->cluster_size - 1)) {
+        return -EINVAL;
+    }
+
+    return 0;
+}
+
 static QemuOptsList qcow2_runtime_opts = {
     .name = "qcow2",
     .head = QTAILQ_HEAD_INITIALIZER(qcow2_runtime_opts.head),
@@ -419,7 +449,8 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
                       Error **errp)
 {
     BDRVQcowState *s = bs->opaque;
-    int len, i, ret = 0;
+    unsigned int len, i;
+    int ret = 0;
     QCowHeader header;
     QemuOpts *opts;
     Error *local_err = NULL;
@@ -453,13 +484,26 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
     if (header.version < 2 || header.version > 3) {
-        report_unsupported(bs, errp, "QCOW version %d", header.version);
+        report_unsupported(bs, errp, "QCOW version %" PRIu32, header.version);
         ret = -ENOTSUP;
         goto fail;
     }
 
     s->qcow_version = header.version;
 
+    /* Initialise cluster size */
+    if (header.cluster_bits < MIN_CLUSTER_BITS ||
+        header.cluster_bits > MAX_CLUSTER_BITS) {
+        error_setg(errp, "Unsupported cluster size: 2^%" PRIu32,
+                   header.cluster_bits);
+        ret = -EINVAL;
+        goto fail;
+    }
+
+    s->cluster_bits = header.cluster_bits;
+    s->cluster_size = 1 << s->cluster_bits;
+    s->cluster_sectors = 1 << (s->cluster_bits - 9);
+
     /* Initialise version 3 header fields */
     if (header.version == 2) {
         header.incompatible_features    = 0;
@@ -473,6 +517,18 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
         be64_to_cpus(&header.autoclear_features);
         be32_to_cpus(&header.refcount_order);
         be32_to_cpus(&header.header_length);
+
+        if (header.header_length < 104) {
+            error_setg(errp, "qcow2 header too short");
+            ret = -EINVAL;
+            goto fail;
+        }
+    }
+
+    if (header.header_length > s->cluster_size) {
+        error_setg(errp, "qcow2 header exceeds cluster size");
+        ret = -EINVAL;
+        goto fail;
     }
 
     if (header.header_length > sizeof(header)) {
@@ -487,6 +543,12 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
         }
     }
 
+    if (header.backing_file_offset > s->cluster_size) {
+        error_setg(errp, "Invalid backing file offset");
+        ret = -EINVAL;
+        goto fail;
+    }
+
     if (header.backing_file_offset) {
         ext_end = header.backing_file_offset;
     } else {
@@ -506,6 +568,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
                                    s->incompatible_features &
                                    ~QCOW2_INCOMPAT_MASK);
         ret = -ENOTSUP;
+        g_free(feature_table);
         goto fail;
     }
 
@@ -529,14 +592,8 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     }
     s->refcount_order = header.refcount_order;
 
-    if (header.cluster_bits < MIN_CLUSTER_BITS ||
-        header.cluster_bits > MAX_CLUSTER_BITS) {
-        error_setg(errp, "Unsupported cluster size: 2^%i", header.cluster_bits);
-        ret = -EINVAL;
-        goto fail;
-    }
     if (header.crypt_method > QCOW_CRYPT_AES) {
-        error_setg(errp, "Unsupported encryption method: %i",
+        error_setg(errp, "Unsupported encryption method: %" PRIu32,
                    header.crypt_method);
         ret = -EINVAL;
         goto fail;
@@ -545,23 +602,52 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     if (s->crypt_method_header) {
         bs->encrypted = 1;
     }
-    s->cluster_bits = header.cluster_bits;
+
-    s->cluster_size = 1 << s->cluster_bits;
-    s->cluster_sectors = 1 << (s->cluster_bits - 9);
     s->l2_bits = s->cluster_bits - 3; /* L2 is always one cluster */
     s->l2_size = 1 << s->l2_bits;
     bs->total_sectors = header.size / 512;
     s->csize_shift = (62 - (s->cluster_bits - 8));
     s->csize_mask = (1 << (s->cluster_bits - 8)) - 1;
     s->cluster_offset_mask = (1LL << s->csize_shift) - 1;
+
     s->refcount_table_offset = header.refcount_table_offset;
     s->refcount_table_size =
         header.refcount_table_clusters << (s->cluster_bits - 3);
 
-    s->snapshots_offset = header.snapshots_offset;
+    if (header.refcount_table_clusters > qcow2_max_refcount_clusters(s)) {
-    s->nb_snapshots = header.nb_snapshots;
+        error_setg(errp, "Reference count table too large");
+        ret = -EINVAL;
+        goto fail;
+    }
+
+    ret = validate_table_offset(bs, s->refcount_table_offset,
+                                s->refcount_table_size, sizeof(uint64_t));
+    if (ret < 0) {
+        error_setg(errp, "Invalid reference count table offset");
+        goto fail;
+    }
+
+    /* Snapshot table offset/length */
+    if (header.nb_snapshots > QCOW_MAX_SNAPSHOTS) {
+        error_setg(errp, "Too many snapshots");
+        ret = -EINVAL;
+        goto fail;
+    }
+
+    ret = validate_table_offset(bs, header.snapshots_offset,
+                                header.nb_snapshots,
+                                sizeof(QCowSnapshotHeader));
+    if (ret < 0) {
+        error_setg(errp, "Invalid snapshot table offset");
+        goto fail;
+    }
 
     /* read the level 1 table */
+    if (header.l1_size > QCOW_MAX_L1_SIZE) {
+        error_setg(errp, "Active L1 table too large");
+        ret = -EFBIG;
+        goto fail;
+    }
     s->l1_size = header.l1_size;
 
     l1_vm_state_index = size_to_l1(s, header.size);
@@ -579,7 +665,16 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
         ret = -EINVAL;
         goto fail;
     }
+
+    ret = validate_table_offset(bs, header.l1_table_offset,
+                                header.l1_size, sizeof(uint64_t));
+    if (ret < 0) {
+        error_setg(errp, "Invalid L1 table offset");
+        goto fail;
+    }
     s->l1_table_offset = header.l1_table_offset;
+
+
     if (s->l1_size > 0) {
         s->l1_table = g_malloc0(
             align_offset(s->l1_size * sizeof(uint64_t), 512));
@@ -625,8 +720,10 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     /* read the backing file name */
     if (header.backing_file_offset != 0) {
         len = header.backing_file_size;
-        if (len > 1023) {
+        if (len > MIN(1023, s->cluster_size - header.backing_file_offset)) {
-            len = 1023;
+            error_setg(errp, "Backing file name too long");
+            ret = -EINVAL;
+            goto fail;
         }
         ret = bdrv_pread(bs->file, header.backing_file_offset,
                          bs->backing_file, len);
@@ -637,6 +734,10 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
         bs->backing_file[len] = '\0';
     }
 
+    /* Internal snapshots */
+    s->snapshots_offset = header.snapshots_offset;
+    s->nb_snapshots = header.nb_snapshots;
+
     ret = qcow2_read_snapshots(bs);
     if (ret < 0) {
         error_setg_errno(errp, -ret, "Could not read snapshots");
@@ -745,6 +846,9 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     if (s->l2_table_cache) {
         qcow2_cache_destroy(bs, s->l2_table_cache);
     }
+    if (s->refcount_block_cache) {
+        qcow2_cache_destroy(bs, s->refcount_block_cache);
+    }
     g_free(s->cluster_cache);
     qemu_vfree(s->cluster_data);
     return ret;
@@ -801,11 +905,25 @@ static int qcow2_set_key(BlockDriverState *bs, const char *key)
     return 0;
 }
 
-/* We have nothing to do for QCOW2 reopen, stubs just return
+/* We have no actual commit/abort logic for qcow2, but we need to write out any
- * success */
+ * unwritten data if we reopen read-only. */
 static int qcow2_reopen_prepare(BDRVReopenState *state,
                                 BlockReopenQueue *queue, Error **errp)
 {
+    int ret;
+
+    if ((state->flags & BDRV_O_RDWR) == 0) {
+        ret = bdrv_flush(state->bs);
+        if (ret < 0) {
+            return ret;
+        }
+
+        ret = qcow2_mark_clean(state->bs);
+        if (ret < 0) {
+            return ret;
+        }
+    }
+
     return 0;
 }
 
@@ -1432,7 +1550,9 @@ static int preallocate(BlockDriverState *bs)
             return ret;
         }
 
-        if (meta != NULL) {
+        while (meta) {
+            QCowL2Meta *next = meta->next;
+
             ret = qcow2_alloc_cluster_link_l2(bs, meta);
             if (ret < 0) {
                 qcow2_free_any_clusters(bs, meta->alloc_offset,
@@ -1443,6 +1563,9 @@ static int preallocate(BlockDriverState *bs)
             /* There are no dependent requests, but we need to remove our
              * request from the list of in-flight requests */
             QLIST_REMOVE(meta, next_in_flight);
+
+            g_free(meta);
+            meta = next;
         }
 
         /* TODO Preallocate data if requested */
@@ -1500,7 +1623,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
      */
     BlockDriverState* bs;
     QCowHeader *header;
-    uint8_t* refcount_table;
+    uint64_t* refcount_table;
     Error *local_err = NULL;
     int ret;
 
@@ -1552,9 +1675,10 @@ static int qcow2_create2(const char *filename, int64_t total_size,
         goto out;
     }
 
-    /* Write an empty refcount table */
+    /* Write a refcount table with one refcount block */
-    refcount_table = g_malloc0(cluster_size);
+    refcount_table = g_malloc0(2 * cluster_size);
-    ret = bdrv_pwrite(bs, cluster_size, refcount_table, cluster_size);
+    refcount_table[0] = cpu_to_be64(2 * cluster_size);
+    ret = bdrv_pwrite(bs, cluster_size, refcount_table, 2 * cluster_size);
     g_free(refcount_table);
 
     if (ret < 0) {
@@ -1579,7 +1703,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
         goto out;
     }
 
-    ret = qcow2_alloc_clusters(bs, 2 * cluster_size);
+    ret = qcow2_alloc_clusters(bs, 3 * cluster_size);
     if (ret < 0) {
         error_setg_errno(errp, -ret, "Could not allocate clusters for qcow2 "
                          "header and refcount table");

block/qcow2.h

@@ -38,6 +38,19 @@
 #define QCOW_CRYPT_AES  1
 
 #define QCOW_MAX_CRYPT_CLUSTERS 32
+#define QCOW_MAX_SNAPSHOTS 65536
+
+/* 8 MB refcount table is enough for 2 PB images at 64k cluster size
+ * (128 GB for 512 byte clusters, 2 EB for 2 MB clusters) */
+#define QCOW_MAX_REFTABLE_SIZE 0x800000
+
+/* 32 MB L1 table is enough for 2 PB images at 64k cluster size
+ * (128 GB for 512 byte clusters, 2 EB for 2 MB clusters) */
+#define QCOW_MAX_L1_SIZE 0x2000000
+
+/* Allow for an average of 1k per snapshot table entry, should be plenty of
+ * space for snapshot names and IDs */
+#define QCOW_MAX_SNAPSHOTS_SIZE (1024 * QCOW_MAX_SNAPSHOTS)
 
 /* indicate that the refcount of the referenced cluster is exactly one. */
 #define QCOW_OFLAG_COPIED     (1ULL << 63)
@@ -97,6 +110,32 @@ typedef struct QCowHeader {
     uint32_t header_length;
 } QEMU_PACKED QCowHeader;
 
+typedef struct QEMU_PACKED QCowSnapshotHeader {
+    /* header is 8 byte aligned */
+    uint64_t l1_table_offset;
+
+    uint32_t l1_size;
+    uint16_t id_str_size;
+    uint16_t name_size;
+
+    uint32_t date_sec;
+    uint32_t date_nsec;
+
+    uint64_t vm_clock_nsec;
+
+    uint32_t vm_state_size;
+    uint32_t extra_data_size; /* for extension */
+    /* extra data follows */
+    /* id_str follows */
+    /* name follows  */
+} QCowSnapshotHeader;
+
+typedef struct QEMU_PACKED QCowSnapshotExtraData {
+    uint64_t vm_state_size_large;
+    uint64_t disk_size;
+} QCowSnapshotExtraData;
+
+
 typedef struct QCowSnapshot {
     uint64_t l1_table_offset;
     uint32_t l1_size;
@@ -191,8 +230,8 @@ typedef struct BDRVQcowState {
     uint64_t *refcount_table;
     uint64_t refcount_table_offset;
     uint32_t refcount_table_size;
-    int64_t free_cluster_index;
+    uint64_t free_cluster_index;
-    int64_t free_byte_offset;
+    uint64_t free_byte_offset;
 
     CoMutex lock;
 
@@ -202,7 +241,7 @@ typedef struct BDRVQcowState {
     AES_KEY aes_decrypt_key;
     uint64_t snapshots_offset;
     int snapshots_size;
-    int nb_snapshots;
+    unsigned int nb_snapshots;
     QCowSnapshot *snapshots;
 
     int flags;
@@ -383,6 +422,11 @@ static inline int64_t qcow2_vm_state_offset(BDRVQcowState *s)
     return (int64_t)s->l1_vm_state_index << (s->cluster_bits + s->l2_bits);
 }
 
+static inline uint64_t qcow2_max_refcount_clusters(BDRVQcowState *s)
+{
+    return QCOW_MAX_REFTABLE_SIZE >> s->cluster_bits;
+}
+
 static inline int qcow2_get_cluster_type(uint64_t l2_entry)
 {
     if (l2_entry & QCOW_OFLAG_COMPRESSED) {
@@ -431,7 +475,7 @@ void qcow2_refcount_close(BlockDriverState *bs);
 int qcow2_update_cluster_refcount(BlockDriverState *bs, int64_t cluster_index,
                                   int addend, enum qcow2_discard_type type);
 
-int64_t qcow2_alloc_clusters(BlockDriverState *bs, int64_t size);
+int64_t qcow2_alloc_clusters(BlockDriverState *bs, uint64_t size);
 int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
     int nb_clusters);
 int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size);

block/qed.c

@@ -650,19 +650,21 @@ static int bdrv_qed_create(const char *filename, QEMUOptionParameter *options,
     }
 
     if (!qed_is_cluster_size_valid(cluster_size)) {
-        fprintf(stderr, "QED cluster size must be within range [%u, %u] and power of 2\n",
+        error_setg(errp, "QED cluster size must be within range [%u, %u] "
-                QED_MIN_CLUSTER_SIZE, QED_MAX_CLUSTER_SIZE);
+                         "and power of 2",
+                   QED_MIN_CLUSTER_SIZE, QED_MAX_CLUSTER_SIZE);
         return -EINVAL;
     }
     if (!qed_is_table_size_valid(table_size)) {
-        fprintf(stderr, "QED table size must be within range [%u, %u] and power of 2\n",
+        error_setg(errp, "QED table size must be within range [%u, %u] "
-                QED_MIN_TABLE_SIZE, QED_MAX_TABLE_SIZE);
+                         "and power of 2",
+                   QED_MIN_TABLE_SIZE, QED_MAX_TABLE_SIZE);
         return -EINVAL;
     }
     if (!qed_is_image_size_valid(image_size, cluster_size, table_size)) {
-        fprintf(stderr, "QED image size must be a non-zero multiple of "
+        error_setg(errp, "QED image size must be a non-zero multiple of "
-                        "cluster size and less than %" PRIu64 " bytes\n",
+                         "cluster size and less than %" PRIu64 " bytes",
-                qed_max_image_size(cluster_size, table_size));
+                   qed_max_image_size(cluster_size, table_size));
         return -EINVAL;
     }
 

block/quorum.c

@@ -753,7 +753,7 @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
 
     opts = qemu_opts_create(&quorum_runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (error_is_set(&local_err)) {
+    if (local_err) {
         ret = -EINVAL;
         goto exit;
     }
@@ -828,7 +828,7 @@ close_exit:
     g_free(opened);
 exit:
     /* propagate error */
-    if (error_is_set(&local_err)) {
+    if (local_err) {
         error_propagate(errp, local_err);
     }
     QDECREF(list);

block/raw-posix.c

@@ -366,7 +366,7 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
     BDRVRawState *s = bs->opaque;
     QemuOpts *opts;
     Error *local_err = NULL;
-    const char *filename;
+    const char *filename = NULL;
     int fd, ret;
     struct stat st;
 
@@ -446,6 +446,9 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
 
     ret = 0;
 fail:
+    if (filename && (bdrv_flags & BDRV_O_TEMPORARY)) {
+        unlink(filename);
+    }
     qemu_opts_del(opts);
     return ret;
 }

block/raw-win32.c

@@ -390,6 +390,9 @@ static void raw_close(BlockDriverState *bs)
 {
     BDRVRawState *s = bs->opaque;
     CloseHandle(s->hfile);
+    if (bs->open_flags & BDRV_O_TEMPORARY) {
+        unlink(bs->filename);
+    }
 }
 
 static int raw_truncate(BlockDriverState *bs, int64_t offset)

block/sheepdog.c

@@ -1099,7 +1099,7 @@ static int find_vdi_name(BDRVSheepdogState *s, const char *filename,
     }
 
     if (rsp->result != SD_RES_SUCCESS) {
-        error_report("cannot get vdi info, %s, %s %d %s",
+        error_report("cannot get vdi info, %s, %s %" PRIu32 " %s",
                      sd_strerror(rsp->result), filename, snapid, tag);
         if (rsp->result == SD_RES_NO_VDI) {
             ret = -ENOENT;
@@ -2316,8 +2316,8 @@ static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
             sn_tab[found].vm_state_size = inode.vm_state_size;
             sn_tab[found].vm_clock_nsec = inode.vm_clock_nsec;
 
-            snprintf(sn_tab[found].id_str, sizeof(sn_tab[found].id_str), "%u",
+            snprintf(sn_tab[found].id_str, sizeof(sn_tab[found].id_str),
-                     inode.snap_id);
+                     "%" PRIu32, inode.snap_id);
             pstrcpy(sn_tab[found].name,
                     MIN(sizeof(sn_tab[found].name), sizeof(inode.tag)),
                     inode.tag);

block/vdi.c

@@ -120,6 +120,11 @@ typedef unsigned char uuid_t[16];
 
 #define VDI_IS_ALLOCATED(X) ((X) < VDI_DISCARDED)
 
+/* max blocks in image is (0xffffffff / 4) */
+#define VDI_BLOCKS_IN_IMAGE_MAX  0x3fffffff
+#define VDI_DISK_SIZE_MAX        ((uint64_t)VDI_BLOCKS_IN_IMAGE_MAX * \
+                                  (uint64_t)DEFAULT_CLUSTER_SIZE)
+
 #if !defined(CONFIG_UUID)
 static inline void uuid_generate(uuid_t out)
 {
@@ -385,6 +390,14 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
     vdi_header_print(&header);
 #endif
 
+    if (header.disk_size > VDI_DISK_SIZE_MAX) {
+        error_setg(errp, "Unsupported VDI image size (size is 0x%" PRIx64
+                          ", max supported is 0x%" PRIx64 ")",
+                          header.disk_size, VDI_DISK_SIZE_MAX);
+        ret = -ENOTSUP;
+        goto fail;
+    }
+
     if (header.disk_size % SECTOR_SIZE != 0) {
         /* 'VBoxManage convertfromraw' can create images with odd disk sizes.
            We accept them but round the disk size to the next multiple of
@@ -395,34 +408,35 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     if (header.signature != VDI_SIGNATURE) {
-        error_setg(errp, "Image not in VDI format (bad signature %08x)", header.signature);
+        error_setg(errp, "Image not in VDI format (bad signature %08" PRIx32
+                   ")", header.signature);
         ret = -EINVAL;
         goto fail;
     } else if (header.version != VDI_VERSION_1_1) {
-        error_setg(errp, "unsupported VDI image (version %u.%u)",
+        error_setg(errp, "unsupported VDI image (version %" PRIu32 ".%" PRIu32
-                   header.version >> 16, header.version & 0xffff);
+                   ")", header.version >> 16, header.version & 0xffff);
         ret = -ENOTSUP;
         goto fail;
     } else if (header.offset_bmap % SECTOR_SIZE != 0) {
         /* We only support block maps which start on a sector boundary. */
         error_setg(errp, "unsupported VDI image (unaligned block map offset "
-                   "0x%x)", header.offset_bmap);
+                   "0x%" PRIx32 ")", header.offset_bmap);
         ret = -ENOTSUP;
         goto fail;
     } else if (header.offset_data % SECTOR_SIZE != 0) {
         /* We only support data blocks which start on a sector boundary. */
-        error_setg(errp, "unsupported VDI image (unaligned data offset 0x%x)",
+        error_setg(errp, "unsupported VDI image (unaligned data offset 0x%"
-                   header.offset_data);
+                   PRIx32 ")", header.offset_data);
         ret = -ENOTSUP;
         goto fail;
     } else if (header.sector_size != SECTOR_SIZE) {
-        error_setg(errp, "unsupported VDI image (sector size %u is not %u)",
+        error_setg(errp, "unsupported VDI image (sector size %" PRIu32
-                   header.sector_size, SECTOR_SIZE);
+                   " is not %u)", header.sector_size, SECTOR_SIZE);
         ret = -ENOTSUP;
         goto fail;
-    } else if (header.block_size != 1 * MiB) {
+    } else if (header.block_size != DEFAULT_CLUSTER_SIZE) {
-        error_setg(errp, "unsupported VDI image (sector size %u is not %u)",
+        error_setg(errp, "unsupported VDI image (block size %" PRIu32
-                   header.block_size, 1 * MiB);
+                   " is not %u)", header.block_size, DEFAULT_CLUSTER_SIZE);
         ret = -ENOTSUP;
         goto fail;
     } else if (header.disk_size >
@@ -441,6 +455,12 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
         error_setg(errp, "unsupported VDI image (non-NULL parent UUID)");
         ret = -ENOTSUP;
         goto fail;
+    } else if (header.blocks_in_image > VDI_BLOCKS_IN_IMAGE_MAX) {
+        error_setg(errp, "unsupported VDI image "
+                         "(too many blocks %u, max is %u)",
+                          header.blocks_in_image, VDI_BLOCKS_IN_IMAGE_MAX);
+        ret = -ENOTSUP;
+        goto fail;
     }
 
     bs->total_sectors = header.disk_size / SECTOR_SIZE;
@@ -689,11 +709,20 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options,
         options++;
     }
 
+    if (bytes > VDI_DISK_SIZE_MAX) {
+        result = -ENOTSUP;
+        error_setg(errp, "Unsupported VDI image size (size is 0x%" PRIx64
+                          ", max supported is 0x%" PRIx64 ")",
+                          bytes, VDI_DISK_SIZE_MAX);
+        goto exit;
+    }
+
     fd = qemu_open(filename,
                    O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
                    0644);
     if (fd < 0) {
-        return -errno;
+        result = -errno;
+        goto exit;
     }
 
     /* We need enough blocks to store the given disk size,
@@ -727,6 +756,7 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options,
     vdi_header_to_le(&header);
     if (write(fd, &header, sizeof(header)) < 0) {
         result = -errno;
+        goto close_and_exit;
     }
 
     if (bmap_size > 0) {
@@ -740,6 +770,8 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options,
         }
         if (write(fd, bmap, bmap_size) < 0) {
             result = -errno;
+            g_free(bmap);
+            goto close_and_exit;
         }
         g_free(bmap);
     }
@@ -747,13 +779,16 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options,
     if (image_type == VDI_TYPE_STATIC) {
         if (ftruncate(fd, sizeof(header) + bmap_size + blocks * block_size)) {
             result = -errno;
+            goto close_and_exit;
         }
     }
 
-    if (close(fd) < 0) {
+close_and_exit:
+    if ((close(fd) < 0) && !result) {
         result = -errno;
     }
 
+exit:
     return result;
 }
 

block/vhdx.c

@@ -780,12 +780,20 @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s)
     le32_to_cpus(&s->logical_sector_size);
     le32_to_cpus(&s->physical_sector_size);
 
-    if (s->logical_sector_size == 0 || s->params.block_size == 0) {
+    if (s->params.block_size < VHDX_BLOCK_SIZE_MIN ||
+        s->params.block_size > VHDX_BLOCK_SIZE_MAX) {
         ret = -EINVAL;
         goto exit;
     }
 
-    /* both block_size and sector_size are guaranteed powers of 2 */
+    /* only 2 supported sector sizes */
+    if (s->logical_sector_size != 512 && s->logical_sector_size != 4096) {
+        ret = -EINVAL;
+        goto exit;
+    }
+
+    /* Both block_size and sector_size are guaranteed powers of 2, below.
+       Due to range checks above, s->sectors_per_block can never be < 256 */
     s->sectors_per_block = s->params.block_size / s->logical_sector_size;
     s->chunk_ratio = (VHDX_MAX_SECTORS_PER_BLOCK) *
                      (uint64_t)s->logical_sector_size /

block/vmdk.c

@@ -262,7 +262,7 @@ static uint32_t vmdk_read_cid(BlockDriverState *bs, int parent)
     p_name = strstr(desc, cid_str);
     if (p_name != NULL) {
         p_name += cid_str_size;
-        sscanf(p_name, "%x", &cid);
+        sscanf(p_name, "%" SCNx32, &cid);
     }
 
     return cid;
@@ -290,7 +290,7 @@ static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid)
     p_name = strstr(desc, "CID");
     if (p_name != NULL) {
         p_name += sizeof("CID");
-        snprintf(p_name, sizeof(desc) - (p_name - desc), "%x\n", cid);
+        snprintf(p_name, sizeof(desc) - (p_name - desc), "%" PRIx32 "\n", cid);
         pstrcat(desc, sizeof(desc), tmp_desc);
     }
 
@@ -640,7 +640,7 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
 
     if (le32_to_cpu(header.version) > 3) {
         char buf[64];
-        snprintf(buf, sizeof(buf), "VMDK version %d",
+        snprintf(buf, sizeof(buf), "VMDK version %" PRId32,
                  le32_to_cpu(header.version));
         error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
                   bs->device_name, "vmdk", buf);
@@ -671,8 +671,9 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
     }
     if (bdrv_getlength(file) <
             le64_to_cpu(header.grain_offset) * BDRV_SECTOR_SIZE) {
-        error_setg(errp, "File truncated, expecting at least %lld bytes",
+        error_setg(errp, "File truncated, expecting at least %" PRId64 " bytes",
-                   le64_to_cpu(header.grain_offset) * BDRV_SECTOR_SIZE);
+                   (int64_t)(le64_to_cpu(header.grain_offset)
+                             * BDRV_SECTOR_SIZE));
         return -EINVAL;
     }
 
@@ -1707,8 +1708,8 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
     const char desc_template[] =
         "# Disk DescriptorFile\n"
         "version=1\n"
-        "CID=%x\n"
+        "CID=%" PRIx32 "\n"
-        "parentCID=%x\n"
+        "parentCID=%" PRIx32 "\n"
         "createType=\"%s\"\n"
         "%s"
         "\n"
@@ -1720,7 +1721,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
         "\n"
         "ddb.virtualHWVersion = \"%d\"\n"
         "ddb.geometry.cylinders = \"%" PRId64 "\"\n"
-        "ddb.geometry.heads = \"%d\"\n"
+        "ddb.geometry.heads = \"%" PRIu32 "\"\n"
         "ddb.geometry.sectors = \"63\"\n"
         "ddb.adapterType = \"%s\"\n";
 
@@ -1780,9 +1781,9 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
              strcmp(fmt, "twoGbMaxExtentFlat"));
     compress = !strcmp(fmt, "streamOptimized");
     if (flat) {
-        desc_extent_line = "RW %lld FLAT \"%s\" 0\n";
+        desc_extent_line = "RW %" PRId64 " FLAT \"%s\" 0\n";
     } else {
-        desc_extent_line = "RW %lld SPARSE \"%s\"\n";
+        desc_extent_line = "RW %" PRId64 " SPARSE \"%s\"\n";
     }
     if (flat && backing_file) {
         error_setg(errp, "Flat image can't have backing file");
@@ -1850,7 +1851,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
     }
     /* generate descriptor file */
     desc = g_strdup_printf(desc_template,
-                           (unsigned int)time(NULL),
+                           (uint32_t)time(NULL),
                            parent_cid,
                            fmt,
                            parent_desc_line,

block/vpc.c

@@ -45,6 +45,8 @@ enum vhd_type {
 // Seconds since Jan 1, 2000 0:00:00 (UTC)
 #define VHD_TIMESTAMP_BASE 946684800
 
+#define VHD_MAX_SECTORS       (65535LL * 255 * 255)
+
 // always big-endian
 typedef struct vhd_footer {
     char        creator[8]; // "conectix"
@@ -164,6 +166,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
     VHDDynDiskHeader *dyndisk_header;
     uint8_t buf[HEADER_SIZE];
     uint32_t checksum;
+    uint64_t computed_size;
     int disk_type = VHD_DYNAMIC;
     int ret;
 
@@ -222,7 +225,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     /* Allow a maximum disk size of approximately 2 TB */
-    if (bs->total_sectors >= 65535LL * 255 * 255) {
+    if (bs->total_sectors >= VHD_MAX_SECTORS) {
         ret = -EFBIG;
         goto fail;
     }
@@ -242,10 +245,31 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
         }
 
         s->block_size = be32_to_cpu(dyndisk_header->block_size);
+        if (!is_power_of_2(s->block_size) || s->block_size < BDRV_SECTOR_SIZE) {
+            error_setg(errp, "Invalid block size %" PRIu32, s->block_size);
+            ret = -EINVAL;
+            goto fail;
+        }
         s->bitmap_size = ((s->block_size / (8 * 512)) + 511) & ~511;
 
         s->max_table_entries = be32_to_cpu(dyndisk_header->max_table_entries);
-        s->pagetable = g_malloc(s->max_table_entries * 4);
+
+        if ((bs->total_sectors * 512) / s->block_size > 0xffffffffU) {
+            ret = -EINVAL;
+            goto fail;
+        }
+        if (s->max_table_entries > (VHD_MAX_SECTORS * 512) / s->block_size) {
+            ret = -EINVAL;
+            goto fail;
+        }
+
+        computed_size = (uint64_t) s->max_table_entries * s->block_size;
+        if (computed_size < bs->total_sectors * 512) {
+            ret = -EINVAL;
+            goto fail;
+        }
+
+        s->pagetable = qemu_blockalign(bs, s->max_table_entries * 4);
 
         s->bat_offset = be64_to_cpu(dyndisk_header->table_offset);
 
@@ -298,7 +322,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
     return 0;
 
 fail:
-    g_free(s->pagetable);
+    qemu_vfree(s->pagetable);
 #ifdef CACHE
     g_free(s->pageentry_u8);
 #endif
@@ -833,7 +857,7 @@ static int vpc_has_zero_init(BlockDriverState *bs)
 static void vpc_close(BlockDriverState *bs)
 {
     BDRVVPCState *s = bs->opaque;
-    g_free(s->pagetable);
+    qemu_vfree(s->pagetable);
 #ifdef CACHE
     g_free(s->pageentry_u8);
 #endif

block/vvfat.c

@@ -1119,6 +1119,7 @@ DLOG(if (stderr == NULL) {
         if (!s->fat_type) {
             s->fat_type = 16;
         }
+        s->first_sectors_number = 0x40;
         cyls = s->fat_type == 12 ? 64 : 1024;
         heads = 16;
         secs = 63;
@@ -1146,7 +1147,6 @@ DLOG(if (stderr == NULL) {
 
     s->current_cluster=0xffffffff;
 
-    s->first_sectors_number=0x40;
     /* read only is the default for safety */
     bs->read_only = 1;
     s->qcow = s->write_target = NULL;
@@ -2947,7 +2947,7 @@ static int enable_write_target(BDRVVVFATState *s)
     unlink(s->qcow_filename);
 #endif
 
-    s->bs->backing_hd = bdrv_new("");
+    s->bs->backing_hd = bdrv_new("", &error_abort);
     s->bs->backing_hd->drv = &vvfat_write_target;
     s->bs->backing_hd->opaque = g_malloc(sizeof(void*));
     *(void**)s->bs->backing_hd->opaque = s;

blockdev.c

@@ -452,16 +452,14 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
         }
     }
 
-    if (bdrv_find_node(qemu_opts_id(opts))) {
-        error_setg(errp, "device id=%s is conflicting with a node-name",
-                   qemu_opts_id(opts));
-        goto early_err;
-    }
-
     /* init */
     dinfo = g_malloc0(sizeof(*dinfo));
     dinfo->id = g_strdup(qemu_opts_id(opts));
-    dinfo->bdrv = bdrv_new(dinfo->id);
+    dinfo->bdrv = bdrv_new(dinfo->id, &error);
+    if (error) {
+        error_propagate(errp, error);
+        goto bdrv_new_err;
+    }
     dinfo->bdrv->open_flags = snapshot ? BDRV_O_SNAPSHOT : 0;
     dinfo->bdrv->read_only = ro;
     dinfo->refcount = 1;
@@ -523,8 +521,9 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
 
 err:
     bdrv_unref(dinfo->bdrv);
-    g_free(dinfo->id);
     QTAILQ_REMOVE(&drives, dinfo, next);
+bdrv_new_err:
+    g_free(dinfo->id);
     g_free(dinfo);
 early_err:
     QDECREF(bs_opts);
@@ -1116,6 +1115,7 @@ typedef struct InternalSnapshotState {
 static void internal_snapshot_prepare(BlkTransactionState *common,
                                       Error **errp)
 {
+    Error *local_err = NULL;
     const char *device;
     const char *name;
     BlockDriverState *bs;
@@ -1164,8 +1164,10 @@ static void internal_snapshot_prepare(BlkTransactionState *common,
     }
 
     /* check whether a snapshot with name exist */
-    ret = bdrv_snapshot_find_by_id_and_name(bs, NULL, name, &old_sn, errp);
+    ret = bdrv_snapshot_find_by_id_and_name(bs, NULL, name, &old_sn,
-    if (error_is_set(errp)) {
+                                            &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
         return;
     } else if (ret) {
         error_setg(errp,
@@ -1521,14 +1523,16 @@ static void eject_device(BlockDriverState *bs, int force, Error **errp)
         return;
     }
     if (!bdrv_dev_has_removable_media(bs)) {
-        error_set(errp, QERR_DEVICE_NOT_REMOVABLE, bdrv_get_device_name(bs));
+        error_setg(errp, "Device '%s' is not removable",
+                   bdrv_get_device_name(bs));
         return;
     }
 
     if (bdrv_dev_is_medium_locked(bs) && !bdrv_dev_is_tray_open(bs)) {
         bdrv_dev_eject_request(bs, force);
         if (!force) {
-            error_set(errp, QERR_DEVICE_LOCKED, bdrv_get_device_name(bs));
+            error_setg(errp, "Device '%s' is locked",
+                       bdrv_get_device_name(bs));
             return;
         }
     }
@@ -1876,6 +1880,10 @@ void qmp_block_commit(const char *device,
      */
     BlockdevOnError on_error = BLOCKDEV_ON_ERROR_REPORT;
 
+    if (!has_speed) {
+        speed = 0;
+    }
+
     /* drain all i/o before commits */
     bdrv_drain_all();
 
@@ -2216,7 +2224,8 @@ void qmp_block_job_cancel(const char *device,
         return;
     }
     if (job->paused && !force) {
-        error_set(errp, QERR_BLOCK_JOB_PAUSED, device);
+        error_setg(errp, "The block job for device '%s' is currently paused",
+                   device);
         return;
     }
 

blockjob.c

@@ -88,7 +88,7 @@ void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)
     Error *local_err = NULL;
 
     if (!job->driver->set_speed) {
-        error_set(errp, QERR_NOT_SUPPORTED);
+        error_set(errp, QERR_UNSUPPORTED);
         return;
     }
     job->driver->set_speed(job, speed, &local_err);

configure

@@ -1087,7 +1087,10 @@ for opt do
   ;;
   --enable-quorum) quorum="yes"
   ;;
-  *) echo "ERROR: unknown option $opt"; show_help="yes"
+  *)
+      echo "ERROR: unknown option $opt"
+      echo "Try '$0 --help' for more information"
+      exit 1
   ;;
   esac
 done
@@ -1217,8 +1220,8 @@ Advanced options (experts only):
   --enable-modules         enable modules support
   --enable-debug-tcg       enable TCG debugging
   --disable-debug-tcg      disable TCG debugging (default)
-  --enable-debug-info       enable debugging information (default)
+  --enable-debug-info      enable debugging information (default)
-  --disable-debug-info      disable debugging information
+  --disable-debug-info     disable debugging information
   --enable-debug           enable common debug build options
   --enable-sparse          enable sparse checker
   --disable-sparse         disable sparse checker (default)
@@ -1230,6 +1233,7 @@ Advanced options (experts only):
   --with-sdlabi            select preferred SDL ABI 1.2 or 2.0
   --disable-gtk            disable gtk UI
   --enable-gtk             enable gtk UI
+  --with-gtkabi            select preferred GTK ABI 2.0 or 3.0
   --disable-virtfs         disable VirtFS
   --enable-virtfs          enable VirtFS
   --disable-vnc            disable VNC
@@ -1353,7 +1357,7 @@ Advanced options (experts only):
 
 NOTE: The object files are built at the place where configure is launched
 EOF
-exit 1
+exit 0
 fi
 
 # Now we have handled --enable-tcg-interpreter and know we're not just
@@ -1448,7 +1452,10 @@ done
 if test "$stack_protector" != "no" ; then
   gcc_flags="-fstack-protector-strong -fstack-protector-all"
   for flag in $gcc_flags; do
-    if compile_prog "-Werror $flag" "" ; then
+    # We need to check both a compile and a link, since some compiler
+    # setups fail only on a .c->.o compile and some only at link time
+    if do_cc $QEMU_CFLAGS -Werror $flag -c -o $TMPO $TMPC &&
+       compile_prog "-Werror $flag" ""; then
       QEMU_CFLAGS="$QEMU_CFLAGS $flag"
       LIBTOOLFLAGS="$LIBTOOLFLAGS -Wc,$flag"
       break
@@ -4092,7 +4099,6 @@ echo "sparse enabled    $sparse"
 echo "strip binaries    $strip_opt"
 echo "profiler          $profiler"
 echo "static build      $static"
-echo "-Werror enabled   $werror"
 if test "$darwin" = "yes" ; then
     echo "Cocoa support     $cocoa"
 fi
@@ -4344,6 +4350,7 @@ if test "$modules" = "yes"; then
 fi
 if test "$sdl" = "yes" ; then
   echo "CONFIG_SDL=y" >> $config_host_mak
+  echo "CONFIG_SDLABI=$sdlabi" >> $config_host_mak
   echo "SDL_CFLAGS=$sdl_cflags" >> $config_host_mak
 fi
 if test "$cocoa" = "yes" ; then
@@ -4427,6 +4434,7 @@ fi
 echo "GLIB_CFLAGS=$glib_cflags" >> $config_host_mak
 if test "$gtk" = "yes" ; then
   echo "CONFIG_GTK=y" >> $config_host_mak
+  echo "CONFIG_GTKABI=$gtkabi" >> $config_host_mak
   echo "GTK_CFLAGS=$gtk_cflags" >> $config_host_mak
 fi
 if test "$vte" = "yes" ; then

cpu-exec.c

@@ -227,6 +227,8 @@ int cpu_exec(CPUArchState *env)
     TranslationBlock *tb;
     uint8_t *tc_ptr;
     uintptr_t next_tb;
+    /* This must be volatile so it is not trashed by longjmp() */
+    volatile bool have_tb_lock = false;
 
     if (cpu->halted) {
         if (!cpu_has_work(cpu)) {
@@ -600,6 +602,7 @@ int cpu_exec(CPUArchState *env)
                     cpu_loop_exit(cpu);
                 }
                 spin_lock(&tcg_ctx.tb_ctx.tb_lock);
+                have_tb_lock = true;
                 tb = tb_find_fast(env);
                 /* Note: we do it here to avoid a gcc bug on Mac OS X when
                    doing it in tb_find_slow */
@@ -621,6 +624,7 @@ int cpu_exec(CPUArchState *env)
                     tb_add_jump((TranslationBlock *)(next_tb & ~TB_EXIT_MASK),
                                 next_tb & TB_EXIT_MASK, tb);
                 }
+                have_tb_lock = false;
                 spin_unlock(&tcg_ctx.tb_ctx.tb_lock);
 
                 /* cpu_interrupt might be called while translating the
@@ -692,6 +696,10 @@ int cpu_exec(CPUArchState *env)
 #ifdef TARGET_I386
             x86_cpu = X86_CPU(cpu);
 #endif
+            if (have_tb_lock) {
+                spin_unlock(&tcg_ctx.tb_ctx.tb_lock);
+                have_tb_lock = false;
+            }
         }
     } /* for(;;) */
 

cpus.c

@@ -1454,7 +1454,7 @@ void qmp_pmemsave(int64_t addr, int64_t size, const char *filename,
         l = sizeof(buf);
         if (l > size)
             l = size;
-        cpu_physical_memory_rw(addr, buf, l, 0);
+        cpu_physical_memory_read(addr, buf, l);
         if (fwrite(buf, 1, l, f) != l) {
             error_set(errp, QERR_IO_ERROR);
             goto exit;

default-configs/usb.mak

@@ -1,6 +1,7 @@
 CONFIG_USB_TABLET_WACOM=y
 CONFIG_USB_STORAGE_BOT=y
 CONFIG_USB_STORAGE_UAS=y
+CONFIG_USB_STORAGE_MTP=y
 CONFIG_USB_SMARTCARD=y
 CONFIG_USB_AUDIO=y
 CONFIG_USB_SERIAL=y

dma-helpers.c

@@ -213,6 +213,7 @@ BlockDriverAIOCB *dma_bdrv_io(
     dbs->sg_cur_index = 0;
     dbs->sg_cur_byte = 0;
     dbs->dir = dir;
+    dbs->in_cancel = false;
     dbs->io_func = io_func;
     dbs->bh = NULL;
     qemu_iovec_init(&dbs->iov, sg->nsg);

docs/specs/standard-vga.txt

@@ -5,9 +5,10 @@ QEMU Standard VGA
 Exists in two variants, for isa and pci.
 
 command line switches:
-    -vga std            [ picks isa for -M isapc, otherwise pci ]
+    -vga std               [ picks isa for -M isapc, otherwise pci ]
-    -device VGA         [ pci variant ]
+    -device VGA            [ pci variant ]
-    -device isa-vga     [ isa variant ]
+    -device isa-vga        [ isa variant ]
+    -device secondary-vga  [ legacy-free pci variant ]
 
 
 PCI spec
@@ -31,9 +32,15 @@ PCI ROM Region:
    Holds the vgabios (qemu 0.14+).
 
 
+The legacy-free variant has no ROM and has PCI_CLASS_DISPLAY_OTHER
+instead of PCI_CLASS_DISPLAY_VGA.
+
+
 IO ports used
 -------------
 
+Doesn't apply to the legacy-free pci variant, use the MMIO bar instead.
+
 03c0 - 03df : standard vga ports
 01ce        : bochs vbe interface index port
 01cf        : bochs vbe interface data port (x86 only)

docs/writing-qmp-commands.txt

@@ -311,7 +311,7 @@ void hmp_hello_world(Monitor *mon, const QDict *qdict)
     Error *errp = NULL;
 
     qmp_hello_world(!!message, message, &errp);
-    if (error_is_set(&errp)) {
+    if (errp) {
         monitor_printf(mon, "%s\n", error_get_pretty(errp));
         error_free(errp);
         return;
@@ -483,7 +483,7 @@ void hmp_info_alarm_clock(Monitor *mon)
     Error *errp = NULL;
 
     clock = qmp_query_alarm_clock(&errp);
-    if (error_is_set(&errp)) {
+    if (errp) {
         monitor_printf(mon, "Could not query alarm clock information\n");
         error_free(errp);
         return;
@@ -634,7 +634,7 @@ void hmp_info_alarm_methods(Monitor *mon)
     Error *errp = NULL;
 
     method_list = qmp_query_alarm_methods(&errp);
-    if (error_is_set(&errp)) {
+    if (errp) {
         monitor_printf(mon, "Could not query alarm methods\n");
         error_free(errp);
         return;

fpu/softfloat.c

@@ -1626,6 +1626,26 @@ uint64 float32_to_uint64(float32 a STATUS_PARAM)
     return roundAndPackUint64(aSign, aSig64, aSigExtra STATUS_VAR);
 }
 
+/*----------------------------------------------------------------------------
+| Returns the result of converting the single-precision floating-point value
+| `a' to the 64-bit unsigned integer format.  The conversion is
+| performed according to the IEC/IEEE Standard for Binary Floating-Point
+| Arithmetic, except that the conversion is always rounded toward zero.  If
+| `a' is a NaN, the largest unsigned integer is returned.  Otherwise, if the
+| conversion overflows, the largest unsigned integer is returned.  If the
+| 'a' is negative, the result is rounded and zero is returned; values that do
+| not round to zero will raise the inexact flag.
+*----------------------------------------------------------------------------*/
+
+uint64 float32_to_uint64_round_to_zero(float32 a STATUS_PARAM)
+{
+    signed char current_rounding_mode = STATUS(float_rounding_mode);
+    set_float_rounding_mode(float_round_to_zero STATUS_VAR);
+    int64_t v = float32_to_uint64(a STATUS_VAR);
+    set_float_rounding_mode(current_rounding_mode STATUS_VAR);
+    return v;
+}
+
 /*----------------------------------------------------------------------------
 | Returns the result of converting the single-precision floating-point value
 | `a' to the 64-bit two's complement integer format.  The conversion is

fsdev/virtfs-proxy-helper.c

@@ -760,6 +760,7 @@ static int proxy_socket(const char *path, uid_t uid, gid_t gid)
         return -1;
     }
 
+    size = sizeof(qemu);
     client = accept(sock, (struct sockaddr *)&qemu, &size);
     if (client < 0) {
         do_perror("accept");

hmp-commands.hx

@@ -176,7 +176,7 @@ ETEXI
 
     {
         .name       = "drive_del",
-        .args_type  = "id:s",
+        .args_type  = "id:B",
         .params     = "device",
         .help       = "remove host block device",
         .user_print = monitor_user_noop,
@@ -658,6 +658,7 @@ ETEXI
         .help       = "add device, like -device on the command line",
         .user_print = monitor_user_noop,
         .mhandler.cmd_new = do_device_add,
+        .command_completion = device_add_completion,
     },
 
 STEXI
@@ -673,6 +674,7 @@ ETEXI
         .params     = "device",
         .help       = "remove device",
         .mhandler.cmd = hmp_device_del,
+        .command_completion = device_del_completion,
     },
 
 STEXI
@@ -998,26 +1000,34 @@ ETEXI
 
     {
         .name       = "dump-guest-memory",
-        .args_type  = "paging:-p,filename:F,begin:i?,length:i?",
+        .args_type  = "paging:-p,zlib:-z,lzo:-l,snappy:-s,filename:F,begin:i?,length:i?",
-        .params     = "[-p] filename [begin] [length]",
+        .params     = "[-p] [-z|-l|-s] filename [begin length]",
-        .help       = "dump guest memory to file"
+        .help       = "dump guest memory into file 'filename'.\n\t\t\t"
-                      "\n\t\t\t begin(optional): the starting physical address"
+                      "-p: do paging to get guest's memory mapping.\n\t\t\t"
-                      "\n\t\t\t length(optional): the memory size, in bytes",
+                      "-z: dump in kdump-compressed format, with zlib compression.\n\t\t\t"
+                      "-l: dump in kdump-compressed format, with lzo compression.\n\t\t\t"
+                      "-s: dump in kdump-compressed format, with snappy compression.\n\t\t\t"
+                      "begin: the starting physical address.\n\t\t\t"
+                      "length: the memory size, in bytes.",
         .mhandler.cmd = hmp_dump_guest_memory,
     },
 
 
 STEXI
-@item dump-guest-memory [-p] @var{protocol} @var{begin} @var{length}
+@item dump-guest-memory [-p] @var{filename} @var{begin} @var{length}
+@item dump-guest-memory [-z|-l|-s] @var{filename}
 @findex dump-guest-memory
 Dump guest memory to @var{protocol}. The file can be processed with crash or
-gdb.
+gdb. Without -z|-l|-s, the dump format is ELF.
-  filename: dump file name
+        -p: do paging to get guest's memory mapping.
-    paging: do paging to get guest's memory mapping
+        -z: dump in kdump-compressed format, with zlib compression.
+        -l: dump in kdump-compressed format, with lzo compression.
+        -s: dump in kdump-compressed format, with snappy compression.
+  filename: dump file name.
      begin: the starting physical address. It's optional, and should be
-            specified with length together.
+            specified together with length.
     length: the memory size, in bytes. It's optional, and should be specified
-            with begin together.
+            together with begin.
 ETEXI
 
     {
@@ -1254,6 +1264,7 @@ ETEXI
         .params     = "[qom-type=]type,id=str[,prop=value][,...]",
         .help       = "create QOM object",
         .mhandler.cmd = hmp_object_add,
+        .command_completion = object_add_completion,
     },
 
 STEXI
@@ -1268,6 +1279,7 @@ ETEXI
         .params     = "id",
         .help       = "destroy QOM object",
         .mhandler.cmd = hmp_object_del,
+        .command_completion = object_del_completion,
     },
 
 STEXI

hmp.c

@@ -1308,16 +1308,35 @@ void hmp_dump_guest_memory(Monitor *mon, const QDict *qdict)
 {
     Error *errp = NULL;
     int paging = qdict_get_try_bool(qdict, "paging", 0);
+    int zlib = qdict_get_try_bool(qdict, "zlib", 0);
+    int lzo = qdict_get_try_bool(qdict, "lzo", 0);
+    int snappy = qdict_get_try_bool(qdict, "snappy", 0);
     const char *file = qdict_get_str(qdict, "filename");
     bool has_begin = qdict_haskey(qdict, "begin");
     bool has_length = qdict_haskey(qdict, "length");
-    /* kdump-compressed format is not supported for HMP */
-    bool has_format = false;
     int64_t begin = 0;
     int64_t length = 0;
     enum DumpGuestMemoryFormat dump_format = DUMP_GUEST_MEMORY_FORMAT_ELF;
     char *prot;
 
+    if (zlib + lzo + snappy > 1) {
+        error_setg(&errp, "only one of '-z|-l|-s' can be set");
+        hmp_handle_error(mon, &errp);
+        return;
+    }
+
+    if (zlib) {
+        dump_format = DUMP_GUEST_MEMORY_FORMAT_KDUMP_ZLIB;
+    }
+
+    if (lzo) {
+        dump_format = DUMP_GUEST_MEMORY_FORMAT_KDUMP_LZO;
+    }
+
+    if (snappy) {
+        dump_format = DUMP_GUEST_MEMORY_FORMAT_KDUMP_SNAPPY;
+    }
+
     if (has_begin) {
         begin = qdict_get_int(qdict, "begin");
     }
@@ -1328,7 +1347,7 @@ void hmp_dump_guest_memory(Monitor *mon, const QDict *qdict)
     prot = g_strconcat("file:", file, NULL);
 
     qmp_dump_guest_memory(paging, prot, has_begin, begin, has_length, length,
-                          has_format, dump_format, &errp);
+                          true, dump_format, &errp);
     hmp_handle_error(mon, &errp);
     g_free(prot);
 }

hmp.h

@@ -15,6 +15,7 @@
 #define HMP_H
 
 #include "qemu-common.h"
+#include "qemu/readline.h"
 #include "qapi-types.h"
 #include "qapi/qmp/qdict.h"
 
@@ -92,5 +93,9 @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict);
 void hmp_cpu_add(Monitor *mon, const QDict *qdict);
 void hmp_object_add(Monitor *mon, const QDict *qdict);
 void hmp_object_del(Monitor *mon, const QDict *qdict);
+void object_add_completion(ReadLineState *rs, int nb_args, const char *str);
+void object_del_completion(ReadLineState *rs, int nb_args, const char *str);
+void device_add_completion(ReadLineState *rs, int nb_args, const char *str);
+void device_del_completion(ReadLineState *rs, int nb_args, const char *str);
 
 #endif

hw/9pfs/virtio-9p.c

@@ -987,8 +987,9 @@ static void v9fs_attach(void *opaque)
      */
     if (!s->migration_blocker) {
         s->root_fid = fid;
-        error_set(&s->migration_blocker, QERR_VIRTFS_FEATURE_BLOCKS_MIGRATION,
+        error_setg(&s->migration_blocker,
-                  s->ctx.fs_root ? s->ctx.fs_root : "NULL", s->tag);
+                   "Migration is disabled when VirtFS export path '%s' is mounted in the guest using mount_tag '%s'",
+                   s->ctx.fs_root ? s->ctx.fs_root : "NULL", s->tag);
         migrate_add_blocker(s->migration_blocker);
     }
 out:

hw/arm/cubieboard.c

@@ -43,6 +43,19 @@ static void cubieboard_init(QEMUMachineInitArgs *args)
         exit(1);
     }
 
+    object_property_set_int(OBJECT(&s->a10->timer), 32768, "clk0-freq", &err);
+    if (err != NULL) {
+        error_report("Couldn't set clk0 frequency: %s", error_get_pretty(err));
+        exit(1);
+    }
+
+    object_property_set_int(OBJECT(&s->a10->timer), 24000000, "clk1-freq",
+                            &err);
+    if (err != NULL) {
+        error_report("Couldn't set clk1 frequency: %s", error_get_pretty(err));
+        exit(1);
+    }
+
     object_property_set_bool(OBJECT(s->a10), true, "realized", &err);
     if (err != NULL) {
         error_report("Couldn't realize Allwinner A10: %s",

hw/arm/highbank.c

@@ -230,18 +230,23 @@ static void calxeda_init(QEMUMachineInitArgs *args, enum cxmachines machine)
 
     for (n = 0; n < smp_cpus; n++) {
         ObjectClass *oc = cpu_class_by_name(TYPE_ARM_CPU, cpu_model);
+        Object *cpuobj;
         ARMCPU *cpu;
         Error *err = NULL;
 
-        cpu = ARM_CPU(object_new(object_class_get_name(oc)));
+        if (!oc) {
-
+            error_report("Unable to find CPU definition");
-        object_property_set_int(OBJECT(cpu), MPCORE_PERIPHBASE, "reset-cbar",
-                                &err);
-        if (err) {
-            error_report("%s", error_get_pretty(err));
             exit(1);
         }
-        object_property_set_bool(OBJECT(cpu), true, "realized", &err);
+
+        cpuobj = object_new(object_class_get_name(oc));
+        cpu = ARM_CPU(cpuobj);
+
+        if (object_property_find(cpuobj, "reset-cbar", NULL)) {
+            object_property_set_int(cpuobj, MPCORE_PERIPHBASE,
+                                    "reset-cbar", &error_abort);
+        }
+        object_property_set_bool(cpuobj, true, "realized", &err);
         if (err) {
             error_report("%s", error_get_pretty(err));
             exit(1);

hw/arm/vexpress.c

@@ -192,10 +192,9 @@ static void init_cpus(const char *cpu_model, const char *privdev,
         Object *cpuobj = object_new(object_class_get_name(cpu_oc));
         Error *err = NULL;
 
-        object_property_set_int(cpuobj, periphbase, "reset-cbar", &err);
+        if (object_property_find(cpuobj, "reset-cbar", NULL)) {
-        if (err) {
+            object_property_set_int(cpuobj, periphbase,
-            error_report("%s", error_get_pretty(err));
+                                    "reset-cbar", &error_abort);
-            exit(1);
         }
         object_property_set_bool(cpuobj, true, "realized", &err);
         if (err) {

hw/arm/virt.c

@@ -75,8 +75,6 @@ typedef struct MemMapEntry {
 typedef struct VirtBoardInfo {
     struct arm_boot_info bootinfo;
     const char *cpu_model;
-    const char *qdevname;
-    const char *gic_compatible;
     const MemMapEntry *memmap;
     const int *irqmap;
     int smp_cpus;
@@ -98,10 +96,10 @@ typedef struct VirtBoardInfo {
 static const MemMapEntry a15memmap[] = {
     /* Space up to 0x8000000 is reserved for a boot ROM */
     [VIRT_FLASH] = { 0, 0x8000000 },
-    [VIRT_CPUPERIPHS] = { 0x8000000, 0x8000 },
+    [VIRT_CPUPERIPHS] = { 0x8000000, 0x20000 },
     /* GIC distributor and CPU interfaces sit inside the CPU peripheral space */
-    [VIRT_GIC_DIST] = { 0x8001000, 0x1000 },
+    [VIRT_GIC_DIST] = { 0x8000000, 0x10000 },
-    [VIRT_GIC_CPU] = { 0x8002000, 0x1000 },
+    [VIRT_GIC_CPU] = { 0x8010000, 0x10000 },
     [VIRT_UART] = { 0x9000000, 0x1000 },
     [VIRT_MMIO] = { 0xa000000, 0x200 },
     /* ...repeating for a total of NUM_VIRTIO_TRANSPORTS, each of that size */
@@ -117,16 +115,16 @@ static const int a15irqmap[] = {
 static VirtBoardInfo machines[] = {
     {
         .cpu_model = "cortex-a15",
-        .qdevname = "a15mpcore_priv",
+        .memmap = a15memmap,
-        .gic_compatible = "arm,cortex-a15-gic",
+        .irqmap = a15irqmap,
+    },
+    {
+        .cpu_model = "cortex-a57",
         .memmap = a15memmap,
         .irqmap = a15irqmap,
     },
     {
         .cpu_model = "host",
-        /* We use the A15 private peripheral model to get a V2 GIC */
-        .qdevname = "a15mpcore_priv",
-        .gic_compatible = "arm,cortex-a15-gic",
         .memmap = a15memmap,
         .irqmap = a15irqmap,
     },
@@ -251,8 +249,9 @@ static void fdt_add_gic_node(const VirtBoardInfo *vbi)
     qemu_fdt_setprop_cell(vbi->fdt, "/", "interrupt-parent", gic_phandle);
 
     qemu_fdt_add_subnode(vbi->fdt, "/intc");
+    /* 'cortex-a15-gic' means 'GIC v2' */
     qemu_fdt_setprop_string(vbi->fdt, "/intc", "compatible",
-                                vbi->gic_compatible);
+                            "arm,cortex-a15-gic");
     qemu_fdt_setprop_cell(vbi->fdt, "/intc", "#interrupt-cells", 3);
     qemu_fdt_setprop(vbi->fdt, "/intc", "interrupt-controller", NULL, 0);
     qemu_fdt_setprop_sized_cells(vbi->fdt, "/intc", "reg",
@@ -263,6 +262,56 @@ static void fdt_add_gic_node(const VirtBoardInfo *vbi)
     qemu_fdt_setprop_cell(vbi->fdt, "/intc", "phandle", gic_phandle);
 }
 
+static void create_gic(const VirtBoardInfo *vbi, qemu_irq *pic)
+{
+    /* We create a standalone GIC v2 */
+    DeviceState *gicdev;
+    SysBusDevice *gicbusdev;
+    const char *gictype = "arm_gic";
+    int i;
+
+    if (kvm_irqchip_in_kernel()) {
+        gictype = "kvm-arm-gic";
+    }
+
+    gicdev = qdev_create(NULL, gictype);
+    qdev_prop_set_uint32(gicdev, "revision", 2);
+    qdev_prop_set_uint32(gicdev, "num-cpu", smp_cpus);
+    /* Note that the num-irq property counts both internal and external
+     * interrupts; there are always 32 of the former (mandated by GIC spec).
+     */
+    qdev_prop_set_uint32(gicdev, "num-irq", NUM_IRQS + 32);
+    qdev_init_nofail(gicdev);
+    gicbusdev = SYS_BUS_DEVICE(gicdev);
+    sysbus_mmio_map(gicbusdev, 0, vbi->memmap[VIRT_GIC_DIST].base);
+    sysbus_mmio_map(gicbusdev, 1, vbi->memmap[VIRT_GIC_CPU].base);
+
+    /* Wire the outputs from each CPU's generic timer to the
+     * appropriate GIC PPI inputs, and the GIC's IRQ output to
+     * the CPU's IRQ input.
+     */
+    for (i = 0; i < smp_cpus; i++) {
+        DeviceState *cpudev = DEVICE(qemu_get_cpu(i));
+        int ppibase = NUM_IRQS + i * 32;
+        /* physical timer; we wire it up to the non-secure timer's ID,
+         * since a real A15 always has TrustZone but QEMU doesn't.
+         */
+        qdev_connect_gpio_out(cpudev, 0,
+                              qdev_get_gpio_in(gicdev, ppibase + 30));
+        /* virtual timer */
+        qdev_connect_gpio_out(cpudev, 1,
+                              qdev_get_gpio_in(gicdev, ppibase + 27));
+
+        sysbus_connect_irq(gicbusdev, i, qdev_get_gpio_in(cpudev, ARM_CPU_IRQ));
+    }
+
+    for (i = 0; i < NUM_IRQS; i++) {
+        pic[i] = qdev_get_gpio_in(gicdev, i);
+    }
+
+    fdt_add_gic_node(vbi);
+}
+
 static void create_uart(const VirtBoardInfo *vbi, qemu_irq *pic)
 {
     char *nodename;
@@ -340,8 +389,6 @@ static void machvirt_init(QEMUMachineInitArgs *args)
     MemoryRegion *sysmem = get_system_memory();
     int n;
     MemoryRegion *ram = g_new(MemoryRegion, 1);
-    DeviceState *dev;
-    SysBusDevice *busdev;
     const char *cpu_model = args->cpu_model;
     VirtBoardInfo *vbi;
 
@@ -404,25 +451,7 @@ static void machvirt_init(QEMUMachineInitArgs *args)
     vmstate_register_ram_global(ram);
     memory_region_add_subregion(sysmem, vbi->memmap[VIRT_MEM].base, ram);
 
-    dev = qdev_create(NULL, vbi->qdevname);
+    create_gic(vbi, pic);
-    qdev_prop_set_uint32(dev, "num-cpu", smp_cpus);
-    /* Note that the num-irq property counts both internal and external
-     * interrupts; there are always 32 of the former (mandated by GIC spec).
-     */
-    qdev_prop_set_uint32(dev, "num-irq", NUM_IRQS + 32);
-    qdev_init_nofail(dev);
-    busdev = SYS_BUS_DEVICE(dev);
-    sysbus_mmio_map(busdev, 0, vbi->memmap[VIRT_CPUPERIPHS].base);
-    fdt_add_gic_node(vbi);
-    for (n = 0; n < smp_cpus; n++) {
-        DeviceState *cpudev = DEVICE(qemu_get_cpu(n));
-
-        sysbus_connect_irq(busdev, n, qdev_get_gpio_in(cpudev, ARM_CPU_IRQ));
-    }
-
-    for (n = 0; n < NUM_IRQS; n++) {
-        pic[n] = qdev_get_gpio_in(dev, n);
-    }
 
     create_uart(vbi, pic);
 

hw/audio/hda-codec.c

@@ -261,6 +261,9 @@ static void hda_audio_set_amp(HDAAudioStream *st)
     left = left * 255 / QEMU_HDA_AMP_STEPS;
     right = right * 255 / QEMU_HDA_AMP_STEPS;
 
+    if (!st->state->mixer) {
+        return;
+    }
     if (st->output) {
         AUD_set_volume_out(st->voice.out, muted, left, right);
     } else {

hw/block/dataplane/virtio-blk.c

@@ -23,7 +23,7 @@
 #include "virtio-blk.h"
 #include "block/aio.h"
 #include "hw/virtio/virtio-bus.h"
-#include "monitor/monitor.h" /* for object_add() */
+#include "qom/object_interfaces.h"
 
 enum {
     SEG_MAX = 126,                  /* maximum number of I/O segments */
@@ -59,7 +59,7 @@ struct VirtIOBlockDataPlane {
      * use it).
      */
     IOThread *iothread;
-    bool internal_iothread;
+    IOThread internal_iothread_obj;
     AioContext *ctx;
     EventNotifier io_notifier;      /* Linux AIO completion */
     EventNotifier host_notifier;    /* doorbell */
@@ -391,23 +391,19 @@ void virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *blk,
     s->blk = blk;
 
     if (blk->iothread) {
-        s->internal_iothread = false;
         s->iothread = blk->iothread;
+        object_ref(OBJECT(s->iothread));
     } else {
-        /* Create per-device IOThread if none specified */
+        /* Create per-device IOThread if none specified.  This is for
-        Error *local_err = NULL;
+         * x-data-plane option compatibility.  If x-data-plane is removed we
-
+         * can drop this.
-        s->internal_iothread = true;
+         */
-        object_add(TYPE_IOTHREAD, vdev->name, NULL, NULL, &local_err);
+        object_initialize(&s->internal_iothread_obj,
-        if (error_is_set(&local_err)) {
+                          sizeof(s->internal_iothread_obj),
-            error_propagate(errp, local_err);
+                          TYPE_IOTHREAD);
-            g_free(s);
+        user_creatable_complete(OBJECT(&s->internal_iothread_obj), &error_abort);
-            return;
+        s->iothread = &s->internal_iothread_obj;
-        }
-        s->iothread = iothread_find(vdev->name);
-        assert(s->iothread);
     }
-    object_ref(OBJECT(s->iothread));
     s->ctx = iothread_get_aio_context(s->iothread);
 
     /* Prevent block operations that conflict with data plane thread */
@@ -426,9 +422,6 @@ void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s)
     virtio_blk_data_plane_stop(s);
     bdrv_set_in_use(s->blk->conf.bs, 0);
     object_unref(OBJECT(s->iothread));
-    if (s->internal_iothread) {
-        object_unparent(OBJECT(s->iothread));
-    }
     g_free(s);
 }
 

hw/block/nvme.c

@@ -752,8 +752,8 @@ static int nvme_init(PCIDevice *pci_dev)
         return -1;
     }
 
-    bs_size =  bdrv_getlength(n->conf.bs);
+    bs_size = bdrv_getlength(n->conf.bs);
-    if (bs_size <= 0) {
+    if (bs_size < 0) {
         return -1;
     }
 

hw/block/xen_disk.c

@@ -817,11 +817,14 @@ static int blk_connect(struct XenDevice *xendev)
     index = (blkdev->xendev.dev - 202 * 256) / 16;
     blkdev->dinfo = drive_get(IF_XEN, 0, index);
     if (!blkdev->dinfo) {
+        Error *local_err = NULL;
         /* setup via xenbus -> create new block driver instance */
         xen_be_printf(&blkdev->xendev, 2, "create new bdrv (xenbus setup)\n");
-        blkdev->bs = bdrv_new(blkdev->dev);
+        blkdev->bs = bdrv_new(blkdev->dev, &local_err);
+        if (local_err) {
+            blkdev->bs = NULL;
+        }
         if (blkdev->bs) {
-            Error *local_err = NULL;
             BlockDriver *drv = bdrv_find_whitelisted_format(blkdev->fileproto,
                                                            readonly);
             if (bdrv_open(&blkdev->bs, blkdev->filename, NULL, NULL, qflags,

hw/char/serial.c

@@ -225,8 +225,10 @@ static gboolean serial_xmit(GIOChannel *chan, GIOCondition cond, void *opaque)
 
     if (s->tsr_retry <= 0) {
         if (s->fcr & UART_FCR_FE) {
-            s->tsr = fifo8_is_empty(&s->xmit_fifo) ?
+            if (fifo8_is_empty(&s->xmit_fifo)) {
-                        0 : fifo8_pop(&s->xmit_fifo);
+                return FALSE;
+            }
+            s->tsr = fifo8_pop(&s->xmit_fifo);
             if (!s->xmit_fifo.num) {
                 s->lsr |= UART_LSR_THRE;
             }

hw/core/fw-path-provider.c

@@ -3,7 +3,8 @@
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; under version 2 of the License.
+ *  the Free Software Foundation; either version 2 of the License,
+ *  or (at your option) any later version.
  *
  *  This program is distributed in the hope that it will be useful,
  *  but WITHOUT ANY WARRANTY; without even the implied warranty of

hw/core/qdev-properties.c

@@ -587,8 +587,9 @@ static void set_blocksize(Object *obj, Visitor *v, void *opaque,
 
     /* We rely on power-of-2 blocksizes for bitmasks */
     if ((value & (value - 1)) != 0) {
-        error_set(errp, QERR_PROPERTY_VALUE_NOT_POWER_OF_2,
+        error_setg(errp,
-                  dev->id?:"", name, (int64_t)value);
+                  "Property %s.%s doesn't take value '%" PRId64 "', it's not a power of 2",
+                  dev->id ?: "", name, (int64_t)value);
         return;
     }
 
@@ -853,7 +854,7 @@ void error_set_from_qdev_prop_error(Error **errp, int ret, DeviceState *dev,
 {
     switch (ret) {
     case -EEXIST:
-        error_set(errp, QERR_PROPERTY_VALUE_IN_USE,
+        error_setg(errp, "Property '%s.%s' can't take value '%s', it's in use",
                   object_get_typename(OBJECT(dev)), prop->name, value);
         break;
     default:
@@ -862,7 +863,7 @@ void error_set_from_qdev_prop_error(Error **errp, int ret, DeviceState *dev,
                   object_get_typename(OBJECT(dev)), prop->name, value);
         break;
     case -ENOENT:
-        error_set(errp, QERR_PROPERTY_VALUE_NOT_FOUND,
+        error_setg(errp, "Property '%s.%s' can't find value '%s'",
                   object_get_typename(OBJECT(dev)), prop->name, value);
         break;
     case 0:

hw/display/cirrus_vga.c

@@ -2913,7 +2913,7 @@ static void isa_cirrus_vga_realizefn(DeviceState *dev, Error **errp)
     ISACirrusVGAState *d = ISA_CIRRUS_VGA(dev);
     VGACommonState *s = &d->cirrus_vga.vga;
 
-    vga_common_init(s, OBJECT(dev));
+    vga_common_init(s, OBJECT(dev), true);
     cirrus_init_common(&d->cirrus_vga, OBJECT(dev), CIRRUS_ID_CLGD5430, 0,
                        isa_address_space(isadev),
                        isa_address_space_io(isadev));
@@ -2960,7 +2960,7 @@ static int pci_cirrus_vga_initfn(PCIDevice *dev)
      int16_t device_id = pc->device_id;
 
      /* setup VGA */
-     vga_common_init(&s->vga, OBJECT(dev));
+     vga_common_init(&s->vga, OBJECT(dev), true);
      cirrus_init_common(s, OBJECT(dev), device_id, 1, pci_address_space(dev),
                         pci_address_space_io(dev));
      s->vga.con = graphic_console_init(DEVICE(dev), 0, s->vga.hw_ops, &s->vga);

hw/display/qxl.c

@@ -2061,7 +2061,7 @@ static int qxl_init_primary(PCIDevice *dev)
     qxl->id = 0;
     qxl_init_ramsize(qxl);
     vga->vram_size_mb = qxl->vga.vram_size >> 20;
-    vga_common_init(vga, OBJECT(dev));
+    vga_common_init(vga, OBJECT(dev), true);
     vga_init(vga, OBJECT(dev),
              pci_address_space(dev), pci_address_space_io(dev), false);
     portio_list_init(qxl_vga_port_list, OBJECT(dev), qxl_vga_portio_list,

hw/display/vga-isa-mm.c

@@ -132,7 +132,7 @@ int isa_vga_mm_init(hwaddr vram_base,
     s = g_malloc0(sizeof(*s));
 
     s->vga.vram_size_mb = VGA_RAM_SIZE >> 20;
-    vga_common_init(&s->vga, NULL);
+    vga_common_init(&s->vga, NULL, true);
     vga_mm_init(s, vram_base, ctrl_base, it_shift, address_space);
 
     s->vga.con = graphic_console_init(NULL, 0, s->vga.hw_ops, s);

hw/display/vga-isa.c

@@ -56,7 +56,7 @@ static void vga_isa_realizefn(DeviceState *dev, Error **errp)
     MemoryRegion *vga_io_memory;
     const MemoryRegionPortio *vga_ports, *vbe_ports;
 
-    vga_common_init(s, OBJECT(dev));
+    vga_common_init(s, OBJECT(dev), true);
     s->legacy_address_space = isa_address_space(isadev);
     vga_io_memory = vga_init_io(s, OBJECT(dev), &vga_ports, &vbe_ports);
     isa_register_portio_list(isadev, 0x3b0, vga_ports, s, "vga");

hw/display/vga-pci.c

@@ -147,7 +147,7 @@ static int pci_std_vga_initfn(PCIDevice *dev)
     VGACommonState *s = &d->vga;
 
     /* vga + console init */
-    vga_common_init(s, OBJECT(dev));
+    vga_common_init(s, OBJECT(dev), true);
     vga_init(s, OBJECT(dev), pci_address_space(dev), pci_address_space_io(dev),
              true);
 
@@ -179,12 +179,51 @@ static int pci_std_vga_initfn(PCIDevice *dev)
     return 0;
 }
 
+static int pci_secondary_vga_initfn(PCIDevice *dev)
+{
+    PCIVGAState *d = DO_UPCAST(PCIVGAState, dev, dev);
+    VGACommonState *s = &d->vga;
+
+    /* vga + console init */
+    vga_common_init(s, OBJECT(dev), false);
+    s->con = graphic_console_init(DEVICE(dev), 0, s->hw_ops, s);
+
+    /* mmio bar */
+    memory_region_init(&d->mmio, OBJECT(dev), "vga.mmio", 4096);
+    memory_region_init_io(&d->ioport, OBJECT(dev), &pci_vga_ioport_ops, d,
+                          "vga ioports remapped", PCI_VGA_IOPORT_SIZE);
+    memory_region_init_io(&d->bochs, OBJECT(dev), &pci_vga_bochs_ops, d,
+                          "bochs dispi interface", PCI_VGA_BOCHS_SIZE);
+
+    memory_region_add_subregion(&d->mmio, PCI_VGA_IOPORT_OFFSET,
+                                &d->ioport);
+    memory_region_add_subregion(&d->mmio, PCI_VGA_BOCHS_OFFSET,
+                                &d->bochs);
+
+    pci_register_bar(&d->dev, 0, PCI_BASE_ADDRESS_MEM_PREFETCH, &s->vram);
+    pci_register_bar(&d->dev, 2, PCI_BASE_ADDRESS_SPACE_MEMORY, &d->mmio);
+
+    return 0;
+}
+
+static void pci_secondary_vga_reset(DeviceState *dev)
+{
+    PCIVGAState *d = DO_UPCAST(PCIVGAState, dev.qdev, dev);
+
+    vga_common_reset(&d->vga);
+}
+
 static Property vga_pci_properties[] = {
     DEFINE_PROP_UINT32("vgamem_mb", PCIVGAState, vga.vram_size_mb, 16),
     DEFINE_PROP_BIT("mmio", PCIVGAState, flags, PCI_VGA_FLAG_ENABLE_MMIO, true),
     DEFINE_PROP_END_OF_LIST(),
 };
 
+static Property secondary_pci_properties[] = {
+    DEFINE_PROP_UINT32("vgamem_mb", PCIVGAState, vga.vram_size_mb, 16),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
 static void vga_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
@@ -201,6 +240,20 @@ static void vga_class_init(ObjectClass *klass, void *data)
     set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories);
 }
 
+static void secondary_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
+
+    k->init = pci_secondary_vga_initfn;
+    k->vendor_id = PCI_VENDOR_ID_QEMU;
+    k->device_id = PCI_DEVICE_ID_QEMU_VGA;
+    k->class_id = PCI_CLASS_DISPLAY_OTHER;
+    dc->vmsd = &vmstate_vga_pci;
+    dc->props = secondary_pci_properties;
+    dc->reset = pci_secondary_vga_reset;
+}
+
 static const TypeInfo vga_info = {
     .name          = "VGA",
     .parent        = TYPE_PCI_DEVICE,
@@ -208,9 +261,17 @@ static const TypeInfo vga_info = {
     .class_init    = vga_class_init,
 };
 
+static const TypeInfo secondary_info = {
+    .name          = "secondary-vga",
+    .parent        = TYPE_PCI_DEVICE,
+    .instance_size = sizeof(PCIVGAState),
+    .class_init    = secondary_class_init,
+};
+
 static void vga_register_types(void)
 {
     type_register_static(&vga_info);
+    type_register_static(&secondary_info);
 }
 
 type_init(vga_register_types)

hw/display/vga.c

@@ -171,6 +171,10 @@ static void vga_update_memory_access(VGACommonState *s)
     MemoryRegion *region, *old_region = s->chain4_alias;
     hwaddr base, offset, size;
 
+    if (s->legacy_address_space == NULL) {
+        return;
+    }
+
     s->chain4_alias = NULL;
 
     if ((s->sr[VGA_SEQ_PLANE_WRITE] & VGA_SR02_ALL_PLANES) ==
@@ -2252,7 +2256,7 @@ static const GraphicHwOps vga_ops = {
     .text_update = vga_update_text,
 };
 
-void vga_common_init(VGACommonState *s, Object *obj)
+void vga_common_init(VGACommonState *s, Object *obj, bool global_vmstate)
 {
     int i, j, v, b;
 
@@ -2289,7 +2293,7 @@ void vga_common_init(VGACommonState *s, Object *obj)
 
     s->is_vbe_vmstate = 1;
     memory_region_init_ram(&s->vram, obj, "vga.vram", s->vram_size);
-    vmstate_register_ram_global(&s->vram);
+    vmstate_register_ram(&s->vram, global_vmstate ? NULL : DEVICE(obj));
     xen_register_framebuffer(&s->vram);
     s->vram_ptr = memory_region_get_ram_ptr(&s->vram);
     s->get_bpp = vga_get_bpp;

hw/display/vga_int.h

@@ -177,7 +177,7 @@ static inline int c6_to_8(int v)
     return (v << 2) | (b << 1) | b;
 }
 
-void vga_common_init(VGACommonState *s, Object *obj);
+void vga_common_init(VGACommonState *s, Object *obj, bool global_vmstate);
 void vga_init(VGACommonState *s, Object *obj, MemoryRegion *address_space,
               MemoryRegion *address_space_io, bool init_vga_ports);
 MemoryRegion *vga_init_io(VGACommonState *s, Object *obj,

hw/display/vmware_vga.c

@@ -1207,7 +1207,7 @@ static void vmsvga_init(DeviceState *dev, struct vmsvga_state_s *s,
     vmstate_register_ram_global(&s->fifo_ram);
     s->fifo_ptr = memory_region_get_ram_ptr(&s->fifo_ram);
 
-    vga_common_init(&s->vga, OBJECT(dev));
+    vga_common_init(&s->vga, OBJECT(dev), true);
     vga_init(&s->vga, OBJECT(dev), address_space, io, true);
     vmstate_register(NULL, 0, &vmstate_vga_common, &s->vga);
     s->new_depth = 32;

hw/i2c/smbus_eeprom.c

@@ -71,7 +71,7 @@ static void eeprom_write_data(SMBusDevice *dev, uint8_t cmd, uint8_t *buf, int l
     printf("eeprom_write_byte: addr=0x%02x cmd=0x%02x val=0x%02x\n",
            dev->i2c.address, cmd, buf[0]);
 #endif
-    /* An page write operation is not a valid SMBus command.
+    /* A page write operation is not a valid SMBus command.
        It is a block write without a length byte.  Fortunately we
        get the full block anyway.  */
     /* TODO: Should this set the current location?  */

hw/i386/acpi-build.c

@@ -391,7 +391,7 @@ static void build_append_int(GArray *table, uint32_t value)
         build_append_byte(table, 0x01); /* OneOp */
     } else if (value <= 0xFF) {
         build_append_value(table, value, 1);
-    } else if (value <= 0xFFFFF) {
+    } else if (value <= 0xFFFF) {
         build_append_value(table, value, 2);
     } else {
         build_append_value(table, value, 4);

hw/i386/acpi-dsdt-cpu-hotplug.dsl

@@ -93,7 +93,7 @@ Scope(\_SB) {
     }
 
     Device(CPU_HOTPLUG_RESOURCE_DEVICE) {
-        Name(_HID, "ACPI0004")
+        Name(_HID, EisaId("PNP0A06"))
 
         Name(_CRS, ResourceTemplate() {
             IO(Decode16, CPU_STATUS_BASE, CPU_STATUS_BASE, 0, CPU_STATUS_LEN)

hw/i386/acpi-dsdt.hex.generated

@@ -3,12 +3,12 @@ static unsigned char AcpiDsdtAmlCode[] = {
 0x53,
 0x44,
 0x54,
-0x85,
+0x80,
 0x11,
 0x0,
 0x0,
 0x1,
-0x8b,
+0x60,
 0x42,
 0x58,
 0x50,
@@ -31,8 +31,8 @@ static unsigned char AcpiDsdtAmlCode[] = {
 0x4e,
 0x54,
 0x4c,
-0x23,
+0x15,
-0x8,
+0x11,
 0x13,
 0x20,
 0x10,
@@ -4010,7 +4010,7 @@ static unsigned char AcpiDsdtAmlCode[] = {
 0x53,
 0x1,
 0x10,
-0x47,
+0x42,
 0x11,
 0x5f,
 0x53,
@@ -4243,7 +4243,7 @@ static unsigned char AcpiDsdtAmlCode[] = {
 0x60,
 0x5b,
 0x82,
-0x2e,
+0x29,
 0x50,
 0x52,
 0x45,
@@ -4253,16 +4253,11 @@ static unsigned char AcpiDsdtAmlCode[] = {
 0x48,
 0x49,
 0x44,
-0xd,
+0xc,
 0x41,
-0x43,
+0xd0,
-0x50,
+0xa,
-0x49,
+0x6,
-0x30,
-0x30,
-0x30,
-0x34,
-0x0,
 0x8,
 0x5f,
 0x43,

hw/i386/kvmvapic.c

@@ -124,14 +124,14 @@ static const TPRInstruction tpr_instr[] = {
 
 static void read_guest_rom_state(VAPICROMState *s)
 {
-    cpu_physical_memory_rw(s->rom_state_paddr, (void *)&s->rom_state,
+    cpu_physical_memory_read(s->rom_state_paddr, &s->rom_state,
-                           sizeof(GuestROMState), 0);
+                             sizeof(GuestROMState));
 }
 
 static void write_guest_rom_state(VAPICROMState *s)
 {
-    cpu_physical_memory_rw(s->rom_state_paddr, (void *)&s->rom_state,
+    cpu_physical_memory_write(s->rom_state_paddr, &s->rom_state,
-                           sizeof(GuestROMState), 1);
+                              sizeof(GuestROMState));
 }
 
 static void update_guest_rom_state(VAPICROMState *s)
@@ -311,16 +311,14 @@ static int update_rom_mapping(VAPICROMState *s, CPUX86State *env, target_ulong i
     for (pos = le32_to_cpu(s->rom_state.fixup_start);
          pos < le32_to_cpu(s->rom_state.fixup_end);
          pos += 4) {
-        cpu_physical_memory_rw(paddr + pos - s->rom_state.vaddr,
+        cpu_physical_memory_read(paddr + pos - s->rom_state.vaddr,
-                               (void *)&offset, sizeof(offset), 0);
+                                 &offset, sizeof(offset));
         offset = le32_to_cpu(offset);
-        cpu_physical_memory_rw(paddr + offset, (void *)&patch,
+        cpu_physical_memory_read(paddr + offset, &patch, sizeof(patch));
-                               sizeof(patch), 0);
         patch = le32_to_cpu(patch);
         patch += rom_state_vaddr - le32_to_cpu(s->rom_state.vaddr);
         patch = cpu_to_le32(patch);
-        cpu_physical_memory_rw(paddr + offset, (void *)&patch,
+        cpu_physical_memory_write(paddr + offset, &patch, sizeof(patch));
-                               sizeof(patch), 1);
     }
     read_guest_rom_state(s);
     s->vapic_paddr = paddr + le32_to_cpu(s->rom_state.vapic_vaddr) -
@@ -364,8 +362,8 @@ static int vapic_enable(VAPICROMState *s, X86CPU *cpu)
     }
     vapic_paddr = s->vapic_paddr +
         (((hwaddr)cpu_number) << VAPIC_CPU_SHIFT);
-    cpu_physical_memory_rw(vapic_paddr + offsetof(VAPICState, enabled),
+    cpu_physical_memory_write(vapic_paddr + offsetof(VAPICState, enabled),
-                           (void *)&enabled, sizeof(enabled), 1);
+                              &enabled, sizeof(enabled));
     apic_enable_vapic(cpu->apic_state, vapic_paddr);
 
     s->state = VAPIC_ACTIVE;
@@ -535,7 +533,7 @@ static int patch_hypercalls(VAPICROMState *s)
     uint8_t *rom;
 
     rom = g_malloc(s->rom_size);
-    cpu_physical_memory_rw(rom_paddr, rom, s->rom_size, 0);
+    cpu_physical_memory_read(rom_paddr, rom, s->rom_size);
 
     for (pos = 0; pos < s->rom_size - sizeof(vmcall_pattern); pos++) {
         if (kvm_irqchip_in_kernel()) {
@@ -551,8 +549,7 @@ static int patch_hypercalls(VAPICROMState *s)
         }
         if (memcmp(rom + pos, pattern, 7) == 0 &&
             (rom[pos + 7] == alternates[0] || rom[pos + 7] == alternates[1])) {
-            cpu_physical_memory_rw(rom_paddr + pos + 5, (uint8_t *)patch,
+            cpu_physical_memory_write(rom_paddr + pos + 5, patch, 3);
-                                   3, 1);
             /*
              * Don't flush the tb here. Under ordinary conditions, the patched
              * calls are miles away from the current IP. Under malicious
@@ -760,8 +757,8 @@ static int vapic_post_load(void *opaque, int version_id)
             run_on_cpu(first_cpu, do_vapic_enable, s);
         } else {
             zero = g_malloc0(s->rom_state.vapic_size);
-            cpu_physical_memory_rw(s->vapic_paddr, zero,
+            cpu_physical_memory_write(s->vapic_paddr, zero,
-                                   s->rom_state.vapic_size, 1);
+                                      s->rom_state.vapic_size);
             g_free(zero);
         }
     }

hw/i386/pc.c

@@ -612,6 +612,21 @@ int e820_add_entry(uint64_t address, uint64_t length, uint32_t type)
     return e820_entries;
 }
 
+int e820_get_num_entries(void)
+{
+    return e820_entries;
+}
+
+bool e820_get_entry(int idx, uint32_t type, uint64_t *address, uint64_t *length)
+{
+    if (idx < e820_entries && e820_table[idx].type == cpu_to_le32(type)) {
+        *address = le64_to_cpu(e820_table[idx].address);
+        *length = le64_to_cpu(e820_table[idx].length);
+        return true;
+    }
+    return false;
+}
+
 /* Calculates the limit to CPU APIC ID values
  *
  * This function returns the limit for the APIC ID value, so that all
@@ -627,8 +642,8 @@ static unsigned int pc_apic_id_limit(unsigned int max_cpus)
 static FWCfgState *bochs_bios_init(void)
 {
     FWCfgState *fw_cfg;
-    uint8_t *smbios_table;
+    uint8_t *smbios_tables, *smbios_anchor;
-    size_t smbios_len;
+    size_t smbios_tables_len, smbios_anchor_len;
     uint64_t *numa_fw_cfg;
     int i, j;
     unsigned int apic_id_limit = pc_apic_id_limit(max_cpus);
@@ -655,10 +670,21 @@ static FWCfgState *bochs_bios_init(void)
                      acpi_tables, acpi_tables_len);
     fw_cfg_add_i32(fw_cfg, FW_CFG_IRQ0_OVERRIDE, kvm_allows_irq0_override());
 
-    smbios_table = smbios_get_table(&smbios_len);
+    smbios_tables = smbios_get_table_legacy(&smbios_tables_len);
-    if (smbios_table)
+    if (smbios_tables) {
         fw_cfg_add_bytes(fw_cfg, FW_CFG_SMBIOS_ENTRIES,
-                         smbios_table, smbios_len);
+                         smbios_tables, smbios_tables_len);
+    }
+
+    smbios_get_tables(&smbios_tables, &smbios_tables_len,
+                      &smbios_anchor, &smbios_anchor_len);
+    if (smbios_anchor) {
+        fw_cfg_add_file(fw_cfg, "etc/smbios/smbios-tables",
+                        smbios_tables, smbios_tables_len);
+        fw_cfg_add_file(fw_cfg, "etc/smbios/smbios-anchor",
+                        smbios_anchor, smbios_anchor_len);
+    }
+
     fw_cfg_add_bytes(fw_cfg, FW_CFG_E820_TABLE,
                      &e820_reserve, sizeof(e820_reserve));
     fw_cfg_add_file(fw_cfg, "etc/e820", e820_table,
@@ -1027,6 +1053,9 @@ void pc_cpus_init(const char *cpu_model, DeviceState *icc_bridge)
         sysbus_mmio_map_overlap(SYS_BUS_DEVICE(icc_bridge), 0,
                                 APIC_DEFAULT_ADDRESS, 0x1000);
     }
+
+    /* tell smbios about cpuid version and features */
+    smbios_set_cpuid(cpu->env.cpuid_version, cpu->env.features[FEAT_1_EDX]);
 }
 
 /* pci-info ROM file. Little endian format */

hw/i386/pc_piix.c

@@ -60,7 +60,8 @@ static const int ide_irq[MAX_IDE_BUS] = { 14, 15 };
 
 static bool has_pci_info;
 static bool has_acpi_build = true;
-static bool smbios_type1_defaults = true;
+static bool smbios_defaults = true;
+static bool smbios_legacy_mode;
 /* Make sure that guest addresses aligned at 1Gbyte boundaries get mapped to
  * host addresses aligned at 1Gbyte boundaries.  This way we can use 1GByte
  * pages in the host.
@@ -143,10 +144,10 @@ static void pc_init1(QEMUMachineInitArgs *args,
     guest_info->has_pci_info = has_pci_info;
     guest_info->isapc_ram_fw = !pci_enabled;
 
-    if (smbios_type1_defaults) {
+    if (smbios_defaults) {
         /* These values are guest ABI, do not change */
-        smbios_set_type1_defaults("QEMU", "Standard PC (i440FX + PIIX, 1996)",
+        smbios_set_defaults("QEMU", "Standard PC (i440FX + PIIX, 1996)",
-                                  args->machine->name);
+                            args->machine->name, smbios_legacy_mode);
     }
 
     /* allocate ram and load rom/bios */
@@ -262,9 +263,15 @@ static void pc_init_pci(QEMUMachineInitArgs *args)
     pc_init1(args, 1, 1);
 }
 
+static void pc_compat_2_0(QEMUMachineInitArgs *args)
+{
+    smbios_legacy_mode = true;
+}
+
 static void pc_compat_1_7(QEMUMachineInitArgs *args)
 {
-    smbios_type1_defaults = false;
+    pc_compat_2_0(args);
+    smbios_defaults = false;
     gigabyte_align = false;
     option_rom_has_mr = true;
     x86_cpu_compat_disable_kvm_features(FEAT_1_ECX, CPUID_EXT_X2APIC);
@@ -303,6 +310,12 @@ static void pc_compat_1_2(QEMUMachineInitArgs *args)
     x86_cpu_compat_disable_kvm_features(FEAT_KVM, KVM_FEATURE_PV_EOI);
 }
 
+static void pc_init_pci_2_0(QEMUMachineInitArgs *args)
+{
+    pc_compat_2_0(args);
+    pc_init_pci(args);
+}
+
 static void pc_init_pci_1_7(QEMUMachineInitArgs *args)
 {
     pc_compat_1_7(args);
@@ -345,7 +358,7 @@ static void pc_init_pci_no_kvmclock(QEMUMachineInitArgs *args)
 {
     has_pci_info = false;
     has_acpi_build = false;
-    smbios_type1_defaults = false;
+    smbios_defaults = false;
     x86_cpu_compat_disable_kvm_features(FEAT_KVM, KVM_FEATURE_PV_EOI);
     enable_compat_apic_id_mode();
     pc_init1(args, 1, 0);
@@ -355,7 +368,7 @@ static void pc_init_isa(QEMUMachineInitArgs *args)
 {
     has_pci_info = false;
     has_acpi_build = false;
-    smbios_type1_defaults = false;
+    smbios_defaults = false;
     if (!args->cpu_model) {
         args->cpu_model = "486";
     }
@@ -383,16 +396,24 @@ static void pc_xen_hvm_init(QEMUMachineInitArgs *args)
     .desc = "Standard PC (i440FX + PIIX, 1996)", \
     .hot_add_cpu = pc_hot_add_cpu
 
-#define PC_I440FX_2_0_MACHINE_OPTIONS                           \
+#define PC_I440FX_2_1_MACHINE_OPTIONS                           \
     PC_I440FX_MACHINE_OPTIONS,                                  \
     .default_machine_opts = "firmware=bios-256k.bin"
 
+static QEMUMachine pc_i440fx_machine_v2_1 = {
+    PC_I440FX_2_1_MACHINE_OPTIONS,
+    .name = "pc-i440fx-2.1",
+    .alias = "pc",
+    .init = pc_init_pci,
+    .is_default = 1,
+};
+
+#define PC_I440FX_2_0_MACHINE_OPTIONS PC_I440FX_2_1_MACHINE_OPTIONS
+
 static QEMUMachine pc_i440fx_machine_v2_0 = {
     PC_I440FX_2_0_MACHINE_OPTIONS,
     .name = "pc-i440fx-2.0",
-    .alias = "pc",
+    .init = pc_init_pci_2_0,
-    .init = pc_init_pci,
-    .is_default = 1,
 };
 
 #define PC_I440FX_1_7_MACHINE_OPTIONS PC_I440FX_MACHINE_OPTIONS
@@ -817,6 +838,7 @@ static QEMUMachine xenfv_machine = {
 
 static void pc_machine_init(void)
 {
+    qemu_register_machine(&pc_i440fx_machine_v2_1);
     qemu_register_machine(&pc_i440fx_machine_v2_0);
     qemu_register_machine(&pc_i440fx_machine_v1_7);
     qemu_register_machine(&pc_i440fx_machine_v1_6);

hw/i386/pc_q35.c

@@ -50,7 +50,8 @@
 
 static bool has_pci_info;
 static bool has_acpi_build = true;
-static bool smbios_type1_defaults = true;
+static bool smbios_defaults = true;
+static bool smbios_legacy_mode;
 /* Make sure that guest addresses aligned at 1Gbyte boundaries get mapped to
  * host addresses aligned at 1Gbyte boundaries.  This way we can use 1GByte
  * pages in the host.
@@ -130,10 +131,10 @@ static void pc_q35_init(QEMUMachineInitArgs *args)
     guest_info->isapc_ram_fw = false;
     guest_info->has_acpi_build = has_acpi_build;
 
-    if (smbios_type1_defaults) {
+    if (smbios_defaults) {
         /* These values are guest ABI, do not change */
-        smbios_set_type1_defaults("QEMU", "Standard PC (Q35 + ICH9, 2009)",
+        smbios_set_defaults("QEMU", "Standard PC (Q35 + ICH9, 2009)",
-                                  args->machine->name);
+                            args->machine->name, smbios_legacy_mode);
     }
 
     /* allocate ram and load rom/bios */
@@ -240,9 +241,15 @@ static void pc_q35_init(QEMUMachineInitArgs *args)
     }
 }
 
+static void pc_compat_2_0(QEMUMachineInitArgs *args)
+{
+    smbios_legacy_mode = true;
+}
+
 static void pc_compat_1_7(QEMUMachineInitArgs *args)
 {
-    smbios_type1_defaults = false;
+    pc_compat_2_0(args);
+    smbios_defaults = false;
     gigabyte_align = false;
     option_rom_has_mr = true;
     x86_cpu_compat_disable_kvm_features(FEAT_1_ECX, CPUID_EXT_X2APIC);
@@ -268,6 +275,12 @@ static void pc_compat_1_4(QEMUMachineInitArgs *args)
     x86_cpu_compat_set_features("Westmere", FEAT_1_ECX, 0, CPUID_EXT_PCLMULQDQ);
 }
 
+static void pc_q35_init_2_0(QEMUMachineInitArgs *args)
+{
+    pc_compat_2_0(args);
+    pc_q35_init(args);
+}
+
 static void pc_q35_init_1_7(QEMUMachineInitArgs *args)
 {
     pc_compat_1_7(args);
@@ -297,15 +310,23 @@ static void pc_q35_init_1_4(QEMUMachineInitArgs *args)
     .desc = "Standard PC (Q35 + ICH9, 2009)", \
     .hot_add_cpu = pc_hot_add_cpu
 
-#define PC_Q35_2_0_MACHINE_OPTIONS                      \
+#define PC_Q35_2_1_MACHINE_OPTIONS                      \
     PC_Q35_MACHINE_OPTIONS,                             \
     .default_machine_opts = "firmware=bios-256k.bin"
 
+static QEMUMachine pc_q35_machine_v2_1 = {
+    PC_Q35_2_1_MACHINE_OPTIONS,
+    .name = "pc-q35-2.1",
+    .alias = "q35",
+    .init = pc_q35_init,
+};
+
+#define PC_Q35_2_0_MACHINE_OPTIONS PC_Q35_2_1_MACHINE_OPTIONS
+
 static QEMUMachine pc_q35_machine_v2_0 = {
     PC_Q35_2_0_MACHINE_OPTIONS,
     .name = "pc-q35-2.0",
-    .alias = "q35",
+    .init = pc_q35_init_2_0,
-    .init = pc_q35_init,
 };
 
 #define PC_Q35_1_7_MACHINE_OPTIONS PC_Q35_MACHINE_OPTIONS
@@ -358,6 +379,7 @@ static QEMUMachine pc_q35_machine_v1_4 = {
 
 static void pc_q35_machine_init(void)
 {
+    qemu_register_machine(&pc_q35_machine_v2_1);
     qemu_register_machine(&pc_q35_machine_v2_0);
     qemu_register_machine(&pc_q35_machine_v1_7);
     qemu_register_machine(&pc_q35_machine_v1_6);

hw/i386/q35-acpi-dsdt.hex.generated

@@ -3,12 +3,12 @@ static unsigned char Q35AcpiDsdtAmlCode[] = {
 0x53,
 0x44,
 0x54,
-0xd7,
+0xd2,
 0x1c,
 0x0,
 0x0,
 0x1,
-0x3e,
+0x13,
 0x42,
 0x58,
 0x50,
@@ -31,8 +31,8 @@ static unsigned char Q35AcpiDsdtAmlCode[] = {
 0x4e,
 0x54,
 0x4c,
-0x23,
+0x15,
-0x8,
+0x11,
 0x13,
 0x20,
 0x10,
@@ -6959,7 +6959,7 @@ static unsigned char Q35AcpiDsdtAmlCode[] = {
 0x53,
 0x1,
 0x10,
-0x47,
+0x42,
 0x11,
 0x5f,
 0x53,
@@ -7192,7 +7192,7 @@ static unsigned char Q35AcpiDsdtAmlCode[] = {
 0x60,
 0x5b,
 0x82,
-0x2e,
+0x29,
 0x50,
 0x52,
 0x45,
@@ -7202,16 +7202,11 @@ static unsigned char Q35AcpiDsdtAmlCode[] = {
 0x48,
 0x49,
 0x44,
-0xd,
+0xc,
 0x41,
-0x43,
+0xd0,
-0x50,
+0xa,
-0x49,
+0x6,
-0x30,
-0x30,
-0x30,
-0x34,
-0x0,
 0x8,
 0x5f,
 0x43,

hw/i386/smbios.c

@@ -18,12 +18,13 @@
 #include "qemu/config-file.h"
 #include "qemu/error-report.h"
 #include "sysemu/sysemu.h"
+#include "sysemu/cpus.h"
+#include "hw/i386/pc.h"
 #include "hw/i386/smbios.h"
 #include "hw/loader.h"
 
-/*
+
- * Structures shared with the BIOS
+/* legacy structures and constants for <= 2.0 machines */
- */
 struct smbios_header {
     uint16_t length;
     uint8_t type;
@@ -46,14 +47,23 @@ struct smbios_table {
 
 static uint8_t *smbios_entries;
 static size_t smbios_entries_len;
+static bool smbios_legacy = true;
+/* end: legacy structures & constants for <= 2.0 machines */
+
+
+static uint8_t *smbios_tables;
+static size_t smbios_tables_len;
+static unsigned smbios_table_max;
+static unsigned smbios_table_cnt;
+static struct smbios_entry_point ep;
+
 static int smbios_type4_count = 0;
 static bool smbios_immutable;
+static bool smbios_have_defaults;
+static uint32_t smbios_cpuid_version, smbios_cpuid_features, smbios_smp_sockets;
 
-static struct {
+static DECLARE_BITMAP(have_binfile_bitmap, SMBIOS_MAX_TYPE+1);
-    bool seen;
+static DECLARE_BITMAP(have_fields_bitmap, SMBIOS_MAX_TYPE+1);
-    int headertype;
-    Location loc;
-} first_opt[2];
 
 static struct {
     const char *vendor, *version, *date;
@@ -66,6 +76,22 @@ static struct {
     /* uuid is in qemu_uuid[] */
 } type1;
 
+static struct {
+    const char *manufacturer, *product, *version, *serial, *asset, *location;
+} type2;
+
+static struct {
+    const char *manufacturer, *version, *serial, *asset, *sku;
+} type3;
+
+static struct {
+    const char *sock_pfx, *manufacturer, *version, *serial, *asset, *part;
+} type4;
+
+static struct {
+    const char *loc_pfx, *bank, *manufacturer, *serial, *asset, *part;
+} type17;
+
 static QemuOptsList qemu_smbios_opts = {
     .name = "smbios",
     .head = QTAILQ_HEAD_INITIALIZER(qemu_smbios_opts.head),
@@ -149,6 +175,134 @@ static const QemuOptDesc qemu_smbios_type1_opts[] = {
     { /* end of list */ }
 };
 
+static const QemuOptDesc qemu_smbios_type2_opts[] = {
+    {
+        .name = "type",
+        .type = QEMU_OPT_NUMBER,
+        .help = "SMBIOS element type",
+    },{
+        .name = "manufacturer",
+        .type = QEMU_OPT_STRING,
+        .help = "manufacturer name",
+    },{
+        .name = "product",
+        .type = QEMU_OPT_STRING,
+        .help = "product name",
+    },{
+        .name = "version",
+        .type = QEMU_OPT_STRING,
+        .help = "version number",
+    },{
+        .name = "serial",
+        .type = QEMU_OPT_STRING,
+        .help = "serial number",
+    },{
+        .name = "asset",
+        .type = QEMU_OPT_STRING,
+        .help = "asset tag number",
+    },{
+        .name = "location",
+        .type = QEMU_OPT_STRING,
+        .help = "location in chassis",
+    },
+    { /* end of list */ }
+};
+
+static const QemuOptDesc qemu_smbios_type3_opts[] = {
+    {
+        .name = "type",
+        .type = QEMU_OPT_NUMBER,
+        .help = "SMBIOS element type",
+    },{
+        .name = "manufacturer",
+        .type = QEMU_OPT_STRING,
+        .help = "manufacturer name",
+    },{
+        .name = "version",
+        .type = QEMU_OPT_STRING,
+        .help = "version number",
+    },{
+        .name = "serial",
+        .type = QEMU_OPT_STRING,
+        .help = "serial number",
+    },{
+        .name = "asset",
+        .type = QEMU_OPT_STRING,
+        .help = "asset tag number",
+    },{
+        .name = "sku",
+        .type = QEMU_OPT_STRING,
+        .help = "SKU number",
+    },
+    { /* end of list */ }
+};
+
+static const QemuOptDesc qemu_smbios_type4_opts[] = {
+    {
+        .name = "type",
+        .type = QEMU_OPT_NUMBER,
+        .help = "SMBIOS element type",
+    },{
+        .name = "sock_pfx",
+        .type = QEMU_OPT_STRING,
+        .help = "socket designation string prefix",
+    },{
+        .name = "manufacturer",
+        .type = QEMU_OPT_STRING,
+        .help = "manufacturer name",
+    },{
+        .name = "version",
+        .type = QEMU_OPT_STRING,
+        .help = "version number",
+    },{
+        .name = "serial",
+        .type = QEMU_OPT_STRING,
+        .help = "serial number",
+    },{
+        .name = "asset",
+        .type = QEMU_OPT_STRING,
+        .help = "asset tag number",
+    },{
+        .name = "part",
+        .type = QEMU_OPT_STRING,
+        .help = "part number",
+    },
+    { /* end of list */ }
+};
+
+static const QemuOptDesc qemu_smbios_type17_opts[] = {
+    {
+        .name = "type",
+        .type = QEMU_OPT_NUMBER,
+        .help = "SMBIOS element type",
+    },{
+        .name = "loc_pfx",
+        .type = QEMU_OPT_STRING,
+        .help = "device locator string prefix",
+    },{
+        .name = "bank",
+        .type = QEMU_OPT_STRING,
+        .help = "bank locator string",
+    },{
+        .name = "manufacturer",
+        .type = QEMU_OPT_STRING,
+        .help = "manufacturer name",
+    },{
+        .name = "serial",
+        .type = QEMU_OPT_STRING,
+        .help = "serial number",
+    },{
+        .name = "asset",
+        .type = QEMU_OPT_STRING,
+        .help = "asset tag number",
+    },{
+        .name = "part",
+        .type = QEMU_OPT_STRING,
+        .help = "part number",
+    },
+    { /* end of list */ }
+};
+
 static void smbios_register_config(void)
 {
     qemu_add_opts(&qemu_smbios_opts);
@@ -158,35 +312,17 @@ machine_init(smbios_register_config);
 
 static void smbios_validate_table(void)
 {
-    if (smbios_type4_count && smbios_type4_count != smp_cpus) {
+    uint32_t expect_t4_count = smbios_legacy ? smp_cpus : smbios_smp_sockets;
-        error_report("Number of SMBIOS Type 4 tables must match cpu count");
+
+    if (smbios_type4_count && smbios_type4_count != expect_t4_count) {
+        error_report("Expected %d SMBIOS Type 4 tables, got %d instead",
+                     expect_t4_count, smbios_type4_count);
         exit(1);
     }
 }
 
-/*
- * To avoid unresolvable overlaps in data, don't allow both
- * tables and fields for the same smbios type.
- */
-static void smbios_check_collision(int type, int entry)
-{
-    if (type < ARRAY_SIZE(first_opt)) {
-        if (first_opt[type].seen) {
-            if (first_opt[type].headertype != entry) {
-                error_report("Can't mix file= and type= for same type");
-                loc_push_restore(&first_opt[type].loc);
-                error_report("This is the conflicting setting");
-                loc_pop(&first_opt[type].loc);
-                exit(1);
-            }
-        } else {
-            first_opt[type].seen = true;
-            first_opt[type].headertype = entry;
-            loc_save(&first_opt[type].loc);
-        }
-    }
-}
 
+/* legacy setup functions for <= 2.0 machines */
 static void smbios_add_field(int type, int offset, const void *data, size_t len)
 {
     struct smbios_field *field;
@@ -256,22 +392,13 @@ static void smbios_build_type_1_fields(void)
     }
 }
 
-void smbios_set_type1_defaults(const char *manufacturer,
+uint8_t *smbios_get_table_legacy(size_t *length)
-                               const char *product, const char *version)
 {
-    if (!type1.manufacturer) {
+    if (!smbios_legacy) {
-        type1.manufacturer = manufacturer;
+        *length = 0;
+        return NULL;
     }
-    if (!type1.product) {
-        type1.product = product;
-    }
-    if (!type1.version) {
-        type1.version = version;
-    }
-}
 
-uint8_t *smbios_get_table(size_t *length)
-{
     if (!smbios_immutable) {
         smbios_build_type_0_fields();
         smbios_build_type_1_fields();
@@ -281,6 +408,458 @@ uint8_t *smbios_get_table(size_t *length)
     *length = smbios_entries_len;
     return smbios_entries;
 }
+/* end: legacy setup functions for <= 2.0 machines */
+
+
+static bool smbios_skip_table(uint8_t type, bool required_table)
+{
+    if (test_bit(type, have_binfile_bitmap)) {
+        return true; /* user provided their own binary blob(s) */
+    }
+    if (test_bit(type, have_fields_bitmap)) {
+        return false; /* user provided fields via command line */
+    }
+    if (smbios_have_defaults && required_table) {
+        return false; /* we're building tables, and this one's required */
+    }
+    return true;
+}
+
+#define SMBIOS_BUILD_TABLE_PRE(tbl_type, tbl_handle, tbl_required)        \
+    struct smbios_type_##tbl_type *t;                                     \
+    size_t t_off; /* table offset into smbios_tables */                   \
+    int str_index = 0;                                                    \
+    do {                                                                  \
+        /* should we skip building this table ? */                        \
+        if (smbios_skip_table(tbl_type, tbl_required)) {                  \
+            return;                                                       \
+        }                                                                 \
+                                                                          \
+        /* use offset of table t within smbios_tables */                  \
+        /* (pointer must be updated after each realloc) */                \
+        t_off = smbios_tables_len;                                        \
+        smbios_tables_len += sizeof(*t);                                  \
+        smbios_tables = g_realloc(smbios_tables, smbios_tables_len);      \
+        t = (struct smbios_type_##tbl_type *)(smbios_tables + t_off);     \
+                                                                          \
+        t->header.type = tbl_type;                                        \
+        t->header.length = sizeof(*t);                                    \
+        t->header.handle = tbl_handle;                                    \
+    } while (0)
+
+#define SMBIOS_TABLE_SET_STR(tbl_type, field, value)                      \
+    do {                                                                  \
+        int len = (value != NULL) ? strlen(value) + 1 : 0;                \
+        if (len > 1) {                                                    \
+            smbios_tables = g_realloc(smbios_tables,                      \
+                                      smbios_tables_len + len);           \
+            memcpy(smbios_tables + smbios_tables_len, value, len);        \
+            smbios_tables_len += len;                                     \
+            /* update pointer post-realloc */                             \
+            t = (struct smbios_type_##tbl_type *)(smbios_tables + t_off); \
+            t->field = ++str_index;                                       \
+        } else {                                                          \
+            t->field = 0;                                                 \
+        }                                                                 \
+    } while (0)
+
+#define SMBIOS_BUILD_TABLE_POST                                           \
+    do {                                                                  \
+        size_t term_cnt, t_size;                                          \
+                                                                          \
+        /* add '\0' terminator (add two if no strings defined) */         \
+        term_cnt = (str_index == 0) ? 2 : 1;                              \
+        smbios_tables = g_realloc(smbios_tables,                          \
+                                  smbios_tables_len + term_cnt);          \
+        memset(smbios_tables + smbios_tables_len, 0, term_cnt);           \
+        smbios_tables_len += term_cnt;                                    \
+                                                                          \
+        /* update smbios max. element size */                             \
+        t_size = smbios_tables_len - t_off;                               \
+        if (t_size > smbios_table_max) {                                  \
+            smbios_table_max = t_size;                                    \
+        }                                                                 \
+                                                                          \
+        /* update smbios element count */                                 \
+        smbios_table_cnt++;                                               \
+    } while (0)
+
+static void smbios_build_type_0_table(void)
+{
+    SMBIOS_BUILD_TABLE_PRE(0, 0x000, false); /* optional, leave up to BIOS */
+
+    SMBIOS_TABLE_SET_STR(0, vendor_str, type0.vendor);
+    SMBIOS_TABLE_SET_STR(0, bios_version_str, type0.version);
+
+    t->bios_starting_address_segment = 0xE800; /* hardcoded in SeaBIOS */
+
+    SMBIOS_TABLE_SET_STR(0, bios_release_date_str, type0.date);
+
+    t->bios_rom_size = 0; /* hardcoded in SeaBIOS with FIXME comment */
+
+    /* BIOS characteristics not supported */
+    memset(t->bios_characteristics, 0, 8);
+    t->bios_characteristics[0] = 0x08;
+
+    /* Enable targeted content distribution (needed for SVVP, per SeaBIOS) */
+    t->bios_characteristics_extension_bytes[0] = 0;
+    t->bios_characteristics_extension_bytes[1] = 4;
+
+    if (type0.have_major_minor) {
+        t->system_bios_major_release = type0.major;
+        t->system_bios_minor_release = type0.minor;
+    } else {
+        t->system_bios_major_release = 0;
+        t->system_bios_minor_release = 0;
+    }
+
+    /* hardcoded in SeaBIOS */
+    t->embedded_controller_major_release = 0xFF;
+    t->embedded_controller_minor_release = 0xFF;
+
+    SMBIOS_BUILD_TABLE_POST;
+}
+
+static void smbios_build_type_1_table(void)
+{
+    SMBIOS_BUILD_TABLE_PRE(1, 0x100, true); /* required */
+
+    SMBIOS_TABLE_SET_STR(1, manufacturer_str, type1.manufacturer);
+    SMBIOS_TABLE_SET_STR(1, product_name_str, type1.product);
+    SMBIOS_TABLE_SET_STR(1, version_str, type1.version);
+    SMBIOS_TABLE_SET_STR(1, serial_number_str, type1.serial);
+    if (qemu_uuid_set) {
+        memcpy(t->uuid, qemu_uuid, 16);
+    } else {
+        memset(t->uuid, 0, 16);
+    }
+    t->wake_up_type = 0x06; /* power switch */
+    SMBIOS_TABLE_SET_STR(1, sku_number_str, type1.sku);
+    SMBIOS_TABLE_SET_STR(1, family_str, type1.family);
+
+    SMBIOS_BUILD_TABLE_POST;
+}
+
+static void smbios_build_type_2_table(void)
+{
+    SMBIOS_BUILD_TABLE_PRE(2, 0x200, false); /* optional */
+
+    SMBIOS_TABLE_SET_STR(2, manufacturer_str, type2.manufacturer);
+    SMBIOS_TABLE_SET_STR(2, product_str, type2.product);
+    SMBIOS_TABLE_SET_STR(2, version_str, type2.version);
+    SMBIOS_TABLE_SET_STR(2, serial_number_str, type2.serial);
+    SMBIOS_TABLE_SET_STR(2, asset_tag_number_str, type2.asset);
+    t->feature_flags = 0x01; /* Motherboard */
+    SMBIOS_TABLE_SET_STR(2, location_str, type2.location);
+    t->chassis_handle = 0x300; /* Type 3 (System enclosure) */
+    t->board_type = 0x0A; /* Motherboard */
+    t->contained_element_count = 0;
+
+    SMBIOS_BUILD_TABLE_POST;
+}
+
+static void smbios_build_type_3_table(void)
+{
+    SMBIOS_BUILD_TABLE_PRE(3, 0x300, true); /* required */
+
+    SMBIOS_TABLE_SET_STR(3, manufacturer_str, type3.manufacturer);
+    t->type = 0x01; /* Other */
+    SMBIOS_TABLE_SET_STR(3, version_str, type3.version);
+    SMBIOS_TABLE_SET_STR(3, serial_number_str, type3.serial);
+    SMBIOS_TABLE_SET_STR(3, asset_tag_number_str, type3.asset);
+    t->boot_up_state = 0x03; /* Safe */
+    t->power_supply_state = 0x03; /* Safe */
+    t->thermal_state = 0x03; /* Safe */
+    t->security_status = 0x02; /* Unknown */
+    t->oem_defined = 0;
+    t->height = 0;
+    t->number_of_power_cords = 0;
+    t->contained_element_count = 0;
+    SMBIOS_TABLE_SET_STR(3, sku_number_str, type3.sku);
+
+    SMBIOS_BUILD_TABLE_POST;
+}
+
+static void smbios_build_type_4_table(unsigned instance)
+{
+    char sock_str[128];
+
+    SMBIOS_BUILD_TABLE_PRE(4, 0x400 + instance, true); /* required */
+
+    snprintf(sock_str, sizeof(sock_str), "%s%2x", type4.sock_pfx, instance);
+    SMBIOS_TABLE_SET_STR(4, socket_designation_str, sock_str);
+    t->processor_type = 0x03; /* CPU */
+    SMBIOS_TABLE_SET_STR(4, processor_manufacturer_str, type4.manufacturer);
+    t->processor_id[0] = smbios_cpuid_version;
+    t->processor_id[1] = smbios_cpuid_features;
+    SMBIOS_TABLE_SET_STR(4, processor_version_str, type4.version);
+    t->voltage = 0;
+    t->external_clock = 0; /* Unknown */
+    t->max_speed = 0; /* Unknown */
+    t->current_speed = 0; /* Unknown */
+    t->status = 0x41; /* Socket populated, CPU enabled */
+    t->processor_upgrade = 0x01; /* Other */
+    t->l1_cache_handle = 0xFFFF; /* N/A */
+    t->l2_cache_handle = 0xFFFF; /* N/A */
+    t->l3_cache_handle = 0xFFFF; /* N/A */
+    SMBIOS_TABLE_SET_STR(4, serial_number_str, type4.serial);
+    SMBIOS_TABLE_SET_STR(4, asset_tag_number_str, type4.asset);
+    SMBIOS_TABLE_SET_STR(4, part_number_str, type4.part);
+    t->core_count = t->core_enabled = smp_cores;
+    t->thread_count = smp_threads;
+    t->processor_characteristics = 0x02; /* Unknown */
+    t->processor_family = t->processor_family2 = 0x01; /* Other */
+
+    SMBIOS_BUILD_TABLE_POST;
+    smbios_type4_count++;
+}
+
+#define ONE_KB ((ram_addr_t)1 << 10)
+#define ONE_MB ((ram_addr_t)1 << 20)
+#define ONE_GB ((ram_addr_t)1 << 30)
+
+#define MAX_T16_STD_SZ 0x80000000 /* 2T in Kilobytes */
+
+static void smbios_build_type_16_table(unsigned dimm_cnt)
+{
+    ram_addr_t size_kb;
+
+    SMBIOS_BUILD_TABLE_PRE(16, 0x1000, true); /* required */
+
+    t->location = 0x01; /* Other */
+    t->use = 0x03; /* System memory */
+    t->error_correction = 0x06; /* Multi-bit ECC (for Microsoft, per SeaBIOS) */
+    size_kb = QEMU_ALIGN_UP(ram_size, ONE_KB) / ONE_KB;
+    if (size_kb < MAX_T16_STD_SZ) {
+        t->maximum_capacity = size_kb;
+        t->extended_maximum_capacity = 0;
+    } else {
+        t->maximum_capacity = MAX_T16_STD_SZ;
+        t->extended_maximum_capacity = ram_size;
+    }
+    t->memory_error_information_handle = 0xFFFE; /* Not provided */
+    t->number_of_memory_devices = dimm_cnt;
+
+    SMBIOS_BUILD_TABLE_POST;
+}
+
+#define MAX_T17_STD_SZ 0x7FFF /* (32G - 1M), in Megabytes */
+#define MAX_T17_EXT_SZ 0x80000000 /* 2P, in Megabytes */
+
+static void smbios_build_type_17_table(unsigned instance, ram_addr_t size)
+{
+    char loc_str[128];
+    ram_addr_t size_mb;
+
+    SMBIOS_BUILD_TABLE_PRE(17, 0x1100 + instance, true); /* required */
+
+    t->physical_memory_array_handle = 0x1000; /* Type 16 (Phys. Mem. Array) */
+    t->memory_error_information_handle = 0xFFFE; /* Not provided */
+    t->total_width = 0xFFFF; /* Unknown */
+    t->data_width = 0xFFFF; /* Unknown */
+    size_mb = QEMU_ALIGN_UP(size, ONE_MB) / ONE_MB;
+    if (size_mb < MAX_T17_STD_SZ) {
+        t->size = size_mb;
+        t->extended_size = 0;
+    } else {
+        assert(size_mb < MAX_T17_EXT_SZ);
+        t->size = MAX_T17_STD_SZ;
+        t->extended_size = size_mb;
+    }
+    t->form_factor = 0x09; /* DIMM */
+    t->device_set = 0; /* Not in a set */
+    snprintf(loc_str, sizeof(loc_str), "%s %d", type17.loc_pfx, instance);
+    SMBIOS_TABLE_SET_STR(17, device_locator_str, loc_str);
+    SMBIOS_TABLE_SET_STR(17, bank_locator_str, type17.bank);
+    t->memory_type = 0x07; /* RAM */
+    t->type_detail = 0x02; /* Other */
+    t->speed = 0; /* Unknown */
+    SMBIOS_TABLE_SET_STR(17, manufacturer_str, type17.manufacturer);
+    SMBIOS_TABLE_SET_STR(17, serial_number_str, type17.serial);
+    SMBIOS_TABLE_SET_STR(17, asset_tag_number_str, type17.asset);
+    SMBIOS_TABLE_SET_STR(17, part_number_str, type17.part);
+    t->attributes = 0; /* Unknown */
+    t->configured_clock_speed = 0; /* Unknown */
+    t->minimum_voltage = 0; /* Unknown */
+    t->maximum_voltage = 0; /* Unknown */
+    t->configured_voltage = 0; /* Unknown */
+
+    SMBIOS_BUILD_TABLE_POST;
+}
+
+static void smbios_build_type_19_table(unsigned instance,
+                                       ram_addr_t start, ram_addr_t size)
+{
+    ram_addr_t end, start_kb, end_kb;
+
+    SMBIOS_BUILD_TABLE_PRE(19, 0x1300 + instance, true); /* required */
+
+    end = start + size - 1;
+    assert(end > start);
+    start_kb = start / ONE_KB;
+    end_kb = end / ONE_KB;
+    if (start_kb < UINT32_MAX && end_kb < UINT32_MAX) {
+        t->starting_address = start_kb;
+        t->ending_address = end_kb;
+        t->extended_starting_address = t->extended_ending_address = 0;
+    } else {
+        t->starting_address = t->ending_address = UINT32_MAX;
+        t->extended_starting_address = start;
+        t->extended_ending_address = end;
+    }
+    t->memory_array_handle = 0x1000; /* Type 16 (Phys. Mem. Array) */
+    t->partition_width = 1; /* One device per row */
+
+    SMBIOS_BUILD_TABLE_POST;
+}
+
+static void smbios_build_type_32_table(void)
+{
+    SMBIOS_BUILD_TABLE_PRE(32, 0x2000, true); /* required */
+
+    memset(t->reserved, 0, 6);
+    t->boot_status = 0; /* No errors detected */
+
+    SMBIOS_BUILD_TABLE_POST;
+}
+
+static void smbios_build_type_127_table(void)
+{
+    SMBIOS_BUILD_TABLE_PRE(127, 0x7F00, true); /* required */
+    SMBIOS_BUILD_TABLE_POST;
+}
+
+void smbios_set_cpuid(uint32_t version, uint32_t features)
+{
+    smbios_cpuid_version = version;
+    smbios_cpuid_features = features;
+}
+
+#define SMBIOS_SET_DEFAULT(field, value)                                  \
+    if (!field) {                                                         \
+        field = value;                                                    \
+    }
+
+#define G_FREE_UNLESS_NULL(ptr)                                           \
+    if (ptr != NULL) {                                                    \
+        g_free(ptr);                                                      \
+    }
+
+void smbios_set_defaults(const char *manufacturer, const char *product,
+                         const char *version, bool legacy_mode)
+{
+    smbios_have_defaults = true;
+    smbios_legacy = legacy_mode;
+
+    /* drop unwanted version of command-line file blob(s) */
+    if (smbios_legacy) {
+        G_FREE_UNLESS_NULL(smbios_tables);
+        /* in legacy mode, also complain if fields were given for types > 1 */
+        if (find_next_bit(have_fields_bitmap,
+                          SMBIOS_MAX_TYPE+1, 2) < SMBIOS_MAX_TYPE+1) {
+            error_report("can't process fields for smbios "
+                         "types > 1 on machine versions < 2.1!");
+            exit(1);
+        }
+    } else {
+        G_FREE_UNLESS_NULL(smbios_entries);
+    }
+
+    SMBIOS_SET_DEFAULT(type1.manufacturer, manufacturer);
+    SMBIOS_SET_DEFAULT(type1.product, product);
+    SMBIOS_SET_DEFAULT(type1.version, version);
+    SMBIOS_SET_DEFAULT(type2.manufacturer, manufacturer);
+    SMBIOS_SET_DEFAULT(type2.product, product);
+    SMBIOS_SET_DEFAULT(type2.version, version);
+    SMBIOS_SET_DEFAULT(type3.manufacturer, manufacturer);
+    SMBIOS_SET_DEFAULT(type3.version, version);
+    SMBIOS_SET_DEFAULT(type4.sock_pfx, "CPU");
+    SMBIOS_SET_DEFAULT(type4.manufacturer, manufacturer);
+    SMBIOS_SET_DEFAULT(type4.version, version);
+    SMBIOS_SET_DEFAULT(type17.loc_pfx, "DIMM");
+    SMBIOS_SET_DEFAULT(type17.manufacturer, manufacturer);
+}
+
+static void smbios_entry_point_setup(void)
+{
+    memcpy(ep.anchor_string, "_SM_", 4);
+    memcpy(ep.intermediate_anchor_string, "_DMI_", 5);
+    ep.length = sizeof(struct smbios_entry_point);
+    ep.entry_point_revision = 0; /* formatted_area reserved, per spec v2.1+ */
+    memset(ep.formatted_area, 0, 5);
+
+    /* compliant with smbios spec v2.8 */
+    ep.smbios_major_version = 2;
+    ep.smbios_minor_version = 8;
+    ep.smbios_bcd_revision = 0x28;
+
+    /* set during table construction, but BIOS may override: */
+    ep.structure_table_length = smbios_tables_len;
+    ep.max_structure_size = smbios_table_max;
+    ep.number_of_structures = smbios_table_cnt;
+
+    /* BIOS must recalculate: */
+    ep.checksum = 0;
+    ep.intermediate_checksum = 0;
+    ep.structure_table_address = 0; /* where BIOS has copied smbios_tables */
+}
+
+void smbios_get_tables(uint8_t **tables, size_t *tables_len,
+                       uint8_t **anchor, size_t *anchor_len)
+{
+    unsigned i, dimm_cnt, instance;
+
+    if (smbios_legacy) {
+        *tables = *anchor = NULL;
+        *tables_len = *anchor_len = 0;
+        return;
+    }
+
+    if (!smbios_immutable) {
+        smbios_build_type_0_table();
+        smbios_build_type_1_table();
+        smbios_build_type_2_table();
+        smbios_build_type_3_table();
+
+        smbios_smp_sockets = smp_cpus / (smp_cores * smp_threads);
+        assert(smbios_smp_sockets >= 1);
+
+        for (i = 0; i < smbios_smp_sockets; i++) {
+            smbios_build_type_4_table(i);
+        }
+
+#define MAX_DIMM_SZ (16ll * ONE_GB)
+#define GET_DIMM_SZ ((i < dimm_cnt - 1) ? MAX_DIMM_SZ : ram_size % MAX_DIMM_SZ)
+
+        dimm_cnt = QEMU_ALIGN_UP(ram_size, MAX_DIMM_SZ) / MAX_DIMM_SZ;
+
+        smbios_build_type_16_table(dimm_cnt);
+
+        for (i = 0; i < dimm_cnt; i++) {
+            smbios_build_type_17_table(i, GET_DIMM_SZ);
+        }
+
+        for (i = 0, instance = 0; i < e820_get_num_entries(); i++) {
+            uint64_t address, length;
+            if (e820_get_entry(i, E820_RAM, &address, &length)) {
+                smbios_build_type_19_table(instance++, address, length);
+            }
+        }
+
+        smbios_build_type_32_table();
+        smbios_build_type_127_table();
+
+        smbios_validate_table();
+        smbios_entry_point_setup();
+        smbios_immutable = true;
+    }
+
+    /* return tables blob and entry point (anchor), and their sizes */
+    *tables = smbios_tables;
+    *tables_len = smbios_tables_len;
+    *anchor = (uint8_t *)&ep;
+    *anchor_len = sizeof(struct smbios_entry_point);
+}
 
 static void save_opt(const char **dest, QemuOpts *opts, const char *name)
 {
@@ -297,11 +876,12 @@ void smbios_entry_add(QemuOpts *opts)
     const char *val;
 
     assert(!smbios_immutable);
+
     val = qemu_opt_get(opts, "file");
     if (val) {
         struct smbios_structure_header *header;
-        struct smbios_table *table;
         int size;
+        struct smbios_table *table; /* legacy mode only */
 
         qemu_opts_validate(opts, qemu_smbios_file_opts, &local_err);
         if (local_err) {
@@ -315,31 +895,60 @@ void smbios_entry_add(QemuOpts *opts)
             exit(1);
         }
 
-        if (!smbios_entries) {
+        /*
-            smbios_entries_len = sizeof(uint16_t);
+         * NOTE: standard double '\0' terminator expected, per smbios spec.
-            smbios_entries = g_malloc0(smbios_entries_len);
+         * (except in legacy mode, where the second '\0' is implicit and
-        }
+         *  will be inserted by the BIOS).
+         */
+        smbios_tables = g_realloc(smbios_tables, smbios_tables_len + size);
+        header = (struct smbios_structure_header *)(smbios_tables +
+                                                    smbios_tables_len);
 
-        smbios_entries = g_realloc(smbios_entries, smbios_entries_len +
+        if (load_image(val, (uint8_t *)header) != size) {
-                                                      sizeof(*table) + size);
-        table = (struct smbios_table *)(smbios_entries + smbios_entries_len);
-        table->header.type = SMBIOS_TABLE_ENTRY;
-        table->header.length = cpu_to_le16(sizeof(*table) + size);
-
-        if (load_image(val, table->data) != size) {
             error_report("Failed to load SMBIOS file %s", val);
             exit(1);
         }
 
-        header = (struct smbios_structure_header *)(table->data);
+        if (test_bit(header->type, have_fields_bitmap)) {
-        smbios_check_collision(header->type, SMBIOS_TABLE_ENTRY);
+            error_report("can't load type %d struct, fields already specified!",
+                         header->type);
+            exit(1);
+        }
+        set_bit(header->type, have_binfile_bitmap);
+
         if (header->type == 4) {
             smbios_type4_count++;
         }
 
+        smbios_tables_len += size;
+        if (size > smbios_table_max) {
+            smbios_table_max = size;
+        }
+        smbios_table_cnt++;
+
+        /* add a copy of the newly loaded blob to legacy smbios_entries */
+        /* NOTE: This code runs before smbios_set_defaults(), so we don't
+         *       yet know which mode (legacy vs. aggregate-table) will be
+         *       required. We therefore add the binary blob to both legacy
+         *       (smbios_entries) and aggregate (smbios_tables) tables, and
+         *       delete the one we don't need from smbios_set_defaults(),
+         *       once we know which machine version has been requested.
+         */
+        if (!smbios_entries) {
+            smbios_entries_len = sizeof(uint16_t);
+            smbios_entries = g_malloc0(smbios_entries_len);
+        }
+        smbios_entries = g_realloc(smbios_entries, smbios_entries_len +
+                                                   size + sizeof(*table));
+        table = (struct smbios_table *)(smbios_entries + smbios_entries_len);
+        table->header.type = SMBIOS_TABLE_ENTRY;
+        table->header.length = cpu_to_le16(sizeof(*table) + size);
+        memcpy(table->data, header, size);
         smbios_entries_len += sizeof(*table) + size;
         (*(uint16_t *)smbios_entries) =
                 cpu_to_le16(le16_to_cpu(*(uint16_t *)smbios_entries) + 1);
+        /* end: add a copy of the newly loaded blob to legacy smbios_entries */
+
         return;
     }
 
@@ -347,7 +956,16 @@ void smbios_entry_add(QemuOpts *opts)
     if (val) {
         unsigned long type = strtoul(val, NULL, 0);
 
-        smbios_check_collision(type, SMBIOS_FIELD_ENTRY);
+        if (type > SMBIOS_MAX_TYPE) {
+            error_report("out of range!");
+            exit(1);
+        }
+
+        if (test_bit(type, have_binfile_bitmap)) {
+            error_report("can't add fields, binary file already loaded!");
+            exit(1);
+        }
+        set_bit(type, have_fields_bitmap);
 
         switch (type) {
         case 0:
@@ -391,6 +1009,57 @@ void smbios_entry_add(QemuOpts *opts)
                 qemu_uuid_set = true;
             }
             return;
+        case 2:
+            qemu_opts_validate(opts, qemu_smbios_type2_opts, &local_err);
+            if (local_err) {
+                error_report("%s", error_get_pretty(local_err));
+                exit(1);
+            }
+            save_opt(&type2.manufacturer, opts, "manufacturer");
+            save_opt(&type2.product, opts, "product");
+            save_opt(&type2.version, opts, "version");
+            save_opt(&type2.serial, opts, "serial");
+            save_opt(&type2.asset, opts, "asset");
+            save_opt(&type2.location, opts, "location");
+            return;
+        case 3:
+            qemu_opts_validate(opts, qemu_smbios_type3_opts, &local_err);
+            if (local_err) {
+                error_report("%s", error_get_pretty(local_err));
+                exit(1);
+            }
+            save_opt(&type3.manufacturer, opts, "manufacturer");
+            save_opt(&type3.version, opts, "version");
+            save_opt(&type3.serial, opts, "serial");
+            save_opt(&type3.asset, opts, "asset");
+            save_opt(&type3.sku, opts, "sku");
+            return;
+        case 4:
+            qemu_opts_validate(opts, qemu_smbios_type4_opts, &local_err);
+            if (local_err) {
+                error_report("%s", error_get_pretty(local_err));
+                exit(1);
+            }
+            save_opt(&type4.sock_pfx, opts, "sock_pfx");
+            save_opt(&type4.manufacturer, opts, "manufacturer");
+            save_opt(&type4.version, opts, "version");
+            save_opt(&type4.serial, opts, "serial");
+            save_opt(&type4.asset, opts, "asset");
+            save_opt(&type4.part, opts, "part");
+            return;
+        case 17:
+            qemu_opts_validate(opts, qemu_smbios_type17_opts, &local_err);
+            if (local_err) {
+                error_report("%s", error_get_pretty(local_err));
+                exit(1);
+            }
+            save_opt(&type17.loc_pfx, opts, "loc_pfx");
+            save_opt(&type17.bank, opts, "bank");
+            save_opt(&type17.manufacturer, opts, "manufacturer");
+            save_opt(&type17.serial, opts, "serial");
+            save_opt(&type17.asset, opts, "asset");
+            save_opt(&type17.part, opts, "part");
+            return;
         default:
             error_report("Don't know how to build fields for SMBIOS type %ld",
                          type);

hw/ide/ahci.c

@@ -438,9 +438,9 @@ static void check_cmd(AHCIState *s, int port)
 
     if ((pr->cmd & PORT_CMD_START) && pr->cmd_issue) {
         for (slot = 0; (slot < 32) && pr->cmd_issue; slot++) {
-            if ((pr->cmd_issue & (1 << slot)) &&
+            if ((pr->cmd_issue & (1U << slot)) &&
                 !handle_cmd(s, port, slot)) {
-                pr->cmd_issue &= ~(1 << slot);
+                pr->cmd_issue &= ~(1U << slot);
             }
         }
     }

hw/ide/core.c

@@ -1602,7 +1602,7 @@ static bool cmd_smart(IDEState *s, uint8_t cmd)
         case 2: /* extended self test */
             s->smart_selftest_count++;
             if (s->smart_selftest_count > 21) {
-                s->smart_selftest_count = 0;
+                s->smart_selftest_count = 1;
             }
             n = 2 + (s->smart_selftest_count - 1) * 24;
             s->smart_selftest_data[n] = s->sector;

hw/intc/allwinner-a10-pic.c

@@ -23,11 +23,20 @@
 static void aw_a10_pic_update(AwA10PICState *s)
 {
     uint8_t i;
-    int irq = 0, fiq = 0;
+    int irq = 0, fiq = 0, pending;
+
+    s->vector = 0;
 
     for (i = 0; i < AW_A10_PIC_REG_NUM; i++) {
         irq |= s->irq_pending[i] & ~s->mask[i];
         fiq |= s->select[i] & s->irq_pending[i] & ~s->mask[i];
+
+        if (!s->vector) {
+            pending = ffs(s->irq_pending[i] & ~s->mask[i]);
+            if (pending) {
+                s->vector = (i * 32 + pending - 1) * 4;
+            }
+        }
     }
 
     qemu_set_irq(s->parent_irq, !!irq);
@@ -40,6 +49,8 @@ static void aw_a10_pic_set_irq(void *opaque, int irq, int level)
 
     if (level) {
         set_bit(irq % 32, (void *)&s->irq_pending[irq / 32]);
+    } else {
+        clear_bit(irq % 32, (void *)&s->irq_pending[irq / 32]);
     }
     aw_a10_pic_update(s);
 }
@@ -84,9 +95,6 @@ static void aw_a10_pic_write(void *opaque, hwaddr offset, uint64_t value,
     uint8_t index = (offset & 0xc) / 4;
 
     switch (offset) {
-    case AW_A10_PIC_VECTOR:
-        s->vector = value & ~0x3;
-        break;
     case AW_A10_PIC_BASE_ADDR:
         s->base_addr = value & ~0x3;
     case AW_A10_PIC_PROTECT:
@@ -96,7 +104,11 @@ static void aw_a10_pic_write(void *opaque, hwaddr offset, uint64_t value,
         s->nmi = value;
         break;
     case AW_A10_PIC_IRQ_PENDING ... AW_A10_PIC_IRQ_PENDING + 8:
-        s->irq_pending[index] &= ~value;
+        /*
+         * The register is read-only; nevertheless, Linux (including
+         * the version originally shipped by Allwinner) pretends to
+         * write to the register. Just ignore it.
+         */
         break;
     case AW_A10_PIC_FIQ_PENDING ... AW_A10_PIC_FIQ_PENDING + 8:
         s->fiq_pending[index] &= ~value;

hw/intc/apic.c

@@ -98,8 +98,8 @@ static void apic_sync_vapic(APICCommonState *s, int sync_type)
         return;
     }
     if (sync_type & SYNC_FROM_VAPIC) {
-        cpu_physical_memory_rw(s->vapic_paddr, (void *)&vapic_state,
+        cpu_physical_memory_read(s->vapic_paddr, &vapic_state,
-                               sizeof(vapic_state), 0);
+                                 sizeof(vapic_state));
         s->tpr = vapic_state.tpr;
     }
     if (sync_type & (SYNC_TO_VAPIC | SYNC_ISR_IRR_TO_VAPIC)) {

hw/intc/apic_common.c

@@ -117,7 +117,12 @@ void apic_report_irq_delivered(int delivered)
 
 void apic_reset_irq_delivered(void)
 {
-    trace_apic_reset_irq_delivered(apic_irq_delivered);
+    /* Copy this into a local variable to encourage gcc to emit a plain
+     * register for a sys/sdt.h marker.  For details on this workaround, see:
+     * https://sourceware.org/bugzilla/show_bug.cgi?id=13296
+     */
+    volatile int a_i_d = apic_irq_delivered;
+    trace_apic_reset_irq_delivered(a_i_d);
 
     apic_irq_delivered = 0;
 }

hw/intc/armv7m_nvic.c

@@ -173,7 +173,7 @@ static uint32_t nvic_readl(nvic_state *s, uint32_t offset)
         return 10000;
     case 0xd00: /* CPUID Base.  */
         cpu = ARM_CPU(current_cpu);
-        return cpu->env.cp15.c0_cpuid;
+        return cpu->midr;
     case 0xd04: /* Interrupt Control State.  */
         /* VECTACTIVE */
         val = s->gic.running_irq[0];

hw/intc/openpic_kvm.c

@@ -118,6 +118,11 @@ static void kvm_openpic_region_add(MemoryListener *listener,
         abort();
     }
 
+    /* Ignore events on regions that are not us */
+    if (section->mr != &opp->mem) {
+        return;
+    }
+
     reg_base = section->offset_within_address_space;
 
     attr.group = KVM_DEV_MPIC_GRP_MISC;
@@ -140,6 +145,11 @@ static void kvm_openpic_region_del(MemoryListener *listener,
     uint64_t reg_base = 0;
     int ret;
 
+    /* Ignore events on regions that are not us */
+    if (section->mr != &opp->mem) {
+        return;
+    }
+
     attr.group = KVM_DEV_MPIC_GRP_MISC;
     attr.attr = KVM_DEV_MPIC_BASE_ADDR;
     attr.addr = (uint64_t)(unsigned long)&reg_base;
@@ -224,13 +234,9 @@ static void kvm_openpic_realize(DeviceState *dev, Error **errp)
 int kvm_openpic_connect_vcpu(DeviceState *d, CPUState *cs)
 {
     KVMOpenPICState *opp = KVM_OPENPIC(d);
-    struct kvm_enable_cap encap = {};
 
-    encap.cap = KVM_CAP_IRQ_MPIC;
+    return kvm_vcpu_enable_cap(cs, KVM_CAP_IRQ_MPIC, 0, opp->fd,
-    encap.args[0] = opp->fd;
+                               kvm_arch_vcpu_id(cs));
-    encap.args[1] = kvm_arch_vcpu_id(cs);
-
-    return kvm_vcpu_ioctl(cs, KVM_ENABLE_CAP, &encap);
 }
 
 static Property kvm_openpic_properties[] = {

hw/intc/xics_kvm.c

@@ -331,15 +331,11 @@ static void xics_kvm_cpu_setup(XICSState *icp, PowerPCCPU *cpu)
 
     if (icpkvm->kernel_xics_fd != -1) {
         int ret;
-        struct kvm_enable_cap xics_enable_cap = {
-            .cap = KVM_CAP_IRQ_XICS,
-            .flags = 0,
-            .args = {icpkvm->kernel_xics_fd, kvm_arch_vcpu_id(cs), 0, 0},
-        };
 
         ss->cs = cs;
 
-        ret = kvm_vcpu_ioctl(ss->cs, KVM_ENABLE_CAP, &xics_enable_cap);
+        ret = kvm_vcpu_enable_cap(cs, KVM_CAP_IRQ_XICS, 0,
+                                  icpkvm->kernel_xics_fd, kvm_arch_vcpu_id(cs));
         if (ret < 0) {
             error_report("Unable to connect CPU%ld to kernel XICS: %s",
                     kvm_arch_vcpu_id(cs), strerror(errno));

hw/misc/ivshmem.c

@@ -684,8 +684,8 @@ static int pci_ivshmem_init(PCIDevice *dev)
     }
 
     if (s->role_val == IVSHMEM_PEER) {
-        error_set(&s->migration_blocker, QERR_DEVICE_FEATURE_BLOCKS_MIGRATION,
+        error_setg(&s->migration_blocker,
-                  "peer mode", "ivshmem");
+                   "Migration is disabled when using feature 'peer mode' in device 'ivshmem'");
         migrate_add_blocker(s->migration_blocker);
     }
 

hw/misc/tmp105.c

@@ -56,12 +56,14 @@ static void tmp105_get_temperature(Object *obj, Visitor *v, void *opaque,
                                    const char *name, Error **errp)
 {
     TMP105State *s = TMP105(obj);
-    int64_t value = s->temperature;
+    int64_t value = s->temperature * 1000 / 256;
 
     visit_type_int(v, &value, name, errp);
 }
 
-/* Units are 0.001 centigrades relative to 0 C.  */
+/* Units are 0.001 centigrades relative to 0 C.  s->temperature is 8.8
+ * fixed point, so units are 1/256 centigrades.  A simple ratio will do.
+ */
 static void tmp105_set_temperature(Object *obj, Visitor *v, void *opaque,
                                    const char *name, Error **errp)
 {
@@ -78,7 +80,7 @@ static void tmp105_set_temperature(Object *obj, Visitor *v, void *opaque,
         return;
     }
 
-    s->temperature = ((int16_t) (temp * 0x800 / 128000)) << 4;
+    s->temperature = (int16_t) (temp * 256 / 1000);
 
     tmp105_alarm_update(s);
 }

hw/misc/zynq_slcr.c

@@ -19,102 +19,155 @@
 #include "hw/sysbus.h"
 #include "sysemu/sysemu.h"
 
-#ifdef ZYNQ_ARM_SLCR_ERR_DEBUG
+#ifndef ZYNQ_SLCR_ERR_DEBUG
-#define DB_PRINT(...) do { \
+#define ZYNQ_SLCR_ERR_DEBUG 0
-    fprintf(stderr,  ": %s: ", __func__); \
-    fprintf(stderr, ## __VA_ARGS__); \
-    } while (0);
-#else
-    #define DB_PRINT(...)
 #endif
 
+#define DB_PRINT(...) do { \
+        if (ZYNQ_SLCR_ERR_DEBUG) { \
+            fprintf(stderr,  ": %s: ", __func__); \
+            fprintf(stderr, ## __VA_ARGS__); \
+        } \
+    } while (0);
+
 #define XILINX_LOCK_KEY 0x767b
 #define XILINX_UNLOCK_KEY 0xdf0d
 
 #define R_PSS_RST_CTRL_SOFT_RST 0x1
 
-typedef enum {
+enum {
-  ARM_PLL_CTRL,
+    SCL             = 0x000 / 4,
-  DDR_PLL_CTRL,
+    LOCK,
-  IO_PLL_CTRL,
+    UNLOCK,
-  PLL_STATUS,
+    LOCKSTA,
-  ARM_PPL_CFG,
-  DDR_PLL_CFG,
-  IO_PLL_CFG,
-  PLL_BG_CTRL,
-  PLL_MAX
-} PLLValues;
 
-typedef enum {
+    ARM_PLL_CTRL    = 0x100 / 4,
-  ARM_CLK_CTRL,
+    DDR_PLL_CTRL,
-  DDR_CLK_CTRL,
+    IO_PLL_CTRL,
-  DCI_CLK_CTRL,
+    PLL_STATUS,
-  APER_CLK_CTRL,
+    ARM_PLL_CFG,
-  USB0_CLK_CTRL,
+    DDR_PLL_CFG,
-  USB1_CLK_CTRL,
+    IO_PLL_CFG,
-  GEM0_RCLK_CTRL,
-  GEM1_RCLK_CTRL,
-  GEM0_CLK_CTRL,
-  GEM1_CLK_CTRL,
-  SMC_CLK_CTRL,
-  LQSPI_CLK_CTRL,
-  SDIO_CLK_CTRL,
-  UART_CLK_CTRL,
-  SPI_CLK_CTRL,
-  CAN_CLK_CTRL,
-  CAN_MIOCLK_CTRL,
-  DBG_CLK_CTRL,
-  PCAP_CLK_CTRL,
-  TOPSW_CLK_CTRL,
-  CLK_MAX
-} ClkValues;
 
-typedef enum {
+    ARM_CLK_CTRL    = 0x120 / 4,
-  CLK_CTRL,
+    DDR_CLK_CTRL,
-  THR_CTRL,
+    DCI_CLK_CTRL,
-  THR_CNT,
+    APER_CLK_CTRL,
-  THR_STA,
+    USB0_CLK_CTRL,
-  FPGA_MAX
+    USB1_CLK_CTRL,
-} FPGAValues;
+    GEM0_RCLK_CTRL,
+    GEM1_RCLK_CTRL,
+    GEM0_CLK_CTRL,
+    GEM1_CLK_CTRL,
+    SMC_CLK_CTRL,
+    LQSPI_CLK_CTRL,
+    SDIO_CLK_CTRL,
+    UART_CLK_CTRL,
+    SPI_CLK_CTRL,
+    CAN_CLK_CTRL,
+    CAN_MIOCLK_CTRL,
+    DBG_CLK_CTRL,
+    PCAP_CLK_CTRL,
+    TOPSW_CLK_CTRL,
 
-typedef enum {
+#define FPGA_CTRL_REGS(n, start) \
-  SYNC_CTRL,
+    FPGA ## n ## _CLK_CTRL = (start) / 4, \
-  SYNC_STATUS,
+    FPGA ## n ## _THR_CTRL, \
-  BANDGAP_TRIP,
+    FPGA ## n ## _THR_CNT, \
-  CC_TEST,
+    FPGA ## n ## _THR_STA,
-  PLL_PREDIVISOR,
+    FPGA_CTRL_REGS(0, 0x170)
-  CLK_621_TRUE,
+    FPGA_CTRL_REGS(1, 0x180)
-  PICTURE_DBG,
+    FPGA_CTRL_REGS(2, 0x190)
-  PICTURE_DBG_UCNT,
+    FPGA_CTRL_REGS(3, 0x1a0)
-  PICTURE_DBG_LCNT,
-  MISC_MAX
-} MiscValues;
 
-typedef enum {
+    BANDGAP_TRIP    = 0x1b8 / 4,
-  PSS,
+    PLL_PREDIVISOR  = 0x1c0 / 4,
-  DDDR,
+    CLK_621_TRUE,
-  DMAC = 3,
+
-  USB,
+    PSS_RST_CTRL    = 0x200 / 4,
-  GEM,
+    DDR_RST_CTRL,
-  SDIO,
+    TOPSW_RESET_CTRL,
-  SPI,
+    DMAC_RST_CTRL,
-  CAN,
+    USB_RST_CTRL,
-  I2C,
+    GEM_RST_CTRL,
-  UART,
+    SDIO_RST_CTRL,
-  GPIO,
+    SPI_RST_CTRL,
-  LQSPI,
+    CAN_RST_CTRL,
-  SMC,
+    I2C_RST_CTRL,
-  OCM,
+    UART_RST_CTRL,
-  DEVCI,
+    GPIO_RST_CTRL,
-  FPGA,
+    LQSPI_RST_CTRL,
-  A9_CPU,
+    SMC_RST_CTRL,
-  RS_AWDT,
+    OCM_RST_CTRL,
-  RST_REASON,
+    FPGA_RST_CTRL   = 0x240 / 4,
-  RST_REASON_CLR,
+    A9_CPU_RST_CTRL,
-  REBOOT_STATUS,
+
-  BOOT_MODE,
+    RS_AWDT_CTRL    = 0x24c / 4,
-  RESET_MAX
+    RST_REASON,
-} ResetValues;
+
+    REBOOT_STATUS   = 0x258 / 4,
+    BOOT_MODE,
+
+    APU_CTRL        = 0x300 / 4,
+    WDT_CLK_SEL,
+
+    TZ_DMA_NS       = 0x440 / 4,
+    TZ_DMA_IRQ_NS,
+    TZ_DMA_PERIPH_NS,
+
+    PSS_IDCODE      = 0x530 / 4,
+
+    DDR_URGENT      = 0x600 / 4,
+    DDR_CAL_START   = 0x60c / 4,
+    DDR_REF_START   = 0x614 / 4,
+    DDR_CMD_STA,
+    DDR_URGENT_SEL,
+    DDR_DFI_STATUS,
+
+    MIO             = 0x700 / 4,
+#define MIO_LENGTH 54
+
+    MIO_LOOPBACK    = 0x804 / 4,
+    MIO_MST_TRI0,
+    MIO_MST_TRI1,
+
+    SD0_WP_CD_SEL   = 0x830 / 4,
+    SD1_WP_CD_SEL,
+
+    LVL_SHFTR_EN    = 0x900 / 4,
+    OCM_CFG         = 0x910 / 4,
+
+    CPU_RAM         = 0xa00 / 4,
+
+    IOU             = 0xa30 / 4,
+
+    DMAC_RAM        = 0xa50 / 4,
+
+    AFI0            = 0xa60 / 4,
+    AFI1 = AFI0 + 3,
+    AFI2 = AFI1 + 3,
+    AFI3 = AFI2 + 3,
+#define AFI_LENGTH 3
+
+    OCM             = 0xa90 / 4,
+
+    DEVCI_RAM       = 0xaa0 / 4,
+
+    CSG_RAM         = 0xab0 / 4,
+
+    GPIOB_CTRL      = 0xb00 / 4,
+    GPIOB_CFG_CMOS18,
+    GPIOB_CFG_CMOS25,
+    GPIOB_CFG_CMOS33,
+    GPIOB_CFG_HSTL  = 0xb14 / 4,
+    GPIOB_DRVR_BIAS_CTRL,
+
+    DDRIOB          = 0xb40 / 4,
+#define DDRIOB_LENGTH 14
+};
+
+#define ZYNQ_SLCR_MMIO_SIZE     0x1000
+#define ZYNQ_SLCR_NUM_REGS      (ZYNQ_SLCR_MMIO_SIZE / 4)
 
 #define TYPE_ZYNQ_SLCR "xilinx,zynq_slcr"
 #define ZYNQ_SLCR(obj) OBJECT_CHECK(ZynqSLCRState, (obj), TYPE_ZYNQ_SLCR)
@@ -124,42 +177,7 @@ typedef struct ZynqSLCRState {
 
     MemoryRegion iomem;
 
-    union {
+    uint32_t regs[ZYNQ_SLCR_NUM_REGS];
-        struct {
-            uint16_t scl;
-            uint16_t lockval;
-            uint32_t pll[PLL_MAX]; /* 0x100 - 0x11C */
-            uint32_t clk[CLK_MAX]; /* 0x120 - 0x16C */
-            uint32_t fpga[4][FPGA_MAX]; /* 0x170 - 0x1AC */
-            uint32_t misc[MISC_MAX]; /* 0x1B0 - 0x1D8 */
-            uint32_t reset[RESET_MAX]; /* 0x200 - 0x25C */
-            uint32_t apu_ctrl; /* 0x300 */
-            uint32_t wdt_clk_sel; /* 0x304 */
-            uint32_t tz_ocm[3]; /* 0x400 - 0x408 */
-            uint32_t tz_ddr; /* 0x430 */
-            uint32_t tz_dma[3]; /* 0x440 - 0x448 */
-            uint32_t tz_misc[3]; /* 0x450 - 0x458 */
-            uint32_t tz_fpga[2]; /* 0x484 - 0x488 */
-            uint32_t dbg_ctrl; /* 0x500 */
-            uint32_t pss_idcode; /* 0x530 */
-            uint32_t ddr[8]; /* 0x600 - 0x620 - 0x604-missing */
-            uint32_t mio[54]; /* 0x700 - 0x7D4 */
-            uint32_t mio_func[4]; /* 0x800 - 0x810 */
-            uint32_t sd[2]; /* 0x830 - 0x834 */
-            uint32_t lvl_shftr_en; /* 0x900 */
-            uint32_t ocm_cfg; /* 0x910 */
-            uint32_t cpu_ram[8]; /* 0xA00 - 0xA1C */
-            uint32_t iou[7]; /* 0xA30 - 0xA48 */
-            uint32_t dmac_ram; /* 0xA50 */
-            uint32_t afi[4][3]; /* 0xA60 - 0xA8C */
-            uint32_t ocm[3]; /* 0xA90 - 0xA98 */
-            uint32_t devci_ram; /* 0xAA0 */
-            uint32_t csg_ram; /* 0xAB0 */
-            uint32_t gpiob[12]; /* 0xB00 - 0xB2C */
-            uint32_t ddriob[14]; /* 0xB40 - 0xB74 */
-        };
-        uint8_t data[0x1000];
-    };
 } ZynqSLCRState;
 
 static void zynq_slcr_reset(DeviceState *d)
@@ -169,177 +187,169 @@ static void zynq_slcr_reset(DeviceState *d)
 
     DB_PRINT("RESET\n");
 
-    s->lockval = 1;
+    s->regs[LOCKSTA] = 1;
     /* 0x100 - 0x11C */
-    s->pll[ARM_PLL_CTRL] = 0x0001A008;
+    s->regs[ARM_PLL_CTRL]   = 0x0001A008;
-    s->pll[DDR_PLL_CTRL] = 0x0001A008;
+    s->regs[DDR_PLL_CTRL]   = 0x0001A008;
-    s->pll[IO_PLL_CTRL] = 0x0001A008;
+    s->regs[IO_PLL_CTRL]    = 0x0001A008;
-    s->pll[PLL_STATUS] = 0x0000003F;
+    s->regs[PLL_STATUS]     = 0x0000003F;
-    s->pll[ARM_PPL_CFG] = 0x00014000;
+    s->regs[ARM_PLL_CFG]    = 0x00014000;
-    s->pll[DDR_PLL_CFG] = 0x00014000;
+    s->regs[DDR_PLL_CFG]    = 0x00014000;
-    s->pll[IO_PLL_CFG] = 0x00014000;
+    s->regs[IO_PLL_CFG]     = 0x00014000;
 
     /* 0x120 - 0x16C */
-    s->clk[ARM_CLK_CTRL] = 0x1F000400;
+    s->regs[ARM_CLK_CTRL]   = 0x1F000400;
-    s->clk[DDR_CLK_CTRL] = 0x18400003;
+    s->regs[DDR_CLK_CTRL]   = 0x18400003;
-    s->clk[DCI_CLK_CTRL] = 0x01E03201;
+    s->regs[DCI_CLK_CTRL]   = 0x01E03201;
-    s->clk[APER_CLK_CTRL] = 0x01FFCCCD;
+    s->regs[APER_CLK_CTRL]  = 0x01FFCCCD;
-    s->clk[USB0_CLK_CTRL] = s->clk[USB1_CLK_CTRL] = 0x00101941;
+    s->regs[USB0_CLK_CTRL]  = s->regs[USB1_CLK_CTRL]    = 0x00101941;
-    s->clk[GEM0_RCLK_CTRL] = s->clk[GEM1_RCLK_CTRL] = 0x00000001;
+    s->regs[GEM0_RCLK_CTRL] = s->regs[GEM1_RCLK_CTRL]   = 0x00000001;
-    s->clk[GEM0_CLK_CTRL] = s->clk[GEM1_CLK_CTRL] = 0x00003C01;
+    s->regs[GEM0_CLK_CTRL]  = s->regs[GEM1_CLK_CTRL]    = 0x00003C01;
-    s->clk[SMC_CLK_CTRL] = 0x00003C01;
+    s->regs[SMC_CLK_CTRL]   = 0x00003C01;
-    s->clk[LQSPI_CLK_CTRL] = 0x00002821;
+    s->regs[LQSPI_CLK_CTRL] = 0x00002821;
-    s->clk[SDIO_CLK_CTRL] = 0x00001E03;
+    s->regs[SDIO_CLK_CTRL]  = 0x00001E03;
-    s->clk[UART_CLK_CTRL] = 0x00003F03;
+    s->regs[UART_CLK_CTRL]  = 0x00003F03;
-    s->clk[SPI_CLK_CTRL] = 0x00003F03;
+    s->regs[SPI_CLK_CTRL]   = 0x00003F03;
-    s->clk[CAN_CLK_CTRL] = 0x00501903;
+    s->regs[CAN_CLK_CTRL]   = 0x00501903;
-    s->clk[DBG_CLK_CTRL] = 0x00000F03;
+    s->regs[DBG_CLK_CTRL]   = 0x00000F03;
-    s->clk[PCAP_CLK_CTRL] = 0x00000F01;
+    s->regs[PCAP_CLK_CTRL]  = 0x00000F01;
 
     /* 0x170 - 0x1AC */
-    s->fpga[0][CLK_CTRL] = s->fpga[1][CLK_CTRL] = s->fpga[2][CLK_CTRL] =
+    s->regs[FPGA0_CLK_CTRL] = s->regs[FPGA1_CLK_CTRL] = s->regs[FPGA2_CLK_CTRL]
-            s->fpga[3][CLK_CTRL] = 0x00101800;
+                            = s->regs[FPGA3_CLK_CTRL] = 0x00101800;
-    s->fpga[0][THR_STA] = s->fpga[1][THR_STA] = s->fpga[2][THR_STA] =
+    s->regs[FPGA0_THR_STA] = s->regs[FPGA1_THR_STA] = s->regs[FPGA2_THR_STA]
-            s->fpga[3][THR_STA] = 0x00010000;
+                           = s->regs[FPGA3_THR_STA] = 0x00010000;
 
     /* 0x1B0 - 0x1D8 */
-    s->misc[BANDGAP_TRIP] = 0x0000001F;
+    s->regs[BANDGAP_TRIP]   = 0x0000001F;
-    s->misc[PLL_PREDIVISOR] = 0x00000001;
+    s->regs[PLL_PREDIVISOR] = 0x00000001;
-    s->misc[CLK_621_TRUE] = 0x00000001;
+    s->regs[CLK_621_TRUE]   = 0x00000001;
 
     /* 0x200 - 0x25C */
-    s->reset[FPGA] = 0x01F33F0F;
+    s->regs[FPGA_RST_CTRL]  = 0x01F33F0F;
-    s->reset[RST_REASON] = 0x00000040;
+    s->regs[RST_REASON]     = 0x00000040;
+
+    s->regs[BOOT_MODE]      = 0x00000001;
 
     /* 0x700 - 0x7D4 */
     for (i = 0; i < 54; i++) {
-        s->mio[i] = 0x00001601;
+        s->regs[MIO + i] = 0x00001601;
     }
     for (i = 2; i <= 8; i++) {
-        s->mio[i] = 0x00000601;
+        s->regs[MIO + i] = 0x00000601;
     }
 
-    /* MIO_MST_TRI0, MIO_MST_TRI1 */
+    s->regs[MIO_MST_TRI0] = s->regs[MIO_MST_TRI1] = 0xFFFFFFFF;
-    s->mio_func[2] = s->mio_func[3] = 0xFFFFFFFF;
 
-    s->cpu_ram[0] = s->cpu_ram[1] = s->cpu_ram[3] =
+    s->regs[CPU_RAM + 0] = s->regs[CPU_RAM + 1] = s->regs[CPU_RAM + 3]
-            s->cpu_ram[4] = s->cpu_ram[7] = 0x00010101;
+                         = s->regs[CPU_RAM + 4] = s->regs[CPU_RAM + 7]
-    s->cpu_ram[2] = s->cpu_ram[5] = 0x01010101;
+                         = 0x00010101;
-    s->cpu_ram[6] = 0x00000001;
+    s->regs[CPU_RAM + 2] = s->regs[CPU_RAM + 5] = 0x01010101;
+    s->regs[CPU_RAM + 6] = 0x00000001;
 
-    s->iou[0] = s->iou[1] = s->iou[2] = s->iou[3] = 0x09090909;
+    s->regs[IOU + 0] = s->regs[IOU + 1] = s->regs[IOU + 2] = s->regs[IOU + 3]
-    s->iou[4] = s->iou[5] = 0x00090909;
+                     = 0x09090909;
-    s->iou[6] = 0x00000909;
+    s->regs[IOU + 4] = s->regs[IOU + 5] = 0x00090909;
+    s->regs[IOU + 6] = 0x00000909;
 
-    s->dmac_ram = 0x00000009;
+    s->regs[DMAC_RAM] = 0x00000009;
 
-    s->afi[0][0] = s->afi[0][1] = 0x09090909;
+    s->regs[AFI0 + 0] = s->regs[AFI0 + 1] = 0x09090909;
-    s->afi[1][0] = s->afi[1][1] = 0x09090909;
+    s->regs[AFI1 + 0] = s->regs[AFI1 + 1] = 0x09090909;
-    s->afi[2][0] = s->afi[2][1] = 0x09090909;
+    s->regs[AFI2 + 0] = s->regs[AFI2 + 1] = 0x09090909;
-    s->afi[3][0] = s->afi[3][1] = 0x09090909;
+    s->regs[AFI3 + 0] = s->regs[AFI3 + 1] = 0x09090909;
-    s->afi[0][2] = s->afi[1][2] = s->afi[2][2] = s->afi[3][2] = 0x00000909;
+    s->regs[AFI0 + 2] = s->regs[AFI1 + 2] = s->regs[AFI2 + 2]
+                      = s->regs[AFI3 + 2] = 0x00000909;
 
-    s->ocm[0] = 0x01010101;
+    s->regs[OCM + 0]    = 0x01010101;
-    s->ocm[1] = s->ocm[2] = 0x09090909;
+    s->regs[OCM + 1]    = s->regs[OCM + 2] = 0x09090909;
 
-    s->devci_ram = 0x00000909;
+    s->regs[DEVCI_RAM]  = 0x00000909;
-    s->csg_ram = 0x00000001;
+    s->regs[CSG_RAM]    = 0x00000001;
 
-    s->ddriob[0] = s->ddriob[1] = s->ddriob[2] = s->ddriob[3] = 0x00000e00;
+    s->regs[DDRIOB + 0] = s->regs[DDRIOB + 1] = s->regs[DDRIOB + 2]
-    s->ddriob[4] = s->ddriob[5] = s->ddriob[6] = 0x00000e00;
+                        = s->regs[DDRIOB + 3] = 0x00000e00;
-    s->ddriob[12] = 0x00000021;
+    s->regs[DDRIOB + 4] = s->regs[DDRIOB + 5] = s->regs[DDRIOB + 6]
+                        = 0x00000e00;
+    s->regs[DDRIOB + 12] = 0x00000021;
 }
 
-static inline uint32_t zynq_slcr_read_imp(void *opaque,
-    hwaddr offset)
-{
-    ZynqSLCRState *s = (ZynqSLCRState *)opaque;
 
+static bool zynq_slcr_check_offset(hwaddr offset, bool rnw)
+{
     switch (offset) {
-    case 0x0: /* SCL */
+    case LOCK:
-        return s->scl;
+    case UNLOCK:
-    case 0x4: /* LOCK */
+    case DDR_CAL_START:
-    case 0x8: /* UNLOCK */
+    case DDR_REF_START:
-        DB_PRINT("Reading SCLR_LOCK/UNLOCK is not enabled\n");
+        return !rnw; /* Write only */
-        return 0;
+    case LOCKSTA:
-    case 0x0C: /* LOCKSTA */
+    case FPGA0_THR_STA:
-        return s->lockval;
+    case FPGA1_THR_STA:
-    case 0x100 ... 0x11C:
+    case FPGA2_THR_STA:
-        return s->pll[(offset - 0x100) / 4];
+    case FPGA3_THR_STA:
-    case 0x120 ... 0x16C:
+    case BOOT_MODE:
-        return s->clk[(offset - 0x120) / 4];
+    case PSS_IDCODE:
-    case 0x170 ... 0x1AC:
+    case DDR_CMD_STA:
-        return s->fpga[0][(offset - 0x170) / 4];
+    case DDR_DFI_STATUS:
-    case 0x1B0 ... 0x1D8:
+    case PLL_STATUS:
-        return s->misc[(offset - 0x1B0) / 4];
+        return rnw;/* read only */
-    case 0x200 ... 0x258:
+    case SCL:
-        return s->reset[(offset - 0x200) / 4];
+    case ARM_PLL_CTRL ... IO_PLL_CTRL:
-    case 0x25c:
+    case ARM_PLL_CFG ... IO_PLL_CFG:
-        return 1;
+    case ARM_CLK_CTRL ... TOPSW_CLK_CTRL:
-    case 0x300:
+    case FPGA0_CLK_CTRL ... FPGA0_THR_CNT:
-        return s->apu_ctrl;
+    case FPGA1_CLK_CTRL ... FPGA1_THR_CNT:
-    case 0x304:
+    case FPGA2_CLK_CTRL ... FPGA2_THR_CNT:
-        return s->wdt_clk_sel;
+    case FPGA3_CLK_CTRL ... FPGA3_THR_CNT:
-    case 0x400 ... 0x408:
+    case BANDGAP_TRIP:
-        return s->tz_ocm[(offset - 0x400) / 4];
+    case PLL_PREDIVISOR:
-    case 0x430:
+    case CLK_621_TRUE:
-        return s->tz_ddr;
+    case PSS_RST_CTRL ... A9_CPU_RST_CTRL:
-    case 0x440 ... 0x448:
+    case RS_AWDT_CTRL:
-        return s->tz_dma[(offset - 0x440) / 4];
+    case RST_REASON:
-    case 0x450 ... 0x458:
+    case REBOOT_STATUS:
-        return s->tz_misc[(offset - 0x450) / 4];
+    case APU_CTRL:
-    case 0x484 ... 0x488:
+    case WDT_CLK_SEL:
-        return s->tz_fpga[(offset - 0x484) / 4];
+    case TZ_DMA_NS ... TZ_DMA_PERIPH_NS:
-    case 0x500:
+    case DDR_URGENT:
-        return s->dbg_ctrl;
+    case DDR_URGENT_SEL:
-    case 0x530:
+    case MIO ... MIO + MIO_LENGTH - 1:
-        return s->pss_idcode;
+    case MIO_LOOPBACK ... MIO_MST_TRI1:
-    case 0x600 ... 0x620:
+    case SD0_WP_CD_SEL:
-        if (offset == 0x604) {
+    case SD1_WP_CD_SEL:
-            goto bad_reg;
+    case LVL_SHFTR_EN:
-        }
+    case OCM_CFG:
-        return s->ddr[(offset - 0x600) / 4];
+    case CPU_RAM:
-    case 0x700 ... 0x7D4:
+    case IOU:
-        return s->mio[(offset - 0x700) / 4];
+    case DMAC_RAM:
-    case 0x800 ... 0x810:
+    case AFI0 ... AFI3 + AFI_LENGTH - 1:
-        return s->mio_func[(offset - 0x800) / 4];
+    case OCM:
-    case 0x830 ... 0x834:
+    case DEVCI_RAM:
-        return s->sd[(offset - 0x830) / 4];
+    case CSG_RAM:
-    case 0x900:
+    case GPIOB_CTRL ... GPIOB_CFG_CMOS33:
-        return s->lvl_shftr_en;
+    case GPIOB_CFG_HSTL:
-    case 0x910:
+    case GPIOB_DRVR_BIAS_CTRL:
-        return s->ocm_cfg;
+    case DDRIOB ... DDRIOB + DDRIOB_LENGTH - 1:
-    case 0xA00 ... 0xA1C:
+        return true;
-        return s->cpu_ram[(offset - 0xA00) / 4];
-    case 0xA30 ... 0xA48:
-        return s->iou[(offset - 0xA30) / 4];
-    case 0xA50:
-        return s->dmac_ram;
-    case 0xA60 ... 0xA8C:
-        return s->afi[0][(offset - 0xA60) / 4];
-    case 0xA90 ... 0xA98:
-        return s->ocm[(offset - 0xA90) / 4];
-    case 0xAA0:
-        return s->devci_ram;
-    case 0xAB0:
-        return s->csg_ram;
-    case 0xB00 ... 0xB2C:
-        return s->gpiob[(offset - 0xB00) / 4];
-    case 0xB40 ... 0xB74:
-        return s->ddriob[(offset - 0xB40) / 4];
     default:
-    bad_reg:
+        return false;
-        DB_PRINT("Bad register offset 0x%x\n", (int)offset);
-        return 0;
     }
 }
 
 static uint64_t zynq_slcr_read(void *opaque, hwaddr offset,
     unsigned size)
 {
-    uint32_t ret = zynq_slcr_read_imp(opaque, offset);
+    ZynqSLCRState *s = opaque;
+    offset /= 4;
+    uint32_t ret = s->regs[offset];
 
-    DB_PRINT("addr: %08x data: %08x\n", (unsigned)offset, (unsigned)ret);
+    if (!zynq_slcr_check_offset(offset, true)) {
+        qemu_log_mask(LOG_GUEST_ERROR, "zynq_slcr: Invalid read access to "
+                      " addr %" HWADDR_PRIx "\n", offset * 4);
+    }
+
+    DB_PRINT("addr: %08" HWADDR_PRIx " data: %08" PRIx32 "\n", offset * 4, ret);
     return ret;
 }
 
@@ -347,148 +357,55 @@ static void zynq_slcr_write(void *opaque, hwaddr offset,
                           uint64_t val, unsigned size)
 {
     ZynqSLCRState *s = (ZynqSLCRState *)opaque;
+    offset /= 4;
 
-    DB_PRINT("offset: %08x data: %08x\n", (unsigned)offset, (unsigned)val);
+    DB_PRINT("addr: %08" HWADDR_PRIx " data: %08" PRIx64 "\n", offset * 4, val);
+
+    if (!zynq_slcr_check_offset(offset, false)) {
+        qemu_log_mask(LOG_GUEST_ERROR, "zynq_slcr: Invalid write access to "
+                      "addr %" HWADDR_PRIx "\n", offset * 4);
+        return;
+    }
 
     switch (offset) {
-    case 0x00: /* SCL */
+    case SCL:
-        s->scl = val & 0x1;
+        s->regs[SCL] = val & 0x1;
-    return;
+        return;
-    case 0x4: /* SLCR_LOCK */
+    case LOCK:
         if ((val & 0xFFFF) == XILINX_LOCK_KEY) {
             DB_PRINT("XILINX LOCK 0xF8000000 + 0x%x <= 0x%x\n", (int)offset,
                 (unsigned)val & 0xFFFF);
-            s->lockval = 1;
+            s->regs[LOCKSTA] = 1;
         } else {
             DB_PRINT("WRONG XILINX LOCK KEY 0xF8000000 + 0x%x <= 0x%x\n",
                 (int)offset, (unsigned)val & 0xFFFF);
         }
         return;
-    case 0x8: /* SLCR_UNLOCK */
+    case UNLOCK:
         if ((val & 0xFFFF) == XILINX_UNLOCK_KEY) {
             DB_PRINT("XILINX UNLOCK 0xF8000000 + 0x%x <= 0x%x\n", (int)offset,
                 (unsigned)val & 0xFFFF);
-            s->lockval = 0;
+            s->regs[LOCKSTA] = 0;
         } else {
             DB_PRINT("WRONG XILINX UNLOCK KEY 0xF8000000 + 0x%x <= 0x%x\n",
                 (int)offset, (unsigned)val & 0xFFFF);
         }
         return;
-    case 0xc: /* LOCKSTA */
+    }
-        DB_PRINT("Writing SCLR_LOCKSTA is not enabled\n");
+
+    if (!s->regs[LOCKSTA]) {
+        s->regs[offset / 4] = val;
+    } else {
+        DB_PRINT("SCLR registers are locked. Unlock them first\n");
         return;
     }
 
-    if (!s->lockval) {
+    switch (offset) {
-        switch (offset) {
+    case PSS_RST_CTRL:
-        case 0x100 ... 0x11C:
+        if (val & R_PSS_RST_CTRL_SOFT_RST) {
-            if (offset == 0x10C) {
+            qemu_system_reset_request();
-                goto bad_reg;
-            }
-            s->pll[(offset - 0x100) / 4] = val;
-            break;
-        case 0x120 ... 0x16C:
-            s->clk[(offset - 0x120) / 4] = val;
-            break;
-        case 0x170 ... 0x1AC:
-            s->fpga[0][(offset - 0x170) / 4] = val;
-            break;
-        case 0x1B0 ... 0x1D8:
-            s->misc[(offset - 0x1B0) / 4] = val;
-            break;
-        case 0x200 ... 0x25C:
-            if (offset == 0x250) {
-                goto bad_reg;
-            }
-            s->reset[(offset - 0x200) / 4] = val;
-            if (offset == 0x200 && (val & R_PSS_RST_CTRL_SOFT_RST)) {
-                qemu_system_reset_request();
-            }
-            break;
-        case 0x300:
-            s->apu_ctrl = val;
-            break;
-        case 0x304:
-            s->wdt_clk_sel = val;
-            break;
-        case 0x400 ... 0x408:
-            s->tz_ocm[(offset - 0x400) / 4] = val;
-            break;
-        case 0x430:
-            s->tz_ddr = val;
-            break;
-        case 0x440 ... 0x448:
-            s->tz_dma[(offset - 0x440) / 4] = val;
-            break;
-        case 0x450 ... 0x458:
-            s->tz_misc[(offset - 0x450) / 4] = val;
-            break;
-        case 0x484 ... 0x488:
-            s->tz_fpga[(offset - 0x484) / 4] = val;
-            break;
-        case 0x500:
-            s->dbg_ctrl = val;
-            break;
-        case 0x530:
-            s->pss_idcode = val;
-            break;
-        case 0x600 ... 0x620:
-            if (offset == 0x604) {
-                goto bad_reg;
-            }
-            s->ddr[(offset - 0x600) / 4] = val;
-            break;
-        case 0x700 ... 0x7D4:
-            s->mio[(offset - 0x700) / 4] = val;
-            break;
-        case 0x800 ... 0x810:
-            s->mio_func[(offset - 0x800) / 4] = val;
-            break;
-        case 0x830 ... 0x834:
-            s->sd[(offset - 0x830) / 4] = val;
-            break;
-        case 0x900:
-            s->lvl_shftr_en = val;
-            break;
-        case 0x910:
-            break;
-        case 0xA00 ... 0xA1C:
-            s->cpu_ram[(offset - 0xA00) / 4] = val;
-            break;
-        case 0xA30 ... 0xA48:
-            s->iou[(offset - 0xA30) / 4] = val;
-            break;
-        case 0xA50:
-            s->dmac_ram = val;
-            break;
-        case 0xA60 ... 0xA8C:
-            s->afi[0][(offset - 0xA60) / 4] = val;
-            break;
-        case 0xA90:
-            s->ocm[0] = val;
-            break;
-        case 0xAA0:
-            s->devci_ram = val;
-            break;
-        case 0xAB0:
-            s->csg_ram = val;
-            break;
-        case 0xB00 ... 0xB2C:
-            if (offset == 0xB20 || offset == 0xB2C) {
-                goto bad_reg;
-            }
-            s->gpiob[(offset - 0xB00) / 4] = val;
-            break;
-        case 0xB40 ... 0xB74:
-            s->ddriob[(offset - 0xB40) / 4] = val;
-            break;
-        default:
-        bad_reg:
-            DB_PRINT("Bad register write %x <= %08x\n", (int)offset,
-                     (unsigned)val);
         }
-    } else {
+        break;
-        DB_PRINT("SCLR registers are locked. Unlock them first\n");
     }
 }
 
@@ -498,23 +415,22 @@ static const MemoryRegionOps slcr_ops = {
     .endianness = DEVICE_NATIVE_ENDIAN,
 };
 
-static int zynq_slcr_init(SysBusDevice *dev)
+static void zynq_slcr_init(Object *obj)
 {
-    ZynqSLCRState *s = ZYNQ_SLCR(dev);
+    ZynqSLCRState *s = ZYNQ_SLCR(obj);
 
-    memory_region_init_io(&s->iomem, OBJECT(s), &slcr_ops, s, "slcr", 0x1000);
+    memory_region_init_io(&s->iomem, obj, &slcr_ops, s, "slcr",
-    sysbus_init_mmio(dev, &s->iomem);
+                          ZYNQ_SLCR_MMIO_SIZE);
-
+    sysbus_init_mmio(SYS_BUS_DEVICE(obj), &s->iomem);
-    return 0;
 }
 
 static const VMStateDescription vmstate_zynq_slcr = {
     .name = "zynq_slcr",
-    .version_id = 1,
+    .version_id = 2,
-    .minimum_version_id = 1,
+    .minimum_version_id = 2,
-    .minimum_version_id_old = 1,
+    .minimum_version_id_old = 2,
     .fields      = (VMStateField[]) {
-        VMSTATE_UINT8_ARRAY(data, ZynqSLCRState, 0x1000),
+        VMSTATE_UINT32_ARRAY(regs, ZynqSLCRState, ZYNQ_SLCR_NUM_REGS),
         VMSTATE_END_OF_LIST()
     }
 };
@@ -522,9 +438,7 @@ static const VMStateDescription vmstate_zynq_slcr = {
 static void zynq_slcr_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
-    SysBusDeviceClass *sdc = SYS_BUS_DEVICE_CLASS(klass);
 
-    sdc->init = zynq_slcr_init;
     dc->vmsd = &vmstate_zynq_slcr;
     dc->reset = zynq_slcr_reset;
 }
@@ -534,6 +448,7 @@ static const TypeInfo zynq_slcr_info = {
     .name  = TYPE_ZYNQ_SLCR,
     .parent = TYPE_SYS_BUS_DEVICE,
     .instance_size  = sizeof(ZynqSLCRState),
+    .instance_init = zynq_slcr_init,
 };
 
 static void zynq_slcr_register_types(void)

hw/net/allwinner_emac.c

@@ -27,11 +27,11 @@ static uint8_t padding[60];
 static void mii_set_link(RTL8201CPState *mii, bool link_ok)
 {
     if (link_ok) {
-        mii->bmsr |= MII_BMSR_LINK_ST;
+        mii->bmsr |= MII_BMSR_LINK_ST | MII_BMSR_AN_COMP;
         mii->anlpar |= MII_ANAR_TXFD | MII_ANAR_10FD | MII_ANAR_10 |
                        MII_ANAR_CSMACD;
     } else {
-        mii->bmsr &= ~MII_BMSR_LINK_ST;
+        mii->bmsr &= ~(MII_BMSR_LINK_ST | MII_BMSR_AN_COMP);
         mii->anlpar = MII_ANAR_TX;
     }
 }
@@ -391,9 +391,11 @@ static void aw_emac_write(void *opaque, hwaddr offset, uint64_t value,
         break;
     case EMAC_INT_CTL_REG:
         s->int_ctl = value;
+        aw_emac_update_irq(s);
         break;
     case EMAC_INT_STA_REG:
         s->int_sta &= ~value;
+        aw_emac_update_irq(s);
         break;
     case EMAC_MAC_MADR_REG:
         s->phy_target = value;

hw/net/cadence_gem.c

@@ -1093,7 +1093,7 @@ static uint64_t gem_read(void *opaque, hwaddr offset, unsigned size)
             uint32_t phy_addr, reg_num;
 
             phy_addr = (retval & GEM_PHYMNTNC_ADDR) >> GEM_PHYMNTNC_ADDR_SHFT;
-            if (phy_addr == BOARD_PHY_ADDRESS) {
+            if (phy_addr == BOARD_PHY_ADDRESS || phy_addr == 0) {
                 reg_num = (retval & GEM_PHYMNTNC_REG) >> GEM_PHYMNTNC_REG_SHIFT;
                 retval &= 0xFFFF0000;
                 retval |= gem_phy_read(s, reg_num);
@@ -1193,7 +1193,7 @@ static void gem_write(void *opaque, hwaddr offset, uint64_t val,
             uint32_t phy_addr, reg_num;
 
             phy_addr = (val & GEM_PHYMNTNC_ADDR) >> GEM_PHYMNTNC_ADDR_SHFT;
-            if (phy_addr == BOARD_PHY_ADDRESS) {
+            if (phy_addr == BOARD_PHY_ADDRESS || phy_addr == 0) {
                 reg_num = (val & GEM_PHYMNTNC_REG) >> GEM_PHYMNTNC_REG_SHIFT;
                 gem_phy_write(s, reg_num, val);
             }

hw/net/pcnet.c

@@ -718,7 +718,6 @@ static void pcnet_s_reset(PCNetState *s)
     s->csr[94]  = 0x0000;
     s->csr[100] = 0x0200;
     s->csr[103] = 0x0105;
-    s->csr[103] = 0x0105;
     s->csr[112] = 0x0000;
     s->csr[114] = 0x0000;
     s->csr[122] = 0x0000;

hw/net/virtio-net.c

@@ -677,7 +677,7 @@ static int virtio_net_handle_mac(VirtIONet *n, uint8_t cmd,
         goto error;
     }
 
-    if (in_use + mac_data.entries <= MAC_TABLE_ENTRIES) {
+    if (mac_data.entries <= MAC_TABLE_ENTRIES - in_use) {
         s = iov_to_buf(iov, iov_cnt, 0, &macs[in_use * ETH_ALEN],
                        mac_data.entries * ETH_ALEN);
         if (s != mac_data.entries * ETH_ALEN) {

hw/net/vmxnet3.c

@@ -52,6 +52,9 @@
 #define VMXNET3_DEVICE_VERSION    0x1
 #define VMXNET3_DEVICE_REVISION   0x1
 
+/* Number of interrupt vectors for non-MSIx modes */
+#define VMXNET3_MAX_NMSIX_INTRS   (1)
+
 /* Macros for rings descriptors access */
 #define VMXNET3_READ_TX_QUEUE_DESCR8(dpa, field) \
     (vmw_shmem_ld8(dpa + offsetof(struct Vmxnet3_TxQueueDesc, field)))
@@ -1305,6 +1308,51 @@ static bool vmxnet3_verify_intx(VMXNET3State *s, int intx)
            (pci_get_byte(s->parent_obj.config + PCI_INTERRUPT_PIN) - 1));
 }
 
+static void vmxnet3_validate_interrupt_idx(bool is_msix, int idx)
+{
+    int max_ints = is_msix ? VMXNET3_MAX_INTRS : VMXNET3_MAX_NMSIX_INTRS;
+    if (idx >= max_ints) {
+        hw_error("Bad interrupt index: %d\n", idx);
+    }
+}
+
+static void vmxnet3_validate_interrupts(VMXNET3State *s)
+{
+    int i;
+
+    VMW_CFPRN("Verifying event interrupt index (%d)", s->event_int_idx);
+    vmxnet3_validate_interrupt_idx(s->msix_used, s->event_int_idx);
+
+    for (i = 0; i < s->txq_num; i++) {
+        int idx = s->txq_descr[i].intr_idx;
+        VMW_CFPRN("Verifying TX queue %d interrupt index (%d)", i, idx);
+        vmxnet3_validate_interrupt_idx(s->msix_used, idx);
+    }
+
+    for (i = 0; i < s->rxq_num; i++) {
+        int idx = s->rxq_descr[i].intr_idx;
+        VMW_CFPRN("Verifying RX queue %d interrupt index (%d)", i, idx);
+        vmxnet3_validate_interrupt_idx(s->msix_used, idx);
+    }
+}
+
+static void vmxnet3_validate_queues(VMXNET3State *s)
+{
+    /*
+    * txq_num and rxq_num are total number of queues
+    * configured by guest. These numbers must not
+    * exceed corresponding maximal values.
+    */
+
+    if (s->txq_num > VMXNET3_DEVICE_MAX_TX_QUEUES) {
+        hw_error("Bad TX queues number: %d\n", s->txq_num);
+    }
+
+    if (s->rxq_num > VMXNET3_DEVICE_MAX_RX_QUEUES) {
+        hw_error("Bad RX queues number: %d\n", s->rxq_num);
+    }
+}
+
 static void vmxnet3_activate_device(VMXNET3State *s)
 {
     int i;
@@ -1351,7 +1399,7 @@ static void vmxnet3_activate_device(VMXNET3State *s)
         VMXNET3_READ_DRV_SHARED8(s->drv_shmem, devRead.misc.numRxQueues);
 
     VMW_CFPRN("Number of TX/RX queues %u/%u", s->txq_num, s->rxq_num);
-    assert(s->txq_num <= VMXNET3_DEVICE_MAX_TX_QUEUES);
+    vmxnet3_validate_queues(s);
 
     qdescr_table_pa =
         VMXNET3_READ_DRV_SHARED64(s->drv_shmem, devRead.misc.queueDescPA);
@@ -1447,6 +1495,8 @@ static void vmxnet3_activate_device(VMXNET3State *s)
                sizeof(s->rxq_descr[i].rxq_stats));
     }
 
+    vmxnet3_validate_interrupts(s);
+
     /* Make sure everything is in place before device activation */
     smp_wmb();
 
@@ -2005,7 +2055,6 @@ vmxnet3_cleanup_msix(VMXNET3State *s)
     }
 }
 
-#define VMXNET3_MSI_NUM_VECTORS   (1)
 #define VMXNET3_MSI_OFFSET        (0x50)
 #define VMXNET3_USE_64BIT         (true)
 #define VMXNET3_PER_VECTOR_MASK   (false)
@@ -2016,7 +2065,7 @@ vmxnet3_init_msi(VMXNET3State *s)
     PCIDevice *d = PCI_DEVICE(s);
     int res;
 
-    res = msi_init(d, VMXNET3_MSI_OFFSET, VMXNET3_MSI_NUM_VECTORS,
+    res = msi_init(d, VMXNET3_MSI_OFFSET, VMXNET3_MAX_NMSIX_INTRS,
                    VMXNET3_USE_64BIT, VMXNET3_PER_VECTOR_MASK);
     if (0 > res) {
         VMW_WRPRN("Failed to initialize MSI, error %d", res);
@@ -2342,6 +2391,9 @@ static int vmxnet3_post_load(void *opaque, int version_id)
         }
     }
 
+    vmxnet3_validate_queues(s);
+    vmxnet3_validate_interrupts(s);
+
     return 0;
 }
 

hw/net/xilinx_axienet.c

@@ -98,7 +98,7 @@ static unsigned int tdk_read(struct PHY *phy, unsigned int req)
             r |= 1;
             break;
         case 17:
-            /* Marvel PHY on many xilinx boards.  */
+            /* Marvell PHY on many xilinx boards.  */
             r = 0x8000; /* 1000Mb  */
             break;
         case 18:
@@ -142,6 +142,9 @@ tdk_write(struct PHY *phy, unsigned int req, unsigned int data)
             phy->regs[regnum] = data;
             break;
     }
+
+    /* Unconditionally clear regs[BMCR][BMCR_RESET] */
+    phy->regs[0] &= ~0x8000;
 }
 
 static void

hw/pci-host/prep.c

@@ -145,9 +145,9 @@ static uint64_t raven_io_read(void *opaque, hwaddr addr,
     if (size == 1) {
         return buf[0];
     } else if (size == 2) {
-        return lduw_p(buf);
+        return lduw_le_p(buf);
     } else if (size == 4) {
-        return ldl_p(buf);
+        return ldl_le_p(buf);
     } else {
         g_assert_not_reached();
     }
@@ -164,9 +164,9 @@ static void raven_io_write(void *opaque, hwaddr addr,
     if (size == 1) {
         buf[0] = val;
     } else if (size == 2) {
-        stw_p(buf, val);
+        stw_le_p(buf, val);
     } else if (size == 4) {
-        stl_p(buf, val);
+        stl_le_p(buf, val);
     } else {
         g_assert_not_reached();
     }

hw/ppc/e500.c

@@ -649,7 +649,7 @@ void ppce500_init(QEMUMachineInitArgs *args, PPCE500Params *params)
         input = (qemu_irq *)env->irq_inputs;
         irqs[i][OPENPIC_OUTPUT_INT] = input[PPCE500_INPUT_INT];
         irqs[i][OPENPIC_OUTPUT_CINT] = input[PPCE500_INPUT_CINT];
-        env->spr[SPR_BOOKE_PIR] = cs->cpu_index = i;
+        env->spr_cb[SPR_BOOKE_PIR].default_value = cs->cpu_index = i;
         env->mpic_iack = MPC8544_CCSRBAR_BASE +
                          MPC8544_MPIC_REGS_OFFSET + 0xa0;
 

hw/ppc/ppc.c

@@ -620,6 +620,13 @@ static void cpu_ppc_tb_start (CPUPPCState *env)
     }
 }
 
+bool ppc_decr_clear_on_delivery(CPUPPCState *env)
+{
+    ppc_tb_t *tb_env = env->tb_env;
+    int flags = PPC_DECR_UNDERFLOW_TRIGGERED | PPC_DECR_UNDERFLOW_LEVEL;
+    return ((tb_env->flags & flags) == PPC_DECR_UNDERFLOW_TRIGGERED);
+}
+
 static inline uint32_t _cpu_ppc_load_decr(CPUPPCState *env, uint64_t next)
 {
     ppc_tb_t *tb_env = env->tb_env;
@@ -677,6 +684,11 @@ static inline void cpu_ppc_decr_excp(PowerPCCPU *cpu)
     ppc_set_irq(cpu, PPC_INTERRUPT_DECR, 1);
 }
 
+static inline void cpu_ppc_decr_lower(PowerPCCPU *cpu)
+{
+    ppc_set_irq(cpu, PPC_INTERRUPT_DECR, 0);
+}
+
 static inline void cpu_ppc_hdecr_excp(PowerPCCPU *cpu)
 {
     /* Raise it */
@@ -684,11 +696,16 @@ static inline void cpu_ppc_hdecr_excp(PowerPCCPU *cpu)
     ppc_set_irq(cpu, PPC_INTERRUPT_HDECR, 1);
 }
 
+static inline void cpu_ppc_hdecr_lower(PowerPCCPU *cpu)
+{
+    ppc_set_irq(cpu, PPC_INTERRUPT_HDECR, 0);
+}
+
 static void __cpu_ppc_store_decr(PowerPCCPU *cpu, uint64_t *nextp,
                                  QEMUTimer *timer,
-                                 void (*raise_excp)(PowerPCCPU *),
+                                 void (*raise_excp)(void *),
-                                 uint32_t decr, uint32_t value,
+                                 void (*lower_excp)(PowerPCCPU *),
-                                 int is_excp)
+                                 uint32_t decr, uint32_t value)
 {
     CPUPPCState *env = &cpu->env;
     ppc_tb_t *tb_env = env->tb_env;
@@ -702,59 +719,74 @@ static void __cpu_ppc_store_decr(PowerPCCPU *cpu, uint64_t *nextp,
         return;
     }
 
+    /*
+     * Going from 2 -> 1, 1 -> 0 or 0 -> -1 is the event to generate a DEC
+     * interrupt.
+     *
+     * If we get a really small DEC value, we can assume that by the time we
+     * handled it we should inject an interrupt already.
+     *
+     * On MSB level based DEC implementations the MSB always means the interrupt
+     * is pending, so raise it on those.
+     *
+     * On MSB edge based DEC implementations the MSB going from 0 -> 1 triggers
+     * an edge interrupt, so raise it here too.
+     */
+    if ((value < 3) ||
+        ((tb_env->flags & PPC_DECR_UNDERFLOW_LEVEL) && (value & 0x80000000)) ||
+        ((tb_env->flags & PPC_DECR_UNDERFLOW_TRIGGERED) && (value & 0x80000000)
+          && !(decr & 0x80000000))) {
+        (*raise_excp)(cpu);
+        return;
+    }
+
+    /* On MSB level based systems a 0 for the MSB stops interrupt delivery */
+    if (!(value & 0x80000000) && (tb_env->flags & PPC_DECR_UNDERFLOW_LEVEL)) {
+        (*lower_excp)(cpu);
+    }
+
+    /* Calculate the next timer event */
     now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
     next = now + muldiv64(value, get_ticks_per_sec(), tb_env->decr_freq);
-    if (is_excp) {
-        next += *nextp - now;
-    }
-    if (next == now) {
-        next++;
-    }
     *nextp = next;
+
     /* Adjust timer */
     timer_mod(timer, next);
-
-    /* If we set a negative value and the decrementer was positive, raise an
-     * exception.
-     */
-    if ((tb_env->flags & PPC_DECR_UNDERFLOW_TRIGGERED)
-        && (value & 0x80000000)
-        && !(decr & 0x80000000)) {
-        (*raise_excp)(cpu);
-    }
 }
 
 static inline void _cpu_ppc_store_decr(PowerPCCPU *cpu, uint32_t decr,
-                                       uint32_t value, int is_excp)
+                                       uint32_t value)
 {
     ppc_tb_t *tb_env = cpu->env.tb_env;
 
     __cpu_ppc_store_decr(cpu, &tb_env->decr_next, tb_env->decr_timer,
-                         &cpu_ppc_decr_excp, decr, value, is_excp);
+                         tb_env->decr_timer->cb, &cpu_ppc_decr_lower, decr,
+                         value);
 }
 
 void cpu_ppc_store_decr (CPUPPCState *env, uint32_t value)
 {
     PowerPCCPU *cpu = ppc_env_get_cpu(env);
 
-    _cpu_ppc_store_decr(cpu, cpu_ppc_load_decr(env), value, 0);
+    _cpu_ppc_store_decr(cpu, cpu_ppc_load_decr(env), value);
 }
 
 static void cpu_ppc_decr_cb(void *opaque)
 {
     PowerPCCPU *cpu = opaque;
 
-    _cpu_ppc_store_decr(cpu, 0x00000000, 0xFFFFFFFF, 1);
+    cpu_ppc_decr_excp(cpu);
 }
 
 static inline void _cpu_ppc_store_hdecr(PowerPCCPU *cpu, uint32_t hdecr,
-                                        uint32_t value, int is_excp)
+                                        uint32_t value)
 {
     ppc_tb_t *tb_env = cpu->env.tb_env;
 
     if (tb_env->hdecr_timer != NULL) {
         __cpu_ppc_store_decr(cpu, &tb_env->hdecr_next, tb_env->hdecr_timer,
-                             &cpu_ppc_hdecr_excp, hdecr, value, is_excp);
+                             tb_env->hdecr_timer->cb, &cpu_ppc_hdecr_lower,
+                             hdecr, value);
     }
 }
 
@@ -762,14 +794,14 @@ void cpu_ppc_store_hdecr (CPUPPCState *env, uint32_t value)
 {
     PowerPCCPU *cpu = ppc_env_get_cpu(env);
 
-    _cpu_ppc_store_hdecr(cpu, cpu_ppc_load_hdecr(env), value, 0);
+    _cpu_ppc_store_hdecr(cpu, cpu_ppc_load_hdecr(env), value);
 }
 
 static void cpu_ppc_hdecr_cb(void *opaque)
 {
     PowerPCCPU *cpu = opaque;
 
-    _cpu_ppc_store_hdecr(cpu, 0x00000000, 0xFFFFFFFF, 1);
+    cpu_ppc_hdecr_excp(cpu);
 }
 
 static void cpu_ppc_store_purr(PowerPCCPU *cpu, uint64_t value)
@@ -792,8 +824,8 @@ static void cpu_ppc_set_tb_clk (void *opaque, uint32_t freq)
      * if a decrementer exception is pending when it enables msr_ee at startup,
      * it's not ready to handle it...
      */
-    _cpu_ppc_store_decr(cpu, 0xFFFFFFFF, 0xFFFFFFFF, 0);
+    _cpu_ppc_store_decr(cpu, 0xFFFFFFFF, 0xFFFFFFFF);
-    _cpu_ppc_store_hdecr(cpu, 0xFFFFFFFF, 0xFFFFFFFF, 0);
+    _cpu_ppc_store_hdecr(cpu, 0xFFFFFFFF, 0xFFFFFFFF);
     cpu_ppc_store_purr(cpu, 0x0000000000000000ULL);
 }
 
@@ -806,6 +838,10 @@ clk_setup_cb cpu_ppc_tb_init (CPUPPCState *env, uint32_t freq)
     tb_env = g_malloc0(sizeof(ppc_tb_t));
     env->tb_env = tb_env;
     tb_env->flags = PPC_DECR_UNDERFLOW_TRIGGERED;
+    if (env->insns_flags & PPC_SEGMENT_64B) {
+        /* All Book3S 64bit CPUs implement level based DEC logic */
+        tb_env->flags |= PPC_DECR_UNDERFLOW_LEVEL;
+    }
     /* Create new timer */
     tb_env->decr_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, &cpu_ppc_decr_cb, cpu);
     if (0) {

hw/ppc/ppce500_spin.c

@@ -65,9 +65,9 @@ static void spin_reset(void *opaque)
     for (i = 0; i < MAX_CPUS; i++) {
         SpinInfo *info = &s->spin[i];
 
-        info->pir = i;
+        stl_p(&info->pir, i);
-        info->r3 = i;
+        stq_p(&info->r3, i);
-        info->addr = 1;
+        stq_p(&info->addr, 1);
     }
 }
 

hw/scsi/scsi-bus.c

@@ -101,7 +101,6 @@ static void scsi_dma_restart_bh(void *opaque)
                 scsi_req_continue(req);
                 break;
             case SCSI_XFER_NONE:
-                assert(!req->sg);
                 scsi_req_dequeue(req);
                 scsi_req_enqueue(req);
                 break;