input: map INPUT_BUTTON_WHEEL_{UP,DOWN} to legacy input z axis moves.

Unbreaks mouse wheel.

Reported-by: BALATON Zoltan <balaton@eik.bme.hu>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>

.gitignore

@@ -66,6 +66,9 @@ libuser
 *.cp
 *.dvi
 *.exe
+*.dll
+*.so
+*.mo
 *.fn
 *.ky
 *.log

MAINTAINERS

@@ -726,7 +726,7 @@ F: vl.c
 
 Human Monitor (HMP)
 M: Luiz Capitulino <lcapitulino@redhat.com>
-S: Supported
+S: Maintained
 F: monitor.c
 F: hmp.c
 F: hmp-commands.hx
@@ -758,7 +758,7 @@ T: git git://github.com/bonzini/qemu.git nbd-next
 QAPI
 M: Luiz Capitulino <lcapitulino@redhat.com>
 M: Michael Roth <mdroth@linux.vnet.ibm.com>
-S: Supported
+S: Maintained
 F: qapi/
 T: git git://repo.or.cz/qemu/qmp-unstable.git queue/qmp
 
@@ -772,7 +772,7 @@ T: git git://repo.or.cz/qemu/qmp-unstable.git queue/qmp
 
 QMP
 M: Luiz Capitulino <lcapitulino@redhat.com>
-S: Supported
+S: Maintained
 F: qmp.c
 F: monitor.c
 F: qmp-commands.hx

Makefile

@@ -127,13 +127,29 @@ defconfig:
 
 ifneq ($(wildcard config-host.mak),)
 include $(SRC_PATH)/Makefile.objs
+endif
+
+dummy := $(call unnest-vars,, \
+                stub-obj-y \
+                util-obj-y \
+                qga-obj-y \
+                block-obj-y \
+                block-obj-m \
+                common-obj-y \
+                common-obj-m)
+
+ifneq ($(wildcard config-host.mak),)
 include $(SRC_PATH)/tests/Makefile
 endif
 ifeq ($(CONFIG_SMARTCARD_NSS),y)
 include $(SRC_PATH)/libcacard/Makefile
 endif
 
-all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all
+all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all modules
+
+vl.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
+
+vl.o: QEMU_CFLAGS+=$(SDL_CFLAGS)
 
 config-host.h: config-host.h-timestamp
 config-host.h-timestamp: config-host.mak
@@ -143,6 +159,7 @@ qemu-options.def: $(SRC_PATH)/qemu-options.hx
 SUBDIR_RULES=$(patsubst %,subdir-%, $(TARGET_DIRS))
 SOFTMMU_SUBDIR_RULES=$(filter %-softmmu,$(SUBDIR_RULES))
 
+$(SOFTMMU_SUBDIR_RULES): $(block-obj-y)
 $(SOFTMMU_SUBDIR_RULES): config-all-devices.mak
 
 subdir-%:
@@ -192,6 +209,9 @@ Makefile: $(version-obj-y) $(version-lobj-y)
 libqemustub.a: $(stub-obj-y)
 libqemuutil.a: $(util-obj-y) qapi-types.o qapi-visit.o
 
+block-modules = $(foreach o,$(block-obj-m),"$(basename $(subst /,-,$o))",) NULL
+util/module.o-cflags = -D'CONFIG_BLOCK_MODULES=$(block-modules)'
+
 ######################################################################
 
 qemu-img.o: qemu-img-cmds.h
@@ -247,6 +267,8 @@ clean:
 	rm -f qemu-options.def
 	find . -name '*.[oda]' -type f -exec rm -f {} +
 	find . -name '*.l[oa]' -type f -exec rm -f {} +
+	find . -name '*$(DSOSUF)' -type f -exec rm -f {} +
+	find . -name '*.mo' -type f -exec rm -f {} +
 	rm -f $(filter-out %.tlb,$(TOOLS)) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
 	rm -f fsdev/*.pod
 	rm -rf .libs */.libs
@@ -298,7 +320,7 @@ ifdef INSTALL_BLOBS
 BLOBS=bios.bin bios-256k.bin sgabios.bin vgabios.bin vgabios-cirrus.bin \
 vgabios-stdvga.bin vgabios-vmware.bin vgabios-qxl.bin \
 acpi-dsdt.aml q35-acpi-dsdt.aml \
-ppc_rom.bin openbios-sparc32 openbios-sparc64 openbios-ppc QEMU,tcx.bin \
+ppc_rom.bin openbios-sparc32 openbios-sparc64 openbios-ppc QEMU,tcx.bin QEMU,cgthree.bin \
 pxe-e1000.rom pxe-eepro100.rom pxe-ne2k_pci.rom \
 pxe-pcnet.rom pxe-rtl8139.rom pxe-virtio.rom \
 efi-e1000.rom efi-eepro100.rom efi-ne2k_pci.rom \
@@ -354,6 +376,12 @@ install-datadir install-localstatedir
 ifneq ($(TOOLS),)
 	$(INSTALL_PROG) $(STRIP_OPT) $(TOOLS) "$(DESTDIR)$(bindir)"
 endif
+ifneq ($(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//\//-}"; \
+	done
+endif
 ifneq ($(HELPERS-y),)
 	$(INSTALL_DIR) "$(DESTDIR)$(libexecdir)"
 	$(INSTALL_PROG) $(STRIP_OPT) $(HELPERS-y) "$(DESTDIR)$(libexecdir)"
@@ -371,7 +399,7 @@ endif
 		$(INSTALL_DATA) $(SRC_PATH)/pc-bios/keymaps/$$x "$(DESTDIR)$(qemu_datadir)/keymaps"; \
 	done
 	for d in $(TARGET_DIRS); do \
-	$(MAKE) -C $$d $@ || exit 1 ; \
+	$(MAKE) $(SUBDIR_MAKEFLAGS) TARGET_DIR=$$d/ -C $$d $@ || exit 1 ; \
         done
 
 # various test targets

Makefile.objs

@@ -19,11 +19,8 @@ block-obj-y += qemu-coroutine.o qemu-coroutine-lock.o qemu-coroutine-io.o
 block-obj-y += qemu-coroutine-sleep.o
 block-obj-y += coroutine-$(CONFIG_COROUTINE_BACKEND).o
 
-ifeq ($(CONFIG_VIRTIO)$(CONFIG_VIRTFS)$(CONFIG_PCI),yyy)
+block-obj-m = block/
-# Lots of the fsdev/9pcode is pulled in by vl.c via qemu_fsdev_add.
+
-# only pull in the actual virtio-9p device if we also enabled virtio.
-CONFIG_REALLY_VIRTFS=y
-endif
 
 ######################################################################
 # smartcard
@@ -41,7 +38,7 @@ libcacard-y += libcacard/vcardt.o
 # single QEMU executable should support all CPUs and machines.
 
 ifeq ($(CONFIG_SOFTMMU),y)
-common-obj-y = $(block-obj-y) blockdev.o blockdev-nbd.o block/
+common-obj-y = blockdev.o blockdev-nbd.o block/
 common-obj-y += net/
 common-obj-y += qdev-monitor.o device-hotplug.o
 common-obj-$(CONFIG_WIN32) += os-win32.o
@@ -111,18 +108,3 @@ version-lobj-$(CONFIG_WIN32) += $(BUILD_DIR)/version.lo
 # by libqemuutil.a.  These should be moved to a separate .json schema.
 qga-obj-y = qga/ qapi-types.o qapi-visit.o
 qga-vss-dll-obj-y = qga/
-
-vl.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
-
-vl.o: QEMU_CFLAGS+=$(SDL_CFLAGS)
-
-QEMU_CFLAGS+=$(GLIB_CFLAGS)
-
-nested-vars += \
-	stub-obj-y \
-	util-obj-y \
-	qga-obj-y \
-	qga-vss-dll-obj-y \
-	block-obj-y \
-	common-obj-y
-dummy := $(call unnest-vars)

Makefile.target

@@ -130,8 +130,6 @@ else
 obj-y += hw/$(TARGET_BASE_ARCH)/
 endif
 
-main.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
-
 GENERATED_HEADERS += hmp-commands.h qmp-commands-old.h
 
 endif # CONFIG_SOFTMMU
@@ -139,13 +137,26 @@ endif # CONFIG_SOFTMMU
 # Workaround for http://gcc.gnu.org/PR55489, see configure.
 %/translate.o: QEMU_CFLAGS += $(TRANSLATE_OPT_CFLAGS)
 
-nested-vars += obj-y
+dummy := $(call unnest-vars,,obj-y)
 
-# This resolves all nested paths, so it must come last
+# we are making another call to unnest-vars with different vars, protect obj-y,
+# it can be overriden in subdir Makefile.objs
+obj-y-save := $(obj-y)
+
+block-obj-y :=
+common-obj-y :=
 include $(SRC_PATH)/Makefile.objs
+dummy := $(call unnest-vars,.., \
+               block-obj-y \
+               block-obj-m \
+               common-obj-y \
+               common-obj-m)
 
-all-obj-y = $(obj-y)
+# Now restore obj-y
-all-obj-y += $(addprefix ../, $(common-obj-y))
+obj-y := $(obj-y-save)
+
+all-obj-y = $(obj-y) $(common-obj-y)
+all-obj-$(CONFIG_SOFTMMU) += $(block-obj-y)
 
 ifndef CONFIG_HAIKU
 LIBS+=-lm

arch_init.c

@@ -122,7 +122,6 @@ static void check_guest_throttling(void);
 #define RAM_SAVE_FLAG_XBZRLE   0x40
 /* 0x80 is reserved in migration.h start with 0x100 next */
 
-
 static struct defconfig_file {
     const char *filename;
     /* Indicates it is an user config file (disabled by -no-user-config) */
@@ -133,6 +132,7 @@ static struct defconfig_file {
     { NULL }, /* end of list */
 };
 
+static const uint8_t ZERO_TARGET_PAGE[TARGET_PAGE_SIZE];
 
 int qemu_read_default_config_files(bool userconfig)
 {
@@ -273,6 +273,34 @@ static size_t save_block_hdr(QEMUFile *f, RAMBlock *block, ram_addr_t offset,
     return size;
 }
 
+/* This is the last block that we have visited serching for dirty pages
+ */
+static RAMBlock *last_seen_block;
+/* This is the last block from where we have sent data */
+static RAMBlock *last_sent_block;
+static ram_addr_t last_offset;
+static unsigned long *migration_bitmap;
+static uint64_t migration_dirty_pages;
+static uint32_t last_version;
+static bool ram_bulk_stage;
+
+/* Update the xbzrle cache to reflect a page that's been sent as all 0.
+ * The important thing is that a stale (not-yet-0'd) page be replaced
+ * by the new data.
+ * As a bonus, if the page wasn't in the cache it gets added so that
+ * when a small write is made into the 0'd page it gets XBZRLE sent
+ */
+static void xbzrle_cache_zero_page(ram_addr_t current_addr)
+{
+    if (ram_bulk_stage || !migrate_use_xbzrle()) {
+        return;
+    }
+
+    /* We don't care if this fails to allocate a new cache page
+     * as long as it updated an old one */
+    cache_insert(XBZRLE.cache, current_addr, ZERO_TARGET_PAGE);
+}
+
 #define ENCODING_FLAG_XBZRLE 0x1
 
 static int save_xbzrle_page(QEMUFile *f, uint8_t *current_data,
@@ -329,18 +357,6 @@ static int save_xbzrle_page(QEMUFile *f, uint8_t *current_data,
     return bytes_sent;
 }
 
-
-/* This is the last block that we have visited serching for dirty pages
- */
-static RAMBlock *last_seen_block;
-/* This is the last block from where we have sent data */
-static RAMBlock *last_sent_block;
-static ram_addr_t last_offset;
-static unsigned long *migration_bitmap;
-static uint64_t migration_dirty_pages;
-static uint32_t last_version;
-static bool ram_bulk_stage;
-
 static inline
 ram_addr_t migration_bitmap_find_and_reset_dirty(MemoryRegion *mr,
                                                  ram_addr_t start)
@@ -512,6 +528,7 @@ static int ram_save_block(QEMUFile *f, bool last_stage)
         } else {
             int ret;
             uint8_t *p;
+            bool send_async = true;
             int cont = (block == last_sent_block) ?
                 RAM_SAVE_FLAG_CONTINUE : 0;
 
@@ -522,6 +539,7 @@ static int ram_save_block(QEMUFile *f, bool last_stage)
             ret = ram_control_save_page(f, block->offset,
                                offset, TARGET_PAGE_SIZE, &bytes_sent);
 
+            current_addr = block->offset + offset;
             if (ret != RAM_SAVE_CONTROL_NOT_SUPP) {
                 if (ret != RAM_SAVE_CONTROL_DELAYED) {
                     if (bytes_sent > 0) {
@@ -536,19 +554,35 @@ static int ram_save_block(QEMUFile *f, bool last_stage)
                                             RAM_SAVE_FLAG_COMPRESS);
                 qemu_put_byte(f, 0);
                 bytes_sent++;
+                /* Must let xbzrle know, otherwise a previous (now 0'd) cached
+                 * page would be stale
+                 */
+                xbzrle_cache_zero_page(current_addr);
             } else if (!ram_bulk_stage && migrate_use_xbzrle()) {
-                current_addr = block->offset + offset;
                 bytes_sent = save_xbzrle_page(f, p, current_addr, block,
                                               offset, cont, last_stage);
                 if (!last_stage) {
+                    /* We must send exactly what's in the xbzrle cache
+                     * even if the page wasn't xbzrle compressed, so that
+                     * it's right next time.
+                     */
                     p = get_cached_data(XBZRLE.cache, current_addr);
+
+                    /* Can't send this cached data async, since the cache page
+                     * might get updated before it gets to the wire
+                     */
+                    send_async = false;
                 }
             }
 
             /* XBZRLE overflow or normal page */
             if (bytes_sent == -1) {
                 bytes_sent = save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_PAGE);
-                qemu_put_buffer_async(f, p, TARGET_PAGE_SIZE);
+                if (send_async) {
+                    qemu_put_buffer_async(f, p, TARGET_PAGE_SIZE);
+                } else {
+                    qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
+                }
                 bytes_sent += TARGET_PAGE_SIZE;
                 acct_info.norm_pages++;
             }

backends/baum.c

@@ -566,7 +566,7 @@ CharDriverState *chr_baum_init(void)
     BaumDriverState *baum;
     CharDriverState *chr;
     brlapi_handle_t *handle;
-#ifdef CONFIG_SDL
+#if defined(CONFIG_SDL) && SDL_COMPILEDVERSION < SDL_VERSIONNUM(2, 0, 0)
     SDL_SysWMinfo info;
 #endif
     int tty;
@@ -595,7 +595,7 @@ CharDriverState *chr_baum_init(void)
         goto fail;
     }
 
-#ifdef CONFIG_SDL
+#if defined(CONFIG_SDL) && SDL_COMPILEDVERSION < SDL_VERSIONNUM(2, 0, 0)
     memset(&info, 0, sizeof(info));
     SDL_VERSION(&info.version);
     if (SDL_GetWMInfo(&info))

block.c

@@ -547,8 +547,9 @@ int get_tmp_filename(char *filename, int size)
     int fd;
     const char *tmpdir;
     tmpdir = getenv("TMPDIR");
-    if (!tmpdir)
+    if (!tmpdir) {
-        tmpdir = "/tmp";
+        tmpdir = "/var/tmp";
+    }
     if (snprintf(filename, size, "%s/vl.XXXXXX", tmpdir) >= size) {
         return -EOVERFLOW;
     }
@@ -934,7 +935,7 @@ 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);
+    assert((bs->request_alignment != 0) || bs->sg);
 
 #ifndef _WIN32
     if (bs->is_temporary) {
@@ -955,53 +956,27 @@ free_and_fail:
 /*
  * Opens a file using a protocol (file, host_device, nbd, ...)
  *
- * options is a QDict of options to pass to the block drivers, or NULL for an
+ * options is an indirect pointer to a QDict of options to pass to the block
- * empty set of options. The reference to the QDict belongs to the block layer
+ * drivers, or pointer to NULL for an empty set of options. If this function
- * after the call (even on failure), so if the caller intends to reuse the
+ * takes ownership of the QDict reference, it will set *options to NULL;
- * dictionary, it needs to use QINCREF() before calling bdrv_file_open.
+ * otherwise, it will contain unused/unrecognized options after this function
+ * returns. Then, the caller is responsible for freeing it. If it intends to
+ * reuse the QDict, QINCREF() should be called beforehand.
  */
-int bdrv_file_open(BlockDriverState **pbs, const char *filename,
+static int bdrv_file_open(BlockDriverState *bs, const char *filename,
-                   const char *reference, QDict *options, int flags,
+                          QDict **options, int flags, Error **errp)
-                   Error **errp)
 {
-    BlockDriverState *bs = NULL;
     BlockDriver *drv;
     const char *drvname;
     bool allow_protocol_prefix = false;
     Error *local_err = NULL;
     int ret;
 
-    /* NULL means an empty set of options */
-    if (options == NULL) {
-        options = qdict_new();
-    }
-
-    if (reference) {
-        if (filename || qdict_size(options)) {
-            error_setg(errp, "Cannot reference an existing block device with "
-                       "additional options or a new filename");
-            return -EINVAL;
-        }
-        QDECREF(options);
-
-        bs = bdrv_lookup_bs(reference, reference, errp);
-        if (!bs) {
-            return -ENODEV;
-        }
-        bdrv_ref(bs);
-        *pbs = bs;
-        return 0;
-    }
-
-    bs = bdrv_new("");
-    bs->options = options;
-    options = qdict_clone_shallow(options);
-
     /* Fetch the file name from the options QDict if necessary */
     if (!filename) {
-        filename = qdict_get_try_str(options, "filename");
+        filename = qdict_get_try_str(*options, "filename");
-    } else if (filename && !qdict_haskey(options, "filename")) {
+    } else if (filename && !qdict_haskey(*options, "filename")) {
-        qdict_put(options, "filename", qstring_from_str(filename));
+        qdict_put(*options, "filename", qstring_from_str(filename));
         allow_protocol_prefix = true;
     } else {
         error_setg(errp, "Can't specify 'file' and 'filename' options at the "
@@ -1011,13 +986,13 @@ int bdrv_file_open(BlockDriverState **pbs, const char *filename,
     }
 
     /* Find the right block driver */
-    drvname = qdict_get_try_str(options, "driver");
+    drvname = qdict_get_try_str(*options, "driver");
     if (drvname) {
         drv = bdrv_find_format(drvname);
         if (!drv) {
             error_setg(errp, "Unknown driver '%s'", drvname);
         }
-        qdict_del(options, "driver");
+        qdict_del(*options, "driver");
     } else if (filename) {
         drv = bdrv_find_protocol(filename, allow_protocol_prefix);
         if (!drv) {
@@ -1036,46 +1011,35 @@ int bdrv_file_open(BlockDriverState **pbs, const char *filename,
 
     /* Parse the filename and open it */
     if (drv->bdrv_parse_filename && filename) {
-        drv->bdrv_parse_filename(filename, options, &local_err);
+        drv->bdrv_parse_filename(filename, *options, &local_err);
         if (local_err) {
             error_propagate(errp, local_err);
             ret = -EINVAL;
             goto fail;
         }
-        qdict_del(options, "filename");
+
+        if (!drv->bdrv_needs_filename) {
+            qdict_del(*options, "filename");
+        } else {
+            filename = qdict_get_str(*options, "filename");
+        }
     }
 
     if (!drv->bdrv_file_open) {
-        ret = bdrv_open(bs, filename, options, flags, drv, &local_err);
+        ret = bdrv_open(&bs, filename, NULL, *options, flags, drv, &local_err);
-        options = NULL;
+        *options = NULL;
     } else {
-        ret = bdrv_open_common(bs, NULL, options, flags, drv, &local_err);
+        ret = bdrv_open_common(bs, NULL, *options, flags, drv, &local_err);
     }
     if (ret < 0) {
         error_propagate(errp, local_err);
         goto fail;
     }
 
-    /* Check if any unknown options were used */
-    if (options && (qdict_size(options) != 0)) {
-        const QDictEntry *entry = qdict_first(options);
-        error_setg(errp, "Block protocol '%s' doesn't support the option '%s'",
-                   drv->format_name, entry->key);
-        ret = -EINVAL;
-        goto fail;
-    }
-    QDECREF(options);
-
     bs->growable = 1;
-    *pbs = bs;
     return 0;
 
 fail:
-    QDECREF(options);
-    if (!bs->drv) {
-        QDECREF(bs->options);
-    }
-    bdrv_unref(bs);
     return ret;
 }
 
@@ -1115,8 +1079,6 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
                                        sizeof(backing_filename));
     }
 
-    bs->backing_hd = bdrv_new("");
-
     if (bs->backing_format[0] != '\0') {
         back_drv = bdrv_find_format(bs->backing_format);
     }
@@ -1125,11 +1087,11 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
     back_flags = bs->open_flags & ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT |
                                     BDRV_O_COPY_ON_READ);
 
-    ret = bdrv_open(bs->backing_hd,
+    assert(bs->backing_hd == NULL);
-                    *backing_filename ? backing_filename : NULL, options,
+    ret = bdrv_open(&bs->backing_hd,
+                    *backing_filename ? backing_filename : NULL, NULL, options,
                     back_flags, back_drv, &local_err);
     if (ret < 0) {
-        bdrv_unref(bs->backing_hd);
         bs->backing_hd = NULL;
         bs->open_flags |= BDRV_O_NO_BACKING;
         error_setg(errp, "Could not open backing file: %s",
@@ -1153,10 +1115,6 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
  * Opens a disk image whose options are given as BlockdevRef in another block
  * device's options.
  *
- * If force_raw is true, bdrv_file_open() will be used, thereby preventing any
- * image format auto-detection. If it is false and a filename is given,
- * bdrv_open() will be used for auto-detection.
- *
  * If allow_none is true, no image will be opened if filename is false and no
  * BlockdevRef is given. *pbs will remain unchanged and 0 will be returned.
  *
@@ -1166,16 +1124,21 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
  * BlockdevRef.
  *
  * The BlockdevRef will be removed from the options QDict.
+ *
+ * To conform with the behavior of bdrv_open(), *pbs has to be NULL.
  */
 int bdrv_open_image(BlockDriverState **pbs, const char *filename,
                     QDict *options, const char *bdref_key, int flags,
-                    bool force_raw, bool allow_none, Error **errp)
+                    bool allow_none, Error **errp)
 {
     QDict *image_options;
     int ret;
     char *bdref_key_dot;
     const char *reference;
 
+    assert(pbs);
+    assert(*pbs == NULL);
+
     bdref_key_dot = g_strdup_printf("%s.", bdref_key);
     qdict_extract_subqdict(options, &image_options, bdref_key_dot);
     g_free(bdref_key_dot);
@@ -1192,30 +1155,7 @@ int bdrv_open_image(BlockDriverState **pbs, const char *filename,
         goto done;
     }
 
-    if (filename && !force_raw) {
+    ret = bdrv_open(pbs, filename, reference, image_options, flags, NULL, errp);
-        /* If a filename is given and the block driver should be detected
-           automatically (instead of using none), use bdrv_open() in order to do
-           that auto-detection. */
-        BlockDriverState *bs;
-
-        if (reference) {
-            error_setg(errp, "Cannot reference an existing block device while "
-                       "giving a filename");
-            ret = -EINVAL;
-            goto done;
-        }
-
-        bs = bdrv_new("");
-        ret = bdrv_open(bs, filename, image_options, flags, NULL, errp);
-        if (ret < 0) {
-            bdrv_unref(bs);
-        } else {
-            *pbs = bs;
-        }
-    } else {
-        ret = bdrv_file_open(pbs, filename, reference, image_options, flags,
-                             errp);
-    }
 
 done:
     qdict_del(options, bdref_key);
@@ -1229,17 +1169,58 @@ done:
  * empty set of options. The reference to the QDict belongs to the block layer
  * after the call (even on failure), so if the caller intends to reuse the
  * dictionary, it needs to use QINCREF() before calling bdrv_open.
+ *
+ * If *pbs is NULL, a new BDS will be created with a pointer to it stored there.
+ * If it is not NULL, the referenced BDS will be reused.
+ *
+ * The reference parameter may be used to specify an existing block device which
+ * should be opened. If specified, neither options nor a filename may be given,
+ * nor can an existing BDS be reused (that is, *pbs has to be NULL).
  */
-int bdrv_open(BlockDriverState *bs, const char *filename, QDict *options,
+int bdrv_open(BlockDriverState **pbs, const char *filename,
-              int flags, BlockDriver *drv, Error **errp)
+              const char *reference, QDict *options, int flags,
+              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;
+    BlockDriverState *file = NULL, *bs;
     const char *drvname;
     Error *local_err = NULL;
 
+    assert(pbs);
+
+    if (reference) {
+        bool options_non_empty = options ? qdict_size(options) : false;
+        QDECREF(options);
+
+        if (*pbs) {
+            error_setg(errp, "Cannot reuse an existing BDS when referencing "
+                       "another block device");
+            return -EINVAL;
+        }
+
+        if (filename || options_non_empty) {
+            error_setg(errp, "Cannot reference an existing block device with "
+                       "additional options or a new filename");
+            return -EINVAL;
+        }
+
+        bs = bdrv_lookup_bs(reference, reference, errp);
+        if (!bs) {
+            return -ENODEV;
+        }
+        bdrv_ref(bs);
+        *pbs = bs;
+        return 0;
+    }
+
+    if (*pbs) {
+        bs = *pbs;
+    } else {
+        bs = bdrv_new("");
+    }
+
     /* NULL means an empty set of options */
     if (options == NULL) {
         options = qdict_new();
@@ -1248,6 +1229,20 @@ int bdrv_open(BlockDriverState *bs, const char *filename, QDict *options,
     bs->options = options;
     options = qdict_clone_shallow(options);
 
+    if (flags & BDRV_O_PROTOCOL) {
+        assert(!drv);
+        ret = bdrv_file_open(bs, filename, &options, flags & ~BDRV_O_PROTOCOL,
+                             &local_err);
+        if (!ret) {
+            drv = bs->drv;
+            goto done;
+        } else if (bs->drv) {
+            goto close_and_fail;
+        } else {
+            goto fail;
+        }
+    }
+
     /* For snapshot=on, create a temporary qcow2 overlay */
     if (flags & BDRV_O_SNAPSHOT) {
         BlockDriverState *bs1;
@@ -1260,12 +1255,11 @@ int bdrv_open(BlockDriverState *bs, const char *filename, QDict *options,
            instead of opening 'filename' directly */
 
         /* Get the required size from the image */
-        bs1 = bdrv_new("");
         QINCREF(options);
-        ret = bdrv_open(bs1, filename, options, BDRV_O_NO_BACKING,
+        bs1 = NULL;
+        ret = bdrv_open(&bs1, filename, NULL, options, BDRV_O_NO_BACKING,
                         drv, &local_err);
         if (ret < 0) {
-            bdrv_unref(bs1);
             goto fail;
         }
         total_size = bdrv_getlength(bs1) & BDRV_SECTOR_MASK;
@@ -1322,9 +1316,10 @@ int bdrv_open(BlockDriverState *bs, const char *filename, QDict *options,
         flags |= BDRV_O_ALLOW_RDWR;
     }
 
+    assert(file == NULL);
     ret = bdrv_open_image(&file, filename, options, "file",
-                          bdrv_open_flags(bs, flags | BDRV_O_UNMAP), true, true,
+                          bdrv_open_flags(bs, flags | BDRV_O_UNMAP) |
-                          &local_err);
+                          BDRV_O_PROTOCOL, true, &local_err);
     if (ret < 0) {
         goto fail;
     }
@@ -1377,12 +1372,18 @@ int bdrv_open(BlockDriverState *bs, const char *filename, QDict *options,
         }
     }
 
+done:
     /* Check if any unknown options were used */
-    if (qdict_size(options) != 0) {
+    if (options && (qdict_size(options) != 0)) {
         const QDictEntry *entry = qdict_first(options);
-        error_setg(errp, "Block format '%s' used by device '%s' doesn't "
+        if (flags & BDRV_O_PROTOCOL) {
-                   "support the option '%s'", drv->format_name, bs->device_name,
+            error_setg(errp, "Block protocol '%s' doesn't support the option "
-                   entry->key);
+                       "'%s'", drv->format_name, entry->key);
+        } else {
+            error_setg(errp, "Block format '%s' used by device '%s' doesn't "
+                       "support the option '%s'", drv->format_name,
+                       bs->device_name, entry->key);
+        }
 
         ret = -EINVAL;
         goto close_and_fail;
@@ -1393,6 +1394,7 @@ int bdrv_open(BlockDriverState *bs, const char *filename, QDict *options,
         bdrv_dev_change_media_cb(bs, true);
     }
 
+    *pbs = bs;
     return 0;
 
 unlink_and_fail:
@@ -1406,13 +1408,24 @@ fail:
     QDECREF(bs->options);
     QDECREF(options);
     bs->options = NULL;
+    if (!*pbs) {
+        /* If *pbs is NULL, a new BDS has been created in this function and
+           needs to be freed now. Otherwise, it does not need to be closed,
+           since it has not really been opened yet. */
+        bdrv_unref(bs);
+    }
     if (local_err) {
         error_propagate(errp, local_err);
     }
     return ret;
 
 close_and_fail:
-    bdrv_close(bs);
+    /* See fail path, but now the BDS has to be always closed */
+    if (*pbs) {
+        bdrv_close(bs);
+    } else {
+        bdrv_unref(bs);
+    }
     QDECREF(options);
     if (local_err) {
         error_propagate(errp, local_err);
@@ -1840,11 +1853,6 @@ static void bdrv_move_feature_fields(BlockDriverState *bs_dest,
     pstrcpy(bs_dest->device_name, sizeof(bs_dest->device_name),
             bs_src->device_name);
     bs_dest->device_list = bs_src->device_list;
-
-    /* keep the same entry in graph_bdrv_states
-     * We do want to swap name but don't want to swap linked list entries
-     */
-    bs_dest->node_list   = bs_src->node_list;
 }
 
 /*
@@ -1863,6 +1871,17 @@ void bdrv_swap(BlockDriverState *bs_new, BlockDriverState *bs_old)
 {
     BlockDriverState tmp;
 
+    /* The code needs to swap the node_name but simply swapping node_list won't
+     * work so first remove the nodes from the graph list, do the swap then
+     * insert them back if needed.
+     */
+    if (bs_new->node_name[0] != '\0') {
+        QTAILQ_REMOVE(&graph_bdrv_states, bs_new, node_list);
+    }
+    if (bs_old->node_name[0] != '\0') {
+        QTAILQ_REMOVE(&graph_bdrv_states, bs_old, node_list);
+    }
+
     /* bs_new must be anonymous and shouldn't have anything fancy enabled */
     assert(bs_new->device_name[0] == '\0');
     assert(QLIST_EMPTY(&bs_new->dirty_bitmaps));
@@ -1891,6 +1910,14 @@ void bdrv_swap(BlockDriverState *bs_new, BlockDriverState *bs_old)
     assert(bs_new->io_limits_enabled == false);
     assert(!throttle_have_timer(&bs_new->throttle_state));
 
+    /* insert the nodes back into the graph node list if needed */
+    if (bs_new->node_name[0] != '\0') {
+        QTAILQ_INSERT_TAIL(&graph_bdrv_states, bs_new, node_list);
+    }
+    if (bs_old->node_name[0] != '\0') {
+        QTAILQ_INSERT_TAIL(&graph_bdrv_states, bs_old, node_list);
+    }
+
     bdrv_rebind(bs_new);
     bdrv_rebind(bs_old);
 }
@@ -5290,9 +5317,8 @@ void bdrv_img_create(const char *filename, const char *fmt,
             back_flags =
                 flags & ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING);
 
-            bs = bdrv_new("");
+            bs = NULL;
-
+            ret = bdrv_open(&bs, backing_file->value.s, NULL, NULL, back_flags,
-            ret = bdrv_open(bs, backing_file->value.s, NULL, back_flags,
                             backing_drv, &local_err);
             if (ret < 0) {
                 error_setg_errno(errp, -ret, "Could not open '%s': %s",
@@ -5300,7 +5326,6 @@ void bdrv_img_create(const char *filename, const char *fmt,
                                  error_get_pretty(local_err));
                 error_free(local_err);
                 local_err = NULL;
-                bdrv_unref(bs);
                 goto out;
             }
             bdrv_get_geometry(bs, &size);
@@ -5416,11 +5441,7 @@ bool bdrv_is_first_non_filter(BlockDriverState *candidate)
     QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
         bool perm;
 
-        if (!bs->file) {
+        perm = bdrv_recurse_is_first_non_filter(bs, candidate);
-            continue;
-        }
-
-        perm = bdrv_recurse_is_first_non_filter(bs->file, candidate);
 
         /* candidate is the first non filter */
         if (perm) {

block/Makefile.objs

@@ -3,6 +3,7 @@ block-obj-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-c
 block-obj-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
 block-obj-y += qed-check.o
 block-obj-$(CONFIG_VHDX) += vhdx.o vhdx-endian.o vhdx-log.o
+block-obj-$(CONFIG_QUORUM) += quorum.o
 block-obj-y += parallels.o blkdebug.o blkverify.o
 block-obj-y += snapshot.o qapi.o
 block-obj-$(CONFIG_WIN32) += raw-win32.o win32-aio.o
@@ -24,4 +25,15 @@ common-obj-y += commit.o
 common-obj-y += mirror.o
 common-obj-y += backup.o
 
-$(obj)/curl.o: QEMU_CFLAGS+=$(CURL_CFLAGS)
+iscsi.o-cflags     := $(LIBISCSI_CFLAGS)
+iscsi.o-libs       := $(LIBISCSI_LIBS)
+curl.o-cflags      := $(CURL_CFLAGS)
+curl.o-libs        := $(CURL_LIBS)
+rbd.o-cflags       := $(RBD_CFLAGS)
+rbd.o-libs         := $(RBD_LIBS)
+gluster.o-cflags   := $(GLUSTERFS_CFLAGS)
+gluster.o-libs     := $(GLUSTERFS_LIBS)
+ssh.o-cflags       := $(LIBSSH2_CFLAGS)
+ssh.o-libs         := $(LIBSSH2_LIBS)
+qcow.o-libs        := -lz
+linux-aio.o-libs   := -laio

block/blkdebug.c

@@ -410,8 +410,9 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
     s->state = 1;
 
     /* Open the backing file */
+    assert(bs->file == NULL);
     ret = bdrv_open_image(&bs->file, qemu_opt_get(opts, "x-image"), options, "image",
-                          flags, true, false, &local_err);
+                          flags | BDRV_O_PROTOCOL, false, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
         goto out;

block/blkverify.c

@@ -135,16 +135,18 @@ static int blkverify_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     /* Open the raw file */
+    assert(bs->file == NULL);
     ret = bdrv_open_image(&bs->file, qemu_opt_get(opts, "x-raw"), options,
-                          "raw", flags, true, false, &local_err);
+                          "raw", flags | BDRV_O_PROTOCOL, false, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
         goto fail;
     }
 
     /* Open the test file */
+    assert(s->test_file == NULL);
     ret = bdrv_open_image(&s->test_file, qemu_opt_get(opts, "x-image"), options,
-                          "test", flags, false, false, &local_err);
+                          "test", flags, false, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
         s->test_file = NULL;
@@ -171,110 +173,6 @@ static int64_t blkverify_getlength(BlockDriverState *bs)
     return bdrv_getlength(s->test_file);
 }
 
-/**
- * Check that I/O vector contents are identical
- *
- * @a:          I/O vector
- * @b:          I/O vector
- * @ret:        Offset to first mismatching byte or -1 if match
- */
-static ssize_t blkverify_iovec_compare(QEMUIOVector *a, QEMUIOVector *b)
-{
-    int i;
-    ssize_t offset = 0;
-
-    assert(a->niov == b->niov);
-    for (i = 0; i < a->niov; i++) {
-        size_t len = 0;
-        uint8_t *p = (uint8_t *)a->iov[i].iov_base;
-        uint8_t *q = (uint8_t *)b->iov[i].iov_base;
-
-        assert(a->iov[i].iov_len == b->iov[i].iov_len);
-        while (len < a->iov[i].iov_len && *p++ == *q++) {
-            len++;
-        }
-
-        offset += len;
-
-        if (len != a->iov[i].iov_len) {
-            return offset;
-        }
-    }
-    return -1;
-}
-
-typedef struct {
-    int src_index;
-    struct iovec *src_iov;
-    void *dest_base;
-} IOVectorSortElem;
-
-static int sortelem_cmp_src_base(const void *a, const void *b)
-{
-    const IOVectorSortElem *elem_a = a;
-    const IOVectorSortElem *elem_b = b;
-
-    /* Don't overflow */
-    if (elem_a->src_iov->iov_base < elem_b->src_iov->iov_base) {
-        return -1;
-    } else if (elem_a->src_iov->iov_base > elem_b->src_iov->iov_base) {
-        return 1;
-    } else {
-        return 0;
-    }
-}
-
-static int sortelem_cmp_src_index(const void *a, const void *b)
-{
-    const IOVectorSortElem *elem_a = a;
-    const IOVectorSortElem *elem_b = b;
-
-    return elem_a->src_index - elem_b->src_index;
-}
-
-/**
- * Copy contents of I/O vector
- *
- * The relative relationships of overlapping iovecs are preserved.  This is
- * necessary to ensure identical semantics in the cloned I/O vector.
- */
-static void blkverify_iovec_clone(QEMUIOVector *dest, const QEMUIOVector *src,
-                                  void *buf)
-{
-    IOVectorSortElem sortelems[src->niov];
-    void *last_end;
-    int i;
-
-    /* Sort by source iovecs by base address */
-    for (i = 0; i < src->niov; i++) {
-        sortelems[i].src_index = i;
-        sortelems[i].src_iov = &src->iov[i];
-    }
-    qsort(sortelems, src->niov, sizeof(sortelems[0]), sortelem_cmp_src_base);
-
-    /* Allocate buffer space taking into account overlapping iovecs */
-    last_end = NULL;
-    for (i = 0; i < src->niov; i++) {
-        struct iovec *cur = sortelems[i].src_iov;
-        ptrdiff_t rewind = 0;
-
-        /* Detect overlap */
-        if (last_end && last_end > cur->iov_base) {
-            rewind = last_end - cur->iov_base;
-        }
-
-        sortelems[i].dest_base = buf - rewind;
-        buf += cur->iov_len - MIN(rewind, cur->iov_len);
-        last_end = MAX(cur->iov_base + cur->iov_len, last_end);
-    }
-
-    /* Sort by source iovec index and build destination iovec */
-    qsort(sortelems, src->niov, sizeof(sortelems[0]), sortelem_cmp_src_index);
-    for (i = 0; i < src->niov; i++) {
-        qemu_iovec_add(dest, sortelems[i].dest_base, src->iov[i].iov_len);
-    }
-}
-
 static BlkverifyAIOCB *blkverify_aio_get(BlockDriverState *bs, bool is_write,
                                          int64_t sector_num, QEMUIOVector *qiov,
                                          int nb_sectors,
@@ -338,7 +236,7 @@ static void blkverify_aio_cb(void *opaque, int ret)
 
 static void blkverify_verify_readv(BlkverifyAIOCB *acb)
 {
-    ssize_t offset = blkverify_iovec_compare(acb->qiov, &acb->raw_qiov);
+    ssize_t offset = qemu_iovec_compare(acb->qiov, &acb->raw_qiov);
     if (offset != -1) {
         blkverify_err(acb, "contents mismatch in sector %" PRId64,
                       acb->sector_num + (int64_t)(offset / BDRV_SECTOR_SIZE));
@@ -356,7 +254,7 @@ static BlockDriverAIOCB *blkverify_aio_readv(BlockDriverState *bs,
     acb->verify = blkverify_verify_readv;
     acb->buf = qemu_blockalign(bs->file, qiov->size);
     qemu_iovec_init(&acb->raw_qiov, acb->qiov->niov);
-    blkverify_iovec_clone(&acb->raw_qiov, qiov, acb->buf);
+    qemu_iovec_clone(&acb->raw_qiov, qiov, acb->buf);
 
     bdrv_aio_readv(s->test_file, sector_num, qiov, nb_sectors,
                    blkverify_aio_cb, acb);

block/bochs.c

@@ -129,7 +129,8 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
         strcmp(bochs.subtype, GROWING_TYPE) ||
 	((le32_to_cpu(bochs.version) != HEADER_VERSION) &&
 	(le32_to_cpu(bochs.version) != HEADER_V1))) {
-        return -EMEDIUMTYPE;
+        error_setg(errp, "Image not in Bochs format");
+        return -EINVAL;
     }
 
     if (le32_to_cpu(bochs.version) == HEADER_V1) {

block/cow.c

@@ -74,7 +74,8 @@ static int cow_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     if (be32_to_cpu(cow_header.magic) != COW_MAGIC) {
-        ret = -EMEDIUMTYPE;
+        error_setg(errp, "Image not in COW format");
+        ret = -EINVAL;
         goto fail;
     }
 
@@ -82,7 +83,7 @@ static int cow_open(BlockDriverState *bs, QDict *options, int flags,
         char version[64];
         snprintf(version, sizeof(version),
                "COW version %d", cow_header.version);
-        qerror_report(QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+        error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
             bs->device_name, "cow", version);
         ret = -ENOTSUP;
         goto fail;
@@ -346,16 +347,15 @@ static int cow_create(const char *filename, QEMUOptionParameter *options,
 
     ret = bdrv_create_file(filename, options, &local_err);
     if (ret < 0) {
-        qerror_report_err(local_err);
+        error_propagate(errp, local_err);
-        error_free(local_err);
         return ret;
     }
 
-    ret = bdrv_file_open(&cow_bs, filename, NULL, NULL, BDRV_O_RDWR,
+    cow_bs = NULL;
-                         &local_err);
+    ret = bdrv_open(&cow_bs, filename, NULL, NULL,
+                    BDRV_O_RDWR | BDRV_O_PROTOCOL, NULL, &local_err);
     if (ret < 0) {
-        qerror_report_err(local_err);
+        error_propagate(errp, local_err);
-        error_free(local_err);
         return ret;
     }
 

block/curl.c

@@ -456,30 +456,27 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
     static int inited = 0;
 
     if (flags & BDRV_O_RDWR) {
-        qerror_report(ERROR_CLASS_GENERIC_ERROR,
+        error_setg(errp, "curl block device does not support writes");
-                      "curl block device does not support writes");
         return -EROFS;
     }
 
     opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (local_err) {
-        qerror_report_err(local_err);
+        error_propagate(errp, local_err);
-        error_free(local_err);
         goto out_noclean;
     }
 
     s->readahead_size = qemu_opt_get_size(opts, "readahead", READ_AHEAD_SIZE);
     if ((s->readahead_size & 0x1ff) != 0) {
-        fprintf(stderr, "HTTP_READAHEAD_SIZE %zd is not a multiple of 512\n",
+        error_setg(errp, "HTTP_READAHEAD_SIZE %zd is not a multiple of 512",
-                s->readahead_size);
+                   s->readahead_size);
         goto out_noclean;
     }
 
     file = qemu_opt_get(opts, "url");
     if (file == NULL) {
-        qerror_report(ERROR_CLASS_GENERIC_ERROR, "curl block driver requires "
+        error_setg(errp, "curl block driver requires an 'url' option");
-                      "an 'url' option");
         goto out_noclean;
     }
 

block/gluster.c

@@ -3,21 +3,12 @@
  *
  * Copyright (C) 2012 Bharata B Rao <bharata@linux.vnet.ibm.com>
  *
- * Pipe handling mechanism in AIO implementation is derived from
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * block/rbd.c. Hence,
+ * See the COPYING file in the top-level directory.
  *
- * Copyright (C) 2010-2011 Christian Brunner <chb@muc.de>,
- *                         Josh Durgin <josh.durgin@dreamhost.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
- * Contributions after 2012-01-13 are licensed under the terms of the
- * GNU GPL, version 2 or (at your option) any later version.
  */
 #include <glusterfs/api/glfs.h>
 #include "block/block_int.h"
-#include "qemu/sockets.h"
 #include "qemu/uri.h"
 
 typedef struct GlusterAIOCB {
@@ -32,9 +23,6 @@ typedef struct BDRVGlusterState {
     struct glfs_fd *fd;
 } BDRVGlusterState;
 
-#define GLUSTER_FD_READ  0
-#define GLUSTER_FD_WRITE 1
-
 typedef struct GlusterConf {
     char *server;
     int port;
@@ -45,11 +33,13 @@ typedef struct GlusterConf {
 
 static void qemu_gluster_gconf_free(GlusterConf *gconf)
 {
-    g_free(gconf->server);
+    if (gconf) {
-    g_free(gconf->volname);
+        g_free(gconf->server);
-    g_free(gconf->image);
+        g_free(gconf->volname);
-    g_free(gconf->transport);
+        g_free(gconf->image);
-    g_free(gconf);
+        g_free(gconf->transport);
+        g_free(gconf);
+    }
 }
 
 static int parse_volume_options(GlusterConf *gconf, char *path)
@@ -127,7 +117,7 @@ static int qemu_gluster_parseuri(GlusterConf *gconf, const char *filename)
     }
 
     /* transport */
-    if (!strcmp(uri->scheme, "gluster")) {
+    if (!uri->scheme || !strcmp(uri->scheme, "gluster")) {
         gconf->transport = g_strdup("tcp");
     } else if (!strcmp(uri->scheme, "gluster+tcp")) {
         gconf->transport = g_strdup("tcp");
@@ -163,7 +153,7 @@ static int qemu_gluster_parseuri(GlusterConf *gconf, const char *filename)
         }
         gconf->server = g_strdup(qp->p[0].value);
     } else {
-        gconf->server = g_strdup(uri->server);
+        gconf->server = g_strdup(uri->server ? uri->server : "localhost");
         gconf->port = uri->port;
     }
 
@@ -175,7 +165,8 @@ out:
     return ret;
 }
 
-static struct glfs *qemu_gluster_init(GlusterConf *gconf, const char *filename)
+static struct glfs *qemu_gluster_init(GlusterConf *gconf, const char *filename,
+                                      Error **errp)
 {
     struct glfs *glfs = NULL;
     int ret;
@@ -183,8 +174,8 @@ static struct glfs *qemu_gluster_init(GlusterConf *gconf, const char *filename)
 
     ret = qemu_gluster_parseuri(gconf, filename);
     if (ret < 0) {
-        error_report("Usage: file=gluster[+transport]://[server[:port]]/"
+        error_setg(errp, "Usage: file=gluster[+transport]://[server[:port]]/"
-            "volname/image[?socket=...]");
+                   "volname/image[?socket=...]");
         errno = -ret;
         goto out;
     }
@@ -211,9 +202,11 @@ static struct glfs *qemu_gluster_init(GlusterConf *gconf, const char *filename)
 
     ret = glfs_init(glfs);
     if (ret) {
-        error_report("Gluster connection failed for server=%s port=%d "
+        error_setg_errno(errp, errno,
-             "volume=%s image=%s transport=%s", gconf->server, gconf->port,
+                         "Gluster connection failed for server=%s port=%d "
-             gconf->volname, gconf->image, gconf->transport);
+                         "volume=%s image=%s transport=%s", gconf->server,
+                         gconf->port, gconf->volname, gconf->image,
+                         gconf->transport);
         goto out;
     }
     return glfs;
@@ -269,11 +262,28 @@ static QemuOptsList runtime_opts = {
     },
 };
 
+static void qemu_gluster_parse_flags(int bdrv_flags, int *open_flags)
+{
+    assert(open_flags != NULL);
+
+    *open_flags |= O_BINARY;
+
+    if (bdrv_flags & BDRV_O_RDWR) {
+        *open_flags |= O_RDWR;
+    } else {
+        *open_flags |= O_RDONLY;
+    }
+
+    if ((bdrv_flags & BDRV_O_NOCACHE)) {
+        *open_flags |= O_DIRECT;
+    }
+}
+
 static int qemu_gluster_open(BlockDriverState *bs,  QDict *options,
                              int bdrv_flags, Error **errp)
 {
     BDRVGlusterState *s = bs->opaque;
-    int open_flags = O_BINARY;
+    int open_flags = 0;
     int ret = 0;
     GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
     QemuOpts *opts;
@@ -283,29 +293,20 @@ static int qemu_gluster_open(BlockDriverState *bs,  QDict *options,
     opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (local_err) {
-        qerror_report_err(local_err);
+        error_propagate(errp, local_err);
-        error_free(local_err);
         ret = -EINVAL;
         goto out;
     }
 
     filename = qemu_opt_get(opts, "filename");
 
-    s->glfs = qemu_gluster_init(gconf, filename);
+    s->glfs = qemu_gluster_init(gconf, filename, errp);
     if (!s->glfs) {
         ret = -errno;
         goto out;
     }
 
-    if (bdrv_flags & BDRV_O_RDWR) {
+    qemu_gluster_parse_flags(bdrv_flags, &open_flags);
-        open_flags |= O_RDWR;
-    } else {
-        open_flags |= O_RDONLY;
-    }
-
-    if ((bdrv_flags & BDRV_O_NOCACHE)) {
-        open_flags |= O_DIRECT;
-    }
 
     s->fd = glfs_open(s->glfs, gconf->image, open_flags);
     if (!s->fd) {
@@ -327,6 +328,96 @@ out:
     return ret;
 }
 
+typedef struct BDRVGlusterReopenState {
+    struct glfs *glfs;
+    struct glfs_fd *fd;
+} BDRVGlusterReopenState;
+
+
+static int qemu_gluster_reopen_prepare(BDRVReopenState *state,
+                                       BlockReopenQueue *queue, Error **errp)
+{
+    int ret = 0;
+    BDRVGlusterReopenState *reop_s;
+    GlusterConf *gconf = NULL;
+    int open_flags = 0;
+
+    assert(state != NULL);
+    assert(state->bs != NULL);
+
+    state->opaque = g_malloc0(sizeof(BDRVGlusterReopenState));
+    reop_s = state->opaque;
+
+    qemu_gluster_parse_flags(state->flags, &open_flags);
+
+    gconf = g_malloc0(sizeof(GlusterConf));
+
+    reop_s->glfs = qemu_gluster_init(gconf, state->bs->filename, errp);
+    if (reop_s->glfs == NULL) {
+        ret = -errno;
+        goto exit;
+    }
+
+    reop_s->fd = glfs_open(reop_s->glfs, gconf->image, open_flags);
+    if (reop_s->fd == NULL) {
+        /* reops->glfs will be cleaned up in _abort */
+        ret = -errno;
+        goto exit;
+    }
+
+exit:
+    /* state->opaque will be freed in either the _abort or _commit */
+    qemu_gluster_gconf_free(gconf);
+    return ret;
+}
+
+static void qemu_gluster_reopen_commit(BDRVReopenState *state)
+{
+    BDRVGlusterReopenState *reop_s = state->opaque;
+    BDRVGlusterState *s = state->bs->opaque;
+
+
+    /* close the old */
+    if (s->fd) {
+        glfs_close(s->fd);
+    }
+    if (s->glfs) {
+        glfs_fini(s->glfs);
+    }
+
+    /* use the newly opened image / connection */
+    s->fd         = reop_s->fd;
+    s->glfs       = reop_s->glfs;
+
+    g_free(state->opaque);
+    state->opaque = NULL;
+
+    return;
+}
+
+
+static void qemu_gluster_reopen_abort(BDRVReopenState *state)
+{
+    BDRVGlusterReopenState *reop_s = state->opaque;
+
+    if (reop_s == NULL) {
+        return;
+    }
+
+    if (reop_s->fd) {
+        glfs_close(reop_s->fd);
+    }
+
+    if (reop_s->glfs) {
+        glfs_fini(reop_s->glfs);
+    }
+
+    g_free(state->opaque);
+    state->opaque = NULL;
+
+    return;
+}
+
 #ifdef CONFIG_GLUSTERFS_ZEROFILL
 static coroutine_fn int qemu_gluster_co_write_zeroes(BlockDriverState *bs,
         int64_t sector_num, int nb_sectors, BdrvRequestFlags flags)
@@ -389,9 +480,9 @@ static int qemu_gluster_create(const char *filename,
     int64_t total_size = 0;
     GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
 
-    glfs = qemu_gluster_init(gconf, filename);
+    glfs = qemu_gluster_init(gconf, filename, errp);
     if (!glfs) {
-        ret = -errno;
+        ret = -EINVAL;
         goto out;
     }
 
@@ -617,6 +708,9 @@ static BlockDriver bdrv_gluster = {
     .instance_size                = sizeof(BDRVGlusterState),
     .bdrv_needs_filename          = true,
     .bdrv_file_open               = qemu_gluster_open,
+    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
+    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
+    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
     .bdrv_close                   = qemu_gluster_close,
     .bdrv_create                  = qemu_gluster_create,
     .bdrv_getlength               = qemu_gluster_getlength,
@@ -641,6 +735,9 @@ static BlockDriver bdrv_gluster_tcp = {
     .instance_size                = sizeof(BDRVGlusterState),
     .bdrv_needs_filename          = true,
     .bdrv_file_open               = qemu_gluster_open,
+    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
+    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
+    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
     .bdrv_close                   = qemu_gluster_close,
     .bdrv_create                  = qemu_gluster_create,
     .bdrv_getlength               = qemu_gluster_getlength,
@@ -665,6 +762,9 @@ static BlockDriver bdrv_gluster_unix = {
     .instance_size                = sizeof(BDRVGlusterState),
     .bdrv_needs_filename          = true,
     .bdrv_file_open               = qemu_gluster_open,
+    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
+    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
+    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
     .bdrv_close                   = qemu_gluster_close,
     .bdrv_create                  = qemu_gluster_create,
     .bdrv_getlength               = qemu_gluster_getlength,
@@ -689,6 +789,9 @@ static BlockDriver bdrv_gluster_rdma = {
     .instance_size                = sizeof(BDRVGlusterState),
     .bdrv_needs_filename          = true,
     .bdrv_file_open               = qemu_gluster_open,
+    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
+    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
+    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
     .bdrv_close                   = qemu_gluster_close,
     .bdrv_create                  = qemu_gluster_create,
     .bdrv_getlength               = qemu_gluster_getlength,

block/iscsi.c

@@ -145,12 +145,13 @@ iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
 
     if (iTask->retries-- > 0 && status == SCSI_STATUS_CHECK_CONDITION
         && task->sense.key == SCSI_SENSE_UNIT_ATTENTION) {
+        error_report("iSCSI CheckCondition: %s", iscsi_get_error(iscsi));
         iTask->do_retry = 1;
         goto out;
     }
 
     if (status != SCSI_STATUS_GOOD) {
-        error_report("iSCSI: Failure. %s", iscsi_get_error(iscsi));
+        error_report("iSCSI Failure: %s", iscsi_get_error(iscsi));
     }
 
 out:
@@ -325,6 +326,7 @@ retry:
     }
 
     if (iTask.do_retry) {
+        iTask.complete = 0;
         goto retry;
     }
 
@@ -399,6 +401,7 @@ retry:
     }
 
     if (iTask.do_retry) {
+        iTask.complete = 0;
         goto retry;
     }
 
@@ -433,6 +436,7 @@ retry:
     }
 
     if (iTask.do_retry) {
+        iTask.complete = 0;
         goto retry;
     }
 
@@ -683,6 +687,7 @@ retry:
             scsi_free_scsi_task(iTask.task);
             iTask.task = NULL;
         }
+        iTask.complete = 0;
         goto retry;
     }
 
@@ -767,6 +772,7 @@ retry:
     }
 
     if (iTask.do_retry) {
+        iTask.complete = 0;
         goto retry;
     }
 
@@ -830,24 +836,26 @@ retry:
         qemu_coroutine_yield();
     }
 
+    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) {
+        /* WRITE SAME is not supported by the target */
+        iscsilun->has_write_same = false;
+        scsi_free_scsi_task(iTask.task);
+        return -ENOTSUP;
+    }
+
     if (iTask.task != NULL) {
         scsi_free_scsi_task(iTask.task);
         iTask.task = NULL;
     }
 
     if (iTask.do_retry) {
+        iTask.complete = 0;
         goto retry;
     }
 
     if (iTask.status != SCSI_STATUS_GOOD) {
-        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) {
-            /* WRITE SAME is not supported by the target */
-            iscsilun->has_write_same = false;
-            return -ENOTSUP;
-        }
-
         return -EIO;
     }
 
@@ -856,7 +864,8 @@ retry:
 
 #endif /* SCSI_SENSE_ASCQ_CAPACITY_DATA_HAS_CHANGED */
 
-static int parse_chap(struct iscsi_context *iscsi, const char *target)
+static void parse_chap(struct iscsi_context *iscsi, const char *target,
+                       Error **errp)
 {
     QemuOptsList *list;
     QemuOpts *opts;
@@ -865,37 +874,35 @@ static int parse_chap(struct iscsi_context *iscsi, const char *target)
 
     list = qemu_find_opts("iscsi");
     if (!list) {
-        return 0;
+        return;
     }
 
     opts = qemu_opts_find(list, target);
     if (opts == NULL) {
         opts = QTAILQ_FIRST(&list->head);
         if (!opts) {
-            return 0;
+            return;
         }
     }
 
     user = qemu_opt_get(opts, "user");
     if (!user) {
-        return 0;
+        return;
     }
 
     password = qemu_opt_get(opts, "password");
     if (!password) {
-        error_report("CHAP username specified but no password was given");
+        error_setg(errp, "CHAP username specified but no password was given");
-        return -1;
+        return;
     }
 
     if (iscsi_set_initiator_username_pwd(iscsi, user, password)) {
-        error_report("Failed to set initiator username and password");
+        error_setg(errp, "Failed to set initiator username and password");
-        return -1;
     }
-
-    return 0;
 }
 
-static void parse_header_digest(struct iscsi_context *iscsi, const char *target)
+static void parse_header_digest(struct iscsi_context *iscsi, const char *target,
+                                Error **errp)
 {
     QemuOptsList *list;
     QemuOpts *opts;
@@ -928,7 +935,7 @@ static void parse_header_digest(struct iscsi_context *iscsi, const char *target)
     } else if (!strcmp(digest, "NONE-CRC32C")) {
         iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_NONE_CRC32C);
     } else {
-        error_report("Invalid header-digest setting : %s", digest);
+        error_setg(errp, "Invalid header-digest setting : %s", digest);
     }
 }
 
@@ -986,12 +993,11 @@ static void iscsi_nop_timed_event(void *opaque)
 }
 #endif
 
-static int iscsi_readcapacity_sync(IscsiLun *iscsilun)
+static void iscsi_readcapacity_sync(IscsiLun *iscsilun, Error **errp)
 {
     struct scsi_task *task = NULL;
     struct scsi_readcapacity10 *rc10 = NULL;
     struct scsi_readcapacity16 *rc16 = NULL;
-    int ret = 0;
     int retries = ISCSI_CMD_RETRIES; 
 
     do {
@@ -1006,8 +1012,7 @@ static int iscsi_readcapacity_sync(IscsiLun *iscsilun)
             if (task != NULL && task->status == SCSI_STATUS_GOOD) {
                 rc16 = scsi_datain_unmarshall(task);
                 if (rc16 == NULL) {
-                    error_report("iSCSI: Failed to unmarshall readcapacity16 data.");
+                    error_setg(errp, "iSCSI: Failed to unmarshall readcapacity16 data.");
-                    ret = -EINVAL;
                 } else {
                     iscsilun->block_size = rc16->block_length;
                     iscsilun->num_blocks = rc16->returned_lba + 1;
@@ -1021,8 +1026,7 @@ static int iscsi_readcapacity_sync(IscsiLun *iscsilun)
             if (task != NULL && task->status == SCSI_STATUS_GOOD) {
                 rc10 = scsi_datain_unmarshall(task);
                 if (rc10 == NULL) {
-                    error_report("iSCSI: Failed to unmarshall readcapacity10 data.");
+                    error_setg(errp, "iSCSI: Failed to unmarshall readcapacity10 data.");
-                    ret = -EINVAL;
                 } else {
                     iscsilun->block_size = rc10->block_size;
                     if (rc10->lba == 0) {
@@ -1035,20 +1039,18 @@ static int iscsi_readcapacity_sync(IscsiLun *iscsilun)
             }
             break;
         default:
-            return 0;
+            return;
         }
     } while (task != NULL && task->status == SCSI_STATUS_CHECK_CONDITION
              && task->sense.key == SCSI_SENSE_UNIT_ATTENTION
              && retries-- > 0);
 
     if (task == NULL || task->status != SCSI_STATUS_GOOD) {
-        error_report("iSCSI: failed to send readcapacity10 command.");
+        error_setg(errp, "iSCSI: failed to send readcapacity10 command.");
-        ret = -EINVAL;
     }
     if (task) {
         scsi_free_scsi_task(task);
     }
-    return ret;
 }
 
 /* TODO Convert to fine grained options */
@@ -1065,35 +1067,41 @@ static QemuOptsList runtime_opts = {
     },
 };
 
-static struct scsi_task *iscsi_do_inquiry(struct iscsi_context *iscsi,
+static struct scsi_task *iscsi_do_inquiry(struct iscsi_context *iscsi, int lun,
-                                          int lun, int evpd, int pc) {
+                                          int evpd, int pc, void **inq, Error **errp)
-        int full_size;
+{
-        struct scsi_task *task = NULL;
+    int full_size;
-        task = iscsi_inquiry_sync(iscsi, lun, evpd, pc, 64);
+    struct scsi_task *task = NULL;
+    task = iscsi_inquiry_sync(iscsi, lun, evpd, pc, 64);
+    if (task == NULL || task->status != SCSI_STATUS_GOOD) {
+        goto fail;
+    }
+    full_size = scsi_datain_getfullsize(task);
+    if (full_size > task->datain.size) {
+        scsi_free_scsi_task(task);
+
+        /* we need more data for the full list */
+        task = iscsi_inquiry_sync(iscsi, lun, evpd, pc, full_size);
         if (task == NULL || task->status != SCSI_STATUS_GOOD) {
             goto fail;
         }
-        full_size = scsi_datain_getfullsize(task);
+    }
-        if (full_size > task->datain.size) {
-            scsi_free_scsi_task(task);
 
-            /* we need more data for the full list */
+    *inq = scsi_datain_unmarshall(task);
-            task = iscsi_inquiry_sync(iscsi, lun, evpd, pc, full_size);
+    if (*inq == NULL) {
-            if (task == NULL || task->status != SCSI_STATUS_GOOD) {
+        error_setg(errp, "iSCSI: failed to unmarshall inquiry datain blob");
-                goto fail;
+        goto fail;
-            }
+    }
-        }
 
-        return task;
+    return task;
 
 fail:
-        error_report("iSCSI: Inquiry command failed : %s",
+    error_setg(errp, "iSCSI: Inquiry command failed : %s",
-                     iscsi_get_error(iscsi));
+               iscsi_get_error(iscsi));
-        if (task) {
+    if (task != NULL) {
-            scsi_free_scsi_task(task);
+        scsi_free_scsi_task(task);
-            return NULL;
+    }
-        }
+    return NULL;
-        return NULL;
 }
 
 /*
@@ -1112,34 +1120,33 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
     struct iscsi_url *iscsi_url = NULL;
     struct scsi_task *task = NULL;
     struct scsi_inquiry_standard *inq = NULL;
+    struct scsi_inquiry_supported_pages *inq_vpd;
     char *initiator_name = NULL;
     QemuOpts *opts;
     Error *local_err = NULL;
     const char *filename;
-    int ret;
+    int i, ret;
 
     if ((BDRV_SECTOR_SIZE % 512) != 0) {
-        error_report("iSCSI: Invalid BDRV_SECTOR_SIZE. "
+        error_setg(errp, "iSCSI: Invalid BDRV_SECTOR_SIZE. "
-                     "BDRV_SECTOR_SIZE(%lld) is not a multiple "
+                   "BDRV_SECTOR_SIZE(%lld) is not a multiple "
-                     "of 512", BDRV_SECTOR_SIZE);
+                   "of 512", BDRV_SECTOR_SIZE);
         return -EINVAL;
     }
 
     opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (local_err) {
-        qerror_report_err(local_err);
+        error_propagate(errp, local_err);
-        error_free(local_err);
         ret = -EINVAL;
         goto out;
     }
 
     filename = qemu_opt_get(opts, "filename");
 
-
     iscsi_url = iscsi_parse_full_url(iscsi, filename);
     if (iscsi_url == NULL) {
-        error_report("Failed to parse URL : %s", filename);
+        error_setg(errp, "Failed to parse URL : %s", filename);
         ret = -EINVAL;
         goto out;
     }
@@ -1150,13 +1157,13 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
 
     iscsi = iscsi_create_context(initiator_name);
     if (iscsi == NULL) {
-        error_report("iSCSI: Failed to create iSCSI context.");
+        error_setg(errp, "iSCSI: Failed to create iSCSI context.");
         ret = -ENOMEM;
         goto out;
     }
 
     if (iscsi_set_targetname(iscsi, iscsi_url->target)) {
-        error_report("iSCSI: Failed to set target name.");
+        error_setg(errp, "iSCSI: Failed to set target name.");
         ret = -EINVAL;
         goto out;
     }
@@ -1165,21 +1172,22 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
         ret = iscsi_set_initiator_username_pwd(iscsi, iscsi_url->user,
                                               iscsi_url->passwd);
         if (ret != 0) {
-            error_report("Failed to set initiator username and password");
+            error_setg(errp, "Failed to set initiator username and password");
             ret = -EINVAL;
             goto out;
         }
     }
 
     /* check if we got CHAP username/password via the options */
-    if (parse_chap(iscsi, iscsi_url->target) != 0) {
+    parse_chap(iscsi, iscsi_url->target, &local_err);
-        error_report("iSCSI: Failed to set CHAP user/password");
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
         ret = -EINVAL;
         goto out;
     }
 
     if (iscsi_set_session_type(iscsi, ISCSI_SESSION_NORMAL) != 0) {
-        error_report("iSCSI: Failed to set session type to normal.");
+        error_setg(errp, "iSCSI: Failed to set session type to normal.");
         ret = -EINVAL;
         goto out;
     }
@@ -1187,10 +1195,15 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
     iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_NONE_CRC32C);
 
     /* check if we got HEADER_DIGEST via the options */
-    parse_header_digest(iscsi, iscsi_url->target);
+    parse_header_digest(iscsi, iscsi_url->target, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
+        goto out;
+    }
 
     if (iscsi_full_connect_sync(iscsi, iscsi_url->portal, iscsi_url->lun) != 0) {
-        error_report("iSCSI: Failed to connect to LUN : %s",
+        error_setg(errp, "iSCSI: Failed to connect to LUN : %s",
             iscsi_get_error(iscsi));
         ret = -EINVAL;
         goto out;
@@ -1198,79 +1211,76 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
 
     iscsilun->iscsi = iscsi;
     iscsilun->lun   = iscsi_url->lun;
-
-    task = iscsi_inquiry_sync(iscsi, iscsilun->lun, 0, 0, 36);
-
-    if (task == NULL || task->status != SCSI_STATUS_GOOD) {
-        error_report("iSCSI: failed to send inquiry command.");
-        ret = -EINVAL;
-        goto out;
-    }
-
-    inq = scsi_datain_unmarshall(task);
-    if (inq == NULL) {
-        error_report("iSCSI: Failed to unmarshall inquiry data.");
-        ret = -EINVAL;
-        goto out;
-    }
-
-    iscsilun->type = inq->periperal_device_type;
     iscsilun->has_write_same = true;
 
-    if ((ret = iscsi_readcapacity_sync(iscsilun)) != 0) {
+    task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 0, 0,
+                            (void **) &inq, errp);
+    if (task == NULL) {
+        ret = -EINVAL;
+        goto out;
+    }
+    iscsilun->type = inq->periperal_device_type;
+    scsi_free_scsi_task(task);
+    task = NULL;
+
+    iscsi_readcapacity_sync(iscsilun, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
         goto out;
     }
     bs->total_sectors = sector_lun2qemu(iscsilun->num_blocks, iscsilun);
     bs->request_alignment = iscsilun->block_size;
 
-    /* Medium changer or tape. We dont have any emulation for this so this must
+    /* We don't have any emulation for devices other than disks and CD-ROMs, so
-     * be sg ioctl compatible. We force it to be sg, otherwise qemu will try
+     * this must be sg ioctl compatible. We force it to be sg, otherwise qemu
-     * to read from the device to guess the image format.
+     * will try to read from the device to guess the image format.
      */
-    if (iscsilun->type == TYPE_MEDIUM_CHANGER ||
+    if (iscsilun->type != TYPE_DISK && iscsilun->type != TYPE_ROM) {
-        iscsilun->type == TYPE_TAPE) {
         bs->sg = 1;
     }
 
-    if (iscsilun->lbpme) {
+    task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 1,
+                            SCSI_INQUIRY_PAGECODE_SUPPORTED_VPD_PAGES,
+                            (void **) &inq_vpd, errp);
+    if (task == NULL) {
+        ret = -EINVAL;
+        goto out;
+    }
+    for (i = 0; i < inq_vpd->num_pages; i++) {
+        struct scsi_task *inq_task;
         struct scsi_inquiry_logical_block_provisioning *inq_lbp;
-        task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 1,
-                                SCSI_INQUIRY_PAGECODE_LOGICAL_BLOCK_PROVISIONING);
-        if (task == NULL) {
-            ret = -EINVAL;
-            goto out;
-        }
-        inq_lbp = scsi_datain_unmarshall(task);
-        if (inq_lbp == NULL) {
-            error_report("iSCSI: failed to unmarshall inquiry datain blob");
-            ret = -EINVAL;
-            goto out;
-        }
-        memcpy(&iscsilun->lbp, inq_lbp,
-               sizeof(struct scsi_inquiry_logical_block_provisioning));
-        scsi_free_scsi_task(task);
-        task = NULL;
-    }
-
-    if (iscsilun->lbp.lbpu || iscsilun->lbp.lbpws) {
         struct scsi_inquiry_block_limits *inq_bl;
-        task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 1,
+        switch (inq_vpd->pages[i]) {
-                                SCSI_INQUIRY_PAGECODE_BLOCK_LIMITS);
+        case SCSI_INQUIRY_PAGECODE_LOGICAL_BLOCK_PROVISIONING:
-        if (task == NULL) {
+            inq_task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 1,
-            ret = -EINVAL;
+                                        SCSI_INQUIRY_PAGECODE_LOGICAL_BLOCK_PROVISIONING,
-            goto out;
+                                        (void **) &inq_lbp, errp);
+            if (inq_task == NULL) {
+                ret = -EINVAL;
+                goto out;
+            }
+            memcpy(&iscsilun->lbp, inq_lbp,
+                   sizeof(struct scsi_inquiry_logical_block_provisioning));
+            scsi_free_scsi_task(inq_task);
+            break;
+        case SCSI_INQUIRY_PAGECODE_BLOCK_LIMITS:
+            inq_task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 1,
+                                    SCSI_INQUIRY_PAGECODE_BLOCK_LIMITS,
+                                    (void **) &inq_bl, errp);
+            if (inq_task == NULL) {
+                ret = -EINVAL;
+                goto out;
+            }
+            memcpy(&iscsilun->bl, inq_bl,
+                   sizeof(struct scsi_inquiry_block_limits));
+            scsi_free_scsi_task(inq_task);
+            break;
+        default:
+            break;
         }
-        inq_bl = scsi_datain_unmarshall(task);
-        if (inq_bl == NULL) {
-            error_report("iSCSI: failed to unmarshall inquiry datain blob");
-            ret = -EINVAL;
-            goto out;
-        }
-        memcpy(&iscsilun->bl, inq_bl,
-               sizeof(struct scsi_inquiry_block_limits));
-        scsi_free_scsi_task(task);
-        task = NULL;
     }
+    scsi_free_scsi_task(task);
+    task = NULL;
 
 #if defined(LIBISCSI_FEATURE_NOP_COUNTER)
     /* Set up a timer for sending out iSCSI NOPs */
@@ -1353,14 +1363,16 @@ static int iscsi_reopen_prepare(BDRVReopenState *state,
 static int iscsi_truncate(BlockDriverState *bs, int64_t offset)
 {
     IscsiLun *iscsilun = bs->opaque;
-    int ret = 0;
+    Error *local_err = NULL;
 
     if (iscsilun->type != TYPE_DISK) {
         return -ENOTSUP;
     }
 
-    if ((ret = iscsi_readcapacity_sync(iscsilun)) != 0) {
+    iscsi_readcapacity_sync(iscsilun, &local_err);
-        return ret;
+    if (local_err != NULL) {
+        error_free(local_err);
+        return -EIO;
     }
 
     if (offset > iscsi_getlength(bs)) {

block/mirror.c

@@ -520,9 +520,6 @@ static void mirror_complete(BlockJob *job, Error **errp)
 
     ret = bdrv_open_backing_file(s->target, NULL, &local_err);
     if (ret < 0) {
-        char backing_filename[PATH_MAX];
-        bdrv_get_full_backing_filename(s->target, backing_filename,
-                                       sizeof(backing_filename));
         error_propagate(errp, local_err);
         return;
     }

block/nbd.c

@@ -188,31 +188,28 @@ out:
     g_free(file);
 }
 
-static int nbd_config(BDRVNBDState *s, QDict *options, char **export)
+static void nbd_config(BDRVNBDState *s, QDict *options, char **export,
+                       Error **errp)
 {
     Error *local_err = NULL;
 
-    if (qdict_haskey(options, "path")) {
+    if (qdict_haskey(options, "path") == qdict_haskey(options, "host")) {
-        if (qdict_haskey(options, "host")) {
+        if (qdict_haskey(options, "path")) {
-            qerror_report(ERROR_CLASS_GENERIC_ERROR, "path and host may not "
+            error_setg(errp, "path and host may not be used at the same time.");
-                          "be used at the same time.");
+        } else {
-            return -EINVAL;
+            error_setg(errp, "one of path and host must be specified.");
         }
-        s->client.is_unix = true;
+        return;
-    } else if (qdict_haskey(options, "host")) {
-        s->client.is_unix = false;
-    } else {
-        return -EINVAL;
     }
 
+    s->client.is_unix = qdict_haskey(options, "path");
     s->socket_opts = qemu_opts_create(&socket_optslist, NULL, 0,
                                       &error_abort);
 
     qemu_opts_absorb_qdict(s->socket_opts, options, &local_err);
     if (local_err) {
-        qerror_report_err(local_err);
+        error_propagate(errp, local_err);
-        error_free(local_err);
+        return;
-        return -EINVAL;
     }
 
     if (!qemu_opt_get(s->socket_opts, "port")) {
@@ -223,19 +220,17 @@ static int nbd_config(BDRVNBDState *s, QDict *options, char **export)
     if (*export) {
         qdict_del(options, "export");
     }
-
-    return 0;
 }
 
-static int nbd_establish_connection(BlockDriverState *bs)
+static int nbd_establish_connection(BlockDriverState *bs, Error **errp)
 {
     BDRVNBDState *s = bs->opaque;
     int sock;
 
     if (s->client.is_unix) {
-        sock = unix_socket_outgoing(qemu_opt_get(s->socket_opts, "path"));
+        sock = unix_connect_opts(s->socket_opts, errp, NULL, NULL);
     } else {
-        sock = tcp_socket_outgoing_opts(s->socket_opts);
+        sock = inet_connect_opts(s->socket_opts, errp, NULL, NULL);
         if (sock >= 0) {
             socket_set_nodelay(sock);
         }
@@ -256,17 +251,19 @@ static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
     BDRVNBDState *s = bs->opaque;
     char *export = NULL;
     int result, sock;
+    Error *local_err = NULL;
 
     /* Pop the config into our state object. Exit if invalid. */
-    result = nbd_config(s, options, &export);
+    nbd_config(s, options, &export, &local_err);
-    if (result != 0) {
+    if (local_err) {
-        return result;
+        error_propagate(errp, local_err);
+        return -EINVAL;
     }
 
     /* establish TCP connection, return error if it fails
      * TODO: Configurable retry-until-timeout behaviour.
      */
-    sock = nbd_establish_connection(bs);
+    sock = nbd_establish_connection(bs, errp);
     if (sock < 0) {
         return sock;
     }

block/parallels.c

@@ -85,7 +85,8 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
 
     if (memcmp(ph.magic, HEADER_MAGIC, 16) ||
         (le32_to_cpu(ph.version) != HEADER_VERSION)) {
-        ret = -EMEDIUMTYPE;
+        error_setg(errp, "Image not in Parallels format");
+        ret = -EINVAL;
         goto fail;
     }
 

block/qcow.c

@@ -113,23 +113,26 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
     be64_to_cpus(&header.l1_table_offset);
 
     if (header.magic != QCOW_MAGIC) {
-        ret = -EMEDIUMTYPE;
+        error_setg(errp, "Image not in qcow format");
+        ret = -EINVAL;
         goto fail;
     }
     if (header.version != QCOW_VERSION) {
         char version[64];
         snprintf(version, sizeof(version), "QCOW version %d", header.version);
-        qerror_report(QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+        error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
-            bs->device_name, "qcow", version);
+                  bs->device_name, "qcow", version);
         ret = -ENOTSUP;
         goto fail;
     }
 
     if (header.size <= 1 || header.cluster_bits < 9) {
+        error_setg(errp, "invalid value in qcow header");
         ret = -EINVAL;
         goto fail;
     }
     if (header.crypt_method > QCOW_CRYPT_AES) {
+        error_setg(errp, "invalid encryption method in qcow header");
         ret = -EINVAL;
         goto fail;
     }
@@ -686,16 +689,15 @@ static int qcow_create(const char *filename, QEMUOptionParameter *options,
 
     ret = bdrv_create_file(filename, options, &local_err);
     if (ret < 0) {
-        qerror_report_err(local_err);
+        error_propagate(errp, local_err);
-        error_free(local_err);
         return ret;
     }
 
-    ret = bdrv_file_open(&qcow_bs, filename, NULL, NULL, BDRV_O_RDWR,
+    qcow_bs = NULL;
-                         &local_err);
+    ret = bdrv_open(&qcow_bs, filename, NULL, NULL,
+                    BDRV_O_RDWR | BDRV_O_PROTOCOL, NULL, &local_err);
     if (ret < 0) {
-        qerror_report_err(local_err);
+        error_propagate(errp, local_err);
-        error_free(local_err);
         return ret;
     }
 

block/qcow2-cluster.c

@@ -1367,13 +1367,31 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
         uint64_t old_offset;
 
         old_offset = be64_to_cpu(l2_table[l2_index + i]);
-        if ((old_offset & L2E_OFFSET_MASK) == 0) {
+
+        /*
+         * Make sure that a discarded area reads back as zeroes for v3 images
+         * (we cannot do it for v2 without actually writing a zero-filled
+         * buffer). We can skip the operation if the cluster is already marked
+         * as zero, or if it's unallocated and we don't have a backing file.
+         *
+         * 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) {
+            continue;
+        }
+
+        if ((old_offset & L2E_OFFSET_MASK) == 0 && !bs->backing_hd) {
             continue;
         }
 
         /* First remove L2 entries */
         qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
-        l2_table[l2_index + i] = cpu_to_be64(0);
+        if (s->qcow_version >= 3) {
+            l2_table[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO);
+        } else {
+            l2_table[l2_index + i] = cpu_to_be64(0);
+        }
 
         /* Then decrease the refcount */
         qcow2_free_any_clusters(bs, old_offset, 1, type);

block/qcow2.c

@@ -449,7 +449,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
 
     if (header.magic != QCOW_MAGIC) {
         error_setg(errp, "Image is not in qcow2 format");
-        ret = -EMEDIUMTYPE;
+        ret = -EINVAL;
         goto fail;
     }
     if (header.version < 2 || header.version > 3) {
@@ -1493,7 +1493,9 @@ static int qcow2_create2(const char *filename, int64_t total_size,
         return ret;
     }
 
-    ret = bdrv_file_open(&bs, filename, NULL, NULL, BDRV_O_RDWR, &local_err);
+    bs = NULL;
+    ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
+                    NULL, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
         return ret;
@@ -1543,7 +1545,8 @@ static int qcow2_create2(const char *filename, int64_t total_size,
         goto out;
     }
 
-    bdrv_close(bs);
+    bdrv_unref(bs);
+    bs = NULL;
 
     /*
      * And now open the image and make it consistent first (i.e. increase the
@@ -1552,7 +1555,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
      */
     BlockDriver* drv = bdrv_find_format("qcow2");
     assert(drv != NULL);
-    ret = bdrv_open(bs, filename, NULL,
+    ret = bdrv_open(&bs, filename, NULL, NULL,
         BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH, drv, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
@@ -1599,10 +1602,11 @@ static int qcow2_create2(const char *filename, int64_t total_size,
         }
     }
 
-    bdrv_close(bs);
+    bdrv_unref(bs);
+    bs = NULL;
 
     /* Reopen the image without BDRV_O_NO_FLUSH to flush it before returning */
-    ret = bdrv_open(bs, filename, NULL,
+    ret = bdrv_open(&bs, filename, NULL, NULL,
                     BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_BACKING,
                     drv, &local_err);
     if (local_err) {
@@ -1612,7 +1616,9 @@ static int qcow2_create2(const char *filename, int64_t total_size,
 
     ret = 0;
 out:
-    bdrv_unref(bs);
+    if (bs) {
+        bdrv_unref(bs);
+    }
     return ret;
 }
 

block/qed.c

@@ -391,14 +391,15 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
     qed_header_le_to_cpu(&le_header, &s->header);
 
     if (s->header.magic != QED_MAGIC) {
-        return -EMEDIUMTYPE;
+        error_setg(errp, "Image not in QED format");
+        return -EINVAL;
     }
     if (s->header.features & ~QED_FEATURE_MASK) {
         /* image uses unsupported feature bits */
         char buf[64];
         snprintf(buf, sizeof(buf), "%" PRIx64,
             s->header.features & ~QED_FEATURE_MASK);
-        qerror_report(QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+        error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
             bs->device_name, "QED", buf);
         return -ENOTSUP;
     }
@@ -545,7 +546,8 @@ static void bdrv_qed_close(BlockDriverState *bs)
 
 static int qed_create(const char *filename, uint32_t cluster_size,
                       uint64_t image_size, uint32_t table_size,
-                      const char *backing_file, const char *backing_fmt)
+                      const char *backing_file, const char *backing_fmt,
+                      Error **errp)
 {
     QEDHeader header = {
         .magic = QED_MAGIC,
@@ -562,20 +564,20 @@ static int qed_create(const char *filename, uint32_t cluster_size,
     size_t l1_size = header.cluster_size * header.table_size;
     Error *local_err = NULL;
     int ret = 0;
-    BlockDriverState *bs = NULL;
+    BlockDriverState *bs;
 
     ret = bdrv_create_file(filename, NULL, &local_err);
     if (ret < 0) {
-        qerror_report_err(local_err);
+        error_propagate(errp, local_err);
-        error_free(local_err);
         return ret;
     }
 
-    ret = bdrv_file_open(&bs, filename, NULL, NULL,
+    bs = NULL;
-                         BDRV_O_RDWR | BDRV_O_CACHE_WB, &local_err);
+    ret = bdrv_open(&bs, filename, NULL, NULL,
+                    BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL, NULL,
+                    &local_err);
     if (ret < 0) {
-        qerror_report_err(local_err);
+        error_propagate(errp, local_err);
-        error_free(local_err);
         return ret;
     }
 
@@ -665,7 +667,7 @@ static int bdrv_qed_create(const char *filename, QEMUOptionParameter *options,
     }
 
     return qed_create(filename, cluster_size, image_size, table_size,
-                      backing_file, backing_fmt);
+                      backing_file, backing_fmt, errp);
 }
 
 typedef struct {

block/quorum.c

@@ -0,0 +1,873 @@
+/*
+ * Quorum Block filter
+ *
+ * Copyright (C) 2012-2014 Nodalink, EURL.
+ *
+ * Author:
+ *   Benoît Canet <benoit.canet@irqsave.net>
+ *
+ * Based on the design and code of blkverify.c (Copyright (C) 2010 IBM, Corp)
+ * and blkmirror.c (Copyright (C) 2011 Red Hat, Inc).
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include <gnutls/gnutls.h>
+#include <gnutls/crypto.h>
+#include "block/block_int.h"
+#include "qapi/qmp/qjson.h"
+
+#define HASH_LENGTH 32
+
+#define QUORUM_OPT_VOTE_THRESHOLD "vote-threshold"
+#define QUORUM_OPT_BLKVERIFY      "blkverify"
+
+/* This union holds a vote hash value */
+typedef union QuorumVoteValue {
+    char h[HASH_LENGTH];       /* SHA-256 hash */
+    int64_t l;                 /* simpler 64 bits hash */
+} QuorumVoteValue;
+
+/* A vote item */
+typedef struct QuorumVoteItem {
+    int index;
+    QLIST_ENTRY(QuorumVoteItem) next;
+} QuorumVoteItem;
+
+/* this structure is a vote version. A version is the set of votes sharing the
+ * same vote value.
+ * The set of votes will be tracked with the items field and its cardinality is
+ * vote_count.
+ */
+typedef struct QuorumVoteVersion {
+    QuorumVoteValue value;
+    int index;
+    int vote_count;
+    QLIST_HEAD(, QuorumVoteItem) items;
+    QLIST_ENTRY(QuorumVoteVersion) next;
+} QuorumVoteVersion;
+
+/* this structure holds a group of vote versions together */
+typedef struct QuorumVotes {
+    QLIST_HEAD(, QuorumVoteVersion) vote_list;
+    bool (*compare)(QuorumVoteValue *a, QuorumVoteValue *b);
+} QuorumVotes;
+
+/* the following structure holds the state of one quorum instance */
+typedef struct BDRVQuorumState {
+    BlockDriverState **bs; /* children BlockDriverStates */
+    int num_children;      /* children count */
+    int threshold;         /* if less than threshold children reads gave the
+                            * same result a quorum error occurs.
+                            */
+    bool is_blkverify;     /* true if the driver is in blkverify mode
+                            * Writes are mirrored on two children devices.
+                            * On reads the two children devices' contents are
+                            * compared and if a difference is spotted its
+                            * location is printed and the code aborts.
+                            * It is useful to debug other block drivers by
+                            * comparing them with a reference one.
+                            */
+} BDRVQuorumState;
+
+typedef struct QuorumAIOCB QuorumAIOCB;
+
+/* Quorum will create one instance of the following structure per operation it
+ * performs on its children.
+ * So for each read/write operation coming from the upper layer there will be
+ * $children_count QuorumChildRequest.
+ */
+typedef struct QuorumChildRequest {
+    BlockDriverAIOCB *aiocb;
+    QEMUIOVector qiov;
+    uint8_t *buf;
+    int ret;
+    QuorumAIOCB *parent;
+} QuorumChildRequest;
+
+/* Quorum will use the following structure to track progress of each read/write
+ * operation received by the upper layer.
+ * This structure hold pointers to the QuorumChildRequest structures instances
+ * used to do operations on each children and track overall progress.
+ */
+struct QuorumAIOCB {
+    BlockDriverAIOCB common;
+
+    /* Request metadata */
+    uint64_t sector_num;
+    int nb_sectors;
+
+    QEMUIOVector *qiov;         /* calling IOV */
+
+    QuorumChildRequest *qcrs;   /* individual child requests */
+    int count;                  /* number of completed AIOCB */
+    int success_count;          /* number of successfully completed AIOCB */
+
+    QuorumVotes votes;
+
+    bool is_read;
+    int vote_ret;
+};
+
+static void quorum_vote(QuorumAIOCB *acb);
+
+static void quorum_aio_cancel(BlockDriverAIOCB *blockacb)
+{
+    QuorumAIOCB *acb = container_of(blockacb, QuorumAIOCB, common);
+    BDRVQuorumState *s = acb->common.bs->opaque;
+    int i;
+
+    /* cancel all callbacks */
+    for (i = 0; i < s->num_children; i++) {
+        bdrv_aio_cancel(acb->qcrs[i].aiocb);
+    }
+
+    g_free(acb->qcrs);
+    qemu_aio_release(acb);
+}
+
+static AIOCBInfo quorum_aiocb_info = {
+    .aiocb_size         = sizeof(QuorumAIOCB),
+    .cancel             = quorum_aio_cancel,
+};
+
+static void quorum_aio_finalize(QuorumAIOCB *acb)
+{
+    BDRVQuorumState *s = acb->common.bs->opaque;
+    int i, ret = 0;
+
+    if (acb->vote_ret) {
+        ret = acb->vote_ret;
+    }
+
+    acb->common.cb(acb->common.opaque, ret);
+
+    if (acb->is_read) {
+        for (i = 0; i < s->num_children; i++) {
+            qemu_vfree(acb->qcrs[i].buf);
+            qemu_iovec_destroy(&acb->qcrs[i].qiov);
+        }
+    }
+
+    g_free(acb->qcrs);
+    qemu_aio_release(acb);
+}
+
+static bool quorum_sha256_compare(QuorumVoteValue *a, QuorumVoteValue *b)
+{
+    return !memcmp(a->h, b->h, HASH_LENGTH);
+}
+
+static bool quorum_64bits_compare(QuorumVoteValue *a, QuorumVoteValue *b)
+{
+    return a->l == b->l;
+}
+
+static QuorumAIOCB *quorum_aio_get(BDRVQuorumState *s,
+                                   BlockDriverState *bs,
+                                   QEMUIOVector *qiov,
+                                   uint64_t sector_num,
+                                   int nb_sectors,
+                                   BlockDriverCompletionFunc *cb,
+                                   void *opaque)
+{
+    QuorumAIOCB *acb = qemu_aio_get(&quorum_aiocb_info, bs, cb, opaque);
+    int i;
+
+    acb->common.bs->opaque = s;
+    acb->sector_num = sector_num;
+    acb->nb_sectors = nb_sectors;
+    acb->qiov = qiov;
+    acb->qcrs = g_new0(QuorumChildRequest, s->num_children);
+    acb->count = 0;
+    acb->success_count = 0;
+    acb->votes.compare = quorum_sha256_compare;
+    QLIST_INIT(&acb->votes.vote_list);
+    acb->is_read = false;
+    acb->vote_ret = 0;
+
+    for (i = 0; i < s->num_children; i++) {
+        acb->qcrs[i].buf = NULL;
+        acb->qcrs[i].ret = 0;
+        acb->qcrs[i].parent = acb;
+    }
+
+    return acb;
+}
+
+static void quorum_report_bad(QuorumAIOCB *acb, char *node_name, int ret)
+{
+    QObject *data;
+    assert(node_name);
+    data = qobject_from_jsonf("{ 'node-name': %s"
+                              ", 'sector-num': %" PRId64
+                              ", 'sectors-count': %d }",
+                              node_name, acb->sector_num, acb->nb_sectors);
+    if (ret < 0) {
+        QDict *dict = qobject_to_qdict(data);
+        qdict_put(dict, "error", qstring_from_str(strerror(-ret)));
+    }
+    monitor_protocol_event(QEVENT_QUORUM_REPORT_BAD, data);
+    qobject_decref(data);
+}
+
+static void quorum_report_failure(QuorumAIOCB *acb)
+{
+    QObject *data;
+    const char *reference = acb->common.bs->device_name[0] ?
+                            acb->common.bs->device_name :
+                            acb->common.bs->node_name;
+    data = qobject_from_jsonf("{ 'reference': %s"
+                              ", 'sector-num': %" PRId64
+                              ", 'sectors-count': %d }",
+                              reference, acb->sector_num, acb->nb_sectors);
+    monitor_protocol_event(QEVENT_QUORUM_FAILURE, data);
+    qobject_decref(data);
+}
+
+static int quorum_vote_error(QuorumAIOCB *acb);
+
+static bool quorum_has_too_much_io_failed(QuorumAIOCB *acb)
+{
+    BDRVQuorumState *s = acb->common.bs->opaque;
+
+    if (acb->success_count < s->threshold) {
+        acb->vote_ret = quorum_vote_error(acb);
+        quorum_report_failure(acb);
+        return true;
+    }
+
+    return false;
+}
+
+static void quorum_aio_cb(void *opaque, int ret)
+{
+    QuorumChildRequest *sacb = opaque;
+    QuorumAIOCB *acb = sacb->parent;
+    BDRVQuorumState *s = acb->common.bs->opaque;
+
+    sacb->ret = ret;
+    acb->count++;
+    if (ret == 0) {
+        acb->success_count++;
+    } else {
+        quorum_report_bad(acb, sacb->aiocb->bs->node_name, ret);
+    }
+    assert(acb->count <= s->num_children);
+    assert(acb->success_count <= s->num_children);
+    if (acb->count < s->num_children) {
+        return;
+    }
+
+    /* Do the vote on read */
+    if (acb->is_read) {
+        quorum_vote(acb);
+    } else {
+        quorum_has_too_much_io_failed(acb);
+    }
+
+    quorum_aio_finalize(acb);
+}
+
+static void quorum_report_bad_versions(BDRVQuorumState *s,
+                                       QuorumAIOCB *acb,
+                                       QuorumVoteValue *value)
+{
+    QuorumVoteVersion *version;
+    QuorumVoteItem *item;
+
+    QLIST_FOREACH(version, &acb->votes.vote_list, next) {
+        if (acb->votes.compare(&version->value, value)) {
+            continue;
+        }
+        QLIST_FOREACH(item, &version->items, next) {
+            quorum_report_bad(acb, s->bs[item->index]->node_name, 0);
+        }
+    }
+}
+
+static void quorum_copy_qiov(QEMUIOVector *dest, QEMUIOVector *source)
+{
+    int i;
+    assert(dest->niov == source->niov);
+    assert(dest->size == source->size);
+    for (i = 0; i < source->niov; i++) {
+        assert(dest->iov[i].iov_len == source->iov[i].iov_len);
+        memcpy(dest->iov[i].iov_base,
+               source->iov[i].iov_base,
+               source->iov[i].iov_len);
+    }
+}
+
+static void quorum_count_vote(QuorumVotes *votes,
+                              QuorumVoteValue *value,
+                              int index)
+{
+    QuorumVoteVersion *v = NULL, *version = NULL;
+    QuorumVoteItem *item;
+
+    /* look if we have something with this hash */
+    QLIST_FOREACH(v, &votes->vote_list, next) {
+        if (votes->compare(&v->value, value)) {
+            version = v;
+            break;
+        }
+    }
+
+    /* It's a version not yet in the list add it */
+    if (!version) {
+        version = g_new0(QuorumVoteVersion, 1);
+        QLIST_INIT(&version->items);
+        memcpy(&version->value, value, sizeof(version->value));
+        version->index = index;
+        version->vote_count = 0;
+        QLIST_INSERT_HEAD(&votes->vote_list, version, next);
+    }
+
+    version->vote_count++;
+
+    item = g_new0(QuorumVoteItem, 1);
+    item->index = index;
+    QLIST_INSERT_HEAD(&version->items, item, next);
+}
+
+static void quorum_free_vote_list(QuorumVotes *votes)
+{
+    QuorumVoteVersion *version, *next_version;
+    QuorumVoteItem *item, *next_item;
+
+    QLIST_FOREACH_SAFE(version, &votes->vote_list, next, next_version) {
+        QLIST_REMOVE(version, next);
+        QLIST_FOREACH_SAFE(item, &version->items, next, next_item) {
+            QLIST_REMOVE(item, next);
+            g_free(item);
+        }
+        g_free(version);
+    }
+}
+
+static int quorum_compute_hash(QuorumAIOCB *acb, int i, QuorumVoteValue *hash)
+{
+    int j, ret;
+    gnutls_hash_hd_t dig;
+    QEMUIOVector *qiov = &acb->qcrs[i].qiov;
+
+    ret = gnutls_hash_init(&dig, GNUTLS_DIG_SHA256);
+
+    if (ret < 0) {
+        return ret;
+    }
+
+    for (j = 0; j < qiov->niov; j++) {
+        ret = gnutls_hash(dig, qiov->iov[j].iov_base, qiov->iov[j].iov_len);
+        if (ret < 0) {
+            break;
+        }
+    }
+
+    gnutls_hash_deinit(dig, (void *) hash);
+    return ret;
+}
+
+static QuorumVoteVersion *quorum_get_vote_winner(QuorumVotes *votes)
+{
+    int max = 0;
+    QuorumVoteVersion *candidate, *winner = NULL;
+
+    QLIST_FOREACH(candidate, &votes->vote_list, next) {
+        if (candidate->vote_count > max) {
+            max = candidate->vote_count;
+            winner = candidate;
+        }
+    }
+
+    return winner;
+}
+
+/* qemu_iovec_compare is handy for blkverify mode because it returns the first
+ * differing byte location. Yet it is handcoded to compare vectors one byte
+ * after another so it does not benefit from the libc SIMD optimizations.
+ * quorum_iovec_compare is written for speed and should be used in the non
+ * blkverify mode of quorum.
+ */
+static bool quorum_iovec_compare(QEMUIOVector *a, QEMUIOVector *b)
+{
+    int i;
+    int result;
+
+    assert(a->niov == b->niov);
+    for (i = 0; i < a->niov; i++) {
+        assert(a->iov[i].iov_len == b->iov[i].iov_len);
+        result = memcmp(a->iov[i].iov_base,
+                        b->iov[i].iov_base,
+                        a->iov[i].iov_len);
+        if (result) {
+            return false;
+        }
+    }
+
+    return true;
+}
+
+static void GCC_FMT_ATTR(2, 3) quorum_err(QuorumAIOCB *acb,
+                                          const char *fmt, ...)
+{
+    va_list ap;
+
+    va_start(ap, fmt);
+    fprintf(stderr, "quorum: sector_num=%" PRId64 " nb_sectors=%d ",
+            acb->sector_num, acb->nb_sectors);
+    vfprintf(stderr, fmt, ap);
+    fprintf(stderr, "\n");
+    va_end(ap);
+    exit(1);
+}
+
+static bool quorum_compare(QuorumAIOCB *acb,
+                           QEMUIOVector *a,
+                           QEMUIOVector *b)
+{
+    BDRVQuorumState *s = acb->common.bs->opaque;
+    ssize_t offset;
+
+    /* This driver will replace blkverify in this particular case */
+    if (s->is_blkverify) {
+        offset = qemu_iovec_compare(a, b);
+        if (offset != -1) {
+            quorum_err(acb, "contents mismatch in sector %" PRId64,
+                       acb->sector_num +
+                       (uint64_t)(offset / BDRV_SECTOR_SIZE));
+        }
+        return true;
+    }
+
+    return quorum_iovec_compare(a, b);
+}
+
+/* Do a vote to get the error code */
+static int quorum_vote_error(QuorumAIOCB *acb)
+{
+    BDRVQuorumState *s = acb->common.bs->opaque;
+    QuorumVoteVersion *winner = NULL;
+    QuorumVotes error_votes;
+    QuorumVoteValue result_value;
+    int i, ret = 0;
+    bool error = false;
+
+    QLIST_INIT(&error_votes.vote_list);
+    error_votes.compare = quorum_64bits_compare;
+
+    for (i = 0; i < s->num_children; i++) {
+        ret = acb->qcrs[i].ret;
+        if (ret) {
+            error = true;
+            result_value.l = ret;
+            quorum_count_vote(&error_votes, &result_value, i);
+        }
+    }
+
+    if (error) {
+        winner = quorum_get_vote_winner(&error_votes);
+        ret = winner->value.l;
+    }
+
+    quorum_free_vote_list(&error_votes);
+
+    return ret;
+}
+
+static void quorum_vote(QuorumAIOCB *acb)
+{
+    bool quorum = true;
+    int i, j, ret;
+    QuorumVoteValue hash;
+    BDRVQuorumState *s = acb->common.bs->opaque;
+    QuorumVoteVersion *winner;
+
+    if (quorum_has_too_much_io_failed(acb)) {
+        return;
+    }
+
+    /* get the index of the first successful read */
+    for (i = 0; i < s->num_children; i++) {
+        if (!acb->qcrs[i].ret) {
+            break;
+        }
+    }
+
+    assert(i < s->num_children);
+
+    /* compare this read with all other successful reads stopping at quorum
+     * failure
+     */
+    for (j = i + 1; j < s->num_children; j++) {
+        if (acb->qcrs[j].ret) {
+            continue;
+        }
+        quorum = quorum_compare(acb, &acb->qcrs[i].qiov, &acb->qcrs[j].qiov);
+        if (!quorum) {
+            break;
+       }
+    }
+
+    /* Every successful read agrees */
+    if (quorum) {
+        quorum_copy_qiov(acb->qiov, &acb->qcrs[i].qiov);
+        return;
+    }
+
+    /* compute hashes for each successful read, also store indexes */
+    for (i = 0; i < s->num_children; i++) {
+        if (acb->qcrs[i].ret) {
+            continue;
+        }
+        ret = quorum_compute_hash(acb, i, &hash);
+        /* if ever the hash computation failed */
+        if (ret < 0) {
+            acb->vote_ret = ret;
+            goto free_exit;
+        }
+        quorum_count_vote(&acb->votes, &hash, i);
+    }
+
+    /* vote to select the most represented version */
+    winner = quorum_get_vote_winner(&acb->votes);
+
+    /* if the winner count is smaller than threshold the read fails */
+    if (winner->vote_count < s->threshold) {
+        quorum_report_failure(acb);
+        acb->vote_ret = -EIO;
+        goto free_exit;
+    }
+
+    /* we have a winner: copy it */
+    quorum_copy_qiov(acb->qiov, &acb->qcrs[winner->index].qiov);
+
+    /* some versions are bad print them */
+    quorum_report_bad_versions(s, acb, &winner->value);
+
+free_exit:
+    /* free lists */
+    quorum_free_vote_list(&acb->votes);
+}
+
+static BlockDriverAIOCB *quorum_aio_readv(BlockDriverState *bs,
+                                         int64_t sector_num,
+                                         QEMUIOVector *qiov,
+                                         int nb_sectors,
+                                         BlockDriverCompletionFunc *cb,
+                                         void *opaque)
+{
+    BDRVQuorumState *s = bs->opaque;
+    QuorumAIOCB *acb = quorum_aio_get(s, bs, qiov, sector_num,
+                                      nb_sectors, cb, opaque);
+    int i;
+
+    acb->is_read = true;
+
+    for (i = 0; i < s->num_children; i++) {
+        acb->qcrs[i].buf = qemu_blockalign(s->bs[i], qiov->size);
+        qemu_iovec_init(&acb->qcrs[i].qiov, qiov->niov);
+        qemu_iovec_clone(&acb->qcrs[i].qiov, qiov, acb->qcrs[i].buf);
+    }
+
+    for (i = 0; i < s->num_children; i++) {
+        bdrv_aio_readv(s->bs[i], sector_num, &acb->qcrs[i].qiov, nb_sectors,
+                       quorum_aio_cb, &acb->qcrs[i]);
+    }
+
+    return &acb->common;
+}
+
+static BlockDriverAIOCB *quorum_aio_writev(BlockDriverState *bs,
+                                          int64_t sector_num,
+                                          QEMUIOVector *qiov,
+                                          int nb_sectors,
+                                          BlockDriverCompletionFunc *cb,
+                                          void *opaque)
+{
+    BDRVQuorumState *s = bs->opaque;
+    QuorumAIOCB *acb = quorum_aio_get(s, bs, qiov, sector_num, nb_sectors,
+                                      cb, opaque);
+    int i;
+
+    for (i = 0; i < s->num_children; i++) {
+        acb->qcrs[i].aiocb = bdrv_aio_writev(s->bs[i], sector_num, qiov,
+                                             nb_sectors, &quorum_aio_cb,
+                                             &acb->qcrs[i]);
+    }
+
+    return &acb->common;
+}
+
+static int64_t quorum_getlength(BlockDriverState *bs)
+{
+    BDRVQuorumState *s = bs->opaque;
+    int64_t result;
+    int i;
+
+    /* check that all file have the same length */
+    result = bdrv_getlength(s->bs[0]);
+    if (result < 0) {
+        return result;
+    }
+    for (i = 1; i < s->num_children; i++) {
+        int64_t value = bdrv_getlength(s->bs[i]);
+        if (value < 0) {
+            return value;
+        }
+        if (value != result) {
+            return -EIO;
+        }
+    }
+
+    return result;
+}
+
+static void quorum_invalidate_cache(BlockDriverState *bs)
+{
+    BDRVQuorumState *s = bs->opaque;
+    int i;
+
+    for (i = 0; i < s->num_children; i++) {
+        bdrv_invalidate_cache(s->bs[i]);
+    }
+}
+
+static coroutine_fn int quorum_co_flush(BlockDriverState *bs)
+{
+    BDRVQuorumState *s = bs->opaque;
+    QuorumVoteVersion *winner = NULL;
+    QuorumVotes error_votes;
+    QuorumVoteValue result_value;
+    int i;
+    int result = 0;
+
+    QLIST_INIT(&error_votes.vote_list);
+    error_votes.compare = quorum_64bits_compare;
+
+    for (i = 0; i < s->num_children; i++) {
+        result = bdrv_co_flush(s->bs[i]);
+        result_value.l = result;
+        quorum_count_vote(&error_votes, &result_value, i);
+    }
+
+    winner = quorum_get_vote_winner(&error_votes);
+    result = winner->value.l;
+
+    quorum_free_vote_list(&error_votes);
+
+    return result;
+}
+
+static bool quorum_recurse_is_first_non_filter(BlockDriverState *bs,
+                                               BlockDriverState *candidate)
+{
+    BDRVQuorumState *s = bs->opaque;
+    int i;
+
+    for (i = 0; i < s->num_children; i++) {
+        bool perm = bdrv_recurse_is_first_non_filter(s->bs[i],
+                                                     candidate);
+        if (perm) {
+            return true;
+        }
+    }
+
+    return false;
+}
+
+static int quorum_valid_threshold(int threshold, int num_children, Error **errp)
+{
+
+    if (threshold < 1) {
+        error_set(errp, QERR_INVALID_PARAMETER_VALUE,
+                  "vote-threshold", "value >= 1");
+        return -ERANGE;
+    }
+
+    if (threshold > num_children) {
+        error_setg(errp, "threshold may not exceed children count");
+        return -ERANGE;
+    }
+
+    return 0;
+}
+
+static QemuOptsList quorum_runtime_opts = {
+    .name = "quorum",
+    .head = QTAILQ_HEAD_INITIALIZER(quorum_runtime_opts.head),
+    .desc = {
+        {
+            .name = QUORUM_OPT_VOTE_THRESHOLD,
+            .type = QEMU_OPT_NUMBER,
+            .help = "The number of vote needed for reaching quorum",
+        },
+        {
+            .name = QUORUM_OPT_BLKVERIFY,
+            .type = QEMU_OPT_BOOL,
+            .help = "Trigger block verify mode if set",
+        },
+        { /* end of list */ }
+    },
+};
+
+static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
+                       Error **errp)
+{
+    BDRVQuorumState *s = bs->opaque;
+    Error *local_err = NULL;
+    QemuOpts *opts;
+    bool *opened;
+    QDict *sub = NULL;
+    QList *list = NULL;
+    const QListEntry *lentry;
+    int i;
+    int ret = 0;
+
+    qdict_flatten(options);
+    qdict_extract_subqdict(options, &sub, "children.");
+    qdict_array_split(sub, &list);
+
+    if (qdict_size(sub)) {
+        error_setg(&local_err, "Invalid option children.%s",
+                   qdict_first(sub)->key);
+        ret = -EINVAL;
+        goto exit;
+    }
+
+    /* count how many different children are present */
+    s->num_children = qlist_size(list);
+    if (s->num_children < 2) {
+        error_setg(&local_err,
+                   "Number of provided children must be greater than 1");
+        ret = -EINVAL;
+        goto exit;
+    }
+
+    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)) {
+        ret = -EINVAL;
+        goto exit;
+    }
+
+    s->threshold = qemu_opt_get_number(opts, QUORUM_OPT_VOTE_THRESHOLD, 0);
+
+    /* and validate it against s->num_children */
+    ret = quorum_valid_threshold(s->threshold, s->num_children, &local_err);
+    if (ret < 0) {
+        goto exit;
+    }
+
+    /* is the driver in blkverify mode */
+    if (qemu_opt_get_bool(opts, QUORUM_OPT_BLKVERIFY, false) &&
+        s->num_children == 2 && s->threshold == 2) {
+        s->is_blkverify = true;
+    } else if (qemu_opt_get_bool(opts, QUORUM_OPT_BLKVERIFY, false)) {
+        fprintf(stderr, "blkverify mode is set by setting blkverify=on "
+                "and using two files with vote_threshold=2\n");
+    }
+
+    /* allocate the children BlockDriverState array */
+    s->bs = g_new0(BlockDriverState *, s->num_children);
+    opened = g_new0(bool, s->num_children);
+
+    for (i = 0, lentry = qlist_first(list); lentry;
+         lentry = qlist_next(lentry), i++) {
+        QDict *d;
+        QString *string;
+
+        switch (qobject_type(lentry->value))
+        {
+            /* List of options */
+            case QTYPE_QDICT:
+                d = qobject_to_qdict(lentry->value);
+                QINCREF(d);
+                ret = bdrv_open(&s->bs[i], NULL, NULL, d, flags, NULL,
+                                &local_err);
+                break;
+
+            /* QMP reference */
+            case QTYPE_QSTRING:
+                string = qobject_to_qstring(lentry->value);
+                ret = bdrv_open(&s->bs[i], NULL, qstring_get_str(string), NULL,
+                                flags, NULL, &local_err);
+                break;
+
+            default:
+                error_setg(&local_err, "Specification of child block device %i "
+                           "is invalid", i);
+                ret = -EINVAL;
+        }
+
+        if (ret < 0) {
+            goto close_exit;
+        }
+        opened[i] = true;
+    }
+
+    g_free(opened);
+    goto exit;
+
+close_exit:
+    /* cleanup on error */
+    for (i = 0; i < s->num_children; i++) {
+        if (!opened[i]) {
+            continue;
+        }
+        bdrv_unref(s->bs[i]);
+    }
+    g_free(s->bs);
+    g_free(opened);
+exit:
+    /* propagate error */
+    if (error_is_set(&local_err)) {
+        error_propagate(errp, local_err);
+    }
+    QDECREF(list);
+    QDECREF(sub);
+    return ret;
+}
+
+static void quorum_close(BlockDriverState *bs)
+{
+    BDRVQuorumState *s = bs->opaque;
+    int i;
+
+    for (i = 0; i < s->num_children; i++) {
+        bdrv_unref(s->bs[i]);
+    }
+
+    g_free(s->bs);
+}
+
+static BlockDriver bdrv_quorum = {
+    .format_name        = "quorum",
+    .protocol_name      = "quorum",
+
+    .instance_size      = sizeof(BDRVQuorumState),
+
+    .bdrv_file_open     = quorum_open,
+    .bdrv_close         = quorum_close,
+
+    .authorizations     = { true, true },
+
+    .bdrv_co_flush_to_disk = quorum_co_flush,
+
+    .bdrv_getlength     = quorum_getlength,
+
+    .bdrv_aio_readv     = quorum_aio_readv,
+    .bdrv_aio_writev    = quorum_aio_writev,
+    .bdrv_invalidate_cache = quorum_invalidate_cache,
+
+    .bdrv_recurse_is_first_non_filter = quorum_recurse_is_first_non_filter,
+};
+
+static void bdrv_quorum_init(void)
+{
+    bdrv_register(&bdrv_quorum);
+}
+
+block_init(bdrv_quorum_init);

block/raw-posix.c

@@ -336,6 +336,17 @@ error:
 }
 #endif
 
+static void raw_parse_filename(const char *filename, QDict *options,
+                               Error **errp)
+{
+    /* The filename does not have to be prefixed by the protocol name, since
+     * "file" is the default protocol; therefore, the return value of this
+     * function call can be ignored. */
+    strstart(filename, "file:", &filename);
+
+    qdict_put_obj(options, "filename", QOBJECT(qstring_from_str(filename)));
+}
+
 static QemuOptsList raw_runtime_opts = {
     .name = "raw",
     .head = QTAILQ_HEAD_INITIALIZER(raw_runtime_opts.head),
@@ -1230,6 +1241,8 @@ static int raw_create(const char *filename, QEMUOptionParameter *options,
     int result = 0;
     int64_t total_size = 0;
 
+    strstart(filename, "file:", &filename);
+
     /* Read out options */
     while (options && options->name) {
         if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
@@ -1412,6 +1425,7 @@ static BlockDriver bdrv_file = {
     .instance_size = sizeof(BDRVRawState),
     .bdrv_needs_filename = true,
     .bdrv_probe = NULL, /* no probe for protocols */
+    .bdrv_parse_filename = raw_parse_filename,
     .bdrv_file_open = raw_open,
     .bdrv_reopen_prepare = raw_reopen_prepare,
     .bdrv_reopen_commit = raw_reopen_commit,

block/raw-win32.c

@@ -251,6 +251,17 @@ static void raw_parse_flags(int flags, int *access_flags, DWORD *overlapped)
     }
 }
 
+static void raw_parse_filename(const char *filename, QDict *options,
+                               Error **errp)
+{
+    /* The filename does not have to be prefixed by the protocol name, since
+     * "file" is the default protocol; therefore, the return value of this
+     * function call can be ignored. */
+    strstart(filename, "file:", &filename);
+
+    qdict_put_obj(options, "filename", QOBJECT(qstring_from_str(filename)));
+}
+
 static QemuOptsList raw_runtime_opts = {
     .name = "raw",
     .head = QTAILQ_HEAD_INITIALIZER(raw_runtime_opts.head),
@@ -470,6 +481,8 @@ static int raw_create(const char *filename, QEMUOptionParameter *options,
     int fd;
     int64_t total_size = 0;
 
+    strstart(filename, "file:", &filename);
+
     /* Read out options */
     while (options && options->name) {
         if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
@@ -504,6 +517,7 @@ static BlockDriver bdrv_file = {
     .protocol_name	= "file",
     .instance_size	= sizeof(BDRVRawState),
     .bdrv_needs_filename = true,
+    .bdrv_parse_filename = raw_parse_filename,
     .bdrv_file_open	= raw_open,
     .bdrv_close		= raw_close,
     .bdrv_create	= raw_create,

block/sheepdog.c

@@ -1534,7 +1534,8 @@ static int sd_prealloc(const char *filename)
     Error *local_err = NULL;
     int ret;
 
-    ret = bdrv_file_open(&bs, filename, NULL, NULL, BDRV_O_RDWR, &local_err);
+    ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
+                    NULL, &local_err);
     if (ret < 0) {
         qerror_report_err(local_err);
         error_free(local_err);
@@ -1695,7 +1696,9 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
             goto out;
         }
 
-        ret = bdrv_file_open(&bs, backing_file, NULL, NULL, 0, &local_err);
+        bs = NULL;
+        ret = bdrv_open(&bs, backing_file, NULL, NULL, BDRV_O_PROTOCOL, NULL,
+                        &local_err);
         if (ret < 0) {
             qerror_report_err(local_err);
             error_free(local_err);

block/vdi.c

@@ -395,43 +395,50 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     if (header.signature != VDI_SIGNATURE) {
-        logout("bad vdi signature %08x\n", header.signature);
+        error_setg(errp, "Image not in VDI format (bad signature %08x)", header.signature);
-        ret = -EMEDIUMTYPE;
+        ret = -EINVAL;
         goto fail;
     } else if (header.version != VDI_VERSION_1_1) {
-        logout("unsupported version %u.%u\n",
+        error_setg(errp, "unsupported VDI image (version %u.%u)",
-               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. */
-        logout("unsupported block map offset 0x%x B\n", header.offset_bmap);
+        error_setg(errp, "unsupported VDI image (unaligned block map offset "
+                   "0x%x)", 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. */
-        logout("unsupported data offset 0x%x B\n", header.offset_data);
+        error_setg(errp, "unsupported VDI image (unaligned data offset 0x%x)",
+                   header.offset_data);
         ret = -ENOTSUP;
         goto fail;
     } else if (header.sector_size != SECTOR_SIZE) {
-        logout("unsupported sector size %u B\n", header.sector_size);
+        error_setg(errp, "unsupported VDI image (sector size %u is not %u)",
+                   header.sector_size, SECTOR_SIZE);
         ret = -ENOTSUP;
         goto fail;
     } else if (header.block_size != 1 * MiB) {
-        logout("unsupported block size %u B\n", header.block_size);
+        error_setg(errp, "unsupported VDI image (sector size %u is not %u)",
+                   header.block_size, 1 * MiB);
         ret = -ENOTSUP;
         goto fail;
     } else if (header.disk_size >
                (uint64_t)header.blocks_in_image * header.block_size) {
-        logout("unsupported disk size %" PRIu64 " B\n", header.disk_size);
+        error_setg(errp, "unsupported VDI image (disk size %" PRIu64 ", "
+                   "image bitmap has room for %" PRIu64 ")",
+                   header.disk_size,
+                   (uint64_t)header.blocks_in_image * header.block_size);
         ret = -ENOTSUP;
         goto fail;
     } else if (!uuid_is_null(header.uuid_link)) {
-        logout("link uuid != 0, unsupported\n");
+        error_setg(errp, "unsupported VDI image (non-NULL link UUID)");
         ret = -ENOTSUP;
         goto fail;
     } else if (!uuid_is_null(header.uuid_parent)) {
-        logout("parent uuid != 0, unsupported\n");
+        error_setg(errp, "unsupported VDI image (non-NULL parent UUID)");
         ret = -ENOTSUP;
         goto fail;
     }

block/vhdx.c

@@ -402,9 +402,10 @@ int vhdx_update_headers(BlockDriverState *bs, BDRVVHDXState *s,
 }
 
 /* opens the specified header block from the VHDX file header section */
-static int vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s)
+static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s,
+                              Error **errp)
 {
-    int ret = 0;
+    int ret;
     VHDXHeader *header1;
     VHDXHeader *header2;
     bool h1_valid = false;
@@ -462,7 +463,6 @@ static int vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s)
     } else if (!h1_valid && h2_valid) {
         s->curr_header = 1;
     } else if (!h1_valid && !h2_valid) {
-        ret = -EINVAL;
         goto fail;
     } else {
         /* If both headers are valid, then we choose the active one by the
@@ -473,27 +473,22 @@ static int vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s)
         } else if (h2_seq > h1_seq) {
             s->curr_header = 1;
         } else {
-            ret = -EINVAL;
             goto fail;
         }
     }
 
     vhdx_region_register(s, s->headers[s->curr_header]->log_offset,
                             s->headers[s->curr_header]->log_length);
-
-    ret = 0;
-
     goto exit;
 
 fail:
-    qerror_report(ERROR_CLASS_GENERIC_ERROR, "No valid VHDX header found");
+    error_setg_errno(errp, -ret, "No valid VHDX header found");
     qemu_vfree(header1);
     qemu_vfree(header2);
     s->headers[0] = NULL;
     s->headers[1] = NULL;
 exit:
     qemu_vfree(buffer);
-    return ret;
 }
 
 
@@ -878,7 +873,7 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
     int ret = 0;
     uint32_t i;
     uint64_t signature;
-
+    Error *local_err = NULL;
 
     s->bat = NULL;
     s->first_visible_write = true;
@@ -901,8 +896,10 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
      * header update */
     vhdx_guid_generate(&s->session_guid);
 
-    ret = vhdx_parse_header(bs, s);
+    vhdx_parse_header(bs, s, &local_err);
-    if (ret < 0) {
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
         goto fail;
     }
 
@@ -1797,7 +1794,9 @@ static int vhdx_create(const char *filename, QEMUOptionParameter *options,
         goto exit;
     }
 
-    ret = bdrv_file_open(&bs, filename, NULL, NULL, BDRV_O_RDWR, &local_err);
+    bs = NULL;
+    ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
+                    NULL, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
         goto exit;

block/vmdk.c

@@ -526,8 +526,34 @@ static int vmdk_open_vmfs_sparse(BlockDriverState *bs,
     return ret;
 }
 
-static int vmdk_open_desc_file(BlockDriverState *bs, int flags,
+static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
-                               uint64_t desc_offset, Error **errp);
+                               Error **errp);
+
+static char *vmdk_read_desc(BlockDriverState *file, uint64_t desc_offset,
+                            Error **errp)
+{
+    int64_t size;
+    char *buf;
+    int ret;
+
+    size = bdrv_getlength(file);
+    if (size < 0) {
+        error_setg_errno(errp, -size, "Could not access file");
+        return NULL;
+    }
+
+    size = MIN(size, 1 << 20);  /* avoid unbounded allocation */
+    buf = g_malloc0(size + 1);
+
+    ret = bdrv_pread(file, desc_offset, buf, size);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Could not read from file");
+        g_free(buf);
+        return NULL;
+    }
+
+    return buf;
+}
 
 static int vmdk_open_vmdk4(BlockDriverState *bs,
                            BlockDriverState *file,
@@ -546,11 +572,18 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
         error_setg_errno(errp, -ret,
                          "Could not read header from file '%s'",
                          file->filename);
+        return -EINVAL;
     }
     if (header.capacity == 0) {
         uint64_t desc_offset = le64_to_cpu(header.desc_offset);
         if (desc_offset) {
-            return vmdk_open_desc_file(bs, flags, desc_offset << 9, errp);
+            char *buf = vmdk_read_desc(file, desc_offset << 9, errp);
+            if (!buf) {
+                return -EINVAL;
+            }
+            ret = vmdk_open_desc_file(bs, flags, buf, errp);
+            g_free(buf);
+            return ret;
         }
     }
 
@@ -609,8 +642,8 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
         char buf[64];
         snprintf(buf, sizeof(buf), "VMDK version %d",
                  le32_to_cpu(header.version));
-        qerror_report(QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+        error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
-                bs->device_name, "vmdk", buf);
+                  bs->device_name, "vmdk", buf);
         return -ENOTSUP;
     } else if (le32_to_cpu(header.version) == 3 && (flags & BDRV_O_RDWR)) {
         /* VMware KB 2064959 explains that version 3 added support for
@@ -622,7 +655,7 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
     }
 
     if (le32_to_cpu(header.num_gtes_per_gt) > 512) {
-        error_report("L2 table size too big");
+        error_setg(errp, "L2 table size too big");
         return -EINVAL;
     }
 
@@ -638,8 +671,8 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
     }
     if (bdrv_getlength(file) <
             le64_to_cpu(header.grain_offset) * BDRV_SECTOR_SIZE) {
-        error_report("File truncated, expecting at least %lld bytes",
+        error_setg(errp, "File truncated, expecting at least %lld bytes",
-                le64_to_cpu(header.grain_offset) * BDRV_SECTOR_SIZE);
+                   le64_to_cpu(header.grain_offset) * BDRV_SECTOR_SIZE);
         return -EINVAL;
     }
 
@@ -701,16 +734,12 @@ static int vmdk_parse_description(const char *desc, const char *opt_name,
 
 /* Open an extent file and append to bs array */
 static int vmdk_open_sparse(BlockDriverState *bs,
-                            BlockDriverState *file,
+                            BlockDriverState *file, int flags,
-                            int flags, Error **errp)
+                            char *buf, Error **errp)
 {
     uint32_t magic;
 
-    if (bdrv_pread(file, 0, &magic, sizeof(magic)) != sizeof(magic)) {
+    magic = ldl_be_p(buf);
-        return -EIO;
-    }
-
-    magic = be32_to_cpu(magic);
     switch (magic) {
         case VMDK3_MAGIC:
             return vmdk_open_vmfs_sparse(bs, file, flags, errp);
@@ -719,7 +748,8 @@ static int vmdk_open_sparse(BlockDriverState *bs,
             return vmdk_open_vmdk4(bs, file, flags, errp);
             break;
         default:
-            return -EMEDIUMTYPE;
+            error_setg(errp, "Image not in VMDK format");
+            return -EINVAL;
             break;
     }
 }
@@ -776,8 +806,9 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
 
         path_combine(extent_path, sizeof(extent_path),
                 desc_file_path, fname);
-        ret = bdrv_file_open(&extent_file, extent_path, NULL, NULL,
+        extent_file = NULL;
-                             bs->open_flags, errp);
+        ret = bdrv_open(&extent_file, extent_path, NULL, NULL,
+                        bs->open_flags | BDRV_O_PROTOCOL, NULL, errp);
         if (ret) {
             return ret;
         }
@@ -794,8 +825,14 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
             extent->flat_start_offset = flat_offset << 9;
         } else if (!strcmp(type, "SPARSE") || !strcmp(type, "VMFSSPARSE")) {
             /* SPARSE extent and VMFSSPARSE extent are both "COWD" sparse file*/
-            ret = vmdk_open_sparse(bs, extent_file, bs->open_flags, errp);
+            char *buf = vmdk_read_desc(extent_file, 0, errp);
+            if (!buf) {
+                ret = -EINVAL;
+            } else {
+                ret = vmdk_open_sparse(bs, extent_file, bs->open_flags, buf, errp);
+            }
             if (ret) {
+                g_free(buf);
                 bdrv_unref(extent_file);
                 return ret;
             }
@@ -818,29 +855,16 @@ next_line:
     return 0;
 }
 
-static int vmdk_open_desc_file(BlockDriverState *bs, int flags,
+static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
-                               uint64_t desc_offset, Error **errp)
+                               Error **errp)
 {
     int ret;
-    char *buf = NULL;
     char ct[128];
     BDRVVmdkState *s = bs->opaque;
-    int64_t size;
 
-    size = bdrv_getlength(bs->file);
-    if (size < 0) {
-        return -EINVAL;
-    }
-
-    size = MIN(size, 1 << 20);  /* avoid unbounded allocation */
-    buf = g_malloc0(size + 1);
-
-    ret = bdrv_pread(bs->file, desc_offset, buf, size);
-    if (ret < 0) {
-        goto exit;
-    }
     if (vmdk_parse_description(buf, "createType", ct, sizeof(ct))) {
-        ret = -EMEDIUMTYPE;
+        error_setg(errp, "invalid VMDK image descriptor");
+        ret = -EINVAL;
         goto exit;
     }
     if (strcmp(ct, "monolithicFlat") &&
@@ -856,24 +880,37 @@ static int vmdk_open_desc_file(BlockDriverState *bs, int flags,
     s->desc_offset = 0;
     ret = vmdk_parse_extents(buf, bs, bs->file->filename, errp);
 exit:
-    g_free(buf);
     return ret;
 }
 
 static int vmdk_open(BlockDriverState *bs, QDict *options, int flags,
                      Error **errp)
 {
+    char *buf = NULL;
     int ret;
     BDRVVmdkState *s = bs->opaque;
+    uint32_t magic;
 
-    if (vmdk_open_sparse(bs, bs->file, flags, errp) == 0) {
+    buf = vmdk_read_desc(bs->file, 0, errp);
-        s->desc_offset = 0x200;
+    if (!buf) {
-    } else {
+        return -EINVAL;
-        ret = vmdk_open_desc_file(bs, flags, 0, errp);
-        if (ret) {
-            goto fail;
-        }
     }
+
+    magic = ldl_be_p(buf);
+    switch (magic) {
+        case VMDK3_MAGIC:
+        case VMDK4_MAGIC:
+            ret = vmdk_open_sparse(bs, bs->file, flags, buf, errp);
+            s->desc_offset = 0x200;
+            break;
+        default:
+            ret = vmdk_open_desc_file(bs, flags, buf, errp);
+            break;
+    }
+    if (ret) {
+        goto fail;
+    }
+
     /* try to open parent images, if exist */
     ret = vmdk_parent_open(bs);
     if (ret) {
@@ -888,10 +925,11 @@ static int vmdk_open(BlockDriverState *bs, QDict *options, int flags,
               QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
               "vmdk", bs->device_name, "live migration");
     migrate_add_blocker(s->migration_blocker);
-
+    g_free(buf);
     return 0;
 
 fail:
+    g_free(buf);
     g_free(s->create_type);
     s->create_type = NULL;
     vmdk_free_extents(bs);
@@ -1146,7 +1184,7 @@ static int64_t coroutine_fn vmdk_co_get_block_status(BlockDriverState *bs,
         break;
     case VMDK_OK:
         ret = BDRV_BLOCK_DATA;
-        if (extent->file == bs->file) {
+        if (extent->file == bs->file && !extent->compressed) {
             ret |= BDRV_BLOCK_OFFSET_VALID | offset;
         }
 
@@ -1493,7 +1531,9 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
         goto exit;
     }
 
-    ret = bdrv_file_open(&bs, filename, NULL, NULL, BDRV_O_RDWR, &local_err);
+    assert(bs == NULL);
+    ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
+                    NULL, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
         goto exit;
@@ -1755,10 +1795,10 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
         goto exit;
     }
     if (backing_file) {
-        BlockDriverState *bs = bdrv_new("");
+        BlockDriverState *bs = NULL;
-        ret = bdrv_open(bs, backing_file, NULL, BDRV_O_NO_BACKING, NULL, errp);
+        ret = bdrv_open(&bs, backing_file, NULL, NULL, BDRV_O_NO_BACKING, NULL,
+                        errp);
         if (ret != 0) {
-            bdrv_unref(bs);
             goto exit;
         }
         if (strcmp(bs->drv->format_name, "vmdk")) {
@@ -1831,7 +1871,9 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
             goto exit;
         }
     }
-    ret = bdrv_file_open(&new_bs, filename, NULL, NULL, BDRV_O_RDWR, &local_err);
+    assert(new_bs == NULL);
+    ret = bdrv_open(&new_bs, filename, NULL, NULL,
+                    BDRV_O_RDWR | BDRV_O_PROTOCOL, NULL, &local_err);
     if (ret < 0) {
         error_setg_errno(errp, -ret, "Could not write description");
         goto exit;

block/vpc.c

@@ -190,7 +190,8 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
             goto fail;
         }
         if (strncmp(footer->creator, "conectix", 8)) {
-            ret = -EMEDIUMTYPE;
+            error_setg(errp, "invalid VPC image");
+            ret = -EINVAL;
             goto fail;
         }
         disk_type = VHD_FIXED;

block/vvfat.c

@@ -1086,16 +1086,14 @@ DLOG(if (stderr == NULL) {
     opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (local_err) {
-        qerror_report_err(local_err);
+        error_propagate(errp, local_err);
-        error_free(local_err);
         ret = -EINVAL;
         goto fail;
     }
 
     dirname = qemu_opt_get(opts, "dir");
     if (!dirname) {
-        qerror_report(ERROR_CLASS_GENERIC_ERROR, "vvfat block driver requires "
+        error_setg(errp, "vvfat block driver requires a 'dir' option");
-                      "a 'dir' option");
         ret = -EINVAL;
         goto fail;
     }
@@ -1135,8 +1133,7 @@ DLOG(if (stderr == NULL) {
     case 12:
         break;
     default:
-        qerror_report(ERROR_CLASS_GENERIC_ERROR, "Valid FAT types are only "
+        error_setg(errp, "Valid FAT types are only 12, 16 and 32");
-                      "12, 16 and 32");
         ret = -EINVAL;
         goto fail;
     }
@@ -2936,15 +2933,13 @@ static int enable_write_target(BDRVVVFATState *s)
         goto err;
     }
 
-    s->qcow = bdrv_new("");
+    s->qcow = NULL;
-
+    ret = bdrv_open(&s->qcow, s->qcow_filename, NULL, NULL,
-    ret = bdrv_open(s->qcow, s->qcow_filename, NULL,
             BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH, bdrv_qcow,
             &local_err);
     if (ret < 0) {
         qerror_report_err(local_err);
         error_free(local_err);
-        bdrv_unref(s->qcow);
         goto err;
     }
 

blockdev.c

@@ -504,7 +504,7 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
     bdrv_flags |= ro ? 0 : BDRV_O_RDWR;
 
     QINCREF(bs_opts);
-    ret = bdrv_open(dinfo->bdrv, file, bs_opts, bdrv_flags, drv, &error);
+    ret = bdrv_open(&dinfo->bdrv, file, NULL, bs_opts, bdrv_flags, drv, &error);
 
     if (ret < 0) {
         error_setg(errp, "could not open disk image %s: %s",
@@ -1330,12 +1330,12 @@ static void external_snapshot_prepare(BlkTransactionState *common,
                   qstring_from_str(snapshot_node_name));
     }
 
-    /* We will manually add the backing_hd field to the bs later */
-    state->new_bs = bdrv_new("");
     /* TODO Inherit bs->options or only take explicit options with an
      * extended QMP command? */
-    ret = bdrv_open(state->new_bs, new_image_file, options,
+    assert(state->new_bs == NULL);
+    ret = bdrv_open(&state->new_bs, new_image_file, NULL, options,
                     flags | BDRV_O_NO_BACKING, drv, &local_err);
+    /* We will manually add the backing_hd field to the bs later */
     if (ret != 0) {
         error_propagate(errp, local_err);
     }
@@ -1582,7 +1582,7 @@ static void qmp_bdrv_open_encrypted(BlockDriverState *bs, const char *filename,
     Error *local_err = NULL;
     int ret;
 
-    ret = bdrv_open(bs, filename, NULL, bdrv_flags, drv, &local_err);
+    ret = bdrv_open(&bs, filename, NULL, NULL, bdrv_flags, drv, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
         return;
@@ -2018,10 +2018,9 @@ void qmp_drive_backup(const char *device, const char *target,
         return;
     }
 
-    target_bs = bdrv_new("");
+    target_bs = NULL;
-    ret = bdrv_open(target_bs, target, NULL, flags, drv, &local_err);
+    ret = bdrv_open(&target_bs, target, NULL, NULL, flags, drv, &local_err);
     if (ret < 0) {
-        bdrv_unref(target_bs);
         error_propagate(errp, local_err);
         return;
     }
@@ -2162,11 +2161,10 @@ void qmp_drive_mirror(const char *device, const char *target,
     /* Mirroring takes care of copy-on-write using the source's backing
      * file.
      */
-    target_bs = bdrv_new("");
+    target_bs = NULL;
-    ret = bdrv_open(target_bs, target, NULL, flags | BDRV_O_NO_BACKING, drv,
+    ret = bdrv_open(&target_bs, target, NULL, NULL, flags | BDRV_O_NO_BACKING,
-                    &local_err);
+                    drv, &local_err);
     if (ret < 0) {
-        bdrv_unref(target_bs);
         error_propagate(errp, local_err);
         return;
     }
@@ -2268,6 +2266,7 @@ void qmp_block_job_complete(const char *device, Error **errp)
 void qmp_blockdev_add(BlockdevOptions *options, Error **errp)
 {
     QmpOutputVisitor *ov = qmp_output_visitor_new();
+    DriveInfo *dinfo;
     QObject *obj;
     QDict *qdict;
     Error *local_err = NULL;
@@ -2284,8 +2283,10 @@ void qmp_blockdev_add(BlockdevOptions *options, Error **errp)
      *
      * For now, simply forbidding the combination for all drivers will do. */
     if (options->has_aio && options->aio == BLOCKDEV_AIO_OPTIONS_NATIVE) {
-        bool direct = options->cache->has_direct && options->cache->direct;
+        bool direct = options->has_cache &&
-        if (!options->has_cache && !direct) {
+                      options->cache->has_direct &&
+                      options->cache->direct;
+        if (!direct) {
             error_setg(errp, "aio=native requires cache.direct=true");
             goto fail;
         }
@@ -2303,12 +2304,18 @@ void qmp_blockdev_add(BlockdevOptions *options, Error **errp)
 
     qdict_flatten(qdict);
 
-    blockdev_init(NULL, qdict, &local_err);
+    dinfo = blockdev_init(NULL, qdict, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         goto fail;
     }
 
+    if (bdrv_key_required(dinfo->bdrv)) {
+        drive_uninit(dinfo);
+        error_setg(errp, "blockdev-add doesn't support encrypted devices");
+        goto fail;
+    }
+
 fail:
     qmp_output_visitor_cleanup(ov);
 }

configure

@@ -12,12 +12,16 @@ else
 fi
 
 TMPC="${TMPDIR1}/qemu-conf-${RANDOM}-$$-${RANDOM}.c"
-TMPO="${TMPDIR1}/qemu-conf-${RANDOM}-$$-${RANDOM}.o"
+TMPB="qemu-conf-${RANDOM}-$$-${RANDOM}"
+TMPO="${TMPDIR1}/${TMPB}.o"
+TMPCXX="${TMPDIR1}/${TMPB}.cxx"
+TMPL="${TMPDIR1}/${TMPB}.lo"
+TMPA="${TMPDIR1}/lib${TMPB}.la"
 TMPE="${TMPDIR1}/qemu-conf-${RANDOM}-$$-${RANDOM}.exe"
 
 # NB: do not call "exit" in the trap handler; this is buggy with some shells;
 # see <1285349658-3122-1-git-send-email-loic.minier@linaro.org>
-trap "rm -f $TMPC $TMPO $TMPE" EXIT INT QUIT TERM
+trap "rm -f $TMPC $TMPO $TMPCXX $TMPE" EXIT INT QUIT TERM
 rm -f config.log
 
 # Print a helpful header at the top of config.log
@@ -51,10 +55,13 @@ error_exit() {
     exit 1
 }
 
-do_cc() {
+do_compiler() {
-    # Run the compiler, capturing its output to the log.
+    # Run the compiler, capturing its output to the log. First argument
-    echo $cc "$@" >> config.log
+    # is compiler binary to execute.
-    $cc "$@" >> config.log 2>&1 || return $?
+    local compiler="$1"
+    shift
+    echo $compiler "$@" >> config.log
+    $compiler "$@" >> config.log 2>&1 || return $?
     # Test passed. If this is an --enable-werror build, rerun
     # the test with -Werror and bail out if it fails. This
     # makes warning-generating-errors in configure test code
@@ -68,14 +75,39 @@ do_cc() {
            return 0
         ;;
     esac
-    echo $cc -Werror "$@" >> config.log
+    echo $compiler -Werror "$@" >> config.log
-    $cc -Werror "$@" >> config.log 2>&1 && return $?
+    $compiler -Werror "$@" >> config.log 2>&1 && return $?
     error_exit "configure test passed without -Werror but failed with -Werror." \
         "This is probably a bug in the configure script. The failing command" \
         "will be at the bottom of config.log." \
         "You can run configure with --disable-werror to bypass this check."
 }
 
+do_cc() {
+    do_compiler "$cc" "$@"
+}
+
+do_cxx() {
+    do_compiler "$cxx" "$@"
+}
+
+update_cxxflags() {
+    # Set QEMU_CXXFLAGS from QEMU_CFLAGS by filtering out those
+    # options which some versions of GCC's C++ compiler complain about
+    # because they only make sense for C programs.
+    QEMU_CXXFLAGS=
+    for arg in $QEMU_CFLAGS; do
+        case $arg in
+            -Wstrict-prototypes|-Wmissing-prototypes|-Wnested-externs|\
+            -Wold-style-declaration|-Wold-style-definition|-Wredundant-decls)
+                ;;
+            *)
+                QEMU_CXXFLAGS=${QEMU_CXXFLAGS:+$QEMU_CXXFLAGS }$arg
+                ;;
+        esac
+    done
+}
+
 compile_object() {
   do_cc $QEMU_CFLAGS -c -o $TMPO $TMPC
 }
@@ -86,6 +118,38 @@ compile_prog() {
   do_cc $QEMU_CFLAGS $local_cflags -o $TMPE $TMPC $LDFLAGS $local_ldflags
 }
 
+do_libtool() {
+    local mode=$1
+    shift
+    # Run the compiler, capturing its output to the log.
+    echo $libtool $mode --tag=CC $cc "$@" >> config.log
+    $libtool $mode --tag=CC $cc "$@" >> config.log 2>&1 || return $?
+    # Test passed. If this is an --enable-werror build, rerun
+    # the test with -Werror and bail out if it fails. This
+    # makes warning-generating-errors in configure test code
+    # obvious to developers.
+    if test "$werror" != "yes"; then
+        return 0
+    fi
+    # Don't bother rerunning the compile if we were already using -Werror
+    case "$*" in
+        *-Werror*)
+           return 0
+        ;;
+    esac
+    echo $libtool $mode --tag=CC $cc -Werror "$@" >> config.log
+    $libtool $mode --tag=CC $cc -Werror "$@" >> config.log 2>&1 && return $?
+    error_exit "configure test passed without -Werror but failed with -Werror." \
+        "This is probably a bug in the configure script. The failing command" \
+        "will be at the bottom of config.log." \
+        "You can run configure with --disable-werror to bypass this check."
+}
+
+libtool_prog() {
+    do_libtool --mode=compile $QEMU_CFLAGS -c -fPIE -DPIE -o $TMPO $TMPC || return $?
+    do_libtool --mode=link $LDFLAGS -o $TMPA $TMPL -rpath /usr/local/lib
+}
+
 # symbolically link $1 to $2.  Portable version of "ln -sf".
 symlink() {
   rm -rf "$2"
@@ -172,6 +236,7 @@ fdt=""
 netmap="no"
 pixman=""
 sdl=""
+sdlabi="1.2"
 virtfs=""
 vnc="yes"
 sparse="no"
@@ -205,6 +270,9 @@ mingw32="no"
 gcov="no"
 gcov_tool="gcov"
 EXESUF=""
+DSOSUF=".so"
+LDFLAGS_SHARED="-shared"
+modules="no"
 prefix="/usr/local"
 mandir="\${prefix}/share/man"
 datadir="\${prefix}/share"
@@ -245,6 +313,8 @@ libusb=""
 usb_redir=""
 glx=""
 zlib="yes"
+lzo="no"
+snappy="no"
 guest_agent=""
 guest_agent_with_vss="no"
 vss_win32_sdk=""
@@ -264,6 +334,7 @@ gtkabi="2.0"
 tpm="no"
 libssh2=""
 vhdx=""
+quorum="no"
 
 # parse CC options first
 for opt do
@@ -325,12 +396,13 @@ query_pkg_config() {
 }
 pkg_config=query_pkg_config
 sdl_config="${SDL_CONFIG-${cross_prefix}sdl-config}"
+sdl2_config="${SDL2_CONFIG-${cross_prefix}sdl2-config}"
 
 # If the user hasn't specified ARFLAGS, default to 'rv', just as make does.
 ARFLAGS="${ARFLAGS-rv}"
 
 # default flags for all hosts
-QEMU_CFLAGS="-fno-strict-aliasing $QEMU_CFLAGS"
+QEMU_CFLAGS="-fno-strict-aliasing -fno-common $QEMU_CFLAGS"
 QEMU_CFLAGS="-Wall -Wundef -Wwrite-strings -Wmissing-prototypes $QEMU_CFLAGS"
 QEMU_CFLAGS="-Wstrict-prototypes -Wredundant-decls $QEMU_CFLAGS"
 QEMU_CFLAGS="-D_GNU_SOURCE -D_FILE_OFFSET_BITS=64 -D_LARGEFILE_SOURCE $QEMU_CFLAGS"
@@ -515,11 +587,10 @@ OpenBSD)
 Darwin)
   bsd="yes"
   darwin="yes"
+  LDFLAGS_SHARED="-bundle -undefined dynamic_lookup"
   if [ "$cpu" = "x86_64" ] ; then
     QEMU_CFLAGS="-arch x86_64 $QEMU_CFLAGS"
     LDFLAGS="-arch x86_64 $LDFLAGS"
-  else
-    QEMU_CFLAGS="-mdynamic-no-pic $QEMU_CFLAGS"
   fi
   cocoa="yes"
   audio_drv_list="coreaudio"
@@ -610,6 +681,7 @@ fi
 
 if test "$mingw32" = "yes" ; then
   EXESUF=".exe"
+  DSOSUF=".dll"
   QEMU_CFLAGS="-DWIN32_LEAN_AND_MEAN -DWINVER=0x501 $QEMU_CFLAGS"
   # enable C99/POSIX format strings (needs mingw32-runtime 3.15 or later)
   QEMU_CFLAGS="-D__USE_MINGW_ANSI_STDIO=1 $QEMU_CFLAGS"
@@ -676,6 +748,9 @@ for opt do
   ;;
   --disable-debug-info)
   ;;
+  --enable-modules)
+      modules="yes"
+  ;;
   --cpu=*)
   ;;
   --target-list=*) target_list="$optarg"
@@ -731,6 +806,8 @@ for opt do
   ;;
   --enable-sdl) sdl="yes"
   ;;
+  --with-sdlabi=*) sdlabi="$optarg"
+  ;;
   --disable-qom-cast-debug) qom_cast_debug="no"
   ;;
   --enable-qom-cast-debug) qom_cast_debug="yes"
@@ -953,6 +1030,10 @@ for opt do
   ;;
   --disable-zlib-test) zlib="no"
   ;;
+  --enable-lzo) lzo="yes"
+  ;;
+  --enable-snappy) snappy="yes"
+  ;;
   --enable-guest-agent) guest_agent="yes"
   ;;
   --disable-guest-agent) guest_agent="no"
@@ -1005,6 +1086,10 @@ for opt do
   ;;
   --disable-vhdx) vhdx="no"
   ;;
+  --disable-quorum) quorum="no"
+  ;;
+  --enable-quorum) quorum="yes"
+  ;;
   *) echo "ERROR: unknown option $opt"; show_help="yes"
   ;;
   esac
@@ -1131,7 +1216,8 @@ Advanced options (experts only):
   --libdir=PATH            install libraries in PATH
   --sysconfdir=PATH        install config in PATH$confsuffix
   --localstatedir=PATH     install local state in PATH (set at runtime on win32)
-  --with-confsuffix=SUFFIX suffix for QEMU data inside datadir and sysconfdir [$confsuffix]
+  --with-confsuffix=SUFFIX suffix for QEMU data inside datadir/libdir/sysconfdir [$confsuffix]
+  --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)
@@ -1143,6 +1229,7 @@ Advanced options (experts only):
   --disable-werror         disable compilation abort on warning
   --disable-sdl            disable SDL
   --enable-sdl             enable SDL
+  --with-sdlabi            select preferred SDL ABI 1.2 or 2.0
   --disable-gtk            disable gtk UI
   --enable-gtk             enable gtk UI
   --disable-virtfs         disable VirtFS
@@ -1242,6 +1329,8 @@ Advanced options (experts only):
   --enable-libusb          enable libusb (for usb passthrough)
   --disable-usb-redir      disable usb network redirection support
   --enable-usb-redir       enable usb network redirection support
+  --enable-lzo             enable the support of lzo compression library
+  --enable-snappy          enable the support of snappy compression library
   --disable-guest-agent    disable building of the QEMU Guest Agent
   --enable-guest-agent     enable building of the QEMU Guest Agent
   --with-vss-sdk=SDK-path  enable Windows VSS support in QEMU Guest Agent
@@ -1261,6 +1350,8 @@ Advanced options (experts only):
   --enable-libssh2         enable ssh block device support
   --disable-vhdx           disables support for the Microsoft VHDX image format
   --enable-vhdx            enable support for the Microsoft VHDX image format
+  --disable-quorum         disable quorum block filter support
+  --enable-quorum          enable quorum block filter support
 
 NOTE: The object files are built at the place where configure is launched
 EOF
@@ -1278,17 +1369,6 @@ if test "$ARCH" = "unknown"; then
     fi
 fi
 
-# check that the C compiler works.
-cat > $TMPC <<EOF
-int main(void) { return 0; }
-EOF
-
-if compile_object ; then
-  : C compiler works ok
-else
-    error_exit "\"$cc\" either does not exist or does not work"
-fi
-
 # Consult white-list to determine whether to enable werror
 # by default.  Only enable by default for git builds
 z_version=`cut -f3 -d. $source_path/VERSION`
@@ -1302,6 +1382,48 @@ if test -z "$werror" ; then
     fi
 fi
 
+# check that the C compiler works.
+cat > $TMPC <<EOF
+int main(void) { return 0; }
+EOF
+
+if compile_object ; then
+  : C compiler works ok
+else
+    error_exit "\"$cc\" either does not exist or does not work"
+fi
+
+# Check that the C++ compiler exists and works with the C compiler
+if has $cxx; then
+    cat > $TMPC <<EOF
+int c_function(void);
+int main(void) { return c_function(); }
+EOF
+
+    compile_object
+
+    cat > $TMPCXX <<EOF
+extern "C" {
+   int c_function(void);
+}
+int c_function(void) { return 42; }
+EOF
+
+    update_cxxflags
+
+    if do_cxx $QEMU_CXXFLAGS -o $TMPE $TMPCXX $TMPO $LDFLAGS; then
+        # C++ compiler $cxx works ok with C compiler $cc
+        :
+    else
+        echo "C++ compiler $cxx does not work with C compiler $cc"
+        echo "Disabling C++ specific optional code"
+        cxx=
+    fi
+else
+    echo "No C++ compiler available; disabling C++ specific optional code"
+    cxx=
+fi
+
 gcc_flags="-Wold-style-declaration -Wold-style-definition -Wtype-limits"
 gcc_flags="-Wformat-security -Wformat-y2k -Winit-self -Wignored-qualifiers $gcc_flags"
 gcc_flags="-Wmissing-include-dirs -Wempty-body -Wnested-externs $gcc_flags"
@@ -1346,6 +1468,9 @@ if compile_prog "-Werror -fno-gcse" "" ; then
 fi
 
 if test "$static" = "yes" ; then
+  if test "$modules" = "yes" ; then
+    error_exit "static and modules are mutually incompatible"
+  fi
   if test "$pie" = "yes" ; then
     error_exit "static and pie are mutually incompatible"
   else
@@ -1399,6 +1524,32 @@ EOF
   fi
 fi
 
+# check for broken gcc and libtool in RHEL5
+if test -n "$libtool" -a "$pie" != "no" ; then
+  cat > $TMPC <<EOF
+
+void *f(unsigned char *buf, int len);
+void *g(unsigned char *buf, int len);
+
+void *
+f(unsigned char *buf, int len)
+{
+    return (void*)0L;
+}
+
+void *
+g(unsigned char *buf, int len)
+{
+    return f(buf, len);
+}
+
+EOF
+  if ! libtool_prog; then
+    echo "Disabling libtool due to broken toolchain support"
+    libtool=
+  fi
+fi
+
 ##########################################
 # __sync_fetch_and_and requires at least -march=i486. Many toolchains
 # use i686 as default anyway, but for those that don't, an explicit
@@ -1550,7 +1701,43 @@ EOF
             "Make sure to have the zlib libs and headers installed."
     fi
 fi
-libs_softmmu="$libs_softmmu -lz"
+LIBS="$LIBS -lz"
+
+##########################################
+# lzo check
+
+if test "$lzo" != "no" ; then
+    cat > $TMPC << EOF
+#include <lzo/lzo1x.h>
+int main(void) { lzo_version(); return 0; }
+EOF
+    if compile_prog "" "-llzo2" ; then
+        :
+    else
+        error_exit "lzo check failed" \
+            "Make sure to have the lzo libs and headers installed."
+    fi
+
+    libs_softmmu="$libs_softmmu -llzo2"
+fi
+
+##########################################
+# snappy check
+
+if test "$snappy" != "no" ; then
+    cat > $TMPC << EOF
+#include <snappy-c.h>
+int main(void) { snappy_max_compressed_length(4096); return 0; }
+EOF
+    if compile_prog "" "-lsnappy" ; then
+        :
+    else
+        error_exit "snappy check failed" \
+            "Make sure to have the snappy libs and headers installed."
+    fi
+
+    libs_softmmu="$libs_softmmu -lsnappy"
+fi
 
 ##########################################
 # libseccomp check
@@ -1804,12 +1991,22 @@ fi
 
 # Look for sdl configuration program (pkg-config or sdl-config).  Try
 # sdl-config even without cross prefix, and favour pkg-config over sdl-config.
-if test "`basename $sdl_config`" != sdl-config && ! has ${sdl_config}; then
+
-  sdl_config=sdl-config
+if test $sdlabi = "2.0"; then
+    sdl_config=$sdl2_config
+    sdlname=sdl2
+    sdlconfigname=sdl2_config
+else
+    sdlname=sdl
+    sdlconfigname=sdl_config
 fi
 
-if $pkg_config sdl --exists; then
+if test "`basename $sdl_config`" != $sdlconfigname && ! has ${sdl_config}; then
-  sdlconfig="$pkg_config sdl"
+  sdl_config=$sdlconfigname
+fi
+
+if $pkg_config $sdlname --exists; then
+  sdlconfig="$pkg_config $sdlname"
   _sdlversion=`$sdlconfig --modversion 2>/dev/null | sed 's/[^0-9]//g'`
 elif has ${sdl_config}; then
   sdlconfig="$sdl_config"
@@ -1936,6 +2133,30 @@ EOF
   fi
 fi
 
+##########################################
+# Quorum probe (check for gnutls)
+if test "$quorum" != "no" ; then
+cat > $TMPC <<EOF
+#include <gnutls/gnutls.h>
+#include <gnutls/crypto.h>
+int main(void) {char data[4096], digest[32];
+gnutls_hash_fast(GNUTLS_DIG_SHA256, data, 4096, digest);
+return 0;
+}
+EOF
+quorum_tls_cflags=`$pkg_config --cflags gnutls 2> /dev/null`
+quorum_tls_libs=`$pkg_config --libs gnutls 2> /dev/null`
+if compile_prog "$quorum_tls_cflags" "$quorum_tls_libs" ; then
+  qcow_tls=yes
+  libs_softmmu="$quorum_tls_libs $libs_softmmu"
+  libs_tools="$quorum_tls_libs $libs_softmmu"
+  QEMU_CFLAGS="$QEMU_CFLAGS $quorum_tls_cflags"
+else
+  echo "gnutls > 2.10.0 required to compile Quorum"
+  exit 1
+fi
+fi
+
 ##########################################
 # VNC SASL detection
 if test "$vnc" = "yes" -a "$vnc_sasl" != "no" ; then
@@ -2118,13 +2339,21 @@ EOF
 fi
 
 ##########################################
-# netmap headers probe
+# netmap support probe
+# Apart from looking for netmap headers, we make sure that the host API version
+# supports the netmap backend (>=11). The upper bound (15) is meant to simulate
+# a minor/major version number. Minor new features will be marked with values up
+# to 15, and if something happens that requires a change to the backend we will
+# move above 15, submit the backend fixes and modify this two bounds.
 if test "$netmap" != "no" ; then
   cat > $TMPC << EOF
 #include <inttypes.h>
 #include <net/if.h>
 #include <net/netmap.h>
 #include <net/netmap_user.h>
+#if (NETMAP_API < 11) || (NETMAP_API > 15)
+#error
+#endif
 int main(void) { return 0; }
 EOF
   if compile_prog "" "" ; then
@@ -2318,8 +2547,6 @@ EOF
   curl_libs=`$curlconfig --libs 2>/dev/null`
   if compile_prog "$curl_cflags" "$curl_libs" ; then
     curl=yes
-    libs_tools="$curl_libs $libs_tools"
-    libs_softmmu="$curl_libs $libs_softmmu"
   else
     if test "$curl" = "yes" ; then
       feature_not_found "curl" "Install libcurl devel"
@@ -2357,13 +2584,36 @@ if test "$mingw32" = yes; then
 else
     glib_req_ver=2.12
 fi
-if $pkg_config --atleast-version=$glib_req_ver gthread-2.0; then
+glib_modules=gthread-2.0
-    glib_cflags=`$pkg_config --cflags gthread-2.0`
+if test "$modules" = yes; then
-    glib_libs=`$pkg_config --libs gthread-2.0`
+    glib_modules="$glib_modules gmodule-2.0"
-    LIBS="$glib_libs $LIBS"
+fi
-    libs_qga="$glib_libs $libs_qga"
+
-else
+for i in $glib_modules; do
-    error_exit "glib-$glib_req_ver required to compile QEMU"
+    if $pkg_config --atleast-version=$glib_req_ver $i; then
+        glib_cflags=`$pkg_config --cflags $i`
+        glib_libs=`$pkg_config --libs $i`
+        CFLAGS="$glib_cflags $CFLAGS"
+        LIBS="$glib_libs $LIBS"
+        libs_qga="$glib_libs $libs_qga"
+    else
+        error_exit "glib-$glib_req_ver $i is required to compile QEMU"
+    fi
+done
+
+##########################################
+# SHA command probe for modules
+if test "$modules" = yes; then
+    shacmd_probe="sha1sum sha1 shasum"
+    for c in $shacmd_probe; do
+        if which $c &>/dev/null; then
+            shacmd="$c"
+            break
+        fi
+    done
+    if test "$shacmd" = ""; then
+        error_exit "one of the checksum commands is required to enable modules: $shacmd_probe"
+    fi
 fi
 
 ##########################################
@@ -2474,8 +2724,6 @@ EOF
   rbd_libs="-lrbd -lrados"
   if compile_prog "" "$rbd_libs" ; then
     rbd=yes
-    libs_tools="$rbd_libs $libs_tools"
-    libs_softmmu="$rbd_libs $libs_softmmu"
   else
     if test "$rbd" = "yes" ; then
       feature_not_found "rados block device" "Install librbd/ceph devel"
@@ -2492,9 +2740,6 @@ if test "$libssh2" != "no" ; then
     libssh2_cflags=`$pkg_config libssh2 --cflags`
     libssh2_libs=`$pkg_config libssh2 --libs`
     libssh2=yes
-    libs_tools="$libssh2_libs $libs_tools"
-    libs_softmmu="$libssh2_libs $libs_softmmu"
-    QEMU_CFLAGS="$QEMU_CFLAGS $libssh2_cflags"
   else
     if test "$libssh2" = "yes" ; then
       error_exit "libssh2 >= $min_libssh2_version required for --enable-libssh2"
@@ -2540,8 +2785,6 @@ int main(void) { io_setup(0, NULL); io_set_eventfd(NULL, 0); eventfd(0, 0); retu
 EOF
   if compile_prog "" "-laio" ; then
     linux_aio=yes
-    libs_softmmu="$libs_softmmu -laio"
-    libs_tools="$libs_tools -laio"
   else
     if test "$linux_aio" = "yes" ; then
       feature_not_found "linux AIO" "Install libaio devel"
@@ -2710,9 +2953,6 @@ if test "$glusterfs" != "no" ; then
     glusterfs="yes"
     glusterfs_cflags=`$pkg_config --cflags glusterfs-api`
     glusterfs_libs=`$pkg_config --libs glusterfs-api`
-    CFLAGS="$CFLAGS $glusterfs_cflags"
-    libs_tools="$glusterfs_libs $libs_tools"
-    libs_softmmu="$glusterfs_libs $libs_softmmu"
     if $pkg_config --atleast-version=5 glusterfs-api; then
       glusterfs_discard="yes"
     fi
@@ -3083,11 +3323,9 @@ EOF
     libiscsi="yes"
     libiscsi_cflags=$($pkg_config --cflags libiscsi)
     libiscsi_libs=$($pkg_config --libs libiscsi)
-    CFLAGS="$CFLAGS $libiscsi_cflags"
-    LIBS="$LIBS $libiscsi_libs"
   elif compile_prog "" "-liscsi" ; then
     libiscsi="yes"
-    LIBS="$LIBS -liscsi"
+    libiscsi_libs="-liscsi"
   else
     if test "$libiscsi" = "yes" ; then
       feature_not_found "libiscsi" "Install libiscsi devel"
@@ -3688,6 +3926,7 @@ if test "$mingw32" = "yes" ; then
 fi
 
 qemu_confdir=$sysconfdir$confsuffix
+qemu_moddir=$libdir$confsuffix
 qemu_datadir=$datadir$confsuffix
 qemu_localedir="$datadir/locale"
 
@@ -3778,6 +4017,7 @@ echo "Install prefix    $prefix"
 echo "BIOS directory    `eval echo $qemu_datadir`"
 echo "binary directory  `eval echo $bindir`"
 echo "library directory `eval echo $libdir`"
+echo "module directory  `eval echo $qemu_moddir`"
 echo "libexec directory `eval echo $libexecdir`"
 echo "include directory `eval echo $includedir`"
 echo "config directory  `eval echo $sysconfdir`"
@@ -3804,6 +4044,7 @@ echo "python            $python"
 if test "$slirp" = "yes" ; then
     echo "smbd              $smbd"
 fi
+echo "module support    $modules"
 echo "host CPU          $cpu"
 echo "host big endian   $bigendian"
 echo "target list       $target_list"
@@ -3893,6 +4134,9 @@ echo "libssh2 support   $libssh2"
 echo "TPM passthrough   $tpm_passthrough"
 echo "QOM debugging     $qom_cast_debug"
 echo "vhdx              $vhdx"
+echo "Quorum            $quorum"
+echo "lzo support       $lzo"
+echo "snappy support    $snappy"
 
 if test "$sdl_too_old" = "yes"; then
 echo "-> Your SDL version is too old - please upgrade to have SDL support"
@@ -3916,6 +4160,7 @@ echo "sysconfdir=$sysconfdir" >> $config_host_mak
 echo "qemu_confdir=$qemu_confdir" >> $config_host_mak
 echo "qemu_datadir=$qemu_datadir" >> $config_host_mak
 echo "qemu_docdir=$qemu_docdir" >> $config_host_mak
+echo "qemu_moddir=$qemu_moddir" >> $config_host_mak
 if test "$mingw32" = "no" ; then
   echo "qemu_localstatedir=$local_statedir" >> $config_host_mak
 fi
@@ -4048,6 +4293,12 @@ echo "TARGET_DIRS=$target_list" >> $config_host_mak
 if [ "$docs" = "yes" ] ; then
   echo "BUILD_DOCS=yes" >> $config_host_mak
 fi
+if test "$modules" = "yes"; then
+  # $shacmd can generate a hash started with digit, which the compiler doesn't
+  # like as an symbol. So prefix it with an underscore
+  echo "CONFIG_STAMP=_`(echo $qemu_version; echo $pkgversion; cat $0) | $shacmd - | cut -f1 -d\ `" >> $config_host_mak
+  echo "CONFIG_MODULES=y" >> $config_host_mak
+fi
 if test "$sdl" = "yes" ; then
   echo "CONFIG_SDL=y" >> $config_host_mak
   echo "SDL_CFLAGS=$sdl_cflags" >> $config_host_mak
@@ -4119,8 +4370,9 @@ if test "$bswap_h" = "yes" ; then
   echo "CONFIG_MACHINE_BSWAP_H=y" >> $config_host_mak
 fi
 if test "$curl" = "yes" ; then
-  echo "CONFIG_CURL=y" >> $config_host_mak
+  echo "CONFIG_CURL=m" >> $config_host_mak
   echo "CURL_CFLAGS=$curl_cflags" >> $config_host_mak
+  echo "CURL_LIBS=$curl_libs" >> $config_host_mak
 fi
 if test "$brlapi" = "yes" ; then
   echo "CONFIG_BRLAPI=y" >> $config_host_mak
@@ -4208,11 +4460,21 @@ if test "$glx" = "yes" ; then
   echo "GLX_LIBS=$glx_libs" >> $config_host_mak
 fi
 
+if test "$lzo" = "yes" ; then
+  echo "CONFIG_LZO=y" >> $config_host_mak
+fi
+
+if test "$snappy" = "yes" ; then
+  echo "CONFIG_SNAPPY=y" >> $config_host_mak
+fi
+
 if test "$libiscsi" = "yes" ; then
-  echo "CONFIG_LIBISCSI=y" >> $config_host_mak
+  echo "CONFIG_LIBISCSI=m" >> $config_host_mak
   if test "$libiscsi_version" = "1.4.0"; then
     echo "CONFIG_LIBISCSI_1_4=y" >> $config_host_mak
   fi
+  echo "LIBISCSI_CFLAGS=$libiscsi_cflags" >> $config_host_mak
+  echo "LIBISCSI_LIBS=$libiscsi_libs" >> $config_host_mak
 fi
 
 if test "$libnfs" = "yes" ; then
@@ -4237,7 +4499,9 @@ if test "$qom_cast_debug" = "yes" ; then
   echo "CONFIG_QOM_CAST_DEBUG=y" >> $config_host_mak
 fi
 if test "$rbd" = "yes" ; then
-  echo "CONFIG_RBD=y" >> $config_host_mak
+  echo "CONFIG_RBD=m" >> $config_host_mak
+  echo "RBD_CFLAGS=$rbd_cflags" >> $config_host_mak
+  echo "RBD_LIBS=$rbd_libs" >> $config_host_mak
 fi
 
 echo "CONFIG_COROUTINE_BACKEND=$coroutine" >> $config_host_mak
@@ -4280,7 +4544,9 @@ if test "$getauxval" = "yes" ; then
 fi
 
 if test "$glusterfs" = "yes" ; then
-  echo "CONFIG_GLUSTERFS=y" >> $config_host_mak
+  echo "CONFIG_GLUSTERFS=m" >> $config_host_mak
+  echo "GLUSTERFS_CFLAGS=$glusterfs_cflags" >> $config_host_mak
+  echo "GLUSTERFS_LIBS=$glusterfs_libs" >> $config_host_mak
 fi
 
 if test "$glusterfs_discard" = "yes" ; then
@@ -4292,7 +4558,13 @@ if test "$glusterfs_zerofill" = "yes" ; then
 fi
 
 if test "$libssh2" = "yes" ; then
-  echo "CONFIG_LIBSSH2=y" >> $config_host_mak
+  echo "CONFIG_LIBSSH2=m" >> $config_host_mak
+  echo "LIBSSH2_CFLAGS=$libssh2_cflags" >> $config_host_mak
+  echo "LIBSSH2_LIBS=$libssh2_libs" >> $config_host_mak
+fi
+
+if test "$quorum" = "yes" ; then
+  echo "CONFIG_QUORUM=y" >> $config_host_mak
 fi
 
 if test "$virtio_blk_data_plane" = "yes" ; then
@@ -4423,6 +4695,8 @@ echo "LIBTOOLFLAGS=$LIBTOOLFLAGS" >> $config_host_mak
 echo "LIBS+=$LIBS" >> $config_host_mak
 echo "LIBS_TOOLS+=$libs_tools" >> $config_host_mak
 echo "EXESUF=$EXESUF" >> $config_host_mak
+echo "DSOSUF=$DSOSUF" >> $config_host_mak
+echo "LDFLAGS_SHARED=$LDFLAGS_SHARED" >> $config_host_mak
 echo "LIBS_QGA+=$libs_qga" >> $config_host_mak
 echo "POD2MAN=$POD2MAN" >> $config_host_mak
 echo "TRANSLATE_OPT_CFLAGS=$TRANSLATE_OPT_CFLAGS" >> $config_host_mak

cpu-exec.c

@@ -477,7 +477,7 @@ int cpu_exec(CPUArchState *env)
                     }
 #elif defined(TARGET_ARM)
                     if (interrupt_request & CPU_INTERRUPT_FIQ
-                        && !(env->uncached_cpsr & CPSR_F)) {
+                        && !(env->daif & PSTATE_F)) {
                         env->exception_index = EXCP_FIQ;
                         cc->do_interrupt(cpu);
                         next_tb = 0;
@@ -493,7 +493,7 @@ int cpu_exec(CPUArchState *env)
                        pc contains a magic address.  */
                     if (interrupt_request & CPU_INTERRUPT_HARD
                         && ((IS_M(env) && env->regs[15] < 0xfffffff0)
-                            || !(env->uncached_cpsr & CPSR_I))) {
+                            || !(env->daif & PSTATE_I))) {
                         env->exception_index = EXCP_IRQ;
                         cc->do_interrupt(cpu);
                         next_tb = 0;

default-configs/ppc-softmmu.mak

@@ -47,4 +47,5 @@ CONFIG_E500=y
 CONFIG_OPENPIC_KVM=$(and $(CONFIG_E500),$(CONFIG_KVM))
 # For PReP
 CONFIG_MC146818RTC=y
+CONFIG_ETSEC=y
 CONFIG_ISA_TESTDEV=y

default-configs/s390x-softmmu.mak

@@ -1,2 +1,3 @@
 CONFIG_VIRTIO=y
 CONFIG_SCLPCONSOLE=y
+CONFIG_S390_FLIC=$(CONFIG_KVM)

default-configs/sparc-softmmu.mak

@@ -10,6 +10,7 @@ CONFIG_EMPTY_SLOT=y
 CONFIG_PCNET_COMMON=y
 CONFIG_LANCE=y
 CONFIG_TCX=y
+CONFIG_CG3=y
 CONFIG_SLAVIO=y
 CONFIG_CS4231=y
 CONFIG_GRLIB=y

docs/qmp/qmp-events.txt

@@ -225,6 +225,45 @@ Data:
   "timestamp": { "seconds": 1368697518, "microseconds": 326866 } }
 }
 
+QUORUM_FAILURE
+--------------
+
+Emitted by the Quorum block driver if it fails to establish a quorum.
+
+Data:
+
+- "reference":    device name if defined else node name.
+- "sector-num":   Number of the first sector of the failed read operation.
+- "sector-count": Failed read operation sector count.
+
+Example:
+
+{ "event": "QUORUM_FAILURE",
+     "data": { "reference": "usr1", "sector-num": 345435, "sector-count": 5 },
+     "timestamp": { "seconds": 1344522075, "microseconds": 745528 } }
+
+QUORUM_REPORT_BAD
+-----------------
+
+Emitted to report a corruption of a Quorum file.
+
+Data:
+
+- "error":        Error message (json-string, optional)
+                  Only present on failure.  This field contains a human-readable
+                  error message.  There are no semantics other than that the
+                  block layer reported an error and clients should not try to
+                  interpret the error string.
+- "node-name":    The graph node name of the block driver state.
+- "sector-num":   Number of the first sector of the failed read operation.
+- "sector-count": Failed read operation sector count.
+
+Example:
+
+{ "event": "QUORUM_REPORT_BAD",
+     "data": { "node-name": "1.raw", "sector-num": 345435, "sector-count": 5 },
+     "timestamp": { "seconds": 1344522075, "microseconds": 745528 } }
+
 RESET
 -----
 

docs/rdma.txt

@@ -66,7 +66,7 @@ bulk-phase round of the migration and can be enabled for extremely
 high-performance RDMA hardware using the following command:
 
 QEMU Monitor Command:
-$ migrate_set_capability x-rdma-pin-all on # disabled by default
+$ migrate_set_capability rdma-pin-all on # disabled by default
 
 Performing this action will cause all 8GB to be pinned, so if that's
 not what you want, then please ignore this step altogether.
@@ -93,12 +93,12 @@ $ migrate_set_speed 40g # or whatever is the MAX of your RDMA device
 
 Next, on the destination machine, add the following to the QEMU command line:
 
-qemu ..... -incoming x-rdma:host:port
+qemu ..... -incoming rdma:host:port
 
 Finally, perform the actual migration on the source machine:
 
 QEMU Monitor Command:
-$ migrate -d x-rdma:host:port
+$ migrate -d rdma:host:port
 
 PERFORMANCE
 ===========
@@ -120,8 +120,8 @@ For example, in the same 8GB RAM example with all 8GB of memory in
 active use and the VM itself is completely idle using the same 40 gbps
 infiniband link:
 
-1. x-rdma-pin-all disabled total time: approximately 7.5 seconds @ 9.5 Gbps
+1. rdma-pin-all disabled total time: approximately 7.5 seconds @ 9.5 Gbps
-2. x-rdma-pin-all enabled total time: approximately 4 seconds @ 26 Gbps
+2. rdma-pin-all enabled total time: approximately 4 seconds @ 26 Gbps
 
 These numbers would of course scale up to whatever size virtual machine
 you have to migrate using RDMA.
@@ -407,18 +407,14 @@ socket is broken during a non-RDMA based migration.
 
 TODO:
 =====
-1. 'migrate x-rdma:host:port' and '-incoming x-rdma' options will be
+1. Currently, 'ulimit -l' mlock() limits as well as cgroups swap limits
-   renamed to 'rdma' after the experimental phase of this work has
-   completed upstream.
-2. Currently, 'ulimit -l' mlock() limits as well as cgroups swap limits
    are not compatible with infinband memory pinning and will result in
    an aborted migration (but with the source VM left unaffected).
-3. Use of the recent /proc/<pid>/pagemap would likely speed up
+2. Use of the recent /proc/<pid>/pagemap would likely speed up
    the use of KSM and ballooning while using RDMA.
-4. Also, some form of balloon-device usage tracking would also
+3. Also, some form of balloon-device usage tracking would also
    help alleviate some issues.
-5. Move UNREGISTER requests to a separate thread.
+4. Use LRU to provide more fine-grained direction of UNREGISTER
-6. Use LRU to provide more fine-grained direction of UNREGISTER
    requests for unpinning memory in an overcommitted environment.
-7. Expose UNREGISTER support to the user by way of workload-specific
+5. Expose UNREGISTER support to the user by way of workload-specific
    hints about application behavior.

exec.c

@@ -17,9 +17,7 @@
  * License along with this library; if not, see <http://www.gnu.org/licenses/>.
  */
 #include "config.h"
-#ifdef _WIN32
+#ifndef _WIN32
-#include <windows.h>
-#else
 #include <sys/types.h>
 #include <sys/mman.h>
 #endif

fsdev/Makefile.objs

@@ -1,4 +1,6 @@
-ifeq ($(CONFIG_REALLY_VIRTFS),y)
+ifeq ($(CONFIG_VIRTIO)$(CONFIG_VIRTFS)$(CONFIG_PCI),yyy)
+# Lots of the fsdev/9pcode is pulled in by vl.c via qemu_fsdev_add.
+# only pull in the actual virtio-9p device if we also enabled virtio.
 common-obj-y = qemu-fsdev.o virtio-9p-marshal.o
 else
 common-obj-y = qemu-fsdev-dummy.o

fsdev/virtfs-proxy-helper.c

@@ -595,7 +595,7 @@ static int do_readlink(struct iovec *iovec, struct iovec *out_iovec)
     }
     buffer = g_malloc(size);
     v9fs_string_init(&target);
-    retval = readlink(path.data, buffer, size);
+    retval = readlink(path.data, buffer, size - 1);
     if (retval > 0) {
         buffer[retval] = '\0';
         v9fs_string_sprintf(&target, "%s", buffer);

hmp.c

@@ -1311,8 +1311,11 @@ void hmp_dump_guest_memory(Monitor *mon, const QDict *qdict)
     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 (has_begin) {
@@ -1325,7 +1328,7 @@ 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,
-                          &errp);
+                          has_format, dump_format, &errp);
     hmp_handle_error(mon, &errp);
     g_free(prot);
 }

hw/9pfs/cofs.c

@@ -17,35 +17,55 @@
 #include "block/coroutine.h"
 #include "virtio-9p-coth.h"
 
+static ssize_t __readlink(V9fsState *s, V9fsPath *path, V9fsString *buf)
+{
+    ssize_t len, maxlen = PATH_MAX;
+
+    buf->data = g_malloc(PATH_MAX);
+    for(;;) {
+        len = s->ops->readlink(&s->ctx, path, buf->data, maxlen);
+        if (len < 0) {
+            g_free(buf->data);
+            buf->data = NULL;
+            buf->size = 0;
+            break;
+        } else if (len == maxlen) {
+            /*
+             * We dodn't have space to put the NULL or we have more
+             * to read. Increase the size and try again
+             */
+            maxlen *= 2;
+            g_free(buf->data);
+            buf->data = g_malloc(maxlen);
+            continue;
+        }
+        /*
+         * Null terminate the readlink output
+         */
+        buf->data[len] = '\0';
+        buf->size = len;
+        break;
+    }
+    return len;
+}
+
 int v9fs_co_readlink(V9fsPDU *pdu, V9fsPath *path, V9fsString *buf)
 {
     int err;
-    ssize_t len;
     V9fsState *s = pdu->s;
 
     if (v9fs_request_cancelled(pdu)) {
         return -EINTR;
     }
-    buf->data = g_malloc(PATH_MAX);
     v9fs_path_read_lock(s);
     v9fs_co_run_in_worker(
         {
-            len = s->ops->readlink(&s->ctx, path,
+            err = __readlink(s, path, buf);
-                                   buf->data, PATH_MAX - 1);
+            if (err < 0) {
-            if (len > -1) {
-                buf->size = len;
-                buf->data[len] = 0;
-                err = 0;
-            } else {
                 err = -errno;
             }
         });
     v9fs_path_unlock(s);
-    if (err) {
-        g_free(buf->data);
-        buf->data = NULL;
-        buf->size = 0;
-    }
     return err;
 }
 

hw/9pfs/virtio-9p-handle.c

@@ -498,7 +498,7 @@ static int handle_lremovexattr(FsContext *ctx, V9fsPath *fs_path,
 static int handle_name_to_path(FsContext *ctx, V9fsPath *dir_path,
                               const char *name, V9fsPath *target)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
     struct file_handle *fh;
     int dirfd, ret, mnt_id;
     struct handle_data *data = (struct handle_data *)ctx->private;
@@ -513,7 +513,9 @@ static int handle_name_to_path(FsContext *ctx, V9fsPath *dir_path,
         dirfd = open_by_handle(data->mountfd, dir_path->data, O_PATH);
     } else {
         /* relative to export root */
-        dirfd = open(rpath(ctx, ".", buffer), O_DIRECTORY);
+        buffer = rpath(ctx, ".");
+        dirfd = open(buffer, O_DIRECTORY);
+        g_free(buffer);
     }
     if (dirfd < 0) {
         return dirfd;
@@ -521,7 +523,7 @@ static int handle_name_to_path(FsContext *ctx, V9fsPath *dir_path,
     fh = g_malloc(sizeof(struct file_handle) + data->handle_bytes);
     fh->handle_bytes = data->handle_bytes;
     /* add a "./" at the beginning of the path */
-    snprintf(buffer, PATH_MAX, "./%s", name);
+    buffer = g_strdup_printf("./%s", name);
     /* flag = 0 imply don't follow symlink */
     ret = name_to_handle(dirfd, buffer, fh, &mnt_id, 0);
     if (!ret) {
@@ -531,6 +533,7 @@ static int handle_name_to_path(FsContext *ctx, V9fsPath *dir_path,
         g_free(fh);
     }
     close(dirfd);
+    g_free(buffer);
     return ret;
 }
 

hw/9pfs/virtio-9p-local.c

@@ -42,18 +42,18 @@
 
 #define VIRTFS_META_DIR ".virtfs_metadata"
 
-static const char *local_mapped_attr_path(FsContext *ctx,
+static char *local_mapped_attr_path(FsContext *ctx, const char *path)
-                                          const char *path, char *buffer)
 {
     char *dir_name;
     char *tmp_path = g_strdup(path);
     char *base_name = basename(tmp_path);
+    char *buffer;
 
     /* NULL terminate the directory */
     dir_name = tmp_path;
     *(base_name - 1) = '\0';
 
-    snprintf(buffer, PATH_MAX, "%s/%s/%s/%s",
+    buffer = g_strdup_printf("%s/%s/%s/%s",
              ctx->fs_root, dir_name, VIRTFS_META_DIR, base_name);
     g_free(tmp_path);
     return buffer;
@@ -92,10 +92,11 @@ static void local_mapped_file_attr(FsContext *ctx, const char *path,
 {
     FILE *fp;
     char buf[ATTR_MAX];
-    char attr_path[PATH_MAX];
+    char *attr_path;
 
-    local_mapped_attr_path(ctx, path, attr_path);
+    attr_path = local_mapped_attr_path(ctx, path);
     fp = local_fopen(attr_path, "r");
+    g_free(attr_path);
     if (!fp) {
         return;
     }
@@ -118,12 +119,13 @@ static void local_mapped_file_attr(FsContext *ctx, const char *path,
 static int local_lstat(FsContext *fs_ctx, V9fsPath *fs_path, struct stat *stbuf)
 {
     int err;
-    char buffer[PATH_MAX];
+    char *buffer;
     char *path = fs_path->data;
 
-    err =  lstat(rpath(fs_ctx, path, buffer), stbuf);
+    buffer = rpath(fs_ctx, path);
+    err =  lstat(buffer, stbuf);
     if (err) {
-        return err;
+        goto err_out;
     }
     if (fs_ctx->export_flags & V9FS_SM_MAPPED) {
         /* Actual credentials are part of extended attrs */
@@ -131,41 +133,42 @@ static int local_lstat(FsContext *fs_ctx, V9fsPath *fs_path, struct stat *stbuf)
         gid_t tmp_gid;
         mode_t tmp_mode;
         dev_t tmp_dev;
-        if (getxattr(rpath(fs_ctx, path, buffer), "user.virtfs.uid", &tmp_uid,
+        if (getxattr(buffer, "user.virtfs.uid", &tmp_uid, sizeof(uid_t)) > 0) {
-                    sizeof(uid_t)) > 0) {
             stbuf->st_uid = tmp_uid;
         }
-        if (getxattr(rpath(fs_ctx, path, buffer), "user.virtfs.gid", &tmp_gid,
+        if (getxattr(buffer, "user.virtfs.gid", &tmp_gid, sizeof(gid_t)) > 0) {
-                    sizeof(gid_t)) > 0) {
             stbuf->st_gid = tmp_gid;
         }
-        if (getxattr(rpath(fs_ctx, path, buffer), "user.virtfs.mode",
+        if (getxattr(buffer, "user.virtfs.mode",
                     &tmp_mode, sizeof(mode_t)) > 0) {
             stbuf->st_mode = tmp_mode;
         }
-        if (getxattr(rpath(fs_ctx, path, buffer), "user.virtfs.rdev", &tmp_dev,
+        if (getxattr(buffer, "user.virtfs.rdev", &tmp_dev, sizeof(dev_t)) > 0) {
-                        sizeof(dev_t)) > 0) {
                 stbuf->st_rdev = tmp_dev;
         }
     } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
         local_mapped_file_attr(fs_ctx, path, stbuf);
     }
+
+err_out:
+    g_free(buffer);
     return err;
 }
 
 static int local_create_mapped_attr_dir(FsContext *ctx, const char *path)
 {
     int err;
-    char attr_dir[PATH_MAX];
+    char *attr_dir;
     char *tmp_path = g_strdup(path);
 
-    snprintf(attr_dir, PATH_MAX, "%s/%s/%s",
+    attr_dir = g_strdup_printf("%s/%s/%s",
              ctx->fs_root, dirname(tmp_path), VIRTFS_META_DIR);
 
     err = mkdir(attr_dir, 0700);
     if (err < 0 && errno == EEXIST) {
         err = 0;
     }
+    g_free(attr_dir);
     g_free(tmp_path);
     return err;
 }
@@ -176,10 +179,11 @@ static int local_set_mapped_file_attr(FsContext *ctx,
     FILE *fp;
     int ret = 0;
     char buf[ATTR_MAX];
-    char attr_path[PATH_MAX];
+    char *attr_path;
     int uid = -1, gid = -1, mode = -1, rdev = -1;
 
-    fp = local_fopen(local_mapped_attr_path(ctx, path, attr_path), "r");
+    attr_path = local_mapped_attr_path(ctx, path);
+    fp = local_fopen(attr_path, "r");
     if (!fp) {
         goto create_map_file;
     }
@@ -241,6 +245,7 @@ update_map_file:
     fclose(fp);
 
 err_out:
+    g_free(attr_path);
     return ret;
 }
 
@@ -282,36 +287,43 @@ static int local_set_xattr(const char *path, FsCred *credp)
 static int local_post_create_passthrough(FsContext *fs_ctx, const char *path,
                                          FsCred *credp)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
 
-    if (lchown(rpath(fs_ctx, path, buffer), credp->fc_uid,
+    buffer = rpath(fs_ctx, path);
-                credp->fc_gid) < 0) {
+    if (lchown(buffer, credp->fc_uid, credp->fc_gid) < 0) {
         /*
          * If we fail to change ownership and if we are
          * using security model none. Ignore the error
          */
         if ((fs_ctx->export_flags & V9FS_SEC_MASK) != V9FS_SM_NONE) {
-            return -1;
+            goto err;
         }
     }
 
-    if (chmod(rpath(fs_ctx, path, buffer), credp->fc_mode & 07777) < 0) {
+    if (chmod(buffer, credp->fc_mode & 07777) < 0) {
-        return -1;
+        goto err;
     }
+
+    g_free(buffer);
     return 0;
+err:
+    g_free(buffer);
+    return -1;
 }
 
 static ssize_t local_readlink(FsContext *fs_ctx, V9fsPath *fs_path,
                               char *buf, size_t bufsz)
 {
     ssize_t tsize = -1;
-    char buffer[PATH_MAX];
+    char *buffer;
     char *path = fs_path->data;
 
     if ((fs_ctx->export_flags & V9FS_SM_MAPPED) ||
         (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE)) {
         int fd;
-        fd = open(rpath(fs_ctx, path, buffer), O_RDONLY | O_NOFOLLOW);
+        buffer = rpath(fs_ctx, path);
+        fd = open(buffer, O_RDONLY | O_NOFOLLOW);
+        g_free(buffer);
         if (fd == -1) {
             return -1;
         }
@@ -322,7 +334,9 @@ static ssize_t local_readlink(FsContext *fs_ctx, V9fsPath *fs_path,
         return tsize;
     } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) ||
                (fs_ctx->export_flags & V9FS_SM_NONE)) {
-        tsize = readlink(rpath(fs_ctx, path, buffer), buf, bufsz);
+        buffer = rpath(fs_ctx, path);
+        tsize = readlink(buffer, buf, bufsz);
+        g_free(buffer);
     }
     return tsize;
 }
@@ -340,20 +354,24 @@ static int local_closedir(FsContext *ctx, V9fsFidOpenState *fs)
 static int local_open(FsContext *ctx, V9fsPath *fs_path,
                       int flags, V9fsFidOpenState *fs)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
     char *path = fs_path->data;
 
-    fs->fd = open(rpath(ctx, path, buffer), flags | O_NOFOLLOW);
+    buffer = rpath(ctx, path);
+    fs->fd = open(buffer, flags | O_NOFOLLOW);
+    g_free(buffer);
     return fs->fd;
 }
 
 static int local_opendir(FsContext *ctx,
                          V9fsPath *fs_path, V9fsFidOpenState *fs)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
     char *path = fs_path->data;
 
-    fs->dir = opendir(rpath(ctx, path, buffer));
+    buffer = rpath(ctx, path);
+    fs->dir = opendir(buffer);
+    g_free(buffer);
     if (!fs->dir) {
         return -1;
     }
@@ -441,18 +459,23 @@ static ssize_t local_pwritev(FsContext *ctx, V9fsFidOpenState *fs,
 
 static int local_chmod(FsContext *fs_ctx, V9fsPath *fs_path, FsCred *credp)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
+    int ret = -1;
     char *path = fs_path->data;
 
     if (fs_ctx->export_flags & V9FS_SM_MAPPED) {
-        return local_set_xattr(rpath(fs_ctx, path, buffer), credp);
+        buffer = rpath(fs_ctx, path);
+        ret = local_set_xattr(buffer, credp);
+        g_free(buffer);
     } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
         return local_set_mapped_file_attr(fs_ctx, path, credp);
     } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) ||
                (fs_ctx->export_flags & V9FS_SM_NONE)) {
-        return chmod(rpath(fs_ctx, path, buffer), credp->fc_mode);
+        buffer = rpath(fs_ctx, path);
+        ret = chmod(buffer, credp->fc_mode);
+        g_free(buffer);
     }
-    return -1;
+    return ret;
 }
 
 static int local_mknod(FsContext *fs_ctx, V9fsPath *dir_path,
@@ -462,7 +485,7 @@ static int local_mknod(FsContext *fs_ctx, V9fsPath *dir_path,
     int err = -1;
     int serrno = 0;
     V9fsString fullname;
-    char buffer[PATH_MAX];
+    char *buffer;
 
     v9fs_string_init(&fullname);
     v9fs_string_sprintf(&fullname, "%s/%s", dir_path->data, name);
@@ -470,21 +493,23 @@ static int local_mknod(FsContext *fs_ctx, V9fsPath *dir_path,
 
     /* Determine the security model */
     if (fs_ctx->export_flags & V9FS_SM_MAPPED) {
-        err = mknod(rpath(fs_ctx, path, buffer),
+        buffer = rpath(fs_ctx, path);
-                SM_LOCAL_MODE_BITS|S_IFREG, 0);
+        err = mknod(buffer, SM_LOCAL_MODE_BITS|S_IFREG, 0);
         if (err == -1) {
+            g_free(buffer);
             goto out;
         }
-        err = local_set_xattr(rpath(fs_ctx, path, buffer), credp);
+        err = local_set_xattr(buffer, credp);
         if (err == -1) {
             serrno = errno;
             goto err_end;
         }
     } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
 
-        err = mknod(rpath(fs_ctx, path, buffer),
+        buffer = rpath(fs_ctx, path);
-                    SM_LOCAL_MODE_BITS|S_IFREG, 0);
+        err = mknod(buffer, SM_LOCAL_MODE_BITS|S_IFREG, 0);
         if (err == -1) {
+            g_free(buffer);
             goto out;
         }
         err = local_set_mapped_file_attr(fs_ctx, path, credp);
@@ -494,9 +519,10 @@ static int local_mknod(FsContext *fs_ctx, V9fsPath *dir_path,
         }
     } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) ||
                (fs_ctx->export_flags & V9FS_SM_NONE)) {
-        err = mknod(rpath(fs_ctx, path, buffer), credp->fc_mode,
+        buffer = rpath(fs_ctx, path);
-                credp->fc_rdev);
+        err = mknod(buffer, credp->fc_mode, credp->fc_rdev);
         if (err == -1) {
+            g_free(buffer);
             goto out;
         }
         err = local_post_create_passthrough(fs_ctx, path, credp);
@@ -508,8 +534,9 @@ static int local_mknod(FsContext *fs_ctx, V9fsPath *dir_path,
     goto out;
 
 err_end:
-    remove(rpath(fs_ctx, path, buffer));
+    remove(buffer);
     errno = serrno;
+    g_free(buffer);
 out:
     v9fs_string_free(&fullname);
     return err;
@@ -522,7 +549,7 @@ static int local_mkdir(FsContext *fs_ctx, V9fsPath *dir_path,
     int err = -1;
     int serrno = 0;
     V9fsString fullname;
-    char buffer[PATH_MAX];
+    char *buffer;
 
     v9fs_string_init(&fullname);
     v9fs_string_sprintf(&fullname, "%s/%s", dir_path->data, name);
@@ -530,19 +557,23 @@ static int local_mkdir(FsContext *fs_ctx, V9fsPath *dir_path,
 
     /* Determine the security model */
     if (fs_ctx->export_flags & V9FS_SM_MAPPED) {
-        err = mkdir(rpath(fs_ctx, path, buffer), SM_LOCAL_DIR_MODE_BITS);
+        buffer = rpath(fs_ctx, path);
+        err = mkdir(buffer, SM_LOCAL_DIR_MODE_BITS);
         if (err == -1) {
+            g_free(buffer);
             goto out;
         }
         credp->fc_mode = credp->fc_mode|S_IFDIR;
-        err = local_set_xattr(rpath(fs_ctx, path, buffer), credp);
+        err = local_set_xattr(buffer, credp);
         if (err == -1) {
             serrno = errno;
             goto err_end;
         }
     } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
-        err = mkdir(rpath(fs_ctx, path, buffer), SM_LOCAL_DIR_MODE_BITS);
+        buffer = rpath(fs_ctx, path);
+        err = mkdir(buffer, SM_LOCAL_DIR_MODE_BITS);
         if (err == -1) {
+            g_free(buffer);
             goto out;
         }
         credp->fc_mode = credp->fc_mode|S_IFDIR;
@@ -553,8 +584,10 @@ static int local_mkdir(FsContext *fs_ctx, V9fsPath *dir_path,
         }
     } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) ||
                (fs_ctx->export_flags & V9FS_SM_NONE)) {
-        err = mkdir(rpath(fs_ctx, path, buffer), credp->fc_mode);
+        buffer = rpath(fs_ctx, path);
+        err = mkdir(buffer, credp->fc_mode);
         if (err == -1) {
+            g_free(buffer);
             goto out;
         }
         err = local_post_create_passthrough(fs_ctx, path, credp);
@@ -566,8 +599,9 @@ static int local_mkdir(FsContext *fs_ctx, V9fsPath *dir_path,
     goto out;
 
 err_end:
-    remove(rpath(fs_ctx, path, buffer));
+    remove(buffer);
     errno = serrno;
+    g_free(buffer);
 out:
     v9fs_string_free(&fullname);
     return err;
@@ -626,7 +660,7 @@ static int local_open2(FsContext *fs_ctx, V9fsPath *dir_path, const char *name,
     int err = -1;
     int serrno = 0;
     V9fsString fullname;
-    char buffer[PATH_MAX];
+    char *buffer;
 
     /*
      * Mark all the open to not follow symlinks
@@ -639,21 +673,25 @@ static int local_open2(FsContext *fs_ctx, V9fsPath *dir_path, const char *name,
 
     /* Determine the security model */
     if (fs_ctx->export_flags & V9FS_SM_MAPPED) {
-        fd = open(rpath(fs_ctx, path, buffer), flags, SM_LOCAL_MODE_BITS);
+        buffer = rpath(fs_ctx, path);
+        fd = open(buffer, flags, SM_LOCAL_MODE_BITS);
         if (fd == -1) {
+            g_free(buffer);
             err = fd;
             goto out;
         }
         credp->fc_mode = credp->fc_mode|S_IFREG;
         /* Set cleint credentials in xattr */
-        err = local_set_xattr(rpath(fs_ctx, path, buffer), credp);
+        err = local_set_xattr(buffer, credp);
         if (err == -1) {
             serrno = errno;
             goto err_end;
         }
     } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
-        fd = open(rpath(fs_ctx, path, buffer), flags, SM_LOCAL_MODE_BITS);
+        buffer = rpath(fs_ctx, path);
+        fd = open(buffer, flags, SM_LOCAL_MODE_BITS);
         if (fd == -1) {
+            g_free(buffer);
             err = fd;
             goto out;
         }
@@ -666,8 +704,10 @@ static int local_open2(FsContext *fs_ctx, V9fsPath *dir_path, const char *name,
         }
     } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) ||
                (fs_ctx->export_flags & V9FS_SM_NONE)) {
-        fd = open(rpath(fs_ctx, path, buffer), flags, credp->fc_mode);
+        buffer = rpath(fs_ctx, path);
+        fd = open(buffer, flags, credp->fc_mode);
         if (fd == -1) {
+            g_free(buffer);
             err = fd;
             goto out;
         }
@@ -683,8 +723,9 @@ static int local_open2(FsContext *fs_ctx, V9fsPath *dir_path, const char *name,
 
 err_end:
     close(fd);
-    remove(rpath(fs_ctx, path, buffer));
+    remove(buffer);
     errno = serrno;
+    g_free(buffer);
 out:
     v9fs_string_free(&fullname);
     return err;
@@ -698,7 +739,7 @@ static int local_symlink(FsContext *fs_ctx, const char *oldpath,
     int serrno = 0;
     char *newpath;
     V9fsString fullname;
-    char buffer[PATH_MAX];
+    char *buffer;
 
     v9fs_string_init(&fullname);
     v9fs_string_sprintf(&fullname, "%s/%s", dir_path->data, name);
@@ -708,10 +749,10 @@ static int local_symlink(FsContext *fs_ctx, const char *oldpath,
     if (fs_ctx->export_flags & V9FS_SM_MAPPED) {
         int fd;
         ssize_t oldpath_size, write_size;
-        fd = open(rpath(fs_ctx, newpath, buffer),
+        buffer = rpath(fs_ctx, newpath);
-                  O_CREAT|O_EXCL|O_RDWR|O_NOFOLLOW,
+        fd = open(buffer, O_CREAT|O_EXCL|O_RDWR|O_NOFOLLOW, SM_LOCAL_MODE_BITS);
-                  SM_LOCAL_MODE_BITS);
         if (fd == -1) {
+            g_free(buffer);
             err = fd;
             goto out;
         }
@@ -730,7 +771,7 @@ static int local_symlink(FsContext *fs_ctx, const char *oldpath,
         close(fd);
         /* Set cleint credentials in symlink's xattr */
         credp->fc_mode = credp->fc_mode|S_IFLNK;
-        err = local_set_xattr(rpath(fs_ctx, newpath, buffer), credp);
+        err = local_set_xattr(buffer, credp);
         if (err == -1) {
             serrno = errno;
             goto err_end;
@@ -738,10 +779,10 @@ static int local_symlink(FsContext *fs_ctx, const char *oldpath,
     } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
         int fd;
         ssize_t oldpath_size, write_size;
-        fd = open(rpath(fs_ctx, newpath, buffer),
+        buffer = rpath(fs_ctx, newpath);
-                  O_CREAT|O_EXCL|O_RDWR|O_NOFOLLOW,
+        fd = open(buffer, O_CREAT|O_EXCL|O_RDWR|O_NOFOLLOW, SM_LOCAL_MODE_BITS);
-                  SM_LOCAL_MODE_BITS);
         if (fd == -1) {
+            g_free(buffer);
             err = fd;
             goto out;
         }
@@ -767,12 +808,13 @@ static int local_symlink(FsContext *fs_ctx, const char *oldpath,
         }
     } else if ((fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) ||
                (fs_ctx->export_flags & V9FS_SM_NONE)) {
-        err = symlink(oldpath, rpath(fs_ctx, newpath, buffer));
+        buffer = rpath(fs_ctx, newpath);
+        err = symlink(oldpath, buffer);
         if (err) {
+            g_free(buffer);
             goto out;
         }
-        err = lchown(rpath(fs_ctx, newpath, buffer), credp->fc_uid,
+        err = lchown(buffer, credp->fc_uid, credp->fc_gid);
-                     credp->fc_gid);
         if (err == -1) {
             /*
              * If we fail to change ownership and if we are
@@ -788,8 +830,9 @@ static int local_symlink(FsContext *fs_ctx, const char *oldpath,
     goto out;
 
 err_end:
-    remove(rpath(fs_ctx, newpath, buffer));
+    remove(buffer);
     errno = serrno;
+    g_free(buffer);
 out:
     v9fs_string_free(&fullname);
     return err;
@@ -800,13 +843,16 @@ static int local_link(FsContext *ctx, V9fsPath *oldpath,
 {
     int ret;
     V9fsString newpath;
-    char buffer[PATH_MAX], buffer1[PATH_MAX];
+    char *buffer, *buffer1;
 
     v9fs_string_init(&newpath);
     v9fs_string_sprintf(&newpath, "%s/%s", dirpath->data, name);
 
-    ret = link(rpath(ctx, oldpath->data, buffer),
+    buffer = rpath(ctx, oldpath->data);
-               rpath(ctx, newpath.data, buffer1));
+    buffer1 = rpath(ctx, newpath.data);
+    ret = link(buffer, buffer1);
+    g_free(buffer);
+    g_free(buffer1);
 
     /* now link the virtfs_metadata files */
     if (!ret && (ctx->export_flags & V9FS_SM_MAPPED_FILE)) {
@@ -815,8 +861,11 @@ static int local_link(FsContext *ctx, V9fsPath *oldpath,
         if (ret < 0) {
             goto err_out;
         }
-        ret = link(local_mapped_attr_path(ctx, oldpath->data, buffer),
+        buffer = local_mapped_attr_path(ctx, oldpath->data);
-                   local_mapped_attr_path(ctx, newpath.data, buffer1));
+        buffer1 = local_mapped_attr_path(ctx, newpath.data);
+        ret = link(buffer, buffer1);
+        g_free(buffer);
+        g_free(buffer1);
         if (ret < 0 && errno != ENOENT) {
             goto err_out;
         }
@@ -828,17 +877,21 @@ err_out:
 
 static int local_truncate(FsContext *ctx, V9fsPath *fs_path, off_t size)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
+    int ret;
     char *path = fs_path->data;
 
-    return truncate(rpath(ctx, path, buffer), size);
+    buffer = rpath(ctx, path);
+    ret = truncate(buffer, size);
+    g_free(buffer);
+    return ret;
 }
 
 static int local_rename(FsContext *ctx, const char *oldpath,
                         const char *newpath)
 {
     int err;
-    char buffer[PATH_MAX], buffer1[PATH_MAX];
+    char *buffer, *buffer1;
 
     if (ctx->export_flags & V9FS_SM_MAPPED_FILE) {
         err = local_create_mapped_attr_dir(ctx, newpath);
@@ -846,50 +899,69 @@ static int local_rename(FsContext *ctx, const char *oldpath,
             return err;
         }
         /* rename the .virtfs_metadata files */
-        err = rename(local_mapped_attr_path(ctx, oldpath, buffer),
+        buffer = local_mapped_attr_path(ctx, oldpath);
-                     local_mapped_attr_path(ctx, newpath, buffer1));
+        buffer1 = local_mapped_attr_path(ctx, newpath);
+        err = rename(buffer, buffer1);
+        g_free(buffer);
+        g_free(buffer1);
         if (err < 0 && errno != ENOENT) {
             return err;
         }
     }
-    return rename(rpath(ctx, oldpath, buffer), rpath(ctx, newpath, buffer1));
+
+    buffer = rpath(ctx, oldpath);
+    buffer1 = rpath(ctx, newpath);
+    err = rename(buffer, buffer1);
+    g_free(buffer);
+    g_free(buffer1);
+    return err;
 }
 
 static int local_chown(FsContext *fs_ctx, V9fsPath *fs_path, FsCred *credp)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
+    int ret = -1;
     char *path = fs_path->data;
 
     if ((credp->fc_uid == -1 && credp->fc_gid == -1) ||
         (fs_ctx->export_flags & V9FS_SM_PASSTHROUGH) ||
         (fs_ctx->export_flags & V9FS_SM_NONE)) {
-        return lchown(rpath(fs_ctx, path, buffer),
+        buffer = rpath(fs_ctx, path);
-                      credp->fc_uid, credp->fc_gid);
+        ret = lchown(buffer, credp->fc_uid, credp->fc_gid);
+        g_free(buffer);
     } else if (fs_ctx->export_flags & V9FS_SM_MAPPED) {
-        return local_set_xattr(rpath(fs_ctx, path, buffer), credp);
+        buffer = rpath(fs_ctx, path);
+        ret = local_set_xattr(buffer, credp);
+        g_free(buffer);
     } else if (fs_ctx->export_flags & V9FS_SM_MAPPED_FILE) {
         return local_set_mapped_file_attr(fs_ctx, path, credp);
     }
-    return -1;
+    return ret;
 }
 
 static int local_utimensat(FsContext *s, V9fsPath *fs_path,
                            const struct timespec *buf)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
+    int ret;
     char *path = fs_path->data;
 
-    return qemu_utimens(rpath(s, path, buffer), buf);
+    buffer = rpath(s, path);
+    ret = qemu_utimens(buffer, buf);
+    g_free(buffer);
+    return ret;
 }
 
 static int local_remove(FsContext *ctx, const char *path)
 {
     int err;
     struct stat stbuf;
-    char buffer[PATH_MAX];
+    char *buffer;
 
     if (ctx->export_flags & V9FS_SM_MAPPED_FILE) {
-        err =  lstat(rpath(ctx, path, buffer), &stbuf);
+        buffer = rpath(ctx, path);
+        err =  lstat(buffer, &stbuf);
+        g_free(buffer);
         if (err) {
             goto err_out;
         }
@@ -898,8 +970,10 @@ static int local_remove(FsContext *ctx, const char *path)
          * directory
          */
         if (S_ISDIR(stbuf.st_mode)) {
-            sprintf(buffer, "%s/%s/%s", ctx->fs_root, path, VIRTFS_META_DIR);
+            buffer = g_strdup_printf("%s/%s/%s", ctx->fs_root,
+                                     path, VIRTFS_META_DIR);
             err = remove(buffer);
+            g_free(buffer);
             if (err < 0 && errno != ENOENT) {
                 /*
                  * We didn't had the .virtfs_metadata file. May be file created
@@ -912,7 +986,9 @@ static int local_remove(FsContext *ctx, const char *path)
          * Now remove the name from parent directory
          * .virtfs_metadata directory
          */
-        err = remove(local_mapped_attr_path(ctx, path, buffer));
+        buffer = local_mapped_attr_path(ctx, path);
+        err = remove(buffer);
+        g_free(buffer);
         if (err < 0 && errno != ENOENT) {
             /*
              * We didn't had the .virtfs_metadata file. May be file created
@@ -921,7 +997,10 @@ static int local_remove(FsContext *ctx, const char *path)
             goto err_out;
         }
     }
-    return remove(rpath(ctx, path, buffer));
+
+    buffer = rpath(ctx, path);
+    err = remove(buffer);
+    g_free(buffer);
 err_out:
     return err;
 }
@@ -946,10 +1025,14 @@ static int local_fsync(FsContext *ctx, int fid_type,
 
 static int local_statfs(FsContext *s, V9fsPath *fs_path, struct statfs *stbuf)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
+    int ret;
     char *path = fs_path->data;
 
-    return statfs(rpath(s, path, buffer), stbuf);
+    buffer = rpath(s, path);
+    ret = statfs(buffer, stbuf);
+    g_free(buffer);
+    return ret;
 }
 
 static ssize_t local_lgetxattr(FsContext *ctx, V9fsPath *fs_path,
@@ -1022,7 +1105,7 @@ static int local_unlinkat(FsContext *ctx, V9fsPath *dir,
 {
     int ret;
     V9fsString fullname;
-    char buffer[PATH_MAX];
+    char *buffer;
 
     v9fs_string_init(&fullname);
 
@@ -1033,9 +1116,10 @@ static int local_unlinkat(FsContext *ctx, V9fsPath *dir,
              * If directory remove .virtfs_metadata contained in the
              * directory
              */
-            sprintf(buffer, "%s/%s/%s", ctx->fs_root,
+            buffer = g_strdup_printf("%s/%s/%s", ctx->fs_root,
-                    fullname.data, VIRTFS_META_DIR);
+                                     fullname.data, VIRTFS_META_DIR);
             ret = remove(buffer);
+            g_free(buffer);
             if (ret < 0 && errno != ENOENT) {
                 /*
                  * We didn't had the .virtfs_metadata file. May be file created
@@ -1048,7 +1132,9 @@ static int local_unlinkat(FsContext *ctx, V9fsPath *dir,
          * Now remove the name from parent directory
          * .virtfs_metadata directory.
          */
-        ret = remove(local_mapped_attr_path(ctx, fullname.data, buffer));
+        buffer = local_mapped_attr_path(ctx, fullname.data);
+        ret = remove(buffer);
+        g_free(buffer);
         if (ret < 0 && errno != ENOENT) {
             /*
              * We didn't had the .virtfs_metadata file. May be file created
@@ -1058,10 +1144,12 @@ static int local_unlinkat(FsContext *ctx, V9fsPath *dir,
         }
     }
     /* Remove the name finally */
-    ret = remove(rpath(ctx, fullname.data, buffer));
+    buffer = rpath(ctx, fullname.data);
-    v9fs_string_free(&fullname);
+    ret = remove(buffer);
+    g_free(buffer);
 
 err_out:
+    v9fs_string_free(&fullname);
     return ret;
 }
 

hw/9pfs/virtio-9p-posix-acl.c

@@ -26,8 +26,13 @@
 static ssize_t mp_pacl_getxattr(FsContext *ctx, const char *path,
                                 const char *name, void *value, size_t size)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
-    return lgetxattr(rpath(ctx, path, buffer), MAP_ACL_ACCESS, value, size);
+    ssize_t ret;
+
+    buffer = rpath(ctx, path);
+    ret = lgetxattr(buffer, MAP_ACL_ACCESS, value, size);
+    g_free(buffer);
+    return ret;
 }
 
 static ssize_t mp_pacl_listxattr(FsContext *ctx, const char *path,
@@ -52,17 +57,23 @@ static ssize_t mp_pacl_listxattr(FsContext *ctx, const char *path,
 static int mp_pacl_setxattr(FsContext *ctx, const char *path, const char *name,
                             void *value, size_t size, int flags)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
-    return lsetxattr(rpath(ctx, path, buffer), MAP_ACL_ACCESS, value,
+    int ret;
-            size, flags);
+
+    buffer = rpath(ctx, path);
+    ret = lsetxattr(buffer, MAP_ACL_ACCESS, value, size, flags);
+    g_free(buffer);
+    return ret;
 }
 
 static int mp_pacl_removexattr(FsContext *ctx,
                                const char *path, const char *name)
 {
     int ret;
-    char buffer[PATH_MAX];
+    char *buffer;
-    ret  = lremovexattr(rpath(ctx, path, buffer), MAP_ACL_ACCESS);
+
+    buffer = rpath(ctx, path);
+    ret  = lremovexattr(buffer, MAP_ACL_ACCESS);
     if (ret == -1 && errno == ENODATA) {
         /*
          * We don't get ENODATA error when trying to remove a
@@ -72,14 +83,20 @@ static int mp_pacl_removexattr(FsContext *ctx,
         errno = 0;
         ret = 0;
     }
+    g_free(buffer);
     return ret;
 }
 
 static ssize_t mp_dacl_getxattr(FsContext *ctx, const char *path,
                                 const char *name, void *value, size_t size)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
-    return lgetxattr(rpath(ctx, path, buffer), MAP_ACL_DEFAULT, value, size);
+    ssize_t ret;
+
+    buffer = rpath(ctx, path);
+    ret = lgetxattr(buffer, MAP_ACL_DEFAULT, value, size);
+    g_free(buffer);
+    return ret;
 }
 
 static ssize_t mp_dacl_listxattr(FsContext *ctx, const char *path,
@@ -104,17 +121,23 @@ static ssize_t mp_dacl_listxattr(FsContext *ctx, const char *path,
 static int mp_dacl_setxattr(FsContext *ctx, const char *path, const char *name,
                             void *value, size_t size, int flags)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
-    return lsetxattr(rpath(ctx, path, buffer), MAP_ACL_DEFAULT, value,
+    int ret;
-            size, flags);
+
+    buffer = rpath(ctx, path);
+    ret = lsetxattr(buffer, MAP_ACL_DEFAULT, value, size, flags);
+    g_free(buffer);
+    return ret;
 }
 
 static int mp_dacl_removexattr(FsContext *ctx,
                                const char *path, const char *name)
 {
     int ret;
-    char buffer[PATH_MAX];
+    char *buffer;
-    ret  = lremovexattr(rpath(ctx, path, buffer), MAP_ACL_DEFAULT);
+
+    buffer = rpath(ctx, path);
+    ret  = lremovexattr(buffer, MAP_ACL_DEFAULT);
     if (ret == -1 && errno == ENODATA) {
         /*
          * We don't get ENODATA error when trying to remove a
@@ -124,6 +147,7 @@ static int mp_dacl_removexattr(FsContext *ctx,
         errno = 0;
         ret = 0;
     }
+    g_free(buffer);
     return ret;
 }
 

hw/9pfs/virtio-9p-xattr-user.c

@@ -21,7 +21,9 @@
 static ssize_t mp_user_getxattr(FsContext *ctx, const char *path,
                                 const char *name, void *value, size_t size)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
+    ssize_t ret;
+
     if (strncmp(name, "user.virtfs.", 12) == 0) {
         /*
          * Don't allow fetch of user.virtfs namesapce
@@ -30,7 +32,10 @@ static ssize_t mp_user_getxattr(FsContext *ctx, const char *path,
         errno = ENOATTR;
         return -1;
     }
-    return lgetxattr(rpath(ctx, path, buffer), name, value, size);
+    buffer = rpath(ctx, path);
+    ret = lgetxattr(buffer, name, value, size);
+    g_free(buffer);
+    return ret;
 }
 
 static ssize_t mp_user_listxattr(FsContext *ctx, const char *path,
@@ -69,7 +74,9 @@ static ssize_t mp_user_listxattr(FsContext *ctx, const char *path,
 static int mp_user_setxattr(FsContext *ctx, const char *path, const char *name,
                             void *value, size_t size, int flags)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
+    int ret;
+
     if (strncmp(name, "user.virtfs.", 12) == 0) {
         /*
          * Don't allow fetch of user.virtfs namesapce
@@ -78,13 +85,18 @@ static int mp_user_setxattr(FsContext *ctx, const char *path, const char *name,
         errno = EACCES;
         return -1;
     }
-    return lsetxattr(rpath(ctx, path, buffer), name, value, size, flags);
+    buffer = rpath(ctx, path);
+    ret = lsetxattr(buffer, name, value, size, flags);
+    g_free(buffer);
+    return ret;
 }
 
 static int mp_user_removexattr(FsContext *ctx,
                                const char *path, const char *name)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
+    int ret;
+
     if (strncmp(name, "user.virtfs.", 12) == 0) {
         /*
          * Don't allow fetch of user.virtfs namesapce
@@ -93,7 +105,10 @@ static int mp_user_removexattr(FsContext *ctx,
         errno = EACCES;
         return -1;
     }
-    return lremovexattr(rpath(ctx, path, buffer), name);
+    buffer = rpath(ctx, path);
+    ret = lremovexattr(buffer, name);
+    g_free(buffer);
+    return ret;
 }
 
 XattrOperations mapped_user_xattr = {

hw/9pfs/virtio-9p-xattr.c

@@ -67,21 +67,24 @@ ssize_t v9fs_list_xattr(FsContext *ctx, const char *path,
                         void *value, size_t vsize)
 {
     ssize_t size = 0;
-    char buffer[PATH_MAX];
+    char *buffer;
     void *ovalue = value;
     XattrOperations *xops;
     char *orig_value, *orig_value_start;
     ssize_t xattr_len, parsed_len = 0, attr_len;
 
     /* Get the actual len */
-    xattr_len = llistxattr(rpath(ctx, path, buffer), value, 0);
+    buffer = rpath(ctx, path);
+    xattr_len = llistxattr(buffer, value, 0);
     if (xattr_len <= 0) {
+        g_free(buffer);
         return xattr_len;
     }
 
     /* Now fetch the xattr and find the actual size */
     orig_value = g_malloc(xattr_len);
-    xattr_len = llistxattr(rpath(ctx, path, buffer), orig_value, xattr_len);
+    xattr_len = llistxattr(buffer, orig_value, xattr_len);
+    g_free(buffer);
 
     /* store the orig pointer */
     orig_value_start = orig_value;

hw/9pfs/virtio-9p-xattr.h

@@ -54,23 +54,38 @@ ssize_t pt_listxattr(FsContext *ctx, const char *path, char *name, void *value,
 static inline ssize_t pt_getxattr(FsContext *ctx, const char *path,
                                   const char *name, void *value, size_t size)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
-    return lgetxattr(rpath(ctx, path, buffer), name, value, size);
+    ssize_t ret;
+
+    buffer = rpath(ctx, path);
+    ret = lgetxattr(buffer, name, value, size);
+    g_free(buffer);
+    return ret;
 }
 
 static inline int pt_setxattr(FsContext *ctx, const char *path,
                               const char *name, void *value,
                               size_t size, int flags)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
-    return lsetxattr(rpath(ctx, path, buffer), name, value, size, flags);
+    int ret;
+
+    buffer = rpath(ctx, path);
+    ret = lsetxattr(buffer, name, value, size, flags);
+    g_free(buffer);
+    return ret;
 }
 
 static inline int pt_removexattr(FsContext *ctx,
                                  const char *path, const char *name)
 {
-    char buffer[PATH_MAX];
+    char *buffer;
-    return lremovexattr(rpath(ctx, path, buffer), name);
+    int ret;
+
+    buffer = rpath(ctx, path);
+    ret = lremovexattr(path, name);
+    g_free(buffer);
+    return ret;
 }
 
 static inline ssize_t notsup_getxattr(FsContext *ctx, const char *path,

hw/9pfs/virtio-9p.h

@@ -6,6 +6,7 @@
 #include <sys/time.h>
 #include <utime.h>
 #include <sys/resource.h>
+#include <glib.h>
 #include "hw/virtio/virtio.h"
 #include "fsdev/file-op-9p.h"
 #include "fsdev/virtio-9p-marshal.h"
@@ -112,10 +113,9 @@ enum p9_proto_version {
 
 #define FID_REFERENCED          0x1
 #define FID_NON_RECLAIMABLE     0x2
-static inline const char *rpath(FsContext *ctx, const char *path, char *buffer)
+static inline char *rpath(FsContext *ctx, const char *path)
 {
-    snprintf(buffer, PATH_MAX, "%s/%s", ctx->fs_root, path);
+    return g_strdup_printf("%s/%s", ctx->fs_root, path);
-    return buffer;
 }
 
 /*

hw/Makefile.objs

@@ -1,4 +1,4 @@
-devices-dirs-$(CONFIG_REALLY_VIRTFS) += 9pfs/
+devices-dirs-$(call land, $(CONFIG_VIRTIO),$(call land,$(CONFIG_VIRTFS),$(CONFIG_PCI))) += 9pfs/
 devices-dirs-$(CONFIG_ACPI) += acpi/
 devices-dirs-$(CONFIG_SOFTMMU) += audio/
 devices-dirs-$(CONFIG_SOFTMMU) += block/

hw/arm/musicpal.c

@@ -92,8 +92,6 @@
 #define MP_ETH_CRDP3            0x4AC
 #define MP_ETH_CTDP0            0x4E0
 #define MP_ETH_CTDP1            0x4E4
-#define MP_ETH_CTDP2            0x4E8
-#define MP_ETH_CTDP3            0x4EC
 
 /* MII PHY access */
 #define MP_ETH_SMIR_DATA        0x0000FFFF
@@ -308,7 +306,7 @@ static uint64_t mv88w8618_eth_read(void *opaque, hwaddr offset,
     case MP_ETH_CRDP0 ... MP_ETH_CRDP3:
         return s->rx_queue[(offset - MP_ETH_CRDP0)/4];
 
-    case MP_ETH_CTDP0 ... MP_ETH_CTDP3:
+    case MP_ETH_CTDP0 ... MP_ETH_CTDP1:
         return s->tx_queue[(offset - MP_ETH_CTDP0)/4];
 
     default:
@@ -362,7 +360,7 @@ static void mv88w8618_eth_write(void *opaque, hwaddr offset,
             s->cur_rx[(offset - MP_ETH_CRDP0)/4] = value;
         break;
 
-    case MP_ETH_CTDP0 ... MP_ETH_CTDP3:
+    case MP_ETH_CTDP0 ... MP_ETH_CTDP1:
         s->tx_queue[(offset - MP_ETH_CTDP0)/4] = value;
         break;
     }
@@ -632,7 +630,7 @@ static int musicpal_lcd_init(SysBusDevice *sbd)
                           "musicpal-lcd", MP_LCD_SIZE);
     sysbus_init_mmio(sbd, &s->iomem);
 
-    s->con = graphic_console_init(dev, &musicpal_gfx_ops, s);
+    s->con = graphic_console_init(dev, 0, &musicpal_gfx_ops, s);
     qemu_console_resize(s->con, 128*3, 64*3);
 
     qdev_init_gpio_in(dev, musicpal_lcd_gpio_brightness_in, 3);

hw/arm/pxa2xx.c

@@ -272,11 +272,11 @@ static void pxa2xx_pwrmode_write(CPUARMState *env, const ARMCPRegInfo *ri,
         goto message;
 
     case 3:
-        s->cpu->env.uncached_cpsr =
+        s->cpu->env.uncached_cpsr = ARM_CPU_MODE_SVC;
-            ARM_CPU_MODE_SVC | CPSR_A | CPSR_F | CPSR_I;
+        s->cpu->env.daif = PSTATE_A | PSTATE_F | PSTATE_I;
         s->cpu->env.cp15.c1_sys = 0;
         s->cpu->env.cp15.c1_coproc = 0;
-        s->cpu->env.cp15.c2_base0 = 0;
+        s->cpu->env.cp15.ttbr0_el1 = 0;
         s->cpu->env.cp15.c3 = 0;
         s->pm_regs[PSSR >> 2] |= 0x8; /* Set STS */
         s->pm_regs[RCSR >> 2] |= 0x8; /* Set GPR */

hw/block/xen_disk.c

@@ -483,7 +483,18 @@ static void qemu_aio_complete(void *opaque, int ret)
     ioreq->status = ioreq->aio_errors ? BLKIF_RSP_ERROR : BLKIF_RSP_OKAY;
     ioreq_unmap(ioreq);
     ioreq_finish(ioreq);
-    bdrv_acct_done(ioreq->blkdev->bs, &ioreq->acct);
+    switch (ioreq->req.operation) {
+    case BLKIF_OP_WRITE:
+    case BLKIF_OP_FLUSH_DISKCACHE:
+        if (!ioreq->req.nr_segments) {
+            break;
+        }
+    case BLKIF_OP_READ:
+        bdrv_acct_done(ioreq->blkdev->bs, &ioreq->acct);
+        break;
+    default:
+        break;
+    }
     qemu_bh_schedule(ioreq->blkdev->bh);
 }
 
@@ -813,8 +824,8 @@ static int blk_connect(struct XenDevice *xendev)
             Error *local_err = NULL;
             BlockDriver *drv = bdrv_find_whitelisted_format(blkdev->fileproto,
                                                            readonly);
-            if (bdrv_open(blkdev->bs,
+            if (bdrv_open(&blkdev->bs, blkdev->filename, NULL, NULL, qflags,
-                          blkdev->filename, NULL, qflags, drv, &local_err) != 0)
+                          drv, &local_err) != 0)
             {
                 xen_be_printf(&blkdev->xendev, 0, "error: %s\n",
                               error_get_pretty(local_err));

hw/core/loader.c

@@ -284,12 +284,30 @@ static void *load_at(int fd, int offset, int size)
 #define SZ		64
 #include "hw/elf_ops.h"
 
+const char *load_elf_strerror(int error)
+{
+    switch (error) {
+    case 0:
+        return "No error";
+    case ELF_LOAD_FAILED:
+        return "Failed to load ELF";
+    case ELF_LOAD_NOT_ELF:
+        return "The image is not ELF";
+    case ELF_LOAD_WRONG_ARCH:
+        return "The image is from incompatible architecture";
+    case ELF_LOAD_WRONG_ENDIAN:
+        return "The image has incorrect endianness";
+    default:
+        return "Unknown error";
+    }
+}
+
 /* return < 0 if error, otherwise the number of bytes loaded in memory */
 int load_elf(const char *filename, uint64_t (*translate_fn)(void *, uint64_t),
              void *translate_opaque, uint64_t *pentry, uint64_t *lowaddr,
              uint64_t *highaddr, int big_endian, int elf_machine, int clear_lsb)
 {
-    int fd, data_order, target_data_order, must_swab, ret;
+    int fd, data_order, target_data_order, must_swab, ret = ELF_LOAD_FAILED;
     uint8_t e_ident[EI_NIDENT];
 
     fd = open(filename, O_RDONLY | O_BINARY);
@@ -302,8 +320,10 @@ int load_elf(const char *filename, uint64_t (*translate_fn)(void *, uint64_t),
     if (e_ident[0] != ELFMAG0 ||
         e_ident[1] != ELFMAG1 ||
         e_ident[2] != ELFMAG2 ||
-        e_ident[3] != ELFMAG3)
+        e_ident[3] != ELFMAG3) {
+        ret = ELF_LOAD_NOT_ELF;
         goto fail;
+    }
 #ifdef HOST_WORDS_BIGENDIAN
     data_order = ELFDATA2MSB;
 #else
@@ -317,6 +337,7 @@ int load_elf(const char *filename, uint64_t (*translate_fn)(void *, uint64_t),
     }
 
     if (target_data_order != e_ident[EI_DATA]) {
+        ret = ELF_LOAD_WRONG_ENDIAN;
         goto fail;
     }
 
@@ -329,12 +350,9 @@ int load_elf(const char *filename, uint64_t (*translate_fn)(void *, uint64_t),
                          pentry, lowaddr, highaddr, elf_machine, clear_lsb);
     }
 
-    close(fd);
-    return ret;
-
  fail:
     close(fd);
-    return -1;
+    return ret;
 }
 
 static void bswap_uboot_header(uboot_image_header_t *hdr)

hw/core/qdev.c

@@ -440,27 +440,33 @@ DeviceState *qdev_find_recursive(BusState *bus, const char *id)
 static void qbus_realize(BusState *bus, DeviceState *parent, const char *name)
 {
     const char *typename = object_get_typename(OBJECT(bus));
+    BusClass *bc;
     char *buf;
-    int i,len;
+    int i, len, bus_id;
 
     bus->parent = parent;
 
     if (name) {
         bus->name = g_strdup(name);
     } else if (bus->parent && bus->parent->id) {
-        /* parent device has id -> use it for bus name */
+        /* parent device has id -> use it plus parent-bus-id for bus name */
+        bus_id = bus->parent->num_child_bus;
+
         len = strlen(bus->parent->id) + 16;
         buf = g_malloc(len);
-        snprintf(buf, len, "%s.%d", bus->parent->id, bus->parent->num_child_bus);
+        snprintf(buf, len, "%s.%d", bus->parent->id, bus_id);
         bus->name = buf;
     } else {
-        /* no id -> use lowercase bus type for bus name */
+        /* no id -> use lowercase bus type plus global bus-id for bus name */
+        bc = BUS_GET_CLASS(bus);
+        bus_id = bc->automatic_ids++;
+
         len = strlen(typename) + 16;
         buf = g_malloc(len);
-        len = snprintf(buf, len, "%s.%d", typename,
+        len = snprintf(buf, len, "%s.%d", typename, bus_id);
-                       bus->parent ? bus->parent->num_child_bus : 0);
+        for (i = 0; i < len; i++) {
-        for (i = 0; i < len; i++)
             buf[i] = qemu_tolower(buf[i]);
+        }
         bus->name = buf;
     }
 

hw/display/Makefile.objs

@@ -28,6 +28,7 @@ obj-$(CONFIG_OMAP) += omap_lcdc.o
 obj-$(CONFIG_PXA2XX) += pxa2xx_lcd.o
 obj-$(CONFIG_SM501) += sm501.o
 obj-$(CONFIG_TCX) += tcx.o
+obj-$(CONFIG_CG3) += cg3.o
 
 obj-$(CONFIG_VGA) += vga.o
 

hw/display/blizzard.c

@@ -956,7 +956,7 @@ void *s1d13745_init(qemu_irq gpio_int)
 
     s->fb = g_malloc(0x180000);
 
-    s->con = graphic_console_init(NULL, &blizzard_ops, s);
+    s->con = graphic_console_init(NULL, 0, &blizzard_ops, s);
     surface = qemu_console_surface(s->con);
 
     switch (surface_bits_per_pixel(surface)) {

hw/display/cg3.c

@@ -0,0 +1,385 @@
+/*
+ * QEMU CG3 Frame buffer
+ *
+ * Copyright (c) 2012 Bob Breuer
+ * Copyright (c) 2013 Mark Cave-Ayland
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "qemu-common.h"
+#include "qemu/error-report.h"
+#include "ui/console.h"
+#include "hw/sysbus.h"
+#include "hw/loader.h"
+
+/* Change to 1 to enable debugging */
+#define DEBUG_CG3 0
+
+#define CG3_ROM_FILE  "QEMU,cgthree.bin"
+#define FCODE_MAX_ROM_SIZE 0x10000
+
+#define CG3_REG_SIZE            0x20
+
+#define CG3_REG_BT458_ADDR      0x0
+#define CG3_REG_BT458_COLMAP    0x4
+#define CG3_REG_FBC_CTRL        0x10
+#define CG3_REG_FBC_STATUS      0x11
+#define CG3_REG_FBC_CURSTART    0x12
+#define CG3_REG_FBC_CUREND      0x13
+#define CG3_REG_FBC_VCTRL       0x14
+
+/* Control register flags */
+#define CG3_CR_ENABLE_INTS      0x80
+
+/* Status register flags */
+#define CG3_SR_PENDING_INT      0x80
+#define CG3_SR_1152_900_76_B    0x60
+#define CG3_SR_ID_COLOR         0x01
+
+#define CG3_VRAM_SIZE 0x100000
+#define CG3_VRAM_OFFSET 0x800000
+
+#define DPRINTF(fmt, ...) do { \
+    if (DEBUG_CG3) { \
+        printf("CG3: " fmt , ## __VA_ARGS__); \
+    } \
+} while (0);
+
+#define TYPE_CG3 "cgthree"
+#define CG3(obj) OBJECT_CHECK(CG3State, (obj), TYPE_CG3)
+
+typedef struct CG3State {
+    SysBusDevice parent_obj;
+
+    QemuConsole *con;
+    qemu_irq irq;
+    hwaddr prom_addr;
+    MemoryRegion vram_mem;
+    MemoryRegion rom;
+    MemoryRegion reg;
+    uint32_t vram_size;
+    int full_update;
+    uint8_t regs[16];
+    uint8_t r[256], g[256], b[256];
+    uint16_t width, height, depth;
+    uint8_t dac_index, dac_state;
+} CG3State;
+
+static void cg3_update_display(void *opaque)
+{
+    CG3State *s = opaque;
+    DisplaySurface *surface = qemu_console_surface(s->con);
+    const uint8_t *pix;
+    uint32_t *data;
+    uint32_t dval;
+    int x, y, y_start;
+    unsigned int width, height;
+    ram_addr_t page, page_min, page_max;
+
+    if (surface_bits_per_pixel(surface) != 32) {
+        return;
+    }
+    width = s->width;
+    height = s->height;
+
+    y_start = -1;
+    page_min = -1;
+    page_max = 0;
+    page = 0;
+    pix = memory_region_get_ram_ptr(&s->vram_mem);
+    data = (uint32_t *)surface_data(surface);
+
+    for (y = 0; y < height; y++) {
+        int update = s->full_update;
+
+        page = (y * width) & TARGET_PAGE_MASK;
+        update |= memory_region_get_dirty(&s->vram_mem, page, page + width,
+                                          DIRTY_MEMORY_VGA);
+        if (update) {
+            if (y_start < 0) {
+                y_start = y;
+            }
+            if (page < page_min) {
+                page_min = page;
+            }
+            if (page > page_max) {
+                page_max = page;
+            }
+
+            for (x = 0; x < width; x++) {
+                dval = *pix++;
+                dval = (s->r[dval] << 16) | (s->g[dval] << 8) | s->b[dval];
+                *data++ = dval;
+            }
+        } else {
+            if (y_start >= 0) {
+                dpy_gfx_update(s->con, 0, y_start, s->width, y - y_start);
+                y_start = -1;
+            }
+            pix += width;
+            data += width;
+        }
+    }
+    s->full_update = 0;
+    if (y_start >= 0) {
+        dpy_gfx_update(s->con, 0, y_start, s->width, y - y_start);
+    }
+    if (page_max >= page_min) {
+        memory_region_reset_dirty(&s->vram_mem,
+                              page_min, page_max - page_min + TARGET_PAGE_SIZE,
+                              DIRTY_MEMORY_VGA);
+    }
+    /* vsync interrupt? */
+    if (s->regs[0] & CG3_CR_ENABLE_INTS) {
+        s->regs[1] |= CG3_SR_PENDING_INT;
+        qemu_irq_raise(s->irq);
+    }
+}
+
+static void cg3_invalidate_display(void *opaque)
+{
+    CG3State *s = opaque;
+
+    memory_region_set_dirty(&s->vram_mem, 0, CG3_VRAM_SIZE);
+}
+
+static uint64_t cg3_reg_read(void *opaque, hwaddr addr, unsigned size)
+{
+    CG3State *s = opaque;
+    int val;
+
+    switch (addr) {
+    case CG3_REG_BT458_ADDR:
+    case CG3_REG_BT458_COLMAP:
+        val = 0;
+        break;
+    case CG3_REG_FBC_CTRL:
+        val = s->regs[0];
+        break;
+    case CG3_REG_FBC_STATUS:
+        /* monitor ID 6, board type = 1 (color) */
+        val = s->regs[1] | CG3_SR_1152_900_76_B | CG3_SR_ID_COLOR;
+        break;
+    case CG3_REG_FBC_CURSTART ... CG3_REG_SIZE:
+        val = s->regs[addr - 0x10];
+        break;
+    default:
+        qemu_log_mask(LOG_UNIMP,
+                  "cg3: Unimplemented register read "
+                  "reg 0x%" HWADDR_PRIx " size 0x%x\n",
+                  addr, size);
+        val = 0;
+        break;
+    }
+    DPRINTF("read %02x from reg %" HWADDR_PRIx "\n", val, addr);
+    return val;
+}
+
+static void cg3_reg_write(void *opaque, hwaddr addr, uint64_t val,
+                          unsigned size)
+{
+    CG3State *s = opaque;
+    uint8_t regval;
+    int i;
+
+    DPRINTF("write %" PRIx64 " to reg %" HWADDR_PRIx " size %d\n",
+            val, addr, size);
+
+    switch (addr) {
+    case CG3_REG_BT458_ADDR:
+        s->dac_index = val;
+        s->dac_state = 0;
+        break;
+    case CG3_REG_BT458_COLMAP:
+        /* This register can be written to as either a long word or a byte */
+        if (size == 1) {
+            val <<= 24;
+        }
+
+        for (i = 0; i < size; i++) {
+            regval = val >> 24;
+
+            switch (s->dac_state) {
+            case 0:
+                s->r[s->dac_index] = regval;
+                s->dac_state++;
+                break;
+            case 1:
+                s->g[s->dac_index] = regval;
+                s->dac_state++;
+                break;
+            case 2:
+                s->b[s->dac_index] = regval;
+                /* Index autoincrement */
+                s->dac_index = (s->dac_index + 1) & 0xff;
+            default:
+                s->dac_state = 0;
+                break;
+            }
+            val <<= 8;
+        }
+        s->full_update = 1;
+        break;
+    case CG3_REG_FBC_CTRL:
+        s->regs[0] = val;
+        break;
+    case CG3_REG_FBC_STATUS:
+        if (s->regs[1] & CG3_SR_PENDING_INT) {
+            /* clear interrupt */
+            s->regs[1] &= ~CG3_SR_PENDING_INT;
+            qemu_irq_lower(s->irq);
+        }
+        break;
+    case CG3_REG_FBC_CURSTART ... CG3_REG_SIZE:
+        s->regs[addr - 0x10] = val;
+        break;
+    default:
+        qemu_log_mask(LOG_UNIMP,
+                  "cg3: Unimplemented register write "
+                  "reg 0x%" HWADDR_PRIx " size 0x%x value 0x%" PRIx64 "\n",
+                  addr, size, val);
+        break;
+    }
+}
+
+static const MemoryRegionOps cg3_reg_ops = {
+    .read = cg3_reg_read,
+    .write = cg3_reg_write,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+    .valid = {
+        .min_access_size = 1,
+        .max_access_size = 4,
+    },
+};
+
+static const GraphicHwOps cg3_ops = {
+    .invalidate = cg3_invalidate_display,
+    .gfx_update = cg3_update_display,
+};
+
+static void cg3_realizefn(DeviceState *dev, Error **errp)
+{
+    SysBusDevice *sbd = SYS_BUS_DEVICE(dev);
+    CG3State *s = CG3(dev);
+    int ret;
+    char *fcode_filename;
+
+    /* FCode ROM */
+    memory_region_init_ram(&s->rom, NULL, "cg3.prom", FCODE_MAX_ROM_SIZE);
+    vmstate_register_ram_global(&s->rom);
+    memory_region_set_readonly(&s->rom, true);
+    sysbus_init_mmio(sbd, &s->rom);
+
+    fcode_filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, CG3_ROM_FILE);
+    if (fcode_filename) {
+        ret = load_image_targphys(fcode_filename, s->prom_addr,
+                                  FCODE_MAX_ROM_SIZE);
+        if (ret < 0 || ret > FCODE_MAX_ROM_SIZE) {
+            error_report("cg3: could not load prom '%s'", CG3_ROM_FILE);
+        }
+    }
+
+    memory_region_init_io(&s->reg, NULL, &cg3_reg_ops, s, "cg3.reg",
+                          CG3_REG_SIZE);
+    sysbus_init_mmio(sbd, &s->reg);
+
+    memory_region_init_ram(&s->vram_mem, NULL, "cg3.vram", s->vram_size);
+    vmstate_register_ram_global(&s->vram_mem);
+    sysbus_init_mmio(sbd, &s->vram_mem);
+
+    sysbus_init_irq(sbd, &s->irq);
+
+    s->con = graphic_console_init(DEVICE(dev), 0, &cg3_ops, s);
+    qemu_console_resize(s->con, s->width, s->height);
+}
+
+static int vmstate_cg3_post_load(void *opaque, int version_id)
+{
+    CG3State *s = opaque;
+
+    cg3_invalidate_display(s);
+
+    return 0;
+}
+
+static const VMStateDescription vmstate_cg3 = {
+    .name = "cg3",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .post_load = vmstate_cg3_post_load,
+    .fields    = (VMStateField[]) {
+        VMSTATE_UINT16(height, CG3State),
+        VMSTATE_UINT16(width, CG3State),
+        VMSTATE_UINT16(depth, CG3State),
+        VMSTATE_BUFFER(r, CG3State),
+        VMSTATE_BUFFER(g, CG3State),
+        VMSTATE_BUFFER(b, CG3State),
+        VMSTATE_UINT8(dac_index, CG3State),
+        VMSTATE_UINT8(dac_state, CG3State),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static void cg3_reset(DeviceState *d)
+{
+    CG3State *s = CG3(d);
+
+    /* Initialize palette */
+    memset(s->r, 0, 256);
+    memset(s->g, 0, 256);
+    memset(s->b, 0, 256);
+
+    s->dac_state = 0;
+    s->full_update = 1;
+    qemu_irq_lower(s->irq);
+}
+
+static Property cg3_properties[] = {
+    DEFINE_PROP_UINT32("vram-size",    CG3State, vram_size, -1),
+    DEFINE_PROP_UINT16("width",        CG3State, width,     -1),
+    DEFINE_PROP_UINT16("height",       CG3State, height,    -1),
+    DEFINE_PROP_UINT16("depth",        CG3State, depth,     -1),
+    DEFINE_PROP_UINT64("prom-addr",    CG3State, prom_addr, -1),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void cg3_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+
+    dc->realize = cg3_realizefn;
+    dc->reset = cg3_reset;
+    dc->vmsd = &vmstate_cg3;
+    dc->props = cg3_properties;
+}
+
+static const TypeInfo cg3_info = {
+    .name          = TYPE_CG3,
+    .parent        = TYPE_SYS_BUS_DEVICE,
+    .instance_size = sizeof(CG3State),
+    .class_init    = cg3_class_init,
+};
+
+static void cg3_register_types(void)
+{
+    type_register_static(&cg3_info);
+}
+
+type_init(cg3_register_types)

hw/display/cirrus_vga.c

@@ -2917,7 +2917,7 @@ static void isa_cirrus_vga_realizefn(DeviceState *dev, Error **errp)
     cirrus_init_common(&d->cirrus_vga, OBJECT(dev), CIRRUS_ID_CLGD5430, 0,
                        isa_address_space(isadev),
                        isa_address_space_io(isadev));
-    s->con = graphic_console_init(dev, s->hw_ops, s);
+    s->con = graphic_console_init(dev, 0, s->hw_ops, s);
     rom_add_vga(VGABIOS_CIRRUS_FILENAME);
     /* XXX ISA-LFB support */
     /* FIXME not qdev yet */
@@ -2963,7 +2963,7 @@ static int pci_cirrus_vga_initfn(PCIDevice *dev)
      vga_common_init(&s->vga, OBJECT(dev));
      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), s->vga.hw_ops, &s->vga);
+     s->vga.con = graphic_console_init(DEVICE(dev), 0, s->vga.hw_ops, &s->vga);
 
      /* setup PCI */
 

hw/display/exynos4210_fimd.c

@@ -1917,7 +1917,7 @@ static int exynos4210_fimd_init(SysBusDevice *dev)
     memory_region_init_io(&s->iomem, OBJECT(s), &exynos4210_fimd_mmio_ops, s,
             "exynos4210.fimd", FIMD_REGS_SIZE);
     sysbus_init_mmio(dev, &s->iomem);
-    s->console = graphic_console_init(DEVICE(dev), &exynos4210_fimd_ops, s);
+    s->console = graphic_console_init(DEVICE(dev), 0, &exynos4210_fimd_ops, s);
 
     return 0;
 }

hw/display/g364fb.c

@@ -484,7 +484,7 @@ static void g364fb_init(DeviceState *dev, G364State *s)
 {
     s->vram = g_malloc0(s->vram_size);
 
-    s->con = graphic_console_init(dev, &g364fb_ops, s);
+    s->con = graphic_console_init(dev, 0, &g364fb_ops, s);
 
     memory_region_init_io(&s->mem_ctrl, NULL, &g364fb_ctrl_ops, s, "ctrl", 0x180000);
     memory_region_init_ram_ptr(&s->mem_vram, NULL, "vram",

hw/display/jazz_led.c

@@ -271,7 +271,7 @@ static int jazz_led_init(SysBusDevice *dev)
     memory_region_init_io(&s->iomem, OBJECT(s), &led_ops, s, "led", 1);
     sysbus_init_mmio(dev, &s->iomem);
 
-    s->con = graphic_console_init(DEVICE(dev), &jazz_led_ops, s);
+    s->con = graphic_console_init(DEVICE(dev), 0, &jazz_led_ops, s);
 
     return 0;
 }

hw/display/milkymist-vgafb.c

@@ -290,7 +290,7 @@ static int milkymist_vgafb_init(SysBusDevice *dev)
             "milkymist-vgafb", R_MAX * 4);
     sysbus_init_mmio(dev, &s->regs_region);
 
-    s->con = graphic_console_init(DEVICE(dev), &vgafb_ops, s);
+    s->con = graphic_console_init(DEVICE(dev), 0, &vgafb_ops, s);
 
     return 0;
 }

hw/display/omap_lcdc.c

@@ -406,7 +406,7 @@ struct omap_lcd_panel_s *omap_lcdc_init(MemoryRegion *sysmem,
     memory_region_init_io(&s->iomem, NULL, &omap_lcdc_ops, s, "omap.lcdc", 0x100);
     memory_region_add_subregion(sysmem, base, &s->iomem);
 
-    s->con = graphic_console_init(NULL, &omap_ops, s);
+    s->con = graphic_console_init(NULL, 0, &omap_ops, s);
 
     return s;
 }

hw/display/pl110.c

@@ -464,7 +464,7 @@ static int pl110_initfn(SysBusDevice *sbd)
     sysbus_init_mmio(sbd, &s->iomem);
     sysbus_init_irq(sbd, &s->irq);
     qdev_init_gpio_in(dev, pl110_mux_ctrl_set, 1);
-    s->con = graphic_console_init(dev, &pl110_gfx_ops, s);
+    s->con = graphic_console_init(dev, 0, &pl110_gfx_ops, s);
     return 0;
 }
 

hw/display/pxa2xx_lcd.c

@@ -1013,7 +1013,7 @@ PXA2xxLCDState *pxa2xx_lcdc_init(MemoryRegion *sysmem,
                           "pxa2xx-lcd-controller", 0x00100000);
     memory_region_add_subregion(sysmem, base, &s->iomem);
 
-    s->con = graphic_console_init(NULL, &pxa2xx_ops, s);
+    s->con = graphic_console_init(NULL, 0, &pxa2xx_ops, s);
     surface = qemu_console_surface(s->con);
 
     switch (surface_bits_per_pixel(surface)) {

hw/display/qxl.c

@@ -1429,7 +1429,7 @@ static int qxl_destroy_primary(PCIQXLDevice *d, qxl_async_io async)
     return 1;
 }
 
-static void qxl_set_mode(PCIQXLDevice *d, int modenr, int loadvm)
+static void qxl_set_mode(PCIQXLDevice *d, unsigned int modenr, int loadvm)
 {
     pcibus_t start = d->pci.io_regions[QXL_RAM_RANGE_INDEX].addr;
     pcibus_t end   = d->pci.io_regions[QXL_RAM_RANGE_INDEX].size + start;
@@ -1439,6 +1439,12 @@ static void qxl_set_mode(PCIQXLDevice *d, int modenr, int loadvm)
         .mem_start = start,
         .mem_end = end
     };
+
+    if (modenr >= d->modes->n_modes) {
+        qxl_set_guest_bug(d, "mode number out of range");
+        return;
+    }
+
     QXLSurfaceCreate surface = {
         .width      = mode->x_res,
         .height     = mode->y_res,
@@ -2063,7 +2069,7 @@ static int qxl_init_primary(PCIDevice *dev)
     portio_list_set_flush_coalesced(qxl_vga_port_list);
     portio_list_add(qxl_vga_port_list, pci_address_space_io(dev), 0x3b0);
 
-    vga->con = graphic_console_init(DEVICE(dev), &qxl_ops, qxl);
+    vga->con = graphic_console_init(DEVICE(dev), 0, &qxl_ops, qxl);
     qemu_spice_display_init_common(&qxl->ssd);
 
     rc = qxl_init_common(qxl);
@@ -2088,7 +2094,7 @@ static int qxl_init_secondary(PCIDevice *dev)
                            qxl->vga.vram_size);
     vmstate_register_ram(&qxl->vga.vram, &qxl->pci.qdev);
     qxl->vga.vram_ptr = memory_region_get_ram_ptr(&qxl->vga.vram);
-    qxl->vga.con = graphic_console_init(DEVICE(dev), &qxl_ops, qxl);
+    qxl->vga.con = graphic_console_init(DEVICE(dev), 0, &qxl_ops, qxl);
 
     return qxl_init_common(qxl);
 }

hw/display/sm501.c

@@ -1449,5 +1449,5 @@ void sm501_init(MemoryRegion *address_space_mem, uint32_t base,
     }
 
     /* create qemu graphic console */
-    s->con = graphic_console_init(DEVICE(dev), &sm501_ops, s);
+    s->con = graphic_console_init(DEVICE(dev), 0, &sm501_ops, s);
 }

hw/display/ssd0303.c

@@ -299,7 +299,7 @@ static int ssd0303_init(I2CSlave *i2c)
 {
     ssd0303_state *s = SSD0303(i2c);
 
-    s->con = graphic_console_init(DEVICE(i2c), &ssd0303_ops, s);
+    s->con = graphic_console_init(DEVICE(i2c), 0, &ssd0303_ops, s);
     qemu_console_resize(s->con, 96 * MAGNIFY, 16 * MAGNIFY);
     return 0;
 }

hw/display/ssd0323.c

@@ -342,7 +342,7 @@ static int ssd0323_init(SSISlave *dev)
 
     s->col_end = 63;
     s->row_end = 79;
-    s->con = graphic_console_init(DEVICE(dev), &ssd0323_ops, s);
+    s->con = graphic_console_init(DEVICE(dev), 0, &ssd0323_ops, s);
     qemu_console_resize(s->con, 128 * MAGNIFY, 64 * MAGNIFY);
 
     qdev_init_gpio_in(&dev->qdev, ssd0323_cd, 1);

hw/display/tc6393xb.c

@@ -587,7 +587,7 @@ TC6393xbState *tc6393xb_init(MemoryRegion *sysmem, uint32_t base, qemu_irq irq)
     memory_region_add_subregion(sysmem, base + 0x100000, &s->vram);
     s->scr_width = 480;
     s->scr_height = 640;
-    s->con = graphic_console_init(NULL, &tc6393xb_gfx_ops, s);
+    s->con = graphic_console_init(NULL, 0, &tc6393xb_gfx_ops, s);
 
     return s;
 }

hw/display/tcx.c

@@ -602,14 +602,14 @@ static int tcx_init1(SysBusDevice *dev)
                                  &s->vram_mem, vram_offset, size);
         sysbus_init_mmio(dev, &s->vram_cplane);
 
-        s->con = graphic_console_init(DEVICE(dev), &tcx24_ops, s);
+        s->con = graphic_console_init(DEVICE(dev), 0, &tcx24_ops, s);
     } else {
         /* THC 8 bit (dummy) */
         memory_region_init_io(&s->thc8, OBJECT(s), &dummy_ops, s, "tcx.thc8",
                               TCX_THC_NREGS_8);
         sysbus_init_mmio(dev, &s->thc8);
 
-        s->con = graphic_console_init(DEVICE(dev), &tcx_ops, s);
+        s->con = graphic_console_init(DEVICE(dev), 0, &tcx_ops, s);
     }
 
     qemu_console_resize(s->con, s->width, s->height);

hw/display/vga-isa-mm.c

@@ -135,7 +135,7 @@ int isa_vga_mm_init(hwaddr vram_base,
     vga_common_init(&s->vga, NULL);
     vga_mm_init(s, vram_base, ctrl_base, it_shift, address_space);
 
-    s->vga.con = graphic_console_init(NULL, s->vga.hw_ops, s);
+    s->vga.con = graphic_console_init(NULL, 0, s->vga.hw_ops, s);
 
     vga_init_vbe(&s->vga, NULL, address_space);
     return 0;

hw/display/vga-isa.c

@@ -67,7 +67,7 @@ static void vga_isa_realizefn(DeviceState *dev, Error **errp)
                                         isa_mem_base + 0x000a0000,
                                         vga_io_memory, 1);
     memory_region_set_coalescing(vga_io_memory);
-    s->con = graphic_console_init(DEVICE(dev), s->hw_ops, s);
+    s->con = graphic_console_init(DEVICE(dev), 0, s->hw_ops, s);
 
     vga_init_vbe(s, OBJECT(dev), isa_address_space(isadev));
     /* ROM BIOS */

hw/display/vga-pci.c

@@ -151,7 +151,7 @@ static int pci_std_vga_initfn(PCIDevice *dev)
     vga_init(s, OBJECT(dev), pci_address_space(dev), pci_address_space_io(dev),
              true);
 
-    s->con = graphic_console_init(DEVICE(dev), s->hw_ops, s);
+    s->con = graphic_console_init(DEVICE(dev), 0, s->hw_ops, s);
 
     /* XXX: VGA_RAM_SIZE must be a power of two */
     pci_register_bar(&d->dev, 0, PCI_BASE_ADDRESS_MEM_PREFETCH, &s->vram);

hw/display/vmware_vga.c

@@ -1199,7 +1199,7 @@ static void vmsvga_init(DeviceState *dev, struct vmsvga_state_s *s,
     s->scratch_size = SVGA_SCRATCH_SIZE;
     s->scratch = g_malloc(s->scratch_size * 4);
 
-    s->vga.con = graphic_console_init(dev, &vmsvga_ops, s);
+    s->vga.con = graphic_console_init(dev, 0, &vmsvga_ops, s);
 
     s->fifo_size = SVGA_FIFO_SIZE;
     memory_region_init_ram(&s->fifo_ram, NULL, "vmsvga.fifo", s->fifo_size);

hw/display/xenfb.c

@@ -992,7 +992,7 @@ wait_more:
 
     /* vfb */
     fb = container_of(xfb, struct XenFB, c.xendev);
-    fb->c.con = graphic_console_init(NULL, &xenfb_ops, fb);
+    fb->c.con = graphic_console_init(NULL, 0, &xenfb_ops, fb);
     fb->have_console = 1;
 
     /* vkbd */

hw/dma/pl330.c

@@ -227,7 +227,8 @@ static const VMStateDescription vmstate_pl330_queue = {
 };
 
 struct PL330State {
-    SysBusDevice busdev;
+    SysBusDevice parent_obj;
+
     MemoryRegion iomem;
     qemu_irq irq_abort;
     qemu_irq *irq;
@@ -577,7 +578,7 @@ static inline void pl330_queue_remove_tagged(PL330Queue *s, uint8_t tag)
 
 static inline void pl330_fault(PL330Chan *ch, uint32_t flags)
 {
-    DB_PRINT("ch: %p, flags: %x\n", ch, flags);
+    DB_PRINT("ch: %p, flags: %" PRIx32 "\n", ch, flags);
     ch->fault_type |= flags;
     if (ch->state == pl330_chan_fault) {
         return;
@@ -600,10 +601,12 @@ static inline void pl330_fault(PL330Chan *ch, uint32_t flags)
  *   LEN - number of elements in ARGS array
  */
 
-static void pl330_dmaaddh(PL330Chan *ch, uint8_t opcode, uint8_t *args, int len)
+static void pl330_dmaadxh(PL330Chan *ch, uint8_t *args, bool ra, bool neg)
 {
-    uint16_t im = (((uint16_t)args[1]) << 8) | ((uint16_t)args[0]);
+    uint32_t im = (args[1] << 8) | args[0];
-    uint8_t ra = (opcode >> 1) & 1;
+    if (neg) {
+        im |= 0xffffu << 16;
+    }
 
     if (ch->is_manager) {
         pl330_fault(ch, PL330_FAULT_UNDEF_INSTR);
@@ -616,6 +619,16 @@ static void pl330_dmaaddh(PL330Chan *ch, uint8_t opcode, uint8_t *args, int len)
     }
 }
 
+static void pl330_dmaaddh(PL330Chan *ch, uint8_t opcode, uint8_t *args, int len)
+{
+    pl330_dmaadxh(ch, args, extract32(opcode, 1, 1), false);
+}
+
+static void pl330_dmaadnh(PL330Chan *ch, uint8_t opcode, uint8_t *args, int len)
+{
+    pl330_dmaadxh(ch, args, extract32(opcode, 1, 1), true);
+}
+
 static void pl330_dmaend(PL330Chan *ch, uint8_t opcode,
                          uint8_t *args, int len)
 {
@@ -723,7 +736,8 @@ static void pl330_dmald(PL330Chan *ch, uint8_t opcode, uint8_t *args, int len)
     ch->stall = pl330_queue_put_insn(&ch->parent->read_queue, ch->src,
                                     size, num, inc, 0, ch->tag);
     if (!ch->stall) {
-        DB_PRINT("channel:%d address:%08x size:%d num:%d %c\n",
+        DB_PRINT("channel:%" PRId8 " address:%08" PRIx32 " size:%" PRIx32
+                 " num:%" PRId32 " %c\n",
                  ch->tag, ch->src, size, num, inc ? 'Y' : 'N');
         ch->src += inc ? size * num - (ch->src & (size - 1)) : 0;
     }
@@ -868,9 +882,10 @@ static void pl330_dmasev(PL330Chan *ch, uint8_t opcode, uint8_t *args, int len)
     }
     if (ch->parent->inten & (1 << ev_id)) {
         ch->parent->int_status |= (1 << ev_id);
-        DB_PRINT("event interrupt raised %d\n", ev_id);
+        DB_PRINT("event interrupt raised %" PRId8 "\n", ev_id);
         qemu_irq_raise(ch->parent->irq[ev_id]);
     }
+    DB_PRINT("event raised %" PRId8 "\n", ev_id);
     ch->parent->ev_status |= (1 << ev_id);
 }
 
@@ -895,7 +910,8 @@ static void pl330_dmast(PL330Chan *ch, uint8_t opcode, uint8_t *args, int len)
     ch->stall = pl330_queue_put_insn(&ch->parent->write_queue, ch->dst,
                                     size, num, inc, 0, ch->tag);
     if (!ch->stall) {
-        DB_PRINT("channel:%d address:%08x size:%d num:%d %c\n",
+        DB_PRINT("channel:%" PRId8 " address:%08" PRIx32 " size:%" PRIx32
+                 " num:%" PRId32 " %c\n",
                  ch->tag, ch->dst, size, num, inc ? 'Y' : 'N');
         ch->dst += inc ? size * num - (ch->dst & (size - 1)) : 0;
     }
@@ -972,6 +988,7 @@ static void pl330_dmawfe(PL330Chan *ch, uint8_t opcode,
             }
         }
         ch->parent->ev_status &= ~(1 << ev_id);
+        DB_PRINT("event lowered %" PRIx8 "\n", ev_id);
     } else {
         ch->stall = 1;
     }
@@ -1037,6 +1054,7 @@ static void pl330_dmawmb(PL330Chan *ch, uint8_t opcode,
 /* NULL terminated array of the instruction descriptions. */
 static const PL330InsnDesc insn_desc[] = {
     { .opcode = 0x54, .opmask = 0xFD, .size = 3, .exec = pl330_dmaaddh, },
+    { .opcode = 0x5c, .opmask = 0xFD, .size = 3, .exec = pl330_dmaadnh, },
     { .opcode = 0x00, .opmask = 0xFF, .size = 1, .exec = pl330_dmaend, },
     { .opcode = 0x35, .opmask = 0xFF, .size = 2, .exec = pl330_dmaflushp, },
     { .opcode = 0xA0, .opmask = 0xFD, .size = 6, .exec = pl330_dmago, },
@@ -1108,7 +1126,6 @@ static int pl330_chan_exec(PL330Chan *ch)
             ch->state != pl330_chan_waiting_periph &&
             ch->state != pl330_chan_at_barrier &&
             ch->state != pl330_chan_waiting_event) {
-        DB_PRINT("%d\n", ch->state);
         return 0;
     }
     ch->stall = 0;
@@ -1155,7 +1172,7 @@ static int pl330_exec_cycle(PL330Chan *channel)
 
         dma_memory_read(&address_space_memory, q->addr, buf, len);
         if (PL330_ERR_DEBUG > 1) {
-            DB_PRINT("PL330 read from memory @%08x (size = %08x):\n",
+            DB_PRINT("PL330 read from memory @%08" PRIx32 " (size = %08x):\n",
                       q->addr, len);
             qemu_hexdump((char *)buf, stderr, "", len);
         }
@@ -1187,8 +1204,8 @@ static int pl330_exec_cycle(PL330Chan *channel)
         if (fifo_res == PL330_FIFO_OK || q->z) {
             dma_memory_write(&address_space_memory, q->addr, buf, len);
             if (PL330_ERR_DEBUG > 1) {
-                DB_PRINT("PL330 read from memory @%08x (size = %08x):\n",
+                DB_PRINT("PL330 read from memory @%08" PRIx32
-                         q->addr, len);
+                         " (size = %08x):\n", q->addr, len);
                 qemu_hexdump((char *)buf, stderr, "", len);
             }
             if (q->inc) {
@@ -1277,7 +1294,7 @@ static void pl330_debug_exec(PL330State *s)
     args[2] = (s->dbg[1] >>  8) & 0xff;
     args[3] = (s->dbg[1] >> 16) & 0xff;
     args[4] = (s->dbg[1] >> 24) & 0xff;
-    DB_PRINT("chan id: %d\n", chan_id);
+    DB_PRINT("chan id: %" PRIx8 "\n", chan_id);
     if (s->dbg[0] & 1) {
         ch = &s->chan[chan_id];
     } else {
@@ -1311,7 +1328,7 @@ static void pl330_iomem_write(void *opaque, hwaddr offset,
                               uint64_t value, unsigned size)
 {
     PL330State *s = (PL330State *) opaque;
-    uint32_t i;
+    int i;
 
     DB_PRINT("addr: %08x data: %08x\n", (unsigned)offset, (unsigned)value);
 
@@ -1467,8 +1484,8 @@ static inline uint32_t pl330_iomem_read_imp(void *opaque,
 static uint64_t pl330_iomem_read(void *opaque, hwaddr offset,
         unsigned size)
 {
-    int ret = pl330_iomem_read_imp(opaque, offset);
+    uint32_t ret = pl330_iomem_read_imp(opaque, offset);
-    DB_PRINT("addr: %08x data: %08x\n", (unsigned)offset, ret);
+    DB_PRINT("addr: %08" HWADDR_PRIx " data: %08" PRIx32 "\n", offset, ret);
     return ret;
 }
 
@@ -1554,7 +1571,7 @@ static void pl330_realize(DeviceState *dev, Error **errp)
         s->cfg[1] |= 5;
         break;
     default:
-        error_setg(errp, "Bad value for i-cache_len property: %d\n",
+        error_setg(errp, "Bad value for i-cache_len property: %" PRIx8 "\n",
                    s->i_cache_len);
         return;
     }
@@ -1589,7 +1606,7 @@ static void pl330_realize(DeviceState *dev, Error **errp)
         s->cfg[CFG_CRD] |= 0x4;
         break;
     default:
-        error_setg(errp, "Bad value for data_width property: %d\n",
+        error_setg(errp, "Bad value for data_width property: %" PRIx8 "\n",
                    s->data_width);
         return;
     }
@@ -1602,7 +1619,7 @@ static void pl330_realize(DeviceState *dev, Error **errp)
 
     pl330_queue_init(&s->read_queue, s->rd_q_dep, s);
     pl330_queue_init(&s->write_queue, s->wr_q_dep, s);
-    pl330_fifo_init(&s->fifo, s->data_buffer_dep);
+    pl330_fifo_init(&s->fifo, s->data_width / 4 * s->data_buffer_dep);
 }
 
 static Property pl330_properties[] = {

hw/i386/kvm/pci-assign.c

@@ -743,6 +743,7 @@ static void assign_failed_examine(AssignedDevice *dev)
         goto fail;
     }
 
+    driver[r] = 0;
     ns = strrchr(driver, '/');
     if (!ns) {
         goto fail;

hw/i386/pc_piix.c

@@ -221,10 +221,16 @@ static void pc_init1(QEMUMachineInitArgs *args,
     } else {
         for(i = 0; i < MAX_IDE_BUS; i++) {
             ISADevice *dev;
+            char busname[] = "ide.0";
             dev = isa_ide_init(isa_bus, ide_iobase[i], ide_iobase2[i],
                                ide_irq[i],
                                hd[MAX_IDE_DEVS * i], hd[MAX_IDE_DEVS * i + 1]);
-            idebus[i] = qdev_get_child_bus(DEVICE(dev), "ide.0");
+            /*
+             * The ide bus name is ide.0 for the first bus and ide.1 for the
+             * second one.
+             */
+            busname[4] = '0' + i;
+            idebus[i] = qdev_get_child_bus(DEVICE(dev), busname);
         }
     }
 

hw/ide/ahci.h

@@ -40,7 +40,7 @@
 #define AHCI_PORT_PRIV_DMA_SZ     (AHCI_CMD_SLOT_SZ + AHCI_CMD_TBL_AR_SZ + \
                                    AHCI_RX_FIS_SZ)
 
-#define AHCI_IRQ_ON_SG            (1 << 31)
+#define AHCI_IRQ_ON_SG            (1U << 31)
 #define AHCI_CMD_ATAPI            (1 << 5)
 #define AHCI_CMD_WRITE            (1 << 6)
 #define AHCI_CMD_PREFETCH         (1 << 7)
@@ -61,7 +61,7 @@
 /* HOST_CTL bits */
 #define HOST_CTL_RESET            (1 << 0)  /* reset controller; self-clear */
 #define HOST_CTL_IRQ_EN           (1 << 1)  /* global IRQ enable */
-#define HOST_CTL_AHCI_EN          (1 << 31) /* AHCI enabled */
+#define HOST_CTL_AHCI_EN          (1U << 31) /* AHCI enabled */
 
 /* HOST_CAP bits */
 #define HOST_CAP_SSC              (1 << 14) /* Slumber capable */
@@ -69,7 +69,7 @@
 #define HOST_CAP_CLO              (1 << 24) /* Command List Override support */
 #define HOST_CAP_SSS              (1 << 27) /* Staggered Spin-up */
 #define HOST_CAP_NCQ              (1 << 30) /* Native Command Queueing */
-#define HOST_CAP_64               (1 << 31) /* PCI DAC (64-bit DMA) support */
+#define HOST_CAP_64               (1U << 31) /* PCI DAC (64-bit DMA) support */
 
 /* registers for each SATA port */
 #define PORT_LST_ADDR             0x00 /* command list DMA addr */
@@ -89,7 +89,7 @@
 #define PORT_RESERVED             0x3c /* reserved */
 
 /* PORT_IRQ_{STAT,MASK} bits */
-#define PORT_IRQ_COLD_PRES        (1 << 31) /* cold presence detect */
+#define PORT_IRQ_COLD_PRES        (1U << 31) /* cold presence detect */
 #define PORT_IRQ_TF_ERR           (1 << 30) /* task file error */
 #define PORT_IRQ_HBUS_ERR         (1 << 29) /* host bus fatal error */
 #define PORT_IRQ_HBUS_DATA_ERR    (1 << 28) /* host bus data error */
@@ -151,7 +151,7 @@
 #define PORT_IRQ_STAT_HBDS        (1 << 28) /* Host Bus Data Error Status */
 #define PORT_IRQ_STAT_HBFS        (1 << 29) /* Host Bus Fatal Error Status */
 #define PORT_IRQ_STAT_TFES        (1 << 30) /* Task File Error Status */
-#define PORT_IRQ_STAT_CPDS        (1 << 31) /* Code Port Detect Status */
+#define PORT_IRQ_STAT_CPDS        (1U << 31) /* Code Port Detect Status */
 
 /* ap->flags bits */
 #define AHCI_FLAG_NO_NCQ                  (1 << 24)

hw/ide/piix.c

@@ -167,7 +167,7 @@ static int pci_piix_ide_initfn(PCIDevice *dev)
     return 0;
 }
 
-static int pci_piix3_xen_ide_unplug(DeviceState *dev)
+int pci_piix3_xen_ide_unplug(DeviceState *dev)
 {
     PCIIDEState *pci_ide;
     DriveInfo *di;
@@ -266,7 +266,6 @@ static void piix3_ide_xen_class_init(ObjectClass *klass, void *data)
     k->device_id = PCI_DEVICE_ID_INTEL_82371SB_1;
     k->class_id = PCI_CLASS_STORAGE_IDE;
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
-    dc->unplug = pci_piix3_xen_ide_unplug;
 }
 
 static const TypeInfo piix3_ide_xen_info = {

hw/intc/Makefile.objs

@@ -25,3 +25,4 @@ obj-$(CONFIG_SH4) += sh_intc.o
 obj-$(CONFIG_XICS) += xics.o
 obj-$(CONFIG_XICS_KVM) += xics_kvm.o
 obj-$(CONFIG_ALLWINNER_A10_PIC) += allwinner-a10-pic.o
+obj-$(CONFIG_S390_FLIC) += s390_flic.o

hw/intc/arm_gic_kvm.c

@@ -3,6 +3,7 @@
  *
  * Copyright (c) 2012 Linaro Limited
  * Written by Peter Maydell
+ * Save/Restore logic added by Christoffer Dall.
  *
  * 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
@@ -23,6 +24,20 @@
 #include "kvm_arm.h"
 #include "gic_internal.h"
 
+//#define DEBUG_GIC_KVM
+
+#ifdef DEBUG_GIC_KVM
+static const int debug_gic_kvm = 1;
+#else
+static const int debug_gic_kvm = 0;
+#endif
+
+#define DPRINTF(fmt, ...) do { \
+        if (debug_gic_kvm) { \
+            printf("arm_gic: " fmt , ## __VA_ARGS__); \
+        } \
+    } while (0)
+
 #define TYPE_KVM_ARM_GIC "kvm-arm-gic"
 #define KVM_ARM_GIC(obj) \
      OBJECT_CHECK(GICState, (obj), TYPE_KVM_ARM_GIC)
@@ -72,14 +87,419 @@ static void kvm_arm_gic_set_irq(void *opaque, int irq, int level)
     kvm_set_irq(kvm_state, kvm_irq, !!level);
 }
 
+static bool kvm_arm_gic_can_save_restore(GICState *s)
+{
+    return s->dev_fd >= 0;
+}
+
+static void kvm_gic_access(GICState *s, int group, int offset,
+                                   int cpu, uint32_t *val, bool write)
+{
+    struct kvm_device_attr attr;
+    int type;
+    int err;
+
+    cpu = cpu & 0xff;
+
+    attr.flags = 0;
+    attr.group = group;
+    attr.attr = (((uint64_t)cpu << KVM_DEV_ARM_VGIC_CPUID_SHIFT) &
+                 KVM_DEV_ARM_VGIC_CPUID_MASK) |
+                (((uint64_t)offset << KVM_DEV_ARM_VGIC_OFFSET_SHIFT) &
+                 KVM_DEV_ARM_VGIC_OFFSET_MASK);
+    attr.addr = (uintptr_t)val;
+
+    if (write) {
+        type = KVM_SET_DEVICE_ATTR;
+    } else {
+        type = KVM_GET_DEVICE_ATTR;
+    }
+
+    err = kvm_device_ioctl(s->dev_fd, type, &attr);
+    if (err < 0) {
+        fprintf(stderr, "KVM_{SET/GET}_DEVICE_ATTR failed: %s\n",
+                strerror(-err));
+        abort();
+    }
+}
+
+static void kvm_gicd_access(GICState *s, int offset, int cpu,
+                            uint32_t *val, bool write)
+{
+    kvm_gic_access(s, KVM_DEV_ARM_VGIC_GRP_DIST_REGS,
+                   offset, cpu, val, write);
+}
+
+static void kvm_gicc_access(GICState *s, int offset, int cpu,
+                            uint32_t *val, bool write)
+{
+    kvm_gic_access(s, KVM_DEV_ARM_VGIC_GRP_CPU_REGS,
+                   offset, cpu, val, write);
+}
+
+#define for_each_irq_reg(_ctr, _max_irq, _field_width) \
+    for (_ctr = 0; _ctr < ((_max_irq) / (32 / (_field_width))); _ctr++)
+
+/*
+ * Translate from the in-kernel field for an IRQ value to/from the qemu
+ * representation.
+ */
+typedef void (*vgic_translate_fn)(GICState *s, int irq, int cpu,
+                                  uint32_t *field, bool to_kernel);
+
+/* synthetic translate function used for clear/set registers to completely
+ * clear a setting using a clear-register before setting the remaing bits
+ * using a set-register */
+static void translate_clear(GICState *s, int irq, int cpu,
+                            uint32_t *field, bool to_kernel)
+{
+    if (to_kernel) {
+        *field = ~0;
+    } else {
+        /* does not make sense: qemu model doesn't use set/clear regs */
+        abort();
+    }
+}
+
+static void translate_enabled(GICState *s, int irq, int cpu,
+                              uint32_t *field, bool to_kernel)
+{
+    int cm = (irq < GIC_INTERNAL) ? (1 << cpu) : ALL_CPU_MASK;
+
+    if (to_kernel) {
+        *field = GIC_TEST_ENABLED(irq, cm);
+    } else {
+        if (*field & 1) {
+            GIC_SET_ENABLED(irq, cm);
+        }
+    }
+}
+
+static void translate_pending(GICState *s, int irq, int cpu,
+                              uint32_t *field, bool to_kernel)
+{
+    int cm = (irq < GIC_INTERNAL) ? (1 << cpu) : ALL_CPU_MASK;
+
+    if (to_kernel) {
+        *field = gic_test_pending(s, irq, cm);
+    } else {
+        if (*field & 1) {
+            GIC_SET_PENDING(irq, cm);
+            /* TODO: Capture is level-line is held high in the kernel */
+        }
+    }
+}
+
+static void translate_active(GICState *s, int irq, int cpu,
+                             uint32_t *field, bool to_kernel)
+{
+    int cm = (irq < GIC_INTERNAL) ? (1 << cpu) : ALL_CPU_MASK;
+
+    if (to_kernel) {
+        *field = GIC_TEST_ACTIVE(irq, cm);
+    } else {
+        if (*field & 1) {
+            GIC_SET_ACTIVE(irq, cm);
+        }
+    }
+}
+
+static void translate_trigger(GICState *s, int irq, int cpu,
+                              uint32_t *field, bool to_kernel)
+{
+    if (to_kernel) {
+        *field = (GIC_TEST_EDGE_TRIGGER(irq)) ? 0x2 : 0x0;
+    } else {
+        if (*field & 0x2) {
+            GIC_SET_EDGE_TRIGGER(irq);
+        }
+    }
+}
+
+static void translate_priority(GICState *s, int irq, int cpu,
+                               uint32_t *field, bool to_kernel)
+{
+    if (to_kernel) {
+        *field = GIC_GET_PRIORITY(irq, cpu) & 0xff;
+    } else {
+        gic_set_priority(s, cpu, irq, *field & 0xff);
+    }
+}
+
+static void translate_targets(GICState *s, int irq, int cpu,
+                              uint32_t *field, bool to_kernel)
+{
+    if (to_kernel) {
+        *field = s->irq_target[irq] & 0xff;
+    } else {
+        s->irq_target[irq] = *field & 0xff;
+    }
+}
+
+static void translate_sgisource(GICState *s, int irq, int cpu,
+                                uint32_t *field, bool to_kernel)
+{
+    if (to_kernel) {
+        *field = s->sgi_pending[irq][cpu] & 0xff;
+    } else {
+        s->sgi_pending[irq][cpu] = *field & 0xff;
+    }
+}
+
+/* Read a register group from the kernel VGIC */
+static void kvm_dist_get(GICState *s, uint32_t offset, int width,
+                         int maxirq, vgic_translate_fn translate_fn)
+{
+    uint32_t reg;
+    int i;
+    int j;
+    int irq;
+    int cpu;
+    int regsz = 32 / width; /* irqs per kernel register */
+    uint32_t field;
+
+    for_each_irq_reg(i, maxirq, width) {
+        irq = i * regsz;
+        cpu = 0;
+        while ((cpu < s->num_cpu && irq < GIC_INTERNAL) || cpu == 0) {
+            kvm_gicd_access(s, offset, cpu, &reg, false);
+            for (j = 0; j < regsz; j++) {
+                field = extract32(reg, j * width, width);
+                translate_fn(s, irq + j, cpu, &field, false);
+            }
+
+            cpu++;
+        }
+        offset += 4;
+    }
+}
+
+/* Write a register group to the kernel VGIC */
+static void kvm_dist_put(GICState *s, uint32_t offset, int width,
+                         int maxirq, vgic_translate_fn translate_fn)
+{
+    uint32_t reg;
+    int i;
+    int j;
+    int irq;
+    int cpu;
+    int regsz = 32 / width; /* irqs per kernel register */
+    uint32_t field;
+
+    for_each_irq_reg(i, maxirq, width) {
+        irq = i * regsz;
+        cpu = 0;
+        while ((cpu < s->num_cpu && irq < GIC_INTERNAL) || cpu == 0) {
+            reg = 0;
+            for (j = 0; j < regsz; j++) {
+                translate_fn(s, irq + j, cpu, &field, true);
+                reg = deposit32(reg, j * width, width, field);
+            }
+            kvm_gicd_access(s, offset, cpu, &reg, true);
+
+            cpu++;
+        }
+        offset += 4;
+    }
+}
+
 static void kvm_arm_gic_put(GICState *s)
 {
-    /* TODO: there isn't currently a kernel interface to set the GIC state */
+    uint32_t reg;
+    int i;
+    int cpu;
+    int num_cpu;
+    int num_irq;
+
+    if (!kvm_arm_gic_can_save_restore(s)) {
+            DPRINTF("Cannot put kernel gic state, no kernel interface");
+            return;
+    }
+
+    /* Note: We do the restore in a slightly different order than the save
+     * (where the order doesn't matter and is simply ordered according to the
+     * register offset values */
+
+    /*****************************************************************
+     * Distributor State
+     */
+
+    /* s->enabled -> GICD_CTLR */
+    reg = s->enabled;
+    kvm_gicd_access(s, 0x0, 0, &reg, true);
+
+    /* Sanity checking on GICD_TYPER and s->num_irq, s->num_cpu */
+    kvm_gicd_access(s, 0x4, 0, &reg, false);
+    num_irq = ((reg & 0x1f) + 1) * 32;
+    num_cpu = ((reg & 0xe0) >> 5) + 1;
+
+    if (num_irq < s->num_irq) {
+            fprintf(stderr, "Restoring %u IRQs, but kernel supports max %d\n",
+                    s->num_irq, num_irq);
+            abort();
+    } else if (num_cpu != s->num_cpu) {
+            fprintf(stderr, "Restoring %u CPU interfaces, kernel only has %d\n",
+                    s->num_cpu, num_cpu);
+            /* Did we not create the VCPUs in the kernel yet? */
+            abort();
+    }
+
+    /* TODO: Consider checking compatibility with the IIDR ? */
+
+    /* irq_state[n].enabled -> GICD_ISENABLERn */
+    kvm_dist_put(s, 0x180, 1, s->num_irq, translate_clear);
+    kvm_dist_put(s, 0x100, 1, s->num_irq, translate_enabled);
+
+    /* s->irq_target[irq] -> GICD_ITARGETSRn
+     * (restore targets before pending to ensure the pending state is set on
+     * the appropriate CPU interfaces in the kernel) */
+    kvm_dist_put(s, 0x800, 8, s->num_irq, translate_targets);
+
+    /* irq_state[n].pending + irq_state[n].level -> GICD_ISPENDRn */
+    kvm_dist_put(s, 0x280, 1, s->num_irq, translate_clear);
+    kvm_dist_put(s, 0x200, 1, s->num_irq, translate_pending);
+
+    /* irq_state[n].active -> GICD_ISACTIVERn */
+    kvm_dist_put(s, 0x380, 1, s->num_irq, translate_clear);
+    kvm_dist_put(s, 0x300, 1, s->num_irq, translate_active);
+
+    /* irq_state[n].trigger -> GICD_ICFRn */
+    kvm_dist_put(s, 0xc00, 2, s->num_irq, translate_trigger);
+
+    /* s->priorityX[irq] -> ICD_IPRIORITYRn */
+    kvm_dist_put(s, 0x400, 8, s->num_irq, translate_priority);
+
+    /* s->sgi_pending -> ICD_CPENDSGIRn */
+    kvm_dist_put(s, 0xf10, 8, GIC_NR_SGIS, translate_clear);
+    kvm_dist_put(s, 0xf20, 8, GIC_NR_SGIS, translate_sgisource);
+
+
+    /*****************************************************************
+     * CPU Interface(s) State
+     */
+
+    for (cpu = 0; cpu < s->num_cpu; cpu++) {
+        /* s->cpu_enabled[cpu] -> GICC_CTLR */
+        reg = s->cpu_enabled[cpu];
+        kvm_gicc_access(s, 0x00, cpu, &reg, true);
+
+        /* s->priority_mask[cpu] -> GICC_PMR */
+        reg = (s->priority_mask[cpu] & 0xff);
+        kvm_gicc_access(s, 0x04, cpu, &reg, true);
+
+        /* s->bpr[cpu] -> GICC_BPR */
+        reg = (s->bpr[cpu] & 0x7);
+        kvm_gicc_access(s, 0x08, cpu, &reg, true);
+
+        /* s->abpr[cpu] -> GICC_ABPR */
+        reg = (s->abpr[cpu] & 0x7);
+        kvm_gicc_access(s, 0x1c, cpu, &reg, true);
+
+        /* s->apr[n][cpu] -> GICC_APRn */
+        for (i = 0; i < 4; i++) {
+            reg = s->apr[i][cpu];
+            kvm_gicc_access(s, 0xd0 + i * 4, cpu, &reg, true);
+        }
+    }
 }
 
 static void kvm_arm_gic_get(GICState *s)
 {
-    /* TODO: there isn't currently a kernel interface to get the GIC state */
+    uint32_t reg;
+    int i;
+    int cpu;
+
+    if (!kvm_arm_gic_can_save_restore(s)) {
+            DPRINTF("Cannot get kernel gic state, no kernel interface");
+            return;
+    }
+
+    /*****************************************************************
+     * Distributor State
+     */
+
+    /* GICD_CTLR -> s->enabled */
+    kvm_gicd_access(s, 0x0, 0, &reg, false);
+    s->enabled = reg & 1;
+
+    /* Sanity checking on GICD_TYPER -> s->num_irq, s->num_cpu */
+    kvm_gicd_access(s, 0x4, 0, &reg, false);
+    s->num_irq = ((reg & 0x1f) + 1) * 32;
+    s->num_cpu = ((reg & 0xe0) >> 5) + 1;
+
+    if (s->num_irq > GIC_MAXIRQ) {
+            fprintf(stderr, "Too many IRQs reported from the kernel: %d\n",
+                    s->num_irq);
+            abort();
+    }
+
+    /* GICD_IIDR -> ? */
+    kvm_gicd_access(s, 0x8, 0, &reg, false);
+
+    /* Verify no GROUP 1 interrupts configured in the kernel */
+    for_each_irq_reg(i, s->num_irq, 1) {
+        kvm_gicd_access(s, 0x80 + (i * 4), 0, &reg, false);
+        if (reg != 0) {
+            fprintf(stderr, "Unsupported GICD_IGROUPRn value: %08x\n",
+                    reg);
+            abort();
+        }
+    }
+
+    /* Clear all the IRQ settings */
+    for (i = 0; i < s->num_irq; i++) {
+        memset(&s->irq_state[i], 0, sizeof(s->irq_state[0]));
+    }
+
+    /* GICD_ISENABLERn -> irq_state[n].enabled */
+    kvm_dist_get(s, 0x100, 1, s->num_irq, translate_enabled);
+
+    /* GICD_ISPENDRn -> irq_state[n].pending + irq_state[n].level */
+    kvm_dist_get(s, 0x200, 1, s->num_irq, translate_pending);
+
+    /* GICD_ISACTIVERn -> irq_state[n].active */
+    kvm_dist_get(s, 0x300, 1, s->num_irq, translate_active);
+
+    /* GICD_ICFRn -> irq_state[n].trigger */
+    kvm_dist_get(s, 0xc00, 2, s->num_irq, translate_trigger);
+
+    /* GICD_IPRIORITYRn -> s->priorityX[irq] */
+    kvm_dist_get(s, 0x400, 8, s->num_irq, translate_priority);
+
+    /* GICD_ITARGETSRn -> s->irq_target[irq] */
+    kvm_dist_get(s, 0x800, 8, s->num_irq, translate_targets);
+
+    /* GICD_CPENDSGIRn -> s->sgi_pending */
+    kvm_dist_get(s, 0xf10, 8, GIC_NR_SGIS, translate_sgisource);
+
+
+    /*****************************************************************
+     * CPU Interface(s) State
+     */
+
+    for (cpu = 0; cpu < s->num_cpu; cpu++) {
+        /* GICC_CTLR -> s->cpu_enabled[cpu] */
+        kvm_gicc_access(s, 0x00, cpu, &reg, false);
+        s->cpu_enabled[cpu] = (reg & 1);
+
+        /* GICC_PMR -> s->priority_mask[cpu] */
+        kvm_gicc_access(s, 0x04, cpu, &reg, false);
+        s->priority_mask[cpu] = (reg & 0xff);
+
+        /* GICC_BPR -> s->bpr[cpu] */
+        kvm_gicc_access(s, 0x08, cpu, &reg, false);
+        s->bpr[cpu] = (reg & 0x7);
+
+        /* GICC_ABPR -> s->abpr[cpu] */
+        kvm_gicc_access(s, 0x1c, cpu, &reg, false);
+        s->abpr[cpu] = (reg & 0x7);
+
+        /* GICC_APRn -> s->apr[n][cpu] */
+        for (i = 0; i < 4; i++) {
+            kvm_gicc_access(s, 0xd0 + i * 4, cpu, &reg, false);
+            s->apr[i][cpu] = reg;
+        }
+    }
 }
 
 static void kvm_arm_gic_reset(DeviceState *dev)
@@ -97,6 +517,7 @@ static void kvm_arm_gic_realize(DeviceState *dev, Error **errp)
     GICState *s = KVM_ARM_GIC(dev);
     SysBusDevice *sbd = SYS_BUS_DEVICE(dev);
     KVMARMGICClass *kgc = KVM_ARM_GIC_GET_CLASS(s);
+    int ret;
 
     kgc->parent_realize(dev, errp);
     if (error_is_set(errp)) {
@@ -119,13 +540,27 @@ static void kvm_arm_gic_realize(DeviceState *dev, Error **errp)
     for (i = 0; i < s->num_cpu; i++) {
         sysbus_init_irq(sbd, &s->parent_irq[i]);
     }
+
+    /* Try to create the device via the device control API */
+    s->dev_fd = -1;
+    ret = kvm_create_device(kvm_state, KVM_DEV_TYPE_ARM_VGIC_V2, false);
+    if (ret >= 0) {
+        s->dev_fd = ret;
+    } else if (ret != -ENODEV && ret != -ENOTSUP) {
+        error_setg_errno(errp, -ret, "error creating in-kernel VGIC");
+        return;
+    }
+
     /* Distributor */
     memory_region_init_reservation(&s->iomem, OBJECT(s),
                                    "kvm-gic_dist", 0x1000);
     sysbus_init_mmio(sbd, &s->iomem);
     kvm_arm_register_device(&s->iomem,
                             (KVM_ARM_DEVICE_VGIC_V2 << KVM_ARM_DEVICE_ID_SHIFT)
-                            | KVM_VGIC_V2_ADDR_TYPE_DIST);
+                            | KVM_VGIC_V2_ADDR_TYPE_DIST,
+                            KVM_DEV_ARM_VGIC_GRP_ADDR,
+                            KVM_VGIC_V2_ADDR_TYPE_DIST,
+                            s->dev_fd);
     /* CPU interface for current core. Unlike arm_gic, we don't
      * provide the "interface for core #N" memory regions, because
      * cores with a VGIC don't have those.
@@ -135,7 +570,10 @@ static void kvm_arm_gic_realize(DeviceState *dev, Error **errp)
     sysbus_init_mmio(sbd, &s->cpuiomem[0]);
     kvm_arm_register_device(&s->cpuiomem[0],
                             (KVM_ARM_DEVICE_VGIC_V2 << KVM_ARM_DEVICE_ID_SHIFT)
-                            | KVM_VGIC_V2_ADDR_TYPE_CPU);
+                            | KVM_VGIC_V2_ADDR_TYPE_CPU,
+                            KVM_DEV_ARM_VGIC_GRP_ADDR,
+                            KVM_VGIC_V2_ADDR_TYPE_CPU,
+                            s->dev_fd);
 }
 
 static void kvm_arm_gic_class_init(ObjectClass *klass, void *data)

hw/intc/exynos4210_combiner.c

@@ -418,7 +418,7 @@ static int exynos4210_combiner_init(SysBusDevice *sbd)
     qdev_init_gpio_in(dev, exynos4210_combiner_handler, IIC_NIRQ);
 
     /* Connect SysBusDev irqs to device specific irqs */
-    for (i = 0; i < IIC_NIRQ; i++) {
+    for (i = 0; i < IIC_NGRP; i++) {
         sysbus_init_irq(sbd, &s->output_irq[i]);
     }
 

hw/intc/gic_internal.h

@@ -40,7 +40,7 @@
 #define GIC_SET_MODEL(irq) s->irq_state[irq].model = true
 #define GIC_CLEAR_MODEL(irq) s->irq_state[irq].model = false
 #define GIC_TEST_MODEL(irq) s->irq_state[irq].model
-#define GIC_SET_LEVEL(irq, cm) s->irq_state[irq].level = (cm)
+#define GIC_SET_LEVEL(irq, cm) s->irq_state[irq].level |= (cm)
 #define GIC_CLEAR_LEVEL(irq, cm) s->irq_state[irq].level &= ~(cm)
 #define GIC_TEST_LEVEL(irq, cm) ((s->irq_state[irq].level & (cm)) != 0)
 #define GIC_SET_EDGE_TRIGGER(irq) s->irq_state[irq].edge_trigger = true

hw/intc/openpic_kvm.c

@@ -228,7 +228,7 @@ int kvm_openpic_connect_vcpu(DeviceState *d, CPUState *cs)
 
     encap.cap = KVM_CAP_IRQ_MPIC;
     encap.args[0] = opp->fd;
-    encap.args[1] = cs->cpu_index;
+    encap.args[1] = kvm_arch_vcpu_id(cs);
 
     return kvm_vcpu_ioctl(cs, KVM_ENABLE_CAP, &encap);
 }

hw/intc/s390_flic.c

@@ -0,0 +1,322 @@
+/*
+ * QEMU S390x KVM floating interrupt controller (flic)
+ *
+ * Copyright 2014 IBM Corp.
+ * Author(s): Jens Freimann <jfrei@linux.vnet.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or (at
+ * your option) any later version. See the COPYING file in the top-level
+ * directory.
+ */
+
+#include <sys/ioctl.h>
+#include "qemu/error-report.h"
+#include "hw/sysbus.h"
+#include "sysemu/kvm.h"
+#include "migration/qemu-file.h"
+#include "hw/s390x/s390_flic.h"
+#include "trace.h"
+
+#define FLIC_SAVE_INITIAL_SIZE getpagesize()
+#define FLIC_FAILED (-1UL)
+#define FLIC_SAVEVM_VERSION 1
+
+void s390_flic_init(void)
+{
+    DeviceState *dev;
+    int r;
+
+    if (kvm_enabled()) {
+        dev = qdev_create(NULL, "s390-flic");
+        object_property_add_child(qdev_get_machine(), "s390-flic",
+                                OBJECT(dev), NULL);
+        r = qdev_init(dev);
+        if (r) {
+            error_report("flic: couldn't create qdev");
+        }
+    }
+}
+
+/**
+ * flic_get_all_irqs - store all pending irqs in buffer
+ * @buf: pointer to buffer which is passed to kernel
+ * @len: length of buffer
+ * @flic: pointer to flic device state
+ *
+ * Returns: -ENOMEM if buffer is too small,
+ * -EINVAL if attr.group is invalid,
+ * -EFAULT if copying to userspace failed,
+ * on success return number of stored interrupts
+ */
+static int flic_get_all_irqs(KVMS390FLICState *flic,
+                             void *buf, int len)
+{
+    struct kvm_device_attr attr = {
+        .group = KVM_DEV_FLIC_GET_ALL_IRQS,
+        .addr = (uint64_t) buf,
+        .attr = len,
+    };
+    int rc;
+
+    rc = ioctl(flic->fd, KVM_GET_DEVICE_ATTR, &attr);
+
+    return rc == -1 ? -errno : rc;
+}
+
+static void flic_enable_pfault(KVMS390FLICState *flic)
+{
+    struct kvm_device_attr attr = {
+        .group = KVM_DEV_FLIC_APF_ENABLE,
+    };
+    int rc;
+
+    rc = ioctl(flic->fd, KVM_SET_DEVICE_ATTR, &attr);
+
+    if (rc) {
+        fprintf(stderr, "flic: couldn't enable pfault\n");
+    }
+}
+
+static void flic_disable_wait_pfault(KVMS390FLICState *flic)
+{
+    struct kvm_device_attr attr = {
+        .group = KVM_DEV_FLIC_APF_DISABLE_WAIT,
+    };
+    int rc;
+
+    rc = ioctl(flic->fd, KVM_SET_DEVICE_ATTR, &attr);
+
+    if (rc) {
+        fprintf(stderr, "flic: couldn't disable pfault\n");
+    }
+}
+
+/** flic_enqueue_irqs - returns 0 on success
+ * @buf: pointer to buffer which is passed to kernel
+ * @len: length of buffer
+ * @flic: pointer to flic device state
+ *
+ * Returns: -EINVAL if attr.group is unknown
+ */
+static int flic_enqueue_irqs(void *buf, uint64_t len,
+                            KVMS390FLICState *flic)
+{
+    int rc;
+    struct kvm_device_attr attr = {
+        .group = KVM_DEV_FLIC_ENQUEUE,
+        .addr = (uint64_t) buf,
+        .attr = len,
+    };
+
+    rc = ioctl(flic->fd, KVM_SET_DEVICE_ATTR, &attr);
+
+    return rc ? -errno : 0;
+}
+
+/**
+ * __get_all_irqs - store all pending irqs in buffer
+ * @flic: pointer to flic device state
+ * @buf: pointer to pointer to a buffer
+ * @len: length of buffer
+ *
+ * Returns: return value of flic_get_all_irqs
+ * Note: Retry and increase buffer size until flic_get_all_irqs
+ * either returns a value >= 0 or a negative error code.
+ * -ENOMEM is an exception, which means the buffer is too small
+ * and we should try again. Other negative error codes can be
+ * -EFAULT and -EINVAL which we ignore at this point
+ */
+static int __get_all_irqs(KVMS390FLICState *flic,
+                          void **buf, int len)
+{
+    int r;
+
+    do {
+        /* returns -ENOMEM if buffer is too small and number
+         * of queued interrupts on success */
+        r = flic_get_all_irqs(flic, *buf, len);
+        if (r >= 0) {
+            break;
+        }
+        len *= 2;
+        *buf = g_try_realloc(*buf, len);
+        if (!buf) {
+            return -ENOMEM;
+        }
+    } while (r == -ENOMEM && len <= KVM_S390_FLIC_MAX_BUFFER);
+
+    return r;
+}
+
+/**
+ * kvm_flic_save - Save pending floating interrupts
+ * @f: QEMUFile containing migration state
+ * @opaque: pointer to flic device state
+ *
+ * Note: Pass buf and len to kernel. Start with one page and
+ * increase until buffer is sufficient or maxium size is
+ * reached
+ */
+static void kvm_flic_save(QEMUFile *f, void *opaque)
+{
+    KVMS390FLICState *flic = opaque;
+    int len = FLIC_SAVE_INITIAL_SIZE;
+    void *buf;
+    int count;
+
+    flic_disable_wait_pfault((struct KVMS390FLICState *) opaque);
+
+    buf = g_try_malloc0(len);
+    if (!buf) {
+        /* Storing FLIC_FAILED into the count field here will cause the
+         * target system to fail when attempting to load irqs from the
+         * migration state */
+        error_report("flic: couldn't allocate memory");
+        qemu_put_be64(f, FLIC_FAILED);
+        return;
+    }
+
+    count = __get_all_irqs(flic, &buf, len);
+    if (count < 0) {
+        error_report("flic: couldn't retrieve irqs from kernel, rc %d",
+                     count);
+        /* Storing FLIC_FAILED into the count field here will cause the
+         * target system to fail when attempting to load irqs from the
+         * migration state */
+        qemu_put_be64(f, FLIC_FAILED);
+    } else {
+        qemu_put_be64(f, count);
+        qemu_put_buffer(f, (uint8_t *) buf,
+                        count * sizeof(struct kvm_s390_irq));
+    }
+    g_free(buf);
+}
+
+/**
+ * kvm_flic_load - Load pending floating interrupts
+ * @f: QEMUFile containing migration state
+ * @opaque: pointer to flic device state
+ * @version_id: version id for migration
+ *
+ * Returns: value of flic_enqueue_irqs, -EINVAL on error
+ * Note: Do nothing when no interrupts where stored
+ * in QEMUFile
+ */
+static int kvm_flic_load(QEMUFile *f, void *opaque, int version_id)
+{
+    uint64_t len = 0;
+    uint64_t count = 0;
+    void *buf = NULL;
+    int r = 0;
+
+    if (version_id != FLIC_SAVEVM_VERSION) {
+        r = -EINVAL;
+        goto out;
+    }
+
+    flic_enable_pfault((struct KVMS390FLICState *) opaque);
+
+    count = qemu_get_be64(f);
+    len = count * sizeof(struct kvm_s390_irq);
+    if (count == FLIC_FAILED) {
+        r = -EINVAL;
+        goto out;
+    }
+    if (count == 0) {
+        r = 0;
+        goto out;
+    }
+    buf = g_try_malloc0(len);
+    if (!buf) {
+        r = -ENOMEM;
+        goto out;
+    }
+
+    if (qemu_get_buffer(f, (uint8_t *) buf, len) != len) {
+        r = -EINVAL;
+        goto out_free;
+    }
+    r = flic_enqueue_irqs(buf, len, (struct KVMS390FLICState *) opaque);
+
+out_free:
+    g_free(buf);
+out:
+    return r;
+}
+
+static void kvm_s390_flic_realize(DeviceState *dev, Error **errp)
+{
+    KVMS390FLICState *flic_state = KVM_S390_FLIC(dev);
+    struct kvm_create_device cd = {0};
+    int ret;
+
+    flic_state->fd = -1;
+    if (!kvm_check_extension(kvm_state, KVM_CAP_DEVICE_CTRL)) {
+        trace_flic_no_device_api(errno);
+        return;
+    }
+
+    cd.type = KVM_DEV_TYPE_FLIC;
+    ret = kvm_vm_ioctl(kvm_state, KVM_CREATE_DEVICE, &cd);
+    if (ret < 0) {
+        trace_flic_create_device(errno);
+        return;
+    }
+    flic_state->fd = cd.fd;
+
+    /* Register savevm handler for floating interrupts */
+    register_savevm(NULL, "s390-flic", 0, 1, kvm_flic_save,
+                    kvm_flic_load, (void *) flic_state);
+}
+
+static void kvm_s390_flic_unrealize(DeviceState *dev, Error **errp)
+{
+    KVMS390FLICState *flic_state = KVM_S390_FLIC(dev);
+
+    unregister_savevm(DEVICE(flic_state), "s390-flic", flic_state);
+}
+
+static void kvm_s390_flic_reset(DeviceState *dev)
+{
+    KVMS390FLICState *flic = KVM_S390_FLIC(dev);
+    struct kvm_device_attr attr = {
+        .group = KVM_DEV_FLIC_CLEAR_IRQS,
+    };
+    int rc = 0;
+
+    if (flic->fd == -1) {
+        return;
+    }
+
+    flic_disable_wait_pfault(flic);
+
+    rc = ioctl(flic->fd, KVM_SET_DEVICE_ATTR, &attr);
+    if (rc) {
+        trace_flic_reset_failed(errno);
+    }
+
+    flic_enable_pfault(flic);
+}
+
+static void kvm_s390_flic_class_init(ObjectClass *oc, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(oc);
+
+    dc->realize = kvm_s390_flic_realize;
+    dc->unrealize = kvm_s390_flic_unrealize;
+    dc->reset = kvm_s390_flic_reset;
+}
+
+static const TypeInfo kvm_s390_flic_info = {
+    .name          = TYPE_KVM_S390_FLIC,
+    .parent        = TYPE_SYS_BUS_DEVICE,
+    .instance_size = sizeof(KVMS390FLICState),
+    .class_init    = kvm_s390_flic_class_init,
+};
+
+static void kvm_s390_flic_register_types(void)
+{
+    type_register_static(&kvm_s390_flic_info);
+}
+
+type_init(kvm_s390_flic_register_types)

hw/intc/xics.c

@@ -33,6 +33,17 @@
 #include "qemu/error-report.h"
 #include "qapi/visitor.h"
 
+static int get_cpu_index_by_dt_id(int cpu_dt_id)
+{
+    PowerPCCPU *cpu = ppc_get_vcpu_by_dt_id(cpu_dt_id);
+
+    if (cpu) {
+        return cpu->parent_obj.cpu_index;
+    }
+
+    return -1;
+}
+
 void xics_cpu_setup(XICSState *icp, PowerPCCPU *cpu)
 {
     CPUState *cs = CPU(cpu);
@@ -659,7 +670,7 @@ static target_ulong h_cppr(PowerPCCPU *cpu, sPAPREnvironment *spapr,
 static target_ulong h_ipi(PowerPCCPU *cpu, sPAPREnvironment *spapr,
                           target_ulong opcode, target_ulong *args)
 {
-    target_ulong server = args[0];
+    target_ulong server = get_cpu_index_by_dt_id(args[0]);
     target_ulong mfrr = args[1];
 
     if (server >= spapr->icp->nr_servers) {
@@ -728,7 +739,7 @@ static void rtas_set_xive(PowerPCCPU *cpu, sPAPREnvironment *spapr,
     }
 
     nr = rtas_ld(args, 0);
-    server = rtas_ld(args, 1);
+    server = get_cpu_index_by_dt_id(rtas_ld(args, 1));
     priority = rtas_ld(args, 2);
 
     if (!ics_valid_irq(ics, nr) || (server >= ics->icp->nr_servers)

hw/intc/xics_kvm.c

@@ -65,7 +65,7 @@ static void icp_get_kvm_state(ICPState *ss)
     ret = kvm_vcpu_ioctl(ss->cs, KVM_GET_ONE_REG, &reg);
     if (ret != 0) {
         error_report("Unable to retrieve KVM interrupt controller state"
-                " for CPU %d: %s", ss->cs->cpu_index, strerror(errno));
+                " for CPU %ld: %s", kvm_arch_vcpu_id(ss->cs), strerror(errno));
         exit(1);
     }
 
@@ -97,7 +97,7 @@ static int icp_set_kvm_state(ICPState *ss, int version_id)
     ret = kvm_vcpu_ioctl(ss->cs, KVM_SET_ONE_REG, &reg);
     if (ret != 0) {
         error_report("Unable to restore KVM interrupt controller state (0x%"
-                PRIx64 ") for CPU %d: %s", state, ss->cs->cpu_index,
+                PRIx64 ") for CPU %ld: %s", state, kvm_arch_vcpu_id(ss->cs),
                 strerror(errno));
         return ret;
     }
@@ -325,15 +325,15 @@ static void xics_kvm_cpu_setup(XICSState *icp, PowerPCCPU *cpu)
         struct kvm_enable_cap xics_enable_cap = {
             .cap = KVM_CAP_IRQ_XICS,
             .flags = 0,
-            .args = {icpkvm->kernel_xics_fd, cs->cpu_index, 0, 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);
         if (ret < 0) {
-            error_report("Unable to connect CPU%d to kernel XICS: %s",
+            error_report("Unable to connect CPU%ld to kernel XICS: %s",
-                    cs->cpu_index, strerror(errno));
+                    kvm_arch_vcpu_id(cs), strerror(errno));
             exit(1);
         }
     }

hw/microblaze/petalogix_ml605_mmu.c

@@ -32,7 +32,6 @@
 #include "sysemu/sysemu.h"
 #include "hw/devices.h"
 #include "hw/boards.h"
-#include "hw/xilinx.h"
 #include "sysemu/blockdev.h"
 #include "hw/char/serial.h"
 #include "exec/address-spaces.h"
@@ -49,6 +48,7 @@
 
 #define NUM_SPI_FLASHES 4
 
+#define SPI_BASEADDR 0x40a00000
 #define MEMORY_BASEADDR 0x50000000
 #define FLASH_BASEADDR 0x86000000
 #define INTC_BASEADDR 0x81800000
@@ -57,6 +57,13 @@
 #define AXIENET_BASEADDR 0x82780000
 #define AXIDMA_BASEADDR 0x84600000
 
+#define AXIDMA_IRQ1         0
+#define AXIDMA_IRQ0         1
+#define TIMER_IRQ           2
+#define AXIENET_IRQ         3
+#define SPI_IRQ             4
+#define UART16550_IRQ       5
+
 static void machine_cpu_reset(MicroBlazeCPU *cpu)
 {
     CPUMBState *env = &cpu->env;
@@ -111,17 +118,27 @@ petalogix_ml605_init(QEMUMachineInitArgs *args)
                           2, 0x89, 0x18, 0x0000, 0x0, 0);
 
 
-    dev = xilinx_intc_create(INTC_BASEADDR, qdev_get_gpio_in(DEVICE(cpu),
+    dev = qdev_create(NULL, "xlnx.xps-intc");
-                             MB_CPU_IRQ), 4);
+    qdev_prop_set_uint32(dev, "kind-of-intr", 1 << TIMER_IRQ);
+    qdev_init_nofail(dev);
+    sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, INTC_BASEADDR);
+    sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0,
+                       qdev_get_gpio_in(DEVICE(cpu), MB_CPU_IRQ));
     for (i = 0; i < 32; i++) {
         irq[i] = qdev_get_gpio_in(dev, i);
     }
 
     serial_mm_init(address_space_mem, UART16550_BASEADDR + 0x1000, 2,
-                   irq[5], 115200, serial_hds[0], DEVICE_LITTLE_ENDIAN);
+                   irq[UART16550_IRQ], 115200, serial_hds[0],
+                   DEVICE_LITTLE_ENDIAN);
 
     /* 2 timers at irq 2 @ 100 Mhz.  */
-    xilinx_timer_create(TIMER_BASEADDR, irq[2], 0, 100 * 1000000);
+    dev = qdev_create(NULL, "xlnx.xps-timer");
+    qdev_prop_set_uint32(dev, "one-timer-only", 0);
+    qdev_prop_set_uint32(dev, "clock-frequency", 100 * 1000000);
+    qdev_init_nofail(dev);
+    sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, TIMER_BASEADDR);
+    sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, irq[TIMER_IRQ]);
 
     /* axi ethernet and dma initialization. */
     qemu_check_nic_model(&nd_table[0], "xlnx.axi-ethernet");
@@ -138,16 +155,30 @@ petalogix_ml605_init(QEMUMachineInitArgs *args)
                                   "axistream-connected-target", NULL);
     cs = object_property_get_link(OBJECT(dma),
                                   "axistream-control-connected-target", NULL);
-    xilinx_axiethernet_init(eth0, &nd_table[0], STREAM_SLAVE(ds),
+    qdev_set_nic_properties(eth0, &nd_table[0]);
-                            STREAM_SLAVE(cs), 0x82780000, irq[3], 0x1000,
+    qdev_prop_set_uint32(eth0, "rxmem", 0x1000);
-                            0x1000);
+    qdev_prop_set_uint32(eth0, "txmem", 0x1000);
+    object_property_set_link(OBJECT(eth0), OBJECT(ds),
+                             "axistream-connected", &error_abort);
+    object_property_set_link(OBJECT(eth0), OBJECT(cs),
+                             "axistream-control-connected", &error_abort);
+    qdev_init_nofail(eth0);
+    sysbus_mmio_map(SYS_BUS_DEVICE(eth0), 0, AXIENET_BASEADDR);
+    sysbus_connect_irq(SYS_BUS_DEVICE(eth0), 0, irq[AXIENET_IRQ]);
 
     ds = object_property_get_link(OBJECT(eth0),
                                   "axistream-connected-target", NULL);
     cs = object_property_get_link(OBJECT(eth0),
                                   "axistream-control-connected-target", NULL);
-    xilinx_axidma_init(dma, STREAM_SLAVE(ds), STREAM_SLAVE(cs), 0x84600000,
+    qdev_prop_set_uint32(dma, "freqhz", 100 * 1000000);
-                       irq[1], irq[0], 100 * 1000000);
+    object_property_set_link(OBJECT(dma), OBJECT(ds),
+                             "axistream-connected", &error_abort);
+    object_property_set_link(OBJECT(dma), OBJECT(cs),
+                             "axistream-control-connected", &error_abort);
+    qdev_init_nofail(dma);
+    sysbus_mmio_map(SYS_BUS_DEVICE(dma), 0, AXIDMA_BASEADDR);
+    sysbus_connect_irq(SYS_BUS_DEVICE(dma), 0, irq[AXIDMA_IRQ0]);
+    sysbus_connect_irq(SYS_BUS_DEVICE(dma), 1, irq[AXIDMA_IRQ1]);
 
     {
         SSIBus *spi;
@@ -156,8 +187,8 @@ petalogix_ml605_init(QEMUMachineInitArgs *args)
         qdev_prop_set_uint8(dev, "num-ss-bits", NUM_SPI_FLASHES);
         qdev_init_nofail(dev);
         busdev = SYS_BUS_DEVICE(dev);
-        sysbus_mmio_map(busdev, 0, 0x40a00000);
+        sysbus_mmio_map(busdev, 0, SPI_BASEADDR);
-        sysbus_connect_irq(busdev, 0, irq[4]);
+        sysbus_connect_irq(busdev, 0, irq[SPI_IRQ]);
 
         spi = (SSIBus *)qdev_get_child_bus(dev, "spi");
 

hw/microblaze/petalogix_s3adsp1800_mmu.c

@@ -30,7 +30,6 @@
 #include "sysemu/sysemu.h"
 #include "hw/devices.h"
 #include "hw/boards.h"
-#include "hw/xilinx.h"
 #include "sysemu/blockdev.h"
 #include "exec/address-spaces.h"
 
@@ -48,6 +47,10 @@
 #define UARTLITE_BASEADDR 0x84000000
 #define ETHLITE_BASEADDR 0x81000000
 
+#define TIMER_IRQ           0
+#define ETHLITE_IRQ         1
+#define UARTLITE_IRQ        3
+
 static void machine_cpu_reset(MicroBlazeCPU *cpu)
 {
     CPUMBState *env = &cpu->env;
@@ -93,16 +96,36 @@ petalogix_s3adsp1800_init(QEMUMachineInitArgs *args)
                           FLASH_SIZE >> 16,
                           1, 0x89, 0x18, 0x0000, 0x0, 1);
 
-    dev = xilinx_intc_create(INTC_BASEADDR, qdev_get_gpio_in(DEVICE(cpu),
+    dev = qdev_create(NULL, "xlnx.xps-intc");
-                             MB_CPU_IRQ), 0xA);
+    qdev_prop_set_uint32(dev, "kind-of-intr",
+                         1 << ETHLITE_IRQ | 1 << UARTLITE_IRQ);
+    qdev_init_nofail(dev);
+    sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, INTC_BASEADDR);
+    sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0,
+                       qdev_get_gpio_in(DEVICE(cpu), MB_CPU_IRQ));
     for (i = 0; i < 32; i++) {
         irq[i] = qdev_get_gpio_in(dev, i);
     }
 
-    sysbus_create_simple("xlnx.xps-uartlite", UARTLITE_BASEADDR, irq[3]);
+    sysbus_create_simple("xlnx.xps-uartlite", UARTLITE_BASEADDR,
+                         irq[UARTLITE_IRQ]);
+
     /* 2 timers at irq 2 @ 62 Mhz.  */
-    xilinx_timer_create(TIMER_BASEADDR, irq[0], 0, 62 * 1000000);
+    dev = qdev_create(NULL, "xlnx.xps-timer");
-    xilinx_ethlite_create(&nd_table[0], ETHLITE_BASEADDR, irq[1], 0, 0);
+    qdev_prop_set_uint32(dev, "one-timer-only", 0);
+    qdev_prop_set_uint32(dev, "clock-frequency", 62 * 1000000);
+    qdev_init_nofail(dev);
+    sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, TIMER_BASEADDR);
+    sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, irq[TIMER_IRQ]);
+
+    qemu_check_nic_model(&nd_table[0], "xlnx.xps-ethernetlite");
+    dev = qdev_create(NULL, "xlnx.xps-ethernetlite");
+    qdev_set_nic_properties(dev, &nd_table[0]);
+    qdev_prop_set_uint32(dev, "tx-ping-pong", 0);
+    qdev_prop_set_uint32(dev, "rx-ping-pong", 0);
+    qdev_init_nofail(dev);
+    sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, ETHLITE_BASEADDR);
+    sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, irq[ETHLITE_IRQ]);
 
     microblaze_load_kernel(cpu, ddr_base, ram_size,
                            args->initrd_filename,

hw/misc/arm_sysctl.c

@@ -276,7 +276,7 @@ static bool vexpress_cfgctrl_read(arm_sysctl_state *s, unsigned int dcc,
         }
         break;
     case SYS_CFG_OSC:
-        if (site == SYS_CFG_SITE_MB && device < sizeof(s->mb_clock)) {
+        if (site == SYS_CFG_SITE_MB && device < ARRAY_SIZE(s->mb_clock)) {
             /* motherboard clock */
             *val = s->mb_clock[device];
             return true;
@@ -324,7 +324,7 @@ static bool vexpress_cfgctrl_write(arm_sysctl_state *s, unsigned int dcc,
 
     switch (function) {
     case SYS_CFG_OSC:
-        if (site == SYS_CFG_SITE_MB && device < sizeof(s->mb_clock)) {
+        if (site == SYS_CFG_SITE_MB && device < ARRAY_SIZE(s->mb_clock)) {
             /* motherboard clock */
             s->mb_clock[device] = val;
             return true;

hw/misc/vfio.c

@@ -209,6 +209,29 @@ typedef struct VFIOGroup {
     QLIST_ENTRY(VFIOGroup) container_next;
 } VFIOGroup;
 
+typedef struct VFIORomBlacklistEntry {
+    uint16_t vendor_id;
+    uint16_t device_id;
+} VFIORomBlacklistEntry;
+
+/*
+ * List of device ids/vendor ids for which to disable
+ * option rom loading. This avoids the guest hangs during rom
+ * execution as noticed with the BCM 57810 card for lack of a
+ * more better way to handle such issues.
+ * The  user can still override by specifying a romfile or
+ * rombar=1.
+ * Please see https://bugs.launchpad.net/qemu/+bug/1284874
+ * for an analysis of the 57810 card hang. When adding
+ * a new vendor id/device id combination below, please also add
+ * your card/environment details and information that could
+ * help in debugging to the bug tracking this issue
+ */
+static const VFIORomBlacklistEntry romblacklist[] = {
+    /* Broadcom BCM 57810 */
+    { 0x14e4, 0x168e }
+};
+
 #define MSIX_CAP_LENGTH 12
 
 static QLIST_HEAD(, VFIOContainer)
@@ -1197,13 +1220,43 @@ static const MemoryRegionOps vfio_rom_ops = {
     .endianness = DEVICE_LITTLE_ENDIAN,
 };
 
+static bool vfio_blacklist_opt_rom(VFIODevice *vdev)
+{
+    PCIDevice *pdev = &vdev->pdev;
+    uint16_t vendor_id, device_id;
+    int count = 0;
+
+    vendor_id = pci_get_word(pdev->config + PCI_VENDOR_ID);
+    device_id = pci_get_word(pdev->config + PCI_DEVICE_ID);
+
+    while (count < ARRAY_SIZE(romblacklist)) {
+        if (romblacklist[count].vendor_id == vendor_id &&
+            romblacklist[count].device_id == device_id) {
+                return true;
+        }
+        count++;
+    }
+
+    return false;
+}
+
 static void vfio_pci_size_rom(VFIODevice *vdev)
 {
     uint32_t orig, size = cpu_to_le32((uint32_t)PCI_ROM_ADDRESS_MASK);
     off_t offset = vdev->config_offset + PCI_ROM_ADDRESS;
+    DeviceState *dev = DEVICE(vdev);
     char name[32];
 
     if (vdev->pdev.romfile || !vdev->pdev.rom_bar) {
+        /* Since pci handles romfile, just print a message and return */
+        if (vfio_blacklist_opt_rom(vdev) && vdev->pdev.romfile) {
+            error_printf("Warning : Device at %04x:%02x:%02x.%x "
+                         "is known to cause system instability issues during "
+                         "option rom execution. "
+                         "Proceeding anyway since user specified romfile\n",
+                         vdev->host.domain, vdev->host.bus, vdev->host.slot,
+                         vdev->host.function);
+        }
         return;
     }
 
@@ -1227,6 +1280,26 @@ static void vfio_pci_size_rom(VFIODevice *vdev)
         return;
     }
 
+    if (vfio_blacklist_opt_rom(vdev)) {
+        if (dev->opts && qemu_opt_get(dev->opts, "rombar")) {
+            error_printf("Warning : Device at %04x:%02x:%02x.%x "
+                         "is known to cause system instability issues during "
+                         "option rom execution. "
+                         "Proceeding anyway since user specified non zero value for "
+                         "rombar\n",
+                         vdev->host.domain, vdev->host.bus, vdev->host.slot,
+                         vdev->host.function);
+        } else {
+            error_printf("Warning : Rom loading for device at "
+                         "%04x:%02x:%02x.%x has been disabled due to "
+                         "system instability issues. "
+                         "Specify rombar=1 or romfile to force\n",
+                         vdev->host.domain, vdev->host.bus, vdev->host.slot,
+                         vdev->host.function);
+            return;
+        }
+    }
+
     DPRINTF("%04x:%02x:%02x.%x ROM size 0x%x\n", vdev->host.domain,
             vdev->host.bus, vdev->host.slot, vdev->host.function, size);
 
@@ -3681,10 +3754,10 @@ static int vfio_initfn(PCIDevice *pdev)
 
     strncat(path, "iommu_group", sizeof(path) - strlen(path) - 1);
 
-    len = readlink(path, iommu_group_path, PATH_MAX);
+    len = readlink(path, iommu_group_path, sizeof(path));
-    if (len <= 0) {
+    if (len <= 0 || len >= sizeof(path)) {
         error_report("vfio: error no iommu_group for device");
-        return -errno;
+        return len < 0 ? -errno : ENAMETOOLONG;
     }
 
     iommu_group_path[len] = 0;

hw/moxie/moxiesim.c

@@ -55,7 +55,7 @@ static void load_kernel(MoxieCPU *cpu, LoaderParams *loader_params)
                            &entry, &kernel_low, &kernel_high, 1,
                            ELF_MACHINE, 0);
 
-    if (!kernel_size) {
+    if (kernel_size <= 0) {
         fprintf(stderr, "qemu: could not load kernel '%s'\n",
                 loader_params->kernel_filename);
         exit(1);

hw/net/Makefile.objs

@@ -32,3 +32,6 @@ obj-$(CONFIG_XILINX_ETHLITE) += xilinx_ethlite.o
 
 obj-$(CONFIG_VIRTIO) += virtio-net.o
 obj-y += vhost_net.o
+
+obj-$(CONFIG_ETSEC) += fsl_etsec/etsec.o fsl_etsec/registers.o \
+			fsl_etsec/rings.o fsl_etsec/miim.o