Update version for v2.2.1 release

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
vpc: Fix size in fixed image creation
2015-03-10 12:29:35 -05:00 · 2015-03-08 22:58:14 -05:00 · 2015-03-08 22:58:14 -05:00 · 2015-03-08 22:58:14 -05:00 · 2015-03-08 22:58:14 -05:00 · 2015-03-08 22:58:14 -05:00
2420 changed files with 83555 additions and 214724 deletions
@@ -1,2 +0,0 @@
-((c-mode . ((c-file-style . "stroustrup")
-	    (indent-tabs-mode . nil))))
@@ -17,15 +17,12 @@
 /trace/generated-tcg-tracers.h
 /trace/generated-ust-provider.h
 /trace/generated-ust.c
-/ui/shader/texture-blit-frag.h
-/ui/shader/texture-blit-vert.h
+/libcacard/trace/generated-tracers.c
 *-timestamp
 /*-softmmu
 /*-darwin-user
 /*-linux-user
 /*-bsd-user
-/ivshmem-client
-/ivshmem-server
 /libdis*
 /libuser
 /linux-headers/asm
@@ -35,14 +32,19 @@
 /qapi-visit.[ch]
 /qapi-event.[ch]
 /qmp-commands.h
-/qmp-introspect.[ch]
 /qmp-marshal.c
 /qemu-doc.html
 /qemu-tech.html
 /qemu-doc.info
 /qemu-tech.info
+/qemu.1
+/qemu.pod
+/qemu-img.1
+/qemu-img.pod
 /qemu-img
 /qemu-nbd
+/qemu-nbd.8
+/qemu-nbd.pod
 /qemu-options.def
 /qemu-options.texi
 /qemu-img-cmds.texi
@@ -51,17 +53,16 @@
 /qemu-ga
 /qemu-bridge-helper
 /qemu-monitor.texi
-/qemu-monitor-info.texi
 /qmp-commands.txt
 /vscclient
 /fsdev/virtfs-proxy-helper
-*.[1-9]
+/fsdev/virtfs-proxy-helper.1
+/fsdev/virtfs-proxy-helper.pod
 *.a
 *.aux
 *.cp
 *.dvi
 *.exe
-*.msi
 *.dll
 *.so
 *.mo
@@ -69,7 +70,6 @@
 *.ky
 *.log
 *.pdf
-*.pod
 *.cps
 *.fns
 *.kys
@@ -54,7 +54,15 @@ matrix:
  include:
    # Make check target (we only do this once)
    - env:
-        - TARGETS=alpha-softmmu,arm-softmmu,aarch64-softmmu,cris-softmmu,i386-softmmu,x86_64-softmmu,m68k-softmmu,microblaze-softmmu,microblazeel-softmmu,mips-softmmu,mips64-softmmu,mips64el-softmmu,mipsel-softmmu,or32-softmmu,ppc-softmmu,ppc64-softmmu,ppcemb-softmmu,s390x-softmmu,sh4-softmmu,sh4eb-softmmu,sparc-softmmu,sparc64-softmmu,unicore32-softmmu,unicore32-linux-user,lm32-softmmu,moxie-softmmu,tricore-softmmu,xtensa-softmmu,xtensaeb-softmmu
+        - TARGETS=alpha-softmmu,arm-softmmu,aarch64-softmmu,cris-softmmu,
+                  i386-softmmu,x86_64-softmmu,m68k-softmmu,microblaze-softmmu,
+                  microblazeel-softmmu,mips-softmmu,mips64-softmmu,
+                  mips64el-softmmu,mipsel-softmmu,or32-softmmu,ppc-softmmu,
+                  ppc64-softmmu,ppcemb-softmmu,s390x-softmmu,sh4-softmmu,
+                  sh4eb-softmmu,sparc-softmmu,sparc64-softmmu,
+                  unicore32-softmmu,unicore32-linux-user,
+                  lm32-softmmu,moxie-softmmu,tricore-softmmu,xtensa-softmmu,
+                  xtensaeb-softmmu
          TEST_CMD="make check"
      compiler: gcc
    # Debug related options
@@ -90,6 +98,3 @@ matrix:
          EXTRA_PKGS="liblttng-ust-dev liburcu-dev"
          EXTRA_CONFIG="--enable-trace-backends=ust"
      compiler: gcc
-    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-modules"
-      compiler: gcc
@@ -87,15 +87,10 @@ Furthermore, it is the QEMU coding style.

 5. Declarations

-Mixed declarations (interleaving statements and declarations within
-blocks) are generally not allowed; declarations should be at the beginning
-of blocks.
-
-Every now and then, an exception is made for declarations inside a
-#ifdef or #ifndef block: if the code looks nicer, such declarations can
-be placed at the top of the block even if there are statements above.
-On the other hand, however, it's often best to move that #ifdef/#ifndef
-block to a separate function altogether.
+Mixed declarations (interleaving statements and declarations within blocks)
+are not allowed; declarations should be at the beginning of blocks.  In other
+words, the code should not generate warnings if using GCC's
+-Wdeclaration-after-statement option.

 6. Conditional statements

@@ -11,7 +11,7 @@ option) any later version.

 As of July 2013, contributions under version 2 of the GNU General Public
 License (and no later version) are only accepted for the following files
-or directories: bsd-user/, linux-user/, hw/vfio/, hw/xen/xen_pt*.
+or directories: bsd-user/, linux-user/, hw/misc/vfio.c, hw/xen/xen_pt*.

 3) The Tiny Code Generator (TCG) is released under the BSD license
   (see license headers in files).
@@ -3,11 +3,6 @@
 # Always point to the root of the build tree (needs GNU make).
 BUILD_DIR=$(CURDIR)

-# Before including a proper config-host.mak, assume we are in the source tree
-SRC_PATH=.
-
-UNCHECKED_GOALS := %clean TAGS cscope ctags
-
 # All following code might depend on configuration variables
 ifneq ($(wildcard config-host.mak),)
 # Put the all: rule here so that config-host.mak can contain dependencies.
@@ -43,7 +38,7 @@ config-host.mak: $(SRC_PATH)/configure
 	fi
 else
 config-host.mak:
-ifneq ($(filter-out $(UNCHECKED_GOALS),$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
+ifneq ($(filter-out %clean,$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
 	@echo "Please call configure before running make!"
 	@exit 1
 endif
@@ -52,8 +47,6 @@ endif
 GENERATED_HEADERS = config-host.h qemu-options.def
 GENERATED_HEADERS += qmp-commands.h qapi-types.h qapi-visit.h qapi-event.h
 GENERATED_SOURCES += qmp-marshal.c qapi-types.c qapi-visit.c qapi-event.c
-GENERATED_HEADERS += qmp-introspect.h
-GENERATED_SOURCES += qmp-introspect.c

 GENERATED_HEADERS += trace/generated-events.h
 GENERATED_SOURCES += trace/generated-events.c
@@ -81,7 +74,7 @@ Makefile: ;
 configure: ;

 .PHONY: all clean cscope distclean dvi html info install install-doc \
-	pdf recurse-all speed test dist msi
+	pdf recurse-all speed test dist

 $(call set-vpath, $(SRC_PATH))

@@ -90,11 +83,7 @@ LIBS+=-lz $(LIBS_TOOLS)
 HELPERS-$(CONFIG_LINUX) = qemu-bridge-helper$(EXESUF)

 ifdef BUILD_DOCS
-DOCS=qemu-doc.html qemu-tech.html qemu.1 qemu-img.1 qemu-nbd.8 qemu-ga.8
-DOCS+=qmp-commands.txt
-ifdef CONFIG_LINUX
-DOCS+=kvm_stat.1
-endif
+DOCS=qemu-doc.html qemu-tech.html qemu.1 qemu-img.1 qemu-nbd.8 qmp-commands.txt
 ifdef CONFIG_VIRTFS
 DOCS+=fsdev/virtfs-proxy-helper.1
 endif
@@ -120,9 +109,8 @@ endif
 -include $(SUBDIR_DEVICES_MAK_DEP)

 %/config-devices.mak: default-configs/%.mak
-	$(call quiet-command, \
-            $(SHELL) $(SRC_PATH)/scripts/make_device_config.sh $< $*-config-devices.mak.d $@ > $@.tmp, "  GEN   $@.tmp")
-	$(call quiet-command, if test -f $@; then \
+	$(call quiet-command,$(SHELL) $(SRC_PATH)/scripts/make_device_config.sh $@ $<, "  GEN   $@")
+	@if test -f $@; then \
 	  if cmp -s $@.old $@; then \
 	    mv $@.tmp $@; \
 	    cp -p $@ $@.old; \
@@ -138,7 +126,7 @@ endif
 	 else \
 	  mv $@.tmp $@; \
 	  cp -p $@ $@.old; \
-	 fi, "  GEN   $@");
+	 fi

 defconfig:
 	rm -f config-all-devices.mak $(SUBDIR_DEVICES_MAK)
@@ -151,20 +139,18 @@ dummy := $(call unnest-vars,, \
                stub-obj-y \
                util-obj-y \
                qga-obj-y \
-                ivshmem-client-obj-y \
-                ivshmem-server-obj-y \
                qga-vss-dll-obj-y \
                block-obj-y \
                block-obj-m \
-                crypto-obj-y \
-                crypto-aes-obj-y \
-                qom-obj-y \
                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 modules

@@ -177,7 +163,6 @@ SUBDIR_RULES=$(patsubst %,subdir-%, $(TARGET_DIRS))
 SOFTMMU_SUBDIR_RULES=$(filter %-softmmu,$(SUBDIR_RULES))

 $(SOFTMMU_SUBDIR_RULES): $(block-obj-y)
-$(SOFTMMU_SUBDIR_RULES): $(crypto-obj-y)
 $(SOFTMMU_SUBDIR_RULES): config-all-devices.mak

 subdir-%:
@@ -202,7 +187,7 @@ subdir-dtc:dtc/libfdt dtc/tests
 dtc/%:
 	mkdir -p $@

-$(SUBDIR_RULES): libqemuutil.a libqemustub.a $(common-obj-y) $(qom-obj-y) $(crypto-aes-obj-$(CONFIG_USER_ONLY))
+$(SUBDIR_RULES): libqemuutil.a libqemustub.a $(common-obj-y)

 ROMSUBDIR_RULES=$(patsubst %,romsubdir-%, $(ROMS))
 romsubdir-%:
@@ -212,9 +197,9 @@ ALL_SUBDIRS=$(TARGET_DIRS) $(patsubst %,pc-bios/%, $(ROMS))

 recurse-all: $(SUBDIR_RULES) $(ROMSUBDIR_RULES)

-$(BUILD_DIR)/version.o: $(SRC_PATH)/version.rc config-host.h | $(BUILD_DIR)/version.lo
+$(BUILD_DIR)/version.o: $(SRC_PATH)/version.rc $(BUILD_DIR)/config-host.h | $(BUILD_DIR)/version.lo
 	$(call quiet-command,$(WINDRES) -I$(BUILD_DIR) -o $@ $<,"  RC    version.o")
-$(BUILD_DIR)/version.lo: $(SRC_PATH)/version.rc config-host.h
+$(BUILD_DIR)/version.lo: $(SRC_PATH)/version.rc $(BUILD_DIR)/config-host.h
 	$(call quiet-command,$(WINDRES) -I$(BUILD_DIR) -o $@ $<,"  RC    version.lo")

 Makefile: $(version-obj-y) $(version-lobj-y)
@@ -232,9 +217,9 @@ util/module.o-cflags = -D'CONFIG_BLOCK_MODULES=$(block-modules)'

 qemu-img.o: qemu-img-cmds.h

-qemu-img$(EXESUF): qemu-img.o $(block-obj-y) $(crypto-obj-y) $(qom-obj-y) libqemuutil.a libqemustub.a
-qemu-nbd$(EXESUF): qemu-nbd.o $(block-obj-y) $(crypto-obj-y) $(qom-obj-y) libqemuutil.a libqemustub.a
-qemu-io$(EXESUF): qemu-io.o $(block-obj-y) $(crypto-obj-y) $(qom-obj-y) libqemuutil.a libqemustub.a
+qemu-img$(EXESUF): qemu-img.o $(block-obj-y) libqemuutil.a libqemustub.a
+qemu-nbd$(EXESUF): qemu-nbd.o $(block-obj-y) libqemuutil.a libqemustub.a
+qemu-io$(EXESUF): qemu-io.o $(block-obj-y) libqemuutil.a libqemustub.a

 qemu-bridge-helper$(EXESUF): qemu-bridge-helper.o

@@ -254,47 +239,42 @@ qapi-py = $(SRC_PATH)/scripts/qapi.py $(SRC_PATH)/scripts/ordereddict.py
 qga/qapi-generated/qga-qapi-types.c qga/qapi-generated/qga-qapi-types.h :\
 $(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py \
-		$(gen-out-type) -o qga/qapi-generated -p "qga-" $<, \
+		$(gen-out-type) -o qga/qapi-generated -p "qga-" -i $<, \
 		"  GEN   $@")
 qga/qapi-generated/qga-qapi-visit.c qga/qapi-generated/qga-qapi-visit.h :\
 $(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-visit.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py \
-		$(gen-out-type) -o qga/qapi-generated -p "qga-" $<, \
+		$(gen-out-type) -o qga/qapi-generated -p "qga-" -i $<, \
 		"  GEN   $@")
 qga/qapi-generated/qga-qmp-commands.h qga/qapi-generated/qga-qmp-marshal.c :\
 $(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py \
-		$(gen-out-type) -o qga/qapi-generated -p "qga-" $<, \
+		$(gen-out-type) -o qga/qapi-generated -p "qga-" -i $<, \
 		"  GEN   $@")

 qapi-modules = $(SRC_PATH)/qapi-schema.json $(SRC_PATH)/qapi/common.json \
               $(SRC_PATH)/qapi/block.json $(SRC_PATH)/qapi/block-core.json \
-               $(SRC_PATH)/qapi/event.json $(SRC_PATH)/qapi/introspect.json
+               $(SRC_PATH)/qapi/event.json

 qapi-types.c qapi-types.h :\
 $(qapi-modules) $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py \
-		$(gen-out-type) -o "." -b $<, \
+		$(gen-out-type) -o "." -b -i $<, \
 		"  GEN   $@")
 qapi-visit.c qapi-visit.h :\
 $(qapi-modules) $(SRC_PATH)/scripts/qapi-visit.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py \
-		$(gen-out-type) -o "." -b $<, \
+		$(gen-out-type) -o "." -b -i $<, \
 		"  GEN   $@")
 qapi-event.c qapi-event.h :\
 $(qapi-modules) $(SRC_PATH)/scripts/qapi-event.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-event.py \
-		$(gen-out-type) -o "." $<, \
+		$(gen-out-type) -o "." -b -i $<, \
 		"  GEN   $@")
 qmp-commands.h qmp-marshal.c :\
 $(qapi-modules) $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py \
-		$(gen-out-type) -o "." -m $<, \
-		"  GEN   $@")
-qmp-introspect.h qmp-introspect.c :\
-$(qapi-modules) $(SRC_PATH)/scripts/qapi-introspect.py $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-introspect.py \
-		$(gen-out-type) -o "." $<, \
+		$(gen-out-type) -o "." -m -i $<, \
 		"  GEN   $@")

 QGALIB_GEN=$(addprefix qga/qapi-generated/, qga-qapi-types.h qga-qapi-visit.h qga-qmp-commands.h)
@@ -303,44 +283,15 @@ $(qga-obj-y) qemu-ga.o: $(QGALIB_GEN)
 qemu-ga$(EXESUF): $(qga-obj-y) libqemuutil.a libqemustub.a
 	$(call LINK, $^)

-ifdef QEMU_GA_MSI_ENABLED
-QEMU_GA_MSI=qemu-ga-$(ARCH).msi
-
-msi: $(QEMU_GA_MSI)
-
-$(QEMU_GA_MSI): qemu-ga.exe $(QGA_VSS_PROVIDER)
-
-$(QEMU_GA_MSI): config-host.mak
-
-$(QEMU_GA_MSI):  $(SRC_PATH)/qga/installer/qemu-ga.wxs
-	$(call quiet-command,QEMU_GA_VERSION="$(QEMU_GA_VERSION)" QEMU_GA_MANUFACTURER="$(QEMU_GA_MANUFACTURER)" QEMU_GA_DISTRO="$(QEMU_GA_DISTRO)" BUILD_DIR="$(BUILD_DIR)" \
-	wixl -o $@ $(QEMU_GA_MSI_ARCH) $(QEMU_GA_MSI_WITH_VSS) $(QEMU_GA_MSI_MINGW_DLL_PATH) $<, "  WIXL  $@")
-else
-msi:
-	@echo "MSI build not configured or dependency resolution failed (reconfigure with --enable-guest-agent-msi option)"
-endif
-
-ifneq ($(EXESUF),)
-.PHONY: qemu-ga
-qemu-ga: qemu-ga$(EXESUF) $(QGA_VSS_PROVIDER) $(QEMU_GA_MSI)
-endif
-
-ivshmem-client$(EXESUF): $(ivshmem-client-obj-y)
-	$(call LINK, $^)
-ivshmem-server$(EXESUF): $(ivshmem-server-obj-y) libqemuutil.a libqemustub.a
-	$(call LINK, $^)
-
 clean:
 # avoid old build problems by removing potentially incorrect old files
 	rm -f config.mak op-i386.h opc-i386.h gen-op-i386.h op-arm.h opc-arm.h gen-op-arm.h
 	rm -f qemu-options.def
-	rm -f *.msi
 	find . \( -name '*.l[oa]' -o -name '*.so' -o -name '*.dll' -o -name '*.mo' -o -name '*.[oda]' \) -type f -exec rm {} +
 	rm -f $(filter-out %.tlb,$(TOOLS)) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
 	rm -f fsdev/*.pod
 	rm -rf .libs */.libs
 	rm -f qemu-img-cmds.h
-	rm -f ui/shader/*-vert.h ui/shader/*-frag.h
 	@# May not be present in GENERATED_HEADERS
 	rm -f trace/generated-tracers-dtrace.dtrace*
 	rm -f trace/generated-tracers-dtrace.h*
@@ -361,9 +312,9 @@ qemu-%.tar.bz2:
 	$(SRC_PATH)/scripts/make-release "$(SRC_PATH)" "$(patsubst qemu-%.tar.bz2,%,$@)"

 distclean: clean
-	rm -f config-host.mak config-host.h* config-host.ld $(DOCS) qemu-options.texi qemu-img-cmds.texi qemu-monitor.texi qemu-monitor-info.texi
-	rm -f config-all-devices.mak config-all-disas.mak config.status
-	rm -f po/*.mo tests/qemu-iotests/common.env
+	rm -f config-host.mak config-host.h* config-host.ld $(DOCS) qemu-options.texi qemu-img-cmds.texi qemu-monitor.texi
+	rm -f config-all-devices.mak config-all-disas.mak
+	rm -f po/*.mo
 	rm -f roms/seabios/config.mak roms/vgabios/config.mak
 	rm -f qemu-doc.info qemu-doc.aux qemu-doc.cp qemu-doc.cps qemu-doc.dvi
 	rm -f qemu-doc.fn qemu-doc.fns qemu-doc.info qemu-doc.ky qemu-doc.kys
@@ -376,8 +327,8 @@ distclean: clean
 	rm -rf $$d || exit 1 ; \
        done
 	rm -Rf .sdk
-	if test -f pixman/config.log; then $(MAKE) -C pixman distclean; fi
-	if test -f dtc/version_gen.h; then $(MAKE) $(DTC_MAKE_ARGS) clean; fi
+	if test -f pixman/config.log; then make -C pixman distclean; fi
+	if test -f dtc/version_gen.h; then make $(DTC_MAKE_ARGS) clean; fi

 KEYMAPS=da     en-gb  et  fr     fr-ch  is  lt  modifiers  no  pt-br  sv \
 ar      de     en-us  fi  fr-be  hr     it  lv  nl         pl  ru     th \
@@ -386,7 +337,7 @@ bepo    cz

 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 vgabios-virtio.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 QEMU,cgthree.bin \
 pxe-e1000.rom pxe-eepro100.rom pxe-ne2k_pci.rom \
@@ -417,9 +368,6 @@ ifneq ($(TOOLS),)
 	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man8"
 	$(INSTALL_DATA) qemu-nbd.8 "$(DESTDIR)$(mandir)/man8"
 endif
-ifneq (,$(findstring qemu-ga,$(TOOLS)))
-	$(INSTALL_DATA) qemu-ga.8 "$(DESTDIR)$(mandir)/man8"
-endif
 endif
 ifdef CONFIG_VIRTFS
 	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man1"
@@ -436,11 +384,16 @@ ifneq (,$(findstring qemu-ga,$(TOOLS)))
 endif
 endif

+install-confdir:
+	$(INSTALL_DIR) "$(DESTDIR)$(qemu_confdir)"

-install: all $(if $(BUILD_DOCS),install-doc) \
+install-sysconfig: install-datadir install-confdir
+	$(INSTALL_DATA) $(SRC_PATH)/sysconfigs/target/target-x86_64.conf "$(DESTDIR)$(qemu_confdir)"
+
+install: all $(if $(BUILD_DOCS),install-doc) install-sysconfig \
 install-datadir install-localstatedir
 ifneq ($(TOOLS),)
-	$(call install-prog,$(subst qemu-ga,qemu-ga$(EXESUF),$(TOOLS)),$(DESTDIR)$(bindir))
+	$(call install-prog,$(TOOLS),$(DESTDIR)$(bindir))
 endif
 ifneq ($(CONFIG_MODULES),)
 	$(INSTALL_DIR) "$(DESTDIR)$(qemu_moddir)"
@@ -474,36 +427,15 @@ endif
 test speed: all
 	$(MAKE) -C tests/tcg $@

-.PHONY: ctags
-ctags:
-	rm -f $@
-	find "$(SRC_PATH)" -name '*.[hc]' -exec ctags --append {} +
-
 .PHONY: TAGS
 TAGS:
 	rm -f $@
 	find "$(SRC_PATH)" -name '*.[hc]' -exec etags --append {} +

 cscope:
-	rm -f "$(SRC_PATH)"/cscope.*
-	find "$(SRC_PATH)/" -name "*.[chsS]" -print | sed 's,^\./,,' > "$(SRC_PATH)/cscope.files"
-	cscope -b -i"$(SRC_PATH)/cscope.files"
-
-# opengl shader programs
-ui/shader/%-vert.h: $(SRC_PATH)/ui/shader/%.vert $(SRC_PATH)/scripts/shaderinclude.pl
-	@mkdir -p $(dir $@)
-	$(call quiet-command,\
-		perl $(SRC_PATH)/scripts/shaderinclude.pl $< > $@,\
-		"  VERT  $@")
-
-ui/shader/%-frag.h: $(SRC_PATH)/ui/shader/%.frag $(SRC_PATH)/scripts/shaderinclude.pl
-	@mkdir -p $(dir $@)
-	$(call quiet-command,\
-		perl $(SRC_PATH)/scripts/shaderinclude.pl $< > $@,\
-		"  FRAG  $@")
-
-ui/console-gl.o: $(SRC_PATH)/ui/console-gl.c \
-	ui/shader/texture-blit-vert.h ui/shader/texture-blit-frag.h
+	rm -f ./cscope.*
+	find "$(SRC_PATH)" -name "*.[chsS]" -print | sed 's,^\./,,' > ./cscope.files
+	cscope -b

 # documentation
 MAKEINFO=makeinfo
@@ -528,16 +460,13 @@ qemu-options.texi: $(SRC_PATH)/qemu-options.hx
 qemu-monitor.texi: $(SRC_PATH)/hmp-commands.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"  GEN   $@")

-qemu-monitor-info.texi: $(SRC_PATH)/hmp-commands-info.hx
-	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"  GEN   $@")
-
 qmp-commands.txt: $(SRC_PATH)/qmp-commands.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -q < $< > $@,"  GEN   $@")

 qemu-img-cmds.texi: $(SRC_PATH)/qemu-img-cmds.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"  GEN   $@")

-qemu.1: qemu-doc.texi qemu-options.texi qemu-monitor.texi qemu-monitor-info.texi
+qemu.1: qemu-doc.texi qemu-options.texi qemu-monitor.texi
 	$(call quiet-command, \
 	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< qemu.pod && \
 	  $(POD2MAN) --section=1 --center=" " --release=" " qemu.pod > $@, \
@@ -561,18 +490,6 @@ qemu-nbd.8: qemu-nbd.texi
 	  $(POD2MAN) --section=8 --center=" " --release=" " qemu-nbd.pod > $@, \
 	  "  GEN   $@")

-qemu-ga.8: qemu-ga.texi
-	$(call quiet-command, \
-	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< qemu-ga.pod && \
-	  $(POD2MAN) --section=8 --center=" " --release=" " qemu-ga.pod > $@, \
-	  "  GEN   $@")
-
-kvm_stat.1: scripts/kvm/kvm_stat.texi
-	$(call quiet-command, \
-	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< kvm_stat.pod && \
-	  $(POD2MAN) --section=1 --center=" " --release=" " kvm_stat.pod > $@, \
-	  "  GEN   $@")
-
 dvi: qemu-doc.dvi qemu-tech.dvi
 html: qemu-doc.html qemu-tech.html
 info: qemu-doc.info qemu-tech.info
@@ -580,8 +497,7 @@ pdf: qemu-doc.pdf qemu-tech.pdf

 qemu-doc.dvi qemu-doc.html qemu-doc.info qemu-doc.pdf: \
 	qemu-img.texi qemu-nbd.texi qemu-options.texi \
-	qemu-monitor.texi qemu-img-cmds.texi qemu-ga.texi \
-	qemu-monitor-info.texi
+	qemu-monitor.texi qemu-img-cmds.texi

 ifdef CONFIG_WIN32

@@ -606,7 +522,7 @@ installer: $(INSTALLER)
 INSTDIR=/tmp/qemu-nsis

 $(INSTALLER): $(SRC_PATH)/qemu.nsi
-	$(MAKE) install prefix=${INSTDIR}
+	make install prefix=${INSTDIR}
 ifdef SIGNCODE
 	(cd ${INSTDIR}; \
         for i in *.exe; do \
@@ -631,7 +547,6 @@ endif # SIGNCODE
                $(if $(DLL_PATH),-DDLLDIR="$(DLL_PATH)") \
                -DSRCDIR="$(SRC_PATH)" \
                -DOUTFILE="$(INSTALLER)" \
-                -DDISPLAYVERSION="$(VERSION)" \
                $(SRC_PATH)/qemu.nsi
 	rm -r ${INSTDIR}
 ifdef SIGNCODE
@@ -641,7 +556,7 @@ endif # CONFIG_WIN

 # Add a dependency on the generated files, so that they are always
 # rebuilt before other object files
-ifneq ($(filter-out $(UNCHECKED_GOALS),$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
+ifneq ($(filter-out %clean,$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
 Makefile: $(GENERATED_HEADERS)
 endif

@@ -1,8 +1,7 @@
 #######################################################################
 # Common libraries for tools and emulators
 stub-obj-y = stubs/
-util-obj-y = util/ qobject/ qapi/
-util-obj-y += qmp-introspect.o qapi-types.o qapi-visit.o qapi-event.o
+util-obj-y = util/ qobject/ qapi/ qapi-types.o qapi-visit.o qapi-event.o

 #######################################################################
 # block-obj-y is code used by both qemu system emulation and qemu-img
@@ -15,18 +14,24 @@ block-obj-$(CONFIG_WIN32) += aio-win32.o
 block-obj-y += block/
 block-obj-y += qemu-io-cmds.o

+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
+
 block-obj-m = block/

-#######################################################################
-# crypto-obj-y is code used by both qemu system emulation and qemu-img

-crypto-obj-y = crypto/
-crypto-aes-obj-y = crypto/
+######################################################################
+# smartcard

-#######################################################################
-# qom-obj-y is code used by both qemu system emulation and qemu-img
-
-qom-obj-y = qom/
+libcacard-y += libcacard/cac.o libcacard/event.o
+libcacard-y += libcacard/vcard.o libcacard/vreader.o
+libcacard-y += libcacard/vcard_emul_nss.o
+libcacard-y += libcacard/vcard_emul_type.o
+libcacard-y += libcacard/card_7816.o
+libcacard-y += libcacard/vcardt.o
+libcacard/vcard_emul_nss.o-cflags := $(NSS_CFLAGS)
+libcacard/vcard_emul_nss.o-libs := $(NSS_LIBS)

 ######################################################################
 # Target independent part of system emulation. The long term path is to
@@ -43,10 +48,15 @@ common-obj-$(CONFIG_POSIX) += os-posix.o

 common-obj-$(CONFIG_LINUX) += fsdev/

-common-obj-y += migration/
+common-obj-y += migration.o migration-tcp.o
+common-obj-y += vmstate.o
+common-obj-y += qemu-file.o qemu-file-unix.o qemu-file-stdio.o
+common-obj-$(CONFIG_RDMA) += migration-rdma.o
 common-obj-y += qemu-char.o #aio.o
-common-obj-y += page_cache.o
-common-obj-y += qjson.o
+common-obj-y += block-migration.o
+common-obj-y += page_cache.o xbzrle.o
+
+common-obj-$(CONFIG_POSIX) += migration-exec.o migration-unix.o migration-fd.o

 common-obj-$(CONFIG_SPICE) += spice-qemu-char.o

@@ -54,8 +64,6 @@ common-obj-y += audio/
 common-obj-y += hw/
 common-obj-y += accel.o

-common-obj-y += replay/
-
 common-obj-y += ui/
 common-obj-y += bt-host.o bt-vhci.o
 bt-host.o-cflags := $(BLUEZ_CFLAGS)
@@ -71,13 +79,12 @@ common-obj-y += backends/

 common-obj-$(CONFIG_SECCOMP) += qemu-seccomp.o

-common-obj-$(CONFIG_FDT) += device_tree.o
+common-obj-$(CONFIG_SMARTCARD_NSS) += $(libcacard-y)

 ######################################################################
 # qapi

 common-obj-y += qmp-marshal.o
-common-obj-y += qmp-introspect.o
 common-obj-y += qmp.o hmp.o
 endif

@@ -106,8 +113,3 @@ target-obj-y += trace/
 # by libqemuutil.a.  These should be moved to a separate .json schema.
 qga-obj-y = qga/
 qga-vss-dll-obj-y = qga/
-
-######################################################################
-# contrib
-ivshmem-client-obj-y = contrib/ivshmem-client/
-ivshmem-server-obj-y = contrib/ivshmem-server/
@@ -1,13 +1,11 @@
 # -*- Mode: makefile -*-

-BUILD_DIR?=$(CURDIR)/..
-
 include ../config-host.mak
 include config-target.mak
 include config-devices.mak
 include $(SRC_PATH)/rules.mak

-$(call set-vpath, $(SRC_PATH):$(BUILD_DIR))
+$(call set-vpath, $(SRC_PATH))
 ifdef CONFIG_LINUX
 QEMU_CFLAGS += -I../linux-headers
 endif
@@ -85,11 +83,8 @@ all: $(PROGS) stap
 #########################################################
 # cpu emulator library
 obj-y = exec.o translate-all.o cpu-exec.o
-obj-y += translate-common.o
-obj-y += cpu-exec-common.o
-obj-y += tcg/tcg.o tcg/tcg-op.o tcg/optimize.o
+obj-y += tcg/tcg.o tcg/optimize.o
 obj-$(CONFIG_TCG_INTERPRETER) += tci.o
-obj-y += tcg/tcg-common.o
 obj-$(CONFIG_TCG_INTERPRETER) += disas/tci.o
 obj-y += fpu/softfloat.o
 obj-y += target-$(TARGET_BASE_ARCH)/
@@ -134,12 +129,12 @@ ifdef CONFIG_SOFTMMU
 obj-y += arch_init.o cpus.o monitor.o gdbstub.o balloon.o ioport.o numa.o
 obj-y += qtest.o bootdevice.o
 obj-y += hw/
+obj-$(CONFIG_FDT) += device_tree.o
 obj-$(CONFIG_KVM) += kvm-all.o
-obj-y += memory.o cputlb.o
+obj-y += memory.o savevm.o cputlb.o
 obj-y += memory_mapping.o
 obj-y += dump.o
-obj-y += migration/ram.o migration/savevm.o
-LIBS := $(libs_softmmu) $(LIBS)
+LIBS+=$(libs_softmmu)

 # xen support
 obj-$(CONFIG_XEN) += xen-common.o
@@ -154,7 +149,7 @@ else
 obj-y += hw/$(TARGET_BASE_ARCH)/
 endif

-GENERATED_HEADERS += hmp-commands.h hmp-commands-info.h qmp-commands-old.h
+GENERATED_HEADERS += hmp-commands.h qmp-commands-old.h

 endif # CONFIG_SOFTMMU

@@ -173,28 +168,16 @@ target-obj-y-save := $(target-obj-y)
 dummy := $(call unnest-vars,.., \
               block-obj-y \
               block-obj-m \
-               crypto-obj-y \
-               crypto-aes-obj-y \
-               qom-obj-y \
               common-obj-y \
               common-obj-m)
 target-obj-y := $(target-obj-y-save)
 all-obj-y += $(common-obj-y)
 all-obj-y += $(target-obj-y)
-all-obj-y += $(qom-obj-y)
 all-obj-$(CONFIG_SOFTMMU) += $(block-obj-y)
-all-obj-$(CONFIG_USER_ONLY) += $(crypto-aes-obj-y)
-all-obj-$(CONFIG_SOFTMMU) += $(crypto-obj-y)
-
-$(QEMU_PROG_BUILD): config-devices.mak

 # build either PROG or PROGW
 $(QEMU_PROG_BUILD): $(all-obj-y) ../libqemuutil.a ../libqemustub.a
-	$(call LINK, $(filter-out %.mak, $^))
-ifdef CONFIG_DARWIN
-	$(call quiet-command,Rez -append $(SRC_PATH)/pc-bios/qemu.rsrc -o $@,"  REZ   $(TARGET_DIR)$@")
-	$(call quiet-command,SetFile -a C $@,"  SETFILE $(TARGET_DIR)$@")
-endif
+	$(call LINK,$^)

 gdbstub-xml.c: $(TARGET_XML_FILES) $(SRC_PATH)/scripts/feature_to_c.sh
 	$(call quiet-command,rm -f $@ && $(SHELL) $(SRC_PATH)/scripts/feature_to_c.sh $@ $(TARGET_XML_FILES),"  GEN   $(TARGET_DIR)$@")
@@ -202,9 +185,6 @@ gdbstub-xml.c: $(TARGET_XML_FILES) $(SRC_PATH)/scripts/feature_to_c.sh
 hmp-commands.h: $(SRC_PATH)/hmp-commands.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $(TARGET_DIR)$@")

-hmp-commands-info.h: $(SRC_PATH)/hmp-commands-info.hx
-	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $(TARGET_DIR)$@")
-
 qmp-commands-old.h: $(SRC_PATH)/qmp-commands.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $(TARGET_DIR)$@")

@@ -1,107 +1,3 @@
-         QEMU README
-         ===========
+Read the documentation in qemu-doc.html or on http://wiki.qemu-project.org

-QEMU is a generic and open source machine & userspace emulator and
-virtualizer.
-
-QEMU is capable of emulating a complete machine in software without any
-need for hardware virtualization support. By using dynamic translation,
-it achieves very good performance. QEMU can also integrate with the Xen
-and KVM hypervisors to provide emulated hardware while allowing the
-hypervisor to manage the CPU. With hypervisor support, QEMU can achieve
-near native performance for CPUs. When QEMU emulates CPUs directly it is
-capable of running operating systems made for one machine (e.g. an ARMv7
-board) on a different machine (e.g. an x86_64 PC board).
-
-QEMU is also capable of providing userspace API virtualization for Linux
-and BSD kernel interfaces. This allows binaries compiled against one
-architecture ABI (e.g. the Linux PPC64 ABI) to be run on a host using a
-different architecture ABI (e.g. the Linux x86_64 ABI). This does not
-involve any hardware emulation, simply CPU and syscall emulation.
-
-QEMU aims to fit into a variety of use cases. It can be invoked directly
-by users wishing to have full control over its behaviour and settings.
-It also aims to facilitate integration into higher level management
-layers, by providing a stable command line interface and monitor API.
-It is commonly invoked indirectly via the libvirt library when using
-open source applications such as oVirt, OpenStack and virt-manager.
-
-QEMU as a whole is released under the GNU General Public License,
-version 2. For full licensing details, consult the LICENSE file.
-
-
-Building
-========
-
-QEMU is multi-platform software intended to be buildable on all modern
-Linux platforms, OS-X, Win32 (via the Mingw64 toolchain) and a variety
-of other UNIX targets. The simple steps to build QEMU are:
-
-  mkdir build
-  cd build
-  ../configure
-  make
-
-Complete details of the process for building and configuring QEMU for
-all supported host platforms can be found in the qemu-tech.html file.
-Additional information can also be found online via the QEMU website:
-
-  http://qemu-project.org/Hosts/Linux
-  http://qemu-project.org/Hosts/W32
-
-
-Submitting patches
-==================
-
-The QEMU source code is maintained under the GIT version control system.
-
-   git clone git://git.qemu-project.org/qemu.git
-
-When submitting patches, the preferred approach is to use 'git
-format-patch' and/or 'git send-email' to format & send the mail to the
-qemu-devel@nongnu.org mailing list. All patches submitted must contain
-a 'Signed-off-by' line from the author. Patches should follow the
-guidelines set out in the HACKING and CODING_STYLE files.
-
-Additional information on submitting patches can be found online via
-the QEMU website
-
-  http://qemu-project.org/Contribute/SubmitAPatch
-  http://qemu-project.org/Contribute/TrivialPatches
-
-
-Bug reporting
-=============
-
-The QEMU project uses Launchpad as its primary upstream bug tracker. Bugs
-found when running code built from QEMU git or upstream released sources
-should be reported via:
-
-  https://bugs.launchpad.net/qemu/
-
-If using QEMU via an operating system vendor pre-built binary package, it
-is preferable to report bugs to the vendor's own bug tracker first. If
-the bug is also known to affect latest upstream code, it can also be
-reported via launchpad.
-
-For additional information on bug reporting consult:
-
-  http://qemu-project.org/Contribute/ReportABug
-
-
-Contact
-=======
-
-The QEMU community can be contacted in a number of ways, with the two
-main methods being email and IRC
-
- - qemu-devel@nongnu.org
-   http://lists.nongnu.org/mailman/listinfo/qemu-devel
- - #qemu on irc.oftc.net
-
-Information on additional methods of contacting the community can be
-found online via the QEMU website:
-
-  http://qemu-project.org/Contribute/StartHere
-
-- End
+- QEMU team
@@ -1 +1 @@
-2.5.0
+2.2.1
@@ -17,9 +17,6 @@
 #include "block/block.h"
 #include "qemu/queue.h"
 #include "qemu/sockets.h"
-#ifdef CONFIG_EPOLL
-#include <sys/epoll.h>
-#endif

 struct AioHandler
 {
@@ -27,167 +24,11 @@ struct AioHandler
    IOHandler *io_read;
    IOHandler *io_write;
    int deleted;
+    int pollfds_idx;
    void *opaque;
-    bool is_external;
    QLIST_ENTRY(AioHandler) node;
 };

-#ifdef CONFIG_EPOLL
-
-/* The fd number threashold to switch to epoll */
-#define EPOLL_ENABLE_THRESHOLD 64
-
-static void aio_epoll_disable(AioContext *ctx)
-{
-    ctx->epoll_available = false;
-    if (!ctx->epoll_enabled) {
-        return;
-    }
-    ctx->epoll_enabled = false;
-    close(ctx->epollfd);
-}
-
-static inline int epoll_events_from_pfd(int pfd_events)
-{
-    return (pfd_events & G_IO_IN ? EPOLLIN : 0) |
-           (pfd_events & G_IO_OUT ? EPOLLOUT : 0) |
-           (pfd_events & G_IO_HUP ? EPOLLHUP : 0) |
-           (pfd_events & G_IO_ERR ? EPOLLERR : 0);
-}
-
-static bool aio_epoll_try_enable(AioContext *ctx)
-{
-    AioHandler *node;
-    struct epoll_event event;
-
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        int r;
-        if (node->deleted || !node->pfd.events) {
-            continue;
-        }
-        event.events = epoll_events_from_pfd(node->pfd.events);
-        event.data.ptr = node;
-        r = epoll_ctl(ctx->epollfd, EPOLL_CTL_ADD, node->pfd.fd, &event);
-        if (r) {
-            return false;
-        }
-    }
-    ctx->epoll_enabled = true;
-    return true;
-}
-
-static void aio_epoll_update(AioContext *ctx, AioHandler *node, bool is_new)
-{
-    struct epoll_event event;
-    int r;
-
-    if (!ctx->epoll_enabled) {
-        return;
-    }
-    if (!node->pfd.events) {
-        r = epoll_ctl(ctx->epollfd, EPOLL_CTL_DEL, node->pfd.fd, &event);
-        if (r) {
-            aio_epoll_disable(ctx);
-        }
-    } else {
-        event.data.ptr = node;
-        event.events = epoll_events_from_pfd(node->pfd.events);
-        if (is_new) {
-            r = epoll_ctl(ctx->epollfd, EPOLL_CTL_ADD, node->pfd.fd, &event);
-            if (r) {
-                aio_epoll_disable(ctx);
-            }
-        } else {
-            r = epoll_ctl(ctx->epollfd, EPOLL_CTL_MOD, node->pfd.fd, &event);
-            if (r) {
-                aio_epoll_disable(ctx);
-            }
-        }
-    }
-}
-
-static int aio_epoll(AioContext *ctx, GPollFD *pfds,
-                     unsigned npfd, int64_t timeout)
-{
-    AioHandler *node;
-    int i, ret = 0;
-    struct epoll_event events[128];
-
-    assert(npfd == 1);
-    assert(pfds[0].fd == ctx->epollfd);
-    if (timeout > 0) {
-        ret = qemu_poll_ns(pfds, npfd, timeout);
-    }
-    if (timeout <= 0 || ret > 0) {
-        ret = epoll_wait(ctx->epollfd, events,
-                         sizeof(events) / sizeof(events[0]),
-                         timeout);
-        if (ret <= 0) {
-            goto out;
-        }
-        for (i = 0; i < ret; i++) {
-            int ev = events[i].events;
-            node = events[i].data.ptr;
-            node->pfd.revents = (ev & EPOLLIN ? G_IO_IN : 0) |
-                (ev & EPOLLOUT ? G_IO_OUT : 0) |
-                (ev & EPOLLHUP ? G_IO_HUP : 0) |
-                (ev & EPOLLERR ? G_IO_ERR : 0);
-        }
-    }
-out:
-    return ret;
-}
-
-static bool aio_epoll_enabled(AioContext *ctx)
-{
-    /* Fall back to ppoll when external clients are disabled. */
-    return !aio_external_disabled(ctx) && ctx->epoll_enabled;
-}
-
-static bool aio_epoll_check_poll(AioContext *ctx, GPollFD *pfds,
-                                 unsigned npfd, int64_t timeout)
-{
-    if (!ctx->epoll_available) {
-        return false;
-    }
-    if (aio_epoll_enabled(ctx)) {
-        return true;
-    }
-    if (npfd >= EPOLL_ENABLE_THRESHOLD) {
-        if (aio_epoll_try_enable(ctx)) {
-            return true;
-        } else {
-            aio_epoll_disable(ctx);
-        }
-    }
-    return false;
-}
-
-#else
-
-static void aio_epoll_update(AioContext *ctx, AioHandler *node, bool is_new)
-{
-}
-
-static int aio_epoll(AioContext *ctx, GPollFD *pfds,
-                     unsigned npfd, int64_t timeout)
-{
-    assert(false);
-}
-
-static bool aio_epoll_enabled(AioContext *ctx)
-{
-    return false;
-}
-
-static bool aio_epoll_check_poll(AioContext *ctx, GPollFD *pfds,
-                          unsigned npfd, int64_t timeout)
-{
-    return false;
-}
-
-#endif
-
 static AioHandler *find_aio_handler(AioContext *ctx, int fd)
 {
    AioHandler *node;
@@ -203,14 +44,11 @@ static AioHandler *find_aio_handler(AioContext *ctx, int fd)

 void aio_set_fd_handler(AioContext *ctx,
                        int fd,
-                        bool is_external,
                        IOHandler *io_read,
                        IOHandler *io_write,
                        void *opaque)
 {
    AioHandler *node;
-    bool is_new = false;
-    bool deleted = false;

    node = find_aio_handler(ctx, fd);

@@ -229,43 +67,37 @@ void aio_set_fd_handler(AioContext *ctx,
                 * releasing the walking_handlers lock.
                 */
                QLIST_REMOVE(node, node);
-                deleted = true;
+                g_free(node);
            }
        }
    } else {
        if (node == NULL) {
            /* Alloc and insert if it's not already there */
-            node = g_new0(AioHandler, 1);
+            node = g_malloc0(sizeof(AioHandler));
            node->pfd.fd = fd;
            QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);

            g_source_add_poll(&ctx->source, &node->pfd);
-            is_new = true;
        }
        /* Update handler with latest information */
        node->io_read = io_read;
        node->io_write = io_write;
        node->opaque = opaque;
-        node->is_external = is_external;
+        node->pollfds_idx = -1;

        node->pfd.events = (io_read ? G_IO_IN | G_IO_HUP | G_IO_ERR : 0);
        node->pfd.events |= (io_write ? G_IO_OUT | G_IO_ERR : 0);
    }

-    aio_epoll_update(ctx, node, is_new);
    aio_notify(ctx);
-    if (deleted) {
-        g_free(node);
-    }
 }

 void aio_set_event_notifier(AioContext *ctx,
                            EventNotifier *notifier,
-                            bool is_external,
                            EventNotifierHandler *io_read)
 {
    aio_set_fd_handler(ctx, event_notifier_get_fd(notifier),
-                       is_external, (IOHandler *)io_read, NULL, notifier);
+                       (IOHandler *)io_read, NULL, notifier);
 }

 bool aio_prepare(AioContext *ctx)
@@ -354,141 +186,69 @@ bool aio_dispatch(AioContext *ctx)
    return progress;
 }

-/* These thread-local variables are used only in a small part of aio_poll
- * around the call to the poll() system call.  In particular they are not
- * used while aio_poll is performing callbacks, which makes it much easier
- * to think about reentrancy!
- *
- * Stack-allocated arrays would be perfect but they have size limitations;
- * heap allocation is expensive enough that we want to reuse arrays across
- * calls to aio_poll().  And because poll() has to be called without holding
- * any lock, the arrays cannot be stored in AioContext.  Thread-local data
- * has none of the disadvantages of these three options.
- */
-static __thread GPollFD *pollfds;
-static __thread AioHandler **nodes;
-static __thread unsigned npfd, nalloc;
-static __thread Notifier pollfds_cleanup_notifier;
-
-static void pollfds_cleanup(Notifier *n, void *unused)
-{
-    g_assert(npfd == 0);
-    g_free(pollfds);
-    g_free(nodes);
-    nalloc = 0;
-}
-
-static void add_pollfd(AioHandler *node)
-{
-    if (npfd == nalloc) {
-        if (nalloc == 0) {
-            pollfds_cleanup_notifier.notify = pollfds_cleanup;
-            qemu_thread_atexit_add(&pollfds_cleanup_notifier);
-            nalloc = 8;
-        } else {
-            g_assert(nalloc <= INT_MAX);
-            nalloc *= 2;
-        }
-        pollfds = g_renew(GPollFD, pollfds, nalloc);
-        nodes = g_renew(AioHandler *, nodes, nalloc);
-    }
-    nodes[npfd] = node;
-    pollfds[npfd] = (GPollFD) {
-        .fd = node->pfd.fd,
-        .events = node->pfd.events,
-    };
-    npfd++;
-}
-
 bool aio_poll(AioContext *ctx, bool blocking)
 {
    AioHandler *node;
-    int i, ret;
+    bool was_dispatching;
+    int ret;
    bool progress;
-    int64_t timeout;

-    aio_context_acquire(ctx);
+    was_dispatching = ctx->dispatching;
    progress = false;

    /* aio_notify can avoid the expensive event_notifier_set if
     * everything (file descriptors, bottom halves, timers) will
     * be re-evaluated before the next blocking poll().  This is
     * already true when aio_poll is called with blocking == false;
-     * if blocking == true, it is only true after poll() returns,
-     * so disable the optimization now.
+     * if blocking == true, it is only true after poll() returns.
+     *
+     * If we're in a nested event loop, ctx->dispatching might be true.
+     * In that case we can restore it just before returning, but we
+     * have to clear it now.
     */
-    if (blocking) {
-        atomic_add(&ctx->notify_me, 2);
-    }
+    aio_set_dispatching(ctx, !blocking);

    ctx->walking_handlers++;

-    assert(npfd == 0);
+    g_array_set_size(ctx->pollfds, 0);

    /* fill pollfds */
    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        if (!node->deleted && node->pfd.events
-            && !aio_epoll_enabled(ctx)
-            && aio_node_check(ctx, node->is_external)) {
-            add_pollfd(node);
+        node->pollfds_idx = -1;
+        if (!node->deleted && node->pfd.events) {
+            GPollFD pfd = {
+                .fd = node->pfd.fd,
+                .events = node->pfd.events,
+            };
+            node->pollfds_idx = ctx->pollfds->len;
+            g_array_append_val(ctx->pollfds, pfd);
        }
    }

-    timeout = blocking ? aio_compute_timeout(ctx) : 0;
+    ctx->walking_handlers--;

    /* wait until next event */
-    if (timeout) {
-        aio_context_release(ctx);
-    }
-    if (aio_epoll_check_poll(ctx, pollfds, npfd, timeout)) {
-        AioHandler epoll_handler;
-
-        epoll_handler.pfd.fd = ctx->epollfd;
-        epoll_handler.pfd.events = G_IO_IN | G_IO_OUT | G_IO_HUP | G_IO_ERR;
-        npfd = 0;
-        add_pollfd(&epoll_handler);
-        ret = aio_epoll(ctx, pollfds, npfd, timeout);
-    } else  {
-        ret = qemu_poll_ns(pollfds, npfd, timeout);
-    }
-    if (blocking) {
-        atomic_sub(&ctx->notify_me, 2);
-    }
-    if (timeout) {
-        aio_context_acquire(ctx);
-    }
-
-    aio_notify_accept(ctx);
+    ret = qemu_poll_ns((GPollFD *)ctx->pollfds->data,
+                         ctx->pollfds->len,
+                         blocking ? aio_compute_timeout(ctx) : 0);

    /* if we have any readable fds, dispatch event */
    if (ret > 0) {
-        for (i = 0; i < npfd; i++) {
-            nodes[i]->pfd.revents = pollfds[i].revents;
+        QLIST_FOREACH(node, &ctx->aio_handlers, node) {
+            if (node->pollfds_idx != -1) {
+                GPollFD *pfd = &g_array_index(ctx->pollfds, GPollFD,
+                                              node->pollfds_idx);
+                node->pfd.revents = pfd->revents;
+            }
        }
    }

-    npfd = 0;
-    ctx->walking_handlers--;
-
    /* Run dispatch even if there were no readable fds to run timers */
+    aio_set_dispatching(ctx, true);
    if (aio_dispatch(ctx)) {
        progress = true;
    }

-    aio_context_release(ctx);
-
+    aio_set_dispatching(ctx, was_dispatching);
    return progress;
 }
-
-void aio_context_setup(AioContext *ctx, Error **errp)
-{
-#ifdef CONFIG_EPOLL
-    assert(!ctx->epollfd);
-    ctx->epollfd = epoll_create1(EPOLL_CLOEXEC);
-    if (ctx->epollfd == -1) {
-        ctx->epoll_available = false;
-    } else {
-        ctx->epoll_available = true;
-    }
-#endif
-}
@@ -28,13 +28,11 @@ struct AioHandler {
    GPollFD pfd;
    int deleted;
    void *opaque;
-    bool is_external;
    QLIST_ENTRY(AioHandler) node;
 };

 void aio_set_fd_handler(AioContext *ctx,
                        int fd,
-                        bool is_external,
                        IOHandler *io_read,
                        IOHandler *io_write,
                        void *opaque)
@@ -69,7 +67,7 @@ void aio_set_fd_handler(AioContext *ctx,

        if (node == NULL) {
            /* Alloc and insert if it's not already there */
-            node = g_new0(AioHandler, 1);
+            node = g_malloc0(sizeof(AioHandler));
            node->pfd.fd = fd;
            QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
        }
@@ -88,7 +86,6 @@ void aio_set_fd_handler(AioContext *ctx,
        node->opaque = opaque;
        node->io_read = io_read;
        node->io_write = io_write;
-        node->is_external = is_external;

        event = event_notifier_get_handle(&ctx->notifier);
        WSAEventSelect(node->pfd.fd, event,
@@ -101,7 +98,6 @@ void aio_set_fd_handler(AioContext *ctx,

 void aio_set_event_notifier(AioContext *ctx,
                            EventNotifier *e,
-                            bool is_external,
                            EventNotifierHandler *io_notify)
 {
    AioHandler *node;
@@ -133,11 +129,10 @@ void aio_set_event_notifier(AioContext *ctx,
    } else {
        if (node == NULL) {
            /* Alloc and insert if it's not already there */
-            node = g_new0(AioHandler, 1);
+            node = g_malloc0(sizeof(AioHandler));
            node->e = e;
            node->pfd.fd = (uintptr_t)event_notifier_get_handle(e);
            node->pfd.events = G_IO_IN;
-            node->is_external = is_external;
            QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);

            g_source_add_poll(&ctx->source, &node->pfd);
@@ -284,33 +279,36 @@ bool aio_poll(AioContext *ctx, bool blocking)
 {
    AioHandler *node;
    HANDLE events[MAXIMUM_WAIT_OBJECTS + 1];
-    bool progress, have_select_revents, first;
+    bool was_dispatching, progress, have_select_revents, first;
    int count;
    int timeout;

-    aio_context_acquire(ctx);
+    have_select_revents = aio_prepare(ctx);
+    if (have_select_revents) {
+        blocking = false;
+    }
+
+    was_dispatching = ctx->dispatching;
    progress = false;

    /* aio_notify can avoid the expensive event_notifier_set if
     * everything (file descriptors, bottom halves, timers) will
     * be re-evaluated before the next blocking poll().  This is
     * already true when aio_poll is called with blocking == false;
-     * if blocking == true, it is only true after poll() returns,
-     * so disable the optimization now.
+     * if blocking == true, it is only true after poll() returns.
+     *
+     * If we're in a nested event loop, ctx->dispatching might be true.
+     * In that case we can restore it just before returning, but we
+     * have to clear it now.
     */
-    if (blocking) {
-        atomic_add(&ctx->notify_me, 2);
-    }
-
-    have_select_revents = aio_prepare(ctx);
+    aio_set_dispatching(ctx, !blocking);

    ctx->walking_handlers++;

    /* fill fd sets */
    count = 0;
    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        if (!node->deleted && node->io_notify
-            && aio_node_check(ctx, node->is_external)) {
+        if (!node->deleted && node->io_notify) {
            events[count++] = event_notifier_get_handle(node->e);
        }
    }
@@ -318,36 +316,20 @@ bool aio_poll(AioContext *ctx, bool blocking)
    ctx->walking_handlers--;
    first = true;

-    /* ctx->notifier is always registered.  */
-    assert(count > 0);
-
-    /* Multiple iterations, all of them non-blocking except the first,
-     * may be necessary to process all pending events.  After the first
-     * WaitForMultipleObjects call ctx->notify_me will be decremented.
-     */
-    do {
+    /* wait until next event */
+    while (count > 0) {
        HANDLE event;
        int ret;

-        timeout = blocking && !have_select_revents
+        timeout = blocking
            ? qemu_timeout_ns_to_ms(aio_compute_timeout(ctx)) : 0;
-        if (timeout) {
-            aio_context_release(ctx);
-        }
        ret = WaitForMultipleObjects(count, events, FALSE, timeout);
-        if (blocking) {
-            assert(first);
-            atomic_sub(&ctx->notify_me, 2);
-        }
-        if (timeout) {
-            aio_context_acquire(ctx);
-        }
+        aio_set_dispatching(ctx, true);

-        if (first) {
-            aio_notify_accept(ctx);
-            progress |= aio_bh_poll(ctx);
-            first = false;
+        if (first && aio_bh_poll(ctx)) {
+            progress = true;
        }
+        first = false;

        /* if we have any signaled events, dispatch event */
        event = NULL;
@@ -362,14 +344,10 @@ bool aio_poll(AioContext *ctx, bool blocking)
        blocking = false;

        progress |= aio_dispatch_handlers(ctx, event);
-    } while (count > 0);
+    }

    progress |= timerlistgroup_run_timers(&ctx->tlg);

-    aio_context_release(ctx);
+    aio_set_dispatching(ctx, was_dispatching);
    return progress;
 }
-
-void aio_context_setup(AioContext *ctx, Error **errp)
-{
-}
@@ -44,12 +44,10 @@ struct QEMUBH {
 QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
 {
    QEMUBH *bh;
-    bh = g_new(QEMUBH, 1);
-    *bh = (QEMUBH){
-        .ctx = ctx,
-        .cb = cb,
-        .opaque = opaque,
-    };
+    bh = g_malloc0(sizeof(QEMUBH));
+    bh->ctx = ctx;
+    bh->cb = cb;
+    bh->opaque = opaque;
    qemu_mutex_lock(&ctx->bh_lock);
    bh->next = ctx->first_bh;
    /* Make sure that the members are ready before putting bh into list */
@@ -59,11 +57,6 @@ QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
    return bh;
 }

-void aio_bh_call(QEMUBH *bh)
-{
-    bh->cb(bh->opaque);
-}
-
 /* Multiple occurrences of aio_bh_poll cannot be called concurrently */
 int aio_bh_poll(AioContext *ctx)
 {
@@ -77,19 +70,16 @@ int aio_bh_poll(AioContext *ctx)
        /* Make sure that fetching bh happens before accessing its members */
        smp_read_barrier_depends();
        next = bh->next;
-        /* The atomic_xchg is paired with the one in qemu_bh_schedule.  The
-         * implicit memory barrier ensures that the callback sees all writes
-         * done by the scheduling thread.  It also ensures that the scheduling
-         * thread sees the zero before bh->cb has run, and thus will call
-         * aio_notify again if necessary.
-         */
-        if (!bh->deleted && atomic_xchg(&bh->scheduled, 0)) {
-            /* Idle BHs and the notify BH don't count as progress */
-            if (!bh->idle && bh != ctx->notify_dummy_bh) {
+        if (!bh->deleted && bh->scheduled) {
+            bh->scheduled = 0;
+            /* Paired with write barrier in bh schedule to ensure reading for
+             * idle & callbacks coming after bh's scheduling.
+             */
+            smp_rmb();
+            if (!bh->idle)
                ret = 1;
-            }
            bh->idle = 0;
-            aio_bh_call(bh);
+            bh->cb(bh->opaque);
        }
    }

@@ -116,28 +106,33 @@ int aio_bh_poll(AioContext *ctx)

 void qemu_bh_schedule_idle(QEMUBH *bh)
 {
+    if (bh->scheduled)
+        return;
    bh->idle = 1;
    /* Make sure that idle & any writes needed by the callback are done
     * before the locations are read in the aio_bh_poll.
     */
-    atomic_mb_set(&bh->scheduled, 1);
+    smp_wmb();
+    bh->scheduled = 1;
 }

 void qemu_bh_schedule(QEMUBH *bh)
 {
    AioContext *ctx;

+    if (bh->scheduled)
+        return;
    ctx = bh->ctx;
    bh->idle = 0;
-    /* The memory barrier implicit in atomic_xchg makes sure that:
+    /* Make sure that:
     * 1. idle & any writes needed by the callback are done before the
     *    locations are read in the aio_bh_poll.
     * 2. ctx is loaded before scheduled is set and the callback has a chance
     *    to execute.
     */
-    if (atomic_xchg(&bh->scheduled, 1) == 0) {
-        aio_notify(ctx);
-    }
+    smp_mb();
+    bh->scheduled = 1;
+    aio_notify(ctx);
 }


@@ -191,8 +186,6 @@ aio_ctx_prepare(GSource *source, gint    *timeout)
 {
    AioContext *ctx = (AioContext *) source;

-    atomic_or(&ctx->notify_me, 1);
-
    /* We assume there is no timeout already supplied */
    *timeout = qemu_timeout_ns_to_ms(aio_compute_timeout(ctx));

@@ -209,9 +202,6 @@ aio_ctx_check(GSource *source)
    AioContext *ctx = (AioContext *) source;
    QEMUBH *bh;

-    atomic_and(&ctx->notify_me, ~1);
-    aio_notify_accept(ctx);
-
    for (bh = ctx->first_bh; bh; bh = bh->next) {
        if (!bh->deleted && bh->scheduled) {
            return true;
@@ -237,25 +227,12 @@ aio_ctx_finalize(GSource     *source)
 {
    AioContext *ctx = (AioContext *) source;

-    qemu_bh_delete(ctx->notify_dummy_bh);
    thread_pool_free(ctx->thread_pool);
-
-    qemu_mutex_lock(&ctx->bh_lock);
-    while (ctx->first_bh) {
-        QEMUBH *next = ctx->first_bh->next;
-
-        /* qemu_bh_delete() must have been called on BHs in this AioContext */
-        assert(ctx->first_bh->deleted);
-
-        g_free(ctx->first_bh);
-        ctx->first_bh = next;
-    }
-    qemu_mutex_unlock(&ctx->bh_lock);
-
-    aio_set_event_notifier(ctx, &ctx->notifier, false, NULL);
+    aio_set_event_notifier(ctx, &ctx->notifier, NULL);
    event_notifier_cleanup(&ctx->notifier);
    rfifolock_destroy(&ctx->lock);
    qemu_mutex_destroy(&ctx->bh_lock);
+    g_array_free(ctx->pollfds, TRUE);
    timerlistgroup_deinit(&ctx->tlg);
 }

@@ -280,22 +257,24 @@ ThreadPool *aio_get_thread_pool(AioContext *ctx)
    return ctx->thread_pool;
 }

-void aio_notify(AioContext *ctx)
+void aio_set_dispatching(AioContext *ctx, bool dispatching)
 {
-    /* Write e.g. bh->scheduled before reading ctx->notify_me.  Pairs
-     * with atomic_or in aio_ctx_prepare or atomic_add in aio_poll.
-     */
-    smp_mb();
-    if (ctx->notify_me) {
-        event_notifier_set(&ctx->notifier);
-        atomic_mb_set(&ctx->notified, true);
+    ctx->dispatching = dispatching;
+    if (!dispatching) {
+        /* Write ctx->dispatching before reading e.g. bh->scheduled.
+         * Optimization: this is only needed when we're entering the "unsafe"
+         * phase where other threads must call event_notifier_set.
+         */
+        smp_mb();
    }
 }

-void aio_notify_accept(AioContext *ctx)
+void aio_notify(AioContext *ctx)
 {
-    if (atomic_xchg(&ctx->notified, false)) {
-        event_notifier_test_and_clear(&ctx->notifier);
+    /* Write e.g. bh->scheduled before reading ctx->dispatching.  */
+    smp_mb();
+    if (!ctx->dispatching) {
+        event_notifier_set(&ctx->notifier);
    }
 }

@@ -306,54 +285,31 @@ static void aio_timerlist_notify(void *opaque)

 static void aio_rfifolock_cb(void *opaque)
 {
-    AioContext *ctx = opaque;
-
    /* Kick owner thread in case they are blocked in aio_poll() */
-    qemu_bh_schedule(ctx->notify_dummy_bh);
-}
-
-static void notify_dummy_bh(void *opaque)
-{
-    /* Do nothing, we were invoked just to force the event loop to iterate */
-}
-
-static void event_notifier_dummy_cb(EventNotifier *e)
-{
+    aio_notify(opaque);
 }

 AioContext *aio_context_new(Error **errp)
 {
    int ret;
    AioContext *ctx;
-    Error *local_err = NULL;
-
    ctx = (AioContext *) g_source_new(&aio_source_funcs, sizeof(AioContext));
-    aio_context_setup(ctx, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        goto fail;
-    }
    ret = event_notifier_init(&ctx->notifier, false);
    if (ret < 0) {
+        g_source_destroy(&ctx->source);
        error_setg_errno(errp, -ret, "Failed to initialize event notifier");
-        goto fail;
+        return NULL;
    }
-    g_source_set_can_recurse(&ctx->source, true);
    aio_set_event_notifier(ctx, &ctx->notifier,
-                           false,
                           (EventNotifierHandler *)
-                           event_notifier_dummy_cb);
+                           event_notifier_test_and_clear);
+    ctx->pollfds = g_array_new(FALSE, FALSE, sizeof(GPollFD));
    ctx->thread_pool = NULL;
    qemu_mutex_init(&ctx->bh_lock);
    rfifolock_init(&ctx->lock, aio_rfifolock_cb, ctx);
    timerlistgroup_init(&ctx->tlg, aio_timerlist_notify, ctx);

-    ctx->notify_dummy_bh = aio_bh_new(ctx, notify_dummy_bh, NULL);
-
    return ctx;
-fail:
-    g_source_destroy(&ctx->source);
-    return NULL;
 }

 void aio_context_ref(AioContext *ctx)
@@ -5,9 +5,13 @@ common-obj-$(CONFIG_SPICE) += spiceaudio.o
 common-obj-$(CONFIG_COREAUDIO) += coreaudio.o
 common-obj-$(CONFIG_ALSA) += alsaaudio.o
 common-obj-$(CONFIG_DSOUND) += dsoundaudio.o
+common-obj-$(CONFIG_FMOD) += fmodaudio.o
+common-obj-$(CONFIG_ESD) += esdaudio.o
 common-obj-$(CONFIG_PA) += paaudio.o
+common-obj-$(CONFIG_WINWAVE) += winwaveaudio.o
 common-obj-$(CONFIG_AUDIO_PT_INT) += audio_pt_int.o
 common-obj-$(CONFIG_AUDIO_WIN_INT) += audio_win_int.o
 common-obj-y += wavcapture.o

+$(obj)/audio.o $(obj)/fmodaudio.o: QEMU_CFLAGS += $(FMOD_CFLAGS)
 sdlaudio.o-cflags := $(SDL_CFLAGS)
@@ -25,7 +25,6 @@
 #include "qemu-common.h"
 #include "qemu/main-loop.h"
 #include "audio.h"
-#include "trace.h"

 #if QEMU_GNUC_PREREQ(4, 3)
 #pragma GCC diagnostic ignored "-Waddress"
@@ -34,28 +33,9 @@
 #define AUDIO_CAP "alsa"
 #include "audio_int.h"

-typedef struct ALSAConf {
-    int size_in_usec_in;
-    int size_in_usec_out;
-    const char *pcm_name_in;
-    const char *pcm_name_out;
-    unsigned int buffer_size_in;
-    unsigned int period_size_in;
-    unsigned int buffer_size_out;
-    unsigned int period_size_out;
-    unsigned int threshold;
-
-    int buffer_size_in_overridden;
-    int period_size_in_overridden;
-
-    int buffer_size_out_overridden;
-    int period_size_out_overridden;
-} ALSAConf;
-
 struct pollhlp {
    snd_pcm_t *handle;
    struct pollfd *pfds;
-    ALSAConf *conf;
    int count;
    int mask;
 };
@@ -76,6 +56,30 @@ typedef struct ALSAVoiceIn {
    struct pollhlp pollhlp;
 } ALSAVoiceIn;

+static struct {
+    int size_in_usec_in;
+    int size_in_usec_out;
+    const char *pcm_name_in;
+    const char *pcm_name_out;
+    unsigned int buffer_size_in;
+    unsigned int period_size_in;
+    unsigned int buffer_size_out;
+    unsigned int period_size_out;
+    unsigned int threshold;
+
+    int buffer_size_in_overridden;
+    int period_size_in_overridden;
+
+    int buffer_size_out_overridden;
+    int period_size_out_overridden;
+    int verbose;
+} conf = {
+    .buffer_size_out = 4096,
+    .period_size_out = 1024,
+    .pcm_name_out = "default",
+    .pcm_name_in = "default",
+};
+
 struct alsa_params_req {
    int freq;
    snd_pcm_format_t fmt;
@@ -201,7 +205,9 @@ static void alsa_poll_handler (void *opaque)
    }

    if (!(revents & hlp->mask)) {
-        trace_alsa_revents(revents);
+        if (conf.verbose) {
+            dolog ("revents = %d\n", revents);
+        }
        return;
    }

@@ -260,14 +266,31 @@ static int alsa_poll_helper (snd_pcm_t *handle, struct pollhlp *hlp, int mask)

    for (i = 0; i < count; ++i) {
        if (pfds[i].events & POLLIN) {
-            qemu_set_fd_handler (pfds[i].fd, alsa_poll_handler, NULL, hlp);
+            err = qemu_set_fd_handler (pfds[i].fd, alsa_poll_handler,
+                                       NULL, hlp);
        }
        if (pfds[i].events & POLLOUT) {
-            trace_alsa_pollout(i, pfds[i].fd);
-            qemu_set_fd_handler (pfds[i].fd, NULL, alsa_poll_handler, hlp);
+            if (conf.verbose) {
+                dolog ("POLLOUT %d %d\n", i, pfds[i].fd);
+            }
+            err = qemu_set_fd_handler (pfds[i].fd, NULL,
+                                       alsa_poll_handler, hlp);
+        }
+        if (conf.verbose) {
+            dolog ("Set handler events=%#x index=%d fd=%d err=%d\n",
+                   pfds[i].events, i, pfds[i].fd, err);
        }
-        trace_alsa_set_handler(pfds[i].events, i, pfds[i].fd, err);

+        if (err) {
+            dolog ("Failed to set handler events=%#x index=%d fd=%d err=%d\n",
+                   pfds[i].events, i, pfds[i].fd, err);
+
+            while (i--) {
+                qemu_set_fd_handler (pfds[i].fd, NULL, NULL, NULL);
+            }
+            g_free (pfds);
+            return -1;
+        }
    }
    hlp->pfds = pfds;
    hlp->count = count;
@@ -453,15 +476,14 @@ static void alsa_set_threshold (snd_pcm_t *handle, snd_pcm_uframes_t threshold)
 }

 static int alsa_open (int in, struct alsa_params_req *req,
-                      struct alsa_params_obt *obt, snd_pcm_t **handlep,
-                      ALSAConf *conf)
+                      struct alsa_params_obt *obt, snd_pcm_t **handlep)
 {
    snd_pcm_t *handle;
    snd_pcm_hw_params_t *hw_params;
    int err;
    int size_in_usec;
    unsigned int freq, nchannels;
-    const char *pcm_name = in ? conf->pcm_name_in : conf->pcm_name_out;
+    const char *pcm_name = in ? conf.pcm_name_in : conf.pcm_name_out;
    snd_pcm_uframes_t obt_buffer_size;
    const char *typ = in ? "ADC" : "DAC";
    snd_pcm_format_t obtfmt;
@@ -500,7 +522,7 @@ static int alsa_open (int in, struct alsa_params_req *req,
    }

    err = snd_pcm_hw_params_set_format (handle, hw_params, req->fmt);
-    if (err < 0) {
+    if (err < 0 && conf.verbose) {
        alsa_logerr2 (err, typ, "Failed to set format %d\n", req->fmt);
    }

@@ -632,7 +654,7 @@ static int alsa_open (int in, struct alsa_params_req *req,
        goto err;
    }

-    if (!in && conf->threshold) {
+    if (!in && conf.threshold) {
        snd_pcm_uframes_t threshold;
        int bytes_per_sec;

@@ -654,7 +676,7 @@ static int alsa_open (int in, struct alsa_params_req *req,
            break;
        }

-        threshold = (conf->threshold * bytes_per_sec) / 1000;
+        threshold = (conf.threshold * bytes_per_sec) / 1000;
        alsa_set_threshold (handle, threshold);
    }

@@ -664,9 +686,10 @@ static int alsa_open (int in, struct alsa_params_req *req,

    *handlep = handle;

-    if (obtfmt != req->fmt ||
+    if (conf.verbose &&
+        (obtfmt != req->fmt ||
         obt->nchannels != req->nchannels ||
-         obt->freq != req->freq) {
+         obt->freq != req->freq)) {
        dolog ("Audio parameters for %s\n", typ);
        alsa_dump_info (req, obt, obtfmt);
    }
@@ -720,7 +743,9 @@ static void alsa_write_pending (ALSAVoiceOut *alsa)
            if (written <= 0) {
                switch (written) {
                case 0:
-                    trace_alsa_wrote_zero(len);
+                    if (conf.verbose) {
+                        dolog ("Failed to write %d frames (wrote zero)\n", len);
+                    }
                    return;

                case -EPIPE:
@@ -729,7 +754,9 @@ static void alsa_write_pending (ALSAVoiceOut *alsa)
                                     len);
                        return;
                    }
-                    trace_alsa_xrun_out();
+                    if (conf.verbose) {
+                        dolog ("Recovering from playback xrun\n");
+                    }
                    continue;

                case -ESTRPIPE:
@@ -740,7 +767,9 @@ static void alsa_write_pending (ALSAVoiceOut *alsa)
                                     len);
                        return;
                    }
-                    trace_alsa_resume_out();
+                    if (conf.verbose) {
+                        dolog ("Resuming suspended output stream\n");
+                    }
                    continue;

                case -EAGAIN:
@@ -790,27 +819,25 @@ static void alsa_fini_out (HWVoiceOut *hw)
    alsa->pcm_buf = NULL;
 }

-static int alsa_init_out(HWVoiceOut *hw, struct audsettings *as,
-                         void *drv_opaque)
+static int alsa_init_out (HWVoiceOut *hw, struct audsettings *as)
 {
    ALSAVoiceOut *alsa = (ALSAVoiceOut *) hw;
    struct alsa_params_req req;
    struct alsa_params_obt obt;
    snd_pcm_t *handle;
    struct audsettings obt_as;
-    ALSAConf *conf = drv_opaque;

    req.fmt = aud_to_alsafmt (as->fmt, as->endianness);
    req.freq = as->freq;
    req.nchannels = as->nchannels;
-    req.period_size = conf->period_size_out;
-    req.buffer_size = conf->buffer_size_out;
-    req.size_in_usec = conf->size_in_usec_out;
+    req.period_size = conf.period_size_out;
+    req.buffer_size = conf.buffer_size_out;
+    req.size_in_usec = conf.size_in_usec_out;
    req.override_mask =
-        (conf->period_size_out_overridden ? 1 : 0) |
-        (conf->buffer_size_out_overridden ? 2 : 0);
+        (conf.period_size_out_overridden ? 1 : 0) |
+        (conf.buffer_size_out_overridden ? 2 : 0);

-    if (alsa_open (0, &req, &obt, &handle, conf)) {
+    if (alsa_open (0, &req, &obt, &handle)) {
        return -1;
    }

@@ -831,7 +858,6 @@ static int alsa_init_out(HWVoiceOut *hw, struct audsettings *as,
    }

    alsa->handle = handle;
-    alsa->pollhlp.conf = conf;
    return 0;
 }

@@ -902,26 +928,25 @@ static int alsa_ctl_out (HWVoiceOut *hw, int cmd, ...)
    return -1;
 }

-static int alsa_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
+static int alsa_init_in (HWVoiceIn *hw, struct audsettings *as)
 {
    ALSAVoiceIn *alsa = (ALSAVoiceIn *) hw;
    struct alsa_params_req req;
    struct alsa_params_obt obt;
    snd_pcm_t *handle;
    struct audsettings obt_as;
-    ALSAConf *conf = drv_opaque;

    req.fmt = aud_to_alsafmt (as->fmt, as->endianness);
    req.freq = as->freq;
    req.nchannels = as->nchannels;
-    req.period_size = conf->period_size_in;
-    req.buffer_size = conf->buffer_size_in;
-    req.size_in_usec = conf->size_in_usec_in;
+    req.period_size = conf.period_size_in;
+    req.buffer_size = conf.buffer_size_in;
+    req.size_in_usec = conf.size_in_usec_in;
    req.override_mask =
-        (conf->period_size_in_overridden ? 1 : 0) |
-        (conf->buffer_size_in_overridden ? 2 : 0);
+        (conf.period_size_in_overridden ? 1 : 0) |
+        (conf.buffer_size_in_overridden ? 2 : 0);

-    if (alsa_open (1, &req, &obt, &handle, conf)) {
+    if (alsa_open (1, &req, &obt, &handle)) {
        return -1;
    }

@@ -942,7 +967,6 @@ static int alsa_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
    }

    alsa->handle = handle;
-    alsa->pollhlp.conf = conf;
    return 0;
 }

@@ -998,10 +1022,14 @@ static int alsa_run_in (HWVoiceIn *hw)
                dolog ("Failed to resume suspended input stream\n");
                return 0;
            }
-            trace_alsa_resume_in();
+            if (conf.verbose) {
+                dolog ("Resuming suspended input stream\n");
+            }
            break;
        default:
-            trace_alsa_no_frames(state);
+            if (conf.verbose) {
+                dolog ("No frames available and ALSA state is %d\n", state);
+            }
            return 0;
        }
    }
@@ -1036,7 +1064,9 @@ static int alsa_run_in (HWVoiceIn *hw)
            if (nread <= 0) {
                switch (nread) {
                case 0:
-                    trace_alsa_read_zero(len);
+                    if (conf.verbose) {
+                        dolog ("Failed to read %ld frames (read zero)\n", len);
+                    }
                    goto exit;

                case -EPIPE:
@@ -1044,7 +1074,9 @@ static int alsa_run_in (HWVoiceIn *hw)
                        alsa_logerr (nread, "Failed to read %ld frames\n", len);
                        goto exit;
                    }
-                    trace_alsa_xrun_in();
+                    if (conf.verbose) {
+                        dolog ("Recovering from capture xrun\n");
+                    }
                    continue;

                case -EAGAIN:
@@ -1116,85 +1148,82 @@ static int alsa_ctl_in (HWVoiceIn *hw, int cmd, ...)
    return -1;
 }

-static ALSAConf glob_conf = {
-    .buffer_size_out = 4096,
-    .period_size_out = 1024,
-    .pcm_name_out = "default",
-    .pcm_name_in = "default",
-};
-
 static void *alsa_audio_init (void)
 {
-    ALSAConf *conf = g_malloc(sizeof(ALSAConf));
-    *conf = glob_conf;
-    return conf;
+    return &conf;
 }

 static void alsa_audio_fini (void *opaque)
 {
-    g_free(opaque);
+    (void) opaque;
 }

 static struct audio_option alsa_options[] = {
    {
        .name        = "DAC_SIZE_IN_USEC",
        .tag         = AUD_OPT_BOOL,
-        .valp        = &glob_conf.size_in_usec_out,
+        .valp        = &conf.size_in_usec_out,
        .descr       = "DAC period/buffer size in microseconds (otherwise in frames)"
    },
    {
        .name        = "DAC_PERIOD_SIZE",
        .tag         = AUD_OPT_INT,
-        .valp        = &glob_conf.period_size_out,
+        .valp        = &conf.period_size_out,
        .descr       = "DAC period size (0 to go with system default)",
-        .overriddenp = &glob_conf.period_size_out_overridden
+        .overriddenp = &conf.period_size_out_overridden
    },
    {
        .name        = "DAC_BUFFER_SIZE",
        .tag         = AUD_OPT_INT,
-        .valp        = &glob_conf.buffer_size_out,
+        .valp        = &conf.buffer_size_out,
        .descr       = "DAC buffer size (0 to go with system default)",
-        .overriddenp = &glob_conf.buffer_size_out_overridden
+        .overriddenp = &conf.buffer_size_out_overridden
    },
    {
        .name        = "ADC_SIZE_IN_USEC",
        .tag         = AUD_OPT_BOOL,
-        .valp        = &glob_conf.size_in_usec_in,
+        .valp        = &conf.size_in_usec_in,
        .descr       =
        "ADC period/buffer size in microseconds (otherwise in frames)"
    },
    {
        .name        = "ADC_PERIOD_SIZE",
        .tag         = AUD_OPT_INT,
-        .valp        = &glob_conf.period_size_in,
+        .valp        = &conf.period_size_in,
        .descr       = "ADC period size (0 to go with system default)",
-        .overriddenp = &glob_conf.period_size_in_overridden
+        .overriddenp = &conf.period_size_in_overridden
    },
    {
        .name        = "ADC_BUFFER_SIZE",
        .tag         = AUD_OPT_INT,
-        .valp        = &glob_conf.buffer_size_in,
+        .valp        = &conf.buffer_size_in,
        .descr       = "ADC buffer size (0 to go with system default)",
-        .overriddenp = &glob_conf.buffer_size_in_overridden
+        .overriddenp = &conf.buffer_size_in_overridden
    },
    {
        .name        = "THRESHOLD",
        .tag         = AUD_OPT_INT,
-        .valp        = &glob_conf.threshold,
+        .valp        = &conf.threshold,
        .descr       = "(undocumented)"
    },
    {
        .name        = "DAC_DEV",
        .tag         = AUD_OPT_STR,
-        .valp        = &glob_conf.pcm_name_out,
+        .valp        = &conf.pcm_name_out,
        .descr       = "DAC device name (for instance dmix)"
    },
    {
        .name        = "ADC_DEV",
        .tag         = AUD_OPT_STR,
-        .valp        = &glob_conf.pcm_name_in,
+        .valp        = &conf.pcm_name_in,
        .descr       = "ADC device name"
    },
+    {
+        .name        = "VERBOSE",
+        .tag         = AUD_OPT_BOOL,
+        .valp        = &conf.verbose,
+        .descr       = "Behave in a more verbose way"
+    },
    { /* End of list */ }
 };

@@ -30,6 +30,7 @@
 #define AUDIO_CAP "audio"
 #include "audio_int.h"

+/* #define DEBUG_PLIVE */
 /* #define DEBUG_LIVE */
 /* #define DEBUG_OUT */
 /* #define DEBUG_CAPTURE */
@@ -65,6 +66,8 @@ static struct {
        int hertz;
        int64_t ticks;
    } period;
+    int plive;
+    int log_to_monitor;
    int try_poll_in;
    int try_poll_out;
 } conf = {
@@ -93,6 +96,8 @@ static struct {
    },

    .period = { .hertz = 100 },
+    .plive = 0,
+    .log_to_monitor = 0,
    .try_poll_in = 1,
    .try_poll_out = 1,
 };
@@ -326,11 +331,20 @@ static const char *audio_get_conf_str (const char *key,

 void AUD_vlog (const char *cap, const char *fmt, va_list ap)
 {
-    if (cap) {
-        fprintf(stderr, "%s: ", cap);
-    }
+    if (conf.log_to_monitor) {
+        if (cap) {
+            monitor_printf(default_mon, "%s: ", cap);
+        }

-    vfprintf(stderr, fmt, ap);
+        monitor_vprintf(default_mon, fmt, ap);
+    }
+    else {
+        if (cap) {
+            fprintf (stderr, "%s: ", cap);
+        }
+
+        vfprintf (stderr, fmt, ap);
+    }
 }

 void AUD_log (const char *cap, const char *fmt, ...)
@@ -1440,6 +1454,9 @@ static void audio_run_out (AudioState *s)
            while (sw) {
                sw1 = sw->entries.le_next;
                if (!sw->active && !sw->callback.fn) {
+#ifdef DEBUG_PLIVE
+                    dolog ("Finishing with old voice\n");
+#endif
                    audio_close_out (sw);
                }
                sw = sw1;
@@ -1631,6 +1648,18 @@ static struct audio_option audio_options[] = {
        .valp  = &conf.period.hertz,
        .descr = "Timer period in HZ (0 - use lowest possible)"
    },
+    {
+        .name  = "PLIVE",
+        .tag   = AUD_OPT_BOOL,
+        .valp  = &conf.plive,
+        .descr = "(undocumented)"
+    },
+    {
+        .name  = "LOG_TO_MONITOR",
+        .tag   = AUD_OPT_BOOL,
+        .valp  = &conf.log_to_monitor,
+        .descr = "Print logging messages to monitor instead of stderr"
+    },
    { /* End of list */ }
 };

@@ -156,13 +156,13 @@ struct audio_driver {
 };

 struct audio_pcm_ops {
-    int  (*init_out)(HWVoiceOut *hw, struct audsettings *as, void *drv_opaque);
+    int  (*init_out)(HWVoiceOut *hw, struct audsettings *as);
    void (*fini_out)(HWVoiceOut *hw);
    int  (*run_out) (HWVoiceOut *hw, int live);
    int  (*write)   (SWVoiceOut *sw, void *buf, int size);
    int  (*ctl_out) (HWVoiceOut *hw, int cmd, ...);

-    int  (*init_in) (HWVoiceIn *hw, struct audsettings *as, void *drv_opaque);
+    int  (*init_in) (HWVoiceIn *hw, struct audsettings *as);
    void (*fini_in) (HWVoiceIn *hw);
    int  (*run_in)  (HWVoiceIn *hw);
    int  (*read)    (SWVoiceIn *sw, void *buf, int size);
@@ -206,11 +206,14 @@ extern struct audio_driver no_audio_driver;
 extern struct audio_driver oss_audio_driver;
 extern struct audio_driver sdl_audio_driver;
 extern struct audio_driver wav_audio_driver;
+extern struct audio_driver fmod_audio_driver;
 extern struct audio_driver alsa_audio_driver;
 extern struct audio_driver coreaudio_audio_driver;
 extern struct audio_driver dsound_audio_driver;
+extern struct audio_driver esd_audio_driver;
 extern struct audio_driver pa_audio_driver;
 extern struct audio_driver spice_audio_driver;
+extern struct audio_driver winwave_audio_driver;
 extern const struct mixeng_volume nominal_volume;

 void audio_pcm_init_info (struct audio_pcm_info *info, struct audsettings *as);
@@ -262,7 +262,7 @@ static HW *glue (audio_pcm_hw_add_new_, TYPE) (struct audsettings *as)
 #ifdef DAC
    QLIST_INIT (&hw->cap_head);
 #endif
-    if (glue (hw->pcm_ops->init_, TYPE) (hw, as, s->drv_opaque)) {
+    if (glue (hw->pcm_ops->init_, TYPE) (hw, as)) {
        goto err0;
    }

@@ -398,6 +398,10 @@ SW *glue (AUD_open_, TYPE) (
    )
 {
    AudioState *s = &glob_audio_state;
+#ifdef DAC
+    int live = 0;
+    SW *old_sw = NULL;
+#endif

    if (audio_bug (AUDIO_FUNC, !card || !name || !callback_fn || !as)) {
        dolog ("card=%p name=%p callback_fn=%p as=%p\n",
@@ -422,6 +426,29 @@ SW *glue (AUD_open_, TYPE) (
        return sw;
    }

+#ifdef DAC
+    if (conf.plive && sw && (!sw->active && !sw->empty)) {
+        live = sw->total_hw_samples_mixed;
+
+#ifdef DEBUG_PLIVE
+        dolog ("Replacing voice %s with %d live samples\n", SW_NAME (sw), live);
+        dolog ("Old %s freq %d, bits %d, channels %d\n",
+               SW_NAME (sw), sw->info.freq, sw->info.bits, sw->info.nchannels);
+        dolog ("New %s freq %d, bits %d, channels %d\n",
+               name,
+               as->freq,
+               (as->fmt == AUD_FMT_S16 || as->fmt == AUD_FMT_U16) ? 16 : 8,
+               as->nchannels);
+#endif
+
+        if (live) {
+            old_sw = sw;
+            old_sw->callback.fn = NULL;
+            sw = NULL;
+        }
+    }
+#endif
+
    if (!glue (conf.fixed_, TYPE).enabled && sw) {
        glue (AUD_close_, TYPE) (card, sw);
        sw = NULL;
@@ -454,6 +481,20 @@ SW *glue (AUD_open_, TYPE) (
    sw->callback.fn = callback_fn;
    sw->callback.opaque = callback_opaque;

+#ifdef DAC
+    if (live) {
+        int mixed =
+            (live << old_sw->info.shift)
+            * old_sw->info.bytes_per_second
+            / sw->info.bytes_per_second;
+
+#ifdef DEBUG_PLIVE
+        dolog ("Silence will be mixed %d\n", mixed);
+#endif
+        sw->total_hw_samples_mixed += mixed;
+    }
+#endif
+
 #ifdef DEBUG_AUDIO
    dolog ("%s\n", name);
    audio_pcm_print_info ("hw", &sw->hw->info);
@@ -32,16 +32,20 @@
 #define AUDIO_CAP "coreaudio"
 #include "audio_int.h"

-static int isAtexit;
-
-typedef struct {
+struct {
    int buffer_frames;
    int nbuffers;
-} CoreaudioConf;
+    int isAtexit;
+} conf = {
+    .buffer_frames = 512,
+    .nbuffers = 4,
+    .isAtexit = 0
+};

 typedef struct coreaudioVoiceOut {
    HWVoiceOut hw;
    pthread_mutex_t mutex;
+    int isAtexit;
    AudioDeviceID outputDeviceID;
    UInt32 audioDevicePropertyBufferFrameSize;
    AudioStreamBasicDescription outputStreamBasicDescription;
@@ -157,7 +161,7 @@ static inline UInt32 isPlaying (AudioDeviceID outputDeviceID)

 static void coreaudio_atexit (void)
 {
-    isAtexit = 1;
+    conf.isAtexit = 1;
 }

 static int coreaudio_lock (coreaudioVoiceOut *core, const char *fn_name)
@@ -283,8 +287,7 @@ static int coreaudio_write (SWVoiceOut *sw, void *buf, int len)
    return audio_pcm_sw_write (sw, buf, len);
 }

-static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
-                              void *drv_opaque)
+static int coreaudio_init_out (HWVoiceOut *hw, struct audsettings *as)
 {
    OSStatus status;
    coreaudioVoiceOut *core = (coreaudioVoiceOut *) hw;
@@ -292,7 +295,6 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
    int err;
    const char *typ = "playback";
    AudioValueRange frameRange;
-    CoreaudioConf *conf = drv_opaque;

    /* create mutex */
    err = pthread_mutex_init(&core->mutex, NULL);
@@ -334,16 +336,16 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
        return -1;
    }

-    if (frameRange.mMinimum > conf->buffer_frames) {
+    if (frameRange.mMinimum > conf.buffer_frames) {
        core->audioDevicePropertyBufferFrameSize = (UInt32) frameRange.mMinimum;
        dolog ("warning: Upsizing Buffer Frames to %f\n", frameRange.mMinimum);
    }
-    else if (frameRange.mMaximum < conf->buffer_frames) {
+    else if (frameRange.mMaximum < conf.buffer_frames) {
        core->audioDevicePropertyBufferFrameSize = (UInt32) frameRange.mMaximum;
        dolog ("warning: Downsizing Buffer Frames to %f\n", frameRange.mMaximum);
    }
    else {
-        core->audioDevicePropertyBufferFrameSize = conf->buffer_frames;
+        core->audioDevicePropertyBufferFrameSize = conf.buffer_frames;
    }

    /* set Buffer Frame Size */
@@ -377,7 +379,7 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
                           "Could not get device buffer frame size\n");
        return -1;
    }
-    hw->samples = conf->nbuffers * core->audioDevicePropertyBufferFrameSize;
+    hw->samples = conf.nbuffers * core->audioDevicePropertyBufferFrameSize;

    /* get StreamFormat */
    propertySize = sizeof(core->outputStreamBasicDescription);
@@ -441,7 +443,7 @@ static void coreaudio_fini_out (HWVoiceOut *hw)
    int err;
    coreaudioVoiceOut *core = (coreaudioVoiceOut *) hw;

-    if (!isAtexit) {
+    if (!conf.isAtexit) {
        /* stop playback */
        if (isPlaying(core->outputDeviceID)) {
            status = AudioDeviceStop(core->outputDeviceID, audioDeviceIOProc);
@@ -484,7 +486,7 @@ static int coreaudio_ctl_out (HWVoiceOut *hw, int cmd, ...)

    case VOICE_DISABLE:
        /* stop playback */
-        if (!isAtexit) {
+        if (!conf.isAtexit) {
            if (isPlaying(core->outputDeviceID)) {
                status = AudioDeviceStop(core->outputDeviceID, audioDeviceIOProc);
                if (status != kAudioHardwareNoError) {
@@ -497,36 +499,28 @@ static int coreaudio_ctl_out (HWVoiceOut *hw, int cmd, ...)
    return 0;
 }

-static CoreaudioConf glob_conf = {
-    .buffer_frames = 512,
-    .nbuffers = 4,
-};
-
 static void *coreaudio_audio_init (void)
 {
-    CoreaudioConf *conf = g_malloc(sizeof(CoreaudioConf));
-    *conf = glob_conf;
-
    atexit(coreaudio_atexit);
-    return conf;
+    return &coreaudio_audio_init;
 }

 static void coreaudio_audio_fini (void *opaque)
 {
-    g_free(opaque);
+    (void) opaque;
 }

 static struct audio_option coreaudio_options[] = {
    {
        .name  = "BUFFER_SIZE",
        .tag   = AUD_OPT_INT,
-        .valp  = &glob_conf.buffer_frames,
+        .valp  = &conf.buffer_frames,
        .descr = "Size of the buffer in frames"
    },
    {
        .name  = "BUFFER_COUNT",
        .tag   = AUD_OPT_INT,
-        .valp  = &glob_conf.nbuffers,
+        .valp  = &conf.nbuffers,
        .descr = "Number of buffers"
    },
    { /* End of list */ }
@@ -67,11 +67,11 @@ static int glue (dsound_lock_, TYPE) (
    LPVOID *p2p,
    DWORD *blen1p,
    DWORD *blen2p,
-    int entire,
-    dsound *s
+    int entire
    )
 {
    HRESULT hr;
+    int i;
    LPVOID p1 = NULL, p2 = NULL;
    DWORD blen1 = 0, blen2 = 0;
    DWORD flag;
@@ -81,18 +81,37 @@ static int glue (dsound_lock_, TYPE) (
 #else
    flag = entire ? DSBLOCK_ENTIREBUFFER : 0;
 #endif
-    hr = glue(IFACE, _Lock)(buf, pos, len, &p1, &blen1, &p2, &blen2, flag);
+    for (i = 0; i < conf.lock_retries; ++i) {
+        hr = glue (IFACE, _Lock) (
+            buf,
+            pos,
+            len,
+            &p1,
+            &blen1,
+            &p2,
+            &blen2,
+            flag
+            );

-    if (FAILED (hr)) {
+        if (FAILED (hr)) {
 #ifndef DSBTYPE_IN
-        if (hr == DSERR_BUFFERLOST) {
-            if (glue (dsound_restore_, TYPE) (buf, s)) {
-                dsound_logerr (hr, "Could not lock " NAME "\n");
+            if (hr == DSERR_BUFFERLOST) {
+                if (glue (dsound_restore_, TYPE) (buf)) {
+                    dsound_logerr (hr, "Could not lock " NAME "\n");
+                    goto fail;
+                }
+                continue;
            }
+#endif
+            dsound_logerr (hr, "Could not lock " NAME "\n");
            goto fail;
        }
-#endif
-        dsound_logerr (hr, "Could not lock " NAME "\n");
+
+        break;
+    }
+
+    if (i == conf.lock_retries) {
+        dolog ("%d attempts to lock " NAME " failed\n", i);
        goto fail;
    }

@@ -155,19 +174,16 @@ static void dsound_fini_out (HWVoiceOut *hw)
 }

 #ifdef DSBTYPE_IN
-static int dsound_init_in(HWVoiceIn *hw, struct audsettings *as,
-                          void *drv_opaque)
+static int dsound_init_in (HWVoiceIn *hw, struct audsettings *as)
 #else
-static int dsound_init_out(HWVoiceOut *hw, struct audsettings *as,
-                           void *drv_opaque)
+static int dsound_init_out (HWVoiceOut *hw, struct audsettings *as)
 #endif
 {
    int err;
    HRESULT hr;
-    dsound *s = drv_opaque;
+    dsound *s = &glob_dsound;
    WAVEFORMATEX wfx;
    struct audsettings obt_as;
-    DSoundConf *conf = &s->conf;
 #ifdef DSBTYPE_IN
    const char *typ = "ADC";
    DSoundVoiceIn *ds = (DSoundVoiceIn *) hw;
@@ -194,7 +210,7 @@ static int dsound_init_out(HWVoiceOut *hw, struct audsettings *as,
    bd.dwSize = sizeof (bd);
    bd.lpwfxFormat = &wfx;
 #ifdef DSBTYPE_IN
-    bd.dwBufferBytes = conf->bufsize_in;
+    bd.dwBufferBytes = conf.bufsize_in;
    hr = IDirectSoundCapture_CreateCaptureBuffer (
        s->dsound_capture,
        &bd,
@@ -203,7 +219,7 @@ static int dsound_init_out(HWVoiceOut *hw, struct audsettings *as,
        );
 #else
    bd.dwFlags = DSBCAPS_STICKYFOCUS | DSBCAPS_GETCURRENTPOSITION2;
-    bd.dwBufferBytes = conf->bufsize_out;
+    bd.dwBufferBytes = conf.bufsize_out;
    hr = IDirectSound_CreateSoundBuffer (
        s->dsound,
        &bd,
@@ -253,7 +269,6 @@ static int dsound_init_out(HWVoiceOut *hw, struct audsettings *as,
            );
    }
    hw->samples = bc.dwBufferBytes >> hw->info.shift;
-    ds->s = s;

 #ifdef DEBUG_DSOUND
    dolog ("caps %ld, desc %ld\n",
@@ -41,25 +41,42 @@

 /* #define DEBUG_DSOUND */

-typedef struct {
+static struct {
+    int lock_retries;
+    int restore_retries;
+    int getstatus_retries;
+    int set_primary;
    int bufsize_in;
    int bufsize_out;
+    struct audsettings settings;
    int latency_millis;
-} DSoundConf;
+} conf = {
+    .lock_retries       = 1,
+    .restore_retries    = 1,
+    .getstatus_retries  = 1,
+    .set_primary        = 0,
+    .bufsize_in         = 16384,
+    .bufsize_out        = 16384,
+    .settings.freq      = 44100,
+    .settings.nchannels = 2,
+    .settings.fmt       = AUD_FMT_S16,
+    .latency_millis     = 10
+};

 typedef struct {
    LPDIRECTSOUND dsound;
    LPDIRECTSOUNDCAPTURE dsound_capture;
+    LPDIRECTSOUNDBUFFER dsound_primary_buffer;
    struct audsettings settings;
-    DSoundConf conf;
 } dsound;

+static dsound glob_dsound;
+
 typedef struct {
    HWVoiceOut hw;
    LPDIRECTSOUNDBUFFER dsound_buffer;
    DWORD old_pos;
    int first_time;
-    dsound *s;
 #ifdef DEBUG_DSOUND
    DWORD old_ppos;
    DWORD played;
@@ -71,7 +88,6 @@ typedef struct {
    HWVoiceIn hw;
    int first_time;
    LPDIRECTSOUNDCAPTUREBUFFER dsound_capture_buffer;
-    dsound *s;
 } DSoundVoiceIn;

 static void dsound_log_hresult (HRESULT hr)
@@ -265,17 +281,29 @@ static void print_wave_format (WAVEFORMATEX *wfx)
 }
 #endif

-static int dsound_restore_out (LPDIRECTSOUNDBUFFER dsb, dsound *s)
+static int dsound_restore_out (LPDIRECTSOUNDBUFFER dsb)
 {
    HRESULT hr;
+    int i;

-    hr = IDirectSoundBuffer_Restore (dsb);
+    for (i = 0; i < conf.restore_retries; ++i) {
+        hr = IDirectSoundBuffer_Restore (dsb);

-    if (hr != DS_OK) {
-        dsound_logerr (hr, "Could not restore playback buffer\n");
-        return -1;
+        switch (hr) {
+        case DS_OK:
+            return 0;
+
+        case DSERR_BUFFERLOST:
+            continue;
+
+        default:
+            dsound_logerr (hr, "Could not restore playback buffer\n");
+            return -1;
+        }
    }
-    return 0;
+
+    dolog ("%d attempts to restore playback buffer failed\n", i);
+    return -1;
 }

 #include "dsound_template.h"
@@ -283,20 +311,25 @@ static int dsound_restore_out (LPDIRECTSOUNDBUFFER dsb, dsound *s)
 #include "dsound_template.h"
 #undef DSBTYPE_IN

-static int dsound_get_status_out (LPDIRECTSOUNDBUFFER dsb, DWORD *statusp,
-                                  dsound *s)
+static int dsound_get_status_out (LPDIRECTSOUNDBUFFER dsb, DWORD *statusp)
 {
    HRESULT hr;
+    int i;

-    hr = IDirectSoundBuffer_GetStatus (dsb, statusp);
-    if (FAILED (hr)) {
-        dsound_logerr (hr, "Could not get playback buffer status\n");
-        return -1;
-    }
+    for (i = 0; i < conf.getstatus_retries; ++i) {
+        hr = IDirectSoundBuffer_GetStatus (dsb, statusp);
+        if (FAILED (hr)) {
+            dsound_logerr (hr, "Could not get playback buffer status\n");
+            return -1;
+        }

-    if (*statusp & DSERR_BUFFERLOST) {
-        dsound_restore_out(dsb, s);
-        return -1;
+        if (*statusp & DSERR_BUFFERLOST) {
+            if (dsound_restore_out (dsb)) {
+                return -1;
+            }
+            continue;
+        }
+        break;
    }

    return 0;
@@ -343,8 +376,7 @@ static void dsound_write_sample (HWVoiceOut *hw, uint8_t *dst, int dst_len)
    hw->rpos = pos % hw->samples;
 }

-static void dsound_clear_sample (HWVoiceOut *hw, LPDIRECTSOUNDBUFFER dsb,
-                                 dsound *s)
+static void dsound_clear_sample (HWVoiceOut *hw, LPDIRECTSOUNDBUFFER dsb)
 {
    int err;
    LPVOID p1, p2;
@@ -357,8 +389,7 @@ static void dsound_clear_sample (HWVoiceOut *hw, LPDIRECTSOUNDBUFFER dsb,
        hw->samples << hw->info.shift,
        &p1, &p2,
        &blen1, &blen2,
-        1,
-        s
+        1
        );
    if (err) {
        return;
@@ -384,9 +415,25 @@ static void dsound_clear_sample (HWVoiceOut *hw, LPDIRECTSOUNDBUFFER dsb,
    dsound_unlock_out (dsb, p1, p2, blen1, blen2);
 }

-static int dsound_open (dsound *s)
+static void dsound_close (dsound *s)
 {
    HRESULT hr;
+
+    if (s->dsound_primary_buffer) {
+        hr = IDirectSoundBuffer_Release (s->dsound_primary_buffer);
+        if (FAILED (hr)) {
+            dsound_logerr (hr, "Could not release primary buffer\n");
+        }
+        s->dsound_primary_buffer = NULL;
+    }
+}
+
+static int dsound_open (dsound *s)
+{
+    int err;
+    HRESULT hr;
+    WAVEFORMATEX wfx;
+    DSBUFFERDESC dsbd;
    HWND hwnd;

    hwnd = GetForegroundWindow ();
@@ -402,7 +449,63 @@ static int dsound_open (dsound *s)
        return -1;
    }

+    if (!conf.set_primary) {
+        return 0;
+    }
+
+    err = waveformat_from_audio_settings (&wfx, &conf.settings);
+    if (err) {
+        return -1;
+    }
+
+    memset (&dsbd, 0, sizeof (dsbd));
+    dsbd.dwSize = sizeof (dsbd);
+    dsbd.dwFlags = DSBCAPS_PRIMARYBUFFER;
+    dsbd.dwBufferBytes = 0;
+    dsbd.lpwfxFormat = NULL;
+
+    hr = IDirectSound_CreateSoundBuffer (
+        s->dsound,
+        &dsbd,
+        &s->dsound_primary_buffer,
+        NULL
+        );
+    if (FAILED (hr)) {
+        dsound_logerr (hr, "Could not create primary playback buffer\n");
+        return -1;
+    }
+
+    hr = IDirectSoundBuffer_SetFormat (s->dsound_primary_buffer, &wfx);
+    if (FAILED (hr)) {
+        dsound_logerr (hr, "Could not set primary playback buffer format\n");
+    }
+
+    hr = IDirectSoundBuffer_GetFormat (
+        s->dsound_primary_buffer,
+        &wfx,
+        sizeof (wfx),
+        NULL
+        );
+    if (FAILED (hr)) {
+        dsound_logerr (hr, "Could not get primary playback buffer format\n");
+        goto fail0;
+    }
+
+#ifdef DEBUG_DSOUND
+    dolog ("Primary\n");
+    print_wave_format (&wfx);
+#endif
+
+    err = waveformat_to_audio_settings (&wfx, &s->settings);
+    if (err) {
+        goto fail0;
+    }
+
    return 0;
+
+ fail0:
+    dsound_close (s);
+    return -1;
 }

 static int dsound_ctl_out (HWVoiceOut *hw, int cmd, ...)
@@ -411,7 +514,6 @@ static int dsound_ctl_out (HWVoiceOut *hw, int cmd, ...)
    DWORD status;
    DSoundVoiceOut *ds = (DSoundVoiceOut *) hw;
    LPDIRECTSOUNDBUFFER dsb = ds->dsound_buffer;
-    dsound *s = ds->s;

    if (!dsb) {
        dolog ("Attempt to control voice without a buffer\n");
@@ -420,7 +522,7 @@ static int dsound_ctl_out (HWVoiceOut *hw, int cmd, ...)

    switch (cmd) {
    case VOICE_ENABLE:
-        if (dsound_get_status_out (dsb, &status, s)) {
+        if (dsound_get_status_out (dsb, &status)) {
            return -1;
        }

@@ -429,7 +531,7 @@ static int dsound_ctl_out (HWVoiceOut *hw, int cmd, ...)
            return 0;
        }

-        dsound_clear_sample (hw, dsb, s);
+        dsound_clear_sample (hw, dsb);

        hr = IDirectSoundBuffer_Play (dsb, 0, 0, DSBPLAY_LOOPING);
        if (FAILED (hr)) {
@@ -439,7 +541,7 @@ static int dsound_ctl_out (HWVoiceOut *hw, int cmd, ...)
        break;

    case VOICE_DISABLE:
-        if (dsound_get_status_out (dsb, &status, s)) {
+        if (dsound_get_status_out (dsb, &status)) {
            return -1;
        }

@@ -476,8 +578,6 @@ static int dsound_run_out (HWVoiceOut *hw, int live)
    DWORD wpos, ppos, old_pos;
    LPVOID p1, p2;
    int bufsize;
-    dsound *s = ds->s;
-    DSoundConf *conf = &s->conf;

    if (!dsb) {
        dolog ("Attempt to run empty with playback buffer\n");
@@ -500,14 +600,14 @@ static int dsound_run_out (HWVoiceOut *hw, int live)
    len = live << hwshift;

    if (ds->first_time) {
-        if (conf->latency_millis) {
+        if (conf.latency_millis) {
            DWORD cur_blat;

            cur_blat = audio_ring_dist (wpos, ppos, bufsize);
            ds->first_time = 0;
            old_pos = wpos;
            old_pos +=
-                millis_to_bytes (&hw->info, conf->latency_millis) - cur_blat;
+                millis_to_bytes (&hw->info, conf.latency_millis) - cur_blat;
            old_pos %= bufsize;
            old_pos &= ~hw->info.align;
        }
@@ -563,8 +663,7 @@ static int dsound_run_out (HWVoiceOut *hw, int live)
        len,
        &p1, &p2,
        &blen1, &blen2,
-        0,
-        s
+        0
        );
    if (err) {
        return 0;
@@ -667,7 +766,6 @@ static int dsound_run_in (HWVoiceIn *hw)
    DWORD cpos, rpos;
    LPVOID p1, p2;
    int hwshift;
-    dsound *s = ds->s;

    if (!dscb) {
        dolog ("Attempt to run without capture buffer\n");
@@ -722,8 +820,7 @@ static int dsound_run_in (HWVoiceIn *hw)
        &p2,
        &blen1,
        &blen2,
-        0,
-        s
+        0
        );
    if (err) {
        return 0;
@@ -746,19 +843,12 @@ static int dsound_run_in (HWVoiceIn *hw)
    return decr;
 }

-static DSoundConf glob_conf = {
-    .bufsize_in         = 16384,
-    .bufsize_out        = 16384,
-    .latency_millis     = 10
-};
-
 static void dsound_audio_fini (void *opaque)
 {
    HRESULT hr;
    dsound *s = opaque;

    if (!s->dsound) {
-        g_free(s);
        return;
    }

@@ -769,7 +859,6 @@ static void dsound_audio_fini (void *opaque)
    s->dsound = NULL;

    if (!s->dsound_capture) {
-        g_free(s);
        return;
    }

@@ -778,21 +867,17 @@ static void dsound_audio_fini (void *opaque)
        dsound_logerr (hr, "Could not release DirectSoundCapture\n");
    }
    s->dsound_capture = NULL;
-
-    g_free(s);
 }

 static void *dsound_audio_init (void)
 {
    int err;
    HRESULT hr;
-    dsound *s = g_malloc0(sizeof(dsound));
+    dsound *s = &glob_dsound;

-    s->conf = glob_conf;
    hr = CoInitialize (NULL);
    if (FAILED (hr)) {
        dsound_logerr (hr, "Could not initialize COM\n");
-        g_free(s);
        return NULL;
    }

@@ -805,7 +890,6 @@ static void *dsound_audio_init (void)
        );
    if (FAILED (hr)) {
        dsound_logerr (hr, "Could not create DirectSound instance\n");
-        g_free(s);
        return NULL;
    }

@@ -817,7 +901,7 @@ static void *dsound_audio_init (void)
        if (FAILED (hr)) {
            dsound_logerr (hr, "Could not release DirectSound\n");
        }
-        g_free(s);
+        s->dsound = NULL;
        return NULL;
    }

@@ -854,22 +938,64 @@ static void *dsound_audio_init (void)
 }

 static struct audio_option dsound_options[] = {
+    {
+        .name  = "LOCK_RETRIES",
+        .tag   = AUD_OPT_INT,
+        .valp  = &conf.lock_retries,
+        .descr = "Number of times to attempt locking the buffer"
+    },
+    {
+        .name  = "RESTOURE_RETRIES",
+        .tag   = AUD_OPT_INT,
+        .valp  = &conf.restore_retries,
+        .descr = "Number of times to attempt restoring the buffer"
+    },
+    {
+        .name  = "GETSTATUS_RETRIES",
+        .tag   = AUD_OPT_INT,
+        .valp  = &conf.getstatus_retries,
+        .descr = "Number of times to attempt getting status of the buffer"
+    },
+    {
+        .name  = "SET_PRIMARY",
+        .tag   = AUD_OPT_BOOL,
+        .valp  = &conf.set_primary,
+        .descr = "Set the parameters of primary buffer"
+    },
    {
        .name  = "LATENCY_MILLIS",
        .tag   = AUD_OPT_INT,
-        .valp  = &glob_conf.latency_millis,
+        .valp  = &conf.latency_millis,
        .descr = "(undocumented)"
    },
+    {
+        .name  = "PRIMARY_FREQ",
+        .tag   = AUD_OPT_INT,
+        .valp  = &conf.settings.freq,
+        .descr = "Primary buffer frequency"
+    },
+    {
+        .name  = "PRIMARY_CHANNELS",
+        .tag   = AUD_OPT_INT,
+        .valp  = &conf.settings.nchannels,
+        .descr = "Primary buffer number of channels (1 - mono, 2 - stereo)"
+    },
+    {
+        .name  = "PRIMARY_FMT",
+        .tag   = AUD_OPT_FMT,
+        .valp  = &conf.settings.fmt,
+        .descr = "Primary buffer format"
+    },
    {
        .name  = "BUFSIZE_OUT",
        .tag   = AUD_OPT_INT,
-        .valp  = &glob_conf.bufsize_out,
+        .valp  = &conf.bufsize_out,
        .descr = "(undocumented)"
    },
    {
        .name  = "BUFSIZE_IN",
        .tag   = AUD_OPT_INT,
-        .valp  = &glob_conf.bufsize_in,
+        .valp  = &conf.bufsize_in,
        .descr = "(undocumented)"
    },
    { /* End of list */ }
@@ -0,0 +1,557 @@
+/*
+ * QEMU ESD audio driver
+ *
+ * Copyright (c) 2006 Frederick Reeve (brushed up by malc)
+ *
+ * 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 <esd.h>
+#include "qemu-common.h"
+#include "audio.h"
+
+#define AUDIO_CAP "esd"
+#include "audio_int.h"
+#include "audio_pt_int.h"
+
+typedef struct {
+    HWVoiceOut hw;
+    int done;
+    int live;
+    int decr;
+    int rpos;
+    void *pcm_buf;
+    int fd;
+    struct audio_pt pt;
+} ESDVoiceOut;
+
+typedef struct {
+    HWVoiceIn hw;
+    int done;
+    int dead;
+    int incr;
+    int wpos;
+    void *pcm_buf;
+    int fd;
+    struct audio_pt pt;
+} ESDVoiceIn;
+
+static struct {
+    int samples;
+    int divisor;
+    char *dac_host;
+    char *adc_host;
+} conf = {
+    .samples = 1024,
+    .divisor = 2,
+};
+
+static void GCC_FMT_ATTR (2, 3) qesd_logerr (int err, const char *fmt, ...)
+{
+    va_list ap;
+
+    va_start (ap, fmt);
+    AUD_vlog (AUDIO_CAP, fmt, ap);
+    va_end (ap);
+
+    AUD_log (AUDIO_CAP, "Reason: %s\n", strerror (err));
+}
+
+/* playback */
+static void *qesd_thread_out (void *arg)
+{
+    ESDVoiceOut *esd = arg;
+    HWVoiceOut *hw = &esd->hw;
+    int threshold;
+
+    threshold = conf.divisor ? hw->samples / conf.divisor : 0;
+
+    if (audio_pt_lock (&esd->pt, AUDIO_FUNC)) {
+        return NULL;
+    }
+
+    for (;;) {
+        int decr, to_mix, rpos;
+
+        for (;;) {
+            if (esd->done) {
+                goto exit;
+            }
+
+            if (esd->live > threshold) {
+                break;
+            }
+
+            if (audio_pt_wait (&esd->pt, AUDIO_FUNC)) {
+                goto exit;
+            }
+        }
+
+        decr = to_mix = esd->live;
+        rpos = hw->rpos;
+
+        if (audio_pt_unlock (&esd->pt, AUDIO_FUNC)) {
+            return NULL;
+        }
+
+        while (to_mix) {
+            ssize_t written;
+            int chunk = audio_MIN (to_mix, hw->samples - rpos);
+            struct st_sample *src = hw->mix_buf + rpos;
+
+            hw->clip (esd->pcm_buf, src, chunk);
+
+        again:
+            written = write (esd->fd, esd->pcm_buf, chunk << hw->info.shift);
+            if (written == -1) {
+                if (errno == EINTR || errno == EAGAIN) {
+                    goto again;
+                }
+                qesd_logerr (errno, "write failed\n");
+                return NULL;
+            }
+
+            if (written != chunk << hw->info.shift) {
+                int wsamples = written >> hw->info.shift;
+                int wbytes = wsamples << hw->info.shift;
+                if (wbytes != written) {
+                    dolog ("warning: Misaligned write %d (requested %zd), "
+                           "alignment %d\n",
+                           wbytes, written, hw->info.align + 1);
+                }
+                to_mix -= wsamples;
+                rpos = (rpos + wsamples) % hw->samples;
+                break;
+            }
+
+            rpos = (rpos + chunk) % hw->samples;
+            to_mix -= chunk;
+        }
+
+        if (audio_pt_lock (&esd->pt, AUDIO_FUNC)) {
+            return NULL;
+        }
+
+        esd->rpos = rpos;
+        esd->live -= decr;
+        esd->decr += decr;
+    }
+
+ exit:
+    audio_pt_unlock (&esd->pt, AUDIO_FUNC);
+    return NULL;
+}
+
+static int qesd_run_out (HWVoiceOut *hw, int live)
+{
+    int decr;
+    ESDVoiceOut *esd = (ESDVoiceOut *) hw;
+
+    if (audio_pt_lock (&esd->pt, AUDIO_FUNC)) {
+        return 0;
+    }
+
+    decr = audio_MIN (live, esd->decr);
+    esd->decr -= decr;
+    esd->live = live - decr;
+    hw->rpos = esd->rpos;
+    if (esd->live > 0) {
+        audio_pt_unlock_and_signal (&esd->pt, AUDIO_FUNC);
+    }
+    else {
+        audio_pt_unlock (&esd->pt, AUDIO_FUNC);
+    }
+    return decr;
+}
+
+static int qesd_write (SWVoiceOut *sw, void *buf, int len)
+{
+    return audio_pcm_sw_write (sw, buf, len);
+}
+
+static int qesd_init_out (HWVoiceOut *hw, struct audsettings *as)
+{
+    ESDVoiceOut *esd = (ESDVoiceOut *) hw;
+    struct audsettings obt_as = *as;
+    int esdfmt = ESD_STREAM | ESD_PLAY;
+
+    esdfmt |= (as->nchannels == 2) ? ESD_STEREO : ESD_MONO;
+    switch (as->fmt) {
+    case AUD_FMT_S8:
+    case AUD_FMT_U8:
+        esdfmt |= ESD_BITS8;
+        obt_as.fmt = AUD_FMT_U8;
+        break;
+
+    case AUD_FMT_S32:
+    case AUD_FMT_U32:
+        dolog ("Will use 16 instead of 32 bit samples\n");
+        /* fall through */
+    case AUD_FMT_S16:
+    case AUD_FMT_U16:
+    deffmt:
+        esdfmt |= ESD_BITS16;
+        obt_as.fmt = AUD_FMT_S16;
+        break;
+
+    default:
+        dolog ("Internal logic error: Bad audio format %d\n", as->fmt);
+        goto deffmt;
+
+    }
+    obt_as.endianness = AUDIO_HOST_ENDIANNESS;
+
+    audio_pcm_init_info (&hw->info, &obt_as);
+
+    hw->samples = conf.samples;
+    esd->pcm_buf = audio_calloc (AUDIO_FUNC, hw->samples, 1 << hw->info.shift);
+    if (!esd->pcm_buf) {
+        dolog ("Could not allocate buffer (%d bytes)\n",
+               hw->samples << hw->info.shift);
+        return -1;
+    }
+
+    esd->fd = esd_play_stream (esdfmt, as->freq, conf.dac_host, NULL);
+    if (esd->fd < 0) {
+        qesd_logerr (errno, "esd_play_stream failed\n");
+        goto fail1;
+    }
+
+    if (audio_pt_init (&esd->pt, qesd_thread_out, esd, AUDIO_CAP, AUDIO_FUNC)) {
+        goto fail2;
+    }
+
+    return 0;
+
+ fail2:
+    if (close (esd->fd)) {
+        qesd_logerr (errno, "%s: close on esd socket(%d) failed\n",
+                     AUDIO_FUNC, esd->fd);
+    }
+    esd->fd = -1;
+
+ fail1:
+    g_free (esd->pcm_buf);
+    esd->pcm_buf = NULL;
+    return -1;
+}
+
+static void qesd_fini_out (HWVoiceOut *hw)
+{
+    void *ret;
+    ESDVoiceOut *esd = (ESDVoiceOut *) hw;
+
+    audio_pt_lock (&esd->pt, AUDIO_FUNC);
+    esd->done = 1;
+    audio_pt_unlock_and_signal (&esd->pt, AUDIO_FUNC);
+    audio_pt_join (&esd->pt, &ret, AUDIO_FUNC);
+
+    if (esd->fd >= 0) {
+        if (close (esd->fd)) {
+            qesd_logerr (errno, "failed to close esd socket\n");
+        }
+        esd->fd = -1;
+    }
+
+    audio_pt_fini (&esd->pt, AUDIO_FUNC);
+
+    g_free (esd->pcm_buf);
+    esd->pcm_buf = NULL;
+}
+
+static int qesd_ctl_out (HWVoiceOut *hw, int cmd, ...)
+{
+    (void) hw;
+    (void) cmd;
+    return 0;
+}
+
+/* capture */
+static void *qesd_thread_in (void *arg)
+{
+    ESDVoiceIn *esd = arg;
+    HWVoiceIn *hw = &esd->hw;
+    int threshold;
+
+    threshold = conf.divisor ? hw->samples / conf.divisor : 0;
+
+    if (audio_pt_lock (&esd->pt, AUDIO_FUNC)) {
+        return NULL;
+    }
+
+    for (;;) {
+        int incr, to_grab, wpos;
+
+        for (;;) {
+            if (esd->done) {
+                goto exit;
+            }
+
+            if (esd->dead > threshold) {
+                break;
+            }
+
+            if (audio_pt_wait (&esd->pt, AUDIO_FUNC)) {
+                goto exit;
+            }
+        }
+
+        incr = to_grab = esd->dead;
+        wpos = hw->wpos;
+
+        if (audio_pt_unlock (&esd->pt, AUDIO_FUNC)) {
+            return NULL;
+        }
+
+        while (to_grab) {
+            ssize_t nread;
+            int chunk = audio_MIN (to_grab, hw->samples - wpos);
+            void *buf = advance (esd->pcm_buf, wpos);
+
+        again:
+            nread = read (esd->fd, buf, chunk << hw->info.shift);
+            if (nread == -1) {
+                if (errno == EINTR || errno == EAGAIN) {
+                    goto again;
+                }
+                qesd_logerr (errno, "read failed\n");
+                return NULL;
+            }
+
+            if (nread != chunk << hw->info.shift) {
+                int rsamples = nread >> hw->info.shift;
+                int rbytes = rsamples << hw->info.shift;
+                if (rbytes != nread) {
+                    dolog ("warning: Misaligned write %d (requested %zd), "
+                           "alignment %d\n",
+                           rbytes, nread, hw->info.align + 1);
+                }
+                to_grab -= rsamples;
+                wpos = (wpos + rsamples) % hw->samples;
+                break;
+            }
+
+            hw->conv (hw->conv_buf + wpos, buf, nread >> hw->info.shift);
+            wpos = (wpos + chunk) % hw->samples;
+            to_grab -= chunk;
+        }
+
+        if (audio_pt_lock (&esd->pt, AUDIO_FUNC)) {
+            return NULL;
+        }
+
+        esd->wpos = wpos;
+        esd->dead -= incr;
+        esd->incr += incr;
+    }
+
+ exit:
+    audio_pt_unlock (&esd->pt, AUDIO_FUNC);
+    return NULL;
+}
+
+static int qesd_run_in (HWVoiceIn *hw)
+{
+    int live, incr, dead;
+    ESDVoiceIn *esd = (ESDVoiceIn *) hw;
+
+    if (audio_pt_lock (&esd->pt, AUDIO_FUNC)) {
+        return 0;
+    }
+
+    live = audio_pcm_hw_get_live_in (hw);
+    dead = hw->samples - live;
+    incr = audio_MIN (dead, esd->incr);
+    esd->incr -= incr;
+    esd->dead = dead - incr;
+    hw->wpos = esd->wpos;
+    if (esd->dead > 0) {
+        audio_pt_unlock_and_signal (&esd->pt, AUDIO_FUNC);
+    }
+    else {
+        audio_pt_unlock (&esd->pt, AUDIO_FUNC);
+    }
+    return incr;
+}
+
+static int qesd_read (SWVoiceIn *sw, void *buf, int len)
+{
+    return audio_pcm_sw_read (sw, buf, len);
+}
+
+static int qesd_init_in (HWVoiceIn *hw, struct audsettings *as)
+{
+    ESDVoiceIn *esd = (ESDVoiceIn *) hw;
+    struct audsettings obt_as = *as;
+    int esdfmt = ESD_STREAM | ESD_RECORD;
+
+    esdfmt |= (as->nchannels == 2) ? ESD_STEREO : ESD_MONO;
+    switch (as->fmt) {
+    case AUD_FMT_S8:
+    case AUD_FMT_U8:
+        esdfmt |= ESD_BITS8;
+        obt_as.fmt = AUD_FMT_U8;
+        break;
+
+    case AUD_FMT_S16:
+    case AUD_FMT_U16:
+        esdfmt |= ESD_BITS16;
+        obt_as.fmt = AUD_FMT_S16;
+        break;
+
+    case AUD_FMT_S32:
+    case AUD_FMT_U32:
+        dolog ("Will use 16 instead of 32 bit samples\n");
+        esdfmt |= ESD_BITS16;
+        obt_as.fmt = AUD_FMT_S16;
+        break;
+    }
+    obt_as.endianness = AUDIO_HOST_ENDIANNESS;
+
+    audio_pcm_init_info (&hw->info, &obt_as);
+
+    hw->samples = conf.samples;
+    esd->pcm_buf = audio_calloc (AUDIO_FUNC, hw->samples, 1 << hw->info.shift);
+    if (!esd->pcm_buf) {
+        dolog ("Could not allocate buffer (%d bytes)\n",
+               hw->samples << hw->info.shift);
+        return -1;
+    }
+
+    esd->fd = esd_record_stream (esdfmt, as->freq, conf.adc_host, NULL);
+    if (esd->fd < 0) {
+        qesd_logerr (errno, "esd_record_stream failed\n");
+        goto fail1;
+    }
+
+    if (audio_pt_init (&esd->pt, qesd_thread_in, esd, AUDIO_CAP, AUDIO_FUNC)) {
+        goto fail2;
+    }
+
+    return 0;
+
+ fail2:
+    if (close (esd->fd)) {
+        qesd_logerr (errno, "%s: close on esd socket(%d) failed\n",
+                     AUDIO_FUNC, esd->fd);
+    }
+    esd->fd = -1;
+
+ fail1:
+    g_free (esd->pcm_buf);
+    esd->pcm_buf = NULL;
+    return -1;
+}
+
+static void qesd_fini_in (HWVoiceIn *hw)
+{
+    void *ret;
+    ESDVoiceIn *esd = (ESDVoiceIn *) hw;
+
+    audio_pt_lock (&esd->pt, AUDIO_FUNC);
+    esd->done = 1;
+    audio_pt_unlock_and_signal (&esd->pt, AUDIO_FUNC);
+    audio_pt_join (&esd->pt, &ret, AUDIO_FUNC);
+
+    if (esd->fd >= 0) {
+        if (close (esd->fd)) {
+            qesd_logerr (errno, "failed to close esd socket\n");
+        }
+        esd->fd = -1;
+    }
+
+    audio_pt_fini (&esd->pt, AUDIO_FUNC);
+
+    g_free (esd->pcm_buf);
+    esd->pcm_buf = NULL;
+}
+
+static int qesd_ctl_in (HWVoiceIn *hw, int cmd, ...)
+{
+    (void) hw;
+    (void) cmd;
+    return 0;
+}
+
+/* common */
+static void *qesd_audio_init (void)
+{
+    return &conf;
+}
+
+static void qesd_audio_fini (void *opaque)
+{
+    (void) opaque;
+    ldebug ("esd_fini");
+}
+
+struct audio_option qesd_options[] = {
+    {
+        .name  = "SAMPLES",
+        .tag   = AUD_OPT_INT,
+        .valp  = &conf.samples,
+        .descr = "buffer size in samples"
+    },
+    {
+        .name  = "DIVISOR",
+        .tag   = AUD_OPT_INT,
+        .valp  = &conf.divisor,
+        .descr = "threshold divisor"
+    },
+    {
+        .name  = "DAC_HOST",
+        .tag   = AUD_OPT_STR,
+        .valp  = &conf.dac_host,
+        .descr = "playback host"
+    },
+    {
+        .name  = "ADC_HOST",
+        .tag   = AUD_OPT_STR,
+        .valp  = &conf.adc_host,
+        .descr = "capture host"
+    },
+    { /* End of list */ }
+};
+
+static struct audio_pcm_ops qesd_pcm_ops = {
+    .init_out = qesd_init_out,
+    .fini_out = qesd_fini_out,
+    .run_out  = qesd_run_out,
+    .write    = qesd_write,
+    .ctl_out  = qesd_ctl_out,
+
+    .init_in  = qesd_init_in,
+    .fini_in  = qesd_fini_in,
+    .run_in   = qesd_run_in,
+    .read     = qesd_read,
+    .ctl_in   = qesd_ctl_in,
+};
+
+struct audio_driver esd_audio_driver = {
+    .name           = "esd",
+    .descr          = "http://en.wikipedia.org/wiki/Esound",
+    .options        = qesd_options,
+    .init           = qesd_audio_init,
+    .fini           = qesd_audio_fini,
+    .pcm_ops        = &qesd_pcm_ops,
+    .can_be_default = 0,
+    .max_voices_out = INT_MAX,
+    .max_voices_in  = INT_MAX,
+    .voice_size_out = sizeof (ESDVoiceOut),
+    .voice_size_in  = sizeof (ESDVoiceIn)
+};
@@ -0,0 +1,685 @@
+/*
+ * QEMU FMOD audio driver
+ *
+ * Copyright (c) 2004-2005 Vassili Karpov (malc)
+ *
+ * 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 <fmod.h>
+#include <fmod_errors.h>
+#include "qemu-common.h"
+#include "audio.h"
+
+#define AUDIO_CAP "fmod"
+#include "audio_int.h"
+
+typedef struct FMODVoiceOut {
+    HWVoiceOut hw;
+    unsigned int old_pos;
+    FSOUND_SAMPLE *fmod_sample;
+    int channel;
+} FMODVoiceOut;
+
+typedef struct FMODVoiceIn {
+    HWVoiceIn hw;
+    FSOUND_SAMPLE *fmod_sample;
+} FMODVoiceIn;
+
+static struct {
+    const char *drvname;
+    int nb_samples;
+    int freq;
+    int nb_channels;
+    int bufsize;
+    int broken_adc;
+} conf = {
+    .nb_samples  = 2048 * 2,
+    .freq        = 44100,
+    .nb_channels = 2,
+};
+
+static void GCC_FMT_ATTR (1, 2) fmod_logerr (const char *fmt, ...)
+{
+    va_list ap;
+
+    va_start (ap, fmt);
+    AUD_vlog (AUDIO_CAP, fmt, ap);
+    va_end (ap);
+
+    AUD_log (AUDIO_CAP, "Reason: %s\n",
+             FMOD_ErrorString (FSOUND_GetError ()));
+}
+
+static void GCC_FMT_ATTR (2, 3) fmod_logerr2 (
+    const char *typ,
+    const char *fmt,
+    ...
+    )
+{
+    va_list ap;
+
+    AUD_log (AUDIO_CAP, "Could not initialize %s\n", typ);
+
+    va_start (ap, fmt);
+    AUD_vlog (AUDIO_CAP, fmt, ap);
+    va_end (ap);
+
+    AUD_log (AUDIO_CAP, "Reason: %s\n",
+             FMOD_ErrorString (FSOUND_GetError ()));
+}
+
+static int fmod_write (SWVoiceOut *sw, void *buf, int len)
+{
+    return audio_pcm_sw_write (sw, buf, len);
+}
+
+static void fmod_clear_sample (FMODVoiceOut *fmd)
+{
+    HWVoiceOut *hw = &fmd->hw;
+    int status;
+    void *p1 = 0, *p2 = 0;
+    unsigned int len1 = 0, len2 = 0;
+
+    status = FSOUND_Sample_Lock (
+        fmd->fmod_sample,
+        0,
+        hw->samples << hw->info.shift,
+        &p1,
+        &p2,
+        &len1,
+        &len2
+        );
+
+    if (!status) {
+        fmod_logerr ("Failed to lock sample\n");
+        return;
+    }
+
+    if ((len1 & hw->info.align) || (len2 & hw->info.align)) {
+        dolog ("Lock returned misaligned length %d, %d, alignment %d\n",
+               len1, len2, hw->info.align + 1);
+        goto fail;
+    }
+
+    if ((len1 + len2) - (hw->samples << hw->info.shift)) {
+        dolog ("Lock returned incomplete length %d, %d\n",
+               len1 + len2, hw->samples << hw->info.shift);
+        goto fail;
+    }
+
+    audio_pcm_info_clear_buf (&hw->info, p1, hw->samples);
+
+ fail:
+    status = FSOUND_Sample_Unlock (fmd->fmod_sample, p1, p2, len1, len2);
+    if (!status) {
+        fmod_logerr ("Failed to unlock sample\n");
+    }
+}
+
+static void fmod_write_sample (HWVoiceOut *hw, uint8_t *dst, int dst_len)
+{
+    int src_len1 = dst_len;
+    int src_len2 = 0;
+    int pos = hw->rpos + dst_len;
+    struct st_sample *src1 = hw->mix_buf + hw->rpos;
+    struct st_sample *src2 = NULL;
+
+    if (pos > hw->samples) {
+        src_len1 = hw->samples - hw->rpos;
+        src2 = hw->mix_buf;
+        src_len2 = dst_len - src_len1;
+        pos = src_len2;
+    }
+
+    if (src_len1) {
+        hw->clip (dst, src1, src_len1);
+    }
+
+    if (src_len2) {
+        dst = advance (dst, src_len1 << hw->info.shift);
+        hw->clip (dst, src2, src_len2);
+    }
+
+    hw->rpos = pos % hw->samples;
+}
+
+static int fmod_unlock_sample (FSOUND_SAMPLE *sample, void *p1, void *p2,
+                               unsigned int blen1, unsigned int blen2)
+{
+    int status = FSOUND_Sample_Unlock (sample, p1, p2, blen1, blen2);
+    if (!status) {
+        fmod_logerr ("Failed to unlock sample\n");
+        return -1;
+    }
+    return 0;
+}
+
+static int fmod_lock_sample (
+    FSOUND_SAMPLE *sample,
+    struct audio_pcm_info *info,
+    int pos,
+    int len,
+    void **p1,
+    void **p2,
+    unsigned int *blen1,
+    unsigned int *blen2
+    )
+{
+    int status;
+
+    status = FSOUND_Sample_Lock (
+        sample,
+        pos << info->shift,
+        len << info->shift,
+        p1,
+        p2,
+        blen1,
+        blen2
+        );
+
+    if (!status) {
+        fmod_logerr ("Failed to lock sample\n");
+        return -1;
+    }
+
+    if ((*blen1 & info->align) || (*blen2 & info->align)) {
+        dolog ("Lock returned misaligned length %d, %d, alignment %d\n",
+               *blen1, *blen2, info->align + 1);
+
+        fmod_unlock_sample (sample, *p1, *p2, *blen1, *blen2);
+
+        *p1 = NULL - 1;
+        *p2 = NULL - 1;
+        *blen1 = ~0U;
+        *blen2 = ~0U;
+        return -1;
+    }
+
+    if (!*p1 && *blen1) {
+        dolog ("warning: !p1 && blen1=%d\n", *blen1);
+        *blen1 = 0;
+    }
+
+    if (!p2 && *blen2) {
+        dolog ("warning: !p2 && blen2=%d\n", *blen2);
+        *blen2 = 0;
+    }
+
+    return 0;
+}
+
+static int fmod_run_out (HWVoiceOut *hw, int live)
+{
+    FMODVoiceOut *fmd = (FMODVoiceOut *) hw;
+    int decr;
+    void *p1 = 0, *p2 = 0;
+    unsigned int blen1 = 0, blen2 = 0;
+    unsigned int len1 = 0, len2 = 0;
+
+    if (!hw->pending_disable) {
+        return 0;
+    }
+
+    decr = live;
+
+    if (fmd->channel >= 0) {
+        int len = decr;
+        int old_pos = fmd->old_pos;
+        int ppos = FSOUND_GetCurrentPosition (fmd->channel);
+
+        if (ppos == old_pos || !ppos) {
+            return 0;
+        }
+
+        if ((old_pos < ppos) && ((old_pos + len) > ppos)) {
+            len = ppos - old_pos;
+        }
+        else {
+            if ((old_pos > ppos) && ((old_pos + len) > (ppos + hw->samples))) {
+                len = hw->samples - old_pos + ppos;
+            }
+        }
+        decr = len;
+
+        if (audio_bug (AUDIO_FUNC, decr < 0)) {
+            dolog ("decr=%d live=%d ppos=%d old_pos=%d len=%d\n",
+                   decr, live, ppos, old_pos, len);
+            return 0;
+        }
+    }
+
+
+    if (!decr) {
+        return 0;
+    }
+
+    if (fmod_lock_sample (fmd->fmod_sample, &fmd->hw.info,
+                          fmd->old_pos, decr,
+                          &p1, &p2,
+                          &blen1, &blen2)) {
+        return 0;
+    }
+
+    len1 = blen1 >> hw->info.shift;
+    len2 = blen2 >> hw->info.shift;
+    ldebug ("%p %p %d %d %d %d\n", p1, p2, len1, len2, blen1, blen2);
+    decr = len1 + len2;
+
+    if (p1 && len1) {
+        fmod_write_sample (hw, p1, len1);
+    }
+
+    if (p2 && len2) {
+        fmod_write_sample (hw, p2, len2);
+    }
+
+    fmod_unlock_sample (fmd->fmod_sample, p1, p2, blen1, blen2);
+
+    fmd->old_pos = (fmd->old_pos + decr) % hw->samples;
+    return decr;
+}
+
+static int aud_to_fmodfmt (audfmt_e fmt, int stereo)
+{
+    int mode = FSOUND_LOOP_NORMAL;
+
+    switch (fmt) {
+    case AUD_FMT_S8:
+        mode |= FSOUND_SIGNED | FSOUND_8BITS;
+        break;
+
+    case AUD_FMT_U8:
+        mode |= FSOUND_UNSIGNED | FSOUND_8BITS;
+        break;
+
+    case AUD_FMT_S16:
+        mode |= FSOUND_SIGNED | FSOUND_16BITS;
+        break;
+
+    case AUD_FMT_U16:
+        mode |= FSOUND_UNSIGNED | FSOUND_16BITS;
+        break;
+
+    default:
+        dolog ("Internal logic error: Bad audio format %d\n", fmt);
+#ifdef DEBUG_FMOD
+        abort ();
+#endif
+        mode |= FSOUND_8BITS;
+    }
+    mode |= stereo ? FSOUND_STEREO : FSOUND_MONO;
+    return mode;
+}
+
+static void fmod_fini_out (HWVoiceOut *hw)
+{
+    FMODVoiceOut *fmd = (FMODVoiceOut *) hw;
+
+    if (fmd->fmod_sample) {
+        FSOUND_Sample_Free (fmd->fmod_sample);
+        fmd->fmod_sample = 0;
+
+        if (fmd->channel >= 0) {
+            FSOUND_StopSound (fmd->channel);
+        }
+    }
+}
+
+static int fmod_init_out (HWVoiceOut *hw, struct audsettings *as)
+{
+    int mode, channel;
+    FMODVoiceOut *fmd = (FMODVoiceOut *) hw;
+    struct audsettings obt_as = *as;
+
+    mode = aud_to_fmodfmt (as->fmt, as->nchannels == 2 ? 1 : 0);
+    fmd->fmod_sample = FSOUND_Sample_Alloc (
+        FSOUND_FREE,            /* index */
+        conf.nb_samples,        /* length */
+        mode,                   /* mode */
+        as->freq,               /* freq */
+        255,                    /* volume */
+        128,                    /* pan */
+        255                     /* priority */
+        );
+
+    if (!fmd->fmod_sample) {
+        fmod_logerr2 ("DAC", "Failed to allocate FMOD sample\n");
+        return -1;
+    }
+
+    channel = FSOUND_PlaySoundEx (FSOUND_FREE, fmd->fmod_sample, 0, 1);
+    if (channel < 0) {
+        fmod_logerr2 ("DAC", "Failed to start playing sound\n");
+        FSOUND_Sample_Free (fmd->fmod_sample);
+        return -1;
+    }
+    fmd->channel = channel;
+
+    /* FMOD always operates on little endian frames? */
+    obt_as.endianness = 0;
+    audio_pcm_init_info (&hw->info, &obt_as);
+    hw->samples = conf.nb_samples;
+    return 0;
+}
+
+static int fmod_ctl_out (HWVoiceOut *hw, int cmd, ...)
+{
+    int status;
+    FMODVoiceOut *fmd = (FMODVoiceOut *) hw;
+
+    switch (cmd) {
+    case VOICE_ENABLE:
+        fmod_clear_sample (fmd);
+        status = FSOUND_SetPaused (fmd->channel, 0);
+        if (!status) {
+            fmod_logerr ("Failed to resume channel %d\n", fmd->channel);
+        }
+        break;
+
+    case VOICE_DISABLE:
+        status = FSOUND_SetPaused (fmd->channel, 1);
+        if (!status) {
+            fmod_logerr ("Failed to pause channel %d\n", fmd->channel);
+        }
+        break;
+    }
+    return 0;
+}
+
+static int fmod_init_in (HWVoiceIn *hw, struct audsettings *as)
+{
+    int mode;
+    FMODVoiceIn *fmd = (FMODVoiceIn *) hw;
+    struct audsettings obt_as = *as;
+
+    if (conf.broken_adc) {
+        return -1;
+    }
+
+    mode = aud_to_fmodfmt (as->fmt, as->nchannels == 2 ? 1 : 0);
+    fmd->fmod_sample = FSOUND_Sample_Alloc (
+        FSOUND_FREE,            /* index */
+        conf.nb_samples,        /* length */
+        mode,                   /* mode */
+        as->freq,               /* freq */
+        255,                    /* volume */
+        128,                    /* pan */
+        255                     /* priority */
+        );
+
+    if (!fmd->fmod_sample) {
+        fmod_logerr2 ("ADC", "Failed to allocate FMOD sample\n");
+        return -1;
+    }
+
+    /* FMOD always operates on little endian frames? */
+    obt_as.endianness = 0;
+    audio_pcm_init_info (&hw->info, &obt_as);
+    hw->samples = conf.nb_samples;
+    return 0;
+}
+
+static void fmod_fini_in (HWVoiceIn *hw)
+{
+    FMODVoiceIn *fmd = (FMODVoiceIn *) hw;
+
+    if (fmd->fmod_sample) {
+        FSOUND_Record_Stop ();
+        FSOUND_Sample_Free (fmd->fmod_sample);
+        fmd->fmod_sample = 0;
+    }
+}
+
+static int fmod_run_in (HWVoiceIn *hw)
+{
+    FMODVoiceIn *fmd = (FMODVoiceIn *) hw;
+    int hwshift = hw->info.shift;
+    int live, dead, new_pos, len;
+    unsigned int blen1 = 0, blen2 = 0;
+    unsigned int len1, len2;
+    unsigned int decr;
+    void *p1, *p2;
+
+    live = audio_pcm_hw_get_live_in (hw);
+    dead = hw->samples - live;
+    if (!dead) {
+        return 0;
+    }
+
+    new_pos = FSOUND_Record_GetPosition ();
+    if (new_pos < 0) {
+        fmod_logerr ("Could not get recording position\n");
+        return 0;
+    }
+
+    len = audio_ring_dist (new_pos,  hw->wpos, hw->samples);
+    if (!len) {
+        return 0;
+    }
+    len = audio_MIN (len, dead);
+
+    if (fmod_lock_sample (fmd->fmod_sample, &fmd->hw.info,
+                          hw->wpos, len,
+                          &p1, &p2,
+                          &blen1, &blen2)) {
+        return 0;
+    }
+
+    len1 = blen1 >> hwshift;
+    len2 = blen2 >> hwshift;
+    decr = len1 + len2;
+
+    if (p1 && blen1) {
+        hw->conv (hw->conv_buf + hw->wpos, p1, len1);
+    }
+    if (p2 && len2) {
+        hw->conv (hw->conv_buf, p2, len2);
+    }
+
+    fmod_unlock_sample (fmd->fmod_sample, p1, p2, blen1, blen2);
+    hw->wpos = (hw->wpos + decr) % hw->samples;
+    return decr;
+}
+
+static struct {
+    const char *name;
+    int type;
+} drvtab[] = {
+    { .name = "none",   .type = FSOUND_OUTPUT_NOSOUND },
+#ifdef _WIN32
+    { .name = "winmm",  .type = FSOUND_OUTPUT_WINMM   },
+    { .name = "dsound", .type = FSOUND_OUTPUT_DSOUND  },
+    { .name = "a3d",    .type = FSOUND_OUTPUT_A3D     },
+    { .name = "asio",   .type = FSOUND_OUTPUT_ASIO    },
+#endif
+#ifdef __linux__
+    { .name = "oss",    .type = FSOUND_OUTPUT_OSS     },
+    { .name = "alsa",   .type = FSOUND_OUTPUT_ALSA    },
+    { .name = "esd",    .type = FSOUND_OUTPUT_ESD     },
+#endif
+#ifdef __APPLE__
+    { .name = "mac",    .type = FSOUND_OUTPUT_MAC     },
+#endif
+#if 0
+    { .name = "xbox",   .type = FSOUND_OUTPUT_XBOX    },
+    { .name = "ps2",    .type = FSOUND_OUTPUT_PS2     },
+    { .name = "gcube",  .type = FSOUND_OUTPUT_GC      },
+#endif
+    { .name = "none-realtime", .type = FSOUND_OUTPUT_NOSOUND_NONREALTIME }
+};
+
+static void *fmod_audio_init (void)
+{
+    size_t i;
+    double ver;
+    int status;
+    int output_type = -1;
+    const char *drv = conf.drvname;
+
+    ver = FSOUND_GetVersion ();
+    if (ver < FMOD_VERSION) {
+        dolog ("Wrong FMOD version %f, need at least %f\n", ver, FMOD_VERSION);
+        return NULL;
+    }
+
+#ifdef __linux__
+    if (ver < 3.75) {
+        dolog ("FMOD before 3.75 has bug preventing ADC from working\n"
+               "ADC will be disabled.\n");
+        conf.broken_adc = 1;
+    }
+#endif
+
+    if (drv) {
+        int found = 0;
+        for (i = 0; i < ARRAY_SIZE (drvtab); i++) {
+            if (!strcmp (drv, drvtab[i].name)) {
+                output_type = drvtab[i].type;
+                found = 1;
+                break;
+            }
+        }
+        if (!found) {
+            dolog ("Unknown FMOD driver `%s'\n", drv);
+            dolog ("Valid drivers:\n");
+            for (i = 0; i < ARRAY_SIZE (drvtab); i++) {
+                dolog ("  %s\n", drvtab[i].name);
+            }
+        }
+    }
+
+    if (output_type != -1) {
+        status = FSOUND_SetOutput (output_type);
+        if (!status) {
+            fmod_logerr ("FSOUND_SetOutput(%d) failed\n", output_type);
+            return NULL;
+        }
+    }
+
+    if (conf.bufsize) {
+        status = FSOUND_SetBufferSize (conf.bufsize);
+        if (!status) {
+            fmod_logerr ("FSOUND_SetBufferSize (%d) failed\n", conf.bufsize);
+        }
+    }
+
+    status = FSOUND_Init (conf.freq, conf.nb_channels, 0);
+    if (!status) {
+        fmod_logerr ("FSOUND_Init failed\n");
+        return NULL;
+    }
+
+    return &conf;
+}
+
+static int fmod_read (SWVoiceIn *sw, void *buf, int size)
+{
+    return audio_pcm_sw_read (sw, buf, size);
+}
+
+static int fmod_ctl_in (HWVoiceIn *hw, int cmd, ...)
+{
+    int status;
+    FMODVoiceIn *fmd = (FMODVoiceIn *) hw;
+
+    switch (cmd) {
+    case VOICE_ENABLE:
+        status = FSOUND_Record_StartSample (fmd->fmod_sample, 1);
+        if (!status) {
+            fmod_logerr ("Failed to start recording\n");
+        }
+        break;
+
+    case VOICE_DISABLE:
+        status = FSOUND_Record_Stop ();
+        if (!status) {
+            fmod_logerr ("Failed to stop recording\n");
+        }
+        break;
+    }
+    return 0;
+}
+
+static void fmod_audio_fini (void *opaque)
+{
+    (void) opaque;
+    FSOUND_Close ();
+}
+
+static struct audio_option fmod_options[] = {
+    {
+        .name  = "DRV",
+        .tag   = AUD_OPT_STR,
+        .valp  = &conf.drvname,
+        .descr = "FMOD driver"
+    },
+    {
+        .name  = "FREQ",
+        .tag   = AUD_OPT_INT,
+        .valp  = &conf.freq,
+        .descr = "Default frequency"
+    },
+    {
+        .name  = "SAMPLES",
+        .tag   = AUD_OPT_INT,
+        .valp  = &conf.nb_samples,
+        .descr = "Buffer size in samples"
+    },
+    {
+        .name  = "CHANNELS",
+        .tag   = AUD_OPT_INT,
+        .valp  = &conf.nb_channels,
+        .descr = "Number of default channels (1 - mono, 2 - stereo)"
+    },
+    {
+        .name  = "BUFSIZE",
+        .tag   = AUD_OPT_INT,
+        .valp  = &conf.bufsize,
+        .descr = "(undocumented)"
+    },
+    { /* End of list */ }
+};
+
+static struct audio_pcm_ops fmod_pcm_ops = {
+    .init_out = fmod_init_out,
+    .fini_out = fmod_fini_out,
+    .run_out  = fmod_run_out,
+    .write    = fmod_write,
+    .ctl_out  = fmod_ctl_out,
+
+    .init_in  = fmod_init_in,
+    .fini_in  = fmod_fini_in,
+    .run_in   = fmod_run_in,
+    .read     = fmod_read,
+    .ctl_in   = fmod_ctl_in
+};
+
+struct audio_driver fmod_audio_driver = {
+    .name           = "fmod",
+    .descr          = "FMOD 3.xx http://www.fmod.org",
+    .options        = fmod_options,
+    .init           = fmod_audio_init,
+    .fini           = fmod_audio_fini,
+    .pcm_ops        = &fmod_pcm_ops,
+    .can_be_default = 1,
+    .max_voices_out = INT_MAX,
+    .max_voices_in  = INT_MAX,
+    .voice_size_out = sizeof (FMODVoiceOut),
+    .voice_size_in  = sizeof (FMODVoiceIn)
+};
@@ -63,7 +63,7 @@ static int no_write (SWVoiceOut *sw, void *buf, int len)
    return audio_pcm_sw_write (sw, buf, len);
 }

-static int no_init_out(HWVoiceOut *hw, struct audsettings *as, void *drv_opaque)
+static int no_init_out (HWVoiceOut *hw, struct audsettings *as)
 {
    audio_pcm_init_info (&hw->info, as);
    hw->samples = 1024;
@@ -82,7 +82,7 @@ static int no_ctl_out (HWVoiceOut *hw, int cmd, ...)
    return 0;
 }

-static int no_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
+static int no_init_in (HWVoiceIn *hw, struct audsettings *as)
 {
    audio_pcm_init_info (&hw->info, as);
    hw->samples = 1024;
@@ -30,7 +30,6 @@
 #include "qemu/main-loop.h"
 #include "qemu/host-utils.h"
 #include "audio.h"
-#include "trace.h"

 #define AUDIO_CAP "oss"
 #include "audio_int.h"
@@ -39,16 +38,6 @@
 #define USE_DSP_POLICY
 #endif

-typedef struct OSSConf {
-    int try_mmap;
-    int nfrags;
-    int fragsize;
-    const char *devpath_out;
-    const char *devpath_in;
-    int exclusive;
-    int policy;
-} OSSConf;
-
 typedef struct OSSVoiceOut {
    HWVoiceOut hw;
    void *pcm_buf;
@@ -58,7 +47,6 @@ typedef struct OSSVoiceOut {
    int fragsize;
    int mmapped;
    int pending;
-    OSSConf *conf;
 } OSSVoiceOut;

 typedef struct OSSVoiceIn {
@@ -67,9 +55,28 @@ typedef struct OSSVoiceIn {
    int fd;
    int nfrags;
    int fragsize;
-    OSSConf *conf;
 } OSSVoiceIn;

+static struct {
+    int try_mmap;
+    int nfrags;
+    int fragsize;
+    const char *devpath_out;
+    const char *devpath_in;
+    int debug;
+    int exclusive;
+    int policy;
+} conf = {
+    .try_mmap = 0,
+    .nfrags = 4,
+    .fragsize = 4096,
+    .devpath_out = "/dev/dsp",
+    .devpath_in = "/dev/dsp",
+    .debug = 0,
+    .exclusive = 0,
+    .policy = 5
+};
+
 struct oss_params {
    int freq;
    audfmt_e fmt;
@@ -131,18 +138,18 @@ static void oss_helper_poll_in (void *opaque)
    audio_run ("oss_poll_in");
 }

-static void oss_poll_out (HWVoiceOut *hw)
+static int oss_poll_out (HWVoiceOut *hw)
 {
    OSSVoiceOut *oss = (OSSVoiceOut *) hw;

-    qemu_set_fd_handler (oss->fd, NULL, oss_helper_poll_out, NULL);
+    return qemu_set_fd_handler (oss->fd, NULL, oss_helper_poll_out, NULL);
 }

-static void oss_poll_in (HWVoiceIn *hw)
+static int oss_poll_in (HWVoiceIn *hw)
 {
    OSSVoiceIn *oss = (OSSVoiceIn *) hw;

-    qemu_set_fd_handler (oss->fd, oss_helper_poll_in, NULL, NULL);
+    return qemu_set_fd_handler (oss->fd, oss_helper_poll_in, NULL, NULL);
 }

 static int oss_write (SWVoiceOut *sw, void *buf, int len)
@@ -265,18 +272,18 @@ static int oss_get_version (int fd, int *version, const char *typ)
 #endif

 static int oss_open (int in, struct oss_params *req,
-                     struct oss_params *obt, int *pfd, OSSConf* conf)
+                     struct oss_params *obt, int *pfd)
 {
    int fd;
-    int oflags = conf->exclusive ? O_EXCL : 0;
+    int oflags = conf.exclusive ? O_EXCL : 0;
    audio_buf_info abinfo;
    int fmt, freq, nchannels;
    int setfragment = 1;
-    const char *dspname = in ? conf->devpath_in : conf->devpath_out;
+    const char *dspname = in ? conf.devpath_in : conf.devpath_out;
    const char *typ = in ? "ADC" : "DAC";

    /* Kludge needed to have working mmap on Linux */
-    oflags |= conf->try_mmap ? O_RDWR : (in ? O_RDONLY : O_WRONLY);
+    oflags |= conf.try_mmap ? O_RDWR : (in ? O_RDONLY : O_WRONLY);

    fd = open (dspname, oflags | O_NONBLOCK);
    if (-1 == fd) {
@@ -310,18 +317,20 @@ static int oss_open (int in, struct oss_params *req,
    }

 #ifdef USE_DSP_POLICY
-    if (conf->policy >= 0) {
+    if (conf.policy >= 0) {
        int version;

        if (!oss_get_version (fd, &version, typ)) {
-            trace_oss_version(version);
+            if (conf.debug) {
+                dolog ("OSS version = %#x\n", version);
+            }

            if (version >= 0x040000) {
-                int policy = conf->policy;
+                int policy = conf.policy;
                if (ioctl (fd, SNDCTL_DSP_POLICY, &policy)) {
                    oss_logerr2 (errno, typ,
                                 "Failed to set timing policy to %d\n",
-                                 conf->policy);
+                                 conf.policy);
                    goto err;
                }
                setfragment = 0;
@@ -449,12 +458,19 @@ static int oss_run_out (HWVoiceOut *hw, int live)
        }

        if (abinfo.bytes > bufsize) {
-            trace_oss_invalid_available_size(abinfo.bytes, bufsize);
+            if (conf.debug) {
+                dolog ("warning: Invalid available size, size=%d bufsize=%d\n"
+                       "please report your OS/audio hw to av1474@comtv.ru\n",
+                       abinfo.bytes, bufsize);
+            }
            abinfo.bytes = bufsize;
        }

        if (abinfo.bytes < 0) {
-            trace_oss_invalid_available_size(abinfo.bytes, bufsize);
+            if (conf.debug) {
+                dolog ("warning: Invalid available size, size=%d bufsize=%d\n",
+                       abinfo.bytes, bufsize);
+            }
            return 0;
        }

@@ -494,8 +510,7 @@ static void oss_fini_out (HWVoiceOut *hw)
    }
 }

-static int oss_init_out(HWVoiceOut *hw, struct audsettings *as,
-                        void *drv_opaque)
+static int oss_init_out (HWVoiceOut *hw, struct audsettings *as)
 {
    OSSVoiceOut *oss = (OSSVoiceOut *) hw;
    struct oss_params req, obt;
@@ -504,17 +519,16 @@ static int oss_init_out(HWVoiceOut *hw, struct audsettings *as,
    int fd;
    audfmt_e effective_fmt;
    struct audsettings obt_as;
-    OSSConf *conf = drv_opaque;

    oss->fd = -1;

    req.fmt = aud_to_ossfmt (as->fmt, as->endianness);
    req.freq = as->freq;
    req.nchannels = as->nchannels;
-    req.fragsize = conf->fragsize;
-    req.nfrags = conf->nfrags;
+    req.fragsize = conf.fragsize;
+    req.nfrags = conf.nfrags;

-    if (oss_open (0, &req, &obt, &fd, conf)) {
+    if (oss_open (0, &req, &obt, &fd)) {
        return -1;
    }

@@ -541,7 +555,7 @@ static int oss_init_out(HWVoiceOut *hw, struct audsettings *as,
    hw->samples = (obt.nfrags * obt.fragsize) >> hw->info.shift;

    oss->mmapped = 0;
-    if (conf->try_mmap) {
+    if (conf.try_mmap) {
        oss->pcm_buf = mmap (
            NULL,
            hw->samples << hw->info.shift,
@@ -601,7 +615,6 @@ static int oss_init_out(HWVoiceOut *hw, struct audsettings *as,
    }

    oss->fd = fd;
-    oss->conf = conf;
    return 0;
 }

@@ -621,8 +634,7 @@ static int oss_ctl_out (HWVoiceOut *hw, int cmd, ...)
            va_end (ap);

            ldebug ("enabling voice\n");
-            if (poll_mode) {
-                oss_poll_out (hw);
+            if (poll_mode && oss_poll_out (hw)) {
                poll_mode = 0;
            }
            hw->poll_mode = poll_mode;
@@ -664,7 +676,7 @@ static int oss_ctl_out (HWVoiceOut *hw, int cmd, ...)
    return 0;
 }

-static int oss_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
+static int oss_init_in (HWVoiceIn *hw, struct audsettings *as)
 {
    OSSVoiceIn *oss = (OSSVoiceIn *) hw;
    struct oss_params req, obt;
@@ -673,16 +685,15 @@ static int oss_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
    int fd;
    audfmt_e effective_fmt;
    struct audsettings obt_as;
-    OSSConf *conf = drv_opaque;

    oss->fd = -1;

    req.fmt = aud_to_ossfmt (as->fmt, as->endianness);
    req.freq = as->freq;
    req.nchannels = as->nchannels;
-    req.fragsize = conf->fragsize;
-    req.nfrags = conf->nfrags;
-    if (oss_open (1, &req, &obt, &fd, conf)) {
+    req.fragsize = conf.fragsize;
+    req.nfrags = conf.nfrags;
+    if (oss_open (1, &req, &obt, &fd)) {
        return -1;
    }

@@ -716,7 +727,6 @@ static int oss_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
    }

    oss->fd = fd;
-    oss->conf = conf;
    return 0;
 }

@@ -818,8 +828,7 @@ static int oss_ctl_in (HWVoiceIn *hw, int cmd, ...)
            poll_mode = va_arg (ap, int);
            va_end (ap);

-            if (poll_mode) {
-                oss_poll_in (hw);
+            if (poll_mode && oss_poll_in (hw)) {
                poll_mode = 0;
            }
            hw->poll_mode = poll_mode;
@@ -836,79 +845,71 @@ static int oss_ctl_in (HWVoiceIn *hw, int cmd, ...)
    return 0;
 }

-static OSSConf glob_conf = {
-    .try_mmap = 0,
-    .nfrags = 4,
-    .fragsize = 4096,
-    .devpath_out = "/dev/dsp",
-    .devpath_in = "/dev/dsp",
-    .exclusive = 0,
-    .policy = 5
-};
-
 static void *oss_audio_init (void)
 {
-    OSSConf *conf = g_malloc(sizeof(OSSConf));
-    *conf = glob_conf;
-
-    if (access(conf->devpath_in, R_OK | W_OK) < 0 ||
-        access(conf->devpath_out, R_OK | W_OK) < 0) {
-        g_free(conf);
+    if (access(conf.devpath_in, R_OK | W_OK) < 0 ||
+        access(conf.devpath_out, R_OK | W_OK) < 0) {
        return NULL;
    }
-    return conf;
+    return &conf;
 }

 static void oss_audio_fini (void *opaque)
 {
-    g_free(opaque);
+    (void) opaque;
 }

 static struct audio_option oss_options[] = {
    {
        .name  = "FRAGSIZE",
        .tag   = AUD_OPT_INT,
-        .valp  = &glob_conf.fragsize,
+        .valp  = &conf.fragsize,
        .descr = "Fragment size in bytes"
    },
    {
        .name  = "NFRAGS",
        .tag   = AUD_OPT_INT,
-        .valp  = &glob_conf.nfrags,
+        .valp  = &conf.nfrags,
        .descr = "Number of fragments"
    },
    {
        .name  = "MMAP",
        .tag   = AUD_OPT_BOOL,
-        .valp  = &glob_conf.try_mmap,
+        .valp  = &conf.try_mmap,
        .descr = "Try using memory mapped access"
    },
    {
        .name  = "DAC_DEV",
        .tag   = AUD_OPT_STR,
-        .valp  = &glob_conf.devpath_out,
+        .valp  = &conf.devpath_out,
        .descr = "Path to DAC device"
    },
    {
        .name  = "ADC_DEV",
        .tag   = AUD_OPT_STR,
-        .valp  = &glob_conf.devpath_in,
+        .valp  = &conf.devpath_in,
        .descr = "Path to ADC device"
    },
    {
        .name  = "EXCLUSIVE",
        .tag   = AUD_OPT_BOOL,
-        .valp  = &glob_conf.exclusive,
+        .valp  = &conf.exclusive,
        .descr = "Open device in exclusive mode (vmix wont work)"
    },
 #ifdef USE_DSP_POLICY
    {
        .name  = "POLICY",
        .tag   = AUD_OPT_INT,
-        .valp  = &glob_conf.policy,
+        .valp  = &conf.policy,
        .descr = "Set the timing policy of the device, -1 to use fragment mode",
    },
 #endif
+    {
+        .name  = "DEBUG",
+        .tag   = AUD_OPT_BOOL,
+        .valp  = &conf.debug,
+        .descr = "Turn on some debugging messages"
+    },
    { /* End of list */ }
 };

@@ -8,19 +8,6 @@
 #include "audio_int.h"
 #include "audio_pt_int.h"

-typedef struct {
-    int samples;
-    char *server;
-    char *sink;
-    char *source;
-} PAConf;
-
-typedef struct {
-    PAConf conf;
-    pa_threaded_mainloop *mainloop;
-    pa_context *context;
-} paaudio;
-
 typedef struct {
    HWVoiceOut hw;
    int done;
@@ -30,7 +17,6 @@ typedef struct {
    pa_stream *stream;
    void *pcm_buf;
    struct audio_pt pt;
-    paaudio *g;
 } PAVoiceOut;

 typedef struct {
@@ -44,10 +30,20 @@ typedef struct {
    struct audio_pt pt;
    const void *read_data;
    size_t read_index, read_length;
-    paaudio *g;
 } PAVoiceIn;

-static void qpa_audio_fini(void *opaque);
+typedef struct {
+    int samples;
+    char *server;
+    char *sink;
+    char *source;
+    pa_threaded_mainloop *mainloop;
+    pa_context *context;
+} paaudio;
+
+static paaudio glob_paaudio = {
+    .samples = 4096,
+};

 static void GCC_FMT_ATTR (2, 3) qpa_logerr (int err, const char *fmt, ...)
 {
@@ -110,7 +106,7 @@ static inline int PA_STREAM_IS_GOOD(pa_stream_state_t x)

 static int qpa_simple_read (PAVoiceIn *p, void *data, size_t length, int *rerror)
 {
-    paaudio *g = p->g;
+    paaudio *g = &glob_paaudio;

    pa_threaded_mainloop_lock (g->mainloop);

@@ -164,7 +160,7 @@ unlock_and_fail:

 static int qpa_simple_write (PAVoiceOut *p, const void *data, size_t length, int *rerror)
 {
-    paaudio *g = p->g;
+    paaudio *g = &glob_paaudio;

    pa_threaded_mainloop_lock (g->mainloop);

@@ -226,7 +222,7 @@ static void *qpa_thread_out (void *arg)
            }
        }

-        decr = to_mix = audio_MIN (pa->live, pa->g->conf.samples >> 2);
+        decr = to_mix = audio_MIN (pa->live, glob_paaudio.samples >> 2);
        rpos = pa->rpos;

        if (audio_pt_unlock (&pa->pt, AUDIO_FUNC)) {
@@ -318,7 +314,7 @@ static void *qpa_thread_in (void *arg)
            }
        }

-        incr = to_grab = audio_MIN (pa->dead, pa->g->conf.samples >> 2);
+        incr = to_grab = audio_MIN (pa->dead, glob_paaudio.samples >> 2);
        wpos = pa->wpos;

        if (audio_pt_unlock (&pa->pt, AUDIO_FUNC)) {
@@ -434,7 +430,7 @@ static audfmt_e pa_to_audfmt (pa_sample_format_t fmt, int *endianness)

 static void context_state_cb (pa_context *c, void *userdata)
 {
-    paaudio *g = userdata;
+    paaudio *g = &glob_paaudio;

    switch (pa_context_get_state(c)) {
    case PA_CONTEXT_READY:
@@ -453,7 +449,7 @@ static void context_state_cb (pa_context *c, void *userdata)

 static void stream_state_cb (pa_stream *s, void * userdata)
 {
-    paaudio *g = userdata;
+    paaudio *g = &glob_paaudio;

    switch (pa_stream_get_state (s)) {

@@ -471,21 +467,23 @@ static void stream_state_cb (pa_stream *s, void * userdata)

 static void stream_request_cb (pa_stream *s, size_t length, void *userdata)
 {
-    paaudio *g = userdata;
+    paaudio *g = &glob_paaudio;

    pa_threaded_mainloop_signal (g->mainloop, 0);
 }

 static pa_stream *qpa_simple_new (
-        paaudio *g,
+        const char *server,
        const char *name,
        pa_stream_direction_t dir,
        const char *dev,
+        const char *stream_name,
        const pa_sample_spec *ss,
        const pa_channel_map *map,
        const pa_buffer_attr *attr,
        int *rerror)
 {
+    paaudio *g = &glob_paaudio;
    int r;
    pa_stream *stream;

@@ -536,15 +534,13 @@ fail:
    return NULL;
 }

-static int qpa_init_out(HWVoiceOut *hw, struct audsettings *as,
-                        void *drv_opaque)
+static int qpa_init_out (HWVoiceOut *hw, struct audsettings *as)
 {
    int error;
-    pa_sample_spec ss;
-    pa_buffer_attr ba;
+    static pa_sample_spec ss;
+    static pa_buffer_attr ba;
    struct audsettings obt_as = *as;
    PAVoiceOut *pa = (PAVoiceOut *) hw;
-    paaudio *g = pa->g = drv_opaque;

    ss.format = audfmt_to_pa (as->fmt, as->endianness);
    ss.channels = as->nchannels;
@@ -562,10 +558,11 @@ static int qpa_init_out(HWVoiceOut *hw, struct audsettings *as,
    obt_as.fmt = pa_to_audfmt (ss.format, &obt_as.endianness);

    pa->stream = qpa_simple_new (
-        g,
+        glob_paaudio.server,
        "qemu",
        PA_STREAM_PLAYBACK,
-        g->conf.sink,
+        glob_paaudio.sink,
+        "pcm.playback",
        &ss,
        NULL,                   /* channel map */
        &ba,                    /* buffering attributes */
@@ -577,7 +574,7 @@ static int qpa_init_out(HWVoiceOut *hw, struct audsettings *as,
    }

    audio_pcm_init_info (&hw->info, &obt_as);
-    hw->samples = g->conf.samples;
+    hw->samples = glob_paaudio.samples;
    pa->pcm_buf = audio_calloc (AUDIO_FUNC, hw->samples, 1 << hw->info.shift);
    pa->rpos = hw->rpos;
    if (!pa->pcm_buf) {
@@ -604,13 +601,12 @@ static int qpa_init_out(HWVoiceOut *hw, struct audsettings *as,
    return -1;
 }

-static int qpa_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
+static int qpa_init_in (HWVoiceIn *hw, struct audsettings *as)
 {
    int error;
-    pa_sample_spec ss;
+    static pa_sample_spec ss;
    struct audsettings obt_as = *as;
    PAVoiceIn *pa = (PAVoiceIn *) hw;
-    paaudio *g = pa->g = drv_opaque;

    ss.format = audfmt_to_pa (as->fmt, as->endianness);
    ss.channels = as->nchannels;
@@ -619,10 +615,11 @@ static int qpa_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
    obt_as.fmt = pa_to_audfmt (ss.format, &obt_as.endianness);

    pa->stream = qpa_simple_new (
-        g,
+        glob_paaudio.server,
        "qemu",
        PA_STREAM_RECORD,
-        g->conf.source,
+        glob_paaudio.source,
+        "pcm.capture",
        &ss,
        NULL,                   /* channel map */
        NULL,                   /* buffering attributes */
@@ -634,7 +631,7 @@ static int qpa_init_in(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
    }

    audio_pcm_init_info (&hw->info, &obt_as);
-    hw->samples = g->conf.samples;
+    hw->samples = glob_paaudio.samples;
    pa->pcm_buf = audio_calloc (AUDIO_FUNC, hw->samples, 1 << hw->info.shift);
    pa->wpos = hw->wpos;
    if (!pa->pcm_buf) {
@@ -706,7 +703,7 @@ static int qpa_ctl_out (HWVoiceOut *hw, int cmd, ...)
    PAVoiceOut *pa = (PAVoiceOut *) hw;
    pa_operation *op;
    pa_cvolume v;
-    paaudio *g = pa->g;
+    paaudio *g = &glob_paaudio;

 #ifdef PA_CHECK_VERSION    /* macro is present in 0.9.16+ */
    pa_cvolume_init (&v);  /* function is present in 0.9.13+ */
@@ -758,7 +755,7 @@ static int qpa_ctl_in (HWVoiceIn *hw, int cmd, ...)
    PAVoiceIn *pa = (PAVoiceIn *) hw;
    pa_operation *op;
    pa_cvolume v;
-    paaudio *g = pa->g;
+    paaudio *g = &glob_paaudio;

 #ifdef PA_CHECK_VERSION
    pa_cvolume_init (&v);
@@ -808,31 +805,23 @@ static int qpa_ctl_in (HWVoiceIn *hw, int cmd, ...)
 }

 /* common */
-static PAConf glob_conf = {
-    .samples = 4096,
-};
-
 static void *qpa_audio_init (void)
 {
-    paaudio *g = g_malloc(sizeof(paaudio));
-    g->conf = glob_conf;
-    g->mainloop = NULL;
-    g->context = NULL;
+    paaudio *g = &glob_paaudio;

    g->mainloop = pa_threaded_mainloop_new ();
    if (!g->mainloop) {
        goto fail;
    }

-    g->context = pa_context_new (pa_threaded_mainloop_get_api (g->mainloop),
-                                 g->conf.server);
+    g->context = pa_context_new (pa_threaded_mainloop_get_api (g->mainloop), glob_paaudio.server);
    if (!g->context) {
        goto fail;
    }

    pa_context_set_state_callback (g->context, context_state_cb, g);

-    if (pa_context_connect (g->context, g->conf.server, 0, NULL) < 0) {
+    if (pa_context_connect (g->context, glob_paaudio.server, 0, NULL) < 0) {
        qpa_logerr (pa_context_errno (g->context),
                    "pa_context_connect() failed\n");
        goto fail;
@@ -865,13 +854,12 @@ static void *qpa_audio_init (void)

    pa_threaded_mainloop_unlock (g->mainloop);

-    return g;
+    return &glob_paaudio;

 unlock_and_fail:
    pa_threaded_mainloop_unlock (g->mainloop);
 fail:
    AUD_log (AUDIO_CAP, "Failed to initialize PA context");
-    qpa_audio_fini(g);
    return NULL;
 }

@@ -886,38 +874,39 @@ static void qpa_audio_fini (void *opaque)
    if (g->context) {
        pa_context_disconnect (g->context);
        pa_context_unref (g->context);
+        g->context = NULL;
    }

    if (g->mainloop) {
        pa_threaded_mainloop_free (g->mainloop);
    }

-    g_free(g);
+    g->mainloop = NULL;
 }

 struct audio_option qpa_options[] = {
    {
        .name  = "SAMPLES",
        .tag   = AUD_OPT_INT,
-        .valp  = &glob_conf.samples,
+        .valp  = &glob_paaudio.samples,
        .descr = "buffer size in samples"
    },
    {
        .name  = "SERVER",
        .tag   = AUD_OPT_STR,
-        .valp  = &glob_conf.server,
+        .valp  = &glob_paaudio.server,
        .descr = "server address"
    },
    {
        .name  = "SINK",
        .tag   = AUD_OPT_STR,
-        .valp  = &glob_conf.sink,
+        .valp  = &glob_paaudio.sink,
        .descr = "sink device name"
    },
    {
        .name  = "SOURCE",
        .tag   = AUD_OPT_STR,
-        .valp  = &glob_conf.source,
+        .valp  = &glob_paaudio.source,
        .descr = "source device name"
    },
    { /* End of list */ }
@@ -55,7 +55,6 @@ static struct SDLAudioState {
    SDL_mutex *mutex;
    SDL_sem *sem;
    int initialized;
-    bool driver_created;
 } glob_sdl;
 typedef struct SDLAudioState SDLAudioState;

@@ -333,8 +332,7 @@ static void sdl_fini_out (HWVoiceOut *hw)
    sdl_close (&glob_sdl);
 }

-static int sdl_init_out(HWVoiceOut *hw, struct audsettings *as,
-                        void *drv_opaque)
+static int sdl_init_out (HWVoiceOut *hw, struct audsettings *as)
 {
    SDLVoiceOut *sdl = (SDLVoiceOut *) hw;
    SDLAudioState *s = &glob_sdl;
@@ -394,10 +392,6 @@ static int sdl_ctl_out (HWVoiceOut *hw, int cmd, ...)
 static void *sdl_audio_init (void)
 {
    SDLAudioState *s = &glob_sdl;
-    if (s->driver_created) {
-        sdl_logerr("Can't create multiple sdl backends\n");
-        return NULL;
-    }

    if (SDL_InitSubSystem (SDL_INIT_AUDIO)) {
        sdl_logerr ("SDL failed to initialize audio subsystem\n");
@@ -419,7 +413,6 @@ static void *sdl_audio_init (void)
        return NULL;
    }

-    s->driver_created = true;
    return s;
 }

@@ -430,7 +423,6 @@ static void sdl_audio_fini (void *opaque)
    SDL_DestroySemaphore (s->sem);
    SDL_DestroyMutex (s->mutex);
    SDL_QuitSubSystem (SDL_INIT_AUDIO);
-    s->driver_created = false;
 }

 static struct audio_option sdl_options[] = {
@@ -18,7 +18,6 @@
 */

 #include "hw/hw.h"
-#include "qemu/error-report.h"
 #include "qemu/timer.h"
 #include "ui/qemu-spice.h"

@@ -116,8 +115,7 @@ static int rate_get_samples (struct audio_pcm_info *info, SpiceRateCtl *rate)

 /* playback */

-static int line_out_init(HWVoiceOut *hw, struct audsettings *as,
-                         void *drv_opaque)
+static int line_out_init (HWVoiceOut *hw, struct audsettings *as)
 {
    SpiceVoiceOut *out = container_of (hw, SpiceVoiceOut, hw);
    struct audsettings settings;
@@ -245,7 +243,7 @@ static int line_out_ctl (HWVoiceOut *hw, int cmd, ...)

 /* record */

-static int line_in_init(HWVoiceIn *hw, struct audsettings *as, void *drv_opaque)
+static int line_in_init (HWVoiceIn *hw, struct audsettings *as)
 {
    SpiceVoiceIn *in = container_of (hw, SpiceVoiceIn, hw);
    struct audsettings settings;
@@ -36,10 +36,15 @@ typedef struct WAVVoiceOut {
    int total_samples;
 } WAVVoiceOut;

-typedef struct {
+static struct {
    struct audsettings settings;
    const char *wav_path;
-} WAVConf;
+} conf = {
+    .settings.freq      = 44100,
+    .settings.nchannels = 2,
+    .settings.fmt       = AUD_FMT_S16,
+    .wav_path           = "qemu.wav"
+};

 static int wav_run_out (HWVoiceOut *hw, int live)
 {
@@ -100,8 +105,7 @@ static void le_store (uint8_t *buf, uint32_t val, int len)
    }
 }

-static int wav_init_out(HWVoiceOut *hw, struct audsettings *as,
-                        void *drv_opaque)
+static int wav_init_out (HWVoiceOut *hw, struct audsettings *as)
 {
    WAVVoiceOut *wav = (WAVVoiceOut *) hw;
    int bits16 = 0, stereo = 0;
@@ -111,8 +115,9 @@ static int wav_init_out(HWVoiceOut *hw, struct audsettings *as,
        0x02, 0x00, 0x44, 0xac, 0x00, 0x00, 0x10, 0xb1, 0x02, 0x00, 0x04,
        0x00, 0x10, 0x00, 0x64, 0x61, 0x74, 0x61, 0x00, 0x00, 0x00, 0x00
    };
-    WAVConf *conf = drv_opaque;
-    struct audsettings wav_as = conf->settings;
+    struct audsettings wav_as = conf.settings;
+
+    (void) as;

    stereo = wav_as.nchannels == 2;
    switch (wav_as.fmt) {
@@ -150,10 +155,10 @@ static int wav_init_out(HWVoiceOut *hw, struct audsettings *as,
    le_store (hdr + 28, hw->info.freq << (bits16 + stereo), 4);
    le_store (hdr + 32, 1 << (bits16 + stereo), 2);

-    wav->f = fopen (conf->wav_path, "wb");
+    wav->f = fopen (conf.wav_path, "wb");
    if (!wav->f) {
        dolog ("Failed to open wave file `%s'\nReason: %s\n",
-               conf->wav_path, strerror (errno));
+               conf.wav_path, strerror (errno));
        g_free (wav->pcm_buf);
        wav->pcm_buf = NULL;
        return -1;
@@ -221,49 +226,40 @@ static int wav_ctl_out (HWVoiceOut *hw, int cmd, ...)
    return 0;
 }

-static WAVConf glob_conf = {
-    .settings.freq      = 44100,
-    .settings.nchannels = 2,
-    .settings.fmt       = AUD_FMT_S16,
-    .wav_path           = "qemu.wav"
-};
-
 static void *wav_audio_init (void)
 {
-    WAVConf *conf = g_malloc(sizeof(WAVConf));
-    *conf = glob_conf;
-    return conf;
+    return &conf;
 }

 static void wav_audio_fini (void *opaque)
 {
+    (void) opaque;
    ldebug ("wav_fini");
-    g_free(opaque);
 }

 static struct audio_option wav_options[] = {
    {
        .name  = "FREQUENCY",
        .tag   = AUD_OPT_INT,
-        .valp  = &glob_conf.settings.freq,
+        .valp  = &conf.settings.freq,
        .descr = "Frequency"
    },
    {
        .name  = "FORMAT",
        .tag   = AUD_OPT_FMT,
-        .valp  = &glob_conf.settings.fmt,
+        .valp  = &conf.settings.fmt,
        .descr = "Format"
    },
    {
        .name  = "DAC_FIXED_CHANNELS",
        .tag   = AUD_OPT_INT,
-        .valp  = &glob_conf.settings.nchannels,
+        .valp  = &conf.settings.nchannels,
        .descr = "Number of channels (1 - mono, 2 - stereo)"
    },
    {
        .name  = "PATH",
        .tag   = AUD_OPT_STR,
-        .valp  = &glob_conf.wav_path,
+        .valp  = &conf.wav_path,
        .descr = "Path to wave file"
    },
    { /* End of list */ }
@@ -1,6 +1,5 @@
 #include "hw/hw.h"
 #include "monitor/monitor.h"
-#include "qemu/error-report.h"
 #include "audio.h"

 typedef struct {
@@ -0,0 +1,717 @@
+/* public domain */
+
+#include "qemu-common.h"
+#include "sysemu/sysemu.h"
+#include "audio.h"
+
+#define AUDIO_CAP "winwave"
+#include "audio_int.h"
+
+#include <windows.h>
+#include <mmsystem.h>
+
+#include "audio_win_int.h"
+
+static struct {
+    int dac_headers;
+    int dac_samples;
+    int adc_headers;
+    int adc_samples;
+} conf = {
+    .dac_headers = 4,
+    .dac_samples = 1024,
+    .adc_headers = 4,
+    .adc_samples = 1024
+};
+
+typedef struct {
+    HWVoiceOut hw;
+    HWAVEOUT hwo;
+    WAVEHDR *hdrs;
+    HANDLE event;
+    void *pcm_buf;
+    int avail;
+    int pending;
+    int curhdr;
+    int paused;
+    CRITICAL_SECTION crit_sect;
+} WaveVoiceOut;
+
+typedef struct {
+    HWVoiceIn hw;
+    HWAVEIN hwi;
+    WAVEHDR *hdrs;
+    HANDLE event;
+    void *pcm_buf;
+    int curhdr;
+    int paused;
+    int rpos;
+    int avail;
+    CRITICAL_SECTION crit_sect;
+} WaveVoiceIn;
+
+static void winwave_log_mmresult (MMRESULT mr)
+{
+    const char *str = "BUG";
+
+    switch (mr) {
+    case MMSYSERR_NOERROR:
+        str = "Success";
+        break;
+
+    case MMSYSERR_INVALHANDLE:
+        str = "Specified device handle is invalid";
+        break;
+
+    case MMSYSERR_BADDEVICEID:
+        str = "Specified device id is out of range";
+        break;
+
+    case MMSYSERR_NODRIVER:
+        str = "No device driver is present";
+        break;
+
+    case MMSYSERR_NOMEM:
+        str = "Unable to allocate or lock memory";
+        break;
+
+    case WAVERR_SYNC:
+        str = "Device is synchronous but waveOutOpen was called "
+            "without using the WINWAVE_ALLOWSYNC flag";
+        break;
+
+    case WAVERR_UNPREPARED:
+        str = "The data block pointed to by the pwh parameter "
+            "hasn't been prepared";
+        break;
+
+    case WAVERR_STILLPLAYING:
+        str = "There are still buffers in the queue";
+        break;
+
+    default:
+        dolog ("Reason: Unknown (MMRESULT %#x)\n", mr);
+        return;
+    }
+
+    dolog ("Reason: %s\n", str);
+}
+
+static void GCC_FMT_ATTR (2, 3) winwave_logerr (
+    MMRESULT mr,
+    const char *fmt,
+    ...
+    )
+{
+    va_list ap;
+
+    va_start (ap, fmt);
+    AUD_vlog (AUDIO_CAP, fmt, ap);
+    va_end (ap);
+
+    AUD_log (NULL, " failed\n");
+    winwave_log_mmresult (mr);
+}
+
+static void winwave_anal_close_out (WaveVoiceOut *wave)
+{
+    MMRESULT mr;
+
+    mr = waveOutClose (wave->hwo);
+    if (mr != MMSYSERR_NOERROR) {
+        winwave_logerr (mr, "waveOutClose");
+    }
+    wave->hwo = NULL;
+}
+
+static void CALLBACK winwave_callback_out (
+    HWAVEOUT hwo,
+    UINT msg,
+    DWORD_PTR dwInstance,
+    DWORD_PTR dwParam1,
+    DWORD_PTR dwParam2
+    )
+{
+    WaveVoiceOut *wave = (WaveVoiceOut *) dwInstance;
+
+    switch (msg) {
+    case WOM_DONE:
+        {
+            WAVEHDR *h = (WAVEHDR *) dwParam1;
+            if (!h->dwUser) {
+                h->dwUser = 1;
+                EnterCriticalSection (&wave->crit_sect);
+                {
+                    wave->avail += conf.dac_samples;
+                }
+                LeaveCriticalSection (&wave->crit_sect);
+                if (wave->hw.poll_mode) {
+                    if (!SetEvent (wave->event)) {
+                        dolog ("DAC SetEvent failed %lx\n", GetLastError ());
+                    }
+                }
+            }
+        }
+        break;
+
+    case WOM_CLOSE:
+    case WOM_OPEN:
+        break;
+
+    default:
+        dolog ("unknown wave out callback msg %x\n", msg);
+    }
+}
+
+static int winwave_init_out (HWVoiceOut *hw, struct audsettings *as)
+{
+    int i;
+    int err;
+    MMRESULT mr;
+    WAVEFORMATEX wfx;
+    WaveVoiceOut *wave;
+
+    wave = (WaveVoiceOut *) hw;
+
+    InitializeCriticalSection (&wave->crit_sect);
+
+    err = waveformat_from_audio_settings (&wfx, as);
+    if (err) {
+        goto err0;
+    }
+
+    mr = waveOutOpen (&wave->hwo, WAVE_MAPPER, &wfx,
+                      (DWORD_PTR) winwave_callback_out,
+                      (DWORD_PTR) wave, CALLBACK_FUNCTION);
+    if (mr != MMSYSERR_NOERROR) {
+        winwave_logerr (mr, "waveOutOpen");
+        goto err1;
+    }
+
+    wave->hdrs = audio_calloc (AUDIO_FUNC, conf.dac_headers,
+                               sizeof (*wave->hdrs));
+    if (!wave->hdrs) {
+        goto err2;
+    }
+
+    audio_pcm_init_info (&hw->info, as);
+    hw->samples = conf.dac_samples * conf.dac_headers;
+    wave->avail = hw->samples;
+
+    wave->pcm_buf = audio_calloc (AUDIO_FUNC, conf.dac_samples,
+                                  conf.dac_headers << hw->info.shift);
+    if (!wave->pcm_buf) {
+        goto err3;
+    }
+
+    for (i = 0; i < conf.dac_headers; ++i) {
+        WAVEHDR *h = &wave->hdrs[i];
+
+        h->dwUser = 0;
+        h->dwBufferLength = conf.dac_samples << hw->info.shift;
+        h->lpData = advance (wave->pcm_buf, i * h->dwBufferLength);
+        h->dwFlags = 0;
+
+        mr = waveOutPrepareHeader (wave->hwo, h, sizeof (*h));
+        if (mr != MMSYSERR_NOERROR) {
+            winwave_logerr (mr, "waveOutPrepareHeader(%d)", i);
+            goto err4;
+        }
+    }
+
+    return 0;
+
+ err4:
+    g_free (wave->pcm_buf);
+ err3:
+    g_free (wave->hdrs);
+ err2:
+    winwave_anal_close_out (wave);
+ err1:
+ err0:
+    return -1;
+}
+
+static int winwave_write (SWVoiceOut *sw, void *buf, int len)
+{
+    return audio_pcm_sw_write (sw, buf, len);
+}
+
+static int winwave_run_out (HWVoiceOut *hw, int live)
+{
+    WaveVoiceOut *wave = (WaveVoiceOut *) hw;
+    int decr;
+    int doreset;
+
+    EnterCriticalSection (&wave->crit_sect);
+    {
+        decr = audio_MIN (live, wave->avail);
+        decr = audio_pcm_hw_clip_out (hw, wave->pcm_buf, decr, wave->pending);
+        wave->pending += decr;
+        wave->avail -= decr;
+    }
+    LeaveCriticalSection (&wave->crit_sect);
+
+    doreset = hw->poll_mode && (wave->pending >= conf.dac_samples);
+    if (doreset && !ResetEvent (wave->event)) {
+        dolog ("DAC ResetEvent failed %lx\n", GetLastError ());
+    }
+
+    while (wave->pending >= conf.dac_samples) {
+        MMRESULT mr;
+        WAVEHDR *h = &wave->hdrs[wave->curhdr];
+
+        h->dwUser = 0;
+        mr = waveOutWrite (wave->hwo, h, sizeof (*h));
+        if (mr != MMSYSERR_NOERROR) {
+            winwave_logerr (mr, "waveOutWrite(%d)", wave->curhdr);
+            break;
+        }
+
+        wave->pending -= conf.dac_samples;
+        wave->curhdr = (wave->curhdr + 1) % conf.dac_headers;
+    }
+
+    return decr;
+}
+
+static void winwave_poll (void *opaque)
+{
+    (void) opaque;
+    audio_run ("winwave_poll");
+}
+
+static void winwave_fini_out (HWVoiceOut *hw)
+{
+    int i;
+    MMRESULT mr;
+    WaveVoiceOut *wave = (WaveVoiceOut *) hw;
+
+    mr = waveOutReset (wave->hwo);
+    if (mr != MMSYSERR_NOERROR) {
+        winwave_logerr (mr, "waveOutReset");
+    }
+
+    for (i = 0; i < conf.dac_headers; ++i) {
+        mr = waveOutUnprepareHeader (wave->hwo, &wave->hdrs[i],
+                                     sizeof (wave->hdrs[i]));
+        if (mr != MMSYSERR_NOERROR) {
+            winwave_logerr (mr, "waveOutUnprepareHeader(%d)", i);
+        }
+    }
+
+    winwave_anal_close_out (wave);
+
+    if (wave->event) {
+        qemu_del_wait_object (wave->event, winwave_poll, wave);
+        if (!CloseHandle (wave->event)) {
+            dolog ("DAC CloseHandle failed %lx\n", GetLastError ());
+        }
+        wave->event = NULL;
+    }
+
+    g_free (wave->pcm_buf);
+    wave->pcm_buf = NULL;
+
+    g_free (wave->hdrs);
+    wave->hdrs = NULL;
+}
+
+static int winwave_ctl_out (HWVoiceOut *hw, int cmd, ...)
+{
+    MMRESULT mr;
+    WaveVoiceOut *wave = (WaveVoiceOut *) hw;
+
+    switch (cmd) {
+    case VOICE_ENABLE:
+        {
+            va_list ap;
+            int poll_mode;
+
+            va_start (ap, cmd);
+            poll_mode = va_arg (ap, int);
+            va_end (ap);
+
+            if (poll_mode && !wave->event) {
+                wave->event = CreateEvent (NULL, TRUE, TRUE, NULL);
+                if (!wave->event) {
+                    dolog ("DAC CreateEvent: %lx, poll mode will be disabled\n",
+                           GetLastError ());
+                }
+            }
+
+            if (wave->event) {
+                int ret;
+
+                ret = qemu_add_wait_object (wave->event, winwave_poll, wave);
+                hw->poll_mode = (ret == 0);
+            }
+            else {
+                hw->poll_mode = 0;
+            }
+            wave->paused = 0;
+        }
+        return 0;
+
+    case VOICE_DISABLE:
+        if (!wave->paused) {
+            mr = waveOutReset (wave->hwo);
+            if (mr != MMSYSERR_NOERROR) {
+                winwave_logerr (mr, "waveOutReset");
+            }
+            else {
+                wave->paused = 1;
+            }
+        }
+        if (wave->event) {
+            qemu_del_wait_object (wave->event, winwave_poll, wave);
+        }
+        return 0;
+    }
+    return -1;
+}
+
+static void winwave_anal_close_in (WaveVoiceIn *wave)
+{
+    MMRESULT mr;
+
+    mr = waveInClose (wave->hwi);
+    if (mr != MMSYSERR_NOERROR) {
+        winwave_logerr (mr, "waveInClose");
+    }
+    wave->hwi = NULL;
+}
+
+static void CALLBACK winwave_callback_in (
+    HWAVEIN *hwi,
+    UINT msg,
+    DWORD_PTR dwInstance,
+    DWORD_PTR dwParam1,
+    DWORD_PTR dwParam2
+    )
+{
+    WaveVoiceIn *wave = (WaveVoiceIn *) dwInstance;
+
+    switch (msg) {
+    case WIM_DATA:
+        {
+            WAVEHDR *h = (WAVEHDR *) dwParam1;
+            if (!h->dwUser) {
+                h->dwUser = 1;
+                EnterCriticalSection (&wave->crit_sect);
+                {
+                    wave->avail += conf.adc_samples;
+                }
+                LeaveCriticalSection (&wave->crit_sect);
+                if (wave->hw.poll_mode) {
+                    if (!SetEvent (wave->event)) {
+                        dolog ("ADC SetEvent failed %lx\n", GetLastError ());
+                    }
+                }
+            }
+        }
+        break;
+
+    case WIM_CLOSE:
+    case WIM_OPEN:
+        break;
+
+    default:
+        dolog ("unknown wave in callback msg %x\n", msg);
+    }
+}
+
+static void winwave_add_buffers (WaveVoiceIn *wave, int samples)
+{
+    int doreset;
+
+    doreset = wave->hw.poll_mode && (samples >= conf.adc_samples);
+    if (doreset && !ResetEvent (wave->event)) {
+        dolog ("ADC ResetEvent failed %lx\n", GetLastError ());
+    }
+
+    while (samples >= conf.adc_samples) {
+        MMRESULT mr;
+        WAVEHDR *h = &wave->hdrs[wave->curhdr];
+
+        h->dwUser = 0;
+        mr = waveInAddBuffer (wave->hwi, h, sizeof (*h));
+        if (mr != MMSYSERR_NOERROR) {
+            winwave_logerr (mr, "waveInAddBuffer(%d)", wave->curhdr);
+        }
+        wave->curhdr = (wave->curhdr + 1) % conf.adc_headers;
+        samples -= conf.adc_samples;
+    }
+}
+
+static int winwave_init_in (HWVoiceIn *hw, struct audsettings *as)
+{
+    int i;
+    int err;
+    MMRESULT mr;
+    WAVEFORMATEX wfx;
+    WaveVoiceIn *wave;
+
+    wave = (WaveVoiceIn *) hw;
+
+    InitializeCriticalSection (&wave->crit_sect);
+
+    err = waveformat_from_audio_settings (&wfx, as);
+    if (err) {
+        goto err0;
+    }
+
+    mr = waveInOpen (&wave->hwi, WAVE_MAPPER, &wfx,
+                     (DWORD_PTR) winwave_callback_in,
+                     (DWORD_PTR) wave, CALLBACK_FUNCTION);
+    if (mr != MMSYSERR_NOERROR) {
+        winwave_logerr (mr, "waveInOpen");
+        goto err1;
+    }
+
+    wave->hdrs = audio_calloc (AUDIO_FUNC, conf.dac_headers,
+                               sizeof (*wave->hdrs));
+    if (!wave->hdrs) {
+        goto err2;
+    }
+
+    audio_pcm_init_info (&hw->info, as);
+    hw->samples = conf.adc_samples * conf.adc_headers;
+    wave->avail = 0;
+
+    wave->pcm_buf = audio_calloc (AUDIO_FUNC, conf.adc_samples,
+                                  conf.adc_headers << hw->info.shift);
+    if (!wave->pcm_buf) {
+        goto err3;
+    }
+
+    for (i = 0; i < conf.adc_headers; ++i) {
+        WAVEHDR *h = &wave->hdrs[i];
+
+        h->dwUser = 0;
+        h->dwBufferLength = conf.adc_samples << hw->info.shift;
+        h->lpData = advance (wave->pcm_buf, i * h->dwBufferLength);
+        h->dwFlags = 0;
+
+        mr = waveInPrepareHeader (wave->hwi, h, sizeof (*h));
+        if (mr != MMSYSERR_NOERROR) {
+            winwave_logerr (mr, "waveInPrepareHeader(%d)", i);
+            goto err4;
+        }
+    }
+
+    wave->paused = 1;
+    winwave_add_buffers (wave, hw->samples);
+    return 0;
+
+ err4:
+    g_free (wave->pcm_buf);
+ err3:
+    g_free (wave->hdrs);
+ err2:
+    winwave_anal_close_in (wave);
+ err1:
+ err0:
+    return -1;
+}
+
+static void winwave_fini_in (HWVoiceIn *hw)
+{
+    int i;
+    MMRESULT mr;
+    WaveVoiceIn *wave = (WaveVoiceIn *) hw;
+
+    mr = waveInReset (wave->hwi);
+    if (mr != MMSYSERR_NOERROR) {
+        winwave_logerr (mr, "waveInReset");
+    }
+
+    for (i = 0; i < conf.adc_headers; ++i) {
+        mr = waveInUnprepareHeader (wave->hwi, &wave->hdrs[i],
+                                     sizeof (wave->hdrs[i]));
+        if (mr != MMSYSERR_NOERROR) {
+            winwave_logerr (mr, "waveInUnprepareHeader(%d)", i);
+        }
+    }
+
+    winwave_anal_close_in (wave);
+
+    if (wave->event) {
+        qemu_del_wait_object (wave->event, winwave_poll, wave);
+        if (!CloseHandle (wave->event)) {
+            dolog ("ADC CloseHandle failed %lx\n", GetLastError ());
+        }
+        wave->event = NULL;
+    }
+
+    g_free (wave->pcm_buf);
+    wave->pcm_buf = NULL;
+
+    g_free (wave->hdrs);
+    wave->hdrs = NULL;
+}
+
+static int winwave_run_in (HWVoiceIn *hw)
+{
+    WaveVoiceIn *wave = (WaveVoiceIn *) hw;
+    int live = audio_pcm_hw_get_live_in (hw);
+    int dead = hw->samples - live;
+    int decr, ret;
+
+    if (!dead) {
+        return 0;
+    }
+
+    EnterCriticalSection (&wave->crit_sect);
+    {
+        decr = audio_MIN (dead, wave->avail);
+        wave->avail -= decr;
+    }
+    LeaveCriticalSection (&wave->crit_sect);
+
+    ret = decr;
+    while (decr) {
+        int left = hw->samples - hw->wpos;
+        int conv = audio_MIN (left, decr);
+        hw->conv (hw->conv_buf + hw->wpos,
+                  advance (wave->pcm_buf, wave->rpos << hw->info.shift),
+                  conv);
+
+        wave->rpos = (wave->rpos + conv) % hw->samples;
+        hw->wpos = (hw->wpos + conv) % hw->samples;
+        decr -= conv;
+    }
+
+    winwave_add_buffers (wave, ret);
+    return ret;
+}
+
+static int winwave_read (SWVoiceIn *sw, void *buf, int size)
+{
+    return audio_pcm_sw_read (sw, buf, size);
+}
+
+static int winwave_ctl_in (HWVoiceIn *hw, int cmd, ...)
+{
+    MMRESULT mr;
+    WaveVoiceIn *wave = (WaveVoiceIn *) hw;
+
+    switch (cmd) {
+    case VOICE_ENABLE:
+        {
+            va_list ap;
+            int poll_mode;
+
+            va_start (ap, cmd);
+            poll_mode = va_arg (ap, int);
+            va_end (ap);
+
+            if (poll_mode && !wave->event) {
+                wave->event = CreateEvent (NULL, TRUE, TRUE, NULL);
+                if (!wave->event) {
+                    dolog ("ADC CreateEvent: %lx, poll mode will be disabled\n",
+                           GetLastError ());
+                }
+            }
+
+            if (wave->event) {
+                int ret;
+
+                ret = qemu_add_wait_object (wave->event, winwave_poll, wave);
+                hw->poll_mode = (ret == 0);
+            }
+            else {
+                hw->poll_mode = 0;
+            }
+            if (wave->paused) {
+                mr = waveInStart (wave->hwi);
+                if (mr != MMSYSERR_NOERROR) {
+                    winwave_logerr (mr, "waveInStart");
+                }
+                wave->paused = 0;
+            }
+        }
+        return 0;
+
+    case VOICE_DISABLE:
+        if (!wave->paused) {
+            mr = waveInStop (wave->hwi);
+            if (mr != MMSYSERR_NOERROR) {
+                winwave_logerr (mr, "waveInStop");
+            }
+            else {
+                wave->paused = 1;
+            }
+        }
+        if (wave->event) {
+            qemu_del_wait_object (wave->event, winwave_poll, wave);
+        }
+        return 0;
+    }
+    return 0;
+}
+
+static void *winwave_audio_init (void)
+{
+    return &conf;
+}
+
+static void winwave_audio_fini (void *opaque)
+{
+    (void) opaque;
+}
+
+static struct audio_option winwave_options[] = {
+    {
+        .name        = "DAC_HEADERS",
+        .tag         = AUD_OPT_INT,
+        .valp        = &conf.dac_headers,
+        .descr       = "DAC number of headers",
+    },
+    {
+        .name        = "DAC_SAMPLES",
+        .tag         = AUD_OPT_INT,
+        .valp        = &conf.dac_samples,
+        .descr       = "DAC number of samples per header",
+    },
+    {
+        .name        = "ADC_HEADERS",
+        .tag         = AUD_OPT_INT,
+        .valp        = &conf.adc_headers,
+        .descr       = "ADC number of headers",
+    },
+    {
+        .name        = "ADC_SAMPLES",
+        .tag         = AUD_OPT_INT,
+        .valp        = &conf.adc_samples,
+        .descr       = "ADC number of samples per header",
+    },
+    { /* End of list */ }
+};
+
+static struct audio_pcm_ops winwave_pcm_ops = {
+    .init_out = winwave_init_out,
+    .fini_out = winwave_fini_out,
+    .run_out  = winwave_run_out,
+    .write    = winwave_write,
+    .ctl_out  = winwave_ctl_out,
+    .init_in  = winwave_init_in,
+    .fini_in  = winwave_fini_in,
+    .run_in   = winwave_run_in,
+    .read     = winwave_read,
+    .ctl_in   = winwave_ctl_in
+};
+
+struct audio_driver winwave_audio_driver = {
+    .name           = "winwave",
+    .descr          = "Windows Waveform Audio http://msdn.microsoft.com",
+    .options        = winwave_options,
+    .init           = winwave_audio_init,
+    .fini           = winwave_audio_fini,
+    .pcm_ops        = &winwave_pcm_ops,
+    .can_be_default = 1,
+    .max_voices_out = INT_MAX,
+    .max_voices_in  = INT_MAX,
+    .voice_size_out = sizeof (WaveVoiceOut),
+    .voice_size_in  = sizeof (WaveVoiceIn)
+};
@@ -303,7 +303,7 @@ static int baum_eat_packet(BaumDriverState *baum, const uint8_t *buf, int len)
                return 0;
            cur++;
        }
-        DPRINTF("Dropped %td bytes!\n", cur - buf);
+        DPRINTF("Dropped %d bytes!\n", cur - buf);
    }

 #define EAT(c) do {\
@@ -561,10 +561,7 @@ static void baum_close(struct CharDriverState *chr)
    g_free(baum);
 }

-static CharDriverState *chr_baum_init(const char *id,
-                                      ChardevBackend *backend,
-                                      ChardevReturn *ret,
-                                      Error **errp)
+CharDriverState *chr_baum_init(void)
 {
    BaumDriverState *baum;
    CharDriverState *chr;
@@ -589,16 +586,14 @@ static CharDriverState *chr_baum_init(const char *id,

    baum->brlapi_fd = brlapi__openConnection(handle, NULL, NULL);
    if (baum->brlapi_fd == -1) {
-        error_setg(errp, "brlapi__openConnection: %s",
-                   brlapi_strerror(brlapi_error_location()));
+        brlapi_perror("baum_init: brlapi_openConnection");
        goto fail_handle;
    }

    baum->cellCount_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, baum_cellCount_timer_cb, baum);

    if (brlapi__getDisplaySize(handle, &baum->x, &baum->y) == -1) {
-        error_setg(errp, "brlapi__getDisplaySize: %s",
-                   brlapi_strerror(brlapi_error_location()));
+        brlapi_perror("baum_init: brlapi_getDisplaySize");
        goto fail;
    }

@@ -614,8 +609,7 @@ static CharDriverState *chr_baum_init(const char *id,
        tty = BRLAPI_TTY_DEFAULT;

    if (brlapi__enterTtyMode(handle, tty, NULL) == -1) {
-        error_setg(errp, "brlapi__enterTtyMode: %s",
-                   brlapi_strerror(brlapi_error_location()));
+        brlapi_perror("baum_init: brlapi_enterTtyMode");
        goto fail;
    }

@@ -635,8 +629,7 @@ fail_handle:

 static void register_types(void)
 {
-    register_char_driver("braille", CHARDEV_BACKEND_KIND_BRAILLE, NULL,
-                         chr_baum_init);
+    register_char_driver("braille", CHARDEV_BACKEND_KIND_BRAILLE, NULL);
 }

 type_init(register_types);
@@ -43,7 +43,7 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
        return;
    }
    if (!fb->mem_path) {
-        error_setg(errp, "mem-path property not set");
+        error_setg(errp, "mem_path property not set");
        return;
    }
 #ifndef CONFIG_LINUX
@@ -83,7 +83,9 @@ static void set_mem_path(Object *o, const char *str, Error **errp)
        error_setg(errp, "cannot change property value");
        return;
    }
-    g_free(fb->mem_path);
+    if (fb->mem_path) {
+        g_free(fb->mem_path);
+    }
    fb->mem_path = g_strdup(str);
 }

@@ -10,10 +10,10 @@
 * See the COPYING file in the top-level directory.
 */
 #include "sysemu/hostmem.h"
-#include "hw/boards.h"
 #include "qapi/visitor.h"
 #include "qapi-types.h"
 #include "qapi-visit.h"
+#include "qapi/qmp/qerror.h"
 #include "qemu/config-file.h"
 #include "qom/object_interfaces.h"

@@ -113,17 +113,24 @@ host_memory_backend_set_host_nodes(Object *obj, Visitor *v, void *opaque,
 #endif
 }

-static int
-host_memory_backend_get_policy(Object *obj, Error **errp G_GNUC_UNUSED)
+static void
+host_memory_backend_get_policy(Object *obj, Visitor *v, void *opaque,
+                               const char *name, Error **errp)
 {
    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-    return backend->policy;
+    int policy = backend->policy;
+
+    visit_type_enum(v, &policy, HostMemPolicy_lookup, NULL, name, errp);
 }

 static void
-host_memory_backend_set_policy(Object *obj, int policy, Error **errp)
+host_memory_backend_set_policy(Object *obj, Visitor *v, void *opaque,
+                               const char *name, Error **errp)
 {
    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+    int policy;
+
+    visit_type_enum(v, &policy, HostMemPolicy_lookup, NULL, name, errp);
    backend->policy = policy;

 #ifndef CONFIG_NUMA
@@ -223,10 +230,11 @@ static void host_memory_backend_set_prealloc(Object *obj, bool value,
 static void host_memory_backend_init(Object *obj)
 {
    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-    MachineState *machine = MACHINE(qdev_get_machine());

-    backend->merge = machine_mem_merge(machine);
-    backend->dump = machine_dump_guest_core(machine);
+    backend->merge = qemu_opt_get_bool(qemu_get_machine_opts(),
+                                       "mem-merge", true);
+    backend->dump = qemu_opt_get_bool(qemu_get_machine_opts(),
+                                      "dump-guest-core", true);
    backend->prealloc = mem_prealloc;

    object_property_add_bool(obj, "merge",
@@ -244,10 +252,9 @@ static void host_memory_backend_init(Object *obj)
    object_property_add(obj, "host-nodes", "int",
                        host_memory_backend_get_host_nodes,
                        host_memory_backend_set_host_nodes, NULL, NULL, NULL);
-    object_property_add_enum(obj, "policy", "HostMemPolicy",
-                             HostMemPolicy_lookup,
-                             host_memory_backend_get_policy,
-                             host_memory_backend_set_policy, NULL);
+    object_property_add(obj, "policy", "str",
+                        host_memory_backend_get_policy,
+                        host_memory_backend_set_policy, NULL, NULL, NULL);
 }

 MemoryRegion *
@@ -313,11 +320,9 @@ host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
        assert(maxnode <= MAX_NODES);
        if (mbind(ptr, sz, backend->policy,
                  maxnode ? backend->host_nodes : NULL, maxnode + 1, flags)) {
-            if (backend->policy != MPOL_DEFAULT || errno != ENOSYS) {
-                error_setg_errno(errp, errno,
-                                 "cannot bind memory to host NUMA nodes");
-                return;
-            }
+            error_setg_errno(errp, errno,
+                             "cannot bind memory to host NUMA nodes");
+            return;
        }
 #endif
        /* Preallocate memory after the NUMA policy has been instantiated.
@@ -330,26 +335,12 @@ host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
    }
 }

-static bool
-host_memory_backend_can_be_deleted(UserCreatable *uc, Error **errp)
-{
-    MemoryRegion *mr;
-
-    mr = host_memory_backend_get_memory(MEMORY_BACKEND(uc), errp);
-    if (memory_region_is_mapped(mr)) {
-        return false;
-    } else {
-        return true;
-    }
-}
-
 static void
 host_memory_backend_class_init(ObjectClass *oc, void *data)
 {
    UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);

    ucc->complete = host_memory_backend_memory_complete;
-    ucc->can_be_deleted = host_memory_backend_can_be_deleted;
 }

 static const TypeInfo host_memory_backend_info = {
@@ -63,10 +63,7 @@ static void msmouse_chr_close (struct CharDriverState *chr)
    g_free (chr);
 }

-static CharDriverState *qemu_chr_open_msmouse(const char *id,
-                                              ChardevBackend *backend,
-                                              ChardevReturn *ret,
-                                              Error **errp)
+CharDriverState *qemu_chr_open_msmouse(void)
 {
    CharDriverState *chr;

@@ -82,8 +79,7 @@ static CharDriverState *qemu_chr_open_msmouse(const char *id,

 static void register_types(void)
 {
-    register_char_driver("msmouse", CHARDEV_BACKEND_KIND_MSMOUSE, NULL,
-                         qemu_chr_open_msmouse);
+    register_char_driver("msmouse", CHARDEV_BACKEND_KIND_MSMOUSE, NULL);
 }

 type_init(register_types);
@@ -140,20 +140,19 @@ static void rng_egd_opened(RngBackend *b, Error **errp)
    RngEgd *s = RNG_EGD(b);

    if (s->chr_name == NULL) {
-        error_setg(errp, QERR_INVALID_PARAMETER_VALUE,
-                   "chardev", "a valid character device");
+        error_set(errp, QERR_INVALID_PARAMETER_VALUE,
+                  "chardev", "a valid character device");
        return;
    }

    s->chr = qemu_chr_find(s->chr_name);
    if (s->chr == NULL) {
-        error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND,
-                  "Device '%s' not found", s->chr_name);
+        error_set(errp, QERR_DEVICE_NOT_FOUND, s->chr_name);
        return;
    }

    if (qemu_chr_fe_claim(s->chr) != 0) {
-        error_setg(errp, QERR_DEVICE_IN_USE, s->chr_name);
+        error_set(errp, QERR_DEVICE_IN_USE, s->chr_name);
        return;
    }

@@ -168,7 +167,7 @@ static void rng_egd_set_chardev(Object *obj, const char *value, Error **errp)
    RngEgd *s = RNG_EGD(b);

    if (b->opened) {
-        error_setg(errp, QERR_PERMISSION_DENIED);
+        error_set(errp, QERR_PERMISSION_DENIED);
    } else {
        g_free(s->chr_name);
        s->chr_name = g_strdup(value);
@@ -74,8 +74,8 @@ static void rng_random_opened(RngBackend *b, Error **errp)
    RndRandom *s = RNG_RANDOM(b);

    if (s->filename == NULL) {
-        error_setg(errp, QERR_INVALID_PARAMETER_VALUE,
-                   "filename", "a valid filename");
+        error_set(errp, QERR_INVALID_PARAMETER_VALUE,
+                  "filename", "a valid filename");
    } else {
        s->fd = qemu_open(s->filename, O_RDONLY | O_NONBLOCK);
        if (s->fd == -1) {
@@ -88,7 +88,11 @@ static char *rng_random_get_filename(Object *obj, Error **errp)
 {
    RndRandom *s = RNG_RANDOM(obj);

-    return g_strdup(s->filename);
+    if (s->filename) {
+        return g_strdup(s->filename);
+    }
+
+    return NULL;
 }

 static void rng_random_set_filename(Object *obj, const char *filename,
@@ -98,7 +102,7 @@ static void rng_random_set_filename(Object *obj, const char *filename,
    RndRandom *s = RNG_RANDOM(obj);

    if (b->opened) {
-        error_setg(errp, QERR_PERMISSION_DENIED);
+        error_set(errp, QERR_PERMISSION_DENIED);
        return;
    }

@@ -57,7 +57,7 @@ static void rng_backend_prop_set_opened(Object *obj, bool value, Error **errp)
    }

    if (!value && s->opened) {
-        error_setg(errp, QERR_PERMISSION_DENIED);
+        error_set(errp, QERR_PERMISSION_DENIED);
        return;
    }

@@ -108,16 +108,13 @@ static void testdev_close(struct CharDriverState *chr)
    g_free(testdev);
 }

-static CharDriverState *chr_testdev_init(const char *id,
-                                         ChardevBackend *backend,
-                                         ChardevReturn *ret,
-                                         Error **errp)
+CharDriverState *chr_testdev_init(void)
 {
    TestdevCharState *testdev;
    CharDriverState *chr;

-    testdev = g_new0(TestdevCharState, 1);
-    testdev->chr = chr = g_new0(CharDriverState, 1);
+    testdev = g_malloc0(sizeof(TestdevCharState));
+    testdev->chr = chr = g_malloc0(sizeof(CharDriverState));

    chr->opaque = testdev;
    chr->chr_write = testdev_write;
@@ -128,8 +125,7 @@ static CharDriverState *chr_testdev_init(const char *id,

 static void register_types(void)
 {
-    register_char_driver("testdev", CHARDEV_BACKEND_KIND_TESTDEV, NULL,
-                         chr_testdev_init);
+    register_char_driver("testdev", CHARDEV_BACKEND_KIND_TESTDEV, NULL);
 }

 type_init(register_types);
@@ -36,7 +36,7 @@ void tpm_backend_destroy(TPMBackend *s)
 {
    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);

-    k->ops->destroy(s);
+    return k->ops->destroy(s);
 }

 int tpm_backend_init(TPMBackend *s, TPMState *state,
@@ -96,20 +96,6 @@ bool tpm_backend_get_tpm_established_flag(TPMBackend *s)
    return k->ops->get_tpm_established_flag(s);
 }

-int tpm_backend_reset_tpm_established_flag(TPMBackend *s, uint8_t locty)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->reset_tpm_established_flag(s, locty);
-}
-
-TPMVersion tpm_backend_get_tpm_version(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->get_tpm_version(s);
-}
-
 static bool tpm_backend_prop_get_opened(Object *obj, Error **errp)
 {
    TPMBackend *s = TPM_BACKEND(obj);
@@ -133,7 +119,7 @@ static void tpm_backend_prop_set_opened(Object *obj, bool value, Error **errp)
    }

    if (!value && s->opened) {
-        error_setg(errp, QERR_PERMISSION_DENIED);
+        error_set(errp, QERR_PERMISSION_DENIED);
        return;
    }

@@ -179,6 +165,17 @@ void tpm_backend_thread_end(TPMBackendThread *tbt)
    }
 }

+void tpm_backend_thread_tpm_reset(TPMBackendThread *tbt,
+                                  GFunc func, gpointer user_data)
+{
+    if (!tbt->pool) {
+        tpm_backend_thread_create(tbt, func, user_data);
+    } else {
+        g_thread_pool_push(tbt->pool, (gpointer)TPM_BACKEND_CMD_TPM_RESET,
+                           NULL);
+    }
+}
+
 static const TypeInfo tpm_backend_info = {
    .name = TYPE_TPM_BACKEND,
    .parent = TYPE_OBJECT,
@@ -24,44 +24,17 @@
 * THE SOFTWARE.
 */

-#include "qemu-common.h"
+#include "monitor/monitor.h"
 #include "exec/cpu-common.h"
 #include "sysemu/kvm.h"
 #include "sysemu/balloon.h"
 #include "trace.h"
 #include "qmp-commands.h"
-#include "qapi/qmp/qerror.h"
 #include "qapi/qmp/qjson.h"

 static QEMUBalloonEvent *balloon_event_fn;
 static QEMUBalloonStatus *balloon_stat_fn;
 static void *balloon_opaque;
-static bool balloon_inhibited;
-
-bool qemu_balloon_is_inhibited(void)
-{
-    return balloon_inhibited;
-}
-
-void qemu_balloon_inhibit(bool state)
-{
-    balloon_inhibited = state;
-}
-
-static bool have_balloon(Error **errp)
-{
-    if (kvm_enabled() && !kvm_has_sync_mmu()) {
-        error_set(errp, ERROR_CLASS_KVM_MISSING_CAP,
-                  "Using KVM without synchronous MMU, balloon unavailable");
-        return false;
-    }
-    if (!balloon_event_fn) {
-        error_set(errp, ERROR_CLASS_DEVICE_NOT_ACTIVE,
-                  "No balloon device has been activated");
-        return false;
-    }
-    return true;
-}

 int qemu_add_balloon_handler(QEMUBalloonEvent *event_func,
                             QEMUBalloonStatus *stat_func, void *opaque)
@@ -70,6 +43,7 @@ int qemu_add_balloon_handler(QEMUBalloonEvent *event_func,
        /* We're already registered one balloon handler.  How many can
         * a guest really have?
         */
+        error_report("Another balloon device already registered");
        return -1;
    }
    balloon_event_fn = event_func;
@@ -88,30 +62,58 @@ void qemu_remove_balloon_handler(void *opaque)
    balloon_opaque = NULL;
 }

+static int qemu_balloon(ram_addr_t target)
+{
+    if (!balloon_event_fn) {
+        return 0;
+    }
+    trace_balloon_event(balloon_opaque, target);
+    balloon_event_fn(balloon_opaque, target);
+    return 1;
+}
+
+static int qemu_balloon_status(BalloonInfo *info)
+{
+    if (!balloon_stat_fn) {
+        return 0;
+    }
+    balloon_stat_fn(balloon_opaque, info);
+    return 1;
+}
+
 BalloonInfo *qmp_query_balloon(Error **errp)
 {
    BalloonInfo *info;

-    if (!have_balloon(errp)) {
+    if (kvm_enabled() && !kvm_has_sync_mmu()) {
+        error_set(errp, QERR_KVM_MISSING_CAP, "synchronous MMU", "balloon");
        return NULL;
    }

    info = g_malloc0(sizeof(*info));
-    balloon_stat_fn(balloon_opaque, info);
+
+    if (qemu_balloon_status(info) == 0) {
+        error_set(errp, QERR_DEVICE_NOT_ACTIVE, "balloon");
+        qapi_free_BalloonInfo(info);
+        return NULL;
+    }
+
    return info;
 }

-void qmp_balloon(int64_t target, Error **errp)
+void qmp_balloon(int64_t value, Error **errp)
 {
-    if (!have_balloon(errp)) {
+    if (kvm_enabled() && !kvm_has_sync_mmu()) {
+        error_set(errp, QERR_KVM_MISSING_CAP, "synchronous MMU", "balloon");
        return;
    }

-    if (target <= 0) {
-        error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "target", "a size");
+    if (value <= 0) {
+        error_set(errp, QERR_INVALID_PARAMETER_VALUE, "target", "a size");
        return;
    }
-
-    trace_balloon_event(balloon_opaque, target);
-    balloon_event_fn(balloon_opaque, target);
+    
+    if (qemu_balloon(value) == 0) {
+        error_set(errp, QERR_DEVICE_NOT_ACTIVE, "balloon");
+    }
 }
@@ -23,7 +23,6 @@
 #include "migration/block.h"
 #include "migration/migration.h"
 #include "sysemu/blockdev.h"
-#include "sysemu/block-backend.h"
 #include <assert.h>

 #define BLOCK_SIZE                       (1 << 20)
@@ -36,8 +35,6 @@

 #define MAX_IS_ALLOCATED_SEARCH 65536

-#define MAX_INFLIGHT_IO 512
-
 //#define DEBUG_BLK_MIGRATION

 #ifdef DEBUG_BLK_MIGRATION
@@ -306,7 +303,7 @@ static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds)
    blk->aiocb = bdrv_aio_readv(bs, cur_sector, &blk->qiov,
                                nr_sectors, blk_mig_read_cb, blk);

-    bdrv_reset_dirty_bitmap(bmds->dirty_bitmap, cur_sector, nr_sectors);
+    bdrv_reset_dirty(bs, cur_sector, nr_sectors);
    qemu_mutex_unlock_iothread();

    bmds->cur_sector = cur_sector + nr_sectors;
@@ -322,7 +319,7 @@ static int set_dirty_tracking(void)

    QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
        bmds->dirty_bitmap = bdrv_create_dirty_bitmap(bmds->bs, BLOCK_SIZE,
-                                                      NULL, NULL);
+                                                      NULL);
        if (!bmds->dirty_bitmap) {
            ret = -errno;
            goto fail;
@@ -459,7 +456,7 @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
        blk_mig_lock();
        if (bmds_aio_inflight(bmds, sector)) {
            blk_mig_unlock();
-            bdrv_drain(bmds->bs);
+            bdrv_drain_all();
        } else {
            blk_mig_unlock();
        }
@@ -499,7 +496,7 @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
                g_free(blk);
            }

-            bdrv_reset_dirty_bitmap(bmds->dirty_bitmap, sector, nr_sectors);
+            bdrv_reset_dirty(bmds->bs, sector, nr_sectors);
            break;
        }
        sector += BDRV_SECTORS_PER_DIRTY_CHUNK;
@@ -585,7 +582,7 @@ static int64_t get_remaining_dirty(void)
    int64_t dirty = 0;

    QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
-        dirty += bdrv_get_dirty_count(bmds->dirty_bitmap);
+        dirty += bdrv_get_dirty_count(bmds->bs, bmds->dirty_bitmap);
    }

    return dirty << BDRV_SECTOR_BITS;
@@ -593,7 +590,7 @@ static int64_t get_remaining_dirty(void)

 /* Called with iothread lock taken.  */

-static void block_migration_cleanup(void *opaque)
+static void blk_mig_cleanup(void)
 {
    BlkMigDevState *bmds;
    BlkMigBlock *blk;
@@ -620,6 +617,11 @@ static void block_migration_cleanup(void *opaque)
    blk_mig_unlock();
 }

+static void block_migration_cancel(void *opaque)
+{
+    blk_mig_cleanup();
+}
+
 static int block_save_setup(QEMUFile *f, void *opaque)
 {
    int ret;
@@ -667,10 +669,7 @@ static int block_save_iterate(QEMUFile *f, void *opaque)
    blk_mig_lock();
    while ((block_mig_state.submitted +
            block_mig_state.read_done) * BLOCK_SIZE <
-           qemu_file_get_rate_limit(f) &&
-           (block_mig_state.submitted +
-            block_mig_state.read_done) <
-           MAX_INFLIGHT_IO) {
+           qemu_file_get_rate_limit(f)) {
        blk_mig_unlock();
        if (block_mig_state.bulk_completed == 0) {
            /* first finish the bulk phase */
@@ -750,12 +749,11 @@ static int block_save_complete(QEMUFile *f, void *opaque)

    qemu_put_be64(f, BLK_MIG_FLAG_EOS);

+    blk_mig_cleanup();
    return 0;
 }

-static void block_save_pending(QEMUFile *f, void *opaque, uint64_t max_size,
-                               uint64_t *non_postcopiable_pending,
-                               uint64_t *postcopiable_pending)
+static uint64_t block_save_pending(QEMUFile *f, void *opaque, uint64_t max_size)
 {
    /* Estimate pending number of bytes to send */
    uint64_t pending;
@@ -774,8 +772,7 @@ static void block_save_pending(QEMUFile *f, void *opaque, uint64_t max_size,
    qemu_mutex_unlock_iothread();

    DPRINTF("Enter save live pending  %" PRIu64 "\n", pending);
-    /* We don't do postcopy */
-    *non_postcopiable_pending += pending;
+    return pending;
 }

 static int block_load(QEMUFile *f, void *opaque, int version_id)
@@ -785,7 +782,6 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
    char device_name[256];
    int64_t addr;
    BlockDriverState *bs, *bs_prev = NULL;
-    BlockBackend *blk;
    uint8_t *buf;
    int64_t total_sectors = 0;
    int nr_sectors;
@@ -803,15 +799,9 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
            qemu_get_buffer(f, (uint8_t *)device_name, len);
            device_name[len] = '\0';

-            blk = blk_by_name(device_name);
-            if (!blk) {
-                fprintf(stderr, "Error unknown block device %s\n",
-                        device_name);
-                return -EINVAL;
-            }
-            bs = blk_bs(blk);
+            bs = bdrv_find(device_name);
            if (!bs) {
-                fprintf(stderr, "Block device %s has no medium\n",
+                fprintf(stderr, "Error unknown block device %s\n",
                        device_name);
                return -EINVAL;
            }
@@ -884,10 +874,10 @@ static SaveVMHandlers savevm_block_handlers = {
    .set_params = block_set_params,
    .save_live_setup = block_save_setup,
    .save_live_iterate = block_save_iterate,
-    .save_live_complete_precopy = block_save_complete,
+    .save_live_complete = block_save_complete,
    .save_live_pending = block_save_pending,
    .load_state = block_load,
-    .cleanup = block_migration_cleanup,
+    .cancel = block_migration_cancel,
    .is_active = block_is_active,
 };

@@ -1,16 +1,15 @@
-block-obj-y += raw_bsd.o qcow.o vdi.o vmdk.o cloop.o bochs.o vpc.o vvfat.o
+block-obj-y += raw_bsd.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o
 block-obj-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
 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-$(CONFIG_VHDX) += vhdx.o vhdx-endian.o vhdx-log.o
-block-obj-y += quorum.o
+block-obj-$(CONFIG_QUORUM) += quorum.o
 block-obj-y += parallels.o blkdebug.o blkverify.o
 block-obj-y += block-backend.o snapshot.o qapi.o
 block-obj-$(CONFIG_WIN32) += raw-win32.o win32-aio.o
 block-obj-$(CONFIG_POSIX) += raw-posix.o
 block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
-block-obj-y += null.o mirror.o io.o
-block-obj-y += throttle-groups.o
+block-obj-y += null.o mirror.o

 block-obj-y += nbd.o nbd-client.o sheepdog.o
 block-obj-$(CONFIG_LIBISCSI) += iscsi.o
@@ -21,7 +20,6 @@ block-obj-$(CONFIG_GLUSTERFS) += gluster.o
 block-obj-$(CONFIG_ARCHIPELAGO) += archipelago.o
 block-obj-$(CONFIG_LIBSSH2) += ssh.o
 block-obj-y += accounting.o
-block-obj-y += write-threshold.o

 common-obj-y += stream.o
 common-obj-y += commit.o
@@ -38,7 +36,5 @@ gluster.o-libs     := $(GLUSTERFS_LIBS)
 ssh.o-cflags       := $(LIBSSH2_CFLAGS)
 ssh.o-libs         := $(LIBSSH2_LIBS)
 archipelago.o-libs := $(ARCHIPELAGO_LIBS)
-block-obj-m        += dmg.o
-dmg.o-libs         := $(BZIP2_LIBS)
 qcow.o-libs        := -lz
 linux-aio.o-libs   := -laio
@@ -2,7 +2,6 @@
 * QEMU System Emulator block accounting
 *
 * Copyright (c) 2011 Christoph Hellwig
- * Copyright (c) 2015 Igalia, S.L.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
@@ -25,55 +24,6 @@

 #include "block/accounting.h"
 #include "block/block_int.h"
-#include "qemu/timer.h"
-#include "sysemu/qtest.h"
-
-static QEMUClockType clock_type = QEMU_CLOCK_REALTIME;
-static const int qtest_latency_ns = NANOSECONDS_PER_SECOND / 1000;
-
-void block_acct_init(BlockAcctStats *stats, bool account_invalid,
-                     bool account_failed)
-{
-    stats->account_invalid = account_invalid;
-    stats->account_failed = account_failed;
-
-    if (qtest_enabled()) {
-        clock_type = QEMU_CLOCK_VIRTUAL;
-    }
-}
-
-void block_acct_cleanup(BlockAcctStats *stats)
-{
-    BlockAcctTimedStats *s, *next;
-    QSLIST_FOREACH_SAFE(s, &stats->intervals, entries, next) {
-        g_free(s);
-    }
-}
-
-void block_acct_add_interval(BlockAcctStats *stats, unsigned interval_length)
-{
-    BlockAcctTimedStats *s;
-    unsigned i;
-
-    s = g_new0(BlockAcctTimedStats, 1);
-    s->interval_length = interval_length;
-    QSLIST_INSERT_HEAD(&stats->intervals, s, entries);
-
-    for (i = 0; i < BLOCK_MAX_IOTYPE; i++) {
-        timed_average_init(&s->latency[i], clock_type,
-                           (uint64_t) interval_length * NANOSECONDS_PER_SECOND);
-    }
-}
-
-BlockAcctTimedStats *block_acct_interval_next(BlockAcctStats *stats,
-                                              BlockAcctTimedStats *s)
-{
-    if (s == NULL) {
-        return QSLIST_FIRST(&stats->intervals);
-    } else {
-        return QSLIST_NEXT(s, entries);
-    }
-}

 void block_acct_start(BlockAcctStats *stats, BlockAcctCookie *cookie,
                      int64_t bytes, enum BlockAcctType type)
@@ -81,92 +31,24 @@ void block_acct_start(BlockAcctStats *stats, BlockAcctCookie *cookie,
    assert(type < BLOCK_MAX_IOTYPE);

    cookie->bytes = bytes;
-    cookie->start_time_ns = qemu_clock_get_ns(clock_type);
+    cookie->start_time_ns = get_clock();
    cookie->type = type;
 }

 void block_acct_done(BlockAcctStats *stats, BlockAcctCookie *cookie)
 {
-    BlockAcctTimedStats *s;
-    int64_t time_ns = qemu_clock_get_ns(clock_type);
-    int64_t latency_ns = time_ns - cookie->start_time_ns;
-
-    if (qtest_enabled()) {
-        latency_ns = qtest_latency_ns;
-    }
-
    assert(cookie->type < BLOCK_MAX_IOTYPE);

    stats->nr_bytes[cookie->type] += cookie->bytes;
    stats->nr_ops[cookie->type]++;
-    stats->total_time_ns[cookie->type] += latency_ns;
-    stats->last_access_time_ns = time_ns;
+    stats->total_time_ns[cookie->type] += get_clock() - cookie->start_time_ns;
+}

-    QSLIST_FOREACH(s, &stats->intervals, entries) {
-        timed_average_account(&s->latency[cookie->type], latency_ns);
+
+void block_acct_highest_sector(BlockAcctStats *stats, int64_t sector_num,
+                               unsigned int nb_sectors)
+{
+    if (stats->wr_highest_sector < sector_num + nb_sectors - 1) {
+        stats->wr_highest_sector = sector_num + nb_sectors - 1;
    }
 }
-
-void block_acct_failed(BlockAcctStats *stats, BlockAcctCookie *cookie)
-{
-    assert(cookie->type < BLOCK_MAX_IOTYPE);
-
-    stats->failed_ops[cookie->type]++;
-
-    if (stats->account_failed) {
-        BlockAcctTimedStats *s;
-        int64_t time_ns = qemu_clock_get_ns(clock_type);
-        int64_t latency_ns = time_ns - cookie->start_time_ns;
-
-        if (qtest_enabled()) {
-            latency_ns = qtest_latency_ns;
-        }
-
-        stats->total_time_ns[cookie->type] += latency_ns;
-        stats->last_access_time_ns = time_ns;
-
-        QSLIST_FOREACH(s, &stats->intervals, entries) {
-            timed_average_account(&s->latency[cookie->type], latency_ns);
-        }
-    }
-}
-
-void block_acct_invalid(BlockAcctStats *stats, enum BlockAcctType type)
-{
-    assert(type < BLOCK_MAX_IOTYPE);
-
-    /* block_acct_done() and block_acct_failed() update
-     * total_time_ns[], but this one does not. The reason is that
-     * invalid requests are accounted during their submission,
-     * therefore there's no actual I/O involved. */
-
-    stats->invalid_ops[type]++;
-
-    if (stats->account_invalid) {
-        stats->last_access_time_ns = qemu_clock_get_ns(clock_type);
-    }
-}
-
-void block_acct_merge_done(BlockAcctStats *stats, enum BlockAcctType type,
-                      int num_requests)
-{
-    assert(type < BLOCK_MAX_IOTYPE);
-    stats->merged[type] += num_requests;
-}
-
-int64_t block_acct_idle_time_ns(BlockAcctStats *stats)
-{
-    return qemu_clock_get_ns(clock_type) - stats->last_access_time_ns;
-}
-
-double block_acct_queue_depth(BlockAcctTimedStats *stats,
-                              enum BlockAcctType type)
-{
-    uint64_t sum, elapsed;
-
-    assert(type < BLOCK_MAX_IOTYPE);
-
-    sum = timed_average_sum(&stats->latency[type], &elapsed);
-
-    return (double) sum / elapsed;
-}
@@ -291,7 +291,7 @@ static int qemu_archipelago_init(BDRVArchipelagoState *s)

    ret = qemu_archipelago_xseg_init(s);
    if (ret < 0) {
-        error_report("Cannot initialize XSEG. Aborting...");
+        error_report("Cannot initialize XSEG. Aborting...\n");
        goto err_exit;
    }

@@ -645,7 +645,7 @@ static int qemu_archipelago_create_volume(Error **errp, const char *volname,

    target = xseg_get_target(xseg, req);
    if (!target) {
-        error_setg(errp, "Cannot get XSEG target.");
+        error_setg(errp, "Cannot get XSEG target.\n");
        goto err_exit;
    }
    memcpy(target, volname, targetlen);
@@ -889,7 +889,7 @@ static BlockAIOCB *qemu_archipelago_aio_rw(BlockDriverState *bs,
    return &aio_cb->common;

 err_exit:
-    error_report("qemu_archipelago_aio_rw(): I/O Error");
+    error_report("qemu_archipelago_aio_rw(): I/O Error\n");
    qemu_aio_unref(aio_cb);
    return NULL;
 }
@@ -19,9 +19,7 @@
 #include "block/block.h"
 #include "block/block_int.h"
 #include "block/blockjob.h"
-#include "qapi/qmp/qerror.h"
 #include "qemu/ratelimit.h"
-#include "sysemu/block-backend.h"

 #define BACKUP_CLUSTER_BITS 16
 #define BACKUP_CLUSTER_SIZE (1 << BACKUP_CLUSTER_BITS)
@@ -39,8 +37,6 @@ typedef struct CowRequest {
 typedef struct BackupBlockJob {
    BlockJob common;
    BlockDriverState *target;
-    /* bitmap for sync=incremental */
-    BdrvDirtyBitmap *sync_bitmap;
    MirrorSyncMode sync_mode;
    RateLimit limit;
    BlockdevOnError on_source_error;
@@ -90,8 +86,7 @@ static void cow_request_end(CowRequest *req)

 static int coroutine_fn backup_do_cow(BlockDriverState *bs,
                                      int64_t sector_num, int nb_sectors,
-                                      bool *error_is_read,
-                                      bool is_write_notifier)
+                                      bool *error_is_read)
 {
    BackupBlockJob *job = (BackupBlockJob *)bs->job;
    CowRequest cow_request;
@@ -131,14 +126,8 @@ static int coroutine_fn backup_do_cow(BlockDriverState *bs,
        iov.iov_len = n * BDRV_SECTOR_SIZE;
        qemu_iovec_init_external(&bounce_qiov, &iov, 1);

-        if (is_write_notifier) {
-            ret = bdrv_co_readv_no_serialising(bs,
-                                           start * BACKUP_SECTORS_PER_CLUSTER,
-                                           n, &bounce_qiov);
-        } else {
-            ret = bdrv_co_readv(bs, start * BACKUP_SECTORS_PER_CLUSTER, n,
-                                &bounce_qiov);
-        }
+        ret = bdrv_co_readv(bs, start * BACKUP_SECTORS_PER_CLUSTER, n,
+                            &bounce_qiov);
        if (ret < 0) {
            trace_backup_do_cow_read_fail(job, start, ret);
            if (error_is_read) {
@@ -198,7 +187,7 @@ static int coroutine_fn backup_before_write_notify(
    assert((req->offset & (BDRV_SECTOR_SIZE - 1)) == 0);
    assert((req->bytes & (BDRV_SECTOR_SIZE - 1)) == 0);

-    return backup_do_cow(req->bs, sector_num, nb_sectors, NULL, true);
+    return backup_do_cow(req->bs, sector_num, nb_sectors, NULL);
 }

 static void backup_set_speed(BlockJob *job, int64_t speed, Error **errp)
@@ -206,7 +195,7 @@ static void backup_set_speed(BlockJob *job, int64_t speed, Error **errp)
    BackupBlockJob *s = container_of(job, BackupBlockJob, common);

    if (speed < 0) {
-        error_setg(errp, QERR_INVALID_PARAMETER, "speed");
+        error_set(errp, QERR_INVALID_PARAMETER, "speed");
        return;
    }
    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
@@ -216,41 +205,7 @@ static void backup_iostatus_reset(BlockJob *job)
 {
    BackupBlockJob *s = container_of(job, BackupBlockJob, common);

-    if (s->target->blk) {
-        blk_iostatus_reset(s->target->blk);
-    }
-}
-
-static void backup_cleanup_sync_bitmap(BackupBlockJob *job, int ret)
-{
-    BdrvDirtyBitmap *bm;
-    BlockDriverState *bs = job->common.bs;
-
-    if (ret < 0 || block_job_is_cancelled(&job->common)) {
-        /* Merge the successor back into the parent, delete nothing. */
-        bm = bdrv_reclaim_dirty_bitmap(bs, job->sync_bitmap, NULL);
-        assert(bm);
-    } else {
-        /* Everything is fine, delete this bitmap and install the backup. */
-        bm = bdrv_dirty_bitmap_abdicate(bs, job->sync_bitmap, NULL);
-        assert(bm);
-    }
-}
-
-static void backup_commit(BlockJob *job)
-{
-    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
-    if (s->sync_bitmap) {
-        backup_cleanup_sync_bitmap(s, 0);
-    }
-}
-
-static void backup_abort(BlockJob *job)
-{
-    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
-    if (s->sync_bitmap) {
-        backup_cleanup_sync_bitmap(s, -1);
-    }
+    bdrv_iostatus_reset(s->target);
 }

 static const BlockJobDriver backup_job_driver = {
@@ -258,8 +213,6 @@ static const BlockJobDriver backup_job_driver = {
    .job_type       = BLOCK_JOB_TYPE_BACKUP,
    .set_speed      = backup_set_speed,
    .iostatus_reset = backup_iostatus_reset,
-    .commit         = backup_commit,
-    .abort          = backup_abort,
 };

 static BlockErrorAction backup_error_action(BackupBlockJob *job,
@@ -289,92 +242,6 @@ static void backup_complete(BlockJob *job, void *opaque)
    g_free(data);
 }

-static bool coroutine_fn yield_and_check(BackupBlockJob *job)
-{
-    if (block_job_is_cancelled(&job->common)) {
-        return true;
-    }
-
-    /* we need to yield so that bdrv_drain_all() returns.
-     * (without, VM does not reboot)
-     */
-    if (job->common.speed) {
-        uint64_t delay_ns = ratelimit_calculate_delay(&job->limit,
-                                                      job->sectors_read);
-        job->sectors_read = 0;
-        block_job_sleep_ns(&job->common, QEMU_CLOCK_REALTIME, delay_ns);
-    } else {
-        block_job_sleep_ns(&job->common, QEMU_CLOCK_REALTIME, 0);
-    }
-
-    if (block_job_is_cancelled(&job->common)) {
-        return true;
-    }
-
-    return false;
-}
-
-static int coroutine_fn backup_run_incremental(BackupBlockJob *job)
-{
-    bool error_is_read;
-    int ret = 0;
-    int clusters_per_iter;
-    uint32_t granularity;
-    int64_t sector;
-    int64_t cluster;
-    int64_t end;
-    int64_t last_cluster = -1;
-    BlockDriverState *bs = job->common.bs;
-    HBitmapIter hbi;
-
-    granularity = bdrv_dirty_bitmap_granularity(job->sync_bitmap);
-    clusters_per_iter = MAX((granularity / BACKUP_CLUSTER_SIZE), 1);
-    bdrv_dirty_iter_init(job->sync_bitmap, &hbi);
-
-    /* Find the next dirty sector(s) */
-    while ((sector = hbitmap_iter_next(&hbi)) != -1) {
-        cluster = sector / BACKUP_SECTORS_PER_CLUSTER;
-
-        /* Fake progress updates for any clusters we skipped */
-        if (cluster != last_cluster + 1) {
-            job->common.offset += ((cluster - last_cluster - 1) *
-                                   BACKUP_CLUSTER_SIZE);
-        }
-
-        for (end = cluster + clusters_per_iter; cluster < end; cluster++) {
-            do {
-                if (yield_and_check(job)) {
-                    return ret;
-                }
-                ret = backup_do_cow(bs, cluster * BACKUP_SECTORS_PER_CLUSTER,
-                                    BACKUP_SECTORS_PER_CLUSTER, &error_is_read,
-                                    false);
-                if ((ret < 0) &&
-                    backup_error_action(job, error_is_read, -ret) ==
-                    BLOCK_ERROR_ACTION_REPORT) {
-                    return ret;
-                }
-            } while (ret < 0);
-        }
-
-        /* If the bitmap granularity is smaller than the backup granularity,
-         * we need to advance the iterator pointer to the next cluster. */
-        if (granularity < BACKUP_CLUSTER_SIZE) {
-            bdrv_set_dirty_iter(&hbi, cluster * BACKUP_SECTORS_PER_CLUSTER);
-        }
-
-        last_cluster = cluster - 1;
-    }
-
-    /* Play some final catchup with the progress meter */
-    end = DIV_ROUND_UP(job->common.len, BACKUP_CLUSTER_SIZE);
-    if (last_cluster + 1 < end) {
-        job->common.offset += ((end - last_cluster - 1) * BACKUP_CLUSTER_SIZE);
-    }
-
-    return ret;
-}
-
 static void coroutine_fn backup_run(void *opaque)
 {
    BackupBlockJob *job = opaque;
@@ -392,15 +259,14 @@ static void coroutine_fn backup_run(void *opaque)
    qemu_co_rwlock_init(&job->flush_rwlock);

    start = 0;
-    end = DIV_ROUND_UP(job->common.len, BACKUP_CLUSTER_SIZE);
+    end = DIV_ROUND_UP(job->common.len / BDRV_SECTOR_SIZE,
+                       BACKUP_SECTORS_PER_CLUSTER);

    job->bitmap = hbitmap_alloc(end, 0);

    bdrv_set_enable_write_cache(target, true);
-    if (target->blk) {
-        blk_set_on_error(target->blk, on_target_error, on_target_error);
-        blk_iostatus_enable(target->blk);
-    }
+    bdrv_set_on_error(target, on_target_error, on_target_error);
+    bdrv_iostatus_enable(target);

    bdrv_add_before_write_notifier(bs, &before_write);

@@ -412,13 +278,28 @@ static void coroutine_fn backup_run(void *opaque)
            qemu_coroutine_yield();
            job->common.busy = true;
        }
-    } else if (job->sync_mode == MIRROR_SYNC_MODE_INCREMENTAL) {
-        ret = backup_run_incremental(job);
    } else {
        /* Both FULL and TOP SYNC_MODE's require copying.. */
        for (; start < end; start++) {
            bool error_is_read;
-            if (yield_and_check(job)) {
+
+            if (block_job_is_cancelled(&job->common)) {
+                break;
+            }
+
+            /* we need to yield so that qemu_aio_flush() returns.
+             * (without, VM does not reboot)
+             */
+            if (job->common.speed) {
+                uint64_t delay_ns = ratelimit_calculate_delay(
+                        &job->limit, job->sectors_read);
+                job->sectors_read = 0;
+                block_job_sleep_ns(&job->common, QEMU_CLOCK_REALTIME, delay_ns);
+            } else {
+                block_job_sleep_ns(&job->common, QEMU_CLOCK_REALTIME, 0);
+            }
+
+            if (block_job_is_cancelled(&job->common)) {
                break;
            }

@@ -455,7 +336,7 @@ static void coroutine_fn backup_run(void *opaque)
            }
            /* FULL sync mode we copy the whole drive. */
            ret = backup_do_cow(bs, start * BACKUP_SECTORS_PER_CLUSTER,
-                    BACKUP_SECTORS_PER_CLUSTER, &error_is_read, false);
+                    BACKUP_SECTORS_PER_CLUSTER, &error_is_read);
            if (ret < 0) {
                /* Depending on error action, fail now or retry cluster */
                BlockErrorAction action =
@@ -475,12 +356,10 @@ static void coroutine_fn backup_run(void *opaque)
    /* wait until pending backup_do_cow() calls have completed */
    qemu_co_rwlock_wrlock(&job->flush_rwlock);
    qemu_co_rwlock_unlock(&job->flush_rwlock);
+
    hbitmap_free(job->bitmap);

-    if (target->blk) {
-        blk_iostatus_disable(target->blk);
-    }
-    bdrv_op_unblock_all(target, job->common.blocker);
+    bdrv_iostatus_disable(target);

    data = g_malloc(sizeof(*data));
    data->ret = ret;
@@ -489,11 +368,10 @@ static void coroutine_fn backup_run(void *opaque)

 void backup_start(BlockDriverState *bs, BlockDriverState *target,
                  int64_t speed, MirrorSyncMode sync_mode,
-                  BdrvDirtyBitmap *sync_bitmap,
                  BlockdevOnError on_source_error,
                  BlockdevOnError on_target_error,
                  BlockCompletionFunc *cb, void *opaque,
-                  BlockJobTxn *txn, Error **errp)
+                  Error **errp)
 {
    int64_t len;

@@ -501,54 +379,10 @@ void backup_start(BlockDriverState *bs, BlockDriverState *target,
    assert(target);
    assert(cb);

-    if (bs == target) {
-        error_setg(errp, "Source and target cannot be the same");
-        return;
-    }
-
    if ((on_source_error == BLOCKDEV_ON_ERROR_STOP ||
         on_source_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        (!bs->blk || !blk_iostatus_is_enabled(bs->blk))) {
-        error_setg(errp, QERR_INVALID_PARAMETER, "on-source-error");
-        return;
-    }
-
-    if (!bdrv_is_inserted(bs)) {
-        error_setg(errp, "Device is not inserted: %s",
-                   bdrv_get_device_name(bs));
-        return;
-    }
-
-    if (!bdrv_is_inserted(target)) {
-        error_setg(errp, "Device is not inserted: %s",
-                   bdrv_get_device_name(target));
-        return;
-    }
-
-    if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_BACKUP_SOURCE, errp)) {
-        return;
-    }
-
-    if (bdrv_op_is_blocked(target, BLOCK_OP_TYPE_BACKUP_TARGET, errp)) {
-        return;
-    }
-
-    if (sync_mode == MIRROR_SYNC_MODE_INCREMENTAL) {
-        if (!sync_bitmap) {
-            error_setg(errp, "must provide a valid bitmap name for "
-                             "\"incremental\" sync mode");
-            return;
-        }
-
-        /* Create a new bitmap, and freeze/disable this one. */
-        if (bdrv_dirty_bitmap_create_successor(bs, sync_bitmap, errp) < 0) {
-            return;
-        }
-    } else if (sync_bitmap) {
-        error_setg(errp,
-                   "a sync_bitmap was provided to backup_run, "
-                   "but received an incompatible sync_mode (%s)",
-                   MirrorSyncMode_lookup[sync_mode]);
+        !bdrv_iostatus_is_enabled(bs)) {
+        error_set(errp, QERR_INVALID_PARAMETER, "on-source-error");
        return;
    }

@@ -556,31 +390,20 @@ void backup_start(BlockDriverState *bs, BlockDriverState *target,
    if (len < 0) {
        error_setg_errno(errp, -len, "unable to get length for '%s'",
                         bdrv_get_device_name(bs));
-        goto error;
+        return;
    }

    BackupBlockJob *job = block_job_create(&backup_job_driver, bs, speed,
                                           cb, opaque, errp);
    if (!job) {
-        goto error;
+        return;
    }

-    bdrv_op_block_all(target, job->common.blocker);
-
    job->on_source_error = on_source_error;
    job->on_target_error = on_target_error;
    job->target = target;
    job->sync_mode = sync_mode;
-    job->sync_bitmap = sync_mode == MIRROR_SYNC_MODE_INCREMENTAL ?
-                       sync_bitmap : NULL;
    job->common.len = len;
    job->common.co = qemu_coroutine_create(backup_run);
-    block_job_txn_add_job(txn, &job->common);
    qemu_coroutine_enter(job->common.co, job);
-    return;
-
- error:
-    if (sync_bitmap) {
-        bdrv_reclaim_dirty_bitmap(bs, sync_bitmap, NULL);
-    }
 }
@@ -30,7 +30,6 @@
 #include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qint.h"
 #include "qapi/qmp/qstring.h"
-#include "sysemu/qtest.h"

 typedef struct BDRVBlkdebugState {
    int state;
@@ -217,9 +216,10 @@ static int get_event_by_name(const char *name, BlkDebugEvent *event)
 struct add_rule_data {
    BDRVBlkdebugState *s;
    int action;
+    Error **errp;
 };

-static int add_rule(void *opaque, QemuOpts *opts, Error **errp)
+static int add_rule(QemuOpts *opts, void *opaque)
 {
    struct add_rule_data *d = opaque;
    BDRVBlkdebugState *s = d->s;
@@ -230,10 +230,10 @@ static int add_rule(void *opaque, QemuOpts *opts, Error **errp)
    /* Find the right event for the rule */
    event_name = qemu_opt_get(opts, "event");
    if (!event_name) {
-        error_setg(errp, "Missing event name for rule");
+        error_setg(d->errp, "Missing event name for rule");
        return -1;
    } else if (get_event_by_name(event_name, &event) < 0) {
-        error_setg(errp, "Invalid event name \"%s\"", event_name);
+        error_setg(d->errp, "Invalid event name \"%s\"", event_name);
        return -1;
    }

@@ -319,7 +319,8 @@ static int read_config(BDRVBlkdebugState *s, const char *filename,

    d.s = s;
    d.action = ACTION_INJECT_ERROR;
-    qemu_opts_foreach(&inject_error_opts, add_rule, &d, &local_err);
+    d.errp = &local_err;
+    qemu_opts_foreach(&inject_error_opts, add_rule, &d, 1);
    if (local_err) {
        error_propagate(errp, local_err);
        ret = -EINVAL;
@@ -327,7 +328,7 @@ static int read_config(BDRVBlkdebugState *s, const char *filename,
    }

    d.action = ACTION_SET_STATE;
-    qemu_opts_foreach(&set_state_opts, add_rule, &d, &local_err);
+    qemu_opts_foreach(&set_state_opts, add_rule, &d, 1);
    if (local_err) {
        error_propagate(errp, local_err);
        ret = -EINVAL;
@@ -427,11 +428,11 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
    /* Set initial state */
    s->state = 1;

-    /* Open the image file */
-    bs->file = bdrv_open_child(qemu_opt_get(opts, "x-image"), options, "image",
-                               bs, &child_file, false, &local_err);
-    if (local_err) {
-        ret = -EINVAL;
+    /* Open the backing file */
+    assert(bs->file == NULL);
+    ret = bdrv_open_image(&bs->file, qemu_opt_get(opts, "x-image"), options, "image",
+                          flags | BDRV_O_PROTOCOL, false, &local_err);
+    if (ret < 0) {
        error_propagate(errp, local_err);
        goto out;
    }
@@ -450,7 +451,7 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
    goto out;

 fail_unref:
-    bdrv_unref_child(bs, bs->file);
+    bdrv_unref(bs->file);
 out:
    qemu_opts_del(opts);
    return ret;
@@ -471,14 +472,12 @@ static BlockAIOCB *inject_error(BlockDriverState *bs,
    int error = rule->options.inject.error;
    struct BlkdebugAIOCB *acb;
    QEMUBH *bh;
-    bool immediately = rule->options.inject.immediately;

    if (rule->options.inject.once) {
-        QSIMPLEQ_REMOVE(&s->active_rules, rule, BlkdebugRule, active_next);
-        remove_rule(rule);
+        QSIMPLEQ_INIT(&s->active_rules);
    }

-    if (immediately) {
+    if (rule->options.inject.immediately) {
        return NULL;
    }

@@ -511,8 +510,7 @@ static BlockAIOCB *blkdebug_aio_readv(BlockDriverState *bs,
        return inject_error(bs, cb, opaque, rule);
    }

-    return bdrv_aio_readv(bs->file->bs, sector_num, qiov, nb_sectors,
-                          cb, opaque);
+    return bdrv_aio_readv(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
 }

 static BlockAIOCB *blkdebug_aio_writev(BlockDriverState *bs,
@@ -534,8 +532,7 @@ static BlockAIOCB *blkdebug_aio_writev(BlockDriverState *bs,
        return inject_error(bs, cb, opaque, rule);
    }

-    return bdrv_aio_writev(bs->file->bs, sector_num, qiov, nb_sectors,
-                           cb, opaque);
+    return bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
 }

 static BlockAIOCB *blkdebug_aio_flush(BlockDriverState *bs,
@@ -554,7 +551,7 @@ static BlockAIOCB *blkdebug_aio_flush(BlockDriverState *bs,
        return inject_error(bs, cb, opaque, rule);
    }

-    return bdrv_aio_flush(bs->file->bs, cb, opaque);
+    return bdrv_aio_flush(bs->file, cb, opaque);
 }


@@ -584,13 +581,9 @@ static void suspend_request(BlockDriverState *bs, BlkdebugRule *rule)
    remove_rule(rule);
    QLIST_INSERT_HEAD(&s->suspended_reqs, &r, next);

-    if (!qtest_enabled()) {
-        printf("blkdebug: Suspended request '%s'\n", r.tag);
-    }
+    printf("blkdebug: Suspended request '%s'\n", r.tag);
    qemu_coroutine_yield();
-    if (!qtest_enabled()) {
-        printf("blkdebug: Resuming request '%s'\n", r.tag);
-    }
+    printf("blkdebug: Resuming request '%s'\n", r.tag);

    QLIST_REMOVE(&r, next);
    g_free(r.tag);
@@ -723,60 +716,98 @@ static bool blkdebug_debug_is_suspended(BlockDriverState *bs, const char *tag)

 static int64_t blkdebug_getlength(BlockDriverState *bs)
 {
-    return bdrv_getlength(bs->file->bs);
-}
-
-static int blkdebug_truncate(BlockDriverState *bs, int64_t offset)
-{
-    return bdrv_truncate(bs->file->bs, offset);
+    return bdrv_getlength(bs->file);
 }

 static void blkdebug_refresh_filename(BlockDriverState *bs)
 {
+    BDRVBlkdebugState *s = bs->opaque;
+    struct BlkdebugRule *rule;
    QDict *opts;
-    const QDictEntry *e;
-    bool force_json = false;
+    QList *inject_error_list = NULL, *set_state_list = NULL;
+    QList *suspend_list = NULL;
+    int event;

-    for (e = qdict_first(bs->options); e; e = qdict_next(bs->options, e)) {
-        if (strcmp(qdict_entry_key(e), "config") &&
-            strcmp(qdict_entry_key(e), "x-image") &&
-            strcmp(qdict_entry_key(e), "image") &&
-            strncmp(qdict_entry_key(e), "image.", strlen("image.")))
-        {
-            force_json = true;
-            break;
-        }
-    }
-
-    if (force_json && !bs->file->bs->full_open_options) {
+    if (!bs->file->full_open_options) {
        /* The config file cannot be recreated, so creating a plain filename
         * is impossible */
        return;
    }

-    if (!force_json && bs->file->bs->exact_filename[0]) {
-        snprintf(bs->exact_filename, sizeof(bs->exact_filename),
-                 "blkdebug:%s:%s",
-                 qdict_get_try_str(bs->options, "config") ?: "",
-                 bs->file->bs->exact_filename);
-    }
-
    opts = qdict_new();
    qdict_put_obj(opts, "driver", QOBJECT(qstring_from_str("blkdebug")));

-    QINCREF(bs->file->bs->full_open_options);
-    qdict_put_obj(opts, "image", QOBJECT(bs->file->bs->full_open_options));
+    QINCREF(bs->file->full_open_options);
+    qdict_put_obj(opts, "image", QOBJECT(bs->file->full_open_options));

-    for (e = qdict_first(bs->options); e; e = qdict_next(bs->options, e)) {
-        if (strcmp(qdict_entry_key(e), "x-image") &&
-            strcmp(qdict_entry_key(e), "image") &&
-            strncmp(qdict_entry_key(e), "image.", strlen("image.")))
-        {
-            qobject_incref(qdict_entry_value(e));
-            qdict_put_obj(opts, qdict_entry_key(e), qdict_entry_value(e));
+    for (event = 0; event < BLKDBG_EVENT_MAX; event++) {
+        QLIST_FOREACH(rule, &s->rules[event], next) {
+            if (rule->action == ACTION_INJECT_ERROR) {
+                QDict *inject_error = qdict_new();
+
+                qdict_put_obj(inject_error, "event", QOBJECT(qstring_from_str(
+                              BlkdebugEvent_lookup[rule->event])));
+                qdict_put_obj(inject_error, "state",
+                              QOBJECT(qint_from_int(rule->state)));
+                qdict_put_obj(inject_error, "errno", QOBJECT(qint_from_int(
+                              rule->options.inject.error)));
+                qdict_put_obj(inject_error, "sector", QOBJECT(qint_from_int(
+                              rule->options.inject.sector)));
+                qdict_put_obj(inject_error, "once", QOBJECT(qbool_from_int(
+                              rule->options.inject.once)));
+                qdict_put_obj(inject_error, "immediately",
+                              QOBJECT(qbool_from_int(
+                              rule->options.inject.immediately)));
+
+                if (!inject_error_list) {
+                    inject_error_list = qlist_new();
+                }
+
+                qlist_append_obj(inject_error_list, QOBJECT(inject_error));
+            } else if (rule->action == ACTION_SET_STATE) {
+                QDict *set_state = qdict_new();
+
+                qdict_put_obj(set_state, "event", QOBJECT(qstring_from_str(
+                              BlkdebugEvent_lookup[rule->event])));
+                qdict_put_obj(set_state, "state",
+                              QOBJECT(qint_from_int(rule->state)));
+                qdict_put_obj(set_state, "new_state", QOBJECT(qint_from_int(
+                              rule->options.set_state.new_state)));
+
+                if (!set_state_list) {
+                    set_state_list = qlist_new();
+                }
+
+                qlist_append_obj(set_state_list, QOBJECT(set_state));
+            } else if (rule->action == ACTION_SUSPEND) {
+                QDict *suspend = qdict_new();
+
+                qdict_put_obj(suspend, "event", QOBJECT(qstring_from_str(
+                              BlkdebugEvent_lookup[rule->event])));
+                qdict_put_obj(suspend, "state",
+                              QOBJECT(qint_from_int(rule->state)));
+                qdict_put_obj(suspend, "tag", QOBJECT(qstring_from_str(
+                              rule->options.suspend.tag)));
+
+                if (!suspend_list) {
+                    suspend_list = qlist_new();
+                }
+
+                qlist_append_obj(suspend_list, QOBJECT(suspend));
+            }
        }
    }

+    if (inject_error_list) {
+        qdict_put_obj(opts, "inject-error", QOBJECT(inject_error_list));
+    }
+    if (set_state_list) {
+        qdict_put_obj(opts, "set-state", QOBJECT(set_state_list));
+    }
+    if (suspend_list) {
+        qdict_put_obj(opts, "suspend", QOBJECT(suspend_list));
+    }
+
    bs->full_open_options = opts;
 }

@@ -789,7 +820,6 @@ static BlockDriver bdrv_blkdebug = {
    .bdrv_file_open         = blkdebug_open,
    .bdrv_close             = blkdebug_close,
    .bdrv_getlength         = blkdebug_getlength,
-    .bdrv_truncate          = blkdebug_truncate,
    .bdrv_refresh_filename  = blkdebug_refresh_filename,

    .bdrv_aio_readv         = blkdebug_aio_readv,
@@ -14,7 +14,7 @@
 #include "qapi/qmp/qstring.h"

 typedef struct {
-    BdrvChild *test_file;
+    BlockDriverState *test_file;
 } BDRVBlkverifyState;

 typedef struct BlkverifyAIOCB BlkverifyAIOCB;
@@ -123,29 +123,26 @@ static int blkverify_open(BlockDriverState *bs, QDict *options, int flags,
    }

    /* Open the raw file */
-    bs->file = bdrv_open_child(qemu_opt_get(opts, "x-raw"), options, "raw",
-                               bs, &child_file, false, &local_err);
-    if (local_err) {
-        ret = -EINVAL;
+    assert(bs->file == NULL);
+    ret = bdrv_open_image(&bs->file, qemu_opt_get(opts, "x-raw"), options,
+                          "raw", flags | BDRV_O_PROTOCOL, false, &local_err);
+    if (ret < 0) {
        error_propagate(errp, local_err);
        goto fail;
    }

    /* Open the test file */
-    s->test_file = bdrv_open_child(qemu_opt_get(opts, "x-image"), options,
-                                   "test", bs, &child_format, false,
-                                   &local_err);
-    if (local_err) {
-        ret = -EINVAL;
+    assert(s->test_file == NULL);
+    ret = bdrv_open_image(&s->test_file, qemu_opt_get(opts, "x-image"), options,
+                          "test", flags, false, &local_err);
+    if (ret < 0) {
        error_propagate(errp, local_err);
+        s->test_file = NULL;
        goto fail;
    }

    ret = 0;
 fail:
-    if (ret < 0) {
-        bdrv_unref_child(bs, bs->file);
-    }
    qemu_opts_del(opts);
    return ret;
 }
@@ -154,7 +151,7 @@ static void blkverify_close(BlockDriverState *bs)
 {
    BDRVBlkverifyState *s = bs->opaque;

-    bdrv_unref_child(bs, s->test_file);
+    bdrv_unref(s->test_file);
    s->test_file = NULL;
 }

@@ -162,7 +159,7 @@ static int64_t blkverify_getlength(BlockDriverState *bs)
 {
    BDRVBlkverifyState *s = bs->opaque;

-    return bdrv_getlength(s->test_file->bs);
+    return bdrv_getlength(s->test_file);
 }

 static BlkverifyAIOCB *blkverify_aio_get(BlockDriverState *bs, bool is_write,
@@ -241,13 +238,13 @@ static BlockAIOCB *blkverify_aio_readv(BlockDriverState *bs,
                                            nb_sectors, cb, opaque);

    acb->verify = blkverify_verify_readv;
-    acb->buf = qemu_blockalign(bs->file->bs, qiov->size);
+    acb->buf = qemu_blockalign(bs->file, qiov->size);
    qemu_iovec_init(&acb->raw_qiov, acb->qiov->niov);
    qemu_iovec_clone(&acb->raw_qiov, qiov, acb->buf);

-    bdrv_aio_readv(s->test_file->bs, sector_num, qiov, nb_sectors,
+    bdrv_aio_readv(s->test_file, sector_num, qiov, nb_sectors,
                   blkverify_aio_cb, acb);
-    bdrv_aio_readv(bs->file->bs, sector_num, &acb->raw_qiov, nb_sectors,
+    bdrv_aio_readv(bs->file, sector_num, &acb->raw_qiov, nb_sectors,
                   blkverify_aio_cb, acb);
    return &acb->common;
 }
@@ -260,9 +257,9 @@ static BlockAIOCB *blkverify_aio_writev(BlockDriverState *bs,
    BlkverifyAIOCB *acb = blkverify_aio_get(bs, true, sector_num, qiov,
                                            nb_sectors, cb, opaque);

-    bdrv_aio_writev(s->test_file->bs, sector_num, qiov, nb_sectors,
+    bdrv_aio_writev(s->test_file, sector_num, qiov, nb_sectors,
                    blkverify_aio_cb, acb);
-    bdrv_aio_writev(bs->file->bs, sector_num, qiov, nb_sectors,
+    bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors,
                    blkverify_aio_cb, acb);
    return &acb->common;
 }
@@ -274,7 +271,7 @@ static BlockAIOCB *blkverify_aio_flush(BlockDriverState *bs,
    BDRVBlkverifyState *s = bs->opaque;

    /* Only flush test file, the raw file is not important */
-    return bdrv_aio_flush(s->test_file->bs, cb, opaque);
+    return bdrv_aio_flush(s->test_file, cb, opaque);
 }

 static bool blkverify_recurse_is_first_non_filter(BlockDriverState *bs,
@@ -282,13 +279,13 @@ static bool blkverify_recurse_is_first_non_filter(BlockDriverState *bs,
 {
    BDRVBlkverifyState *s = bs->opaque;

-    bool perm = bdrv_recurse_is_first_non_filter(bs->file->bs, candidate);
+    bool perm = bdrv_recurse_is_first_non_filter(bs->file, candidate);

    if (perm) {
        return true;
    }

-    return bdrv_recurse_is_first_non_filter(s->test_file->bs, candidate);
+    return bdrv_recurse_is_first_non_filter(s->test_file, candidate);
 }

 /* Propagate AioContext changes to ->test_file */
@@ -296,7 +293,7 @@ static void blkverify_detach_aio_context(BlockDriverState *bs)
 {
    BDRVBlkverifyState *s = bs->opaque;

-    bdrv_detach_aio_context(s->test_file->bs);
+    bdrv_detach_aio_context(s->test_file);
 }

 static void blkverify_attach_aio_context(BlockDriverState *bs,
@@ -304,38 +301,32 @@ static void blkverify_attach_aio_context(BlockDriverState *bs,
 {
    BDRVBlkverifyState *s = bs->opaque;

-    bdrv_attach_aio_context(s->test_file->bs, new_context);
+    bdrv_attach_aio_context(s->test_file, new_context);
 }

 static void blkverify_refresh_filename(BlockDriverState *bs)
 {
    BDRVBlkverifyState *s = bs->opaque;

-    /* bs->file->bs has already been refreshed */
-    bdrv_refresh_filename(s->test_file->bs);
+    /* bs->file has already been refreshed */
+    bdrv_refresh_filename(s->test_file);

-    if (bs->file->bs->full_open_options
-        && s->test_file->bs->full_open_options)
-    {
+    if (bs->file->full_open_options && s->test_file->full_open_options) {
        QDict *opts = qdict_new();
        qdict_put_obj(opts, "driver", QOBJECT(qstring_from_str("blkverify")));

-        QINCREF(bs->file->bs->full_open_options);
-        qdict_put_obj(opts, "raw", QOBJECT(bs->file->bs->full_open_options));
-        QINCREF(s->test_file->bs->full_open_options);
-        qdict_put_obj(opts, "test",
-                      QOBJECT(s->test_file->bs->full_open_options));
+        QINCREF(bs->file->full_open_options);
+        qdict_put_obj(opts, "raw", QOBJECT(bs->file->full_open_options));
+        QINCREF(s->test_file->full_open_options);
+        qdict_put_obj(opts, "test", QOBJECT(s->test_file->full_open_options));

        bs->full_open_options = opts;
    }

-    if (bs->file->bs->exact_filename[0]
-        && s->test_file->bs->exact_filename[0])
-    {
+    if (bs->file->exact_filename[0] && s->test_file->exact_filename[0]) {
        snprintf(bs->exact_filename, sizeof(bs->exact_filename),
                 "blkverify:%s:%s",
-                 bs->file->bs->exact_filename,
-                 s->test_file->bs->exact_filename);
+                 bs->file->exact_filename, s->test_file->exact_filename);
    }
 }

@@ -103,7 +103,7 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,

    bs->read_only = 1; // no write support yet

-    ret = bdrv_pread(bs->file->bs, 0, &bochs, sizeof(bochs));
+    ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs));
    if (ret < 0) {
        return ret;
    }
@@ -137,7 +137,7 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
        return -ENOMEM;
    }

-    ret = bdrv_pread(bs->file->bs, le32_to_cpu(bochs.header), s->catalog_bitmap,
+    ret = bdrv_pread(bs->file, le32_to_cpu(bochs.header), s->catalog_bitmap,
                     s->catalog_size * 4);
    if (ret < 0) {
        goto fail;
@@ -206,7 +206,7 @@ static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)
        (s->extent_blocks + s->bitmap_blocks));

    /* read in bitmap for current extent */
-    ret = bdrv_pread(bs->file->bs, bitmap_offset + (extent_offset / 8),
+    ret = bdrv_pread(bs->file, bitmap_offset + (extent_offset / 8),
                     &bitmap_entry, 1);
    if (ret < 0) {
        return ret;
@@ -229,7 +229,7 @@ static int bochs_read(BlockDriverState *bs, int64_t sector_num,
        if (block_offset < 0) {
            return block_offset;
        } else if (block_offset > 0) {
-            ret = bdrv_pread(bs->file->bs, block_offset, buf, 512);
+            ret = bdrv_pread(bs->file, block_offset, buf, 512);
            if (ret < 0) {
                return ret;
            }
@@ -66,7 +66,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
    bs->read_only = 1;

    /* read header */
-    ret = bdrv_pread(bs->file->bs, 128, &s->block_size, 4);
+    ret = bdrv_pread(bs->file, 128, &s->block_size, 4);
    if (ret < 0) {
        return ret;
    }
@@ -92,7 +92,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
        return -EINVAL;
    }

-    ret = bdrv_pread(bs->file->bs, 128 + 4, &s->n_blocks, 4);
+    ret = bdrv_pread(bs->file, 128 + 4, &s->n_blocks, 4);
    if (ret < 0) {
        return ret;
    }
@@ -123,7 +123,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
        return -ENOMEM;
    }

-    ret = bdrv_pread(bs->file->bs, 128 + 4 + 4, s->offsets, offsets_size);
+    ret = bdrv_pread(bs->file, 128 + 4 + 4, s->offsets, offsets_size);
    if (ret < 0) {
        goto fail;
    }
@@ -203,8 +203,8 @@ static inline int cloop_read_block(BlockDriverState *bs, int block_num)
        int ret;
        uint32_t bytes = s->offsets[block_num + 1] - s->offsets[block_num];

-        ret = bdrv_pread(bs->file->bs, s->offsets[block_num],
-                         s->compressed_block, bytes);
+        ret = bdrv_pread(bs->file, s->offsets[block_num], s->compressed_block,
+                         bytes);
        if (ret != bytes) {
            return -1;
        }
@@ -15,9 +15,7 @@
 #include "trace.h"
 #include "block/block_int.h"
 #include "block/blockjob.h"
-#include "qapi/qmp/qerror.h"
 #include "qemu/ratelimit.h"
-#include "sysemu/block-backend.h"

 enum {
    /*
@@ -188,7 +186,7 @@ static void commit_set_speed(BlockJob *job, int64_t speed, Error **errp)
    CommitBlockJob *s = container_of(job, CommitBlockJob, common);

    if (speed < 0) {
-        error_setg(errp, QERR_INVALID_PARAMETER, "speed");
+        error_set(errp, QERR_INVALID_PARAMETER, "speed");
        return;
    }
    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
@@ -214,7 +212,7 @@ void commit_start(BlockDriverState *bs, BlockDriverState *base,

    if ((on_error == BLOCKDEV_ON_ERROR_STOP ||
         on_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        (!bs->blk || !blk_iostatus_is_enabled(bs->blk))) {
+        !bdrv_iostatus_is_enabled(bs)) {
        error_setg(errp, "Invalid parameter combination");
        return;
    }
@@ -236,14 +234,14 @@ void commit_start(BlockDriverState *bs, BlockDriverState *base,
    orig_overlay_flags = bdrv_get_flags(overlay_bs);

    /* convert base & overlay_bs to r/w, if necessary */
-    if (!(orig_overlay_flags & BDRV_O_RDWR)) {
-        reopen_queue = bdrv_reopen_queue(reopen_queue, overlay_bs, NULL,
-                                         orig_overlay_flags | BDRV_O_RDWR);
-    }
    if (!(orig_base_flags & BDRV_O_RDWR)) {
-        reopen_queue = bdrv_reopen_queue(reopen_queue, base, NULL,
+        reopen_queue = bdrv_reopen_queue(reopen_queue, base,
                                         orig_base_flags | BDRV_O_RDWR);
    }
+    if (!(orig_overlay_flags & BDRV_O_RDWR)) {
+        reopen_queue = bdrv_reopen_queue(reopen_queue, overlay_bs,
+                                         orig_overlay_flags | BDRV_O_RDWR);
+    }
    if (reopen_queue) {
        bdrv_reopen_multiple(reopen_queue, &local_err);
        if (local_err != NULL) {
@@ -22,10 +22,8 @@
 * THE SOFTWARE.
 */
 #include "qemu-common.h"
-#include "qemu/error-report.h"
 #include "block/block_int.h"
 #include "qapi/qmp/qbool.h"
-#include "qapi/qmp/qstring.h"
 #include <curl/curl.h>

 // #define DEBUG_CURL
@@ -154,20 +152,18 @@ static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
    DPRINTF("CURL (AIO): Sock action %d on fd %d\n", action, fd);
    switch (action) {
        case CURL_POLL_IN:
-            aio_set_fd_handler(s->aio_context, fd, false,
-                               curl_multi_read, NULL, state);
+            aio_set_fd_handler(s->aio_context, fd, curl_multi_read,
+                               NULL, state);
            break;
        case CURL_POLL_OUT:
-            aio_set_fd_handler(s->aio_context, fd, false,
-                               NULL, curl_multi_do, state);
+            aio_set_fd_handler(s->aio_context, fd, NULL, curl_multi_do, state);
            break;
        case CURL_POLL_INOUT:
-            aio_set_fd_handler(s->aio_context, fd, false,
-                               curl_multi_read, curl_multi_do, state);
+            aio_set_fd_handler(s->aio_context, fd, curl_multi_read,
+                               curl_multi_do, state);
            break;
        case CURL_POLL_REMOVE:
-            aio_set_fd_handler(s->aio_context, fd, false,
-                               NULL, NULL, NULL);
+            aio_set_fd_handler(s->aio_context, fd, NULL, NULL, NULL);
            break;
    }

@@ -301,18 +297,6 @@ static void curl_multi_check_completion(BDRVCURLState *s)
            /* ACBs for successful messages get completed in curl_read_cb */
            if (msg->data.result != CURLE_OK) {
                int i;
-                static int errcount = 100;
-
-                /* Don't lose the original error message from curl, since
-                 * it contains extra data.
-                 */
-                if (errcount > 0) {
-                    error_report("curl: %s", state->errmsg);
-                    if (--errcount == 0) {
-                        error_report("curl: further errors suppressed");
-                    }
-                }
-
                for (i = 0; i < CURL_NUM_ACB; i++) {
                    CURLAIOCB *acb = state->acb[i];

@@ -320,7 +304,7 @@ static void curl_multi_check_completion(BDRVCURLState *s)
                        continue;
                    }

-                    acb->common.cb(acb->common.opaque, -EPROTO);
+                    acb->common.cb(acb->common.opaque, -EIO);
                    qemu_aio_unref(acb);
                    state->acb[i] = NULL;
                }
@@ -24,13 +24,8 @@
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "qemu/bswap.h"
-#include "qemu/error-report.h"
 #include "qemu/module.h"
 #include <zlib.h>
-#ifdef CONFIG_BZIP2
-#include <bzlib.h>
-#endif
-#include <glib.h>

 enum {
    /* Limit chunk sizes to prevent unreasonable amounts of memory being used
@@ -60,9 +55,6 @@ typedef struct BDRVDMGState {
    uint8_t *compressed_chunk;
    uint8_t *uncompressed_chunk;
    z_stream zstream;
-#ifdef CONFIG_BZIP2
-    bz_stream bzstream;
-#endif
 } BDRVDMGState;

 static int dmg_probe(const uint8_t *buf, int buf_size, const char *filename)
@@ -85,7 +77,7 @@ static int read_uint64(BlockDriverState *bs, int64_t offset, uint64_t *result)
    uint64_t buffer;
    int ret;

-    ret = bdrv_pread(bs->file->bs, offset, &buffer, 8);
+    ret = bdrv_pread(bs->file, offset, &buffer, 8);
    if (ret < 0) {
        return ret;
    }
@@ -99,7 +91,7 @@ static int read_uint32(BlockDriverState *bs, int64_t offset, uint32_t *result)
    uint32_t buffer;
    int ret;

-    ret = bdrv_pread(bs->file->bs, offset, &buffer, 4);
+    ret = bdrv_pread(bs->file, offset, &buffer, 4);
    if (ret < 0) {
        return ret;
    }
@@ -108,16 +100,6 @@ static int read_uint32(BlockDriverState *bs, int64_t offset, uint32_t *result)
    return 0;
 }

-static inline uint64_t buff_read_uint64(const uint8_t *buffer, int64_t offset)
-{
-    return be64_to_cpu(*(uint64_t *)&buffer[offset]);
-}
-
-static inline uint32_t buff_read_uint32(const uint8_t *buffer, int64_t offset)
-{
-    return be32_to_cpu(*(uint32_t *)&buffer[offset]);
-}
-
 /* Increase max chunk sizes, if necessary.  This function is used to calculate
 * the buffer sizes needed for compressed/uncompressed chunk I/O.
 */
@@ -130,7 +112,6 @@ static void update_max_chunk_size(BDRVDMGState *s, uint32_t chunk,

    switch (s->types[chunk]) {
    case 0x80000005: /* zlib compressed */
-    case 0x80000006: /* bzip2 compressed */
        compressed_size = s->lengths[chunk];
        uncompressed_sectors = s->sectorcounts[chunk];
        break;
@@ -138,9 +119,7 @@ static void update_max_chunk_size(BDRVDMGState *s, uint32_t chunk,
        uncompressed_sectors = (s->lengths[chunk] + 511) / 512;
        break;
    case 2: /* zero */
-        /* as the all-zeroes block may be large, it is treated specially: the
-         * sector is not copied from a large buffer, a simple memset is used
-         * instead. Therefore uncompressed_sectors does not need to be set. */
+        uncompressed_sectors = s->sectorcounts[chunk];
        break;
    }

@@ -152,372 +131,163 @@ static void update_max_chunk_size(BDRVDMGState *s, uint32_t chunk,
    }
 }

-static int64_t dmg_find_koly_offset(BlockDriverState *file_bs, Error **errp)
-{
-    int64_t length;
-    int64_t offset = 0;
-    uint8_t buffer[515];
-    int i, ret;
-
-    /* bdrv_getlength returns a multiple of block size (512), rounded up. Since
-     * dmg images can have odd sizes, try to look for the "koly" magic which
-     * marks the begin of the UDIF trailer (512 bytes). This magic can be found
-     * in the last 511 bytes of the second-last sector or the first 4 bytes of
-     * the last sector (search space: 515 bytes) */
-    length = bdrv_getlength(file_bs);
-    if (length < 0) {
-        error_setg_errno(errp, -length,
-            "Failed to get file size while reading UDIF trailer");
-        return length;
-    } else if (length < 512) {
-        error_setg(errp, "dmg file must be at least 512 bytes long");
-        return -EINVAL;
-    }
-    if (length > 511 + 512) {
-        offset = length - 511 - 512;
-    }
-    length = length < 515 ? length : 515;
-    ret = bdrv_pread(file_bs, offset, buffer, length);
-    if (ret < 0) {
-        error_setg_errno(errp, -ret, "Failed while reading UDIF trailer");
-        return ret;
-    }
-    for (i = 0; i < length - 3; i++) {
-        if (buffer[i] == 'k' && buffer[i+1] == 'o' &&
-            buffer[i+2] == 'l' && buffer[i+3] == 'y') {
-            return offset + i;
-        }
-    }
-    error_setg(errp, "Could not locate UDIF trailer in dmg file");
-    return -EINVAL;
-}
-
-/* used when building the sector table */
-typedef struct DmgHeaderState {
-    /* used internally by dmg_read_mish_block to remember offsets of blocks
-     * across calls */
-    uint64_t data_fork_offset;
-    /* exported for dmg_open */
-    uint32_t max_compressed_size;
-    uint32_t max_sectors_per_chunk;
-} DmgHeaderState;
-
-static bool dmg_is_known_block_type(uint32_t entry_type)
-{
-    switch (entry_type) {
-    case 0x00000001:    /* uncompressed */
-    case 0x00000002:    /* zeroes */
-    case 0x80000005:    /* zlib */
-#ifdef CONFIG_BZIP2
-    case 0x80000006:    /* bzip2 */
-#endif
-        return true;
-    default:
-        return false;
-    }
-}
-
-static int dmg_read_mish_block(BDRVDMGState *s, DmgHeaderState *ds,
-                               uint8_t *buffer, uint32_t count)
-{
-    uint32_t type, i;
-    int ret;
-    size_t new_size;
-    uint32_t chunk_count;
-    int64_t offset = 0;
-    uint64_t data_offset;
-    uint64_t in_offset = ds->data_fork_offset;
-    uint64_t out_offset;
-
-    type = buff_read_uint32(buffer, offset);
-    /* skip data that is not a valid MISH block (invalid magic or too small) */
-    if (type != 0x6d697368 || count < 244) {
-        /* assume success for now */
-        return 0;
-    }
-
-    /* chunk offsets are relative to this sector number */
-    out_offset = buff_read_uint64(buffer, offset + 8);
-
-    /* location in data fork for (compressed) blob (in bytes) */
-    data_offset = buff_read_uint64(buffer, offset + 0x18);
-    in_offset += data_offset;
-
-    /* move to begin of chunk entries */
-    offset += 204;
-
-    chunk_count = (count - 204) / 40;
-    new_size = sizeof(uint64_t) * (s->n_chunks + chunk_count);
-    s->types = g_realloc(s->types, new_size / 2);
-    s->offsets = g_realloc(s->offsets, new_size);
-    s->lengths = g_realloc(s->lengths, new_size);
-    s->sectors = g_realloc(s->sectors, new_size);
-    s->sectorcounts = g_realloc(s->sectorcounts, new_size);
-
-    for (i = s->n_chunks; i < s->n_chunks + chunk_count; i++) {
-        s->types[i] = buff_read_uint32(buffer, offset);
-        if (!dmg_is_known_block_type(s->types[i])) {
-            chunk_count--;
-            i--;
-            offset += 40;
-            continue;
-        }
-
-        /* sector number */
-        s->sectors[i] = buff_read_uint64(buffer, offset + 8);
-        s->sectors[i] += out_offset;
-
-        /* sector count */
-        s->sectorcounts[i] = buff_read_uint64(buffer, offset + 0x10);
-
-        /* all-zeroes sector (type 2) does not need to be "uncompressed" and can
-         * therefore be unbounded. */
-        if (s->types[i] != 2 && s->sectorcounts[i] > DMG_SECTORCOUNTS_MAX) {
-            error_report("sector count %" PRIu64 " for chunk %" PRIu32
-                         " is larger than max (%u)",
-                         s->sectorcounts[i], i, DMG_SECTORCOUNTS_MAX);
-            ret = -EINVAL;
-            goto fail;
-        }
-
-        /* offset in (compressed) data fork */
-        s->offsets[i] = buff_read_uint64(buffer, offset + 0x18);
-        s->offsets[i] += in_offset;
-
-        /* length in (compressed) data fork */
-        s->lengths[i] = buff_read_uint64(buffer, offset + 0x20);
-
-        if (s->lengths[i] > DMG_LENGTHS_MAX) {
-            error_report("length %" PRIu64 " for chunk %" PRIu32
-                         " is larger than max (%u)",
-                         s->lengths[i], i, DMG_LENGTHS_MAX);
-            ret = -EINVAL;
-            goto fail;
-        }
-
-        update_max_chunk_size(s, i, &ds->max_compressed_size,
-                              &ds->max_sectors_per_chunk);
-        offset += 40;
-    }
-    s->n_chunks += chunk_count;
-    return 0;
-
-fail:
-    return ret;
-}
-
-static int dmg_read_resource_fork(BlockDriverState *bs, DmgHeaderState *ds,
-                                  uint64_t info_begin, uint64_t info_length)
-{
-    BDRVDMGState *s = bs->opaque;
-    int ret;
-    uint32_t count, rsrc_data_offset;
-    uint8_t *buffer = NULL;
-    uint64_t info_end;
-    uint64_t offset;
-
-    /* read offset from begin of resource fork (info_begin) to resource data */
-    ret = read_uint32(bs, info_begin, &rsrc_data_offset);
-    if (ret < 0) {
-        goto fail;
-    } else if (rsrc_data_offset > info_length) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    /* read length of resource data */
-    ret = read_uint32(bs, info_begin + 8, &count);
-    if (ret < 0) {
-        goto fail;
-    } else if (count == 0 || rsrc_data_offset + count > info_length) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    /* begin of resource data (consisting of one or more resources) */
-    offset = info_begin + rsrc_data_offset;
-
-    /* end of resource data (there is possibly a following resource map
-     * which will be ignored). */
-    info_end = offset + count;
-
-    /* read offsets (mish blocks) from one or more resources in resource data */
-    while (offset < info_end) {
-        /* size of following resource */
-        ret = read_uint32(bs, offset, &count);
-        if (ret < 0) {
-            goto fail;
-        } else if (count == 0 || count > info_end - offset) {
-            ret = -EINVAL;
-            goto fail;
-        }
-        offset += 4;
-
-        buffer = g_realloc(buffer, count);
-        ret = bdrv_pread(bs->file->bs, offset, buffer, count);
-        if (ret < 0) {
-            goto fail;
-        }
-
-        ret = dmg_read_mish_block(s, ds, buffer, count);
-        if (ret < 0) {
-            goto fail;
-        }
-        /* advance offset by size of resource */
-        offset += count;
-    }
-    ret = 0;
-
-fail:
-    g_free(buffer);
-    return ret;
-}
-
-static int dmg_read_plist_xml(BlockDriverState *bs, DmgHeaderState *ds,
-                              uint64_t info_begin, uint64_t info_length)
-{
-    BDRVDMGState *s = bs->opaque;
-    int ret;
-    uint8_t *buffer = NULL;
-    char *data_begin, *data_end;
-
-    /* Have at least some length to avoid NULL for g_malloc. Attempt to set a
-     * safe upper cap on the data length. A test sample had a XML length of
-     * about 1 MiB. */
-    if (info_length == 0 || info_length > 16 * 1024 * 1024) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    buffer = g_malloc(info_length + 1);
-    buffer[info_length] = '\0';
-    ret = bdrv_pread(bs->file->bs, info_begin, buffer, info_length);
-    if (ret != info_length) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    /* look for <data>...</data>. The data is 284 (0x11c) bytes after base64
-     * decode. The actual data element has 431 (0x1af) bytes which includes tabs
-     * and line feeds. */
-    data_end = (char *)buffer;
-    while ((data_begin = strstr(data_end, "<data>")) != NULL) {
-        guchar *mish;
-        gsize out_len = 0;
-
-        data_begin += 6;
-        data_end = strstr(data_begin, "</data>");
-        /* malformed XML? */
-        if (data_end == NULL) {
-            ret = -EINVAL;
-            goto fail;
-        }
-        *data_end++ = '\0';
-        mish = g_base64_decode(data_begin, &out_len);
-        ret = dmg_read_mish_block(s, ds, mish, (uint32_t)out_len);
-        g_free(mish);
-        if (ret < 0) {
-            goto fail;
-        }
-    }
-    ret = 0;
-
-fail:
-    g_free(buffer);
-    return ret;
-}
-
 static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
                    Error **errp)
 {
    BDRVDMGState *s = bs->opaque;
-    DmgHeaderState ds;
-    uint64_t rsrc_fork_offset, rsrc_fork_length;
-    uint64_t plist_xml_offset, plist_xml_length;
+    uint64_t info_begin, info_end, last_in_offset, last_out_offset;
+    uint32_t count, tmp;
+    uint32_t max_compressed_size = 1, max_sectors_per_chunk = 1, i;
    int64_t offset;
    int ret;

    bs->read_only = 1;
    s->n_chunks = 0;
    s->offsets = s->lengths = s->sectors = s->sectorcounts = NULL;
-    /* used by dmg_read_mish_block to keep track of the current I/O position */
-    ds.data_fork_offset = 0;
-    ds.max_compressed_size = 1;
-    ds.max_sectors_per_chunk = 1;

-    /* locate the UDIF trailer */
-    offset = dmg_find_koly_offset(bs->file->bs, errp);
+    /* read offset of info blocks */
+    offset = bdrv_getlength(bs->file);
    if (offset < 0) {
        ret = offset;
        goto fail;
    }
+    offset -= 0x1d8;

-    /* offset of data fork (DataForkOffset) */
-    ret = read_uint64(bs, offset + 0x18, &ds.data_fork_offset);
+    ret = read_uint64(bs, offset, &info_begin);
    if (ret < 0) {
        goto fail;
-    } else if (ds.data_fork_offset > offset) {
+    } else if (info_begin == 0) {
        ret = -EINVAL;
        goto fail;
    }

-    /* offset of resource fork (RsrcForkOffset) */
-    ret = read_uint64(bs, offset + 0x28, &rsrc_fork_offset);
+    ret = read_uint32(bs, info_begin, &tmp);
    if (ret < 0) {
        goto fail;
-    }
-    ret = read_uint64(bs, offset + 0x30, &rsrc_fork_length);
-    if (ret < 0) {
-        goto fail;
-    }
-    if (rsrc_fork_offset >= offset ||
-        rsrc_fork_length > offset - rsrc_fork_offset) {
+    } else if (tmp != 0x100) {
        ret = -EINVAL;
        goto fail;
    }
-    /* offset of property list (XMLOffset) */
-    ret = read_uint64(bs, offset + 0xd8, &plist_xml_offset);
+
+    ret = read_uint32(bs, info_begin + 4, &count);
    if (ret < 0) {
        goto fail;
-    }
-    ret = read_uint64(bs, offset + 0xe0, &plist_xml_length);
-    if (ret < 0) {
-        goto fail;
-    }
-    if (plist_xml_offset >= offset ||
-        plist_xml_length > offset - plist_xml_offset) {
+    } else if (count == 0) {
        ret = -EINVAL;
        goto fail;
    }
-    ret = read_uint64(bs, offset + 0x1ec, (uint64_t *)&bs->total_sectors);
-    if (ret < 0) {
-        goto fail;
-    }
-    if (bs->total_sectors < 0) {
-        ret = -EINVAL;
-        goto fail;
-    }
-    if (rsrc_fork_length != 0) {
-        ret = dmg_read_resource_fork(bs, &ds,
-                                     rsrc_fork_offset, rsrc_fork_length);
+    info_end = info_begin + count;
+
+    offset = info_begin + 0x100;
+
+    /* read offsets */
+    last_in_offset = last_out_offset = 0;
+    while (offset < info_end) {
+        uint32_t type;
+
+        ret = read_uint32(bs, offset, &count);
+        if (ret < 0) {
+            goto fail;
+        } else if (count == 0) {
+            ret = -EINVAL;
+            goto fail;
+        }
+        offset += 4;
+
+        ret = read_uint32(bs, offset, &type);
        if (ret < 0) {
            goto fail;
        }
-    } else if (plist_xml_length != 0) {
-        ret = dmg_read_plist_xml(bs, &ds, plist_xml_offset, plist_xml_length);
-        if (ret < 0) {
-            goto fail;
+
+        if (type == 0x6d697368 && count >= 244) {
+            size_t new_size;
+            uint32_t chunk_count;
+
+            offset += 4;
+            offset += 200;
+
+            chunk_count = (count - 204) / 40;
+            new_size = sizeof(uint64_t) * (s->n_chunks + chunk_count);
+            s->types = g_realloc(s->types, new_size / 2);
+            s->offsets = g_realloc(s->offsets, new_size);
+            s->lengths = g_realloc(s->lengths, new_size);
+            s->sectors = g_realloc(s->sectors, new_size);
+            s->sectorcounts = g_realloc(s->sectorcounts, new_size);
+
+            for (i = s->n_chunks; i < s->n_chunks + chunk_count; i++) {
+                ret = read_uint32(bs, offset, &s->types[i]);
+                if (ret < 0) {
+                    goto fail;
+                }
+                offset += 4;
+                if (s->types[i] != 0x80000005 && s->types[i] != 1 &&
+                    s->types[i] != 2) {
+                    if (s->types[i] == 0xffffffff && i > 0) {
+                        last_in_offset = s->offsets[i - 1] + s->lengths[i - 1];
+                        last_out_offset = s->sectors[i - 1] +
+                                          s->sectorcounts[i - 1];
+                    }
+                    chunk_count--;
+                    i--;
+                    offset += 36;
+                    continue;
+                }
+                offset += 4;
+
+                ret = read_uint64(bs, offset, &s->sectors[i]);
+                if (ret < 0) {
+                    goto fail;
+                }
+                s->sectors[i] += last_out_offset;
+                offset += 8;
+
+                ret = read_uint64(bs, offset, &s->sectorcounts[i]);
+                if (ret < 0) {
+                    goto fail;
+                }
+                offset += 8;
+
+                if (s->sectorcounts[i] > DMG_SECTORCOUNTS_MAX) {
+                    error_report("sector count %" PRIu64 " for chunk %" PRIu32
+                                 " is larger than max (%u)",
+                                 s->sectorcounts[i], i, DMG_SECTORCOUNTS_MAX);
+                    ret = -EINVAL;
+                    goto fail;
+                }
+
+                ret = read_uint64(bs, offset, &s->offsets[i]);
+                if (ret < 0) {
+                    goto fail;
+                }
+                s->offsets[i] += last_in_offset;
+                offset += 8;
+
+                ret = read_uint64(bs, offset, &s->lengths[i]);
+                if (ret < 0) {
+                    goto fail;
+                }
+                offset += 8;
+
+                if (s->lengths[i] > DMG_LENGTHS_MAX) {
+                    error_report("length %" PRIu64 " for chunk %" PRIu32
+                                 " is larger than max (%u)",
+                                 s->lengths[i], i, DMG_LENGTHS_MAX);
+                    ret = -EINVAL;
+                    goto fail;
+                }
+
+                update_max_chunk_size(s, i, &max_compressed_size,
+                                      &max_sectors_per_chunk);
+            }
+            s->n_chunks += chunk_count;
        }
-    } else {
-        ret = -EINVAL;
-        goto fail;
    }

    /* initialize zlib engine */
-    s->compressed_chunk = qemu_try_blockalign(bs->file->bs,
-                                              ds.max_compressed_size + 1);
-    s->uncompressed_chunk = qemu_try_blockalign(bs->file->bs,
-                                                512 * ds.max_sectors_per_chunk);
+    s->compressed_chunk = qemu_try_blockalign(bs->file,
+                                              max_compressed_size + 1);
+    s->uncompressed_chunk = qemu_try_blockalign(bs->file,
+                                                512 * max_sectors_per_chunk);
    if (s->compressed_chunk == NULL || s->uncompressed_chunk == NULL) {
        ret = -ENOMEM;
        goto fail;
@@ -579,20 +349,17 @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num)
    if (!is_sector_in_chunk(s, s->current_chunk, sector_num)) {
        int ret;
        uint32_t chunk = search_chunk(s, sector_num);
-#ifdef CONFIG_BZIP2
-        uint64_t total_out;
-#endif

        if (chunk >= s->n_chunks) {
            return -1;
        }

        s->current_chunk = s->n_chunks;
-        switch (s->types[chunk]) { /* block entry type */
+        switch (s->types[chunk]) {
        case 0x80000005: { /* zlib compressed */
            /* we need to buffer, because only the chunk as whole can be
             * inflated. */
-            ret = bdrv_pread(bs->file->bs, s->offsets[chunk],
+            ret = bdrv_pread(bs->file, s->offsets[chunk],
                             s->compressed_chunk, s->lengths[chunk]);
            if (ret != s->lengths[chunk]) {
                return -1;
@@ -612,44 +379,15 @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num)
                return -1;
            }
            break; }
-#ifdef CONFIG_BZIP2
-        case 0x80000006: /* bzip2 compressed */
-            /* we need to buffer, because only the chunk as whole can be
-             * inflated. */
-            ret = bdrv_pread(bs->file->bs, s->offsets[chunk],
-                             s->compressed_chunk, s->lengths[chunk]);
-            if (ret != s->lengths[chunk]) {
-                return -1;
-            }
-
-            ret = BZ2_bzDecompressInit(&s->bzstream, 0, 0);
-            if (ret != BZ_OK) {
-                return -1;
-            }
-            s->bzstream.next_in = (char *)s->compressed_chunk;
-            s->bzstream.avail_in = (unsigned int) s->lengths[chunk];
-            s->bzstream.next_out = (char *)s->uncompressed_chunk;
-            s->bzstream.avail_out = (unsigned int) 512 * s->sectorcounts[chunk];
-            ret = BZ2_bzDecompress(&s->bzstream);
-            total_out = ((uint64_t)s->bzstream.total_out_hi32 << 32) +
-                        s->bzstream.total_out_lo32;
-            BZ2_bzDecompressEnd(&s->bzstream);
-            if (ret != BZ_STREAM_END ||
-                total_out != 512 * s->sectorcounts[chunk]) {
-                return -1;
-            }
-            break;
-#endif /* CONFIG_BZIP2 */
        case 1: /* copy */
-            ret = bdrv_pread(bs->file->bs, s->offsets[chunk],
+            ret = bdrv_pread(bs->file, s->offsets[chunk],
                             s->uncompressed_chunk, s->lengths[chunk]);
            if (ret != s->lengths[chunk]) {
                return -1;
            }
            break;
        case 2: /* zero */
-            /* see dmg_read, it is treated specially. No buffer needs to be
-             * pre-filled, the zeroes can be set directly. */
+            memset(s->uncompressed_chunk, 0, 512 * s->sectorcounts[chunk]);
            break;
        }
        s->current_chunk = chunk;
@@ -668,13 +406,6 @@ static int dmg_read(BlockDriverState *bs, int64_t sector_num,
        if (dmg_read_chunk(bs, sector_num + i) != 0) {
            return -1;
        }
-        /* Special case: current chunk is all zeroes. Do not perform a memcpy as
-         * s->uncompressed_chunk may be too small to cover the large all-zeroes
-         * section. dmg_read_chunk is called to find s->current_chunk */
-        if (s->types[s->current_chunk] == 2) { /* all zeroes block entry */
-            memset(buf + i * 512, 0, 512);
-            continue;
-        }
        sector_offset_in_chunk = sector_num + i - s->sectors[s->current_chunk];
        memcpy(buf + i * 512,
               s->uncompressed_chunk + sector_offset_in_chunk * 512, 512);
@@ -429,23 +429,28 @@ static coroutine_fn int qemu_gluster_co_write_zeroes(BlockDriverState *bs,
        int64_t sector_num, int nb_sectors, BdrvRequestFlags flags)
 {
    int ret;
-    GlusterAIOCB acb;
+    GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
    BDRVGlusterState *s = bs->opaque;
    off_t size = nb_sectors * BDRV_SECTOR_SIZE;
    off_t offset = sector_num * BDRV_SECTOR_SIZE;

-    acb.size = size;
-    acb.ret = 0;
-    acb.coroutine = qemu_coroutine_self();
-    acb.aio_context = bdrv_get_aio_context(bs);
+    acb->size = size;
+    acb->ret = 0;
+    acb->coroutine = qemu_coroutine_self();
+    acb->aio_context = bdrv_get_aio_context(bs);

-    ret = glfs_zerofill_async(s->fd, offset, size, gluster_finish_aiocb, &acb);
+    ret = glfs_zerofill_async(s->fd, offset, size, &gluster_finish_aiocb, acb);
    if (ret < 0) {
-        return -errno;
+        ret = -errno;
+        goto out;
    }

    qemu_coroutine_yield();
-    return acb.ret;
+    ret = acb->ret;
+
+out:
+    g_slice_free(GlusterAIOCB, acb);
+    return ret;
 }

 static inline bool gluster_supports_zerofill(void)
@@ -536,30 +541,35 @@ static coroutine_fn int qemu_gluster_co_rw(BlockDriverState *bs,
        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov, int write)
 {
    int ret;
-    GlusterAIOCB acb;
+    GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
    BDRVGlusterState *s = bs->opaque;
    size_t size = nb_sectors * BDRV_SECTOR_SIZE;
    off_t offset = sector_num * BDRV_SECTOR_SIZE;

-    acb.size = size;
-    acb.ret = 0;
-    acb.coroutine = qemu_coroutine_self();
-    acb.aio_context = bdrv_get_aio_context(bs);
+    acb->size = size;
+    acb->ret = 0;
+    acb->coroutine = qemu_coroutine_self();
+    acb->aio_context = bdrv_get_aio_context(bs);

    if (write) {
        ret = glfs_pwritev_async(s->fd, qiov->iov, qiov->niov, offset, 0,
-            gluster_finish_aiocb, &acb);
+            &gluster_finish_aiocb, acb);
    } else {
        ret = glfs_preadv_async(s->fd, qiov->iov, qiov->niov, offset, 0,
-            gluster_finish_aiocb, &acb);
+            &gluster_finish_aiocb, acb);
    }

    if (ret < 0) {
-        return -errno;
+        ret = -errno;
+        goto out;
    }

    qemu_coroutine_yield();
-    return acb.ret;
+    ret = acb->ret;
+
+out:
+    g_slice_free(GlusterAIOCB, acb);
+    return ret;
 }

 static int qemu_gluster_truncate(BlockDriverState *bs, int64_t offset)
@@ -590,21 +600,26 @@ static coroutine_fn int qemu_gluster_co_writev(BlockDriverState *bs,
 static coroutine_fn int qemu_gluster_co_flush_to_disk(BlockDriverState *bs)
 {
    int ret;
-    GlusterAIOCB acb;
+    GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
    BDRVGlusterState *s = bs->opaque;

-    acb.size = 0;
-    acb.ret = 0;
-    acb.coroutine = qemu_coroutine_self();
-    acb.aio_context = bdrv_get_aio_context(bs);
+    acb->size = 0;
+    acb->ret = 0;
+    acb->coroutine = qemu_coroutine_self();
+    acb->aio_context = bdrv_get_aio_context(bs);

-    ret = glfs_fsync_async(s->fd, gluster_finish_aiocb, &acb);
+    ret = glfs_fsync_async(s->fd, &gluster_finish_aiocb, acb);
    if (ret < 0) {
-        return -errno;
+        ret = -errno;
+        goto out;
    }

    qemu_coroutine_yield();
-    return acb.ret;
+    ret = acb->ret;
+
+out:
+    g_slice_free(GlusterAIOCB, acb);
+    return ret;
 }

 #ifdef CONFIG_GLUSTERFS_DISCARD
@@ -612,23 +627,28 @@ static coroutine_fn int qemu_gluster_co_discard(BlockDriverState *bs,
        int64_t sector_num, int nb_sectors)
 {
    int ret;
-    GlusterAIOCB acb;
+    GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
    BDRVGlusterState *s = bs->opaque;
    size_t size = nb_sectors * BDRV_SECTOR_SIZE;
    off_t offset = sector_num * BDRV_SECTOR_SIZE;

-    acb.size = 0;
-    acb.ret = 0;
-    acb.coroutine = qemu_coroutine_self();
-    acb.aio_context = bdrv_get_aio_context(bs);
+    acb->size = 0;
+    acb->ret = 0;
+    acb->coroutine = qemu_coroutine_self();
+    acb->aio_context = bdrv_get_aio_context(bs);

-    ret = glfs_discard_async(s->fd, offset, size, gluster_finish_aiocb, &acb);
+    ret = glfs_discard_async(s->fd, offset, size, &gluster_finish_aiocb, acb);
    if (ret < 0) {
-        return -errno;
+        ret = -errno;
+        goto out;
    }

    qemu_coroutine_yield();
-    return acb.ret;
+    ret = acb->ret;
+
+out:
+    g_slice_free(GlusterAIOCB, acb);
+    return ret;
 }
 #endif

@@ -2,7 +2,7 @@
 * QEMU Block driver for iSCSI images
 *
 * Copyright (c) 2010-2011 Ronnie Sahlberg <ronniesahlberg@gmail.com>
- * Copyright (c) 2012-2015 Peter Lieven <pl@kamp.de>
+ * Copyright (c) 2012-2014 Peter Lieven <pl@kamp.de>
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
@@ -38,7 +38,6 @@
 #include "qemu/iov.h"
 #include "sysemu/sysemu.h"
 #include "qmp-commands.h"
-#include "qapi/qmp/qstring.h"

 #include <iscsi/iscsi.h>
 #include <iscsi/scsi-lowlevel.h>
@@ -57,20 +56,15 @@ typedef struct IscsiLun {
    uint64_t num_blocks;
    int events;
    QEMUTimer *nop_timer;
-    QEMUTimer *event_timer;
+    uint8_t lbpme;
+    uint8_t lbprz;
+    uint8_t has_write_same;
    struct scsi_inquiry_logical_block_provisioning lbp;
    struct scsi_inquiry_block_limits bl;
    unsigned char *zeroblock;
    unsigned long *allocationmap;
    int cluster_sectors;
    bool use_16_for_rw;
-    bool write_protected;
-    bool lbpme;
-    bool lbprz;
-    bool dpofua;
-    bool has_write_same;
-    bool force_next_flush;
-    bool request_timed_out;
 } IscsiLun;

 typedef struct IscsiTask {
@@ -83,8 +77,6 @@ typedef struct IscsiTask {
    QEMUBH *bh;
    IscsiLun *iscsilun;
    QEMUTimer retry_timer;
-    bool force_next_flush;
-    int err_code;
 } IscsiTask;

 typedef struct IscsiAIOCB {
@@ -97,18 +89,15 @@ typedef struct IscsiAIOCB {
    int status;
    int64_t sector_num;
    int nb_sectors;
-    int ret;
 #ifdef __linux__
    sg_io_hdr_t *ioh;
 #endif
 } IscsiAIOCB;

-/* libiscsi uses time_t so its enough to process events every second */
-#define EVENT_INTERVAL 1000
 #define NOP_INTERVAL 5000
 #define MAX_NOP_FAILURES 3
 #define ISCSI_CMD_RETRIES ARRAY_SIZE(iscsi_retry_times)
-static const unsigned iscsi_retry_times[] = {8, 32, 128, 512, 2048, 8192, 32768};
+static const unsigned iscsi_retry_times[] = {8, 32, 128, 512, 2048};

 /* this threshold is a trade-off knob to choose between
 * the potential additional overhead of an extra GET_LBA_STATUS request
@@ -171,70 +160,6 @@ static inline unsigned exp_random(double mean)
    return -mean * log((double)rand() / RAND_MAX);
 }

-/* SCSI_SENSE_ASCQ_INVALID_FIELD_IN_PARAMETER_LIST was introduced in
- * libiscsi 1.10.0, together with other constants we need.  Use it as
- * a hint that we have to define them ourselves if needed, to keep the
- * minimum required libiscsi version at 1.9.0.  We use an ASCQ macro for
- * the test because SCSI_STATUS_* is an enum.
- *
- * To guard against future changes where SCSI_SENSE_ASCQ_* also becomes
- * an enum, check against the LIBISCSI_API_VERSION macro, which was
- * introduced in 1.11.0.  If it is present, there is no need to define
- * anything.
- */
-#if !defined(SCSI_SENSE_ASCQ_INVALID_FIELD_IN_PARAMETER_LIST) && \
-    !defined(LIBISCSI_API_VERSION)
-#define SCSI_STATUS_TASK_SET_FULL                          0x28
-#define SCSI_STATUS_TIMEOUT                                0x0f000002
-#define SCSI_SENSE_ASCQ_INVALID_FIELD_IN_PARAMETER_LIST    0x2600
-#define SCSI_SENSE_ASCQ_PARAMETER_LIST_LENGTH_ERROR        0x1a00
-#endif
-
-static int iscsi_translate_sense(struct scsi_sense *sense)
-{
-    int ret;
-
-    switch (sense->key) {
-    case SCSI_SENSE_NOT_READY:
-        return -EBUSY;
-    case SCSI_SENSE_DATA_PROTECTION:
-        return -EACCES;
-    case SCSI_SENSE_COMMAND_ABORTED:
-        return -ECANCELED;
-    case SCSI_SENSE_ILLEGAL_REQUEST:
-        /* Parse ASCQ */
-        break;
-    default:
-        return -EIO;
-    }
-    switch (sense->ascq) {
-    case SCSI_SENSE_ASCQ_PARAMETER_LIST_LENGTH_ERROR:
-    case SCSI_SENSE_ASCQ_INVALID_OPERATION_CODE:
-    case SCSI_SENSE_ASCQ_INVALID_FIELD_IN_CDB:
-    case SCSI_SENSE_ASCQ_INVALID_FIELD_IN_PARAMETER_LIST:
-        ret = -EINVAL;
-        break;
-    case SCSI_SENSE_ASCQ_LBA_OUT_OF_RANGE:
-        ret = -ENOSPC;
-        break;
-    case SCSI_SENSE_ASCQ_LOGICAL_UNIT_NOT_SUPPORTED:
-        ret = -ENOTSUP;
-        break;
-    case SCSI_SENSE_ASCQ_MEDIUM_NOT_PRESENT:
-    case SCSI_SENSE_ASCQ_MEDIUM_NOT_PRESENT_TRAY_CLOSED:
-    case SCSI_SENSE_ASCQ_MEDIUM_NOT_PRESENT_TRAY_OPEN:
-        ret = -ENOMEDIUM;
-        break;
-    case SCSI_SENSE_ASCQ_WRITE_PROTECTED:
-        ret = -EACCES;
-        break;
-    default:
-        ret = -EIO;
-        break;
-    }
-    return ret;
-}
-
 static void
 iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
                        void *command_data, void *opaque)
@@ -255,19 +180,10 @@ iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
                iTask->do_retry = 1;
                goto out;
            }
-            if (status == SCSI_STATUS_BUSY ||
-                status == SCSI_STATUS_TIMEOUT ||
-                status == SCSI_STATUS_TASK_SET_FULL) {
+            if (status == SCSI_STATUS_BUSY) {
                unsigned retry_time =
                    exp_random(iscsi_retry_times[iTask->retries - 1]);
-                if (status == SCSI_STATUS_TIMEOUT) {
-                    /* make sure the request is rescheduled AFTER the
-                     * reconnect is initiated */
-                    retry_time = EVENT_INTERVAL * 2;
-                    iTask->iscsilun->request_timed_out = true;
-                }
-                error_report("iSCSI Busy/TaskSetFull/TimeOut"
-                             " (retry #%u in %u ms): %s",
+                error_report("iSCSI Busy (retry #%u in %u ms): %s",
                             iTask->retries, retry_time,
                             iscsi_get_error(iscsi));
                aio_timer_init(iTask->iscsilun->aio_context,
@@ -279,10 +195,7 @@ iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
                return;
            }
        }
-        iTask->err_code = iscsi_translate_sense(&task->sense);
        error_report("iSCSI Failure: %s", iscsi_get_error(iscsi));
-    } else {
-        iTask->iscsilun->force_next_flush |= iTask->force_next_flush;
    }

 out:
@@ -342,36 +255,21 @@ static void
 iscsi_set_events(IscsiLun *iscsilun)
 {
    struct iscsi_context *iscsi = iscsilun->iscsi;
-    int ev = iscsi_which_events(iscsi);
+    int ev;

+    /* We always register a read handler.  */
+    ev = POLLIN;
+    ev |= iscsi_which_events(iscsi);
    if (ev != iscsilun->events) {
-        aio_set_fd_handler(iscsilun->aio_context, iscsi_get_fd(iscsi),
-                           false,
-                           (ev & POLLIN) ? iscsi_process_read : NULL,
+        aio_set_fd_handler(iscsilun->aio_context,
+                           iscsi_get_fd(iscsi),
+                           iscsi_process_read,
                           (ev & POLLOUT) ? iscsi_process_write : NULL,
                           iscsilun);
-        iscsilun->events = ev;
-    }
-}

-static void iscsi_timed_check_events(void *opaque)
-{
-    IscsiLun *iscsilun = opaque;
-
-    /* check for timed out requests */
-    iscsi_service(iscsilun->iscsi, 0);
-
-    if (iscsilun->request_timed_out) {
-        iscsilun->request_timed_out = false;
-        iscsi_reconnect(iscsilun->iscsi);
    }

-    /* newer versions of libiscsi may return zero events. Ensure we are able
-     * to return to service once this situation changes. */
-    iscsi_set_events(iscsilun);
-
-    timer_mod(iscsilun->event_timer,
-              qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + EVENT_INTERVAL);
+    iscsilun->events = ev;
 }

 static void
@@ -459,7 +357,6 @@ static int coroutine_fn iscsi_co_writev(BlockDriverState *bs,
    struct IscsiTask iTask;
    uint64_t lba;
    uint32_t num_sectors;
-    int fua;

    if (!is_request_lun_aligned(sector_num, nb_sectors, iscsilun)) {
        return -EINVAL;
@@ -475,17 +372,15 @@ static int coroutine_fn iscsi_co_writev(BlockDriverState *bs,
    num_sectors = sector_qemu2lun(nb_sectors, iscsilun);
    iscsi_co_init_iscsitask(iscsilun, &iTask);
 retry:
-    fua = iscsilun->dpofua && !bs->enable_write_cache;
-    iTask.force_next_flush = !fua;
    if (iscsilun->use_16_for_rw) {
        iTask.task = iscsi_write16_task(iscsilun->iscsi, iscsilun->lun, lba,
                                        NULL, num_sectors * iscsilun->block_size,
-                                        iscsilun->block_size, 0, 0, fua, 0, 0,
+                                        iscsilun->block_size, 0, 0, 0, 0, 0,
                                        iscsi_co_generic_cb, &iTask);
    } else {
        iTask.task = iscsi_write10_task(iscsilun->iscsi, iscsilun->lun, lba,
                                        NULL, num_sectors * iscsilun->block_size,
-                                        iscsilun->block_size, 0, 0, fua, 0, 0,
+                                        iscsilun->block_size, 0, 0, 0, 0, 0,
                                        iscsi_co_generic_cb, &iTask);
    }
    if (iTask.task == NULL) {
@@ -509,7 +404,7 @@ retry:
    }

    if (iTask.status != SCSI_STATUS_GOOD) {
-        return iTask.err_code;
+        return -EIO;
    }

    iscsi_allocationmap_set(iscsilun, sector_num, nb_sectors);
@@ -553,7 +448,7 @@ static int64_t coroutine_fn iscsi_co_get_block_status(BlockDriverState *bs,
    *pnum = nb_sectors;

    /* LUN does not support logical block provisioning */
-    if (!iscsilun->lbpme) {
+    if (iscsilun->lbpme == 0) {
        goto out;
    }

@@ -698,7 +593,7 @@ retry:
    }

    if (iTask.status != SCSI_STATUS_GOOD) {
-        return iTask.err_code;
+        return -EIO;
    }

    return 0;
@@ -709,12 +604,12 @@ static int coroutine_fn iscsi_co_flush(BlockDriverState *bs)
    IscsiLun *iscsilun = bs->opaque;
    struct IscsiTask iTask;

-    if (!iscsilun->force_next_flush) {
+    if (bs->sg) {
        return 0;
    }
-    iscsilun->force_next_flush = false;

    iscsi_co_init_iscsitask(iscsilun, &iTask);
+
 retry:
    if (iscsi_synchronizecache10_task(iscsilun->iscsi, iscsilun->lun, 0, 0, 0,
                                      0, iscsi_co_generic_cb, &iTask) == NULL) {
@@ -737,7 +632,7 @@ retry:
    }

    if (iTask.status != SCSI_STATUS_GOOD) {
-        return iTask.err_code;
+        return -EIO;
    }

    return 0;
@@ -757,7 +652,7 @@ iscsi_aio_ioctl_cb(struct iscsi_context *iscsi, int status,
    if (status < 0) {
        error_report("Failed to ioctl(SG_IO) to iSCSI lun. %s",
                     iscsi_get_error(iscsi));
-        acb->status = iscsi_translate_sense(&acb->task->sense);
+        acb->status = -EIO;
    }

    acb->ioh->driver_status = 0;
@@ -780,38 +675,6 @@ iscsi_aio_ioctl_cb(struct iscsi_context *iscsi, int status,
    iscsi_schedule_bh(acb);
 }

-static void iscsi_ioctl_bh_completion(void *opaque)
-{
-    IscsiAIOCB *acb = opaque;
-
-    qemu_bh_delete(acb->bh);
-    acb->common.cb(acb->common.opaque, acb->ret);
-    qemu_aio_unref(acb);
-}
-
-static void iscsi_ioctl_handle_emulated(IscsiAIOCB *acb, int req, void *buf)
-{
-    BlockDriverState *bs = acb->common.bs;
-    IscsiLun *iscsilun = bs->opaque;
-    int ret = 0;
-
-    switch (req) {
-    case SG_GET_VERSION_NUM:
-        *(int *)buf = 30000;
-        break;
-    case SG_GET_SCSI_ID:
-        ((struct sg_scsi_id *)buf)->scsi_type = iscsilun->type;
-        break;
-    default:
-        ret = -EINVAL;
-    }
-    assert(!acb->bh);
-    acb->bh = aio_bh_new(bdrv_get_aio_context(bs),
-                         iscsi_ioctl_bh_completion, acb);
-    acb->ret = ret;
-    qemu_bh_schedule(acb->bh);
-}
-
 static BlockAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
        unsigned long int req, void *buf,
        BlockCompletionFunc *cb, void *opaque)
@@ -821,6 +684,8 @@ static BlockAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
    struct iscsi_data data;
    IscsiAIOCB *acb;

+    assert(req == SG_IO);
+
    acb = qemu_aio_get(&iscsi_aiocb_info, bs, cb, opaque);

    acb->iscsilun = iscsilun;
@@ -829,11 +694,6 @@ static BlockAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
    acb->buf         = NULL;
    acb->ioh         = buf;

-    if (req != SG_IO) {
-        iscsi_ioctl_handle_emulated(acb, req, buf);
-        return &acb->common;
-    }
-
    acb->task = malloc(sizeof(struct scsi_task));
    if (acb->task == NULL) {
        error_report("iSCSI: Failed to allocate task for scsi command. %s",
@@ -898,6 +758,38 @@ static BlockAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
    return &acb->common;
 }

+static void ioctl_cb(void *opaque, int status)
+{
+    int *p_status = opaque;
+    *p_status = status;
+}
+
+static int iscsi_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
+{
+    IscsiLun *iscsilun = bs->opaque;
+    int status;
+
+    switch (req) {
+    case SG_GET_VERSION_NUM:
+        *(int *)buf = 30000;
+        break;
+    case SG_GET_SCSI_ID:
+        ((struct sg_scsi_id *)buf)->scsi_type = iscsilun->type;
+        break;
+    case SG_IO:
+        status = -EINPROGRESS;
+        iscsi_aio_ioctl(bs, req, buf, ioctl_cb, &status);
+
+        while (status == -EINPROGRESS) {
+            aio_poll(iscsilun->aio_context, true);
+        }
+
+        return 0;
+    default:
+        return -1;
+    }
+    return 0;
+}
 #endif

 static int64_t
@@ -962,7 +854,7 @@ retry:
    }

    if (iTask.status != SCSI_STATUS_GOOD) {
-        return iTask.err_code;
+        return -EIO;
    }

    iscsi_allocationmap_clear(iscsilun, sector_num, nb_sectors);
@@ -1013,7 +905,6 @@ coroutine_fn iscsi_co_write_zeroes(BlockDriverState *bs, int64_t sector_num,
    }

    iscsi_co_init_iscsitask(iscsilun, &iTask);
-    iTask.force_next_flush = true;
 retry:
    if (use_16_for_ws) {
        iTask.task = iscsi_writesame16_task(iscsilun->iscsi, iscsilun->lun, lba,
@@ -1056,7 +947,7 @@ retry:
    }

    if (iTask.status != SCSI_STATUS_GOOD) {
-        return iTask.err_code;
+        return -EIO;
    }

    if (flags & BDRV_REQ_MAY_UNMAP) {
@@ -1177,37 +1068,16 @@ static char *parse_initiator_name(const char *target)
    return iscsi_name;
 }

-static int parse_timeout(const char *target)
-{
-    QemuOptsList *list;
-    QemuOpts *opts;
-    const char *timeout;
-
-    list = qemu_find_opts("iscsi");
-    if (list) {
-        opts = qemu_opts_find(list, target);
-        if (!opts) {
-            opts = QTAILQ_FIRST(&list->head);
-        }
-        if (opts) {
-            timeout = qemu_opt_get(opts, "timeout");
-            if (timeout) {
-                return atoi(timeout);
-            }
-        }
-    }
-
-    return 0;
-}
-
 static void iscsi_nop_timed_event(void *opaque)
 {
    IscsiLun *iscsilun = opaque;

-    if (iscsi_get_nops_in_flight(iscsilun->iscsi) >= MAX_NOP_FAILURES) {
+    if (iscsi_get_nops_in_flight(iscsilun->iscsi) > MAX_NOP_FAILURES) {
        error_report("iSCSI: NOP timeout. Reconnecting...");
-        iscsilun->request_timed_out = true;
-    } else if (iscsi_nop_out_async(iscsilun->iscsi, NULL, NULL, 0, NULL) != 0) {
+        iscsi_reconnect(iscsilun->iscsi);
+    }
+
+    if (iscsi_nop_out_async(iscsilun->iscsi, NULL, NULL, 0, NULL) != 0) {
        error_report("iSCSI: failed to sent NOP-Out. Disabling NOP messages.");
        return;
    }
@@ -1239,8 +1109,8 @@ static void iscsi_readcapacity_sync(IscsiLun *iscsilun, Error **errp)
                } else {
                    iscsilun->block_size = rc16->block_length;
                    iscsilun->num_blocks = rc16->returned_lba + 1;
-                    iscsilun->lbpme = !!rc16->lbpme;
-                    iscsilun->lbprz = !!rc16->lbprz;
+                    iscsilun->lbpme = rc16->lbpme;
+                    iscsilun->lbprz = rc16->lbprz;
                    iscsilun->use_16_for_rw = (rc16->returned_lba > 0xffffffff);
                }
            }
@@ -1271,10 +1141,6 @@ static void iscsi_readcapacity_sync(IscsiLun *iscsilun, Error **errp)

    if (task == NULL || task->status != SCSI_STATUS_GOOD) {
        error_setg(errp, "iSCSI: failed to send readcapacity10 command.");
-    } else if (!iscsilun->block_size ||
-               iscsilun->block_size % BDRV_SECTOR_SIZE) {
-        error_setg(errp, "iSCSI: the target returned an invalid "
-                   "block size of %d.", iscsilun->block_size);
    }
    if (task) {
        scsi_free_scsi_task(task);
@@ -1337,8 +1203,9 @@ static void iscsi_detach_aio_context(BlockDriverState *bs)
 {
    IscsiLun *iscsilun = bs->opaque;

-    aio_set_fd_handler(iscsilun->aio_context, iscsi_get_fd(iscsilun->iscsi),
-                       false, NULL, NULL, NULL);
+    aio_set_fd_handler(iscsilun->aio_context,
+                       iscsi_get_fd(iscsilun->iscsi),
+                       NULL, NULL, NULL);
    iscsilun->events = 0;

    if (iscsilun->nop_timer) {
@@ -1346,11 +1213,6 @@ static void iscsi_detach_aio_context(BlockDriverState *bs)
        timer_free(iscsilun->nop_timer);
        iscsilun->nop_timer = NULL;
    }
-    if (iscsilun->event_timer) {
-        timer_del(iscsilun->event_timer);
-        timer_free(iscsilun->event_timer);
-        iscsilun->event_timer = NULL;
-    }
 }

 static void iscsi_attach_aio_context(BlockDriverState *bs,
@@ -1367,22 +1229,13 @@ static void iscsi_attach_aio_context(BlockDriverState *bs,
                                        iscsi_nop_timed_event, iscsilun);
    timer_mod(iscsilun->nop_timer,
              qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + NOP_INTERVAL);
-
-    /* Set up a timer for periodic calls to iscsi_set_events and to
-     * scan for command timeout */
-    iscsilun->event_timer = aio_timer_new(iscsilun->aio_context,
-                                          QEMU_CLOCK_REALTIME, SCALE_MS,
-                                          iscsi_timed_check_events, iscsilun);
-    timer_mod(iscsilun->event_timer,
-              qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + EVENT_INTERVAL);
 }

-static void iscsi_modesense_sync(IscsiLun *iscsilun)
+static bool iscsi_is_write_protected(IscsiLun *iscsilun)
 {
    struct scsi_task *task;
    struct scsi_mode_sense *ms = NULL;
-    iscsilun->write_protected = false;
-    iscsilun->dpofua = false;
+    bool wrprotected = false;

    task = iscsi_modesense6_sync(iscsilun->iscsi, iscsilun->lun,
                                 1, SCSI_MODESENSE_PC_CURRENT,
@@ -1403,18 +1256,22 @@ static void iscsi_modesense_sync(IscsiLun *iscsilun)
                     iscsi_get_error(iscsilun->iscsi));
        goto out;
    }
-    iscsilun->write_protected = ms->device_specific_parameter & 0x80;
-    iscsilun->dpofua          = ms->device_specific_parameter & 0x10;
+    wrprotected = ms->device_specific_parameter & 0x80;

 out:
    if (task) {
        scsi_free_scsi_task(task);
    }
+    return wrprotected;
 }

 /*
 * We support iscsi url's on the form
 * iscsi://[<username>%<password>@]<host>[:<port>]/<targetname>/<lun>
+ *
+ * Note: flags are currently not used by iscsi_open.  If this function
+ * is changed such that flags are used, please examine iscsi_reopen_prepare()
+ * to see if needs to be changed as well.
 */
 static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
                      Error **errp)
@@ -1429,7 +1286,14 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
    QemuOpts *opts;
    Error *local_err = NULL;
    const char *filename;
-    int i, ret = 0, timeout = 0;
+    int i, ret = 0;
+
+    if ((BDRV_SECTOR_SIZE % 512) != 0) {
+        error_setg(errp, "iSCSI: Invalid BDRV_SECTOR_SIZE. "
+                   "BDRV_SECTOR_SIZE(%lld) is not a multiple "
+                   "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);
@@ -1465,7 +1329,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
        goto out;
    }

-    if (iscsi_url->user[0] != '\0') {
+    if (iscsi_url->user != NULL) {
        ret = iscsi_set_initiator_username_pwd(iscsi, iscsi_url->user,
                                              iscsi_url->passwd);
        if (ret != 0) {
@@ -1499,16 +1363,6 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
        goto out;
    }

-    /* timeout handling is broken in libiscsi before 1.15.0 */
-    timeout = parse_timeout(iscsi_url->target);
-#if defined(LIBISCSI_API_VERSION) && LIBISCSI_API_VERSION >= 20150621
-    iscsi_set_timeout(iscsi, timeout);
-#else
-    if (timeout) {
-        error_report("iSCSI: ignoring timeout value for libiscsi <1.15.0");
-    }
-#endif
-
    if (iscsi_full_connect_sync(iscsi, iscsi_url->portal, iscsi_url->lun) != 0) {
        error_setg(errp, "iSCSI: Failed to connect to LUN : %s",
            iscsi_get_error(iscsi));
@@ -1531,11 +1385,9 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
    scsi_free_scsi_task(task);
    task = NULL;

-    iscsi_modesense_sync(iscsilun);
-
    /* Check the write protect flag of the LUN if we want to write */
    if (iscsilun->type == TYPE_DISK && (flags & BDRV_O_RDWR) &&
-        iscsilun->write_protected) {
+        iscsi_is_write_protected(iscsilun)) {
        error_setg(errp, "Cannot open a write protected LUN as read-write");
        ret = -EACCES;
        goto out;
@@ -1610,7 +1462,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
        iscsilun->bl.opt_unmap_gran * iscsilun->block_size <= 16 * 1024 * 1024) {
        iscsilun->cluster_sectors = (iscsilun->bl.opt_unmap_gran *
                                     iscsilun->block_size) >> BDRV_SECTOR_BITS;
-        if (iscsilun->lbprz) {
+        if (iscsilun->lbprz && !(bs->open_flags & BDRV_O_NOCACHE)) {
            iscsilun->allocationmap = iscsi_allocationmap_init(iscsilun);
            if (iscsilun->allocationmap == NULL) {
                ret = -ENOMEM;
@@ -1630,9 +1482,6 @@ out:

    if (ret) {
        if (iscsi != NULL) {
-            if (iscsi_is_logged_in(iscsi)) {
-                iscsi_logout_sync(iscsi);
-            }
            iscsi_destroy_context(iscsi);
        }
        memset(iscsilun, 0, sizeof(IscsiLun));
@@ -1646,9 +1495,6 @@ static void iscsi_close(BlockDriverState *bs)
    struct iscsi_context *iscsi = iscsilun->iscsi;

    iscsi_detach_aio_context(bs);
-    if (iscsi_is_logged_in(iscsi)) {
-        iscsi_logout_sync(iscsi);
-    }
    iscsi_destroy_context(iscsi);
    g_free(iscsilun->zeroblock);
    g_free(iscsilun->allocationmap);
@@ -1695,17 +1541,13 @@ static void iscsi_refresh_limits(BlockDriverState *bs, Error **errp)
        sector_limits_lun2qemu(iscsilun->bl.opt_xfer_len, iscsilun);
 }

-/* Note that this will not re-establish a connection with an iSCSI target - it
- * is effectively a NOP.  */
+/* Since iscsi_open() ignores bdrv_flags, there is nothing to do here in
+ * prepare.  Note that this will not re-establish a connection with an iSCSI
+ * target - it is effectively a NOP.  */
 static int iscsi_reopen_prepare(BDRVReopenState *state,
                                BlockReopenQueue *queue, Error **errp)
 {
-    IscsiLun *iscsilun = state->bs->opaque;
-
-    if (state->flags & BDRV_O_RDWR && iscsilun->write_protected) {
-        error_setg(errp, "Cannot open a write protected LUN as read-write");
-        return -EACCES;
-    }
+    /* NOP */
    return 0;
 }

@@ -1784,7 +1626,7 @@ out:
 static int iscsi_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
 {
    IscsiLun *iscsilun = bs->opaque;
-    bdi->unallocated_blocks_are_zero = iscsilun->lbprz;
+    bdi->unallocated_blocks_are_zero = !!iscsilun->lbprz;
    bdi->can_write_zeroes_with_unmap = iscsilun->lbprz && iscsilun->lbp.lbpws;
    bdi->cluster_size = iscsilun->cluster_sectors * BDRV_SECTOR_SIZE;
    return 0;
@@ -1828,6 +1670,7 @@ static BlockDriver bdrv_iscsi = {
    .bdrv_co_flush_to_disk = iscsi_co_flush,

 #ifdef __linux__
+    .bdrv_ioctl       = iscsi_ioctl,
    .bdrv_aio_ioctl   = iscsi_aio_ioctl,
 #endif

@@ -1856,10 +1699,6 @@ static QemuOptsList qemu_iscsi_opts = {
            .name = "initiator-name",
            .type = QEMU_OPT_STRING,
            .help = "Initiator iqn name to use when connecting",
-        },{
-            .name = "timeout",
-            .type = QEMU_OPT_NUMBER,
-            .help = "Request timeout in seconds (default 0 = no timeout)",
        },
        { /* end of list */ }
    },
@@ -35,14 +35,14 @@ struct qemu_laiocb {
    size_t nbytes;
    QEMUIOVector *qiov;
    bool is_read;
-    QSIMPLEQ_ENTRY(qemu_laiocb) next;
+    QLIST_ENTRY(qemu_laiocb) node;
 };

 typedef struct {
+    struct iocb *iocbs[MAX_QUEUED_IO];
    int plugged;
-    unsigned int n;
-    bool blocked;
-    QSIMPLEQ_HEAD(, qemu_laiocb) pending;
+    unsigned int size;
+    unsigned int idx;
 } LaioQueue;

 struct qemu_laio_state {
@@ -59,8 +59,6 @@ struct qemu_laio_state {
    int event_max;
 };

-static void ioq_submit(struct qemu_laio_state *s);
-
 static inline ssize_t io_event_ret(struct io_event *ev)
 {
    return (ssize_t)(((uint64_t)ev->res2 << 32) | ev->res);
@@ -137,10 +135,6 @@ static void qemu_laio_completion_bh(void *opaque)

        qemu_laio_process_completion(s, laiocb);
    }
-
-    if (!s->io_q.plugged && !QSIMPLEQ_EMPTY(&s->io_q.pending)) {
-        ioq_submit(s);
-    }
 }

 static void qemu_laio_completion_cb(EventNotifier *e)
@@ -178,41 +172,50 @@ static const AIOCBInfo laio_aiocb_info = {

 static void ioq_init(LaioQueue *io_q)
 {
-    QSIMPLEQ_INIT(&io_q->pending);
+    io_q->size = MAX_QUEUED_IO;
+    io_q->idx = 0;
    io_q->plugged = 0;
-    io_q->n = 0;
-    io_q->blocked = false;
 }

-static void ioq_submit(struct qemu_laio_state *s)
+static int ioq_submit(struct qemu_laio_state *s)
 {
-    int ret, len;
-    struct qemu_laiocb *aiocb;
-    struct iocb *iocbs[MAX_QUEUED_IO];
-    QSIMPLEQ_HEAD(, qemu_laiocb) completed;
+    int ret, i = 0;
+    int len = s->io_q.idx;

    do {
-        len = 0;
-        QSIMPLEQ_FOREACH(aiocb, &s->io_q.pending, next) {
-            iocbs[len++] = &aiocb->iocb;
-            if (len == MAX_QUEUED_IO) {
-                break;
-            }
-        }
+        ret = io_submit(s->ctx, len, s->io_q.iocbs);
+    } while (i++ < 3 && ret == -EAGAIN);

-        ret = io_submit(s->ctx, len, iocbs);
-        if (ret == -EAGAIN) {
-            break;
-        }
-        if (ret < 0) {
-            abort();
-        }
+    /* empty io queue */
+    s->io_q.idx = 0;

-        s->io_q.n -= ret;
-        aiocb = container_of(iocbs[ret - 1], struct qemu_laiocb, iocb);
-        QSIMPLEQ_SPLIT_AFTER(&s->io_q.pending, aiocb, next, &completed);
-    } while (ret == len && !QSIMPLEQ_EMPTY(&s->io_q.pending));
-    s->io_q.blocked = (s->io_q.n > 0);
+    if (ret < 0) {
+        i = 0;
+    } else {
+        i = ret;
+    }
+
+    for (; i < len; i++) {
+        struct qemu_laiocb *laiocb =
+            container_of(s->io_q.iocbs[i], struct qemu_laiocb, iocb);
+
+        laiocb->ret = (ret < 0) ? ret : -EIO;
+        qemu_laio_process_completion(s, laiocb);
+    }
+    return ret;
+}
+
+static void ioq_enqueue(struct qemu_laio_state *s, struct iocb *iocb)
+{
+    unsigned int idx = s->io_q.idx;
+
+    s->io_q.iocbs[idx++] = iocb;
+    s->io_q.idx = idx;
+
+    /* submit immediately if queue is full */
+    if (idx == s->io_q.size) {
+        ioq_submit(s);
+    }
 }

 void laio_io_plug(BlockDriverState *bs, void *aio_ctx)
@@ -222,19 +225,22 @@ void laio_io_plug(BlockDriverState *bs, void *aio_ctx)
    s->io_q.plugged++;
 }

-void laio_io_unplug(BlockDriverState *bs, void *aio_ctx, bool unplug)
+int laio_io_unplug(BlockDriverState *bs, void *aio_ctx, bool unplug)
 {
    struct qemu_laio_state *s = aio_ctx;
+    int ret = 0;

    assert(s->io_q.plugged > 0 || !unplug);

    if (unplug && --s->io_q.plugged > 0) {
-        return;
+        return 0;
    }

-    if (!s->io_q.blocked && !QSIMPLEQ_EMPTY(&s->io_q.pending)) {
-        ioq_submit(s);
+    if (s->io_q.idx > 0) {
+        ret = ioq_submit(s);
    }
+
+    return ret;
 }

 BlockAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
@@ -270,11 +276,12 @@ BlockAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
    }
    io_set_eventfd(&laiocb->iocb, event_notifier_get_fd(&s->e));

-    QSIMPLEQ_INSERT_TAIL(&s->io_q.pending, laiocb, next);
-    s->io_q.n++;
-    if (!s->io_q.blocked &&
-        (!s->io_q.plugged || s->io_q.n >= MAX_QUEUED_IO)) {
-        ioq_submit(s);
+    if (!s->io_q.plugged) {
+        if (io_submit(s->ctx, 1, &iocbs) < 0) {
+            goto out_free_aiocb;
+        }
+    } else {
+        ioq_enqueue(s, iocbs);
    }
    return &laiocb->common;

@@ -287,7 +294,7 @@ void laio_detach_aio_context(void *s_, AioContext *old_context)
 {
    struct qemu_laio_state *s = s_;

-    aio_set_event_notifier(old_context, &s->e, false, NULL);
+    aio_set_event_notifier(old_context, &s->e, NULL);
    qemu_bh_delete(s->completion_bh);
 }

@@ -296,8 +303,7 @@ void laio_attach_aio_context(void *s_, AioContext *new_context)
    struct qemu_laio_state *s = s_;

    s->completion_bh = aio_bh_new(new_context, qemu_laio_completion_bh, s);
-    aio_set_event_notifier(new_context, &s->e, false,
-                           qemu_laio_completion_cb);
+    aio_set_event_notifier(new_context, &s->e, qemu_laio_completion_cb);
 }

 void *laio_init(void)
@@ -14,14 +14,11 @@
 #include "trace.h"
 #include "block/blockjob.h"
 #include "block/block_int.h"
-#include "sysemu/block-backend.h"
-#include "qapi/qmp/qerror.h"
 #include "qemu/ratelimit.h"
 #include "qemu/bitmap.h"

 #define SLICE_TIME    100000000ULL /* ns */
 #define MAX_IN_FLIGHT 16
-#define DEFAULT_MIRROR_BUF_SIZE   (10 << 20)

 /* The mirroring buffer is a list of granularity-sized chunks.
 * Free chunks are organized in a list.
@@ -60,8 +57,6 @@ typedef struct MirrorBlockJob {
    int in_flight;
    int sectors_in_flight;
    int ret;
-    bool unmap;
-    bool waiting_for_io;
 } MirrorBlockJob;

 typedef struct MirrorOp {
@@ -114,9 +109,13 @@ static void mirror_iteration_done(MirrorOp *op, int ret)
    }

    qemu_iovec_destroy(&op->qiov);
-    g_free(op);
+    g_slice_free(MirrorOp, op);

-    if (s->waiting_for_io) {
+    /* Enter coroutine when it is not sleeping.  The coroutine sleeps to
+     * rate-limit itself.  The coroutine will eventually resume since there is
+     * a sleep timeout so don't wake it early.
+     */
+    if (s->common.busy) {
        qemu_coroutine_enter(s->common.co, NULL);
    }
 }
@@ -126,9 +125,10 @@ static void mirror_write_complete(void *opaque, int ret)
    MirrorOp *op = opaque;
    MirrorBlockJob *s = op->s;
    if (ret < 0) {
+        BlockDriverState *source = s->common.bs;
        BlockErrorAction action;

-        bdrv_set_dirty_bitmap(s->dirty_bitmap, op->sector_num, op->nb_sectors);
+        bdrv_set_dirty(source, op->sector_num, op->nb_sectors);
        action = mirror_error_action(s, false, -ret);
        if (action == BLOCK_ERROR_ACTION_REPORT && s->ret >= 0) {
            s->ret = ret;
@@ -142,9 +142,10 @@ static void mirror_read_complete(void *opaque, int ret)
    MirrorOp *op = opaque;
    MirrorBlockJob *s = op->s;
    if (ret < 0) {
+        BlockDriverState *source = s->common.bs;
        BlockErrorAction action;

-        bdrv_set_dirty_bitmap(s->dirty_bitmap, op->sector_num, op->nb_sectors);
+        bdrv_set_dirty(source, op->sector_num, op->nb_sectors);
        action = mirror_error_action(s, true, -ret);
        if (action == BLOCK_ERROR_ACTION_REPORT && s->ret >= 0) {
            s->ret = ret;
@@ -164,14 +165,13 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
    int64_t end, sector_num, next_chunk, next_sector, hbitmap_next_sector;
    uint64_t delay_ns = 0;
    MirrorOp *op;
-    int pnum;
-    int64_t ret;

    s->sector_num = hbitmap_iter_next(&s->hbi);
    if (s->sector_num < 0) {
-        bdrv_dirty_iter_init(s->dirty_bitmap, &s->hbi);
+        bdrv_dirty_iter_init(source, s->dirty_bitmap, &s->hbi);
        s->sector_num = hbitmap_iter_next(&s->hbi);
-        trace_mirror_restart_iter(s, bdrv_get_dirty_count(s->dirty_bitmap));
+        trace_mirror_restart_iter(s,
+                                  bdrv_get_dirty_count(source, s->dirty_bitmap));
        assert(s->sector_num >= 0);
    }

@@ -201,9 +201,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
    /* Wait for I/O to this cluster (from a previous iteration) to be done.  */
    while (test_bit(next_chunk, s->in_flight_bitmap)) {
        trace_mirror_yield_in_flight(s, sector_num, s->in_flight);
-        s->waiting_for_io = true;
        qemu_coroutine_yield();
-        s->waiting_for_io = false;
    }

    do {
@@ -239,18 +237,12 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
         */
        while (nb_chunks == 0 && s->buf_free_count < added_chunks) {
            trace_mirror_yield_buf_busy(s, nb_chunks, s->in_flight);
-            s->waiting_for_io = true;
            qemu_coroutine_yield();
-            s->waiting_for_io = false;
        }
        if (s->buf_free_count < nb_chunks + added_chunks) {
            trace_mirror_break_buf_busy(s, nb_chunks, s->in_flight);
            break;
        }
-        if (IOV_MAX < nb_chunks + added_chunks) {
-            trace_mirror_break_iov_max(s, nb_chunks, added_chunks);
-            break;
-        }

        /* We have enough free space to copy these sectors.  */
        bitmap_set(s->in_flight_bitmap, next_chunk, added_chunks);
@@ -265,7 +257,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
    } while (delay_ns == 0 && next_sector < end);

    /* Allocate a MirrorOp that is used as an AIO callback.  */
-    op = g_new(MirrorOp, 1);
+    op = g_slice_new(MirrorOp);
    op->s = s;
    op->sector_num = sector_num;
    op->nb_sectors = nb_sectors;
@@ -294,28 +286,14 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
        next_sector += sectors_per_chunk;
    }

-    bdrv_reset_dirty_bitmap(s->dirty_bitmap, sector_num, nb_sectors);
+    bdrv_reset_dirty(source, sector_num, nb_sectors);

    /* Copy the dirty cluster.  */
    s->in_flight++;
    s->sectors_in_flight += nb_sectors;
    trace_mirror_one_iteration(s, sector_num, nb_sectors);
-
-    ret = bdrv_get_block_status_above(source, NULL, sector_num,
-                                      nb_sectors, &pnum);
-    if (ret < 0 || pnum < nb_sectors ||
-            (ret & BDRV_BLOCK_DATA && !(ret & BDRV_BLOCK_ZERO))) {
-        bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors,
-                       mirror_read_complete, op);
-    } else if (ret & BDRV_BLOCK_ZERO) {
-        bdrv_aio_write_zeroes(s->target, sector_num, op->nb_sectors,
-                              s->unmap ? BDRV_REQ_MAY_UNMAP : 0,
-                              mirror_write_complete, op);
-    } else {
-        assert(!(ret & BDRV_BLOCK_DATA));
-        bdrv_aio_discard(s->target, sector_num, op->nb_sectors,
-                         mirror_write_complete, op);
-    }
+    bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors,
+                   mirror_read_complete, op);
    return delay_ns;
 }

@@ -339,9 +317,7 @@ static void mirror_free_init(MirrorBlockJob *s)
 static void mirror_drain(MirrorBlockJob *s)
 {
    while (s->in_flight > 0) {
-        s->waiting_for_io = true;
        qemu_coroutine_yield();
-        s->waiting_for_io = false;
    }
 }

@@ -354,11 +330,6 @@ static void mirror_exit(BlockJob *job, void *opaque)
    MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
    MirrorExitData *data = opaque;
    AioContext *replace_aio_context = NULL;
-    BlockDriverState *src = s->common.bs;
-
-    /* Make sure that the source BDS doesn't go away before we called
-     * block_job_completed(). */
-    bdrv_ref(src);

    if (s->to_replace) {
        replace_aio_context = bdrv_get_aio_context(s->to_replace);
@@ -373,7 +344,14 @@ static void mirror_exit(BlockJob *job, void *opaque)
        if (bdrv_get_flags(s->target) != bdrv_get_flags(to_replace)) {
            bdrv_reopen(s->target, bdrv_get_flags(to_replace), NULL);
        }
-        bdrv_replace_in_backing_chain(to_replace, s->target);
+        bdrv_swap(s->target, to_replace);
+        if (s->common.driver->job_type == BLOCK_JOB_TYPE_COMMIT) {
+            /* drop the bs loop chain formed by the swap: break the loop then
+             * trigger the unref from the top one */
+            BlockDriverState *p = s->base->backing_hd;
+            bdrv_set_backing_hd(s->base, NULL);
+            bdrv_unref(p);
+        }
    }
    if (s->to_replace) {
        bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
@@ -384,12 +362,9 @@ static void mirror_exit(BlockJob *job, void *opaque)
        aio_context_release(replace_aio_context);
    }
    g_free(s->replaces);
-    bdrv_op_unblock_all(s->target, s->common.blocker);
    bdrv_unref(s->target);
    block_job_completed(&s->common, data->ret);
    g_free(data);
-    bdrv_drained_end(src);
-    bdrv_unref(src);
 }

 static void coroutine_fn mirror_run(void *opaque)
@@ -397,11 +372,10 @@ static void coroutine_fn mirror_run(void *opaque)
    MirrorBlockJob *s = opaque;
    MirrorExitData *data;
    BlockDriverState *bs = s->common.bs;
-    int64_t sector_num, end, length;
+    int64_t sector_num, end, sectors_per_chunk, length;
    uint64_t last_pause_ns;
    BlockDriverInfo bdi;
-    char backing_filename[2]; /* we only need 2 characters because we are only
-                                 checking for a NULL string */
+    char backing_filename[1024];
    int ret = 0;
    int n;

@@ -433,7 +407,7 @@ static void coroutine_fn mirror_run(void *opaque)
     */
    bdrv_get_backing_filename(s->target, backing_filename,
                              sizeof(backing_filename));
-    if (backing_filename[0] && !s->target->backing) {
+    if (backing_filename[0] && !s->target->backing_hd) {
        ret = bdrv_get_info(s->target, &bdi);
        if (ret < 0) {
            goto immediate_exit;
@@ -451,44 +425,33 @@ static void coroutine_fn mirror_run(void *opaque)
        goto immediate_exit;
    }

+    sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
    mirror_free_init(s);

-    last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
    if (!s->is_none_mode) {
        /* First part, loop on the sectors and initialize the dirty bitmap.  */
        BlockDriverState *base = s->base;
-        bool mark_all_dirty = s->base == NULL && !bdrv_has_zero_init(s->target);
-
        for (sector_num = 0; sector_num < end; ) {
-            /* Just to make sure we are not exceeding int limit. */
-            int nb_sectors = MIN(INT_MAX >> BDRV_SECTOR_BITS,
-                                 end - sector_num);
-            int64_t now = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
-
-            if (now - last_pause_ns > SLICE_TIME) {
-                last_pause_ns = now;
-                block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, 0);
-            }
-
-            if (block_job_is_cancelled(&s->common)) {
-                goto immediate_exit;
-            }
-
-            ret = bdrv_is_allocated_above(bs, base, sector_num, nb_sectors, &n);
+            int64_t next = (sector_num | (sectors_per_chunk - 1)) + 1;
+            ret = bdrv_is_allocated_above(bs, base,
+                                          sector_num, next - sector_num, &n);

            if (ret < 0) {
                goto immediate_exit;
            }

            assert(n > 0);
-            if (ret == 1 || mark_all_dirty) {
-                bdrv_set_dirty_bitmap(s->dirty_bitmap, sector_num, n);
+            if (ret == 1) {
+                bdrv_set_dirty(bs, sector_num, n);
+                sector_num = next;
+            } else {
+                sector_num += n;
            }
-            sector_num += n;
        }
    }

-    bdrv_dirty_iter_init(s->dirty_bitmap, &s->hbi);
+    bdrv_dirty_iter_init(bs, s->dirty_bitmap, &s->hbi);
+    last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
    for (;;) {
        uint64_t delay_ns = 0;
        int64_t cnt;
@@ -499,7 +462,7 @@ static void coroutine_fn mirror_run(void *opaque)
            goto immediate_exit;
        }

-        cnt = bdrv_get_dirty_count(s->dirty_bitmap);
+        cnt = bdrv_get_dirty_count(bs, s->dirty_bitmap);
        /* s->common.offset contains the number of bytes already processed so
         * far, cnt is the number of dirty sectors remaining and
         * s->sectors_in_flight is the number of sectors currently being
@@ -508,7 +471,7 @@ static void coroutine_fn mirror_run(void *opaque)
                        (cnt + s->sectors_in_flight) * BDRV_SECTOR_SIZE;

        /* Note that even when no rate limit is applied we need to yield
-         * periodically with no pending I/O so that bdrv_drain_all() returns.
+         * periodically with no pending I/O so that qemu_aio_flush() returns.
         * We do so every SLICE_TIME nanoseconds, or when there is an error,
         * or when the source is clean, whichever comes first.
         */
@@ -517,12 +480,13 @@ static void coroutine_fn mirror_run(void *opaque)
            if (s->in_flight == MAX_IN_FLIGHT || s->buf_free_count == 0 ||
                (cnt == 0 && s->in_flight > 0)) {
                trace_mirror_yield(s, s->in_flight, s->buf_free_count, cnt);
-                s->waiting_for_io = true;
                qemu_coroutine_yield();
-                s->waiting_for_io = false;
                continue;
            } else if (cnt != 0) {
                delay_ns = mirror_iteration(s);
+                if (delay_ns == 0) {
+                    continue;
+                }
            }
        }

@@ -548,7 +512,7 @@ static void coroutine_fn mirror_run(void *opaque)

                should_complete = s->should_complete ||
                    block_job_is_cancelled(&s->common);
-                cnt = bdrv_get_dirty_count(s->dirty_bitmap);
+                cnt = bdrv_get_dirty_count(bs, s->dirty_bitmap);
            }
        }

@@ -563,7 +527,7 @@ static void coroutine_fn mirror_run(void *opaque)
             */
            trace_mirror_before_drain(s, cnt);
            bdrv_drain(bs);
-            cnt = bdrv_get_dirty_count(s->dirty_bitmap);
+            cnt = bdrv_get_dirty_count(bs, s->dirty_bitmap);
        }

        ret = 0;
@@ -602,15 +566,10 @@ immediate_exit:
    g_free(s->cow_bitmap);
    g_free(s->in_flight_bitmap);
    bdrv_release_dirty_bitmap(bs, s->dirty_bitmap);
-    if (s->target->blk) {
-        blk_iostatus_disable(s->target->blk);
-    }
+    bdrv_iostatus_disable(s->target);

    data = g_malloc(sizeof(*data));
    data->ret = ret;
-    /* Before we switch to target in mirror_exit, make sure data doesn't
-     * change. */
-    bdrv_drained_begin(s->common.bs);
    block_job_defer_to_main_loop(&s->common, mirror_exit, data);
 }

@@ -619,7 +578,7 @@ static void mirror_set_speed(BlockJob *job, int64_t speed, Error **errp)
    MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);

    if (speed < 0) {
-        error_setg(errp, QERR_INVALID_PARAMETER, "speed");
+        error_set(errp, QERR_INVALID_PARAMETER, "speed");
        return;
    }
    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
@@ -629,9 +588,7 @@ static void mirror_iostatus_reset(BlockJob *job)
 {
    MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);

-    if (s->target->blk) {
-        blk_iostatus_reset(s->target->blk);
-    }
+    bdrv_iostatus_reset(s->target);
 }

 static void mirror_complete(BlockJob *job, Error **errp)
@@ -646,7 +603,8 @@ static void mirror_complete(BlockJob *job, Error **errp)
        return;
    }
    if (!s->synced) {
-        error_setg(errp, QERR_BLOCK_JOB_NOT_READY, job->id);
+        error_set(errp, QERR_BLOCK_JOB_NOT_READY,
+                  bdrv_get_device_name(job->bs));
        return;
    }

@@ -654,9 +612,9 @@ static void mirror_complete(BlockJob *job, Error **errp)
    if (s->replaces) {
        AioContext *replace_aio_context;

-        s->to_replace = bdrv_find_node(s->replaces);
+        s->to_replace = check_to_replace_node(s->replaces, &local_err);
        if (!s->to_replace) {
-            error_setg(errp, "Node name '%s' not found", s->replaces);
+            error_propagate(errp, local_err);
            return;
        }

@@ -672,7 +630,7 @@ static void mirror_complete(BlockJob *job, Error **errp)
    }

    s->should_complete = true;
-    block_job_enter(&s->common);
+    block_job_resume(job);
 }

 static const BlockJobDriver mirror_job_driver = {
@@ -694,11 +652,10 @@ static const BlockJobDriver commit_active_job_driver = {

 static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
                             const char *replaces,
-                             int64_t speed, uint32_t granularity,
+                             int64_t speed, int64_t granularity,
                             int64_t buf_size,
                             BlockdevOnError on_source_error,
                             BlockdevOnError on_target_error,
-                             bool unmap,
                             BlockCompletionFunc *cb,
                             void *opaque, Error **errp,
                             const BlockJobDriver *driver,
@@ -707,26 +664,26 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
    MirrorBlockJob *s;

    if (granularity == 0) {
-        granularity = bdrv_get_default_bitmap_granularity(target);
+        /* Choose the default granularity based on the target file's cluster
+         * size, clamped between 4k and 64k.  */
+        BlockDriverInfo bdi;
+        if (bdrv_get_info(target, &bdi) >= 0 && bdi.cluster_size != 0) {
+            granularity = MAX(4096, bdi.cluster_size);
+            granularity = MIN(65536, granularity);
+        } else {
+            granularity = 65536;
+        }
    }

    assert ((granularity & (granularity - 1)) == 0);

    if ((on_source_error == BLOCKDEV_ON_ERROR_STOP ||
         on_source_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        (!bs->blk || !blk_iostatus_is_enabled(bs->blk))) {
-        error_setg(errp, QERR_INVALID_PARAMETER, "on-source-error");
+        !bdrv_iostatus_is_enabled(bs)) {
+        error_set(errp, QERR_INVALID_PARAMETER, "on-source-error");
        return;
    }

-    if (buf_size < 0) {
-        error_setg(errp, "Invalid parameter 'buf-size'");
-        return;
-    }
-
-    if (buf_size == 0) {
-        buf_size = DEFAULT_MIRROR_BUF_SIZE;
-    }

    s = block_job_create(driver, bs, speed, cb, opaque, errp);
    if (!s) {
@@ -740,23 +697,15 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
    s->is_none_mode = is_none_mode;
    s->base = base;
    s->granularity = granularity;
-    s->buf_size = ROUND_UP(buf_size, granularity);
-    s->unmap = unmap;
+    s->buf_size = MAX(buf_size, granularity);

-    s->dirty_bitmap = bdrv_create_dirty_bitmap(bs, granularity, NULL, errp);
+    s->dirty_bitmap = bdrv_create_dirty_bitmap(bs, granularity, errp);
    if (!s->dirty_bitmap) {
-        g_free(s->replaces);
-        block_job_unref(&s->common);
        return;
    }
-
-    bdrv_op_block_all(s->target, s->common.blocker);
-
    bdrv_set_enable_write_cache(s->target, true);
-    if (s->target->blk) {
-        blk_set_on_error(s->target->blk, on_target_error, on_target_error);
-        blk_iostatus_enable(s->target->blk);
-    }
+    bdrv_set_on_error(s->target, on_target_error, on_target_error);
+    bdrv_iostatus_enable(s->target);
    s->common.co = qemu_coroutine_create(mirror_run);
    trace_mirror_start(bs, s, s->common.co, opaque);
    qemu_coroutine_enter(s->common.co, s);
@@ -764,25 +713,20 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,

 void mirror_start(BlockDriverState *bs, BlockDriverState *target,
                  const char *replaces,
-                  int64_t speed, uint32_t granularity, int64_t buf_size,
+                  int64_t speed, int64_t granularity, int64_t buf_size,
                  MirrorSyncMode mode, BlockdevOnError on_source_error,
                  BlockdevOnError on_target_error,
-                  bool unmap,
                  BlockCompletionFunc *cb,
                  void *opaque, Error **errp)
 {
    bool is_none_mode;
    BlockDriverState *base;

-    if (mode == MIRROR_SYNC_MODE_INCREMENTAL) {
-        error_setg(errp, "Sync mode 'incremental' not supported");
-        return;
-    }
    is_none_mode = mode == MIRROR_SYNC_MODE_NONE;
-    base = mode == MIRROR_SYNC_MODE_TOP ? backing_bs(bs) : NULL;
+    base = mode == MIRROR_SYNC_MODE_TOP ? bs->backing_hd : NULL;
    mirror_start_job(bs, target, replaces,
                     speed, granularity, buf_size,
-                     on_source_error, on_target_error, unmap, cb, opaque, errp,
+                     on_source_error, on_target_error, cb, opaque, errp,
                     &mirror_job_driver, is_none_mode, base);
 }

@@ -830,7 +774,7 @@ void commit_active_start(BlockDriverState *bs, BlockDriverState *base,

    bdrv_ref(base);
    mirror_start_job(bs, base, NULL, speed, 0, 0,
-                     on_error, on_error, false, cb, opaque, &local_err,
+                     on_error, on_error, cb, opaque, &local_err,
                     &commit_active_job_driver, false, base);
    if (local_err) {
        error_propagate(errp, local_err);
@@ -43,23 +43,20 @@ static void nbd_recv_coroutines_enter_all(NbdClientSession *s)
    }
 }

-static void nbd_teardown_connection(BlockDriverState *bs)
+static void nbd_teardown_connection(NbdClientSession *client)
 {
-    NbdClientSession *client = nbd_get_client_session(bs);
-
    /* finish any pending coroutines */
    shutdown(client->sock, 2);
    nbd_recv_coroutines_enter_all(client);

-    nbd_client_detach_aio_context(bs);
+    nbd_client_session_detach_aio_context(client);
    closesocket(client->sock);
    client->sock = -1;
 }

 static void nbd_reply_ready(void *opaque)
 {
-    BlockDriverState *bs = opaque;
-    NbdClientSession *s = nbd_get_client_session(bs);
+    NbdClientSession *s = opaque;
    uint64_t i;
    int ret;

@@ -92,40 +89,28 @@ static void nbd_reply_ready(void *opaque)
    }

 fail:
-    nbd_teardown_connection(bs);
+    nbd_teardown_connection(s);
 }

 static void nbd_restart_write(void *opaque)
 {
-    BlockDriverState *bs = opaque;
+    NbdClientSession *s = opaque;

-    qemu_coroutine_enter(nbd_get_client_session(bs)->send_coroutine, NULL);
+    qemu_coroutine_enter(s->send_coroutine, NULL);
 }

-static int nbd_co_send_request(BlockDriverState *bs,
-                               struct nbd_request *request,
-                               QEMUIOVector *qiov, int offset)
+static int nbd_co_send_request(NbdClientSession *s,
+    struct nbd_request *request,
+    QEMUIOVector *qiov, int offset)
 {
-    NbdClientSession *s = nbd_get_client_session(bs);
    AioContext *aio_context;
-    int rc, ret, i;
+    int rc, ret;

    qemu_co_mutex_lock(&s->send_mutex);
-
-    for (i = 0; i < MAX_NBD_REQUESTS; i++) {
-        if (s->recv_coroutine[i] == NULL) {
-            s->recv_coroutine[i] = qemu_coroutine_self();
-            break;
-        }
-    }
-
-    assert(i < MAX_NBD_REQUESTS);
-    request->handle = INDEX_TO_HANDLE(s, i);
    s->send_coroutine = qemu_coroutine_self();
-    aio_context = bdrv_get_aio_context(bs);
-
-    aio_set_fd_handler(aio_context, s->sock, false,
-                       nbd_reply_ready, nbd_restart_write, bs);
+    aio_context = bdrv_get_aio_context(s->bs);
+    aio_set_fd_handler(aio_context, s->sock,
+                       nbd_reply_ready, nbd_restart_write, s);
    if (qiov) {
        if (!s->is_unix) {
            socket_set_cork(s->sock, 1);
@@ -144,8 +129,7 @@ static int nbd_co_send_request(BlockDriverState *bs,
    } else {
        rc = nbd_send_request(s->sock, request);
    }
-    aio_set_fd_handler(aio_context, s->sock, false,
-                       nbd_reply_ready, NULL, bs);
+    aio_set_fd_handler(aio_context, s->sock, nbd_reply_ready, NULL, s);
    s->send_coroutine = NULL;
    qemu_co_mutex_unlock(&s->send_mutex);
    return rc;
@@ -180,6 +164,8 @@ static void nbd_co_receive_reply(NbdClientSession *s,
 static void nbd_coroutine_start(NbdClientSession *s,
   struct nbd_request *request)
 {
+    int i;
+
    /* Poor man semaphore.  The free_sema is locked when no other request
     * can be accepted, and unlocked after receiving one reply.  */
    if (s->in_flight >= MAX_NBD_REQUESTS - 1) {
@@ -188,7 +174,15 @@ static void nbd_coroutine_start(NbdClientSession *s,
    }
    s->in_flight++;

-    /* s->recv_coroutine[i] is set as soon as we get the send_lock.  */
+    for (i = 0; i < MAX_NBD_REQUESTS; i++) {
+        if (s->recv_coroutine[i] == NULL) {
+            s->recv_coroutine[i] = qemu_coroutine_self();
+            break;
+        }
+    }
+
+    assert(i < MAX_NBD_REQUESTS);
+    request->handle = INDEX_TO_HANDLE(s, i);
 }

 static void nbd_coroutine_end(NbdClientSession *s,
@@ -201,11 +195,10 @@ static void nbd_coroutine_end(NbdClientSession *s,
    }
 }

-static int nbd_co_readv_1(BlockDriverState *bs, int64_t sector_num,
+static int nbd_co_readv_1(NbdClientSession *client, int64_t sector_num,
                          int nb_sectors, QEMUIOVector *qiov,
                          int offset)
 {
-    NbdClientSession *client = nbd_get_client_session(bs);
    struct nbd_request request = { .type = NBD_CMD_READ };
    struct nbd_reply reply;
    ssize_t ret;
@@ -214,7 +207,7 @@ static int nbd_co_readv_1(BlockDriverState *bs, int64_t sector_num,
    request.len = nb_sectors * 512;

    nbd_coroutine_start(client, &request);
-    ret = nbd_co_send_request(bs, &request, NULL, 0);
+    ret = nbd_co_send_request(client, &request, NULL, 0);
    if (ret < 0) {
        reply.error = -ret;
    } else {
@@ -225,16 +218,15 @@ static int nbd_co_readv_1(BlockDriverState *bs, int64_t sector_num,

 }

-static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num,
+static int nbd_co_writev_1(NbdClientSession *client, int64_t sector_num,
                           int nb_sectors, QEMUIOVector *qiov,
                           int offset)
 {
-    NbdClientSession *client = nbd_get_client_session(bs);
    struct nbd_request request = { .type = NBD_CMD_WRITE };
    struct nbd_reply reply;
    ssize_t ret;

-    if (!bdrv_enable_write_cache(bs) &&
+    if (!bdrv_enable_write_cache(client->bs) &&
        (client->nbdflags & NBD_FLAG_SEND_FUA)) {
        request.type |= NBD_CMD_FLAG_FUA;
    }
@@ -243,7 +235,7 @@ static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num,
    request.len = nb_sectors * 512;

    nbd_coroutine_start(client, &request);
-    ret = nbd_co_send_request(bs, &request, qiov, offset);
+    ret = nbd_co_send_request(client, &request, qiov, offset);
    if (ret < 0) {
        reply.error = -ret;
    } else {
@@ -257,13 +249,14 @@ static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num,
 * remain aligned to 4K. */
 #define NBD_MAX_SECTORS 2040

-int nbd_client_co_readv(BlockDriverState *bs, int64_t sector_num,
-                        int nb_sectors, QEMUIOVector *qiov)
+int nbd_client_session_co_readv(NbdClientSession *client, int64_t sector_num,
+    int nb_sectors, QEMUIOVector *qiov)
 {
    int offset = 0;
    int ret;
    while (nb_sectors > NBD_MAX_SECTORS) {
-        ret = nbd_co_readv_1(bs, sector_num, NBD_MAX_SECTORS, qiov, offset);
+        ret = nbd_co_readv_1(client, sector_num,
+                             NBD_MAX_SECTORS, qiov, offset);
        if (ret < 0) {
            return ret;
        }
@@ -271,16 +264,17 @@ int nbd_client_co_readv(BlockDriverState *bs, int64_t sector_num,
        sector_num += NBD_MAX_SECTORS;
        nb_sectors -= NBD_MAX_SECTORS;
    }
-    return nbd_co_readv_1(bs, sector_num, nb_sectors, qiov, offset);
+    return nbd_co_readv_1(client, sector_num, nb_sectors, qiov, offset);
 }

-int nbd_client_co_writev(BlockDriverState *bs, int64_t sector_num,
-                         int nb_sectors, QEMUIOVector *qiov)
+int nbd_client_session_co_writev(NbdClientSession *client, int64_t sector_num,
+                                 int nb_sectors, QEMUIOVector *qiov)
 {
    int offset = 0;
    int ret;
    while (nb_sectors > NBD_MAX_SECTORS) {
-        ret = nbd_co_writev_1(bs, sector_num, NBD_MAX_SECTORS, qiov, offset);
+        ret = nbd_co_writev_1(client, sector_num,
+                              NBD_MAX_SECTORS, qiov, offset);
        if (ret < 0) {
            return ret;
        }
@@ -288,12 +282,11 @@ int nbd_client_co_writev(BlockDriverState *bs, int64_t sector_num,
        sector_num += NBD_MAX_SECTORS;
        nb_sectors -= NBD_MAX_SECTORS;
    }
-    return nbd_co_writev_1(bs, sector_num, nb_sectors, qiov, offset);
+    return nbd_co_writev_1(client, sector_num, nb_sectors, qiov, offset);
 }

-int nbd_client_co_flush(BlockDriverState *bs)
+int nbd_client_session_co_flush(NbdClientSession *client)
 {
-    NbdClientSession *client = nbd_get_client_session(bs);
    struct nbd_request request = { .type = NBD_CMD_FLUSH };
    struct nbd_reply reply;
    ssize_t ret;
@@ -310,7 +303,7 @@ int nbd_client_co_flush(BlockDriverState *bs)
    request.len = 0;

    nbd_coroutine_start(client, &request);
-    ret = nbd_co_send_request(bs, &request, NULL, 0);
+    ret = nbd_co_send_request(client, &request, NULL, 0);
    if (ret < 0) {
        reply.error = -ret;
    } else {
@@ -320,10 +313,9 @@ int nbd_client_co_flush(BlockDriverState *bs)
    return -reply.error;
 }

-int nbd_client_co_discard(BlockDriverState *bs, int64_t sector_num,
-                          int nb_sectors)
+int nbd_client_session_co_discard(NbdClientSession *client, int64_t sector_num,
+    int nb_sectors)
 {
-    NbdClientSession *client = nbd_get_client_session(bs);
    struct nbd_request request = { .type = NBD_CMD_TRIM };
    struct nbd_reply reply;
    ssize_t ret;
@@ -335,7 +327,7 @@ int nbd_client_co_discard(BlockDriverState *bs, int64_t sector_num,
    request.len = nb_sectors * 512;

    nbd_coroutine_start(client, &request);
-    ret = nbd_co_send_request(bs, &request, NULL, 0);
+    ret = nbd_co_send_request(client, &request, NULL, 0);
    if (ret < 0) {
        reply.error = -ret;
    } else {
@@ -346,49 +338,51 @@ int nbd_client_co_discard(BlockDriverState *bs, int64_t sector_num,

 }

-void nbd_client_detach_aio_context(BlockDriverState *bs)
+void nbd_client_session_detach_aio_context(NbdClientSession *client)
 {
-    aio_set_fd_handler(bdrv_get_aio_context(bs),
-                       nbd_get_client_session(bs)->sock,
-                       false, NULL, NULL, NULL);
+    aio_set_fd_handler(bdrv_get_aio_context(client->bs), client->sock,
+                       NULL, NULL, NULL);
 }

-void nbd_client_attach_aio_context(BlockDriverState *bs,
-                                   AioContext *new_context)
+void nbd_client_session_attach_aio_context(NbdClientSession *client,
+                                           AioContext *new_context)
 {
-    aio_set_fd_handler(new_context, nbd_get_client_session(bs)->sock,
-                       false, nbd_reply_ready, NULL, bs);
+    aio_set_fd_handler(new_context, client->sock,
+                       nbd_reply_ready, NULL, client);
 }

-void nbd_client_close(BlockDriverState *bs)
+void nbd_client_session_close(NbdClientSession *client)
 {
-    NbdClientSession *client = nbd_get_client_session(bs);
    struct nbd_request request = {
        .type = NBD_CMD_DISC,
        .from = 0,
        .len = 0
    };

+    if (!client->bs) {
+        return;
+    }
    if (client->sock == -1) {
        return;
    }

    nbd_send_request(client->sock, &request);

-    nbd_teardown_connection(bs);
+    nbd_teardown_connection(client);
+    client->bs = NULL;
 }

-int nbd_client_init(BlockDriverState *bs, int sock, const char *export,
-                    Error **errp)
+int nbd_client_session_init(NbdClientSession *client, BlockDriverState *bs,
+    int sock, const char *export)
 {
-    NbdClientSession *client = nbd_get_client_session(bs);
    int ret;

    /* NBD handshake */
    logout("session init %s\n", export);
    qemu_set_block(sock);
    ret = nbd_receive_negotiate(sock, export,
-                                &client->nbdflags, &client->size, errp);
+                                &client->nbdflags, &client->size,
+                                &client->blocksize);
    if (ret < 0) {
        logout("Failed to negotiate with the NBD server\n");
        closesocket(sock);
@@ -397,12 +391,13 @@ int nbd_client_init(BlockDriverState *bs, int sock, const char *export,

    qemu_co_mutex_init(&client->send_mutex);
    qemu_co_mutex_init(&client->free_sema);
+    client->bs = bs;
    client->sock = sock;

    /* Now that we're connected, set the socket to be non-blocking and
     * kick the reply mechanism.  */
    qemu_set_nonblock(sock);
-    nbd_client_attach_aio_context(bs, bdrv_get_aio_context(bs));
+    nbd_client_session_attach_aio_context(client, bdrv_get_aio_context(bs));

    logout("Established connection with NBD server\n");
    return 0;
@@ -20,6 +20,7 @@ typedef struct NbdClientSession {
    int sock;
    uint32_t nbdflags;
    off_t size;
+    size_t blocksize;

    CoMutex send_mutex;
    CoMutex free_sema;
@@ -30,24 +31,24 @@ typedef struct NbdClientSession {
    struct nbd_reply reply;

    bool is_unix;
+
+    BlockDriverState *bs;
 } NbdClientSession;

-NbdClientSession *nbd_get_client_session(BlockDriverState *bs);
+int nbd_client_session_init(NbdClientSession *client, BlockDriverState *bs,
+                            int sock, const char *export_name);
+void nbd_client_session_close(NbdClientSession *client);

-int nbd_client_init(BlockDriverState *bs, int sock, const char *export_name,
-                    Error **errp);
-void nbd_client_close(BlockDriverState *bs);
+int nbd_client_session_co_discard(NbdClientSession *client, int64_t sector_num,
+                                  int nb_sectors);
+int nbd_client_session_co_flush(NbdClientSession *client);
+int nbd_client_session_co_writev(NbdClientSession *client, int64_t sector_num,
+                                 int nb_sectors, QEMUIOVector *qiov);
+int nbd_client_session_co_readv(NbdClientSession *client, int64_t sector_num,
+                                int nb_sectors, QEMUIOVector *qiov);

-int nbd_client_co_discard(BlockDriverState *bs, int64_t sector_num,
-                          int nb_sectors);
-int nbd_client_co_flush(BlockDriverState *bs);
-int nbd_client_co_writev(BlockDriverState *bs, int64_t sector_num,
-                         int nb_sectors, QEMUIOVector *qiov);
-int nbd_client_co_readv(BlockDriverState *bs, int64_t sector_num,
-                        int nb_sectors, QEMUIOVector *qiov);
-
-void nbd_client_detach_aio_context(BlockDriverState *bs);
-void nbd_client_attach_aio_context(BlockDriverState *bs,
-                                   AioContext *new_context);
+void nbd_client_session_detach_aio_context(NbdClientSession *client);
+void nbd_client_session_attach_aio_context(NbdClientSession *client,
+                                           AioContext *new_context);

 #endif /* NBD_CLIENT_H */
@@ -43,6 +43,7 @@

 typedef struct BDRVNBDState {
    NbdClientSession client;
+    QemuOpts *socket_opts;
 } BDRVNBDState;

 static int nbd_parse_uri(const char *filename, QDict *options)
@@ -189,10 +190,10 @@ out:
    g_free(file);
 }

-static SocketAddress *nbd_config(BDRVNBDState *s, QDict *options, char **export,
-                                 Error **errp)
+static void nbd_config(BDRVNBDState *s, QDict *options, char **export,
+                       Error **errp)
 {
-    SocketAddress *saddr;
+    Error *local_err = NULL;

    if (qdict_haskey(options, "path") == qdict_haskey(options, "host")) {
        if (qdict_haskey(options, "path")) {
@@ -200,61 +201,47 @@ static SocketAddress *nbd_config(BDRVNBDState *s, QDict *options, char **export,
        } else {
            error_setg(errp, "one of path and host must be specified.");
        }
-        return NULL;
+        return;
    }

-    saddr = g_new0(SocketAddress, 1);
+    s->client.is_unix = qdict_haskey(options, "path");
+    s->socket_opts = qemu_opts_create(&socket_optslist, NULL, 0,
+                                      &error_abort);

-    if (qdict_haskey(options, "path")) {
-        saddr->type = SOCKET_ADDRESS_KIND_UNIX;
-        saddr->u.q_unix = g_new0(UnixSocketAddress, 1);
-        saddr->u.q_unix->path = g_strdup(qdict_get_str(options, "path"));
-        qdict_del(options, "path");
-    } else {
-        saddr->type = SOCKET_ADDRESS_KIND_INET;
-        saddr->u.inet = g_new0(InetSocketAddress, 1);
-        saddr->u.inet->host = g_strdup(qdict_get_str(options, "host"));
-        if (!qdict_get_try_str(options, "port")) {
-            saddr->u.inet->port = g_strdup_printf("%d", NBD_DEFAULT_PORT);
-        } else {
-            saddr->u.inet->port = g_strdup(qdict_get_str(options, "port"));
-        }
-        qdict_del(options, "host");
-        qdict_del(options, "port");
+    qemu_opts_absorb_qdict(s->socket_opts, options, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
    }

-    s->client.is_unix = saddr->type == SOCKET_ADDRESS_KIND_UNIX;
+    if (!qemu_opt_get(s->socket_opts, "port")) {
+        qemu_opt_set_number(s->socket_opts, "port", NBD_DEFAULT_PORT);
+    }

    *export = g_strdup(qdict_get_try_str(options, "export"));
    if (*export) {
        qdict_del(options, "export");
    }
-
-    return saddr;
 }

-NbdClientSession *nbd_get_client_session(BlockDriverState *bs)
-{
-    BDRVNBDState *s = bs->opaque;
-    return &s->client;
-}
-
-static int nbd_establish_connection(BlockDriverState *bs,
-                                    SocketAddress *saddr,
-                                    Error **errp)
+static int nbd_establish_connection(BlockDriverState *bs, Error **errp)
 {
    BDRVNBDState *s = bs->opaque;
    int sock;

-    sock = socket_connect(saddr, errp, NULL, NULL);
-
-    if (sock < 0) {
-        logout("Failed to establish connection to NBD server\n");
-        return -EIO;
+    if (s->client.is_unix) {
+        sock = unix_connect_opts(s->socket_opts, errp, NULL, NULL);
+    } else {
+        sock = inet_connect_opts(s->socket_opts, errp, NULL, NULL);
+        if (sock >= 0) {
+            socket_set_nodelay(sock);
+        }
    }

-    if (!s->client.is_unix) {
-        socket_set_nodelay(sock);
+    /* Failed to establish connection */
+    if (sock < 0) {
+        logout("Failed to establish connection to NBD server\n");
+        return -errno;
    }

    return sock;
@@ -266,26 +253,25 @@ static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
    BDRVNBDState *s = bs->opaque;
    char *export = NULL;
    int result, sock;
-    SocketAddress *saddr;
+    Error *local_err = NULL;

    /* Pop the config into our state object. Exit if invalid. */
-    saddr = nbd_config(s, options, &export, errp);
-    if (!saddr) {
+    nbd_config(s, options, &export, &local_err);
+    if (local_err) {
+        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, saddr, errp);
-    qapi_free_SocketAddress(saddr);
+    sock = nbd_establish_connection(bs, errp);
    if (sock < 0) {
-        g_free(export);
        return sock;
    }

    /* NBD handshake */
-    result = nbd_client_init(bs, sock, export, errp);
+    result = nbd_client_session_init(&s->client, bs, sock, export);
    g_free(export);
    return result;
 }
@@ -293,35 +279,43 @@ static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
 static int nbd_co_readv(BlockDriverState *bs, int64_t sector_num,
                        int nb_sectors, QEMUIOVector *qiov)
 {
-    return nbd_client_co_readv(bs, sector_num, nb_sectors, qiov);
+    BDRVNBDState *s = bs->opaque;
+
+    return nbd_client_session_co_readv(&s->client, sector_num,
+                                       nb_sectors, qiov);
 }

 static int nbd_co_writev(BlockDriverState *bs, int64_t sector_num,
                         int nb_sectors, QEMUIOVector *qiov)
 {
-    return nbd_client_co_writev(bs, sector_num, nb_sectors, qiov);
+    BDRVNBDState *s = bs->opaque;
+
+    return nbd_client_session_co_writev(&s->client, sector_num,
+                                        nb_sectors, qiov);
 }

 static int nbd_co_flush(BlockDriverState *bs)
 {
-    return nbd_client_co_flush(bs);
-}
+    BDRVNBDState *s = bs->opaque;

-static void nbd_refresh_limits(BlockDriverState *bs, Error **errp)
-{
-    bs->bl.max_discard = UINT32_MAX >> BDRV_SECTOR_BITS;
-    bs->bl.max_transfer_length = UINT32_MAX >> BDRV_SECTOR_BITS;
+    return nbd_client_session_co_flush(&s->client);
 }

 static int nbd_co_discard(BlockDriverState *bs, int64_t sector_num,
                          int nb_sectors)
 {
-    return nbd_client_co_discard(bs, sector_num, nb_sectors);
+    BDRVNBDState *s = bs->opaque;
+
+    return nbd_client_session_co_discard(&s->client, sector_num,
+                                         nb_sectors);
 }

 static void nbd_close(BlockDriverState *bs)
 {
-    nbd_client_close(bs);
+    BDRVNBDState *s = bs->opaque;
+
+    qemu_opts_del(s->socket_opts);
+    nbd_client_session_close(&s->client);
 }

 static int64_t nbd_getlength(BlockDriverState *bs)
@@ -333,13 +327,17 @@ static int64_t nbd_getlength(BlockDriverState *bs)

 static void nbd_detach_aio_context(BlockDriverState *bs)
 {
-    nbd_client_detach_aio_context(bs);
+    BDRVNBDState *s = bs->opaque;
+
+    nbd_client_session_detach_aio_context(&s->client);
 }

 static void nbd_attach_aio_context(BlockDriverState *bs,
                                   AioContext *new_context)
 {
-    nbd_client_attach_aio_context(bs, new_context);
+    BDRVNBDState *s = bs->opaque;
+
+    nbd_client_session_attach_aio_context(&s->client, new_context);
 }

 static void nbd_refresh_filename(BlockDriverState *bs)
@@ -398,7 +396,6 @@ static BlockDriver bdrv_nbd = {
    .bdrv_close                 = nbd_close,
    .bdrv_co_flush_to_os        = nbd_co_flush,
    .bdrv_co_discard            = nbd_co_discard,
-    .bdrv_refresh_limits        = nbd_refresh_limits,
    .bdrv_getlength             = nbd_getlength,
    .bdrv_detach_aio_context    = nbd_detach_aio_context,
    .bdrv_attach_aio_context    = nbd_attach_aio_context,
@@ -416,7 +413,6 @@ static BlockDriver bdrv_nbd_tcp = {
    .bdrv_close                 = nbd_close,
    .bdrv_co_flush_to_os        = nbd_co_flush,
    .bdrv_co_discard            = nbd_co_discard,
-    .bdrv_refresh_limits        = nbd_refresh_limits,
    .bdrv_getlength             = nbd_getlength,
    .bdrv_detach_aio_context    = nbd_detach_aio_context,
    .bdrv_attach_aio_context    = nbd_attach_aio_context,
@@ -434,7 +430,6 @@ static BlockDriver bdrv_nbd_unix = {
    .bdrv_close                 = nbd_close,
    .bdrv_co_flush_to_os        = nbd_co_flush,
    .bdrv_co_discard            = nbd_co_discard,
-    .bdrv_refresh_limits        = nbd_refresh_limits,
    .bdrv_getlength             = nbd_getlength,
    .bdrv_detach_aio_context    = nbd_detach_aio_context,
    .bdrv_attach_aio_context    = nbd_attach_aio_context,
@@ -35,15 +35,12 @@
 #include "sysemu/sysemu.h"
 #include <nfsc/libnfs.h>

-#define QEMU_NFS_MAX_READAHEAD_SIZE 1048576
-
 typedef struct NFSClient {
    struct nfs_context *context;
    struct nfsfh *fh;
    int events;
    bool has_zero_init;
    AioContext *aio_context;
-    blkcnt_t st_blocks;
 } NFSClient;

 typedef struct NFSRPC {
@@ -63,10 +60,11 @@ static void nfs_set_events(NFSClient *client)
 {
    int ev = nfs_which_events(client->context);
    if (ev != client->events) {
-        aio_set_fd_handler(client->aio_context, nfs_get_fd(client->context),
-                           false,
+        aio_set_fd_handler(client->aio_context,
+                           nfs_get_fd(client->context),
                           (ev & POLLIN) ? nfs_process_read : NULL,
-                           (ev & POLLOUT) ? nfs_process_write : NULL, client);
+                           (ev & POLLOUT) ? nfs_process_write : NULL,
+                           client);

    }
    client->events = ev;
@@ -241,8 +239,9 @@ static void nfs_detach_aio_context(BlockDriverState *bs)
 {
    NFSClient *client = bs->opaque;

-    aio_set_fd_handler(client->aio_context, nfs_get_fd(client->context),
-                       false, NULL, NULL, NULL);
+    aio_set_fd_handler(client->aio_context,
+                       nfs_get_fd(client->context),
+                       NULL, NULL, NULL);
    client->events = 0;
 }

@@ -261,8 +260,9 @@ static void nfs_client_close(NFSClient *client)
        if (client->fh) {
            nfs_close(client->context, client->fh);
        }
-        aio_set_fd_handler(client->aio_context, nfs_get_fd(client->context),
-                           false, NULL, NULL, NULL);
+        aio_set_fd_handler(client->aio_context,
+                           nfs_get_fd(client->context),
+                           NULL, NULL, NULL);
        nfs_destroy_context(client->context);
    }
    memset(client, 0, sizeof(NFSClient));
@@ -327,11 +327,6 @@ static int64_t nfs_client_open(NFSClient *client, const char *filename,
            nfs_set_tcp_syncnt(client->context, val);
 #ifdef LIBNFS_FEATURE_READAHEAD
        } else if (!strcmp(qp->p[i].name, "readahead")) {
-            if (val > QEMU_NFS_MAX_READAHEAD_SIZE) {
-                error_report("NFS Warning: Truncating NFS readahead"
-                             " size to %d", QEMU_NFS_MAX_READAHEAD_SIZE);
-                val = QEMU_NFS_MAX_READAHEAD_SIZE;
-            }
            nfs_set_readahead(client->context, val);
 #endif
        } else {
@@ -372,7 +367,6 @@ static int64_t nfs_client_open(NFSClient *client, const char *filename,
    }

    ret = DIV_ROUND_UP(st.st_size, BDRV_SECTOR_SIZE);
-    client->st_blocks = st.st_blocks;
    client->has_zero_init = S_ISREG(st.st_mode);
    goto out;
 fail:
@@ -463,11 +457,6 @@ static int64_t nfs_get_allocated_file_size(BlockDriverState *bs)
    NFSRPC task = {0};
    struct stat st;

-    if (bdrv_is_read_only(bs) &&
-        !(bs->open_flags & BDRV_O_NOCACHE)) {
-        return client->st_blocks * 512;
-    }
-
    task.st = &st;
    if (nfs_fstat_async(client->context, client->fh, nfs_co_generic_cb,
                        &task) != 0) {
@@ -479,7 +468,7 @@ static int64_t nfs_get_allocated_file_size(BlockDriverState *bs)
        aio_poll(client->aio_context, true);
    }

-    return (task.ret < 0 ? task.ret : st.st_blocks * 512);
+    return (task.ret < 0 ? task.ret : st.st_blocks * st.st_blksize);
 }

 static int nfs_file_truncate(BlockDriverState *bs, int64_t offset)
@@ -488,34 +477,6 @@ static int nfs_file_truncate(BlockDriverState *bs, int64_t offset)
    return nfs_ftruncate(client->context, client->fh, offset);
 }

-/* Note that this will not re-establish a connection with the NFS server
- * - it is effectively a NOP.  */
-static int nfs_reopen_prepare(BDRVReopenState *state,
-                              BlockReopenQueue *queue, Error **errp)
-{
-    NFSClient *client = state->bs->opaque;
-    struct stat st;
-    int ret = 0;
-
-    if (state->flags & BDRV_O_RDWR && bdrv_is_read_only(state->bs)) {
-        error_setg(errp, "Cannot open a read-only mount as read-write");
-        return -EACCES;
-    }
-
-    /* Update cache for read-only reopens */
-    if (!(state->flags & BDRV_O_RDWR)) {
-        ret = nfs_fstat(client->context, client->fh, &st);
-        if (ret < 0) {
-            error_setg(errp, "Failed to fstat file: %s",
-                       nfs_get_error(client->context));
-            return ret;
-        }
-        client->st_blocks = st.st_blocks;
-    }
-
-    return 0;
-}
-
 static BlockDriver bdrv_nfs = {
    .format_name                    = "nfs",
    .protocol_name                  = "nfs",
@@ -531,7 +492,6 @@ static BlockDriver bdrv_nfs = {
    .bdrv_file_open                 = nfs_file_open,
    .bdrv_close                     = nfs_file_close,
    .bdrv_create                    = nfs_file_create,
-    .bdrv_reopen_prepare            = nfs_reopen_prepare,

    .bdrv_co_readv                  = nfs_co_readv,
    .bdrv_co_writev                 = nfs_co_writev,
@@ -12,11 +12,8 @@

 #include "block/block_int.h"

-#define NULL_OPT_LATENCY "latency-ns"
-
 typedef struct {
    int64_t length;
-    int64_t latency_ns;
 } BDRVNullState;

 static QemuOptsList runtime_opts = {
@@ -33,12 +30,6 @@ static QemuOptsList runtime_opts = {
            .type = QEMU_OPT_SIZE,
            .help = "size of the null block",
        },
-        {
-            .name = NULL_OPT_LATENCY,
-            .type = QEMU_OPT_NUMBER,
-            .help = "nanoseconds (approximated) to wait "
-                    "before completing request",
-        },
        { /* end of list */ }
    },
 };
@@ -48,20 +39,13 @@ static int null_file_open(BlockDriverState *bs, QDict *options, int flags,
 {
    QemuOpts *opts;
    BDRVNullState *s = bs->opaque;
-    int ret = 0;

    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
    qemu_opts_absorb_qdict(opts, options, &error_abort);
    s->length =
        qemu_opt_get_size(opts, BLOCK_OPT_SIZE, 1 << 30);
-    s->latency_ns =
-        qemu_opt_get_number(opts, NULL_OPT_LATENCY, 0);
-    if (s->latency_ns < 0) {
-        error_setg(errp, "latency-ns is invalid");
-        ret = -EINVAL;
-    }
    qemu_opts_del(opts);
-    return ret;
+    return 0;
 }

 static void null_close(BlockDriverState *bs)
@@ -74,40 +58,28 @@ static int64_t null_getlength(BlockDriverState *bs)
    return s->length;
 }

-static coroutine_fn int null_co_common(BlockDriverState *bs)
-{
-    BDRVNullState *s = bs->opaque;
-
-    if (s->latency_ns) {
-        co_aio_sleep_ns(bdrv_get_aio_context(bs), QEMU_CLOCK_REALTIME,
-                        s->latency_ns);
-    }
-    return 0;
-}
-
 static coroutine_fn int null_co_readv(BlockDriverState *bs,
                                      int64_t sector_num, int nb_sectors,
                                      QEMUIOVector *qiov)
 {
-    return null_co_common(bs);
+    return 0;
 }

 static coroutine_fn int null_co_writev(BlockDriverState *bs,
                                       int64_t sector_num, int nb_sectors,
                                       QEMUIOVector *qiov)
 {
-    return null_co_common(bs);
+    return 0;
 }

 static coroutine_fn int null_co_flush(BlockDriverState *bs)
 {
-    return null_co_common(bs);
+    return 0;
 }

 typedef struct {
    BlockAIOCB common;
    QEMUBH *bh;
-    QEMUTimer timer;
 } NullAIOCB;

 static const AIOCBInfo null_aiocb_info = {
@@ -122,33 +94,15 @@ static void null_bh_cb(void *opaque)
    qemu_aio_unref(acb);
 }

-static void null_timer_cb(void *opaque)
-{
-    NullAIOCB *acb = opaque;
-    acb->common.cb(acb->common.opaque, 0);
-    timer_deinit(&acb->timer);
-    qemu_aio_unref(acb);
-}
-
 static inline BlockAIOCB *null_aio_common(BlockDriverState *bs,
                                          BlockCompletionFunc *cb,
                                          void *opaque)
 {
    NullAIOCB *acb;
-    BDRVNullState *s = bs->opaque;

    acb = qemu_aio_get(&null_aiocb_info, bs, cb, opaque);
-    /* Only emulate latency after vcpu is running. */
-    if (s->latency_ns) {
-        aio_timer_init(bdrv_get_aio_context(bs), &acb->timer,
-                       QEMU_CLOCK_REALTIME, SCALE_NS,
-                       null_timer_cb, acb);
-        timer_mod_ns(&acb->timer,
-                     qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + s->latency_ns);
-    } else {
-        acb->bh = aio_bh_new(bdrv_get_aio_context(bs), null_bh_cb, acb);
-        qemu_bh_schedule(acb->bh);
-    }
+    acb->bh = aio_bh_new(bdrv_get_aio_context(bs), null_bh_cb, acb);
+    qemu_bh_schedule(acb->bh);
    return &acb->common;
 }

@@ -177,12 +131,6 @@ static BlockAIOCB *null_aio_flush(BlockDriverState *bs,
    return null_aio_common(bs, cb, opaque);
 }

-static int null_reopen_prepare(BDRVReopenState *reopen_state,
-                               BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
-}
-
 static BlockDriver bdrv_null_co = {
    .format_name            = "null-co",
    .protocol_name          = "null-co",
@@ -195,7 +143,6 @@ static BlockDriver bdrv_null_co = {
    .bdrv_co_readv          = null_co_readv,
    .bdrv_co_writev         = null_co_writev,
    .bdrv_co_flush_to_disk  = null_co_flush,
-    .bdrv_reopen_prepare    = null_reopen_prepare,
 };

 static BlockDriver bdrv_null_aio = {
@@ -210,7 +157,6 @@ static BlockDriver bdrv_null_aio = {
    .bdrv_aio_readv         = null_aio_readv,
    .bdrv_aio_writev        = null_aio_writev,
    .bdrv_aio_flush         = null_aio_flush,
-    .bdrv_reopen_prepare    = null_reopen_prepare,
 };

 static void bdrv_null_init(void)
@@ -2,12 +2,8 @@
 * Block driver for Parallels disk image format
 *
 * Copyright (c) 2007 Alex Beregszaszi
- * Copyright (c) 2015 Denis V. Lunev <den@openvz.org>
 *
- * This code was originally based on comparing different disk images created
- * by Parallels. Currently it is based on opened OpenVZ sources
- * available at
- *     http://git.openvz.org/?p=ploop;a=summary
+ * This code is based on comparing different disk images created by Parallels.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
@@ -30,543 +26,65 @@
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "qemu/module.h"
-#include "qemu/bitmap.h"
-#include "qapi/util.h"

 /**************************************************************/

 #define HEADER_MAGIC "WithoutFreeSpace"
 #define HEADER_MAGIC2 "WithouFreSpacExt"
 #define HEADER_VERSION 2
-#define HEADER_INUSE_MAGIC  (0x746F6E59)
-
-#define DEFAULT_CLUSTER_SIZE 1048576        /* 1 MiB */
-
+#define HEADER_SIZE 64

 // always little-endian
-typedef struct ParallelsHeader {
+struct parallels_header {
    char magic[16]; // "WithoutFreeSpace"
    uint32_t version;
    uint32_t heads;
    uint32_t cylinders;
    uint32_t tracks;
-    uint32_t bat_entries;
+    uint32_t catalog_entries;
    uint64_t nb_sectors;
    uint32_t inuse;
    uint32_t data_off;
    char padding[12];
-} QEMU_PACKED ParallelsHeader;
-
-
-typedef enum ParallelsPreallocMode {
-    PRL_PREALLOC_MODE_FALLOCATE = 0,
-    PRL_PREALLOC_MODE_TRUNCATE = 1,
-    PRL_PREALLOC_MODE_MAX = 2,
-} ParallelsPreallocMode;
-
-static const char *prealloc_mode_lookup[] = {
-    "falloc",
-    "truncate",
-    NULL,
-};
-
+} QEMU_PACKED;

 typedef struct BDRVParallelsState {
-    /** Locking is conservative, the lock protects
-     *   - image file extending (truncate, fallocate)
-     *   - any access to block allocation table
-     */
    CoMutex lock;

-    ParallelsHeader *header;
-    uint32_t header_size;
-    bool header_unclean;
-
-    unsigned long *bat_dirty_bmap;
-    unsigned int  bat_dirty_block;
-
-    uint32_t *bat_bitmap;
-    unsigned int bat_size;
-
-    int64_t  data_end;
-    uint64_t prealloc_size;
-    ParallelsPreallocMode prealloc_mode;
+    uint32_t *catalog_bitmap;
+    unsigned int catalog_size;

    unsigned int tracks;

    unsigned int off_multiplier;
 } BDRVParallelsState;

-
-#define PARALLELS_OPT_PREALLOC_MODE     "prealloc-mode"
-#define PARALLELS_OPT_PREALLOC_SIZE     "prealloc-size"
-
-static QemuOptsList parallels_runtime_opts = {
-    .name = "parallels",
-    .head = QTAILQ_HEAD_INITIALIZER(parallels_runtime_opts.head),
-    .desc = {
-        {
-            .name = PARALLELS_OPT_PREALLOC_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Preallocation size on image expansion",
-            .def_value_str = "128MiB",
-        },
-        {
-            .name = PARALLELS_OPT_PREALLOC_MODE,
-            .type = QEMU_OPT_STRING,
-            .help = "Preallocation mode on image expansion "
-                    "(allowed values: falloc, truncate)",
-            .def_value_str = "falloc",
-        },
-        { /* end of list */ },
-    },
-};
-
-
-static int64_t bat2sect(BDRVParallelsState *s, uint32_t idx)
+static int parallels_probe(const uint8_t *buf, int buf_size, const char *filename)
 {
-    return (uint64_t)le32_to_cpu(s->bat_bitmap[idx]) * s->off_multiplier;
-}
+    const struct parallels_header *ph = (const void *)buf;

-static uint32_t bat_entry_off(uint32_t idx)
-{
-    return sizeof(ParallelsHeader) + sizeof(uint32_t) * idx;
-}
-
-static int64_t seek_to_sector(BDRVParallelsState *s, int64_t sector_num)
-{
-    uint32_t index, offset;
-
-    index = sector_num / s->tracks;
-    offset = sector_num % s->tracks;
-
-    /* not allocated */
-    if ((index >= s->bat_size) || (s->bat_bitmap[index] == 0)) {
-        return -1;
-    }
-    return bat2sect(s, index) + offset;
-}
-
-static int cluster_remainder(BDRVParallelsState *s, int64_t sector_num,
-        int nb_sectors)
-{
-    int ret = s->tracks - sector_num % s->tracks;
-    return MIN(nb_sectors, ret);
-}
-
-static int64_t block_status(BDRVParallelsState *s, int64_t sector_num,
-                            int nb_sectors, int *pnum)
-{
-    int64_t start_off = -2, prev_end_off = -2;
-
-    *pnum = 0;
-    while (nb_sectors > 0 || start_off == -2) {
-        int64_t offset = seek_to_sector(s, sector_num);
-        int to_end;
-
-        if (start_off == -2) {
-            start_off = offset;
-            prev_end_off = offset;
-        } else if (offset != prev_end_off) {
-            break;
-        }
-
-        to_end = cluster_remainder(s, sector_num, nb_sectors);
-        nb_sectors -= to_end;
-        sector_num += to_end;
-        *pnum += to_end;
-
-        if (offset > 0) {
-            prev_end_off += to_end;
-        }
-    }
-    return start_off;
-}
-
-static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num,
-                                 int nb_sectors, int *pnum)
-{
-    BDRVParallelsState *s = bs->opaque;
-    uint32_t idx, to_allocate, i;
-    int64_t pos, space;
-
-    pos = block_status(s, sector_num, nb_sectors, pnum);
-    if (pos > 0) {
-        return pos;
-    }
-
-    idx = sector_num / s->tracks;
-    if (idx >= s->bat_size) {
-        return -EINVAL;
-    }
-
-    to_allocate = (sector_num + *pnum + s->tracks - 1) / s->tracks - idx;
-    space = to_allocate * s->tracks;
-    if (s->data_end + space > bdrv_getlength(bs->file->bs) >> BDRV_SECTOR_BITS) {
-        int ret;
-        space += s->prealloc_size;
-        if (s->prealloc_mode == PRL_PREALLOC_MODE_FALLOCATE) {
-            ret = bdrv_write_zeroes(bs->file->bs, s->data_end, space, 0);
-        } else {
-            ret = bdrv_truncate(bs->file->bs,
-                                (s->data_end + space) << BDRV_SECTOR_BITS);
-        }
-        if (ret < 0) {
-            return ret;
-        }
-    }
-
-    for (i = 0; i < to_allocate; i++) {
-        s->bat_bitmap[idx + i] = cpu_to_le32(s->data_end / s->off_multiplier);
-        s->data_end += s->tracks;
-        bitmap_set(s->bat_dirty_bmap,
-                   bat_entry_off(idx + i) / s->bat_dirty_block, 1);
-    }
-
-    return bat2sect(s, idx) + sector_num % s->tracks;
-}
-
-
-static coroutine_fn int parallels_co_flush_to_os(BlockDriverState *bs)
-{
-    BDRVParallelsState *s = bs->opaque;
-    unsigned long size = DIV_ROUND_UP(s->header_size, s->bat_dirty_block);
-    unsigned long bit;
-
-    qemu_co_mutex_lock(&s->lock);
-
-    bit = find_first_bit(s->bat_dirty_bmap, size);
-    while (bit < size) {
-        uint32_t off = bit * s->bat_dirty_block;
-        uint32_t to_write = s->bat_dirty_block;
-        int ret;
-
-        if (off + to_write > s->header_size) {
-            to_write = s->header_size - off;
-        }
-        ret = bdrv_pwrite(bs->file->bs, off, (uint8_t *)s->header + off,
-                          to_write);
-        if (ret < 0) {
-            qemu_co_mutex_unlock(&s->lock);
-            return ret;
-        }
-        bit = find_next_bit(s->bat_dirty_bmap, size, bit + 1);
-    }
-    bitmap_zero(s->bat_dirty_bmap, size);
-
-    qemu_co_mutex_unlock(&s->lock);
-    return 0;
-}
-
-
-static int64_t coroutine_fn parallels_co_get_block_status(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *pnum)
-{
-    BDRVParallelsState *s = bs->opaque;
-    int64_t offset;
-
-    qemu_co_mutex_lock(&s->lock);
-    offset = block_status(s, sector_num, nb_sectors, pnum);
-    qemu_co_mutex_unlock(&s->lock);
-
-    if (offset < 0) {
+    if (buf_size < HEADER_SIZE)
        return 0;
-    }
-
-    return (offset << BDRV_SECTOR_BITS) |
-        BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
-}
-
-static coroutine_fn int parallels_co_writev(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
-{
-    BDRVParallelsState *s = bs->opaque;
-    uint64_t bytes_done = 0;
-    QEMUIOVector hd_qiov;
-    int ret = 0;
-
-    qemu_iovec_init(&hd_qiov, qiov->niov);
-
-    while (nb_sectors > 0) {
-        int64_t position;
-        int n, nbytes;
-
-        qemu_co_mutex_lock(&s->lock);
-        position = allocate_clusters(bs, sector_num, nb_sectors, &n);
-        qemu_co_mutex_unlock(&s->lock);
-        if (position < 0) {
-            ret = (int)position;
-            break;
-        }
-
-        nbytes = n << BDRV_SECTOR_BITS;
-
-        qemu_iovec_reset(&hd_qiov);
-        qemu_iovec_concat(&hd_qiov, qiov, bytes_done, nbytes);
-
-        ret = bdrv_co_writev(bs->file->bs, position, n, &hd_qiov);
-        if (ret < 0) {
-            break;
-        }
-
-        nb_sectors -= n;
-        sector_num += n;
-        bytes_done += nbytes;
-    }
-
-    qemu_iovec_destroy(&hd_qiov);
-    return ret;
-}
-
-static coroutine_fn int parallels_co_readv(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
-{
-    BDRVParallelsState *s = bs->opaque;
-    uint64_t bytes_done = 0;
-    QEMUIOVector hd_qiov;
-    int ret = 0;
-
-    qemu_iovec_init(&hd_qiov, qiov->niov);
-
-    while (nb_sectors > 0) {
-        int64_t position;
-        int n, nbytes;
-
-        qemu_co_mutex_lock(&s->lock);
-        position = block_status(s, sector_num, nb_sectors, &n);
-        qemu_co_mutex_unlock(&s->lock);
-
-        nbytes = n << BDRV_SECTOR_BITS;
-
-        if (position < 0) {
-            qemu_iovec_memset(qiov, bytes_done, 0, nbytes);
-        } else {
-            qemu_iovec_reset(&hd_qiov);
-            qemu_iovec_concat(&hd_qiov, qiov, bytes_done, nbytes);
-
-            ret = bdrv_co_readv(bs->file->bs, position, n, &hd_qiov);
-            if (ret < 0) {
-                break;
-            }
-        }
-
-        nb_sectors -= n;
-        sector_num += n;
-        bytes_done += nbytes;
-    }
-
-    qemu_iovec_destroy(&hd_qiov);
-    return ret;
-}
-
-
-static int parallels_check(BlockDriverState *bs, BdrvCheckResult *res,
-                           BdrvCheckMode fix)
-{
-    BDRVParallelsState *s = bs->opaque;
-    int64_t size, prev_off, high_off;
-    int ret;
-    uint32_t i;
-    bool flush_bat = false;
-    int cluster_size = s->tracks << BDRV_SECTOR_BITS;
-
-    size = bdrv_getlength(bs->file->bs);
-    if (size < 0) {
-        res->check_errors++;
-        return size;
-    }
-
-    if (s->header_unclean) {
-        fprintf(stderr, "%s image was not closed correctly\n",
-                fix & BDRV_FIX_ERRORS ? "Repairing" : "ERROR");
-        res->corruptions++;
-        if (fix & BDRV_FIX_ERRORS) {
-            /* parallels_close will do the job right */
-            res->corruptions_fixed++;
-            s->header_unclean = false;
-        }
-    }
-
-    res->bfi.total_clusters = s->bat_size;
-    res->bfi.compressed_clusters = 0; /* compression is not supported */
-
-    high_off = 0;
-    prev_off = 0;
-    for (i = 0; i < s->bat_size; i++) {
-        int64_t off = bat2sect(s, i) << BDRV_SECTOR_BITS;
-        if (off == 0) {
-            prev_off = 0;
-            continue;
-        }
-
-        /* cluster outside the image */
-        if (off > size) {
-            fprintf(stderr, "%s cluster %u is outside image\n",
-                    fix & BDRV_FIX_ERRORS ? "Repairing" : "ERROR", i);
-            res->corruptions++;
-            if (fix & BDRV_FIX_ERRORS) {
-                prev_off = 0;
-                s->bat_bitmap[i] = 0;
-                res->corruptions_fixed++;
-                flush_bat = true;
-                continue;
-            }
-        }
-
-        res->bfi.allocated_clusters++;
-        if (off > high_off) {
-            high_off = off;
-        }
-
-        if (prev_off != 0 && (prev_off + cluster_size) != off) {
-            res->bfi.fragmented_clusters++;
-        }
-        prev_off = off;
-    }
-
-    if (flush_bat) {
-        ret = bdrv_pwrite_sync(bs->file->bs, 0, s->header, s->header_size);
-        if (ret < 0) {
-            res->check_errors++;
-            return ret;
-        }
-    }
-
-    res->image_end_offset = high_off + cluster_size;
-    if (size > res->image_end_offset) {
-        int64_t count;
-        count = DIV_ROUND_UP(size - res->image_end_offset, cluster_size);
-        fprintf(stderr, "%s space leaked at the end of the image %" PRId64 "\n",
-                fix & BDRV_FIX_LEAKS ? "Repairing" : "ERROR",
-                size - res->image_end_offset);
-        res->leaks += count;
-        if (fix & BDRV_FIX_LEAKS) {
-            ret = bdrv_truncate(bs->file->bs, res->image_end_offset);
-            if (ret < 0) {
-                res->check_errors++;
-                return ret;
-            }
-            res->leaks_fixed += count;
-        }
-    }
-
-    return 0;
-}
-
-
-static int parallels_create(const char *filename, QemuOpts *opts, Error **errp)
-{
-    int64_t total_size, cl_size;
-    uint8_t tmp[BDRV_SECTOR_SIZE];
-    Error *local_err = NULL;
-    BlockDriverState *file;
-    uint32_t bat_entries, bat_sectors;
-    ParallelsHeader header;
-    int ret;
-
-    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
-                          BDRV_SECTOR_SIZE);
-    cl_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_CLUSTER_SIZE,
-                          DEFAULT_CLUSTER_SIZE), BDRV_SECTOR_SIZE);
-
-    ret = bdrv_create_file(filename, opts, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        return ret;
-    }
-
-    file = NULL;
-    ret = bdrv_open(&file, filename, NULL, NULL,
-                    BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        return ret;
-    }
-    ret = bdrv_truncate(file, 0);
-    if (ret < 0) {
-        goto exit;
-    }
-
-    bat_entries = DIV_ROUND_UP(total_size, cl_size);
-    bat_sectors = DIV_ROUND_UP(bat_entry_off(bat_entries), cl_size);
-    bat_sectors = (bat_sectors *  cl_size) >> BDRV_SECTOR_BITS;
-
-    memset(&header, 0, sizeof(header));
-    memcpy(header.magic, HEADER_MAGIC2, sizeof(header.magic));
-    header.version = cpu_to_le32(HEADER_VERSION);
-    /* don't care much about geometry, it is not used on image level */
-    header.heads = cpu_to_le32(16);
-    header.cylinders = cpu_to_le32(total_size / BDRV_SECTOR_SIZE / 16 / 32);
-    header.tracks = cpu_to_le32(cl_size >> BDRV_SECTOR_BITS);
-    header.bat_entries = cpu_to_le32(bat_entries);
-    header.nb_sectors = cpu_to_le64(DIV_ROUND_UP(total_size, BDRV_SECTOR_SIZE));
-    header.data_off = cpu_to_le32(bat_sectors);
-
-    /* write all the data */
-    memset(tmp, 0, sizeof(tmp));
-    memcpy(tmp, &header, sizeof(header));
-
-    ret = bdrv_pwrite(file, 0, tmp, BDRV_SECTOR_SIZE);
-    if (ret < 0) {
-        goto exit;
-    }
-    ret = bdrv_write_zeroes(file, 1, bat_sectors - 1, 0);
-    if (ret < 0) {
-        goto exit;
-    }
-    ret = 0;
-
-done:
-    bdrv_unref(file);
-    return ret;
-
-exit:
-    error_setg_errno(errp, -ret, "Failed to create Parallels image");
-    goto done;
-}
-
-
-static int parallels_probe(const uint8_t *buf, int buf_size,
-                           const char *filename)
-{
-    const ParallelsHeader *ph = (const void *)buf;
-
-    if (buf_size < sizeof(ParallelsHeader)) {
-        return 0;
-    }

    if ((!memcmp(ph->magic, HEADER_MAGIC, 16) ||
-           !memcmp(ph->magic, HEADER_MAGIC2, 16)) &&
-           (le32_to_cpu(ph->version) == HEADER_VERSION)) {
+        !memcmp(ph->magic, HEADER_MAGIC2, 16)) &&
+        (le32_to_cpu(ph->version) == HEADER_VERSION))
        return 100;
-    }

    return 0;
 }

-static int parallels_update_header(BlockDriverState *bs)
-{
-    BDRVParallelsState *s = bs->opaque;
-    unsigned size = MAX(bdrv_opt_mem_align(bs->file->bs),
-                        sizeof(ParallelsHeader));
-
-    if (size > s->header_size) {
-        size = s->header_size;
-    }
-    return bdrv_pwrite_sync(bs->file->bs, 0, s->header, size);
-}
-
 static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
                          Error **errp)
 {
    BDRVParallelsState *s = bs->opaque;
-    ParallelsHeader ph;
-    int ret, size, i;
-    QemuOpts *opts = NULL;
-    Error *local_err = NULL;
-    char *buf;
+    int i;
+    struct parallels_header ph;
+    int ret;

-    ret = bdrv_pread(bs->file->bs, 0, &ph, sizeof(ph));
+    bs->read_only = 1; // no write support yet
+
+    ret = bdrv_pread(bs->file, 0, &ph, sizeof(ph));
    if (ret < 0) {
        goto fail;
    }
@@ -597,90 +115,25 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
        goto fail;
    }

-    s->bat_size = le32_to_cpu(ph.bat_entries);
-    if (s->bat_size > INT_MAX / sizeof(uint32_t)) {
+    s->catalog_size = le32_to_cpu(ph.catalog_entries);
+    if (s->catalog_size > INT_MAX / 4) {
        error_setg(errp, "Catalog too large");
        ret = -EFBIG;
        goto fail;
    }
-
-    size = bat_entry_off(s->bat_size);
-    s->header_size = ROUND_UP(size, bdrv_opt_mem_align(bs->file->bs));
-    s->header = qemu_try_blockalign(bs->file->bs, s->header_size);
-    if (s->header == NULL) {
+    s->catalog_bitmap = g_try_new(uint32_t, s->catalog_size);
+    if (s->catalog_size && s->catalog_bitmap == NULL) {
        ret = -ENOMEM;
        goto fail;
    }
-    s->data_end = le32_to_cpu(ph.data_off);
-    if (s->data_end == 0) {
-        s->data_end = ROUND_UP(bat_entry_off(s->bat_size), BDRV_SECTOR_SIZE);
-    }
-    if (s->data_end < s->header_size) {
-        /* there is not enough unused space to fit to block align between BAT
-           and actual data. We can't avoid read-modify-write... */
-        s->header_size = size;
-    }

-    ret = bdrv_pread(bs->file->bs, 0, s->header, s->header_size);
+    ret = bdrv_pread(bs->file, 64, s->catalog_bitmap, s->catalog_size * 4);
    if (ret < 0) {
        goto fail;
    }
-    s->bat_bitmap = (uint32_t *)(s->header + 1);

-    for (i = 0; i < s->bat_size; i++) {
-        int64_t off = bat2sect(s, i);
-        if (off >= s->data_end) {
-            s->data_end = off + s->tracks;
-        }
-    }
-
-    if (le32_to_cpu(ph.inuse) == HEADER_INUSE_MAGIC) {
-        /* Image was not closed correctly. The check is mandatory */
-        s->header_unclean = true;
-        if ((flags & BDRV_O_RDWR) && !(flags & BDRV_O_CHECK)) {
-            error_setg(errp, "parallels: Image was not closed correctly; "
-                       "cannot be opened read/write");
-            ret = -EACCES;
-            goto fail;
-        }
-    }
-
-    opts = qemu_opts_create(&parallels_runtime_opts, NULL, 0, &local_err);
-    if (local_err != NULL) {
-        goto fail_options;
-    }
-
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err != NULL) {
-        goto fail_options;
-    }
-
-    s->prealloc_size =
-        qemu_opt_get_size_del(opts, PARALLELS_OPT_PREALLOC_SIZE, 0);
-    s->prealloc_size = MAX(s->tracks, s->prealloc_size >> BDRV_SECTOR_BITS);
-    buf = qemu_opt_get_del(opts, PARALLELS_OPT_PREALLOC_MODE);
-    s->prealloc_mode = qapi_enum_parse(prealloc_mode_lookup, buf,
-            PRL_PREALLOC_MODE_MAX, PRL_PREALLOC_MODE_FALLOCATE, &local_err);
-    g_free(buf);
-    if (local_err != NULL) {
-        goto fail_options;
-    }
-    if (!bdrv_has_zero_init(bs->file->bs) ||
-            bdrv_truncate(bs->file->bs, bdrv_getlength(bs->file->bs)) != 0) {
-        s->prealloc_mode = PRL_PREALLOC_MODE_FALLOCATE;
-    }
-
-    if (flags & BDRV_O_RDWR) {
-        s->header->inuse = cpu_to_le32(HEADER_INUSE_MAGIC);
-        ret = parallels_update_header(bs);
-        if (ret < 0) {
-            goto fail;
-        }
-    }
-
-    s->bat_dirty_block = 4 * getpagesize();
-    s->bat_dirty_bmap =
-        bitmap_new(DIV_ROUND_UP(s->header_size, s->bat_dirty_block));
+    for (i = 0; i < s->catalog_size; i++)
+        le32_to_cpus(&s->catalog_bitmap[i]);

    qemu_co_mutex_init(&s->lock);
    return 0;
@@ -689,67 +142,67 @@ fail_format:
    error_setg(errp, "Image not in Parallels format");
    ret = -EINVAL;
 fail:
-    qemu_vfree(s->header);
+    g_free(s->catalog_bitmap);
    return ret;
-
-fail_options:
-    error_propagate(errp, local_err);
-    ret = -EINVAL;
-    goto fail;
 }

+static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)
+{
+    BDRVParallelsState *s = bs->opaque;
+    uint32_t index, offset;
+
+    index = sector_num / s->tracks;
+    offset = sector_num % s->tracks;
+
+    /* not allocated */
+    if ((index >= s->catalog_size) || (s->catalog_bitmap[index] == 0))
+        return -1;
+    return
+        ((uint64_t)s->catalog_bitmap[index] * s->off_multiplier + offset) * 512;
+}
+
+static int parallels_read(BlockDriverState *bs, int64_t sector_num,
+                    uint8_t *buf, int nb_sectors)
+{
+    while (nb_sectors > 0) {
+        int64_t position = seek_to_sector(bs, sector_num);
+        if (position >= 0) {
+            if (bdrv_pread(bs->file, position, buf, 512) != 512)
+                return -1;
+        } else {
+            memset(buf, 0, 512);
+        }
+        nb_sectors--;
+        sector_num++;
+        buf += 512;
+    }
+    return 0;
+}
+
+static coroutine_fn int parallels_co_read(BlockDriverState *bs, int64_t sector_num,
+                                          uint8_t *buf, int nb_sectors)
+{
+    int ret;
+    BDRVParallelsState *s = bs->opaque;
+    qemu_co_mutex_lock(&s->lock);
+    ret = parallels_read(bs, sector_num, buf, nb_sectors);
+    qemu_co_mutex_unlock(&s->lock);
+    return ret;
+}

 static void parallels_close(BlockDriverState *bs)
 {
    BDRVParallelsState *s = bs->opaque;
-
-    if (bs->open_flags & BDRV_O_RDWR) {
-        s->header->inuse = 0;
-        parallels_update_header(bs);
-    }
-
-    if (bs->open_flags & BDRV_O_RDWR) {
-        bdrv_truncate(bs->file->bs, s->data_end << BDRV_SECTOR_BITS);
-    }
-
-    g_free(s->bat_dirty_bmap);
-    qemu_vfree(s->header);
+    g_free(s->catalog_bitmap);
 }

-static QemuOptsList parallels_create_opts = {
-    .name = "parallels-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(parallels_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size",
-        },
-        {
-            .name = BLOCK_OPT_CLUSTER_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Parallels image cluster size",
-            .def_value_str = stringify(DEFAULT_CLUSTER_SIZE),
-        },
-        { /* end of list */ }
-    }
-};
-
 static BlockDriver bdrv_parallels = {
    .format_name	= "parallels",
    .instance_size	= sizeof(BDRVParallelsState),
    .bdrv_probe		= parallels_probe,
    .bdrv_open		= parallels_open,
+    .bdrv_read          = parallels_co_read,
    .bdrv_close		= parallels_close,
-    .bdrv_co_get_block_status = parallels_co_get_block_status,
-    .bdrv_has_zero_init       = bdrv_has_zero_init_1,
-    .bdrv_co_flush_to_os      = parallels_co_flush_to_os,
-    .bdrv_co_readv  = parallels_co_readv,
-    .bdrv_co_writev = parallels_co_writev,
-
-    .bdrv_create    = parallels_create,
-    .bdrv_check     = parallels_check,
-    .create_opts    = &parallels_create_opts,
 };

 static void bdrv_parallels_init(void)
@@ -24,18 +24,14 @@

 #include "block/qapi.h"
 #include "block/block_int.h"
-#include "block/throttle-groups.h"
-#include "block/write-threshold.h"
 #include "qmp-commands.h"
 #include "qapi-visit.h"
 #include "qapi/qmp-output-visitor.h"
 #include "qapi/qmp/types.h"
 #include "sysemu/block-backend.h"

-BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs, Error **errp)
+BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs)
 {
-    ImageInfo **p_image_info;
-    BlockDriverState *bs0;
    BlockDeviceInfo *info = g_malloc0(sizeof(*info));

    info->file                   = g_strdup(bs->filename);
@@ -44,13 +40,6 @@ BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs, Error **errp)
    info->encrypted              = bs->encrypted;
    info->encryption_key_missing = bdrv_key_required(bs);

-    info->cache = g_new(BlockdevCacheInfo, 1);
-    *info->cache = (BlockdevCacheInfo) {
-        .writeback      = bdrv_enable_write_cache(bs),
-        .direct         = !!(bs->open_flags & BDRV_O_NOCACHE),
-        .no_flush       = !!(bs->open_flags & BDRV_O_NO_FLUSH),
-    };
-
    if (bs->node_name[0]) {
        info->has_node_name = true;
        info->node_name = g_strdup(bs->node_name);
@@ -64,11 +53,9 @@ BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs, Error **errp)
    info->backing_file_depth = bdrv_get_backing_file_depth(bs);
    info->detect_zeroes = bs->detect_zeroes;

-    if (bs->throttle_state) {
+    if (bs->io_limits_enabled) {
        ThrottleConfig cfg;
-
-        throttle_group_get_config(bs, &cfg);
-
+        throttle_get_config(&bs->throttle_state, &cfg);
        info->bps     = cfg.buckets[THROTTLE_BPS_TOTAL].avg;
        info->bps_rd  = cfg.buckets[THROTTLE_BPS_READ].avg;
        info->bps_wr  = cfg.buckets[THROTTLE_BPS_WRITE].avg;
@@ -93,30 +80,6 @@ BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs, Error **errp)

        info->has_iops_size = cfg.op_size;
        info->iops_size = cfg.op_size;
-
-        info->has_group = true;
-        info->group = g_strdup(throttle_group_get_name(bs));
-    }
-
-    info->write_threshold = bdrv_write_threshold_get(bs);
-
-    bs0 = bs;
-    p_image_info = &info->image;
-    while (1) {
-        Error *local_err = NULL;
-        bdrv_query_image_info(bs0, p_image_info, &local_err);
-        if (local_err) {
-            error_propagate(errp, local_err);
-            qapi_free_BlockDeviceInfo(info);
-            return NULL;
-        }
-        if (bs0->drv && bs0->backing) {
-            bs0 = bs0->backing->bs;
-            (*p_image_info)->has_backing_image = true;
-            p_image_info = &((*p_image_info)->backing_image);
-        } else {
-            break;
-        }
    }

    return info;
@@ -205,6 +168,7 @@ void bdrv_query_image_info(BlockDriverState *bs,
 {
    int64_t size;
    const char *backing_filename;
+    char backing_filename2[1024];
    BlockDriverInfo bdi;
    int ret;
    Error *err = NULL;
@@ -240,16 +204,10 @@ void bdrv_query_image_info(BlockDriverState *bs,

    backing_filename = bs->backing_file;
    if (backing_filename[0] != '\0') {
-        char *backing_filename2 = g_malloc0(PATH_MAX);
        info->backing_filename = g_strdup(backing_filename);
        info->has_backing_filename = true;
-        bdrv_get_full_backing_filename(bs, backing_filename2, PATH_MAX, &err);
-        if (err) {
-            error_propagate(errp, err);
-            qapi_free_ImageInfo(info);
-            g_free(backing_filename2);
-            return;
-        }
+        bdrv_get_full_backing_filename(bs, backing_filename2,
+                                       sizeof(backing_filename2));

        if (strcmp(backing_filename, backing_filename2) != 0) {
            info->full_backing_filename =
@@ -261,7 +219,6 @@ void bdrv_query_image_info(BlockDriverState *bs,
            info->backing_filename_format = g_strdup(bs->backing_format);
            info->has_backing_filename_format = true;
        }
-        g_free(backing_filename2);
    }

    ret = bdrv_query_snapshot_info_list(bs, &info->snapshots, &err);
@@ -291,6 +248,9 @@ static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
 {
    BlockInfo *info = g_malloc0(sizeof(*info));
    BlockDriverState *bs = blk_bs(blk);
+    BlockDriverState *bs0;
+    ImageInfo **p_image_info;
+    Error *local_err = NULL;
    info->device = g_strdup(blk_name(blk));
    info->type = g_strdup("unknown");
    info->locked = blk_dev_is_medium_locked(blk);
@@ -301,21 +261,35 @@ static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
        info->tray_open = blk_dev_is_tray_open(blk);
    }

-    if (blk_iostatus_is_enabled(blk)) {
+    if (bdrv_iostatus_is_enabled(bs)) {
        info->has_io_status = true;
-        info->io_status = blk_iostatus(blk);
+        info->io_status = bs->iostatus;
    }

-    if (bs && !QLIST_EMPTY(&bs->dirty_bitmaps)) {
+    if (!QLIST_EMPTY(&bs->dirty_bitmaps)) {
        info->has_dirty_bitmaps = true;
        info->dirty_bitmaps = bdrv_query_dirty_bitmaps(bs);
    }

-    if (bs && bs->drv) {
+    if (bs->drv) {
        info->has_inserted = true;
-        info->inserted = bdrv_block_device_info(bs, errp);
-        if (info->inserted == NULL) {
-            goto err;
+        info->inserted = bdrv_block_device_info(bs);
+
+        bs0 = bs;
+        p_image_info = &info->inserted->image;
+        while (1) {
+            bdrv_query_image_info(bs0, p_image_info, &local_err);
+            if (local_err) {
+                error_propagate(errp, local_err);
+                goto err;
+            }
+            if (bs0->drv && bs0->backing_hd) {
+                bs0 = bs0->backing_hd;
+                (*p_image_info)->has_backing_image = true;
+                p_image_info = &((*p_image_info)->backing_image);
+            } else {
+                break;
+            }
        }
    }

@@ -326,8 +300,7 @@ static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
    qapi_free_BlockInfo(info);
 }

-static BlockStats *bdrv_query_stats(const BlockDriverState *bs,
-                                    bool query_backing)
+static BlockStats *bdrv_query_stats(const BlockDriverState *bs)
 {
    BlockStats *s;

@@ -338,88 +311,26 @@ static BlockStats *bdrv_query_stats(const BlockDriverState *bs,
        s->device = g_strdup(bdrv_get_device_name(bs));
    }

-    if (bdrv_get_node_name(bs)[0]) {
-        s->has_node_name = true;
-        s->node_name = g_strdup(bdrv_get_node_name(bs));
-    }
-
    s->stats = g_malloc0(sizeof(*s->stats));
-    if (bs->blk) {
-        BlockAcctStats *stats = blk_get_stats(bs->blk);
-        BlockAcctTimedStats *ts = NULL;
-
-        s->stats->rd_bytes = stats->nr_bytes[BLOCK_ACCT_READ];
-        s->stats->wr_bytes = stats->nr_bytes[BLOCK_ACCT_WRITE];
-        s->stats->rd_operations = stats->nr_ops[BLOCK_ACCT_READ];
-        s->stats->wr_operations = stats->nr_ops[BLOCK_ACCT_WRITE];
-
-        s->stats->failed_rd_operations = stats->failed_ops[BLOCK_ACCT_READ];
-        s->stats->failed_wr_operations = stats->failed_ops[BLOCK_ACCT_WRITE];
-        s->stats->failed_flush_operations = stats->failed_ops[BLOCK_ACCT_FLUSH];
-
-        s->stats->invalid_rd_operations = stats->invalid_ops[BLOCK_ACCT_READ];
-        s->stats->invalid_wr_operations = stats->invalid_ops[BLOCK_ACCT_WRITE];
-        s->stats->invalid_flush_operations =
-            stats->invalid_ops[BLOCK_ACCT_FLUSH];
-
-        s->stats->rd_merged = stats->merged[BLOCK_ACCT_READ];
-        s->stats->wr_merged = stats->merged[BLOCK_ACCT_WRITE];
-        s->stats->flush_operations = stats->nr_ops[BLOCK_ACCT_FLUSH];
-        s->stats->wr_total_time_ns = stats->total_time_ns[BLOCK_ACCT_WRITE];
-        s->stats->rd_total_time_ns = stats->total_time_ns[BLOCK_ACCT_READ];
-        s->stats->flush_total_time_ns = stats->total_time_ns[BLOCK_ACCT_FLUSH];
-
-        s->stats->has_idle_time_ns = stats->last_access_time_ns > 0;
-        if (s->stats->has_idle_time_ns) {
-            s->stats->idle_time_ns = block_acct_idle_time_ns(stats);
-        }
-
-        s->stats->account_invalid = stats->account_invalid;
-        s->stats->account_failed = stats->account_failed;
-
-        while ((ts = block_acct_interval_next(stats, ts))) {
-            BlockDeviceTimedStatsList *timed_stats =
-                g_malloc0(sizeof(*timed_stats));
-            BlockDeviceTimedStats *dev_stats = g_malloc0(sizeof(*dev_stats));
-            timed_stats->next = s->stats->timed_stats;
-            timed_stats->value = dev_stats;
-            s->stats->timed_stats = timed_stats;
-
-            TimedAverage *rd = &ts->latency[BLOCK_ACCT_READ];
-            TimedAverage *wr = &ts->latency[BLOCK_ACCT_WRITE];
-            TimedAverage *fl = &ts->latency[BLOCK_ACCT_FLUSH];
-
-            dev_stats->interval_length = ts->interval_length;
-
-            dev_stats->min_rd_latency_ns = timed_average_min(rd);
-            dev_stats->max_rd_latency_ns = timed_average_max(rd);
-            dev_stats->avg_rd_latency_ns = timed_average_avg(rd);
-
-            dev_stats->min_wr_latency_ns = timed_average_min(wr);
-            dev_stats->max_wr_latency_ns = timed_average_max(wr);
-            dev_stats->avg_wr_latency_ns = timed_average_avg(wr);
-
-            dev_stats->min_flush_latency_ns = timed_average_min(fl);
-            dev_stats->max_flush_latency_ns = timed_average_max(fl);
-            dev_stats->avg_flush_latency_ns = timed_average_avg(fl);
-
-            dev_stats->avg_rd_queue_depth =
-                block_acct_queue_depth(ts, BLOCK_ACCT_READ);
-            dev_stats->avg_wr_queue_depth =
-                block_acct_queue_depth(ts, BLOCK_ACCT_WRITE);
-        }
-    }
-
-    s->stats->wr_highest_offset = bs->wr_highest_offset;
+    s->stats->rd_bytes = bs->stats.nr_bytes[BLOCK_ACCT_READ];
+    s->stats->wr_bytes = bs->stats.nr_bytes[BLOCK_ACCT_WRITE];
+    s->stats->rd_operations = bs->stats.nr_ops[BLOCK_ACCT_READ];
+    s->stats->wr_operations = bs->stats.nr_ops[BLOCK_ACCT_WRITE];
+    s->stats->wr_highest_offset =
+        bs->stats.wr_highest_sector * BDRV_SECTOR_SIZE;
+    s->stats->flush_operations = bs->stats.nr_ops[BLOCK_ACCT_FLUSH];
+    s->stats->wr_total_time_ns = bs->stats.total_time_ns[BLOCK_ACCT_WRITE];
+    s->stats->rd_total_time_ns = bs->stats.total_time_ns[BLOCK_ACCT_READ];
+    s->stats->flush_total_time_ns = bs->stats.total_time_ns[BLOCK_ACCT_FLUSH];

    if (bs->file) {
        s->has_parent = true;
-        s->parent = bdrv_query_stats(bs->file->bs, query_backing);
+        s->parent = bdrv_query_stats(bs->file);
    }

-    if (query_backing && bs->backing) {
+    if (bs->backing_hd) {
        s->has_backing = true;
-        s->backing = bdrv_query_stats(bs->backing->bs, query_backing);
+        s->backing = bdrv_query_stats(bs->backing_hd);
    }

    return s;
@@ -436,9 +347,7 @@ BlockInfoList *qmp_query_block(Error **errp)
        bdrv_query_info(blk, &info->value, &local_err);
        if (local_err) {
            error_propagate(errp, local_err);
-            g_free(info);
-            qapi_free_BlockInfoList(head);
-            return NULL;
+            goto err;
        }

        *p_next = info;
@@ -446,24 +355,23 @@ BlockInfoList *qmp_query_block(Error **errp)
    }

    return head;
+
+ err:
+    qapi_free_BlockInfoList(head);
+    return NULL;
 }

-BlockStatsList *qmp_query_blockstats(bool has_query_nodes,
-                                     bool query_nodes,
-                                     Error **errp)
+BlockStatsList *qmp_query_blockstats(Error **errp)
 {
    BlockStatsList *head = NULL, **p_next = &head;
    BlockDriverState *bs = NULL;

-    /* Just to be safe if query_nodes is not always initialized */
-    query_nodes = has_query_nodes && query_nodes;
-
-    while ((bs = query_nodes ? bdrv_next_node(bs) : bdrv_next(bs))) {
+     while ((bs = bdrv_next(bs))) {
        BlockStatsList *info = g_malloc0(sizeof(*info));
        AioContext *ctx = bdrv_get_aio_context(bs);

        aio_context_acquire(ctx);
-        info->value = bdrv_query_stats(bs, !query_nodes);
+        info->value = bdrv_query_stats(bs);
        aio_context_release(ctx);

        *p_next = info;
@@ -477,7 +385,7 @@ BlockStatsList *qmp_query_blockstats(bool has_query_nodes,

 static char *get_human_readable_size(char *buf, int buf_size, int64_t size)
 {
-    static const char suffixes[NB_SUFFIXES] = {'K', 'M', 'G', 'T'};
+    static const char suffixes[NB_SUFFIXES] = "KMGT";
    int64_t base;
    int i;

@@ -573,9 +481,18 @@ static void dump_qobject(fprintf_function func_fprintf, void *f,
        }
        case QTYPE_QBOOL: {
            QBool *value = qobject_to_qbool(obj);
-            func_fprintf(f, "%s", qbool_get_bool(value) ? "true" : "false");
+            func_fprintf(f, "%s", qbool_get_int(value) ? "true" : "false");
            break;
        }
+        case QTYPE_QERROR: {
+            QString *value = qerror_human((QError *)obj);
+            func_fprintf(f, "%s", qstring_get_str(value));
+            QDECREF(value);
+            break;
+        }
+        case QTYPE_NONE:
+            break;
+        case QTYPE_MAX:
        default:
            abort();
    }
@@ -25,8 +25,7 @@
 #include "block/block_int.h"
 #include "qemu/module.h"
 #include <zlib.h>
-#include "qapi/qmp/qerror.h"
-#include "crypto/cipher.h"
+#include "qemu/aes.h"
 #include "migration/migration.h"

 /**************************************************************/
@@ -72,8 +71,10 @@ typedef struct BDRVQcowState {
    uint8_t *cluster_cache;
    uint8_t *cluster_data;
    uint64_t cluster_cache_offset;
-    QCryptoCipher *cipher; /* NULL if no key yet */
+    uint32_t crypt_method; /* current crypt method, 0 if no key yet */
    uint32_t crypt_method_header;
+    AES_KEY aes_encrypt_key;
+    AES_KEY aes_decrypt_key;
    CoMutex lock;
    Error *migration_blocker;
 } BDRVQcowState;
@@ -100,7 +101,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
    int ret;
    QCowHeader header;

-    ret = bdrv_pread(bs->file->bs, 0, &header, sizeof(header));
+    ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
    if (ret < 0) {
        goto fail;
    }
@@ -122,8 +123,8 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
        char version[64];
        snprintf(version, sizeof(version), "QCOW version %" PRIu32,
                 header.version);
-        error_setg(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
-                   bdrv_get_device_or_node_name(bs), "qcow", version);
+        error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+                  bdrv_get_device_name(bs), "qcow", version);
        ret = -ENOTSUP;
        goto fail;
    }
@@ -152,11 +153,6 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
        ret = -EINVAL;
        goto fail;
    }
-    if (!qcrypto_cipher_supports(QCRYPTO_CIPHER_ALG_AES_128)) {
-        error_setg(errp, "AES cipher not available");
-        ret = -EINVAL;
-        goto fail;
-    }
    s->crypt_method_header = header.crypt_method;
    if (s->crypt_method_header) {
        bs->encrypted = 1;
@@ -193,7 +189,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
        goto fail;
    }

-    ret = bdrv_pread(bs->file->bs, s->l1_table_offset, s->l1_table,
+    ret = bdrv_pread(bs->file, s->l1_table_offset, s->l1_table,
               s->l1_size * sizeof(uint64_t));
    if (ret < 0) {
        goto fail;
@@ -205,7 +201,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,

    /* alloc L2 cache (max. 64k * 16 * 8 = 8 MB) */
    s->l2_cache =
-        qemu_try_blockalign(bs->file->bs,
+        qemu_try_blockalign(bs->file,
                            s->l2_size * L2_CACHE_SIZE * sizeof(uint64_t));
    if (s->l2_cache == NULL) {
        error_setg(errp, "Could not allocate L2 table cache");
@@ -219,12 +215,12 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
    /* read the backing file name */
    if (header.backing_file_offset != 0) {
        len = header.backing_file_size;
-        if (len > 1023 || len >= sizeof(bs->backing_file)) {
+        if (len > 1023) {
            error_setg(errp, "Backing file name too long");
            ret = -EINVAL;
            goto fail;
        }
-        ret = bdrv_pread(bs->file->bs, header.backing_file_offset,
+        ret = bdrv_pread(bs->file, header.backing_file_offset,
                   bs->backing_file, len);
        if (ret < 0) {
            goto fail;
@@ -233,9 +229,9 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
    }

    /* Disable migration when qcow images are used */
-    error_setg(&s->migration_blocker, "The qcow format used by node '%s' "
-               "does not support live migration",
-               bdrv_get_device_or_node_name(bs));
+    error_set(&s->migration_blocker,
+              QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
+              "qcow", bdrv_get_device_name(bs), "live migration");
    migrate_add_blocker(s->migration_blocker);

    qemu_co_mutex_init(&s->lock);
@@ -263,7 +259,6 @@ static int qcow_set_key(BlockDriverState *bs, const char *key)
    BDRVQcowState *s = bs->opaque;
    uint8_t keybuf[16];
    int len, i;
-    Error *err;

    memset(keybuf, 0, 16);
    len = strlen(key);
@@ -274,68 +269,38 @@ static int qcow_set_key(BlockDriverState *bs, const char *key)
    for(i = 0;i < len;i++) {
        keybuf[i] = key[i];
    }
-    assert(bs->encrypted);
+    s->crypt_method = s->crypt_method_header;

-    qcrypto_cipher_free(s->cipher);
-    s->cipher = qcrypto_cipher_new(
-        QCRYPTO_CIPHER_ALG_AES_128,
-        QCRYPTO_CIPHER_MODE_CBC,
-        keybuf, G_N_ELEMENTS(keybuf),
-        &err);
-
-    if (!s->cipher) {
-        /* XXX would be nice if errors in this method could
-         * be properly propagate to the caller. Would need
-         * the bdrv_set_key() API signature to be fixed. */
-        error_free(err);
+    if (AES_set_encrypt_key(keybuf, 128, &s->aes_encrypt_key) != 0)
+        return -1;
+    if (AES_set_decrypt_key(keybuf, 128, &s->aes_decrypt_key) != 0)
        return -1;
-    }
    return 0;
 }

 /* The crypt function is compatible with the linux cryptoloop
   algorithm for < 4 GB images. NOTE: out_buf == in_buf is
   supported */
-static int encrypt_sectors(BDRVQcowState *s, int64_t sector_num,
-                           uint8_t *out_buf, const uint8_t *in_buf,
-                           int nb_sectors, bool enc, Error **errp)
+static void encrypt_sectors(BDRVQcowState *s, int64_t sector_num,
+                            uint8_t *out_buf, const uint8_t *in_buf,
+                            int nb_sectors, int enc,
+                            const AES_KEY *key)
 {
    union {
        uint64_t ll[2];
        uint8_t b[16];
    } ivec;
    int i;
-    int ret;

    for(i = 0; i < nb_sectors; i++) {
        ivec.ll[0] = cpu_to_le64(sector_num);
        ivec.ll[1] = 0;
-        if (qcrypto_cipher_setiv(s->cipher,
-                                 ivec.b, G_N_ELEMENTS(ivec.b),
-                                 errp) < 0) {
-            return -1;
-        }
-        if (enc) {
-            ret = qcrypto_cipher_encrypt(s->cipher,
-                                         in_buf,
-                                         out_buf,
-                                         512,
-                                         errp);
-        } else {
-            ret = qcrypto_cipher_decrypt(s->cipher,
-                                         in_buf,
-                                         out_buf,
-                                         512,
-                                         errp);
-        }
-        if (ret < 0) {
-            return -1;
-        }
+        AES_cbc_encrypt(in_buf, out_buf, 512, key,
+                        ivec.b, enc);
        sector_num++;
        in_buf += 512;
        out_buf += 512;
    }
-    return 0;
 }

 /* 'allocate' is:
@@ -369,13 +334,13 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
        if (!allocate)
            return 0;
        /* allocate a new l2 entry */
-        l2_offset = bdrv_getlength(bs->file->bs);
+        l2_offset = bdrv_getlength(bs->file);
        /* round to cluster size */
        l2_offset = (l2_offset + s->cluster_size - 1) & ~(s->cluster_size - 1);
        /* update the L1 entry */
        s->l1_table[l1_index] = l2_offset;
        tmp = cpu_to_be64(l2_offset);
-        if (bdrv_pwrite_sync(bs->file->bs,
+        if (bdrv_pwrite_sync(bs->file,
                s->l1_table_offset + l1_index * sizeof(tmp),
                &tmp, sizeof(tmp)) < 0)
            return 0;
@@ -405,12 +370,11 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
    l2_table = s->l2_cache + (min_index << s->l2_bits);
    if (new_l2_table) {
        memset(l2_table, 0, s->l2_size * sizeof(uint64_t));
-        if (bdrv_pwrite_sync(bs->file->bs, l2_offset, l2_table,
+        if (bdrv_pwrite_sync(bs->file, l2_offset, l2_table,
                s->l2_size * sizeof(uint64_t)) < 0)
            return 0;
    } else {
-        if (bdrv_pread(bs->file->bs, l2_offset, l2_table,
-                       s->l2_size * sizeof(uint64_t)) !=
+        if (bdrv_pread(bs->file, l2_offset, l2_table, s->l2_size * sizeof(uint64_t)) !=
            s->l2_size * sizeof(uint64_t))
            return 0;
    }
@@ -431,42 +395,34 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
               overwritten */
            if (decompress_cluster(bs, cluster_offset) < 0)
                return 0;
-            cluster_offset = bdrv_getlength(bs->file->bs);
+            cluster_offset = bdrv_getlength(bs->file);
            cluster_offset = (cluster_offset + s->cluster_size - 1) &
                ~(s->cluster_size - 1);
            /* write the cluster content */
-            if (bdrv_pwrite(bs->file->bs, cluster_offset, s->cluster_cache,
-                            s->cluster_size) !=
+            if (bdrv_pwrite(bs->file, cluster_offset, s->cluster_cache, s->cluster_size) !=
                s->cluster_size)
                return -1;
        } else {
-            cluster_offset = bdrv_getlength(bs->file->bs);
+            cluster_offset = bdrv_getlength(bs->file);
            if (allocate == 1) {
                /* round to cluster size */
                cluster_offset = (cluster_offset + s->cluster_size - 1) &
                    ~(s->cluster_size - 1);
-                bdrv_truncate(bs->file->bs, cluster_offset + s->cluster_size);
+                bdrv_truncate(bs->file, cluster_offset + s->cluster_size);
                /* if encrypted, we must initialize the cluster
                   content which won't be written */
-                if (bs->encrypted &&
+                if (s->crypt_method &&
                    (n_end - n_start) < s->cluster_sectors) {
                    uint64_t start_sect;
-                    assert(s->cipher);
                    start_sect = (offset & ~(s->cluster_size - 1)) >> 9;
                    memset(s->cluster_data + 512, 0x00, 512);
                    for(i = 0; i < s->cluster_sectors; i++) {
                        if (i < n_start || i >= n_end) {
-                            Error *err = NULL;
-                            if (encrypt_sectors(s, start_sect + i,
-                                                s->cluster_data,
-                                                s->cluster_data + 512, 1,
-                                                true, &err) < 0) {
-                                error_free(err);
-                                errno = EIO;
-                                return -1;
-                            }
-                            if (bdrv_pwrite(bs->file->bs,
-                                            cluster_offset + i * 512,
+                            encrypt_sectors(s, start_sect + i,
+                                            s->cluster_data,
+                                            s->cluster_data + 512, 1, 1,
+                                            &s->aes_encrypt_key);
+                            if (bdrv_pwrite(bs->file, cluster_offset + i * 512,
                                            s->cluster_data, 512) != 512)
                                return -1;
                        }
@@ -480,7 +436,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
        /* update L2 table */
        tmp = cpu_to_be64(cluster_offset);
        l2_table[l2_index] = tmp;
-        if (bdrv_pwrite_sync(bs->file->bs, l2_offset + l2_index * sizeof(tmp),
+        if (bdrv_pwrite_sync(bs->file, l2_offset + l2_index * sizeof(tmp),
                &tmp, sizeof(tmp)) < 0)
            return 0;
    }
@@ -505,7 +461,7 @@ static int64_t coroutine_fn qcow_co_get_block_status(BlockDriverState *bs,
    if (!cluster_offset) {
        return 0;
    }
-    if ((cluster_offset & QCOW_OFLAG_COMPRESSED) || s->cipher) {
+    if ((cluster_offset & QCOW_OFLAG_COMPRESSED) || s->crypt_method) {
        return BDRV_BLOCK_DATA;
    }
    cluster_offset |= (index_in_cluster << BDRV_SECTOR_BITS);
@@ -549,7 +505,7 @@ static int decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
    if (s->cluster_cache_offset != coffset) {
        csize = cluster_offset >> (63 - s->cluster_bits);
        csize &= (s->cluster_size - 1);
-        ret = bdrv_pread(bs->file->bs, coffset, s->cluster_data, csize);
+        ret = bdrv_pread(bs->file, coffset, s->cluster_data, csize);
        if (ret != csize)
            return -1;
        if (decompress_buffer(s->cluster_cache, s->cluster_size,
@@ -572,7 +528,6 @@ static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num,
    QEMUIOVector hd_qiov;
    uint8_t *buf;
    void *orig_buf;
-    Error *err = NULL;

    if (qiov->niov > 1) {
        buf = orig_buf = qemu_try_blockalign(bs, qiov->size);
@@ -597,13 +552,13 @@ static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num,
        }

        if (!cluster_offset) {
-            if (bs->backing) {
+            if (bs->backing_hd) {
                /* read from the base image */
                hd_iov.iov_base = (void *)buf;
                hd_iov.iov_len = n * 512;
                qemu_iovec_init_external(&hd_qiov, &hd_iov, 1);
                qemu_co_mutex_unlock(&s->lock);
-                ret = bdrv_co_readv(bs->backing->bs, sector_num,
+                ret = bdrv_co_readv(bs->backing_hd, sector_num,
                                    n, &hd_qiov);
                qemu_co_mutex_lock(&s->lock);
                if (ret < 0) {
@@ -628,19 +583,17 @@ static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num,
            hd_iov.iov_len = n * 512;
            qemu_iovec_init_external(&hd_qiov, &hd_iov, 1);
            qemu_co_mutex_unlock(&s->lock);
-            ret = bdrv_co_readv(bs->file->bs,
+            ret = bdrv_co_readv(bs->file,
                                (cluster_offset >> 9) + index_in_cluster,
                                n, &hd_qiov);
            qemu_co_mutex_lock(&s->lock);
            if (ret < 0) {
                break;
            }
-            if (bs->encrypted) {
-                assert(s->cipher);
-                if (encrypt_sectors(s, sector_num, buf, buf,
-                                    n, false, &err) < 0) {
-                    goto fail;
-                }
+            if (s->crypt_method) {
+                encrypt_sectors(s, sector_num, buf, buf,
+                                n, 0,
+                                &s->aes_decrypt_key);
            }
        }
        ret = 0;
@@ -661,7 +614,6 @@ done:
    return ret;

 fail:
-    error_free(err);
    ret = -EIO;
    goto done;
 }
@@ -709,18 +661,12 @@ static coroutine_fn int qcow_co_writev(BlockDriverState *bs, int64_t sector_num,
            ret = -EIO;
            break;
        }
-        if (bs->encrypted) {
-            Error *err = NULL;
-            assert(s->cipher);
+        if (s->crypt_method) {
            if (!cluster_data) {
                cluster_data = g_malloc0(s->cluster_size);
            }
-            if (encrypt_sectors(s, sector_num, cluster_data, buf,
-                                n, true, &err) < 0) {
-                error_free(err);
-                ret = -EIO;
-                break;
-            }
+            encrypt_sectors(s, sector_num, cluster_data, buf,
+                            n, 1, &s->aes_encrypt_key);
            src_buf = cluster_data;
        } else {
            src_buf = buf;
@@ -730,7 +676,7 @@ static coroutine_fn int qcow_co_writev(BlockDriverState *bs, int64_t sector_num,
        hd_iov.iov_len = n * 512;
        qemu_iovec_init_external(&hd_qiov, &hd_iov, 1);
        qemu_co_mutex_unlock(&s->lock);
-        ret = bdrv_co_writev(bs->file->bs,
+        ret = bdrv_co_writev(bs->file,
                             (cluster_offset >> 9) + index_in_cluster,
                             n, &hd_qiov);
        qemu_co_mutex_lock(&s->lock);
@@ -757,8 +703,6 @@ static void qcow_close(BlockDriverState *bs)
 {
    BDRVQcowState *s = bs->opaque;

-    qcrypto_cipher_free(s->cipher);
-    s->cipher = NULL;
    g_free(s->l1_table);
    qemu_vfree(s->l2_cache);
    g_free(s->cluster_cache);
@@ -796,7 +740,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)

    qcow_bs = NULL;
    ret = bdrv_open(&qcow_bs, filename, NULL, NULL,
-                    BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                    BDRV_O_RDWR | BDRV_O_PROTOCOL, NULL, &local_err);
    if (ret < 0) {
        error_propagate(errp, local_err);
        goto cleanup;
@@ -882,10 +826,10 @@ static int qcow_make_empty(BlockDriverState *bs)
    int ret;

    memset(s->l1_table, 0, l1_length);
-    if (bdrv_pwrite_sync(bs->file->bs, s->l1_table_offset, s->l1_table,
+    if (bdrv_pwrite_sync(bs->file, s->l1_table_offset, s->l1_table,
            l1_length) < 0)
        return -1;
-    ret = bdrv_truncate(bs->file->bs, s->l1_table_offset + l1_length);
+    ret = bdrv_truncate(bs->file, s->l1_table_offset + l1_length);
    if (ret < 0)
        return ret;

@@ -965,7 +909,7 @@ static int qcow_write_compressed(BlockDriverState *bs, int64_t sector_num,
        }

        cluster_offset &= s->cluster_offset_mask;
-        ret = bdrv_pwrite(bs->file->bs, cluster_offset, out_buf, out_len);
+        ret = bdrv_pwrite(bs->file, cluster_offset, out_buf, out_len);
        if (ret < 0) {
            goto fail;
        }
@@ -22,133 +22,68 @@
 * THE SOFTWARE.
 */

-/* Needed for CONFIG_MADVISE */
-#include "config-host.h"
-
-#if defined(CONFIG_MADVISE) || defined(CONFIG_POSIX_MADVISE)
-#include <sys/mman.h>
-#endif
-
 #include "block/block_int.h"
 #include "qemu-common.h"
-#include "qemu/osdep.h"
 #include "qcow2.h"
 #include "trace.h"

 typedef struct Qcow2CachedTable {
-    int64_t  offset;
-    uint64_t lru_counter;
-    int      ref;
-    bool     dirty;
+    void*   table;
+    int64_t offset;
+    bool    dirty;
+    int     cache_hits;
+    int     ref;
 } Qcow2CachedTable;

 struct Qcow2Cache {
-    Qcow2CachedTable       *entries;
-    struct Qcow2Cache      *depends;
+    Qcow2CachedTable*       entries;
+    struct Qcow2Cache*      depends;
    int                     size;
    bool                    depends_on_flush;
-    void                   *table_array;
-    uint64_t                lru_counter;
-    uint64_t                cache_clean_lru_counter;
 };

-static inline void *qcow2_cache_get_table_addr(BlockDriverState *bs,
-                    Qcow2Cache *c, int table)
-{
-    BDRVQcow2State *s = bs->opaque;
-    return (uint8_t *) c->table_array + (size_t) table * s->cluster_size;
-}
-
-static inline int qcow2_cache_get_table_idx(BlockDriverState *bs,
-                  Qcow2Cache *c, void *table)
-{
-    BDRVQcow2State *s = bs->opaque;
-    ptrdiff_t table_offset = (uint8_t *) table - (uint8_t *) c->table_array;
-    int idx = table_offset / s->cluster_size;
-    assert(idx >= 0 && idx < c->size && table_offset % s->cluster_size == 0);
-    return idx;
-}
-
-static void qcow2_cache_table_release(BlockDriverState *bs, Qcow2Cache *c,
-                                      int i, int num_tables)
-{
-#if QEMU_MADV_DONTNEED != QEMU_MADV_INVALID
-    BDRVQcow2State *s = bs->opaque;
-    void *t = qcow2_cache_get_table_addr(bs, c, i);
-    int align = getpagesize();
-    size_t mem_size = (size_t) s->cluster_size * num_tables;
-    size_t offset = QEMU_ALIGN_UP((uintptr_t) t, align) - (uintptr_t) t;
-    size_t length = QEMU_ALIGN_DOWN(mem_size - offset, align);
-    if (length > 0) {
-        qemu_madvise((uint8_t *) t + offset, length, QEMU_MADV_DONTNEED);
-    }
-#endif
-}
-
-static inline bool can_clean_entry(Qcow2Cache *c, int i)
-{
-    Qcow2CachedTable *t = &c->entries[i];
-    return t->ref == 0 && !t->dirty && t->offset != 0 &&
-        t->lru_counter <= c->cache_clean_lru_counter;
-}
-
-void qcow2_cache_clean_unused(BlockDriverState *bs, Qcow2Cache *c)
-{
-    int i = 0;
-    while (i < c->size) {
-        int to_clean = 0;
-
-        /* Skip the entries that we don't need to clean */
-        while (i < c->size && !can_clean_entry(c, i)) {
-            i++;
-        }
-
-        /* And count how many we can clean in a row */
-        while (i < c->size && can_clean_entry(c, i)) {
-            c->entries[i].offset = 0;
-            c->entries[i].lru_counter = 0;
-            i++;
-            to_clean++;
-        }
-
-        if (to_clean > 0) {
-            qcow2_cache_table_release(bs, c, i - to_clean, to_clean);
-        }
-    }
-
-    c->cache_clean_lru_counter = c->lru_counter;
-}
-
 Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    Qcow2Cache *c;
+    int i;

    c = g_new0(Qcow2Cache, 1);
    c->size = num_tables;
    c->entries = g_try_new0(Qcow2CachedTable, num_tables);
-    c->table_array = qemu_try_blockalign(bs->file->bs,
-                                         (size_t) num_tables * s->cluster_size);
+    if (!c->entries) {
+        goto fail;
+    }

-    if (!c->entries || !c->table_array) {
-        qemu_vfree(c->table_array);
-        g_free(c->entries);
-        g_free(c);
-        c = NULL;
+    for (i = 0; i < c->size; i++) {
+        c->entries[i].table = qemu_try_blockalign(bs->file, s->cluster_size);
+        if (c->entries[i].table == NULL) {
+            goto fail;
+        }
    }

    return c;
+
+fail:
+    if (c->entries) {
+        for (i = 0; i < c->size; i++) {
+            qemu_vfree(c->entries[i].table);
+        }
+    }
+    g_free(c->entries);
+    g_free(c);
+    return NULL;
 }

-int qcow2_cache_destroy(BlockDriverState *bs, Qcow2Cache *c)
+int qcow2_cache_destroy(BlockDriverState* bs, Qcow2Cache *c)
 {
    int i;

    for (i = 0; i < c->size; i++) {
        assert(c->entries[i].ref == 0);
+        qemu_vfree(c->entries[i].table);
    }

-    qemu_vfree(c->table_array);
    g_free(c->entries);
    g_free(c);

@@ -172,7 +107,7 @@ static int qcow2_cache_flush_dependency(BlockDriverState *bs, Qcow2Cache *c)

 static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    int ret = 0;

    if (!c->entries[i].dirty || !c->entries[i].offset) {
@@ -185,7 +120,7 @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)
    if (c->depends) {
        ret = qcow2_cache_flush_dependency(bs, c);
    } else if (c->depends_on_flush) {
-        ret = bdrv_flush(bs->file->bs);
+        ret = bdrv_flush(bs->file);
        if (ret >= 0) {
            c->depends_on_flush = false;
        }
@@ -216,8 +151,8 @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)
        BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE);
    }

-    ret = bdrv_pwrite(bs->file->bs, c->entries[i].offset,
-                      qcow2_cache_get_table_addr(bs, c, i), s->cluster_size);
+    ret = bdrv_pwrite(bs->file, c->entries[i].offset, c->entries[i].table,
+        s->cluster_size);
    if (ret < 0) {
        return ret;
    }
@@ -229,7 +164,7 @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)

 int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    int result = 0;
    int ret;
    int i;
@@ -244,7 +179,7 @@ int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c)
    }

    if (result == 0) {
-        ret = bdrv_flush(bs->file->bs);
+        ret = bdrv_flush(bs->file);
        if (ret < 0) {
            result = ret;
        }
@@ -293,55 +228,66 @@ int qcow2_cache_empty(BlockDriverState *bs, Qcow2Cache *c)
    for (i = 0; i < c->size; i++) {
        assert(c->entries[i].ref == 0);
        c->entries[i].offset = 0;
-        c->entries[i].lru_counter = 0;
+        c->entries[i].cache_hits = 0;
    }

-    qcow2_cache_table_release(bs, c, 0, c->size);
-
-    c->lru_counter = 0;
-
    return 0;
 }

+static int qcow2_cache_find_entry_to_replace(Qcow2Cache *c)
+{
+    int i;
+    int min_count = INT_MAX;
+    int min_index = -1;
+
+
+    for (i = 0; i < c->size; i++) {
+        if (c->entries[i].ref) {
+            continue;
+        }
+
+        if (c->entries[i].cache_hits < min_count) {
+            min_index = i;
+            min_count = c->entries[i].cache_hits;
+        }
+
+        /* Give newer hits priority */
+        /* TODO Check how to optimize the replacement strategy */
+        c->entries[i].cache_hits /= 2;
+    }
+
+    if (min_index == -1) {
+        /* This can't happen in current synchronous code, but leave the check
+         * here as a reminder for whoever starts using AIO with the cache */
+        abort();
+    }
+    return min_index;
+}
+
 static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c,
    uint64_t offset, void **table, bool read_from_disk)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    int i;
    int ret;
-    int lookup_index;
-    uint64_t min_lru_counter = UINT64_MAX;
-    int min_lru_index = -1;

    trace_qcow2_cache_get(qemu_coroutine_self(), c == s->l2_table_cache,
                          offset, read_from_disk);

    /* Check if the table is already cached */
-    i = lookup_index = (offset / s->cluster_size * 4) % c->size;
-    do {
-        const Qcow2CachedTable *t = &c->entries[i];
-        if (t->offset == offset) {
+    for (i = 0; i < c->size; i++) {
+        if (c->entries[i].offset == offset) {
            goto found;
        }
-        if (t->ref == 0 && t->lru_counter < min_lru_counter) {
-            min_lru_counter = t->lru_counter;
-            min_lru_index = i;
-        }
-        if (++i == c->size) {
-            i = 0;
-        }
-    } while (i != lookup_index);
-
-    if (min_lru_index == -1) {
-        /* This can't happen in current synchronous code, but leave the check
-         * here as a reminder for whoever starts using AIO with the cache */
-        abort();
    }

-    /* Cache miss: write a table back and replace it */
-    i = min_lru_index;
+    /* If not, write a table back and replace it */
+    i = qcow2_cache_find_entry_to_replace(c);
    trace_qcow2_cache_get_replace_entry(qemu_coroutine_self(),
                                        c == s->l2_table_cache, i);
+    if (i < 0) {
+        return i;
+    }

    ret = qcow2_cache_entry_flush(bs, c, i);
    if (ret < 0) {
@@ -356,20 +302,22 @@ static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c,
            BLKDBG_EVENT(bs->file, BLKDBG_L2_LOAD);
        }

-        ret = bdrv_pread(bs->file->bs, offset,
-                         qcow2_cache_get_table_addr(bs, c, i),
-                         s->cluster_size);
+        ret = bdrv_pread(bs->file, offset, c->entries[i].table, s->cluster_size);
        if (ret < 0) {
            return ret;
        }
    }

+    /* Give the table some hits for the start so that it won't be replaced
+     * immediately. The number 32 is completely arbitrary. */
+    c->entries[i].cache_hits = 32;
    c->entries[i].offset = offset;

    /* And return the right table */
 found:
+    c->entries[i].cache_hits++;
    c->entries[i].ref++;
-    *table = qcow2_cache_get_table_addr(bs, c, i);
+    *table = c->entries[i].table;

    trace_qcow2_cache_get_done(qemu_coroutine_self(),
                               c == s->l2_table_cache, i);
@@ -389,24 +337,36 @@ int qcow2_cache_get_empty(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset,
    return qcow2_cache_do_get(bs, c, offset, table, false);
 }

-void qcow2_cache_put(BlockDriverState *bs, Qcow2Cache *c, void **table)
+int qcow2_cache_put(BlockDriverState *bs, Qcow2Cache *c, void **table)
 {
-    int i = qcow2_cache_get_table_idx(bs, c, *table);
+    int i;

+    for (i = 0; i < c->size; i++) {
+        if (c->entries[i].table == *table) {
+            goto found;
+        }
+    }
+    return -ENOENT;
+
+found:
    c->entries[i].ref--;
    *table = NULL;

-    if (c->entries[i].ref == 0) {
-        c->entries[i].lru_counter = ++c->lru_counter;
-    }
-
    assert(c->entries[i].ref >= 0);
+    return 0;
 }

-void qcow2_cache_entry_mark_dirty(BlockDriverState *bs, Qcow2Cache *c,
-     void *table)
+void qcow2_cache_entry_mark_dirty(Qcow2Cache *c, void *table)
 {
-    int i = qcow2_cache_get_table_idx(bs, c, table);
-    assert(c->entries[i].offset != 0);
+    int i;
+
+    for (i = 0; i < c->size; i++) {
+        if (c->entries[i].table == table) {
+            goto found;
+        }
+    }
+    abort();
+
+found:
    c->entries[i].dirty = true;
 }
@@ -32,7 +32,7 @@
 int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
                        bool exact_size)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    int new_l1_size2, ret, i;
    uint64_t *new_l1_table;
    int64_t old_l1_table_offset, old_l1_size;
@@ -72,7 +72,7 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
 #endif

    new_l1_size2 = sizeof(uint64_t) * new_l1_size;
-    new_l1_table = qemu_try_blockalign(bs->file->bs,
+    new_l1_table = qemu_try_blockalign(bs->file,
                                       align_offset(new_l1_size2, 512));
    if (new_l1_table == NULL) {
        return -ENOMEM;
@@ -105,8 +105,7 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
    BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_WRITE_TABLE);
    for(i = 0; i < s->l1_size; i++)
        new_l1_table[i] = cpu_to_be64(new_l1_table[i]);
-    ret = bdrv_pwrite_sync(bs->file->bs, new_l1_table_offset,
-                           new_l1_table, new_l1_size2);
+    ret = bdrv_pwrite_sync(bs->file, new_l1_table_offset, new_l1_table, new_l1_size2);
    if (ret < 0)
        goto fail;
    for(i = 0; i < s->l1_size; i++)
@@ -116,8 +115,7 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
    BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_ACTIVATE_TABLE);
    cpu_to_be32w((uint32_t*)data, new_l1_size);
    stq_be_p(data + 4, new_l1_table_offset);
-    ret = bdrv_pwrite_sync(bs->file->bs, offsetof(QCowHeader, l1_size),
-                           data, sizeof(data));
+    ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, l1_size), data,sizeof(data));
    if (ret < 0) {
        goto fail;
    }
@@ -150,7 +148,7 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
 static int l2_load(BlockDriverState *bs, uint64_t l2_offset,
    uint64_t **l2_table)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    int ret;

    ret = qcow2_cache_get(bs, s->l2_table_cache, l2_offset, (void**) l2_table);
@@ -165,7 +163,7 @@ static int l2_load(BlockDriverState *bs, uint64_t l2_offset,
 #define L1_ENTRIES_PER_SECTOR (512 / 8)
 int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    uint64_t buf[L1_ENTRIES_PER_SECTOR] = { 0 };
    int l1_start_index;
    int i, ret;
@@ -184,9 +182,8 @@ int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index)
    }

    BLKDBG_EVENT(bs->file, BLKDBG_L1_UPDATE);
-    ret = bdrv_pwrite_sync(bs->file->bs,
-                           s->l1_table_offset + 8 * l1_start_index,
-                           buf, sizeof(buf));
+    ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset + 8 * l1_start_index,
+        buf, sizeof(buf));
    if (ret < 0) {
        return ret;
    }
@@ -206,7 +203,7 @@ int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index)

 static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    uint64_t old_l2_offset;
    uint64_t *l2_table = NULL;
    int64_t l2_offset;
@@ -256,14 +253,17 @@ static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table)

        memcpy(l2_table, old_table, s->cluster_size);

-        qcow2_cache_put(bs, s->l2_table_cache, (void **) &old_table);
+        ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &old_table);
+        if (ret < 0) {
+            goto fail;
+        }
    }

    /* write the l2 table to the file */
    BLKDBG_EVENT(bs->file, BLKDBG_L2_ALLOC_WRITE);

    trace_qcow2_l2_allocate_write_l2(bs, l1_index);
-    qcow2_cache_entry_mark_dirty(bs, s->l2_table_cache, l2_table);
+    qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
    ret = qcow2_cache_flush(bs, s->l2_table_cache);
    if (ret < 0) {
        goto fail;
@@ -301,7 +301,7 @@ fail:
 * as contiguous. (This allows it, for example, to stop at the first compressed
 * cluster which may require a different handling)
 */
-static int count_contiguous_clusters(int nb_clusters, int cluster_size,
+static int count_contiguous_clusters(uint64_t nb_clusters, int cluster_size,
        uint64_t *l2_table, uint64_t stop_flags)
 {
    int i;
@@ -312,7 +312,7 @@ static int count_contiguous_clusters(int nb_clusters, int cluster_size,
    if (!offset)
        return 0;

-    assert(qcow2_get_cluster_type(first_entry) == QCOW2_CLUSTER_NORMAL);
+    assert(qcow2_get_cluster_type(first_entry) != QCOW2_CLUSTER_COMPRESSED);

    for (i = 0; i < nb_clusters; i++) {
        uint64_t l2_entry = be64_to_cpu(l2_table[i]) & mask;
@@ -324,16 +324,14 @@ static int count_contiguous_clusters(int nb_clusters, int cluster_size,
 	return i;
 }

-static int count_contiguous_clusters_by_type(int nb_clusters,
-                                             uint64_t *l2_table,
-                                             int wanted_type)
+static int count_contiguous_free_clusters(uint64_t nb_clusters, uint64_t *l2_table)
 {
    int i;

    for (i = 0; i < nb_clusters; i++) {
        int type = qcow2_get_cluster_type(be64_to_cpu(l2_table[i]));

-        if (type != wanted_type) {
+        if (type != QCOW2_CLUSTER_UNALLOCATED) {
            break;
        }
    }
@@ -344,47 +342,26 @@ static int count_contiguous_clusters_by_type(int nb_clusters,
 /* The crypt function is compatible with the linux cryptoloop
   algorithm for < 4 GB images. NOTE: out_buf == in_buf is
   supported */
-int qcow2_encrypt_sectors(BDRVQcow2State *s, int64_t sector_num,
-                          uint8_t *out_buf, const uint8_t *in_buf,
-                          int nb_sectors, bool enc,
-                          Error **errp)
+void qcow2_encrypt_sectors(BDRVQcowState *s, int64_t sector_num,
+                           uint8_t *out_buf, const uint8_t *in_buf,
+                           int nb_sectors, int enc,
+                           const AES_KEY *key)
 {
    union {
        uint64_t ll[2];
        uint8_t b[16];
    } ivec;
    int i;
-    int ret;

    for(i = 0; i < nb_sectors; i++) {
        ivec.ll[0] = cpu_to_le64(sector_num);
        ivec.ll[1] = 0;
-        if (qcrypto_cipher_setiv(s->cipher,
-                                 ivec.b, G_N_ELEMENTS(ivec.b),
-                                 errp) < 0) {
-            return -1;
-        }
-        if (enc) {
-            ret = qcrypto_cipher_encrypt(s->cipher,
-                                         in_buf,
-                                         out_buf,
-                                         512,
-                                         errp);
-        } else {
-            ret = qcrypto_cipher_decrypt(s->cipher,
-                                         in_buf,
-                                         out_buf,
-                                         512,
-                                         errp);
-        }
-        if (ret < 0) {
-            return -1;
-        }
+        AES_cbc_encrypt(in_buf, out_buf, 512, key,
+                        ivec.b, enc);
        sector_num++;
        in_buf += 512;
        out_buf += 512;
    }
-    return 0;
 }

 static int coroutine_fn copy_sectors(BlockDriverState *bs,
@@ -392,7 +369,7 @@ static int coroutine_fn copy_sectors(BlockDriverState *bs,
                                     uint64_t cluster_offset,
                                     int n_start, int n_end)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    QEMUIOVector qiov;
    struct iovec iov;
    int n, ret;
@@ -426,16 +403,10 @@ static int coroutine_fn copy_sectors(BlockDriverState *bs,
        goto out;
    }

-    if (bs->encrypted) {
-        Error *err = NULL;
-        assert(s->cipher);
-        if (qcow2_encrypt_sectors(s, start_sect + n_start,
-                                  iov.iov_base, iov.iov_base, n,
-                                  true, &err) < 0) {
-            ret = -EIO;
-            error_free(err);
-            goto out;
-        }
+    if (s->crypt_method) {
+        qcow2_encrypt_sectors(s, start_sect + n_start,
+                        iov.iov_base, iov.iov_base, n, 1,
+                        &s->aes_encrypt_key);
    }

    ret = qcow2_pre_write_overlap_check(bs, 0,
@@ -445,8 +416,7 @@ static int coroutine_fn copy_sectors(BlockDriverState *bs,
    }

    BLKDBG_EVENT(bs->file, BLKDBG_COW_WRITE);
-    ret = bdrv_co_writev(bs->file->bs, (cluster_offset >> 9) + n_start, n,
-                         &qiov);
+    ret = bdrv_co_writev(bs->file, (cluster_offset >> 9) + n_start, n, &qiov);
    if (ret < 0) {
        goto out;
    }
@@ -475,7 +445,7 @@ out:
 int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
    int *num, uint64_t *cluster_offset)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    unsigned int l2_index;
    uint64_t l1_index, l2_offset, *l2_table;
    int l1_bits, c;
@@ -501,11 +471,10 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
    if (nb_needed > nb_available) {
        nb_needed = nb_available;
    }
-    assert(nb_needed <= INT_MAX);

    *cluster_offset = 0;

-    /* seek to the l2 offset in the l1 table */
+    /* seek the the l2 offset in the l1 table */

    l1_index = offset >> l1_bits;
    if (l1_index >= s->l1_size) {
@@ -537,8 +506,6 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,

    l2_index = (offset >> s->cluster_bits) & (s->l2_size - 1);
    *cluster_offset = be64_to_cpu(l2_table[l2_index]);
-
-    /* nb_needed <= INT_MAX, thus nb_clusters <= INT_MAX, too */
    nb_clusters = size_to_clusters(s, nb_needed << 9);

    ret = qcow2_get_cluster_type(*cluster_offset);
@@ -556,14 +523,13 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
            ret = -EIO;
            goto fail;
        }
-        c = count_contiguous_clusters_by_type(nb_clusters, &l2_table[l2_index],
-                                              QCOW2_CLUSTER_ZERO);
+        c = count_contiguous_clusters(nb_clusters, s->cluster_size,
+                &l2_table[l2_index], QCOW_OFLAG_ZERO);
        *cluster_offset = 0;
        break;
    case QCOW2_CLUSTER_UNALLOCATED:
        /* how many empty clusters ? */
-        c = count_contiguous_clusters_by_type(nb_clusters, &l2_table[l2_index],
-                                              QCOW2_CLUSTER_UNALLOCATED);
+        c = count_contiguous_free_clusters(nb_clusters, &l2_table[l2_index]);
        *cluster_offset = 0;
        break;
    case QCOW2_CLUSTER_NORMAL:
@@ -616,13 +582,13 @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset,
                             uint64_t **new_l2_table,
                             int *new_l2_index)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    unsigned int l2_index;
    uint64_t l1_index, l2_offset;
    uint64_t *l2_table = NULL;
    int ret;

-    /* seek to the l2 offset in the l1 table */
+    /* seek the the l2 offset in the l1 table */

    l1_index = offset >> (s->l2_bits + s->cluster_bits);
    if (l1_index >= s->l1_size) {
@@ -690,7 +656,7 @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
                                               uint64_t offset,
                                               int compressed_size)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    int l2_index, ret;
    uint64_t *l2_table;
    int64_t cluster_offset;
@@ -726,16 +692,19 @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
    /* compressed clusters never have the copied flag */

    BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE_COMPRESSED);
-    qcow2_cache_entry_mark_dirty(bs, s->l2_table_cache, l2_table);
+    qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
    l2_table[l2_index] = cpu_to_be64(cluster_offset);
-    qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table);
+    ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+    if (ret < 0) {
+        return 0;
+    }

    return cluster_offset;
 }

 static int perform_cow(BlockDriverState *bs, QCowL2Meta *m, Qcow2COWRegion *r)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    int ret;

    if (r->nb_sectors == 0) {
@@ -764,7 +733,7 @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m, Qcow2COWRegion *r)

 int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    int i, j = 0, l2_index, ret;
    uint64_t *old_cluster, *l2_table;
    uint64_t cluster_offset = m->alloc_offset;
@@ -802,7 +771,7 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
    if (ret < 0) {
        goto err;
    }
-    qcow2_cache_entry_mark_dirty(bs, s->l2_table_cache, l2_table);
+    qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);

    assert(l2_index + m->nb_clusters <= s->l2_size);
    for (i = 0; i < m->nb_clusters; i++) {
@@ -820,10 +789,14 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
     }


-    qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table);
+    ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+    if (ret < 0) {
+        goto err;
+    }

    /*
     * If this was a COW, we need to decrease the refcount of the old cluster.
+     * Also flush bs->file to get the right order for L2 and refcount update.
     *
     * Don't discard clusters that reach a refcount of 0 (e.g. compressed
     * clusters), the next write will reuse them anyway.
@@ -846,7 +819,7 @@ err:
 * write, but require COW to be performed (this includes yet unallocated space,
 * which must copy from the backing file)
 */
-static int count_cow_clusters(BDRVQcow2State *s, int nb_clusters,
+static int count_cow_clusters(BDRVQcowState *s, int nb_clusters,
    uint64_t *l2_table, int l2_index)
 {
    int i;
@@ -892,7 +865,7 @@ out:
 static int handle_dependencies(BlockDriverState *bs, uint64_t guest_offset,
    uint64_t *cur_bytes, QCowL2Meta **m)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    QCowL2Meta *old_alloc;
    uint64_t bytes = *cur_bytes;

@@ -965,13 +938,13 @@ static int handle_dependencies(BlockDriverState *bs, uint64_t guest_offset,
 static int handle_copied(BlockDriverState *bs, uint64_t guest_offset,
    uint64_t *host_offset, uint64_t *bytes, QCowL2Meta **m)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    int l2_index;
    uint64_t cluster_offset;
    uint64_t *l2_table;
-    uint64_t nb_clusters;
+    unsigned int nb_clusters;
    unsigned int keep_clusters;
-    int ret;
+    int ret, pret;

    trace_qcow2_handle_copied(qemu_coroutine_self(), guest_offset, *host_offset,
                              *bytes);
@@ -988,7 +961,6 @@ static int handle_copied(BlockDriverState *bs, uint64_t guest_offset,

    l2_index = offset_to_l2_index(s, guest_offset);
    nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
-    assert(nb_clusters <= INT_MAX);

    /* Find L2 entry for the first involved cluster */
    ret = get_cluster_table(bs, guest_offset, &l2_table, &l2_index);
@@ -1039,7 +1011,10 @@ static int handle_copied(BlockDriverState *bs, uint64_t guest_offset,

    /* Cleanup */
 out:
-    qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table);
+    pret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+    if (pret < 0) {
+        return pret;
+    }

    /* Only return a host offset if we actually made progress. Otherwise we
     * would make requirements for handle_alloc() that it can't fulfill */
@@ -1071,9 +1046,9 @@ out:
 * restarted, but the whole request should not be failed.
 */
 static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset,
-                                   uint64_t *host_offset, uint64_t *nb_clusters)
+    uint64_t *host_offset, unsigned int *nb_clusters)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;

    trace_qcow2_do_alloc_clusters_offset(qemu_coroutine_self(), guest_offset,
                                         *host_offset, *nb_clusters);
@@ -1089,7 +1064,7 @@ static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset,
        *host_offset = cluster_offset;
        return 0;
    } else {
-        int64_t ret = qcow2_alloc_clusters_at(bs, *host_offset, *nb_clusters);
+        int ret = qcow2_alloc_clusters_at(bs, *host_offset, *nb_clusters);
        if (ret < 0) {
            return ret;
        }
@@ -1121,11 +1096,11 @@ static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset,
 static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset,
    uint64_t *host_offset, uint64_t *bytes, QCowL2Meta **m)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    int l2_index;
    uint64_t *l2_table;
    uint64_t entry;
-    uint64_t nb_clusters;
+    unsigned int nb_clusters;
    int ret;

    uint64_t alloc_cluster_offset;
@@ -1143,7 +1118,6 @@ static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset,

    l2_index = offset_to_l2_index(s, guest_offset);
    nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
-    assert(nb_clusters <= INT_MAX);

    /* Find L2 entry for the first involved cluster */
    ret = get_cluster_table(bs, guest_offset, &l2_table, &l2_index);
@@ -1165,7 +1139,10 @@ static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset,
     * wrong with our code. */
    assert(nb_clusters > 0);

-    qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table);
+    ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+    if (ret < 0) {
+        return ret;
+    }

    /* Allocate, if necessary at a given offset in the image file */
    alloc_cluster_offset = start_of_cluster(s, *host_offset);
@@ -1274,7 +1251,7 @@ fail:
 int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
    int *num, uint64_t *host_offset, QCowL2Meta **m)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    uint64_t start, remaining;
    uint64_t cluster_offset;
    uint64_t cur_bytes;
@@ -1408,7 +1385,7 @@ static int decompress_buffer(uint8_t *out_buf, int out_buf_size,

 int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    int ret, csize, nb_csectors, sector_offset;
    uint64_t coffset;

@@ -1418,8 +1395,7 @@ int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
        sector_offset = coffset & 511;
        csize = nb_csectors * 512 - sector_offset;
        BLKDBG_EVENT(bs->file, BLKDBG_READ_COMPRESSED);
-        ret = bdrv_read(bs->file->bs, coffset >> 9, s->cluster_data,
-                        nb_csectors);
+        ret = bdrv_read(bs->file, coffset >> 9, s->cluster_data, nb_csectors);
        if (ret < 0) {
            return ret;
        }
@@ -1438,10 +1414,9 @@ int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
 * clusters.
 */
 static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
-                             uint64_t nb_clusters, enum qcow2_discard_type type,
-                             bool full_discard)
+    unsigned int nb_clusters, enum qcow2_discard_type type, bool full_discard)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    uint64_t *l2_table;
    int l2_index;
    int ret;
@@ -1454,7 +1429,6 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,

    /* Limit nb_clusters to one L2 table */
    nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
-    assert(nb_clusters <= INT_MAX);

    for (i = 0; i < nb_clusters; i++) {
        uint64_t old_l2_entry;
@@ -1476,7 +1450,7 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
         */
        switch (qcow2_get_cluster_type(old_l2_entry)) {
            case QCOW2_CLUSTER_UNALLOCATED:
-                if (full_discard || !bs->backing) {
+                if (full_discard || !bs->backing_hd) {
                    continue;
                }
                break;
@@ -1496,7 +1470,7 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
        }

        /* First remove L2 entries */
-        qcow2_cache_entry_mark_dirty(bs, s->l2_table_cache, l2_table);
+        qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
        if (!full_discard && s->qcow_version >= 3) {
            l2_table[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO);
        } else {
@@ -1507,7 +1481,10 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
        qcow2_free_any_clusters(bs, old_l2_entry, 1, type);
    }

-    qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table);
+    ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+    if (ret < 0) {
+        return ret;
+    }

    return nb_clusters;
 }
@@ -1515,9 +1492,9 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
 int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
    int nb_sectors, enum qcow2_discard_type type, bool full_discard)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    uint64_t end_offset;
-    uint64_t nb_clusters;
+    unsigned int nb_clusters;
    int ret;

    end_offset = offset + (nb_sectors << BDRV_SECTOR_BITS);
@@ -1559,9 +1536,9 @@ fail:
 * clusters.
 */
 static int zero_single_l2(BlockDriverState *bs, uint64_t offset,
-                          uint64_t nb_clusters)
+    unsigned int nb_clusters)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    uint64_t *l2_table;
    int l2_index;
    int ret;
@@ -1574,7 +1551,6 @@ static int zero_single_l2(BlockDriverState *bs, uint64_t offset,

    /* Limit nb_clusters to one L2 table */
    nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
-    assert(nb_clusters <= INT_MAX);

    for (i = 0; i < nb_clusters; i++) {
        uint64_t old_offset;
@@ -1582,7 +1558,7 @@ static int zero_single_l2(BlockDriverState *bs, uint64_t offset,
        old_offset = be64_to_cpu(l2_table[l2_index + i]);

        /* Update L2 entries */
-        qcow2_cache_entry_mark_dirty(bs, s->l2_table_cache, l2_table);
+        qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
        if (old_offset & QCOW_OFLAG_COMPRESSED) {
            l2_table[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO);
            qcow2_free_any_clusters(bs, old_offset, 1, QCOW2_DISCARD_REQUEST);
@@ -1591,15 +1567,18 @@ static int zero_single_l2(BlockDriverState *bs, uint64_t offset,
        }
    }

-    qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table);
+    ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+    if (ret < 0) {
+        return ret;
+    }

    return nb_clusters;
 }

 int qcow2_zero_clusters(BlockDriverState *bs, uint64_t offset, int nb_sectors)
 {
-    BDRVQcow2State *s = bs->opaque;
-    uint64_t nb_clusters;
+    BDRVQcowState *s = bs->opaque;
+    unsigned int nb_clusters;
    int ret;

    /* The zero flag is only supported by version 3 and newer */
@@ -1643,7 +1622,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
                                      int64_t l1_entries,
                                      BlockDriverAmendStatusCB *status_cb)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    bool is_active_l1 = (l1_table == s->l1_table);
    uint64_t *l2_table = NULL;
    int ret;
@@ -1652,7 +1631,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
    if (!is_active_l1) {
        /* inactive L2 tables require a buffer to be stored in when loading
         * them from disk */
-        l2_table = qemu_try_blockalign(bs->file->bs, s->cluster_size);
+        l2_table = qemu_try_blockalign(bs->file, s->cluster_size);
        if (l2_table == NULL) {
            return -ENOMEM;
        }
@@ -1661,7 +1640,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
    for (i = 0; i < l1_size; i++) {
        uint64_t l2_offset = l1_table[i] & L1E_OFFSET_MASK;
        bool l2_dirty = false;
-        uint64_t l2_refcount;
+        int l2_refcount;

        if (!l2_offset) {
            /* unallocated */
@@ -1672,30 +1651,22 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
            continue;
        }

-        if (offset_into_cluster(s, l2_offset)) {
-            qcow2_signal_corruption(bs, true, -1, -1, "L2 table offset %#"
-                                    PRIx64 " unaligned (L1 index: %#x)",
-                                    l2_offset, i);
-            ret = -EIO;
-            goto fail;
-        }
-
        if (is_active_l1) {
            /* get active L2 tables from cache */
            ret = qcow2_cache_get(bs, s->l2_table_cache, l2_offset,
                    (void **)&l2_table);
        } else {
            /* load inactive L2 tables from disk */
-            ret = bdrv_read(bs->file->bs, l2_offset / BDRV_SECTOR_SIZE,
-                            (void *)l2_table, s->cluster_sectors);
+            ret = bdrv_read(bs->file, l2_offset / BDRV_SECTOR_SIZE,
+                    (void *)l2_table, s->cluster_sectors);
        }
        if (ret < 0) {
            goto fail;
        }

-        ret = qcow2_get_refcount(bs, l2_offset >> s->cluster_bits,
-                                 &l2_refcount);
-        if (ret < 0) {
+        l2_refcount = qcow2_get_refcount(bs, l2_offset >> s->cluster_bits);
+        if (l2_refcount < 0) {
+            ret = l2_refcount;
            goto fail;
        }

@@ -1710,7 +1681,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
            }

            if (!preallocated) {
-                if (!bs->backing) {
+                if (!bs->backing_hd) {
                    /* not backed; therefore we can simply deallocate the
                     * cluster */
                    l2_table[j] = 0;
@@ -1728,8 +1699,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
                    /* For shared L2 tables, set the refcount accordingly (it is
                     * already 1 and needs to be l2_refcount) */
                    ret = qcow2_update_cluster_refcount(bs,
-                            offset >> s->cluster_bits,
-                            refcount_diff(1, l2_refcount), false,
+                            offset >> s->cluster_bits, l2_refcount - 1,
                            QCOW2_DISCARD_OTHER);
                    if (ret < 0) {
                        qcow2_free_clusters(bs, offset, s->cluster_size,
@@ -1739,19 +1709,6 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
                }
            }

-            if (offset_into_cluster(s, offset)) {
-                qcow2_signal_corruption(bs, true, -1, -1, "Data cluster offset "
-                                        "%#" PRIx64 " unaligned (L2 offset: %#"
-                                        PRIx64 ", L2 index: %#x)", offset,
-                                        l2_offset, j);
-                if (!preallocated) {
-                    qcow2_free_clusters(bs, offset, s->cluster_size,
-                                        QCOW2_DISCARD_ALWAYS);
-                }
-                ret = -EIO;
-                goto fail;
-            }
-
            ret = qcow2_pre_write_overlap_check(bs, 0, offset, s->cluster_size);
            if (ret < 0) {
                if (!preallocated) {
@@ -1761,7 +1718,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
                goto fail;
            }

-            ret = bdrv_write_zeroes(bs->file->bs, offset / BDRV_SECTOR_SIZE,
+            ret = bdrv_write_zeroes(bs->file, offset / BDRV_SECTOR_SIZE,
                                    s->cluster_sectors, 0);
            if (ret < 0) {
                if (!preallocated) {
@@ -1781,10 +1738,14 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,

        if (is_active_l1) {
            if (l2_dirty) {
-                qcow2_cache_entry_mark_dirty(bs, s->l2_table_cache, l2_table);
+                qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
                qcow2_cache_depends_on_flush(s->l2_table_cache);
            }
-            qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table);
+            ret = qcow2_cache_put(bs, s->l2_table_cache, (void **)&l2_table);
+            if (ret < 0) {
+                l2_table = NULL;
+                goto fail;
+            }
        } else {
            if (l2_dirty) {
                ret = qcow2_pre_write_overlap_check(bs,
@@ -1794,8 +1755,8 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
                    goto fail;
                }

-                ret = bdrv_write(bs->file->bs, l2_offset / BDRV_SECTOR_SIZE,
-                                 (void *)l2_table, s->cluster_sectors);
+                ret = bdrv_write(bs->file, l2_offset / BDRV_SECTOR_SIZE,
+                        (void *)l2_table, s->cluster_sectors);
                if (ret < 0) {
                    goto fail;
                }
@@ -1815,7 +1776,12 @@ fail:
        if (!is_active_l1) {
            qemu_vfree(l2_table);
        } else {
-            qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table);
+            if (ret < 0) {
+                qcow2_cache_put(bs, s->l2_table_cache, (void **)&l2_table);
+            } else {
+                ret = qcow2_cache_put(bs, s->l2_table_cache,
+                        (void **)&l2_table);
+            }
        }
    }
    return ret;
@@ -1830,7 +1796,7 @@ fail:
 int qcow2_expand_zero_clusters(BlockDriverState *bs,
                               BlockDriverAmendStatusCB *status_cb)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    uint64_t *l1_table = NULL;
    int64_t l1_entries = 0, visited_l1_entries = 0;
    int ret;
@@ -1868,9 +1834,8 @@ int qcow2_expand_zero_clusters(BlockDriverState *bs,

        l1_table = g_realloc(l1_table, l1_sectors * BDRV_SECTOR_SIZE);

-        ret = bdrv_read(bs->file->bs,
-                        s->snapshots[i].l1_table_offset / BDRV_SECTOR_SIZE,
-                        (void *)l1_table, l1_sectors);
+        ret = bdrv_read(bs->file, s->snapshots[i].l1_table_offset /
+                BDRV_SECTOR_SIZE, (void *)l1_table, l1_sectors);
        if (ret < 0) {
            goto fail;
        }
@@ -25,11 +25,10 @@
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "block/qcow2.h"
-#include "qemu/error-report.h"

 void qcow2_free_snapshots(BlockDriverState *bs)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    int i;

    for(i = 0; i < s->nb_snapshots; i++) {
@@ -43,7 +42,7 @@ void qcow2_free_snapshots(BlockDriverState *bs)

 int qcow2_read_snapshots(BlockDriverState *bs)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    QCowSnapshotHeader h;
    QCowSnapshotExtraData extra;
    QCowSnapshot *sn;
@@ -64,7 +63,7 @@ int qcow2_read_snapshots(BlockDriverState *bs)
    for(i = 0; i < s->nb_snapshots; i++) {
        /* Read statically sized part of the snapshot header */
        offset = align_offset(offset, 8);
-        ret = bdrv_pread(bs->file->bs, offset, &h, sizeof(h));
+        ret = bdrv_pread(bs->file, offset, &h, sizeof(h));
        if (ret < 0) {
            goto fail;
        }
@@ -83,7 +82,7 @@ int qcow2_read_snapshots(BlockDriverState *bs)
        name_size = be16_to_cpu(h.name_size);

        /* Read extra data */
-        ret = bdrv_pread(bs->file->bs, offset, &extra,
+        ret = bdrv_pread(bs->file, offset, &extra,
                         MIN(sizeof(extra), extra_data_size));
        if (ret < 0) {
            goto fail;
@@ -102,7 +101,7 @@ int qcow2_read_snapshots(BlockDriverState *bs)

        /* Read snapshot ID */
        sn->id_str = g_malloc(id_str_size + 1);
-        ret = bdrv_pread(bs->file->bs, offset, sn->id_str, id_str_size);
+        ret = bdrv_pread(bs->file, offset, sn->id_str, id_str_size);
        if (ret < 0) {
            goto fail;
        }
@@ -111,7 +110,7 @@ int qcow2_read_snapshots(BlockDriverState *bs)

        /* Read snapshot name */
        sn->name = g_malloc(name_size + 1);
-        ret = bdrv_pread(bs->file->bs, offset, sn->name, name_size);
+        ret = bdrv_pread(bs->file, offset, sn->name, name_size);
        if (ret < 0) {
            goto fail;
        }
@@ -136,7 +135,7 @@ fail:
 /* add at the end of the file a new list of snapshots */
 static int qcow2_write_snapshots(BlockDriverState *bs)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    QCowSnapshot *sn;
    QCowSnapshotHeader h;
    QCowSnapshotExtraData extra;
@@ -214,25 +213,25 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
        h.name_size = cpu_to_be16(name_size);
        offset = align_offset(offset, 8);

-        ret = bdrv_pwrite(bs->file->bs, offset, &h, sizeof(h));
+        ret = bdrv_pwrite(bs->file, offset, &h, sizeof(h));
        if (ret < 0) {
            goto fail;
        }
        offset += sizeof(h);

-        ret = bdrv_pwrite(bs->file->bs, offset, &extra, sizeof(extra));
+        ret = bdrv_pwrite(bs->file, offset, &extra, sizeof(extra));
        if (ret < 0) {
            goto fail;
        }
        offset += sizeof(extra);

-        ret = bdrv_pwrite(bs->file->bs, offset, sn->id_str, id_str_size);
+        ret = bdrv_pwrite(bs->file, offset, sn->id_str, id_str_size);
        if (ret < 0) {
            goto fail;
        }
        offset += id_str_size;

-        ret = bdrv_pwrite(bs->file->bs, offset, sn->name, name_size);
+        ret = bdrv_pwrite(bs->file, offset, sn->name, name_size);
        if (ret < 0) {
            goto fail;
        }
@@ -254,7 +253,7 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
    header_data.nb_snapshots        = cpu_to_be32(s->nb_snapshots);
    header_data.snapshots_offset    = cpu_to_be64(snapshots_offset);

-    ret = bdrv_pwrite_sync(bs->file->bs, offsetof(QCowHeader, nb_snapshots),
+    ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, nb_snapshots),
                           &header_data, sizeof(header_data));
    if (ret < 0) {
        goto fail;
@@ -278,7 +277,7 @@ fail:
 static void find_new_snapshot_id(BlockDriverState *bs,
                                 char *id_str, int id_str_size)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    QCowSnapshot *sn;
    int i;
    unsigned long id, id_max = 0;
@@ -296,7 +295,7 @@ static int find_snapshot_by_id_and_name(BlockDriverState *bs,
                                        const char *id,
                                        const char *name)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    int i;

    if (id && name) {
@@ -338,7 +337,7 @@ static int find_snapshot_by_id_or_name(BlockDriverState *bs,
 /* if no id is provided, a new one is constructed */
 int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    QCowSnapshot *new_snapshot_list = NULL;
    QCowSnapshot *old_snapshot_list = NULL;
    QCowSnapshot sn1, *sn = &sn1;
@@ -352,8 +351,10 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)

    memset(sn, 0, sizeof(*sn));

-    /* Generate an ID */
-    find_new_snapshot_id(bs, sn_info->id_str, sizeof(sn_info->id_str));
+    /* Generate an ID if it wasn't passed */
+    if (sn_info->id_str[0] == '\0') {
+        find_new_snapshot_id(bs, sn_info->id_str, sizeof(sn_info->id_str));
+    }

    /* Check that the ID is unique */
    if (find_snapshot_by_id_and_name(bs, sn_info->id_str, NULL) >= 0) {
@@ -396,7 +397,7 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
        goto fail;
    }

-    ret = bdrv_pwrite(bs->file->bs, sn->l1_table_offset, l1_table,
+    ret = bdrv_pwrite(bs->file, sn->l1_table_offset, l1_table,
                      s->l1_size * sizeof(uint64_t));
    if (ret < 0) {
        goto fail;
@@ -461,7 +462,7 @@ fail:
 /* copy the snapshot 'snapshot_name' into the current disk image */
 int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    QCowSnapshot *sn;
    int i, snapshot_index;
    int cur_l1_bytes, sn_l1_bytes;
@@ -509,8 +510,7 @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
        goto fail;
    }

-    ret = bdrv_pread(bs->file->bs, sn->l1_table_offset,
-                     sn_l1_table, sn_l1_bytes);
+    ret = bdrv_pread(bs->file, sn->l1_table_offset, sn_l1_table, sn_l1_bytes);
    if (ret < 0) {
        goto fail;
    }
@@ -527,7 +527,7 @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
        goto fail;
    }

-    ret = bdrv_pwrite_sync(bs->file->bs, s->l1_table_offset, sn_l1_table,
+    ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset, sn_l1_table,
                           cur_l1_bytes);
    if (ret < 0) {
        goto fail;
@@ -588,7 +588,7 @@ int qcow2_snapshot_delete(BlockDriverState *bs,
                          const char *name,
                          Error **errp)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    QCowSnapshot sn;
    int snapshot_index, ret;

@@ -651,7 +651,7 @@ int qcow2_snapshot_delete(BlockDriverState *bs,

 int qcow2_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
 {
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    QEMUSnapshotInfo *sn_tab, *sn_info;
    QCowSnapshot *sn;
    int i;
@@ -684,7 +684,7 @@ int qcow2_snapshot_load_tmp(BlockDriverState *bs,
                            Error **errp)
 {
    int i, snapshot_index;
-    BDRVQcow2State *s = bs->opaque;
+    BDRVQcowState *s = bs->opaque;
    QCowSnapshot *sn;
    uint64_t *new_l1_table;
    int new_l1_bytes;
@@ -702,19 +702,18 @@ int qcow2_snapshot_load_tmp(BlockDriverState *bs,
    sn = &s->snapshots[snapshot_index];

    /* Allocate and read in the snapshot's L1 table */
-    if (sn->l1_size > QCOW_MAX_L1_SIZE / sizeof(uint64_t)) {
+    if (sn->l1_size > QCOW_MAX_L1_SIZE) {
        error_setg(errp, "Snapshot L1 table too large");
        return -EFBIG;
    }
    new_l1_bytes = sn->l1_size * sizeof(uint64_t);
-    new_l1_table = qemu_try_blockalign(bs->file->bs,
+    new_l1_table = qemu_try_blockalign(bs->file,
                                       align_offset(new_l1_bytes, 512));
    if (new_l1_table == NULL) {
        return -ENOMEM;
    }

-    ret = bdrv_pread(bs->file->bs, sn->l1_table_offset,
-                     new_l1_table, new_l1_bytes);
+    ret = bdrv_pread(bs->file, sn->l1_table_offset, new_l1_table, new_l1_bytes);
    if (ret < 0) {
        error_setg(errp, "Failed to read l1 table for snapshot");
        qemu_vfree(new_l1_table);
@@ -25,8 +25,8 @@
 #ifndef BLOCK_QCOW2_H
 #define BLOCK_QCOW2_H

-#include "crypto/cipher.h"
-#include "qemu/coroutine.h"
+#include "qemu/aes.h"
+#include "block/coroutine.h"

 //#define DEBUG_ALLOC
 //#define DEBUG_ALLOC2
@@ -62,14 +62,11 @@
 #define MIN_CLUSTER_BITS 9
 #define MAX_CLUSTER_BITS 21

-/* Must be at least 2 to cover COW */
-#define MIN_L2_CACHE_SIZE 2 /* clusters */
+#define MIN_L2_CACHE_SIZE 1 /* cluster */

 /* Must be at least 4 to cover all cases of refcount table growth */
 #define MIN_REFCOUNT_CACHE_SIZE 4 /* clusters */

-/* Whichever is more */
-#define DEFAULT_L2_CACHE_CLUSTERS 8 /* clusters */
 #define DEFAULT_L2_CACHE_BYTE_SIZE 1048576 /* bytes */

 /* The refblock cache needs only a fourth of the L2 cache size to cover as many
@@ -96,7 +93,6 @@
 #define QCOW2_OPT_CACHE_SIZE "cache-size"
 #define QCOW2_OPT_L2_CACHE_SIZE "l2-cache-size"
 #define QCOW2_OPT_REFCOUNT_CACHE_SIZE "refcount-cache-size"
-#define QCOW2_OPT_CACHE_CLEAN_INTERVAL "cache-clean-interval"

 typedef struct QCowHeader {
    uint32_t magic;
@@ -217,12 +213,7 @@ typedef struct Qcow2DiscardRegion {
    QTAILQ_ENTRY(Qcow2DiscardRegion) next;
 } Qcow2DiscardRegion;

-typedef uint64_t Qcow2GetRefcountFunc(const void *refcount_array,
-                                      uint64_t index);
-typedef void Qcow2SetRefcountFunc(void *refcount_array,
-                                  uint64_t index, uint64_t value);
-
-typedef struct BDRVQcow2State {
+typedef struct BDRVQcowState {
    int cluster_bits;
    int cluster_size;
    int cluster_sectors;
@@ -240,8 +231,6 @@ typedef struct BDRVQcow2State {

    Qcow2Cache* l2_table_cache;
    Qcow2Cache* refcount_block_cache;
-    QEMUTimer *cache_clean_timer;
-    unsigned cache_clean_interval;

    uint8_t *cluster_cache;
    uint8_t *cluster_data;
@@ -256,8 +245,10 @@ typedef struct BDRVQcow2State {

    CoMutex lock;

-    QCryptoCipher *cipher; /* current cipher, NULL if no key yet */
+    uint32_t crypt_method; /* current crypt method, 0 if no key yet */
    uint32_t crypt_method_header;
+    AES_KEY aes_encrypt_key;
+    AES_KEY aes_decrypt_key;
    uint64_t snapshots_offset;
    int snapshots_size;
    unsigned int nb_snapshots;
@@ -267,11 +258,6 @@ typedef struct BDRVQcow2State {
    int qcow_version;
    bool use_lazy_refcounts;
    int refcount_order;
-    int refcount_bits;
-    uint64_t refcount_max;
-
-    Qcow2GetRefcountFunc *get_refcount;
-    Qcow2SetRefcountFunc *set_refcount;

    bool discard_passthrough[QCOW2_DISCARD_MAX];

@@ -287,13 +273,20 @@ typedef struct BDRVQcow2State {
    QLIST_HEAD(, Qcow2UnknownHeaderExtension) unknown_header_ext;
    QTAILQ_HEAD (, Qcow2DiscardRegion) discards;
    bool cache_discards;
+} BDRVQcowState;

-    /* Backing file path and format as stored in the image (this is not the
-     * effective path/format, which may be the result of a runtime option
-     * override) */
-    char *image_backing_file;
-    char *image_backing_format;
-} BDRVQcow2State;
+/* XXX: use std qcow open function ? */
+typedef struct QCowCreateState {
+    int cluster_size;
+    int cluster_bits;
+    uint16_t *refcount_block;
+    uint64_t *refcount_table;
+    int64_t l1_table_offset;
+    int64_t refcount_table_offset;
+    int64_t refcount_block_offset;
+} QCowCreateState;
+
+struct QCowAIOCB;

 typedef struct Qcow2COWRegion {
    /**
@@ -403,28 +396,28 @@ typedef enum QCow2MetadataOverlap {

 #define REFT_OFFSET_MASK 0xfffffffffffffe00ULL

-static inline int64_t start_of_cluster(BDRVQcow2State *s, int64_t offset)
+static inline int64_t start_of_cluster(BDRVQcowState *s, int64_t offset)
 {
    return offset & ~(s->cluster_size - 1);
 }

-static inline int64_t offset_into_cluster(BDRVQcow2State *s, int64_t offset)
+static inline int64_t offset_into_cluster(BDRVQcowState *s, int64_t offset)
 {
    return offset & (s->cluster_size - 1);
 }

-static inline uint64_t size_to_clusters(BDRVQcow2State *s, uint64_t size)
+static inline int size_to_clusters(BDRVQcowState *s, int64_t size)
 {
    return (size + (s->cluster_size - 1)) >> s->cluster_bits;
 }

-static inline int64_t size_to_l1(BDRVQcow2State *s, int64_t size)
+static inline int64_t size_to_l1(BDRVQcowState *s, int64_t size)
 {
    int shift = s->cluster_bits + s->l2_bits;
    return (size + (1ULL << shift) - 1) >> shift;
 }

-static inline int offset_to_l2_index(BDRVQcow2State *s, int64_t offset)
+static inline int offset_to_l2_index(BDRVQcowState *s, int64_t offset)
 {
    return (offset >> s->cluster_bits) & (s->l2_size - 1);
 }
@@ -435,12 +428,12 @@ static inline int64_t align_offset(int64_t offset, int n)
    return offset;
 }

-static inline int64_t qcow2_vm_state_offset(BDRVQcow2State *s)
+static inline int64_t qcow2_vm_state_offset(BDRVQcowState *s)
 {
    return (int64_t)s->l1_vm_state_index << (s->cluster_bits + s->l2_bits);
 }

-static inline uint64_t qcow2_max_refcount_clusters(BDRVQcow2State *s)
+static inline uint64_t qcow2_max_refcount_clusters(BDRVQcowState *s)
 {
    return QCOW_MAX_REFTABLE_SIZE >> s->cluster_bits;
 }
@@ -459,7 +452,7 @@ static inline int qcow2_get_cluster_type(uint64_t l2_entry)
 }

 /* Check whether refcounts are eager or lazy */
-static inline bool qcow2_need_accurate_refcounts(BDRVQcow2State *s)
+static inline bool qcow2_need_accurate_refcounts(BDRVQcowState *s)
 {
    return !(s->incompatible_features & QCOW2_INCOMPAT_DIRTY);
 }
@@ -475,11 +468,6 @@ static inline uint64_t l2meta_cow_end(QCowL2Meta *m)
        + (m->cow_end.nb_sectors << BDRV_SECTOR_BITS);
 }

-static inline uint64_t refcount_diff(uint64_t r1, uint64_t r2)
-{
-    return r1 > r2 ? r1 - r2 : r2 - r1;
-}
-
 // FIXME Need qcow2_ prefix to global functions

 /* qcow2.c functions */
@@ -499,16 +487,14 @@ void qcow2_signal_corruption(BlockDriverState *bs, bool fatal, int64_t offset,
 int qcow2_refcount_init(BlockDriverState *bs);
 void qcow2_refcount_close(BlockDriverState *bs);

-int qcow2_get_refcount(BlockDriverState *bs, int64_t cluster_index,
-                       uint64_t *refcount);
+int qcow2_get_refcount(BlockDriverState *bs, int64_t cluster_index);

 int qcow2_update_cluster_refcount(BlockDriverState *bs, int64_t cluster_index,
-                                  uint64_t addend, bool decrease,
-                                  enum qcow2_discard_type type);
+                                  int addend, enum qcow2_discard_type type);

 int64_t qcow2_alloc_clusters(BlockDriverState *bs, uint64_t size);
-int64_t qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
-                                int64_t nb_clusters);
+int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
+    int nb_clusters);
 int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size);
 void qcow2_free_clusters(BlockDriverState *bs,
                          int64_t offset, int64_t size,
@@ -535,9 +521,10 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
 int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index);
 void qcow2_l2_cache_reset(BlockDriverState *bs);
 int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset);
-int qcow2_encrypt_sectors(BDRVQcow2State *s, int64_t sector_num,
-                          uint8_t *out_buf, const uint8_t *in_buf,
-                          int nb_sectors, bool enc, Error **errp);
+void qcow2_encrypt_sectors(BDRVQcowState *s, int64_t sector_num,
+                     uint8_t *out_buf, const uint8_t *in_buf,
+                     int nb_sectors, int enc,
+                     const AES_KEY *key);

 int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
    int *num, uint64_t *cluster_offset);
@@ -575,20 +562,18 @@ int qcow2_read_snapshots(BlockDriverState *bs);
 Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables);
 int qcow2_cache_destroy(BlockDriverState* bs, Qcow2Cache *c);

-void qcow2_cache_entry_mark_dirty(BlockDriverState *bs, Qcow2Cache *c,
-     void *table);
+void qcow2_cache_entry_mark_dirty(Qcow2Cache *c, void *table);
 int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c);
 int qcow2_cache_set_dependency(BlockDriverState *bs, Qcow2Cache *c,
    Qcow2Cache *dependency);
 void qcow2_cache_depends_on_flush(Qcow2Cache *c);

-void qcow2_cache_clean_unused(BlockDriverState *bs, Qcow2Cache *c);
 int qcow2_cache_empty(BlockDriverState *bs, Qcow2Cache *c);

 int qcow2_cache_get(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset,
    void **table);
 int qcow2_cache_get_empty(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset,
    void **table);
-void qcow2_cache_put(BlockDriverState *bs, Qcow2Cache *c, void **table);
+int qcow2_cache_put(BlockDriverState *bs, Qcow2Cache *c, void **table);

 #endif
@@ -63,7 +63,7 @@ static void qed_read_table(BDRVQEDState *s, uint64_t offset, QEDTable *table,
    read_table_cb->iov.iov_len = s->header.cluster_size * s->header.table_size,

    qemu_iovec_init_external(qiov, &read_table_cb->iov, 1);
-    bdrv_aio_readv(s->bs->file->bs, offset / BDRV_SECTOR_SIZE, qiov,
+    bdrv_aio_readv(s->bs->file, offset / BDRV_SECTOR_SIZE, qiov,
                   qiov->size / BDRV_SECTOR_SIZE,
                   qed_read_table_cb, read_table_cb);
 }
@@ -152,7 +152,7 @@ static void qed_write_table(BDRVQEDState *s, uint64_t offset, QEDTable *table,
    /* Adjust for offset into table */
    offset += start * sizeof(uint64_t);

-    bdrv_aio_writev(s->bs->file->bs, offset / BDRV_SECTOR_SIZE,
+    bdrv_aio_writev(s->bs->file, offset / BDRV_SECTOR_SIZE,
                    &write_table_cb->qiov,
                    write_table_cb->qiov.size / BDRV_SECTOR_SIZE,
                    qed_write_table_cb, write_table_cb);
@@ -82,7 +82,7 @@ int qed_write_header_sync(BDRVQEDState *s)
    int ret;

    qed_header_cpu_to_le(&s->header, &le);
-    ret = bdrv_pwrite(s->bs->file->bs, 0, &le, sizeof(le));
+    ret = bdrv_pwrite(s->bs->file, 0, &le, sizeof(le));
    if (ret != sizeof(le)) {
        return ret;
    }
@@ -119,7 +119,7 @@ static void qed_write_header_read_cb(void *opaque, int ret)
    /* Update header */
    qed_header_cpu_to_le(&s->header, (QEDHeader *)write_header_cb->buf);

-    bdrv_aio_writev(s->bs->file->bs, 0, &write_header_cb->qiov,
+    bdrv_aio_writev(s->bs->file, 0, &write_header_cb->qiov,
                    write_header_cb->nsectors, qed_write_header_cb,
                    write_header_cb);
 }
@@ -152,7 +152,7 @@ static void qed_write_header(BDRVQEDState *s, BlockCompletionFunc cb,
    write_header_cb->iov.iov_len = len;
    qemu_iovec_init_external(&write_header_cb->qiov, &write_header_cb->iov, 1);

-    bdrv_aio_readv(s->bs->file->bs, 0, &write_header_cb->qiov, nsectors,
+    bdrv_aio_readv(s->bs->file, 0, &write_header_cb->qiov, nsectors,
                   qed_write_header_read_cb, write_header_cb);
 }

@@ -354,6 +354,12 @@ static void qed_cancel_need_check_timer(BDRVQEDState *s)
    timer_del(s->need_check_timer);
 }

+static void bdrv_qed_rebind(BlockDriverState *bs)
+{
+    BDRVQEDState *s = bs->opaque;
+    s->bs = bs;
+}
+
 static void bdrv_qed_detach_aio_context(BlockDriverState *bs)
 {
    BDRVQEDState *s = bs->opaque;
@@ -375,18 +381,6 @@ static void bdrv_qed_attach_aio_context(BlockDriverState *bs,
    }
 }

-static void bdrv_qed_drain(BlockDriverState *bs)
-{
-    BDRVQEDState *s = bs->opaque;
-
-    /* Cancel timer and start doing I/O that were meant to happen as if it
-     * fired, that way we get bdrv_drain() taking care of the ongoing requests
-     * correctly. */
-    qed_cancel_need_check_timer(s);
-    qed_plug_allocating_write_reqs(s);
-    bdrv_aio_flush(s->bs, qed_clear_need_check, s);
-}
-
 static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
                         Error **errp)
 {
@@ -398,7 +392,7 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
    s->bs = bs;
    QSIMPLEQ_INIT(&s->allocating_write_reqs);

-    ret = bdrv_pread(bs->file->bs, 0, &le_header, sizeof(le_header));
+    ret = bdrv_pread(bs->file, 0, &le_header, sizeof(le_header));
    if (ret < 0) {
        return ret;
    }
@@ -413,8 +407,8 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
        char buf[64];
        snprintf(buf, sizeof(buf), "%" PRIx64,
            s->header.features & ~QED_FEATURE_MASK);
-        error_setg(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
-                   bdrv_get_device_or_node_name(bs), "QED", buf);
+        error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+            bdrv_get_device_name(bs), "QED", buf);
        return -ENOTSUP;
    }
    if (!qed_is_cluster_size_valid(s->header.cluster_size)) {
@@ -422,7 +416,7 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
    }

    /* Round down file size to the last cluster */
-    file_size = bdrv_getlength(bs->file->bs);
+    file_size = bdrv_getlength(bs->file);
    if (file_size < 0) {
        return file_size;
    }
@@ -442,14 +436,9 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,

    s->table_nelems = (s->header.cluster_size * s->header.table_size) /
                      sizeof(uint64_t);
-    s->l2_shift = ctz32(s->header.cluster_size);
+    s->l2_shift = ffs(s->header.cluster_size) - 1;
    s->l2_mask = s->table_nelems - 1;
-    s->l1_shift = s->l2_shift + ctz32(s->table_nelems);
-
-    /* Header size calculation must not overflow uint32_t */
-    if (s->header.header_size > UINT32_MAX / s->header.cluster_size) {
-        return -EINVAL;
-    }
+    s->l1_shift = s->l2_shift + ffs(s->table_nelems) - 1;

    if ((s->header.features & QED_F_BACKING_FILE)) {
        if ((uint64_t)s->header.backing_filename_offset +
@@ -458,7 +447,7 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
            return -EINVAL;
        }

-        ret = qed_read_string(bs->file->bs, s->header.backing_filename_offset,
+        ret = qed_read_string(bs->file, s->header.backing_filename_offset,
                              s->header.backing_filename_size, bs->backing_file,
                              sizeof(bs->backing_file));
        if (ret < 0) {
@@ -477,7 +466,7 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
     * feature is no longer valid.
     */
    if ((s->header.autoclear_features & ~QED_AUTOCLEAR_FEATURE_MASK) != 0 &&
-        !bdrv_is_read_only(bs->file->bs) && !(flags & BDRV_O_INCOMING)) {
+        !bdrv_is_read_only(bs->file) && !(flags & BDRV_O_INCOMING)) {
        s->header.autoclear_features &= QED_AUTOCLEAR_FEATURE_MASK;

        ret = qed_write_header_sync(s);
@@ -486,7 +475,7 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
        }

        /* From here on only known autoclear feature bits are valid */
-        bdrv_flush(bs->file->bs);
+        bdrv_flush(bs->file);
    }

    s->l1_table = qed_alloc_table(s);
@@ -504,7 +493,7 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
         * potentially inconsistent images to be opened read-only.  This can
         * aid data recovery from an otherwise inconsistent image.
         */
-        if (!bdrv_is_read_only(bs->file->bs) &&
+        if (!bdrv_is_read_only(bs->file) &&
            !(flags & BDRV_O_INCOMING)) {
            BdrvCheckResult result = {0};

@@ -547,7 +536,7 @@ static void bdrv_qed_close(BlockDriverState *bs)
    bdrv_qed_detach_aio_context(bs);

    /* Ensure writes reach stable storage */
-    bdrv_flush(bs->file->bs);
+    bdrv_flush(bs->file);

    /* Clean shutdown, no check required on next open */
    if (s->header.features & QED_F_NEED_CHECK) {
@@ -589,7 +578,7 @@ static int qed_create(const char *filename, uint32_t cluster_size,

    bs = NULL;
    ret = bdrv_open(&bs, filename, NULL, NULL,
-                    BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
+                    BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL, NULL,
                    &local_err);
    if (ret < 0) {
        error_propagate(errp, local_err);
@@ -778,8 +767,8 @@ static void qed_read_backing_file(BDRVQEDState *s, uint64_t pos,
    /* If there is a backing file, get its length.  Treat the absence of a
     * backing file like a zero length backing file.
     */
-    if (s->bs->backing) {
-        int64_t l = bdrv_getlength(s->bs->backing->bs);
+    if (s->bs->backing_hd) {
+        int64_t l = bdrv_getlength(s->bs->backing_hd);
        if (l < 0) {
            cb(opaque, l);
            return;
@@ -808,7 +797,7 @@ static void qed_read_backing_file(BDRVQEDState *s, uint64_t pos,
    qemu_iovec_concat(*backing_qiov, qiov, 0, size);

    BLKDBG_EVENT(s->bs->file, BLKDBG_READ_BACKING_AIO);
-    bdrv_aio_readv(s->bs->backing->bs, pos / BDRV_SECTOR_SIZE,
+    bdrv_aio_readv(s->bs->backing_hd, pos / BDRV_SECTOR_SIZE,
                   *backing_qiov, size / BDRV_SECTOR_SIZE, cb, opaque);
 }

@@ -845,7 +834,7 @@ static void qed_copy_from_backing_file_write(void *opaque, int ret)
    }

    BLKDBG_EVENT(s->bs->file, BLKDBG_COW_WRITE);
-    bdrv_aio_writev(s->bs->file->bs, copy_cb->offset / BDRV_SECTOR_SIZE,
+    bdrv_aio_writev(s->bs->file, copy_cb->offset / BDRV_SECTOR_SIZE,
                    &copy_cb->qiov, copy_cb->qiov.size / BDRV_SECTOR_SIZE,
                    qed_copy_from_backing_file_cb, copy_cb);
 }
@@ -1061,7 +1050,7 @@ static void qed_aio_write_flush_before_l2_update(void *opaque, int ret)
    QEDAIOCB *acb = opaque;
    BDRVQEDState *s = acb_to_s(acb);

-    if (!bdrv_aio_flush(s->bs->file->bs, qed_aio_write_l2_update_cb, opaque)) {
+    if (!bdrv_aio_flush(s->bs->file, qed_aio_write_l2_update_cb, opaque)) {
        qed_aio_complete(acb, -EIO);
    }
 }
@@ -1087,7 +1076,7 @@ static void qed_aio_write_main(void *opaque, int ret)
    if (acb->find_cluster_ret == QED_CLUSTER_FOUND) {
        next_fn = qed_aio_next_io;
    } else {
-        if (s->bs->backing) {
+        if (s->bs->backing_hd) {
            next_fn = qed_aio_write_flush_before_l2_update;
        } else {
            next_fn = qed_aio_write_l2_update_cb;
@@ -1095,7 +1084,7 @@ static void qed_aio_write_main(void *opaque, int ret)
    }

    BLKDBG_EVENT(s->bs->file, BLKDBG_WRITE_AIO);
-    bdrv_aio_writev(s->bs->file->bs, offset / BDRV_SECTOR_SIZE,
+    bdrv_aio_writev(s->bs->file, offset / BDRV_SECTOR_SIZE,
                    &acb->cur_qiov, acb->cur_qiov.size / BDRV_SECTOR_SIZE,
                    next_fn, acb);
 }
@@ -1145,7 +1134,7 @@ static void qed_aio_write_prefill(void *opaque, int ret)
 static bool qed_should_set_need_check(BDRVQEDState *s)
 {
    /* The flush before L2 update path ensures consistency */
-    if (s->bs->backing) {
+    if (s->bs->backing_hd) {
        return false;
    }

@@ -1327,7 +1316,7 @@ static void qed_aio_read_data(void *opaque, int ret,
    }

    BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
-    bdrv_aio_readv(bs->file->bs, offset / BDRV_SECTOR_SIZE,
+    bdrv_aio_readv(bs->file, offset / BDRV_SECTOR_SIZE,
                   &acb->cur_qiov, acb->cur_qiov.size / BDRV_SECTOR_SIZE,
                   qed_aio_next_io, acb);
    return;
@@ -1449,7 +1438,7 @@ static int coroutine_fn bdrv_qed_co_write_zeroes(BlockDriverState *bs,
    struct iovec iov;

    /* Refuse if there are untouched backing file sectors */
-    if (bs->backing) {
+    if (bs->backing_hd) {
        if (qed_offset_into_cluster(s, sector_num * BDRV_SECTOR_SIZE) != 0) {
            return -ENOTSUP;
        }
@@ -1586,7 +1575,7 @@ static int bdrv_qed_change_backing_file(BlockDriverState *bs,
    }

    /* Write new header */
-    ret = bdrv_pwrite_sync(bs->file->bs, 0, buffer, buffer_len);
+    ret = bdrv_pwrite_sync(bs->file, 0, buffer, buffer_len);
    g_free(buffer);
    if (ret == 0) {
        memcpy(&s->header, &new_header, sizeof(new_header));
@@ -1602,7 +1591,7 @@ static void bdrv_qed_invalidate_cache(BlockDriverState *bs, Error **errp)

    bdrv_qed_close(bs);

-    bdrv_invalidate_cache(bs->file->bs, &local_err);
+    bdrv_invalidate_cache(bs->file, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        return;
@@ -1670,6 +1659,7 @@ static BlockDriver bdrv_qed = {
    .supports_backing         = true,

    .bdrv_probe               = bdrv_qed_probe,
+    .bdrv_rebind              = bdrv_qed_rebind,
    .bdrv_open                = bdrv_qed_open,
    .bdrv_close               = bdrv_qed_close,
    .bdrv_reopen_prepare      = bdrv_qed_reopen_prepare,
@@ -1688,7 +1678,6 @@ static BlockDriver bdrv_qed = {
    .bdrv_check               = bdrv_qed_check,
    .bdrv_detach_aio_context  = bdrv_qed_detach_aio_context,
    .bdrv_attach_aio_context  = bdrv_qed_attach_aio_context,
-    .bdrv_drain               = bdrv_qed_drain,
 };

 static void bdrv_qed_init(void)
@@ -133,6 +133,7 @@ typedef struct QEDAIOCB {
    int bh_ret;                     /* final return status for completion bh */
    QSIMPLEQ_ENTRY(QEDAIOCB) next;  /* next request */
    int flags;                      /* QED_AIOCB_* bits ORed together */
+    bool *finished;                 /* signal for cancel completion */
    uint64_t end_pos;               /* request end on block device, in bytes */

    /* User scatter-gather list */
@@ -13,16 +13,16 @@
 * 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/qbool.h"
 #include "qapi/qmp/qdict.h"
-#include "qapi/qmp/qerror.h"
 #include "qapi/qmp/qint.h"
 #include "qapi/qmp/qjson.h"
 #include "qapi/qmp/qlist.h"
 #include "qapi/qmp/qstring.h"
 #include "qapi-event.h"
-#include "crypto/hash.h"

 #define HASH_LENGTH 32

@@ -33,7 +33,7 @@

 /* This union holds a vote hash value */
 typedef union QuorumVoteValue {
-    uint8_t h[HASH_LENGTH];    /* SHA-256 hash */
+    char h[HASH_LENGTH];       /* SHA-256 hash */
    int64_t l;                 /* simpler 64 bits hash */
 } QuorumVoteValue;

@@ -64,7 +64,7 @@ typedef struct QuorumVotes {

 /* the following structure holds the state of one quorum instance */
 typedef struct BDRVQuorumState {
-    BdrvChild **children;  /* children BlockDriverStates */
+    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.
@@ -226,7 +226,10 @@ static void quorum_report_bad(QuorumAIOCB *acb, char *node_name, int ret)

 static void quorum_report_failure(QuorumAIOCB *acb)
 {
-    const char *reference = bdrv_get_device_or_node_name(acb->common.bs);
+    const char *reference = bdrv_get_device_name(acb->common.bs)[0] ?
+                            bdrv_get_device_name(acb->common.bs) :
+                            acb->common.bs->node_name;
+
    qapi_event_send_quorum_failure(reference, acb->sector_num,
                                   acb->nb_sectors, &error_abort);
 }
@@ -336,7 +339,7 @@ static void quorum_report_bad_versions(BDRVQuorumState *s,
            continue;
        }
        QLIST_FOREACH(item, &version->items, next) {
-            quorum_report_bad(acb, s->children[item->index]->bs->node_name, 0);
+            quorum_report_bad(acb, s->bs[item->index]->node_name, 0);
        }
    }
 }
@@ -369,9 +372,8 @@ static bool quorum_rewrite_bad_versions(BDRVQuorumState *s, QuorumAIOCB *acb,
            continue;
        }
        QLIST_FOREACH(item, &version->items, next) {
-            bdrv_aio_writev(s->children[item->index]->bs, acb->sector_num,
-                            acb->qiov, acb->nb_sectors, quorum_rewrite_aio_cb,
-                            acb);
+            bdrv_aio_writev(s->bs[item->index], acb->sector_num, acb->qiov,
+                            acb->nb_sectors, quorum_rewrite_aio_cb, acb);
        }
    }

@@ -428,21 +430,25 @@ static void quorum_free_vote_list(QuorumVotes *votes)

 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;
-    size_t len = sizeof(hash->h);
-    uint8_t *data = hash->h;

-    /* XXX - would be nice if we could pass in the Error **
-     * and propagate that back, but this quorum code is
-     * restricted to just errno values currently */
-    if (qcrypto_hash_bytesv(QCRYPTO_HASH_ALG_SHA256,
-                            qiov->iov, qiov->niov,
-                            &data, &len,
-                            NULL) < 0) {
-        return -EINVAL;
+    ret = gnutls_hash_init(&dig, GNUTLS_DIG_SHA256);
+
+    if (ret < 0) {
+        return ret;
    }

-    return 0;
+    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)
@@ -640,13 +646,13 @@ static BlockAIOCB *read_quorum_children(QuorumAIOCB *acb)
    int i;

    for (i = 0; i < s->num_children; i++) {
-        acb->qcrs[i].buf = qemu_blockalign(s->children[i]->bs, acb->qiov->size);
+        acb->qcrs[i].buf = qemu_blockalign(s->bs[i], acb->qiov->size);
        qemu_iovec_init(&acb->qcrs[i].qiov, acb->qiov->niov);
        qemu_iovec_clone(&acb->qcrs[i].qiov, acb->qiov, acb->qcrs[i].buf);
    }

    for (i = 0; i < s->num_children; i++) {
-        bdrv_aio_readv(s->children[i]->bs, acb->sector_num, &acb->qcrs[i].qiov,
+        bdrv_aio_readv(s->bs[i], acb->sector_num, &acb->qcrs[i].qiov,
                       acb->nb_sectors, quorum_aio_cb, &acb->qcrs[i]);
    }

@@ -657,12 +663,12 @@ static BlockAIOCB *read_fifo_child(QuorumAIOCB *acb)
 {
    BDRVQuorumState *s = acb->common.bs->opaque;

-    acb->qcrs[acb->child_iter].buf =
-        qemu_blockalign(s->children[acb->child_iter]->bs, acb->qiov->size);
+    acb->qcrs[acb->child_iter].buf = qemu_blockalign(s->bs[acb->child_iter],
+                                                     acb->qiov->size);
    qemu_iovec_init(&acb->qcrs[acb->child_iter].qiov, acb->qiov->niov);
    qemu_iovec_clone(&acb->qcrs[acb->child_iter].qiov, acb->qiov,
                     acb->qcrs[acb->child_iter].buf);
-    bdrv_aio_readv(s->children[acb->child_iter]->bs, acb->sector_num,
+    bdrv_aio_readv(s->bs[acb->child_iter], acb->sector_num,
                   &acb->qcrs[acb->child_iter].qiov, acb->nb_sectors,
                   quorum_aio_cb, &acb->qcrs[acb->child_iter]);

@@ -703,8 +709,8 @@ static BlockAIOCB *quorum_aio_writev(BlockDriverState *bs,
    int i;

    for (i = 0; i < s->num_children; i++) {
-        acb->qcrs[i].aiocb = bdrv_aio_writev(s->children[i]->bs, sector_num,
-                                             qiov, nb_sectors, &quorum_aio_cb,
+        acb->qcrs[i].aiocb = bdrv_aio_writev(s->bs[i], sector_num, qiov,
+                                             nb_sectors, &quorum_aio_cb,
                                             &acb->qcrs[i]);
    }

@@ -718,12 +724,12 @@ static int64_t quorum_getlength(BlockDriverState *bs)
    int i;

    /* check that all file have the same length */
-    result = bdrv_getlength(s->children[0]->bs);
+    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->children[i]->bs);
+        int64_t value = bdrv_getlength(s->bs[i]);
        if (value < 0) {
            return value;
        }
@@ -742,7 +748,7 @@ static void quorum_invalidate_cache(BlockDriverState *bs, Error **errp)
    int i;

    for (i = 0; i < s->num_children; i++) {
-        bdrv_invalidate_cache(s->children[i]->bs, &local_err);
+        bdrv_invalidate_cache(s->bs[i], &local_err);
        if (local_err) {
            error_propagate(errp, local_err);
            return;
@@ -763,7 +769,7 @@ static coroutine_fn int quorum_co_flush(BlockDriverState *bs)
    error_votes.compare = quorum_64bits_compare;

    for (i = 0; i < s->num_children; i++) {
-        result = bdrv_co_flush(s->children[i]->bs);
+        result = bdrv_co_flush(s->bs[i]);
        result_value.l = result;
        quorum_count_vote(&error_votes, &result_value, i);
    }
@@ -783,7 +789,7 @@ static bool quorum_recurse_is_first_non_filter(BlockDriverState *bs,
    int i;

    for (i = 0; i < s->num_children; i++) {
-        bool perm = bdrv_recurse_is_first_non_filter(s->children[i]->bs,
+        bool perm = bdrv_recurse_is_first_non_filter(s->bs[i],
                                                     candidate);
        if (perm) {
            return true;
@@ -797,8 +803,8 @@ static int quorum_valid_threshold(int threshold, int num_children, Error **errp)
 {

    if (threshold < 1) {
-        error_setg(errp, QERR_INVALID_PARAMETER_VALUE,
-                   "vote-threshold", "value >= 1");
+        error_set(errp, QERR_INVALID_PARAMETER_VALUE,
+                  "vote-threshold", "value >= 1");
        return -ERANGE;
    }

@@ -863,18 +869,25 @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
    Error *local_err = NULL;
    QemuOpts *opts = NULL;
    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);

-    /* count how many different children are present */
-    s->num_children = qdict_array_entries(options, "children.");
-    if (s->num_children < 0) {
-        error_setg(&local_err, "Option children is not a valid array");
+    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");
@@ -890,12 +903,6 @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
    }

    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;
-    }
-
    ret = parse_read_pattern(qemu_opt_get(opts, QUORUM_OPT_READ_PATTERN));
    if (ret < 0) {
        error_setg(&local_err, "Please set read-pattern as fifo or quorum");
@@ -904,6 +911,12 @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
    s->read_pattern = ret;

    if (s->read_pattern == QUORUM_READ_PATTERN_QUORUM) {
+        /* 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) {
@@ -923,22 +936,41 @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
        }
    }

-    /* allocate the children array */
-    s->children = g_new0(BdrvChild *, s->num_children);
+    /* allocate the children BlockDriverState array */
+    s->bs = g_new0(BlockDriverState *, s->num_children);
    opened = g_new0(bool, s->num_children);

-    for (i = 0; i < s->num_children; i++) {
-        char indexstr[32];
-        ret = snprintf(indexstr, 32, "children.%d", i);
-        assert(ret < 32);
+    for (i = 0, lentry = qlist_first(list); lentry;
+         lentry = qlist_next(lentry), i++) {
+        QDict *d;
+        QString *string;

-        s->children[i] = bdrv_open_child(NULL, options, indexstr, bs,
-                                         &child_format, false, &local_err);
-        if (local_err) {
-            ret = -EINVAL;
-            goto close_exit;
+        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;
    }

@@ -951,9 +983,9 @@ close_exit:
        if (!opened[i]) {
            continue;
        }
-        bdrv_unref_child(bs, s->children[i]);
+        bdrv_unref(s->bs[i]);
    }
-    g_free(s->children);
+    g_free(s->bs);
    g_free(opened);
 exit:
    qemu_opts_del(opts);
@@ -961,6 +993,8 @@ exit:
    if (local_err) {
        error_propagate(errp, local_err);
    }
+    QDECREF(list);
+    QDECREF(sub);
    return ret;
 }

@@ -970,10 +1004,10 @@ static void quorum_close(BlockDriverState *bs)
    int i;

    for (i = 0; i < s->num_children; i++) {
-        bdrv_unref_child(bs, s->children[i]);
+        bdrv_unref(s->bs[i]);
    }

-    g_free(s->children);
+    g_free(s->bs);
 }

 static void quorum_detach_aio_context(BlockDriverState *bs)
@@ -982,7 +1016,7 @@ static void quorum_detach_aio_context(BlockDriverState *bs)
    int i;

    for (i = 0; i < s->num_children; i++) {
-        bdrv_detach_aio_context(s->children[i]->bs);
+        bdrv_detach_aio_context(s->bs[i]);
    }
 }

@@ -993,7 +1027,7 @@ static void quorum_attach_aio_context(BlockDriverState *bs,
    int i;

    for (i = 0; i < s->num_children; i++) {
-        bdrv_attach_aio_context(s->children[i]->bs, new_context);
+        bdrv_attach_aio_context(s->bs[i], new_context);
    }
 }

@@ -1005,17 +1039,16 @@ static void quorum_refresh_filename(BlockDriverState *bs)
    int i;

    for (i = 0; i < s->num_children; i++) {
-        bdrv_refresh_filename(s->children[i]->bs);
-        if (!s->children[i]->bs->full_open_options) {
+        bdrv_refresh_filename(s->bs[i]);
+        if (!s->bs[i]->full_open_options) {
            return;
        }
    }

    children = qlist_new();
    for (i = 0; i < s->num_children; i++) {
-        QINCREF(s->children[i]->bs->full_open_options);
-        qlist_append_obj(children,
-                         QOBJECT(s->children[i]->bs->full_open_options));
+        QINCREF(s->bs[i]->full_open_options);
+        qlist_append_obj(children, QOBJECT(s->bs[i]->full_open_options));
    }

    opts = qdict_new();
@@ -1023,9 +1056,9 @@ static void quorum_refresh_filename(BlockDriverState *bs)
    qdict_put_obj(opts, QUORUM_OPT_VOTE_THRESHOLD,
                  QOBJECT(qint_from_int(s->threshold)));
    qdict_put_obj(opts, QUORUM_OPT_BLKVERIFY,
-                  QOBJECT(qbool_from_bool(s->is_blkverify)));
+                  QOBJECT(qbool_from_int(s->is_blkverify)));
    qdict_put_obj(opts, QUORUM_OPT_REWRITE,
-                  QOBJECT(qbool_from_bool(s->rewrite_corrupted)));
+                  QOBJECT(qbool_from_int(s->rewrite_corrupted)));
    qdict_put_obj(opts, "children", QOBJECT(children));

    bs->full_open_options = opts;
@@ -1058,10 +1091,6 @@ static BlockDriver bdrv_quorum = {

 static void bdrv_quorum_init(void)
 {
-    if (!qcrypto_hash_supports(QCRYPTO_HASH_ALG_SHA256)) {
-        /* SHA256 hash support is required for quorum device */
-        return;
-    }
    bdrv_register(&bdrv_quorum);
 }

@@ -41,7 +41,7 @@ BlockAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
 void laio_detach_aio_context(void *s, AioContext *old_context);
 void laio_attach_aio_context(void *s, AioContext *new_context);
 void laio_io_plug(BlockDriverState *bs, void *aio_ctx);
-void laio_io_unplug(BlockDriverState *bs, void *aio_ctx, bool unplug);
+int laio_io_unplug(BlockDriverState *bs, void *aio_ctx, bool unplug);
 #endif

 #ifdef _WIN32
@@ -29,7 +29,6 @@
 #include "trace.h"
 #include "block/thread-pool.h"
 #include "qemu/iov.h"
-#include "qapi/qmp/qstring.h"
 #include <windows.h>
 #include <winioctl.h>

@@ -102,7 +101,7 @@ static int aio_worker(void *arg)
    switch (aiocb->aio_type & QEMU_AIO_TYPE_MASK) {
    case QEMU_AIO_READ:
        count = handle_aiocb_rw(aiocb);
-        if (count < aiocb->aio_nbytes) {
+        if (count < aiocb->aio_nbytes && aiocb->bs->growable) {
            /* A short read means that we have reached EOF. Pad the buffer
             * with zeros for bytes after EOF. */
            iov_memset(aiocb->aio_iov, aiocb->aio_niov, count,
@@ -119,9 +118,9 @@ static int aio_worker(void *arg)
    case QEMU_AIO_WRITE:
        count = handle_aiocb_rw(aiocb);
        if (count == aiocb->aio_nbytes) {
-            ret = 0;
+            count = 0;
        } else {
-            ret = -EINVAL;
+            count = -EINVAL;
        }
        break;
    case QEMU_AIO_FLUSH:
@@ -135,7 +134,7 @@ static int aio_worker(void *arg)
        break;
    }

-    g_free(aiocb);
+    g_slice_free(RawWin32AIOData, aiocb);
    return ret;
 }

@@ -143,7 +142,7 @@ static BlockAIOCB *paio_submit(BlockDriverState *bs, HANDLE hfile,
        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
        BlockCompletionFunc *cb, void *opaque, int type)
 {
-    RawWin32AIOData *acb = g_new(RawWin32AIOData, 1);
+    RawWin32AIOData *acb = g_slice_new(RawWin32AIOData);
    ThreadPool *pool;

    acb->bs = bs;
@@ -52,64 +52,14 @@ static int coroutine_fn raw_co_readv(BlockDriverState *bs, int64_t sector_num,
                                     int nb_sectors, QEMUIOVector *qiov)
 {
    BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
-    return bdrv_co_readv(bs->file->bs, sector_num, nb_sectors, qiov);
+    return bdrv_co_readv(bs->file, sector_num, nb_sectors, qiov);
 }

 static int coroutine_fn raw_co_writev(BlockDriverState *bs, int64_t sector_num,
                                      int nb_sectors, QEMUIOVector *qiov)
 {
-    void *buf = NULL;
-    BlockDriver *drv;
-    QEMUIOVector local_qiov;
-    int ret;
-
-    if (bs->probed && sector_num == 0) {
-        /* As long as these conditions are true, we can't get partial writes to
-         * the probe buffer and can just directly check the request. */
-        QEMU_BUILD_BUG_ON(BLOCK_PROBE_BUF_SIZE != 512);
-        QEMU_BUILD_BUG_ON(BDRV_SECTOR_SIZE != 512);
-
-        if (nb_sectors == 0) {
-            /* qemu_iovec_to_buf() would fail, but we want to return success
-             * instead of -EINVAL in this case. */
-            return 0;
-        }
-
-        buf = qemu_try_blockalign(bs->file->bs, 512);
-        if (!buf) {
-            ret = -ENOMEM;
-            goto fail;
-        }
-
-        ret = qemu_iovec_to_buf(qiov, 0, buf, 512);
-        if (ret != 512) {
-            ret = -EINVAL;
-            goto fail;
-        }
-
-        drv = bdrv_probe_all(buf, 512, NULL);
-        if (drv != bs->drv) {
-            ret = -EPERM;
-            goto fail;
-        }
-
-        /* Use the checked buffer, a malicious guest might be overwriting its
-         * original buffer in the background. */
-        qemu_iovec_init(&local_qiov, qiov->niov + 1);
-        qemu_iovec_add(&local_qiov, buf, 512);
-        qemu_iovec_concat(&local_qiov, qiov, 512, qiov->size - 512);
-        qiov = &local_qiov;
-    }
-
    BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
-    ret = bdrv_co_writev(bs->file->bs, sector_num, nb_sectors, qiov);
-
-fail:
-    if (qiov == &local_qiov) {
-        qemu_iovec_destroy(&local_qiov);
-    }
-    qemu_vfree(buf);
-    return ret;
+    return bdrv_co_writev(bs->file, sector_num, nb_sectors, qiov);
 }

 static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs,
@@ -125,48 +75,58 @@ static int coroutine_fn raw_co_write_zeroes(BlockDriverState *bs,
                                            int64_t sector_num, int nb_sectors,
                                            BdrvRequestFlags flags)
 {
-    return bdrv_co_write_zeroes(bs->file->bs, sector_num, nb_sectors, flags);
+    return bdrv_co_write_zeroes(bs->file, sector_num, nb_sectors, flags);
 }

 static int coroutine_fn raw_co_discard(BlockDriverState *bs,
                                       int64_t sector_num, int nb_sectors)
 {
-    return bdrv_co_discard(bs->file->bs, sector_num, nb_sectors);
+    return bdrv_co_discard(bs->file, sector_num, nb_sectors);
 }

 static int64_t raw_getlength(BlockDriverState *bs)
 {
-    return bdrv_getlength(bs->file->bs);
+    return bdrv_getlength(bs->file);
 }

 static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
 {
-    return bdrv_get_info(bs->file->bs, bdi);
+    return bdrv_get_info(bs->file, bdi);
 }

 static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
 {
-    bs->bl = bs->file->bs->bl;
+    bs->bl = bs->file->bl;
 }

 static int raw_truncate(BlockDriverState *bs, int64_t offset)
 {
-    return bdrv_truncate(bs->file->bs, offset);
+    return bdrv_truncate(bs->file, offset);
+}
+
+static int raw_is_inserted(BlockDriverState *bs)
+{
+    return bdrv_is_inserted(bs->file);
 }

 static int raw_media_changed(BlockDriverState *bs)
 {
-    return bdrv_media_changed(bs->file->bs);
+    return bdrv_media_changed(bs->file);
 }

 static void raw_eject(BlockDriverState *bs, bool eject_flag)
 {
-    bdrv_eject(bs->file->bs, eject_flag);
+    bdrv_eject(bs->file, eject_flag);
 }

 static void raw_lock_medium(BlockDriverState *bs, bool locked)
 {
-    bdrv_lock_medium(bs->file->bs, locked);
+    bdrv_lock_medium(bs->file, locked);
+}
+
+static int raw_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
+{
+    return bdrv_ioctl(bs->file, req, buf);
 }

 static BlockAIOCB *raw_aio_ioctl(BlockDriverState *bs,
@@ -174,12 +134,12 @@ static BlockAIOCB *raw_aio_ioctl(BlockDriverState *bs,
                                 BlockCompletionFunc *cb,
                                 void *opaque)
 {
-    return bdrv_aio_ioctl(bs->file->bs, req, buf, cb, opaque);
+    return bdrv_aio_ioctl(bs->file, req, buf, cb, opaque);
 }

 static int raw_has_zero_init(BlockDriverState *bs)
 {
-    return bdrv_has_zero_init(bs->file->bs);
+    return bdrv_has_zero_init(bs->file);
 }

 static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
@@ -197,19 +157,7 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
 static int raw_open(BlockDriverState *bs, QDict *options, int flags,
                    Error **errp)
 {
-    bs->sg = bs->file->bs->sg;
-
-    if (bs->probed && !bdrv_is_read_only(bs)) {
-        fprintf(stderr,
-                "WARNING: Image format was not specified for '%s' and probing "
-                "guessed raw.\n"
-                "         Automatically detecting the format is dangerous for "
-                "raw images, write operations on block 0 will be restricted.\n"
-                "         Specify the 'raw' format explicitly to remove the "
-                "restrictions.\n",
-                bs->file->bs->filename);
-    }
-
+    bs->sg = bs->file->sg;
    return 0;
 }

@@ -225,16 +173,6 @@ static int raw_probe(const uint8_t *buf, int buf_size, const char *filename)
    return 1;
 }

-static int raw_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz)
-{
-    return bdrv_probe_blocksizes(bs->file->bs, bsz);
-}
-
-static int raw_probe_geometry(BlockDriverState *bs, HDGeometry *geo)
-{
-    return bdrv_probe_geometry(bs->file->bs, geo);
-}
-
 BlockDriver bdrv_raw = {
    .format_name          = "raw",
    .bdrv_probe           = &raw_probe,
@@ -252,11 +190,11 @@ BlockDriver bdrv_raw = {
    .has_variable_length  = true,
    .bdrv_get_info        = &raw_get_info,
    .bdrv_refresh_limits  = &raw_refresh_limits,
-    .bdrv_probe_blocksizes = &raw_probe_blocksizes,
-    .bdrv_probe_geometry  = &raw_probe_geometry,
+    .bdrv_is_inserted     = &raw_is_inserted,
    .bdrv_media_changed   = &raw_media_changed,
    .bdrv_eject           = &raw_eject,
    .bdrv_lock_medium     = &raw_lock_medium,
+    .bdrv_ioctl           = &raw_ioctl,
    .bdrv_aio_ioctl       = &raw_aio_ioctl,
    .create_opts          = &raw_create_opts,
    .bdrv_has_zero_init   = &raw_has_zero_init
@@ -74,18 +74,25 @@ typedef struct RBDAIOCB {
    QEMUIOVector *qiov;
    char *bounce;
    RBDAIOCmd cmd;
+    int64_t sector_num;
    int error;
    struct BDRVRBDState *s;
+    int status;
 } RBDAIOCB;

 typedef struct RADOSCB {
+    int rcbid;
    RBDAIOCB *acb;
    struct BDRVRBDState *s;
+    int done;
    int64_t size;
    char *buf;
    int64_t ret;
 } RADOSCB;

+#define RBD_FD_READ 0
+#define RBD_FD_WRITE 1
+
 typedef struct BDRVRBDState {
    rados_t cluster;
    rados_ioctx_t io_ctx;
@@ -228,9 +235,7 @@ static char *qemu_rbd_parse_clientname(const char *conf, char *clientname)
    return NULL;
 }

-static int qemu_rbd_set_conf(rados_t cluster, const char *conf,
-                             bool only_read_conf_file,
-                             Error **errp)
+static int qemu_rbd_set_conf(rados_t cluster, const char *conf, Error **errp)
 {
    char *p, *buf;
    char name[RBD_MAX_CONF_NAME_SIZE];
@@ -262,18 +267,14 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf,
        qemu_rbd_unescape(value);

        if (strcmp(name, "conf") == 0) {
-            /* read the conf file alone, so it doesn't override more
-               specific settings for a particular device */
-            if (only_read_conf_file) {
-                ret = rados_conf_read_file(cluster, value);
-                if (ret < 0) {
-                    error_setg(errp, "error reading conf file %s", value);
-                    break;
-                }
+            ret = rados_conf_read_file(cluster, value);
+            if (ret < 0) {
+                error_setg(errp, "error reading conf file %s", value);
+                break;
            }
        } else if (strcmp(name, "id") == 0) {
            /* ignore, this is parsed by qemu_rbd_parse_clientname() */
-        } else if (!only_read_conf_file) {
+        } else {
            ret = rados_conf_set(cluster, name, value);
            if (ret < 0) {
                error_setg(errp, "invalid conf option %s", name);
@@ -324,7 +325,7 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
            error_setg(errp, "obj size too small");
            return -EINVAL;
        }
-        obj_order = ctz32(objsize);
+        obj_order = ffs(objsize) - 1;
    }

    clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
@@ -336,15 +337,10 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
    if (strstr(conf, "conf=") == NULL) {
        /* try default location, but ignore failure */
        rados_conf_read_file(cluster, NULL);
-    } else if (conf[0] != '\0' &&
-               qemu_rbd_set_conf(cluster, conf, true, &local_err) < 0) {
-        rados_shutdown(cluster);
-        error_propagate(errp, local_err);
-        return -EIO;
    }

    if (conf[0] != '\0' &&
-        qemu_rbd_set_conf(cluster, conf, false, &local_err) < 0) {
+        qemu_rbd_set_conf(cluster, conf, &local_err) < 0) {
        rados_shutdown(cluster);
        error_propagate(errp, local_err);
        return -EIO;
@@ -409,6 +405,7 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
    }
    qemu_vfree(acb->bounce);
    acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
+    acb->status = 0;

    qemu_aio_unref(acb);
 }
@@ -462,7 +459,7 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
    clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
    r = rados_create(&s->cluster, clientname);
    if (r < 0) {
-        error_setg(errp, "error initializing");
+        error_setg(&local_err, "error initializing");
        goto failed_opts;
    }

@@ -471,23 +468,6 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
        s->snap = g_strdup(snap_buf);
    }

-    if (strstr(conf, "conf=") == NULL) {
-        /* try default location, but ignore failure */
-        rados_conf_read_file(s->cluster, NULL);
-    } else if (conf[0] != '\0') {
-        r = qemu_rbd_set_conf(s->cluster, conf, true, errp);
-        if (r < 0) {
-            goto failed_shutdown;
-        }
-    }
-
-    if (conf[0] != '\0') {
-        r = qemu_rbd_set_conf(s->cluster, conf, false, errp);
-        if (r < 0) {
-            goto failed_shutdown;
-        }
-    }
-
    /*
     * Fallback to more conservative semantics if setting cache
     * options fails. Ignore errors from setting rbd_cache because the
@@ -501,21 +481,33 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
        rados_conf_set(s->cluster, "rbd_cache", "true");
    }

+    if (strstr(conf, "conf=") == NULL) {
+        /* try default location, but ignore failure */
+        rados_conf_read_file(s->cluster, NULL);
+    }
+
+    if (conf[0] != '\0') {
+        r = qemu_rbd_set_conf(s->cluster, conf, errp);
+        if (r < 0) {
+            goto failed_shutdown;
+        }
+    }
+
    r = rados_connect(s->cluster);
    if (r < 0) {
-        error_setg(errp, "error connecting");
+        error_setg(&local_err, "error connecting");
        goto failed_shutdown;
    }

    r = rados_ioctx_create(s->cluster, pool, &s->io_ctx);
    if (r < 0) {
-        error_setg(errp, "error opening pool %s", pool);
+        error_setg(&local_err, "error opening pool %s", pool);
        goto failed_shutdown;
    }

    r = rbd_open(s->io_ctx, s->name, &s->image, s->snap);
    if (r < 0) {
-        error_setg(errp, "error reading header from %s", s->name);
+        error_setg(&local_err, "error reading header from %s", s->name);
        goto failed_open;
    }

@@ -629,6 +621,7 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
    acb->error = 0;
    acb->s = s;
    acb->bh = NULL;
+    acb->status = -EINPROGRESS;

    if (cmd == RBD_AIO_WRITE) {
        qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
@@ -640,6 +633,7 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
    size = nb_sectors * BDRV_SECTOR_SIZE;

    rcb = g_new(RADOSCB, 1);
+    rcb->done = 0;
    rcb->acb = acb;
    rcb->buf = buf;
    rcb->s = acb->s;
@@ -24,7 +24,6 @@

 #include "block/snapshot.h"
 #include "block/block_int.h"
-#include "qapi/qmp/qerror.h"

 QemuOptsList internal_snapshot_opts = {
    .name = "snapshot",
@@ -149,7 +148,7 @@ int bdrv_can_snapshot(BlockDriverState *bs)

    if (!drv->bdrv_snapshot_create) {
        if (bs->file != NULL) {
-            return bdrv_can_snapshot(bs->file->bs);
+            return bdrv_can_snapshot(bs->file);
        }
        return 0;
    }
@@ -168,7 +167,7 @@ int bdrv_snapshot_create(BlockDriverState *bs,
        return drv->bdrv_snapshot_create(bs, sn_info);
    }
    if (bs->file) {
-        return bdrv_snapshot_create(bs->file->bs, sn_info);
+        return bdrv_snapshot_create(bs->file, sn_info);
    }
    return -ENOTSUP;
 }
@@ -188,10 +187,10 @@ int bdrv_snapshot_goto(BlockDriverState *bs,

    if (bs->file) {
        drv->bdrv_close(bs);
-        ret = bdrv_snapshot_goto(bs->file->bs, snapshot_id);
+        ret = bdrv_snapshot_goto(bs->file, snapshot_id);
        open_ret = drv->bdrv_open(bs, NULL, bs->open_flags, NULL);
        if (open_ret < 0) {
-            bdrv_unref(bs->file->bs);
+            bdrv_unref(bs->file);
            bs->drv = NULL;
            return open_ret;
        }
@@ -230,7 +229,7 @@ int bdrv_snapshot_delete(BlockDriverState *bs,
 {
    BlockDriver *drv = bs->drv;
    if (!drv) {
-        error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM, bdrv_get_device_name(bs));
+        error_set(errp, QERR_DEVICE_HAS_NO_MEDIUM, bdrv_get_device_name(bs));
        return -ENOMEDIUM;
    }
    if (!snapshot_id && !name) {
@@ -239,23 +238,23 @@ int bdrv_snapshot_delete(BlockDriverState *bs,
    }

    /* drain all pending i/o before deleting snapshot */
-    bdrv_drain(bs);
+    bdrv_drain_all();

    if (drv->bdrv_snapshot_delete) {
        return drv->bdrv_snapshot_delete(bs, snapshot_id, name, errp);
    }
    if (bs->file) {
-        return bdrv_snapshot_delete(bs->file->bs, snapshot_id, name, errp);
+        return bdrv_snapshot_delete(bs->file, snapshot_id, name, errp);
    }
-    error_setg(errp, "Block format '%s' used by device '%s' "
-               "does not support internal snapshot deletion",
-               drv->format_name, bdrv_get_device_name(bs));
+    error_set(errp, QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
+              drv->format_name, bdrv_get_device_name(bs),
+              "internal snapshot deletion");
    return -ENOTSUP;
 }

-int bdrv_snapshot_delete_by_id_or_name(BlockDriverState *bs,
-                                       const char *id_or_name,
-                                       Error **errp)
+void bdrv_snapshot_delete_by_id_or_name(BlockDriverState *bs,
+                                        const char *id_or_name,
+                                        Error **errp)
 {
    int ret;
    Error *local_err = NULL;
@@ -270,7 +269,6 @@ int bdrv_snapshot_delete_by_id_or_name(BlockDriverState *bs,
    if (ret < 0) {
        error_propagate(errp, local_err);
    }
-    return ret;
 }

 int bdrv_snapshot_list(BlockDriverState *bs,
@@ -284,7 +282,7 @@ int bdrv_snapshot_list(BlockDriverState *bs,
        return drv->bdrv_snapshot_list(bs, psn_info);
    }
    if (bs->file) {
-        return bdrv_snapshot_list(bs->file->bs, psn_info);
+        return bdrv_snapshot_list(bs->file, psn_info);
    }
    return -ENOTSUP;
 }
@@ -317,7 +315,7 @@ int bdrv_snapshot_load_tmp(BlockDriverState *bs,
    BlockDriver *drv = bs->drv;

    if (!drv) {
-        error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM, bdrv_get_device_name(bs));
+        error_set(errp, QERR_DEVICE_HAS_NO_MEDIUM, bdrv_get_device_name(bs));
        return -ENOMEDIUM;
    }
    if (!snapshot_id && !name) {
@@ -331,9 +329,9 @@ int bdrv_snapshot_load_tmp(BlockDriverState *bs,
    if (drv->bdrv_snapshot_load_tmp) {
        return drv->bdrv_snapshot_load_tmp(bs, snapshot_id, name, errp);
    }
-    error_setg(errp, "Block format '%s' used by device '%s' "
-               "does not support temporarily loading internal snapshots",
-               drv->format_name, bdrv_get_device_name(bs));
+    error_set(errp, QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
+              drv->format_name, bdrv_get_device_name(bs),
+              "temporarily load internal snapshot");
    return -ENOTSUP;
 }

@@ -357,130 +355,3 @@ int bdrv_snapshot_load_tmp_by_id_or_name(BlockDriverState *bs,

    return ret;
 }
-
-
-/* Group operations. All block drivers are involved.
- * These functions will properly handle dataplane (take aio_context_acquire
- * when appropriate for appropriate block drivers) */
-
-bool bdrv_all_can_snapshot(BlockDriverState **first_bad_bs)
-{
-    bool ok = true;
-    BlockDriverState *bs = NULL;
-
-    while (ok && (bs = bdrv_next(bs))) {
-        AioContext *ctx = bdrv_get_aio_context(bs);
-
-        aio_context_acquire(ctx);
-        if (bdrv_is_inserted(bs) && !bdrv_is_read_only(bs)) {
-            ok = bdrv_can_snapshot(bs);
-        }
-        aio_context_release(ctx);
-    }
-
-    *first_bad_bs = bs;
-    return ok;
-}
-
-int bdrv_all_delete_snapshot(const char *name, BlockDriverState **first_bad_bs,
-                             Error **err)
-{
-    int ret = 0;
-    BlockDriverState *bs = NULL;
-    QEMUSnapshotInfo sn1, *snapshot = &sn1;
-
-    while (ret == 0 && (bs = bdrv_next(bs))) {
-        AioContext *ctx = bdrv_get_aio_context(bs);
-
-        aio_context_acquire(ctx);
-        if (bdrv_can_snapshot(bs) &&
-                bdrv_snapshot_find(bs, snapshot, name) >= 0) {
-            ret = bdrv_snapshot_delete_by_id_or_name(bs, name, err);
-        }
-        aio_context_release(ctx);
-    }
-
-    *first_bad_bs = bs;
-    return ret;
-}
-
-
-int bdrv_all_goto_snapshot(const char *name, BlockDriverState **first_bad_bs)
-{
-    int err = 0;
-    BlockDriverState *bs = NULL;
-
-    while (err == 0 && (bs = bdrv_next(bs))) {
-        AioContext *ctx = bdrv_get_aio_context(bs);
-
-        aio_context_acquire(ctx);
-        if (bdrv_can_snapshot(bs)) {
-            err = bdrv_snapshot_goto(bs, name);
-        }
-        aio_context_release(ctx);
-    }
-
-    *first_bad_bs = bs;
-    return err;
-}
-
-int bdrv_all_find_snapshot(const char *name, BlockDriverState **first_bad_bs)
-{
-    QEMUSnapshotInfo sn;
-    int err = 0;
-    BlockDriverState *bs = NULL;
-
-    while (err == 0 && (bs = bdrv_next(bs))) {
-        AioContext *ctx = bdrv_get_aio_context(bs);
-
-        aio_context_acquire(ctx);
-        if (bdrv_can_snapshot(bs)) {
-            err = bdrv_snapshot_find(bs, &sn, name);
-        }
-        aio_context_release(ctx);
-    }
-
-    *first_bad_bs = bs;
-    return err;
-}
-
-int bdrv_all_create_snapshot(QEMUSnapshotInfo *sn,
-                             BlockDriverState *vm_state_bs,
-                             uint64_t vm_state_size,
-                             BlockDriverState **first_bad_bs)
-{
-    int err = 0;
-    BlockDriverState *bs = NULL;
-
-    while (err == 0 && (bs = bdrv_next(bs))) {
-        AioContext *ctx = bdrv_get_aio_context(bs);
-
-        aio_context_acquire(ctx);
-        if (bs == vm_state_bs) {
-            sn->vm_state_size = vm_state_size;
-            err = bdrv_snapshot_create(bs, sn);
-        } else if (bdrv_can_snapshot(bs)) {
-            sn->vm_state_size = 0;
-            err = bdrv_snapshot_create(bs, sn);
-        }
-        aio_context_release(ctx);
-    }
-
-    *first_bad_bs = bs;
-    return err;
-}
-
-BlockDriverState *bdrv_all_find_vmstate_bs(void)
-{
-    bool not_found = true;
-    BlockDriverState *bs = NULL;
-
-    while (not_found && (bs = bdrv_next(bs))) {
-        AioContext *ctx = bdrv_get_aio_context(bs);
-
-        aio_context_acquire(ctx);
-        not_found = !bdrv_can_snapshot(bs);
-        aio_context_release(ctx);
-    }
-    return bs;
-}
@@ -30,11 +30,9 @@
 #include <libssh2_sftp.h>

 #include "block/block_int.h"
-#include "qemu/error-report.h"
 #include "qemu/sockets.h"
 #include "qemu/uri.h"
 #include "qapi/qmp/qint.h"
-#include "qapi/qmp/qstring.h"

 /* DEBUG_SSH=1 enables the DPRINTF (debugging printf) statements in
 * this block driver code.
@@ -193,7 +191,7 @@ sftp_error_report(BDRVSSHState *s, const char *fs, ...)
 static int parse_uri(const char *filename, QDict *options, Error **errp)
 {
    URI *uri = NULL;
-    QueryParams *qp;
+    QueryParams *qp = NULL;
    int i;

    uri = uri_parse(filename);
@@ -249,6 +247,9 @@ static int parse_uri(const char *filename, QDict *options, Error **errp)
    return 0;

 err:
+    if (qp) {
+      query_params_free(qp);
+    }
    if (uri) {
      uri_free(uri);
    }
@@ -560,7 +561,7 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
    /* Open the socket and connect. */
    s->sock = inet_connect(s->hostport, errp);
    if (s->sock < 0) {
-        ret = -EIO;
+        ret = -errno;
        goto err;
    }

@@ -800,15 +801,14 @@ static coroutine_fn void set_fd_handler(BDRVSSHState *s, BlockDriverState *bs)
            rd_handler, wr_handler);

    aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock,
-                       false, rd_handler, wr_handler, co);
+                       rd_handler, wr_handler, co);
 }

 static coroutine_fn void clear_fd_handler(BDRVSSHState *s,
                                          BlockDriverState *bs)
 {
    DPRINTF("s->sock=%d", s->sock);
-    aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock,
-                       false, NULL, NULL, NULL);
+    aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock, NULL, NULL, NULL);
 }

 /* A non-blocking call returned EAGAIN, so yield, ensuring the
@@ -14,9 +14,7 @@
 #include "trace.h"
 #include "block/block_int.h"
 #include "block/blockjob.h"
-#include "qapi/qmp/qerror.h"
 #include "qemu/ratelimit.h"
-#include "sysemu/block-backend.h"

 enum {
    /*
@@ -53,6 +51,34 @@ static int coroutine_fn stream_populate(BlockDriverState *bs,
    return bdrv_co_copy_on_readv(bs, sector_num, nb_sectors, &qiov);
 }

+static void close_unused_images(BlockDriverState *top, BlockDriverState *base,
+                                const char *base_id)
+{
+    BlockDriverState *intermediate;
+    intermediate = top->backing_hd;
+
+    /* Must assign before bdrv_delete() to prevent traversing dangling pointer
+     * while we delete backing image instances.
+     */
+    bdrv_set_backing_hd(top, base);
+
+    while (intermediate) {
+        BlockDriverState *unused;
+
+        /* reached base */
+        if (intermediate == base) {
+            break;
+        }
+
+        unused = intermediate;
+        intermediate = intermediate->backing_hd;
+        bdrv_set_backing_hd(unused, NULL);
+        bdrv_unref(unused);
+    }
+
+    bdrv_refresh_limits(top, NULL);
+}
+
 typedef struct {
    int ret;
    bool reached_end;
@@ -74,7 +100,7 @@ static void stream_complete(BlockJob *job, void *opaque)
            }
        }
        data->ret = bdrv_change_backing_file(job->bs, base_id, base_fmt);
-        bdrv_set_backing_hd(job->bs, base);
+        close_unused_images(job->bs, base, base_id);
    }

    g_free(s->backing_file_str);
@@ -94,7 +120,7 @@ static void coroutine_fn stream_run(void *opaque)
    int n = 0;
    void *buf;

-    if (!bs->backing) {
+    if (!bs->backing_hd) {
        block_job_completed(&s->common, 0);
        return;
    }
@@ -139,7 +165,7 @@ wait:
        } else if (ret >= 0) {
            /* Copy if allocated in the intermediate images.  Limit to the
             * known-unallocated area [sector_num, sector_num+n).  */
-            ret = bdrv_is_allocated_above(backing_bs(bs), base,
+            ret = bdrv_is_allocated_above(bs->backing_hd, base,
                                          sector_num, n, &n);

            /* Finish early if end of backing file has been reached */
@@ -201,7 +227,7 @@ static void stream_set_speed(BlockJob *job, int64_t speed, Error **errp)
    StreamBlockJob *s = container_of(job, StreamBlockJob, common);

    if (speed < 0) {
-        error_setg(errp, QERR_INVALID_PARAMETER, "speed");
+        error_set(errp, QERR_INVALID_PARAMETER, "speed");
        return;
    }
    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
@@ -223,8 +249,8 @@ void stream_start(BlockDriverState *bs, BlockDriverState *base,

    if ((on_error == BLOCKDEV_ON_ERROR_STOP ||
         on_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        (!bs->blk || !blk_iostatus_is_enabled(bs->blk))) {
-        error_setg(errp, QERR_INVALID_PARAMETER, "on-error");
+        !bdrv_iostatus_is_enabled(bs)) {
+        error_set(errp, QERR_INVALID_PARAMETER, "on-error");
        return;
    }

@@ -1,482 +0,0 @@
-/*
- * QEMU block throttling group infrastructure
- *
- * Copyright (C) Nodalink, EURL. 2014
- * Copyright (C) Igalia, S.L. 2015
- *
- * Authors:
- *   Benoît Canet <benoit.canet@nodalink.com>
- *   Alberto Garcia <berto@igalia.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 or
- * (at your option) version 3 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "block/throttle-groups.h"
-#include "qemu/queue.h"
-#include "qemu/thread.h"
-#include "sysemu/qtest.h"
-
-/* The ThrottleGroup structure (with its ThrottleState) is shared
- * among different BlockDriverState and it's independent from
- * AioContext, so in order to use it from different threads it needs
- * its own locking.
- *
- * This locking is however handled internally in this file, so it's
- * transparent to outside users.
- *
- * The whole ThrottleGroup structure is private and invisible to
- * outside users, that only use it through its ThrottleState.
- *
- * In addition to the ThrottleGroup structure, BlockDriverState has
- * fields that need to be accessed by other members of the group and
- * therefore also need to be protected by this lock. Once a BDS is
- * registered in a group those fields can be accessed by other threads
- * any time.
- *
- * Again, all this is handled internally and is mostly transparent to
- * the outside. The 'throttle_timers' field however has an additional
- * constraint because it may be temporarily invalid (see for example
- * bdrv_set_aio_context()). Therefore in this file a thread will
- * access some other BDS's timers only after verifying that that BDS
- * has throttled requests in the queue.
- */
-typedef struct ThrottleGroup {
-    char *name; /* This is constant during the lifetime of the group */
-
-    QemuMutex lock; /* This lock protects the following four fields */
-    ThrottleState ts;
-    QLIST_HEAD(, BlockDriverState) head;
-    BlockDriverState *tokens[2];
-    bool any_timer_armed[2];
-
-    /* These two are protected by the global throttle_groups_lock */
-    unsigned refcount;
-    QTAILQ_ENTRY(ThrottleGroup) list;
-} ThrottleGroup;
-
-static QemuMutex throttle_groups_lock;
-static QTAILQ_HEAD(, ThrottleGroup) throttle_groups =
-    QTAILQ_HEAD_INITIALIZER(throttle_groups);
-
-/* Increments the reference count of a ThrottleGroup given its name.
- *
- * If no ThrottleGroup is found with the given name a new one is
- * created.
- *
- * @name: the name of the ThrottleGroup
- * @ret:  the ThrottleState member of the ThrottleGroup
- */
-ThrottleState *throttle_group_incref(const char *name)
-{
-    ThrottleGroup *tg = NULL;
-    ThrottleGroup *iter;
-
-    qemu_mutex_lock(&throttle_groups_lock);
-
-    /* Look for an existing group with that name */
-    QTAILQ_FOREACH(iter, &throttle_groups, list) {
-        if (!strcmp(name, iter->name)) {
-            tg = iter;
-            break;
-        }
-    }
-
-    /* Create a new one if not found */
-    if (!tg) {
-        tg = g_new0(ThrottleGroup, 1);
-        tg->name = g_strdup(name);
-        qemu_mutex_init(&tg->lock);
-        throttle_init(&tg->ts);
-        QLIST_INIT(&tg->head);
-
-        QTAILQ_INSERT_TAIL(&throttle_groups, tg, list);
-    }
-
-    tg->refcount++;
-
-    qemu_mutex_unlock(&throttle_groups_lock);
-
-    return &tg->ts;
-}
-
-/* Decrease the reference count of a ThrottleGroup.
- *
- * When the reference count reaches zero the ThrottleGroup is
- * destroyed.
- *
- * @ts:  The ThrottleGroup to unref, given by its ThrottleState member
- */
-void throttle_group_unref(ThrottleState *ts)
-{
-    ThrottleGroup *tg = container_of(ts, ThrottleGroup, ts);
-
-    qemu_mutex_lock(&throttle_groups_lock);
-    if (--tg->refcount == 0) {
-        QTAILQ_REMOVE(&throttle_groups, tg, list);
-        qemu_mutex_destroy(&tg->lock);
-        g_free(tg->name);
-        g_free(tg);
-    }
-    qemu_mutex_unlock(&throttle_groups_lock);
-}
-
-/* Get the name from a BlockDriverState's ThrottleGroup. The name (and
- * the pointer) is guaranteed to remain constant during the lifetime
- * of the group.
- *
- * @bs:   a BlockDriverState that is member of a throttling group
- * @ret:  the name of the group.
- */
-const char *throttle_group_get_name(BlockDriverState *bs)
-{
-    ThrottleGroup *tg = container_of(bs->throttle_state, ThrottleGroup, ts);
-    return tg->name;
-}
-
-/* Return the next BlockDriverState in the round-robin sequence,
- * simulating a circular list.
- *
- * This assumes that tg->lock is held.
- *
- * @bs:  the current BlockDriverState
- * @ret: the next BlockDriverState in the sequence
- */
-static BlockDriverState *throttle_group_next_bs(BlockDriverState *bs)
-{
-    ThrottleState *ts = bs->throttle_state;
-    ThrottleGroup *tg = container_of(ts, ThrottleGroup, ts);
-    BlockDriverState *next = QLIST_NEXT(bs, round_robin);
-
-    if (!next) {
-        return QLIST_FIRST(&tg->head);
-    }
-
-    return next;
-}
-
-/* Return the next BlockDriverState in the round-robin sequence with
- * pending I/O requests.
- *
- * This assumes that tg->lock is held.
- *
- * @bs:        the current BlockDriverState
- * @is_write:  the type of operation (read/write)
- * @ret:       the next BlockDriverState with pending requests, or bs
- *             if there is none.
- */
-static BlockDriverState *next_throttle_token(BlockDriverState *bs,
-                                             bool is_write)
-{
-    ThrottleGroup *tg = container_of(bs->throttle_state, ThrottleGroup, ts);
-    BlockDriverState *token, *start;
-
-    start = token = tg->tokens[is_write];
-
-    /* get next bs round in round robin style */
-    token = throttle_group_next_bs(token);
-    while (token != start && !token->pending_reqs[is_write]) {
-        token = throttle_group_next_bs(token);
-    }
-
-    /* If no IO are queued for scheduling on the next round robin token
-     * then decide the token is the current bs because chances are
-     * the current bs get the current request queued.
-     */
-    if (token == start && !token->pending_reqs[is_write]) {
-        token = bs;
-    }
-
-    return token;
-}
-
-/* Check if the next I/O request for a BlockDriverState needs to be
- * throttled or not. If there's no timer set in this group, set one
- * and update the token accordingly.
- *
- * This assumes that tg->lock is held.
- *
- * @bs:         the current BlockDriverState
- * @is_write:   the type of operation (read/write)
- * @ret:        whether the I/O request needs to be throttled or not
- */
-static bool throttle_group_schedule_timer(BlockDriverState *bs,
-                                          bool is_write)
-{
-    ThrottleState *ts = bs->throttle_state;
-    ThrottleTimers *tt = &bs->throttle_timers;
-    ThrottleGroup *tg = container_of(ts, ThrottleGroup, ts);
-    bool must_wait;
-
-    /* Check if any of the timers in this group is already armed */
-    if (tg->any_timer_armed[is_write]) {
-        return true;
-    }
-
-    must_wait = throttle_schedule_timer(ts, tt, is_write);
-
-    /* If a timer just got armed, set bs as the current token */
-    if (must_wait) {
-        tg->tokens[is_write] = bs;
-        tg->any_timer_armed[is_write] = true;
-    }
-
-    return must_wait;
-}
-
-/* Look for the next pending I/O request and schedule it.
- *
- * This assumes that tg->lock is held.
- *
- * @bs:        the current BlockDriverState
- * @is_write:  the type of operation (read/write)
- */
-static void schedule_next_request(BlockDriverState *bs, bool is_write)
-{
-    ThrottleGroup *tg = container_of(bs->throttle_state, ThrottleGroup, ts);
-    bool must_wait;
-    BlockDriverState *token;
-
-    /* Check if there's any pending request to schedule next */
-    token = next_throttle_token(bs, is_write);
-    if (!token->pending_reqs[is_write]) {
-        return;
-    }
-
-    /* Set a timer for the request if it needs to be throttled */
-    must_wait = throttle_group_schedule_timer(token, is_write);
-
-    /* If it doesn't have to wait, queue it for immediate execution */
-    if (!must_wait) {
-        /* Give preference to requests from the current bs */
-        if (qemu_in_coroutine() &&
-            qemu_co_queue_next(&bs->throttled_reqs[is_write])) {
-            token = bs;
-        } else {
-            ThrottleTimers *tt = &token->throttle_timers;
-            int64_t now = qemu_clock_get_ns(tt->clock_type);
-            timer_mod(tt->timers[is_write], now + 1);
-            tg->any_timer_armed[is_write] = true;
-        }
-        tg->tokens[is_write] = token;
-    }
-}
-
-/* Check if an I/O request needs to be throttled, wait and set a timer
- * if necessary, and schedule the next request using a round robin
- * algorithm.
- *
- * @bs:        the current BlockDriverState
- * @bytes:     the number of bytes for this I/O
- * @is_write:  the type of operation (read/write)
- */
-void coroutine_fn throttle_group_co_io_limits_intercept(BlockDriverState *bs,
-                                                        unsigned int bytes,
-                                                        bool is_write)
-{
-    bool must_wait;
-    BlockDriverState *token;
-
-    ThrottleGroup *tg = container_of(bs->throttle_state, ThrottleGroup, ts);
-    qemu_mutex_lock(&tg->lock);
-
-    /* First we check if this I/O has to be throttled. */
-    token = next_throttle_token(bs, is_write);
-    must_wait = throttle_group_schedule_timer(token, is_write);
-
-    /* Wait if there's a timer set or queued requests of this type */
-    if (must_wait || bs->pending_reqs[is_write]) {
-        bs->pending_reqs[is_write]++;
-        qemu_mutex_unlock(&tg->lock);
-        qemu_co_queue_wait(&bs->throttled_reqs[is_write]);
-        qemu_mutex_lock(&tg->lock);
-        bs->pending_reqs[is_write]--;
-    }
-
-    /* The I/O will be executed, so do the accounting */
-    throttle_account(bs->throttle_state, is_write, bytes);
-
-    /* Schedule the next request */
-    schedule_next_request(bs, is_write);
-
-    qemu_mutex_unlock(&tg->lock);
-}
-
-/* Update the throttle configuration for a particular group. Similar
- * to throttle_config(), but guarantees atomicity within the
- * throttling group.
- *
- * @bs:  a BlockDriverState that is member of the group
- * @cfg: the configuration to set
- */
-void throttle_group_config(BlockDriverState *bs, ThrottleConfig *cfg)
-{
-    ThrottleTimers *tt = &bs->throttle_timers;
-    ThrottleState *ts = bs->throttle_state;
-    ThrottleGroup *tg = container_of(ts, ThrottleGroup, ts);
-    qemu_mutex_lock(&tg->lock);
-    /* throttle_config() cancels the timers */
-    if (timer_pending(tt->timers[0])) {
-        tg->any_timer_armed[0] = false;
-    }
-    if (timer_pending(tt->timers[1])) {
-        tg->any_timer_armed[1] = false;
-    }
-    throttle_config(ts, tt, cfg);
-    qemu_mutex_unlock(&tg->lock);
-}
-
-/* Get the throttle configuration from a particular group. Similar to
- * throttle_get_config(), but guarantees atomicity within the
- * throttling group.
- *
- * @bs:  a BlockDriverState that is member of the group
- * @cfg: the configuration will be written here
- */
-void throttle_group_get_config(BlockDriverState *bs, ThrottleConfig *cfg)
-{
-    ThrottleState *ts = bs->throttle_state;
-    ThrottleGroup *tg = container_of(ts, ThrottleGroup, ts);
-    qemu_mutex_lock(&tg->lock);
-    throttle_get_config(ts, cfg);
-    qemu_mutex_unlock(&tg->lock);
-}
-
-/* ThrottleTimers callback. This wakes up a request that was waiting
- * because it had been throttled.
- *
- * @bs:        the BlockDriverState whose request had been throttled
- * @is_write:  the type of operation (read/write)
- */
-static void timer_cb(BlockDriverState *bs, bool is_write)
-{
-    ThrottleState *ts = bs->throttle_state;
-    ThrottleGroup *tg = container_of(ts, ThrottleGroup, ts);
-    bool empty_queue;
-
-    /* The timer has just been fired, so we can update the flag */
-    qemu_mutex_lock(&tg->lock);
-    tg->any_timer_armed[is_write] = false;
-    qemu_mutex_unlock(&tg->lock);
-
-    /* Run the request that was waiting for this timer */
-    empty_queue = !qemu_co_enter_next(&bs->throttled_reqs[is_write]);
-
-    /* If the request queue was empty then we have to take care of
-     * scheduling the next one */
-    if (empty_queue) {
-        qemu_mutex_lock(&tg->lock);
-        schedule_next_request(bs, is_write);
-        qemu_mutex_unlock(&tg->lock);
-    }
-}
-
-static void read_timer_cb(void *opaque)
-{
-    timer_cb(opaque, false);
-}
-
-static void write_timer_cb(void *opaque)
-{
-    timer_cb(opaque, true);
-}
-
-/* Register a BlockDriverState in the throttling group, also
- * initializing its timers and updating its throttle_state pointer to
- * point to it. If a throttling group with that name does not exist
- * yet, it will be created.
- *
- * @bs:        the BlockDriverState to insert
- * @groupname: the name of the group
- */
-void throttle_group_register_bs(BlockDriverState *bs, const char *groupname)
-{
-    int i;
-    ThrottleState *ts = throttle_group_incref(groupname);
-    ThrottleGroup *tg = container_of(ts, ThrottleGroup, ts);
-    int clock_type = QEMU_CLOCK_REALTIME;
-
-    if (qtest_enabled()) {
-        /* For testing block IO throttling only */
-        clock_type = QEMU_CLOCK_VIRTUAL;
-    }
-
-    bs->throttle_state = ts;
-
-    qemu_mutex_lock(&tg->lock);
-    /* If the ThrottleGroup is new set this BlockDriverState as the token */
-    for (i = 0; i < 2; i++) {
-        if (!tg->tokens[i]) {
-            tg->tokens[i] = bs;
-        }
-    }
-
-    QLIST_INSERT_HEAD(&tg->head, bs, round_robin);
-
-    throttle_timers_init(&bs->throttle_timers,
-                         bdrv_get_aio_context(bs),
-                         clock_type,
-                         read_timer_cb,
-                         write_timer_cb,
-                         bs);
-
-    qemu_mutex_unlock(&tg->lock);
-}
-
-/* Unregister a BlockDriverState from its group, removing it from the
- * list, destroying the timers and setting the throttle_state pointer
- * to NULL.
- *
- * The BlockDriverState must not have pending throttled requests, so
- * the caller has to drain them first.
- *
- * The group will be destroyed if it's empty after this operation.
- *
- * @bs: the BlockDriverState to remove
- */
-void throttle_group_unregister_bs(BlockDriverState *bs)
-{
-    ThrottleGroup *tg = container_of(bs->throttle_state, ThrottleGroup, ts);
-    int i;
-
-    assert(bs->pending_reqs[0] == 0 && bs->pending_reqs[1] == 0);
-    assert(qemu_co_queue_empty(&bs->throttled_reqs[0]));
-    assert(qemu_co_queue_empty(&bs->throttled_reqs[1]));
-
-    qemu_mutex_lock(&tg->lock);
-    for (i = 0; i < 2; i++) {
-        if (tg->tokens[i] == bs) {
-            BlockDriverState *token = throttle_group_next_bs(bs);
-            /* Take care of the case where this is the last bs in the group */
-            if (token == bs) {
-                token = NULL;
-            }
-            tg->tokens[i] = token;
-        }
-    }
-
-    /* remove the current bs from the list */
-    QLIST_REMOVE(bs, round_robin);
-    throttle_timers_destroy(&bs->throttle_timers);
-    qemu_mutex_unlock(&tg->lock);
-
-    throttle_group_unref(&tg->ts);
-    bs->throttle_state = NULL;
-}
-
-static void throttle_groups_init(void)
-{
-    qemu_mutex_init(&throttle_groups_lock);
-}
-
-block_init(throttle_groups_init);
@@ -53,7 +53,6 @@
 #include "block/block_int.h"
 #include "qemu/module.h"
 #include "migration/migration.h"
-#include "qemu/coroutine.h"

 #if defined(CONFIG_UUID)
 #include <uuid/uuid.h>
@@ -197,8 +196,6 @@ typedef struct {
    /* VDI header (converted to host endianness). */
    VdiHeader header;

-    CoMutex write_lock;
-
    Error *migration_blocker;
 } BDRVVdiState;

@@ -399,7 +396,7 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,

    logout("\n");

-    ret = bdrv_read(bs->file->bs, 0, (uint8_t *)&header, 1);
+    ret = bdrv_read(bs->file, 0, (uint8_t *)&header, 1);
    if (ret < 0) {
        goto fail;
    }
@@ -490,26 +487,23 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,

    bmap_size = header.blocks_in_image * sizeof(uint32_t);
    bmap_size = DIV_ROUND_UP(bmap_size, SECTOR_SIZE);
-    s->bmap = qemu_try_blockalign(bs->file->bs, bmap_size * SECTOR_SIZE);
+    s->bmap = qemu_try_blockalign(bs->file, bmap_size * SECTOR_SIZE);
    if (s->bmap == NULL) {
        ret = -ENOMEM;
        goto fail;
    }

-    ret = bdrv_read(bs->file->bs, s->bmap_sector, (uint8_t *)s->bmap,
-                    bmap_size);
+    ret = bdrv_read(bs->file, s->bmap_sector, (uint8_t *)s->bmap, bmap_size);
    if (ret < 0) {
        goto fail_free_bmap;
    }

    /* Disable migration when vdi images are used */
-    error_setg(&s->migration_blocker, "The vdi format used by node '%s' "
-               "does not support live migration",
-               bdrv_get_device_or_node_name(bs));
+    error_set(&s->migration_blocker,
+              QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
+              "vdi", bdrv_get_device_name(bs), "live migration");
    migrate_add_blocker(s->migration_blocker);

-    qemu_co_mutex_init(&s->write_lock);
-
    return 0;

 fail_free_bmap:
@@ -586,7 +580,7 @@ static int vdi_co_read(BlockDriverState *bs,
            uint64_t offset = s->header.offset_data / SECTOR_SIZE +
                              (uint64_t)bmap_entry * s->block_sectors +
                              sector_in_block;
-            ret = bdrv_read(bs->file->bs, offset, buf, n_sectors);
+            ret = bdrv_read(bs->file, offset, buf, n_sectors);
        }
        logout("%u sectors read\n", n_sectors);

@@ -645,32 +639,12 @@ static int vdi_co_write(BlockDriverState *bs,
                   buf, n_sectors * SECTOR_SIZE);
            memset(block + (sector_in_block + n_sectors) * SECTOR_SIZE, 0,
                   (s->block_sectors - n_sectors - sector_in_block) * SECTOR_SIZE);
-
-            /* Note that this coroutine does not yield anywhere from reading the
-             * bmap entry until here, so in regards to all the coroutines trying
-             * to write to this cluster, the one doing the allocation will
-             * always be the first to try to acquire the lock.
-             * Therefore, it is also the first that will actually be able to
-             * acquire the lock and thus the padded cluster is written before
-             * the other coroutines can write to the affected area. */
-            qemu_co_mutex_lock(&s->write_lock);
-            ret = bdrv_write(bs->file->bs, offset, block, s->block_sectors);
-            qemu_co_mutex_unlock(&s->write_lock);
+            ret = bdrv_write(bs->file, offset, block, s->block_sectors);
        } else {
            uint64_t offset = s->header.offset_data / SECTOR_SIZE +
                              (uint64_t)bmap_entry * s->block_sectors +
                              sector_in_block;
-            qemu_co_mutex_lock(&s->write_lock);
-            /* This lock is only used to make sure the following write operation
-             * is executed after the write issued by the coroutine allocating
-             * this cluster, therefore we do not need to keep it locked.
-             * As stated above, the allocating coroutine will always try to lock
-             * the mutex before all the other concurrent accesses to that
-             * cluster, therefore at this point we can be absolutely certain
-             * that that write operation has returned (there may be other writes
-             * in flight, but they do not concern this very operation). */
-            qemu_co_mutex_unlock(&s->write_lock);
-            ret = bdrv_write(bs->file->bs, offset, buf, n_sectors);
+            ret = bdrv_write(bs->file, offset, buf, n_sectors);
        }

        nb_sectors -= n_sectors;
@@ -695,7 +669,7 @@ static int vdi_co_write(BlockDriverState *bs,
        assert(VDI_IS_ALLOCATED(bmap_first));
        *header = s->header;
        vdi_header_to_le(header);
-        ret = bdrv_write(bs->file->bs, 0, block, 1);
+        ret = bdrv_write(bs->file, 0, block, 1);
        g_free(block);
        block = NULL;

@@ -713,7 +687,7 @@ static int vdi_co_write(BlockDriverState *bs,
        base = ((uint8_t *)&s->bmap[0]) + bmap_first * SECTOR_SIZE;
        logout("will write %u block map sectors starting from entry %u\n",
               n_sectors, bmap_first);
-        ret = bdrv_write(bs->file->bs, offset, base, n_sectors);
+        ret = bdrv_write(bs->file, offset, base, n_sectors);
    }

    return ret;
@@ -765,7 +739,7 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
        goto exit;
    }
    ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
-                    &local_err);
+                    NULL, &local_err);
    if (ret < 0) {
        error_propagate(errp, local_err);
        goto exit;
@@ -878,6 +852,11 @@ static QemuOptsList vdi_create_opts = {
            .def_value_str = "off"
        },
 #endif
+        {
+            .name = BLOCK_OPT_NOCOW,
+            .type = QEMU_OPT_BOOL,
+            .help = "Turn off copy-on-write (valid only on btrfs)"
+        },
        /* TODO: An additional option to set UUID values might be useful. */
        { /* end of list */ }
    }
@@ -19,7 +19,6 @@
 */
 #include "qemu-common.h"
 #include "block/block_int.h"
-#include "qemu/error-report.h"
 #include "qemu/module.h"
 #include "block/vhdx.h"

@@ -81,7 +80,7 @@ static int vhdx_log_peek_hdr(BlockDriverState *bs, VHDXLogEntries *log,

    offset = log->offset + read;

-    ret = bdrv_pread(bs->file->bs, offset, hdr, sizeof(VHDXLogEntryHeader));
+    ret = bdrv_pread(bs->file, offset, hdr, sizeof(VHDXLogEntryHeader));
    if (ret < 0) {
        goto exit;
    }
@@ -141,7 +140,7 @@ static int vhdx_log_read_sectors(BlockDriverState *bs, VHDXLogEntries *log,
        }
        offset = log->offset + read;

-        ret = bdrv_pread(bs->file->bs, offset, buffer, VHDX_LOG_SECTOR_SIZE);
+        ret = bdrv_pread(bs->file, offset, buffer, VHDX_LOG_SECTOR_SIZE);
        if (ret < 0) {
            goto exit;
        }
@@ -191,8 +190,7 @@ static int vhdx_log_write_sectors(BlockDriverState *bs, VHDXLogEntries *log,
            /* full */
            break;
        }
-        ret = bdrv_pwrite(bs->file->bs, offset, buffer_tmp,
-                          VHDX_LOG_SECTOR_SIZE);
+        ret = bdrv_pwrite(bs->file, offset, buffer_tmp, VHDX_LOG_SECTOR_SIZE);
        if (ret < 0) {
            goto exit;
        }
@@ -354,7 +352,7 @@ static int vhdx_log_read_desc(BlockDriverState *bs, BDRVVHDXState *s,
    }

    desc_sectors = vhdx_compute_desc_sectors(hdr.descriptor_count);
-    desc_entries = qemu_try_blockalign(bs->file->bs,
+    desc_entries = qemu_try_blockalign(bs->file,
                                       desc_sectors * VHDX_LOG_SECTOR_SIZE);
    if (desc_entries == NULL) {
        ret = -ENOMEM;
@@ -463,7 +461,7 @@ static int vhdx_log_flush_desc(BlockDriverState *bs, VHDXLogDescriptor *desc,

    /* count is only > 1 if we are writing zeroes */
    for (i = 0; i < count; i++) {
-        ret = bdrv_pwrite_sync(bs->file->bs, file_offset, buffer,
+        ret = bdrv_pwrite_sync(bs->file, file_offset, buffer,
                               VHDX_LOG_SECTOR_SIZE);
        if (ret < 0) {
            goto exit;
@@ -510,7 +508,7 @@ static int vhdx_log_flush(BlockDriverState *bs, BDRVVHDXState *s,
        /* if the log shows a FlushedFileOffset larger than our current file
         * size, then that means the file has been truncated / corrupted, and
         * we must refused to open it / use it */
-        if (hdr_tmp.flushed_file_offset > bdrv_getlength(bs->file->bs)) {
+        if (hdr_tmp.flushed_file_offset > bdrv_getlength(bs->file)) {
            ret = -EINVAL;
            goto exit;
        }
@@ -540,12 +538,12 @@ static int vhdx_log_flush(BlockDriverState *bs, BDRVVHDXState *s,
                goto exit;
            }
        }
-        if (bdrv_getlength(bs->file->bs) < desc_entries->hdr.last_file_offset) {
+        if (bdrv_getlength(bs->file) < desc_entries->hdr.last_file_offset) {
            new_file_size = desc_entries->hdr.last_file_offset;
            if (new_file_size % (1024*1024)) {
                /* round up to nearest 1MB boundary */
                new_file_size = ((new_file_size >> 20) + 1) << 20;
-                bdrv_truncate(bs->file->bs, new_file_size);
+                bdrv_truncate(bs->file, new_file_size);
            }
        }
        qemu_vfree(desc_entries);
@@ -909,8 +907,8 @@ static int vhdx_log_write(BlockDriverState *bs, BDRVVHDXState *s,
                .sequence_number     = s->log.sequence,
                .descriptor_count    = sectors,
                .reserved            = 0,
-                .flushed_file_offset = bdrv_getlength(bs->file->bs),
-                .last_file_offset    = bdrv_getlength(bs->file->bs),
+                .flushed_file_offset = bdrv_getlength(bs->file),
+                .last_file_offset    = bdrv_getlength(bs->file),
              };

    new_hdr.log_guid = header->log_guid;
@@ -941,7 +939,7 @@ static int vhdx_log_write(BlockDriverState *bs, BDRVVHDXState *s,

        if (i == 0 && leading_length) {
            /* partial sector at the front of the buffer */
-            ret = bdrv_pread(bs->file->bs, file_offset, merged_sector,
+            ret = bdrv_pread(bs->file, file_offset, merged_sector,
                             VHDX_LOG_SECTOR_SIZE);
            if (ret < 0) {
                goto exit;
@@ -951,7 +949,7 @@ static int vhdx_log_write(BlockDriverState *bs, BDRVVHDXState *s,
            sector_write = merged_sector;
        } else if (i == sectors - 1 && trailing_length) {
            /* partial sector at the end of the buffer */
-            ret = bdrv_pread(bs->file->bs,
+            ret = bdrv_pread(bs->file,
                            file_offset,
                            merged_sector + trailing_length,
                            VHDX_LOG_SECTOR_SIZE - trailing_length);
@@ -375,7 +375,7 @@ static int vhdx_update_header(BlockDriverState *bs, BDRVVHDXState *s,
        inactive_header->log_guid = *log_guid;
    }

-    ret = vhdx_write_header(bs->file->bs, inactive_header, header_offset, true);
+    ret = vhdx_write_header(bs->file, inactive_header, header_offset, true);
    if (ret < 0) {
        goto exit;
    }
@@ -427,8 +427,7 @@ static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s,
    /* We have to read the whole VHDX_HEADER_SIZE instead of
     * sizeof(VHDXHeader), because the checksum is over the whole
     * region */
-    ret = bdrv_pread(bs->file->bs, VHDX_HEADER1_OFFSET, buffer,
-                     VHDX_HEADER_SIZE);
+    ret = bdrv_pread(bs->file, VHDX_HEADER1_OFFSET, buffer, VHDX_HEADER_SIZE);
    if (ret < 0) {
        goto fail;
    }
@@ -444,8 +443,7 @@ static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s,
        }
    }

-    ret = bdrv_pread(bs->file->bs, VHDX_HEADER2_OFFSET, buffer,
-                     VHDX_HEADER_SIZE);
+    ret = bdrv_pread(bs->file, VHDX_HEADER2_OFFSET, buffer, VHDX_HEADER_SIZE);
    if (ret < 0) {
        goto fail;
    }
@@ -518,7 +516,7 @@ static int vhdx_open_region_tables(BlockDriverState *bs, BDRVVHDXState *s)
     * whole block */
    buffer = qemu_blockalign(bs, VHDX_HEADER_BLOCK_SIZE);

-    ret = bdrv_pread(bs->file->bs, VHDX_REGION_TABLE_OFFSET, buffer,
+    ret = bdrv_pread(bs->file, VHDX_REGION_TABLE_OFFSET, buffer,
                     VHDX_HEADER_BLOCK_SIZE);
    if (ret < 0) {
        goto fail;
@@ -631,7 +629,7 @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s)

    buffer = qemu_blockalign(bs, VHDX_METADATA_TABLE_MAX_SIZE);

-    ret = bdrv_pread(bs->file->bs, s->metadata_rt.file_offset, buffer,
+    ret = bdrv_pread(bs->file, s->metadata_rt.file_offset, buffer,
                     VHDX_METADATA_TABLE_MAX_SIZE);
    if (ret < 0) {
        goto exit;
@@ -734,7 +732,7 @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s)
        goto exit;
    }

-    ret = bdrv_pread(bs->file->bs,
+    ret = bdrv_pread(bs->file,
                     s->metadata_entries.file_parameters_entry.offset
                                         + s->metadata_rt.file_offset,
                     &s->params,
@@ -769,7 +767,7 @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s)
    /* determine virtual disk size, logical sector size,
     * and phys sector size */

-    ret = bdrv_pread(bs->file->bs,
+    ret = bdrv_pread(bs->file,
                     s->metadata_entries.virtual_disk_size_entry.offset
                                           + s->metadata_rt.file_offset,
                     &s->virtual_disk_size,
@@ -777,7 +775,7 @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s)
    if (ret < 0) {
        goto exit;
    }
-    ret = bdrv_pread(bs->file->bs,
+    ret = bdrv_pread(bs->file,
                     s->metadata_entries.logical_sector_size_entry.offset
                                             + s->metadata_rt.file_offset,
                     &s->logical_sector_size,
@@ -785,7 +783,7 @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s)
    if (ret < 0) {
        goto exit;
    }
-    ret = bdrv_pread(bs->file->bs,
+    ret = bdrv_pread(bs->file,
                     s->metadata_entries.phys_sector_size_entry.offset
                                          + s->metadata_rt.file_offset,
                     &s->physical_sector_size,
@@ -908,7 +906,7 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
    QLIST_INIT(&s->regions);

    /* validate the file signature */
-    ret = bdrv_pread(bs->file->bs, 0, &signature, sizeof(uint64_t));
+    ret = bdrv_pread(bs->file, 0, &signature, sizeof(uint64_t));
    if (ret < 0) {
        goto fail;
    }
@@ -961,13 +959,13 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
    }

    /* s->bat is freed in vhdx_close() */
-    s->bat = qemu_try_blockalign(bs->file->bs, s->bat_rt.length);
+    s->bat = qemu_try_blockalign(bs->file, s->bat_rt.length);
    if (s->bat == NULL) {
        ret = -ENOMEM;
        goto fail;
    }

-    ret = bdrv_pread(bs->file->bs, s->bat_offset, s->bat, s->bat_rt.length);
+    ret = bdrv_pread(bs->file, s->bat_offset, s->bat, s->bat_rt.length);
    if (ret < 0) {
        goto fail;
    }
@@ -1004,9 +1002,9 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
    /* TODO: differencing files */

    /* Disable migration when VHDX images are used */
-    error_setg(&s->migration_blocker, "The vhdx format used by node '%s' "
-               "does not support live migration",
-               bdrv_get_device_or_node_name(bs));
+    error_set(&s->migration_blocker,
+            QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
+            "vhdx", bdrv_get_device_name(bs), "live migration");
    migrate_add_blocker(s->migration_blocker);

    return 0;
@@ -1111,16 +1109,15 @@ static coroutine_fn int vhdx_co_readv(BlockDriverState *bs, int64_t sector_num,
            /* check the payload block state */
            switch (s->bat[sinfo.bat_idx] & VHDX_BAT_STATE_BIT_MASK) {
            case PAYLOAD_BLOCK_NOT_PRESENT: /* fall through */
-            case PAYLOAD_BLOCK_UNDEFINED:
-            case PAYLOAD_BLOCK_UNMAPPED:
-            case PAYLOAD_BLOCK_UNMAPPED_v095:
+            case PAYLOAD_BLOCK_UNDEFINED:   /* fall through */
+            case PAYLOAD_BLOCK_UNMAPPED:    /* fall through */
            case PAYLOAD_BLOCK_ZERO:
                /* return zero */
                qemu_iovec_memset(&hd_qiov, 0, 0, sinfo.bytes_avail);
                break;
            case PAYLOAD_BLOCK_FULLY_PRESENT:
                qemu_co_mutex_unlock(&s->lock);
-                ret = bdrv_co_readv(bs->file->bs,
+                ret = bdrv_co_readv(bs->file,
                                    sinfo.file_offset >> BDRV_SECTOR_BITS,
                                    sinfo.sectors_avail, &hd_qiov);
                qemu_co_mutex_lock(&s->lock);
@@ -1158,12 +1155,12 @@ exit:
 static int vhdx_allocate_block(BlockDriverState *bs, BDRVVHDXState *s,
                                    uint64_t *new_offset)
 {
-    *new_offset = bdrv_getlength(bs->file->bs);
+    *new_offset = bdrv_getlength(bs->file);

    /* per the spec, the address for a block is in units of 1MB */
    *new_offset = ROUND_UP(*new_offset, 1024 * 1024);

-    return bdrv_truncate(bs->file->bs, *new_offset + s->block_size);
+    return bdrv_truncate(bs->file, *new_offset + s->block_size);
 }

 /*
@@ -1176,18 +1173,7 @@ static void vhdx_update_bat_table_entry(BlockDriverState *bs, BDRVVHDXState *s,
 {
    /* The BAT entry is a uint64, with 44 bits for the file offset in units of
     * 1MB, and 3 bits for the block state. */
-    if ((state == PAYLOAD_BLOCK_ZERO)        ||
-        (state == PAYLOAD_BLOCK_UNDEFINED)   ||
-        (state == PAYLOAD_BLOCK_NOT_PRESENT) ||
-        (state == PAYLOAD_BLOCK_UNMAPPED)) {
-        s->bat[sinfo->bat_idx]  = 0;  /* For PAYLOAD_BLOCK_ZERO, the
-                                         FileOffsetMB field is denoted as
-                                         'reserved' in the v1.0 spec.  If it is
-                                         non-zero, MS Hyper-V will fail to read
-                                         the disk image */
-    } else {
-        s->bat[sinfo->bat_idx]  = sinfo->file_offset;
-    }
+    s->bat[sinfo->bat_idx]  = sinfo->file_offset;

    s->bat[sinfo->bat_idx] |= state & VHDX_BAT_STATE_BIT_MASK;

@@ -1262,7 +1248,7 @@ static coroutine_fn int vhdx_co_writev(BlockDriverState *bs, int64_t sector_num,
                /* Queue another write of zero buffers if the underlying file
                 * does not zero-fill on file extension */

-                if (bdrv_has_zero_init(bs->file->bs) == 0) {
+                if (bdrv_has_zero_init(bs->file) == 0) {
                    use_zero_buffers = true;

                    /* zero fill the front, if any */
@@ -1271,7 +1257,7 @@ static coroutine_fn int vhdx_co_writev(BlockDriverState *bs, int64_t sector_num,
                        iov1.iov_base = qemu_blockalign(bs, iov1.iov_len);
                        memset(iov1.iov_base, 0, iov1.iov_len);
                        qemu_iovec_concat_iov(&hd_qiov, &iov1, 1, 0,
-                                              iov1.iov_len);
+                                              sinfo.block_offset);
                        sectors_to_write += iov1.iov_len >> BDRV_SECTOR_BITS;
                    }

@@ -1287,15 +1273,15 @@ static coroutine_fn int vhdx_co_writev(BlockDriverState *bs, int64_t sector_num,
                        iov2.iov_base = qemu_blockalign(bs, iov2.iov_len);
                        memset(iov2.iov_base, 0, iov2.iov_len);
                        qemu_iovec_concat_iov(&hd_qiov, &iov2, 1, 0,
-                                              iov2.iov_len);
+                                              sinfo.block_offset);
                        sectors_to_write += iov2.iov_len >> BDRV_SECTOR_BITS;
                    }
                }
+
                /* fall through */
            case PAYLOAD_BLOCK_NOT_PRESENT: /* fall through */
-            case PAYLOAD_BLOCK_UNMAPPED:
-            case PAYLOAD_BLOCK_UNMAPPED_v095:
-            case PAYLOAD_BLOCK_UNDEFINED:
+            case PAYLOAD_BLOCK_UNMAPPED:    /* fall through */
+            case PAYLOAD_BLOCK_UNDEFINED:   /* fall through */
                bat_prior_offset = sinfo.file_offset;
                ret = vhdx_allocate_block(bs, s, &sinfo.file_offset);
                if (ret < 0) {
@@ -1329,7 +1315,7 @@ static coroutine_fn int vhdx_co_writev(BlockDriverState *bs, int64_t sector_num,
                }
                /* block exists, so we can just overwrite it */
                qemu_co_mutex_unlock(&s->lock);
-                ret = bdrv_co_writev(bs->file->bs,
+                ret = bdrv_co_writev(bs->file,
                                    sinfo.file_offset >> BDRV_SECTOR_BITS,
                                    sectors_to_write, &hd_qiov);
                qemu_co_mutex_lock(&s->lock);
@@ -1456,7 +1442,7 @@ static int vhdx_create_new_metadata(BlockDriverState *bs,
    uint32_t offset = 0;
    void *buffer = NULL;
    void *entry_buffer;
-    VHDXMetadataTableHeader *md_table;
+    VHDXMetadataTableHeader *md_table;;
    VHDXMetadataTableEntry  *md_table_entry;

    /* Metadata entries */
@@ -1787,7 +1773,7 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
    log_size = qemu_opt_get_size_del(opts, VHDX_BLOCK_OPT_LOG_SIZE, 0);
    block_size = qemu_opt_get_size_del(opts, VHDX_BLOCK_OPT_BLOCK_SIZE, 0);
    type = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT);
-    use_zero_blocks = qemu_opt_get_bool_del(opts, VHDX_BLOCK_OPT_ZERO, true);
+    use_zero_blocks = qemu_opt_get_bool_del(opts, VHDX_BLOCK_OPT_ZERO, false);

    if (image_size > VHDX_MAX_IMAGE_SIZE) {
        error_setg_errno(errp, EINVAL, "Image size too large; max of 64TB");
@@ -1844,7 +1830,7 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)

    bs = NULL;
    ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
-                    &local_err);
+                    NULL, &local_err);
    if (ret < 0) {
        error_propagate(errp, local_err);
        goto exit;
@@ -1949,9 +1935,7 @@ static QemuOptsList vhdx_create_opts = {
       {
           .name = VHDX_BLOCK_OPT_ZERO,
           .type = QEMU_OPT_BOOL,
-           .help = "Force use of payload blocks of type 'ZERO'. "\
-                   "Non-standard, but default.  Do not set to 'off' when "\
-                   "using 'qemu-img convert' with subformat=dynamic."
+           .help = "Force use of payload blocks of type 'ZERO'.  Non-standard."
       },
       { NULL }
    }
@@ -1969,7 +1953,6 @@ static BlockDriver bdrv_vhdx = {
    .bdrv_create            = vhdx_create,
    .bdrv_get_info          = vhdx_get_info,
    .bdrv_check             = vhdx_check,
-    .bdrv_has_zero_init     = bdrv_has_zero_init_1,

    .create_opts            = &vhdx_create_opts,
 };
@@ -226,8 +226,7 @@ typedef struct QEMU_PACKED VHDXLogDataSector {
 #define PAYLOAD_BLOCK_NOT_PRESENT       0
 #define PAYLOAD_BLOCK_UNDEFINED         1
 #define PAYLOAD_BLOCK_ZERO              2
-#define PAYLOAD_BLOCK_UNMAPPED          3
-#define PAYLOAD_BLOCK_UNMAPPED_v095     5
+#define PAYLOAD_BLOCK_UNMAPPED          5
 #define PAYLOAD_BLOCK_FULLY_PRESENT     6
 #define PAYLOAD_BLOCK_PARTIALLY_PRESENT 7

@@ -25,12 +25,9 @@

 #include "qemu-common.h"
 #include "block/block_int.h"
-#include "qapi/qmp/qerror.h"
-#include "qemu/error-report.h"
 #include "qemu/module.h"
 #include "migration/migration.h"
 #include <zlib.h>
-#include <glib.h>

 #define VMDK3_MAGIC (('C' << 24) | ('O' << 16) | ('W' << 8) | 'D')
 #define VMDK4_MAGIC (('K' << 24) | ('D' << 16) | ('M' << 8) | 'V')
@@ -87,7 +84,7 @@ typedef struct {
 #define L2_CACHE_SIZE 16

 typedef struct VmdkExtent {
-    BdrvChild *file;
+    BlockDriverState *file;
    bool flat;
    bool compressed;
    bool has_marker;
@@ -222,7 +219,7 @@ static void vmdk_free_extents(BlockDriverState *bs)
        g_free(e->l1_backup_table);
        g_free(e->type);
        if (e->file != bs->file) {
-            bdrv_unref_child(bs, e->file);
+            bdrv_unref(e->file);
        }
    }
    g_free(s->extents);
@@ -248,7 +245,7 @@ static uint32_t vmdk_read_cid(BlockDriverState *bs, int parent)
    BDRVVmdkState *s = bs->opaque;
    int ret;

-    ret = bdrv_pread(bs->file->bs, s->desc_offset, desc, DESC_SIZE);
+    ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE);
    if (ret < 0) {
        return 0;
    }
@@ -278,7 +275,7 @@ static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid)
    BDRVVmdkState *s = bs->opaque;
    int ret;

-    ret = bdrv_pread(bs->file->bs, s->desc_offset, desc, DESC_SIZE);
+    ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE);
    if (ret < 0) {
        return ret;
    }
@@ -297,7 +294,7 @@ static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid)
        pstrcat(desc, sizeof(desc), tmp_desc);
    }

-    ret = bdrv_pwrite_sync(bs->file->bs, s->desc_offset, desc, DESC_SIZE);
+    ret = bdrv_pwrite_sync(bs->file, s->desc_offset, desc, DESC_SIZE);
    if (ret < 0) {
        return ret;
    }
@@ -308,11 +305,10 @@ static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid)
 static int vmdk_is_cid_valid(BlockDriverState *bs)
 {
    BDRVVmdkState *s = bs->opaque;
+    BlockDriverState *p_bs = bs->backing_hd;
    uint32_t cur_pcid;

-    if (!s->cid_checked && bs->backing) {
-        BlockDriverState *p_bs = bs->backing->bs;
-
+    if (!s->cid_checked && p_bs) {
        cur_pcid = vmdk_read_cid(p_bs, 0);
        if (s->parent_cid != cur_pcid) {
            /* CID not valid */
@@ -324,13 +320,37 @@ static int vmdk_is_cid_valid(BlockDriverState *bs)
    return 1;
 }

-/* We have nothing to do for VMDK reopen, stubs just return success */
+/* Queue extents, if any, for reopen() */
 static int vmdk_reopen_prepare(BDRVReopenState *state,
                               BlockReopenQueue *queue, Error **errp)
 {
+    BDRVVmdkState *s;
+    int ret = -1;
+    int i;
+    VmdkExtent *e;
+
    assert(state != NULL);
    assert(state->bs != NULL);
-    return 0;
+
+    if (queue == NULL) {
+        error_setg(errp, "No reopen queue for VMDK extents");
+        goto exit;
+    }
+
+    s = state->bs->opaque;
+
+    assert(s != NULL);
+
+    for (i = 0; i < s->num_extents; i++) {
+        e = &s->extents[i];
+        if (e->file != state->bs->file) {
+            bdrv_reopen_queue(queue, e->file, state->flags);
+        }
+    }
+    ret = 0;
+
+exit:
+    return ret;
 }

 static int vmdk_parent_open(BlockDriverState *bs)
@@ -341,7 +361,7 @@ static int vmdk_parent_open(BlockDriverState *bs)
    int ret;

    desc[DESC_SIZE] = '\0';
-    ret = bdrv_pread(bs->file->bs, s->desc_offset, desc, DESC_SIZE);
+    ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE);
    if (ret < 0) {
        return ret;
    }
@@ -368,7 +388,7 @@ static int vmdk_parent_open(BlockDriverState *bs)
 /* Create and append extent to the extent array. Return the added VmdkExtent
 * address. return NULL if allocation failed. */
 static int vmdk_add_extent(BlockDriverState *bs,
-                           BdrvChild *file, bool flat, int64_t sectors,
+                           BlockDriverState *file, bool flat, int64_t sectors,
                           int64_t l1_offset, int64_t l1_backup_offset,
                           uint32_t l1_size,
                           int l2_size, uint64_t cluster_sectors,
@@ -393,7 +413,7 @@ static int vmdk_add_extent(BlockDriverState *bs,
        return -EFBIG;
    }

-    nb_sectors = bdrv_nb_sectors(file->bs);
+    nb_sectors = bdrv_nb_sectors(file);
    if (nb_sectors < 0) {
        return nb_sectors;
    }
@@ -430,8 +450,7 @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,
                            Error **errp)
 {
    int ret;
-    size_t l1_size;
-    int i;
+    int l1_size, i;

    /* read the L1 table */
    l1_size = extent->l1_size * sizeof(uint32_t);
@@ -440,14 +459,14 @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,
        return -ENOMEM;
    }

-    ret = bdrv_pread(extent->file->bs,
+    ret = bdrv_pread(extent->file,
                     extent->l1_table_offset,
                     extent->l1_table,
                     l1_size);
    if (ret < 0) {
        error_setg_errno(errp, -ret,
                         "Could not read l1 table from extent '%s'",
-                         extent->file->bs->filename);
+                         extent->file->filename);
        goto fail_l1;
    }
    for (i = 0; i < extent->l1_size; i++) {
@@ -460,14 +479,14 @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,
            ret = -ENOMEM;
            goto fail_l1;
        }
-        ret = bdrv_pread(extent->file->bs,
+        ret = bdrv_pread(extent->file,
                         extent->l1_backup_table_offset,
                         extent->l1_backup_table,
                         l1_size);
        if (ret < 0) {
            error_setg_errno(errp, -ret,
                             "Could not read l1 backup table from extent '%s'",
-                             extent->file->bs->filename);
+                             extent->file->filename);
            goto fail_l1b;
        }
        for (i = 0; i < extent->l1_size; i++) {
@@ -486,7 +505,7 @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,
 }

 static int vmdk_open_vmfs_sparse(BlockDriverState *bs,
-                                 BdrvChild *file,
+                                 BlockDriverState *file,
                                 int flags, Error **errp)
 {
    int ret;
@@ -494,16 +513,16 @@ static int vmdk_open_vmfs_sparse(BlockDriverState *bs,
    VMDK3Header header;
    VmdkExtent *extent;

-    ret = bdrv_pread(file->bs, sizeof(magic), &header, sizeof(header));
+    ret = bdrv_pread(file, sizeof(magic), &header, sizeof(header));
    if (ret < 0) {
        error_setg_errno(errp, -ret,
                         "Could not read header from file '%s'",
-                         file->bs->filename);
+                         file->filename);
        return ret;
    }
    ret = vmdk_add_extent(bs, file, false,
                          le32_to_cpu(header.disk_sectors),
-                          (int64_t)le32_to_cpu(header.l1dir_offset) << 9,
+                          le32_to_cpu(header.l1dir_offset) << 9,
                          0,
                          le32_to_cpu(header.l1dir_size),
                          4096,
@@ -522,7 +541,7 @@ static int vmdk_open_vmfs_sparse(BlockDriverState *bs,
 }

 static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
-                               QDict *options, Error **errp);
+                               Error **errp);

 static char *vmdk_read_desc(BlockDriverState *file, uint64_t desc_offset,
                            Error **errp)
@@ -537,16 +556,8 @@ static char *vmdk_read_desc(BlockDriverState *file, uint64_t desc_offset,
        return NULL;
    }

-    if (size < 4) {
-        /* Both descriptor file and sparse image must be much larger than 4
-         * bytes, also callers of vmdk_read_desc want to compare the first 4
-         * bytes with VMDK4_MAGIC, let's error out if less is read. */
-        error_setg(errp, "File is too small, not a valid image");
-        return NULL;
-    }
-
-    size = MIN(size, (1 << 20) - 1);  /* avoid unbounded allocation */
-    buf = g_malloc(size + 1);
+    size = MIN(size, 1 << 20);  /* avoid unbounded allocation */
+    buf = g_malloc0(size + 1);

    ret = bdrv_pread(file, desc_offset, buf, size);
    if (ret < 0) {
@@ -554,14 +565,13 @@ static char *vmdk_read_desc(BlockDriverState *file, uint64_t desc_offset,
        g_free(buf);
        return NULL;
    }
-    buf[ret] = 0;

    return buf;
 }

 static int vmdk_open_vmdk4(BlockDriverState *bs,
-                           BdrvChild *file,
-                           int flags, QDict *options, Error **errp)
+                           BlockDriverState *file,
+                           int flags, Error **errp)
 {
    int ret;
    uint32_t magic;
@@ -571,21 +581,21 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
    BDRVVmdkState *s = bs->opaque;
    int64_t l1_backup_offset = 0;

-    ret = bdrv_pread(file->bs, sizeof(magic), &header, sizeof(header));
+    ret = bdrv_pread(file, sizeof(magic), &header, sizeof(header));
    if (ret < 0) {
        error_setg_errno(errp, -ret,
                         "Could not read header from file '%s'",
-                         file->bs->filename);
+                         file->filename);
        return -EINVAL;
    }
    if (header.capacity == 0) {
        uint64_t desc_offset = le64_to_cpu(header.desc_offset);
        if (desc_offset) {
-            char *buf = vmdk_read_desc(file->bs, 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, options, errp);
+            ret = vmdk_open_desc_file(bs, flags, buf, errp);
            g_free(buf);
            return ret;
        }
@@ -621,11 +631,10 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
            } QEMU_PACKED eos_marker;
        } QEMU_PACKED footer;

-        ret = bdrv_pread(file->bs,
-            bs->file->bs->total_sectors * 512 - 1536,
+        ret = bdrv_pread(file,
+            bs->file->total_sectors * 512 - 1536,
            &footer, sizeof(footer));
        if (ret < 0) {
-            error_setg_errno(errp, -ret, "Failed to read footer");
            return ret;
        }

@@ -637,7 +646,6 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
            le32_to_cpu(footer.eos_marker.size) != 0  ||
            le32_to_cpu(footer.eos_marker.type) != MARKER_END_OF_STREAM)
        {
-            error_setg(errp, "Invalid footer");
            return -EINVAL;
        }

@@ -648,8 +656,8 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
        char buf[64];
        snprintf(buf, sizeof(buf), "VMDK version %" PRId32,
                 le32_to_cpu(header.version));
-        error_setg(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
-                   bdrv_get_device_or_node_name(bs), "vmdk", buf);
+        error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+                  bdrv_get_device_name(bs), "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
@@ -668,7 +676,6 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
    l1_entry_sectors = le32_to_cpu(header.num_gtes_per_gt)
                        * le64_to_cpu(header.granularity);
    if (l1_entry_sectors == 0) {
-        error_setg(errp, "L1 entry size is invalid");
        return -EINVAL;
    }
    l1_size = (le64_to_cpu(header.capacity) + l1_entry_sectors - 1)
@@ -676,7 +683,7 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
    if (le32_to_cpu(header.flags) & VMDK4_FLAG_RGD) {
        l1_backup_offset = le64_to_cpu(header.rgd_offset) << 9;
    }
-    if (bdrv_nb_sectors(file->bs) < le64_to_cpu(header.grain_offset)) {
+    if (bdrv_nb_sectors(file) < le64_to_cpu(header.grain_offset)) {
        error_setg(errp, "File truncated, expecting at least %" PRId64 " bytes",
                   (int64_t)(le64_to_cpu(header.grain_offset)
                             * BDRV_SECTOR_SIZE));
@@ -740,8 +747,9 @@ 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, BdrvChild *file, int flags,
-                            char *buf, QDict *options, Error **errp)
+static int vmdk_open_sparse(BlockDriverState *bs,
+                            BlockDriverState *file, int flags,
+                            char *buf, Error **errp)
 {
    uint32_t magic;

@@ -751,7 +759,7 @@ static int vmdk_open_sparse(BlockDriverState *bs, BdrvChild *file, int flags,
            return vmdk_open_vmfs_sparse(bs, file, flags, errp);
            break;
        case VMDK4_MAGIC:
-            return vmdk_open_vmdk4(bs, file, flags, options, errp);
+            return vmdk_open_vmdk4(bs, file, flags, errp);
            break;
        default:
            error_setg(errp, "Image not in VMDK format");
@@ -761,50 +769,44 @@ static int vmdk_open_sparse(BlockDriverState *bs, BdrvChild *file, int flags,
 }

 static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
-                              const char *desc_file_path, QDict *options,
-                              Error **errp)
+                              const char *desc_file_path, Error **errp)
 {
    int ret;
-    int matches;
    char access[11];
    char type[11];
    char fname[512];
    const char *p = desc;
    int64_t sectors = 0;
    int64_t flat_offset;
-    char *extent_path;
-    BdrvChild *extent_file;
+    char extent_path[PATH_MAX];
+    BlockDriverState *extent_file;
    BDRVVmdkState *s = bs->opaque;
    VmdkExtent *extent;
-    char extent_opt_prefix[32];
-    Error *local_err = NULL;

    while (*p) {
-        /* parse extent line in one of below formats:
-         *
+        /* parse extent line:
         * RW [size in sectors] FLAT "file-name.vmdk" OFFSET
+         * or
         * RW [size in sectors] SPARSE "file-name.vmdk"
-         * RW [size in sectors] VMFS "file-name.vmdk"
-         * RW [size in sectors] VMFSSPARSE "file-name.vmdk"
         */
        flat_offset = -1;
-        matches = sscanf(p, "%10s %" SCNd64 " %10s \"%511[^\n\r\"]\" %" SCNd64,
-                         access, &sectors, type, fname, &flat_offset);
-        if (matches < 4 || strcmp(access, "RW")) {
+        ret = sscanf(p, "%10s %" SCNd64 " %10s \"%511[^\n\r\"]\" %" SCNd64,
+                access, &sectors, type, fname, &flat_offset);
+        if (ret < 4 || strcmp(access, "RW")) {
            goto next_line;
        } else if (!strcmp(type, "FLAT")) {
-            if (matches != 5 || flat_offset < 0) {
+            if (ret != 5 || flat_offset < 0) {
                error_setg(errp, "Invalid extent lines: \n%s", p);
                return -EINVAL;
            }
        } else if (!strcmp(type, "VMFS")) {
-            if (matches == 4) {
+            if (ret == 4) {
                flat_offset = 0;
            } else {
                error_setg(errp, "Invalid extent lines:\n%s", p);
                return -EINVAL;
            }
-        } else if (matches != 4) {
+        } else if (ret != 4) {
            error_setg(errp, "Invalid extent lines:\n%s", p);
            return -EINVAL;
        }
@@ -816,26 +818,13 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
            goto next_line;
        }

-        if (!path_is_absolute(fname) && !path_has_protocol(fname) &&
-            !desc_file_path[0])
-        {
-            error_setg(errp, "Cannot use relative extent paths with VMDK "
-                       "descriptor file '%s'", bs->file->bs->filename);
-            return -EINVAL;
-        }
-
-        extent_path = g_malloc0(PATH_MAX);
-        path_combine(extent_path, PATH_MAX, desc_file_path, fname);
-
-        ret = snprintf(extent_opt_prefix, 32, "extents.%d", s->num_extents);
-        assert(ret < 32);
-
-        extent_file = bdrv_open_child(extent_path, options, extent_opt_prefix,
-                                      bs, &child_file, false, &local_err);
-        g_free(extent_path);
-        if (local_err) {
-            error_propagate(errp, local_err);
-            return -EINVAL;
+        path_combine(extent_path, sizeof(extent_path),
+                desc_file_path, fname);
+        extent_file = NULL;
+        ret = bdrv_open(&extent_file, extent_path, NULL, NULL,
+                        bs->open_flags | BDRV_O_PROTOCOL, NULL, errp);
+        if (ret) {
+            return ret;
        }

        /* save to extents array */
@@ -845,28 +834,27 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
            ret = vmdk_add_extent(bs, extent_file, true, sectors,
                            0, 0, 0, 0, 0, &extent, errp);
            if (ret < 0) {
-                bdrv_unref_child(bs, extent_file);
+                bdrv_unref(extent_file);
                return ret;
            }
            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*/
-            char *buf = vmdk_read_desc(extent_file->bs, 0, 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,
-                                       options, errp);
+                ret = vmdk_open_sparse(bs, extent_file, bs->open_flags, buf, errp);
            }
            g_free(buf);
            if (ret) {
-                bdrv_unref_child(bs, extent_file);
+                bdrv_unref(extent_file);
                return ret;
            }
            extent = &s->extents[s->num_extents - 1];
        } else {
            error_setg(errp, "Unsupported extent type '%s'", type);
-            bdrv_unref_child(bs, extent_file);
+            bdrv_unref(extent_file);
            return -ENOTSUP;
        }
        extent->type = g_strdup(type);
@@ -884,7 +872,7 @@ next_line:
 }

 static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
-                               QDict *options, Error **errp)
+                               Error **errp)
 {
    int ret;
    char ct[128];
@@ -906,8 +894,7 @@ static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
    }
    s->create_type = g_strdup(ct);
    s->desc_offset = 0;
-    ret = vmdk_parse_extents(buf, bs, bs->file->bs->exact_filename, options,
-                             errp);
+    ret = vmdk_parse_extents(buf, bs, bs->file->filename, errp);
 exit:
    return ret;
 }
@@ -915,12 +902,12 @@ exit:
 static int vmdk_open(BlockDriverState *bs, QDict *options, int flags,
                     Error **errp)
 {
-    char *buf;
+    char *buf = NULL;
    int ret;
    BDRVVmdkState *s = bs->opaque;
    uint32_t magic;

-    buf = vmdk_read_desc(bs->file->bs, 0, errp);
+    buf = vmdk_read_desc(bs->file, 0, errp);
    if (!buf) {
        return -EINVAL;
    }
@@ -929,12 +916,11 @@ static int vmdk_open(BlockDriverState *bs, QDict *options, int flags,
    switch (magic) {
        case VMDK3_MAGIC:
        case VMDK4_MAGIC:
-            ret = vmdk_open_sparse(bs, bs->file, flags, buf, options,
-                                   errp);
+            ret = vmdk_open_sparse(bs, bs->file, flags, buf, errp);
            s->desc_offset = 0x200;
            break;
        default:
-            ret = vmdk_open_desc_file(bs, flags, buf, options, errp);
+            ret = vmdk_open_desc_file(bs, flags, buf, errp);
            break;
    }
    if (ret) {
@@ -951,9 +937,9 @@ static int vmdk_open(BlockDriverState *bs, QDict *options, int flags,
    qemu_co_mutex_init(&s->lock);

    /* Disable migration when VMDK images are used */
-    error_setg(&s->migration_blocker, "The vmdk format used by node '%s' "
-               "does not support live migration",
-               bdrv_get_device_or_node_name(bs));
+    error_set(&s->migration_blocker,
+              QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
+              "vmdk", bdrv_get_device_name(bs), "live migration");
    migrate_add_blocker(s->migration_blocker);
    g_free(buf);
    return 0;
@@ -1007,7 +993,7 @@ static int get_whole_cluster(BlockDriverState *bs,
    cluster_bytes = extent->cluster_sectors << BDRV_SECTOR_BITS;
    whole_grain = qemu_blockalign(bs, cluster_bytes);

-    if (!bs->backing) {
+    if (!bs->backing_hd) {
        memset(whole_grain, 0,  skip_start_sector << BDRV_SECTOR_BITS);
        memset(whole_grain + (skip_end_sector << BDRV_SECTOR_BITS), 0,
               cluster_bytes - (skip_end_sector << BDRV_SECTOR_BITS));
@@ -1016,22 +1002,22 @@ static int get_whole_cluster(BlockDriverState *bs,
    assert(skip_end_sector <= extent->cluster_sectors);
    /* we will be here if it's first write on non-exist grain(cluster).
     * try to read from parent image, if exist */
-    if (bs->backing && !vmdk_is_cid_valid(bs)) {
+    if (bs->backing_hd && !vmdk_is_cid_valid(bs)) {
        ret = VMDK_ERROR;
        goto exit;
    }

    /* Read backing data before skip range */
    if (skip_start_sector > 0) {
-        if (bs->backing) {
-            ret = bdrv_read(bs->backing->bs, sector_num,
+        if (bs->backing_hd) {
+            ret = bdrv_read(bs->backing_hd, sector_num,
                            whole_grain, skip_start_sector);
            if (ret < 0) {
                ret = VMDK_ERROR;
                goto exit;
            }
        }
-        ret = bdrv_write(extent->file->bs, cluster_sector_num, whole_grain,
+        ret = bdrv_write(extent->file, cluster_sector_num, whole_grain,
                         skip_start_sector);
        if (ret < 0) {
            ret = VMDK_ERROR;
@@ -1040,8 +1026,8 @@ static int get_whole_cluster(BlockDriverState *bs,
    }
    /* Read backing data after skip range */
    if (skip_end_sector < extent->cluster_sectors) {
-        if (bs->backing) {
-            ret = bdrv_read(bs->backing->bs, sector_num + skip_end_sector,
+        if (bs->backing_hd) {
+            ret = bdrv_read(bs->backing_hd, sector_num + skip_end_sector,
                            whole_grain + (skip_end_sector << BDRV_SECTOR_BITS),
                            extent->cluster_sectors - skip_end_sector);
            if (ret < 0) {
@@ -1049,7 +1035,7 @@ static int get_whole_cluster(BlockDriverState *bs,
                goto exit;
            }
        }
-        ret = bdrv_write(extent->file->bs, cluster_sector_num + skip_end_sector,
+        ret = bdrv_write(extent->file, cluster_sector_num + skip_end_sector,
                         whole_grain + (skip_end_sector << BDRV_SECTOR_BITS),
                         extent->cluster_sectors - skip_end_sector);
        if (ret < 0) {
@@ -1069,7 +1055,7 @@ static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data,
    offset = cpu_to_le32(offset);
    /* update L2 table */
    if (bdrv_pwrite_sync(
-                extent->file->bs,
+                extent->file,
                ((int64_t)m_data->l2_offset * 512)
                    + (m_data->l2_index * sizeof(offset)),
                &offset, sizeof(offset)) < 0) {
@@ -1079,7 +1065,7 @@ static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data,
    if (extent->l1_backup_table_offset != 0) {
        m_data->l2_offset = extent->l1_backup_table[m_data->l1_index];
        if (bdrv_pwrite_sync(
-                    extent->file->bs,
+                    extent->file,
                    ((int64_t)m_data->l2_offset * 512)
                        + (m_data->l2_index * sizeof(offset)),
                    &offset, sizeof(offset)) < 0) {
@@ -1169,7 +1155,7 @@ static int get_cluster_offset(BlockDriverState *bs,
    }
    l2_table = extent->l2_cache + (min_index * extent->l2_size);
    if (bdrv_pread(
-                extent->file->bs,
+                extent->file,
                (int64_t)l2_offset * 512,
                l2_table,
                extent->l2_size * sizeof(uint32_t)
@@ -1236,17 +1222,6 @@ static VmdkExtent *find_extent(BDRVVmdkState *s,
    return NULL;
 }

-static inline uint64_t vmdk_find_index_in_cluster(VmdkExtent *extent,
-                                                  int64_t sector_num)
-{
-    uint64_t index_in_cluster, extent_begin_sector, extent_relative_sector_num;
-
-    extent_begin_sector = extent->end_sector - extent->sectors;
-    extent_relative_sector_num = sector_num - extent_begin_sector;
-    index_in_cluster = extent_relative_sector_num % extent->cluster_sectors;
-    return index_in_cluster;
-}
-
 static int64_t coroutine_fn vmdk_co_get_block_status(BlockDriverState *bs,
        int64_t sector_num, int nb_sectors, int *pnum)
 {
@@ -1284,7 +1259,7 @@ static int64_t coroutine_fn vmdk_co_get_block_status(BlockDriverState *bs,
        break;
    }

-    index_in_cluster = vmdk_find_index_in_cluster(extent, sector_num);
+    index_in_cluster = sector_num % extent->cluster_sectors;
    n = extent->cluster_sectors - index_in_cluster;
    if (n > nb_sectors) {
        n = nb_sectors;
@@ -1302,8 +1277,6 @@ static int vmdk_write_extent(VmdkExtent *extent, int64_t cluster_offset,
    uLongf buf_len;
    const uint8_t *write_buf = buf;
    int write_len = nb_sectors * 512;
-    int64_t write_offset;
-    int64_t write_end_sector;

    if (extent->compressed) {
        if (!extent->has_marker) {
@@ -1322,18 +1295,10 @@ static int vmdk_write_extent(VmdkExtent *extent, int64_t cluster_offset,
        write_buf = (uint8_t *)data;
        write_len = buf_len + sizeof(VmdkGrainMarker);
    }
-    write_offset = cluster_offset + offset_in_cluster,
-    ret = bdrv_pwrite(extent->file->bs, write_offset, write_buf, write_len);
-
-    write_end_sector = DIV_ROUND_UP(write_offset + write_len, BDRV_SECTOR_SIZE);
-
-    if (extent->compressed) {
-        extent->next_cluster_sector = write_end_sector;
-    } else {
-        extent->next_cluster_sector = MAX(extent->next_cluster_sector,
-                                          write_end_sector);
-    }
-
+    ret = bdrv_pwrite(extent->file,
+                        cluster_offset + offset_in_cluster,
+                        write_buf,
+                        write_len);
    if (ret != write_len) {
        ret = ret < 0 ? ret : -EIO;
        goto out;
@@ -1358,7 +1323,7 @@ static int vmdk_read_extent(VmdkExtent *extent, int64_t cluster_offset,


    if (!extent->compressed) {
-        ret = bdrv_pread(extent->file->bs,
+        ret = bdrv_pread(extent->file,
                          cluster_offset + offset_in_cluster,
                          buf, nb_sectors * 512);
        if (ret == nb_sectors * 512) {
@@ -1372,7 +1337,7 @@ static int vmdk_read_extent(VmdkExtent *extent, int64_t cluster_offset,
    buf_bytes = cluster_bytes * 2;
    cluster_buf = g_malloc(buf_bytes);
    uncomp_buf = g_malloc(cluster_bytes);
-    ret = bdrv_pread(extent->file->bs,
+    ret = bdrv_pread(extent->file,
                cluster_offset,
                cluster_buf, buf_bytes);
    if (ret < 0) {
@@ -1416,6 +1381,7 @@ static int vmdk_read(BlockDriverState *bs, int64_t sector_num,
    BDRVVmdkState *s = bs->opaque;
    int ret;
    uint64_t n, index_in_cluster;
+    uint64_t extent_begin_sector, extent_relative_sector_num;
    VmdkExtent *extent = NULL;
    uint64_t cluster_offset;

@@ -1427,18 +1393,20 @@ static int vmdk_read(BlockDriverState *bs, int64_t sector_num,
        ret = get_cluster_offset(bs, extent, NULL,
                                 sector_num << 9, false, &cluster_offset,
                                 0, 0);
-        index_in_cluster = vmdk_find_index_in_cluster(extent, sector_num);
+        extent_begin_sector = extent->end_sector - extent->sectors;
+        extent_relative_sector_num = sector_num - extent_begin_sector;
+        index_in_cluster = extent_relative_sector_num % extent->cluster_sectors;
        n = extent->cluster_sectors - index_in_cluster;
        if (n > nb_sectors) {
            n = nb_sectors;
        }
        if (ret != VMDK_OK) {
            /* if not allocated, try to read from parent image, if exist */
-            if (bs->backing && ret != VMDK_ZEROED) {
+            if (bs->backing_hd && ret != VMDK_ZEROED) {
                if (!vmdk_is_cid_valid(bs)) {
                    return -EINVAL;
                }
-                ret = bdrv_read(bs->backing->bs, sector_num, buf, n);
+                ret = bdrv_read(bs->backing_hd, sector_num, buf, n);
                if (ret < 0) {
                    return ret;
                }
@@ -1489,6 +1457,7 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
    VmdkExtent *extent = NULL;
    int ret;
    int64_t index_in_cluster, n;
+    uint64_t extent_begin_sector, extent_relative_sector_num;
    uint64_t cluster_offset;
    VmdkMetaData m_data;

@@ -1504,7 +1473,9 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
        if (!extent) {
            return -EIO;
        }
-        index_in_cluster = vmdk_find_index_in_cluster(extent, sector_num);
+        extent_begin_sector = extent->end_sector - extent->sectors;
+        extent_relative_sector_num = sector_num - extent_begin_sector;
+        index_in_cluster = extent_relative_sector_num % extent->cluster_sectors;
        n = extent->cluster_sectors - index_in_cluster;
        if (n > nb_sectors) {
            n = nb_sectors;
@@ -1567,7 +1538,7 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
        /* update CID on the first write every time the virtual disk is
         * opened */
        if (!s->cid_updated) {
-            ret = vmdk_write_cid(bs, g_random_int());
+            ret = vmdk_write_cid(bs, time(NULL));
            if (ret < 0) {
                return ret;
            }
@@ -1639,7 +1610,7 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,

    assert(bs == NULL);
    ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
-                    &local_err);
+                    NULL, &local_err);
    if (ret < 0) {
        error_propagate(errp, local_err);
        goto exit;
@@ -1697,12 +1668,12 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
    /* write all the data */
    ret = bdrv_pwrite(bs, 0, &magic, sizeof(magic));
    if (ret < 0) {
-        error_setg(errp, QERR_IO_ERROR);
+        error_set(errp, QERR_IO_ERROR);
        goto exit;
    }
    ret = bdrv_pwrite(bs, sizeof(magic), &header, sizeof(header));
    if (ret < 0) {
-        error_setg(errp, QERR_IO_ERROR);
+        error_set(errp, QERR_IO_ERROR);
        goto exit;
    }

@@ -1722,7 +1693,7 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
    ret = bdrv_pwrite(bs, le64_to_cpu(header.rgd_offset) * BDRV_SECTOR_SIZE,
                      gd_buf, gd_buf_size);
    if (ret < 0) {
-        error_setg(errp, QERR_IO_ERROR);
+        error_set(errp, QERR_IO_ERROR);
        goto exit;
    }

@@ -1734,7 +1705,7 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
    ret = bdrv_pwrite(bs, le64_to_cpu(header.gd_offset) * BDRV_SECTOR_SIZE,
                      gd_buf, gd_buf_size);
    if (ret < 0) {
-        error_setg(errp, QERR_IO_ERROR);
+        error_set(errp, QERR_IO_ERROR);
        goto exit;
    }

@@ -1801,15 +1772,10 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
    int ret = 0;
    bool flat, split, compress;
    GString *ext_desc_lines;
-    char *path = g_malloc0(PATH_MAX);
-    char *prefix = g_malloc0(PATH_MAX);
-    char *postfix = g_malloc0(PATH_MAX);
-    char *desc_line = g_malloc0(BUF_SIZE);
-    char *ext_filename = g_malloc0(PATH_MAX);
-    char *desc_filename = g_malloc0(PATH_MAX);
+    char path[PATH_MAX], prefix[PATH_MAX], postfix[PATH_MAX];
    const int64_t split_size = 0x80000000;  /* VMDK has constant split size */
    const char *desc_extent_line;
-    char *parent_desc_line = g_malloc0(BUF_SIZE);
+    char parent_desc_line[BUF_SIZE] = "";
    uint32_t parent_cid = 0xffffffff;
    uint32_t number_heads = 16;
    bool zeroed_grain = false;
@@ -1902,18 +1868,8 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
    }
    if (backing_file) {
        BlockDriverState *bs = NULL;
-        char *full_backing = g_new0(char, PATH_MAX);
-        bdrv_get_full_backing_filename_from_filename(filename, backing_file,
-                                                     full_backing, PATH_MAX,
-                                                     &local_err);
-        if (local_err) {
-            g_free(full_backing);
-            error_propagate(errp, local_err);
-            ret = -ENOENT;
-            goto exit;
-        }
-        ret = bdrv_open(&bs, full_backing, NULL, NULL, BDRV_O_NO_BACKING, errp);
-        g_free(full_backing);
+        ret = bdrv_open(&bs, backing_file, NULL, NULL, BDRV_O_NO_BACKING, NULL,
+                        errp);
        if (ret != 0) {
            goto exit;
        }
@@ -1924,27 +1880,33 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
        }
        parent_cid = vmdk_read_cid(bs, 0);
        bdrv_unref(bs);
-        snprintf(parent_desc_line, BUF_SIZE,
+        snprintf(parent_desc_line, sizeof(parent_desc_line),
                "parentFileNameHint=\"%s\"", backing_file);
    }

    /* Create extents */
    filesize = total_size;
    while (filesize > 0) {
+        char desc_line[BUF_SIZE];
+        char ext_filename[PATH_MAX];
+        char desc_filename[PATH_MAX];
        int64_t size = filesize;

        if (split && size > split_size) {
            size = split_size;
        }
        if (split) {
-            snprintf(desc_filename, PATH_MAX, "%s-%c%03d%s",
+            snprintf(desc_filename, sizeof(desc_filename), "%s-%c%03d%s",
                    prefix, flat ? 'f' : 's', ++idx, postfix);
        } else if (flat) {
-            snprintf(desc_filename, PATH_MAX, "%s-flat%s", prefix, postfix);
+            snprintf(desc_filename, sizeof(desc_filename), "%s-flat%s",
+                    prefix, postfix);
        } else {
-            snprintf(desc_filename, PATH_MAX, "%s%s", prefix, postfix);
+            snprintf(desc_filename, sizeof(desc_filename), "%s%s",
+                    prefix, postfix);
        }
-        snprintf(ext_filename, PATH_MAX, "%s%s", path, desc_filename);
+        snprintf(ext_filename, sizeof(ext_filename), "%s%s",
+                path, desc_filename);

        if (vmdk_create_extent(ext_filename, size,
                               flat, compress, zeroed_grain, opts, errp)) {
@@ -1954,13 +1916,13 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
        filesize -= size;

        /* Format description line */
-        snprintf(desc_line, BUF_SIZE,
+        snprintf(desc_line, sizeof(desc_line),
                    desc_extent_line, size / BDRV_SECTOR_SIZE, desc_filename);
        g_string_append(ext_desc_lines, desc_line);
    }
    /* generate descriptor file */
    desc = g_strdup_printf(desc_template,
-                           g_random_int(),
+                           (uint32_t)time(NULL),
                           parent_cid,
                           fmt,
                           parent_desc_line,
@@ -1983,7 +1945,7 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
    }
    assert(new_bs == NULL);
    ret = bdrv_open(&new_bs, filename, NULL, NULL,
-                    BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+                    BDRV_O_RDWR | BDRV_O_PROTOCOL, NULL, &local_err);
    if (ret < 0) {
        error_propagate(errp, local_err);
        goto exit;
@@ -2009,13 +1971,6 @@ exit:
    g_free(backing_file);
    g_free(fmt);
    g_free(desc);
-    g_free(path);
-    g_free(prefix);
-    g_free(postfix);
-    g_free(desc_line);
-    g_free(ext_filename);
-    g_free(desc_filename);
-    g_free(parent_desc_line);
    g_string_free(ext_desc_lines, true);
    return ret;
 }
@@ -2038,7 +1993,7 @@ static coroutine_fn int vmdk_co_flush(BlockDriverState *bs)
    int ret = 0;

    for (i = 0; i < s->num_extents; i++) {
-        err = bdrv_co_flush(s->extents[i].file->bs);
+        err = bdrv_co_flush(s->extents[i].file);
        if (err < 0) {
            ret = err;
        }
@@ -2053,7 +2008,7 @@ static int64_t vmdk_get_allocated_file_size(BlockDriverState *bs)
    int64_t r;
    BDRVVmdkState *s = bs->opaque;

-    ret = bdrv_get_allocated_file_size(bs->file->bs);
+    ret = bdrv_get_allocated_file_size(bs->file);
    if (ret < 0) {
        return ret;
    }
@@ -2061,7 +2016,7 @@ static int64_t vmdk_get_allocated_file_size(BlockDriverState *bs)
        if (s->extents[i].file == bs->file) {
            continue;
        }
-        r = bdrv_get_allocated_file_size(s->extents[i].file->bs);
+        r = bdrv_get_allocated_file_size(s->extents[i].file);
        if (r < 0) {
            return r;
        }
@@ -2079,7 +2034,7 @@ static int vmdk_has_zero_init(BlockDriverState *bs)
     * return 0. */
    for (i = 0; i < s->num_extents; i++) {
        if (s->extents[i].flat) {
-            if (!bdrv_has_zero_init(s->extents[i].file->bs)) {
+            if (!bdrv_has_zero_init(s->extents[i].file)) {
                return 0;
            }
        }
@@ -2092,7 +2047,7 @@ static ImageInfo *vmdk_get_extent_info(VmdkExtent *extent)
    ImageInfo *info = g_new0(ImageInfo, 1);

    *info = (ImageInfo){
-        .filename         = g_strdup(extent->file->bs->filename),
+        .filename         = g_strdup(extent->file->filename),
        .format           = g_strdup(extent->type),
        .virtual_size     = extent->sectors * BDRV_SECTOR_SIZE,
        .compressed       = extent->compressed,
@@ -2138,9 +2093,7 @@ static int vmdk_check(BlockDriverState *bs, BdrvCheckResult *result,
                    PRId64 "\n", sector_num);
            break;
        }
-        if (ret == VMDK_OK &&
-            cluster_offset >= bdrv_getlength(extent->file->bs))
-        {
+        if (ret == VMDK_OK && cluster_offset >= bdrv_getlength(extent->file)) {
            fprintf(stderr,
                    "ERROR: cluster offset for sector %"
                    PRId64 " points after EOF\n", sector_num);
@@ -2161,19 +2114,19 @@ static ImageInfoSpecific *vmdk_get_specific_info(BlockDriverState *bs)
    ImageInfoList **next;

    *spec_info = (ImageInfoSpecific){
-        .type = IMAGE_INFO_SPECIFIC_KIND_VMDK,
+        .kind = IMAGE_INFO_SPECIFIC_KIND_VMDK,
        {
            .vmdk = g_new0(ImageInfoSpecificVmdk, 1),
        },
    };

-    *spec_info->u.vmdk = (ImageInfoSpecificVmdk) {
+    *spec_info->vmdk = (ImageInfoSpecificVmdk) {
        .create_type = g_strdup(s->create_type),
        .cid = s->cid,
        .parent_cid = s->parent_cid,
    };

-    next = &spec_info->u.vmdk->extents;
+    next = &spec_info->vmdk->extents;
    for (i = 0; i < s->num_extents; i++) {
        *next = g_new0(ImageInfoList, 1);
        (*next)->value = vmdk_get_extent_info(&s->extents[i]);
@@ -2216,7 +2169,7 @@ static void vmdk_detach_aio_context(BlockDriverState *bs)
    int i;

    for (i = 0; i < s->num_extents; i++) {
-        bdrv_detach_aio_context(s->extents[i].file->bs);
+        bdrv_detach_aio_context(s->extents[i].file);
    }
 }

@@ -2227,7 +2180,7 @@ static void vmdk_attach_aio_context(BlockDriverState *bs,
    int i;

    for (i = 0; i < s->num_extents; i++) {
-        bdrv_attach_aio_context(s->extents[i].file->bs, new_context);
+        bdrv_attach_aio_context(s->extents[i].file, new_context);
    }
 }

@@ -46,7 +46,6 @@ enum vhd_type {
 #define VHD_TIMESTAMP_BASE 946684800

 #define VHD_MAX_SECTORS       (65535LL * 255 * 255)
-#define VHD_MAX_GEOMETRY      (65535LL *  16 * 255)

 // always big-endian
 typedef struct vhd_footer {
@@ -66,7 +65,7 @@ typedef struct vhd_footer {
    char        creator_os[4]; // "Wi2k"

    uint64_t    orig_size;
-    uint64_t    current_size;
+    uint64_t    size;

    uint16_t    cyls;
    uint8_t     heads;
@@ -168,18 +167,17 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
    uint8_t buf[HEADER_SIZE];
    uint32_t checksum;
    uint64_t computed_size;
-    uint64_t pagetable_size;
    int disk_type = VHD_DYNAMIC;
    int ret;

-    ret = bdrv_pread(bs->file->bs, 0, s->footer_buf, HEADER_SIZE);
+    ret = bdrv_pread(bs->file, 0, s->footer_buf, HEADER_SIZE);
    if (ret < 0) {
        goto fail;
    }

    footer = (VHDFooter *) s->footer_buf;
    if (strncmp(footer->creator, "conectix", 8)) {
-        int64_t offset = bdrv_getlength(bs->file->bs);
+        int64_t offset = bdrv_getlength(bs->file);
        if (offset < 0) {
            ret = offset;
            goto fail;
@@ -189,7 +187,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
        }

        /* If a fixed disk, the footer is found only at the end of the file */
-        ret = bdrv_pread(bs->file->bs, offset-HEADER_SIZE, s->footer_buf,
+        ret = bdrv_pread(bs->file, offset-HEADER_SIZE, s->footer_buf,
                         HEADER_SIZE);
        if (ret < 0) {
            goto fail;
@@ -217,12 +215,13 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
    bs->total_sectors = (int64_t)
        be16_to_cpu(footer->cyls) * footer->heads * footer->secs_per_cyl;

-    /* Images that have exactly the maximum geometry are probably bigger and
-     * would be truncated if we adhered to the geometry for them. Rely on
-     * footer->current_size for them. */
-    if (bs->total_sectors == VHD_MAX_GEOMETRY) {
-        bs->total_sectors = be64_to_cpu(footer->current_size) /
-                            BDRV_SECTOR_SIZE;
+    /* images created with disk2vhd report a far higher virtual size
+     * than expected with the cyls * heads * sectors_per_cyl formula.
+     * use the footer->size instead if the image was created with
+     * disk2vhd.
+     */
+    if (!strncmp(footer->creator_app, "d2v", 4)) {
+        bs->total_sectors = be64_to_cpu(footer->size) / BDRV_SECTOR_SIZE;
    }

    /* Allow a maximum disk size of approximately 2 TB */
@@ -232,7 +231,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
    }

    if (disk_type == VHD_DYNAMIC) {
-        ret = bdrv_pread(bs->file->bs, be64_to_cpu(footer->data_offset), buf,
+        ret = bdrv_pread(bs->file, be64_to_cpu(footer->data_offset), buf,
                         HEADER_SIZE);
        if (ret < 0) {
            goto fail;
@@ -270,17 +269,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
            goto fail;
        }

-        if (s->max_table_entries > SIZE_MAX / 4 ||
-            s->max_table_entries > (int) INT_MAX / 4) {
-            error_setg(errp, "Max Table Entries too large (%" PRId32 ")",
-                        s->max_table_entries);
-            ret = -EINVAL;
-            goto fail;
-        }
-
-        pagetable_size = (uint64_t) s->max_table_entries * 4;
-
-        s->pagetable = qemu_try_blockalign(bs->file->bs, pagetable_size);
+        s->pagetable = qemu_try_blockalign(bs->file, s->max_table_entries * 4);
        if (s->pagetable == NULL) {
            ret = -ENOMEM;
            goto fail;
@@ -288,14 +277,14 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,

        s->bat_offset = be64_to_cpu(dyndisk_header->table_offset);

-        ret = bdrv_pread(bs->file->bs, s->bat_offset, s->pagetable,
-                         pagetable_size);
+        ret = bdrv_pread(bs->file, s->bat_offset, s->pagetable,
+                         s->max_table_entries * 4);
        if (ret < 0) {
            goto fail;
        }

        s->free_data_block_offset =
-            ROUND_UP(s->bat_offset + pagetable_size, 512);
+            (s->bat_offset + (s->max_table_entries * 4) + 511) & ~511;

        for (i = 0; i < s->max_table_entries; i++) {
            be32_to_cpus(&s->pagetable[i]);
@@ -309,7 +298,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
            }
        }

-        if (s->free_data_block_offset > bdrv_getlength(bs->file->bs)) {
+        if (s->free_data_block_offset > bdrv_getlength(bs->file)) {
            error_setg(errp, "block-vpc: free_data_block_offset points after "
                             "the end of file. The image has been truncated.");
            ret = -EINVAL;
@@ -329,9 +318,9 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
    qemu_co_mutex_init(&s->lock);

    /* Disable migration when VHD images are used */
-    error_setg(&s->migration_blocker, "The vpc format used by node '%s' "
-               "does not support live migration",
-               bdrv_get_device_or_node_name(bs));
+    error_set(&s->migration_blocker,
+              QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
+              "vpc", bdrv_get_device_name(bs), "live migration");
    migrate_add_blocker(s->migration_blocker);

    return 0;
@@ -384,9 +373,41 @@ static inline int64_t get_sector_offset(BlockDriverState *bs,

        s->last_bitmap_offset = bitmap_offset;
        memset(bitmap, 0xff, s->bitmap_size);
-        bdrv_pwrite_sync(bs->file->bs, bitmap_offset, bitmap, s->bitmap_size);
+        bdrv_pwrite_sync(bs->file, bitmap_offset, bitmap, s->bitmap_size);
    }

+//    printf("sector: %" PRIx64 ", index: %x, offset: %x, bioff: %" PRIx64 ", bloff: %" PRIx64 "\n",
+//	sector_num, pagetable_index, pageentry_index,
+//	bitmap_offset, block_offset);
+
+// disabled by reason
+#if 0
+#ifdef CACHE
+    if (bitmap_offset != s->last_bitmap)
+    {
+	lseek(s->fd, bitmap_offset, SEEK_SET);
+
+	s->last_bitmap = bitmap_offset;
+
+	// Scary! Bitmap is stored as big endian 32bit entries,
+	// while we used to look it up byte by byte
+	read(s->fd, s->pageentry_u8, 512);
+	for (i = 0; i < 128; i++)
+	    be32_to_cpus(&s->pageentry_u32[i]);
+    }
+
+    if ((s->pageentry_u8[pageentry_index / 8] >> (pageentry_index % 8)) & 1)
+	return -1;
+#else
+    lseek(s->fd, bitmap_offset + (pageentry_index / 8), SEEK_SET);
+
+    read(s->fd, &bitmap_entry, 1);
+
+    if ((bitmap_entry >> (pageentry_index % 8)) & 1)
+	return -1; // not allocated
+#endif
+#endif
+
    return block_offset;
 }

@@ -402,7 +423,7 @@ static int rewrite_footer(BlockDriverState* bs)
    BDRVVPCState *s = bs->opaque;
    int64_t offset = s->free_data_block_offset;

-    ret = bdrv_pwrite_sync(bs->file->bs, offset, s->footer_buf, HEADER_SIZE);
+    ret = bdrv_pwrite_sync(bs->file, offset, s->footer_buf, HEADER_SIZE);
    if (ret < 0)
        return ret;

@@ -437,7 +458,7 @@ static int64_t alloc_block(BlockDriverState* bs, int64_t sector_num)

    // Initialize the block's bitmap
    memset(bitmap, 0xff, s->bitmap_size);
-    ret = bdrv_pwrite_sync(bs->file->bs, s->free_data_block_offset, bitmap,
+    ret = bdrv_pwrite_sync(bs->file, s->free_data_block_offset, bitmap,
        s->bitmap_size);
    if (ret < 0) {
        return ret;
@@ -452,7 +473,7 @@ static int64_t alloc_block(BlockDriverState* bs, int64_t sector_num)
    // Write BAT entry to disk
    bat_offset = s->bat_offset + (4 * index);
    bat_value = cpu_to_be32(s->pagetable[index]);
-    ret = bdrv_pwrite_sync(bs->file->bs, bat_offset, &bat_value, 4);
+    ret = bdrv_pwrite_sync(bs->file, bat_offset, &bat_value, 4);
    if (ret < 0)
        goto fail;

@@ -486,7 +507,7 @@ static int vpc_read(BlockDriverState *bs, int64_t sector_num,
    VHDFooter *footer = (VHDFooter *) s->footer_buf;

    if (be32_to_cpu(footer->type) == VHD_FIXED) {
-        return bdrv_read(bs->file->bs, sector_num, buf, nb_sectors);
+        return bdrv_read(bs->file, sector_num, buf, nb_sectors);
    }
    while (nb_sectors > 0) {
        offset = get_sector_offset(bs, sector_num, 0);
@@ -500,7 +521,7 @@ static int vpc_read(BlockDriverState *bs, int64_t sector_num,
        if (offset == -1) {
            memset(buf, 0, sectors * BDRV_SECTOR_SIZE);
        } else {
-            ret = bdrv_pread(bs->file->bs, offset, buf,
+            ret = bdrv_pread(bs->file, offset, buf,
                sectors * BDRV_SECTOR_SIZE);
            if (ret != sectors * BDRV_SECTOR_SIZE) {
                return -1;
@@ -535,7 +556,7 @@ static int vpc_write(BlockDriverState *bs, int64_t sector_num,
    VHDFooter *footer =  (VHDFooter *) s->footer_buf;

    if (be32_to_cpu(footer->type) == VHD_FIXED) {
-        return bdrv_write(bs->file->bs, sector_num, buf, nb_sectors);
+        return bdrv_write(bs->file, sector_num, buf, nb_sectors);
    }
    while (nb_sectors > 0) {
        offset = get_sector_offset(bs, sector_num, 1);
@@ -552,8 +573,7 @@ static int vpc_write(BlockDriverState *bs, int64_t sector_num,
                return -1;
        }

-        ret = bdrv_pwrite(bs->file->bs, offset, buf,
-                          sectors * BDRV_SECTOR_SIZE);
+        ret = bdrv_pwrite(bs->file, offset, buf, sectors * BDRV_SECTOR_SIZE);
        if (ret != sectors * BDRV_SECTOR_SIZE) {
            return -1;
        }
@@ -577,49 +597,6 @@ static coroutine_fn int vpc_co_write(BlockDriverState *bs, int64_t sector_num,
    return ret;
 }

-static int64_t coroutine_fn vpc_co_get_block_status(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *pnum)
-{
-    BDRVVPCState *s = bs->opaque;
-    VHDFooter *footer = (VHDFooter*) s->footer_buf;
-    int64_t start, offset;
-    bool allocated;
-    int n;
-
-    if (be32_to_cpu(footer->type) == VHD_FIXED) {
-        *pnum = nb_sectors;
-        return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID | BDRV_BLOCK_DATA |
-               (sector_num << BDRV_SECTOR_BITS);
-    }
-
-    offset = get_sector_offset(bs, sector_num, 0);
-    start = offset;
-    allocated = (offset != -1);
-    *pnum = 0;
-
-    do {
-        /* All sectors in a block are contiguous (without using the bitmap) */
-        n = ROUND_UP(sector_num + 1, s->block_size / BDRV_SECTOR_SIZE)
-          - sector_num;
-        n = MIN(n, nb_sectors);
-
-        *pnum += n;
-        sector_num += n;
-        nb_sectors -= n;
-        /* *pnum can't be greater than one block for allocated
-         * sectors since there is always a bitmap in between. */
-        if (allocated) {
-            return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | start;
-        }
-        if (nb_sectors == 0) {
-            break;
-        }
-        offset = get_sector_offset(bs, sector_num, 0);
-    } while (offset == -1);
-
-    return 0;
-}
-
 /*
 * Calculates the number of cylinders, heads and sectors per cylinder
 * based on a given number of sectors. This is the algorithm described
@@ -637,20 +614,26 @@ static int calculate_geometry(int64_t total_sectors, uint16_t* cyls,
 {
    uint32_t cyls_times_heads;

-    total_sectors = MIN(total_sectors, VHD_MAX_GEOMETRY);
+    /* Allow a maximum disk size of approximately 2 TB */
+    if (total_sectors > 65535LL * 255 * 255) {
+        return -EFBIG;
+    }

-    if (total_sectors >= 65535LL * 16 * 63) {
+    if (total_sectors > 65535 * 16 * 63) {
        *secs_per_cyl = 255;
-        *heads = 16;
+        if (total_sectors > 65535 * 16 * 255) {
+            *heads = 255;
+        } else {
+            *heads = 16;
+        }
        cyls_times_heads = total_sectors / *secs_per_cyl;
    } else {
        *secs_per_cyl = 17;
        cyls_times_heads = total_sectors / *secs_per_cyl;
        *heads = (cyls_times_heads + 1023) / 1024;

-        if (*heads < 4) {
+        if (*heads < 4)
            *heads = 4;
-        }

        if (cyls_times_heads >= (*heads * 1024) || *heads > 16) {
            *secs_per_cyl = 31;
@@ -796,7 +779,7 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
        goto out;
    }
    ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
-                    &local_err);
+                    NULL, &local_err);
    if (ret < 0) {
        error_propagate(errp, local_err);
        goto out;
@@ -806,28 +789,20 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
     * Calculate matching total_size and geometry. Increase the number of
     * sectors requested until we get enough (or fail). This ensures that
     * qemu-img convert doesn't truncate images, but rather rounds up.
-     *
-     * If the image size can't be represented by a spec conform CHS geometry,
-     * we set the geometry to 65535 x 16 x 255 (CxHxS) sectors and use
-     * the image size from the VHD footer to calculate total_sectors.
     */
-    total_sectors = MIN(VHD_MAX_GEOMETRY, total_size / BDRV_SECTOR_SIZE);
+    total_sectors = total_size / BDRV_SECTOR_SIZE;
    for (i = 0; total_sectors > (int64_t)cyls * heads * secs_per_cyl; i++) {
-        calculate_geometry(total_sectors + i, &cyls, &heads, &secs_per_cyl);
-    }
-
-    if ((int64_t)cyls * heads * secs_per_cyl == VHD_MAX_GEOMETRY) {
-        total_sectors = total_size / BDRV_SECTOR_SIZE;
-        /* Allow a maximum disk size of approximately 2 TB */
-        if (total_sectors > VHD_MAX_SECTORS) {
+        if (calculate_geometry(total_sectors + i, &cyls, &heads,
+                               &secs_per_cyl))
+        {
            ret = -EFBIG;
            goto out;
        }
-    } else {
-        total_sectors = (int64_t)cyls * heads * secs_per_cyl;
-        total_size = total_sectors * BDRV_SECTOR_SIZE;
    }

+    total_sectors = (int64_t) cyls * heads * secs_per_cyl;
+    total_size = total_sectors * BDRV_SECTOR_SIZE;
+
    /* Prepare the Hard Disk Footer */
    memset(buf, 0, 1024);

@@ -849,7 +824,7 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
    footer->major = cpu_to_be16(0x0005);
    footer->minor = cpu_to_be16(0x0003);
    footer->orig_size = cpu_to_be64(total_size);
-    footer->current_size = cpu_to_be64(total_size);
+    footer->size = cpu_to_be64(total_size);
    footer->cyls = cpu_to_be16(cyls);
    footer->heads = heads;
    footer->secs_per_cyl = secs_per_cyl;
@@ -880,7 +855,7 @@ static int vpc_has_zero_init(BlockDriverState *bs)
    VHDFooter *footer =  (VHDFooter *) s->footer_buf;

    if (be32_to_cpu(footer->type) == VHD_FIXED) {
-        return bdrv_has_zero_init(bs->file->bs);
+        return bdrv_has_zero_init(bs->file);
    } else {
        return 1;
    }
@@ -914,6 +889,11 @@ static QemuOptsList vpc_create_opts = {
                "Type of virtual hard disk format. Supported formats are "
                "{dynamic (default) | fixed} "
        },
+        {
+            .name = BLOCK_OPT_NOCOW,
+            .type = QEMU_OPT_BOOL,
+            .help = "Turn off copy-on-write (valid only on btrfs)"
+        },
        { /* end of list */ }
    }
 };
@@ -928,9 +908,8 @@ static BlockDriver bdrv_vpc = {
    .bdrv_reopen_prepare    = vpc_reopen_prepare,
    .bdrv_create            = vpc_create,

-    .bdrv_read                  = vpc_co_read,
-    .bdrv_write                 = vpc_co_write,
-    .bdrv_co_get_block_status   = vpc_co_get_block_status,
+    .bdrv_read              = vpc_co_read,
+    .bdrv_write             = vpc_co_write,

    .bdrv_get_info          = vpc_get_info,

@@ -30,7 +30,6 @@
 #include "migration/migration.h"
 #include "qapi/qmp/qint.h"
 #include "qapi/qmp/qbool.h"
-#include "qapi/qmp/qstring.h"

 #ifndef S_IWGRP
 #define S_IWGRP 0
@@ -323,7 +322,6 @@ typedef struct BDRVVVFATState {

    int fat_type; /* 16 or 32 */
    array_t fat,directory,mapping;
-    char volume_label[11];

    unsigned int cluster_size;
    unsigned int sectors_per_cluster;
@@ -861,7 +859,7 @@ static int init_directories(BDRVVVFATState* s,
    {
 	direntry_t* entry=array_get_next(&(s->directory));
 	entry->attributes=0x28; /* archive | volume label */
-        memcpy(entry->name, s->volume_label, sizeof(entry->name));
+        memcpy(entry->name, "QEMU VVFAT ", sizeof(entry->name));
    }

    /* Now build FAT, and write back information into directory */
@@ -970,8 +968,7 @@ static int init_directories(BDRVVVFATState* s,
    bootsector->u.fat16.signature=0x29;
    bootsector->u.fat16.id=cpu_to_le32(0xfabe1afd);

-    memcpy(bootsector->u.fat16.volume_label, s->volume_label,
-           sizeof(bootsector->u.fat16.volume_label));
+    memcpy(bootsector->u.fat16.volume_label,"QEMU VVFAT ",11);
    memcpy(bootsector->fat_type,(s->fat_type==12?"FAT12   ":s->fat_type==16?"FAT16   ":"FAT32   "),8);
    bootsector->magic[0]=0x55; bootsector->magic[1]=0xaa;

@@ -985,6 +982,12 @@ static BDRVVVFATState *vvv = NULL;
 static int enable_write_target(BDRVVVFATState *s, Error **errp);
 static int is_consistent(BDRVVVFATState *s);

+static void vvfat_rebind(BlockDriverState *bs)
+{
+    BDRVVVFATState *s = bs->opaque;
+    s->bs = bs;
+}
+
 static QemuOptsList runtime_opts = {
    .name = "vvfat",
    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
@@ -1004,11 +1007,6 @@ static QemuOptsList runtime_opts = {
            .type = QEMU_OPT_BOOL,
            .help = "Create a floppy rather than a hard disk image",
        },
-        {
-            .name = "label",
-            .type = QEMU_OPT_STRING,
-            .help = "Use a volume label other than QEMU VVFAT",
-        },
        {
            .name = "rw",
            .type = QEMU_OPT_BOOL,
@@ -1061,8 +1059,8 @@ static void vvfat_parse_filename(const char *filename, QDict *options,
    /* Fill in the options QDict */
    qdict_put(options, "dir", qstring_from_str(filename));
    qdict_put(options, "fat-type", qint_from_int(fat_type));
-    qdict_put(options, "floppy", qbool_from_bool(floppy));
-    qdict_put(options, "rw", qbool_from_bool(rw));
+    qdict_put(options, "floppy", qbool_from_int(floppy));
+    qdict_put(options, "rw", qbool_from_int(rw));
 }

 static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
@@ -1071,7 +1069,7 @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
    BDRVVVFATState *s = bs->opaque;
    int cyls, heads, secs;
    bool floppy;
-    const char *dirname, *label;
+    const char *dirname;
    QemuOpts *opts;
    Error *local_err = NULL;
    int ret;
@@ -1098,18 +1096,6 @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
    s->fat_type = qemu_opt_get_number(opts, "fat-type", 0);
    floppy = qemu_opt_get_bool(opts, "floppy", false);

-    memset(s->volume_label, ' ', sizeof(s->volume_label));
-    label = qemu_opt_get(opts, "label");
-    if (label) {
-        size_t label_length = strlen(label);
-        if (label_length > 11) {
-            error_setg(errp, "vvfat label cannot be longer than 11 bytes");
-            ret = -EINVAL;
-            goto fail;
-        }
-        memcpy(s->volume_label, label, label_length);
-    }
-
    if (floppy) {
        /* 1.44MB or 2.88MB floppy.  2.88MB can be FAT12 (default) or FAT16. */
        if (!s->fat_type) {
@@ -1194,10 +1180,9 @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,

    /* Disable migration when vvfat is used rw */
    if (s->qcow) {
-        error_setg(&s->migration_blocker,
-                   "The vvfat (rw) format used by node '%s' "
-                   "does not support live migration",
-                   bdrv_get_device_or_node_name(bs));
+        error_set(&s->migration_blocker,
+                  QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
+                  "vvfat (rw)", bdrv_get_device_name(bs), "live migration");
        migrate_add_blocker(s->migration_blocker);
    }

@@ -2917,18 +2902,15 @@ static BlockDriver vvfat_write_target = {
 static int enable_write_target(BDRVVVFATState *s, Error **errp)
 {
    BlockDriver *bdrv_qcow = NULL;
-    BlockDriverState *backing;
    QemuOpts *opts = NULL;
    int ret;
    int size = sector2cluster(s, s->sector_count);
-    QDict *options;
-
    s->used_clusters = calloc(size, 1);

    array_init(&(s->commits), sizeof(commit_t));

-    s->qcow_filename = g_malloc(PATH_MAX);
-    ret = get_tmp_filename(s->qcow_filename, PATH_MAX);
+    s->qcow_filename = g_malloc(1024);
+    ret = get_tmp_filename(s->qcow_filename, 1024);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "can't create temporary file");
        goto err;
@@ -2942,9 +2924,8 @@ static int enable_write_target(BDRVVVFATState *s, Error **errp)
    }

    opts = qemu_opts_create(bdrv_qcow->create_opts, NULL, 0, &error_abort);
-    qemu_opt_set_number(opts, BLOCK_OPT_SIZE, s->sector_count * 512,
-                        &error_abort);
-    qemu_opt_set(opts, BLOCK_OPT_BACKING_FILE, "fat:", &error_abort);
+    qemu_opt_set_number(opts, BLOCK_OPT_SIZE, s->sector_count * 512);
+    qemu_opt_set(opts, BLOCK_OPT_BACKING_FILE, "fat:");

    ret = bdrv_create(bdrv_qcow, s->qcow_filename, opts, errp);
    qemu_opts_del(opts);
@@ -2953,11 +2934,9 @@ static int enable_write_target(BDRVVVFATState *s, Error **errp)
    }

    s->qcow = NULL;
-    options = qdict_new();
-    qdict_put(options, "driver", qstring_from_str("qcow"));
-    ret = bdrv_open(&s->qcow, s->qcow_filename, NULL, options,
+    ret = bdrv_open(&s->qcow, s->qcow_filename, NULL, NULL,
                    BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH,
-                    errp);
+                    bdrv_qcow, errp);
    if (ret < 0) {
        goto err;
    }
@@ -2966,13 +2945,10 @@ static int enable_write_target(BDRVVVFATState *s, Error **errp)
    unlink(s->qcow_filename);
 #endif

-    backing = bdrv_new();
-    bdrv_set_backing_hd(s->bs, backing);
-    bdrv_unref(backing);
-
-    s->bs->backing->bs->drv = &vvfat_write_target;
-    s->bs->backing->bs->opaque = g_new(void *, 1);
-    *(void**)s->bs->backing->bs->opaque = s;
+    bdrv_set_backing_hd(s->bs, bdrv_new());
+    s->bs->backing_hd->drv = &vvfat_write_target;
+    s->bs->backing_hd->opaque = g_new(void *, 1);
+    *(void**)s->bs->backing_hd->opaque = s;

    return 0;

@@ -3006,6 +2982,7 @@ static BlockDriver bdrv_vvfat = {
    .bdrv_parse_filename    = vvfat_parse_filename,
    .bdrv_file_open         = vvfat_open,
    .bdrv_close             = vvfat_close,
+    .bdrv_rebind            = vvfat_rebind,

    .bdrv_read              = vvfat_co_read,
    .bdrv_write             = vvfat_co_write,
@@ -174,7 +174,7 @@ int win32_aio_attach(QEMUWin32AIOState *aio, HANDLE hfile)
 void win32_aio_detach_aio_context(QEMUWin32AIOState *aio,
                                  AioContext *old_context)
 {
-    aio_set_event_notifier(old_context, &aio->e, false, NULL);
+    aio_set_event_notifier(old_context, &aio->e, NULL);
    aio->is_aio_context_attached = false;
 }

@@ -182,8 +182,7 @@ void win32_aio_attach_aio_context(QEMUWin32AIOState *aio,
                                  AioContext *new_context)
 {
    aio->is_aio_context_attached = true;
-    aio_set_event_notifier(new_context, &aio->e, false,
-                           win32_aio_completion_cb);
+    aio_set_event_notifier(new_context, &aio->e, win32_aio_completion_cb);
 }

 QEMUWin32AIOState *win32_aio_init(void)
@@ -1,125 +0,0 @@
-/*
- * QEMU System Emulator block write threshold notification
- *
- * Copyright Red Hat, Inc. 2014
- *
- * Authors:
- *  Francesco Romani <fromani@redhat.com>
- *
- * This work is licensed under the terms of the GNU LGPL, version 2 or later.
- * See the COPYING.LIB file in the top-level directory.
- */
-
-#include "block/block_int.h"
-#include "qemu/coroutine.h"
-#include "block/write-threshold.h"
-#include "qemu/notify.h"
-#include "qapi-event.h"
-#include "qmp-commands.h"
-
-
-uint64_t bdrv_write_threshold_get(const BlockDriverState *bs)
-{
-    return bs->write_threshold_offset;
-}
-
-bool bdrv_write_threshold_is_set(const BlockDriverState *bs)
-{
-    return bs->write_threshold_offset > 0;
-}
-
-static void write_threshold_disable(BlockDriverState *bs)
-{
-    if (bdrv_write_threshold_is_set(bs)) {
-        notifier_with_return_remove(&bs->write_threshold_notifier);
-        bs->write_threshold_offset = 0;
-    }
-}
-
-uint64_t bdrv_write_threshold_exceeded(const BlockDriverState *bs,
-                                       const BdrvTrackedRequest *req)
-{
-    if (bdrv_write_threshold_is_set(bs)) {
-        if (req->offset > bs->write_threshold_offset) {
-            return (req->offset - bs->write_threshold_offset) + req->bytes;
-        }
-        if ((req->offset + req->bytes) > bs->write_threshold_offset) {
-            return (req->offset + req->bytes) - bs->write_threshold_offset;
-        }
-    }
-    return 0;
-}
-
-static int coroutine_fn before_write_notify(NotifierWithReturn *notifier,
-                                            void *opaque)
-{
-    BdrvTrackedRequest *req = opaque;
-    BlockDriverState *bs = req->bs;
-    uint64_t amount = 0;
-
-    amount = bdrv_write_threshold_exceeded(bs, req);
-    if (amount > 0) {
-        qapi_event_send_block_write_threshold(
-            bs->node_name,
-            amount,
-            bs->write_threshold_offset,
-            &error_abort);
-
-        /* autodisable to avoid flooding the monitor */
-        write_threshold_disable(bs);
-    }
-
-    return 0; /* should always let other notifiers run */
-}
-
-static void write_threshold_register_notifier(BlockDriverState *bs)
-{
-    bs->write_threshold_notifier.notify = before_write_notify;
-    notifier_with_return_list_add(&bs->before_write_notifiers,
-                                  &bs->write_threshold_notifier);
-}
-
-static void write_threshold_update(BlockDriverState *bs,
-                                   int64_t threshold_bytes)
-{
-    bs->write_threshold_offset = threshold_bytes;
-}
-
-void bdrv_write_threshold_set(BlockDriverState *bs, uint64_t threshold_bytes)
-{
-    if (bdrv_write_threshold_is_set(bs)) {
-        if (threshold_bytes > 0) {
-            write_threshold_update(bs, threshold_bytes);
-        } else {
-            write_threshold_disable(bs);
-        }
-    } else {
-        if (threshold_bytes > 0) {
-            /* avoid multiple registration */
-            write_threshold_register_notifier(bs);
-            write_threshold_update(bs, threshold_bytes);
-        }
-        /* discard bogus disable request */
-    }
-}
-
-void qmp_block_set_write_threshold(const char *node_name,
-                                   uint64_t threshold_bytes,
-                                   Error **errp)
-{
-    BlockDriverState *bs;
-    AioContext *aio_context;
-
-    bs = bdrv_find_node(node_name);
-    if (!bs) {
-        error_setg(errp, "Device '%s' not found", node_name);
-        return;
-    }
-
-    aio_context = bdrv_get_aio_context(bs);
-    aio_context_acquire(aio_context);
-
-    bdrv_write_threshold_set(bs, threshold_bytes);
-
-    aio_context_release(aio_context);
-}
@@ -10,8 +10,8 @@
 */

 #include "sysemu/blockdev.h"
-#include "sysemu/block-backend.h"
 #include "hw/block/block.h"
+#include "monitor/monitor.h"
 #include "qapi/qmp/qerror.h"
 #include "sysemu/sysemu.h"
 #include "qmp-commands.h"
@@ -42,13 +42,12 @@ void qmp_nbd_server_start(SocketAddress *addr, Error **errp)

    server_fd = socket_listen(addr, errp);
    if (server_fd != -1) {
-        qemu_set_fd_handler(server_fd, nbd_accept, NULL, NULL);
+        qemu_set_fd_handler2(server_fd, NULL, nbd_accept, NULL, NULL);
    }
 }

-/*
- * Hook into the BlockBackend notifiers to close the export when the
- * backend is closed.
+/* Hook into the BlockDriverState notifiers to close the export when
+ * the file is closed.
 */
 typedef struct NBDCloseNotifier {
    Notifier n;
@@ -74,7 +73,7 @@ static void nbd_close_notifier(Notifier *n, void *data)
 void qmp_nbd_server_add(const char *device, bool has_writable, bool writable,
                        Error **errp)
 {
-    BlockBackend *blk;
+    BlockDriverState *bs;
    NBDExport *exp;
    NBDCloseNotifier *n;

@@ -88,36 +87,31 @@ void qmp_nbd_server_add(const char *device, bool has_writable, bool writable,
        return;
    }

-    blk = blk_by_name(device);
-    if (!blk) {
-        error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND,
-                  "Device '%s' not found", device);
+    bs = bdrv_find(device);
+    if (!bs) {
+        error_set(errp, QERR_DEVICE_NOT_FOUND, device);
        return;
    }
-    if (!blk_is_inserted(blk)) {
-        error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM, device);
+    if (!bdrv_is_inserted(bs)) {
+        error_set(errp, QERR_DEVICE_HAS_NO_MEDIUM, device);
        return;
    }

    if (!has_writable) {
        writable = false;
    }
-    if (blk_is_read_only(blk)) {
+    if (bdrv_is_read_only(bs)) {
        writable = false;
    }

-    exp = nbd_export_new(blk, 0, -1, writable ? 0 : NBD_FLAG_READ_ONLY, NULL,
-                         errp);
-    if (!exp) {
-        return;
-    }
+    exp = nbd_export_new(bs, 0, -1, writable ? 0 : NBD_FLAG_READ_ONLY, NULL);

    nbd_export_set_name(exp, device);

    n = g_new0(NBDCloseNotifier, 1);
    n->n.notify = nbd_close_notifier;
    n->exp = exp;
-    blk_add_close_notifier(blk, &n->n);
+    bdrv_add_close_notifier(bs, &n->n);
    QTAILQ_INSERT_TAIL(&close_notifiers, n, next);
 }

@@ -129,7 +123,7 @@ void qmp_nbd_server_stop(Error **errp)
    }

    if (server_fd != -1) {
-        qemu_set_fd_handler(server_fd, NULL, NULL, NULL);
+        qemu_set_fd_handler2(server_fd, NULL, NULL, NULL, NULL);
        close(server_fd);
        server_fd = -1;
    }
--- a/Show More
+++ b/Show More
@@ -1 +1 @@
 .5.0
 .2.1