Update VERSION for 1.7.2 release

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Allow mismatched virtio config-len
2014-07-21 17:42:15 -05:00 · 2014-07-15 19:28:02 -05:00 · 2014-07-15 19:28:02 -05:00 · 2014-07-15 19:28:02 -05:00 · 2014-07-15 19:28:02 -05:00 · 2014-07-15 19:28:02 -05:00
1263 changed files with 99867 additions and 159135 deletions
@@ -1,75 +1,68 @@
-/config-devices.*
-/config-all-devices.*
-/config-all-disas.*
-/config-host.*
-/config-target.*
-/config.status
-/trace/generated-tracers.h
-/trace/generated-tracers.c
-/trace/generated-tracers-dtrace.h
-/trace/generated-tracers.dtrace
-/trace/generated-events.h
-/trace/generated-events.c
-/trace/generated-ust-provider.h
-/trace/generated-ust.c
-/libcacard/trace/generated-tracers.c
+config-devices.*
+config-all-devices.*
+config-all-disas.*
+config-host.*
+config-target.*
+trace/generated-tracers.h
+trace/generated-tracers.c
+trace/generated-tracers-dtrace.h
+trace/generated-tracers.dtrace
+trace/generated-events.h
+trace/generated-events.c
+libcacard/trace/generated-tracers.c
 *-timestamp
-/*-softmmu
-/*-darwin-user
-/*-linux-user
-/*-bsd-user
+*-softmmu
+*-darwin-user
+*-linux-user
+*-bsd-user
 libdis*
 libuser
-/linux-headers/asm
-/qga/qapi-generated
-/qapi-generated
-/qapi-types.[ch]
-/qapi-visit.[ch]
-/qmp-commands.h
-/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
-/qemu-img-cmds.h
-/qemu-io
-/qemu-ga
-/qemu-bridge-helper
-/qemu-monitor.texi
-/qmp-commands.txt
-/vscclient
-/test-bitops
-/test-coroutine
-/test-int128
-/test-opts-visitor
-/test-qmp-input-visitor
-/test-qmp-output-visitor
-/test-string-input-visitor
-/test-string-output-visitor
-/test-visitor-serialization
-/fsdev/virtfs-proxy-helper
-/fsdev/virtfs-proxy-helper.1
-/fsdev/virtfs-proxy-helper.pod
-/.gdbinit
+linux-headers/asm
+qapi-generated
+qapi-types.[ch]
+qapi-visit.[ch]
+qmp-commands.h
+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
+qemu-img-cmds.h
+qemu-io
+qemu-ga
+qemu-bridge-helper
+qemu-monitor.texi
+vscclient
+qmp-commands.txt
+test-bitops
+test-coroutine
+test-int128
+test-opts-visitor
+test-qmp-input-visitor
+test-qmp-output-visitor
+test-string-input-visitor
+test-string-output-visitor
+test-visitor-serialization
+fsdev/virtfs-proxy-helper
+fsdev/virtfs-proxy-helper.1
+fsdev/virtfs-proxy-helper.pod
+.gdbinit
 *.a
 *.aux
 *.cp
 *.dvi
 *.exe
-*.dll
-*.so
-*.mo
 *.fn
 *.ky
 *.log
@@ -83,7 +76,7 @@ libuser
 *.tp
 *.vr
 *.d
-!/scripts/qemu-guest-agent/fsfreeze-hook.d
+!scripts/qemu-guest-agent/fsfreeze-hook.d
 *.o
 *.lo
 *.la
@@ -96,22 +89,22 @@ libuser
 *.gcda
 *.gcno
 patches
-/pc-bios/bios-pq/status
-/pc-bios/vgabios-pq/status
-/pc-bios/optionrom/linuxboot.asm
-/pc-bios/optionrom/linuxboot.bin
-/pc-bios/optionrom/linuxboot.raw
-/pc-bios/optionrom/linuxboot.img
-/pc-bios/optionrom/multiboot.asm
-/pc-bios/optionrom/multiboot.bin
-/pc-bios/optionrom/multiboot.raw
-/pc-bios/optionrom/multiboot.img
-/pc-bios/optionrom/kvmvapic.asm
-/pc-bios/optionrom/kvmvapic.bin
-/pc-bios/optionrom/kvmvapic.raw
-/pc-bios/optionrom/kvmvapic.img
-/pc-bios/s390-ccw/s390-ccw.elf
-/pc-bios/s390-ccw/s390-ccw.img
+pc-bios/bios-pq/status
+pc-bios/vgabios-pq/status
+pc-bios/optionrom/linuxboot.asm
+pc-bios/optionrom/linuxboot.bin
+pc-bios/optionrom/linuxboot.raw
+pc-bios/optionrom/linuxboot.img
+pc-bios/optionrom/multiboot.asm
+pc-bios/optionrom/multiboot.bin
+pc-bios/optionrom/multiboot.raw
+pc-bios/optionrom/multiboot.img
+pc-bios/optionrom/kvmvapic.asm
+pc-bios/optionrom/kvmvapic.bin
+pc-bios/optionrom/kvmvapic.raw
+pc-bios/optionrom/kvmvapic.img
+pc-bios/s390-ccw/s390-ccw.elf
+pc-bios/s390-ccw/s390-ccw.img
 .stgit-*
 cscope.*
 tags
@@ -13,9 +13,6 @@
 [submodule "roms/openbios"]
 	path = roms/openbios
 	url = git://git.qemu-project.org/openbios.git
-[submodule "roms/openhackware"]
-	path = roms/openhackware
-	url = git://git.qemu-project.org/openhackware.git
 [submodule "roms/qemu-palcode"]
 	path = roms/qemu-palcode
 	url = git://github.com/rth7680/qemu-palcode.git
@@ -4,12 +4,6 @@ python:
 compiler:
  - gcc
  - clang
-notifications:
-  irc:
-    channels:
-      - "irc.oftc.net#qemu"
-    on_success: change
-    on_failure: always
 env:
  global:
    - TEST_CMD="make check"
@@ -20,23 +14,22 @@ env:
    - GUI_PKGS="libgtk-3-dev libvte-2.90-dev libsdl1.2-dev libpng12-dev libpixman-1-dev"
    - EXTRA_PKGS=""
  matrix:
-    - TARGETS=alpha-softmmu,alpha-linux-user
-    - TARGETS=arm-softmmu,arm-linux-user
-    - TARGETS=aarch64-softmmu,aarch64-linux-user
-    - TARGETS=cris-softmmu
-    - TARGETS=i386-softmmu,x86_64-softmmu
-    - TARGETS=lm32-softmmu
-    - TARGETS=m68k-softmmu
-    - TARGETS=microblaze-softmmu,microblazeel-softmmu
-    - TARGETS=mips-softmmu,mips64-softmmu,mips64el-softmmu,mipsel-softmmu
-    - TARGETS=moxie-softmmu
-    - TARGETS=or32-softmmu,
-    - TARGETS=ppc-softmmu,ppc64-softmmu,ppcemb-softmmu
-    - TARGETS=s390x-softmmu
-    - TARGETS=sh4-softmmu,sh4eb-softmmu
-    - TARGETS=sparc-softmmu,sparc64-softmmu
-    - TARGETS=unicore32-softmmu
-    - TARGETS=xtensa-softmmu,xtensaeb-softmmu
+  - TARGETS=alpha-softmmu,alpha-linux-user
+  - TARGETS=arm-softmmu,arm-linux-user
+  - TARGETS=cris-softmmu
+  - TARGETS=i386-softmmu,x86_64-softmmu
+  - TARGETS=lm32-softmmu
+  - TARGETS=m68k-softmmu
+  - TARGETS=microblaze-softmmu,microblazeel-softmmu
+  - TARGETS=mips-softmmu,mips64-softmmu,mips64el-softmmu,mipsel-softmmu
+  - TARGETS=moxie-softmmu
+  - TARGETS=or32-softmmu,
+  - TARGETS=ppc-softmmu,ppc64-softmmu,ppcemb-softmmu
+  - TARGETS=s390x-softmmu
+  - TARGETS=sh4-softmmu,sh4eb-softmmu
+  - TARGETS=sparc-softmmu,sparc64-softmmu
+  - TARGETS=unicore32-softmmu
+  - TARGETS=xtensa-softmmu,xtensaeb-softmmu
 before_install:
  - git submodule update --init --recursive
  - sudo apt-get update -qq
@@ -52,10 +45,6 @@ matrix:
    - env: TARGETS=i386-softmmu,x86_64-softmmu
           EXTRA_CONFIG="--enable-debug --enable-tcg-interpreter"
      compiler: gcc
-    # All the extra -dev packages
-    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_PKGS="libaio-dev libcap-ng-dev libattr1-dev libbrlapi-dev uuid-dev libusb-1.0.0-dev"
-      compiler: gcc
    # Currently configure doesn't force --disable-pie
    - env: TARGETS=i386-softmmu,x86_64-softmmu
           EXTRA_CONFIG="--enable-gprof --enable-gcov --disable-pie"
@@ -75,7 +64,8 @@ matrix:
           EXTRA_CONFIG="--enable-trace-backend=ftrace"
           TEST_CMD=""
      compiler: gcc
-    - env: TARGETS=i386-softmmu,x86_64-softmmu
-          EXTRA_PKGS="liblttng-ust-dev liburcu-dev"
-          EXTRA_CONFIG="--enable-trace-backend=ust"
-      compiler: gcc
+    # This disabled make check for the ftrace backend which needs more setting up
+    # Currently broken on 12.04 due to mis-packaged liburcu and changed API, will be pulled.
+    #- env: TARGETS=i386-softmmu,x86_64-softmmu
+    #       EXTRA_PKGS="liblttng-ust-dev liburcu-dev"
+    #       EXTRA_CONFIG="--enable-trace-backend=ust"
@@ -84,10 +84,3 @@ and clarity it comes on a line by itself:
 Rationale: a consistent (except for functions...) bracing style reduces
 ambiguity and avoids needless churn when lines are added or removed.
 Furthermore, it is the QEMU coding style.
-
-5. Declarations
-
-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.
@@ -158,6 +158,7 @@ Guest CPU Cores (KVM):
 ----------------------

 Overall
+M: Gleb Natapov <gleb@redhat.com>
 M: Paolo Bonzini <pbonzini@redhat.com>
 L: kvm@vger.kernel.org
 S: Supported
@@ -175,14 +176,12 @@ S: Maintained
 F: target-ppc/kvm.c

 S390
-M: Christian Borntraeger <borntraeger@de.ibm.com>
-M: Cornelia Huck <cornelia.huck@de.ibm.com>
 M: Alexander Graf <agraf@suse.de>
 S: Maintained
 F: target-s390x/kvm.c
-F: hw/intc/s390_flic.[hc]

 X86
+M: Gleb Natapov <gleb@redhat.com>
 M: Marcelo Tosatti <mtosatti@redhat.com>
 L: kvm@vger.kernel.org
 S: Supported
@@ -220,13 +219,6 @@ F: *win32*

 ARM Machines
 ------------
-Allwinner-a10
-M: Li Guang <lig.fnst@cn.fujitsu.com>
-S: Maintained
-F: hw/*/allwinner-a10*
-F: include/hw/*/allwinner-a10*
-F: hw/arm/cubieboard.c
-
 Exynos
 M: Evgeny Voevodin <e.voevodin@samsung.com>
 M: Maksim Kozlov <m.kozlov@samsung.com>
@@ -241,12 +233,6 @@ S: Supported
 F: hw/arm/highbank.c
 F: hw/net/xgmac.c

-Canon DIGIC
-M: Antony Pavlov <antonynpavlov@gmail.com>
-S: Maintained
-F: include/hw/arm/digic.h
-F: hw/*/digic*
-
 Gumstix
 M: qemu-devel@nongnu.org
 S: Orphan
@@ -304,7 +290,7 @@ S: Maintained
 F: hw/*/versatile*

 Xilinx Zynq
-M: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
+M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
 S: Maintained
 F: hw/arm/xilinx_zynq.c
 F: hw/misc/zynq_slcr.c
@@ -353,7 +339,7 @@ S: Maintained
 F: hw/microblaze/petalogix_s3adsp1800_mmu.c

 petalogix_ml605
-M: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
+M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
 S: Maintained
 F: hw/microblaze/petalogix_ml605_mmu.c

@@ -496,13 +482,10 @@ F: hw/s390x/s390-*.c

 S390 Virtio-ccw
 M: Cornelia Huck <cornelia.huck@de.ibm.com>
-M: Christian Borntraeger <borntraeger@de.ibm.com>
 M: Alexander Graf <agraf@suse.de>
 S: Supported
 F: hw/s390x/s390-virtio-ccw.c
 F: hw/s390x/css.[hc]
-F: hw/s390x/sclp*.[hc]
-F: hw/s390x/ipl*.[hc]
 T: git git://github.com/cohuck/qemu virtio-ccw-upstr

 UniCore32 Machines
@@ -517,23 +500,9 @@ X86 Machines
 ------------
 PC
 M: Anthony Liguori <aliguori@amazon.com>
-M: Michael S. Tsirkin <mst@redhat.com>
 S: Supported
-F: include/hw/i386/
-F: hw/i386/
-F: hw/pci-host/piix.c
-F: hw/pci-host/q35.c
-F: hw/pci-host/pam.c
-F: include/hw/pci-host/q35.h
-F: include/hw/pci-host/pam.h
-F: hw/isa/piix4.c
-F: hw/isa/lpc_ich9.c
-F: hw/i2c/smbus_ich9.c
-F: hw/acpi/piix4.c
-F: hw/acpi/ich9.c
-F: include/hw/acpi/ich9.h
-F: include/hw/acpi/piix.h
-
+F: hw/i386/pc.[ch]
+F: hw/i386/pc_piix.c

 Xtensa Machines
 ---------------
@@ -592,7 +561,7 @@ S: Orphan
 F: hw/scsi/lsi53c895a.c

 SSI
-M: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
+M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
 S: Maintained
 F: hw/ssi/*
 F: hw/block/m25p80.c
@@ -614,7 +583,6 @@ F: hw/*/*vhost*

 virtio
 M: Anthony Liguori <aliguori@amazon.com>
-M: Michael S. Tsirkin <mst@redhat.com>
 S: Supported
 F: hw/*/virtio*

@@ -623,7 +591,6 @@ M: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
 S: Supported
 F: hw/9pfs/
 F: fsdev/
-F: tests/virtio-9p-test.c
 T: git git://github.com/kvaneesh/QEMU.git

 virtio-blk
@@ -634,7 +601,6 @@ F: hw/block/virtio-blk.c

 virtio-ccw
 M: Cornelia Huck <cornelia.huck@de.ibm.com>
-M: Christian Borntraeger <borntraeger@de.ibm.com>
 S: Supported
 F: hw/s390x/virtio-ccw.[hc]
 T: git git://github.com/cohuck/qemu virtio-ccw-upstr
@@ -649,10 +615,9 @@ nvme
 M: Keith Busch <keith.busch@intel.com>
 S: Supported
 F: hw/block/nvme*
-F: tests/nvme-test.c

 Xilinx EDK
-M: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
+M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
 M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
 S: Maintained
 F: hw/*/xilinx_*
@@ -696,7 +661,7 @@ F: include/hw/cpu/icc_bus.h
 F: hw/cpu/icc_bus.c

 Device Tree
-M: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
+M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
 M: Alexander Graf <agraf@suse.de>
 S: Maintained
 F: device_tree.[ch]
@@ -717,13 +682,11 @@ F: hw/display/qxl*

 Graphics
 M: Anthony Liguori <aliguori@amazon.com>
-M: Gerd Hoffmann <kraxel@redhat.com>
-S: Odd Fixes
+S: Maintained
 F: ui/

 Cocoa graphics
 M: Andreas Färber <andreas.faerber@web.de>
-M: Peter Maydell <peter.maydell@linaro.org>
 S: Odd Fixes
 F: ui/cocoa.m

@@ -734,7 +697,7 @@ F: vl.c

 Human Monitor (HMP)
 M: Luiz Capitulino <lcapitulino@redhat.com>
-S: Maintained
+S: Supported
 F: monitor.c
 F: hmp.c
 F: hmp-commands.hx
@@ -747,14 +710,6 @@ S: Maintained
 F: net/
 T: git git://github.com/stefanha/qemu.git net

-Netmap network backend
-M: Luigi Rizzo <rizzo@iet.unipi.it>
-M: Giuseppe Lettieri <g.lettieri@iet.unipi.it>
-M: Vincenzo Maffione <v.maffione@gmail.com>
-W: http://info.iet.unipi.it/~luigi/netmap/
-S: Maintained
-F: net/netmap.c
-
 Network Block Device (NBD)
 M: Paolo Bonzini <pbonzini@redhat.com>
 S: Odd Fixes
@@ -766,7 +721,7 @@ T: git git://github.com/bonzini/qemu.git nbd-next
 QAPI
 M: Luiz Capitulino <lcapitulino@redhat.com>
 M: Michael Roth <mdroth@linux.vnet.ibm.com>
-S: Maintained
+S: Supported
 F: qapi/
 T: git git://repo.or.cz/qemu/qmp-unstable.git queue/qmp

@@ -780,7 +735,7 @@ T: git git://repo.or.cz/qemu/qmp-unstable.git queue/qmp

 QMP
 M: Luiz Capitulino <lcapitulino@redhat.com>
-S: Maintained
+S: Supported
 F: qmp.c
 F: monitor.c
 F: qmp-commands.hx
@@ -924,7 +879,6 @@ F: block/rbd.c
 Sheepdog
 M: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
 M: Liu Yuan <namei.unix@gmail.com>
-L: sheepdog@lists.wpkg.org
 S: Supported
 F: block/sheepdog.c

@@ -945,11 +899,6 @@ M: Peter Lieven <pl@kamp.de>
 S: Supported
 F: block/iscsi.c

-NFS
-M: Peter Lieven <pl@kamp.de>
-S: Maintained
-F: block/nfs.c
-
 SSH
 M: Richard W.M. Jones <rjones@redhat.com>
 S: Supported
@@ -57,11 +57,6 @@ GENERATED_HEADERS += trace/generated-tracers-dtrace.h
 endif
 GENERATED_SOURCES += trace/generated-tracers.c

-ifeq ($(TRACE_BACKEND),ust)
-GENERATED_HEADERS += trace/generated-ust-provider.h
-GENERATED_SOURCES += trace/generated-ust.c
-endif
-
 # Don't try to regenerate Makefile or configure
 # We don't generate any of them
 Makefile: ;
@@ -127,30 +122,13 @@ defconfig:

 ifneq ($(wildcard config-host.mak),)
 include $(SRC_PATH)/Makefile.objs
-endif
-
-dummy := $(call unnest-vars,, \
-                stub-obj-y \
-                util-obj-y \
-                qga-obj-y \
-                qga-vss-dll-obj-y \
-                block-obj-y \
-                block-obj-m \
-                common-obj-y \
-                common-obj-m)
-
-ifneq ($(wildcard config-host.mak),)
 include $(SRC_PATH)/tests/Makefile
 endif
 ifeq ($(CONFIG_SMARTCARD_NSS),y)
 include $(SRC_PATH)/libcacard/Makefile
 endif

-all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all modules
-
-vl.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
-
-vl.o: QEMU_CFLAGS+=$(SDL_CFLAGS)
+all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all

 config-host.h: config-host.h-timestamp
 config-host.h-timestamp: config-host.mak
@@ -160,7 +138,6 @@ qemu-options.def: $(SRC_PATH)/qemu-options.hx
 SUBDIR_RULES=$(patsubst %,subdir-%, $(TARGET_DIRS))
 SOFTMMU_SUBDIR_RULES=$(filter %-softmmu,$(SUBDIR_RULES))

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

 subdir-%:
@@ -210,9 +187,6 @@ Makefile: $(version-obj-y) $(version-lobj-y)
 libqemustub.a: $(stub-obj-y)
 libqemuutil.a: $(util-obj-y) qapi-types.o qapi-visit.o

-block-modules = $(foreach o,$(block-obj-m),"$(basename $(subst /,-,$o))",) NULL
-util/module.o-cflags = -D'CONFIG_BLOCK_MODULES=$(block-modules)'
-
 ######################################################################

 qemu-img.o: qemu-img-cmds.h
@@ -266,7 +240,8 @@ 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
-	find . \( -name '*.l[oa]' -o -name '*.so' -o -name '*.dll' -o -name '*.mo' -o -name '*.[oda]' \) -type f -exec rm {} +
+	find . -name '*.[oda]' -type f -exec rm -f {} +
+	find . -name '*.l[oa]' -type f -exec rm -f {} +
 	rm -f $(filter-out %.tlb,$(TOOLS)) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
 	rm -f fsdev/*.pod
 	rm -rf .libs */.libs
@@ -315,10 +290,10 @@ common  de-ch  es     fo  fr-ca  hu     ja  mk  nl-be      pt  sl     tr \
 bepo    cz

 ifdef INSTALL_BLOBS
-BLOBS=bios.bin bios-256k.bin sgabios.bin vgabios.bin vgabios-cirrus.bin \
+BLOBS=bios.bin sgabios.bin vgabios.bin vgabios-cirrus.bin \
 vgabios-stdvga.bin vgabios-vmware.bin vgabios-qxl.bin \
 acpi-dsdt.aml q35-acpi-dsdt.aml \
-ppc_rom.bin openbios-sparc32 openbios-sparc64 openbios-ppc QEMU,tcx.bin QEMU,cgthree.bin \
+ppc_rom.bin openbios-sparc32 openbios-sparc64 openbios-ppc QEMU,tcx.bin \
 pxe-e1000.rom pxe-eepro100.rom pxe-ne2k_pci.rom \
 pxe-pcnet.rom pxe-rtl8139.rom pxe-virtio.rom \
 efi-e1000.rom efi-eepro100.rom efi-ne2k_pci.rom \
@@ -374,12 +349,6 @@ install-datadir install-localstatedir
 ifneq ($(TOOLS),)
 	$(INSTALL_PROG) $(STRIP_OPT) $(TOOLS) "$(DESTDIR)$(bindir)"
 endif
-ifneq ($(CONFIG_MODULES),)
-	$(INSTALL_DIR) "$(DESTDIR)$(qemu_moddir)"
-	for s in $(patsubst %.mo,%$(DSOSUF),$(modules-m)); do \
-		$(INSTALL_PROG) $(STRIP_OPT) $$s "$(DESTDIR)$(qemu_moddir)/$$(echo $$s | tr / -)"; \
-	done
-endif
 ifneq ($(HELPERS-y),)
 	$(INSTALL_DIR) "$(DESTDIR)$(libexecdir)"
 	$(INSTALL_PROG) $(STRIP_OPT) $(HELPERS-y) "$(DESTDIR)$(libexecdir)"
@@ -397,7 +366,7 @@ endif
 		$(INSTALL_DATA) $(SRC_PATH)/pc-bios/keymaps/$$x "$(DESTDIR)$(qemu_datadir)/keymaps"; \
 	done
 	for d in $(TARGET_DIRS); do \
-	$(MAKE) $(SUBDIR_MAKEFLAGS) TARGET_DIR=$$d/ -C $$d $@ || exit 1 ; \
+	$(MAKE) -C $$d $@ || exit 1 ; \
        done

 # various test targets
@@ -19,8 +19,11 @@ 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/
-
+ifeq ($(CONFIG_VIRTIO)$(CONFIG_VIRTFS)$(CONFIG_PCI),yyy)
+# Lots of the fsdev/9pcode is pulled in by vl.c via qemu_fsdev_add.
+# only pull in the actual virtio-9p device if we also enabled virtio.
+CONFIG_REALLY_VIRTFS=y
+endif

 ######################################################################
 # smartcard
@@ -38,9 +41,9 @@ libcacard-y += libcacard/vcardt.o
 # single QEMU executable should support all CPUs and machines.

 ifeq ($(CONFIG_SOFTMMU),y)
-common-obj-y = blockdev.o blockdev-nbd.o block/
-common-obj-y += iothread.o
+common-obj-y = $(block-obj-y) blockdev.o blockdev-nbd.o block/
 common-obj-y += net/
+common-obj-y += readline.o
 common-obj-y += qdev-monitor.o device-hotplug.o
 common-obj-$(CONFIG_WIN32) += os-win32.o
 common-obj-$(CONFIG_POSIX) += os-posix.o
@@ -48,8 +51,6 @@ common-obj-$(CONFIG_POSIX) += os-posix.o
 common-obj-$(CONFIG_LINUX) += fsdev/

 common-obj-y += migration.o migration-tcp.o
-common-obj-y += vmstate.o
-common-obj-y += qemu-file.o
 common-obj-$(CONFIG_RDMA) += migration-rdma.o
 common-obj-y += qemu-char.o #aio.o
 common-obj-y += block-migration.o
@@ -109,3 +110,18 @@ version-lobj-$(CONFIG_WIN32) += $(BUILD_DIR)/version.lo
 # by libqemuutil.a.  These should be moved to a separate .json schema.
 qga-obj-y = qga/ qapi-types.o qapi-visit.o
 qga-vss-dll-obj-y = qga/
+
+vl.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
+
+vl.o: QEMU_CFLAGS+=$(SDL_CFLAGS)
+
+QEMU_CFLAGS+=$(GLIB_CFLAGS)
+
+nested-vars += \
+	stub-obj-y \
+	util-obj-y \
+	qga-obj-y \
+	qga-vss-dll-obj-y \
+	block-obj-y \
+	common-obj-y
+dummy := $(call unnest-vars)
@@ -130,6 +130,8 @@ else
 obj-y += hw/$(TARGET_BASE_ARCH)/
 endif

+main.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
+
 GENERATED_HEADERS += hmp-commands.h qmp-commands-old.h

 endif # CONFIG_SOFTMMU
@@ -137,26 +139,13 @@ endif # CONFIG_SOFTMMU
 # Workaround for http://gcc.gnu.org/PR55489, see configure.
 %/translate.o: QEMU_CFLAGS += $(TRANSLATE_OPT_CFLAGS)

-dummy := $(call unnest-vars,,obj-y)
+nested-vars += obj-y

-# we are making another call to unnest-vars with different vars, protect obj-y,
-# it can be overriden in subdir Makefile.objs
-obj-y-save := $(obj-y)
-
-block-obj-y :=
-common-obj-y :=
+# This resolves all nested paths, so it must come last
 include $(SRC_PATH)/Makefile.objs
-dummy := $(call unnest-vars,.., \
-               block-obj-y \
-               block-obj-m \
-               common-obj-y \
-               common-obj-m)

-# Now restore obj-y
-obj-y := $(obj-y-save)
-
-all-obj-y = $(obj-y) $(common-obj-y)
-all-obj-$(CONFIG_SOFTMMU) += $(block-obj-y)
+all-obj-y = $(obj-y)
+all-obj-y += $(addprefix ../, $(common-obj-y))

 ifndef CONFIG_HAIKU
 LIBS+=-lm
@@ -1 +1 @@
-2.0.2
+1.7.2
@@ -217,6 +217,11 @@ bool aio_poll(AioContext *ctx, bool blocking)

    ctx->walking_handlers--;

+    /* early return if we only have the aio_notify() fd */
+    if (ctx->pollfds->len == 1) {
+        return progress;
+    }
+
    /* wait until next event */
    ret = qemu_poll_ns((GPollFD *)ctx->pollfds->data,
                         ctx->pollfds->len,
@@ -161,6 +161,11 @@ bool aio_poll(AioContext *ctx, bool blocking)

    ctx->walking_handlers--;

+    /* early return if we only have the aio_notify() fd */
+    if (count == 1) {
+        return progress;
+    }
+
    /* wait until next event */
    while (count > 0) {
        int ret;
@@ -48,9 +48,7 @@
 #include "qmp-commands.h"
 #include "trace.h"
 #include "exec/cpu-all.h"
-#include "exec/ram_addr.h"
 #include "hw/acpi/acpi.h"
-#include "qemu/host-utils.h"

 #ifdef DEBUG_ARCH_INIT
 #define DPRINTF(fmt, ...) \
@@ -122,6 +120,7 @@ static void check_guest_throttling(void);
 #define RAM_SAVE_FLAG_XBZRLE   0x40
 /* 0x80 is reserved in migration.h start with 0x100 next */

+
 static struct defconfig_file {
    const char *filename;
    /* Indicates it is an user config file (disabled by -no-user-config) */
@@ -132,7 +131,6 @@ static struct defconfig_file {
    { NULL }, /* end of list */
 };

-static const uint8_t ZERO_TARGET_PAGE[TARGET_PAGE_SIZE];

 int qemu_read_default_config_files(bool userconfig)
 {
@@ -164,63 +162,24 @@ static struct {
    uint8_t *encoded_buf;
    /* buffer for storing page content */
    uint8_t *current_buf;
-    /* Cache for XBZRLE, Protected by lock. */
+    /* buffer used for XBZRLE decoding */
+    uint8_t *decoded_buf;
+    /* Cache for XBZRLE */
    PageCache *cache;
-    QemuMutex lock;
 } XBZRLE = {
    .encoded_buf = NULL,
    .current_buf = NULL,
+    .decoded_buf = NULL,
    .cache = NULL,
 };
-/* buffer used for XBZRLE decoding */
-static uint8_t *xbzrle_decoded_buf;

-static void XBZRLE_cache_lock(void)
-{
-    if (migrate_use_xbzrle())
-        qemu_mutex_lock(&XBZRLE.lock);
-}
-
-static void XBZRLE_cache_unlock(void)
-{
-    if (migrate_use_xbzrle())
-        qemu_mutex_unlock(&XBZRLE.lock);
-}

 int64_t xbzrle_cache_resize(int64_t new_size)
 {
-    PageCache *new_cache, *cache_to_free;
-
-    if (new_size < TARGET_PAGE_SIZE) {
-        return -1;
-    }
-
-    /* no need to lock, the current thread holds qemu big lock */
    if (XBZRLE.cache != NULL) {
-        /* check XBZRLE.cache again later */
-        if (pow2floor(new_size) == migrate_xbzrle_cache_size()) {
-            return pow2floor(new_size);
-        }
-        new_cache = cache_init(new_size / TARGET_PAGE_SIZE,
-                                        TARGET_PAGE_SIZE);
-        if (!new_cache) {
-            DPRINTF("Error creating cache\n");
-            return -1;
-        }
-
-        XBZRLE_cache_lock();
-        /* the XBZRLE.cache may have be destroyed, check it again */
-        if (XBZRLE.cache != NULL) {
-            cache_to_free = XBZRLE.cache;
-            XBZRLE.cache = new_cache;
-        } else {
-            cache_to_free = new_cache;
-        }
-        XBZRLE_cache_unlock();
-
-        cache_fini(cache_to_free);
+        return cache_resize(XBZRLE.cache, new_size / TARGET_PAGE_SIZE) *
+            TARGET_PAGE_SIZE;
    }
-
    return pow2floor(new_size);
 }

@@ -310,34 +269,6 @@ static size_t save_block_hdr(QEMUFile *f, RAMBlock *block, ram_addr_t offset,
    return size;
 }

-/* This is the last block that we have visited serching for dirty pages
- */
-static RAMBlock *last_seen_block;
-/* This is the last block from where we have sent data */
-static RAMBlock *last_sent_block;
-static ram_addr_t last_offset;
-static unsigned long *migration_bitmap;
-static uint64_t migration_dirty_pages;
-static uint32_t last_version;
-static bool ram_bulk_stage;
-
-/* Update the xbzrle cache to reflect a page that's been sent as all 0.
- * The important thing is that a stale (not-yet-0'd) page be replaced
- * by the new data.
- * As a bonus, if the page wasn't in the cache it gets added so that
- * when a small write is made into the 0'd page it gets XBZRLE sent
- */
-static void xbzrle_cache_zero_page(ram_addr_t current_addr)
-{
-    if (ram_bulk_stage || !migrate_use_xbzrle()) {
-        return;
-    }
-
-    /* We don't care if this fails to allocate a new cache page
-     * as long as it updated an old one */
-    cache_insert(XBZRLE.cache, current_addr, ZERO_TARGET_PAGE);
-}
-
 #define ENCODING_FLAG_XBZRLE 0x1

 static int save_xbzrle_page(QEMUFile *f, uint8_t *current_data,
@@ -349,9 +280,7 @@ static int save_xbzrle_page(QEMUFile *f, uint8_t *current_data,

    if (!cache_is_cached(XBZRLE.cache, current_addr)) {
        if (!last_stage) {
-            if (cache_insert(XBZRLE.cache, current_addr, current_data) == -1) {
-                return -1;
-            }
+            cache_insert(XBZRLE.cache, current_addr, current_data);
        }
        acct_info.xbzrle_cache_miss++;
        return -1;
@@ -394,6 +323,18 @@ static int save_xbzrle_page(QEMUFile *f, uint8_t *current_data,
    return bytes_sent;
 }

+
+/* This is the last block that we have visited serching for dirty pages
+ */
+static RAMBlock *last_seen_block;
+/* This is the last block from where we have sent data */
+static RAMBlock *last_sent_block;
+static ram_addr_t last_offset;
+static unsigned long *migration_bitmap;
+static uint64_t migration_dirty_pages;
+static uint32_t last_version;
+static bool ram_bulk_stage;
+
 static inline
 ram_addr_t migration_bitmap_find_and_reset_dirty(MemoryRegion *mr,
                                                 ram_addr_t start)
@@ -418,10 +359,11 @@ ram_addr_t migration_bitmap_find_and_reset_dirty(MemoryRegion *mr,
    return (next - base) << TARGET_PAGE_BITS;
 }

-static inline bool migration_bitmap_set_dirty(ram_addr_t addr)
+static inline bool migration_bitmap_set_dirty(MemoryRegion *mr,
+                                              ram_addr_t offset)
 {
    bool ret;
-    int nr = addr >> TARGET_PAGE_BITS;
+    int nr = (mr->ram_addr + offset) >> TARGET_PAGE_BITS;

    ret = test_and_set_bit(nr, migration_bitmap);

@@ -431,47 +373,12 @@ static inline bool migration_bitmap_set_dirty(ram_addr_t addr)
    return ret;
 }

-static void migration_bitmap_sync_range(ram_addr_t start, ram_addr_t length)
-{
-    ram_addr_t addr;
-    unsigned long page = BIT_WORD(start >> TARGET_PAGE_BITS);
-
-    /* start address is aligned at the start of a word? */
-    if (((page * BITS_PER_LONG) << TARGET_PAGE_BITS) == start) {
-        int k;
-        int nr = BITS_TO_LONGS(length >> TARGET_PAGE_BITS);
-        unsigned long *src = ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION];
-
-        for (k = page; k < page + nr; k++) {
-            if (src[k]) {
-                unsigned long new_dirty;
-                new_dirty = ~migration_bitmap[k];
-                migration_bitmap[k] |= src[k];
-                new_dirty &= src[k];
-                migration_dirty_pages += ctpopl(new_dirty);
-                src[k] = 0;
-            }
-        }
-    } else {
-        for (addr = 0; addr < length; addr += TARGET_PAGE_SIZE) {
-            if (cpu_physical_memory_get_dirty(start + addr,
-                                              TARGET_PAGE_SIZE,
-                                              DIRTY_MEMORY_MIGRATION)) {
-                cpu_physical_memory_reset_dirty(start + addr,
-                                                TARGET_PAGE_SIZE,
-                                                DIRTY_MEMORY_MIGRATION);
-                migration_bitmap_set_dirty(start + addr);
-            }
-        }
-    }
-}
-
-
 /* Needs iothread lock! */

 static void migration_bitmap_sync(void)
 {
    RAMBlock *block;
+    ram_addr_t addr;
    uint64_t num_dirty_pages_init = migration_dirty_pages;
    MigrationState *s = migrate_get_current();
    static int64_t start_time;
@@ -492,7 +399,13 @@ static void migration_bitmap_sync(void)
    address_space_sync_dirty_bitmap(&address_space_memory);

    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
-        migration_bitmap_sync_range(block->mr->ram_addr, block->length);
+        for (addr = 0; addr < block->length; addr += TARGET_PAGE_SIZE) {
+            if (memory_region_test_and_clear_dirty(block->mr,
+                                                   addr, TARGET_PAGE_SIZE,
+                                                   DIRTY_MEMORY_MIGRATION)) {
+                migration_bitmap_set_dirty(block->mr, addr);
+            }
+        }
    }
    trace_migration_bitmap_sync_end(migration_dirty_pages
                                    - num_dirty_pages_init);
@@ -565,7 +478,6 @@ static int ram_save_block(QEMUFile *f, bool last_stage)
        } else {
            int ret;
            uint8_t *p;
-            bool send_async = true;
            int cont = (block == last_sent_block) ?
                RAM_SAVE_FLAG_CONTINUE : 0;

@@ -576,9 +488,6 @@ static int ram_save_block(QEMUFile *f, bool last_stage)
            ret = ram_control_save_page(f, block->offset,
                               offset, TARGET_PAGE_SIZE, &bytes_sent);

-            XBZRLE_cache_lock();
-
-            current_addr = block->offset + offset;
            if (ret != RAM_SAVE_CONTROL_NOT_SUPP) {
                if (ret != RAM_SAVE_CONTROL_DELAYED) {
                    if (bytes_sent > 0) {
@@ -593,40 +502,23 @@ static int ram_save_block(QEMUFile *f, bool last_stage)
                                            RAM_SAVE_FLAG_COMPRESS);
                qemu_put_byte(f, 0);
                bytes_sent++;
-                /* Must let xbzrle know, otherwise a previous (now 0'd) cached
-                 * page would be stale
-                 */
-                xbzrle_cache_zero_page(current_addr);
            } else if (!ram_bulk_stage && migrate_use_xbzrle()) {
+                current_addr = block->offset + offset;
                bytes_sent = save_xbzrle_page(f, p, current_addr, block,
                                              offset, cont, last_stage);
                if (!last_stage) {
-                    /* We must send exactly what's in the xbzrle cache
-                     * even if the page wasn't xbzrle compressed, so that
-                     * it's right next time.
-                     */
                    p = get_cached_data(XBZRLE.cache, current_addr);
-
-                    /* Can't send this cached data async, since the cache page
-                     * might get updated before it gets to the wire
-                     */
-                    send_async = false;
                }
            }

            /* XBZRLE overflow or normal page */
            if (bytes_sent == -1) {
                bytes_sent = save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_PAGE);
-                if (send_async) {
-                    qemu_put_buffer_async(f, p, TARGET_PAGE_SIZE);
-                } else {
-                    qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
-                }
+                qemu_put_buffer_async(f, p, TARGET_PAGE_SIZE);
                bytes_sent += TARGET_PAGE_SIZE;
                acct_info.norm_pages++;
            }

-            XBZRLE_cache_unlock();
            /* if page is unmodified, continue to the next */
            if (bytes_sent > 0) {
                last_sent_block = block;
@@ -680,12 +572,6 @@ uint64_t ram_bytes_total(void)
    return total;
 }

-void free_xbzrle_decoded_buf(void)
-{
-    g_free(xbzrle_decoded_buf);
-    xbzrle_decoded_buf = NULL;
-}
-
 static void migration_end(void)
 {
    if (migration_bitmap) {
@@ -694,17 +580,14 @@ static void migration_end(void)
        migration_bitmap = NULL;
    }

-    XBZRLE_cache_lock();
    if (XBZRLE.cache) {
        cache_fini(XBZRLE.cache);
        g_free(XBZRLE.cache);
        g_free(XBZRLE.encoded_buf);
        g_free(XBZRLE.current_buf);
+        g_free(XBZRLE.decoded_buf);
        XBZRLE.cache = NULL;
-        XBZRLE.encoded_buf = NULL;
-        XBZRLE.current_buf = NULL;
    }
-    XBZRLE_cache_unlock();
 }

 static void ram_migration_cancel(void *opaque)
@@ -735,33 +618,15 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
    dirty_rate_high_cnt = 0;

    if (migrate_use_xbzrle()) {
-        qemu_mutex_lock_iothread();
        XBZRLE.cache = cache_init(migrate_xbzrle_cache_size() /
                                  TARGET_PAGE_SIZE,
                                  TARGET_PAGE_SIZE);
        if (!XBZRLE.cache) {
-            qemu_mutex_unlock_iothread();
            DPRINTF("Error creating cache\n");
            return -1;
        }
-        qemu_mutex_init(&XBZRLE.lock);
-        qemu_mutex_unlock_iothread();
-
-        /* We prefer not to abort if there is no memory */
-        XBZRLE.encoded_buf = g_try_malloc0(TARGET_PAGE_SIZE);
-        if (!XBZRLE.encoded_buf) {
-            DPRINTF("Error allocating encoded_buf\n");
-            return -1;
-        }
-
-        XBZRLE.current_buf = g_try_malloc(TARGET_PAGE_SIZE);
-        if (!XBZRLE.current_buf) {
-            DPRINTF("Error allocating current_buf\n");
-            g_free(XBZRLE.encoded_buf);
-            XBZRLE.encoded_buf = NULL;
-            return -1;
-        }
-
+        XBZRLE.encoded_buf = g_malloc0(TARGET_PAGE_SIZE);
+        XBZRLE.current_buf = g_malloc(TARGET_PAGE_SIZE);
        acct_clear();
    }

@@ -912,8 +777,8 @@ static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
    unsigned int xh_len;
    int xh_flags;

-    if (!xbzrle_decoded_buf) {
-        xbzrle_decoded_buf = g_malloc(TARGET_PAGE_SIZE);
+    if (!XBZRLE.decoded_buf) {
+        XBZRLE.decoded_buf = g_malloc(TARGET_PAGE_SIZE);
    }

    /* extract RLE header */
@@ -930,10 +795,10 @@ static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
        return -1;
    }
    /* load data and decode */
-    qemu_get_buffer(f, xbzrle_decoded_buf, xh_len);
+    qemu_get_buffer(f, XBZRLE.decoded_buf, xh_len);

    /* decode RLE */
-    ret = xbzrle_decode_buffer(xbzrle_decoded_buf, xh_len, host,
+    ret = xbzrle_decode_buffer(XBZRLE.decoded_buf, xh_len, host,
                               TARGET_PAGE_SIZE);
    if (ret == -1) {
        fprintf(stderr, "Failed to load XBZRLE page - decode error!\n");
@@ -997,7 +862,7 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
    seq_iter++;

    if (version_id != 4) {
-        ret = -EINVAL;
+        return -EINVAL;
    }

    while (!ret) {
@@ -1051,9 +916,7 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)

            host = host_from_stream_offset(f, addr, flags);
            if (!host) {
-                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
-                ret = -EINVAL;
-                break;
+                return -EINVAL;
            }

            ch = qemu_get_byte(f);
@@ -1063,18 +926,14 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)

            host = host_from_stream_offset(f, addr, flags);
            if (!host) {
-                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
-                ret = -EINVAL;
-                break;
+                return -EINVAL;
            }

            qemu_get_buffer(f, host, TARGET_PAGE_SIZE);
        } else if (flags & RAM_SAVE_FLAG_XBZRLE) {
            void *host = host_from_stream_offset(f, addr, flags);
            if (!host) {
-                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
-                ret = -EINVAL;
-                break;
+                return -EINVAL;
            }

            if (load_xbzrle(f, addr, host) < 0) {
@@ -220,7 +220,6 @@ aio_ctx_finalize(GSource     *source)
    thread_pool_free(ctx->thread_pool);
    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);
@@ -257,12 +256,6 @@ static void aio_timerlist_notify(void *opaque)
    aio_notify(opaque);
 }

-static void aio_rfifolock_cb(void *opaque)
-{
-    /* Kick owner thread in case they are blocked in aio_poll() */
-    aio_notify(opaque);
-}
-
 AioContext *aio_context_new(void)
 {
    AioContext *ctx;
@@ -270,7 +263,6 @@ AioContext *aio_context_new(void)
    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);
    event_notifier_init(&ctx->notifier, false);
    aio_set_event_notifier(ctx, &ctx->notifier, 
                           (EventNotifierHandler *)
@@ -289,13 +281,3 @@ void aio_context_unref(AioContext *ctx)
 {
    g_source_unref(&ctx->source);
 }
-
-void aio_context_acquire(AioContext *ctx)
-{
-    rfifolock_lock(&ctx->lock);
-}
-
-void aio_context_release(AioContext *ctx)
-{
-    rfifolock_unlock(&ctx->lock);
-}
@@ -95,7 +95,7 @@ static struct {
        }
    },

-    .period = { .hertz = 100 },
+    .period = { .hertz = 250 },
    .plive = 0,
    .log_to_monitor = 0,
    .try_poll_in = 1,
@@ -547,11 +547,11 @@ static int qpa_init_out (HWVoiceOut *hw, struct audsettings *as)
    ss.rate = as->freq;

    /*
-     * qemu audio tick runs at 100 Hz (by default), so processing
-     * data chunks worth 10 ms of sound should be a good fit.
+     * qemu audio tick runs at 250 Hz (by default), so processing
+     * data chunks worth 4 ms of sound should be a good fit.
     */
-    ba.tlength = pa_usec_to_bytes (10 * 1000, &ss);
-    ba.minreq = pa_usec_to_bytes (5 * 1000, &ss);
+    ba.tlength = pa_usec_to_bytes (4 * 1000, &ss);
+    ba.minreq = pa_usec_to_bytes (2 * 1000, &ss);
    ba.maxlength = -1;
    ba.prebuf = -1;

@@ -25,17 +25,8 @@
 #include "audio.h"
 #include "audio_int.h"

-#if SPICE_INTERFACE_PLAYBACK_MAJOR > 1 || SPICE_INTERFACE_PLAYBACK_MINOR >= 3
-#define LINE_OUT_SAMPLES (480 * 4)
-#else
-#define LINE_OUT_SAMPLES (256 * 4)
-#endif
-
-#if SPICE_INTERFACE_RECORD_MAJOR > 2 || SPICE_INTERFACE_RECORD_MINOR >= 3
-#define LINE_IN_SAMPLES (480 * 4)
-#else
-#define LINE_IN_SAMPLES (256 * 4)
-#endif
+#define LINE_IN_SAMPLES 1024
+#define LINE_OUT_SAMPLES 1024

 typedef struct SpiceRateCtl {
    int64_t               start_ticks;
@@ -120,11 +111,7 @@ static int line_out_init (HWVoiceOut *hw, struct audsettings *as)
    SpiceVoiceOut *out = container_of (hw, SpiceVoiceOut, hw);
    struct audsettings settings;

-#if SPICE_INTERFACE_PLAYBACK_MAJOR > 1 || SPICE_INTERFACE_PLAYBACK_MINOR >= 3
-    settings.freq       = spice_server_get_best_playback_rate(NULL);
-#else
    settings.freq       = SPICE_INTERFACE_PLAYBACK_FREQ;
-#endif
    settings.nchannels  = SPICE_INTERFACE_PLAYBACK_CHAN;
    settings.fmt        = AUD_FMT_S16;
    settings.endianness = AUDIO_HOST_ENDIANNESS;
@@ -135,9 +122,6 @@ static int line_out_init (HWVoiceOut *hw, struct audsettings *as)

    out->sin.base.sif = &playback_sif.base;
    qemu_spice_add_interface (&out->sin.base);
-#if SPICE_INTERFACE_PLAYBACK_MAJOR > 1 || SPICE_INTERFACE_PLAYBACK_MINOR >= 3
-    spice_server_set_playback_rate(&out->sin, settings.freq);
-#endif
    return 0;
 }

@@ -248,11 +232,7 @@ static int line_in_init (HWVoiceIn *hw, struct audsettings *as)
    SpiceVoiceIn *in = container_of (hw, SpiceVoiceIn, hw);
    struct audsettings settings;

-#if SPICE_INTERFACE_RECORD_MAJOR > 2 || SPICE_INTERFACE_RECORD_MINOR >= 3
-    settings.freq       = spice_server_get_best_record_rate(NULL);
-#else
    settings.freq       = SPICE_INTERFACE_RECORD_FREQ;
-#endif
    settings.nchannels  = SPICE_INTERFACE_RECORD_CHAN;
    settings.fmt        = AUD_FMT_S16;
    settings.endianness = AUDIO_HOST_ENDIANNESS;
@@ -263,9 +243,6 @@ static int line_in_init (HWVoiceIn *hw, struct audsettings *as)

    in->sin.base.sif = &record_sif.base;
    qemu_spice_add_interface (&in->sin.base);
-#if SPICE_INTERFACE_RECORD_MAJOR > 2 || SPICE_INTERFACE_RECORD_MINOR >= 3
-    spice_server_set_record_rate(&in->sin, settings.freq);
-#endif
    return 0;
 }

@@ -566,10 +566,8 @@ CharDriverState *chr_baum_init(void)
    BaumDriverState *baum;
    CharDriverState *chr;
    brlapi_handle_t *handle;
-#if defined(CONFIG_SDL)
-#if SDL_COMPILEDVERSION < SDL_VERSIONNUM(2, 0, 0)
+#ifdef CONFIG_SDL
    SDL_SysWMinfo info;
-#endif
 #endif
    int tty;

@@ -597,14 +595,12 @@ CharDriverState *chr_baum_init(void)
        goto fail;
    }

-#if defined(CONFIG_SDL)
-#if SDL_COMPILEDVERSION < SDL_VERSIONNUM(2, 0, 0)
+#ifdef CONFIG_SDL
    memset(&info, 0, sizeof(info));
    SDL_VERSION(&info.version);
    if (SDL_GetWMInfo(&info))
        tty = info.info.x11.wmwindow;
    else
-#endif
 #endif
        tty = BRLAPI_TTY_DEFAULT;

@@ -123,15 +123,15 @@ static void rng_random_init(Object *obj)
                            NULL);

    s->filename = g_strdup("/dev/random");
-    s->fd = -1;
 }

 static void rng_random_finalize(Object *obj)
 {
    RndRandom *s = RNG_RANDOM(obj);

+    qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
+
    if (s->fd != -1) {
-        qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
        qemu_close(s->fd);
    }

@@ -12,7 +12,6 @@

 #include "sysemu/rng.h"
 #include "qapi/qmp/qerror.h"
-#include "qom/object_interfaces.h"

 void rng_backend_request_entropy(RngBackend *s, size_t size,
                                 EntropyReceiveFunc *receive_entropy,
@@ -41,9 +40,9 @@ static bool rng_backend_prop_get_opened(Object *obj, Error **errp)
    return s->opened;
 }

-static void rng_backend_complete(UserCreatable *uc, Error **errp)
+void rng_backend_open(RngBackend *s, Error **errp)
 {
-    object_property_set_bool(OBJECT(uc), true, "opened", errp);
+    object_property_set_bool(OBJECT(s), true, "opened", errp);
 }

 static void rng_backend_prop_set_opened(Object *obj, bool value, Error **errp)
@@ -77,25 +76,13 @@ static void rng_backend_init(Object *obj)
                             NULL);
 }

-static void rng_backend_class_init(ObjectClass *oc, void *data)
-{
-    UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
-
-    ucc->complete = rng_backend_complete;
-}
-
 static const TypeInfo rng_backend_info = {
    .name = TYPE_RNG_BACKEND,
    .parent = TYPE_OBJECT,
    .instance_size = sizeof(RngBackend),
    .instance_init = rng_backend_init,
    .class_size = sizeof(RngBackendClass),
-    .class_init = rng_backend_class_init,
    .abstract = true,
-    .interfaces = (InterfaceInfo[]) {
-        { TYPE_USER_CREATABLE },
-        { }
-    }
 };

 static void register_types(void)
@@ -58,7 +58,6 @@ typedef struct BlkMigDevState {
    /* Protected by block migration lock.  */
    unsigned long *aio_bitmap;
    int64_t completed_sectors;
-    BdrvDirtyBitmap *dirty_bitmap;
 } BlkMigDevState;

 typedef struct BlkMigBlock {
@@ -310,21 +309,12 @@ static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds)

 /* Called with iothread lock taken.  */

-static void set_dirty_tracking(void)
+static void set_dirty_tracking(int enable)
 {
    BlkMigDevState *bmds;

    QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
-        bmds->dirty_bitmap = bdrv_create_dirty_bitmap(bmds->bs, BLOCK_SIZE);
-    }
-}
-
-static void unset_dirty_tracking(void)
-{
-    BlkMigDevState *bmds;
-
-    QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
-        bdrv_release_dirty_bitmap(bmds->bs, bmds->dirty_bitmap);
+        bdrv_set_dirty_tracking(bmds->bs, enable ? BLOCK_SIZE : 0);
    }
 }

@@ -442,7 +432,7 @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
        } else {
            blk_mig_unlock();
        }
-        if (bdrv_get_dirty(bmds->bs, bmds->dirty_bitmap, sector)) {
+        if (bdrv_get_dirty(bmds->bs, sector)) {

            if (total_sectors - sector < BDRV_SECTORS_PER_DIRTY_CHUNK) {
                nr_sectors = total_sectors - sector;
@@ -564,7 +554,7 @@ 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->bs, bmds->dirty_bitmap);
+        dirty += bdrv_get_dirty_count(bmds->bs);
    }

    return dirty << BDRV_SECTOR_BITS;
@@ -579,7 +569,7 @@ static void blk_mig_cleanup(void)

    bdrv_drain_all();

-    unset_dirty_tracking();
+    set_dirty_tracking(0);

    blk_mig_lock();
    while ((bmds = QSIMPLEQ_FIRST(&block_mig_state.bmds_list)) != NULL) {
@@ -614,7 +604,7 @@ static int block_save_setup(QEMUFile *f, void *opaque)
    init_blk_migration(f);

    /* start track dirty blocks */
-    set_dirty_tracking();
+    set_dirty_tracking(1);
    qemu_mutex_unlock_iothread();

    ret = flush_blks(f);
@@ -790,8 +780,7 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
            }

            if (flags & BLK_MIG_FLAG_ZERO_BLOCK) {
-                ret = bdrv_write_zeroes(bs, addr, nr_sectors,
-                                        BDRV_REQ_MAY_UNMAP);
+                ret = bdrv_write_zeroes(bs, addr, nr_sectors);
            } else {
                buf = g_malloc(BLOCK_SIZE);
                qemu_get_buffer(f, buf, BLOCK_SIZE);
@@ -3,7 +3,6 @@ block-obj-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-c
 block-obj-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
 block-obj-y += qed-check.o
 block-obj-$(CONFIG_VHDX) += vhdx.o vhdx-endian.o vhdx-log.o
-block-obj-$(CONFIG_QUORUM) += quorum.o
 block-obj-y += parallels.o blkdebug.o blkverify.o
 block-obj-y += snapshot.o qapi.o
 block-obj-$(CONFIG_WIN32) += raw-win32.o win32-aio.o
@@ -11,9 +10,8 @@ block-obj-$(CONFIG_POSIX) += raw-posix.o
 block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o

 ifeq ($(CONFIG_POSIX),y)
-block-obj-y += nbd.o nbd-client.o sheepdog.o
+block-obj-y += nbd.o sheepdog.o
 block-obj-$(CONFIG_LIBISCSI) += iscsi.o
-block-obj-$(CONFIG_LIBNFS) += nfs.o
 block-obj-$(CONFIG_CURL) += curl.o
 block-obj-$(CONFIG_RBD) += rbd.o
 block-obj-$(CONFIG_GLUSTERFS) += gluster.o
@@ -25,15 +23,4 @@ common-obj-y += commit.o
 common-obj-y += mirror.o
 common-obj-y += backup.o

-iscsi.o-cflags     := $(LIBISCSI_CFLAGS)
-iscsi.o-libs       := $(LIBISCSI_LIBS)
-curl.o-cflags      := $(CURL_CFLAGS)
-curl.o-libs        := $(CURL_LIBS)
-rbd.o-cflags       := $(RBD_CFLAGS)
-rbd.o-libs         := $(RBD_LIBS)
-gluster.o-cflags   := $(GLUSTERFS_CFLAGS)
-gluster.o-libs     := $(GLUSTERFS_LIBS)
-ssh.o-cflags       := $(LIBSSH2_CFLAGS)
-ssh.o-libs         := $(LIBSSH2_LIBS)
-qcow.o-libs        := -lz
-linux-aio.o-libs   := -laio
+$(obj)/curl.o: QEMU_CFLAGS+=$(CURL_CFLAGS)
@@ -138,8 +138,7 @@ static int coroutine_fn backup_do_cow(BlockDriverState *bs,

        if (buffer_is_zero(iov.iov_base, iov.iov_len)) {
            ret = bdrv_co_write_zeroes(job->target,
-                                       start * BACKUP_SECTORS_PER_CLUSTER,
-                                       n, BDRV_REQ_MAY_UNMAP);
+                                       start * BACKUP_SECTORS_PER_CLUSTER, n);
        } else {
            ret = bdrv_co_writev(job->target,
                                 start * BACKUP_SECTORS_PER_CLUSTER, n,
@@ -181,13 +180,8 @@ static int coroutine_fn backup_before_write_notify(
        void *opaque)
 {
    BdrvTrackedRequest *req = opaque;
-    int64_t sector_num = req->offset >> BDRV_SECTOR_BITS;
-    int nb_sectors = req->bytes >> BDRV_SECTOR_BITS;

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

 static void backup_set_speed(BlockJob *job, int64_t speed, Error **errp)
@@ -186,14 +186,6 @@ static const char *event_names[BLKDBG_EVENT_MAX] = {

    [BLKDBG_FLUSH_TO_OS]                    = "flush_to_os",
    [BLKDBG_FLUSH_TO_DISK]                  = "flush_to_disk",
-
-    [BLKDBG_PWRITEV_RMW_HEAD]               = "pwritev_rmw.head",
-    [BLKDBG_PWRITEV_RMW_AFTER_HEAD]         = "pwritev_rmw.after_head",
-    [BLKDBG_PWRITEV_RMW_TAIL]               = "pwritev_rmw.tail",
-    [BLKDBG_PWRITEV_RMW_AFTER_TAIL]         = "pwritev_rmw.after_tail",
-    [BLKDBG_PWRITEV]                        = "pwritev",
-    [BLKDBG_PWRITEV_ZERO]                   = "pwritev_zero",
-    [BLKDBG_PWRITEV_DONE]                   = "pwritev_done",
 };

 static int get_event_by_name(const char *name, BlkDebugEvent *event)
@@ -279,33 +271,19 @@ static void remove_rule(BlkdebugRule *rule)
    g_free(rule);
 }

-static int read_config(BDRVBlkdebugState *s, const char *filename,
-                       QDict *options, Error **errp)
+static int read_config(BDRVBlkdebugState *s, const char *filename)
 {
-    FILE *f = NULL;
+    FILE *f;
    int ret;
    struct add_rule_data d;
-    Error *local_err = NULL;

-    if (filename) {
-        f = fopen(filename, "r");
-        if (f == NULL) {
-            error_setg_errno(errp, errno, "Could not read blkdebug config file");
-            return -errno;
-        }
-
-        ret = qemu_config_parse(f, config_groups, filename);
-        if (ret < 0) {
-            error_setg(errp, "Could not parse blkdebug config file");
-            ret = -EINVAL;
-            goto fail;
-        }
+    f = fopen(filename, "r");
+    if (f == NULL) {
+        return -errno;
    }

-    qemu_config_parse_qdict(options, config_groups, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        ret = -EINVAL;
+    ret = qemu_config_parse(f, config_groups, filename);
+    if (ret < 0) {
        goto fail;
    }

@@ -320,9 +298,7 @@ static int read_config(BDRVBlkdebugState *s, const char *filename,
 fail:
    qemu_opts_reset(&inject_error_opts);
    qemu_opts_reset(&set_state_opts);
-    if (f) {
-        fclose(f);
-    }
+    fclose(f);
    return ret;
 }

@@ -334,9 +310,7 @@ static void blkdebug_parse_filename(const char *filename, QDict *options,

    /* Parse the blkdebug: prefix */
    if (!strstart(filename, "blkdebug:", &filename)) {
-        /* There was no prefix; therefore, all options have to be already
-           present in the QDict (except for the filename) */
-        qdict_put(options, "x-image", qstring_from_str(filename));
+        error_setg(errp, "File name string must start with 'blkdebug:'");
        return;
    }

@@ -372,11 +346,6 @@ static QemuOptsList runtime_opts = {
            .type = QEMU_OPT_STRING,
            .help = "[internal use only, will be removed]",
        },
-        {
-            .name = "align",
-            .type = QEMU_OPT_SIZE,
-            .help = "Required alignment in bytes",
-        },
        { /* end of list */ }
    },
 };
@@ -387,53 +356,46 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
    BDRVBlkdebugState *s = bs->opaque;
    QemuOpts *opts;
    Error *local_err = NULL;
-    const char *config;
-    uint64_t align;
+    const char *filename, *config;
    int ret;

-    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
+    opts = qemu_opts_create_nofail(&runtime_opts);
    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
        ret = -EINVAL;
-        goto out;
+        goto fail;
    }

-    /* Read rules from config file or command line options */
+    /* Read rules from config file */
    config = qemu_opt_get(opts, "config");
-    ret = read_config(s, config, options, errp);
-    if (ret) {
-        goto out;
+    if (config) {
+        ret = read_config(s, config);
+        if (ret < 0) {
+            error_setg_errno(errp, -ret, "Could not read blkdebug config file");
+            goto fail;
+        }
    }

    /* Set initial state */
    s->state = 1;

    /* Open the backing file */
-    assert(bs->file == NULL);
-    ret = bdrv_open_image(&bs->file, qemu_opt_get(opts, "x-image"), options, "image",
-                          flags | BDRV_O_PROTOCOL, false, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto out;
+    filename = qemu_opt_get(opts, "x-image");
+    if (filename == NULL) {
+        error_setg(errp, "Could not retrieve image file name");
+        ret = -EINVAL;
+        goto fail;
    }

-    /* Set request alignment */
-    align = qemu_opt_get_size(opts, "align", bs->request_alignment);
-    if (align > 0 && align < INT_MAX && !(align & (align - 1))) {
-        bs->request_alignment = align;
-    } else {
-        error_setg(errp, "Invalid alignment");
-        ret = -EINVAL;
-        goto fail_unref;
+    ret = bdrv_file_open(&bs->file, filename, NULL, flags, &local_err);
+    if (ret < 0) {
+        error_propagate(errp, local_err);
+        goto fail;
    }

    ret = 0;
-    goto out;
-
-fail_unref:
-    bdrv_unref(bs->file);
-out:
+fail:
    qemu_opts_del(opts);
    return ret;
 }
@@ -632,9 +594,9 @@ static int blkdebug_debug_breakpoint(BlockDriverState *bs, const char *event,
 static int blkdebug_debug_resume(BlockDriverState *bs, const char *tag)
 {
    BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugSuspendedReq *r, *next;
+    BlkdebugSuspendedReq *r;

-    QLIST_FOREACH_SAFE(r, &s->suspended_reqs, next, next) {
+    QLIST_FOREACH(r, &s->suspended_reqs, next) {
        if (!strcmp(r->tag, tag)) {
            qemu_coroutine_enter(r->co, NULL);
            return 0;
@@ -643,31 +605,6 @@ static int blkdebug_debug_resume(BlockDriverState *bs, const char *tag)
    return -ENOENT;
 }

-static int blkdebug_debug_remove_breakpoint(BlockDriverState *bs,
-                                            const char *tag)
-{
-    BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugSuspendedReq *r, *r_next;
-    BlkdebugRule *rule, *next;
-    int i, ret = -ENOENT;
-
-    for (i = 0; i < BLKDBG_EVENT_MAX; i++) {
-        QLIST_FOREACH_SAFE(rule, &s->rules[i], next, next) {
-            if (rule->action == ACTION_SUSPEND &&
-                !strcmp(rule->options.suspend.tag, tag)) {
-                remove_rule(rule);
-                ret = 0;
-            }
-        }
-    }
-    QLIST_FOREACH_SAFE(r, &s->suspended_reqs, next, r_next) {
-        if (!strcmp(r->tag, tag)) {
-            qemu_coroutine_enter(r->co, NULL);
-            ret = 0;
-        }
-    }
-    return ret;
-}

 static bool blkdebug_debug_is_suspended(BlockDriverState *bs, const char *tag)
 {
@@ -702,8 +639,6 @@ static BlockDriver bdrv_blkdebug = {

    .bdrv_debug_event           = blkdebug_debug_event,
    .bdrv_debug_breakpoint      = blkdebug_debug_breakpoint,
-    .bdrv_debug_remove_breakpoint
-                                = blkdebug_debug_remove_breakpoint,
    .bdrv_debug_resume          = blkdebug_debug_resume,
    .bdrv_debug_is_suspended    = blkdebug_debug_is_suspended,
 };
@@ -78,9 +78,7 @@ static void blkverify_parse_filename(const char *filename, QDict *options,

    /* Parse the blkverify: prefix */
    if (!strstart(filename, "blkverify:", &filename)) {
-        /* There was no prefix; therefore, all options have to be already
-           present in the QDict (except for the filename) */
-        qdict_put(options, "x-image", qstring_from_str(filename));
+        error_setg(errp, "File name string must start with 'blkverify:'");
        return;
    }

@@ -124,31 +122,44 @@ static int blkverify_open(BlockDriverState *bs, QDict *options, int flags,
    BDRVBlkverifyState *s = bs->opaque;
    QemuOpts *opts;
    Error *local_err = NULL;
+    const char *filename, *raw;
    int ret;

-    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
+    opts = qemu_opts_create_nofail(&runtime_opts);
    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
        ret = -EINVAL;
        goto fail;
    }

-    /* Open the raw file */
-    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);
+    /* Parse the raw image filename */
+    raw = qemu_opt_get(opts, "x-raw");
+    if (raw == NULL) {
+        error_setg(errp, "Could not retrieve raw image filename");
+        ret = -EINVAL;
+        goto fail;
+    }
+
+    ret = bdrv_file_open(&bs->file, raw, NULL, flags, &local_err);
    if (ret < 0) {
        error_propagate(errp, local_err);
        goto fail;
    }

    /* Open the test file */
-    assert(s->test_file == NULL);
-    ret = bdrv_open_image(&s->test_file, qemu_opt_get(opts, "x-image"), options,
-                          "test", flags, false, &local_err);
+    filename = qemu_opt_get(opts, "x-image");
+    if (filename == NULL) {
+        error_setg(errp, "Could not retrieve test image filename");
+        ret = -EINVAL;
+        goto fail;
+    }
+
+    s->test_file = bdrv_new("");
+    ret = bdrv_open(s->test_file, filename, NULL, flags, NULL, &local_err);
    if (ret < 0) {
        error_propagate(errp, local_err);
+        bdrv_unref(s->test_file);
        s->test_file = NULL;
        goto fail;
    }
@@ -173,6 +184,110 @@ static int64_t blkverify_getlength(BlockDriverState *bs)
    return bdrv_getlength(s->test_file);
 }

+/**
+ * Check that I/O vector contents are identical
+ *
+ * @a:          I/O vector
+ * @b:          I/O vector
+ * @ret:        Offset to first mismatching byte or -1 if match
+ */
+static ssize_t blkverify_iovec_compare(QEMUIOVector *a, QEMUIOVector *b)
+{
+    int i;
+    ssize_t offset = 0;
+
+    assert(a->niov == b->niov);
+    for (i = 0; i < a->niov; i++) {
+        size_t len = 0;
+        uint8_t *p = (uint8_t *)a->iov[i].iov_base;
+        uint8_t *q = (uint8_t *)b->iov[i].iov_base;
+
+        assert(a->iov[i].iov_len == b->iov[i].iov_len);
+        while (len < a->iov[i].iov_len && *p++ == *q++) {
+            len++;
+        }
+
+        offset += len;
+
+        if (len != a->iov[i].iov_len) {
+            return offset;
+        }
+    }
+    return -1;
+}
+
+typedef struct {
+    int src_index;
+    struct iovec *src_iov;
+    void *dest_base;
+} IOVectorSortElem;
+
+static int sortelem_cmp_src_base(const void *a, const void *b)
+{
+    const IOVectorSortElem *elem_a = a;
+    const IOVectorSortElem *elem_b = b;
+
+    /* Don't overflow */
+    if (elem_a->src_iov->iov_base < elem_b->src_iov->iov_base) {
+        return -1;
+    } else if (elem_a->src_iov->iov_base > elem_b->src_iov->iov_base) {
+        return 1;
+    } else {
+        return 0;
+    }
+}
+
+static int sortelem_cmp_src_index(const void *a, const void *b)
+{
+    const IOVectorSortElem *elem_a = a;
+    const IOVectorSortElem *elem_b = b;
+
+    return elem_a->src_index - elem_b->src_index;
+}
+
+/**
+ * Copy contents of I/O vector
+ *
+ * The relative relationships of overlapping iovecs are preserved.  This is
+ * necessary to ensure identical semantics in the cloned I/O vector.
+ */
+static void blkverify_iovec_clone(QEMUIOVector *dest, const QEMUIOVector *src,
+                                  void *buf)
+{
+    IOVectorSortElem sortelems[src->niov];
+    void *last_end;
+    int i;
+
+    /* Sort by source iovecs by base address */
+    for (i = 0; i < src->niov; i++) {
+        sortelems[i].src_index = i;
+        sortelems[i].src_iov = &src->iov[i];
+    }
+    qsort(sortelems, src->niov, sizeof(sortelems[0]), sortelem_cmp_src_base);
+
+    /* Allocate buffer space taking into account overlapping iovecs */
+    last_end = NULL;
+    for (i = 0; i < src->niov; i++) {
+        struct iovec *cur = sortelems[i].src_iov;
+        ptrdiff_t rewind = 0;
+
+        /* Detect overlap */
+        if (last_end && last_end > cur->iov_base) {
+            rewind = last_end - cur->iov_base;
+        }
+
+        sortelems[i].dest_base = buf - rewind;
+        buf += cur->iov_len - MIN(rewind, cur->iov_len);
+        last_end = MAX(cur->iov_base + cur->iov_len, last_end);
+    }
+
+    /* Sort by source iovec index and build destination iovec */
+    qsort(sortelems, src->niov, sizeof(sortelems[0]), sortelem_cmp_src_index);
+    for (i = 0; i < src->niov; i++) {
+        qemu_iovec_add(dest, sortelems[i].dest_base, src->iov[i].iov_len);
+    }
+}
+
 static BlkverifyAIOCB *blkverify_aio_get(BlockDriverState *bs, bool is_write,
                                         int64_t sector_num, QEMUIOVector *qiov,
                                         int nb_sectors,
@@ -236,7 +351,7 @@ static void blkverify_aio_cb(void *opaque, int ret)

 static void blkverify_verify_readv(BlkverifyAIOCB *acb)
 {
-    ssize_t offset = qemu_iovec_compare(acb->qiov, &acb->raw_qiov);
+    ssize_t offset = blkverify_iovec_compare(acb->qiov, &acb->raw_qiov);
    if (offset != -1) {
        blkverify_err(acb, "contents mismatch in sector %" PRId64,
                      acb->sector_num + (int64_t)(offset / BDRV_SECTOR_SIZE));
@@ -254,7 +369,7 @@ static BlockDriverAIOCB *blkverify_aio_readv(BlockDriverState *bs,
    acb->verify = blkverify_verify_readv;
    acb->buf = qemu_blockalign(bs->file, qiov->size);
    qemu_iovec_init(&acb->raw_qiov, acb->qiov->niov);
-    qemu_iovec_clone(&acb->raw_qiov, qiov, acb->buf);
+    blkverify_iovec_clone(&acb->raw_qiov, qiov, acb->buf);

    bdrv_aio_readv(s->test_file, sector_num, qiov, nb_sectors,
                   blkverify_aio_cb, acb);
@@ -288,20 +403,6 @@ static BlockDriverAIOCB *blkverify_aio_flush(BlockDriverState *bs,
    return bdrv_aio_flush(s->test_file, cb, opaque);
 }

-static bool blkverify_recurse_is_first_non_filter(BlockDriverState *bs,
-                                                  BlockDriverState *candidate)
-{
-    BDRVBlkverifyState *s = bs->opaque;
-
-    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, candidate);
-}
-
 static BlockDriver bdrv_blkverify = {
    .format_name            = "blkverify",
    .protocol_name          = "blkverify",
@@ -316,8 +417,7 @@ static BlockDriver bdrv_blkverify = {
    .bdrv_aio_writev        = blkverify_aio_writev,
    .bdrv_aio_flush         = blkverify_aio_flush,

-    .is_filter              = true,
-    .bdrv_recurse_is_first_non_filter = blkverify_recurse_is_first_non_filter,
+    .bdrv_check_ext_snapshot = bdrv_check_ext_snapshot_forbidden,
 };

 static void bdrv_blkverify_init(void)
@@ -113,8 +113,7 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
        strcmp(bochs.subtype, GROWING_TYPE) ||
 	((le32_to_cpu(bochs.version) != HEADER_VERSION) &&
 	(le32_to_cpu(bochs.version) != HEADER_V1))) {
-        error_setg(errp, "Image not in Bochs format");
-        return -EINVAL;
+        return -EMEDIUMTYPE;
    }

    if (le32_to_cpu(bochs.version) == HEADER_V1) {
@@ -148,26 +147,16 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
    s->extent_blocks = 1 + (le32_to_cpu(bochs.extent) - 1) / 512;

    s->extent_size = le32_to_cpu(bochs.extent);
-    if (s->extent_size < BDRV_SECTOR_SIZE) {
-        /* bximage actually never creates extents smaller than 4k */
-        error_setg(errp, "Extent size must be at least 512");
-        ret = -EINVAL;
-        goto fail;
-    } else if (!is_power_of_2(s->extent_size)) {
-        error_setg(errp, "Extent size %" PRIu32 " is not a power of two",
-                   s->extent_size);
-        ret = -EINVAL;
-        goto fail;
+    if (s->extent_size == 0) {
+        error_setg(errp, "Extent size may not be zero");
+        return -EINVAL;
    } else if (s->extent_size > 0x800000) {
        error_setg(errp, "Extent size %" PRIu32 " is too large",
                   s->extent_size);
-        ret = -EINVAL;
-        goto fail;
+        return -EINVAL;
    }

-    if (s->catalog_size < DIV_ROUND_UP(bs->total_sectors,
-                                       s->extent_size / BDRV_SECTOR_SIZE))
-    {
+    if (s->catalog_size < bs->total_sectors / s->extent_size) {
        error_setg(errp, "Catalog size is too small for this disk size");
        ret = -EINVAL;
        goto fail;
@@ -198,7 +198,13 @@ void commit_start(BlockDriverState *bs, BlockDriverState *base,
        return;
    }

-    assert(top != bs);
+    /* Once we support top == active layer, remove this check */
+    if (top == bs) {
+        error_setg(errp,
+                   "Top image as the active layer is currently unsupported");
+        return;
+    }
+
    if (top == base) {
        error_setg(errp, "Invalid files for merge: top and base are the same");
        return;
@@ -74,8 +74,7 @@ static int cow_open(BlockDriverState *bs, QDict *options, int flags,
    }

    if (be32_to_cpu(cow_header.magic) != COW_MAGIC) {
-        error_setg(errp, "Image not in COW format");
-        ret = -EINVAL;
+        ret = -EMEDIUMTYPE;
        goto fail;
    }

@@ -83,7 +82,7 @@ static int cow_open(BlockDriverState *bs, QDict *options, int flags,
        char version[64];
        snprintf(version, sizeof(version),
               "COW version %d", cow_header.version);
-        error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+        qerror_report(QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
            bs->device_name, "cow", version);
        ret = -ENOTSUP;
        goto fail;
@@ -104,18 +103,40 @@ static int cow_open(BlockDriverState *bs, QDict *options, int flags,
    return ret;
 }

-static inline void cow_set_bits(uint8_t *bitmap, int start, int64_t nb_sectors)
+/*
+ * XXX(hch): right now these functions are extremely inefficient.
+ * We should just read the whole bitmap we'll need in one go instead.
+ */
+static inline int cow_set_bit(BlockDriverState *bs, int64_t bitnum, bool *first)
 {
-    int64_t bitnum = start, last = start + nb_sectors;
-    while (bitnum < last) {
-        if ((bitnum & 7) == 0 && bitnum + 8 <= last) {
-            bitmap[bitnum / 8] = 0xFF;
-            bitnum += 8;
-            continue;
-        }
-        bitmap[bitnum/8] |= (1 << (bitnum % 8));
-        bitnum++;
+    uint64_t offset = sizeof(struct cow_header_v2) + bitnum / 8;
+    uint8_t bitmap;
+    int ret;
+
+    ret = bdrv_pread(bs->file, offset, &bitmap, sizeof(bitmap));
+    if (ret < 0) {
+       return ret;
    }
+
+    if (bitmap & (1 << (bitnum % 8))) {
+        return 0;
+    }
+
+    if (*first) {
+        ret = bdrv_flush(bs->file);
+        if (ret < 0) {
+            return ret;
+        }
+        *first = false;
+    }
+
+    bitmap |= (1 << (bitnum % 8));
+
+    ret = bdrv_pwrite(bs->file, offset, &bitmap, sizeof(bitmap));
+    if (ret < 0) {
+       return ret;
+    }
+    return 0;
 }

 #define BITS_PER_BITMAP_SECTOR (512 * 8)
@@ -153,34 +174,18 @@ static int coroutine_fn cow_co_is_allocated(BlockDriverState *bs,
 {
    int64_t bitnum = sector_num + sizeof(struct cow_header_v2) * 8;
    uint64_t offset = (bitnum / 8) & -BDRV_SECTOR_SIZE;
-    bool first = true;
-    int changed = 0, same = 0;
+    uint8_t bitmap[BDRV_SECTOR_SIZE];
+    int ret;
+    int changed;

-    do {
-        int ret;
-        uint8_t bitmap[BDRV_SECTOR_SIZE];
+    ret = bdrv_pread(bs->file, offset, &bitmap, sizeof(bitmap));
+    if (ret < 0) {
+        return ret;
+    }

-        bitnum &= BITS_PER_BITMAP_SECTOR - 1;
-        int sector_bits = MIN(nb_sectors, BITS_PER_BITMAP_SECTOR - bitnum);
-
-        ret = bdrv_pread(bs->file, offset, &bitmap, sizeof(bitmap));
-        if (ret < 0) {
-            return ret;
-        }
-
-        if (first) {
-            changed = cow_test_bit(bitnum, bitmap);
-            first = false;
-        }
-
-        same += cow_find_streak(bitmap, changed, bitnum, nb_sectors);
-
-        bitnum += sector_bits;
-        nb_sectors -= sector_bits;
-        offset += BDRV_SECTOR_SIZE;
-    } while (nb_sectors);
-
-    *num_same = same;
+    bitnum &= BITS_PER_BITMAP_SECTOR - 1;
+    changed = cow_test_bit(bitnum, bitmap);
+    *num_same = cow_find_streak(bitmap, changed, bitnum, nb_sectors);
    return changed;
 }

@@ -199,52 +204,18 @@ static int64_t coroutine_fn cow_co_get_block_status(BlockDriverState *bs,
 static int cow_update_bitmap(BlockDriverState *bs, int64_t sector_num,
        int nb_sectors)
 {
-    int64_t bitnum = sector_num + sizeof(struct cow_header_v2) * 8;
-    uint64_t offset = (bitnum / 8) & -BDRV_SECTOR_SIZE;
+    int error = 0;
+    int i;
    bool first = true;
-    int sector_bits;

-    for ( ; nb_sectors;
-            bitnum += sector_bits,
-            nb_sectors -= sector_bits,
-            offset += BDRV_SECTOR_SIZE) {
-        int ret, set;
-        uint8_t bitmap[BDRV_SECTOR_SIZE];
-
-        bitnum &= BITS_PER_BITMAP_SECTOR - 1;
-        sector_bits = MIN(nb_sectors, BITS_PER_BITMAP_SECTOR - bitnum);
-
-        ret = bdrv_pread(bs->file, offset, &bitmap, sizeof(bitmap));
-        if (ret < 0) {
-            return ret;
-        }
-
-        /* Skip over any already set bits */
-        set = cow_find_streak(bitmap, 1, bitnum, sector_bits);
-        bitnum += set;
-        sector_bits -= set;
-        nb_sectors -= set;
-        if (!sector_bits) {
-            continue;
-        }
-
-        if (first) {
-            ret = bdrv_flush(bs->file);
-            if (ret < 0) {
-                return ret;
-            }
-            first = false;
-        }
-
-        cow_set_bits(bitmap, bitnum, sector_bits);
-
-        ret = bdrv_pwrite(bs->file, offset, &bitmap, sizeof(bitmap));
-        if (ret < 0) {
-            return ret;
+    for (i = 0; i < nb_sectors; i++) {
+        error = cow_set_bit(bs, sector_num + i, &first);
+        if (error) {
+            break;
        }
    }

-    return 0;
+    return error;
 }

 static int coroutine_fn cow_read(BlockDriverState *bs, int64_t sector_num,
@@ -347,15 +318,15 @@ static int cow_create(const char *filename, QEMUOptionParameter *options,

    ret = bdrv_create_file(filename, options, &local_err);
    if (ret < 0) {
-        error_propagate(errp, local_err);
+        qerror_report_err(local_err);
+        error_free(local_err);
        return ret;
    }

-    cow_bs = NULL;
-    ret = bdrv_open(&cow_bs, filename, NULL, NULL,
-                    BDRV_O_RDWR | BDRV_O_PROTOCOL, NULL, &local_err);
+    ret = bdrv_file_open(&cow_bs, filename, NULL, BDRV_O_RDWR, &local_err);
    if (ret < 0) {
-        error_propagate(errp, local_err);
+        qerror_report_err(local_err);
+        error_free(local_err);
        return ret;
    }

@@ -461,27 +461,30 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
    static int inited = 0;

    if (flags & BDRV_O_RDWR) {
-        error_setg(errp, "curl block device does not support writes");
+        qerror_report(ERROR_CLASS_GENERIC_ERROR,
+                      "curl block device does not support writes");
        return -EROFS;
    }

-    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
+    opts = qemu_opts_create_nofail(&runtime_opts);
    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
+    if (error_is_set(&local_err)) {
+        qerror_report_err(local_err);
+        error_free(local_err);
        goto out_noclean;
    }

    s->readahead_size = qemu_opt_get_size(opts, "readahead", READ_AHEAD_SIZE);
    if ((s->readahead_size & 0x1ff) != 0) {
-        error_setg(errp, "HTTP_READAHEAD_SIZE %zd is not a multiple of 512",
-                   s->readahead_size);
+        fprintf(stderr, "HTTP_READAHEAD_SIZE %zd is not a multiple of 512\n",
+                s->readahead_size);
        goto out_noclean;
    }

    file = qemu_opt_get(opts, "url");
    if (file == NULL) {
-        error_setg(errp, "curl block driver requires an 'url' option");
+        qerror_report(ERROR_CLASS_GENERIC_ERROR, "curl block driver requires "
+                      "an 'url' option");
        goto out_noclean;
    }

@@ -3,26 +3,42 @@
 *
 * Copyright (C) 2012 Bharata B Rao <bharata@linux.vnet.ibm.com>
 *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
+ * Pipe handling mechanism in AIO implementation is derived from
+ * block/rbd.c. Hence,
 *
+ * Copyright (C) 2010-2011 Christian Brunner <chb@muc.de>,
+ *                         Josh Durgin <josh.durgin@dreamhost.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Contributions after 2012-01-13 are licensed under the terms of the
+ * GNU GPL, version 2 or (at your option) any later version.
 */
 #include <glusterfs/api/glfs.h>
 #include "block/block_int.h"
+#include "qemu/sockets.h"
 #include "qemu/uri.h"

 typedef struct GlusterAIOCB {
+    BlockDriverAIOCB common;
    int64_t size;
    int ret;
+    bool *finished;
    QEMUBH *bh;
-    Coroutine *coroutine;
 } GlusterAIOCB;

 typedef struct BDRVGlusterState {
    struct glfs *glfs;
+    int fds[2];
    struct glfs_fd *fd;
+    int event_reader_pos;
+    GlusterAIOCB *event_acb;
 } BDRVGlusterState;

+#define GLUSTER_FD_READ  0
+#define GLUSTER_FD_WRITE 1
+
 typedef struct GlusterConf {
    char *server;
    int port;
@@ -33,13 +49,11 @@ typedef struct GlusterConf {

 static void qemu_gluster_gconf_free(GlusterConf *gconf)
 {
-    if (gconf) {
-        g_free(gconf->server);
-        g_free(gconf->volname);
-        g_free(gconf->image);
-        g_free(gconf->transport);
-        g_free(gconf);
-    }
+    g_free(gconf->server);
+    g_free(gconf->volname);
+    g_free(gconf->image);
+    g_free(gconf->transport);
+    g_free(gconf);
 }

 static int parse_volume_options(GlusterConf *gconf, char *path)
@@ -80,7 +94,7 @@ static int parse_volume_options(GlusterConf *gconf, char *path)
 * 'server' specifies the server where the volume file specification for
 * the given volume resides. This can be either hostname, ipv4 address
 * or ipv6 address. ipv6 address needs to be within square brackets [ ].
- * If transport type is 'unix', then 'server' field should not be specified.
+ * If transport type is 'unix', then 'server' field should not be specifed.
 * The 'socket' field needs to be populated with the path to unix domain
 * socket.
 *
@@ -117,7 +131,7 @@ static int qemu_gluster_parseuri(GlusterConf *gconf, const char *filename)
    }

    /* transport */
-    if (!uri->scheme || !strcmp(uri->scheme, "gluster")) {
+    if (!strcmp(uri->scheme, "gluster")) {
        gconf->transport = g_strdup("tcp");
    } else if (!strcmp(uri->scheme, "gluster+tcp")) {
        gconf->transport = g_strdup("tcp");
@@ -153,7 +167,7 @@ static int qemu_gluster_parseuri(GlusterConf *gconf, const char *filename)
        }
        gconf->server = g_strdup(qp->p[0].value);
    } else {
-        gconf->server = g_strdup(uri->server ? uri->server : "localhost");
+        gconf->server = g_strdup(uri->server);
        gconf->port = uri->port;
    }

@@ -165,8 +179,7 @@ out:
    return ret;
 }

-static struct glfs *qemu_gluster_init(GlusterConf *gconf, const char *filename,
-                                      Error **errp)
+static struct glfs *qemu_gluster_init(GlusterConf *gconf, const char *filename)
 {
    struct glfs *glfs = NULL;
    int ret;
@@ -174,8 +187,8 @@ static struct glfs *qemu_gluster_init(GlusterConf *gconf, const char *filename,

    ret = qemu_gluster_parseuri(gconf, filename);
    if (ret < 0) {
-        error_setg(errp, "Usage: file=gluster[+transport]://[server[:port]]/"
-                   "volname/image[?socket=...]");
+        error_report("Usage: file=gluster[+transport]://[server[:port]]/"
+            "volname/image[?socket=...]");
        errno = -ret;
        goto out;
    }
@@ -202,11 +215,9 @@ static struct glfs *qemu_gluster_init(GlusterConf *gconf, const char *filename,

    ret = glfs_init(glfs);
    if (ret) {
-        error_setg_errno(errp, errno,
-                         "Gluster connection failed for server=%s port=%d "
-                         "volume=%s image=%s transport=%s", gconf->server,
-                         gconf->port, gconf->volname, gconf->image,
-                         gconf->transport);
+        error_report("Gluster connection failed for server=%s port=%d "
+             "volume=%s image=%s transport=%s", gconf->server, gconf->port,
+             gconf->volname, gconf->image, gconf->transport);
        goto out;
    }
    return glfs;
@@ -220,32 +231,46 @@ out:
    return NULL;
 }

-static void qemu_gluster_complete_aio(void *opaque)
+static void qemu_gluster_complete_aio(GlusterAIOCB *acb, BDRVGlusterState *s)
 {
-    GlusterAIOCB *acb = (GlusterAIOCB *)opaque;
+    int ret;
+    bool *finished = acb->finished;
+    BlockDriverCompletionFunc *cb = acb->common.cb;
+    void *opaque = acb->common.opaque;

-    qemu_bh_delete(acb->bh);
-    acb->bh = NULL;
-    qemu_coroutine_enter(acb->coroutine, NULL);
-}
-
-/*
- * AIO callback routine called from GlusterFS thread.
- */
-static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg)
-{
-    GlusterAIOCB *acb = (GlusterAIOCB *)arg;
-
-    if (!ret || ret == acb->size) {
-        acb->ret = 0; /* Success */
-    } else if (ret < 0) {
-        acb->ret = ret; /* Read/Write failed */
+    if (!acb->ret || acb->ret == acb->size) {
+        ret = 0; /* Success */
+    } else if (acb->ret < 0) {
+        ret = acb->ret; /* Read/Write failed */
    } else {
-        acb->ret = -EIO; /* Partial read/write - fail it */
+        ret = -EIO; /* Partial read/write - fail it */
    }

-    acb->bh = qemu_bh_new(qemu_gluster_complete_aio, acb);
-    qemu_bh_schedule(acb->bh);
+    qemu_aio_release(acb);
+    cb(opaque, ret);
+    if (finished) {
+        *finished = true;
+    }
+}
+
+static void qemu_gluster_aio_event_reader(void *opaque)
+{
+    BDRVGlusterState *s = opaque;
+    ssize_t ret;
+
+    do {
+        char *p = (char *)&s->event_acb;
+
+        ret = read(s->fds[GLUSTER_FD_READ], p + s->event_reader_pos,
+                   sizeof(s->event_acb) - s->event_reader_pos);
+        if (ret > 0) {
+            s->event_reader_pos += ret;
+            if (s->event_reader_pos == sizeof(s->event_acb)) {
+                s->event_reader_pos = 0;
+                qemu_gluster_complete_aio(s->event_acb, s);
+            }
+        }
+    } while (ret < 0 && errno == EINTR);
 }

 /* TODO Convert to fine grained options */
@@ -262,57 +287,60 @@ static QemuOptsList runtime_opts = {
    },
 };

-static void qemu_gluster_parse_flags(int bdrv_flags, int *open_flags)
-{
-    assert(open_flags != NULL);
-
-    *open_flags |= O_BINARY;
-
-    if (bdrv_flags & BDRV_O_RDWR) {
-        *open_flags |= O_RDWR;
-    } else {
-        *open_flags |= O_RDONLY;
-    }
-
-    if ((bdrv_flags & BDRV_O_NOCACHE)) {
-        *open_flags |= O_DIRECT;
-    }
-}
-
 static int qemu_gluster_open(BlockDriverState *bs,  QDict *options,
                             int bdrv_flags, Error **errp)
 {
    BDRVGlusterState *s = bs->opaque;
-    int open_flags = 0;
+    int open_flags = O_BINARY;
    int ret = 0;
    GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
    QemuOpts *opts;
    Error *local_err = NULL;
    const char *filename;

-    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
+    opts = qemu_opts_create_nofail(&runtime_opts);
    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
+    if (error_is_set(&local_err)) {
+        qerror_report_err(local_err);
+        error_free(local_err);
        ret = -EINVAL;
        goto out;
    }

    filename = qemu_opt_get(opts, "filename");

-    s->glfs = qemu_gluster_init(gconf, filename, errp);
+
+    s->glfs = qemu_gluster_init(gconf, filename);
    if (!s->glfs) {
        ret = -errno;
        goto out;
    }

-    qemu_gluster_parse_flags(bdrv_flags, &open_flags);
+    if (bdrv_flags & BDRV_O_RDWR) {
+        open_flags |= O_RDWR;
+    } else {
+        open_flags |= O_RDONLY;
+    }
+
+    if ((bdrv_flags & BDRV_O_NOCACHE)) {
+        open_flags |= O_DIRECT;
+    }

    s->fd = glfs_open(s->glfs, gconf->image, open_flags);
    if (!s->fd) {
        ret = -errno;
+        goto out;
    }

+    ret = qemu_pipe(s->fds);
+    if (ret < 0) {
+        ret = -errno;
+        goto out;
+    }
+    fcntl(s->fds[GLUSTER_FD_READ], F_SETFL, O_NONBLOCK);
+    qemu_aio_set_fd_handler(s->fds[GLUSTER_FD_READ],
+        qemu_gluster_aio_event_reader, NULL, s);
+
 out:
    qemu_opts_del(opts);
    qemu_gluster_gconf_free(gconf);
@@ -328,180 +356,24 @@ out:
    return ret;
 }

-typedef struct BDRVGlusterReopenState {
-    struct glfs *glfs;
-    struct glfs_fd *fd;
-} BDRVGlusterReopenState;
-
-
-static int qemu_gluster_reopen_prepare(BDRVReopenState *state,
-                                       BlockReopenQueue *queue, Error **errp)
-{
-    int ret = 0;
-    BDRVGlusterReopenState *reop_s;
-    GlusterConf *gconf = NULL;
-    int open_flags = 0;
-
-    assert(state != NULL);
-    assert(state->bs != NULL);
-
-    state->opaque = g_malloc0(sizeof(BDRVGlusterReopenState));
-    reop_s = state->opaque;
-
-    qemu_gluster_parse_flags(state->flags, &open_flags);
-
-    gconf = g_malloc0(sizeof(GlusterConf));
-
-    reop_s->glfs = qemu_gluster_init(gconf, state->bs->filename, errp);
-    if (reop_s->glfs == NULL) {
-        ret = -errno;
-        goto exit;
-    }
-
-    reop_s->fd = glfs_open(reop_s->glfs, gconf->image, open_flags);
-    if (reop_s->fd == NULL) {
-        /* reops->glfs will be cleaned up in _abort */
-        ret = -errno;
-        goto exit;
-    }
-
-exit:
-    /* state->opaque will be freed in either the _abort or _commit */
-    qemu_gluster_gconf_free(gconf);
-    return ret;
-}
-
-static void qemu_gluster_reopen_commit(BDRVReopenState *state)
-{
-    BDRVGlusterReopenState *reop_s = state->opaque;
-    BDRVGlusterState *s = state->bs->opaque;
-
-
-    /* close the old */
-    if (s->fd) {
-        glfs_close(s->fd);
-    }
-    if (s->glfs) {
-        glfs_fini(s->glfs);
-    }
-
-    /* use the newly opened image / connection */
-    s->fd         = reop_s->fd;
-    s->glfs       = reop_s->glfs;
-
-    g_free(state->opaque);
-    state->opaque = NULL;
-
-    return;
-}
-
-
-static void qemu_gluster_reopen_abort(BDRVReopenState *state)
-{
-    BDRVGlusterReopenState *reop_s = state->opaque;
-
-    if (reop_s == NULL) {
-        return;
-    }
-
-    if (reop_s->fd) {
-        glfs_close(reop_s->fd);
-    }
-
-    if (reop_s->glfs) {
-        glfs_fini(reop_s->glfs);
-    }
-
-    g_free(state->opaque);
-    state->opaque = NULL;
-
-    return;
-}
-
-#ifdef CONFIG_GLUSTERFS_ZEROFILL
-static coroutine_fn int qemu_gluster_co_write_zeroes(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, BdrvRequestFlags flags)
-{
-    int ret;
-    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();
-
-    ret = glfs_zerofill_async(s->fd, offset, size, &gluster_finish_aiocb, acb);
-    if (ret < 0) {
-        ret = -errno;
-        goto out;
-    }
-
-    qemu_coroutine_yield();
-    ret = acb->ret;
-
-out:
-    g_slice_free(GlusterAIOCB, acb);
-    return ret;
-}
-
-static inline bool gluster_supports_zerofill(void)
-{
-    return 1;
-}
-
-static inline int qemu_gluster_zerofill(struct glfs_fd *fd, int64_t offset,
-        int64_t size)
-{
-    return glfs_zerofill(fd, offset, size);
-}
-
-#else
-static inline bool gluster_supports_zerofill(void)
-{
-    return 0;
-}
-
-static inline int qemu_gluster_zerofill(struct glfs_fd *fd, int64_t offset,
-        int64_t size)
-{
-    return 0;
-}
-#endif
-
 static int qemu_gluster_create(const char *filename,
        QEMUOptionParameter *options, Error **errp)
 {
    struct glfs *glfs;
    struct glfs_fd *fd;
    int ret = 0;
-    int prealloc = 0;
    int64_t total_size = 0;
    GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));

-    glfs = qemu_gluster_init(gconf, filename, errp);
+    glfs = qemu_gluster_init(gconf, filename);
    if (!glfs) {
-        ret = -EINVAL;
+        ret = -errno;
        goto out;
    }

    while (options && options->name) {
        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
            total_size = options->value.n / BDRV_SECTOR_SIZE;
-        } else if (!strcmp(options->name, BLOCK_OPT_PREALLOC)) {
-            if (!options->value.s || !strcmp(options->value.s, "off")) {
-                prealloc = 0;
-            } else if (!strcmp(options->value.s, "full") &&
-                    gluster_supports_zerofill()) {
-                prealloc = 1;
-            } else {
-                error_setg(errp, "Invalid preallocation mode: '%s'"
-                    " or GlusterFS doesn't support zerofill API",
-                           options->value.s);
-                ret = -EINVAL;
-                goto out;
-            }
        }
        options++;
    }
@@ -511,15 +383,9 @@ static int qemu_gluster_create(const char *filename,
    if (!fd) {
        ret = -errno;
    } else {
-        if (!glfs_ftruncate(fd, total_size * BDRV_SECTOR_SIZE)) {
-            if (prealloc && qemu_gluster_zerofill(fd, 0,
-                    total_size * BDRV_SECTOR_SIZE)) {
-                ret = -errno;
-            }
-        } else {
+        if (glfs_ftruncate(fd, total_size * BDRV_SECTOR_SIZE) != 0) {
            ret = -errno;
        }
-
        if (glfs_close(fd) != 0) {
            ret = -errno;
        }
@@ -532,18 +398,58 @@ out:
    return ret;
 }

-static coroutine_fn int qemu_gluster_co_rw(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov, int write)
+static void qemu_gluster_aio_cancel(BlockDriverAIOCB *blockacb)
+{
+    GlusterAIOCB *acb = (GlusterAIOCB *)blockacb;
+    bool finished = false;
+
+    acb->finished = &finished;
+    while (!finished) {
+        qemu_aio_wait();
+    }
+}
+
+static const AIOCBInfo gluster_aiocb_info = {
+    .aiocb_size = sizeof(GlusterAIOCB),
+    .cancel = qemu_gluster_aio_cancel,
+};
+
+static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg)
+{
+    GlusterAIOCB *acb = (GlusterAIOCB *)arg;
+    BlockDriverState *bs = acb->common.bs;
+    BDRVGlusterState *s = bs->opaque;
+    int retval;
+
+    acb->ret = ret;
+    retval = qemu_write_full(s->fds[GLUSTER_FD_WRITE], &acb, sizeof(acb));
+    if (retval != sizeof(acb)) {
+        /*
+         * Gluster AIO callback thread failed to notify the waiting
+         * QEMU thread about IO completion.
+         */
+        error_report("Gluster AIO completion failed: %s", strerror(errno));
+        abort();
+    }
+}
+
+static BlockDriverAIOCB *qemu_gluster_aio_rw(BlockDriverState *bs,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockDriverCompletionFunc *cb, void *opaque, int write)
 {
    int ret;
-    GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
+    GlusterAIOCB *acb;
    BDRVGlusterState *s = bs->opaque;
-    size_t size = nb_sectors * BDRV_SECTOR_SIZE;
-    off_t offset = sector_num * BDRV_SECTOR_SIZE;
+    size_t size;
+    off_t offset;

+    offset = sector_num * BDRV_SECTOR_SIZE;
+    size = nb_sectors * BDRV_SECTOR_SIZE;
+
+    acb = qemu_aio_get(&gluster_aiocb_info, bs, cb, opaque);
    acb->size = size;
    acb->ret = 0;
-    acb->coroutine = qemu_coroutine_self();
+    acb->finished = NULL;

    if (write) {
        ret = glfs_pwritev_async(s->fd, qiov->iov, qiov->niov, offset, 0,
@@ -554,16 +460,13 @@ static coroutine_fn int qemu_gluster_co_rw(BlockDriverState *bs,
    }

    if (ret < 0) {
-        ret = -errno;
        goto out;
    }
-
-    qemu_coroutine_yield();
-    ret = acb->ret;
+    return &acb->common;

 out:
-    g_slice_free(GlusterAIOCB, acb);
-    return ret;
+    qemu_aio_release(acb);
+    return NULL;
 }

 static int qemu_gluster_truncate(BlockDriverState *bs, int64_t offset)
@@ -579,68 +482,71 @@ static int qemu_gluster_truncate(BlockDriverState *bs, int64_t offset)
    return 0;
 }

-static coroutine_fn int qemu_gluster_co_readv(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
+static BlockDriverAIOCB *qemu_gluster_aio_readv(BlockDriverState *bs,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockDriverCompletionFunc *cb, void *opaque)
 {
-    return qemu_gluster_co_rw(bs, sector_num, nb_sectors, qiov, 0);
+    return qemu_gluster_aio_rw(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
 }

-static coroutine_fn int qemu_gluster_co_writev(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
+static BlockDriverAIOCB *qemu_gluster_aio_writev(BlockDriverState *bs,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockDriverCompletionFunc *cb, void *opaque)
 {
-    return qemu_gluster_co_rw(bs, sector_num, nb_sectors, qiov, 1);
+    return qemu_gluster_aio_rw(bs, sector_num, qiov, nb_sectors, cb, opaque, 1);
 }

-static coroutine_fn int qemu_gluster_co_flush_to_disk(BlockDriverState *bs)
+static BlockDriverAIOCB *qemu_gluster_aio_flush(BlockDriverState *bs,
+        BlockDriverCompletionFunc *cb, void *opaque)
 {
    int ret;
-    GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
+    GlusterAIOCB *acb;
    BDRVGlusterState *s = bs->opaque;

+    acb = qemu_aio_get(&gluster_aiocb_info, bs, cb, opaque);
    acb->size = 0;
    acb->ret = 0;
-    acb->coroutine = qemu_coroutine_self();
+    acb->finished = NULL;

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

 out:
-    g_slice_free(GlusterAIOCB, acb);
-    return ret;
+    qemu_aio_release(acb);
+    return NULL;
 }

 #ifdef CONFIG_GLUSTERFS_DISCARD
-static coroutine_fn int qemu_gluster_co_discard(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors)
+static BlockDriverAIOCB *qemu_gluster_aio_discard(BlockDriverState *bs,
+        int64_t sector_num, int nb_sectors, BlockDriverCompletionFunc *cb,
+        void *opaque)
 {
    int ret;
-    GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
+    GlusterAIOCB *acb;
    BDRVGlusterState *s = bs->opaque;
-    size_t size = nb_sectors * BDRV_SECTOR_SIZE;
-    off_t offset = sector_num * BDRV_SECTOR_SIZE;
+    size_t size;
+    off_t offset;

+    offset = sector_num * BDRV_SECTOR_SIZE;
+    size = nb_sectors * BDRV_SECTOR_SIZE;
+
+    acb = qemu_aio_get(&gluster_aiocb_info, bs, cb, opaque);
    acb->size = 0;
    acb->ret = 0;
-    acb->coroutine = qemu_coroutine_self();
+    acb->finished = NULL;

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

 out:
-    g_slice_free(GlusterAIOCB, acb);
-    return ret;
+    qemu_aio_release(acb);
+    return NULL;
 }
 #endif

@@ -675,6 +581,10 @@ static void qemu_gluster_close(BlockDriverState *bs)
 {
    BDRVGlusterState *s = bs->opaque;

+    close(s->fds[GLUSTER_FD_READ]);
+    close(s->fds[GLUSTER_FD_WRITE]);
+    qemu_aio_set_fd_handler(s->fds[GLUSTER_FD_READ], NULL, NULL, NULL);
+
    if (s->fd) {
        glfs_close(s->fd);
        s->fd = NULL;
@@ -694,11 +604,6 @@ static QEMUOptionParameter qemu_gluster_create_options[] = {
        .type = OPT_SIZE,
        .help = "Virtual disk size"
    },
-    {
-        .name = BLOCK_OPT_PREALLOC,
-        .type = OPT_STRING,
-        .help = "Preallocation mode (allowed values: off, full)"
-    },
    { NULL }
 };

@@ -708,23 +613,17 @@ static BlockDriver bdrv_gluster = {
    .instance_size                = sizeof(BDRVGlusterState),
    .bdrv_needs_filename          = true,
    .bdrv_file_open               = qemu_gluster_open,
-    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
-    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
-    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
    .bdrv_close                   = qemu_gluster_close,
    .bdrv_create                  = qemu_gluster_create,
    .bdrv_getlength               = qemu_gluster_getlength,
    .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
    .bdrv_truncate                = qemu_gluster_truncate,
-    .bdrv_co_readv                = qemu_gluster_co_readv,
-    .bdrv_co_writev               = qemu_gluster_co_writev,
-    .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
+    .bdrv_aio_readv               = qemu_gluster_aio_readv,
+    .bdrv_aio_writev              = qemu_gluster_aio_writev,
+    .bdrv_aio_flush               = qemu_gluster_aio_flush,
    .bdrv_has_zero_init           = qemu_gluster_has_zero_init,
 #ifdef CONFIG_GLUSTERFS_DISCARD
-    .bdrv_co_discard              = qemu_gluster_co_discard,
-#endif
-#ifdef CONFIG_GLUSTERFS_ZEROFILL
-    .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
+    .bdrv_aio_discard             = qemu_gluster_aio_discard,
 #endif
    .create_options               = qemu_gluster_create_options,
 };
@@ -735,23 +634,17 @@ static BlockDriver bdrv_gluster_tcp = {
    .instance_size                = sizeof(BDRVGlusterState),
    .bdrv_needs_filename          = true,
    .bdrv_file_open               = qemu_gluster_open,
-    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
-    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
-    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
    .bdrv_close                   = qemu_gluster_close,
    .bdrv_create                  = qemu_gluster_create,
    .bdrv_getlength               = qemu_gluster_getlength,
    .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
    .bdrv_truncate                = qemu_gluster_truncate,
-    .bdrv_co_readv                = qemu_gluster_co_readv,
-    .bdrv_co_writev               = qemu_gluster_co_writev,
-    .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
+    .bdrv_aio_readv               = qemu_gluster_aio_readv,
+    .bdrv_aio_writev              = qemu_gluster_aio_writev,
+    .bdrv_aio_flush               = qemu_gluster_aio_flush,
    .bdrv_has_zero_init           = qemu_gluster_has_zero_init,
 #ifdef CONFIG_GLUSTERFS_DISCARD
-    .bdrv_co_discard              = qemu_gluster_co_discard,
-#endif
-#ifdef CONFIG_GLUSTERFS_ZEROFILL
-    .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
+    .bdrv_aio_discard             = qemu_gluster_aio_discard,
 #endif
    .create_options               = qemu_gluster_create_options,
 };
@@ -762,23 +655,17 @@ static BlockDriver bdrv_gluster_unix = {
    .instance_size                = sizeof(BDRVGlusterState),
    .bdrv_needs_filename          = true,
    .bdrv_file_open               = qemu_gluster_open,
-    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
-    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
-    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
    .bdrv_close                   = qemu_gluster_close,
    .bdrv_create                  = qemu_gluster_create,
    .bdrv_getlength               = qemu_gluster_getlength,
    .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
    .bdrv_truncate                = qemu_gluster_truncate,
-    .bdrv_co_readv                = qemu_gluster_co_readv,
-    .bdrv_co_writev               = qemu_gluster_co_writev,
-    .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
+    .bdrv_aio_readv               = qemu_gluster_aio_readv,
+    .bdrv_aio_writev              = qemu_gluster_aio_writev,
+    .bdrv_aio_flush               = qemu_gluster_aio_flush,
    .bdrv_has_zero_init           = qemu_gluster_has_zero_init,
 #ifdef CONFIG_GLUSTERFS_DISCARD
-    .bdrv_co_discard              = qemu_gluster_co_discard,
-#endif
-#ifdef CONFIG_GLUSTERFS_ZEROFILL
-    .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
+    .bdrv_aio_discard             = qemu_gluster_aio_discard,
 #endif
    .create_options               = qemu_gluster_create_options,
 };
@@ -789,23 +676,17 @@ static BlockDriver bdrv_gluster_rdma = {
    .instance_size                = sizeof(BDRVGlusterState),
    .bdrv_needs_filename          = true,
    .bdrv_file_open               = qemu_gluster_open,
-    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
-    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
-    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
    .bdrv_close                   = qemu_gluster_close,
    .bdrv_create                  = qemu_gluster_create,
    .bdrv_getlength               = qemu_gluster_getlength,
    .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
    .bdrv_truncate                = qemu_gluster_truncate,
-    .bdrv_co_readv                = qemu_gluster_co_readv,
-    .bdrv_co_writev               = qemu_gluster_co_writev,
-    .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
+    .bdrv_aio_readv               = qemu_gluster_aio_readv,
+    .bdrv_aio_writev              = qemu_gluster_aio_writev,
+    .bdrv_aio_flush               = qemu_gluster_aio_flush,
    .bdrv_has_zero_init           = qemu_gluster_has_zero_init,
 #ifdef CONFIG_GLUSTERFS_DISCARD
-    .bdrv_co_discard              = qemu_gluster_co_discard,
-#endif
-#ifdef CONFIG_GLUSTERFS_ZEROFILL
-    .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
+    .bdrv_aio_discard             = qemu_gluster_aio_discard,
 #endif
    .create_options               = qemu_gluster_create_options,
 };
@@ -31,8 +31,7 @@ typedef struct MirrorBlockJob {
    BlockJob common;
    RateLimit limit;
    BlockDriverState *target;
-    BlockDriverState *base;
-    bool is_none_mode;
+    MirrorSyncMode mode;
    BlockdevOnError on_source_error, on_target_error;
    bool synced;
    bool should_complete;
@@ -40,7 +39,6 @@ typedef struct MirrorBlockJob {
    int64_t granularity;
    size_t buf_size;
    unsigned long *cow_bitmap;
-    BdrvDirtyBitmap *dirty_bitmap;
    HBitmapIter hbi;
    uint8_t *buf;
    QSIMPLEQ_HEAD(, MirrorBuffer) buf_free;
@@ -96,7 +94,6 @@ static void mirror_iteration_done(MirrorOp *op, int ret)
        bitmap_set(s->cow_bitmap, chunk_num, nb_chunks);
    }

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

    /* Enter coroutine when it is not sleeping.  The coroutine sleeps to
@@ -156,10 +153,9 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)

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

@@ -195,7 +191,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
    do {
        int added_sectors, added_chunks;

-        if (!bdrv_get_dirty(source, s->dirty_bitmap, next_sector) ||
+        if (!bdrv_get_dirty(source, next_sector) ||
            test_bit(next_chunk, s->in_flight_bitmap)) {
            assert(nb_sectors > 0);
            break;
@@ -259,17 +255,14 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
    next_sector = sector_num;
    while (nb_chunks-- > 0) {
        MirrorBuffer *buf = QSIMPLEQ_FIRST(&s->buf_free);
-        size_t remaining = (nb_sectors * BDRV_SECTOR_SIZE) - op->qiov.size;
-
        QSIMPLEQ_REMOVE_HEAD(&s->buf_free, next);
        s->buf_free_count--;
-        qemu_iovec_add(&op->qiov, buf, MIN(s->granularity, remaining));
+        qemu_iovec_add(&op->qiov, buf, s->granularity);

        /* Advance the HBitmapIter in parallel, so that we do not examine
         * the same sector twice.
         */
-        if (next_sector > hbitmap_next_sector
-            && bdrv_get_dirty(source, s->dirty_bitmap, next_sector)) {
+        if (next_sector > hbitmap_next_sector && bdrv_get_dirty(source, next_sector)) {
            hbitmap_next_sector = hbitmap_iter_next(&s->hbi);
        }

@@ -326,18 +319,9 @@ static void coroutine_fn mirror_run(void *opaque)
    }

    s->common.len = bdrv_getlength(bs);
-    if (s->common.len < 0) {
-        ret = s->common.len;
-        goto immediate_exit;
-    } else if (s->common.len == 0) {
-        /* Report BLOCK_JOB_READY and wait for complete. */
-        block_job_ready(&s->common);
-        s->synced = true;
-        while (!block_job_is_cancelled(&s->common) && !s->should_complete) {
-            block_job_yield(&s->common);
-        }
-        s->common.cancelled = false;
-        goto immediate_exit;
+    if (s->common.len <= 0) {
+        block_job_completed(&s->common, s->common.len);
+        return;
    }

    length = (bdrv_getlength(bs) + s->granularity - 1) / s->granularity;
@@ -362,9 +346,10 @@ static void coroutine_fn mirror_run(void *opaque)
    sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
    mirror_free_init(s);

-    if (!s->is_none_mode) {
+    if (s->mode != MIRROR_SYNC_MODE_NONE) {
        /* First part, loop on the sectors and initialize the dirty bitmap.  */
-        BlockDriverState *base = s->base;
+        BlockDriverState *base;
+        base = s->mode == MIRROR_SYNC_MODE_FULL ? NULL : bs->backing_hd;
        for (sector_num = 0; sector_num < end; ) {
            int64_t next = (sector_num | (sectors_per_chunk - 1)) + 1;
            ret = bdrv_is_allocated_above(bs, base,
@@ -384,7 +369,7 @@ static void coroutine_fn mirror_run(void *opaque)
        }
    }

-    bdrv_dirty_iter_init(bs, s->dirty_bitmap, &s->hbi);
+    bdrv_dirty_iter_init(bs, &s->hbi);
    last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
    for (;;) {
        uint64_t delay_ns = 0;
@@ -396,7 +381,7 @@ static void coroutine_fn mirror_run(void *opaque)
            goto immediate_exit;
        }

-        cnt = bdrv_get_dirty_count(bs, s->dirty_bitmap);
+        cnt = bdrv_get_dirty_count(bs);

        /* Note that even when no rate limit is applied we need to yield
         * periodically with no pending I/O so that qemu_aio_flush() returns.
@@ -440,7 +425,7 @@ static void coroutine_fn mirror_run(void *opaque)

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

@@ -455,7 +440,7 @@ static void coroutine_fn mirror_run(void *opaque)
             */
            trace_mirror_before_drain(s, cnt);
            bdrv_drain_all();
-            cnt = bdrv_get_dirty_count(bs, s->dirty_bitmap);
+            cnt = bdrv_get_dirty_count(bs);
        }

        ret = 0;
@@ -495,21 +480,15 @@ immediate_exit:
    qemu_vfree(s->buf);
    g_free(s->cow_bitmap);
    g_free(s->in_flight_bitmap);
-    bdrv_release_dirty_bitmap(bs, s->dirty_bitmap);
+    bdrv_set_dirty_tracking(bs, 0);
    bdrv_iostatus_disable(s->target);
    if (s->should_complete && ret == 0) {
        if (bdrv_get_flags(s->target) != bdrv_get_flags(s->common.bs)) {
            bdrv_reopen(s->target, bdrv_get_flags(s->common.bs), NULL);
        }
        bdrv_swap(s->target, s->common.bs);
-        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;
-            s->base->backing_hd = NULL;
-            bdrv_unref(p);
-        }
    }
+    bdrv_close(s->target);
    bdrv_unref(s->target);
    block_job_completed(&s->common, ret);
 }
@@ -540,6 +519,9 @@ static void mirror_complete(BlockJob *job, Error **errp)

    ret = bdrv_open_backing_file(s->target, NULL, &local_err);
    if (ret < 0) {
+        char backing_filename[PATH_MAX];
+        bdrv_get_full_backing_filename(s->target, backing_filename,
+                                       sizeof(backing_filename));
        error_propagate(errp, local_err);
        return;
    }
@@ -560,24 +542,12 @@ static const BlockJobDriver mirror_job_driver = {
    .complete      = mirror_complete,
 };

-static const BlockJobDriver commit_active_job_driver = {
-    .instance_size = sizeof(MirrorBlockJob),
-    .job_type      = BLOCK_JOB_TYPE_COMMIT,
-    .set_speed     = mirror_set_speed,
-    .iostatus_reset
-                   = mirror_iostatus_reset,
-    .complete      = mirror_complete,
-};
-
-static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
-                            int64_t speed, int64_t granularity,
-                            int64_t buf_size,
-                            BlockdevOnError on_source_error,
-                            BlockdevOnError on_target_error,
-                            BlockDriverCompletionFunc *cb,
-                            void *opaque, Error **errp,
-                            const BlockJobDriver *driver,
-                            bool is_none_mode, BlockDriverState *base)
+void mirror_start(BlockDriverState *bs, BlockDriverState *target,
+                  int64_t speed, int64_t granularity, int64_t buf_size,
+                  MirrorSyncMode mode, BlockdevOnError on_source_error,
+                  BlockdevOnError on_target_error,
+                  BlockDriverCompletionFunc *cb,
+                  void *opaque, Error **errp)
 {
    MirrorBlockJob *s;

@@ -602,8 +572,7 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
        return;
    }

-
-    s = block_job_create(driver, bs, speed, cb, opaque, errp);
+    s = block_job_create(&mirror_job_driver, bs, speed, cb, opaque, errp);
    if (!s) {
        return;
    }
@@ -611,12 +580,11 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
    s->on_source_error = on_source_error;
    s->on_target_error = on_target_error;
    s->target = target;
-    s->is_none_mode = is_none_mode;
-    s->base = base;
+    s->mode = mode;
    s->granularity = granularity;
    s->buf_size = MAX(buf_size, granularity);

-    s->dirty_bitmap = bdrv_create_dirty_bitmap(bs, granularity);
+    bdrv_set_dirty_tracking(bs, granularity);
    bdrv_set_enable_write_cache(s->target, true);
    bdrv_set_on_error(s->target, on_target_error, on_target_error);
    bdrv_iostatus_enable(s->target);
@@ -624,80 +592,3 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
    trace_mirror_start(bs, s, s->common.co, opaque);
    qemu_coroutine_enter(s->common.co, s);
 }
-
-void mirror_start(BlockDriverState *bs, BlockDriverState *target,
-                  int64_t speed, int64_t granularity, int64_t buf_size,
-                  MirrorSyncMode mode, BlockdevOnError on_source_error,
-                  BlockdevOnError on_target_error,
-                  BlockDriverCompletionFunc *cb,
-                  void *opaque, Error **errp)
-{
-    bool is_none_mode;
-    BlockDriverState *base;
-
-    is_none_mode = mode == MIRROR_SYNC_MODE_NONE;
-    base = mode == MIRROR_SYNC_MODE_TOP ? bs->backing_hd : NULL;
-    mirror_start_job(bs, target, speed, granularity, buf_size,
-                     on_source_error, on_target_error, cb, opaque, errp,
-                     &mirror_job_driver, is_none_mode, base);
-}
-
-void commit_active_start(BlockDriverState *bs, BlockDriverState *base,
-                         int64_t speed,
-                         BlockdevOnError on_error,
-                         BlockDriverCompletionFunc *cb,
-                         void *opaque, Error **errp)
-{
-    int64_t length, base_length;
-    int orig_base_flags;
-    int ret;
-    Error *local_err = NULL;
-
-    orig_base_flags = bdrv_get_flags(base);
-
-    if (bdrv_reopen(base, bs->open_flags, errp)) {
-        return;
-    }
-
-    length = bdrv_getlength(bs);
-    if (length < 0) {
-        error_setg_errno(errp, -length,
-                         "Unable to determine length of %s", bs->filename);
-        goto error_restore_flags;
-    }
-
-    base_length = bdrv_getlength(base);
-    if (base_length < 0) {
-        error_setg_errno(errp, -base_length,
-                         "Unable to determine length of %s", base->filename);
-        goto error_restore_flags;
-    }
-
-    if (length > base_length) {
-        ret = bdrv_truncate(base, length);
-        if (ret < 0) {
-            error_setg_errno(errp, -ret,
-                            "Top image %s is larger than base image %s, and "
-                             "resize of base image failed",
-                             bs->filename, base->filename);
-            goto error_restore_flags;
-        }
-    }
-
-    bdrv_ref(base);
-    mirror_start_job(bs, base, speed, 0, 0,
-                     on_error, on_error, cb, opaque, &local_err,
-                     &commit_active_job_driver, false, base);
-    if (error_is_set(&local_err)) {
-        error_propagate(errp, local_err);
-        goto error_restore_flags;
-    }
-
-    return;
-
-error_restore_flags:
-    /* ignore error and errp for bdrv_reopen, because we want to propagate
-     * the original error */
-    bdrv_reopen(base, orig_base_flags, NULL);
-    return;
-}
@@ -1,388 +0,0 @@
-/*
- * QEMU Block driver for  NBD
- *
- * Copyright (C) 2008 Bull S.A.S.
- *     Author: Laurent Vivier <Laurent.Vivier@bull.net>
- *
- * Some parts:
- *    Copyright (C) 2007 Anthony Liguori <anthony@codemonkey.ws>
- *
- * 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 "nbd-client.h"
-#include "qemu/sockets.h"
-
-#define HANDLE_TO_INDEX(bs, handle) ((handle) ^ ((uint64_t)(intptr_t)bs))
-#define INDEX_TO_HANDLE(bs, index)  ((index)  ^ ((uint64_t)(intptr_t)bs))
-
-static void nbd_recv_coroutines_enter_all(NbdClientSession *s)
-{
-    int i;
-
-    for (i = 0; i < MAX_NBD_REQUESTS; i++) {
-        if (s->recv_coroutine[i]) {
-            qemu_coroutine_enter(s->recv_coroutine[i], NULL);
-        }
-    }
-}
-
-static void nbd_teardown_connection(NbdClientSession *client)
-{
-    /* finish any pending coroutines */
-    shutdown(client->sock, 2);
-    nbd_recv_coroutines_enter_all(client);
-
-    qemu_aio_set_fd_handler(client->sock, NULL, NULL, NULL);
-    closesocket(client->sock);
-    client->sock = -1;
-}
-
-static void nbd_reply_ready(void *opaque)
-{
-    NbdClientSession *s = opaque;
-    uint64_t i;
-    int ret;
-
-    if (s->reply.handle == 0) {
-        /* No reply already in flight.  Fetch a header.  It is possible
-         * that another thread has done the same thing in parallel, so
-         * the socket is not readable anymore.
-         */
-        ret = nbd_receive_reply(s->sock, &s->reply);
-        if (ret == -EAGAIN) {
-            return;
-        }
-        if (ret < 0) {
-            s->reply.handle = 0;
-            goto fail;
-        }
-    }
-
-    /* There's no need for a mutex on the receive side, because the
-     * handler acts as a synchronization point and ensures that only
-     * one coroutine is called until the reply finishes.  */
-    i = HANDLE_TO_INDEX(s, s->reply.handle);
-    if (i >= MAX_NBD_REQUESTS) {
-        goto fail;
-    }
-
-    if (s->recv_coroutine[i]) {
-        qemu_coroutine_enter(s->recv_coroutine[i], NULL);
-        return;
-    }
-
-fail:
-    nbd_teardown_connection(s);
-}
-
-static void nbd_restart_write(void *opaque)
-{
-    NbdClientSession *s = opaque;
-
-    qemu_coroutine_enter(s->send_coroutine, NULL);
-}
-
-static int nbd_co_send_request(NbdClientSession *s,
-    struct nbd_request *request,
-    QEMUIOVector *qiov, int offset)
-{
-    int rc, ret;
-
-    qemu_co_mutex_lock(&s->send_mutex);
-    s->send_coroutine = qemu_coroutine_self();
-    qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, nbd_restart_write, s);
-    if (qiov) {
-        if (!s->is_unix) {
-            socket_set_cork(s->sock, 1);
-        }
-        rc = nbd_send_request(s->sock, request);
-        if (rc >= 0) {
-            ret = qemu_co_sendv(s->sock, qiov->iov, qiov->niov,
-                                offset, request->len);
-            if (ret != request->len) {
-                rc = -EIO;
-            }
-        }
-        if (!s->is_unix) {
-            socket_set_cork(s->sock, 0);
-        }
-    } else {
-        rc = nbd_send_request(s->sock, request);
-    }
-    qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, NULL, s);
-    s->send_coroutine = NULL;
-    qemu_co_mutex_unlock(&s->send_mutex);
-    return rc;
-}
-
-static void nbd_co_receive_reply(NbdClientSession *s,
-    struct nbd_request *request, struct nbd_reply *reply,
-    QEMUIOVector *qiov, int offset)
-{
-    int ret;
-
-    /* Wait until we're woken up by the read handler.  TODO: perhaps
-     * peek at the next reply and avoid yielding if it's ours?  */
-    qemu_coroutine_yield();
-    *reply = s->reply;
-    if (reply->handle != request->handle) {
-        reply->error = EIO;
-    } else {
-        if (qiov && reply->error == 0) {
-            ret = qemu_co_recvv(s->sock, qiov->iov, qiov->niov,
-                                offset, request->len);
-            if (ret != request->len) {
-                reply->error = EIO;
-            }
-        }
-
-        /* Tell the read handler to read another header.  */
-        s->reply.handle = 0;
-    }
-}
-
-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) {
-        qemu_co_mutex_lock(&s->free_sema);
-        assert(s->in_flight < MAX_NBD_REQUESTS);
-    }
-    s->in_flight++;
-
-    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,
-    struct nbd_request *request)
-{
-    int i = HANDLE_TO_INDEX(s, request->handle);
-    s->recv_coroutine[i] = NULL;
-    if (s->in_flight-- == MAX_NBD_REQUESTS) {
-        qemu_co_mutex_unlock(&s->free_sema);
-    }
-}
-
-static int nbd_co_readv_1(NbdClientSession *client, int64_t sector_num,
-                          int nb_sectors, QEMUIOVector *qiov,
-                          int offset)
-{
-    struct nbd_request request = { .type = NBD_CMD_READ };
-    struct nbd_reply reply;
-    ssize_t ret;
-
-    request.from = sector_num * 512;
-    request.len = nb_sectors * 512;
-
-    nbd_coroutine_start(client, &request);
-    ret = nbd_co_send_request(client, &request, NULL, 0);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(client, &request, &reply, qiov, offset);
-    }
-    nbd_coroutine_end(client, &request);
-    return -reply.error;
-
-}
-
-static int nbd_co_writev_1(NbdClientSession *client, int64_t sector_num,
-                           int nb_sectors, QEMUIOVector *qiov,
-                           int offset)
-{
-    struct nbd_request request = { .type = NBD_CMD_WRITE };
-    struct nbd_reply reply;
-    ssize_t ret;
-
-    if (!bdrv_enable_write_cache(client->bs) &&
-        (client->nbdflags & NBD_FLAG_SEND_FUA)) {
-        request.type |= NBD_CMD_FLAG_FUA;
-    }
-
-    request.from = sector_num * 512;
-    request.len = nb_sectors * 512;
-
-    nbd_coroutine_start(client, &request);
-    ret = nbd_co_send_request(client, &request, qiov, offset);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(client, &request, &reply, NULL, 0);
-    }
-    nbd_coroutine_end(client, &request);
-    return -reply.error;
-}
-
-/* qemu-nbd has a limit of slightly less than 1M per request.  Try to
- * remain aligned to 4K. */
-#define NBD_MAX_SECTORS 2040
-
-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(client, sector_num,
-                             NBD_MAX_SECTORS, qiov, offset);
-        if (ret < 0) {
-            return ret;
-        }
-        offset += NBD_MAX_SECTORS * 512;
-        sector_num += NBD_MAX_SECTORS;
-        nb_sectors -= NBD_MAX_SECTORS;
-    }
-    return nbd_co_readv_1(client, sector_num, nb_sectors, qiov, offset);
-}
-
-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(client, sector_num,
-                              NBD_MAX_SECTORS, qiov, offset);
-        if (ret < 0) {
-            return ret;
-        }
-        offset += NBD_MAX_SECTORS * 512;
-        sector_num += NBD_MAX_SECTORS;
-        nb_sectors -= NBD_MAX_SECTORS;
-    }
-    return nbd_co_writev_1(client, sector_num, nb_sectors, qiov, offset);
-}
-
-int nbd_client_session_co_flush(NbdClientSession *client)
-{
-    struct nbd_request request = { .type = NBD_CMD_FLUSH };
-    struct nbd_reply reply;
-    ssize_t ret;
-
-    if (!(client->nbdflags & NBD_FLAG_SEND_FLUSH)) {
-        return 0;
-    }
-
-    if (client->nbdflags & NBD_FLAG_SEND_FUA) {
-        request.type |= NBD_CMD_FLAG_FUA;
-    }
-
-    request.from = 0;
-    request.len = 0;
-
-    nbd_coroutine_start(client, &request);
-    ret = nbd_co_send_request(client, &request, NULL, 0);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(client, &request, &reply, NULL, 0);
-    }
-    nbd_coroutine_end(client, &request);
-    return -reply.error;
-}
-
-int nbd_client_session_co_discard(NbdClientSession *client, int64_t sector_num,
-    int nb_sectors)
-{
-    struct nbd_request request = { .type = NBD_CMD_TRIM };
-    struct nbd_reply reply;
-    ssize_t ret;
-
-    if (!(client->nbdflags & NBD_FLAG_SEND_TRIM)) {
-        return 0;
-    }
-    request.from = sector_num * 512;
-    request.len = nb_sectors * 512;
-
-    nbd_coroutine_start(client, &request);
-    ret = nbd_co_send_request(client, &request, NULL, 0);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(client, &request, &reply, NULL, 0);
-    }
-    nbd_coroutine_end(client, &request);
-    return -reply.error;
-
-}
-
-void nbd_client_session_close(NbdClientSession *client)
-{
-    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(client);
-    client->bs = NULL;
-}
-
-int nbd_client_session_init(NbdClientSession *client, BlockDriverState *bs,
-    int sock, const char *export)
-{
-    int ret;
-
-    /* NBD handshake */
-    logout("session init %s\n", export);
-    qemu_set_block(sock);
-    ret = nbd_receive_negotiate(sock, export,
-                                &client->nbdflags, &client->size,
-                                &client->blocksize);
-    if (ret < 0) {
-        logout("Failed to negotiate with the NBD server\n");
-        closesocket(sock);
-        return ret;
-    }
-
-    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);
-    qemu_aio_set_fd_handler(sock, nbd_reply_ready, NULL, client);
-
-    logout("Established connection with NBD server\n");
-    return 0;
-}
@@ -1,50 +0,0 @@
-#ifndef NBD_CLIENT_H
-#define NBD_CLIENT_H
-
-#include "qemu-common.h"
-#include "block/nbd.h"
-#include "block/block_int.h"
-
-/* #define DEBUG_NBD */
-
-#if defined(DEBUG_NBD)
-#define logout(fmt, ...) \
-    fprintf(stderr, "nbd\t%-24s" fmt, __func__, ##__VA_ARGS__)
-#else
-#define logout(fmt, ...) ((void)0)
-#endif
-
-#define MAX_NBD_REQUESTS    16
-
-typedef struct NbdClientSession {
-    int sock;
-    uint32_t nbdflags;
-    off_t size;
-    size_t blocksize;
-
-    CoMutex send_mutex;
-    CoMutex free_sema;
-    Coroutine *send_coroutine;
-    int in_flight;
-
-    Coroutine *recv_coroutine[MAX_NBD_REQUESTS];
-    struct nbd_reply reply;
-
-    bool is_unix;
-
-    BlockDriverState *bs;
-} NbdClientSession;
-
-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_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);
-
-#endif /* NBD_CLIENT_H */
@@ -26,7 +26,8 @@
 * THE SOFTWARE.
 */

-#include "block/nbd-client.h"
+#include "qemu-common.h"
+#include "block/nbd.h"
 #include "qemu/uri.h"
 #include "block/block_int.h"
 #include "qemu/module.h"
@@ -39,9 +40,37 @@

 #define EN_OPTSTR ":exportname="

+/* #define DEBUG_NBD */
+
+#if defined(DEBUG_NBD)
+#define logout(fmt, ...) \
+                fprintf(stderr, "nbd\t%-24s" fmt, __func__, ##__VA_ARGS__)
+#else
+#define logout(fmt, ...) ((void)0)
+#endif
+
+#define MAX_NBD_REQUESTS	16
+#define HANDLE_TO_INDEX(bs, handle) ((handle) ^ ((uint64_t)(intptr_t)bs))
+#define INDEX_TO_HANDLE(bs, index)  ((index)  ^ ((uint64_t)(intptr_t)bs))
+
 typedef struct BDRVNBDState {
-    NbdClientSession client;
+    int sock;
+    uint32_t nbdflags;
+    off_t size;
+    size_t blocksize;
+
+    CoMutex send_mutex;
+    CoMutex free_sema;
+    Coroutine *send_coroutine;
+    int in_flight;
+
+    Coroutine *recv_coroutine[MAX_NBD_REQUESTS];
+    struct nbd_reply reply;
+
+    bool is_unix;
    QemuOpts *socket_opts;
+
+    char *export_name; /* An NBD server may export several devices */
 } BDRVNBDState;

 static int nbd_parse_uri(const char *filename, QDict *options)
@@ -188,49 +217,195 @@ out:
    g_free(file);
 }

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

-    if (qdict_haskey(options, "path") == qdict_haskey(options, "host")) {
-        if (qdict_haskey(options, "path")) {
-            error_setg(errp, "path and host may not be used at the same time.");
-        } else {
-            error_setg(errp, "one of path and host must be specified.");
+    if (qdict_haskey(options, "path")) {
+        if (qdict_haskey(options, "host")) {
+            qerror_report(ERROR_CLASS_GENERIC_ERROR, "path and host may not "
+                          "be used at the same time.");
+            return -EINVAL;
        }
-        return;
+        s->is_unix = true;
+    } else if (qdict_haskey(options, "host")) {
+        s->is_unix = false;
+    } else {
+        return -EINVAL;
    }

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

    qemu_opts_absorb_qdict(s->socket_opts, options, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        return;
+    if (error_is_set(&local_err)) {
+        qerror_report_err(local_err);
+        error_free(local_err);
+        return -EINVAL;
    }

    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) {
+    s->export_name = g_strdup(qdict_get_try_str(options, "export"));
+    if (s->export_name) {
        qdict_del(options, "export");
    }
+
+    return 0;
+}
+
+
+static void nbd_coroutine_start(BDRVNBDState *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) {
+        qemu_co_mutex_lock(&s->free_sema);
+        assert(s->in_flight < MAX_NBD_REQUESTS);
+    }
+    s->in_flight++;
+
+    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_reply_ready(void *opaque)
+{
+    BDRVNBDState *s = opaque;
+    uint64_t i;
+    int ret;
+
+    if (s->reply.handle == 0) {
+        /* No reply already in flight.  Fetch a header.  It is possible
+         * that another thread has done the same thing in parallel, so
+         * the socket is not readable anymore.
+         */
+        ret = nbd_receive_reply(s->sock, &s->reply);
+        if (ret == -EAGAIN) {
+            return;
+        }
+        if (ret < 0) {
+            s->reply.handle = 0;
+            goto fail;
+        }
+    }
+
+    /* There's no need for a mutex on the receive side, because the
+     * handler acts as a synchronization point and ensures that only
+     * one coroutine is called until the reply finishes.  */
+    i = HANDLE_TO_INDEX(s, s->reply.handle);
+    if (i >= MAX_NBD_REQUESTS) {
+        goto fail;
+    }
+
+    if (s->recv_coroutine[i]) {
+        qemu_coroutine_enter(s->recv_coroutine[i], NULL);
+        return;
+    }
+
+fail:
+    for (i = 0; i < MAX_NBD_REQUESTS; i++) {
+        if (s->recv_coroutine[i]) {
+            qemu_coroutine_enter(s->recv_coroutine[i], NULL);
+        }
+    }
 }

-static int nbd_establish_connection(BlockDriverState *bs, Error **errp)
+static void nbd_restart_write(void *opaque)
+{
+    BDRVNBDState *s = opaque;
+    qemu_coroutine_enter(s->send_coroutine, NULL);
+}
+
+static int nbd_co_send_request(BDRVNBDState *s, struct nbd_request *request,
+                               QEMUIOVector *qiov, int offset)
+{
+    int rc, ret;
+
+    qemu_co_mutex_lock(&s->send_mutex);
+    s->send_coroutine = qemu_coroutine_self();
+    qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, nbd_restart_write, s);
+    if (qiov) {
+        if (!s->is_unix) {
+            socket_set_cork(s->sock, 1);
+        }
+        rc = nbd_send_request(s->sock, request);
+        if (rc >= 0) {
+            ret = qemu_co_sendv(s->sock, qiov->iov, qiov->niov,
+                                offset, request->len);
+            if (ret != request->len) {
+                rc = -EIO;
+            }
+        }
+        if (!s->is_unix) {
+            socket_set_cork(s->sock, 0);
+        }
+    } else {
+        rc = nbd_send_request(s->sock, request);
+    }
+    qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, NULL, s);
+    s->send_coroutine = NULL;
+    qemu_co_mutex_unlock(&s->send_mutex);
+    return rc;
+}
+
+static void nbd_co_receive_reply(BDRVNBDState *s, struct nbd_request *request,
+                                 struct nbd_reply *reply,
+                                 QEMUIOVector *qiov, int offset)
+{
+    int ret;
+
+    /* Wait until we're woken up by the read handler.  TODO: perhaps
+     * peek at the next reply and avoid yielding if it's ours?  */
+    qemu_coroutine_yield();
+    *reply = s->reply;
+    if (reply->handle != request->handle) {
+        reply->error = EIO;
+    } else {
+        if (qiov && reply->error == 0) {
+            ret = qemu_co_recvv(s->sock, qiov->iov, qiov->niov,
+                                offset, request->len);
+            if (ret != request->len) {
+                reply->error = EIO;
+            }
+        }
+
+        /* Tell the read handler to read another header.  */
+        s->reply.handle = 0;
+    }
+}
+
+static void nbd_coroutine_end(BDRVNBDState *s, struct nbd_request *request)
+{
+    int i = HANDLE_TO_INDEX(s, request->handle);
+    s->recv_coroutine[i] = NULL;
+    if (s->in_flight-- == MAX_NBD_REQUESTS) {
+        qemu_co_mutex_unlock(&s->free_sema);
+    }
+}
+
+static int nbd_establish_connection(BlockDriverState *bs)
 {
    BDRVNBDState *s = bs->opaque;
    int sock;
+    int ret;
+    off_t size;
+    size_t blocksize;

-    if (s->client.is_unix) {
-        sock = unix_connect_opts(s->socket_opts, errp, NULL, NULL);
+    if (s->is_unix) {
+        sock = unix_socket_outgoing(qemu_opt_get(s->socket_opts, "path"));
    } else {
-        sock = inet_connect_opts(s->socket_opts, errp, NULL, NULL);
+        sock = tcp_socket_outgoing_opts(s->socket_opts);
        if (sock >= 0) {
            socket_set_nodelay(sock);
        }
@@ -242,85 +417,226 @@ static int nbd_establish_connection(BlockDriverState *bs, Error **errp)
        return -errno;
    }

-    return sock;
+    /* NBD handshake */
+    ret = nbd_receive_negotiate(sock, s->export_name, &s->nbdflags, &size,
+                                &blocksize);
+    if (ret < 0) {
+        logout("Failed to negotiate with the NBD server\n");
+        closesocket(sock);
+        return ret;
+    }
+
+    /* Now that we're connected, set the socket to be non-blocking and
+     * kick the reply mechanism.  */
+    qemu_set_nonblock(sock);
+    qemu_aio_set_fd_handler(sock, nbd_reply_ready, NULL, s);
+
+    s->sock = sock;
+    s->size = size;
+    s->blocksize = blocksize;
+
+    logout("Established connection with NBD server\n");
+    return 0;
+}
+
+static void nbd_teardown_connection(BlockDriverState *bs)
+{
+    BDRVNBDState *s = bs->opaque;
+    struct nbd_request request;
+
+    request.type = NBD_CMD_DISC;
+    request.from = 0;
+    request.len = 0;
+    nbd_send_request(s->sock, &request);
+
+    qemu_aio_set_fd_handler(s->sock, NULL, NULL, NULL);
+    closesocket(s->sock);
 }

 static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
                    Error **errp)
 {
    BDRVNBDState *s = bs->opaque;
-    char *export = NULL;
-    int result, sock;
-    Error *local_err = NULL;
+    int result;
+
+    qemu_co_mutex_init(&s->send_mutex);
+    qemu_co_mutex_init(&s->free_sema);

    /* Pop the config into our state object. Exit if invalid. */
-    nbd_config(s, options, &export, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        return -EINVAL;
+    result = nbd_config(s, options);
+    if (result != 0) {
+        return result;
    }

    /* establish TCP connection, return error if it fails
     * TODO: Configurable retry-until-timeout behaviour.
     */
-    sock = nbd_establish_connection(bs, errp);
-    if (sock < 0) {
-        return sock;
-    }
+    result = nbd_establish_connection(bs);

-    /* NBD handshake */
-    result = nbd_client_session_init(&s->client, bs, sock, export);
-    g_free(export);
    return result;
 }

+static int nbd_co_readv_1(BlockDriverState *bs, int64_t sector_num,
+                          int nb_sectors, QEMUIOVector *qiov,
+                          int offset)
+{
+    BDRVNBDState *s = bs->opaque;
+    struct nbd_request request;
+    struct nbd_reply reply;
+    ssize_t ret;
+
+    request.type = NBD_CMD_READ;
+    request.from = sector_num * 512;
+    request.len = nb_sectors * 512;
+
+    nbd_coroutine_start(s, &request);
+    ret = nbd_co_send_request(s, &request, NULL, 0);
+    if (ret < 0) {
+        reply.error = -ret;
+    } else {
+        nbd_co_receive_reply(s, &request, &reply, qiov, offset);
+    }
+    nbd_coroutine_end(s, &request);
+    return -reply.error;
+
+}
+
+static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num,
+                           int nb_sectors, QEMUIOVector *qiov,
+                           int offset)
+{
+    BDRVNBDState *s = bs->opaque;
+    struct nbd_request request;
+    struct nbd_reply reply;
+    ssize_t ret;
+
+    request.type = NBD_CMD_WRITE;
+    if (!bdrv_enable_write_cache(bs) && (s->nbdflags & NBD_FLAG_SEND_FUA)) {
+        request.type |= NBD_CMD_FLAG_FUA;
+    }
+
+    request.from = sector_num * 512;
+    request.len = nb_sectors * 512;
+
+    nbd_coroutine_start(s, &request);
+    ret = nbd_co_send_request(s, &request, qiov, offset);
+    if (ret < 0) {
+        reply.error = -ret;
+    } else {
+        nbd_co_receive_reply(s, &request, &reply, NULL, 0);
+    }
+    nbd_coroutine_end(s, &request);
+    return -reply.error;
+}
+
+/* qemu-nbd has a limit of slightly less than 1M per request.  Try to
+ * remain aligned to 4K. */
+#define NBD_MAX_SECTORS 2040
+
 static int nbd_co_readv(BlockDriverState *bs, int64_t sector_num,
                        int nb_sectors, QEMUIOVector *qiov)
 {
-    BDRVNBDState *s = bs->opaque;
-
-    return nbd_client_session_co_readv(&s->client, sector_num,
-                                       nb_sectors, 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);
+        if (ret < 0) {
+            return ret;
+        }
+        offset += NBD_MAX_SECTORS * 512;
+        sector_num += NBD_MAX_SECTORS;
+        nb_sectors -= NBD_MAX_SECTORS;
+    }
+    return nbd_co_readv_1(bs, sector_num, nb_sectors, qiov, offset);
 }

 static int nbd_co_writev(BlockDriverState *bs, int64_t sector_num,
                         int nb_sectors, QEMUIOVector *qiov)
 {
-    BDRVNBDState *s = bs->opaque;
-
-    return nbd_client_session_co_writev(&s->client, sector_num,
-                                        nb_sectors, 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);
+        if (ret < 0) {
+            return ret;
+        }
+        offset += NBD_MAX_SECTORS * 512;
+        sector_num += NBD_MAX_SECTORS;
+        nb_sectors -= NBD_MAX_SECTORS;
+    }
+    return nbd_co_writev_1(bs, sector_num, nb_sectors, qiov, offset);
 }

 static int nbd_co_flush(BlockDriverState *bs)
 {
    BDRVNBDState *s = bs->opaque;
+    struct nbd_request request;
+    struct nbd_reply reply;
+    ssize_t ret;

-    return nbd_client_session_co_flush(&s->client);
+    if (!(s->nbdflags & NBD_FLAG_SEND_FLUSH)) {
+        return 0;
+    }
+
+    request.type = NBD_CMD_FLUSH;
+    if (s->nbdflags & NBD_FLAG_SEND_FUA) {
+        request.type |= NBD_CMD_FLAG_FUA;
+    }
+
+    request.from = 0;
+    request.len = 0;
+
+    nbd_coroutine_start(s, &request);
+    ret = nbd_co_send_request(s, &request, NULL, 0);
+    if (ret < 0) {
+        reply.error = -ret;
+    } else {
+        nbd_co_receive_reply(s, &request, &reply, NULL, 0);
+    }
+    nbd_coroutine_end(s, &request);
+    return -reply.error;
 }

 static int nbd_co_discard(BlockDriverState *bs, int64_t sector_num,
                          int nb_sectors)
 {
    BDRVNBDState *s = bs->opaque;
+    struct nbd_request request;
+    struct nbd_reply reply;
+    ssize_t ret;

-    return nbd_client_session_co_discard(&s->client, sector_num,
-                                         nb_sectors);
+    if (!(s->nbdflags & NBD_FLAG_SEND_TRIM)) {
+        return 0;
+    }
+    request.type = NBD_CMD_TRIM;
+    request.from = sector_num * 512;
+    request.len = nb_sectors * 512;
+
+    nbd_coroutine_start(s, &request);
+    ret = nbd_co_send_request(s, &request, NULL, 0);
+    if (ret < 0) {
+        reply.error = -ret;
+    } else {
+        nbd_co_receive_reply(s, &request, &reply, NULL, 0);
+    }
+    nbd_coroutine_end(s, &request);
+    return -reply.error;
 }

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

 static int64_t nbd_getlength(BlockDriverState *bs)
 {
    BDRVNBDState *s = bs->opaque;

-    return s->client.size;
+    return s->size;
 }

 static BlockDriver bdrv_nbd = {
@@ -1,442 +0,0 @@
-/*
- * QEMU Block driver for native access to files on NFS shares
- *
- * Copyright (c) 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
- * 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 "config-host.h"
-
-#include <poll.h>
-#include "qemu-common.h"
-#include "qemu/config-file.h"
-#include "qemu/error-report.h"
-#include "block/block_int.h"
-#include "trace.h"
-#include "qemu/iov.h"
-#include "qemu/uri.h"
-#include "sysemu/sysemu.h"
-#include <nfsc/libnfs.h>
-
-typedef struct NFSClient {
-    struct nfs_context *context;
-    struct nfsfh *fh;
-    int events;
-    bool has_zero_init;
-} NFSClient;
-
-typedef struct NFSRPC {
-    int ret;
-    int complete;
-    QEMUIOVector *iov;
-    struct stat *st;
-    Coroutine *co;
-    QEMUBH *bh;
-} NFSRPC;
-
-static void nfs_process_read(void *arg);
-static void nfs_process_write(void *arg);
-
-static void nfs_set_events(NFSClient *client)
-{
-    int ev = nfs_which_events(client->context);
-    if (ev != client->events) {
-        qemu_aio_set_fd_handler(nfs_get_fd(client->context),
-                      (ev & POLLIN) ? nfs_process_read : NULL,
-                      (ev & POLLOUT) ? nfs_process_write : NULL,
-                      client);
-
-    }
-    client->events = ev;
-}
-
-static void nfs_process_read(void *arg)
-{
-    NFSClient *client = arg;
-    nfs_service(client->context, POLLIN);
-    nfs_set_events(client);
-}
-
-static void nfs_process_write(void *arg)
-{
-    NFSClient *client = arg;
-    nfs_service(client->context, POLLOUT);
-    nfs_set_events(client);
-}
-
-static void nfs_co_init_task(NFSClient *client, NFSRPC *task)
-{
-    *task = (NFSRPC) {
-        .co         = qemu_coroutine_self(),
-    };
-}
-
-static void nfs_co_generic_bh_cb(void *opaque)
-{
-    NFSRPC *task = opaque;
-    qemu_bh_delete(task->bh);
-    qemu_coroutine_enter(task->co, NULL);
-}
-
-static void
-nfs_co_generic_cb(int ret, struct nfs_context *nfs, void *data,
-                  void *private_data)
-{
-    NFSRPC *task = private_data;
-    task->complete = 1;
-    task->ret = ret;
-    if (task->ret > 0 && task->iov) {
-        if (task->ret <= task->iov->size) {
-            qemu_iovec_from_buf(task->iov, 0, data, task->ret);
-        } else {
-            task->ret = -EIO;
-        }
-    }
-    if (task->ret == 0 && task->st) {
-        memcpy(task->st, data, sizeof(struct stat));
-    }
-    if (task->ret < 0) {
-        error_report("NFS Error: %s", nfs_get_error(nfs));
-    }
-    if (task->co) {
-        task->bh = qemu_bh_new(nfs_co_generic_bh_cb, task);
-        qemu_bh_schedule(task->bh);
-    }
-}
-
-static int coroutine_fn nfs_co_readv(BlockDriverState *bs,
-                                     int64_t sector_num, int nb_sectors,
-                                     QEMUIOVector *iov)
-{
-    NFSClient *client = bs->opaque;
-    NFSRPC task;
-
-    nfs_co_init_task(client, &task);
-    task.iov = iov;
-
-    if (nfs_pread_async(client->context, client->fh,
-                        sector_num * BDRV_SECTOR_SIZE,
-                        nb_sectors * BDRV_SECTOR_SIZE,
-                        nfs_co_generic_cb, &task) != 0) {
-        return -ENOMEM;
-    }
-
-    while (!task.complete) {
-        nfs_set_events(client);
-        qemu_coroutine_yield();
-    }
-
-    if (task.ret < 0) {
-        return task.ret;
-    }
-
-    /* zero pad short reads */
-    if (task.ret < iov->size) {
-        qemu_iovec_memset(iov, task.ret, 0, iov->size - task.ret);
-    }
-
-    return 0;
-}
-
-static int coroutine_fn nfs_co_writev(BlockDriverState *bs,
-                                        int64_t sector_num, int nb_sectors,
-                                        QEMUIOVector *iov)
-{
-    NFSClient *client = bs->opaque;
-    NFSRPC task;
-    char *buf = NULL;
-
-    nfs_co_init_task(client, &task);
-
-    buf = g_malloc(nb_sectors * BDRV_SECTOR_SIZE);
-    qemu_iovec_to_buf(iov, 0, buf, nb_sectors * BDRV_SECTOR_SIZE);
-
-    if (nfs_pwrite_async(client->context, client->fh,
-                         sector_num * BDRV_SECTOR_SIZE,
-                         nb_sectors * BDRV_SECTOR_SIZE,
-                         buf, nfs_co_generic_cb, &task) != 0) {
-        g_free(buf);
-        return -ENOMEM;
-    }
-
-    while (!task.complete) {
-        nfs_set_events(client);
-        qemu_coroutine_yield();
-    }
-
-    g_free(buf);
-
-    if (task.ret != nb_sectors * BDRV_SECTOR_SIZE) {
-        return task.ret < 0 ? task.ret : -EIO;
-    }
-
-    return 0;
-}
-
-static int coroutine_fn nfs_co_flush(BlockDriverState *bs)
-{
-    NFSClient *client = bs->opaque;
-    NFSRPC task;
-
-    nfs_co_init_task(client, &task);
-
-    if (nfs_fsync_async(client->context, client->fh, nfs_co_generic_cb,
-                        &task) != 0) {
-        return -ENOMEM;
-    }
-
-    while (!task.complete) {
-        nfs_set_events(client);
-        qemu_coroutine_yield();
-    }
-
-    return task.ret;
-}
-
-/* TODO Convert to fine grained options */
-static QemuOptsList runtime_opts = {
-    .name = "nfs",
-    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
-    .desc = {
-        {
-            .name = "filename",
-            .type = QEMU_OPT_STRING,
-            .help = "URL to the NFS file",
-        },
-        { /* end of list */ }
-    },
-};
-
-static void nfs_client_close(NFSClient *client)
-{
-    if (client->context) {
-        if (client->fh) {
-            nfs_close(client->context, client->fh);
-        }
-        qemu_aio_set_fd_handler(nfs_get_fd(client->context), NULL, NULL, NULL);
-        nfs_destroy_context(client->context);
-    }
-    memset(client, 0, sizeof(NFSClient));
-}
-
-static void nfs_file_close(BlockDriverState *bs)
-{
-    NFSClient *client = bs->opaque;
-    nfs_client_close(client);
-}
-
-static int64_t nfs_client_open(NFSClient *client, const char *filename,
-                               int flags, Error **errp)
-{
-    int ret = -EINVAL, i;
-    struct stat st;
-    URI *uri;
-    QueryParams *qp = NULL;
-    char *file = NULL, *strp = NULL;
-
-    uri = uri_parse(filename);
-    if (!uri) {
-        error_setg(errp, "Invalid URL specified");
-        goto fail;
-    }
-    strp = strrchr(uri->path, '/');
-    if (strp == NULL) {
-        error_setg(errp, "Invalid URL specified");
-        goto fail;
-    }
-    file = g_strdup(strp);
-    *strp = 0;
-
-    client->context = nfs_init_context();
-    if (client->context == NULL) {
-        error_setg(errp, "Failed to init NFS context");
-        goto fail;
-    }
-
-    qp = query_params_parse(uri->query);
-    for (i = 0; i < qp->n; i++) {
-        if (!qp->p[i].value) {
-            error_setg(errp, "Value for NFS parameter expected: %s",
-                       qp->p[i].name);
-            goto fail;
-        }
-        if (!strncmp(qp->p[i].name, "uid", 3)) {
-            nfs_set_uid(client->context, atoi(qp->p[i].value));
-        } else if (!strncmp(qp->p[i].name, "gid", 3)) {
-            nfs_set_gid(client->context, atoi(qp->p[i].value));
-        } else if (!strncmp(qp->p[i].name, "tcp-syncnt", 10)) {
-            nfs_set_tcp_syncnt(client->context, atoi(qp->p[i].value));
-        } else {
-            error_setg(errp, "Unknown NFS parameter name: %s",
-                       qp->p[i].name);
-            goto fail;
-        }
-    }
-
-    ret = nfs_mount(client->context, uri->server, uri->path);
-    if (ret < 0) {
-        error_setg(errp, "Failed to mount nfs share: %s",
-                   nfs_get_error(client->context));
-        goto fail;
-    }
-
-    if (flags & O_CREAT) {
-        ret = nfs_creat(client->context, file, 0600, &client->fh);
-        if (ret < 0) {
-            error_setg(errp, "Failed to create file: %s",
-                       nfs_get_error(client->context));
-            goto fail;
-        }
-    } else {
-        ret = nfs_open(client->context, file, flags, &client->fh);
-        if (ret < 0) {
-            error_setg(errp, "Failed to open file : %s",
-                       nfs_get_error(client->context));
-            goto fail;
-        }
-    }
-
-    ret = nfs_fstat(client->context, client->fh, &st);
-    if (ret < 0) {
-        error_setg(errp, "Failed to fstat file: %s",
-                   nfs_get_error(client->context));
-        goto fail;
-    }
-
-    ret = DIV_ROUND_UP(st.st_size, BDRV_SECTOR_SIZE);
-    client->has_zero_init = S_ISREG(st.st_mode);
-    goto out;
-fail:
-    nfs_client_close(client);
-out:
-    if (qp) {
-        query_params_free(qp);
-    }
-    uri_free(uri);
-    g_free(file);
-    return ret;
-}
-
-static int nfs_file_open(BlockDriverState *bs, QDict *options, int flags,
-                         Error **errp) {
-    NFSClient *client = bs->opaque;
-    int64_t ret;
-    QemuOpts *opts;
-    Error *local_err = NULL;
-
-    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (error_is_set(&local_err)) {
-        error_propagate(errp, local_err);
-        return -EINVAL;
-    }
-    ret = nfs_client_open(client, qemu_opt_get(opts, "filename"),
-                          (flags & BDRV_O_RDWR) ? O_RDWR : O_RDONLY,
-                          errp);
-    if (ret < 0) {
-        return ret;
-    }
-    bs->total_sectors = ret;
-    return 0;
-}
-
-static int nfs_file_create(const char *url, QEMUOptionParameter *options,
-                           Error **errp)
-{
-    int ret = 0;
-    int64_t total_size = 0;
-    NFSClient *client = g_malloc0(sizeof(NFSClient));
-
-    /* Read out options */
-    while (options && options->name) {
-        if (!strcmp(options->name, "size")) {
-            total_size = options->value.n;
-        }
-        options++;
-    }
-
-    ret = nfs_client_open(client, url, O_CREAT, errp);
-    if (ret < 0) {
-        goto out;
-    }
-    ret = nfs_ftruncate(client->context, client->fh, total_size);
-    nfs_client_close(client);
-out:
-    g_free(client);
-    return ret;
-}
-
-static int nfs_has_zero_init(BlockDriverState *bs)
-{
-    NFSClient *client = bs->opaque;
-    return client->has_zero_init;
-}
-
-static int64_t nfs_get_allocated_file_size(BlockDriverState *bs)
-{
-    NFSClient *client = bs->opaque;
-    NFSRPC task = {0};
-    struct stat st;
-
-    task.st = &st;
-    if (nfs_fstat_async(client->context, client->fh, nfs_co_generic_cb,
-                        &task) != 0) {
-        return -ENOMEM;
-    }
-
-    while (!task.complete) {
-        nfs_set_events(client);
-        qemu_aio_wait();
-    }
-
-    return (task.ret < 0 ? task.ret : st.st_blocks * st.st_blksize);
-}
-
-static int nfs_file_truncate(BlockDriverState *bs, int64_t offset)
-{
-    NFSClient *client = bs->opaque;
-    return nfs_ftruncate(client->context, client->fh, offset);
-}
-
-static BlockDriver bdrv_nfs = {
-    .format_name     = "nfs",
-    .protocol_name   = "nfs",
-
-    .instance_size   = sizeof(NFSClient),
-    .bdrv_needs_filename = true,
-    .bdrv_has_zero_init = nfs_has_zero_init,
-    .bdrv_get_allocated_file_size = nfs_get_allocated_file_size,
-    .bdrv_truncate = nfs_file_truncate,
-
-    .bdrv_file_open  = nfs_file_open,
-    .bdrv_close      = nfs_file_close,
-    .bdrv_create     = nfs_file_create,
-
-    .bdrv_co_readv         = nfs_co_readv,
-    .bdrv_co_writev        = nfs_co_writev,
-    .bdrv_co_flush_to_disk = nfs_co_flush,
-};
-
-static void nfs_block_init(void)
-{
-    bdrv_register(&bdrv_nfs);
-}
-
-block_init(nfs_block_init);
@@ -85,8 +85,7 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,

    if (memcmp(ph.magic, HEADER_MAGIC, 16) ||
        (le32_to_cpu(ph.version) != HEADER_VERSION)) {
-        error_setg(errp, "Image not in Parallels format");
-        ret = -EINVAL;
+        ret = -EMEDIUMTYPE;
        goto fail;
    }

@@ -29,60 +29,6 @@
 #include "qapi/qmp-output-visitor.h"
 #include "qapi/qmp/types.h"

-BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs)
-{
-    BlockDeviceInfo *info = g_malloc0(sizeof(*info));
-
-    info->file                   = g_strdup(bs->filename);
-    info->ro                     = bs->read_only;
-    info->drv                    = g_strdup(bs->drv->format_name);
-    info->encrypted              = bs->encrypted;
-    info->encryption_key_missing = bdrv_key_required(bs);
-
-    if (bs->node_name[0]) {
-        info->has_node_name = true;
-        info->node_name = g_strdup(bs->node_name);
-    }
-
-    if (bs->backing_file[0]) {
-        info->has_backing_file = true;
-        info->backing_file = g_strdup(bs->backing_file);
-    }
-
-    info->backing_file_depth = bdrv_get_backing_file_depth(bs);
-
-    if (bs->io_limits_enabled) {
-        ThrottleConfig 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;
-
-        info->iops    = cfg.buckets[THROTTLE_OPS_TOTAL].avg;
-        info->iops_rd = cfg.buckets[THROTTLE_OPS_READ].avg;
-        info->iops_wr = cfg.buckets[THROTTLE_OPS_WRITE].avg;
-
-        info->has_bps_max     = cfg.buckets[THROTTLE_BPS_TOTAL].max;
-        info->bps_max         = cfg.buckets[THROTTLE_BPS_TOTAL].max;
-        info->has_bps_rd_max  = cfg.buckets[THROTTLE_BPS_READ].max;
-        info->bps_rd_max      = cfg.buckets[THROTTLE_BPS_READ].max;
-        info->has_bps_wr_max  = cfg.buckets[THROTTLE_BPS_WRITE].max;
-        info->bps_wr_max      = cfg.buckets[THROTTLE_BPS_WRITE].max;
-
-        info->has_iops_max    = cfg.buckets[THROTTLE_OPS_TOTAL].max;
-        info->iops_max        = cfg.buckets[THROTTLE_OPS_TOTAL].max;
-        info->has_iops_rd_max = cfg.buckets[THROTTLE_OPS_READ].max;
-        info->iops_rd_max     = cfg.buckets[THROTTLE_OPS_READ].max;
-        info->has_iops_wr_max = cfg.buckets[THROTTLE_OPS_WRITE].max;
-        info->iops_wr_max     = cfg.buckets[THROTTLE_OPS_WRITE].max;
-
-        info->has_iops_size = cfg.op_size;
-        info->iops_size = cfg.op_size;
-    }
-
-    return info;
-}
-
 /*
 * Returns 0 on success, with *p_list either set to describe snapshot
 * information, or NULL because there are no snapshots.  Returns -errno on
@@ -258,20 +204,76 @@ void bdrv_query_info(BlockDriverState *bs,
        info->io_status = bs->iostatus;
    }

-    if (!QLIST_EMPTY(&bs->dirty_bitmaps)) {
-        info->has_dirty_bitmaps = true;
-        info->dirty_bitmaps = bdrv_query_dirty_bitmaps(bs);
+    if (bs->dirty_bitmap) {
+        info->has_dirty = true;
+        info->dirty = g_malloc0(sizeof(*info->dirty));
+        info->dirty->count = bdrv_get_dirty_count(bs) * BDRV_SECTOR_SIZE;
+        info->dirty->granularity =
+         ((int64_t) BDRV_SECTOR_SIZE << hbitmap_granularity(bs->dirty_bitmap));
    }

    if (bs->drv) {
        info->has_inserted = true;
-        info->inserted = bdrv_block_device_info(bs);
+        info->inserted = g_malloc0(sizeof(*info->inserted));
+        info->inserted->file = g_strdup(bs->filename);
+        info->inserted->ro = bs->read_only;
+        info->inserted->drv = g_strdup(bs->drv->format_name);
+        info->inserted->encrypted = bs->encrypted;
+        info->inserted->encryption_key_missing = bdrv_key_required(bs);
+
+        if (bs->backing_file[0]) {
+            info->inserted->has_backing_file = true;
+            info->inserted->backing_file = g_strdup(bs->backing_file);
+        }
+
+        info->inserted->backing_file_depth = bdrv_get_backing_file_depth(bs);
+
+        if (bs->io_limits_enabled) {
+            ThrottleConfig cfg;
+            throttle_get_config(&bs->throttle_state, &cfg);
+            info->inserted->bps     = cfg.buckets[THROTTLE_BPS_TOTAL].avg;
+            info->inserted->bps_rd  = cfg.buckets[THROTTLE_BPS_READ].avg;
+            info->inserted->bps_wr  = cfg.buckets[THROTTLE_BPS_WRITE].avg;
+
+            info->inserted->iops    = cfg.buckets[THROTTLE_OPS_TOTAL].avg;
+            info->inserted->iops_rd = cfg.buckets[THROTTLE_OPS_READ].avg;
+            info->inserted->iops_wr = cfg.buckets[THROTTLE_OPS_WRITE].avg;
+
+            info->inserted->has_bps_max     =
+                cfg.buckets[THROTTLE_BPS_TOTAL].max;
+            info->inserted->bps_max         =
+                cfg.buckets[THROTTLE_BPS_TOTAL].max;
+            info->inserted->has_bps_rd_max  =
+                cfg.buckets[THROTTLE_BPS_READ].max;
+            info->inserted->bps_rd_max      =
+                cfg.buckets[THROTTLE_BPS_READ].max;
+            info->inserted->has_bps_wr_max  =
+                cfg.buckets[THROTTLE_BPS_WRITE].max;
+            info->inserted->bps_wr_max      =
+                cfg.buckets[THROTTLE_BPS_WRITE].max;
+
+            info->inserted->has_iops_max    =
+                cfg.buckets[THROTTLE_OPS_TOTAL].max;
+            info->inserted->iops_max        =
+                cfg.buckets[THROTTLE_OPS_TOTAL].max;
+            info->inserted->has_iops_rd_max =
+                cfg.buckets[THROTTLE_OPS_READ].max;
+            info->inserted->iops_rd_max     =
+                cfg.buckets[THROTTLE_OPS_READ].max;
+            info->inserted->has_iops_wr_max =
+                cfg.buckets[THROTTLE_OPS_WRITE].max;
+            info->inserted->iops_wr_max     =
+                cfg.buckets[THROTTLE_OPS_WRITE].max;
+
+            info->inserted->has_iops_size = cfg.op_size;
+            info->inserted->iops_size = cfg.op_size;
+        }

        bs0 = bs;
        p_image_info = &info->inserted->image;
        while (1) {
            bdrv_query_image_info(bs0, p_image_info, &local_err);
-            if (local_err) {
+            if (error_is_set(&local_err)) {
                error_propagate(errp, local_err);
                goto err;
            }
@@ -319,11 +321,6 @@ BlockStats *bdrv_query_stats(const BlockDriverState *bs)
        s->parent = bdrv_query_stats(bs->file);
    }

-    if (bs->backing_hd) {
-        s->has_backing = true;
-        s->backing = bdrv_query_stats(bs->backing_hd);
-    }
-
    return s;
 }

@@ -336,7 +333,7 @@ BlockInfoList *qmp_query_block(Error **errp)
     while ((bs = bdrv_next(bs))) {
        BlockInfoList *info = g_malloc0(sizeof(*info));
        bdrv_query_info(bs, &info->value, &local_err);
-        if (local_err) {
+        if (error_is_set(&local_err)) {
            error_propagate(errp, local_err);
            goto err;
        }
@@ -115,15 +115,14 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
    be64_to_cpus(&header.l1_table_offset);

    if (header.magic != QCOW_MAGIC) {
-        error_setg(errp, "Image not in qcow format");
-        ret = -EINVAL;
+        ret = -EMEDIUMTYPE;
        goto fail;
    }
    if (header.version != QCOW_VERSION) {
        char version[64];
        snprintf(version, sizeof(version), "QCOW version %d", header.version);
-        error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
-                  bs->device_name, "qcow", version);
+        qerror_report(QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+            bs->device_name, "qcow", version);
        ret = -ENOTSUP;
        goto fail;
    }
@@ -148,7 +147,6 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
    }

    if (header.crypt_method > QCOW_CRYPT_AES) {
-        error_setg(errp, "invalid encryption method in qcow header");
        ret = -EINVAL;
        goto fail;
    }
@@ -719,15 +717,15 @@ static int qcow_create(const char *filename, QEMUOptionParameter *options,

    ret = bdrv_create_file(filename, options, &local_err);
    if (ret < 0) {
-        error_propagate(errp, local_err);
+        qerror_report_err(local_err);
+        error_free(local_err);
        return ret;
    }

-    qcow_bs = NULL;
-    ret = bdrv_open(&qcow_bs, filename, NULL, NULL,
-                    BDRV_O_RDWR | BDRV_O_PROTOCOL, NULL, &local_err);
+    ret = bdrv_file_open(&qcow_bs, filename, NULL, BDRV_O_RDWR, &local_err);
    if (ret < 0) {
-        error_propagate(errp, local_err);
+        qerror_report_err(local_err);
+        error_free(local_err);
        return ret;
    }

@@ -753,7 +751,7 @@ static int qcow_create(const char *filename, QEMUOptionParameter *options,
            backing_file = NULL;
        }
        header.cluster_bits = 9; /* 512 byte cluster to avoid copying
-                                    unmodified sectors */
+                                    unmodifyed sectors */
        header.l2_bits = 12; /* 32 KB L2 tables */
    } else {
        header.cluster_bits = 12; /* 4 KB clusters */
@@ -371,10 +371,6 @@ static int coroutine_fn copy_sectors(BlockDriverState *bs,

    BLKDBG_EVENT(bs->file, BLKDBG_COW_READ);

-    if (!bs->drv) {
-        return -ENOMEDIUM;
-    }
-
    /* Call .bdrv_co_readv() directly instead of using the public block-layer
     * interface.  This avoids double I/O throttling and request tracking,
     * which can lead to deadlock when block layer copy-on-read is enabled.
@@ -491,7 +487,6 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
        break;
    case QCOW2_CLUSTER_ZERO:
        if (s->qcow_version < 3) {
-            qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
            return -EIO;
        }
        c = count_contiguous_clusters(nb_clusters, s->cluster_size,
@@ -1178,7 +1173,7 @@ fail:
 * Return 0 on success and -errno in error cases
 */
 int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
-    int *num, uint64_t *host_offset, QCowL2Meta **m)
+    int n_start, int n_end, int *num, uint64_t *host_offset, QCowL2Meta **m)
 {
    BDRVQcowState *s = bs->opaque;
    uint64_t start, remaining;
@@ -1186,13 +1181,15 @@ int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
    uint64_t cur_bytes;
    int ret;

-    trace_qcow2_alloc_clusters_offset(qemu_coroutine_self(), offset, *num);
+    trace_qcow2_alloc_clusters_offset(qemu_coroutine_self(), offset,
+                                      n_start, n_end);

-    assert((offset & ~BDRV_SECTOR_MASK) == 0);
+    assert(n_start * BDRV_SECTOR_SIZE == offset_into_cluster(s, offset));
+    offset = start_of_cluster(s, offset);

 again:
-    start = offset;
-    remaining = *num << BDRV_SECTOR_BITS;
+    start = offset + (n_start << BDRV_SECTOR_BITS);
+    remaining = (n_end - n_start) << BDRV_SECTOR_BITS;
    cluster_offset = 0;
    *host_offset = 0;
    cur_bytes = 0;
@@ -1278,7 +1275,7 @@ again:
        }
    }

-    *num -= remaining >> BDRV_SECTOR_BITS;
+    *num = (n_end - n_start) - (remaining >> BDRV_SECTOR_BITS);
    assert(*num > 0);
    assert(*host_offset != 0);

@@ -1363,31 +1360,13 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
        uint64_t old_offset;

        old_offset = be64_to_cpu(l2_table[l2_index + i]);
-
-        /*
-         * Make sure that a discarded area reads back as zeroes for v3 images
-         * (we cannot do it for v2 without actually writing a zero-filled
-         * buffer). We can skip the operation if the cluster is already marked
-         * as zero, or if it's unallocated and we don't have a backing file.
-         *
-         * TODO We might want to use bdrv_get_block_status(bs) here, but we're
-         * holding s->lock, so that doesn't work today.
-         */
-        if (old_offset & QCOW_OFLAG_ZERO) {
-            continue;
-        }
-
-        if ((old_offset & L2E_OFFSET_MASK) == 0 && !bs->backing_hd) {
+        if ((old_offset & L2E_OFFSET_MASK) == 0) {
            continue;
        }

        /* First remove L2 entries */
        qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
-        if (s->qcow_version >= 3) {
-            l2_table[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO);
-        } else {
-            l2_table[l2_index + i] = cpu_to_be64(0);
-        }
+        l2_table[l2_index + i] = cpu_to_be64(0);

        /* Then decrease the refcount */
        qcow2_free_any_clusters(bs, old_offset, 1, type);
@@ -1413,7 +1392,7 @@ int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,

    /* Round start up and end down */
    offset = align_offset(offset, s->cluster_size);
-    end_offset = start_of_cluster(s, end_offset);
+    end_offset &= ~(s->cluster_size - 1);

    if (offset > end_offset) {
        return 0;
@@ -1625,7 +1604,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
            }

            ret = bdrv_write_zeroes(bs->file, offset / BDRV_SECTOR_SIZE,
-                                    s->cluster_sectors, 0);
+                                    s->cluster_sectors);
            if (ret < 0) {
                if (!preallocated) {
                    qcow2_free_clusters(bs, offset, s->cluster_size,
@@ -98,8 +98,7 @@ static int get_refcount(BlockDriverState *bs, int64_t cluster_index)
    refcount_table_index = cluster_index >> (s->cluster_bits - REFCOUNT_SHIFT);
    if (refcount_table_index >= s->refcount_table_size)
        return 0;
-    refcount_block_offset =
-        s->refcount_table[refcount_table_index] & REFT_OFFSET_MASK;
+    refcount_block_offset = s->refcount_table[refcount_table_index];
    if (!refcount_block_offset)
        return 0;

@@ -524,8 +523,8 @@ static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
            s->l2_table_cache);
    }

-    start = start_of_cluster(s, offset);
-    last = start_of_cluster(s, offset + length - 1);
+    start = offset & ~(s->cluster_size - 1);
+    last = (offset + length - 1) & ~(s->cluster_size - 1);
    for(cluster_offset = start; cluster_offset <= last;
        cluster_offset += s->cluster_size)
    {
@@ -740,7 +739,7 @@ int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size)
    }
 redo:
    free_in_cluster = s->cluster_size -
-        offset_into_cluster(s, s->free_byte_offset);
+        (s->free_byte_offset & (s->cluster_size - 1));
    if (size <= free_in_cluster) {
        /* enough space in current cluster */
        offset = s->free_byte_offset;
@@ -748,7 +747,7 @@ int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size)
        free_in_cluster -= size;
        if (free_in_cluster == 0)
            s->free_byte_offset = 0;
-        if (offset_into_cluster(s, offset) != 0)
+        if ((offset & (s->cluster_size - 1)) != 0)
            qcow2_update_cluster_refcount(bs, offset >> s->cluster_bits, 1,
                                          QCOW2_DISCARD_NEVER);
    } else {
@@ -756,7 +755,7 @@ int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size)
        if (offset < 0) {
            return offset;
        }
-        cluster_offset = start_of_cluster(s, s->free_byte_offset);
+        cluster_offset = s->free_byte_offset & ~(s->cluster_size - 1);
        if ((cluster_offset + s->cluster_size) == offset) {
            /* we are lucky: contiguous data */
            offset = s->free_byte_offset;
@@ -1025,8 +1024,8 @@ static void inc_refcounts(BlockDriverState *bs,
    if (size <= 0)
        return;

-    start = start_of_cluster(s, offset);
-    last = start_of_cluster(s, offset + size - 1);
+    start = offset & ~(s->cluster_size - 1);
+    last = (offset + size - 1) & ~(s->cluster_size - 1);
    for(cluster_offset = start; cluster_offset <= last;
        cluster_offset += s->cluster_size) {
        k = cluster_offset >> s->cluster_bits;
@@ -1133,7 +1132,7 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res,
                offset, s->cluster_size);

            /* Correct offsets are cluster aligned */
-            if (offset_into_cluster(s, offset)) {
+            if (offset & (s->cluster_size - 1)) {
                fprintf(stderr, "ERROR offset=%" PRIx64 ": Cluster is not "
                    "properly aligned; L2 entry corrupted.\n", offset);
                res->corruptions++;
@@ -1205,7 +1204,7 @@ static int check_refcounts_l1(BlockDriverState *bs,
                l2_offset, s->cluster_size);

            /* L2 tables are cluster aligned */
-            if (offset_into_cluster(s, l2_offset)) {
+            if (l2_offset & (s->cluster_size - 1)) {
                fprintf(stderr, "ERROR l2_offset=%" PRIx64 ": Table is not "
                    "cluster aligned; L1 entry corrupted\n", l2_offset);
                res->corruptions++;
@@ -1387,7 +1386,7 @@ static int write_reftable_entry(BlockDriverState *bs, int rt_index)
 * does _not_ decrement the reference count for the currently occupied cluster.
 *
 * This function prints an informative message to stderr on error (and returns
- * -errno); on success, the offset of the newly allocated cluster is returned.
+ * -errno); on success, 0 is returned.
 */
 static int64_t realloc_refcount_block(BlockDriverState *bs, int reftable_index,
                                      uint64_t offset)
@@ -1403,14 +1402,14 @@ static int64_t realloc_refcount_block(BlockDriverState *bs, int reftable_index,
        fprintf(stderr, "Could not allocate new cluster: %s\n",
                strerror(-new_offset));
        ret = new_offset;
-        goto done;
+        goto fail;
    }

    /* fetch current refcount block content */
    ret = qcow2_cache_get(bs, s->refcount_block_cache, offset, &refcount_block);
    if (ret < 0) {
        fprintf(stderr, "Could not fetch refcount block: %s\n", strerror(-ret));
-        goto fail_free_cluster;
+        goto fail;
    }

    /* new block has not yet been entered into refcount table, therefore it is
@@ -1421,7 +1420,8 @@ static int64_t realloc_refcount_block(BlockDriverState *bs, int reftable_index,
                "check failed: %s\n", strerror(-ret));
        /* the image will be marked corrupt, so don't even attempt on freeing
         * the cluster */
-        goto done;
+        new_offset = 0;
+        goto fail;
    }

    /* write to new block */
@@ -1429,37 +1429,34 @@ static int64_t realloc_refcount_block(BlockDriverState *bs, int reftable_index,
            s->cluster_sectors);
    if (ret < 0) {
        fprintf(stderr, "Could not write refcount block: %s\n", strerror(-ret));
-        goto fail_free_cluster;
+        goto fail;
    }

    /* update refcount table */
-    assert(!offset_into_cluster(s, new_offset));
+    assert(!(new_offset & (s->cluster_size - 1)));
    s->refcount_table[reftable_index] = new_offset;
    ret = write_reftable_entry(bs, reftable_index);
    if (ret < 0) {
        fprintf(stderr, "Could not update refcount table: %s\n",
                strerror(-ret));
-        goto fail_free_cluster;
+        goto fail;
    }

-    goto done;
-
-fail_free_cluster:
-    qcow2_free_clusters(bs, new_offset, s->cluster_size, QCOW2_DISCARD_OTHER);
-
-done:
+fail:
+    if (new_offset && (ret < 0)) {
+        qcow2_free_clusters(bs, new_offset, s->cluster_size,
+                QCOW2_DISCARD_ALWAYS);
+    }
    if (refcount_block) {
-        /* This should never fail, as it would only do so if the given refcount
-         * block cannot be found in the cache. As this is impossible as long as
-         * there are no bugs, assert the success. */
-        int tmp = qcow2_cache_put(bs, s->refcount_block_cache, &refcount_block);
-        assert(tmp == 0);
+        if (ret < 0) {
+            qcow2_cache_put(bs, s->refcount_block_cache, &refcount_block);
+        } else {
+            ret = qcow2_cache_put(bs, s->refcount_block_cache, &refcount_block);
+        }
    }
-
    if (ret < 0) {
        return ret;
    }
-
    return new_offset;
 }

@@ -1525,7 +1522,7 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
        cluster = offset >> s->cluster_bits;

        /* Refcount blocks are cluster aligned */
-        if (offset_into_cluster(s, offset)) {
+        if (offset & (s->cluster_size - 1)) {
            fprintf(stderr, "ERROR refcount block %" PRId64 " is not "
                "cluster aligned; refcount table entry corrupted\n", i);
            res->corruptions++;
@@ -116,14 +116,8 @@ int qcow2_read_snapshots(BlockDriverState *bs)
        }
        offset += name_size;
        sn->name[name_size] = '\0';
-
-        if (offset - s->snapshots_offset > QCOW_MAX_SNAPSHOTS_SIZE) {
-            ret = -EFBIG;
-            goto fail;
-        }
    }

-    assert(offset - s->snapshots_offset <= INT_MAX);
    s->snapshots_size = offset - s->snapshots_offset;
    return 0;

@@ -144,7 +138,7 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
        uint32_t nb_snapshots;
        uint64_t snapshots_offset;
    } QEMU_PACKED header_data;
-    int64_t offset, snapshots_offset = 0;
+    int64_t offset, snapshots_offset;
    int ret;

    /* compute the size of the snapshots */
@@ -156,14 +150,7 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
        offset += sizeof(extra);
        offset += strlen(sn->id_str);
        offset += strlen(sn->name);
-
-        if (offset > QCOW_MAX_SNAPSHOTS_SIZE) {
-            ret = -EFBIG;
-            goto fail;
-        }
    }
-
-    assert(offset <= INT_MAX);
    snapshots_size = offset;

    /* Allocate space for the new snapshot list */
@@ -598,8 +585,7 @@ int qcow2_snapshot_delete(BlockDriverState *bs,
    s->nb_snapshots--;
    ret = qcow2_write_snapshots(bs);
    if (ret < 0) {
-        error_setg_errno(errp, -ret,
-                         "Failed to remove snapshot from snapshot list");
+        error_setg(errp, "Failed to remove snapshot from snapshot list");
        return ret;
    }

@@ -617,7 +603,7 @@ int qcow2_snapshot_delete(BlockDriverState *bs,
    ret = qcow2_update_snapshot_refcount(bs, sn.l1_table_offset,
                                         sn.l1_size, -1);
    if (ret < 0) {
-        error_setg_errno(errp, -ret, "Failed to free the cluster and L1 table");
+        error_setg(errp, "Failed to free the cluster and L1 table");
        return ret;
    }
    qcow2_free_clusters(bs, sn.l1_table_offset, sn.l1_size * sizeof(uint64_t),
@@ -626,8 +612,7 @@ int qcow2_snapshot_delete(BlockDriverState *bs,
    /* must update the copied flag on the current cluster offsets */
    ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 0);
    if (ret < 0) {
-        error_setg_errno(errp, -ret,
-                         "Failed to update snapshot status in disk");
+        error_setg(errp, "Failed to update snapshot status in disk");
        return ret;
    }

@@ -669,10 +654,7 @@ int qcow2_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
    return s->nb_snapshots;
 }

-int qcow2_snapshot_load_tmp(BlockDriverState *bs,
-                            const char *snapshot_id,
-                            const char *name,
-                            Error **errp)
+int qcow2_snapshot_load_tmp(BlockDriverState *bs, const char *snapshot_name)
 {
    int i, snapshot_index;
    BDRVQcowState *s = bs->opaque;
@@ -684,17 +666,15 @@ int qcow2_snapshot_load_tmp(BlockDriverState *bs,
    assert(bs->read_only);

    /* Search the snapshot */
-    snapshot_index = find_snapshot_by_id_and_name(bs, snapshot_id, name);
+    snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_name);
    if (snapshot_index < 0) {
-        error_setg(errp,
-                   "Can't find snapshot");
        return -ENOENT;
    }
    sn = &s->snapshots[snapshot_index];

    /* Allocate and read in the snapshot's L1 table */
    if (sn->l1_size > QCOW_MAX_L1_SIZE) {
-        error_setg(errp, "Snapshot L1 table too large");
+        error_report("Snapshot L1 table too large");
        return -EFBIG;
    }
    new_l1_bytes = sn->l1_size * sizeof(uint64_t);
@@ -702,7 +682,6 @@ int qcow2_snapshot_load_tmp(BlockDriverState *bs,

    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");
        g_free(new_l1_table);
        return ret;
    }
@@ -479,7 +479,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,

    if (header.magic != QCOW_MAGIC) {
        error_setg(errp, "Image is not in qcow2 format");
-        ret = -EINVAL;
+        ret = -EMEDIUMTYPE;
        goto fail;
    }
    if (header.version < 2 || header.version > 3) {
@@ -566,7 +566,6 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
                                   s->incompatible_features &
                                   ~QCOW2_INCOMPAT_MASK);
        ret = -ENOTSUP;
-        g_free(feature_table);
        goto fail;
    }

@@ -743,7 +742,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
    }

    /* Clear unknown autoclear feature bits */
-    if (!bs->read_only && !(flags & BDRV_O_INCOMING) && s->autoclear_features) {
+    if (!bs->read_only && s->autoclear_features != 0) {
        s->autoclear_features = 0;
        ret = qcow2_update_header(bs);
        if (ret < 0) {
@@ -756,7 +755,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
    qemu_co_mutex_init(&s->lock);

    /* Repair image if dirty */
-    if (!(flags & (BDRV_O_CHECK | BDRV_O_INCOMING)) && !bs->read_only &&
+    if (!(flags & BDRV_O_CHECK) && !bs->read_only &&
        (s->incompatible_features & QCOW2_INCOMPAT_DIRTY)) {
        BdrvCheckResult result = {0};

@@ -768,9 +767,9 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
    }

    /* Enable lazy_refcounts according to image and command line options */
-    opts = qemu_opts_create(&qcow2_runtime_opts, NULL, 0, &error_abort);
+    opts = qemu_opts_create_nofail(&qcow2_runtime_opts);
    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
        ret = -EINVAL;
        goto fail;
@@ -844,23 +843,11 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
    if (s->l2_table_cache) {
        qcow2_cache_destroy(bs, s->l2_table_cache);
    }
-    if (s->refcount_block_cache) {
-        qcow2_cache_destroy(bs, s->refcount_block_cache);
-    }
    g_free(s->cluster_cache);
    qemu_vfree(s->cluster_data);
    return ret;
 }

-static int qcow2_refresh_limits(BlockDriverState *bs)
-{
-    BDRVQcowState *s = bs->opaque;
-
-    bs->bl.write_zeroes_alignment = s->cluster_sectors;
-
-    return 0;
-}
-
 static int qcow2_set_key(BlockDriverState *bs, const char *key)
 {
    BDRVQcowState *s = bs->opaque;
@@ -1116,6 +1103,7 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
 {
    BDRVQcowState *s = bs->opaque;
    int index_in_cluster;
+    int n_end;
    int ret;
    int cur_nr_sectors; /* number of sectors in current iteration */
    uint64_t cluster_offset;
@@ -1139,16 +1127,14 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,

        trace_qcow2_writev_start_part(qemu_coroutine_self());
        index_in_cluster = sector_num & (s->cluster_sectors - 1);
-        cur_nr_sectors = remaining_sectors;
+        n_end = index_in_cluster + remaining_sectors;
        if (s->crypt_method &&
-            cur_nr_sectors >
-            QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors - index_in_cluster) {
-            cur_nr_sectors =
-                QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors - index_in_cluster;
+            n_end > QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors) {
+            n_end = QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors;
        }

        ret = qcow2_alloc_cluster_offset(bs, sector_num << 9,
-            &cur_nr_sectors, &cluster_offset, &l2meta);
+            index_in_cluster, n_end, &cur_nr_sectors, &cluster_offset, &l2meta);
        if (ret < 0) {
            goto fail;
        }
@@ -1253,12 +1239,10 @@ static void qcow2_close(BlockDriverState *bs)
    /* else pre-write overlap checks in cache_destroy may crash */
    s->l1_table = NULL;

-    if (!(bs->open_flags & BDRV_O_INCOMING)) {
-        qcow2_cache_flush(bs, s->l2_table_cache);
-        qcow2_cache_flush(bs, s->refcount_block_cache);
+    qcow2_cache_flush(bs, s->l2_table_cache);
+    qcow2_cache_flush(bs, s->refcount_block_cache);

-        qcow2_mark_clean(bs);
-    }
+    qcow2_mark_clean(bs);

    qcow2_cache_destroy(bs, s->l2_table_cache);
    qcow2_cache_destroy(bs, s->refcount_block_cache);
@@ -1272,7 +1256,7 @@ static void qcow2_close(BlockDriverState *bs)
    qcow2_free_snapshots(bs);
 }

-static void qcow2_invalidate_cache(BlockDriverState *bs, Error **errp)
+static void qcow2_invalidate_cache(BlockDriverState *bs)
 {
    BDRVQcowState *s = bs->opaque;
    int flags = s->flags;
@@ -1280,8 +1264,6 @@ static void qcow2_invalidate_cache(BlockDriverState *bs, Error **errp)
    AES_KEY aes_decrypt_key;
    uint32_t crypt_method = 0;
    QDict *options;
-    Error *local_err = NULL;
-    int ret;

    /*
     * Backing files are read-only which makes all of their metadata immutable,
@@ -1296,26 +1278,14 @@ static void qcow2_invalidate_cache(BlockDriverState *bs, Error **errp)

    qcow2_close(bs);

-    bdrv_invalidate_cache(bs->file, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        return;
-    }
+    options = qdict_new();
+    qdict_put(options, QCOW2_OPT_LAZY_REFCOUNTS,
+              qbool_from_int(s->use_lazy_refcounts));

    memset(s, 0, sizeof(BDRVQcowState));
-    options = qdict_clone_shallow(bs->options);
+    qcow2_open(bs, options, flags, NULL);

-    ret = qcow2_open(bs, options, flags, &local_err);
    QDECREF(options);
-    if (local_err) {
-        error_setg(errp, "Could not reopen qcow2 layer: %s",
-                   error_get_pretty(local_err));
-        error_free(local_err);
-        return;
-    } else if (ret < 0) {
-        error_setg_errno(errp, -ret, "Could not reopen qcow2 layer");
-        return;
-    }

    if (crypt_method) {
        s->crypt_method = crypt_method;
@@ -1536,39 +1506,34 @@ static int preallocate(BlockDriverState *bs)
    int ret;
    QCowL2Meta *meta;

-    nb_sectors = bdrv_getlength(bs) >> BDRV_SECTOR_BITS;
+    nb_sectors = bdrv_getlength(bs) >> 9;
    offset = 0;

    while (nb_sectors) {
-        num = MIN(nb_sectors, INT_MAX >> BDRV_SECTOR_BITS);
-        ret = qcow2_alloc_cluster_offset(bs, offset, &num,
+        num = MIN(nb_sectors, INT_MAX >> 9);
+        ret = qcow2_alloc_cluster_offset(bs, offset, 0, num, &num,
                                         &host_offset, &meta);
        if (ret < 0) {
            return ret;
        }

-        while (meta) {
-            QCowL2Meta *next = meta->next;
+        ret = qcow2_alloc_cluster_link_l2(bs, meta);
+        if (ret < 0) {
+            qcow2_free_any_clusters(bs, meta->alloc_offset, meta->nb_clusters,
+                                    QCOW2_DISCARD_NEVER);
+            return ret;
+        }

-            ret = qcow2_alloc_cluster_link_l2(bs, meta);
-            if (ret < 0) {
-                qcow2_free_any_clusters(bs, meta->alloc_offset,
-                                        meta->nb_clusters, QCOW2_DISCARD_NEVER);
-                return ret;
-            }
-
-            /* There are no dependent requests, but we need to remove our
-             * request from the list of in-flight requests */
+        /* There are no dependent requests, but we need to remove our request
+         * from the list of in-flight requests */
+        if (meta != NULL) {
            QLIST_REMOVE(meta, next_in_flight);
-
-            g_free(meta);
-            meta = next;
        }

        /* TODO Preallocate data if requested */

        nb_sectors -= num;
-        offset += num << BDRV_SECTOR_BITS;
+        offset += num << 9;
    }

    /*
@@ -1577,10 +1542,9 @@ static int preallocate(BlockDriverState *bs)
     * EOF). Extend the image to the last allocated sector.
     */
    if (host_offset != 0) {
-        uint8_t buf[BDRV_SECTOR_SIZE];
-        memset(buf, 0, BDRV_SECTOR_SIZE);
-        ret = bdrv_write(bs->file, (host_offset >> BDRV_SECTOR_BITS) + num - 1,
-                         buf, 1);
+        uint8_t buf[512];
+        memset(buf, 0, 512);
+        ret = bdrv_write(bs->file, (host_offset >> 9) + num - 1, buf, 1);
        if (ret < 0) {
            return ret;
        }
@@ -1630,9 +1594,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
        return ret;
    }

-    bs = NULL;
-    ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
-                    NULL, &local_err);
+    ret = bdrv_file_open(&bs, filename, NULL, BDRV_O_RDWR, &local_err);
    if (ret < 0) {
        error_propagate(errp, local_err);
        return ret;
@@ -1683,8 +1645,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
        goto out;
    }

-    bdrv_unref(bs);
-    bs = NULL;
+    bdrv_close(bs);

    /*
     * And now open the image and make it consistent first (i.e. increase the
@@ -1693,7 +1654,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
     */
    BlockDriver* drv = bdrv_find_format("qcow2");
    assert(drv != NULL);
-    ret = bdrv_open(&bs, filename, NULL, NULL,
+    ret = bdrv_open(bs, filename, NULL,
        BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH, drv, &local_err);
    if (ret < 0) {
        error_propagate(errp, local_err);
@@ -1740,23 +1701,20 @@ static int qcow2_create2(const char *filename, int64_t total_size,
        }
    }

-    bdrv_unref(bs);
-    bs = NULL;
+    bdrv_close(bs);

    /* Reopen the image without BDRV_O_NO_FLUSH to flush it before returning */
-    ret = bdrv_open(&bs, filename, NULL, NULL,
+    ret = bdrv_open(bs, filename, NULL,
                    BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_BACKING,
                    drv, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
        goto out;
    }

    ret = 0;
 out:
-    if (bs) {
-        bdrv_unref(bs);
-    }
+    bdrv_unref(bs);
    return ret;
 }

@@ -1829,14 +1787,34 @@ static int qcow2_create(const char *filename, QEMUOptionParameter *options,

    ret = qcow2_create2(filename, sectors, backing_file, backing_fmt, flags,
                        cluster_size, prealloc, options, version, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
    }
    return ret;
 }

+static int qcow2_make_empty(BlockDriverState *bs)
+{
+#if 0
+    /* XXX: not correct */
+    BDRVQcowState *s = bs->opaque;
+    uint32_t l1_length = s->l1_size * sizeof(uint64_t);
+    int ret;
+
+    memset(s->l1_table, 0, l1_length);
+    if (bdrv_pwrite(bs->file, s->l1_table_offset, s->l1_table, l1_length) < 0)
+        return -1;
+    ret = bdrv_truncate(bs->file, s->l1_table_offset + l1_length);
+    if (ret < 0)
+        return ret;
+
+    l2_cache_reset(bs);
+#endif
+    return 0;
+}
+
 static coroutine_fn int qcow2_co_write_zeroes(BlockDriverState *bs,
-    int64_t sector_num, int nb_sectors, BdrvRequestFlags flags)
+    int64_t sector_num, int nb_sectors)
 {
    int ret;
    BDRVQcowState *s = bs->opaque;
@@ -2032,8 +2010,6 @@ static coroutine_fn int qcow2_co_flush_to_os(BlockDriverState *bs)
 static int qcow2_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
 {
    BDRVQcowState *s = bs->opaque;
-    bdi->unallocated_blocks_are_zero = true;
-    bdi->can_write_zeroes_with_unmap = (s->qcow_version >= 3);
    bdi->cluster_size = s->cluster_size;
    bdi->vm_state_offset = qcow2_vm_state_offset(s);
    return 0;
@@ -2378,6 +2354,7 @@ static BlockDriver bdrv_qcow2 = {
    .bdrv_has_zero_init = bdrv_has_zero_init_1,
    .bdrv_co_get_block_status = qcow2_co_get_block_status,
    .bdrv_set_key       = qcow2_set_key,
+    .bdrv_make_empty    = qcow2_make_empty,

    .bdrv_co_readv          = qcow2_co_readv,
    .bdrv_co_writev         = qcow2_co_writev,
@@ -2401,7 +2378,6 @@ static BlockDriver bdrv_qcow2 = {

    .bdrv_change_backing_file   = qcow2_change_backing_file,

-    .bdrv_refresh_limits        = qcow2_refresh_limits,
    .bdrv_invalidate_cache      = qcow2_invalidate_cache,

    .create_options = qcow2_create_options,
@@ -48,10 +48,6 @@
 * (128 GB for 512 byte clusters, 2 EB for 2 MB clusters) */
 #define QCOW_MAX_L1_SIZE 0x2000000

-/* Allow for an average of 1k per snapshot table entry, should be plenty of
- * space for snapshot names and IDs */
-#define QCOW_MAX_SNAPSHOTS_SIZE (1024 * QCOW_MAX_SNAPSHOTS)
-
 /* indicate that the refcount of the referenced cluster is exactly one. */
 #define QCOW_OFLAG_COPIED     (1ULL << 63)
 /* indicate that the cluster is compressed (they never have the copied flag) */
@@ -379,11 +375,11 @@ typedef enum QCow2MetadataOverlap {
 #define QCOW2_OL_ALL \
    (QCOW2_OL_CACHED | QCOW2_OL_INACTIVE_L2)

-#define L1E_OFFSET_MASK 0x00fffffffffffe00ULL
-#define L2E_OFFSET_MASK 0x00fffffffffffe00ULL
+#define L1E_OFFSET_MASK 0x00ffffffffffff00ULL
+#define L2E_OFFSET_MASK 0x00ffffffffffff00ULL
 #define L2E_COMPRESSED_OFFSET_SIZE_MASK 0x3fffffffffffffffULL

-#define REFT_OFFSET_MASK 0xfffffffffffffe00ULL
+#define REFT_OFFSET_MASK 0xffffffffffffff00ULL

 static inline int64_t start_of_cluster(BDRVQcowState *s, int64_t offset)
 {
@@ -512,7 +508,7 @@ void qcow2_encrypt_sectors(BDRVQcowState *s, int64_t sector_num,
 int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
    int *num, uint64_t *cluster_offset);
 int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
-    int *num, uint64_t *host_offset, QCowL2Meta **m);
+    int n_start, int n_end, int *num, uint64_t *host_offset, QCowL2Meta **m);
 uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
                                         uint64_t offset,
                                         int compressed_size);
@@ -532,10 +528,7 @@ int qcow2_snapshot_delete(BlockDriverState *bs,
                          const char *name,
                          Error **errp);
 int qcow2_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab);
-int qcow2_snapshot_load_tmp(BlockDriverState *bs,
-                            const char *snapshot_id,
-                            const char *name,
-                            Error **errp);
+int qcow2_snapshot_load_tmp(BlockDriverState *bs, const char *snapshot_name);

 void qcow2_free_snapshots(BlockDriverState *bs);
 int qcow2_read_snapshots(BlockDriverState *bs);
@@ -391,15 +391,14 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
    qed_header_le_to_cpu(&le_header, &s->header);

    if (s->header.magic != QED_MAGIC) {
-        error_setg(errp, "Image not in QED format");
-        return -EINVAL;
+        return -EMEDIUMTYPE;
    }
    if (s->header.features & ~QED_FEATURE_MASK) {
        /* image uses unsupported feature bits */
        char buf[64];
        snprintf(buf, sizeof(buf), "%" PRIx64,
            s->header.features & ~QED_FEATURE_MASK);
-        error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+        qerror_report(QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
            bs->device_name, "QED", buf);
        return -ENOTSUP;
    }
@@ -507,15 +506,6 @@ out:
    return ret;
 }

-static int bdrv_qed_refresh_limits(BlockDriverState *bs)
-{
-    BDRVQEDState *s = bs->opaque;
-
-    bs->bl.write_zeroes_alignment = s->header.cluster_size >> BDRV_SECTOR_BITS;
-
-    return 0;
-}
-
 /* We have nothing to do for QED reopen, stubs just return
 * success */
 static int bdrv_qed_reopen_prepare(BDRVReopenState *state,
@@ -546,8 +536,7 @@ static void bdrv_qed_close(BlockDriverState *bs)

 static int qed_create(const char *filename, uint32_t cluster_size,
                      uint64_t image_size, uint32_t table_size,
-                      const char *backing_file, const char *backing_fmt,
-                      Error **errp)
+                      const char *backing_file, const char *backing_fmt)
 {
    QEDHeader header = {
        .magic = QED_MAGIC,
@@ -564,20 +553,20 @@ static int qed_create(const char *filename, uint32_t cluster_size,
    size_t l1_size = header.cluster_size * header.table_size;
    Error *local_err = NULL;
    int ret = 0;
-    BlockDriverState *bs;
+    BlockDriverState *bs = NULL;

    ret = bdrv_create_file(filename, NULL, &local_err);
    if (ret < 0) {
-        error_propagate(errp, local_err);
+        qerror_report_err(local_err);
+        error_free(local_err);
        return ret;
    }

-    bs = NULL;
-    ret = bdrv_open(&bs, filename, NULL, NULL,
-                    BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL, NULL,
-                    &local_err);
+    ret = bdrv_file_open(&bs, filename, NULL, BDRV_O_RDWR | BDRV_O_CACHE_WB,
+                         &local_err);
    if (ret < 0) {
-        error_propagate(errp, local_err);
+        qerror_report_err(local_err);
+        error_free(local_err);
        return ret;
    }

@@ -667,7 +656,7 @@ static int bdrv_qed_create(const char *filename, QEMUOptionParameter *options,
    }

    return qed_create(filename, cluster_size, image_size, table_size,
-                      backing_file, backing_fmt, errp);
+                      backing_file, backing_fmt);
 }

 typedef struct {
@@ -733,6 +722,11 @@ static int64_t coroutine_fn bdrv_qed_co_get_block_status(BlockDriverState *bs,
    return cb.status;
 }

+static int bdrv_qed_make_empty(BlockDriverState *bs)
+{
+    return -ENOTSUP;
+}
+
 static BDRVQEDState *acb_to_s(QEDAIOCB *acb)
 {
    return acb->common.bs->opaque;
@@ -1403,8 +1397,7 @@ static void coroutine_fn qed_co_write_zeroes_cb(void *opaque, int ret)

 static int coroutine_fn bdrv_qed_co_write_zeroes(BlockDriverState *bs,
                                                 int64_t sector_num,
-                                                 int nb_sectors,
-                                                 BdrvRequestFlags flags)
+                                                 int nb_sectors)
 {
    BlockDriverAIOCB *blockacb;
    BDRVQEDState *s = bs->opaque;
@@ -1481,8 +1474,6 @@ static int bdrv_qed_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
    memset(bdi, 0, sizeof(*bdi));
    bdi->cluster_size = s->header.cluster_size;
    bdi->is_dirty = s->header.features & QED_F_NEED_CHECK;
-    bdi->unallocated_blocks_are_zero = true;
-    bdi->can_write_zeroes_with_unmap = true;
    return 0;
 }

@@ -1558,31 +1549,13 @@ static int bdrv_qed_change_backing_file(BlockDriverState *bs,
    return ret;
 }

-static void bdrv_qed_invalidate_cache(BlockDriverState *bs, Error **errp)
+static void bdrv_qed_invalidate_cache(BlockDriverState *bs)
 {
    BDRVQEDState *s = bs->opaque;
-    Error *local_err = NULL;
-    int ret;

    bdrv_qed_close(bs);
-
-    bdrv_invalidate_cache(bs->file, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        return;
-    }
-
    memset(s, 0, sizeof(BDRVQEDState));
-    ret = bdrv_qed_open(bs, NULL, bs->open_flags, &local_err);
-    if (local_err) {
-        error_setg(errp, "Could not reopen qed layer: %s",
-                   error_get_pretty(local_err));
-        error_free(local_err);
-        return;
-    } else if (ret < 0) {
-        error_setg_errno(errp, -ret, "Could not reopen qed layer");
-        return;
-    }
+    bdrv_qed_open(bs, NULL, bs->open_flags, NULL);
 }

 static int bdrv_qed_check(BlockDriverState *bs, BdrvCheckResult *result,
@@ -1632,13 +1605,13 @@ static BlockDriver bdrv_qed = {
    .bdrv_create              = bdrv_qed_create,
    .bdrv_has_zero_init       = bdrv_has_zero_init_1,
    .bdrv_co_get_block_status = bdrv_qed_co_get_block_status,
+    .bdrv_make_empty          = bdrv_qed_make_empty,
    .bdrv_aio_readv           = bdrv_qed_aio_readv,
    .bdrv_aio_writev          = bdrv_qed_aio_writev,
    .bdrv_co_write_zeroes     = bdrv_qed_co_write_zeroes,
    .bdrv_truncate            = bdrv_qed_truncate,
    .bdrv_getlength           = bdrv_qed_getlength,
    .bdrv_get_info            = bdrv_qed_get_info,
-    .bdrv_refresh_limits      = bdrv_qed_refresh_limits,
    .bdrv_change_backing_file = bdrv_qed_change_backing_file,
    .bdrv_invalidate_cache    = bdrv_qed_invalidate_cache,
    .bdrv_check               = bdrv_qed_check,
@@ -1,877 +0,0 @@
-/*
- * Quorum Block filter
- *
- * Copyright (C) 2012-2014 Nodalink, EURL.
- *
- * Author:
- *   Benoît Canet <benoit.canet@irqsave.net>
- *
- * Based on the design and code of blkverify.c (Copyright (C) 2010 IBM, Corp)
- * and blkmirror.c (Copyright (C) 2011 Red Hat, Inc).
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-
-#include <gnutls/gnutls.h>
-#include <gnutls/crypto.h>
-#include "block/block_int.h"
-#include "qapi/qmp/qjson.h"
-
-#define HASH_LENGTH 32
-
-#define QUORUM_OPT_VOTE_THRESHOLD "vote-threshold"
-#define QUORUM_OPT_BLKVERIFY      "blkverify"
-
-/* This union holds a vote hash value */
-typedef union QuorumVoteValue {
-    char h[HASH_LENGTH];       /* SHA-256 hash */
-    int64_t l;                 /* simpler 64 bits hash */
-} QuorumVoteValue;
-
-/* A vote item */
-typedef struct QuorumVoteItem {
-    int index;
-    QLIST_ENTRY(QuorumVoteItem) next;
-} QuorumVoteItem;
-
-/* this structure is a vote version. A version is the set of votes sharing the
- * same vote value.
- * The set of votes will be tracked with the items field and its cardinality is
- * vote_count.
- */
-typedef struct QuorumVoteVersion {
-    QuorumVoteValue value;
-    int index;
-    int vote_count;
-    QLIST_HEAD(, QuorumVoteItem) items;
-    QLIST_ENTRY(QuorumVoteVersion) next;
-} QuorumVoteVersion;
-
-/* this structure holds a group of vote versions together */
-typedef struct QuorumVotes {
-    QLIST_HEAD(, QuorumVoteVersion) vote_list;
-    bool (*compare)(QuorumVoteValue *a, QuorumVoteValue *b);
-} QuorumVotes;
-
-/* the following structure holds the state of one quorum instance */
-typedef struct BDRVQuorumState {
-    BlockDriverState **bs; /* children BlockDriverStates */
-    int num_children;      /* children count */
-    int threshold;         /* if less than threshold children reads gave the
-                            * same result a quorum error occurs.
-                            */
-    bool is_blkverify;     /* true if the driver is in blkverify mode
-                            * Writes are mirrored on two children devices.
-                            * On reads the two children devices' contents are
-                            * compared and if a difference is spotted its
-                            * location is printed and the code aborts.
-                            * It is useful to debug other block drivers by
-                            * comparing them with a reference one.
-                            */
-} BDRVQuorumState;
-
-typedef struct QuorumAIOCB QuorumAIOCB;
-
-/* Quorum will create one instance of the following structure per operation it
- * performs on its children.
- * So for each read/write operation coming from the upper layer there will be
- * $children_count QuorumChildRequest.
- */
-typedef struct QuorumChildRequest {
-    BlockDriverAIOCB *aiocb;
-    QEMUIOVector qiov;
-    uint8_t *buf;
-    int ret;
-    QuorumAIOCB *parent;
-} QuorumChildRequest;
-
-/* Quorum will use the following structure to track progress of each read/write
- * operation received by the upper layer.
- * This structure hold pointers to the QuorumChildRequest structures instances
- * used to do operations on each children and track overall progress.
- */
-struct QuorumAIOCB {
-    BlockDriverAIOCB common;
-
-    /* Request metadata */
-    uint64_t sector_num;
-    int nb_sectors;
-
-    QEMUIOVector *qiov;         /* calling IOV */
-
-    QuorumChildRequest *qcrs;   /* individual child requests */
-    int count;                  /* number of completed AIOCB */
-    int success_count;          /* number of successfully completed AIOCB */
-
-    QuorumVotes votes;
-
-    bool is_read;
-    int vote_ret;
-};
-
-static void quorum_vote(QuorumAIOCB *acb);
-
-static void quorum_aio_cancel(BlockDriverAIOCB *blockacb)
-{
-    QuorumAIOCB *acb = container_of(blockacb, QuorumAIOCB, common);
-    BDRVQuorumState *s = acb->common.bs->opaque;
-    int i;
-
-    /* cancel all callbacks */
-    for (i = 0; i < s->num_children; i++) {
-        bdrv_aio_cancel(acb->qcrs[i].aiocb);
-    }
-
-    g_free(acb->qcrs);
-    qemu_aio_release(acb);
-}
-
-static AIOCBInfo quorum_aiocb_info = {
-    .aiocb_size         = sizeof(QuorumAIOCB),
-    .cancel             = quorum_aio_cancel,
-};
-
-static void quorum_aio_finalize(QuorumAIOCB *acb)
-{
-    BDRVQuorumState *s = acb->common.bs->opaque;
-    int i, ret = 0;
-
-    if (acb->vote_ret) {
-        ret = acb->vote_ret;
-    }
-
-    acb->common.cb(acb->common.opaque, ret);
-
-    if (acb->is_read) {
-        for (i = 0; i < s->num_children; i++) {
-            qemu_vfree(acb->qcrs[i].buf);
-            qemu_iovec_destroy(&acb->qcrs[i].qiov);
-        }
-    }
-
-    g_free(acb->qcrs);
-    qemu_aio_release(acb);
-}
-
-static bool quorum_sha256_compare(QuorumVoteValue *a, QuorumVoteValue *b)
-{
-    return !memcmp(a->h, b->h, HASH_LENGTH);
-}
-
-static bool quorum_64bits_compare(QuorumVoteValue *a, QuorumVoteValue *b)
-{
-    return a->l == b->l;
-}
-
-static QuorumAIOCB *quorum_aio_get(BDRVQuorumState *s,
-                                   BlockDriverState *bs,
-                                   QEMUIOVector *qiov,
-                                   uint64_t sector_num,
-                                   int nb_sectors,
-                                   BlockDriverCompletionFunc *cb,
-                                   void *opaque)
-{
-    QuorumAIOCB *acb = qemu_aio_get(&quorum_aiocb_info, bs, cb, opaque);
-    int i;
-
-    acb->common.bs->opaque = s;
-    acb->sector_num = sector_num;
-    acb->nb_sectors = nb_sectors;
-    acb->qiov = qiov;
-    acb->qcrs = g_new0(QuorumChildRequest, s->num_children);
-    acb->count = 0;
-    acb->success_count = 0;
-    acb->votes.compare = quorum_sha256_compare;
-    QLIST_INIT(&acb->votes.vote_list);
-    acb->is_read = false;
-    acb->vote_ret = 0;
-
-    for (i = 0; i < s->num_children; i++) {
-        acb->qcrs[i].buf = NULL;
-        acb->qcrs[i].ret = 0;
-        acb->qcrs[i].parent = acb;
-    }
-
-    return acb;
-}
-
-static void quorum_report_bad(QuorumAIOCB *acb, char *node_name, int ret)
-{
-    QObject *data;
-    assert(node_name);
-    data = qobject_from_jsonf("{ 'node-name': %s"
-                              ", 'sector-num': %" PRId64
-                              ", 'sectors-count': %d }",
-                              node_name, acb->sector_num, acb->nb_sectors);
-    if (ret < 0) {
-        QDict *dict = qobject_to_qdict(data);
-        qdict_put(dict, "error", qstring_from_str(strerror(-ret)));
-    }
-    monitor_protocol_event(QEVENT_QUORUM_REPORT_BAD, data);
-    qobject_decref(data);
-}
-
-static void quorum_report_failure(QuorumAIOCB *acb)
-{
-    QObject *data;
-    const char *reference = acb->common.bs->device_name[0] ?
-                            acb->common.bs->device_name :
-                            acb->common.bs->node_name;
-    data = qobject_from_jsonf("{ 'reference': %s"
-                              ", 'sector-num': %" PRId64
-                              ", 'sectors-count': %d }",
-                              reference, acb->sector_num, acb->nb_sectors);
-    monitor_protocol_event(QEVENT_QUORUM_FAILURE, data);
-    qobject_decref(data);
-}
-
-static int quorum_vote_error(QuorumAIOCB *acb);
-
-static bool quorum_has_too_much_io_failed(QuorumAIOCB *acb)
-{
-    BDRVQuorumState *s = acb->common.bs->opaque;
-
-    if (acb->success_count < s->threshold) {
-        acb->vote_ret = quorum_vote_error(acb);
-        quorum_report_failure(acb);
-        return true;
-    }
-
-    return false;
-}
-
-static void quorum_aio_cb(void *opaque, int ret)
-{
-    QuorumChildRequest *sacb = opaque;
-    QuorumAIOCB *acb = sacb->parent;
-    BDRVQuorumState *s = acb->common.bs->opaque;
-
-    sacb->ret = ret;
-    acb->count++;
-    if (ret == 0) {
-        acb->success_count++;
-    } else {
-        quorum_report_bad(acb, sacb->aiocb->bs->node_name, ret);
-    }
-    assert(acb->count <= s->num_children);
-    assert(acb->success_count <= s->num_children);
-    if (acb->count < s->num_children) {
-        return;
-    }
-
-    /* Do the vote on read */
-    if (acb->is_read) {
-        quorum_vote(acb);
-    } else {
-        quorum_has_too_much_io_failed(acb);
-    }
-
-    quorum_aio_finalize(acb);
-}
-
-static void quorum_report_bad_versions(BDRVQuorumState *s,
-                                       QuorumAIOCB *acb,
-                                       QuorumVoteValue *value)
-{
-    QuorumVoteVersion *version;
-    QuorumVoteItem *item;
-
-    QLIST_FOREACH(version, &acb->votes.vote_list, next) {
-        if (acb->votes.compare(&version->value, value)) {
-            continue;
-        }
-        QLIST_FOREACH(item, &version->items, next) {
-            quorum_report_bad(acb, s->bs[item->index]->node_name, 0);
-        }
-    }
-}
-
-static void quorum_copy_qiov(QEMUIOVector *dest, QEMUIOVector *source)
-{
-    int i;
-    assert(dest->niov == source->niov);
-    assert(dest->size == source->size);
-    for (i = 0; i < source->niov; i++) {
-        assert(dest->iov[i].iov_len == source->iov[i].iov_len);
-        memcpy(dest->iov[i].iov_base,
-               source->iov[i].iov_base,
-               source->iov[i].iov_len);
-    }
-}
-
-static void quorum_count_vote(QuorumVotes *votes,
-                              QuorumVoteValue *value,
-                              int index)
-{
-    QuorumVoteVersion *v = NULL, *version = NULL;
-    QuorumVoteItem *item;
-
-    /* look if we have something with this hash */
-    QLIST_FOREACH(v, &votes->vote_list, next) {
-        if (votes->compare(&v->value, value)) {
-            version = v;
-            break;
-        }
-    }
-
-    /* It's a version not yet in the list add it */
-    if (!version) {
-        version = g_new0(QuorumVoteVersion, 1);
-        QLIST_INIT(&version->items);
-        memcpy(&version->value, value, sizeof(version->value));
-        version->index = index;
-        version->vote_count = 0;
-        QLIST_INSERT_HEAD(&votes->vote_list, version, next);
-    }
-
-    version->vote_count++;
-
-    item = g_new0(QuorumVoteItem, 1);
-    item->index = index;
-    QLIST_INSERT_HEAD(&version->items, item, next);
-}
-
-static void quorum_free_vote_list(QuorumVotes *votes)
-{
-    QuorumVoteVersion *version, *next_version;
-    QuorumVoteItem *item, *next_item;
-
-    QLIST_FOREACH_SAFE(version, &votes->vote_list, next, next_version) {
-        QLIST_REMOVE(version, next);
-        QLIST_FOREACH_SAFE(item, &version->items, next, next_item) {
-            QLIST_REMOVE(item, next);
-            g_free(item);
-        }
-        g_free(version);
-    }
-}
-
-static int quorum_compute_hash(QuorumAIOCB *acb, int i, QuorumVoteValue *hash)
-{
-    int j, ret;
-    gnutls_hash_hd_t dig;
-    QEMUIOVector *qiov = &acb->qcrs[i].qiov;
-
-    ret = gnutls_hash_init(&dig, GNUTLS_DIG_SHA256);
-
-    if (ret < 0) {
-        return ret;
-    }
-
-    for (j = 0; j < qiov->niov; j++) {
-        ret = gnutls_hash(dig, qiov->iov[j].iov_base, qiov->iov[j].iov_len);
-        if (ret < 0) {
-            break;
-        }
-    }
-
-    gnutls_hash_deinit(dig, (void *) hash);
-    return ret;
-}
-
-static QuorumVoteVersion *quorum_get_vote_winner(QuorumVotes *votes)
-{
-    int max = 0;
-    QuorumVoteVersion *candidate, *winner = NULL;
-
-    QLIST_FOREACH(candidate, &votes->vote_list, next) {
-        if (candidate->vote_count > max) {
-            max = candidate->vote_count;
-            winner = candidate;
-        }
-    }
-
-    return winner;
-}
-
-/* qemu_iovec_compare is handy for blkverify mode because it returns the first
- * differing byte location. Yet it is handcoded to compare vectors one byte
- * after another so it does not benefit from the libc SIMD optimizations.
- * quorum_iovec_compare is written for speed and should be used in the non
- * blkverify mode of quorum.
- */
-static bool quorum_iovec_compare(QEMUIOVector *a, QEMUIOVector *b)
-{
-    int i;
-    int result;
-
-    assert(a->niov == b->niov);
-    for (i = 0; i < a->niov; i++) {
-        assert(a->iov[i].iov_len == b->iov[i].iov_len);
-        result = memcmp(a->iov[i].iov_base,
-                        b->iov[i].iov_base,
-                        a->iov[i].iov_len);
-        if (result) {
-            return false;
-        }
-    }
-
-    return true;
-}
-
-static void GCC_FMT_ATTR(2, 3) quorum_err(QuorumAIOCB *acb,
-                                          const char *fmt, ...)
-{
-    va_list ap;
-
-    va_start(ap, fmt);
-    fprintf(stderr, "quorum: sector_num=%" PRId64 " nb_sectors=%d ",
-            acb->sector_num, acb->nb_sectors);
-    vfprintf(stderr, fmt, ap);
-    fprintf(stderr, "\n");
-    va_end(ap);
-    exit(1);
-}
-
-static bool quorum_compare(QuorumAIOCB *acb,
-                           QEMUIOVector *a,
-                           QEMUIOVector *b)
-{
-    BDRVQuorumState *s = acb->common.bs->opaque;
-    ssize_t offset;
-
-    /* This driver will replace blkverify in this particular case */
-    if (s->is_blkverify) {
-        offset = qemu_iovec_compare(a, b);
-        if (offset != -1) {
-            quorum_err(acb, "contents mismatch in sector %" PRId64,
-                       acb->sector_num +
-                       (uint64_t)(offset / BDRV_SECTOR_SIZE));
-        }
-        return true;
-    }
-
-    return quorum_iovec_compare(a, b);
-}
-
-/* Do a vote to get the error code */
-static int quorum_vote_error(QuorumAIOCB *acb)
-{
-    BDRVQuorumState *s = acb->common.bs->opaque;
-    QuorumVoteVersion *winner = NULL;
-    QuorumVotes error_votes;
-    QuorumVoteValue result_value;
-    int i, ret = 0;
-    bool error = false;
-
-    QLIST_INIT(&error_votes.vote_list);
-    error_votes.compare = quorum_64bits_compare;
-
-    for (i = 0; i < s->num_children; i++) {
-        ret = acb->qcrs[i].ret;
-        if (ret) {
-            error = true;
-            result_value.l = ret;
-            quorum_count_vote(&error_votes, &result_value, i);
-        }
-    }
-
-    if (error) {
-        winner = quorum_get_vote_winner(&error_votes);
-        ret = winner->value.l;
-    }
-
-    quorum_free_vote_list(&error_votes);
-
-    return ret;
-}
-
-static void quorum_vote(QuorumAIOCB *acb)
-{
-    bool quorum = true;
-    int i, j, ret;
-    QuorumVoteValue hash;
-    BDRVQuorumState *s = acb->common.bs->opaque;
-    QuorumVoteVersion *winner;
-
-    if (quorum_has_too_much_io_failed(acb)) {
-        return;
-    }
-
-    /* get the index of the first successful read */
-    for (i = 0; i < s->num_children; i++) {
-        if (!acb->qcrs[i].ret) {
-            break;
-        }
-    }
-
-    assert(i < s->num_children);
-
-    /* compare this read with all other successful reads stopping at quorum
-     * failure
-     */
-    for (j = i + 1; j < s->num_children; j++) {
-        if (acb->qcrs[j].ret) {
-            continue;
-        }
-        quorum = quorum_compare(acb, &acb->qcrs[i].qiov, &acb->qcrs[j].qiov);
-        if (!quorum) {
-            break;
-       }
-    }
-
-    /* Every successful read agrees */
-    if (quorum) {
-        quorum_copy_qiov(acb->qiov, &acb->qcrs[i].qiov);
-        return;
-    }
-
-    /* compute hashes for each successful read, also store indexes */
-    for (i = 0; i < s->num_children; i++) {
-        if (acb->qcrs[i].ret) {
-            continue;
-        }
-        ret = quorum_compute_hash(acb, i, &hash);
-        /* if ever the hash computation failed */
-        if (ret < 0) {
-            acb->vote_ret = ret;
-            goto free_exit;
-        }
-        quorum_count_vote(&acb->votes, &hash, i);
-    }
-
-    /* vote to select the most represented version */
-    winner = quorum_get_vote_winner(&acb->votes);
-
-    /* if the winner count is smaller than threshold the read fails */
-    if (winner->vote_count < s->threshold) {
-        quorum_report_failure(acb);
-        acb->vote_ret = -EIO;
-        goto free_exit;
-    }
-
-    /* we have a winner: copy it */
-    quorum_copy_qiov(acb->qiov, &acb->qcrs[winner->index].qiov);
-
-    /* some versions are bad print them */
-    quorum_report_bad_versions(s, acb, &winner->value);
-
-free_exit:
-    /* free lists */
-    quorum_free_vote_list(&acb->votes);
-}
-
-static BlockDriverAIOCB *quorum_aio_readv(BlockDriverState *bs,
-                                         int64_t sector_num,
-                                         QEMUIOVector *qiov,
-                                         int nb_sectors,
-                                         BlockDriverCompletionFunc *cb,
-                                         void *opaque)
-{
-    BDRVQuorumState *s = bs->opaque;
-    QuorumAIOCB *acb = quorum_aio_get(s, bs, qiov, sector_num,
-                                      nb_sectors, cb, opaque);
-    int i;
-
-    acb->is_read = true;
-
-    for (i = 0; i < s->num_children; i++) {
-        acb->qcrs[i].buf = qemu_blockalign(s->bs[i], qiov->size);
-        qemu_iovec_init(&acb->qcrs[i].qiov, qiov->niov);
-        qemu_iovec_clone(&acb->qcrs[i].qiov, qiov, acb->qcrs[i].buf);
-    }
-
-    for (i = 0; i < s->num_children; i++) {
-        bdrv_aio_readv(s->bs[i], sector_num, &acb->qcrs[i].qiov, nb_sectors,
-                       quorum_aio_cb, &acb->qcrs[i]);
-    }
-
-    return &acb->common;
-}
-
-static BlockDriverAIOCB *quorum_aio_writev(BlockDriverState *bs,
-                                          int64_t sector_num,
-                                          QEMUIOVector *qiov,
-                                          int nb_sectors,
-                                          BlockDriverCompletionFunc *cb,
-                                          void *opaque)
-{
-    BDRVQuorumState *s = bs->opaque;
-    QuorumAIOCB *acb = quorum_aio_get(s, bs, qiov, sector_num, nb_sectors,
-                                      cb, opaque);
-    int i;
-
-    for (i = 0; i < s->num_children; i++) {
-        acb->qcrs[i].aiocb = bdrv_aio_writev(s->bs[i], sector_num, qiov,
-                                             nb_sectors, &quorum_aio_cb,
-                                             &acb->qcrs[i]);
-    }
-
-    return &acb->common;
-}
-
-static int64_t quorum_getlength(BlockDriverState *bs)
-{
-    BDRVQuorumState *s = bs->opaque;
-    int64_t result;
-    int i;
-
-    /* check that all file have the same length */
-    result = bdrv_getlength(s->bs[0]);
-    if (result < 0) {
-        return result;
-    }
-    for (i = 1; i < s->num_children; i++) {
-        int64_t value = bdrv_getlength(s->bs[i]);
-        if (value < 0) {
-            return value;
-        }
-        if (value != result) {
-            return -EIO;
-        }
-    }
-
-    return result;
-}
-
-static void quorum_invalidate_cache(BlockDriverState *bs, Error **errp)
-{
-    BDRVQuorumState *s = bs->opaque;
-    Error *local_err = NULL;
-    int i;
-
-    for (i = 0; i < s->num_children; i++) {
-        bdrv_invalidate_cache(s->bs[i], &local_err);
-        if (local_err) {
-            error_propagate(errp, local_err);
-            return;
-        }
-    }
-}
-
-static coroutine_fn int quorum_co_flush(BlockDriverState *bs)
-{
-    BDRVQuorumState *s = bs->opaque;
-    QuorumVoteVersion *winner = NULL;
-    QuorumVotes error_votes;
-    QuorumVoteValue result_value;
-    int i;
-    int result = 0;
-
-    QLIST_INIT(&error_votes.vote_list);
-    error_votes.compare = quorum_64bits_compare;
-
-    for (i = 0; i < s->num_children; i++) {
-        result = bdrv_co_flush(s->bs[i]);
-        result_value.l = result;
-        quorum_count_vote(&error_votes, &result_value, i);
-    }
-
-    winner = quorum_get_vote_winner(&error_votes);
-    result = winner->value.l;
-
-    quorum_free_vote_list(&error_votes);
-
-    return result;
-}
-
-static bool quorum_recurse_is_first_non_filter(BlockDriverState *bs,
-                                               BlockDriverState *candidate)
-{
-    BDRVQuorumState *s = bs->opaque;
-    int i;
-
-    for (i = 0; i < s->num_children; i++) {
-        bool perm = bdrv_recurse_is_first_non_filter(s->bs[i],
-                                                     candidate);
-        if (perm) {
-            return true;
-        }
-    }
-
-    return false;
-}
-
-static int quorum_valid_threshold(int threshold, int num_children, Error **errp)
-{
-
-    if (threshold < 1) {
-        error_set(errp, QERR_INVALID_PARAMETER_VALUE,
-                  "vote-threshold", "value >= 1");
-        return -ERANGE;
-    }
-
-    if (threshold > num_children) {
-        error_setg(errp, "threshold may not exceed children count");
-        return -ERANGE;
-    }
-
-    return 0;
-}
-
-static QemuOptsList quorum_runtime_opts = {
-    .name = "quorum",
-    .head = QTAILQ_HEAD_INITIALIZER(quorum_runtime_opts.head),
-    .desc = {
-        {
-            .name = QUORUM_OPT_VOTE_THRESHOLD,
-            .type = QEMU_OPT_NUMBER,
-            .help = "The number of vote needed for reaching quorum",
-        },
-        {
-            .name = QUORUM_OPT_BLKVERIFY,
-            .type = QEMU_OPT_BOOL,
-            .help = "Trigger block verify mode if set",
-        },
-        { /* end of list */ }
-    },
-};
-
-static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
-                       Error **errp)
-{
-    BDRVQuorumState *s = bs->opaque;
-    Error *local_err = NULL;
-    QemuOpts *opts;
-    bool *opened;
-    QDict *sub = NULL;
-    QList *list = NULL;
-    const QListEntry *lentry;
-    int i;
-    int ret = 0;
-
-    qdict_flatten(options);
-    qdict_extract_subqdict(options, &sub, "children.");
-    qdict_array_split(sub, &list);
-
-    if (qdict_size(sub)) {
-        error_setg(&local_err, "Invalid option children.%s",
-                   qdict_first(sub)->key);
-        ret = -EINVAL;
-        goto exit;
-    }
-
-    /* count how many different children are present */
-    s->num_children = qlist_size(list);
-    if (s->num_children < 2) {
-        error_setg(&local_err,
-                   "Number of provided children must be greater than 1");
-        ret = -EINVAL;
-        goto exit;
-    }
-
-    opts = qemu_opts_create(&quorum_runtime_opts, NULL, 0, &error_abort);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (error_is_set(&local_err)) {
-        ret = -EINVAL;
-        goto exit;
-    }
-
-    s->threshold = qemu_opt_get_number(opts, QUORUM_OPT_VOTE_THRESHOLD, 0);
-
-    /* and validate it against s->num_children */
-    ret = quorum_valid_threshold(s->threshold, s->num_children, &local_err);
-    if (ret < 0) {
-        goto exit;
-    }
-
-    /* is the driver in blkverify mode */
-    if (qemu_opt_get_bool(opts, QUORUM_OPT_BLKVERIFY, false) &&
-        s->num_children == 2 && s->threshold == 2) {
-        s->is_blkverify = true;
-    } else if (qemu_opt_get_bool(opts, QUORUM_OPT_BLKVERIFY, false)) {
-        fprintf(stderr, "blkverify mode is set by setting blkverify=on "
-                "and using two files with vote_threshold=2\n");
-    }
-
-    /* allocate the children BlockDriverState array */
-    s->bs = g_new0(BlockDriverState *, s->num_children);
-    opened = g_new0(bool, s->num_children);
-
-    for (i = 0, lentry = qlist_first(list); lentry;
-         lentry = qlist_next(lentry), i++) {
-        QDict *d;
-        QString *string;
-
-        switch (qobject_type(lentry->value))
-        {
-            /* List of options */
-            case QTYPE_QDICT:
-                d = qobject_to_qdict(lentry->value);
-                QINCREF(d);
-                ret = bdrv_open(&s->bs[i], NULL, NULL, d, flags, NULL,
-                                &local_err);
-                break;
-
-            /* QMP reference */
-            case QTYPE_QSTRING:
-                string = qobject_to_qstring(lentry->value);
-                ret = bdrv_open(&s->bs[i], NULL, qstring_get_str(string), NULL,
-                                flags, NULL, &local_err);
-                break;
-
-            default:
-                error_setg(&local_err, "Specification of child block device %i "
-                           "is invalid", i);
-                ret = -EINVAL;
-        }
-
-        if (ret < 0) {
-            goto close_exit;
-        }
-        opened[i] = true;
-    }
-
-    g_free(opened);
-    goto exit;
-
-close_exit:
-    /* cleanup on error */
-    for (i = 0; i < s->num_children; i++) {
-        if (!opened[i]) {
-            continue;
-        }
-        bdrv_unref(s->bs[i]);
-    }
-    g_free(s->bs);
-    g_free(opened);
-exit:
-    /* propagate error */
-    if (error_is_set(&local_err)) {
-        error_propagate(errp, local_err);
-    }
-    QDECREF(list);
-    QDECREF(sub);
-    return ret;
-}
-
-static void quorum_close(BlockDriverState *bs)
-{
-    BDRVQuorumState *s = bs->opaque;
-    int i;
-
-    for (i = 0; i < s->num_children; i++) {
-        bdrv_unref(s->bs[i]);
-    }
-
-    g_free(s->bs);
-}
-
-static BlockDriver bdrv_quorum = {
-    .format_name        = "quorum",
-    .protocol_name      = "quorum",
-
-    .instance_size      = sizeof(BDRVQuorumState),
-
-    .bdrv_file_open     = quorum_open,
-    .bdrv_close         = quorum_close,
-
-    .bdrv_co_flush_to_disk = quorum_co_flush,
-
-    .bdrv_getlength     = quorum_getlength,
-
-    .bdrv_aio_readv     = quorum_aio_readv,
-    .bdrv_aio_writev    = quorum_aio_writev,
-    .bdrv_invalidate_cache = quorum_invalidate_cache,
-
-    .is_filter           = true,
-    .bdrv_recurse_is_first_non_filter = quorum_recurse_is_first_non_filter,
-};
-
-static void bdrv_quorum_init(void)
-{
-    bdrv_register(&bdrv_quorum);
-}
-
-block_init(bdrv_quorum_init);
@@ -21,10 +21,9 @@
 #define QEMU_AIO_IOCTL        0x0004
 #define QEMU_AIO_FLUSH        0x0008
 #define QEMU_AIO_DISCARD      0x0010
-#define QEMU_AIO_WRITE_ZEROES 0x0020
 #define QEMU_AIO_TYPE_MASK \
        (QEMU_AIO_READ|QEMU_AIO_WRITE|QEMU_AIO_IOCTL|QEMU_AIO_FLUSH| \
-         QEMU_AIO_DISCARD|QEMU_AIO_WRITE_ZEROES)
+         QEMU_AIO_DISCARD)

 /* AIO flags */
 #define QEMU_AIO_MISALIGNED   0x1000
@@ -127,8 +127,6 @@ typedef struct BDRVRawState {
    int fd;
    int type;
    int open_flags;
-    size_t buf_align;
-
 #if defined(__linux__)
    /* linux floppy specific */
    int64_t fd_open_time;
@@ -141,11 +139,9 @@ typedef struct BDRVRawState {
    void *aio_ctx;
 #endif
 #ifdef CONFIG_XFS
-    bool is_xfs:1;
+    bool is_xfs : 1;
 #endif
-    bool has_discard:1;
-    bool has_write_zeroes:1;
-    bool discard_zeroes:1;
+    bool has_discard : 1;
 } BDRVRawState;

 typedef struct BDRVRawReopenState {
@@ -215,76 +211,6 @@ static int raw_normalize_devicepath(const char **filename)
 }
 #endif

-static void raw_probe_alignment(BlockDriverState *bs)
-{
-    BDRVRawState *s = bs->opaque;
-    char *buf;
-    unsigned int sector_size;
-
-    /* For /dev/sg devices the alignment is not really used.
-       With buffered I/O, we don't have any restrictions. */
-    if (bs->sg || !(s->open_flags & O_DIRECT)) {
-        bs->request_alignment = 1;
-        s->buf_align = 1;
-        return;
-    }
-
-    /* Try a few ioctls to get the right size */
-    bs->request_alignment = 0;
-    s->buf_align = 0;
-
-#ifdef BLKSSZGET
-    if (ioctl(s->fd, BLKSSZGET, &sector_size) >= 0) {
-        bs->request_alignment = sector_size;
-    }
-#endif
-#ifdef DKIOCGETBLOCKSIZE
-    if (ioctl(s->fd, DKIOCGETBLOCKSIZE, &sector_size) >= 0) {
-        bs->request_alignment = sector_size;
-    }
-#endif
-#ifdef DIOCGSECTORSIZE
-    if (ioctl(s->fd, DIOCGSECTORSIZE, &sector_size) >= 0) {
-        bs->request_alignment = sector_size;
-    }
-#endif
-#ifdef CONFIG_XFS
-    if (s->is_xfs) {
-        struct dioattr da;
-        if (xfsctl(NULL, s->fd, XFS_IOC_DIOINFO, &da) >= 0) {
-            bs->request_alignment = da.d_miniosz;
-            /* The kernel returns wrong information for d_mem */
-            /* s->buf_align = da.d_mem; */
-        }
-    }
-#endif
-
-    /* If we could not get the sizes so far, we can only guess them */
-    if (!s->buf_align) {
-        size_t align;
-        buf = qemu_memalign(MAX_BLOCKSIZE, 2 * MAX_BLOCKSIZE);
-        for (align = 512; align <= MAX_BLOCKSIZE; align <<= 1) {
-            if (pread(s->fd, buf + align, MAX_BLOCKSIZE, 0) >= 0) {
-                s->buf_align = align;
-                break;
-            }
-        }
-        qemu_vfree(buf);
-    }
-
-    if (!bs->request_alignment) {
-        size_t align;
-        buf = qemu_memalign(s->buf_align, MAX_BLOCKSIZE);
-        for (align = 512; align <= MAX_BLOCKSIZE; align <<= 1) {
-            if (pread(s->fd, buf, align, 0) >= 0) {
-                bs->request_alignment = align;
-                break;
-            }
-        }
-        qemu_vfree(buf);
-    }
-}
-
 static void raw_parse_flags(int bdrv_flags, int *open_flags)
 {
    assert(open_flags != NULL);
@@ -336,17 +262,6 @@ error:
 }
 #endif

-static void raw_parse_filename(const char *filename, QDict *options,
-                               Error **errp)
-{
-    /* The filename does not have to be prefixed by the protocol name, since
-     * "file" is the default protocol; therefore, the return value of this
-     * function call can be ignored. */
-    strstart(filename, "file:", &filename);
-
-    qdict_put_obj(options, "filename", QOBJECT(qstring_from_str(filename)));
-}
-
 static QemuOptsList raw_runtime_opts = {
    .name = "raw",
    .head = QTAILQ_HEAD_INITIALIZER(raw_runtime_opts.head),
@@ -368,11 +283,10 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
    Error *local_err = NULL;
    const char *filename;
    int fd, ret;
-    struct stat st;

-    opts = qemu_opts_create(&raw_runtime_opts, NULL, 0, &error_abort);
+    opts = qemu_opts_create_nofail(&raw_runtime_opts);
    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
        ret = -EINVAL;
        goto fail;
@@ -409,38 +323,10 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
    }
 #endif

-    s->has_discard = true;
-    s->has_write_zeroes = true;
-
-    if (fstat(s->fd, &st) < 0) {
-        error_setg_errno(errp, errno, "Could not stat file");
-        goto fail;
-    }
-    if (S_ISREG(st.st_mode)) {
-        s->discard_zeroes = true;
-    }
-    if (S_ISBLK(st.st_mode)) {
-#ifdef BLKDISCARDZEROES
-        unsigned int arg;
-        if (ioctl(s->fd, BLKDISCARDZEROES, &arg) == 0 && arg) {
-            s->discard_zeroes = true;
-        }
-#endif
-#ifdef __linux__
-        /* On Linux 3.10, BLKDISCARD leaves stale data in the page cache.  Do
-         * not rely on the contents of discarded blocks unless using O_DIRECT.
-         * Same for BLKZEROOUT.
-         */
-        if (!(bs->open_flags & BDRV_O_NOCACHE)) {
-            s->discard_zeroes = false;
-            s->has_write_zeroes = false;
-        }
-#endif
-    }
-
+    s->has_discard = 1;
 #ifdef CONFIG_XFS
    if (platform_test_xfs_fd(s->fd)) {
-        s->is_xfs = true;
+        s->is_xfs = 1;
    }
 #endif

@@ -459,7 +345,7 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,

    s->type = FTYPE_FILE;
    ret = raw_open_common(bs, options, flags, 0, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
    }
    return ret;
@@ -546,6 +432,7 @@ static int raw_reopen_prepare(BDRVReopenState *state,
    return ret;
 }

+
 static void raw_reopen_commit(BDRVReopenState *state)
 {
    BDRVRawReopenState *raw_s = state->opaque;
@@ -581,15 +468,23 @@ static void raw_reopen_abort(BDRVReopenState *state)
    state->opaque = NULL;
 }

-static int raw_refresh_limits(BlockDriverState *bs)
-{
-    BDRVRawState *s = bs->opaque;

-    raw_probe_alignment(bs);
-    bs->bl.opt_mem_alignment = s->buf_align;
-
-    return 0;
-}
+/* XXX: use host sector size if necessary with:
+#ifdef DIOCGSECTORSIZE
+        {
+            unsigned int sectorsize = 512;
+            if (!ioctl(fd, DIOCGSECTORSIZE, &sectorsize) &&
+                sectorsize > bufsize)
+                bufsize = sectorsize;
+        }
+#endif
+#ifdef CONFIG_COCOA
+        uint32_t blockSize = 512;
+        if ( !ioctl( fd, DKIOCGETBLOCKSIZE, &blockSize ) && blockSize > bufsize) {
+            bufsize = blockSize;
+        }
+#endif
+*/

 static ssize_t handle_aiocb_ioctl(RawPosixAIOData *aiocb)
 {
@@ -780,23 +675,6 @@ static ssize_t handle_aiocb_rw(RawPosixAIOData *aiocb)
 }

 #ifdef CONFIG_XFS
-static int xfs_write_zeroes(BDRVRawState *s, int64_t offset, uint64_t bytes)
-{
-    struct xfs_flock64 fl;
-
-    memset(&fl, 0, sizeof(fl));
-    fl.l_whence = SEEK_SET;
-    fl.l_start = offset;
-    fl.l_len = bytes;
-
-    if (xfsctl(NULL, s->fd, XFS_IOC_ZERO_RANGE, &fl) < 0) {
-        DEBUG_BLOCK_PRINT("cannot write zero range (%s)\n", strerror(errno));
-        return -errno;
-    }
-
-    return 0;
-}
-
 static int xfs_discard(BDRVRawState *s, int64_t offset, uint64_t bytes)
 {
    struct xfs_flock64 fl;
@@ -815,49 +693,13 @@ static int xfs_discard(BDRVRawState *s, int64_t offset, uint64_t bytes)
 }
 #endif

-static ssize_t handle_aiocb_write_zeroes(RawPosixAIOData *aiocb)
-{
-    int ret = -EOPNOTSUPP;
-    BDRVRawState *s = aiocb->bs->opaque;
-
-    if (s->has_write_zeroes == 0) {
-        return -ENOTSUP;
-    }
-
-    if (aiocb->aio_type & QEMU_AIO_BLKDEV) {
-#ifdef BLKZEROOUT
-        do {
-            uint64_t range[2] = { aiocb->aio_offset, aiocb->aio_nbytes };
-            if (ioctl(aiocb->aio_fildes, BLKZEROOUT, range) == 0) {
-                return 0;
-            }
-        } while (errno == EINTR);
-
-        ret = -errno;
-#endif
-    } else {
-#ifdef CONFIG_XFS
-        if (s->is_xfs) {
-            return xfs_write_zeroes(s, aiocb->aio_offset, aiocb->aio_nbytes);
-        }
-#endif
-    }
-
-    if (ret == -ENODEV || ret == -ENOSYS || ret == -EOPNOTSUPP ||
-        ret == -ENOTTY) {
-        s->has_write_zeroes = false;
-        ret = -ENOTSUP;
-    }
-    return ret;
-}
-
 static ssize_t handle_aiocb_discard(RawPosixAIOData *aiocb)
 {
    int ret = -EOPNOTSUPP;
    BDRVRawState *s = aiocb->bs->opaque;

-    if (!s->has_discard) {
-        return -ENOTSUP;
+    if (s->has_discard == 0) {
+        return 0;
    }

    if (aiocb->aio_type & QEMU_AIO_BLKDEV) {
@@ -892,8 +734,8 @@ static ssize_t handle_aiocb_discard(RawPosixAIOData *aiocb)

    if (ret == -ENODEV || ret == -ENOSYS || ret == -EOPNOTSUPP ||
        ret == -ENOTTY) {
-        s->has_discard = false;
-        ret = -ENOTSUP;
+        s->has_discard = 0;
+        ret = 0;
    }
    return ret;
 }
@@ -935,9 +777,6 @@ static int aio_worker(void *arg)
    case QEMU_AIO_DISCARD:
        ret = handle_aiocb_discard(aiocb);
        break;
-    case QEMU_AIO_WRITE_ZEROES:
-        ret = handle_aiocb_write_zeroes(aiocb);
-        break;
    default:
        fprintf(stderr, "invalid aio request (0x%x)\n", aiocb->aio_type);
        ret = -EINVAL;
@@ -948,29 +787,6 @@ static int aio_worker(void *arg)
    return ret;
 }

-static int paio_submit_co(BlockDriverState *bs, int fd,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        int type)
-{
-    RawPosixAIOData *acb = g_slice_new(RawPosixAIOData);
-    ThreadPool *pool;
-
-    acb->bs = bs;
-    acb->aio_type = type;
-    acb->aio_fildes = fd;
-
-    if (qiov) {
-        acb->aio_iov = qiov->iov;
-        acb->aio_niov = qiov->niov;
-    }
-    acb->aio_nbytes = nb_sectors * 512;
-    acb->aio_offset = sector_num * 512;
-
-    trace_paio_submit_co(sector_num, nb_sectors, type);
-    pool = aio_get_thread_pool(bdrv_get_aio_context(bs));
-    return thread_pool_submit_co(pool, aio_worker, acb);
-}
-
 static BlockDriverAIOCB *paio_submit(BlockDriverState *bs, int fd,
        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
        BlockDriverCompletionFunc *cb, void *opaque, int type)
@@ -1241,8 +1057,6 @@ static int raw_create(const char *filename, QEMUOptionParameter *options,
    int result = 0;
    int64_t total_size = 0;

-    strstart(filename, "file:", &filename);
-
    /* Read out options */
    while (options && options->name) {
        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
@@ -1385,31 +1199,6 @@ static coroutine_fn BlockDriverAIOCB *raw_aio_discard(BlockDriverState *bs,
                       cb, opaque, QEMU_AIO_DISCARD);
 }

-static int coroutine_fn raw_co_write_zeroes(
-    BlockDriverState *bs, int64_t sector_num,
-    int nb_sectors, BdrvRequestFlags flags)
-{
-    BDRVRawState *s = bs->opaque;
-
-    if (!(flags & BDRV_REQ_MAY_UNMAP)) {
-        return paio_submit_co(bs, s->fd, sector_num, NULL, nb_sectors,
-                              QEMU_AIO_WRITE_ZEROES);
-    } else if (s->discard_zeroes) {
-        return paio_submit_co(bs, s->fd, sector_num, NULL, nb_sectors,
-                              QEMU_AIO_DISCARD);
-    }
-    return -ENOTSUP;
-}
-
-static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
-{
-    BDRVRawState *s = bs->opaque;
-
-    bdi->unallocated_blocks_are_zero = s->discard_zeroes;
-    bdi->can_write_zeroes_with_unmap = s->discard_zeroes;
-    return 0;
-}
-
 static QEMUOptionParameter raw_create_options[] = {
    {
        .name = BLOCK_OPT_SIZE,
@@ -1425,7 +1214,6 @@ static BlockDriver bdrv_file = {
    .instance_size = sizeof(BDRVRawState),
    .bdrv_needs_filename = true,
    .bdrv_probe = NULL, /* no probe for protocols */
-    .bdrv_parse_filename = raw_parse_filename,
    .bdrv_file_open = raw_open,
    .bdrv_reopen_prepare = raw_reopen_prepare,
    .bdrv_reopen_commit = raw_reopen_commit,
@@ -1434,17 +1222,14 @@ static BlockDriver bdrv_file = {
    .bdrv_create = raw_create,
    .bdrv_has_zero_init = bdrv_has_zero_init_1,
    .bdrv_co_get_block_status = raw_co_get_block_status,
-    .bdrv_co_write_zeroes = raw_co_write_zeroes,

    .bdrv_aio_readv = raw_aio_readv,
    .bdrv_aio_writev = raw_aio_writev,
    .bdrv_aio_flush = raw_aio_flush,
    .bdrv_aio_discard = raw_aio_discard,
-    .bdrv_refresh_limits = raw_refresh_limits,

    .bdrv_truncate = raw_truncate,
    .bdrv_getlength = raw_getlength,
-    .bdrv_get_info = raw_get_info,
    .bdrv_get_allocated_file_size
                        = raw_get_allocated_file_size,

@@ -1561,15 +1346,6 @@ static int check_hdev_writable(BDRVRawState *s)
    return 0;
 }

-static void hdev_parse_filename(const char *filename, QDict *options,
-                                Error **errp)
-{
-    /* The prefix is optional, just as for "file". */
-    strstart(filename, "host_device:", &filename);
-
-    qdict_put_obj(options, "filename", QOBJECT(qstring_from_str(filename)));
-}
-
 static int hdev_open(BlockDriverState *bs, QDict *options, int flags,
                     Error **errp)
 {
@@ -1620,7 +1396,7 @@ static int hdev_open(BlockDriverState *bs, QDict *options, int flags,

    ret = raw_open_common(bs, options, flags, 0, &local_err);
    if (ret < 0) {
-        if (local_err) {
+        if (error_is_set(&local_err)) {
            error_propagate(errp, local_err);
        }
        return ret;
@@ -1749,26 +1525,6 @@ static coroutine_fn BlockDriverAIOCB *hdev_aio_discard(BlockDriverState *bs,
                       cb, opaque, QEMU_AIO_DISCARD|QEMU_AIO_BLKDEV);
 }

-static coroutine_fn int hdev_co_write_zeroes(BlockDriverState *bs,
-    int64_t sector_num, int nb_sectors, BdrvRequestFlags flags)
-{
-    BDRVRawState *s = bs->opaque;
-    int rc;
-
-    rc = fd_open(bs);
-    if (rc < 0) {
-        return rc;
-    }
-    if (!(flags & BDRV_REQ_MAY_UNMAP)) {
-        return paio_submit_co(bs, s->fd, sector_num, NULL, nb_sectors,
-                              QEMU_AIO_WRITE_ZEROES|QEMU_AIO_BLKDEV);
-    } else if (s->discard_zeroes) {
-        return paio_submit_co(bs, s->fd, sector_num, NULL, nb_sectors,
-                              QEMU_AIO_DISCARD|QEMU_AIO_BLKDEV);
-    }
-    return -ENOTSUP;
-}
-
 static int hdev_create(const char *filename, QEMUOptionParameter *options,
                       Error **errp)
 {
@@ -1776,18 +1532,6 @@ static int hdev_create(const char *filename, QEMUOptionParameter *options,
    int ret = 0;
    struct stat stat_buf;
    int64_t total_size = 0;
-    bool has_prefix;
-
-    /* This function is used by all three protocol block drivers and therefore
-     * any of these three prefixes may be given.
-     * The return value has to be stored somewhere, otherwise this is an error
-     * due to -Werror=unused-value. */
-    has_prefix =
-        strstart(filename, "host_device:", &filename) ||
-        strstart(filename, "host_cdrom:" , &filename) ||
-        strstart(filename, "host_floppy:", &filename);
-
-    (void)has_prefix;

    /* Read out options */
    while (options && options->name) {
@@ -1826,7 +1570,6 @@ static BlockDriver bdrv_host_device = {
    .instance_size      = sizeof(BDRVRawState),
    .bdrv_needs_filename = true,
    .bdrv_probe_device  = hdev_probe_device,
-    .bdrv_parse_filename = hdev_parse_filename,
    .bdrv_file_open     = hdev_open,
    .bdrv_close         = raw_close,
    .bdrv_reopen_prepare = raw_reopen_prepare,
@@ -1834,17 +1577,14 @@ static BlockDriver bdrv_host_device = {
    .bdrv_reopen_abort   = raw_reopen_abort,
    .bdrv_create        = hdev_create,
    .create_options     = raw_create_options,
-    .bdrv_co_write_zeroes = hdev_co_write_zeroes,

    .bdrv_aio_readv	= raw_aio_readv,
    .bdrv_aio_writev	= raw_aio_writev,
    .bdrv_aio_flush	= raw_aio_flush,
    .bdrv_aio_discard   = hdev_aio_discard,
-    .bdrv_refresh_limits = raw_refresh_limits,

    .bdrv_truncate      = raw_truncate,
    .bdrv_getlength	= raw_getlength,
-    .bdrv_get_info = raw_get_info,
    .bdrv_get_allocated_file_size
                        = raw_get_allocated_file_size,

@@ -1856,15 +1596,6 @@ static BlockDriver bdrv_host_device = {
 };

 #ifdef __linux__
-static void floppy_parse_filename(const char *filename, QDict *options,
-                                  Error **errp)
-{
-    /* The prefix is optional, just as for "file". */
-    strstart(filename, "host_floppy:", &filename);
-
-    qdict_put_obj(options, "filename", QOBJECT(qstring_from_str(filename)));
-}
-
 static int floppy_open(BlockDriverState *bs, QDict *options, int flags,
                       Error **errp)
 {
@@ -1877,7 +1608,7 @@ static int floppy_open(BlockDriverState *bs, QDict *options, int flags,
    /* open will not fail even if no floppy is inserted, so add O_NONBLOCK */
    ret = raw_open_common(bs, options, flags, O_NONBLOCK, &local_err);
    if (ret) {
-        if (local_err) {
+        if (error_is_set(&local_err)) {
            error_propagate(errp, local_err);
        }
        return ret;
@@ -1970,7 +1701,6 @@ static BlockDriver bdrv_host_floppy = {
    .instance_size      = sizeof(BDRVRawState),
    .bdrv_needs_filename = true,
    .bdrv_probe_device	= floppy_probe_device,
-    .bdrv_parse_filename = floppy_parse_filename,
    .bdrv_file_open     = floppy_open,
    .bdrv_close         = raw_close,
    .bdrv_reopen_prepare = raw_reopen_prepare,
@@ -1982,7 +1712,6 @@ static BlockDriver bdrv_host_floppy = {
    .bdrv_aio_readv     = raw_aio_readv,
    .bdrv_aio_writev    = raw_aio_writev,
    .bdrv_aio_flush	= raw_aio_flush,
-    .bdrv_refresh_limits = raw_refresh_limits,

    .bdrv_truncate      = raw_truncate,
    .bdrv_getlength      = raw_getlength,
@@ -1995,20 +1724,7 @@ static BlockDriver bdrv_host_floppy = {
    .bdrv_media_changed = floppy_media_changed,
    .bdrv_eject         = floppy_eject,
 };
-#endif

-#if defined(__linux__) || defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
-static void cdrom_parse_filename(const char *filename, QDict *options,
-                                 Error **errp)
-{
-    /* The prefix is optional, just as for "file". */
-    strstart(filename, "host_cdrom:", &filename);
-
-    qdict_put_obj(options, "filename", QOBJECT(qstring_from_str(filename)));
-}
-#endif
-
-#ifdef __linux__
 static int cdrom_open(BlockDriverState *bs, QDict *options, int flags,
                      Error **errp)
 {
@@ -2020,7 +1736,7 @@ static int cdrom_open(BlockDriverState *bs, QDict *options, int flags,

    /* open will not fail even if no CD is inserted, so add O_NONBLOCK */
    ret = raw_open_common(bs, options, flags, O_NONBLOCK, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
    }
    return ret;
@@ -2095,7 +1811,6 @@ static BlockDriver bdrv_host_cdrom = {
    .instance_size      = sizeof(BDRVRawState),
    .bdrv_needs_filename = true,
    .bdrv_probe_device	= cdrom_probe_device,
-    .bdrv_parse_filename = cdrom_parse_filename,
    .bdrv_file_open     = cdrom_open,
    .bdrv_close         = raw_close,
    .bdrv_reopen_prepare = raw_reopen_prepare,
@@ -2107,7 +1822,6 @@ static BlockDriver bdrv_host_cdrom = {
    .bdrv_aio_readv     = raw_aio_readv,
    .bdrv_aio_writev    = raw_aio_writev,
    .bdrv_aio_flush	= raw_aio_flush,
-    .bdrv_refresh_limits = raw_refresh_limits,

    .bdrv_truncate      = raw_truncate,
    .bdrv_getlength      = raw_getlength,
@@ -2138,7 +1852,7 @@ static int cdrom_open(BlockDriverState *bs, QDict *options, int flags,

    ret = raw_open_common(bs, options, flags, 0, &local_err);
    if (ret) {
-        if (local_err) {
+        if (error_is_set(&local_err)) {
            error_propagate(errp, local_err);
        }
        return ret;
@@ -2226,7 +1940,6 @@ static BlockDriver bdrv_host_cdrom = {
    .instance_size      = sizeof(BDRVRawState),
    .bdrv_needs_filename = true,
    .bdrv_probe_device	= cdrom_probe_device,
-    .bdrv_parse_filename = cdrom_parse_filename,
    .bdrv_file_open     = cdrom_open,
    .bdrv_close         = raw_close,
    .bdrv_reopen_prepare = raw_reopen_prepare,
@@ -2238,7 +1951,6 @@ static BlockDriver bdrv_host_cdrom = {
    .bdrv_aio_readv     = raw_aio_readv,
    .bdrv_aio_writev    = raw_aio_writev,
    .bdrv_aio_flush	= raw_aio_flush,
-    .bdrv_refresh_limits = raw_refresh_limits,

    .bdrv_truncate      = raw_truncate,
    .bdrv_getlength      = raw_getlength,
@@ -202,35 +202,6 @@ static int set_sparse(int fd)
 				 NULL, 0, NULL, 0, &returned, NULL);
 }

-static void raw_probe_alignment(BlockDriverState *bs)
-{
-    BDRVRawState *s = bs->opaque;
-    DWORD sectorsPerCluster, freeClusters, totalClusters, count;
-    DISK_GEOMETRY_EX dg;
-    BOOL status;
-
-    if (s->type == FTYPE_CD) {
-        bs->request_alignment = 2048;
-        return;
-    }
-    if (s->type == FTYPE_HARDDISK) {
-        status = DeviceIoControl(s->hfile, IOCTL_DISK_GET_DRIVE_GEOMETRY_EX,
-                                 NULL, 0, &dg, sizeof(dg), &count, NULL);
-        if (status != 0) {
-            bs->request_alignment = dg.Geometry.BytesPerSector;
-            return;
-        }
-        /* try GetDiskFreeSpace too */
-    }
-
-    if (s->drive_path[0]) {
-        GetDiskFreeSpace(s->drive_path, &sectorsPerCluster,
-                         &dg.Geometry.BytesPerSector,
-                         &freeClusters, &totalClusters);
-        bs->request_alignment = dg.Geometry.BytesPerSector;
-    }
-}
-
 static void raw_parse_flags(int flags, int *access_flags, DWORD *overlapped)
 {
    assert(access_flags != NULL);
@@ -251,17 +222,6 @@ static void raw_parse_flags(int flags, int *access_flags, DWORD *overlapped)
    }
 }

-static void raw_parse_filename(const char *filename, QDict *options,
-                               Error **errp)
-{
-    /* The filename does not have to be prefixed by the protocol name, since
-     * "file" is the default protocol; therefore, the return value of this
-     * function call can be ignored. */
-    strstart(filename, "file:", &filename);
-
-    qdict_put_obj(options, "filename", QOBJECT(qstring_from_str(filename)));
-}
-
 static QemuOptsList raw_runtime_opts = {
    .name = "raw",
    .head = QTAILQ_HEAD_INITIALIZER(raw_runtime_opts.head),
@@ -288,9 +248,9 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,

    s->type = FTYPE_FILE;

-    opts = qemu_opts_create(&raw_runtime_opts, NULL, 0, &error_abort);
+    opts = qemu_opts_create_nofail(&raw_runtime_opts);
    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
        ret = -EINVAL;
        goto fail;
@@ -309,17 +269,6 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
        }
    }

-    if (filename[0] && filename[1] == ':') {
-        snprintf(s->drive_path, sizeof(s->drive_path), "%c:\\", filename[0]);
-    } else if (filename[0] == '\\' && filename[1] == '\\') {
-        s->drive_path[0] = 0;
-    } else {
-        /* Relative path.  */
-        char buf[MAX_PATH];
-        GetCurrentDirectory(MAX_PATH, buf);
-        snprintf(s->drive_path, sizeof(s->drive_path), "%c:\\", buf[0]);
-    }
-
    s->hfile = CreateFile(filename, access_flags,
                          FILE_SHARE_READ, NULL,
                          OPEN_EXISTING, overlapped, NULL);
@@ -344,7 +293,6 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
        s->aio = aio;
    }

-    raw_probe_alignment(bs);
    ret = 0;
 fail:
    qemu_opts_del(opts);
@@ -481,8 +429,6 @@ static int raw_create(const char *filename, QEMUOptionParameter *options,
    int fd;
    int64_t total_size = 0;

-    strstart(filename, "file:", &filename);
-
    /* Read out options */
    while (options && options->name) {
        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
@@ -517,7 +463,6 @@ static BlockDriver bdrv_file = {
    .protocol_name	= "file",
    .instance_size	= sizeof(BDRVRawState),
    .bdrv_needs_filename = true,
-    .bdrv_parse_filename = raw_parse_filename,
    .bdrv_file_open	= raw_open,
    .bdrv_close		= raw_close,
    .bdrv_create	= raw_create,
@@ -593,15 +538,6 @@ static int hdev_probe_device(const char *filename)
    return 0;
 }

-static void hdev_parse_filename(const char *filename, QDict *options,
-                                Error **errp)
-{
-    /* The prefix is optional, just as for "file". */
-    strstart(filename, "host_device:", &filename);
-
-    qdict_put_obj(options, "filename", QOBJECT(qstring_from_str(filename)));
-}
-
 static int hdev_open(BlockDriverState *bs, QDict *options, int flags,
                     Error **errp)
 {
@@ -614,10 +550,9 @@ static int hdev_open(BlockDriverState *bs, QDict *options, int flags,
    Error *local_err = NULL;
    const char *filename;

-    QemuOpts *opts = qemu_opts_create(&raw_runtime_opts, NULL, 0,
-                                      &error_abort);
+    QemuOpts *opts = qemu_opts_create_nofail(&raw_runtime_opts);
    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
        ret = -EINVAL;
        goto done;
@@ -672,7 +607,6 @@ static BlockDriver bdrv_host_device = {
    .protocol_name	= "host_device",
    .instance_size	= sizeof(BDRVRawState),
    .bdrv_needs_filename = true,
-    .bdrv_parse_filename = hdev_parse_filename,
    .bdrv_probe_device	= hdev_probe_device,
    .bdrv_file_open	= hdev_open,
    .bdrv_close		= raw_close,
@@ -68,10 +68,9 @@ static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs,
 }

 static int coroutine_fn raw_co_write_zeroes(BlockDriverState *bs,
-                                            int64_t sector_num, int nb_sectors,
-                                            BdrvRequestFlags flags)
+                                            int64_t sector_num, int nb_sectors)
 {
-    return bdrv_co_write_zeroes(bs->file, sector_num, nb_sectors, flags);
+    return bdrv_co_write_zeroes(bs->file, sector_num, nb_sectors);
 }

 static int coroutine_fn raw_co_discard(BlockDriverState *bs,
@@ -90,12 +89,6 @@ static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
    return bdrv_get_info(bs->file, bdi);
 }

-static int raw_refresh_limits(BlockDriverState *bs)
-{
-    bs->bl = bs->file->bl;
-    return 0;
-}
-
 static int raw_truncate(BlockDriverState *bs, int64_t offset)
 {
    return bdrv_truncate(bs->file, offset);
@@ -146,7 +139,7 @@ static int raw_create(const char *filename, QEMUOptionParameter *options,
    int ret;

    ret = bdrv_create_file(filename, options, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
    }
    return ret;
@@ -187,7 +180,6 @@ static BlockDriver bdrv_raw = {
    .bdrv_getlength       = &raw_getlength,
    .has_variable_length  = true,
    .bdrv_get_info        = &raw_get_info,
-    .bdrv_refresh_limits  = &raw_refresh_limits,
    .bdrv_is_inserted     = &raw_is_inserted,
    .bdrv_media_changed   = &raw_media_changed,
    .bdrv_eject           = &raw_eject,
@@ -95,13 +95,18 @@ typedef struct RADOSCB {
 #define RBD_FD_WRITE 1

 typedef struct BDRVRBDState {
+    int fds[2];
    rados_t cluster;
    rados_ioctx_t io_ctx;
    rbd_image_t image;
    char name[RBD_MAX_IMAGE_NAME_SIZE];
    char *snap;
+    int event_reader_pos;
+    RADOSCB *event_rcb;
 } BDRVRBDState;

+static void rbd_aio_bh_cb(void *opaque);
+
 static int qemu_rbd_next_tok(char *dst, int dst_len,
                             char *src, char delim,
                             const char *name,
@@ -364,8 +369,9 @@ static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options,
 }

 /*
- * This aio completion is being called from rbd_finish_bh() and runs in qemu
- * BH context.
+ * This aio completion is being called from qemu_rbd_aio_event_reader()
+ * and runs in qemu context. It schedules a bh, but just in case the aio
+ * was not cancelled before.
 */
 static void qemu_rbd_complete_aio(RADOSCB *rcb)
 {
@@ -395,19 +401,36 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
            acb->ret = r;
        }
    }
-
+    /* Note that acb->bh can be NULL in case where the aio was cancelled */
+    acb->bh = qemu_bh_new(rbd_aio_bh_cb, acb);
+    qemu_bh_schedule(acb->bh);
    g_free(rcb);
+}

-    if (acb->cmd == RBD_AIO_READ) {
-        qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size);
-    }
-    qemu_vfree(acb->bounce);
-    acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
-    acb->status = 0;
+/*
+ * aio fd read handler. It runs in the qemu context and calls the
+ * completion handling of completed rados aio operations.
+ */
+static void qemu_rbd_aio_event_reader(void *opaque)
+{
+    BDRVRBDState *s = opaque;

-    if (!acb->cancelled) {
-        qemu_aio_release(acb);
-    }
+    ssize_t ret;
+
+    do {
+        char *p = (char *)&s->event_rcb;
+
+        /* now read the rcb pointer that was sent from a non qemu thread */
+        ret = read(s->fds[RBD_FD_READ], p + s->event_reader_pos,
+                   sizeof(s->event_rcb) - s->event_reader_pos);
+        if (ret > 0) {
+            s->event_reader_pos += ret;
+            if (s->event_reader_pos == sizeof(s->event_rcb)) {
+                s->event_reader_pos = 0;
+                qemu_rbd_complete_aio(s->event_rcb);
+            }
+        }
+    } while (ret < 0 && errno == EINTR);
 }

 /* TODO Convert to fine grained options */
@@ -438,9 +461,9 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
    const char *filename;
    int r;

-    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
+    opts = qemu_opts_create_nofail(&runtime_opts);
    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        qerror_report_err(local_err);
        error_free(local_err);
        qemu_opts_del(opts);
@@ -515,9 +538,23 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,

    bs->read_only = (s->snap != NULL);

+    s->event_reader_pos = 0;
+    r = qemu_pipe(s->fds);
+    if (r < 0) {
+        error_report("error opening eventfd");
+        goto failed;
+    }
+    fcntl(s->fds[0], F_SETFL, O_NONBLOCK);
+    fcntl(s->fds[1], F_SETFL, O_NONBLOCK);
+    qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], qemu_rbd_aio_event_reader,
+                            NULL, s);
+
+
    qemu_opts_del(opts);
    return 0;

+failed:
+    rbd_close(s->image);
 failed_open:
    rados_ioctx_destroy(s->io_ctx);
 failed_shutdown:
@@ -532,6 +569,10 @@ static void qemu_rbd_close(BlockDriverState *bs)
 {
    BDRVRBDState *s = bs->opaque;

+    close(s->fds[0]);
+    close(s->fds[1]);
+    qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], NULL, NULL, NULL);
+
    rbd_close(s->image);
    rados_ioctx_destroy(s->io_ctx);
    g_free(s->snap);
@@ -559,11 +600,34 @@ static const AIOCBInfo rbd_aiocb_info = {
    .cancel = qemu_rbd_aio_cancel,
 };

-static void rbd_finish_bh(void *opaque)
+static int qemu_rbd_send_pipe(BDRVRBDState *s, RADOSCB *rcb)
 {
-    RADOSCB *rcb = opaque;
-    qemu_bh_delete(rcb->acb->bh);
-    qemu_rbd_complete_aio(rcb);
+    int ret = 0;
+    while (1) {
+        fd_set wfd;
+        int fd = s->fds[RBD_FD_WRITE];
+
+        /* send the op pointer to the qemu thread that is responsible
+           for the aio/op completion. Must do it in a qemu thread context */
+        ret = write(fd, (void *)&rcb, sizeof(rcb));
+        if (ret >= 0) {
+            break;
+        }
+        if (errno == EINTR) {
+            continue;
+        }
+        if (errno != EAGAIN) {
+            break;
+        }
+
+        FD_ZERO(&wfd);
+        FD_SET(fd, &wfd);
+        do {
+            ret = select(fd + 1, NULL, &wfd, NULL, NULL);
+        } while (ret < 0 && errno == EINTR);
+    }
+
+    return ret;
 }

 /*
@@ -571,18 +635,40 @@ static void rbd_finish_bh(void *opaque)
 *
 * Note: this function is being called from a non qemu thread so
 * we need to be careful about what we do here. Generally we only
- * schedule a BH, and do the rest of the io completion handling
- * from rbd_finish_bh() which runs in a qemu context.
+ * write to the block notification pipe, and do the rest of the
+ * io completion handling from qemu_rbd_aio_event_reader() which
+ * runs in a qemu context.
 */
 static void rbd_finish_aiocb(rbd_completion_t c, RADOSCB *rcb)
 {
-    RBDAIOCB *acb = rcb->acb;
-
+    int ret;
    rcb->ret = rbd_aio_get_return_value(c);
    rbd_aio_release(c);
+    ret = qemu_rbd_send_pipe(rcb->s, rcb);
+    if (ret < 0) {
+        error_report("failed writing to acb->s->fds");
+        g_free(rcb);
+    }
+}

-    acb->bh = qemu_bh_new(rbd_finish_bh, rcb);
-    qemu_bh_schedule(acb->bh);
+/* Callback when all queued rbd_aio requests are complete */
+
+static void rbd_aio_bh_cb(void *opaque)
+{
+    RBDAIOCB *acb = opaque;
+
+    if (acb->cmd == RBD_AIO_READ) {
+        qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size);
+    }
+    qemu_vfree(acb->bounce);
+    acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
+    qemu_bh_delete(acb->bh);
+    acb->bh = NULL;
+    acb->status = 0;
+
+    if (!acb->cancelled) {
+        qemu_aio_release(acb);
+    }
 }

 static int rbd_aio_discard_wrapper(rbd_image_t image,
@@ -91,14 +91,6 @@
 #define SD_NR_VDIS   (1U << 24)
 #define SD_DATA_OBJ_SIZE (UINT64_C(1) << 22)
 #define SD_MAX_VDI_SIZE (SD_DATA_OBJ_SIZE * MAX_DATA_OBJS)
-/*
- * For erasure coding, we use at most SD_EC_MAX_STRIP for data strips and
- * (SD_EC_MAX_STRIP - 1) for parity strips
- *
- * SD_MAX_COPIES is sum of number of data strips and parity strips.
- */
-#define SD_EC_MAX_STRIP 16
-#define SD_MAX_COPIES (SD_EC_MAX_STRIP * 2 - 1)

 #define SD_INODE_SIZE (sizeof(SheepdogInode))
 #define CURRENT_VDI_ID 0
@@ -161,7 +153,7 @@ typedef struct SheepdogVdiReq {
    uint32_t id;
    uint32_t data_length;
    uint64_t vdi_size;
-    uint32_t base_vdi_id;
+    uint32_t vdi_id;
    uint8_t copies;
    uint8_t copy_policy;
    uint8_t reserved[2];
@@ -909,9 +901,9 @@ static void co_write_request(void *opaque)
 }

 /*
- * Return a socket descriptor to read/write objects.
+ * Return a socket discriptor to read/write objects.
 *
- * We cannot use this descriptor for other operations because
+ * We cannot use this discriptor for other operations because
 * the block driver may be on waiting response from the server.
 */
 static int get_sheep_fd(BDRVSheepdogState *s)
@@ -1383,9 +1375,9 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags,

    s->bs = bs;

-    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
+    opts = qemu_opts_create_nofail(&runtime_opts);
    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        qerror_report_err(local_err);
        error_free(local_err);
        ret = -EINVAL;
@@ -1472,7 +1464,9 @@ out:
    return ret;
 }

-static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot)
+static int do_sd_create(BDRVSheepdogState *s, char *filename, int64_t vdi_size,
+                        uint32_t base_vid, uint32_t *vdi_id, int snapshot,
+                        uint8_t copy_policy)
 {
    SheepdogVdiReq hdr;
    SheepdogVdiRsp *rsp = (SheepdogVdiRsp *)&hdr;
@@ -1489,11 +1483,11 @@ static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot)
     * does not fit in buf?  For now, just truncate and avoid buffer overrun.
     */
    memset(buf, 0, sizeof(buf));
-    pstrcpy(buf, sizeof(buf), s->name);
+    pstrcpy(buf, sizeof(buf), filename);

    memset(&hdr, 0, sizeof(hdr));
    hdr.opcode = SD_OP_NEW_VDI;
-    hdr.base_vdi_id = s->inode.vdi_id;
+    hdr.vdi_id = base_vid;

    wlen = SD_MAX_VDI_LEN;

@@ -1501,9 +1495,8 @@ static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot)
    hdr.snapid = snapshot;

    hdr.data_length = wlen;
-    hdr.vdi_size = s->inode.vdi_size;
-    hdr.copy_policy = s->inode.copy_policy;
-    hdr.copies = s->inode.nr_copies;
+    hdr.vdi_size = vdi_size;
+    hdr.copy_policy = copy_policy;

    ret = do_req(fd, (SheepdogReq *)&hdr, buf, &wlen, &rlen);

@@ -1514,7 +1507,7 @@ static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot)
    }

    if (rsp->result != SD_RES_SUCCESS) {
-        error_report("%s, %s", sd_strerror(rsp->result), s->inode.name);
+        error_report("%s, %s", sd_strerror(rsp->result), filename);
        return -EIO;
    }

@@ -1534,8 +1527,7 @@ static int sd_prealloc(const char *filename)
    Error *local_err = NULL;
    int ret;

-    ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
-                    NULL, &local_err);
+    ret = bdrv_file_open(&bs, filename, NULL, BDRV_O_RDWR, &local_err);
    if (ret < 0) {
        qerror_report_err(local_err);
        error_free(local_err);
@@ -1572,79 +1564,27 @@ out:
    return ret;
 }

-/*
- * Sheepdog support two kinds of redundancy, full replication and erasure
- * coding.
- *
- * # create a fully replicated vdi with x copies
- * -o redundancy=x (1 <= x <= SD_MAX_COPIES)
- *
- * # create a erasure coded vdi with x data strips and y parity strips
- * -o redundancy=x:y (x must be one of {2,4,8,16} and 1 <= y < SD_EC_MAX_STRIP)
- */
-static int parse_redundancy(BDRVSheepdogState *s, const char *opt)
-{
-    struct SheepdogInode *inode = &s->inode;
-    const char *n1, *n2;
-    long copy, parity;
-    char p[10];
-
-    pstrcpy(p, sizeof(p), opt);
-    n1 = strtok(p, ":");
-    n2 = strtok(NULL, ":");
-
-    if (!n1) {
-        return -EINVAL;
-    }
-
-    copy = strtol(n1, NULL, 10);
-    if (copy > SD_MAX_COPIES || copy < 1) {
-        return -EINVAL;
-    }
-    if (!n2) {
-        inode->copy_policy = 0;
-        inode->nr_copies = copy;
-        return 0;
-    }
-
-    if (copy != 2 && copy != 4 && copy != 8 && copy != 16) {
-        return -EINVAL;
-    }
-
-    parity = strtol(n2, NULL, 10);
-    if (parity >= SD_EC_MAX_STRIP || parity < 1) {
-        return -EINVAL;
-    }
-
-    /*
-     * 4 bits for parity and 4 bits for data.
-     * We have to compress upper data bits because it can't represent 16
-     */
-    inode->copy_policy = ((copy / 2) << 4) + parity;
-    inode->nr_copies = copy + parity;
-
-    return 0;
-}
-
 static int sd_create(const char *filename, QEMUOptionParameter *options,
                     Error **errp)
 {
    int ret = 0;
-    uint32_t vid = 0;
+    uint32_t vid = 0, base_vid = 0;
+    int64_t vdi_size = 0;
    char *backing_file = NULL;
    BDRVSheepdogState *s;
-    char tag[SD_MAX_VDI_TAG_LEN];
+    char vdi[SD_MAX_VDI_LEN], tag[SD_MAX_VDI_TAG_LEN];
    uint32_t snapid;
    bool prealloc = false;
    Error *local_err = NULL;

    s = g_malloc0(sizeof(BDRVSheepdogState));

+    memset(vdi, 0, sizeof(vdi));
    memset(tag, 0, sizeof(tag));
    if (strstr(filename, "://")) {
-        ret = sd_parse_uri(s, filename, s->name, &snapid, tag);
+        ret = sd_parse_uri(s, filename, vdi, &snapid, tag);
    } else {
-        ret = parse_vdiname(s, filename, s->name, &snapid, tag);
+        ret = parse_vdiname(s, filename, vdi, &snapid, tag);
    }
    if (ret < 0) {
        goto out;
@@ -1652,7 +1592,7 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,

    while (options && options->name) {
        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
-            s->inode.vdi_size = options->value.n;
+            vdi_size = options->value.n;
        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
            backing_file = options->value.s;
        } else if (!strcmp(options->name, BLOCK_OPT_PREALLOC)) {
@@ -1666,18 +1606,11 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
                ret = -EINVAL;
                goto out;
            }
-        } else if (!strcmp(options->name, BLOCK_OPT_REDUNDANCY)) {
-            if (options->value.s) {
-                ret = parse_redundancy(s, options->value.s);
-                if (ret < 0) {
-                    goto out;
-                }
-            }
        }
        options++;
    }

-    if (s->inode.vdi_size > SD_MAX_VDI_SIZE) {
+    if (vdi_size > SD_MAX_VDI_SIZE) {
        error_report("too big image size");
        ret = -EINVAL;
        goto out;
@@ -1685,7 +1618,7 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,

    if (backing_file) {
        BlockDriverState *bs;
-        BDRVSheepdogState *base;
+        BDRVSheepdogState *s;
        BlockDriver *drv;

        /* Currently, only Sheepdog backing image is supported. */
@@ -1696,28 +1629,28 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
            goto out;
        }

-        bs = NULL;
-        ret = bdrv_open(&bs, backing_file, NULL, NULL, BDRV_O_PROTOCOL, NULL,
-                        &local_err);
+        ret = bdrv_file_open(&bs, backing_file, NULL, 0, &local_err);
        if (ret < 0) {
            qerror_report_err(local_err);
            error_free(local_err);
            goto out;
        }

-        base = bs->opaque;
+        s = bs->opaque;

-        if (!is_snapshot(&base->inode)) {
+        if (!is_snapshot(&s->inode)) {
            error_report("cannot clone from a non snapshot vdi");
            bdrv_unref(bs);
            ret = -EINVAL;
            goto out;
        }
-        s->inode.vdi_id = base->inode.vdi_id;
+
+        base_vid = s->inode.vdi_id;
        bdrv_unref(bs);
    }

-    ret = do_sd_create(s, &vid, 0);
+    /* TODO: allow users to specify copy number */
+    ret = do_sd_create(s, vdi, vdi_size, base_vid, &vid, 0, 0);
    if (!prealloc || ret) {
        goto out;
    }
@@ -1746,7 +1679,7 @@ static void sd_close(BlockDriverState *bs)
    memset(&hdr, 0, sizeof(hdr));

    hdr.opcode = SD_OP_RELEASE_VDI;
-    hdr.base_vdi_id = s->inode.vdi_id;
+    hdr.vdi_id = s->inode.vdi_id;
    wlen = strlen(s->name) + 1;
    hdr.data_length = wlen;
    hdr.flags = SD_FLAG_CMD_WRITE;
@@ -1849,7 +1782,7 @@ static bool sd_delete(BDRVSheepdogState *s)
    unsigned int wlen = SD_MAX_VDI_LEN, rlen = 0;
    SheepdogVdiReq hdr = {
        .opcode = SD_OP_DEL_VDI,
-        .base_vdi_id = s->inode.vdi_id,
+        .vdi_id = s->inode.vdi_id,
        .data_length = wlen,
        .flags = SD_FLAG_CMD_WRITE,
    };
@@ -1896,11 +1829,12 @@ static int sd_create_branch(BDRVSheepdogState *s)

    /*
     * Even If deletion fails, we will just create extra snapshot based on
-     * the working VDI which was supposed to be deleted. So no need to
+     * the workding VDI which was supposed to be deleted. So no need to
     * false bail out.
     */
    deleted = sd_delete(s);
-    ret = do_sd_create(s, &vid, !deleted);
+    ret = do_sd_create(s, s->name, s->inode.vdi_size, s->inode.vdi_id, &vid,
+                       !deleted, s->inode.copy_policy);
    if (ret) {
        goto out;
    }
@@ -2051,14 +1985,13 @@ static coroutine_fn int sd_co_writev(BlockDriverState *bs, int64_t sector_num,
 {
    SheepdogAIOCB *acb;
    int ret;
-    int64_t offset = (sector_num + nb_sectors) * BDRV_SECTOR_SIZE;
-    BDRVSheepdogState *s = bs->opaque;

-    if (bs->growable && offset > s->inode.vdi_size) {
-        ret = sd_truncate(bs, offset);
+    if (bs->growable && sector_num + nb_sectors > bs->total_sectors) {
+        ret = sd_truncate(bs, (sector_num + nb_sectors) * BDRV_SECTOR_SIZE);
        if (ret < 0) {
            return ret;
        }
+        bs->total_sectors = sector_num + nb_sectors;
    }

    acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors);
@@ -2165,7 +2098,8 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
        goto cleanup;
    }

-    ret = do_sd_create(s, &new_vid, 1);
+    ret = do_sd_create(s, s->name, s->inode.vdi_size, s->inode.vdi_id, &new_vid,
+                       1, s->inode.copy_policy);
    if (ret < 0) {
        error_report("failed to create inode for snapshot. %s",
                     strerror(errno));
@@ -2194,7 +2128,7 @@ cleanup:
 * We implement rollback(loadvm) operation to the specified snapshot by
 * 1) switch to the snapshot
 * 2) rely on sd_create_branch to delete working VDI and
- * 3) create a new working VDI based on the specified snapshot
+ * 3) create a new working VDI based on the speicified snapshot
 */
 static int sd_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
 {
@@ -2445,12 +2379,11 @@ sd_co_get_block_status(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
 {
    BDRVSheepdogState *s = bs->opaque;
    SheepdogInode *inode = &s->inode;
-    uint64_t offset = sector_num * BDRV_SECTOR_SIZE;
-    unsigned long start = offset / SD_DATA_OBJ_SIZE,
+    unsigned long start = sector_num * BDRV_SECTOR_SIZE / SD_DATA_OBJ_SIZE,
                  end = DIV_ROUND_UP((sector_num + nb_sectors) *
                                     BDRV_SECTOR_SIZE, SD_DATA_OBJ_SIZE);
    unsigned long idx;
-    int64_t ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | offset;
+    int64_t ret = BDRV_BLOCK_DATA;

    for (idx = start; idx < end; idx++) {
        if (inode->data_vdi_id[idx] == 0) {
@@ -2474,22 +2407,6 @@ sd_co_get_block_status(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
    return ret;
 }

-static int64_t sd_get_allocated_file_size(BlockDriverState *bs)
-{
-    BDRVSheepdogState *s = bs->opaque;
-    SheepdogInode *inode = &s->inode;
-    unsigned long i, last = DIV_ROUND_UP(inode->vdi_size, SD_DATA_OBJ_SIZE);
-    uint64_t size = 0;
-
-    for (i = 0; i < last; i++) {
-        if (inode->data_vdi_id[i] == 0) {
-            continue;
-        }
-        size += SD_DATA_OBJ_SIZE;
-    }
-    return size;
-}
-
 static QEMUOptionParameter sd_create_options[] = {
    {
        .name = BLOCK_OPT_SIZE,
@@ -2506,11 +2423,6 @@ static QEMUOptionParameter sd_create_options[] = {
        .type = OPT_STRING,
        .help = "Preallocation mode (allowed values: off, full)"
    },
-    {
-        .name = BLOCK_OPT_REDUNDANCY,
-        .type = OPT_STRING,
-        .help = "Redundancy of the image"
-    },
    { NULL }
 };

@@ -2524,7 +2436,6 @@ static BlockDriver bdrv_sheepdog = {
    .bdrv_create    = sd_create,
    .bdrv_has_zero_init = bdrv_has_zero_init_1,
    .bdrv_getlength = sd_getlength,
-    .bdrv_get_allocated_file_size = sd_get_allocated_file_size,
    .bdrv_truncate  = sd_truncate,

    .bdrv_co_readv  = sd_co_readv,
@@ -2554,7 +2465,6 @@ static BlockDriver bdrv_sheepdog_tcp = {
    .bdrv_create    = sd_create,
    .bdrv_has_zero_init = bdrv_has_zero_init_1,
    .bdrv_getlength = sd_getlength,
-    .bdrv_get_allocated_file_size = sd_get_allocated_file_size,
    .bdrv_truncate  = sd_truncate,

    .bdrv_co_readv  = sd_co_readv,
@@ -2584,7 +2494,6 @@ static BlockDriver bdrv_sheepdog_unix = {
    .bdrv_create    = sd_create,
    .bdrv_has_zero_init = bdrv_has_zero_init_1,
    .bdrv_getlength = sd_getlength,
-    .bdrv_get_allocated_file_size = sd_get_allocated_file_size,
    .bdrv_truncate  = sd_truncate,

    .bdrv_co_readv  = sd_co_readv,
@@ -25,24 +25,6 @@
 #include "block/snapshot.h"
 #include "block/block_int.h"

-QemuOptsList internal_snapshot_opts = {
-    .name = "snapshot",
-    .head = QTAILQ_HEAD_INITIALIZER(internal_snapshot_opts.head),
-    .desc = {
-        {
-            .name = SNAPSHOT_OPT_ID,
-            .type = QEMU_OPT_STRING,
-            .help = "snapshot id"
-        },{
-            .name = SNAPSHOT_OPT_NAME,
-            .type = QEMU_OPT_STRING,
-            .help = "snapshot name"
-        },{
-            /* end of list */
-        }
-    },
-};
-
 int bdrv_snapshot_find(BlockDriverState *bs, QEMUSnapshotInfo *sn_info,
                       const char *name)
 {
@@ -212,7 +194,7 @@ int bdrv_snapshot_goto(BlockDriverState *bs,
 * If only @snapshot_id is specified, delete the first one with id
 * @snapshot_id.
 * If only @name is specified, delete the first one with name @name.
- * if none is specified, return -EINVAL.
+ * if none is specified, return -ENINVAL.
 *
 * Returns: 0 on success, -errno on failure. If @bs is not inserted, return
 * -ENOMEDIUM. If @snapshot_id and @name are both NULL, return -EINVAL. If @bs
@@ -283,71 +265,18 @@ int bdrv_snapshot_list(BlockDriverState *bs,
    return -ENOTSUP;
 }

-/**
- * Temporarily load an internal snapshot by @snapshot_id and @name.
- * @bs: block device used in the operation
- * @snapshot_id: unique snapshot ID, or NULL
- * @name: snapshot name, or NULL
- * @errp: location to store error
- *
- * If both @snapshot_id and @name are specified, load the first one with
- * id @snapshot_id and name @name.
- * If only @snapshot_id is specified, load the first one with id
- * @snapshot_id.
- * If only @name is specified, load the first one with name @name.
- * if none is specified, return -EINVAL.
- *
- * Returns: 0 on success, -errno on fail. If @bs is not inserted, return
- * -ENOMEDIUM. If @bs is not readonly, return -EINVAL. If @bs did not support
- * internal snapshot, return -ENOTSUP. If qemu can't find a matching @id and
- * @name, return -ENOENT. If @errp != NULL, it will always be filled on
- * failure.
- */
 int bdrv_snapshot_load_tmp(BlockDriverState *bs,
-                           const char *snapshot_id,
-                           const char *name,
-                           Error **errp)
+        const char *snapshot_name)
 {
    BlockDriver *drv = bs->drv;
-
    if (!drv) {
-        error_set(errp, QERR_DEVICE_HAS_NO_MEDIUM, bdrv_get_device_name(bs));
        return -ENOMEDIUM;
    }
-    if (!snapshot_id && !name) {
-        error_setg(errp, "snapshot_id and name are both NULL");
-        return -EINVAL;
-    }
    if (!bs->read_only) {
-        error_setg(errp, "Device is not readonly");
        return -EINVAL;
    }
    if (drv->bdrv_snapshot_load_tmp) {
-        return drv->bdrv_snapshot_load_tmp(bs, snapshot_id, name, errp);
+        return drv->bdrv_snapshot_load_tmp(bs, snapshot_name);
    }
-    error_set(errp, QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
-              drv->format_name, bdrv_get_device_name(bs),
-              "temporarily load internal snapshot");
    return -ENOTSUP;
 }
-
-int bdrv_snapshot_load_tmp_by_id_or_name(BlockDriverState *bs,
-                                         const char *id_or_name,
-                                         Error **errp)
-{
-    int ret;
-    Error *local_err = NULL;
-
-    ret = bdrv_snapshot_load_tmp(bs, id_or_name, NULL, &local_err);
-    if (ret == -ENOENT || ret == -EINVAL) {
-        error_free(local_err);
-        local_err = NULL;
-        ret = bdrv_snapshot_load_tmp(bs, NULL, id_or_name, &local_err);
-    }
-
-    if (local_err) {
-        error_propagate(errp, local_err);
-    }
-
-    return ret;
-}
@@ -75,8 +75,6 @@ static void close_unused_images(BlockDriverState *top, BlockDriverState *base,
        unused->backing_hd = NULL;
        bdrv_unref(unused);
    }
-
-    bdrv_refresh_limits(top);
 }

 static void coroutine_fn stream_run(void *opaque)
@@ -90,11 +88,6 @@ static void coroutine_fn stream_run(void *opaque)
    int n = 0;
    void *buf;

-    if (!bs->backing_hd) {
-        block_job_completed(&s->common, 0);
-        return;
-    }
-
    s->common.len = bdrv_getlength(bs);
    if (s->common.len < 0) {
        block_job_completed(&s->common, s->common.len);
@@ -31,7 +31,7 @@
 * Allocation of blocks could be optimized (less writes to block map and
 * header).
 *
- * Read and write of adjacent blocks could be done in one operation
+ * Read and write of adjacents blocks could be done in one operation
 * (current code uses one operation per block (1 MiB).
 *
 * The code is not thread safe (missing locks for changes in header and
@@ -336,7 +336,6 @@ static int vdi_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
    logout("\n");
    bdi->cluster_size = s->block_size;
    bdi->vm_state_offset = 0;
-    bdi->unallocated_blocks_are_zero = true;
    return 0;
 }

@@ -391,9 +390,8 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
 #endif

    if (header.disk_size > VDI_DISK_SIZE_MAX) {
-        error_setg(errp, "Unsupported VDI image size (size is 0x%" PRIx64
-                          ", max supported is 0x%" PRIx64 ")",
-                          header.disk_size, VDI_DISK_SIZE_MAX);
+        logout("disk size is 0x%" PRIx64 ", max supported is 0x%" PRIx64,
+               header.disk_size, VDI_DISK_SIZE_MAX);
        ret = -ENOTSUP;
        goto fail;
    }
@@ -408,56 +406,48 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
    }

    if (header.signature != VDI_SIGNATURE) {
-        error_setg(errp, "Image not in VDI format (bad signature %08x)", header.signature);
-        ret = -EINVAL;
+        logout("bad vdi signature %08x\n", header.signature);
+        ret = -EMEDIUMTYPE;
        goto fail;
    } else if (header.version != VDI_VERSION_1_1) {
-        error_setg(errp, "unsupported VDI image (version %u.%u)",
-                   header.version >> 16, header.version & 0xffff);
+        logout("unsupported version %u.%u\n",
+               header.version >> 16, header.version & 0xffff);
        ret = -ENOTSUP;
        goto fail;
    } else if (header.offset_bmap % SECTOR_SIZE != 0) {
        /* We only support block maps which start on a sector boundary. */
-        error_setg(errp, "unsupported VDI image (unaligned block map offset "
-                   "0x%x)", header.offset_bmap);
+        logout("unsupported block map offset 0x%x B\n", header.offset_bmap);
        ret = -ENOTSUP;
        goto fail;
    } else if (header.offset_data % SECTOR_SIZE != 0) {
        /* We only support data blocks which start on a sector boundary. */
-        error_setg(errp, "unsupported VDI image (unaligned data offset 0x%x)",
-                   header.offset_data);
+        logout("unsupported data offset 0x%x B\n", header.offset_data);
        ret = -ENOTSUP;
        goto fail;
    } else if (header.sector_size != SECTOR_SIZE) {
-        error_setg(errp, "unsupported VDI image (sector size %u is not %u)",
-                   header.sector_size, SECTOR_SIZE);
+        logout("unsupported sector size %u B\n", header.sector_size);
        ret = -ENOTSUP;
        goto fail;
    } else if (header.block_size != DEFAULT_CLUSTER_SIZE) {
-        error_setg(errp, "unsupported VDI image (block size %u is not %u)",
-                   header.block_size, DEFAULT_CLUSTER_SIZE);
+        logout("unsupported block size %u B\n", header.block_size);
        ret = -ENOTSUP;
        goto fail;
    } else if (header.disk_size >
               (uint64_t)header.blocks_in_image * header.block_size) {
-        error_setg(errp, "unsupported VDI image (disk size %" PRIu64 ", "
-                   "image bitmap has room for %" PRIu64 ")",
-                   header.disk_size,
-                   (uint64_t)header.blocks_in_image * header.block_size);
+        logout("unsupported disk size %" PRIu64 " B\n", header.disk_size);
        ret = -ENOTSUP;
        goto fail;
    } else if (!uuid_is_null(header.uuid_link)) {
-        error_setg(errp, "unsupported VDI image (non-NULL link UUID)");
+        logout("link uuid != 0, unsupported\n");
        ret = -ENOTSUP;
        goto fail;
    } else if (!uuid_is_null(header.uuid_parent)) {
-        error_setg(errp, "unsupported VDI image (non-NULL parent UUID)");
+        logout("parent uuid != 0, unsupported\n");
        ret = -ENOTSUP;
        goto fail;
    } else if (header.blocks_in_image > VDI_BLOCKS_IN_IMAGE_MAX) {
-        error_setg(errp, "unsupported VDI image "
-                         "(too many blocks %u, max is %u)",
-                          header.blocks_in_image, VDI_BLOCKS_IN_IMAGE_MAX);
+        logout("too many blocks %u, max is %u)",
+               header.blocks_in_image, VDI_BLOCKS_IN_IMAGE_MAX);
        ret = -ENOTSUP;
        goto fail;
    }
@@ -710,9 +700,9 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options,

    if (bytes > VDI_DISK_SIZE_MAX) {
        result = -ENOTSUP;
-        error_setg(errp, "Unsupported VDI image size (size is 0x%" PRIx64
-                          ", max supported is 0x%" PRIx64 ")",
-                          bytes, VDI_DISK_SIZE_MAX);
+        logout("image size (size is 0x%" PRIx64
+               ", max supported is 0x%" PRIx64 ")",
+               bytes, VDI_DISK_SIZE_MAX);
        goto exit;
    }

@@ -578,7 +578,7 @@ static int vhdx_validate_log_entry(BlockDriverState *bs, BDRVVHDXState *s,
    total_sectors = hdr.entry_length / VHDX_LOG_SECTOR_SIZE;


-    /* read_desc() will increment the read idx */
+    /* read_desc() will incrememnt the read idx */
    ret = vhdx_log_read_desc(bs, s, log, &desc_buffer);
    if (ret < 0) {
        goto free_and_exit;
@@ -706,8 +706,7 @@ exit:
 *
 * If read-only, we must replay the log in RAM (or refuse to open
 * a dirty VHDX file read-only) */
-int vhdx_parse_log(BlockDriverState *bs, BDRVVHDXState *s, bool *flushed,
-                   Error **errp)
+int vhdx_parse_log(BlockDriverState *bs, BDRVVHDXState *s, bool *flushed)
 {
    int ret = 0;
    VHDXHeader *hdr;
@@ -762,16 +761,6 @@ int vhdx_parse_log(BlockDriverState *bs, BDRVVHDXState *s, bool *flushed,
    }

    if (logs.valid) {
-        if (bs->read_only) {
-            ret = -EPERM;
-            error_setg_errno(errp, EPERM,
-                             "VHDX image file '%s' opened read-only, but "
-                             "contains a log that needs to be replayed.  To "
-                             "replay the log, execute:\n qemu-img check -r "
-                             "all '%s'",
-                             bs->filename, bs->filename);
-            goto exit;
-        }
        /* now flush the log */
        ret = vhdx_log_flush(bs, s, &logs);
        if (ret < 0) {
@@ -965,8 +954,8 @@ static int vhdx_log_write(BlockDriverState *bs, BDRVVHDXState *s,
    cpu_to_le32s((uint32_t *)(buffer + 4));

    /* now write to the log */
-    ret = vhdx_log_write_sectors(bs, &s->log, &sectors_written, buffer,
-                                 desc_sectors + sectors);
+    vhdx_log_write_sectors(bs, &s->log, &sectors_written, buffer,
+                           desc_sectors + sectors);
    if (ret < 0) {
        goto exit;
    }
@@ -374,7 +374,7 @@ static int vhdx_update_header(BlockDriverState *bs, BDRVVHDXState *s,
        inactive_header->log_guid = *log_guid;
    }

-    ret = vhdx_write_header(bs->file, inactive_header, header_offset, true);
+    vhdx_write_header(bs->file, inactive_header, header_offset, true);
    if (ret < 0) {
        goto exit;
    }
@@ -402,10 +402,9 @@ int vhdx_update_headers(BlockDriverState *bs, BDRVVHDXState *s,
 }

 /* opens the specified header block from the VHDX file header section */
-static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s,
-                              Error **errp)
+static int vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s)
 {
-    int ret;
+    int ret = 0;
    VHDXHeader *header1;
    VHDXHeader *header2;
    bool h1_valid = false;
@@ -463,6 +462,7 @@ static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s,
    } else if (!h1_valid && h2_valid) {
        s->curr_header = 1;
    } else if (!h1_valid && !h2_valid) {
+        ret = -EINVAL;
        goto fail;
    } else {
        /* If both headers are valid, then we choose the active one by the
@@ -473,22 +473,27 @@ static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s,
        } else if (h2_seq > h1_seq) {
            s->curr_header = 1;
        } else {
+            ret = -EINVAL;
            goto fail;
        }
    }

    vhdx_region_register(s, s->headers[s->curr_header]->log_offset,
                            s->headers[s->curr_header]->log_length);
+
+    ret = 0;
+
    goto exit;

 fail:
-    error_setg_errno(errp, -ret, "No valid VHDX header found");
+    qerror_report(ERROR_CLASS_GENERIC_ERROR, "No valid VHDX header found");
    qemu_vfree(header1);
    qemu_vfree(header2);
    s->headers[0] = NULL;
    s->headers[1] = NULL;
 exit:
    qemu_vfree(buffer);
+    return ret;
 }


@@ -881,7 +886,8 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
    int ret = 0;
    uint32_t i;
    uint64_t signature;
-    Error *local_err = NULL;
+    bool log_flushed = false;
+

    s->bat = NULL;
    s->first_visible_write = true;
@@ -904,14 +910,12 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
     * header update */
    vhdx_guid_generate(&s->session_guid);

-    vhdx_parse_header(bs, s, &local_err);
-    if (local_err != NULL) {
-        error_propagate(errp, local_err);
-        ret = -EINVAL;
+    ret = vhdx_parse_header(bs, s);
+    if (ret < 0) {
        goto fail;
    }

-    ret = vhdx_parse_log(bs, s, &s->log_replayed_on_open, errp);
+    ret = vhdx_parse_log(bs, s, &log_flushed);
    if (ret < 0) {
        goto fail;
    }
@@ -1047,18 +1051,6 @@ static void vhdx_block_translate(BDRVVHDXState *s, int64_t sector_num,
 }


-static int vhdx_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
-{
-    BDRVVHDXState *s = bs->opaque;
-
-    bdi->cluster_size = s->block_size;
-
-    bdi->unallocated_blocks_are_zero =
-        (s->params.data_bits & VHDX_PARAMS_HAS_PARENT) == 0;
-
-    return 0;
-}
-

 static coroutine_fn int vhdx_co_readv(BlockDriverState *bs, int64_t sector_num,
                                      int nb_sectors, QEMUIOVector *qiov)
@@ -1802,9 +1794,7 @@ static int vhdx_create(const char *filename, QEMUOptionParameter *options,
        goto exit;
    }

-    bs = NULL;
-    ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
-                    NULL, &local_err);
+    ret = bdrv_file_open(&bs, filename, NULL, BDRV_O_RDWR, &local_err);
    if (ret < 0) {
        error_propagate(errp, local_err);
        goto exit;
@@ -1817,13 +1807,13 @@ static int vhdx_create(const char *filename, QEMUOptionParameter *options,
    creator = g_utf8_to_utf16("QEMU v" QEMU_VERSION, -1, NULL,
                              &creator_items, NULL);
    signature = cpu_to_le64(VHDX_FILE_SIGNATURE);
-    ret = bdrv_pwrite(bs, VHDX_FILE_ID_OFFSET, &signature, sizeof(signature));
+    bdrv_pwrite(bs, VHDX_FILE_ID_OFFSET, &signature, sizeof(signature));
    if (ret < 0) {
        goto delete_and_exit;
    }
    if (creator) {
-        ret = bdrv_pwrite(bs, VHDX_FILE_ID_OFFSET + sizeof(signature),
-                          creator, creator_items * sizeof(gunichar2));
+        bdrv_pwrite(bs, VHDX_FILE_ID_OFFSET + sizeof(signature), creator,
+                    creator_items * sizeof(gunichar2));
        if (ret < 0) {
            goto delete_and_exit;
        }
@@ -1860,24 +1850,6 @@ exit:
    return ret;
 }

-/* If opened r/w, the VHDX driver will automatically replay the log,
- * if one is present, inside the vhdx_open() call.
- *
- * If qemu-img check -r all is called, the image is automatically opened
- * r/w and any log has already been replayed, so there is nothing (currently)
- * for us to do here
- */
-static int vhdx_check(BlockDriverState *bs, BdrvCheckResult *result,
-                       BdrvCheckMode fix)
-{
-    BDRVVHDXState *s = bs->opaque;
-
-    if (s->log_replayed_on_open) {
-        result->corruptions_fixed++;
-    }
-    return 0;
-}
-
 static QEMUOptionParameter vhdx_create_options[] = {
    {
        .name = BLOCK_OPT_SIZE,
@@ -1921,8 +1893,6 @@ static BlockDriver bdrv_vhdx = {
    .bdrv_co_readv          = vhdx_co_readv,
    .bdrv_co_writev         = vhdx_co_writev,
    .bdrv_create            = vhdx_create,
-    .bdrv_get_info          = vhdx_get_info,
-    .bdrv_check             = vhdx_check,

    .create_options         = vhdx_create_options,
 };
@@ -61,7 +61,7 @@
 /* These structures are ones that are defined in the VHDX specification
 * document */

-#define VHDX_FILE_SIGNATURE 0x656C696678646876ULL  /* "vhdxfile" in ASCII */
+#define VHDX_FILE_SIGNATURE 0x656C696678646876  /* "vhdxfile" in ASCII */
 typedef struct VHDXFileIdentifier {
    uint64_t    signature;              /* "vhdxfile" in ASCII */
    uint16_t    creator[256];           /* optional; utf-16 string to identify
@@ -238,7 +238,7 @@ typedef struct QEMU_PACKED VHDXLogDataSector {
 /* upper 44 bits are the file offset in 1MB units lower 3 bits are the state
   other bits are reserved */
 #define VHDX_BAT_STATE_BIT_MASK 0x07
-#define VHDX_BAT_FILE_OFF_MASK  0xFFFFFFFFFFF00000ULL /* upper 44 bits */
+#define VHDX_BAT_FILE_OFF_MASK  0xFFFFFFFFFFF00000 /* upper 44 bits */
 typedef uint64_t VHDXBatEntry;

 /* ---- METADATA REGION STRUCTURES ---- */
@@ -247,7 +247,7 @@ typedef uint64_t VHDXBatEntry;
 #define VHDX_METADATA_MAX_ENTRIES 2047  /* not including the header */
 #define VHDX_METADATA_TABLE_MAX_SIZE \
    (VHDX_METADATA_ENTRY_SIZE * (VHDX_METADATA_MAX_ENTRIES+1))
-#define VHDX_METADATA_SIGNATURE 0x617461646174656DULL  /* "metadata" in ASCII */
+#define VHDX_METADATA_SIGNATURE 0x617461646174656D  /* "metadata" in ASCII */
 typedef struct QEMU_PACKED VHDXMetadataTableHeader {
    uint64_t    signature;              /* "metadata" in ASCII */
    uint16_t    reserved;
@@ -394,8 +394,6 @@ typedef struct BDRVVHDXState {

    Error *migration_blocker;

-    bool log_replayed_on_open;
-
    QLIST_HEAD(VHDXRegionHead, VHDXRegionEntry) regions;
 } BDRVVHDXState;

@@ -410,8 +408,7 @@ uint32_t vhdx_checksum_calc(uint32_t crc, uint8_t *buf, size_t size,

 bool vhdx_checksum_is_valid(uint8_t *buf, size_t size, int crc_offset);

-int vhdx_parse_log(BlockDriverState *bs, BDRVVHDXState *s, bool *flushed,
-                   Error **errp);
+int vhdx_parse_log(BlockDriverState *bs, BDRVVHDXState *s, bool *flushed);

 int vhdx_log_write_and_flush(BlockDriverState *bs, BDRVVHDXState *s,
                             void *data, uint32_t length, uint64_t offset);
@@ -526,34 +526,8 @@ static int vmdk_open_vmfs_sparse(BlockDriverState *bs,
    return ret;
 }

-static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
-                               Error **errp);
-
-static char *vmdk_read_desc(BlockDriverState *file, uint64_t desc_offset,
-                            Error **errp)
-{
-    int64_t size;
-    char *buf;
-    int ret;
-
-    size = bdrv_getlength(file);
-    if (size < 0) {
-        error_setg_errno(errp, -size, "Could not access file");
-        return NULL;
-    }
-
-    size = MIN(size, 1 << 20);  /* avoid unbounded allocation */
-    buf = g_malloc0(size + 1);
-
-    ret = bdrv_pread(file, desc_offset, buf, size);
-    if (ret < 0) {
-        error_setg_errno(errp, -ret, "Could not read from file");
-        g_free(buf);
-        return NULL;
-    }
-
-    return buf;
-}
+static int vmdk_open_desc_file(BlockDriverState *bs, int flags,
+                               uint64_t desc_offset, Error **errp);

 static int vmdk_open_vmdk4(BlockDriverState *bs,
                           BlockDriverState *file,
@@ -572,18 +546,11 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
        error_setg_errno(errp, -ret,
                         "Could not read header from file '%s'",
                         file->filename);
-        return -EINVAL;
    }
    if (header.capacity == 0) {
        uint64_t desc_offset = le64_to_cpu(header.desc_offset);
        if (desc_offset) {
-            char *buf = vmdk_read_desc(file, desc_offset << 9, errp);
-            if (!buf) {
-                return -EINVAL;
-            }
-            ret = vmdk_open_desc_file(bs, flags, buf, errp);
-            g_free(buf);
-            return ret;
+            return vmdk_open_desc_file(bs, flags, desc_offset << 9, errp);
        }
    }

@@ -638,24 +605,17 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
        header = footer.header;
    }

-    if (le32_to_cpu(header.version) > 3) {
+    if (le32_to_cpu(header.version) >= 3) {
        char buf[64];
        snprintf(buf, sizeof(buf), "VMDK version %d",
                 le32_to_cpu(header.version));
-        error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
-                  bs->device_name, "vmdk", buf);
+        qerror_report(QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+                bs->device_name, "vmdk", buf);
        return -ENOTSUP;
-    } else if (le32_to_cpu(header.version) == 3 && (flags & BDRV_O_RDWR)) {
-        /* VMware KB 2064959 explains that version 3 added support for
-         * persistent changed block tracking (CBT), and backup software can
-         * read it as version=1 if it doesn't care about the changed area
-         * information. So we are safe to enable read only. */
-        error_setg(errp, "VMDK version 3 must be read only");
-        return -EINVAL;
    }

    if (le32_to_cpu(header.num_gtes_per_gt) > 512) {
-        error_setg(errp, "L2 table size too big");
+        error_report("L2 table size too big");
        return -EINVAL;
    }

@@ -669,13 +629,6 @@ 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_getlength(file) <
-            le64_to_cpu(header.grain_offset) * BDRV_SECTOR_SIZE) {
-        error_setg(errp, "File truncated, expecting at least %lld bytes",
-                   le64_to_cpu(header.grain_offset) * BDRV_SECTOR_SIZE);
-        return -EINVAL;
-    }
-
    ret = vmdk_add_extent(bs, file, false,
                          le64_to_cpu(header.capacity),
                          le64_to_cpu(header.gd_offset) << 9,
@@ -690,10 +643,6 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
    }
    extent->compressed =
        le16_to_cpu(header.compressAlgorithm) == VMDK4_COMPRESSION_DEFLATE;
-    if (extent->compressed) {
-        g_free(s->create_type);
-        s->create_type = g_strdup("streamOptimized");
-    }
    extent->has_marker = le32_to_cpu(header.flags) & VMDK4_FLAG_MARKER;
    extent->version = le32_to_cpu(header.version);
    extent->has_zero_grain = le32_to_cpu(header.flags) & VMDK4_FLAG_ZERO_GRAIN;
@@ -734,12 +683,16 @@ static int vmdk_parse_description(const char *desc, const char *opt_name,

 /* Open an extent file and append to bs array */
 static int vmdk_open_sparse(BlockDriverState *bs,
-                            BlockDriverState *file, int flags,
-                            char *buf, Error **errp)
+                            BlockDriverState *file,
+                            int flags, Error **errp)
 {
    uint32_t magic;

-    magic = ldl_be_p(buf);
+    if (bdrv_pread(file, 0, &magic, sizeof(magic)) != sizeof(magic)) {
+        return -EIO;
+    }
+
+    magic = be32_to_cpu(magic);
    switch (magic) {
        case VMDK3_MAGIC:
            return vmdk_open_vmfs_sparse(bs, file, flags, errp);
@@ -748,8 +701,7 @@ static int vmdk_open_sparse(BlockDriverState *bs,
            return vmdk_open_vmdk4(bs, file, flags, errp);
            break;
        default:
-            error_setg(errp, "Image not in VMDK format");
-            return -EINVAL;
+            return -EMEDIUMTYPE;
            break;
    }
 }
@@ -786,14 +738,9 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
                return -EINVAL;
            }
        } else if (!strcmp(type, "VMFS")) {
-            if (ret == 4) {
-                flat_offset = 0;
-            } else {
-                error_setg(errp, "Invalid extent lines:\n%s", p);
-                return -EINVAL;
-            }
+            flat_offset = 0;
        } else if (ret != 4) {
-            error_setg(errp, "Invalid extent lines:\n%s", p);
+            error_setg(errp, "Invalid extent lines: \n%s", p);
            return -EINVAL;
        }

@@ -806,9 +753,8 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,

        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);
+        ret = bdrv_file_open(&extent_file, extent_path, NULL, bs->open_flags,
+                             errp);
        if (ret) {
            return ret;
        }
@@ -825,14 +771,8 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
            extent->flat_start_offset = flat_offset << 9;
        } else if (!strcmp(type, "SPARSE") || !strcmp(type, "VMFSSPARSE")) {
            /* SPARSE extent and VMFSSPARSE extent are both "COWD" sparse file*/
-            char *buf = vmdk_read_desc(extent_file, 0, errp);
-            if (!buf) {
-                ret = -EINVAL;
-            } else {
-                ret = vmdk_open_sparse(bs, extent_file, bs->open_flags, buf, errp);
-            }
+            ret = vmdk_open_sparse(bs, extent_file, bs->open_flags, errp);
            if (ret) {
-                g_free(buf);
                bdrv_unref(extent_file);
                return ret;
            }
@@ -855,16 +795,29 @@ next_line:
    return 0;
 }

-static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
-                               Error **errp)
+static int vmdk_open_desc_file(BlockDriverState *bs, int flags,
+                               uint64_t desc_offset, Error **errp)
 {
    int ret;
+    char *buf = NULL;
    char ct[128];
    BDRVVmdkState *s = bs->opaque;
+    int64_t size;

+    size = bdrv_getlength(bs->file);
+    if (size < 0) {
+        return -EINVAL;
+    }
+
+    size = MIN(size, 1 << 20);  /* avoid unbounded allocation */
+    buf = g_malloc0(size + 1);
+
+    ret = bdrv_pread(bs->file, desc_offset, buf, size);
+    if (ret < 0) {
+        goto exit;
+    }
    if (vmdk_parse_description(buf, "createType", ct, sizeof(ct))) {
-        error_setg(errp, "invalid VMDK image descriptor");
-        ret = -EINVAL;
+        ret = -EMEDIUMTYPE;
        goto exit;
    }
    if (strcmp(ct, "monolithicFlat") &&
@@ -880,37 +833,24 @@ static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
    s->desc_offset = 0;
    ret = vmdk_parse_extents(buf, bs, bs->file->filename, errp);
 exit:
+    g_free(buf);
    return ret;
 }

 static int vmdk_open(BlockDriverState *bs, QDict *options, int flags,
                     Error **errp)
 {
-    char *buf = NULL;
    int ret;
    BDRVVmdkState *s = bs->opaque;
-    uint32_t magic;

-    buf = vmdk_read_desc(bs->file, 0, errp);
-    if (!buf) {
-        return -EINVAL;
+    if (vmdk_open_sparse(bs, bs->file, flags, errp) == 0) {
+        s->desc_offset = 0x200;
+    } else {
+        ret = vmdk_open_desc_file(bs, flags, 0, errp);
+        if (ret) {
+            goto fail;
+        }
    }
-
-    magic = ldl_be_p(buf);
-    switch (magic) {
-        case VMDK3_MAGIC:
-        case VMDK4_MAGIC:
-            ret = vmdk_open_sparse(bs, bs->file, flags, buf, errp);
-            s->desc_offset = 0x200;
-            break;
-        default:
-            ret = vmdk_open_desc_file(bs, flags, buf, errp);
-            break;
-    }
-    if (ret) {
-        goto fail;
-    }
-
    /* try to open parent images, if exist */
    ret = vmdk_parent_open(bs);
    if (ret) {
@@ -925,34 +865,16 @@ static int vmdk_open(BlockDriverState *bs, QDict *options, int flags,
              QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
              "vmdk", bs->device_name, "live migration");
    migrate_add_blocker(s->migration_blocker);
-    g_free(buf);
+
    return 0;

 fail:
-    g_free(buf);
    g_free(s->create_type);
    s->create_type = NULL;
    vmdk_free_extents(bs);
    return ret;
 }

-
-static int vmdk_refresh_limits(BlockDriverState *bs)
-{
-    BDRVVmdkState *s = bs->opaque;
-    int i;
-
-    for (i = 0; i < s->num_extents; i++) {
-        if (!s->extents[i].flat) {
-            bs->bl.write_zeroes_alignment =
-                MAX(bs->bl.write_zeroes_alignment,
-                    s->extents[i].cluster_sectors);
-        }
-    }
-
-    return 0;
-}
-
 static int get_whole_cluster(BlockDriverState *bs,
                VmdkExtent *extent,
                uint64_t cluster_offset,
@@ -1184,7 +1106,7 @@ static int64_t coroutine_fn vmdk_co_get_block_status(BlockDriverState *bs,
        break;
    case VMDK_OK:
        ret = BDRV_BLOCK_DATA;
-        if (extent->file == bs->file && !extent->compressed) {
+        if (extent->file == bs->file) {
            ret |= BDRV_BLOCK_OFFSET_VALID | offset;
        }

@@ -1387,8 +1309,8 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
 {
    BDRVVmdkState *s = bs->opaque;
    VmdkExtent *extent = NULL;
-    int ret;
-    int64_t index_in_cluster, n;
+    int n, ret;
+    int64_t index_in_cluster;
    uint64_t extent_begin_sector, extent_relative_sector_num;
    uint64_t cluster_offset;
    VmdkMetaData m_data;
@@ -1497,8 +1419,7 @@ static coroutine_fn int vmdk_co_write(BlockDriverState *bs, int64_t sector_num,

 static int coroutine_fn vmdk_co_write_zeroes(BlockDriverState *bs,
                                             int64_t sector_num,
-                                             int nb_sectors,
-                                             BdrvRequestFlags flags)
+                                             int nb_sectors)
 {
    int ret;
    BDRVVmdkState *s = bs->opaque;
@@ -1514,35 +1435,23 @@ static int coroutine_fn vmdk_co_write_zeroes(BlockDriverState *bs,
 }

 static int vmdk_create_extent(const char *filename, int64_t filesize,
-                              bool flat, bool compress, bool zeroed_grain,
-                              Error **errp)
+                              bool flat, bool compress, bool zeroed_grain)
 {
    int ret, i;
-    BlockDriverState *bs = NULL;
+    int fd = 0;
    VMDK4Header header;
-    Error *local_err;
-    uint32_t tmp, magic, grains, gd_sectors, gt_size, gt_count;
-    uint32_t *gd_buf = NULL;
-    int gd_buf_size;
+    uint32_t tmp, magic, grains, gd_size, gt_size, gt_count;

-    ret = bdrv_create_file(filename, NULL, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto exit;
+    fd = qemu_open(filename,
+                   O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
+                   0644);
+    if (fd < 0) {
+        return -errno;
    }
-
-    assert(bs == NULL);
-    ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
-                    NULL, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto exit;
-    }
-
    if (flat) {
-        ret = bdrv_truncate(bs, filesize);
+        ret = ftruncate(fd, filesize);
        if (ret < 0) {
-            error_setg_errno(errp, -ret, "Could not truncate file");
+            ret = -errno;
        }
        goto exit;
    }
@@ -1553,23 +1462,24 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
                   | (compress ? VMDK4_FLAG_COMPRESS | VMDK4_FLAG_MARKER : 0)
                   | (zeroed_grain ? VMDK4_FLAG_ZERO_GRAIN : 0);
    header.compressAlgorithm = compress ? VMDK4_COMPRESSION_DEFLATE : 0;
-    header.capacity = filesize / BDRV_SECTOR_SIZE;
+    header.capacity = filesize / 512;
    header.granularity = 128;
-    header.num_gtes_per_gt = BDRV_SECTOR_SIZE;
+    header.num_gtes_per_gt = 512;

-    grains = DIV_ROUND_UP(filesize / BDRV_SECTOR_SIZE, header.granularity);
-    gt_size = DIV_ROUND_UP(header.num_gtes_per_gt * sizeof(uint32_t),
-                           BDRV_SECTOR_SIZE);
-    gt_count = DIV_ROUND_UP(grains, header.num_gtes_per_gt);
-    gd_sectors = DIV_ROUND_UP(gt_count * sizeof(uint32_t), BDRV_SECTOR_SIZE);
+    grains = (filesize / 512 + header.granularity - 1) / header.granularity;
+    gt_size = ((header.num_gtes_per_gt * sizeof(uint32_t)) + 511) >> 9;
+    gt_count =
+        (grains + header.num_gtes_per_gt - 1) / header.num_gtes_per_gt;
+    gd_size = (gt_count * sizeof(uint32_t) + 511) >> 9;

    header.desc_offset = 1;
    header.desc_size = 20;
    header.rgd_offset = header.desc_offset + header.desc_size;
-    header.gd_offset = header.rgd_offset + gd_sectors + (gt_size * gt_count);
+    header.gd_offset = header.rgd_offset + gd_size + (gt_size * gt_count);
    header.grain_offset =
-        ROUND_UP(header.gd_offset + gd_sectors + (gt_size * gt_count),
-                 header.granularity);
+       ((header.gd_offset + gd_size + (gt_size * gt_count) +
+         header.granularity - 1) / header.granularity) *
+        header.granularity;
    /* swap endianness for all header fields */
    header.version = cpu_to_le32(header.version);
    header.flags = cpu_to_le32(header.flags);
@@ -1589,55 +1499,48 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
    header.check_bytes[3] = 0xa;

    /* write all the data */
-    ret = bdrv_pwrite(bs, 0, &magic, sizeof(magic));
-    if (ret < 0) {
-        error_set(errp, QERR_IO_ERROR);
+    ret = qemu_write_full(fd, &magic, sizeof(magic));
+    if (ret != sizeof(magic)) {
+        ret = -errno;
        goto exit;
    }
-    ret = bdrv_pwrite(bs, sizeof(magic), &header, sizeof(header));
-    if (ret < 0) {
-        error_set(errp, QERR_IO_ERROR);
+    ret = qemu_write_full(fd, &header, sizeof(header));
+    if (ret != sizeof(header)) {
+        ret = -errno;
        goto exit;
    }

-    ret = bdrv_truncate(bs, le64_to_cpu(header.grain_offset) << 9);
+    ret = ftruncate(fd, le64_to_cpu(header.grain_offset) << 9);
    if (ret < 0) {
-        error_setg_errno(errp, -ret, "Could not truncate file");
+        ret = -errno;
        goto exit;
    }

    /* write grain directory */
-    gd_buf_size = gd_sectors * BDRV_SECTOR_SIZE;
-    gd_buf = g_malloc0(gd_buf_size);
-    for (i = 0, tmp = le64_to_cpu(header.rgd_offset) + gd_sectors;
+    lseek(fd, le64_to_cpu(header.rgd_offset) << 9, SEEK_SET);
+    for (i = 0, tmp = le64_to_cpu(header.rgd_offset) + gd_size;
         i < gt_count; i++, tmp += gt_size) {
-        gd_buf[i] = cpu_to_le32(tmp);
-    }
-    ret = bdrv_pwrite(bs, le64_to_cpu(header.rgd_offset) * BDRV_SECTOR_SIZE,
-                      gd_buf, gd_buf_size);
-    if (ret < 0) {
-        error_set(errp, QERR_IO_ERROR);
-        goto exit;
+        ret = qemu_write_full(fd, &tmp, sizeof(tmp));
+        if (ret != sizeof(tmp)) {
+            ret = -errno;
+            goto exit;
+        }
    }

    /* write backup grain directory */
-    for (i = 0, tmp = le64_to_cpu(header.gd_offset) + gd_sectors;
+    lseek(fd, le64_to_cpu(header.gd_offset) << 9, SEEK_SET);
+    for (i = 0, tmp = le64_to_cpu(header.gd_offset) + gd_size;
         i < gt_count; i++, tmp += gt_size) {
-        gd_buf[i] = cpu_to_le32(tmp);
-    }
-    ret = bdrv_pwrite(bs, le64_to_cpu(header.gd_offset) * BDRV_SECTOR_SIZE,
-                      gd_buf, gd_buf_size);
-    if (ret < 0) {
-        error_set(errp, QERR_IO_ERROR);
-        goto exit;
+        ret = qemu_write_full(fd, &tmp, sizeof(tmp));
+        if (ret != sizeof(tmp)) {
+            ret = -errno;
+            goto exit;
+        }
    }

    ret = 0;
-exit:
-    if (bs) {
-        bdrv_unref(bs);
-    }
-    g_free(gd_buf);
+ exit:
+    qemu_close(fd);
    return ret;
 }

@@ -1684,10 +1587,8 @@ static int filename_decompose(const char *filename, char *path, char *prefix,
 static int vmdk_create(const char *filename, QEMUOptionParameter *options,
                       Error **errp)
 {
-    int idx = 0;
-    BlockDriverState *new_bs = NULL;
-    Error *local_err;
-    char *desc = NULL;
+    int fd, idx = 0;
+    char desc[BUF_SIZE];
    int64_t total_size = 0, filesize;
    const char *adapter_type = NULL;
    const char *backing_file = NULL;
@@ -1695,7 +1596,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
    int flags = 0;
    int ret = 0;
    bool flat, split, compress;
-    GString *ext_desc_lines;
+    char ext_desc_lines[BUF_SIZE] = "";
    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;
@@ -1703,7 +1604,6 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
    uint32_t parent_cid = 0xffffffff;
    uint32_t number_heads = 16;
    bool zeroed_grain = false;
-    uint32_t desc_offset = 0, desc_len;
    const char desc_template[] =
        "# Disk DescriptorFile\n"
        "version=1\n"
@@ -1724,11 +1624,8 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
        "ddb.geometry.sectors = \"63\"\n"
        "ddb.adapterType = \"%s\"\n";

-    ext_desc_lines = g_string_new(NULL);
-
    if (filename_decompose(filename, path, prefix, postfix, PATH_MAX, errp)) {
-        ret = -EINVAL;
-        goto exit;
+        return -EINVAL;
    }
    /* Read out options */
    while (options && options->name) {
@@ -1754,8 +1651,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
               strcmp(adapter_type, "lsilogic") &&
               strcmp(adapter_type, "legacyESX")) {
        error_setg(errp, "Unknown adapter type: '%s'", adapter_type);
-        ret = -EINVAL;
-        goto exit;
+        return -EINVAL;
    }
    if (strcmp(adapter_type, "ide") != 0) {
        /* that's the number of heads with which vmware operates when
@@ -1771,8 +1667,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
               strcmp(fmt, "twoGbMaxExtentFlat") &&
               strcmp(fmt, "streamOptimized")) {
        error_setg(errp, "Unknown subformat: '%s'", fmt);
-        ret = -EINVAL;
-        goto exit;
+        return -EINVAL;
    }
    split = !(strcmp(fmt, "twoGbMaxExtentFlat") &&
              strcmp(fmt, "twoGbMaxExtentSparse"));
@@ -1786,25 +1681,22 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
    }
    if (flat && backing_file) {
        error_setg(errp, "Flat image can't have backing file");
-        ret = -ENOTSUP;
-        goto exit;
+        return -ENOTSUP;
    }
    if (flat && zeroed_grain) {
        error_setg(errp, "Flat image can't enable zeroed grain");
-        ret = -ENOTSUP;
-        goto exit;
+        return -ENOTSUP;
    }
    if (backing_file) {
-        BlockDriverState *bs = NULL;
-        ret = bdrv_open(&bs, backing_file, NULL, NULL, BDRV_O_NO_BACKING, NULL,
-                        errp);
+        BlockDriverState *bs = bdrv_new("");
+        ret = bdrv_open(bs, backing_file, NULL, BDRV_O_NO_BACKING, NULL, errp);
        if (ret != 0) {
-            goto exit;
+            bdrv_unref(bs);
+            return ret;
        }
        if (strcmp(bs->drv->format_name, "vmdk")) {
            bdrv_unref(bs);
-            ret = -EINVAL;
-            goto exit;
+            return -EINVAL;
        }
        parent_cid = vmdk_read_cid(bs, 0);
        bdrv_unref(bs);
@@ -1837,66 +1729,51 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
                path, desc_filename);

        if (vmdk_create_extent(ext_filename, size,
-                               flat, compress, zeroed_grain, errp)) {
-            ret = -EINVAL;
-            goto exit;
+                               flat, compress, zeroed_grain)) {
+            return -EINVAL;
        }
        filesize -= size;

        /* Format description line */
        snprintf(desc_line, sizeof(desc_line),
-                    desc_extent_line, size / BDRV_SECTOR_SIZE, desc_filename);
-        g_string_append(ext_desc_lines, desc_line);
+                    desc_extent_line, size / 512, desc_filename);
+        pstrcat(ext_desc_lines, sizeof(ext_desc_lines), desc_line);
    }
    /* generate descriptor file */
-    desc = g_strdup_printf(desc_template,
-                           (unsigned int)time(NULL),
-                           parent_cid,
-                           fmt,
-                           parent_desc_line,
-                           ext_desc_lines->str,
-                           (flags & BLOCK_FLAG_COMPAT6 ? 6 : 4),
-                           total_size /
-                               (int64_t)(63 * number_heads * BDRV_SECTOR_SIZE),
-                           number_heads,
-                           adapter_type);
-    desc_len = strlen(desc);
-    /* the descriptor offset = 0x200 */
-    if (!split && !flat) {
-        desc_offset = 0x200;
+    snprintf(desc, sizeof(desc), desc_template,
+            (unsigned int)time(NULL),
+            parent_cid,
+            fmt,
+            parent_desc_line,
+            ext_desc_lines,
+            (flags & BLOCK_FLAG_COMPAT6 ? 6 : 4),
+            total_size / (int64_t)(63 * number_heads * 512), number_heads,
+                adapter_type);
+    if (split || flat) {
+        fd = qemu_open(filename,
+                       O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
+                       0644);
    } else {
-        ret = bdrv_create_file(filename, options, &local_err);
-        if (ret < 0) {
-            error_setg_errno(errp, -ret, "Could not create image file");
-            goto exit;
-        }
+        fd = qemu_open(filename,
+                       O_WRONLY | O_BINARY | O_LARGEFILE,
+                       0644);
    }
-    assert(new_bs == NULL);
-    ret = bdrv_open(&new_bs, filename, NULL, NULL,
-                    BDRV_O_RDWR | BDRV_O_PROTOCOL, NULL, &local_err);
-    if (ret < 0) {
-        error_setg_errno(errp, -ret, "Could not write description");
+    if (fd < 0) {
+        return -errno;
+    }
+    /* the descriptor offset = 0x200 */
+    if (!split && !flat && 0x200 != lseek(fd, 0x200, SEEK_SET)) {
+        ret = -errno;
        goto exit;
    }
-    ret = bdrv_pwrite(new_bs, desc_offset, desc, desc_len);
-    if (ret < 0) {
-        error_setg_errno(errp, -ret, "Could not write description");
+    ret = qemu_write_full(fd, desc, strlen(desc));
+    if (ret != strlen(desc)) {
+        ret = -errno;
        goto exit;
    }
-    /* bdrv_pwrite write padding zeros to align to sector, we don't need that
-     * for description file */
-    if (desc_offset == 0) {
-        ret = bdrv_truncate(new_bs, desc_len);
-        if (ret < 0) {
-            error_setg_errno(errp, -ret, "Could not truncate file");
-        }
-    }
+    ret = 0;
 exit:
-    if (new_bs) {
-        bdrv_unref(new_bs);
-    }
-    g_free(desc);
-    g_string_free(ext_desc_lines, true);
+    qemu_close(fd);
    return ret;
 }

@@ -1984,53 +1861,6 @@ static ImageInfo *vmdk_get_extent_info(VmdkExtent *extent)
    return info;
 }

-static int vmdk_check(BlockDriverState *bs, BdrvCheckResult *result,
-                      BdrvCheckMode fix)
-{
-    BDRVVmdkState *s = bs->opaque;
-    VmdkExtent *extent = NULL;
-    int64_t sector_num = 0;
-    int64_t total_sectors = bdrv_getlength(bs) / BDRV_SECTOR_SIZE;
-    int ret;
-    uint64_t cluster_offset;
-
-    if (fix) {
-        return -ENOTSUP;
-    }
-
-    for (;;) {
-        if (sector_num >= total_sectors) {
-            return 0;
-        }
-        extent = find_extent(s, sector_num, extent);
-        if (!extent) {
-            fprintf(stderr,
-                    "ERROR: could not find extent for sector %" PRId64 "\n",
-                    sector_num);
-            break;
-        }
-        ret = get_cluster_offset(bs, extent, NULL,
-                                 sector_num << BDRV_SECTOR_BITS,
-                                 0, &cluster_offset);
-        if (ret == VMDK_ERROR) {
-            fprintf(stderr,
-                    "ERROR: could not get cluster_offset for sector %"
-                    PRId64 "\n", sector_num);
-            break;
-        }
-        if (ret == VMDK_OK && cluster_offset >= bdrv_getlength(extent->file)) {
-            fprintf(stderr,
-                    "ERROR: cluster offset for sector %"
-                    PRId64 " points after EOF\n", sector_num);
-            break;
-        }
-        sector_num += extent->cluster_sectors;
-    }
-
-    result->corruptions++;
-    return 0;
-}
-
 static ImageInfoSpecific *vmdk_get_specific_info(BlockDriverState *bs)
 {
    int i;
@@ -2104,7 +1934,6 @@ static BlockDriver bdrv_vmdk = {
    .instance_size                = sizeof(BDRVVmdkState),
    .bdrv_probe                   = vmdk_probe,
    .bdrv_open                    = vmdk_open,
-    .bdrv_check                   = vmdk_check,
    .bdrv_reopen_prepare          = vmdk_reopen_prepare,
    .bdrv_read                    = vmdk_co_read,
    .bdrv_write                   = vmdk_co_write,
@@ -2116,7 +1945,6 @@ static BlockDriver bdrv_vmdk = {
    .bdrv_get_allocated_file_size = vmdk_get_allocated_file_size,
    .bdrv_has_zero_init           = vmdk_has_zero_init,
    .bdrv_get_specific_info       = vmdk_get_specific_info,
-    .bdrv_refresh_limits          = vmdk_refresh_limits,

    .create_options               = vmdk_create_options,
 };
@@ -193,8 +193,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
            goto fail;
        }
        if (strncmp(footer->creator, "conectix", 8)) {
-            error_setg(errp, "invalid VPC image");
-            ret = -EINVAL;
+            ret = -EMEDIUMTYPE;
            goto fail;
        }
        disk_type = VHD_FIXED;
@@ -480,19 +479,6 @@ fail:
    return -1;
 }

-static int vpc_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
-{
-    BDRVVPCState *s = (BDRVVPCState *)bs->opaque;
-    VHDFooter *footer = (VHDFooter *) s->footer_buf;
-
-    if (cpu_to_be32(footer->type) != VHD_FIXED) {
-        bdi->cluster_size = s->block_size;
-    }
-
-    bdi->unallocated_blocks_are_zero = true;
-    return 0;
-}
-
 static int vpc_read(BlockDriverState *bs, int64_t sector_num,
                    uint8_t *buf, int nb_sectors)
 {
@@ -895,8 +881,6 @@ static BlockDriver bdrv_vpc = {
    .bdrv_read              = vpc_co_read,
    .bdrv_write             = vpc_co_write,

-    .bdrv_get_info          = vpc_get_info,
-
    .create_options         = vpc_create_options,
    .bdrv_has_zero_init     = vpc_has_zero_init,
 };
@@ -266,7 +266,8 @@ typedef struct mbr_t {
 } QEMU_PACKED mbr_t;

 typedef struct direntry_t {
-    uint8_t name[8 + 3];
+    uint8_t name[8];
+    uint8_t extension[3];
    uint8_t attributes;
    uint8_t reserved[2];
    uint16_t ctime;
@@ -517,9 +518,11 @@ static inline uint8_t fat_chksum(const direntry_t* entry)
    uint8_t chksum=0;
    int i;

-    for (i = 0; i < ARRAY_SIZE(entry->name); i++) {
-        chksum = (((chksum & 0xfe) >> 1) |
-                  ((chksum & 0x01) ? 0x80 : 0)) + entry->name[i];
+    for(i=0;i<11;i++) {
+        unsigned char c;
+
+        c = (i < 8) ? entry->name[i] : entry->extension[i-8];
+        chksum=(((chksum&0xfe)>>1)|((chksum&0x01)?0x80:0)) + c;
    }

    return chksum;
@@ -614,7 +617,7 @@ static inline direntry_t* create_short_and_long_name(BDRVVVFATState* s,

    if(is_dot) {
 	entry=array_get_next(&(s->directory));
-        memset(entry->name, 0x20, sizeof(entry->name));
+	memset(entry->name,0x20,11);
 	memcpy(entry->name,filename,strlen(filename));
 	return entry;
    }
@@ -629,14 +632,12 @@ static inline direntry_t* create_short_and_long_name(BDRVVVFATState* s,
 	i = 8;

    entry=array_get_next(&(s->directory));
-    memset(entry->name, 0x20, sizeof(entry->name));
+    memset(entry->name,0x20,11);
    memcpy(entry->name, filename, i);

-    if (j > 0) {
-        for (i = 0; i < 3 && filename[j + 1 + i]; i++) {
-            entry->name[8 + i] = filename[j + 1 + i];
-        }
-    }
+    if(j > 0)
+	for (i = 0; i < 3 && filename[j+1+i]; i++)
+	    entry->extension[i] = filename[j+1+i];

    /* upcase & remove unwanted characters */
    for(i=10;i>=0;i--) {
@@ -862,7 +863,8 @@ static int init_directories(BDRVVVFATState* s,
    {
 	direntry_t* entry=array_get_next(&(s->directory));
 	entry->attributes=0x28; /* archive | volume label */
-        memcpy(entry->name, "QEMU VVFAT ", sizeof(entry->name));
+	memcpy(entry->name,"QEMU VVF",8);
+	memcpy(entry->extension,"AT ",3);
    }

    /* Now build FAT, and write back information into directory */
@@ -1085,17 +1087,19 @@ DLOG(if (stderr == NULL) {
    setbuf(stderr, NULL);
 })

-    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
+    opts = qemu_opts_create_nofail(&runtime_opts);
    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
+    if (error_is_set(&local_err)) {
+        qerror_report_err(local_err);
+        error_free(local_err);
        ret = -EINVAL;
        goto fail;
    }

    dirname = qemu_opt_get(opts, "dir");
    if (!dirname) {
-        error_setg(errp, "vvfat block driver requires a 'dir' option");
+        qerror_report(ERROR_CLASS_GENERIC_ERROR, "vvfat block driver requires "
+                      "a 'dir' option");
        ret = -EINVAL;
        goto fail;
    }
@@ -1121,7 +1125,6 @@ DLOG(if (stderr == NULL) {
        if (!s->fat_type) {
            s->fat_type = 16;
        }
-        s->first_sectors_number = 0x40;
        cyls = s->fat_type == 12 ? 64 : 1024;
        heads = 16;
        secs = 63;
@@ -1136,7 +1139,8 @@ DLOG(if (stderr == NULL) {
    case 12:
        break;
    default:
-        error_setg(errp, "Valid FAT types are only 12, 16 and 32");
+        qerror_report(ERROR_CLASS_GENERIC_ERROR, "Valid FAT types are only "
+                      "12, 16 and 32");
        ret = -EINVAL;
        goto fail;
    }
@@ -1149,6 +1153,7 @@ DLOG(if (stderr == NULL) {

    s->current_cluster=0xffffffff;

+    s->first_sectors_number=0x40;
    /* read only is the default for safety */
    bs->read_only = 1;
    s->qcow = s->write_target = NULL;
@@ -1588,20 +1593,17 @@ static int parse_short_name(BDRVVVFATState* s,
 	    lfn->name[i] = direntry->name[i];
    }

-    for (j = 2; j >= 0 && direntry->name[8 + j] == ' '; j--) {
-    }
+    for (j = 2; j >= 0 && direntry->extension[j] == ' '; j--);
    if (j >= 0) {
 	lfn->name[i++] = '.';
 	lfn->name[i + j + 1] = '\0';
 	for (;j >= 0; j--) {
-            uint8_t c = direntry->name[8 + j];
-            if (c <= ' ' || c > 0x7f) {
-                return -2;
-            } else if (s->downcase_short_names) {
-                lfn->name[i + j] = qemu_tolower(c);
-            } else {
-                lfn->name[i + j] = c;
-            }
+	    if (direntry->extension[j] <= ' ' || direntry->extension[j] > 0x7f)
+		return -2;
+	    else if (s->downcase_short_names)
+		lfn->name[i + j] = qemu_tolower(direntry->extension[j]);
+	    else
+		lfn->name[i + j] = direntry->extension[j];
 	}
    } else
 	lfn->name[i + j + 1] = '\0';
@@ -2935,13 +2937,15 @@ static int enable_write_target(BDRVVVFATState *s)
        goto err;
    }

-    s->qcow = NULL;
-    ret = bdrv_open(&s->qcow, s->qcow_filename, NULL, NULL,
+    s->qcow = bdrv_new("");
+
+    ret = bdrv_open(s->qcow, s->qcow_filename, NULL,
            BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH, bdrv_qcow,
            &local_err);
    if (ret < 0) {
        qerror_report_err(local_err);
        error_free(local_err);
+        bdrv_unref(s->qcow);
        goto err;
    }

@@ -307,10 +307,12 @@ static bool check_throttle_config(ThrottleConfig *cfg, Error **errp)
 typedef enum { MEDIA_DISK, MEDIA_CDROM } DriveMediaType;

 /* Takes the ownership of bs_opts */
-static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
+static DriveInfo *blockdev_init(QDict *bs_opts,
+                                BlockInterfaceType type,
                                Error **errp)
 {
    const char *buf;
+    const char *file = NULL;
    const char *serial;
    int ro = 0;
    int bdrv_flags = 0;
@@ -330,13 +332,13 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
     * stay in bs_opts for processing by bdrv_open(). */
    id = qdict_get_try_str(bs_opts, "id");
    opts = qemu_opts_create(&qemu_common_drive_opts, id, 1, &error);
-    if (error) {
+    if (error_is_set(&error)) {
        error_propagate(errp, error);
        goto err_no_opts;
    }

    qemu_opts_absorb_qdict(opts, bs_opts, &error);
-    if (error) {
+    if (error_is_set(&error)) {
        error_propagate(errp, error);
        goto early_err;
    }
@@ -352,6 +354,7 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
    ro = qemu_opt_get_bool(opts, "read-only", 0);
    copy_on_read = qemu_opt_get_bool(opts, "copy-on-read", false);

+    file = qemu_opt_get(opts, "file");
    serial = qemu_opt_get(opts, "serial");

    if ((buf = qemu_opt_get(opts, "discard")) != NULL) {
@@ -436,8 +439,13 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,

    on_write_error = BLOCKDEV_ON_ERROR_ENOSPC;
    if ((buf = qemu_opt_get(opts, "werror")) != NULL) {
+        if (type != IF_IDE && type != IF_SCSI && type != IF_VIRTIO && type != IF_NONE) {
+            error_setg(errp, "werror is not supported by this bus type");
+            goto early_err;
+        }
+
        on_write_error = parse_block_error_action(buf, 0, &error);
-        if (error) {
+        if (error_is_set(&error)) {
            error_propagate(errp, error);
            goto early_err;
        }
@@ -445,25 +453,25 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,

    on_read_error = BLOCKDEV_ON_ERROR_REPORT;
    if ((buf = qemu_opt_get(opts, "rerror")) != NULL) {
+        if (type != IF_IDE && type != IF_VIRTIO && type != IF_SCSI && type != IF_NONE) {
+            error_report("rerror is not supported by this bus type");
+            goto early_err;
+        }
+
        on_read_error = parse_block_error_action(buf, 1, &error);
-        if (error) {
+        if (error_is_set(&error)) {
            error_propagate(errp, error);
            goto early_err;
        }
    }

-    if (bdrv_find_node(qemu_opts_id(opts))) {
-        error_setg(errp, "device id=%s is conflicting with a node-name",
-                   qemu_opts_id(opts));
-        goto early_err;
-    }
-
    /* init */
    dinfo = g_malloc0(sizeof(*dinfo));
    dinfo->id = g_strdup(qemu_opts_id(opts));
    dinfo->bdrv = bdrv_new(dinfo->id);
    dinfo->bdrv->open_flags = snapshot ? BDRV_O_SNAPSHOT : 0;
    dinfo->bdrv->read_only = ro;
+    dinfo->type = type;
    dinfo->refcount = 1;
    if (serial != NULL) {
        dinfo->serial = g_strdup(serial);
@@ -504,7 +512,7 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
    bdrv_flags |= ro ? 0 : BDRV_O_RDWR;

    QINCREF(bs_opts);
-    ret = bdrv_open(&dinfo->bdrv, file, NULL, bs_opts, bdrv_flags, drv, &error);
+    ret = bdrv_open(dinfo->bdrv, file, bs_opts, bdrv_flags, drv, &error);

    if (ret < 0) {
        error_setg(errp, "could not open disk image %s: %s",
@@ -592,10 +600,6 @@ QemuOptsList qemu_legacy_drive_opts = {
            .name = "addr",
            .type = QEMU_OPT_STRING,
            .help = "pci address (virtio only)",
-        },{
-            .name = "file",
-            .type = QEMU_OPT_STRING,
-            .help = "file name",
        },

        /* Options that are passed on, but have special semantics with -drive */
@@ -603,14 +607,6 @@ QemuOptsList qemu_legacy_drive_opts = {
            .name = "read-only",
            .type = QEMU_OPT_BOOL,
            .help = "open drive file as read-only",
-        },{
-            .name = "rerror",
-            .type = QEMU_OPT_STRING,
-            .help = "read error action",
-        },{
-            .name = "werror",
-            .type = QEMU_OPT_STRING,
-            .help = "write error action",
        },{
            .name = "copy-on-read",
            .type = QEMU_OPT_BOOL,
@@ -632,10 +628,8 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
    int cyls, heads, secs, translation;
    int max_devs, bus_id, unit_id, index;
    const char *devaddr;
-    const char *werror, *rerror;
    bool read_only = false;
    bool copy_on_read;
-    const char *filename;
    Error *local_err = NULL;

    /* Change legacy command line options into QMP ones */
@@ -689,10 +683,9 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
    bs_opts = qdict_new();
    qemu_opts_to_qdict(all_opts, bs_opts);

-    legacy_opts = qemu_opts_create(&qemu_legacy_drive_opts, NULL, 0,
-                                   &error_abort);
+    legacy_opts = qemu_opts_create_nofail(&qemu_legacy_drive_opts);
    qemu_opts_absorb_qdict(legacy_opts, bs_opts, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        qerror_report_err(local_err);
        error_free(local_err);
        goto fail;
@@ -780,10 +773,6 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
            translation = BIOS_ATA_TRANSLATION_NONE;
        } else if (!strcmp(value, "lba")) {
            translation = BIOS_ATA_TRANSLATION_LBA;
-        } else if (!strcmp(value, "large")) {
-            translation = BIOS_ATA_TRANSLATION_LARGE;
-        } else if (!strcmp(value, "rechs")) {
-            translation = BIOS_ATA_TRANSLATION_RECHS;
        } else if (!strcmp(value, "auto")) {
            translation = BIOS_ATA_TRANSLATION_AUTO;
        } else {
@@ -865,8 +854,7 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)

    if (type == IF_VIRTIO) {
        QemuOpts *devopts;
-        devopts = qemu_opts_create(qemu_find_opts("device"), NULL, 0,
-                                   &error_abort);
+        devopts = qemu_opts_create_nofail(qemu_find_opts("device"));
        if (arch_type == QEMU_ARCH_S390X) {
            qemu_opt_set(devopts, "driver", "virtio-blk-s390");
        } else {
@@ -878,40 +866,17 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
        }
    }

-    filename = qemu_opt_get(legacy_opts, "file");
-
-    /* Check werror/rerror compatibility with if=... */
-    werror = qemu_opt_get(legacy_opts, "werror");
-    if (werror != NULL) {
-        if (type != IF_IDE && type != IF_SCSI && type != IF_VIRTIO &&
-            type != IF_NONE) {
-            error_report("werror is not supported by this bus type");
-            goto fail;
-        }
-        qdict_put(bs_opts, "werror", qstring_from_str(werror));
-    }
-
-    rerror = qemu_opt_get(legacy_opts, "rerror");
-    if (rerror != NULL) {
-        if (type != IF_IDE && type != IF_VIRTIO && type != IF_SCSI &&
-            type != IF_NONE) {
-            error_report("rerror is not supported by this bus type");
-            goto fail;
-        }
-        qdict_put(bs_opts, "rerror", qstring_from_str(rerror));
-    }
-
    /* Actual block device init: Functionality shared with blockdev-add */
-    dinfo = blockdev_init(filename, bs_opts, &local_err);
+    dinfo = blockdev_init(bs_opts, type, &local_err);
    bs_opts = NULL;
    if (dinfo == NULL) {
-        if (local_err) {
+        if (error_is_set(&local_err)) {
            qerror_report_err(local_err);
            error_free(local_err);
        }
        goto fail;
    } else {
-        assert(!local_err);
+        assert(!error_is_set(&local_err));
    }

    /* Set legacy DriveInfo fields */
@@ -923,7 +888,6 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
    dinfo->secs = secs;
    dinfo->trans = translation;

-    dinfo->type = type;
    dinfo->bus = bus_id;
    dinfo->unit = unit_id;
    dinfo->devaddr = devaddr;
@@ -979,22 +943,14 @@ static void blockdev_do_action(int kind, void *data, Error **errp)
    qmp_transaction(&list, errp);
 }

-void qmp_blockdev_snapshot_sync(bool has_device, const char *device,
-                                bool has_node_name, const char *node_name,
-                                const char *snapshot_file,
-                                bool has_snapshot_node_name,
-                                const char *snapshot_node_name,
+void qmp_blockdev_snapshot_sync(const char *device, const char *snapshot_file,
                                bool has_format, const char *format,
-                                bool has_mode, NewImageMode mode, Error **errp)
+                                bool has_mode, enum NewImageMode mode,
+                                Error **errp)
 {
    BlockdevSnapshot snapshot = {
-        .has_device = has_device,
        .device = (char *) device,
-        .has_node_name = has_node_name,
-        .node_name = (char *) node_name,
        .snapshot_file = (char *) snapshot_file,
-        .has_snapshot_node_name = has_snapshot_node_name,
-        .snapshot_node_name = (char *) snapshot_node_name,
        .has_format = has_format,
        .format = (char *) format,
        .has_mode = has_mode,
@@ -1049,7 +1005,7 @@ SnapshotInfo *qmp_blockdev_snapshot_delete_internal_sync(const char *device,
    }

    ret = bdrv_snapshot_find_by_id_and_name(bs, id, name, &sn, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
        return NULL;
    }
@@ -1062,7 +1018,7 @@ SnapshotInfo *qmp_blockdev_snapshot_delete_internal_sync(const char *device,
    }

    bdrv_snapshot_delete(bs, id, name, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
        return NULL;
    }
@@ -1232,14 +1188,8 @@ static void external_snapshot_prepare(BlkTransactionState *common,
 {
    BlockDriver *drv;
    int flags, ret;
-    QDict *options = NULL;
    Error *local_err = NULL;
-    bool has_device = false;
    const char *device;
-    bool has_node_name = false;
-    const char *node_name;
-    bool has_snapshot_node_name = false;
-    const char *snapshot_node_name;
    const char *new_image_file;
    const char *format = "qcow2";
    enum NewImageMode mode = NEW_IMAGE_MODE_ABSOLUTE_PATHS;
@@ -1250,14 +1200,7 @@ static void external_snapshot_prepare(BlkTransactionState *common,
    /* get parameters */
    g_assert(action->kind == TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_SYNC);

-    has_device = action->blockdev_snapshot_sync->has_device;
    device = action->blockdev_snapshot_sync->device;
-    has_node_name = action->blockdev_snapshot_sync->has_node_name;
-    node_name = action->blockdev_snapshot_sync->node_name;
-    has_snapshot_node_name =
-        action->blockdev_snapshot_sync->has_snapshot_node_name;
-    snapshot_node_name = action->blockdev_snapshot_sync->snapshot_node_name;
-
    new_image_file = action->blockdev_snapshot_sync->snapshot_file;
    if (action->blockdev_snapshot_sync->has_format) {
        format = action->blockdev_snapshot_sync->format;
@@ -1273,21 +1216,9 @@ static void external_snapshot_prepare(BlkTransactionState *common,
        return;
    }

-    state->old_bs = bdrv_lookup_bs(has_device ? device : NULL,
-                                   has_node_name ? node_name : NULL,
-                                   &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        return;
-    }
-
-    if (has_node_name && !has_snapshot_node_name) {
-        error_setg(errp, "New snapshot node name missing");
-        return;
-    }
-
-    if (has_snapshot_node_name && bdrv_find_node(snapshot_node_name)) {
-        error_setg(errp, "New snapshot node name already existing");
+    state->old_bs = bdrv_find(device);
+    if (!state->old_bs) {
+        error_set(errp, QERR_DEVICE_NOT_FOUND, device);
        return;
    }

@@ -1308,7 +1239,7 @@ static void external_snapshot_prepare(BlkTransactionState *common,
        }
    }

-    if (!bdrv_is_first_non_filter(state->old_bs)) {
+    if (bdrv_check_ext_snapshot(state->old_bs) != EXT_SNAPSHOT_ALLOWED) {
        error_set(errp, QERR_FEATURE_DISABLED, "snapshot");
        return;
    }
@@ -1321,24 +1252,18 @@ static void external_snapshot_prepare(BlkTransactionState *common,
                        state->old_bs->filename,
                        state->old_bs->drv->format_name,
                        NULL, -1, flags, &local_err, false);
-        if (local_err) {
+        if (error_is_set(&local_err)) {
            error_propagate(errp, local_err);
            return;
        }
    }

-    if (has_snapshot_node_name) {
-        options = qdict_new();
-        qdict_put(options, "node-name",
-                  qstring_from_str(snapshot_node_name));
-    }
-
+    /* We will manually add the backing_hd field to the bs later */
+    state->new_bs = bdrv_new("");
    /* TODO Inherit bs->options or only take explicit options with an
     * extended QMP command? */
-    assert(state->new_bs == NULL);
-    ret = bdrv_open(&state->new_bs, new_image_file, NULL, options,
+    ret = bdrv_open(state->new_bs, new_image_file, NULL,
                    flags | BDRV_O_NO_BACKING, drv, &local_err);
-    /* We will manually add the backing_hd field to the bs later */
    if (ret != 0) {
        error_propagate(errp, local_err);
    }
@@ -1390,7 +1315,7 @@ static void drive_backup_prepare(BlkTransactionState *common, Error **errp)
                     backup->has_on_source_error, backup->on_source_error,
                     backup->has_on_target_error, backup->on_target_error,
                     &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
        state->bs = NULL;
        state->job = NULL;
@@ -1482,7 +1407,7 @@ void qmp_transaction(TransactionActionList *dev_list, Error **errp)
        QSIMPLEQ_INSERT_TAIL(&snap_bdrv_states, state, entry);

        state->ops->prepare(state, &local_err);
-        if (local_err) {
+        if (error_is_set(&local_err)) {
            error_propagate(errp, local_err);
            goto delete_and_fail;
        }
@@ -1552,19 +1477,14 @@ void qmp_eject(const char *device, bool has_force, bool force, Error **errp)
    eject_device(bs, force, errp);
 }

-void qmp_block_passwd(bool has_device, const char *device,
-                      bool has_node_name, const char *node_name,
-                      const char *password, Error **errp)
+void qmp_block_passwd(const char *device, const char *password, Error **errp)
 {
-    Error *local_err = NULL;
    BlockDriverState *bs;
    int err;

-    bs = bdrv_lookup_bs(has_device ? device : NULL,
-                        has_node_name ? node_name : NULL,
-                        &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
+    bs = bdrv_find(device);
+    if (!bs) {
+        error_set(errp, QERR_DEVICE_NOT_FOUND, device);
        return;
    }

@@ -1585,7 +1505,7 @@ static void qmp_bdrv_open_encrypted(BlockDriverState *bs, const char *filename,
    Error *local_err = NULL;
    int ret;

-    ret = bdrv_open(&bs, filename, NULL, NULL, bdrv_flags, drv, &local_err);
+    ret = bdrv_open(bs, filename, NULL, bdrv_flags, drv, &local_err);
    if (ret < 0) {
        error_propagate(errp, local_err);
        return;
@@ -1606,7 +1526,7 @@ static void qmp_bdrv_open_encrypted(BlockDriverState *bs, const char *filename,
 }

 void qmp_change_blockdev(const char *device, const char *filename,
-                         const char *format, Error **errp)
+                         bool has_format, const char *format, Error **errp)
 {
    BlockDriverState *bs;
    BlockDriver *drv = NULL;
@@ -1628,7 +1548,7 @@ void qmp_change_blockdev(const char *device, const char *filename,
    }

    eject_device(bs, 0, &err);
-    if (err) {
+    if (error_is_set(&err)) {
        error_propagate(errp, err);
        return;
    }
@@ -1754,24 +1674,14 @@ int do_drive_del(Monitor *mon, const QDict *qdict, QObject **ret_data)
    return 0;
 }

-void qmp_block_resize(bool has_device, const char *device,
-                      bool has_node_name, const char *node_name,
-                      int64_t size, Error **errp)
+void qmp_block_resize(const char *device, int64_t size, Error **errp)
 {
-    Error *local_err = NULL;
    BlockDriverState *bs;
    int ret;

-    bs = bdrv_lookup_bs(has_device ? device : NULL,
-                        has_node_name ? node_name : NULL,
-                        &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        return;
-    }
-
-    if (!bdrv_is_first_non_filter(bs)) {
-        error_set(errp, QERR_FEATURE_DISABLED, "resize");
+    bs = bdrv_find(device);
+    if (!bs) {
+        error_set(errp, QERR_DEVICE_NOT_FOUND, device);
        return;
    }

@@ -1858,7 +1768,7 @@ void qmp_block_stream(const char *device, bool has_base,

    stream_start(bs, base_bs, base, has_speed ? speed : 0,
                 on_error, block_job_cb, bs, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
        return;
    }
@@ -1867,8 +1777,7 @@ void qmp_block_stream(const char *device, bool has_base,
 }

 void qmp_block_commit(const char *device,
-                      bool has_base, const char *base,
-                      bool has_top, const char *top,
+                      bool has_base, const char *base, const char *top,
                      bool has_speed, int64_t speed,
                      Error **errp)
 {
@@ -1887,11 +1796,6 @@ void qmp_block_commit(const char *device,
    /* drain all i/o before commits */
    bdrv_drain_all();

-    /* Important Note:
-     *  libvirt relies on the DeviceNotFound error class in order to probe for
-     *  live commit feature versions; for this to work, we must make sure to
-     *  perform the device lookup before any generic errors that may occur in a
-     *  scenario in which all optional arguments are omitted. */
    bs = bdrv_find(device);
    if (!bs) {
        error_set(errp, QERR_DEVICE_NOT_FOUND, device);
@@ -1901,7 +1805,7 @@ void qmp_block_commit(const char *device,
    /* default top_bs is the active layer */
    top_bs = bs;

-    if (has_top && top) {
+    if (top) {
        if (strcmp(bs->filename, top) != 0) {
            top_bs = bdrv_find_backing_image(bs, top);
        }
@@ -1923,19 +1827,8 @@ void qmp_block_commit(const char *device,
        return;
    }

-    /* Do not allow attempts to commit an image into itself */
-    if (top_bs == base_bs) {
-        error_setg(errp, "cannot commit an image into itself");
-        return;
-    }
-
-    if (top_bs == bs) {
-        commit_active_start(bs, base_bs, speed, on_error, block_job_cb,
-                            bs, &local_err);
-    } else {
-        commit_start(bs, base_bs, top_bs, speed, on_error, block_job_cb, bs,
-                    &local_err);
-    }
+    commit_start(bs, base_bs, top_bs, speed, on_error, block_job_cb, bs,
+                &local_err);
    if (local_err != NULL) {
        error_propagate(errp, local_err);
        return;
@@ -2032,14 +1925,15 @@ void qmp_drive_backup(const char *device, const char *target,
        }
    }

-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
        return;
    }

-    target_bs = NULL;
-    ret = bdrv_open(&target_bs, target, NULL, NULL, flags, drv, &local_err);
+    target_bs = bdrv_new("");
+    ret = bdrv_open(target_bs, target, NULL, flags, drv, &local_err);
    if (ret < 0) {
+        bdrv_unref(target_bs);
        error_propagate(errp, local_err);
        return;
    }
@@ -2053,11 +1947,6 @@ void qmp_drive_backup(const char *device, const char *target,
    }
 }

-BlockDeviceInfoList *qmp_query_named_block_nodes(Error **errp)
-{
-    return bdrv_named_nodes_list();
-}
-
 #define DEFAULT_MIRROR_BUF_SIZE   (10 << 20)

 void qmp_drive_mirror(const char *device, const char *target,
@@ -2172,7 +2061,7 @@ void qmp_drive_mirror(const char *device, const char *target,
        }
    }

-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
        return;
    }
@@ -2180,10 +2069,11 @@ void qmp_drive_mirror(const char *device, const char *target,
    /* Mirroring takes care of copy-on-write using the source's backing
     * file.
     */
-    target_bs = NULL;
-    ret = bdrv_open(&target_bs, target, NULL, NULL, flags | BDRV_O_NO_BACKING,
-                    drv, &local_err);
+    target_bs = bdrv_new("");
+    ret = bdrv_open(target_bs, target, NULL, flags | BDRV_O_NO_BACKING, drv,
+                    &local_err);
    if (ret < 0) {
+        bdrv_unref(target_bs);
        error_propagate(errp, local_err);
        return;
    }
@@ -2285,7 +2175,6 @@ void qmp_block_job_complete(const char *device, Error **errp)
 void qmp_blockdev_add(BlockdevOptions *options, Error **errp)
 {
    QmpOutputVisitor *ov = qmp_output_visitor_new();
-    DriveInfo *dinfo;
    QObject *obj;
    QDict *qdict;
    Error *local_err = NULL;
@@ -2302,10 +2191,8 @@ void qmp_blockdev_add(BlockdevOptions *options, Error **errp)
     *
     * For now, simply forbidding the combination for all drivers will do. */
    if (options->has_aio && options->aio == BLOCKDEV_AIO_OPTIONS_NATIVE) {
-        bool direct = options->has_cache &&
-                      options->cache->has_direct &&
-                      options->cache->direct;
-        if (!direct) {
+        bool direct = options->cache->has_direct && options->cache->direct;
+        if (!options->has_cache && !direct) {
            error_setg(errp, "aio=native requires cache.direct=true");
            goto fail;
        }
@@ -2313,7 +2200,7 @@ void qmp_blockdev_add(BlockdevOptions *options, Error **errp)

    visit_type_BlockdevOptions(qmp_output_get_visitor(ov),
                               &options, NULL, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
        goto fail;
    }
@@ -2323,18 +2210,12 @@ void qmp_blockdev_add(BlockdevOptions *options, Error **errp)

    qdict_flatten(qdict);

-    dinfo = blockdev_init(NULL, qdict, &local_err);
-    if (local_err) {
+    blockdev_init(qdict, IF_NONE, &local_err);
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
        goto fail;
    }

-    if (bdrv_key_required(dinfo->bdrv)) {
-        drive_uninit(dinfo);
-        error_setg(errp, "blockdev-add doesn't support encrypted devices");
-        goto fail;
-    }
-
 fail:
    qmp_output_visitor_cleanup(ov);
 }
@@ -2369,6 +2250,10 @@ QemuOptsList qemu_common_drive_opts = {
            .name = "snapshot",
            .type = QEMU_OPT_BOOL,
            .help = "enable/disable snapshot mode",
+        },{
+            .name = "file",
+            .type = QEMU_OPT_STRING,
+            .help = "disk image",
        },{
            .name = "discard",
            .type = QEMU_OPT_STRING,
@@ -61,7 +61,7 @@ void *block_job_create(const BlockJobDriver *driver, BlockDriverState *bs,
        Error *local_err = NULL;

        block_job_set_speed(job, speed, &local_err);
-        if (local_err) {
+        if (error_is_set(&local_err)) {
            bs->job = NULL;
            g_free(job);
            bdrv_set_in_use(bs, 0);
@@ -92,7 +92,7 @@ void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)
        return;
    }
    job->driver->set_speed(job, speed, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
        return;
    }
@@ -206,20 +206,6 @@ void block_job_sleep_ns(BlockJob *job, QEMUClockType type, int64_t ns)
    job->busy = true;
 }

-void block_job_yield(BlockJob *job)
-{
-    assert(job->busy);
-
-    /* Check cancellation *before* setting busy = false, too!  */
-    if (block_job_is_cancelled(job)) {
-        return;
-    }
-
-    job->busy = false;
-    qemu_coroutine_yield();
-    job->busy = true;
-}
-
 BlockJobInfo *block_job_query(BlockJob *job)
 {
    BlockJobInfo *info = g_new0(BlockJobInfo, 1);
@@ -1000,7 +1000,7 @@ int main(int argc, char **argv)
    memset(ts, 0, sizeof(TaskState));
    init_task_state(ts);
    ts->info = info;
-    cpu->opaque = ts;
+    env->opaque = ts;

 #if defined(TARGET_I386)
    cpu_x86_set_cpl(env, 3);
@@ -23,22 +23,29 @@
 #include "qemu/atomic.h"
 #include "sysemu/qtest.h"

-void cpu_loop_exit(CPUState *cpu)
+bool qemu_cpu_has_work(CPUState *cpu)
 {
+    return cpu_has_work(cpu);
+}
+
+void cpu_loop_exit(CPUArchState *env)
+{
+    CPUState *cpu = ENV_GET_CPU(env);
+
    cpu->current_tb = NULL;
-    siglongjmp(cpu->jmp_env, 1);
+    siglongjmp(env->jmp_env, 1);
 }

 /* exit the current TB from a signal handler. The host registers are
   restored in a state compatible with the CPU emulator
 */
 #if defined(CONFIG_SOFTMMU)
-void cpu_resume_from_signal(CPUState *cpu, void *puc)
+void cpu_resume_from_signal(CPUArchState *env, void *puc)
 {
    /* XXX: restore cpu registers saved in host registers */

-    cpu->exception_index = -1;
-    siglongjmp(cpu->jmp_env, 1);
+    env->exception_index = -1;
+    siglongjmp(env->jmp_env, 1);
 }
 #endif

@@ -46,25 +53,7 @@ void cpu_resume_from_signal(CPUState *cpu, void *puc)
 static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, uint8_t *tb_ptr)
 {
    CPUArchState *env = cpu->env_ptr;
-    uintptr_t next_tb;
-
-#if defined(DEBUG_DISAS)
-    if (qemu_loglevel_mask(CPU_LOG_TB_CPU)) {
-#if defined(TARGET_I386)
-        log_cpu_state(cpu, CPU_DUMP_CCOP);
-#elif defined(TARGET_M68K)
-        /* ??? Should not modify env state for dumping.  */
-        cpu_m68k_flush_flags(env, env->cc_op);
-        env->cc_op = CC_OP_FLAGS;
-        env->sr = (env->sr & 0xffe0) | env->cc_dest | (env->cc_x << 4);
-        log_cpu_state(cpu, 0);
-#else
-        log_cpu_state(cpu, 0);
-#endif
-    }
-#endif /* DEBUG_DISAS */
-
-    next_tb = tcg_qemu_tb_exec(env, tb_ptr);
+    uintptr_t next_tb = tcg_qemu_tb_exec(env, tb_ptr);
    if ((next_tb & TB_EXIT_MASK) > TB_EXIT_IDX1) {
        /* We didn't start executing this TB (eg because the instruction
         * counter hit zero); we must restore the guest PC to the address
@@ -101,7 +90,7 @@ static void cpu_exec_nocache(CPUArchState *env, int max_cycles,
    if (max_cycles > CF_COUNT_MASK)
        max_cycles = CF_COUNT_MASK;

-    tb = tb_gen_code(cpu, orig_tb->pc, orig_tb->cs_base, orig_tb->flags,
+    tb = tb_gen_code(env, orig_tb->pc, orig_tb->cs_base, orig_tb->flags,
                     max_cycles);
    cpu->current_tb = tb;
    /* execute the generated code */
@@ -116,7 +105,6 @@ static TranslationBlock *tb_find_slow(CPUArchState *env,
                                      target_ulong cs_base,
                                      uint64_t flags)
 {
-    CPUState *cpu = ENV_GET_CPU(env);
    TranslationBlock *tb, **ptb1;
    unsigned int h;
    tb_page_addr_t phys_pc, phys_page1;
@@ -154,7 +142,7 @@ static TranslationBlock *tb_find_slow(CPUArchState *env,
    }
 not_found:
   /* if no translated code available, then translate it now */
-    tb = tb_gen_code(cpu, pc, cs_base, flags, 0);
+    tb = tb_gen_code(env, pc, cs_base, flags, 0);

 found:
    /* Move the last found TB to the head of the list */
@@ -164,13 +152,12 @@ static TranslationBlock *tb_find_slow(CPUArchState *env,
        tcg_ctx.tb_ctx.tb_phys_hash[h] = tb;
    }
    /* we add the TB in the virtual pc hash table */
-    cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)] = tb;
+    env->tb_jmp_cache[tb_jmp_cache_hash_func(pc)] = tb;
    return tb;
 }

 static inline TranslationBlock *tb_find_fast(CPUArchState *env)
 {
-    CPUState *cpu = ENV_GET_CPU(env);
    TranslationBlock *tb;
    target_ulong cs_base, pc;
    int flags;
@@ -179,7 +166,7 @@ static inline TranslationBlock *tb_find_fast(CPUArchState *env)
       always be the same before a given translated block
       is executed. */
    cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
-    tb = cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)];
+    tb = env->tb_jmp_cache[tb_jmp_cache_hash_func(pc)];
    if (unlikely(!tb || tb->pc != pc || tb->cs_base != cs_base ||
                 tb->flags != flags)) {
        tb = tb_find_slow(env, pc, cs_base, flags);
@@ -196,11 +183,10 @@ void cpu_set_debug_excp_handler(CPUDebugExcpHandler *handler)

 static void cpu_handle_debug_exception(CPUArchState *env)
 {
-    CPUState *cpu = ENV_GET_CPU(env);
    CPUWatchpoint *wp;

-    if (!cpu->watchpoint_hit) {
-        QTAILQ_FOREACH(wp, &cpu->watchpoints, entry) {
+    if (!env->watchpoint_hit) {
+        QTAILQ_FOREACH(wp, &env->watchpoints, entry) {
            wp->flags &= ~BP_WATCHPOINT_HIT;
        }
    }
@@ -219,16 +205,11 @@ int cpu_exec(CPUArchState *env)
 #if !(defined(CONFIG_USER_ONLY) && \
      (defined(TARGET_M68K) || defined(TARGET_PPC) || defined(TARGET_S390X)))
    CPUClass *cc = CPU_GET_CLASS(cpu);
-#endif
-#ifdef TARGET_I386
-    X86CPU *x86_cpu = X86_CPU(cpu);
 #endif
    int ret, interrupt_request;
    TranslationBlock *tb;
    uint8_t *tc_ptr;
    uintptr_t next_tb;
-    /* This must be volatile so it is not trashed by longjmp() */
-    volatile bool have_tb_lock = false;

    if (cpu->halted) {
        if (!cpu_has_work(cpu)) {
@@ -281,16 +262,16 @@ int cpu_exec(CPUArchState *env)
 #else
 #error unsupported target CPU
 #endif
-    cpu->exception_index = -1;
+    env->exception_index = -1;

    /* prepare setjmp context for exception handling */
    for(;;) {
-        if (sigsetjmp(cpu->jmp_env, 0) == 0) {
+        if (sigsetjmp(env->jmp_env, 0) == 0) {
            /* if an exception is pending, we execute it here */
-            if (cpu->exception_index >= 0) {
-                if (cpu->exception_index >= EXCP_INTERRUPT) {
+            if (env->exception_index >= 0) {
+                if (env->exception_index >= EXCP_INTERRUPT) {
                    /* exit request from the cpu execution loop */
-                    ret = cpu->exception_index;
+                    ret = env->exception_index;
                    if (ret == EXCP_DEBUG) {
                        cpu_handle_debug_exception(env);
                    }
@@ -303,11 +284,11 @@ int cpu_exec(CPUArchState *env)
 #if defined(TARGET_I386)
                    cc->do_interrupt(cpu);
 #endif
-                    ret = cpu->exception_index;
+                    ret = env->exception_index;
                    break;
 #else
                    cc->do_interrupt(cpu);
-                    cpu->exception_index = -1;
+                    env->exception_index = -1;
 #endif
                }
            }
@@ -322,8 +303,8 @@ int cpu_exec(CPUArchState *env)
                    }
                    if (interrupt_request & CPU_INTERRUPT_DEBUG) {
                        cpu->interrupt_request &= ~CPU_INTERRUPT_DEBUG;
-                        cpu->exception_index = EXCP_DEBUG;
-                        cpu_loop_exit(cpu);
+                        env->exception_index = EXCP_DEBUG;
+                        cpu_loop_exit(env);
                    }
 #if defined(TARGET_ARM) || defined(TARGET_SPARC) || defined(TARGET_MIPS) || \
    defined(TARGET_PPC) || defined(TARGET_ALPHA) || defined(TARGET_CRIS) || \
@@ -331,32 +312,32 @@ int cpu_exec(CPUArchState *env)
                    if (interrupt_request & CPU_INTERRUPT_HALT) {
                        cpu->interrupt_request &= ~CPU_INTERRUPT_HALT;
                        cpu->halted = 1;
-                        cpu->exception_index = EXCP_HLT;
-                        cpu_loop_exit(cpu);
+                        env->exception_index = EXCP_HLT;
+                        cpu_loop_exit(env);
                    }
 #endif
 #if defined(TARGET_I386)
 #if !defined(CONFIG_USER_ONLY)
                    if (interrupt_request & CPU_INTERRUPT_POLL) {
                        cpu->interrupt_request &= ~CPU_INTERRUPT_POLL;
-                        apic_poll_irq(x86_cpu->apic_state);
+                        apic_poll_irq(env->apic_state);
                    }
 #endif
                    if (interrupt_request & CPU_INTERRUPT_INIT) {
                            cpu_svm_check_intercept_param(env, SVM_EXIT_INIT,
                                                          0);
-                            do_cpu_init(x86_cpu);
-                            cpu->exception_index = EXCP_HALTED;
-                            cpu_loop_exit(cpu);
+                            do_cpu_init(x86_env_get_cpu(env));
+                            env->exception_index = EXCP_HALTED;
+                            cpu_loop_exit(env);
                    } else if (interrupt_request & CPU_INTERRUPT_SIPI) {
-                            do_cpu_sipi(x86_cpu);
+                            do_cpu_sipi(x86_env_get_cpu(env));
                    } else if (env->hflags2 & HF2_GIF_MASK) {
                        if ((interrupt_request & CPU_INTERRUPT_SMI) &&
                            !(env->hflags & HF_SMM_MASK)) {
                            cpu_svm_check_intercept_param(env, SVM_EXIT_SMI,
                                                          0);
                            cpu->interrupt_request &= ~CPU_INTERRUPT_SMI;
-                            do_smm_enter(x86_cpu);
+                            do_smm_enter(x86_env_get_cpu(env));
                            next_tb = 0;
                        } else if ((interrupt_request & CPU_INTERRUPT_NMI) &&
                                   !(env->hflags2 & HF2_NMI_MASK)) {
@@ -393,10 +374,7 @@ int cpu_exec(CPUArchState *env)
                            /* FIXME: this should respect TPR */
                            cpu_svm_check_intercept_param(env, SVM_EXIT_VINTR,
                                                          0);
-                            intno = ldl_phys(cpu->as,
-                                             env->vm_vmcb
-                                             + offsetof(struct vmcb,
-                                                        control.int_vector));
+                            intno = ldl_phys(env->vm_vmcb + offsetof(struct vmcb, control.int_vector));
                            qemu_log_mask(CPU_LOG_TB_IN_ASM, "Servicing virtual hardware INT=0x%02x\n", intno);
                            do_interrupt_x86_hardirq(env, intno, 1);
                            cpu->interrupt_request &= ~CPU_INTERRUPT_VIRQ;
@@ -418,7 +396,7 @@ int cpu_exec(CPUArchState *env)
 #elif defined(TARGET_LM32)
                    if ((interrupt_request & CPU_INTERRUPT_HARD)
                        && (env->ie & IE_IE)) {
-                        cpu->exception_index = EXCP_IRQ;
+                        env->exception_index = EXCP_IRQ;
                        cc->do_interrupt(cpu);
                        next_tb = 0;
                    }
@@ -427,7 +405,7 @@ int cpu_exec(CPUArchState *env)
                        && (env->sregs[SR_MSR] & MSR_IE)
                        && !(env->sregs[SR_MSR] & (MSR_EIP | MSR_BIP))
                        && !(env->iflags & (D_FLAG | IMM_FLAG))) {
-                        cpu->exception_index = EXCP_IRQ;
+                        env->exception_index = EXCP_IRQ;
                        cc->do_interrupt(cpu);
                        next_tb = 0;
                    }
@@ -435,7 +413,7 @@ int cpu_exec(CPUArchState *env)
                    if ((interrupt_request & CPU_INTERRUPT_HARD) &&
                        cpu_mips_hw_interrupts_pending(env)) {
                        /* Raise it */
-                        cpu->exception_index = EXCP_EXT_INTERRUPT;
+                        env->exception_index = EXCP_EXT_INTERRUPT;
                        env->error_code = 0;
                        cc->do_interrupt(cpu);
                        next_tb = 0;
@@ -452,7 +430,7 @@ int cpu_exec(CPUArchState *env)
                            idx = EXCP_TICK;
                        }
                        if (idx >= 0) {
-                            cpu->exception_index = idx;
+                            env->exception_index = idx;
                            cc->do_interrupt(cpu);
                            next_tb = 0;
                        }
@@ -467,7 +445,7 @@ int cpu_exec(CPUArchState *env)
                            if (((type == TT_EXTINT) &&
                                  cpu_pil_allowed(env, pil)) ||
                                  type != TT_EXTINT) {
-                                cpu->exception_index = env->interrupt_index;
+                                env->exception_index = env->interrupt_index;
                                cc->do_interrupt(cpu);
                                next_tb = 0;
                            }
@@ -475,8 +453,8 @@ int cpu_exec(CPUArchState *env)
                    }
 #elif defined(TARGET_ARM)
                    if (interrupt_request & CPU_INTERRUPT_FIQ
-                        && !(env->daif & PSTATE_F)) {
-                        cpu->exception_index = EXCP_FIQ;
+                        && !(env->uncached_cpsr & CPSR_F)) {
+                        env->exception_index = EXCP_FIQ;
                        cc->do_interrupt(cpu);
                        next_tb = 0;
                    }
@@ -491,15 +469,15 @@ int cpu_exec(CPUArchState *env)
                       pc contains a magic address.  */
                    if (interrupt_request & CPU_INTERRUPT_HARD
                        && ((IS_M(env) && env->regs[15] < 0xfffffff0)
-                            || !(env->daif & PSTATE_I))) {
-                        cpu->exception_index = EXCP_IRQ;
+                            || !(env->uncached_cpsr & CPSR_I))) {
+                        env->exception_index = EXCP_IRQ;
                        cc->do_interrupt(cpu);
                        next_tb = 0;
                    }
 #elif defined(TARGET_UNICORE32)
                    if (interrupt_request & CPU_INTERRUPT_HARD
                        && !(env->uncached_asr & ASR_I)) {
-                        cpu->exception_index = UC32_EXCP_INTR;
+                        env->exception_index = UC32_EXCP_INTR;
                        cc->do_interrupt(cpu);
                        next_tb = 0;
                    }
@@ -534,7 +512,7 @@ int cpu_exec(CPUArchState *env)
                            }
                        }
                        if (idx >= 0) {
-                            cpu->exception_index = idx;
+                            env->exception_index = idx;
                            env->error_code = 0;
                            cc->do_interrupt(cpu);
                            next_tb = 0;
@@ -544,7 +522,7 @@ int cpu_exec(CPUArchState *env)
                    if (interrupt_request & CPU_INTERRUPT_HARD
                        && (env->pregs[PR_CCS] & I_FLAG)
                        && !env->locked_irq) {
-                        cpu->exception_index = EXCP_IRQ;
+                        env->exception_index = EXCP_IRQ;
                        cc->do_interrupt(cpu);
                        next_tb = 0;
                    }
@@ -556,7 +534,7 @@ int cpu_exec(CPUArchState *env)
                            m_flag_archval = M_FLAG_V32;
                        }
                        if ((env->pregs[PR_CCS] & m_flag_archval)) {
-                            cpu->exception_index = EXCP_NMI;
+                            env->exception_index = EXCP_NMI;
                            cc->do_interrupt(cpu);
                            next_tb = 0;
                        }
@@ -570,7 +548,7 @@ int cpu_exec(CPUArchState *env)
                           hardware doesn't rely on this, so we
                           provide/save the vector when the interrupt is
                           first signalled.  */
-                        cpu->exception_index = env->pending_vector;
+                        env->exception_index = env->pending_vector;
                        do_interrupt_m68k_hardirq(env);
                        next_tb = 0;
                    }
@@ -582,7 +560,7 @@ int cpu_exec(CPUArchState *env)
                    }
 #elif defined(TARGET_XTENSA)
                    if (interrupt_request & CPU_INTERRUPT_HARD) {
-                        cpu->exception_index = EXC_IRQ;
+                        env->exception_index = EXC_IRQ;
                        cc->do_interrupt(cpu);
                        next_tb = 0;
                    }
@@ -598,11 +576,26 @@ int cpu_exec(CPUArchState *env)
                }
                if (unlikely(cpu->exit_request)) {
                    cpu->exit_request = 0;
-                    cpu->exception_index = EXCP_INTERRUPT;
-                    cpu_loop_exit(cpu);
+                    env->exception_index = EXCP_INTERRUPT;
+                    cpu_loop_exit(env);
                }
+#if defined(DEBUG_DISAS)
+                if (qemu_loglevel_mask(CPU_LOG_TB_CPU)) {
+                    /* restore flags in standard format */
+#if defined(TARGET_I386)
+                    log_cpu_state(cpu, CPU_DUMP_CCOP);
+#elif defined(TARGET_M68K)
+                    cpu_m68k_flush_flags(env, env->cc_op);
+                    env->cc_op = CC_OP_FLAGS;
+                    env->sr = (env->sr & 0xffe0)
+                              | env->cc_dest | (env->cc_x << 4);
+                    log_cpu_state(cpu, 0);
+#else
+                    log_cpu_state(cpu, 0);
+#endif
+                }
+#endif /* DEBUG_DISAS */
                spin_lock(&tcg_ctx.tb_ctx.tb_lock);
-                have_tb_lock = true;
                tb = tb_find_fast(env);
                /* Note: we do it here to avoid a gcc bug on Mac OS X when
                   doing it in tb_find_slow */
@@ -624,7 +617,6 @@ int cpu_exec(CPUArchState *env)
                    tb_add_jump((TranslationBlock *)(next_tb & ~TB_EXIT_MASK),
                                next_tb & TB_EXIT_MASK, tb);
                }
-                have_tb_lock = false;
                spin_unlock(&tcg_ctx.tb_ctx.tb_lock);

                /* cpu_interrupt might be called while translating the
@@ -654,25 +646,25 @@ int cpu_exec(CPUArchState *env)
                        /* Instruction counter expired.  */
                        int insns_left;
                        tb = (TranslationBlock *)(next_tb & ~TB_EXIT_MASK);
-                        insns_left = cpu->icount_decr.u32;
-                        if (cpu->icount_extra && insns_left >= 0) {
+                        insns_left = env->icount_decr.u32;
+                        if (env->icount_extra && insns_left >= 0) {
                            /* Refill decrementer and continue execution.  */
-                            cpu->icount_extra += insns_left;
-                            if (cpu->icount_extra > 0xffff) {
+                            env->icount_extra += insns_left;
+                            if (env->icount_extra > 0xffff) {
                                insns_left = 0xffff;
                            } else {
-                                insns_left = cpu->icount_extra;
+                                insns_left = env->icount_extra;
                            }
-                            cpu->icount_extra -= insns_left;
-                            cpu->icount_decr.u16.low = insns_left;
+                            env->icount_extra -= insns_left;
+                            env->icount_decr.u16.low = insns_left;
                        } else {
                            if (insns_left > 0) {
                                /* Execute remaining instructions.  */
                                cpu_exec_nocache(env, insns_left, tb);
                            }
-                            cpu->exception_index = EXCP_INTERRUPT;
+                            env->exception_index = EXCP_INTERRUPT;
                            next_tb = 0;
-                            cpu_loop_exit(cpu);
+                            cpu_loop_exit(env);
                        }
                        break;
                    }
@@ -693,13 +685,6 @@ int cpu_exec(CPUArchState *env)
      (defined(TARGET_M68K) || defined(TARGET_PPC) || defined(TARGET_S390X)))
            cc = CPU_GET_CLASS(cpu);
 #endif
-#ifdef TARGET_I386
-            x86_cpu = X86_CPU(cpu);
-#endif
-            if (have_tb_lock) {
-                spin_unlock(&tcg_ctx.tb_ctx.tb_lock);
-                have_tb_lock = false;
-            }
        }
    } /* for(;;) */

@@ -76,7 +76,7 @@ static bool cpu_thread_is_idle(CPUState *cpu)
    if (cpu_is_stopped(cpu)) {
        return true;
    }
-    if (!cpu->halted || cpu_has_work(cpu) ||
+    if (!cpu->halted || qemu_cpu_has_work(cpu) ||
        kvm_halt_in_kernel()) {
        return false;
    }
@@ -139,10 +139,11 @@ static int64_t cpu_get_icount_locked(void)

    icount = qemu_icount;
    if (cpu) {
-        if (!cpu_can_do_io(cpu)) {
+        CPUArchState *env = cpu->env_ptr;
+        if (!can_do_io(env)) {
            fprintf(stderr, "Bad clock read\n");
        }
-        icount -= (cpu->icount_decr.u16.low + cpu->icount_extra);
+        icount -= (env->icount_decr.u16.low + env->icount_extra);
    }
    return qemu_icount_bias + (icount << icount_time_shift);
 }
@@ -1116,25 +1117,16 @@ void resume_all_vcpus(void)
    }
 }

-/* For temporary buffers for forming a name */
-#define VCPU_THREAD_NAME_SIZE 16
-
 static void qemu_tcg_init_vcpu(CPUState *cpu)
 {
-    char thread_name[VCPU_THREAD_NAME_SIZE];
-
-    tcg_cpu_address_space_init(cpu, cpu->as);
-
    /* share a single thread for all cpus with TCG */
    if (!tcg_cpu_thread) {
        cpu->thread = g_malloc0(sizeof(QemuThread));
        cpu->halt_cond = g_malloc0(sizeof(QemuCond));
        qemu_cond_init(cpu->halt_cond);
        tcg_halt_cond = cpu->halt_cond;
-        snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/TCG",
-                 cpu->cpu_index);
-        qemu_thread_create(cpu->thread, thread_name, qemu_tcg_cpu_thread_fn,
-                           cpu, QEMU_THREAD_JOINABLE);
+        qemu_thread_create(cpu->thread, qemu_tcg_cpu_thread_fn, cpu,
+                           QEMU_THREAD_JOINABLE);
 #ifdef _WIN32
        cpu->hThread = qemu_thread_get_handle(cpu->thread);
 #endif
@@ -1150,15 +1142,11 @@ static void qemu_tcg_init_vcpu(CPUState *cpu)

 static void qemu_kvm_start_vcpu(CPUState *cpu)
 {
-    char thread_name[VCPU_THREAD_NAME_SIZE];
-
    cpu->thread = g_malloc0(sizeof(QemuThread));
    cpu->halt_cond = g_malloc0(sizeof(QemuCond));
    qemu_cond_init(cpu->halt_cond);
-    snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/KVM",
-             cpu->cpu_index);
-    qemu_thread_create(cpu->thread, thread_name, qemu_kvm_cpu_thread_fn,
-                       cpu, QEMU_THREAD_JOINABLE);
+    qemu_thread_create(cpu->thread, qemu_kvm_cpu_thread_fn, cpu,
+                       QEMU_THREAD_JOINABLE);
    while (!cpu->created) {
        qemu_cond_wait(&qemu_cpu_cond, &qemu_global_mutex);
    }
@@ -1166,14 +1154,10 @@ static void qemu_kvm_start_vcpu(CPUState *cpu)

 static void qemu_dummy_start_vcpu(CPUState *cpu)
 {
-    char thread_name[VCPU_THREAD_NAME_SIZE];
-
    cpu->thread = g_malloc0(sizeof(QemuThread));
    cpu->halt_cond = g_malloc0(sizeof(QemuCond));
    qemu_cond_init(cpu->halt_cond);
-    snprintf(thread_name, VCPU_THREAD_NAME_SIZE, "CPU %d/DUMMY",
-             cpu->cpu_index);
-    qemu_thread_create(cpu->thread, thread_name, qemu_dummy_cpu_thread_fn, cpu,
+    qemu_thread_create(cpu->thread, qemu_dummy_cpu_thread_fn, cpu,
                       QEMU_THREAD_JOINABLE);
    while (!cpu->created) {
        qemu_cond_wait(&qemu_cpu_cond, &qemu_global_mutex);
@@ -1235,7 +1219,6 @@ int vm_stop_force_state(RunState state)

 static int tcg_cpu_exec(CPUArchState *env)
 {
-    CPUState *cpu = ENV_GET_CPU(env);
    int ret;
 #ifdef CONFIG_PROFILER
    int64_t ti;
@@ -1248,9 +1231,9 @@ static int tcg_cpu_exec(CPUArchState *env)
        int64_t count;
        int64_t deadline;
        int decr;
-        qemu_icount -= (cpu->icount_decr.u16.low + cpu->icount_extra);
-        cpu->icount_decr.u16.low = 0;
-        cpu->icount_extra = 0;
+        qemu_icount -= (env->icount_decr.u16.low + env->icount_extra);
+        env->icount_decr.u16.low = 0;
+        env->icount_extra = 0;
        deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL);

        /* Maintain prior (possibly buggy) behaviour where if no deadline
@@ -1266,8 +1249,8 @@ static int tcg_cpu_exec(CPUArchState *env)
        qemu_icount += count;
        decr = (count > 0xffff) ? 0xffff : count;
        count -= decr;
-        cpu->icount_decr.u16.low = decr;
-        cpu->icount_extra = count;
+        env->icount_decr.u16.low = decr;
+        env->icount_extra = count;
    }
    ret = cpu_exec(env);
 #ifdef CONFIG_PROFILER
@@ -1276,9 +1259,10 @@ static int tcg_cpu_exec(CPUArchState *env)
    if (use_icount) {
        /* Fold pending instructions back into the
           instruction counter, and clear the interrupt flag.  */
-        qemu_icount -= (cpu->icount_decr.u16.low + cpu->icount_extra);
-        cpu->icount_decr.u32 = 0;
-        cpu->icount_extra = 0;
+        qemu_icount -= (env->icount_decr.u16.low
+                        + env->icount_extra);
+        env->icount_decr.u32 = 0;
+        env->icount_extra = 0;
    }
    return ret;
 }
@@ -1474,11 +1458,12 @@ void qmp_inject_nmi(Error **errp)

    CPU_FOREACH(cs) {
        X86CPU *cpu = X86_CPU(cs);
+        CPUX86State *env = &cpu->env;

-        if (!cpu->apic_state) {
+        if (!env->apic_state) {
            cpu_interrupt(cs, CPU_INTERRUPT_NMI);
        } else {
-            apic_deliver_nmi(cpu->apic_state);
+            apic_deliver_nmi(env->apic_state);
        }
    }
 #elif defined(TARGET_S390X)
@@ -26,7 +26,6 @@
 #include "exec/cputlb.h"

 #include "exec/memory-internal.h"
-#include "exec/ram_addr.h"

 //#define DEBUG_TLB
 //#define DEBUG_TLB_CHECK
@@ -34,6 +33,13 @@
 /* statistics */
 int tlb_flush_count;

+static const CPUTLBEntry s_cputlb_empty_entry = {
+    .addr_read  = -1,
+    .addr_write = -1,
+    .addr_code  = -1,
+    .addend     = -1,
+};
+
 /* NOTE:
 * If flush_global is true (the usual case), flush all tlb entries.
 * If flush_global is false, flush (at least) all tlb entries not
@@ -46,9 +52,10 @@ int tlb_flush_count;
 * entries from the TLB at any time, so flushing more entries than
 * required is only an efficiency issue, not a correctness issue.
 */
-void tlb_flush(CPUState *cpu, int flush_global)
+void tlb_flush(CPUArchState *env, int flush_global)
 {
-    CPUArchState *env = cpu->env_ptr;
+    CPUState *cpu = ENV_GET_CPU(env);
+    int i;

 #if defined(DEBUG_TLB)
    printf("tlb_flush:\n");
@@ -57,8 +64,15 @@ void tlb_flush(CPUState *cpu, int flush_global)
       links while we are modifying them */
    cpu->current_tb = NULL;

-    memset(env->tlb_table, -1, sizeof(env->tlb_table));
-    memset(cpu->tb_jmp_cache, 0, sizeof(cpu->tb_jmp_cache));
+    for (i = 0; i < CPU_TLB_SIZE; i++) {
+        int mmu_idx;
+
+        for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
+            env->tlb_table[mmu_idx][i] = s_cputlb_empty_entry;
+        }
+    }
+
+    memset(env->tb_jmp_cache, 0, TB_JMP_CACHE_SIZE * sizeof (void *));

    env->tlb_flush_addr = -1;
    env->tlb_flush_mask = 0;
@@ -73,13 +87,13 @@ static inline void tlb_flush_entry(CPUTLBEntry *tlb_entry, target_ulong addr)
                 (TARGET_PAGE_MASK | TLB_INVALID_MASK)) ||
        addr == (tlb_entry->addr_code &
                 (TARGET_PAGE_MASK | TLB_INVALID_MASK))) {
-        memset(tlb_entry, -1, sizeof(*tlb_entry));
+        *tlb_entry = s_cputlb_empty_entry;
    }
 }

-void tlb_flush_page(CPUState *cpu, target_ulong addr)
+void tlb_flush_page(CPUArchState *env, target_ulong addr)
 {
-    CPUArchState *env = cpu->env_ptr;
+    CPUState *cpu = ENV_GET_CPU(env);
    int i;
    int mmu_idx;

@@ -93,7 +107,7 @@ void tlb_flush_page(CPUState *cpu, target_ulong addr)
               TARGET_FMT_lx "/" TARGET_FMT_lx ")\n",
               env->tlb_flush_addr, env->tlb_flush_mask);
 #endif
-        tlb_flush(cpu, 1);
+        tlb_flush(env, 1);
        return;
    }
    /* must reset current TB so that interrupts cannot modify the
@@ -106,23 +120,24 @@ void tlb_flush_page(CPUState *cpu, target_ulong addr)
        tlb_flush_entry(&env->tlb_table[mmu_idx][i], addr);
    }

-    tb_flush_jmp_cache(cpu, addr);
+    tb_flush_jmp_cache(env, addr);
 }

 /* update the TLBs so that writes to code in the virtual page 'addr'
   can be detected */
 void tlb_protect_code(ram_addr_t ram_addr)
 {
-    cpu_physical_memory_reset_dirty(ram_addr, TARGET_PAGE_SIZE,
-                                    DIRTY_MEMORY_CODE);
+    cpu_physical_memory_reset_dirty(ram_addr,
+                                    ram_addr + TARGET_PAGE_SIZE,
+                                    CODE_DIRTY_FLAG);
 }

 /* update the TLB so that writes in physical page 'phys_addr' are no longer
   tested for self modifying code */
-void tlb_unprotect_code_phys(CPUState *cpu, ram_addr_t ram_addr,
+void tlb_unprotect_code_phys(CPUArchState *env, ram_addr_t ram_addr,
                             target_ulong vaddr)
 {
-    cpu_physical_memory_set_dirty_flag(ram_addr, DIRTY_MEMORY_CODE);
+    cpu_physical_memory_set_dirty_flags(ram_addr, CODE_DIRTY_FLAG);
 }

 static bool tlb_is_dirty_ram(CPUTLBEntry *tlbe)
@@ -221,11 +236,10 @@ static void tlb_add_large_page(CPUArchState *env, target_ulong vaddr,
 /* Add a new TLB entry. At most one entry for a given virtual address
   is permitted. Only a single TARGET_PAGE_SIZE region is mapped, the
   supplied size is only used by tlb_flush_page.  */
-void tlb_set_page(CPUState *cpu, target_ulong vaddr,
+void tlb_set_page(CPUArchState *env, target_ulong vaddr,
                  hwaddr paddr, int prot,
                  int mmu_idx, target_ulong size)
 {
-    CPUArchState *env = cpu->env_ptr;
    MemoryRegionSection *section;
    unsigned int index;
    target_ulong address;
@@ -240,7 +254,7 @@ void tlb_set_page(CPUState *cpu, target_ulong vaddr,
    }

    sz = size;
-    section = address_space_translate_for_iotlb(cpu->as, paddr,
+    section = address_space_translate_for_iotlb(&address_space_memory, paddr,
                                                &xlat, &sz);
    assert(sz >= TARGET_PAGE_SIZE);

@@ -261,7 +275,7 @@ void tlb_set_page(CPUState *cpu, target_ulong vaddr,
    }

    code_address = address;
-    iotlb = memory_region_section_get_iotlb(cpu, section, vaddr, paddr, xlat,
+    iotlb = memory_region_section_get_iotlb(env, section, vaddr, paddr, xlat,
                                            prot, &address);

    index = (vaddr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
@@ -285,8 +299,7 @@ void tlb_set_page(CPUState *cpu, target_ulong vaddr,
            /* Write access calls the I/O callback.  */
            te->addr_write = address | TLB_MMIO;
        } else if (memory_region_is_ram(section->mr)
-                   && cpu_physical_memory_is_clean(section->mr->ram_addr
-                                                   + xlat)) {
+                   && !cpu_physical_memory_is_dirty(section->mr->ram_addr + xlat)) {
            te->addr_write = address | TLB_NOTDIRTY;
        } else {
            te->addr_write = address;
@@ -306,7 +319,6 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr)
    int mmu_idx, page_index, pd;
    void *p;
    MemoryRegion *mr;
-    CPUState *cpu = ENV_GET_CPU(env1);

    page_index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
    mmu_idx = cpu_mmu_index(env1);
@@ -315,14 +327,15 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr)
        cpu_ldub_code(env1, addr);
    }
    pd = env1->iotlb[mmu_idx][page_index] & ~TARGET_PAGE_MASK;
-    mr = iotlb_to_region(cpu->as, pd);
+    mr = iotlb_to_region(pd);
    if (memory_region_is_unassigned(mr)) {
+        CPUState *cpu = ENV_GET_CPU(env1);
        CPUClass *cc = CPU_GET_CLASS(cpu);

        if (cc->do_unassigned_access) {
            cc->do_unassigned_access(cpu, addr, false, true, 0, 4);
        } else {
-            cpu_abort(cpu, "Trying to execute code outside RAM or ROM at 0x"
+            cpu_abort(env1, "Trying to execute code outside RAM or ROM at 0x"
                      TARGET_FMT_lx "\n", addr);
        }
    }
@@ -1,3 +0,0 @@
-# Default configuration for aarch64-linux-user
-
-CONFIG_GDBSTUB_XML=y
@@ -1,6 +0,0 @@
-# Default configuration for aarch64-softmmu
-
-# We support all the 32 bit boards so need all their config
-include arm-softmmu.mak
-
-# Currently no 64-bit specific config requirements
@@ -27,7 +27,6 @@ CONFIG_SSI_SD=y
 CONFIG_SSI_M25P80=y
 CONFIG_LAN9118=y
 CONFIG_SMC91C111=y
-CONFIG_ALLWINNER_EMAC=y
 CONFIG_DS1338=y
 CONFIG_PFLASH_CFI01=y
 CONFIG_PFLASH_CFI02=y
@@ -42,7 +41,6 @@ CONFIG_ARM_GIC=y
 CONFIG_ARM_GIC_KVM=$(CONFIG_KVM)
 CONFIG_ARM_TIMER=y
 CONFIG_ARM_MPTIMER=y
-CONFIG_A9_GTIMER=y
 CONFIG_PL011=y
 CONFIG_PL022=y
 CONFIG_PL031=y
@@ -65,7 +63,6 @@ CONFIG_XILINX_SPIPS=y

 CONFIG_ARM11SCU=y
 CONFIG_A9SCU=y
-CONFIG_DIGIC=y
 CONFIG_MARVELL_88W8618=y
 CONFIG_OMAP=y
 CONFIG_TSC210X=y
@@ -84,7 +81,3 @@ CONFIG_VERSATILE_I2C=y

 CONFIG_SDHCI=y
 CONFIG_INTEGRATOR_DEBUG=y
-
-CONFIG_ALLWINNER_A10_PIT=y
-CONFIG_ALLWINNER_A10_PIC=y
-CONFIG_ALLWINNER_A10=y
@@ -41,11 +41,8 @@ CONFIG_I8259=y
 CONFIG_XILINX=y
 CONFIG_XILINX_ETHLITE=y
 CONFIG_OPENPIC=y
-CONFIG_PREP=y
-CONFIG_MAC=y
 CONFIG_E500=y
 CONFIG_OPENPIC_KVM=$(and $(CONFIG_E500),$(CONFIG_KVM))
 # For PReP
 CONFIG_MC146818RTC=y
-CONFIG_ETSEC=y
 CONFIG_ISA_TESTDEV=y
@@ -42,8 +42,6 @@ CONFIG_XILINX=y
 CONFIG_XILINX_ETHLITE=y
 CONFIG_OPENPIC=y
 CONFIG_PSERIES=y
-CONFIG_PREP=y
-CONFIG_MAC=y
 CONFIG_E500=y
 CONFIG_OPENPIC_KVM=$(and $(CONFIG_E500),$(CONFIG_KVM))
 # For pSeries
@@ -3,12 +3,32 @@
 include pci.mak
 include sound.mak
 include usb.mak
+CONFIG_ISA_MMIO=y
+CONFIG_ESCC=y
 CONFIG_M48T59=y
 CONFIG_VGA=y
 CONFIG_VGA_PCI=y
 CONFIG_SERIAL=y
+CONFIG_I8254=y
+CONFIG_PCKBD=y
+CONFIG_FDC=y
 CONFIG_I8257=y
 CONFIG_OPENPIC=y
+CONFIG_PREP_PCI=y
+CONFIG_MACIO=y
+CONFIG_CUDA=y
+CONFIG_ADB=y
+CONFIG_MAC_NVRAM=y
+CONFIG_MAC_DBDMA=y
+CONFIG_HEATHROW_PIC=y
+CONFIG_GRACKLE_PCI=y
+CONFIG_UNIN_PCI=y
+CONFIG_DEC_PCI=y
+CONFIG_PPCE500_PCI=y
+CONFIG_IDE_ISA=y
+CONFIG_IDE_CMD646=y
+CONFIG_IDE_MACIO=y
+CONFIG_NE2000_ISA=y
 CONFIG_PFLASH_CFI01=y
 CONFIG_PFLASH_CFI02=y
 CONFIG_PTIMER=y
@@ -16,3 +36,8 @@ CONFIG_I8259=y
 CONFIG_XILINX=y
 CONFIG_XILINX_ETHLITE=y
 CONFIG_OPENPIC=y
+CONFIG_E500=y
+CONFIG_OPENPIC_KVM=$(and $(CONFIG_E500),$(CONFIG_KVM))
+# For PReP
+CONFIG_MC146818RTC=y
+CONFIG_ISA_TESTDEV=y
@@ -1,3 +1,2 @@
 CONFIG_VIRTIO=y
 CONFIG_SCLPCONSOLE=y
-CONFIG_S390_FLIC=$(CONFIG_KVM)
@@ -10,7 +10,6 @@ CONFIG_EMPTY_SLOT=y
 CONFIG_PCNET_COMMON=y
 CONFIG_LANCE=y
 CONFIG_TCX=y
-CONFIG_CG3=y
 CONFIG_SLAVIO=y
 CONFIG_CS4231=y
 CONFIG_GRLIB=y
@@ -33,14 +33,12 @@ DriveInfo *add_init_drive(const char *optstr)
 {
    DriveInfo *dinfo;
    QemuOpts *opts;
-    MachineClass *mc;

    opts = drive_def(optstr);
    if (!opts)
        return NULL;

-    mc = MACHINE_GET_CLASS(current_machine);
-    dinfo = drive_init(opts, mc->qemu_machine->block_default_type);
+    dinfo = drive_init(opts, current_machine->block_default_type);
    if (!dinfo) {
        qemu_opts_del(opts);
        return NULL;
@@ -41,10 +41,6 @@ void *create_device_tree(int *sizep)
    if (ret < 0) {
        goto fail;
    }
-    ret = fdt_finish_reservemap(fdt);
-    if (ret < 0) {
-        goto fail;
-    }
    ret = fdt_begin_node(fdt, "");
    if (ret < 0) {
        goto fail;
@@ -131,12 +127,12 @@ static int findnode_nofail(void *fdt, const char *node_path)
    return offset;
 }

-int qemu_fdt_setprop(void *fdt, const char *node_path,
-                     const char *property, const void *val, int size)
+int qemu_devtree_setprop(void *fdt, const char *node_path,
+                         const char *property, const void *val_array, int size)
 {
    int r;

-    r = fdt_setprop(fdt, findnode_nofail(fdt, node_path), property, val, size);
+    r = fdt_setprop(fdt, findnode_nofail(fdt, node_path), property, val_array, size);
    if (r < 0) {
        fprintf(stderr, "%s: Couldn't set %s/%s: %s\n", __func__, node_path,
                property, fdt_strerror(r));
@@ -146,8 +142,8 @@ int qemu_fdt_setprop(void *fdt, const char *node_path,
    return r;
 }

-int qemu_fdt_setprop_cell(void *fdt, const char *node_path,
-                          const char *property, uint32_t val)
+int qemu_devtree_setprop_cell(void *fdt, const char *node_path,
+                              const char *property, uint32_t val)
 {
    int r;

@@ -161,15 +157,15 @@ int qemu_fdt_setprop_cell(void *fdt, const char *node_path,
    return r;
 }

-int qemu_fdt_setprop_u64(void *fdt, const char *node_path,
-                         const char *property, uint64_t val)
+int qemu_devtree_setprop_u64(void *fdt, const char *node_path,
+                             const char *property, uint64_t val)
 {
    val = cpu_to_be64(val);
-    return qemu_fdt_setprop(fdt, node_path, property, &val, sizeof(val));
+    return qemu_devtree_setprop(fdt, node_path, property, &val, sizeof(val));
 }

-int qemu_fdt_setprop_string(void *fdt, const char *node_path,
-                            const char *property, const char *string)
+int qemu_devtree_setprop_string(void *fdt, const char *node_path,
+                                const char *property, const char *string)
 {
    int r;

@@ -183,8 +179,8 @@ int qemu_fdt_setprop_string(void *fdt, const char *node_path,
    return r;
 }

-const void *qemu_fdt_getprop(void *fdt, const char *node_path,
-                             const char *property, int *lenp)
+const void *qemu_devtree_getprop(void *fdt, const char *node_path,
+                                 const char *property, int *lenp)
 {
    int len;
    const void *r;
@@ -200,11 +196,11 @@ const void *qemu_fdt_getprop(void *fdt, const char *node_path,
    return r;
 }

-uint32_t qemu_fdt_getprop_cell(void *fdt, const char *node_path,
-                               const char *property)
+uint32_t qemu_devtree_getprop_cell(void *fdt, const char *node_path,
+                                   const char *property)
 {
    int len;
-    const uint32_t *p = qemu_fdt_getprop(fdt, node_path, property, &len);
+    const uint32_t *p = qemu_devtree_getprop(fdt, node_path, property, &len);
    if (len != 4) {
        fprintf(stderr, "%s: %s/%s not 4 bytes long (not a cell?)\n",
                __func__, node_path, property);
@@ -213,7 +209,7 @@ uint32_t qemu_fdt_getprop_cell(void *fdt, const char *node_path,
    return be32_to_cpu(*p);
 }

-uint32_t qemu_fdt_get_phandle(void *fdt, const char *path)
+uint32_t qemu_devtree_get_phandle(void *fdt, const char *path)
 {
    uint32_t r;

@@ -227,15 +223,15 @@ uint32_t qemu_fdt_get_phandle(void *fdt, const char *path)
    return r;
 }

-int qemu_fdt_setprop_phandle(void *fdt, const char *node_path,
-                             const char *property,
-                             const char *target_node_path)
+int qemu_devtree_setprop_phandle(void *fdt, const char *node_path,
+                                 const char *property,
+                                 const char *target_node_path)
 {
-    uint32_t phandle = qemu_fdt_get_phandle(fdt, target_node_path);
-    return qemu_fdt_setprop_cell(fdt, node_path, property, phandle);
+    uint32_t phandle = qemu_devtree_get_phandle(fdt, target_node_path);
+    return qemu_devtree_setprop_cell(fdt, node_path, property, phandle);
 }

-uint32_t qemu_fdt_alloc_phandle(void *fdt)
+uint32_t qemu_devtree_alloc_phandle(void *fdt)
 {
    static int phandle = 0x0;

@@ -259,7 +255,7 @@ uint32_t qemu_fdt_alloc_phandle(void *fdt)
    return phandle++;
 }

-int qemu_fdt_nop_node(void *fdt, const char *node_path)
+int qemu_devtree_nop_node(void *fdt, const char *node_path)
 {
    int r;

@@ -273,7 +269,7 @@ int qemu_fdt_nop_node(void *fdt, const char *node_path)
    return r;
 }

-int qemu_fdt_add_subnode(void *fdt, const char *name)
+int qemu_devtree_add_subnode(void *fdt, const char *name)
 {
    char *dupname = g_strdup(name);
    char *basename = strrchr(dupname, '/');
@@ -303,7 +299,7 @@ int qemu_fdt_add_subnode(void *fdt, const char *name)
    return retval;
 }

-void qemu_fdt_dumpdtb(void *fdt, int size)
+void qemu_devtree_dumpdtb(void *fdt, int size)
 {
    const char *dumpdtb = qemu_opt_get(qemu_get_machine_opts(), "dumpdtb");

@@ -313,11 +309,11 @@ void qemu_fdt_dumpdtb(void *fdt, int size)
    }
 }

-int qemu_fdt_setprop_sized_cells_from_array(void *fdt,
-                                            const char *node_path,
-                                            const char *property,
-                                            int numvalues,
-                                            uint64_t *values)
+int qemu_devtree_setprop_sized_cells_from_array(void *fdt,
+                                                const char *node_path,
+                                                const char *property,
+                                                int numvalues,
+                                                uint64_t *values)
 {
    uint32_t *propcells;
    uint64_t value;
@@ -342,6 +338,6 @@ int qemu_fdt_setprop_sized_cells_from_array(void *fdt,
        propcells[cellnum++] = cpu_to_be32(value);
    }

-    return qemu_fdt_setprop(fdt, node_path, property, propcells,
-                            cellnum * sizeof(uint32_t));
+    return qemu_devtree_setprop(fdt, node_path, property, propcells,
+                                cellnum * sizeof(uint32_t));
 }
@@ -190,7 +190,7 @@ static int print_insn_od_target(bfd_vma pc, disassemble_info *info)
 /* Disassemble this for me please... (debugging). 'flags' has the following
   values:
    i386 - 1 means 16 bit code, 2 means 64 bit code
-    arm  - bit 0 = thumb, bit 1 = reverse endian, bit 2 = A64
+    arm  - bit 0 = thumb, bit 1 = reverse endian
    ppc  - nonzero means little endian
    other targets - unused
 */
@@ -225,15 +225,7 @@ void target_disas(FILE *out, CPUArchState *env, target_ulong code,
    }
    print_insn = print_insn_i386;
 #elif defined(TARGET_ARM)
-    if (flags & 4) {
-        /* We might not be compiled with the A64 disassembler
-         * because it needs a C++ compiler; in that case we will
-         * fall through to the default print_insn_od case.
-         */
-#if defined(CONFIG_ARM_A64_DIS)
-        print_insn = print_insn_arm_a64;
-#endif
-    } else if (flags & 1) {
+    if (flags & 1) {
        print_insn = print_insn_thumb1;
    } else {
        print_insn = print_insn_arm;
@@ -364,8 +356,6 @@ void disas(FILE *out, void *code, unsigned long size)
 #elif defined(_ARCH_PPC)
    s.info.disassembler_options = (char *)"any";
    print_insn = print_insn_ppc;
-#elif defined(__aarch64__) && defined(CONFIG_ARM_A64_DIS)
-    print_insn = print_insn_arm_a64;
 #elif defined(__alpha__)
    print_insn = print_insn_alpha;
 #elif defined(__sparc__)
@@ -1,10 +1,5 @@
-
 common-obj-$(CONFIG_ALPHA_DIS) += alpha.o
 common-obj-$(CONFIG_ARM_DIS) += arm.o
-common-obj-$(CONFIG_ARM_A64_DIS) += arm-a64.o
-common-obj-$(CONFIG_ARM_A64_DIS) += libvixl/
-libvixldir = $(SRC_PATH)/disas/libvixl
-$(obj)/arm-a64.o: QEMU_CFLAGS := -I$(libvixldir) $(QEMU_CFLAGS)
 common-obj-$(CONFIG_CRIS_DIS) += cris.o
 common-obj-$(CONFIG_HPPA_DIS) += hppa.o
 common-obj-$(CONFIG_I386_DIS) += i386.o
@@ -1,87 +0,0 @@
-/*
- * ARM A64 disassembly output wrapper to libvixl
- * Copyright (c) 2013 Linaro Limited
- * Written by Claudio Fontana
- *
- * 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 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * 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 "a64/disasm-a64.h"
-
-extern "C" {
-#include "disas/bfd.h"
-}
-
-using namespace vixl;
-
-static Decoder *vixl_decoder = NULL;
-static Disassembler *vixl_disasm = NULL;
-
-/* We don't use libvixl's PrintDisassembler because its output
- * is a little unhelpful (trailing newlines, for example).
- * Instead we use our own very similar variant so we have
- * control over the format.
- */
-class QEMUDisassembler : public Disassembler {
-public:
-    explicit QEMUDisassembler(FILE *stream) : stream_(stream) { }
-    ~QEMUDisassembler() { }
-
-protected:
-    void ProcessOutput(Instruction *instr) {
-        fprintf(stream_, "%08" PRIx32 "      %s",
-                instr->InstructionBits(), GetOutput());
-    }
-
-private:
-    FILE *stream_;
-};
-
-static int vixl_is_initialized(void)
-{
-    return vixl_decoder != NULL;
-}
-
-static void vixl_init(FILE *f) {
-    vixl_decoder = new Decoder();
-    vixl_disasm = new QEMUDisassembler(f);
-    vixl_decoder->AppendVisitor(vixl_disasm);
-}
-
-#define INSN_SIZE 4
-
-/* Disassemble ARM A64 instruction. This is our only entry
- * point from QEMU's C code.
- */
-int print_insn_arm_a64(uint64_t addr, disassemble_info *info)
-{
-    uint8_t bytes[INSN_SIZE];
-    uint32_t instr;
-    int status;
-
-    status = info->read_memory_func(addr, bytes, INSN_SIZE, info);
-    if (status != 0) {
-        info->memory_error_func(status, addr, info);
-        return -1;
-    }
-
-    if (!vixl_is_initialized()) {
-        vixl_init(info->stream);
-    }
-
-    instr = bytes[0] | bytes[1] << 8 | bytes[2] << 16 | bytes[3] << 24;
-    vixl_decoder->Decode(reinterpret_cast<Instruction*>(&instr));
-
-    return INSN_SIZE;
-}
@@ -171,7 +171,6 @@ static void print_operand_value (char *buf, size_t bufsize, int hex, bfd_vma dis
 static void print_displacement (char *, bfd_vma);
 static void OP_E (int, int);
 static void OP_G (int, int);
-static void OP_vvvv (int, int);
 static bfd_vma get64 (void);
 static bfd_signed_vma get32 (void);
 static bfd_signed_vma get32s (void);
@@ -265,9 +264,6 @@ static int rex_used;
   current instruction.  */
 static int used_prefixes;

-/* The VEX.vvvv register, unencoded.  */
-static int vex_reg;
-
 /* Flags stored in PREFIXES.  */
 #define PREFIX_REPZ 1
 #define PREFIX_REPNZ 2
@@ -282,10 +278,6 @@ static int vex_reg;
 #define PREFIX_ADDR 0x400
 #define PREFIX_FWAIT 0x800

-#define PREFIX_VEX_0F    0x1000
-#define PREFIX_VEX_0F38  0x2000
-#define PREFIX_VEX_0F3A  0x4000
-
 /* Make sure that bytes from INFO->PRIVATE_DATA->BUFFER (inclusive)
   to ADDR (exclusive) are valid.  Returns 1 for success, longjmps
   on error.  */
@@ -331,7 +323,6 @@ fetch_data(struct disassemble_info *info, bfd_byte *addr)

 #define XX { NULL, 0 }

-#define Bv { OP_vvvv, v_mode }
 #define Eb { OP_E, b_mode }
 #define Ev { OP_E, v_mode }
 #define Ed { OP_E, d_mode }
@@ -680,8 +671,7 @@ fetch_data(struct disassemble_info *info, bfd_byte *addr)
 #define PREGRP102 NULL, { { NULL, USE_PREFIX_USER_TABLE }, { NULL, 102 } }
 #define PREGRP103 NULL, { { NULL, USE_PREFIX_USER_TABLE }, { NULL, 103 } }
 #define PREGRP104 NULL, { { NULL, USE_PREFIX_USER_TABLE }, { NULL, 104 } }
-#define PREGRP105 NULL, { { NULL, USE_PREFIX_USER_TABLE }, { NULL, 105 } }
-#define PREGRP106 NULL, { { NULL, USE_PREFIX_USER_TABLE }, { NULL, 106 } }
+

 #define X86_64_0  NULL, { { NULL, X86_64_SPECIAL }, { NULL, 0 } }
 #define X86_64_1  NULL, { { NULL, X86_64_SPECIAL }, { NULL, 1 } }
@@ -1459,7 +1449,7 @@ static const unsigned char threebyte_0x38_uses_DATA_prefix[256] = {
  /* c0 */ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* cf */
  /* d0 */ 0,0,0,0,0,0,0,0,0,0,0,1,1,1,1,1, /* df */
  /* e0 */ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* ef */
-  /* f0 */ 0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0, /* ff */
+  /* f0 */ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* ff */
  /*       -------------------------------        */
  /*       0 1 2 3 4 5 6 7 8 9 a b c d e f        */
 };
@@ -1483,7 +1473,7 @@ static const unsigned char threebyte_0x38_uses_REPNZ_prefix[256] = {
  /* c0 */ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* cf */
  /* d0 */ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* df */
  /* e0 */ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* ef */
-  /* f0 */ 1,1,0,0,0,0,0,1,0,0,0,0,0,0,0,0, /* ff */
+  /* f0 */ 1,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* ff */
  /*       -------------------------------        */
  /*       0 1 2 3 4 5 6 7 8 9 a b c d e f        */
 };
@@ -1507,7 +1497,7 @@ static const unsigned char threebyte_0x38_uses_REPZ_prefix[256] = {
  /* c0 */ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* cf */
  /* d0 */ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* df */
  /* e0 */ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* ef */
-  /* f0 */ 0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0, /* ff */
+  /* f0 */ 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* ff */
  /*       -------------------------------        */
  /*       0 1 2 3 4 5 6 7 8 9 a b c d e f        */
 };
@@ -2642,17 +2632,17 @@ static const struct dis386 prefix_user_table[][4] = {

  /* PREGRP87 */
  {
-    { "movbe",	{ Gv, Ev } },
    { "(bad)",	{ XX } },
-    { "movbe",	{ Gv, Ev } },
+    { "(bad)",	{ XX } },
+    { "(bad)",	{ XX } },
    { "crc32",	{ Gdq, { CRC32_Fixup, b_mode } } },
  },

  /* PREGRP88 */
  {
-    { "movbe",	{ Ev, Gv } },
    { "(bad)",	{ XX } },
-    { "movbe",	{ Ev, Gv } },
+    { "(bad)",	{ XX } },
+    { "(bad)",	{ XX } },
    { "crc32",	{ Gdq, { CRC32_Fixup, v_mode } } },
  },

@@ -2784,22 +2774,6 @@ static const struct dis386 prefix_user_table[][4] = {
    { "(bad)",	{ XX } },
  },

-  /* PREGRP105 */
-  {
-    { "andnS",	{ Gv, Bv, Ev } },
-    { "(bad)",	{ XX } },
-    { "(bad)",	{ XX } },
-    { "(bad)",	{ XX } },
-  },
-
-  /* PREGRP106 */
-  {
-    { "bextrS",	{ Gv, Ev, Bv } },
-    { "sarxS",	{ Gv, Ev, Bv } },
-    { "shlxS",	{ Gv, Ev, Bv } },
-    { "shrxS",	{ Gv, Ev, Bv } },
-  },
-
 };

 static const struct dis386 x86_64_table[][2] = {
@@ -3097,12 +3071,12 @@ static const struct dis386 three_byte_table[][256] = {
    /* f0 */
    { PREGRP87 },
    { PREGRP88 },
-    { PREGRP105 },
    { "(bad)", { XX } },
    { "(bad)", { XX } },
    { "(bad)", { XX } },
    { "(bad)", { XX } },
-    { PREGRP106 },
+    { "(bad)", { XX } },
+    { "(bad)", { XX } },
    /* f8 */
    { "(bad)", { XX } },
    { "(bad)", { XX } },
@@ -3503,74 +3477,6 @@ ckprefix (void)
    }
 }

-static void
-ckvexprefix (void)
-{
-    int op, vex2, vex3, newrex = 0, newpfx = prefixes;
-
-    if (address_mode == mode_16bit) {
-        return;
-    }
-
-    fetch_data(the_info, codep + 1);
-    op = *codep;
-
-    if (op != 0xc4 && op != 0xc5) {
-        return;
-    }
-
-    fetch_data(the_info, codep + 2);
-    vex2 = codep[1];
-
-    if (address_mode == mode_32bit && (vex2 & 0xc0) != 0xc0) {
-        return;
-    }
-
-    if (op == 0xc4) {
-        /* Three byte VEX prefix.  */
-        fetch_data(the_info, codep + 3);
-        vex3 = codep[2];
-
-        newrex |= (vex2 & 0x80 ? 0 : REX_R);
-        newrex |= (vex2 & 0x40 ? 0 : REX_X);
-        newrex |= (vex2 & 0x20 ? 0 : REX_B);
-        newrex |= (vex3 & 0x80 ? REX_W : 0);
-        switch (vex2 & 0x1f) {      /* VEX.m-mmmm */
-        case 1:
-            newpfx |= PREFIX_VEX_0F;
-            break;
-        case 2:
-            newpfx |= PREFIX_VEX_0F | PREFIX_VEX_0F38;
-            break;
-        case 3:
-            newpfx |= PREFIX_VEX_0F | PREFIX_VEX_0F3A;
-            break;
-        }
-        vex2 = vex3;
-        codep += 3;
-    } else {
-        /* Two byte VEX prefix.  */
-        newrex |= (vex2 & 0x80 ? 0 : REX_R);
-        codep += 2;
-    }
-
-    vex_reg = (~vex2 >> 3) & 15;     /* VEX.vvvv */
-    switch (vex2 & 3) {              /* VEX.pp */
-    case 1:
-        newpfx |= PREFIX_DATA;     /* 0x66 */
-        break;
-    case 2:
-        newpfx |= PREFIX_REPZ;     /* 0xf3 */
-        break;
-    case 3:
-        newpfx |= PREFIX_REPNZ;    /* 0xf2 */
-        break;
-    }
-
-    rex = newrex;
-    prefixes = newpfx;
-}
-
 /* Return the name of the prefix byte PREF, or NULL if PREF is not a
   prefix byte.  */

@@ -3692,7 +3598,6 @@ print_insn (bfd_vma pc, disassemble_info *info)
  const char *p;
  struct dis_private priv;
  unsigned char op;
-  unsigned char threebyte;

  if (info->mach == bfd_mach_x86_64_intel_syntax
      || info->mach == bfd_mach_x86_64)
@@ -3847,7 +3752,6 @@ print_insn (bfd_vma pc, disassemble_info *info)

  obufp = obuf;
  ckprefix ();
-  ckvexprefix ();

  insn_codep = codep;
  sizeflag = priv.orig_sizeflag;
@@ -3871,29 +3775,18 @@ print_insn (bfd_vma pc, disassemble_info *info)
    }

  op = 0;
-  if (prefixes & PREFIX_VEX_0F)
-    {
-      used_prefixes |= PREFIX_VEX_0F | PREFIX_VEX_0F38 | PREFIX_VEX_0F3A;
-      if (prefixes & PREFIX_VEX_0F38)
-        threebyte = 0x38;
-      else if (prefixes & PREFIX_VEX_0F3A)
-        threebyte = 0x3a;
-      else
-        threebyte = *codep++;
-      goto vex_opcode;
-    }
  if (*codep == 0x0f)
    {
+      unsigned char threebyte;
      fetch_data(info, codep + 2);
-      threebyte = codep[1];
-      codep += 2;
-    vex_opcode:
+      threebyte = *++codep;
      dp = &dis386_twobyte[threebyte];
-      need_modrm = twobyte_has_modrm[threebyte];
-      uses_DATA_prefix = twobyte_uses_DATA_prefix[threebyte];
-      uses_REPNZ_prefix = twobyte_uses_REPNZ_prefix[threebyte];
-      uses_REPZ_prefix = twobyte_uses_REPZ_prefix[threebyte];
-      uses_LOCK_prefix = (threebyte & ~0x02) == 0x20;
+      need_modrm = twobyte_has_modrm[*codep];
+      uses_DATA_prefix = twobyte_uses_DATA_prefix[*codep];
+      uses_REPNZ_prefix = twobyte_uses_REPNZ_prefix[*codep];
+      uses_REPZ_prefix = twobyte_uses_REPZ_prefix[*codep];
+      uses_LOCK_prefix = (*codep & ~0x02) == 0x20;
+      codep++;
      if (dp->name == NULL && dp->op[0].bytemode == IS_3BYTE_OPCODE)
 	{
          fetch_data(info, codep + 2);
@@ -5398,17 +5291,6 @@ OP_G (int bytemode, int sizeflag)
    }
 }

-static void
-OP_vvvv (int bytemode, int sizeflags)
-{
-    USED_REX (REX_W);
-    if (rex & REX_W) {
-        oappend(names64[vex_reg]);
-    } else {
-        oappend(names32[vex_reg]);
-    }
-}
-
 static bfd_vma
 get64 (void)
 {
@@ -1,30 +0,0 @@
-LICENCE
-=======
-
-The software in this repository is covered by the following licence.
-
-// Copyright 2013, ARM Limited
-// All rights reserved.
-//
-// Redistribution and use in source and binary forms, with or without
-// modification, are permitted provided that the following conditions are met:
-//
-//   * Redistributions of source code must retain the above copyright notice,
-//     this list of conditions and the following disclaimer.
-//   * Redistributions in binary form must reproduce the above copyright notice,
-//     this list of conditions and the following disclaimer in the documentation
-//     and/or other materials provided with the distribution.
-//   * Neither the name of ARM Limited nor the names of its contributors may be
-//     used to endorse or promote products derived from this software without
-//     specific prior written permission.
-//
-// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
-// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
-// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
@@ -1,8 +0,0 @@
-libvixl_OBJS = utils.o \
-               a64/instructions-a64.o \
-               a64/decoder-a64.o \
-               a64/disasm-a64.o
-
-$(addprefix $(obj)/,$(libvixl_OBJS)): QEMU_CFLAGS := -I$(SRC_PATH)/disas/libvixl $(QEMU_CFLAGS)
-
-common-obj-$(CONFIG_ARM_A64_DIS) += $(libvixl_OBJS)
@@ -1,12 +0,0 @@
-
-The code in this directory is a subset of libvixl:
- https://github.com/armvixl/vixl
-(specifically, it is the set of files needed for disassembly only,
-taken from libvixl 1.1).
-Bugfixes should preferably be sent upstream initially.
-
-The disassembler does not currently support the entire A64 instruction
-set. Notably:
- * No Advanced SIMD support.
- * Limited support for system instructions.
- * A few miscellaneous integer and floating point instructions are missing.
@@ -1,56 +0,0 @@
-// Copyright 2013, ARM Limited
-// All rights reserved.
-//
-// Redistribution and use in source and binary forms, with or without
-// modification, are permitted provided that the following conditions are met:
-//
-//   * Redistributions of source code must retain the above copyright notice,
-//     this list of conditions and the following disclaimer.
-//   * Redistributions in binary form must reproduce the above copyright notice,
-//     this list of conditions and the following disclaimer in the documentation
-//     and/or other materials provided with the distribution.
-//   * Neither the name of ARM Limited nor the names of its contributors may be
-//     used to endorse or promote products derived from this software without
-//     specific prior written permission.
-//
-// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
-// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
-// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-#ifndef VIXL_CPU_A64_H
-#define VIXL_CPU_A64_H
-
-#include "globals.h"
-
-namespace vixl {
-
-class CPU {
- public:
-  // Initialise CPU support.
-  static void SetUp();
-
-  // Ensures the data at a given address and with a given size is the same for
-  // the I and D caches. I and D caches are not automatically coherent on ARM
-  // so this operation is required before any dynamically generated code can
-  // safely run.
-  static void EnsureIAndDCacheCoherency(void *address, size_t length);
-
- private:
-  // Return the content of the cache type register.
-  static uint32_t GetCacheType();
-
-  // I and D cache line size in bytes.
-  static unsigned icache_line_size_;
-  static unsigned dcache_line_size_;
-};
-
-}  // namespace vixl
-
-#endif  // VIXL_CPU_A64_H
@@ -1,712 +0,0 @@
-// Copyright 2013, ARM Limited
-// All rights reserved.
-//
-// Redistribution and use in source and binary forms, with or without
-// modification, are permitted provided that the following conditions are met:
-//
-//   * Redistributions of source code must retain the above copyright notice,
-//     this list of conditions and the following disclaimer.
-//   * Redistributions in binary form must reproduce the above copyright notice,
-//     this list of conditions and the following disclaimer in the documentation
-//     and/or other materials provided with the distribution.
-//   * Neither the name of ARM Limited nor the names of its contributors may be
-//     used to endorse or promote products derived from this software without
-//     specific prior written permission.
-//
-// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
-// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
-// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-#include "globals.h"
-#include "utils.h"
-#include "a64/decoder-a64.h"
-
-namespace vixl {
-// Top-level instruction decode function.
-void Decoder::Decode(Instruction *instr) {
-  if (instr->Bits(28, 27) == 0) {
-    VisitUnallocated(instr);
-  } else {
-    switch (instr->Bits(27, 24)) {
-      // 0:   PC relative addressing.
-      case 0x0: DecodePCRelAddressing(instr); break;
-
-      // 1:   Add/sub immediate.
-      case 0x1: DecodeAddSubImmediate(instr); break;
-
-      // A:   Logical shifted register.
-      //      Add/sub with carry.
-      //      Conditional compare register.
-      //      Conditional compare immediate.
-      //      Conditional select.
-      //      Data processing 1 source.
-      //      Data processing 2 source.
-      // B:   Add/sub shifted register.
-      //      Add/sub extended register.
-      //      Data processing 3 source.
-      case 0xA:
-      case 0xB: DecodeDataProcessing(instr); break;
-
-      // 2:   Logical immediate.
-      //      Move wide immediate.
-      case 0x2: DecodeLogical(instr); break;
-
-      // 3:   Bitfield.
-      //      Extract.
-      case 0x3: DecodeBitfieldExtract(instr); break;
-
-      // 4:   Unconditional branch immediate.
-      //      Exception generation.
-      //      Compare and branch immediate.
-      // 5:   Compare and branch immediate.
-      //      Conditional branch.
-      //      System.
-      // 6,7: Unconditional branch.
-      //      Test and branch immediate.
-      case 0x4:
-      case 0x5:
-      case 0x6:
-      case 0x7: DecodeBranchSystemException(instr); break;
-
-      // 8,9: Load/store register pair post-index.
-      //      Load register literal.
-      //      Load/store register unscaled immediate.
-      //      Load/store register immediate post-index.
-      //      Load/store register immediate pre-index.
-      //      Load/store register offset.
-      //      Load/store exclusive.
-      // C,D: Load/store register pair offset.
-      //      Load/store register pair pre-index.
-      //      Load/store register unsigned immediate.
-      //      Advanced SIMD.
-      case 0x8:
-      case 0x9:
-      case 0xC:
-      case 0xD: DecodeLoadStore(instr); break;
-
-      // E:   FP fixed point conversion.
-      //      FP integer conversion.
-      //      FP data processing 1 source.
-      //      FP compare.
-      //      FP immediate.
-      //      FP data processing 2 source.
-      //      FP conditional compare.
-      //      FP conditional select.
-      //      Advanced SIMD.
-      // F:   FP data processing 3 source.
-      //      Advanced SIMD.
-      case 0xE:
-      case 0xF: DecodeFP(instr); break;
-    }
-  }
-}
-
-void Decoder::AppendVisitor(DecoderVisitor* new_visitor) {
-  visitors_.remove(new_visitor);
-  visitors_.push_front(new_visitor);
-}
-
-
-void Decoder::PrependVisitor(DecoderVisitor* new_visitor) {
-  visitors_.remove(new_visitor);
-  visitors_.push_back(new_visitor);
-}
-
-
-void Decoder::InsertVisitorBefore(DecoderVisitor* new_visitor,
-                                  DecoderVisitor* registered_visitor) {
-  visitors_.remove(new_visitor);
-  std::list<DecoderVisitor*>::iterator it;
-  for (it = visitors_.begin(); it != visitors_.end(); it++) {
-    if (*it == registered_visitor) {
-      visitors_.insert(it, new_visitor);
-      return;
-    }
-  }
-  // We reached the end of the list. The last element must be
-  // registered_visitor.
-  ASSERT(*it == registered_visitor);
-  visitors_.insert(it, new_visitor);
-}
-
-
-void Decoder::InsertVisitorAfter(DecoderVisitor* new_visitor,
-                                 DecoderVisitor* registered_visitor) {
-  visitors_.remove(new_visitor);
-  std::list<DecoderVisitor*>::iterator it;
-  for (it = visitors_.begin(); it != visitors_.end(); it++) {
-    if (*it == registered_visitor) {
-      it++;
-      visitors_.insert(it, new_visitor);
-      return;
-    }
-  }
-  // We reached the end of the list. The last element must be
-  // registered_visitor.
-  ASSERT(*it == registered_visitor);
-  visitors_.push_back(new_visitor);
-}
-
-
-void Decoder::RemoveVisitor(DecoderVisitor* visitor) {
-  visitors_.remove(visitor);
-}
-
-
-void Decoder::DecodePCRelAddressing(Instruction* instr) {
-  ASSERT(instr->Bits(27, 24) == 0x0);
-  // We know bit 28 is set, as <b28:b27> = 0 is filtered out at the top level
-  // decode.
-  ASSERT(instr->Bit(28) == 0x1);
-  VisitPCRelAddressing(instr);
-}
-
-
-void Decoder::DecodeBranchSystemException(Instruction* instr) {
-  ASSERT((instr->Bits(27, 24) == 0x4) ||
-         (instr->Bits(27, 24) == 0x5) ||
-         (instr->Bits(27, 24) == 0x6) ||
-         (instr->Bits(27, 24) == 0x7) );
-
-  switch (instr->Bits(31, 29)) {
-    case 0:
-    case 4: {
-      VisitUnconditionalBranch(instr);
-      break;
-    }
-    case 1:
-    case 5: {
-      if (instr->Bit(25) == 0) {
-        VisitCompareBranch(instr);
-      } else {
-        VisitTestBranch(instr);
-      }
-      break;
-    }
-    case 2: {
-      if (instr->Bit(25) == 0) {
-        if ((instr->Bit(24) == 0x1) ||
-            (instr->Mask(0x01000010) == 0x00000010)) {
-          VisitUnallocated(instr);
-        } else {
-          VisitConditionalBranch(instr);
-        }
-      } else {
-        VisitUnallocated(instr);
-      }
-      break;
-    }
-    case 6: {
-      if (instr->Bit(25) == 0) {
-        if (instr->Bit(24) == 0) {
-          if ((instr->Bits(4, 2) != 0) ||
-              (instr->Mask(0x00E0001D) == 0x00200001) ||
-              (instr->Mask(0x00E0001D) == 0x00400001) ||
-              (instr->Mask(0x00E0001E) == 0x00200002) ||
-              (instr->Mask(0x00E0001E) == 0x00400002) ||
-              (instr->Mask(0x00E0001C) == 0x00600000) ||
-              (instr->Mask(0x00E0001C) == 0x00800000) ||
-              (instr->Mask(0x00E0001F) == 0x00A00000) ||
-              (instr->Mask(0x00C0001C) == 0x00C00000)) {
-            VisitUnallocated(instr);
-          } else {
-            VisitException(instr);
-          }
-        } else {
-          if (instr->Bits(23, 22) == 0) {
-            const Instr masked_003FF0E0 = instr->Mask(0x003FF0E0);
-            if ((instr->Bits(21, 19) == 0x4) ||
-                (masked_003FF0E0 == 0x00033000) ||
-                (masked_003FF0E0 == 0x003FF020) ||
-                (masked_003FF0E0 == 0x003FF060) ||
-                (masked_003FF0E0 == 0x003FF0E0) ||
-                (instr->Mask(0x00388000) == 0x00008000) ||
-                (instr->Mask(0x0038E000) == 0x00000000) ||
-                (instr->Mask(0x0039E000) == 0x00002000) ||
-                (instr->Mask(0x003AE000) == 0x00002000) ||
-                (instr->Mask(0x003CE000) == 0x00042000) ||
-                (instr->Mask(0x003FFFC0) == 0x000320C0) ||
-                (instr->Mask(0x003FF100) == 0x00032100) ||
-                (instr->Mask(0x003FF200) == 0x00032200) ||
-                (instr->Mask(0x003FF400) == 0x00032400) ||
-                (instr->Mask(0x003FF800) == 0x00032800) ||
-                (instr->Mask(0x0038F000) == 0x00005000) ||
-                (instr->Mask(0x0038E000) == 0x00006000)) {
-              VisitUnallocated(instr);
-            } else {
-              VisitSystem(instr);
-            }
-          } else {
-            VisitUnallocated(instr);
-          }
-        }
-      } else {
-        if ((instr->Bit(24) == 0x1) ||
-            (instr->Bits(20, 16) != 0x1F) ||
-            (instr->Bits(15, 10) != 0) ||
-            (instr->Bits(4, 0) != 0) ||
-            (instr->Bits(24, 21) == 0x3) ||
-            (instr->Bits(24, 22) == 0x3)) {
-          VisitUnallocated(instr);
-        } else {
-          VisitUnconditionalBranchToRegister(instr);
-        }
-      }
-      break;
-    }
-    case 3:
-    case 7: {
-      VisitUnallocated(instr);
-      break;
-    }
-  }
-}
-
-
-void Decoder::DecodeLoadStore(Instruction* instr) {
-  ASSERT((instr->Bits(27, 24) == 0x8) ||
-         (instr->Bits(27, 24) == 0x9) ||
-         (instr->Bits(27, 24) == 0xC) ||
-         (instr->Bits(27, 24) == 0xD) );
-
-  if (instr->Bit(24) == 0) {
-    if (instr->Bit(28) == 0) {
-      if (instr->Bit(29) == 0) {
-        if (instr->Bit(26) == 0) {
-          // TODO: VisitLoadStoreExclusive.
-          VisitUnimplemented(instr);
-        } else {
-          DecodeAdvSIMDLoadStore(instr);
-        }
-      } else {
-        if ((instr->Bits(31, 30) == 0x3) ||
-            (instr->Mask(0xC4400000) == 0x40000000)) {
-          VisitUnallocated(instr);
-        } else {
-          if (instr->Bit(23) == 0) {
-            if (instr->Mask(0xC4400000) == 0xC0400000) {
-              VisitUnallocated(instr);
-            } else {
-              VisitLoadStorePairNonTemporal(instr);
-            }
-          } else {
-            VisitLoadStorePairPostIndex(instr);
-          }
-        }
-      }
-    } else {
-      if (instr->Bit(29) == 0) {
-        if (instr->Mask(0xC4000000) == 0xC4000000) {
-          VisitUnallocated(instr);
-        } else {
-          VisitLoadLiteral(instr);
-        }
-      } else {
-        if ((instr->Mask(0x84C00000) == 0x80C00000) ||
-            (instr->Mask(0x44800000) == 0x44800000) ||
-            (instr->Mask(0x84800000) == 0x84800000)) {
-          VisitUnallocated(instr);
-        } else {
-          if (instr->Bit(21) == 0) {
-            switch (instr->Bits(11, 10)) {
-              case 0: {
-                VisitLoadStoreUnscaledOffset(instr);
-                break;
-              }
-              case 1: {
-                if (instr->Mask(0xC4C00000) == 0xC0800000) {
-                  VisitUnallocated(instr);
-                } else {
-                  VisitLoadStorePostIndex(instr);
-                }
-                break;
-              }
-              case 2: {
-                // TODO: VisitLoadStoreRegisterOffsetUnpriv.
-                VisitUnimplemented(instr);
-                break;
-              }
-              case 3: {
-                if (instr->Mask(0xC4C00000) == 0xC0800000) {
-                  VisitUnallocated(instr);
-                } else {
-                  VisitLoadStorePreIndex(instr);
-                }
-                break;
-              }
-            }
-          } else {
-            if (instr->Bits(11, 10) == 0x2) {
-              if (instr->Bit(14) == 0) {
-                VisitUnallocated(instr);
-              } else {
-                VisitLoadStoreRegisterOffset(instr);
-              }
-            } else {
-              VisitUnallocated(instr);
-            }
-          }
-        }
-      }
-    }
-  } else {
-    if (instr->Bit(28) == 0) {
-      if (instr->Bit(29) == 0) {
-        VisitUnallocated(instr);
-      } else {
-        if ((instr->Bits(31, 30) == 0x3) ||
-            (instr->Mask(0xC4400000) == 0x40000000)) {
-          VisitUnallocated(instr);
-        } else {
-          if (instr->Bit(23) == 0) {
-            VisitLoadStorePairOffset(instr);
-          } else {
-            VisitLoadStorePairPreIndex(instr);
-          }
-        }
-      }
-    } else {
-      if (instr->Bit(29) == 0) {
-        VisitUnallocated(instr);
-      } else {
-        if ((instr->Mask(0x84C00000) == 0x80C00000) ||
-            (instr->Mask(0x44800000) == 0x44800000) ||
-            (instr->Mask(0x84800000) == 0x84800000)) {
-          VisitUnallocated(instr);
-        } else {
-          VisitLoadStoreUnsignedOffset(instr);
-        }
-      }
-    }
-  }
-}
-
-
-void Decoder::DecodeLogical(Instruction* instr) {
-  ASSERT(instr->Bits(27, 24) == 0x2);
-
-  if (instr->Mask(0x80400000) == 0x00400000) {
-    VisitUnallocated(instr);
-  } else {
-    if (instr->Bit(23) == 0) {
-      VisitLogicalImmediate(instr);
-    } else {
-      if (instr->Bits(30, 29) == 0x1) {
-        VisitUnallocated(instr);
-      } else {
-        VisitMoveWideImmediate(instr);
-      }
-    }
-  }
-}
-
-
-void Decoder::DecodeBitfieldExtract(Instruction* instr) {
-  ASSERT(instr->Bits(27, 24) == 0x3);
-
-  if ((instr->Mask(0x80400000) == 0x80000000) ||
-      (instr->Mask(0x80400000) == 0x00400000) ||
-      (instr->Mask(0x80008000) == 0x00008000)) {
-    VisitUnallocated(instr);
-  } else if (instr->Bit(23) == 0) {
-    if ((instr->Mask(0x80200000) == 0x00200000) ||
-        (instr->Mask(0x60000000) == 0x60000000)) {
-      VisitUnallocated(instr);
-    } else {
-      VisitBitfield(instr);
-    }
-  } else {
-    if ((instr->Mask(0x60200000) == 0x00200000) ||
-        (instr->Mask(0x60000000) != 0x00000000)) {
-      VisitUnallocated(instr);
-    } else {
-      VisitExtract(instr);
-    }
-  }
-}
-
-
-void Decoder::DecodeAddSubImmediate(Instruction* instr) {
-  ASSERT(instr->Bits(27, 24) == 0x1);
-  if (instr->Bit(23) == 1) {
-    VisitUnallocated(instr);
-  } else {
-    VisitAddSubImmediate(instr);
-  }
-}
-
-
-void Decoder::DecodeDataProcessing(Instruction* instr) {
-  ASSERT((instr->Bits(27, 24) == 0xA) ||
-         (instr->Bits(27, 24) == 0xB) );
-
-  if (instr->Bit(24) == 0) {
-    if (instr->Bit(28) == 0) {
-      if (instr->Mask(0x80008000) == 0x00008000) {
-        VisitUnallocated(instr);
-      } else {
-        VisitLogicalShifted(instr);
-      }
-    } else {
-      switch (instr->Bits(23, 21)) {
-        case 0: {
-          if (instr->Mask(0x0000FC00) != 0) {
-            VisitUnallocated(instr);
-          } else {
-            VisitAddSubWithCarry(instr);
-          }
-          break;
-        }
-        case 2: {
-          if ((instr->Bit(29) == 0) ||
-              (instr->Mask(0x00000410) != 0)) {
-            VisitUnallocated(instr);
-          } else {
-            if (instr->Bit(11) == 0) {
-              VisitConditionalCompareRegister(instr);
-            } else {
-              VisitConditionalCompareImmediate(instr);
-            }
-          }
-          break;
-        }
-        case 4: {
-          if (instr->Mask(0x20000800) != 0x00000000) {
-            VisitUnallocated(instr);
-          } else {
-            VisitConditionalSelect(instr);
-          }
-          break;
-        }
-        case 6: {
-          if (instr->Bit(29) == 0x1) {
-            VisitUnallocated(instr);
-          } else {
-            if (instr->Bit(30) == 0) {
-              if ((instr->Bit(15) == 0x1) ||
-                  (instr->Bits(15, 11) == 0) ||
-                  (instr->Bits(15, 12) == 0x1) ||
-                  (instr->Bits(15, 12) == 0x3) ||
-                  (instr->Bits(15, 13) == 0x3) ||
-                  (instr->Mask(0x8000EC00) == 0x00004C00) ||
-                  (instr->Mask(0x8000E800) == 0x80004000) ||
-                  (instr->Mask(0x8000E400) == 0x80004000)) {
-                VisitUnallocated(instr);
-              } else {
-                VisitDataProcessing2Source(instr);
-              }
-            } else {
-              if ((instr->Bit(13) == 1) ||
-                  (instr->Bits(20, 16) != 0) ||
-                  (instr->Bits(15, 14) != 0) ||
-                  (instr->Mask(0xA01FFC00) == 0x00000C00) ||
-                  (instr->Mask(0x201FF800) == 0x00001800)) {
-                VisitUnallocated(instr);
-              } else {
-                VisitDataProcessing1Source(instr);
-              }
-            }
-            break;
-          }
-        }
-        case 1:
-        case 3:
-        case 5:
-        case 7: VisitUnallocated(instr); break;
-      }
-    }
-  } else {
-    if (instr->Bit(28) == 0) {
-     if (instr->Bit(21) == 0) {
-        if ((instr->Bits(23, 22) == 0x3) ||
-            (instr->Mask(0x80008000) == 0x00008000)) {
-          VisitUnallocated(instr);
-        } else {
-          VisitAddSubShifted(instr);
-        }
-      } else {
-        if ((instr->Mask(0x00C00000) != 0x00000000) ||
-            (instr->Mask(0x00001400) == 0x00001400) ||
-            (instr->Mask(0x00001800) == 0x00001800)) {
-          VisitUnallocated(instr);
-        } else {
-          VisitAddSubExtended(instr);
-        }
-      }
-    } else {
-      if ((instr->Bit(30) == 0x1) ||
-          (instr->Bits(30, 29) == 0x1) ||
-          (instr->Mask(0xE0600000) == 0x00200000) ||
-          (instr->Mask(0xE0608000) == 0x00400000) ||
-          (instr->Mask(0x60608000) == 0x00408000) ||
-          (instr->Mask(0x60E00000) == 0x00E00000) ||
-          (instr->Mask(0x60E00000) == 0x00800000) ||
-          (instr->Mask(0x60E00000) == 0x00600000)) {
-        VisitUnallocated(instr);
-      } else {
-        VisitDataProcessing3Source(instr);
-      }
-    }
-  }
-}
-
-
-void Decoder::DecodeFP(Instruction* instr) {
-  ASSERT((instr->Bits(27, 24) == 0xE) ||
-         (instr->Bits(27, 24) == 0xF) );
-
-  if (instr->Bit(28) == 0) {
-    DecodeAdvSIMDDataProcessing(instr);
-  } else {
-    if (instr->Bit(29) == 1) {
-      VisitUnallocated(instr);
-    } else {
-      if (instr->Bits(31, 30) == 0x3) {
-        VisitUnallocated(instr);
-      } else if (instr->Bits(31, 30) == 0x1) {
-        DecodeAdvSIMDDataProcessing(instr);
-      } else {
-        if (instr->Bit(24) == 0) {
-          if (instr->Bit(21) == 0) {
-            if ((instr->Bit(23) == 1) ||
-                (instr->Bit(18) == 1) ||
-                (instr->Mask(0x80008000) == 0x00000000) ||
-                (instr->Mask(0x000E0000) == 0x00000000) ||
-                (instr->Mask(0x000E0000) == 0x000A0000) ||
-                (instr->Mask(0x00160000) == 0x00000000) ||
-                (instr->Mask(0x00160000) == 0x00120000)) {
-              VisitUnallocated(instr);
-            } else {
-              VisitFPFixedPointConvert(instr);
-            }
-          } else {
-            if (instr->Bits(15, 10) == 32) {
-              VisitUnallocated(instr);
-            } else if (instr->Bits(15, 10) == 0) {
-              if ((instr->Bits(23, 22) == 0x3) ||
-                  (instr->Mask(0x000E0000) == 0x000A0000) ||
-                  (instr->Mask(0x000E0000) == 0x000C0000) ||
-                  (instr->Mask(0x00160000) == 0x00120000) ||
-                  (instr->Mask(0x00160000) == 0x00140000) ||
-                  (instr->Mask(0x20C40000) == 0x00800000) ||
-                  (instr->Mask(0x20C60000) == 0x00840000) ||
-                  (instr->Mask(0xA0C60000) == 0x80060000) ||
-                  (instr->Mask(0xA0C60000) == 0x00860000) ||
-                  (instr->Mask(0xA0C60000) == 0x00460000) ||
-                  (instr->Mask(0xA0CE0000) == 0x80860000) ||
-                  (instr->Mask(0xA0CE0000) == 0x804E0000) ||
-                  (instr->Mask(0xA0CE0000) == 0x000E0000) ||
-                  (instr->Mask(0xA0D60000) == 0x00160000) ||
-                  (instr->Mask(0xA0D60000) == 0x80560000) ||
-                  (instr->Mask(0xA0D60000) == 0x80960000)) {
-                VisitUnallocated(instr);
-              } else {
-                VisitFPIntegerConvert(instr);
-              }
-            } else if (instr->Bits(14, 10) == 16) {
-              const Instr masked_A0DF8000 = instr->Mask(0xA0DF8000);
-              if ((instr->Mask(0x80180000) != 0) ||
-                  (masked_A0DF8000 == 0x00020000) ||
-                  (masked_A0DF8000 == 0x00030000) ||
-                  (masked_A0DF8000 == 0x00068000) ||
-                  (masked_A0DF8000 == 0x00428000) ||
-                  (masked_A0DF8000 == 0x00430000) ||
-                  (masked_A0DF8000 == 0x00468000) ||
-                  (instr->Mask(0xA0D80000) == 0x00800000) ||
-                  (instr->Mask(0xA0DE0000) == 0x00C00000) ||
-                  (instr->Mask(0xA0DF0000) == 0x00C30000) ||
-                  (instr->Mask(0xA0DC0000) == 0x00C40000)) {
-                VisitUnallocated(instr);
-              } else {
-                VisitFPDataProcessing1Source(instr);
-              }
-            } else if (instr->Bits(13, 10) == 8) {
-              if ((instr->Bits(15, 14) != 0) ||
-                  (instr->Bits(2, 0) != 0) ||
-                  (instr->Mask(0x80800000) != 0x00000000)) {
-                VisitUnallocated(instr);
-              } else {
-                VisitFPCompare(instr);
-              }
-            } else if (instr->Bits(12, 10) == 4) {
-              if ((instr->Bits(9, 5) != 0) ||
-                  (instr->Mask(0x80800000) != 0x00000000)) {
-                VisitUnallocated(instr);
-              } else {
-                VisitFPImmediate(instr);
-              }
-            } else {
-              if (instr->Mask(0x80800000) != 0x00000000) {
-                VisitUnallocated(instr);
-              } else {
-                switch (instr->Bits(11, 10)) {
-                  case 1: {
-                    VisitFPConditionalCompare(instr);
-                    break;
-                  }
-                  case 2: {
-                    if ((instr->Bits(15, 14) == 0x3) ||
-                        (instr->Mask(0x00009000) == 0x00009000) ||
-                        (instr->Mask(0x0000A000) == 0x0000A000)) {
-                      VisitUnallocated(instr);
-                    } else {
-                      VisitFPDataProcessing2Source(instr);
-                    }
-                    break;
-                  }
-                  case 3: {
-                    VisitFPConditionalSelect(instr);
-                    break;
-                  }
-                  default: UNREACHABLE();
-                }
-              }
-            }
-          }
-        } else {
-          // Bit 30 == 1 has been handled earlier.
-          ASSERT(instr->Bit(30) == 0);
-          if (instr->Mask(0xA0800000) != 0) {
-            VisitUnallocated(instr);
-          } else {
-            VisitFPDataProcessing3Source(instr);
-          }
-        }
-      }
-    }
-  }
-}
-
-
-void Decoder::DecodeAdvSIMDLoadStore(Instruction* instr) {
-  // TODO: Implement Advanced SIMD load/store instruction decode.
-  ASSERT(instr->Bits(29, 25) == 0x6);
-  VisitUnimplemented(instr);
-}
-
-
-void Decoder::DecodeAdvSIMDDataProcessing(Instruction* instr) {
-  // TODO: Implement Advanced SIMD data processing instruction decode.
-  ASSERT(instr->Bits(27, 25) == 0x7);
-  VisitUnimplemented(instr);
-}
-
-
-#define DEFINE_VISITOR_CALLERS(A)                                              \
-  void Decoder::Visit##A(Instruction *instr) {                                 \
-    ASSERT(instr->Mask(A##FMask) == A##Fixed);                                 \
-    std::list<DecoderVisitor*>::iterator it;                                   \
-    for (it = visitors_.begin(); it != visitors_.end(); it++) {                \
-      (*it)->Visit##A(instr);                                                  \
-    }                                                                          \
-  }
-VISITOR_LIST(DEFINE_VISITOR_CALLERS)
-#undef DEFINE_VISITOR_CALLERS
-}  // namespace vixl
@@ -1,198 +0,0 @@
-// Copyright 2013, ARM Limited
-// All rights reserved.
-//
-// Redistribution and use in source and binary forms, with or without
-// modification, are permitted provided that the following conditions are met:
-//
-//   * Redistributions of source code must retain the above copyright notice,
-//     this list of conditions and the following disclaimer.
-//   * Redistributions in binary form must reproduce the above copyright notice,
-//     this list of conditions and the following disclaimer in the documentation
-//     and/or other materials provided with the distribution.
-//   * Neither the name of ARM Limited nor the names of its contributors may be
-//     used to endorse or promote products derived from this software without
-//     specific prior written permission.
-//
-// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
-// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
-// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-#ifndef VIXL_A64_DECODER_A64_H_
-#define VIXL_A64_DECODER_A64_H_
-
-#include <list>
-
-#include "globals.h"
-#include "a64/instructions-a64.h"
-
-
-// List macro containing all visitors needed by the decoder class.
-
-#define VISITOR_LIST(V)             \
-  V(PCRelAddressing)                \
-  V(AddSubImmediate)                \
-  V(LogicalImmediate)               \
-  V(MoveWideImmediate)              \
-  V(Bitfield)                       \
-  V(Extract)                        \
-  V(UnconditionalBranch)            \
-  V(UnconditionalBranchToRegister)  \
-  V(CompareBranch)                  \
-  V(TestBranch)                     \
-  V(ConditionalBranch)              \
-  V(System)                         \
-  V(Exception)                      \
-  V(LoadStorePairPostIndex)         \
-  V(LoadStorePairOffset)            \
-  V(LoadStorePairPreIndex)          \
-  V(LoadStorePairNonTemporal)       \
-  V(LoadLiteral)                    \
-  V(LoadStoreUnscaledOffset)        \
-  V(LoadStorePostIndex)             \
-  V(LoadStorePreIndex)              \
-  V(LoadStoreRegisterOffset)        \
-  V(LoadStoreUnsignedOffset)        \
-  V(LogicalShifted)                 \
-  V(AddSubShifted)                  \
-  V(AddSubExtended)                 \
-  V(AddSubWithCarry)                \
-  V(ConditionalCompareRegister)     \
-  V(ConditionalCompareImmediate)    \
-  V(ConditionalSelect)              \
-  V(DataProcessing1Source)          \
-  V(DataProcessing2Source)          \
-  V(DataProcessing3Source)          \
-  V(FPCompare)                      \
-  V(FPConditionalCompare)           \
-  V(FPConditionalSelect)            \
-  V(FPImmediate)                    \
-  V(FPDataProcessing1Source)        \
-  V(FPDataProcessing2Source)        \
-  V(FPDataProcessing3Source)        \
-  V(FPIntegerConvert)               \
-  V(FPFixedPointConvert)            \
-  V(Unallocated)                    \
-  V(Unimplemented)
-
-namespace vixl {
-
-// The Visitor interface. Disassembler and simulator (and other tools)
-// must provide implementations for all of these functions.
-class DecoderVisitor {
- public:
-  #define DECLARE(A) virtual void Visit##A(Instruction* instr) = 0;
-  VISITOR_LIST(DECLARE)
-  #undef DECLARE
-
-  virtual ~DecoderVisitor() {}
-
- private:
-  // Visitors are registered in a list.
-  std::list<DecoderVisitor*> visitors_;
-
-  friend class Decoder;
-};
-
-
-class Decoder: public DecoderVisitor {
- public:
-  Decoder() {}
-
-  // Top-level instruction decoder function. Decodes an instruction and calls
-  // the visitor functions registered with the Decoder class.
-  void Decode(Instruction *instr);
-
-  // Register a new visitor class with the decoder.
-  // Decode() will call the corresponding visitor method from all registered
-  // visitor classes when decoding reaches the leaf node of the instruction
-  // decode tree.
-  // Visitors are called in the order.
-  // A visitor can only be registered once.
-  // Registering an already registered visitor will update its position.
-  //
-  //   d.AppendVisitor(V1);
-  //   d.AppendVisitor(V2);
-  //   d.PrependVisitor(V2);            // Move V2 at the start of the list.
-  //   d.InsertVisitorBefore(V3, V2);
-  //   d.AppendVisitor(V4);
-  //   d.AppendVisitor(V4);             // No effect.
-  //
-  //   d.Decode(i);
-  //
-  // will call in order visitor methods in V3, V2, V1, V4.
-  void AppendVisitor(DecoderVisitor* visitor);
-  void PrependVisitor(DecoderVisitor* visitor);
-  void InsertVisitorBefore(DecoderVisitor* new_visitor,
-                           DecoderVisitor* registered_visitor);
-  void InsertVisitorAfter(DecoderVisitor* new_visitor,
-                          DecoderVisitor* registered_visitor);
-
-  // Remove a previously registered visitor class from the list of visitors
-  // stored by the decoder.
-  void RemoveVisitor(DecoderVisitor* visitor);
-
-  #define DECLARE(A) void Visit##A(Instruction* instr);
-  VISITOR_LIST(DECLARE)
-  #undef DECLARE
-
- private:
-  // Decode the PC relative addressing instruction, and call the corresponding
-  // visitors.
-  // On entry, instruction bits 27:24 = 0x0.
-  void DecodePCRelAddressing(Instruction* instr);
-
-  // Decode the add/subtract immediate instruction, and call the correspoding
-  // visitors.
-  // On entry, instruction bits 27:24 = 0x1.
-  void DecodeAddSubImmediate(Instruction* instr);
-
-  // Decode the branch, system command, and exception generation parts of
-  // the instruction tree, and call the corresponding visitors.
-  // On entry, instruction bits 27:24 = {0x4, 0x5, 0x6, 0x7}.
-  void DecodeBranchSystemException(Instruction* instr);
-
-  // Decode the load and store parts of the instruction tree, and call
-  // the corresponding visitors.
-  // On entry, instruction bits 27:24 = {0x8, 0x9, 0xC, 0xD}.
-  void DecodeLoadStore(Instruction* instr);
-
-  // Decode the logical immediate and move wide immediate parts of the
-  // instruction tree, and call the corresponding visitors.
-  // On entry, instruction bits 27:24 = 0x2.
-  void DecodeLogical(Instruction* instr);
-
-  // Decode the bitfield and extraction parts of the instruction tree,
-  // and call the corresponding visitors.
-  // On entry, instruction bits 27:24 = 0x3.
-  void DecodeBitfieldExtract(Instruction* instr);
-
-  // Decode the data processing parts of the instruction tree, and call the
-  // corresponding visitors.
-  // On entry, instruction bits 27:24 = {0x1, 0xA, 0xB}.
-  void DecodeDataProcessing(Instruction* instr);
-
-  // Decode the floating point parts of the instruction tree, and call the
-  // corresponding visitors.
-  // On entry, instruction bits 27:24 = {0xE, 0xF}.
-  void DecodeFP(Instruction* instr);
-
-  // Decode the Advanced SIMD (NEON) load/store part of the instruction tree,
-  // and call the corresponding visitors.
-  // On entry, instruction bits 29:25 = 0x6.
-  void DecodeAdvSIMDLoadStore(Instruction* instr);
-
-  // Decode the Advanced SIMD (NEON) data processing part of the instruction
-  // tree, and call the corresponding visitors.
-  // On entry, instruction bits 27:25 = 0x7.
-  void DecodeAdvSIMDDataProcessing(Instruction* instr);
-};
-}  // namespace vixl
-
-#endif  // VIXL_A64_DECODER_A64_H_
@@ -1,109 +0,0 @@
-// Copyright 2013, ARM Limited
-// All rights reserved.
-//
-// Redistribution and use in source and binary forms, with or without
-// modification, are permitted provided that the following conditions are met:
-//
-//   * Redistributions of source code must retain the above copyright notice,
-//     this list of conditions and the following disclaimer.
-//   * Redistributions in binary form must reproduce the above copyright notice,
-//     this list of conditions and the following disclaimer in the documentation
-//     and/or other materials provided with the distribution.
-//   * Neither the name of ARM Limited nor the names of its contributors may be
-//     used to endorse or promote products derived from this software without
-//     specific prior written permission.
-//
-// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
-// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
-// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-#ifndef VIXL_A64_DISASM_A64_H
-#define VIXL_A64_DISASM_A64_H
-
-#include "globals.h"
-#include "utils.h"
-#include "instructions-a64.h"
-#include "decoder-a64.h"
-
-namespace vixl {
-
-class Disassembler: public DecoderVisitor {
- public:
-  Disassembler();
-  Disassembler(char* text_buffer, int buffer_size);
-  virtual ~Disassembler();
-  char* GetOutput();
-
-  // Declare all Visitor functions.
-  #define DECLARE(A)  void Visit##A(Instruction* instr);
-  VISITOR_LIST(DECLARE)
-  #undef DECLARE
-
- protected:
-  virtual void ProcessOutput(Instruction* instr);
-
- private:
-  void Format(Instruction* instr, const char* mnemonic, const char* format);
-  void Substitute(Instruction* instr, const char* string);
-  int SubstituteField(Instruction* instr, const char* format);
-  int SubstituteRegisterField(Instruction* instr, const char* format);
-  int SubstituteImmediateField(Instruction* instr, const char* format);
-  int SubstituteLiteralField(Instruction* instr, const char* format);
-  int SubstituteBitfieldImmediateField(Instruction* instr, const char* format);
-  int SubstituteShiftField(Instruction* instr, const char* format);
-  int SubstituteExtendField(Instruction* instr, const char* format);
-  int SubstituteConditionField(Instruction* instr, const char* format);
-  int SubstitutePCRelAddressField(Instruction* instr, const char* format);
-  int SubstituteBranchTargetField(Instruction* instr, const char* format);
-  int SubstituteLSRegOffsetField(Instruction* instr, const char* format);
-  int SubstitutePrefetchField(Instruction* instr, const char* format);
-
-  inline bool RdIsZROrSP(Instruction* instr) const {
-    return (instr->Rd() == kZeroRegCode);
-  }
-
-  inline bool RnIsZROrSP(Instruction* instr) const {
-    return (instr->Rn() == kZeroRegCode);
-  }
-
-  inline bool RmIsZROrSP(Instruction* instr) const {
-    return (instr->Rm() == kZeroRegCode);
-  }
-
-  inline bool RaIsZROrSP(Instruction* instr) const {
-    return (instr->Ra() == kZeroRegCode);
-  }
-
-  bool IsMovzMovnImm(unsigned reg_size, uint64_t value);
-
-  void ResetOutput();
-  void AppendToOutput(const char* string, ...);
-
-  char* buffer_;
-  uint32_t buffer_pos_;
-  uint32_t buffer_size_;
-  bool own_buffer_;
-};
-
-
-class PrintDisassembler: public Disassembler {
- public:
-  explicit PrintDisassembler(FILE* stream) : stream_(stream) { }
-  ~PrintDisassembler() { }
-
- protected:
-  virtual void ProcessOutput(Instruction* instr);
-
- private:
-  FILE *stream_;
-};
-}  // namespace vixl
-
-#endif  // VIXL_A64_DISASM_A64_H
@@ -1,238 +0,0 @@
-// Copyright 2013, ARM Limited
-// All rights reserved.
-//
-// Redistribution and use in source and binary forms, with or without
-// modification, are permitted provided that the following conditions are met:
-//
-//   * Redistributions of source code must retain the above copyright notice,
-//     this list of conditions and the following disclaimer.
-//   * Redistributions in binary form must reproduce the above copyright notice,
-//     this list of conditions and the following disclaimer in the documentation
-//     and/or other materials provided with the distribution.
-//   * Neither the name of ARM Limited nor the names of its contributors may be
-//     used to endorse or promote products derived from this software without
-//     specific prior written permission.
-//
-// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
-// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
-// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-#include "a64/instructions-a64.h"
-#include "a64/assembler-a64.h"
-
-namespace vixl {
-
-
-static uint64_t RotateRight(uint64_t value,
-                            unsigned int rotate,
-                            unsigned int width) {
-  ASSERT(width <= 64);
-  rotate &= 63;
-  return ((value & ((1UL << rotate) - 1UL)) << (width - rotate)) |
-         (value >> rotate);
-}
-
-
-static uint64_t RepeatBitsAcrossReg(unsigned reg_size,
-                                    uint64_t value,
-                                    unsigned width) {
-  ASSERT((width == 2) || (width == 4) || (width == 8) || (width == 16) ||
-         (width == 32));
-  ASSERT((reg_size == kWRegSize) || (reg_size == kXRegSize));
-  uint64_t result = value & ((1UL << width) - 1UL);
-  for (unsigned i = width; i < reg_size; i *= 2) {
-    result |= (result << i);
-  }
-  return result;
-}
-
-
-// Logical immediates can't encode zero, so a return value of zero is used to
-// indicate a failure case. Specifically, where the constraints on imm_s are
-// not met.
-uint64_t Instruction::ImmLogical() {
-  unsigned reg_size = SixtyFourBits() ? kXRegSize : kWRegSize;
-  int64_t n = BitN();
-  int64_t imm_s = ImmSetBits();
-  int64_t imm_r = ImmRotate();
-
-  // An integer is constructed from the n, imm_s and imm_r bits according to
-  // the following table:
-  //
-  //  N   imms    immr    size        S             R
-  //  1  ssssss  rrrrrr    64    UInt(ssssss)  UInt(rrrrrr)
-  //  0  0sssss  xrrrrr    32    UInt(sssss)   UInt(rrrrr)
-  //  0  10ssss  xxrrrr    16    UInt(ssss)    UInt(rrrr)
-  //  0  110sss  xxxrrr     8    UInt(sss)     UInt(rrr)
-  //  0  1110ss  xxxxrr     4    UInt(ss)      UInt(rr)
-  //  0  11110s  xxxxxr     2    UInt(s)       UInt(r)
-  // (s bits must not be all set)
-  //
-  // A pattern is constructed of size bits, where the least significant S+1
-  // bits are set. The pattern is rotated right by R, and repeated across a
-  // 32 or 64-bit value, depending on destination register width.
-  //
-
-  if (n == 1) {
-    if (imm_s == 0x3F) {
-      return 0;
-    }
-    uint64_t bits = (1UL << (imm_s + 1)) - 1;
-    return RotateRight(bits, imm_r, 64);
-  } else {
-    if ((imm_s >> 1) == 0x1F) {
-      return 0;
-    }
-    for (int width = 0x20; width >= 0x2; width >>= 1) {
-      if ((imm_s & width) == 0) {
-        int mask = width - 1;
-        if ((imm_s & mask) == mask) {
-          return 0;
-        }
-        uint64_t bits = (1UL << ((imm_s & mask) + 1)) - 1;
-        return RepeatBitsAcrossReg(reg_size,
-                                   RotateRight(bits, imm_r & mask, width),
-                                   width);
-      }
-    }
-  }
-  UNREACHABLE();
-  return 0;
-}
-
-
-float Instruction::ImmFP32() {
-  //  ImmFP: abcdefgh (8 bits)
-  // Single: aBbb.bbbc.defg.h000.0000.0000.0000.0000 (32 bits)
-  // where B is b ^ 1
-  uint32_t bits = ImmFP();
-  uint32_t bit7 = (bits >> 7) & 0x1;
-  uint32_t bit6 = (bits >> 6) & 0x1;
-  uint32_t bit5_to_0 = bits & 0x3f;
-  uint32_t result = (bit7 << 31) | ((32 - bit6) << 25) | (bit5_to_0 << 19);
-
-  return rawbits_to_float(result);
-}
-
-
-double Instruction::ImmFP64() {
-  //  ImmFP: abcdefgh (8 bits)
-  // Double: aBbb.bbbb.bbcd.efgh.0000.0000.0000.0000
-  //         0000.0000.0000.0000.0000.0000.0000.0000 (64 bits)
-  // where B is b ^ 1
-  uint32_t bits = ImmFP();
-  uint64_t bit7 = (bits >> 7) & 0x1;
-  uint64_t bit6 = (bits >> 6) & 0x1;
-  uint64_t bit5_to_0 = bits & 0x3f;
-  uint64_t result = (bit7 << 63) | ((256 - bit6) << 54) | (bit5_to_0 << 48);
-
-  return rawbits_to_double(result);
-}
-
-
-LSDataSize CalcLSPairDataSize(LoadStorePairOp op) {
-  switch (op) {
-    case STP_x:
-    case LDP_x:
-    case STP_d:
-    case LDP_d: return LSDoubleWord;
-    default: return LSWord;
-  }
-}
-
-
-Instruction* Instruction::ImmPCOffsetTarget() {
-  ptrdiff_t offset;
-  if (IsPCRelAddressing()) {
-    // PC-relative addressing. Only ADR is supported.
-    offset = ImmPCRel();
-  } else {
-    // All PC-relative branches.
-    ASSERT(BranchType() != UnknownBranchType);
-    // Relative branch offsets are instruction-size-aligned.
-    offset = ImmBranch() << kInstructionSizeLog2;
-  }
-  return this + offset;
-}
-
-
-inline int Instruction::ImmBranch() const {
-  switch (BranchType()) {
-    case CondBranchType: return ImmCondBranch();
-    case UncondBranchType: return ImmUncondBranch();
-    case CompareBranchType: return ImmCmpBranch();
-    case TestBranchType: return ImmTestBranch();
-    default: UNREACHABLE();
-  }
-  return 0;
-}
-
-
-void Instruction::SetImmPCOffsetTarget(Instruction* target) {
-  if (IsPCRelAddressing()) {
-    SetPCRelImmTarget(target);
-  } else {
-    SetBranchImmTarget(target);
-  }
-}
-
-
-void Instruction::SetPCRelImmTarget(Instruction* target) {
-  // ADRP is not supported, so 'this' must point to an ADR instruction.
-  ASSERT(Mask(PCRelAddressingMask) == ADR);
-
-  Instr imm = Assembler::ImmPCRelAddress(target - this);
-
-  SetInstructionBits(Mask(~ImmPCRel_mask) | imm);
-}
-
-
-void Instruction::SetBranchImmTarget(Instruction* target) {
-  ASSERT(((target - this) & 3) == 0);
-  Instr branch_imm = 0;
-  uint32_t imm_mask = 0;
-  int offset = (target - this) >> kInstructionSizeLog2;
-  switch (BranchType()) {
-    case CondBranchType: {
-      branch_imm = Assembler::ImmCondBranch(offset);
-      imm_mask = ImmCondBranch_mask;
-      break;
-    }
-    case UncondBranchType: {
-      branch_imm = Assembler::ImmUncondBranch(offset);
-      imm_mask = ImmUncondBranch_mask;
-      break;
-    }
-    case CompareBranchType: {
-      branch_imm = Assembler::ImmCmpBranch(offset);
-      imm_mask = ImmCmpBranch_mask;
-      break;
-    }
-    case TestBranchType: {
-      branch_imm = Assembler::ImmTestBranch(offset);
-      imm_mask = ImmTestBranch_mask;
-      break;
-    }
-    default: UNREACHABLE();
-  }
-  SetInstructionBits(Mask(~imm_mask) | branch_imm);
-}
-
-
-void Instruction::SetImmLLiteral(Instruction* source) {
-  ASSERT(((source - this) & 3) == 0);
-  int offset = (source - this) >> kLiteralEntrySizeLog2;
-  Instr imm = Assembler::ImmLLiteral(offset);
-  Instr mask = ImmLLiteral_mask;
-
-  SetInstructionBits(Mask(~mask) | imm);
-}
-}  // namespace vixl
-
@@ -1,344 +0,0 @@
-// Copyright 2013, ARM Limited
-// All rights reserved.
-//
-// Redistribution and use in source and binary forms, with or without
-// modification, are permitted provided that the following conditions are met:
-//
-//   * Redistributions of source code must retain the above copyright notice,
-//     this list of conditions and the following disclaimer.
-//   * Redistributions in binary form must reproduce the above copyright notice,
-//     this list of conditions and the following disclaimer in the documentation
-//     and/or other materials provided with the distribution.
-//   * Neither the name of ARM Limited nor the names of its contributors may be
-//     used to endorse or promote products derived from this software without
-//     specific prior written permission.
-//
-// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
-// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
-// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-#ifndef VIXL_A64_INSTRUCTIONS_A64_H_
-#define VIXL_A64_INSTRUCTIONS_A64_H_
-
-#include "globals.h"
-#include "utils.h"
-#include "a64/constants-a64.h"
-
-namespace vixl {
-// ISA constants. --------------------------------------------------------------
-
-typedef uint32_t Instr;
-const unsigned kInstructionSize = 4;
-const unsigned kInstructionSizeLog2 = 2;
-const unsigned kLiteralEntrySize = 4;
-const unsigned kLiteralEntrySizeLog2 = 2;
-const unsigned kMaxLoadLiteralRange = 1 * MBytes;
-
-const unsigned kWRegSize = 32;
-const unsigned kWRegSizeLog2 = 5;
-const unsigned kWRegSizeInBytes = kWRegSize / 8;
-const unsigned kXRegSize = 64;
-const unsigned kXRegSizeLog2 = 6;
-const unsigned kXRegSizeInBytes = kXRegSize / 8;
-const unsigned kSRegSize = 32;
-const unsigned kSRegSizeLog2 = 5;
-const unsigned kSRegSizeInBytes = kSRegSize / 8;
-const unsigned kDRegSize = 64;
-const unsigned kDRegSizeLog2 = 6;
-const unsigned kDRegSizeInBytes = kDRegSize / 8;
-const int64_t kWRegMask = 0x00000000ffffffffLL;
-const int64_t kXRegMask = 0xffffffffffffffffLL;
-const int64_t kSRegMask = 0x00000000ffffffffLL;
-const int64_t kDRegMask = 0xffffffffffffffffLL;
-const int64_t kXSignMask = 0x1LL << 63;
-const int64_t kWSignMask = 0x1LL << 31;
-const int64_t kByteMask = 0xffL;
-const int64_t kHalfWordMask = 0xffffL;
-const int64_t kWordMask = 0xffffffffLL;
-const uint64_t kXMaxUInt = 0xffffffffffffffffULL;
-const uint64_t kWMaxUInt = 0xffffffffULL;
-const int64_t kXMaxInt = 0x7fffffffffffffffLL;
-const int64_t kXMinInt = 0x8000000000000000LL;
-const int32_t kWMaxInt = 0x7fffffff;
-const int32_t kWMinInt = 0x80000000;
-const unsigned kLinkRegCode = 30;
-const unsigned kZeroRegCode = 31;
-const unsigned kSPRegInternalCode = 63;
-const unsigned kRegCodeMask = 0x1f;
-
-// AArch64 floating-point specifics. These match IEEE-754.
-const unsigned kDoubleMantissaBits = 52;
-const unsigned kDoubleExponentBits = 11;
-const unsigned kFloatMantissaBits = 23;
-const unsigned kFloatExponentBits = 8;
-
-const float kFP32PositiveInfinity = rawbits_to_float(0x7f800000);
-const float kFP32NegativeInfinity = rawbits_to_float(0xff800000);
-const double kFP64PositiveInfinity = rawbits_to_double(0x7ff0000000000000ULL);
-const double kFP64NegativeInfinity = rawbits_to_double(0xfff0000000000000ULL);
-
-// This value is a signalling NaN as both a double and as a float (taking the
-// least-significant word).
-static const double kFP64SignallingNaN = rawbits_to_double(0x7ff000007f800001ULL);
-static const float kFP32SignallingNaN = rawbits_to_float(0x7f800001);
-
-// A similar value, but as a quiet NaN.
-static const double kFP64QuietNaN = rawbits_to_double(0x7ff800007fc00001ULL);
-static const float kFP32QuietNaN = rawbits_to_float(0x7fc00001);
-
-enum LSDataSize {
-  LSByte        = 0,
-  LSHalfword    = 1,
-  LSWord        = 2,
-  LSDoubleWord  = 3
-};
-
-LSDataSize CalcLSPairDataSize(LoadStorePairOp op);
-
-enum ImmBranchType {
-  UnknownBranchType = 0,
-  CondBranchType    = 1,
-  UncondBranchType  = 2,
-  CompareBranchType = 3,
-  TestBranchType    = 4
-};
-
-enum AddrMode {
-  Offset,
-  PreIndex,
-  PostIndex
-};
-
-enum FPRounding {
-  // The first four values are encodable directly by FPCR<RMode>.
-  FPTieEven = 0x0,
-  FPPositiveInfinity = 0x1,
-  FPNegativeInfinity = 0x2,
-  FPZero = 0x3,
-
-  // The final rounding mode is only available when explicitly specified by the
-  // instruction (such as with fcvta). It cannot be set in FPCR.
-  FPTieAway
-};
-
-enum Reg31Mode {
-  Reg31IsStackPointer,
-  Reg31IsZeroRegister
-};
-
-// Instructions. ---------------------------------------------------------------
-
-class Instruction {
- public:
-  inline Instr InstructionBits() const {
-    return *(reinterpret_cast<const Instr*>(this));
-  }
-
-  inline void SetInstructionBits(Instr new_instr) {
-    *(reinterpret_cast<Instr*>(this)) = new_instr;
-  }
-
-  inline int Bit(int pos) const {
-    return (InstructionBits() >> pos) & 1;
-  }
-
-  inline uint32_t Bits(int msb, int lsb) const {
-    return unsigned_bitextract_32(msb, lsb, InstructionBits());
-  }
-
-  inline int32_t SignedBits(int msb, int lsb) const {
-    int32_t bits = *(reinterpret_cast<const int32_t*>(this));
-    return signed_bitextract_32(msb, lsb, bits);
-  }
-
-  inline Instr Mask(uint32_t mask) const {
-    return InstructionBits() & mask;
-  }
-
-  #define DEFINE_GETTER(Name, HighBit, LowBit, Func)             \
-  inline int64_t Name() const { return Func(HighBit, LowBit); }
-  INSTRUCTION_FIELDS_LIST(DEFINE_GETTER)
-  #undef DEFINE_GETTER
-
-  // ImmPCRel is a compound field (not present in INSTRUCTION_FIELDS_LIST),
-  // formed from ImmPCRelLo and ImmPCRelHi.
-  int ImmPCRel() const {
-    int const offset = ((ImmPCRelHi() << ImmPCRelLo_width) | ImmPCRelLo());
-    int const width = ImmPCRelLo_width + ImmPCRelHi_width;
-    return signed_bitextract_32(width-1, 0, offset);
-  }
-
-  uint64_t ImmLogical();
-  float ImmFP32();
-  double ImmFP64();
-
-  inline LSDataSize SizeLSPair() const {
-    return CalcLSPairDataSize(
-             static_cast<LoadStorePairOp>(Mask(LoadStorePairMask)));
-  }
-
-  // Helpers.
-  inline bool IsCondBranchImm() const {
-    return Mask(ConditionalBranchFMask) == ConditionalBranchFixed;
-  }
-
-  inline bool IsUncondBranchImm() const {
-    return Mask(UnconditionalBranchFMask) == UnconditionalBranchFixed;
-  }
-
-  inline bool IsCompareBranch() const {
-    return Mask(CompareBranchFMask) == CompareBranchFixed;
-  }
-
-  inline bool IsTestBranch() const {
-    return Mask(TestBranchFMask) == TestBranchFixed;
-  }
-
-  inline bool IsPCRelAddressing() const {
-    return Mask(PCRelAddressingFMask) == PCRelAddressingFixed;
-  }
-
-  inline bool IsLogicalImmediate() const {
-    return Mask(LogicalImmediateFMask) == LogicalImmediateFixed;
-  }
-
-  inline bool IsAddSubImmediate() const {
-    return Mask(AddSubImmediateFMask) == AddSubImmediateFixed;
-  }
-
-  inline bool IsAddSubExtended() const {
-    return Mask(AddSubExtendedFMask) == AddSubExtendedFixed;
-  }
-
-  inline bool IsLoadOrStore() const {
-    return Mask(LoadStoreAnyFMask) == LoadStoreAnyFixed;
-  }
-
-  inline bool IsMovn() const {
-    return (Mask(MoveWideImmediateMask) == MOVN_x) ||
-           (Mask(MoveWideImmediateMask) == MOVN_w);
-  }
-
-  // Indicate whether Rd can be the stack pointer or the zero register. This
-  // does not check that the instruction actually has an Rd field.
-  inline Reg31Mode RdMode() const {
-    // The following instructions use sp or wsp as Rd:
-    //  Add/sub (immediate) when not setting the flags.
-    //  Add/sub (extended) when not setting the flags.
-    //  Logical (immediate) when not setting the flags.
-    // Otherwise, r31 is the zero register.
-    if (IsAddSubImmediate() || IsAddSubExtended()) {
-      if (Mask(AddSubSetFlagsBit)) {
-        return Reg31IsZeroRegister;
-      } else {
-        return Reg31IsStackPointer;
-      }
-    }
-    if (IsLogicalImmediate()) {
-      // Of the logical (immediate) instructions, only ANDS (and its aliases)
-      // can set the flags. The others can all write into sp.
-      // Note that some logical operations are not available to
-      // immediate-operand instructions, so we have to combine two masks here.
-      if (Mask(LogicalImmediateMask & LogicalOpMask) == ANDS) {
-        return Reg31IsZeroRegister;
-      } else {
-        return Reg31IsStackPointer;
-      }
-    }
-    return Reg31IsZeroRegister;
-  }
-
-  // Indicate whether Rn can be the stack pointer or the zero register. This
-  // does not check that the instruction actually has an Rn field.
-  inline Reg31Mode RnMode() const {
-    // The following instructions use sp or wsp as Rn:
-    //  All loads and stores.
-    //  Add/sub (immediate).
-    //  Add/sub (extended).
-    // Otherwise, r31 is the zero register.
-    if (IsLoadOrStore() || IsAddSubImmediate() || IsAddSubExtended()) {
-      return Reg31IsStackPointer;
-    }
-    return Reg31IsZeroRegister;
-  }
-
-  inline ImmBranchType BranchType() const {
-    if (IsCondBranchImm()) {
-      return CondBranchType;
-    } else if (IsUncondBranchImm()) {
-      return UncondBranchType;
-    } else if (IsCompareBranch()) {
-      return CompareBranchType;
-    } else if (IsTestBranch()) {
-      return TestBranchType;
-    } else {
-      return UnknownBranchType;
-    }
-  }
-
-  // Find the target of this instruction. 'this' may be a branch or a
-  // PC-relative addressing instruction.
-  Instruction* ImmPCOffsetTarget();
-
-  // Patch a PC-relative offset to refer to 'target'. 'this' may be a branch or
-  // a PC-relative addressing instruction.
-  void SetImmPCOffsetTarget(Instruction* target);
-  // Patch a literal load instruction to load from 'source'.
-  void SetImmLLiteral(Instruction* source);
-
-  inline uint8_t* LiteralAddress() {
-    int offset = ImmLLiteral() << kLiteralEntrySizeLog2;
-    return reinterpret_cast<uint8_t*>(this) + offset;
-  }
-
-  inline uint32_t Literal32() {
-    uint32_t literal;
-    memcpy(&literal, LiteralAddress(), sizeof(literal));
-
-    return literal;
-  }
-
-  inline uint64_t Literal64() {
-    uint64_t literal;
-    memcpy(&literal, LiteralAddress(), sizeof(literal));
-
-    return literal;
-  }
-
-  inline float LiteralFP32() {
-    return rawbits_to_float(Literal32());
-  }
-
-  inline double LiteralFP64() {
-    return rawbits_to_double(Literal64());
-  }
-
-  inline Instruction* NextInstruction() {
-    return this + kInstructionSize;
-  }
-
-  inline Instruction* InstructionAtOffset(int64_t offset) {
-    ASSERT(IsWordAligned(this + offset));
-    return this + offset;
-  }
-
-  template<typename T> static inline Instruction* Cast(T src) {
-    return reinterpret_cast<Instruction*>(src);
-  }
-
- private:
-  inline int ImmBranch() const;
-
-  void SetPCRelImmTarget(Instruction* target);
-  void SetBranchImmTarget(Instruction* target);
-};
-}  // namespace vixl
-
-#endif  // VIXL_A64_INSTRUCTIONS_A64_H_
@@ -1,65 +0,0 @@
-// Copyright 2013, ARM Limited
-// All rights reserved.
-//
-// Redistribution and use in source and binary forms, with or without
-// modification, are permitted provided that the following conditions are met:
-//
-//   * Redistributions of source code must retain the above copyright notice,
-//     this list of conditions and the following disclaimer.
-//   * Redistributions in binary form must reproduce the above copyright notice,
-//     this list of conditions and the following disclaimer in the documentation
-//     and/or other materials provided with the distribution.
-//   * Neither the name of ARM Limited nor the names of its contributors may be
-//     used to endorse or promote products derived from this software without
-//     specific prior written permission.
-//
-// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
-// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
-// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-#ifndef VIXL_GLOBALS_H
-#define VIXL_GLOBALS_H
-
-// Get the standard printf format macros for C99 stdint types.
-#define __STDC_FORMAT_MACROS
-#include <inttypes.h>
-
-#include <assert.h>
-#include <stdarg.h>
-#include <stdio.h>
-#include <stdint.h>
-#include <stdlib.h>
-#include <stddef.h>
-#include "platform.h"
-
-
-typedef uint8_t byte;
-
-const int KBytes = 1024;
-const int MBytes = 1024 * KBytes;
-
-  #define ABORT() printf("in %s, line %i", __FILE__, __LINE__); abort()
-#ifdef DEBUG
-  #define ASSERT(condition) assert(condition)
-  #define CHECK(condition) ASSERT(condition)
-  #define UNIMPLEMENTED() printf("UNIMPLEMENTED\t"); ABORT()
-  #define UNREACHABLE() printf("UNREACHABLE\t"); ABORT()
-#else
-  #define ASSERT(condition) ((void) 0)
-  #define CHECK(condition) assert(condition)
-  #define UNIMPLEMENTED() ((void) 0)
-  #define UNREACHABLE() ((void) 0)
-#endif
-
-template <typename T> inline void USE(T) {}
-
-#define ALIGNMENT_EXCEPTION() printf("ALIGNMENT EXCEPTION\t"); ABORT()
-
-#endif  // VIXL_GLOBALS_H
@@ -1,43 +0,0 @@
-// Copyright 2013, ARM Limited
-// All rights reserved.
-//
-// Redistribution and use in source and binary forms, with or without
-// modification, are permitted provided that the following conditions are met:
-//
-//   * Redistributions of source code must retain the above copyright notice,
-//     this list of conditions and the following disclaimer.
-//   * Redistributions in binary form must reproduce the above copyright notice,
-//     this list of conditions and the following disclaimer in the documentation
-//     and/or other materials provided with the distribution.
-//   * Neither the name of ARM Limited nor the names of its contributors may be
-//     used to endorse or promote products derived from this software without
-//     specific prior written permission.
-//
-// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
-// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
-// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-#ifndef PLATFORM_H
-#define PLATFORM_H
-
-// Define platform specific functionalities.
-
-namespace vixl {
-#ifdef USE_SIMULATOR
-// Currently we assume running the simulator implies running on x86 hardware.
-inline void HostBreakpoint() { asm("int3"); }
-#else
-inline void HostBreakpoint() {
-  // TODO: Implement HostBreakpoint on a64.
-}
-#endif
-}  // namespace vixl
-
-#endif
@@ -1,126 +0,0 @@
-// Copyright 2013, ARM Limited
-// All rights reserved.
-//
-// Redistribution and use in source and binary forms, with or without
-// modification, are permitted provided that the following conditions are met:
-//
-//   * Redistributions of source code must retain the above copyright notice,
-//     this list of conditions and the following disclaimer.
-//   * Redistributions in binary form must reproduce the above copyright notice,
-//     this list of conditions and the following disclaimer in the documentation
-//     and/or other materials provided with the distribution.
-//   * Neither the name of ARM Limited nor the names of its contributors may be
-//     used to endorse or promote products derived from this software without
-//     specific prior written permission.
-//
-// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
-// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
-// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-#include "utils.h"
-#include <stdio.h>
-
-namespace vixl {
-
-uint32_t float_to_rawbits(float value) {
-  uint32_t bits = 0;
-  memcpy(&bits, &value, 4);
-  return bits;
-}
-
-
-uint64_t double_to_rawbits(double value) {
-  uint64_t bits = 0;
-  memcpy(&bits, &value, 8);
-  return bits;
-}
-
-
-float rawbits_to_float(uint32_t bits) {
-  float value = 0.0;
-  memcpy(&value, &bits, 4);
-  return value;
-}
-
-
-double rawbits_to_double(uint64_t bits) {
-  double value = 0.0;
-  memcpy(&value, &bits, 8);
-  return value;
-}
-
-
-int CountLeadingZeros(uint64_t value, int width) {
-  ASSERT((width == 32) || (width == 64));
-  int count = 0;
-  uint64_t bit_test = 1UL << (width - 1);
-  while ((count < width) && ((bit_test & value) == 0)) {
-    count++;
-    bit_test >>= 1;
-  }
-  return count;
-}
-
-
-int CountLeadingSignBits(int64_t value, int width) {
-  ASSERT((width == 32) || (width == 64));
-  if (value >= 0) {
-    return CountLeadingZeros(value, width) - 1;
-  } else {
-    return CountLeadingZeros(~value, width) - 1;
-  }
-}
-
-
-int CountTrailingZeros(uint64_t value, int width) {
-  ASSERT((width == 32) || (width == 64));
-  int count = 0;
-  while ((count < width) && (((value >> count) & 1) == 0)) {
-    count++;
-  }
-  return count;
-}
-
-
-int CountSetBits(uint64_t value, int width) {
-  // TODO: Other widths could be added here, as the implementation already
-  // supports them.
-  ASSERT((width == 32) || (width == 64));
-
-  // Mask out unused bits to ensure that they are not counted.
-  value &= (0xffffffffffffffffULL >> (64-width));
-
-  // Add up the set bits.
-  // The algorithm works by adding pairs of bit fields together iteratively,
-  // where the size of each bit field doubles each time.
-  // An example for an 8-bit value:
-  // Bits:  h  g  f  e  d  c  b  a
-  //         \ |   \ |   \ |   \ |
-  // value = h+g   f+e   d+c   b+a
-  //            \    |      \    |
-  // value =   h+g+f+e     d+c+b+a
-  //                  \          |
-  // value =       h+g+f+e+d+c+b+a
-  value = ((value >> 1) & 0x5555555555555555ULL) +
-           (value & 0x5555555555555555ULL);
-  value = ((value >> 2) & 0x3333333333333333ULL) +
-           (value & 0x3333333333333333ULL);
-  value = ((value >> 4) & 0x0f0f0f0f0f0f0f0fULL) +
-           (value & 0x0f0f0f0f0f0f0f0fULL);
-  value = ((value >> 8) & 0x00ff00ff00ff00ffULL) +
-           (value & 0x00ff00ff00ff00ffULL);
-  value = ((value >> 16) & 0x0000ffff0000ffffULL) +
-           (value & 0x0000ffff0000ffffULL);
-  value = ((value >> 32) & 0x00000000ffffffffULL) +
-           (value & 0x00000000ffffffffULL);
-
-  return value;
-}
-}  // namespace vixl
@@ -1,126 +0,0 @@
-// Copyright 2013, ARM Limited
-// All rights reserved.
-//
-// Redistribution and use in source and binary forms, with or without
-// modification, are permitted provided that the following conditions are met:
-//
-//   * Redistributions of source code must retain the above copyright notice,
-//     this list of conditions and the following disclaimer.
-//   * Redistributions in binary form must reproduce the above copyright notice,
-//     this list of conditions and the following disclaimer in the documentation
-//     and/or other materials provided with the distribution.
-//   * Neither the name of ARM Limited nor the names of its contributors may be
-//     used to endorse or promote products derived from this software without
-//     specific prior written permission.
-//
-// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS CONTRIBUTORS "AS IS" AND
-// ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-// WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
-// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
-// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
-// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
-// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-#ifndef VIXL_UTILS_H
-#define VIXL_UTILS_H
-
-
-#include <string.h>
-#include "globals.h"
-
-namespace vixl {
-
-// Check number width.
-inline bool is_intn(unsigned n, int64_t x) {
-  ASSERT((0 < n) && (n < 64));
-  int64_t limit = 1ULL << (n - 1);
-  return (-limit <= x) && (x < limit);
-}
-
-inline bool is_uintn(unsigned n, int64_t x) {
-  ASSERT((0 < n) && (n < 64));
-  return !(x >> n);
-}
-
-inline unsigned truncate_to_intn(unsigned n, int64_t x) {
-  ASSERT((0 < n) && (n < 64));
-  return (x & ((1ULL << n) - 1));
-}
-
-#define INT_1_TO_63_LIST(V)                                                    \
-V(1)  V(2)  V(3)  V(4)  V(5)  V(6)  V(7)  V(8)                                 \
-V(9)  V(10) V(11) V(12) V(13) V(14) V(15) V(16)                                \
-V(17) V(18) V(19) V(20) V(21) V(22) V(23) V(24)                                \
-V(25) V(26) V(27) V(28) V(29) V(30) V(31) V(32)                                \
-V(33) V(34) V(35) V(36) V(37) V(38) V(39) V(40)                                \
-V(41) V(42) V(43) V(44) V(45) V(46) V(47) V(48)                                \
-V(49) V(50) V(51) V(52) V(53) V(54) V(55) V(56)                                \
-V(57) V(58) V(59) V(60) V(61) V(62) V(63)
-
-#define DECLARE_IS_INT_N(N)                                                    \
-inline bool is_int##N(int64_t x) { return is_intn(N, x); }
-#define DECLARE_IS_UINT_N(N)                                                   \
-inline bool is_uint##N(int64_t x) { return is_uintn(N, x); }
-#define DECLARE_TRUNCATE_TO_INT_N(N)                                           \
-inline int truncate_to_int##N(int x) { return truncate_to_intn(N, x); }
-INT_1_TO_63_LIST(DECLARE_IS_INT_N)
-INT_1_TO_63_LIST(DECLARE_IS_UINT_N)
-INT_1_TO_63_LIST(DECLARE_TRUNCATE_TO_INT_N)
-#undef DECLARE_IS_INT_N
-#undef DECLARE_IS_UINT_N
-#undef DECLARE_TRUNCATE_TO_INT_N
-
-// Bit field extraction.
-inline uint32_t unsigned_bitextract_32(int msb, int lsb, uint32_t x) {
-  return (x >> lsb) & ((1 << (1 + msb - lsb)) - 1);
-}
-
-inline uint64_t unsigned_bitextract_64(int msb, int lsb, uint64_t x) {
-  return (x >> lsb) & ((static_cast<uint64_t>(1) << (1 + msb - lsb)) - 1);
-}
-
-inline int32_t signed_bitextract_32(int msb, int lsb, int32_t x) {
-  return (x << (31 - msb)) >> (lsb + 31 - msb);
-}
-
-inline int64_t signed_bitextract_64(int msb, int lsb, int64_t x) {
-  return (x << (63 - msb)) >> (lsb + 63 - msb);
-}
-
-// floating point representation
-uint32_t float_to_rawbits(float value);
-uint64_t double_to_rawbits(double value);
-float rawbits_to_float(uint32_t bits);
-double rawbits_to_double(uint64_t bits);
-
-// Bits counting.
-int CountLeadingZeros(uint64_t value, int width);
-int CountLeadingSignBits(int64_t value, int width);
-int CountTrailingZeros(uint64_t value, int width);
-int CountSetBits(uint64_t value, int width);
-
-// Pointer alignment
-// TODO: rename/refactor to make it specific to instructions.
-template<typename T>
-bool IsWordAligned(T pointer) {
-  ASSERT(sizeof(pointer) == sizeof(intptr_t));   // NOLINT(runtime/sizeof)
-  return (reinterpret_cast<intptr_t>(pointer) & 3) == 0;
-}
-
-// Increment a pointer until it has the specified alignment.
-template<class T>
-T AlignUp(T pointer, size_t alignment) {
-  ASSERT(sizeof(pointer) == sizeof(uintptr_t));
-  uintptr_t pointer_raw = reinterpret_cast<uintptr_t>(pointer);
-  size_t align_step = (alignment - pointer_raw) % alignment;
-  ASSERT((pointer_raw + align_step) % alignment == 0);
-  return reinterpret_cast<T>(pointer_raw + align_step);
-}
-
-
-}  // namespace vixl
-
-#endif  // VIXL_UTILS_H
@@ -213,7 +213,6 @@ BlockDriverAIOCB *dma_bdrv_io(
    dbs->sg_cur_index = 0;
    dbs->sg_cur_byte = 0;
    dbs->dir = dir;
-    dbs->in_cancel = false;
    dbs->io_func = io_func;
    dbs->bh = NULL;
    qemu_iovec_init(&dbs->iov, sg->nsg);
@@ -139,7 +139,6 @@ static const VMStateDescription vmstate_kbd = {
    .name = "pckbd",
    .version_id = 3,
    .minimum_version_id = 3,
-    .minimum_version_id_old = 3,
    .fields      = (VMStateField []) {
        VMSTATE_UINT8(write_cmd, KBDState),
        VMSTATE_UINT8(status, KBDState),
@@ -168,12 +167,13 @@ You can see that there are several version fields:
 - minimum_version_id: the minimum version_id that VMState is able to understand
  for that device.
 - minimum_version_id_old: For devices that were not able to port to vmstate, we can
-  assign a function that knows how to read this old state.
+  assign a function that knows how to read this old state. This field is
+  ignored if there is no load_state_old handler.

 So, VMState is able to read versions from minimum_version_id to
-version_id.  And the function load_state_old() is able to load state
-from minimum_version_id_old to minimum_version_id.  This function is
-deprecated and will be removed when no more users are left.
+version_id.  And the function load_state_old() (if present) is able to
+load state from minimum_version_id_old to minimum_version_id.  This
+function is deprecated and will be removed when no more users are left.

 ===  Massaging functions ===

@@ -255,7 +255,6 @@ const VMStateDescription vmstate_ide_drive_pio_state = {
    .name = "ide_drive/pio_state",
    .version_id = 1,
    .minimum_version_id = 1,
-    .minimum_version_id_old = 1,
    .pre_save = ide_drive_pio_pre_save,
    .post_load = ide_drive_pio_post_load,
    .fields      = (VMStateField []) {
@@ -275,7 +274,6 @@ const VMStateDescription vmstate_ide_drive = {
    .name = "ide_drive",
    .version_id = 3,
    .minimum_version_id = 0,
-    .minimum_version_id_old = 0,
    .post_load = ide_drive_post_load,
    .fields      = (VMStateField []) {
        .... several fields ....
--- a/Show More
+++ b/Show More
@@ -1 +1 @@
 .0.2
 .7.2