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
1841 changed files with 130739 additions and 237277 deletions
@@ -1,67 +1,68 @@
-/config-devices.*
-/config-all-devices.*
-/config-all-disas.*
-/config-host.*
-/config-target.*
-/config.status
-/config-temp
-/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
-/libdis*
-/libuser
-/linux-headers/asm
-/qga/qapi-generated
-/qapi-generated
-/qapi-types.[ch]
-/qapi-visit.[ch]
-/qapi-event.[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
-/fsdev/virtfs-proxy-helper
-/fsdev/virtfs-proxy-helper.1
-/fsdev/virtfs-proxy-helper.pod
+*-softmmu
+*-darwin-user
+*-linux-user
+*-bsd-user
+libdis*
+libuser
+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
@@ -75,31 +76,35 @@
 *.tp
 *.vr
 *.d
-!/scripts/qemu-guest-agent/fsfreeze-hook.d
+!scripts/qemu-guest-agent/fsfreeze-hook.d
 *.o
 *.lo
 *.la
 *.pc
 .libs
 .sdk
+*.swp
+*.orig
+.pc
 *.gcda
 *.gcno
-/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
+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
 .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
@@ -28,6 +25,3 @@
 [submodule "dtc"]
 	path = dtc
 	url = git://git.qemu-project.org/dtc.git
-[submodule "roms/u-boot"]
-	path = roms/u-boot
-	url = git://git.qemu-project.org/u-boot.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"
@@ -66,16 +55,17 @@ matrix:
      compiler: gcc
    # All the trace backends (apart from dtrace)
    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-trace-backends=stderr"
+           EXTRA_CONFIG="--enable-trace-backend=stderr"
      compiler: gcc
    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-trace-backends=simple"
+           EXTRA_CONFIG="--enable-trace-backend=simple"
      compiler: gcc
    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-trace-backends=ftrace"
+           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-backends=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.
@@ -52,13 +52,6 @@ General Project Administration
 ------------------------------
 M: Anthony Liguori <aliguori@amazon.com>

-Responsible Disclosure, Reporting Security Issues
------------------------------
-W: http://wiki.qemu.org/SecurityProcess
-M: Michael S. Tsirkin <mst@redhat.com>
-M: Anthony Liguori <aliguori@amazon.com>
-L: secalert@redhat.com
-
 Guest CPU cores (TCG):
 ----------------------
 Alpha
@@ -165,6 +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
@@ -176,25 +170,18 @@ M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
 F: target-arm/kvm.c

-MIPS
-M: James Hogan <james.hogan@imgtec.com>
-S: Maintained
-F: target-mips/kvm.c
-
 PPC
 M: Alexander Graf <agraf@suse.de>
 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
@@ -232,13 +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>
@@ -248,17 +228,11 @@ S: Maintained
 F: hw/*/exynos*

 Calxeda Highbank
-M: Rob Herring <robh@kernel.org>
-S: Maintained
+M: Mark Langsdorf <mark.langsdorf@calxeda.com>
+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
@@ -316,7 +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
@@ -365,7 +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

@@ -508,13 +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
@@ -529,23 +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
 ---------------
@@ -563,7 +520,6 @@ Devices
 -------
 IDE
 M: Kevin Wolf <kwolf@redhat.com>
-M: Stefan Hajnoczi <stefanha@redhat.com>
 S: Odd Fixes
 F: include/hw/ide.h
 F: hw/ide/
@@ -605,7 +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 +570,6 @@ USB
 M: Gerd Hoffmann <kraxel@redhat.com>
 S: Maintained
 F: hw/usb/*
-F: tests/usb-hcd-ehci-test.c

 VFIO
 M: Alex Williamson <alex.williamson@redhat.com>
@@ -628,7 +583,6 @@ F: hw/*/*vhost*

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

@@ -637,7 +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
@@ -648,7 +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
@@ -663,16 +615,9 @@ nvme
 M: Keith Busch <keith.busch@intel.com>
 S: Supported
 F: hw/block/nvme*
-F: tests/nvme-test.c
-
-megasas
-M: Hannes Reinecke <hare@suse.de>
-S: Supported
-F: hw/scsi/megasas.c
-F: hw/scsi/mfi.h

 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_*
@@ -686,9 +631,6 @@ M: Gerd Hoffmann <kraxel@redhat.com>
 S: Maintained
 F: audio/
 F: hw/audio/
-F: tests/ac97-test.c
-F: tests/es1370-test.c
-F: tests/intel-hda-test.c

 Block
 M: Kevin Wolf <kwolf@redhat.com>
@@ -697,8 +639,6 @@ S: Supported
 F: block*
 F: block/
 F: hw/block/
-F: qemu-img*
-F: qemu-io*
 T: git git://repo.or.cz/qemu/kevin.git block
 T: git git://github.com/stefanha/qemu.git block

@@ -721,7 +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]
@@ -732,16 +672,6 @@ S: Odd Fixes
 F: gdbstub*
 F: gdb-xml/

-Memory API
-M: Paolo Bonzini <pbonzini@redhat.com>
-S: Supported
-F: include/exec/ioport.h
-F: ioport.c
-F: include/exec/memory.h
-F: memory.c
-F: include/exec/memory-internal.h
-F: exec.c
-
 SPICE
 M: Gerd Hoffmann <kraxel@redhat.com>
 S: Supported
@@ -752,13 +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

@@ -769,7 +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
@@ -782,14 +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
@@ -801,7 +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

@@ -813,20 +733,9 @@ S: Supported
 F: qapi-schema.json
 T: git git://repo.or.cz/qemu/qmp-unstable.git queue/qmp

-QOM
-M: Anthony Liguori <aliguori@amazon.com>
-M: Andreas Färber <afaerber@suse.de>
-S: Supported
-T: git git://github.com/afaerber/qemu-cpu.git qom-next
-F: include/qom/
-X: include/qom/cpu.h
-F: qom/
-X: qom/cpu.c
-F: tests/qom-test.c
-
 QMP
 M: Luiz Capitulino <lcapitulino@redhat.com>
-S: Maintained
+S: Supported
 F: qmp.c
 F: monitor.c
 F: qmp-commands.hx
@@ -854,7 +763,7 @@ S: Odd Fixes
 F: scripts/checkpatch.pl

 Seccomp
-M: Eduardo Otubo <eduardo.otubo@profitbricks.com>
+M: Eduardo Otubo <otubo@linux.vnet.ibm.com>
 S: Supported
 F: qemu-seccomp.c
 F: include/sysemu/seccomp.h
@@ -970,7 +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

@@ -991,11 +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
@@ -45,23 +45,18 @@ endif
 endif

 GENERATED_HEADERS = config-host.h qemu-options.def
-GENERATED_HEADERS += qmp-commands.h qapi-types.h qapi-visit.h qapi-event.h
-GENERATED_SOURCES += qmp-marshal.c qapi-types.c qapi-visit.c qapi-event.c
+GENERATED_HEADERS += qmp-commands.h qapi-types.h qapi-visit.h
+GENERATED_SOURCES += qmp-marshal.c qapi-types.c qapi-visit.c

 GENERATED_HEADERS += trace/generated-events.h
 GENERATED_SOURCES += trace/generated-events.c

 GENERATED_HEADERS += trace/generated-tracers.h
-ifeq ($(findstring dtrace,$(TRACE_BACKENDS)),dtrace)
+ifeq ($(TRACE_BACKEND),dtrace)
 GENERATED_HEADERS += trace/generated-tracers-dtrace.h
 endif
 GENERATED_SOURCES += trace/generated-tracers.c

-ifeq ($(findstring ust,$(TRACE_BACKENDS)),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: ;
@@ -127,26 +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
+all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all

 config-host.h: config-host.h-timestamp
 config-host.h-timestamp: config-host.mak
@@ -156,7 +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-%:
@@ -191,6 +172,8 @@ ALL_SUBDIRS=$(TARGET_DIRS) $(patsubst %,pc-bios/%, $(ROMS))

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

+bt-host.o: QEMU_CFLAGS += $(BLUEZ_CFLAGS)
+
 $(BUILD_DIR)/version.o: $(SRC_PATH)/version.rc $(BUILD_DIR)/config-host.h | $(BUILD_DIR)/version.lo
 	$(call quiet-command,$(WINDRES) -I$(BUILD_DIR) -o $@ $<,"  RC    version.o")
 $(BUILD_DIR)/version.lo: $(SRC_PATH)/version.rc $(BUILD_DIR)/config-host.h
@@ -202,10 +185,7 @@ Makefile: $(version-obj-y) $(version-lobj-y)
 # Build libraries

 libqemustub.a: $(stub-obj-y)
-libqemuutil.a: $(util-obj-y) qapi-types.o qapi-visit.o qapi-event.o
-
-block-modules = $(foreach o,$(block-obj-m),"$(basename $(subst /,-,$o))",) NULL
-util/module.o-cflags = -D'CONFIG_BLOCK_MODULES=$(block-modules)'
+libqemuutil.a: $(util-obj-y) qapi-types.o qapi-visit.o

 ######################################################################

@@ -232,44 +212,23 @@ qapi-py = $(SRC_PATH)/scripts/qapi.py $(SRC_PATH)/scripts/ordereddict.py

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

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

 QGALIB_GEN=$(addprefix qga/qapi-generated/, qga-qapi-types.h qga-qapi-visit.h qga-qmp-commands.h)
 $(qga-obj-y) qemu-ga.o: $(QGALIB_GEN)
@@ -281,7 +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
@@ -330,10 +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 \
@@ -344,8 +304,7 @@ multiboot.bin linuxboot.bin kvmvapic.bin \
 s390-zipl.rom \
 s390-ccw.img \
 spapr-rtas.bin slof.bin \
-palcode-clipper \
-u-boot.e500
+palcode-clipper
 else
 BLOBS=
 endif
@@ -386,19 +345,13 @@ install-sysconfig: install-datadir install-confdir

 install: all $(if $(BUILD_DOCS),install-doc) install-sysconfig \
 install-datadir install-localstatedir
+	$(INSTALL_DIR) "$(DESTDIR)$(bindir)"
 ifneq ($(TOOLS),)
-	$(call install-prog,$(TOOLS),$(DESTDIR)$(bindir))
-endif
-ifneq ($(CONFIG_MODULES),)
-	$(INSTALL_DIR) "$(DESTDIR)$(qemu_moddir)"
-	for s in $(modules-m:.mo=$(DSOSUF)); do \
-		t="$(DESTDIR)$(qemu_moddir)/$$(echo $$s | tr / -)"; \
-		$(INSTALL_LIB) $$s "$$t"; \
-		test -z "$(STRIP)" || $(STRIP) "$$t"; \
-	done
+	$(INSTALL_PROG) $(STRIP_OPT) $(TOOLS) "$(DESTDIR)$(bindir)"
 endif
 ifneq ($(HELPERS-y),)
-	$(call install-prog,$(HELPERS-y),$(DESTDIR)$(libexecdir))
+	$(INSTALL_DIR) "$(DESTDIR)$(libexecdir)"
+	$(INSTALL_PROG) $(STRIP_OPT) $(HELPERS-y) "$(DESTDIR)$(libexecdir)"
 endif
 ifneq ($(BLOBS),)
 	set -e; for x in $(BLOBS); do \
@@ -413,7 +366,7 @@ endif
 		$(INSTALL_DATA) $(SRC_PATH)/pc-bios/keymaps/$$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
@@ -12,15 +12,18 @@ block-obj-y += main-loop.o iohandler.o qemu-timer.o
 block-obj-$(CONFIG_POSIX) += aio-posix.o
 block-obj-$(CONFIG_WIN32) += aio-win32.o
 block-obj-y += block/
-block-obj-y += qapi-types.o qapi-visit.o qapi-event.o
+block-obj-y += qapi-types.o qapi-visit.o
 block-obj-y += qemu-io-cmds.o

 block-obj-y += qemu-coroutine.o qemu-coroutine-lock.o qemu-coroutine-io.o
 block-obj-y += qemu-coroutine-sleep.o
 block-obj-y += coroutine-$(CONFIG_COROUTINE_BACKEND).o

-block-obj-m = block/
-
+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
@@ -31,8 +34,6 @@ libcacard-y += libcacard/vcard_emul_nss.o
 libcacard-y += libcacard/vcard_emul_type.o
 libcacard-y += libcacard/card_7816.o
 libcacard-y += libcacard/vcardt.o
-libcacard/vcard_emul_nss.o-cflags := $(NSS_CFLAGS)
-libcacard/vcard_emul_nss.o-libs := $(NSS_LIBS)

 ######################################################################
 # Target independent part of system emulation. The long term path is to
@@ -40,9 +41,9 @@ libcacard/vcard_emul_nss.o-libs := $(NSS_LIBS)
 # 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-$(CONFIG_POSIX) += os-posix.o
@@ -50,8 +51,6 @@ common-obj-$(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
@@ -66,11 +65,9 @@ common-obj-y += hw/

 common-obj-y += ui/
 common-obj-y += bt-host.o bt-vhci.o
-bt-host.o-cflags := $(BLUEZ_CFLAGS)

 common-obj-y += dma-helpers.o
 common-obj-y += vl.o
-vl.o-cflags := $(GPROF_CFLAGS) $(SDL_CFLAGS)
 common-obj-y += tpm.o

 common-obj-$(CONFIG_SLIRP) += slirp/
@@ -113,3 +110,18 @@ version-lobj-$(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 := $(call unnest-vars)
@@ -16,22 +16,19 @@ QEMU_CFLAGS+=-I$(SRC_PATH)/include
 ifdef CONFIG_USER_ONLY
 # user emulator name
 QEMU_PROG=qemu-$(TARGET_NAME)
-QEMU_PROG_BUILD = $(QEMU_PROG)
 else
 # system emulator name
-QEMU_PROG=qemu-system-$(TARGET_NAME)$(EXESUF)
 ifneq (,$(findstring -mwindows,$(libs_softmmu)))
 # Terminate program name with a 'w' because the linker builds a windows executable.
 QEMU_PROGW=qemu-system-$(TARGET_NAME)w$(EXESUF)
-$(QEMU_PROG): $(QEMU_PROGW)
-	$(call quiet-command,$(OBJCOPY) --subsystem console $(QEMU_PROGW) $(QEMU_PROG),"  GEN   $(TARGET_DIR)$(QEMU_PROG)")
-QEMU_PROG_BUILD = $(QEMU_PROGW)
-else
-QEMU_PROG_BUILD = $(QEMU_PROG)
-endif
+endif # windows executable
+QEMU_PROG=qemu-system-$(TARGET_NAME)$(EXESUF)
 endif

-PROGS=$(QEMU_PROG) $(QEMU_PROGW)
+PROGS=$(QEMU_PROG)
+ifdef QEMU_PROGW
+PROGS+=$(QEMU_PROGW)
+endif
 STPFILES=

 config-target.h: config-target.h-timestamp
@@ -49,7 +46,7 @@ endif
 $(QEMU_PROG).stp-installed: $(SRC_PATH)/trace-events
 	$(call quiet-command,$(TRACETOOL) \
 		--format=stap \
-		--backends=$(TRACE_BACKENDS) \
+		--backend=$(TRACE_BACKEND) \
 		--binary=$(bindir)/$(QEMU_PROG) \
 		--target-name=$(TARGET_NAME) \
 		--target-type=$(TARGET_TYPE) \
@@ -58,7 +55,7 @@ $(QEMU_PROG).stp-installed: $(SRC_PATH)/trace-events
 $(QEMU_PROG).stp: $(SRC_PATH)/trace-events
 	$(call quiet-command,$(TRACETOOL) \
 		--format=stap \
-		--backends=$(TRACE_BACKENDS) \
+		--backend=$(TRACE_BACKEND) \
 		--binary=$(realpath .)/$(QEMU_PROG) \
 		--target-name=$(TARGET_NAME) \
 		--target-type=$(TARGET_TYPE) \
@@ -85,12 +82,6 @@ obj-y += disas.o
 obj-$(call notempty,$(TARGET_XML_FILES)) += gdbstub-xml.o
 obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o

-obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/decContext.o
-obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/decNumber.o
-obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/dpd/decimal32.o
-obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/dpd/decimal64.o
-obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/dpd/decimal128.o
-
 #########################################################
 # Linux user emulator target

@@ -108,8 +99,7 @@ endif #CONFIG_LINUX_USER

 ifdef CONFIG_BSD_USER

-QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ABI_DIR) \
-			 -I$(SRC_PATH)/bsd-user/$(HOST_VARIANT_DIR)
+QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ABI_DIR)

 obj-y += bsd-user/
 obj-y += gdbstub.o user-exec.o
@@ -119,7 +109,7 @@ endif #CONFIG_BSD_USER
 #########################################################
 # System emulator target
 ifdef CONFIG_SOFTMMU
-obj-y += arch_init.o cpus.o monitor.o gdbstub.o balloon.o ioport.o numa.o
+obj-y += arch_init.o cpus.o monitor.o gdbstub.o balloon.o ioport.o
 obj-y += qtest.o
 obj-y += hw/
 obj-$(CONFIG_FDT) += device_tree.o
@@ -130,10 +120,8 @@ obj-y += dump.o
 LIBS+=$(libs_softmmu)

 # xen support
-obj-$(CONFIG_XEN) += xen-common.o
-obj-$(CONFIG_XEN_I386) += xen-hvm.o xen-mapcache.o
-obj-$(call lnot,$(CONFIG_XEN)) += xen-common-stub.o
-obj-$(call lnot,$(CONFIG_XEN_I386)) += xen-hvm-stub.o
+obj-$(CONFIG_XEN) += xen-all.o xen-mapcache.o
+obj-$(call lnot,$(CONFIG_XEN)) += xen-stub.o

 # Hardware support
 ifeq ($(TARGET_NAME), sparc64)
@@ -142,6 +130,8 @@ else
 obj-y += hw/$(TARGET_BASE_ARCH)/
 endif

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

 endif # CONFIG_SOFTMMU
@@ -149,23 +139,28 @@ 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)
-all-obj-y := $(obj-y)
+nested-vars += 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)
-all-obj-y += $(common-obj-y)
-all-obj-$(CONFIG_SOFTMMU) += $(block-obj-y)

-# build either PROG or PROGW
-$(QEMU_PROG_BUILD): $(all-obj-y) ../libqemuutil.a ../libqemustub.a
+all-obj-y = $(obj-y)
+all-obj-y += $(addprefix ../, $(common-obj-y))
+
+ifndef CONFIG_HAIKU
+LIBS+=-lm
+endif
+
+ifdef QEMU_PROGW
+# The linker builds a windows executable. Make also a console executable.
+$(QEMU_PROGW): $(all-obj-y) ../libqemuutil.a ../libqemustub.a
 	$(call LINK,$^)
+$(QEMU_PROG): $(QEMU_PROGW)
+	$(call quiet-command,$(OBJCOPY) --subsystem console $(QEMU_PROGW) $(QEMU_PROG),"  GEN   $(TARGET_DIR)$(QEMU_PROG)")
+else
+$(QEMU_PROG): $(all-obj-y) ../libqemuutil.a ../libqemustub.a
+	$(call LINK,$^)
+endif

 gdbstub-xml.c: $(TARGET_XML_FILES) $(SRC_PATH)/scripts/feature_to_c.sh
 	$(call quiet-command,rm -f $@ && $(SHELL) $(SRC_PATH)/scripts/feature_to_c.sh $@ $(TARGET_XML_FILES),"  GEN   $(TARGET_DIR)$@")
@@ -186,7 +181,10 @@ endif

 install: all
 ifneq ($(PROGS),)
-	$(call install-prog,$(PROGS),$(DESTDIR)$(bindir))
+	$(INSTALL) -m 755 $(PROGS) "$(DESTDIR)$(bindir)"
+ifneq ($(STRIP),)
+	$(STRIP) $(patsubst %,"$(DESTDIR)$(bindir)/%",$(PROGS))
+endif
 endif
 ifdef CONFIG_TRACE_SYSTEMTAP
 	$(INSTALL_DIR) "$(DESTDIR)$(qemu_datadir)/../systemtap/tapset"
@@ -1 +1 @@
-2.1.3
+1.7.2
@@ -125,7 +125,7 @@ static bool aio_dispatch(AioContext *ctx)
    bool progress = false;

    /*
-     * We have to walk very carefully in case aio_set_fd_handler is
+     * We have to walk very carefully in case qemu_aio_set_fd_handler is
     * called while we're walking.
     */
    node = QLIST_FIRST(&ctx->aio_handlers);
@@ -175,56 +175,27 @@ static bool aio_dispatch(AioContext *ctx)
 bool aio_poll(AioContext *ctx, bool blocking)
 {
    AioHandler *node;
-    bool was_dispatching;
    int ret;
    bool progress;

-    was_dispatching = ctx->dispatching;
    progress = false;

-    /* aio_notify can avoid the expensive event_notifier_set if
-     * everything (file descriptors, bottom halves, timers) will
-     * be re-evaluated before the next blocking poll().  This happens
-     * in two cases:
-     *
-     * 1) when aio_poll is called with blocking == false
-     *
-     * 2) when we are called after poll().  If we are called before
-     *    poll(), bottom halves will not be re-evaluated and we need
-     *    aio_notify() if blocking == true.
-     *
-     * The first aio_dispatch() only does something when AioContext is
-     * running as a GSource, and in that case aio_poll is used only
-     * with blocking == false, so this optimization is already quite
-     * effective.  However, the code is ugly and should be restructured
-     * to have a single aio_dispatch() call.  To do this, we need to
-     * reorganize aio_poll into a prepare/poll/dispatch model like
-     * glib's.
-     *
-     * If we're in a nested event loop, ctx->dispatching might be true.
-     * In that case we can restore it just before returning, but we
-     * have to clear it now.
-     */
-    aio_set_dispatching(ctx, !blocking);
-
    /*
     * If there are callbacks left that have been queued, we need to call them.
     * Do not call select in this case, because it is possible that the caller
-     * does not need a complete flush (as is the case for aio_poll loops).
+     * does not need a complete flush (as is the case for qemu_aio_wait loops).
     */
    if (aio_bh_poll(ctx)) {
        blocking = false;
        progress = true;
    }

-    /* Re-evaluate condition (1) above.  */
-    aio_set_dispatching(ctx, !blocking);
    if (aio_dispatch(ctx)) {
        progress = true;
    }

    if (progress && !blocking) {
-        goto out;
+        return true;
    }

    ctx->walking_handlers++;
@@ -246,6 +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,
@@ -263,12 +239,9 @@ bool aio_poll(AioContext *ctx, bool blocking)
    }

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

-out:
-    aio_set_dispatching(ctx, was_dispatching);
    return progress;
 }
@@ -102,7 +102,7 @@ bool aio_poll(AioContext *ctx, bool blocking)
    /*
     * If there are callbacks left that have been queued, we need to call then.
     * Do not call select in this case, because it is possible that the caller
-     * does not need a complete flush (as is the case for aio_poll loops).
+     * does not need a complete flush (as is the case for qemu_aio_wait loops).
     */
    if (aio_bh_poll(ctx)) {
        blocking = false;
@@ -115,7 +115,7 @@ bool aio_poll(AioContext *ctx, bool blocking)
    /*
     * Then dispatch any pending callbacks from the GSource.
     *
-     * We have to walk very carefully in case aio_set_fd_handler is
+     * We have to walk very carefully in case qemu_aio_set_fd_handler is
     * called while we're walking.
     */
    node = QLIST_FIRST(&ctx->aio_handlers);
@@ -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;
@@ -177,7 +182,7 @@ bool aio_poll(AioContext *ctx, bool blocking)
        blocking = false;

        /* we have to walk very carefully in case
-         * aio_set_fd_handler is called while we're walking */
+         * qemu_aio_set_fd_handler is called while we're walking */
        node = QLIST_FIRST(&ctx->aio_handlers);
        while (node) {
            AioHandler *tmp;
@@ -45,13 +45,10 @@
 #include "hw/audio/pcspk.h"
 #include "migration/page_cache.h"
 #include "qemu/config-file.h"
-#include "qemu/error-report.h"
 #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, ...) \
@@ -111,8 +108,6 @@ static bool mig_throttle_on;
 static int dirty_rate_high_cnt;
 static void check_guest_throttling(void);

-static uint64_t bitmap_sync_count;
-
 /***********************************************************/
 /* ram save/restore */

@@ -125,6 +120,7 @@ static uint64_t bitmap_sync_count;
 #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) */
@@ -135,7 +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)
 {
@@ -167,64 +162,25 @@ 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;
+} 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);
-}
-
-/*
- * called from qmp_migrate_set_cache_size in main thread, possibly while
- * a migration is in progress.
- * A running migration maybe using the cache and might finish during this
- * call, hence changes to the cache are protected by XBZRLE.lock().
- */
 int64_t xbzrle_cache_resize(int64_t new_size)
 {
-    PageCache *new_cache;
-    int64_t ret;
-
-    if (new_size < TARGET_PAGE_SIZE) {
-        return -1;
-    }
-
-    XBZRLE_cache_lock();
-
    if (XBZRLE.cache != NULL) {
-        if (pow2floor(new_size) == migrate_xbzrle_cache_size()) {
-            goto out_new_size;
-        }
-        new_cache = cache_init(new_size / TARGET_PAGE_SIZE,
-                                        TARGET_PAGE_SIZE);
-        if (!new_cache) {
-            error_report("Error creating cache");
-            ret = -1;
-            goto out;
-        }
-
-        cache_fini(XBZRLE.cache);
-        XBZRLE.cache = new_cache;
+        return cache_resize(XBZRLE.cache, new_size / TARGET_PAGE_SIZE) *
+            TARGET_PAGE_SIZE;
    }
-
-out_new_size:
-    ret = pow2floor(new_size);
-out:
-    XBZRLE_cache_unlock();
-    return ret;
+    return pow2floor(new_size);
 }

 /* accounting for migration statistics */
@@ -236,7 +192,6 @@ typedef struct AccountingInfo {
    uint64_t xbzrle_bytes;
    uint64_t xbzrle_pages;
    uint64_t xbzrle_cache_miss;
-    double xbzrle_cache_miss_rate;
    uint64_t xbzrle_overflows;
 } AccountingInfo;

@@ -292,11 +247,6 @@ uint64_t xbzrle_mig_pages_cache_miss(void)
    return acct_info.xbzrle_cache_miss;
 }

-double xbzrle_mig_cache_miss_rate(void)
-{
-    return acct_info.xbzrle_cache_miss_rate;
-}
-
 uint64_t xbzrle_mig_pages_overflow(void)
 {
    return acct_info.xbzrle_overflows;
@@ -319,37 +269,9 @@ 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,
+static int save_xbzrle_page(QEMUFile *f, uint8_t *current_data,
                            ram_addr_t current_addr, RAMBlock *block,
                            ram_addr_t offset, int cont, bool last_stage)
 {
@@ -357,23 +279,17 @@ static int save_xbzrle_page(QEMUFile *f, uint8_t **current_data,
    uint8_t *prev_cached_page;

    if (!cache_is_cached(XBZRLE.cache, current_addr)) {
-        acct_info.xbzrle_cache_miss++;
        if (!last_stage) {
-            if (cache_insert(XBZRLE.cache, current_addr, *current_data) == -1) {
-                return -1;
-            } else {
-                /* update *current_data when the page has been
-                   inserted into cache */
-                *current_data = get_cached_data(XBZRLE.cache, current_addr);
-            }
+            cache_insert(XBZRLE.cache, current_addr, current_data);
        }
+        acct_info.xbzrle_cache_miss++;
        return -1;
    }

    prev_cached_page = get_cached_data(XBZRLE.cache, current_addr);

    /* save current buffer into memory */
-    memcpy(XBZRLE.current_buf, *current_data, TARGET_PAGE_SIZE);
+    memcpy(XBZRLE.current_buf, current_data, TARGET_PAGE_SIZE);

    /* XBZRLE encoding (if there is no overflow) */
    encoded_len = xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_buf,
@@ -386,10 +302,7 @@ static int save_xbzrle_page(QEMUFile *f, uint8_t **current_data,
        DPRINTF("Overflow\n");
        acct_info.xbzrle_overflows++;
        /* update data in the cache */
-        if (!last_stage) {
-            memcpy(prev_cached_page, *current_data, TARGET_PAGE_SIZE);
-            *current_data = prev_cached_page;
-        }
+        memcpy(prev_cached_page, current_data, TARGET_PAGE_SIZE);
        return -1;
    }

@@ -410,6 +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)
@@ -434,10 +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);

@@ -447,47 +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;
@@ -495,10 +386,6 @@ static void migration_bitmap_sync(void)
    static int64_t num_dirty_pages_period;
    int64_t end_time;
    int64_t bytes_xfer_now;
-    static uint64_t xbzrle_cache_miss_prev;
-    static uint64_t iterations_prev;
-
-    bitmap_sync_count++;

    if (!bytes_xfer_prev) {
        bytes_xfer_prev = ram_bytes_transferred();
@@ -512,7 +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);
@@ -540,113 +433,29 @@ static void migration_bitmap_sync(void)
        } else {
             mig_throttle_on = false;
        }
-        if (migrate_use_xbzrle()) {
-            if (iterations_prev != 0) {
-                acct_info.xbzrle_cache_miss_rate =
-                   (double)(acct_info.xbzrle_cache_miss -
-                            xbzrle_cache_miss_prev) /
-                   (acct_info.iterations - iterations_prev);
-            }
-            iterations_prev = acct_info.iterations;
-            xbzrle_cache_miss_prev = acct_info.xbzrle_cache_miss;
-        }
        s->dirty_pages_rate = num_dirty_pages_period * 1000
            / (end_time - start_time);
        s->dirty_bytes_rate = s->dirty_pages_rate * TARGET_PAGE_SIZE;
        start_time = end_time;
        num_dirty_pages_period = 0;
-        s->dirty_sync_count = bitmap_sync_count;
    }
 }

 /*
- * ram_save_page: Send the given page to the stream
- *
- * Returns: Number of bytes written.
- */
-static int ram_save_page(QEMUFile *f, RAMBlock* block, ram_addr_t offset,
-                         bool last_stage)
-{
-    int bytes_sent;
-    int cont;
-    ram_addr_t current_addr;
-    MemoryRegion *mr = block->mr;
-    uint8_t *p;
-    int ret;
-    bool send_async = true;
-
-    cont = (block == last_sent_block) ? RAM_SAVE_FLAG_CONTINUE : 0;
-
-    p = memory_region_get_ram_ptr(mr) + offset;
-
-    /* In doubt sent page as normal */
-    bytes_sent = -1;
-    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) {
-                acct_info.norm_pages++;
-            } else if (bytes_sent == 0) {
-                acct_info.dup_pages++;
-            }
-        }
-    } else if (is_zero_range(p, TARGET_PAGE_SIZE)) {
-        acct_info.dup_pages++;
-        bytes_sent = save_block_hdr(f, block, offset, cont,
-                                    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()) {
-        bytes_sent = save_xbzrle_page(f, &p, current_addr, block,
-                                      offset, cont, last_stage);
-        if (!last_stage) {
-            /* 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);
-        }
-        bytes_sent += TARGET_PAGE_SIZE;
-        acct_info.norm_pages++;
-    }
-
-    XBZRLE_cache_unlock();
-
-    return bytes_sent;
-}
-
-/*
- * ram_find_and_save_block: Finds a page to send and sends it to f
+ * ram_save_block: Writes a page of memory to the stream f
 *
 * Returns:  The number of bytes written.
 *           0 means no dirty pages
 */

-static int ram_find_and_save_block(QEMUFile *f, bool last_stage)
+static int ram_save_block(QEMUFile *f, bool last_stage)
 {
    RAMBlock *block = last_seen_block;
    ram_addr_t offset = last_offset;
    bool complete_round = false;
    int bytes_sent = 0;
    MemoryRegion *mr;
+    ram_addr_t current_addr;

    if (!block)
        block = QTAILQ_FIRST(&ram_list.blocks);
@@ -667,7 +476,48 @@ static int ram_find_and_save_block(QEMUFile *f, bool last_stage)
                ram_bulk_stage = false;
            }
        } else {
-            bytes_sent = ram_save_page(f, block, offset, last_stage);
+            int ret;
+            uint8_t *p;
+            int cont = (block == last_sent_block) ?
+                RAM_SAVE_FLAG_CONTINUE : 0;
+
+            p = memory_region_get_ram_ptr(mr) + offset;
+
+            /* In doubt sent page as normal */
+            bytes_sent = -1;
+            ret = ram_control_save_page(f, block->offset,
+                               offset, TARGET_PAGE_SIZE, &bytes_sent);
+
+            if (ret != RAM_SAVE_CONTROL_NOT_SUPP) {
+                if (ret != RAM_SAVE_CONTROL_DELAYED) {
+                    if (bytes_sent > 0) {
+                        acct_info.norm_pages++;
+                    } else if (bytes_sent == 0) {
+                        acct_info.dup_pages++;
+                    }
+                }
+            } else if (is_zero_range(p, TARGET_PAGE_SIZE)) {
+                acct_info.dup_pages++;
+                bytes_sent = save_block_hdr(f, block, offset, cont,
+                                            RAM_SAVE_FLAG_COMPRESS);
+                qemu_put_byte(f, 0);
+                bytes_sent++;
+            } 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) {
+                    p = get_cached_data(XBZRLE.cache, current_addr);
+                }
+            }
+
+            /* XBZRLE overflow or normal page */
+            if (bytes_sent == -1) {
+                bytes_sent = save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_PAGE);
+                qemu_put_buffer_async(f, p, TARGET_PAGE_SIZE);
+                bytes_sent += TARGET_PAGE_SIZE;
+                acct_info.norm_pages++;
+            }

            /* if page is unmodified, continue to the next */
            if (bytes_sent > 0) {
@@ -722,12 +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) {
@@ -736,16 +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)
@@ -767,39 +609,24 @@ static void reset_ram_globals(void)
 static int ram_save_setup(QEMUFile *f, void *opaque)
 {
    RAMBlock *block;
-    int64_t ram_bitmap_pages; /* Size of bitmap in pages, including gaps */
+    int64_t ram_pages = last_ram_offset() >> TARGET_PAGE_BITS;

+    migration_bitmap = bitmap_new(ram_pages);
+    bitmap_set(migration_bitmap, 0, ram_pages);
+    migration_dirty_pages = ram_pages;
    mig_throttle_on = false;
    dirty_rate_high_cnt = 0;
-    bitmap_sync_count = 0;

    if (migrate_use_xbzrle()) {
-        XBZRLE_cache_lock();
        XBZRLE.cache = cache_init(migrate_xbzrle_cache_size() /
                                  TARGET_PAGE_SIZE,
                                  TARGET_PAGE_SIZE);
        if (!XBZRLE.cache) {
-            XBZRLE_cache_unlock();
-            error_report("Error creating cache");
+            DPRINTF("Error creating cache\n");
            return -1;
        }
-        XBZRLE_cache_unlock();
-
-        /* We prefer not to abort if there is no memory */
-        XBZRLE.encoded_buf = g_try_malloc0(TARGET_PAGE_SIZE);
-        if (!XBZRLE.encoded_buf) {
-            error_report("Error allocating encoded_buf");
-            return -1;
-        }
-
-        XBZRLE.current_buf = g_try_malloc(TARGET_PAGE_SIZE);
-        if (!XBZRLE.current_buf) {
-            error_report("Error allocating current_buf");
-            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();
    }

@@ -808,22 +635,6 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
    bytes_transferred = 0;
    reset_ram_globals();

-    ram_bitmap_pages = last_ram_offset() >> TARGET_PAGE_BITS;
-    migration_bitmap = bitmap_new(ram_bitmap_pages);
-    bitmap_set(migration_bitmap, 0, ram_bitmap_pages);
-
-    /*
-     * Count the total number of pages used by ram blocks not including any
-     * gaps due to alignment or unplugs.
-     */
-    migration_dirty_pages = 0;
-    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
-        uint64_t block_pages;
-
-        block_pages = block->length >> TARGET_PAGE_BITS;
-        migration_dirty_pages += block_pages;
-    }
-
    memory_global_dirty_log_start();
    migration_bitmap_sync();
    qemu_mutex_unlock_iothread();
@@ -866,7 +677,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
    while ((ret = qemu_file_rate_limit(f)) == 0) {
        int bytes_sent;

-        bytes_sent = ram_find_and_save_block(f, false);
+        bytes_sent = ram_save_block(f, false);
        /* no more blocks to sent */
        if (bytes_sent == 0) {
            break;
@@ -928,7 +739,7 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
    while (true) {
        int bytes_sent;

-        bytes_sent = ram_find_and_save_block(f, true);
+        bytes_sent = ram_save_block(f, true);
        /* no more blocks to sent */
        if (bytes_sent == 0) {
            break;
@@ -962,11 +773,12 @@ static uint64_t ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size)

 static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
 {
+    int ret, rc = 0;
    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 */
@@ -974,25 +786,30 @@ static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
    xh_len = qemu_get_be16(f);

    if (xh_flags != ENCODING_FLAG_XBZRLE) {
-        error_report("Failed to load XBZRLE page - wrong compression!");
+        fprintf(stderr, "Failed to load XBZRLE page - wrong compression!\n");
        return -1;
    }

    if (xh_len > TARGET_PAGE_SIZE) {
-        error_report("Failed to load XBZRLE page - len overflow!");
+        fprintf(stderr, "Failed to load XBZRLE page - len overflow!\n");
        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 */
-    if (xbzrle_decode_buffer(xbzrle_decoded_buf, xh_len, host,
-                             TARGET_PAGE_SIZE) == -1) {
-        error_report("Failed to load XBZRLE page - decode error!");
-        return -1;
+    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");
+        rc = -1;
+    } else  if (ret > TARGET_PAGE_SIZE) {
+        fprintf(stderr, "Failed to load XBZRLE page - size %d exceeds %d!\n",
+                ret, TARGET_PAGE_SIZE);
+        abort();
    }

-    return 0;
+    return rc;
 }

 static inline void *host_from_stream_offset(QEMUFile *f,
@@ -1005,7 +822,7 @@ static inline void *host_from_stream_offset(QEMUFile *f,

    if (flags & RAM_SAVE_FLAG_CONTINUE) {
        if (!block) {
-            error_report("Ack, bad migration stream!");
+            fprintf(stderr, "Ack, bad migration stream!\n");
            return NULL;
        }

@@ -1021,7 +838,7 @@ static inline void *host_from_stream_offset(QEMUFile *f,
            return memory_region_get_ram_ptr(block->mr) + offset;
    }

-    error_report("Can't find block %s!", id);
+    fprintf(stderr, "Can't find block %s!\n", id);
    return NULL;
 }

@@ -1045,7 +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) {
@@ -1072,9 +889,10 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
                QTAILQ_FOREACH(block, &ram_list.blocks, next) {
                    if (!strncmp(id, block->idstr, sizeof(id))) {
                        if (block->length != length) {
-                            error_report("Length mismatch: %s: " RAM_ADDR_FMT
-                                         " in != " RAM_ADDR_FMT, id, length,
-                                         block->length);
+                            fprintf(stderr,
+                                    "Length mismatch: %s: " RAM_ADDR_FMT
+                                    " in != " RAM_ADDR_FMT "\n", id, length,
+                                    block->length);
                            ret =  -EINVAL;
                        }
                        break;
@@ -1082,8 +900,8 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
                }

                if (!block) {
-                    error_report("Unknown ramblock \"%s\", cannot "
-                                 "accept migration", id);
+                    fprintf(stderr, "Unknown ramblock \"%s\", cannot "
+                            "accept migration\n", id);
                    ret = -EINVAL;
                }
                if (ret) {
@@ -1098,9 +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);
@@ -1110,18 +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) {
@@ -1148,7 +960,7 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
    return ret;
 }

-static SaveVMHandlers savevm_ram_handlers = {
+SaveVMHandlers savevm_ram_handlers = {
    .save_live_setup = ram_save_setup,
    .save_live_iterate = ram_save_iterate,
    .save_live_complete = ram_save_complete,
@@ -1157,12 +969,6 @@ static SaveVMHandlers savevm_ram_handlers = {
    .cancel = ram_migration_cancel,
 };

-void ram_mig_init(void)
-{
-    qemu_mutex_init(&XBZRLE.lock);
-    register_savevm_live(NULL, "ram", 0, 4, &savevm_ram_handlers, NULL);
-}
-
 struct soundhw {
    const char *name;
    const char *descr;
@@ -1245,11 +1051,12 @@ void select_soundhw(const char *optarg)

            if (!c->name) {
                if (l > 80) {
-                    error_report("Unknown sound card name (too big to show)");
+                    fprintf(stderr,
+                            "Unknown sound card name (too big to show)\n");
                }
                else {
-                    error_report("Unknown sound card name `%.*s'",
-                                 (int) l, p);
+                    fprintf(stderr, "Unknown sound card name `%.*s'\n",
+                            (int) l, p);
                }
                bad_card = 1;
            }
@@ -1272,13 +1079,13 @@ void audio_init(void)
        if (c->enabled) {
            if (c->isa) {
                if (!isa_bus) {
-                    error_report("ISA bus not available for %s", c->name);
+                    fprintf(stderr, "ISA bus not available for %s\n", c->name);
                    exit(1);
                }
                c->init.init_isa(isa_bus);
            } else {
                if (!pci_bus) {
-                    error_report("PCI bus not available for %s", c->name);
+                    fprintf(stderr, "PCI bus not available for %s\n", c->name);
                    exit(1);
                }
                c->init.init_pci(pci_bus);
@@ -26,7 +26,6 @@
 #include "block/aio.h"
 #include "block/thread-pool.h"
 #include "qemu/main-loop.h"
-#include "qemu/atomic.h"

 /***********************************************************/
 /* bottom halves (can be seen as timers which expire ASAP) */
@@ -221,7 +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);
@@ -248,25 +246,9 @@ ThreadPool *aio_get_thread_pool(AioContext *ctx)
    return ctx->thread_pool;
 }

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

 static void aio_timerlist_notify(void *opaque)
@@ -274,12 +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;
@@ -287,7 +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 *)
@@ -306,13 +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);
-}
@@ -14,4 +14,4 @@ common-obj-$(CONFIG_AUDIO_WIN_INT) += audio_win_int.o
 common-obj-y += wavcapture.o

 $(obj)/audio.o $(obj)/fmodaudio.o: QEMU_CFLAGS += $(FMOD_CFLAGS)
-sdlaudio.o-cflags := $(SDL_CFLAGS)
+$(obj)/sdlaudio.o: QEMU_CFLAGS += $(SDL_CFLAGS)
@@ -815,8 +815,10 @@ static void alsa_fini_out (HWVoiceOut *hw)
    ldebug ("alsa_fini\n");
    alsa_anal_close (&alsa->handle, &alsa->pollhlp);

-    g_free(alsa->pcm_buf);
-    alsa->pcm_buf = NULL;
+    if (alsa->pcm_buf) {
+        g_free (alsa->pcm_buf);
+        alsa->pcm_buf = NULL;
+    }
 }

 static int alsa_init_out (HWVoiceOut *hw, struct audsettings *as)
@@ -976,8 +978,10 @@ static void alsa_fini_in (HWVoiceIn *hw)

    alsa_anal_close (&alsa->handle, &alsa->pollhlp);

-    g_free(alsa->pcm_buf);
-    alsa->pcm_buf = NULL;
+    if (alsa->pcm_buf) {
+        g_free (alsa->pcm_buf);
+        alsa->pcm_buf = NULL;
+    }
 }

 static int alsa_run_in (HWVoiceIn *hw)
@@ -95,7 +95,7 @@ static struct {
        }
    },

-    .period = { .hertz = 100 },
+    .period = { .hertz = 250 },
    .plive = 0,
    .log_to_monitor = 0,
    .try_poll_in = 1,
@@ -1812,7 +1812,8 @@ static const VMStateDescription vmstate_audio = {
    .name = "audio",
    .version_id = 1,
    .minimum_version_id = 1,
-    .fields = (VMStateField[]) {
+    .minimum_version_id_old = 1,
+    .fields      = (VMStateField []) {
        VMSTATE_END_OF_LIST()
    }
 };
@@ -71,7 +71,10 @@ static void glue (audio_init_nb_voices_, TYPE) (struct audio_driver *drv)

 static void glue (audio_pcm_hw_free_resources_, TYPE) (HW *hw)
 {
-    g_free (HWBUF);
+    if (HWBUF) {
+        g_free (HWBUF);
+    }
+
    HWBUF = NULL;
 }

@@ -89,7 +92,9 @@ static int glue (audio_pcm_hw_alloc_resources_, TYPE) (HW *hw)

 static void glue (audio_pcm_sw_free_resources_, TYPE) (SW *sw)
 {
-    g_free (sw->buf);
+    if (sw->buf) {
+        g_free (sw->buf);
+    }

    if (sw->rate) {
        st_rate_stop (sw->rate);
@@ -167,8 +172,10 @@ static int glue (audio_pcm_sw_init_, TYPE) (
 static void glue (audio_pcm_sw_fini_, TYPE) (SW *sw)
 {
    glue (audio_pcm_sw_free_resources_, TYPE) (sw);
-    g_free (sw->name);
-    sw->name = NULL;
+    if (sw->name) {
+        g_free (sw->name);
+        sw->name = NULL;
+    }
 }

 static void glue (audio_pcm_hw_add_sw_, TYPE) (HW *hw, SW *sw)
@@ -191,9 +198,9 @@ static void glue (audio_pcm_hw_gc_, TYPE) (HW **hwp)
        audio_detach_capture (hw);
 #endif
        QLIST_REMOVE (hw, entries);
-        glue (hw->pcm_ops->fini_, TYPE) (hw);
        glue (s->nb_hw_voices_, TYPE) += 1;
        glue (audio_pcm_hw_free_resources_ ,TYPE) (hw);
+        glue (hw->pcm_ops->fini_, TYPE) (hw);
        g_free (hw);
        *hwp = NULL;
    }
@@ -736,8 +736,10 @@ static void oss_fini_in (HWVoiceIn *hw)

    oss_anal_close (&oss->fd);

-    g_free(oss->pcm_buf);
-    oss->pcm_buf = NULL;
+    if (oss->pcm_buf) {
+        g_free (oss->pcm_buf);
+        oss->pcm_buf = NULL;
+    }
 }

 static int oss_run_in (HWVoiceIn *hw)
@@ -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;
@@ -105,7 +96,7 @@ static int rate_get_samples (struct audio_pcm_info *info, SpiceRateCtl *rate)
    bytes = muldiv64 (ticks, info->bytes_per_second, get_ticks_per_sec ());
    samples = (bytes - rate->bytes_sent) >> info->shift;
    if (samples < 0 || samples > 65536) {
-        error_report("Resetting rate control (%" PRId64 " samples)", samples);
+        fprintf (stderr, "Resetting rate control (%" PRId64 " samples)\n", samples);
        rate_start (rate);
        samples = 0;
    }
@@ -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;
 }

@@ -63,7 +63,8 @@ static void wav_destroy (void *opaque)
        }
    doclose:
        if (fclose (wav->f)) {
-            error_report("wav_destroy: fclose failed: %s", strerror(errno));
+            fprintf (stderr, "wav_destroy: fclose failed: %s",
+                     strerror (errno));
        }
    }

@@ -3,9 +3,6 @@ common-obj-$(CONFIG_POSIX) += rng-random.o

 common-obj-y += msmouse.o
 common-obj-$(CONFIG_BRLAPI) += baum.o
-baum.o-cflags := $(SDL_CFLAGS)
+$(obj)/baum.o: QEMU_CFLAGS += $(SDL_CFLAGS) 

 common-obj-$(CONFIG_TPM) += tpm.o
-
-common-obj-y += hostmem.o hostmem-ram.o
-common-obj-$(CONFIG_LINUX) += hostmem-file.o
@@ -566,15 +566,13 @@ 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;

    baum = g_malloc0(sizeof(BaumDriverState));
-    baum->chr = chr = qemu_chr_alloc();
+    baum->chr = chr = g_malloc0(sizeof(CharDriverState));

    chr->opaque = baum;
    chr->chr_write = baum_write;
@@ -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;

@@ -1,134 +0,0 @@
-/*
- * QEMU Host Memory Backend for hugetlbfs
- *
- * Copyright (C) 2013-2014 Red Hat Inc
- *
- * Authors:
- *   Paolo Bonzini <pbonzini@redhat.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.
- */
-#include "qemu-common.h"
-#include "sysemu/hostmem.h"
-#include "sysemu/sysemu.h"
-#include "qom/object_interfaces.h"
-
-/* hostmem-file.c */
-/**
- * @TYPE_MEMORY_BACKEND_FILE:
- * name of backend that uses mmap on a file descriptor
- */
-#define TYPE_MEMORY_BACKEND_FILE "memory-backend-file"
-
-#define MEMORY_BACKEND_FILE(obj) \
-    OBJECT_CHECK(HostMemoryBackendFile, (obj), TYPE_MEMORY_BACKEND_FILE)
-
-typedef struct HostMemoryBackendFile HostMemoryBackendFile;
-
-struct HostMemoryBackendFile {
-    HostMemoryBackend parent_obj;
-
-    bool share;
-    char *mem_path;
-};
-
-static void
-file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
-{
-    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(backend);
-
-    if (!backend->size) {
-        error_setg(errp, "can't create backend with size 0");
-        return;
-    }
-    if (!fb->mem_path) {
-        error_setg(errp, "mem_path property not set");
-        return;
-    }
-#ifndef CONFIG_LINUX
-    error_setg(errp, "-mem-path not supported on this host");
-#else
-    if (!memory_region_size(&backend->mr)) {
-        backend->force_prealloc = mem_prealloc;
-        memory_region_init_ram_from_file(&backend->mr, OBJECT(backend),
-                                 object_get_canonical_path(OBJECT(backend)),
-                                 backend->size, fb->share,
-                                 fb->mem_path, errp);
-    }
-#endif
-}
-
-static void
-file_backend_class_init(ObjectClass *oc, void *data)
-{
-    HostMemoryBackendClass *bc = MEMORY_BACKEND_CLASS(oc);
-
-    bc->alloc = file_backend_memory_alloc;
-}
-
-static char *get_mem_path(Object *o, Error **errp)
-{
-    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
-
-    return g_strdup(fb->mem_path);
-}
-
-static void set_mem_path(Object *o, const char *str, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(o);
-    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
-
-    if (memory_region_size(&backend->mr)) {
-        error_setg(errp, "cannot change property value");
-        return;
-    }
-    if (fb->mem_path) {
-        g_free(fb->mem_path);
-    }
-    fb->mem_path = g_strdup(str);
-}
-
-static bool file_memory_backend_get_share(Object *o, Error **errp)
-{
-    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
-
-    return fb->share;
-}
-
-static void file_memory_backend_set_share(Object *o, bool value, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(o);
-    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
-
-    if (memory_region_size(&backend->mr)) {
-        error_setg(errp, "cannot change property value");
-        return;
-    }
-    fb->share = value;
-}
-
-static void
-file_backend_instance_init(Object *o)
-{
-    object_property_add_bool(o, "share",
-                        file_memory_backend_get_share,
-                        file_memory_backend_set_share, NULL);
-    object_property_add_str(o, "mem-path", get_mem_path,
-                            set_mem_path, NULL);
-}
-
-static const TypeInfo file_backend_info = {
-    .name = TYPE_MEMORY_BACKEND_FILE,
-    .parent = TYPE_MEMORY_BACKEND,
-    .class_init = file_backend_class_init,
-    .instance_init = file_backend_instance_init,
-    .instance_size = sizeof(HostMemoryBackendFile),
-};
-
-static void register_types(void)
-{
-    type_register_static(&file_backend_info);
-}
-
-type_init(register_types);
@@ -1,53 +0,0 @@
-/*
- * QEMU Host Memory Backend
- *
- * Copyright (C) 2013-2014 Red Hat Inc
- *
- * Authors:
- *   Igor Mammedov <imammedo@redhat.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.
- */
-#include "sysemu/hostmem.h"
-#include "qom/object_interfaces.h"
-
-#define TYPE_MEMORY_BACKEND_RAM "memory-backend-ram"
-
-
-static void
-ram_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
-{
-    char *path;
-
-    if (!backend->size) {
-        error_setg(errp, "can't create backend with size 0");
-        return;
-    }
-
-    path = object_get_canonical_path_component(OBJECT(backend));
-    memory_region_init_ram(&backend->mr, OBJECT(backend), path,
-                           backend->size);
-    g_free(path);
-}
-
-static void
-ram_backend_class_init(ObjectClass *oc, void *data)
-{
-    HostMemoryBackendClass *bc = MEMORY_BACKEND_CLASS(oc);
-
-    bc->alloc = ram_backend_memory_alloc;
-}
-
-static const TypeInfo ram_backend_info = {
-    .name = TYPE_MEMORY_BACKEND_RAM,
-    .parent = TYPE_MEMORY_BACKEND,
-    .class_init = ram_backend_class_init,
-};
-
-static void register_types(void)
-{
-    type_register_static(&ram_backend_info);
-}
-
-type_init(register_types);
@@ -1,375 +0,0 @@
-/*
- * QEMU Host Memory Backend
- *
- * Copyright (C) 2013-2014 Red Hat Inc
- *
- * Authors:
- *   Igor Mammedov <imammedo@redhat.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.
- */
-#include "sysemu/hostmem.h"
-#include "qapi/visitor.h"
-#include "qapi-types.h"
-#include "qapi-visit.h"
-#include "qapi/qmp/qerror.h"
-#include "qemu/config-file.h"
-#include "qom/object_interfaces.h"
-
-#ifdef CONFIG_NUMA
-#include <numaif.h>
-QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_DEFAULT != MPOL_DEFAULT);
-QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_PREFERRED != MPOL_PREFERRED);
-QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_BIND != MPOL_BIND);
-QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_INTERLEAVE != MPOL_INTERLEAVE);
-#endif
-
-static void
-host_memory_backend_get_size(Object *obj, Visitor *v, void *opaque,
-                             const char *name, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-    uint64_t value = backend->size;
-
-    visit_type_size(v, &value, name, errp);
-}
-
-static void
-host_memory_backend_set_size(Object *obj, Visitor *v, void *opaque,
-                             const char *name, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-    Error *local_err = NULL;
-    uint64_t value;
-
-    if (memory_region_size(&backend->mr)) {
-        error_setg(&local_err, "cannot change property value");
-        goto out;
-    }
-
-    visit_type_size(v, &value, name, &local_err);
-    if (local_err) {
-        goto out;
-    }
-    if (!value) {
-        error_setg(&local_err, "Property '%s.%s' doesn't take value '%"
-                   PRIu64 "'", object_get_typename(obj), name, value);
-        goto out;
-    }
-    backend->size = value;
-out:
-    error_propagate(errp, local_err);
-}
-
-static void
-host_memory_backend_get_host_nodes(Object *obj, Visitor *v, void *opaque,
-                                   const char *name, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-    uint16List *host_nodes = NULL;
-    uint16List **node = &host_nodes;
-    unsigned long value;
-
-    value = find_first_bit(backend->host_nodes, MAX_NODES);
-    if (value == MAX_NODES) {
-        return;
-    }
-
-    *node = g_malloc0(sizeof(**node));
-    (*node)->value = value;
-    node = &(*node)->next;
-
-    do {
-        value = find_next_bit(backend->host_nodes, MAX_NODES, value + 1);
-        if (value == MAX_NODES) {
-            break;
-        }
-
-        *node = g_malloc0(sizeof(**node));
-        (*node)->value = value;
-        node = &(*node)->next;
-    } while (true);
-
-    visit_type_uint16List(v, &host_nodes, name, errp);
-}
-
-static void
-host_memory_backend_set_host_nodes(Object *obj, Visitor *v, void *opaque,
-                                   const char *name, Error **errp)
-{
-#ifdef CONFIG_NUMA
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-    uint16List *l = NULL;
-
-    visit_type_uint16List(v, &l, name, errp);
-
-    while (l) {
-        bitmap_set(backend->host_nodes, l->value, 1);
-        l = l->next;
-    }
-#else
-    error_setg(errp, "NUMA node binding are not supported by this QEMU");
-#endif
-}
-
-static void
-host_memory_backend_get_policy(Object *obj, Visitor *v, void *opaque,
-                               const char *name, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-    int policy = backend->policy;
-
-    visit_type_enum(v, &policy, HostMemPolicy_lookup, NULL, name, errp);
-}
-
-static void
-host_memory_backend_set_policy(Object *obj, Visitor *v, void *opaque,
-                               const char *name, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-    int policy;
-
-    visit_type_enum(v, &policy, HostMemPolicy_lookup, NULL, name, errp);
-    backend->policy = policy;
-
-#ifndef CONFIG_NUMA
-    if (policy != HOST_MEM_POLICY_DEFAULT) {
-        error_setg(errp, "NUMA policies are not supported by this QEMU");
-    }
-#endif
-}
-
-static bool host_memory_backend_get_merge(Object *obj, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-
-    return backend->merge;
-}
-
-static void host_memory_backend_set_merge(Object *obj, bool value, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-
-    if (!memory_region_size(&backend->mr)) {
-        backend->merge = value;
-        return;
-    }
-
-    if (value != backend->merge) {
-        void *ptr = memory_region_get_ram_ptr(&backend->mr);
-        uint64_t sz = memory_region_size(&backend->mr);
-
-        qemu_madvise(ptr, sz,
-                     value ? QEMU_MADV_MERGEABLE : QEMU_MADV_UNMERGEABLE);
-        backend->merge = value;
-    }
-}
-
-static bool host_memory_backend_get_dump(Object *obj, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-
-    return backend->dump;
-}
-
-static void host_memory_backend_set_dump(Object *obj, bool value, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-
-    if (!memory_region_size(&backend->mr)) {
-        backend->dump = value;
-        return;
-    }
-
-    if (value != backend->dump) {
-        void *ptr = memory_region_get_ram_ptr(&backend->mr);
-        uint64_t sz = memory_region_size(&backend->mr);
-
-        qemu_madvise(ptr, sz,
-                     value ? QEMU_MADV_DODUMP : QEMU_MADV_DONTDUMP);
-        backend->dump = value;
-    }
-}
-
-static bool host_memory_backend_get_prealloc(Object *obj, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-
-    return backend->prealloc || backend->force_prealloc;
-}
-
-static void host_memory_backend_set_prealloc(Object *obj, bool value,
-                                             Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-
-    if (backend->force_prealloc) {
-        if (value) {
-            error_setg(errp,
-                       "remove -mem-prealloc to use the prealloc property");
-            return;
-        }
-    }
-
-    if (!memory_region_size(&backend->mr)) {
-        backend->prealloc = value;
-        return;
-    }
-
-    if (value && !backend->prealloc) {
-        int fd = memory_region_get_fd(&backend->mr);
-        void *ptr = memory_region_get_ram_ptr(&backend->mr);
-        uint64_t sz = memory_region_size(&backend->mr);
-
-        os_mem_prealloc(fd, ptr, sz);
-        backend->prealloc = true;
-    }
-}
-
-static void host_memory_backend_init(Object *obj)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-
-    backend->merge = qemu_opt_get_bool(qemu_get_machine_opts(),
-                                       "mem-merge", true);
-    backend->dump = qemu_opt_get_bool(qemu_get_machine_opts(),
-                                      "dump-guest-core", true);
-    backend->prealloc = mem_prealloc;
-
-    object_property_add_bool(obj, "merge",
-                        host_memory_backend_get_merge,
-                        host_memory_backend_set_merge, NULL);
-    object_property_add_bool(obj, "dump",
-                        host_memory_backend_get_dump,
-                        host_memory_backend_set_dump, NULL);
-    object_property_add_bool(obj, "prealloc",
-                        host_memory_backend_get_prealloc,
-                        host_memory_backend_set_prealloc, NULL);
-    object_property_add(obj, "size", "int",
-                        host_memory_backend_get_size,
-                        host_memory_backend_set_size, NULL, NULL, NULL);
-    object_property_add(obj, "host-nodes", "int",
-                        host_memory_backend_get_host_nodes,
-                        host_memory_backend_set_host_nodes, NULL, NULL, NULL);
-    object_property_add(obj, "policy", "str",
-                        host_memory_backend_get_policy,
-                        host_memory_backend_set_policy, NULL, NULL, NULL);
-}
-
-static void host_memory_backend_finalize(Object *obj)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-
-    if (memory_region_size(&backend->mr)) {
-        memory_region_destroy(&backend->mr);
-    }
-}
-
-MemoryRegion *
-host_memory_backend_get_memory(HostMemoryBackend *backend, Error **errp)
-{
-    return memory_region_size(&backend->mr) ? &backend->mr : NULL;
-}
-
-static void
-host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(uc);
-    HostMemoryBackendClass *bc = MEMORY_BACKEND_GET_CLASS(uc);
-    Error *local_err = NULL;
-    void *ptr;
-    uint64_t sz;
-
-    if (bc->alloc) {
-        bc->alloc(backend, &local_err);
-        if (local_err) {
-            error_propagate(errp, local_err);
-            return;
-        }
-
-        ptr = memory_region_get_ram_ptr(&backend->mr);
-        sz = memory_region_size(&backend->mr);
-
-        if (backend->merge) {
-            qemu_madvise(ptr, sz, QEMU_MADV_MERGEABLE);
-        }
-        if (!backend->dump) {
-            qemu_madvise(ptr, sz, QEMU_MADV_DONTDUMP);
-        }
-#ifdef CONFIG_NUMA
-        unsigned long lastbit = find_last_bit(backend->host_nodes, MAX_NODES);
-        /* lastbit == MAX_NODES means maxnode = 0 */
-        unsigned long maxnode = (lastbit + 1) % (MAX_NODES + 1);
-        /* ensure policy won't be ignored in case memory is preallocated
-         * before mbind(). note: MPOL_MF_STRICT is ignored on hugepages so
-         * this doesn't catch hugepage case. */
-        unsigned flags = MPOL_MF_STRICT | MPOL_MF_MOVE;
-
-        /* check for invalid host-nodes and policies and give more verbose
-         * error messages than mbind(). */
-        if (maxnode && backend->policy == MPOL_DEFAULT) {
-            error_setg(errp, "host-nodes must be empty for policy default,"
-                       " or you should explicitly specify a policy other"
-                       " than default");
-            return;
-        } else if (maxnode == 0 && backend->policy != MPOL_DEFAULT) {
-            error_setg(errp, "host-nodes must be set for policy %s",
-                       HostMemPolicy_lookup[backend->policy]);
-            return;
-        }
-
-        /* We can have up to MAX_NODES nodes, but we need to pass maxnode+1
-         * as argument to mbind() due to an old Linux bug (feature?) which
-         * cuts off the last specified node. This means backend->host_nodes
-         * must have MAX_NODES+1 bits available.
-         */
-        assert(sizeof(backend->host_nodes) >=
-               BITS_TO_LONGS(MAX_NODES + 1) * sizeof(unsigned long));
-        assert(maxnode <= MAX_NODES);
-        if (mbind(ptr, sz, backend->policy,
-                  maxnode ? backend->host_nodes : NULL, maxnode + 1, flags)) {
-            error_setg_errno(errp, errno,
-                             "cannot bind memory to host NUMA nodes");
-            return;
-        }
-#endif
-        /* Preallocate memory after the NUMA policy has been instantiated.
-         * This is necessary to guarantee memory is allocated with
-         * specified NUMA policy in place.
-         */
-        if (backend->prealloc) {
-            os_mem_prealloc(memory_region_get_fd(&backend->mr), ptr, sz);
-        }
-    }
-}
-
-static void
-host_memory_backend_class_init(ObjectClass *oc, void *data)
-{
-    UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
-
-    ucc->complete = host_memory_backend_memory_complete;
-}
-
-static const TypeInfo host_memory_backend_info = {
-    .name = TYPE_MEMORY_BACKEND,
-    .parent = TYPE_OBJECT,
-    .abstract = true,
-    .class_size = sizeof(HostMemoryBackendClass),
-    .class_init = host_memory_backend_class_init,
-    .instance_size = sizeof(HostMemoryBackend),
-    .instance_init = host_memory_backend_init,
-    .instance_finalize = host_memory_backend_finalize,
-    .interfaces = (InterfaceInfo[]) {
-        { TYPE_USER_CREATABLE },
-        { }
-    }
-};
-
-static void register_types(void)
-{
-    type_register_static(&host_memory_backend_info);
-}
-
-type_init(register_types);
@@ -67,7 +67,7 @@ CharDriverState *qemu_chr_open_msmouse(void)
 {
    CharDriverState *chr;

-    chr = qemu_chr_alloc();
+    chr = g_malloc0(sizeof(CharDriverState));
    chr->chr_write = msmouse_chr_write;
    chr->chr_close = msmouse_chr_close;
    chr->explicit_be_open = true;
@@ -169,7 +169,6 @@ static void rng_egd_set_chardev(Object *obj, const char *value, Error **errp)
    if (b->opened) {
        error_set(errp, QERR_PERMISSION_DENIED);
    } else {
-        g_free(s->chr_name);
        s->chr_name = g_strdup(value);
    }
 }
@@ -106,7 +106,10 @@ static void rng_random_set_filename(Object *obj, const char *filename,
        return;
    }

-    g_free(s->filename);
+    if (s->filename) {
+        g_free(s->filename);
+    }
+
    s->filename = g_strdup(filename);
 }

@@ -120,15 +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,
@@ -41,16 +40,15 @@ 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)
 {
    RngBackend *s = RNG_BACKEND(obj);
    RngBackendClass *k = RNG_BACKEND_GET_CLASS(s);
-    Error *local_err = NULL;

    if (value == s->opened) {
        return;
@@ -62,14 +60,12 @@ static void rng_backend_prop_set_opened(Object *obj, bool value, Error **errp)
    }

    if (k->opened) {
-        k->opened(s, &local_err);
-        if (local_err) {
-            error_propagate(errp, local_err);
-            return;
-        }
+        k->opened(s, errp);
    }

-    s->opened = true;
+    if (!error_is_set(errp)) {
+        s->opened = value;
+    }
 }

 static void rng_backend_init(Object *obj)
@@ -80,25 +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)
@@ -112,7 +112,6 @@ static void tpm_backend_prop_set_opened(Object *obj, bool value, Error **errp)
 {
    TPMBackend *s = TPM_BACKEND(obj);
    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-    Error *local_err = NULL;

    if (value == s->opened) {
        return;
@@ -124,14 +123,12 @@ static void tpm_backend_prop_set_opened(Object *obj, bool value, Error **errp)
    }

    if (k->opened) {
-        k->opened(s, &local_err);
-        if (local_err) {
-            error_propagate(errp, local_err);
-            return;
-        }
+        k->opened(s, errp);
    }

-    s->opened = true;
+    if (!error_is_set(errp)) {
+        s->opened = value;
+    }
 }

 static void tpm_backend_instance_init(Object *obj)
@@ -81,6 +81,19 @@ static int qemu_balloon_status(BalloonInfo *info)
    return 1;
 }

+void qemu_balloon_changed(int64_t actual)
+{
+    QObject *data;
+
+    data = qobject_from_jsonf("{ 'actual': %" PRId64 " }",
+                              actual);
+
+    monitor_protocol_event(QEVENT_BALLOON_CHANGE, data);
+
+    qobject_decref(data);
+}
+
+
 BalloonInfo *qmp_query_balloon(Error **errp)
 {
    BalloonInfo *info;
@@ -58,8 +58,6 @@ typedef struct BlkMigDevState {
    /* Protected by block migration lock.  */
    unsigned long *aio_bitmap;
    int64_t completed_sectors;
-    BdrvDirtyBitmap *dirty_bitmap;
-    Error *blocker;
 } BlkMigDevState;

 typedef struct BlkMigBlock {
@@ -311,36 +309,12 @@ static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds)

 /* Called with iothread lock taken.  */

-static int set_dirty_tracking(void)
-{
-    BlkMigDevState *bmds;
-    int ret;
-
-    QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
-        bmds->dirty_bitmap = bdrv_create_dirty_bitmap(bmds->bs, BLOCK_SIZE,
-                                                      NULL);
-        if (!bmds->dirty_bitmap) {
-            ret = -errno;
-            goto fail;
-        }
-    }
-    return 0;
-
-fail:
-    QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
-        if (bmds->dirty_bitmap) {
-            bdrv_release_dirty_bitmap(bmds->bs, bmds->dirty_bitmap);
-        }
-    }
-    return ret;
-}
-
-static void unset_dirty_tracking(void)
+static void set_dirty_tracking(int enable)
 {
    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);
    }
 }

@@ -362,8 +336,7 @@ static void init_blk_migration_it(void *opaque, BlockDriverState *bs)
        bmds->completed_sectors = 0;
        bmds->shared_base = block_mig_state.shared_base;
        alloc_aio_bitmap(bmds);
-        error_setg(&bmds->blocker, "block device is in use by migration");
-        bdrv_op_block_all(bs, bmds->blocker);
+        bdrv_set_in_use(bs, 1);
        bdrv_ref(bs);

        block_mig_state.total_sector_sum += sectors;
@@ -459,7 +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;
@@ -581,7 +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;
@@ -596,13 +569,12 @@ 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) {
        QSIMPLEQ_REMOVE_HEAD(&block_mig_state.bmds_list, entry);
-        bdrv_op_unblock_all(bmds->bs, bmds->blocker);
-        error_free(bmds->blocker);
+        bdrv_set_in_use(bmds->bs, 0);
        bdrv_unref(bmds->bs);
        g_free(bmds->aio_bitmap);
        g_free(bmds);
@@ -632,13 +604,7 @@ static int block_save_setup(QEMUFile *f, void *opaque)
    init_blk_migration(f);

    /* start track dirty blocks */
-    ret = set_dirty_tracking();
-
-    if (ret) {
-        qemu_mutex_unlock_iothread();
-        return ret;
-    }
-
+    set_dirty_tracking(1);
    qemu_mutex_unlock_iothread();

    ret = flush_blks(f);
@@ -652,7 +618,6 @@ static int block_save_iterate(QEMUFile *f, void *opaque)
 {
    int ret;
    int64_t last_ftell = qemu_ftell(f);
-    int64_t delta_ftell;

    DPRINTF("Enter save live iterate submitted %d transferred %d\n",
            block_mig_state.submitted, block_mig_state.transferred);
@@ -702,14 +667,7 @@ static int block_save_iterate(QEMUFile *f, void *opaque)
    }

    qemu_put_be64(f, BLK_MIG_FLAG_EOS);
-    delta_ftell = qemu_ftell(f) - last_ftell;
-    if (delta_ftell > 0) {
-        return 1;
-    } else if (delta_ftell < 0) {
-        return -1;
-    } else {
-        return 0;
-    }
+    return qemu_ftell(f) - last_ftell;
 }

 /* Called with iothread lock taken.  */
@@ -764,8 +722,8 @@ static uint64_t block_save_pending(QEMUFile *f, void *opaque, uint64_t max_size)
                       block_mig_state.read_done * BLOCK_SIZE;

    /* Report at least one block pending during bulk phase */
-    if (pending <= max_size && !block_mig_state.bulk_completed) {
-        pending = max_size + BLOCK_SIZE;
+    if (pending == 0 && !block_mig_state.bulk_completed) {
+        pending = BLOCK_SIZE;
    }
    blk_mig_unlock();
    qemu_mutex_unlock_iothread();
@@ -822,8 +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);
@@ -869,7 +826,7 @@ static bool block_is_active(void *opaque)
    return block_mig_state.blk_enable == 1;
 }

-static SaveVMHandlers savevm_block_handlers = {
+SaveVMHandlers savevm_block_handlers = {
    .set_params = block_set_params,
    .save_live_setup = block_save_setup,
    .save_live_iterate = block_save_iterate,
@@ -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)
@@ -307,7 +301,7 @@ static void coroutine_fn backup_run(void *opaque)
                                BACKUP_SECTORS_PER_CLUSTER - i, &n);
                    i += n;

-                    if (alloced == 1 || n == 0) {
+                    if (alloced == 1) {
                        break;
                    }
                }
@@ -325,7 +319,7 @@ static void coroutine_fn backup_run(void *opaque)
                /* Depending on error action, fail now or retry cluster */
                BlockErrorAction action =
                    backup_error_action(job, error_is_read, -ret);
-                if (action == BLOCK_ERROR_ACTION_REPORT) {
+                if (action == BDRV_ACTION_REPORT) {
                    break;
                } else {
                    start--;
@@ -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;
 }
@@ -449,10 +411,6 @@ static void error_callback_bh(void *opaque)
 static void blkdebug_aio_cancel(BlockDriverAIOCB *blockacb)
 {
    BlkdebugAIOCB *acb = container_of(blockacb, BlkdebugAIOCB, common);
-    if (acb->bh) {
-        qemu_bh_delete(acb->bh);
-        acb->bh = NULL;
-    }
    qemu_aio_release(acb);
 }

@@ -475,7 +433,7 @@ static BlockDriverAIOCB *inject_error(BlockDriverState *bs,
    acb = qemu_aio_get(&blkdebug_aiocb_info, bs, cb, opaque);
    acb->ret = -error;

-    bh = aio_bh_new(bdrv_get_aio_context(bs), error_callback_bh, acb);
+    bh = qemu_bh_new(error_callback_bh, acb);
    acb->bh = bh;
    qemu_bh_schedule(bh);

@@ -526,25 +484,6 @@ static BlockDriverAIOCB *blkdebug_aio_writev(BlockDriverState *bs,
    return bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
 }

-static BlockDriverAIOCB *blkdebug_aio_flush(BlockDriverState *bs,
-    BlockDriverCompletionFunc *cb, void *opaque)
-{
-    BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugRule *rule = NULL;
-
-    QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
-        if (rule->options.inject.sector == -1) {
-            break;
-        }
-    }
-
-    if (rule && rule->options.inject.error) {
-        return inject_error(bs, cb, opaque, rule);
-    }
-
-    return bdrv_aio_flush(bs->file, cb, opaque);
-}
-

 static void blkdebug_close(BlockDriverState *bs)
 {
@@ -655,9 +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;
@@ -666,31 +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)
 {
@@ -722,12 +636,9 @@ static BlockDriver bdrv_blkdebug = {

    .bdrv_aio_readv         = blkdebug_aio_readv,
    .bdrv_aio_writev        = blkdebug_aio_writev,
-    .bdrv_aio_flush         = blkdebug_aio_flush,

    .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,
 };
@@ -39,13 +39,12 @@ struct BlkverifyAIOCB {
 static void blkverify_aio_cancel(BlockDriverAIOCB *blockacb)
 {
    BlkverifyAIOCB *acb = (BlkverifyAIOCB *)blockacb;
-    AioContext *aio_context = bdrv_get_aio_context(blockacb->bs);
    bool finished = false;

    /* Wait until request completes, invokes its callback, and frees itself */
    acb->finished = &finished;
    while (!finished) {
-        aio_poll(aio_context, true);
+        qemu_aio_wait();
    }
 }

@@ -79,9 +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;
    }

@@ -125,31 +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;
    }
@@ -174,6 +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,
@@ -229,8 +343,7 @@ static void blkverify_aio_cb(void *opaque, int ret)
            acb->verify(acb);
        }

-        acb->bh = aio_bh_new(bdrv_get_aio_context(acb->common.bs),
-                             blkverify_aio_bh, acb);
+        acb->bh = qemu_bh_new(blkverify_aio_bh, acb);
        qemu_bh_schedule(acb->bh);
        break;
    }
@@ -238,7 +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));
@@ -256,7 +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);
@@ -290,55 +403,21 @@ 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);
-}
-
-/* Propagate AioContext changes to ->test_file */
-static void blkverify_detach_aio_context(BlockDriverState *bs)
-{
-    BDRVBlkverifyState *s = bs->opaque;
-
-    bdrv_detach_aio_context(s->test_file);
-}
-
-static void blkverify_attach_aio_context(BlockDriverState *bs,
-                                         AioContext *new_context)
-{
-    BDRVBlkverifyState *s = bs->opaque;
-
-    bdrv_attach_aio_context(s->test_file, new_context);
-}
-
 static BlockDriver bdrv_blkverify = {
-    .format_name                      = "blkverify",
-    .protocol_name                    = "blkverify",
-    .instance_size                    = sizeof(BDRVBlkverifyState),
+    .format_name            = "blkverify",
+    .protocol_name          = "blkverify",
+    .instance_size          = sizeof(BDRVBlkverifyState),

-    .bdrv_parse_filename              = blkverify_parse_filename,
-    .bdrv_file_open                   = blkverify_open,
-    .bdrv_close                       = blkverify_close,
-    .bdrv_getlength                   = blkverify_getlength,
+    .bdrv_parse_filename    = blkverify_parse_filename,
+    .bdrv_file_open         = blkverify_open,
+    .bdrv_close             = blkverify_close,
+    .bdrv_getlength         = blkverify_getlength,

-    .bdrv_aio_readv                   = blkverify_aio_readv,
-    .bdrv_aio_writev                  = blkverify_aio_writev,
-    .bdrv_aio_flush                   = blkverify_aio_flush,
+    .bdrv_aio_readv         = blkverify_aio_readv,
+    .bdrv_aio_writev        = blkverify_aio_writev,
+    .bdrv_aio_flush         = blkverify_aio_flush,

-    .bdrv_attach_aio_context          = blkverify_attach_aio_context,
-    .bdrv_detach_aio_context          = blkverify_detach_aio_context,
-
-    .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;
@@ -187,14 +176,13 @@ static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)
    uint64_t offset = sector_num * 512;
    uint64_t extent_index, extent_offset, bitmap_offset;
    char bitmap_entry;
-    int ret;

    // seek to sector
    extent_index = offset / s->extent_size;
    extent_offset = (offset % s->extent_size) / 512;

    if (s->catalog_bitmap[extent_index] == 0xffffffff) {
-	return 0; /* not allocated */
+	return -1; /* not allocated */
    }

    bitmap_offset = s->data_offset +
@@ -202,14 +190,13 @@ static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)
        (s->extent_blocks + s->bitmap_blocks));

    /* read in bitmap for current extent */
-    ret = bdrv_pread(bs->file, bitmap_offset + (extent_offset / 8),
-                     &bitmap_entry, 1);
-    if (ret < 0) {
-        return ret;
+    if (bdrv_pread(bs->file, bitmap_offset + (extent_offset / 8),
+                   &bitmap_entry, 1) != 1) {
+        return -1;
    }

    if (!((bitmap_entry >> (extent_offset % 8)) & 1)) {
-	return 0; /* not allocated */
+	return -1; /* not allocated */
    }

    return bitmap_offset + (512 * (s->bitmap_blocks + extent_offset));
@@ -222,16 +209,13 @@ static int bochs_read(BlockDriverState *bs, int64_t sector_num,

    while (nb_sectors > 0) {
        int64_t block_offset = seek_to_sector(bs, sector_num);
-        if (block_offset < 0) {
-            return block_offset;
-        } else if (block_offset > 0) {
+        if (block_offset >= 0) {
            ret = bdrv_pread(bs->file, block_offset, buf, 512);
-            if (ret < 0) {
-                return ret;
+            if (ret != 512) {
+                return -1;
            }
-        } else {
+        } else
            memset(buf, 0, 512);
-        }
        nb_sectors--;
        sector_num++;
        buf += 512;
@@ -72,7 +72,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
    }
    s->block_size = be32_to_cpu(s->block_size);
    if (s->block_size % 512) {
-        error_setg(errp, "block_size %" PRIu32 " must be a multiple of 512",
+        error_setg(errp, "block_size %u must be a multiple of 512",
                   s->block_size);
        return -EINVAL;
    }
@@ -86,7 +86,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
     * need a buffer this big.
     */
    if (s->block_size > MAX_BLOCK_SIZE) {
-        error_setg(errp, "block_size %" PRIu32 " must be %u MB or less",
+        error_setg(errp, "block_size %u must be %u MB or less",
                   s->block_size,
                   MAX_BLOCK_SIZE / (1024 * 1024));
        return -EINVAL;
@@ -101,7 +101,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
    /* read offsets */
    if (s->n_blocks > (UINT32_MAX - 1) / sizeof(uint64_t)) {
        /* Prevent integer overflow */
-        error_setg(errp, "n_blocks %" PRIu32 " must be %zu or less",
+        error_setg(errp, "n_blocks %u must be %zu or less",
                   s->n_blocks,
                   (UINT32_MAX - 1) / sizeof(uint64_t));
        return -EINVAL;
@@ -133,7 +133,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,

        if (s->offsets[i] < s->offsets[i - 1]) {
            error_setg(errp, "offsets not monotonically increasing at "
-                       "index %" PRIu32 ", image file is corrupt", i);
+                       "index %u, image file is corrupt", i);
            ret = -EINVAL;
            goto fail;
        }
@@ -146,8 +146,8 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
         * ridiculous s->compressed_block allocation.
         */
        if (size > 2 * MAX_BLOCK_SIZE) {
-            error_setg(errp, "invalid compressed block size at index %" PRIu32
-                       ", image file is corrupt", i);
+            error_setg(errp, "invalid compressed block size at index %u, "
+                       "image file is corrupt", i);
            ret = -EINVAL;
            goto fail;
        }
@@ -37,7 +37,6 @@ typedef struct CommitBlockJob {
    BlockdevOnError on_error;
    int base_flags;
    int orig_overlay_flags;
-    char *backing_file_str;
 } CommitBlockJob;

 static int coroutine_fn commit_populate(BlockDriverState *bs,
@@ -142,7 +141,7 @@ wait:

    if (!block_job_is_cancelled(&s->common) && sector_num == end) {
        /* success */
-        ret = bdrv_drop_intermediate(active, top, base, s->backing_file_str);
+        ret = bdrv_drop_intermediate(active, top, base);
    }

 exit_free_buf:
@@ -159,7 +158,7 @@ exit_restore_reopen:
    if (overlay_bs && s->orig_overlay_flags != bdrv_get_flags(overlay_bs)) {
        bdrv_reopen(overlay_bs, s->orig_overlay_flags, NULL);
    }
-    g_free(s->backing_file_str);
+
    block_job_completed(&s->common, ret);
 }

@@ -183,7 +182,7 @@ static const BlockJobDriver commit_job_driver = {
 void commit_start(BlockDriverState *bs, BlockDriverState *base,
                  BlockDriverState *top, int64_t speed,
                  BlockdevOnError on_error, BlockDriverCompletionFunc *cb,
-                  void *opaque, const char *backing_file_str, Error **errp)
+                  void *opaque, Error **errp)
 {
    CommitBlockJob *s;
    BlockReopenQueue *reopen_queue = NULL;
@@ -195,11 +194,17 @@ void commit_start(BlockDriverState *bs, BlockDriverState *base,
    if ((on_error == BLOCKDEV_ON_ERROR_STOP ||
         on_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
        !bdrv_iostatus_is_enabled(bs)) {
-        error_setg(errp, "Invalid parameter combination");
+        error_set(errp, QERR_INVALID_PARAMETER_COMBINATION);
+        return;
+    }
+
+    /* 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;
    }

-    assert(top != bs);
    if (top == base) {
        error_setg(errp, "Invalid files for merge: top and base are the same");
        return;
@@ -245,8 +250,6 @@ void commit_start(BlockDriverState *bs, BlockDriverState *base,
    s->base_flags          = orig_base_flags;
    s->orig_overlay_flags  = orig_overlay_flags;

-    s->backing_file_str = g_strdup(backing_file_str);
-
    s->on_error = on_error;
    s->common.co = qemu_coroutine_create(commit_run);

@@ -74,16 +74,15 @@ 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;
    }

    if (be32_to_cpu(cow_header.version) != COW_VERSION) {
        char version[64];
        snprintf(version, sizeof(version),
-               "COW version %" PRIu32, cow_header.version);
-        error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+               "COW version %d", cow_header.version);
+        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,
@@ -324,31 +295,39 @@ static void cow_close(BlockDriverState *bs)
 {
 }

-static int cow_create(const char *filename, QemuOpts *opts, Error **errp)
+static int cow_create(const char *filename, QEMUOptionParameter *options,
+                      Error **errp)
 {
    struct cow_header_v2 cow_header;
    struct stat st;
    int64_t image_sectors = 0;
-    char *image_filename = NULL;
+    const char *image_filename = NULL;
    Error *local_err = NULL;
    int ret;
-    BlockDriverState *cow_bs = NULL;
+    BlockDriverState *cow_bs;

    /* Read out options */
-    image_sectors = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
-    image_filename = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
-
-    ret = bdrv_create_file(filename, opts, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto exit;
+    while (options && options->name) {
+        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+            image_sectors = options->value.n / 512;
+        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
+            image_filename = options->value.s;
+        }
+        options++;
    }

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

    memset(&cow_header, 0, sizeof(cow_header));
@@ -381,29 +360,22 @@ static int cow_create(const char *filename, QemuOpts *opts, Error **errp)
    }

 exit:
-    g_free(image_filename);
-    if (cow_bs) {
-        bdrv_unref(cow_bs);
-    }
+    bdrv_unref(cow_bs);
    return ret;
 }

-static QemuOptsList cow_create_opts = {
-    .name = "cow-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(cow_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        {
-            .name = BLOCK_OPT_BACKING_FILE,
-            .type = QEMU_OPT_STRING,
-            .help = "File name of a base image"
-        },
-        { /* end of list */ }
-    }
+static QEMUOptionParameter cow_create_options[] = {
+    {
+        .name = BLOCK_OPT_SIZE,
+        .type = OPT_SIZE,
+        .help = "Virtual disk size"
+    },
+    {
+        .name = BLOCK_OPT_BACKING_FILE,
+        .type = OPT_STRING,
+        .help = "File name of a base image"
+    },
+    { NULL }
 };

 static BlockDriver bdrv_cow = {
@@ -415,13 +387,12 @@ static BlockDriver bdrv_cow = {
    .bdrv_close     = cow_close,
    .bdrv_create    = cow_create,
    .bdrv_has_zero_init     = bdrv_has_zero_init_1,
-    .supports_backing       = true,

    .bdrv_read              = cow_co_read,
    .bdrv_write             = cow_co_write,
    .bdrv_co_get_block_status   = cow_co_get_block_status,

-    .create_opts    = &cow_create_opts,
+    .create_options = cow_create_options,
 };

 static void bdrv_cow_init(void)
@@ -23,7 +23,6 @@
 */
 #include "qemu-common.h"
 #include "block/block_int.h"
-#include "qapi/qmp/qbool.h"
 #include <curl/curl.h>

 // #define DEBUG
@@ -38,21 +37,6 @@
 #if LIBCURL_VERSION_NUM >= 0x071000
 /* The multi interface timer callback was introduced in 7.16.0 */
 #define NEED_CURL_TIMER_CALLBACK
-#define HAVE_SOCKET_ACTION
-#endif
-
-#ifndef HAVE_SOCKET_ACTION
-/* If curl_multi_socket_action isn't available, define it statically here in
- * terms of curl_multi_socket. Note that ev_bitmask will be ignored, which is
- * less efficient but still safe. */
-static CURLMcode __curl_multi_socket_action(CURLM *multi_handle,
-                                            curl_socket_t sockfd,
-                                            int ev_bitmask,
-                                            int *running_handles)
-{
-    return curl_multi_socket(multi_handle, sockfd, running_handles);
-}
-#define curl_multi_socket_action __curl_multi_socket_action
 #endif

 #define PROTOCOLS (CURLPROTO_HTTP | CURLPROTO_HTTPS | \
@@ -62,16 +46,12 @@ static CURLMcode __curl_multi_socket_action(CURLM *multi_handle,
 #define CURL_NUM_STATES 8
 #define CURL_NUM_ACB    8
 #define SECTOR_SIZE     512
-#define READ_AHEAD_DEFAULT (256 * 1024)
+#define READ_AHEAD_SIZE (256 * 1024)

 #define FIND_RET_NONE   0
 #define FIND_RET_OK     1
 #define FIND_RET_WAIT   2

-#define CURL_BLOCK_OPT_URL       "url"
-#define CURL_BLOCK_OPT_READAHEAD "readahead"
-#define CURL_BLOCK_OPT_SSLVERIFY "sslverify"
-
 struct BDRVCURLState;

 typedef struct CURLAIOCB {
@@ -91,7 +71,6 @@ typedef struct CURLState
    struct BDRVCURLState *s;
    CURLAIOCB *acb[CURL_NUM_ACB];
    CURL *curl;
-    curl_socket_t sock_fd;
    char *orig_buf;
    size_t buf_start;
    size_t buf_off;
@@ -108,14 +87,11 @@ typedef struct BDRVCURLState {
    CURLState states[CURL_NUM_STATES];
    char *url;
    size_t readahead_size;
-    bool sslverify;
    bool accept_range;
-    AioContext *aio_context;
 } BDRVCURLState;

 static void curl_clean_state(CURLState *s);
 static void curl_multi_do(void *arg);
-static void curl_multi_read(void *arg);

 #ifdef NEED_CURL_TIMER_CALLBACK
 static int curl_timer_cb(CURLM *multi, long timeout_ms, void *opaque)
@@ -135,29 +111,21 @@ static int curl_timer_cb(CURLM *multi, long timeout_ms, void *opaque)
 #endif

 static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
-                        void *userp, void *sp)
+                        void *s, void *sp)
 {
-    BDRVCURLState *s;
-    CURLState *state = NULL;
-    curl_easy_getinfo(curl, CURLINFO_PRIVATE, (char **)&state);
-    state->sock_fd = fd;
-    s = state->s;
-
    DPRINTF("CURL (AIO): Sock action %d on fd %d\n", action, fd);
    switch (action) {
        case CURL_POLL_IN:
-            aio_set_fd_handler(s->aio_context, fd, curl_multi_read,
-                               NULL, state);
+            qemu_aio_set_fd_handler(fd, curl_multi_do, NULL, s);
            break;
        case CURL_POLL_OUT:
-            aio_set_fd_handler(s->aio_context, fd, NULL, curl_multi_do, state);
+            qemu_aio_set_fd_handler(fd, NULL, curl_multi_do, s);
            break;
        case CURL_POLL_INOUT:
-            aio_set_fd_handler(s->aio_context, fd, curl_multi_read,
-                               curl_multi_do, state);
+            qemu_aio_set_fd_handler(fd, curl_multi_do, curl_multi_do, s);
            break;
        case CURL_POLL_REMOVE:
-            aio_set_fd_handler(s->aio_context, fd, NULL, NULL, NULL);
+            qemu_aio_set_fd_handler(fd, NULL, NULL, NULL);
            break;
    }

@@ -187,7 +155,7 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
    DPRINTF("CURL: Just reading %zd bytes\n", realsize);

    if (!s || !s->orig_buf)
-        return 0;
+        goto read_end;

    if (s->buf_off >= s->buf_len) {
        /* buffer full, read nothing */
@@ -212,6 +180,7 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
        }
    }

+read_end:
    return realsize;
 }

@@ -246,8 +215,7 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
        }

        // Wait for unfinished chunks
-        if (state->in_use &&
-            (start >= state->buf_start) &&
+        if ((start >= state->buf_start) &&
            (start <= buf_fend) &&
            (end >= state->buf_start) &&
            (end <= buf_fend))
@@ -269,69 +237,68 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
    return FIND_RET_NONE;
 }

-static void curl_multi_check_completion(BDRVCURLState *s)
+static void curl_multi_read(BDRVCURLState *s)
 {
    int msgs_in_queue;

    /* Try to find done transfers, so we can free the easy
     * handle again. */
-    for (;;) {
+    do {
        CURLMsg *msg;
        msg = curl_multi_info_read(s->multi, &msgs_in_queue);

-        /* Quit when there are no more completions */
        if (!msg)
            break;
-
-        if (msg->msg == CURLMSG_DONE) {
-            CURLState *state = NULL;
-            curl_easy_getinfo(msg->easy_handle, CURLINFO_PRIVATE,
-                              (char **)&state);
-
-            /* ACBs for successful messages get completed in curl_read_cb */
-            if (msg->data.result != CURLE_OK) {
-                int i;
-                for (i = 0; i < CURL_NUM_ACB; i++) {
-                    CURLAIOCB *acb = state->acb[i];
-
-                    if (acb == NULL) {
-                        continue;
-                    }
-
-                    acb->common.cb(acb->common.opaque, -EIO);
-                    qemu_aio_release(acb);
-                    state->acb[i] = NULL;
-                }
-            }
-
-            curl_clean_state(state);
+        if (msg->msg == CURLMSG_NONE)
            break;
+
+        switch (msg->msg) {
+            case CURLMSG_DONE:
+            {
+                CURLState *state = NULL;
+                curl_easy_getinfo(msg->easy_handle, CURLINFO_PRIVATE, (char**)&state);
+
+                /* ACBs for successful messages get completed in curl_read_cb */
+                if (msg->data.result != CURLE_OK) {
+                    int i;
+                    for (i = 0; i < CURL_NUM_ACB; i++) {
+                        CURLAIOCB *acb = state->acb[i];
+
+                        if (acb == NULL) {
+                            continue;
+                        }
+
+                        acb->common.cb(acb->common.opaque, -EIO);
+                        qemu_aio_release(acb);
+                        state->acb[i] = NULL;
+                    }
+                }
+
+                curl_clean_state(state);
+                break;
+            }
+            default:
+                msgs_in_queue = 0;
+                break;
        }
-    }
+    } while(msgs_in_queue);
 }

 static void curl_multi_do(void *arg)
 {
-    CURLState *s = (CURLState *)arg;
+    BDRVCURLState *s = (BDRVCURLState *)arg;
    int running;
    int r;

-    if (!s->s->multi) {
+    if (!s->multi) {
        return;
    }

    do {
-        r = curl_multi_socket_action(s->s->multi, s->sock_fd, 0, &running);
+        r = curl_multi_socket_all(s->multi, &running);
    } while(r == CURLM_CALL_MULTI_PERFORM);

-}
-
-static void curl_multi_read(void *arg)
-{
-    CURLState *s = (CURLState *)arg;
-
-    curl_multi_do(arg);
-    curl_multi_check_completion(s->s);
+    curl_multi_read(s);
 }

 static void curl_multi_timeout_do(void *arg)
@@ -346,7 +313,7 @@ static void curl_multi_timeout_do(void *arg)

    curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);

-    curl_multi_check_completion(s);
+    curl_multi_read(s);
 #else
    abort();
 #endif
@@ -370,44 +337,44 @@ static CURLState *curl_init_state(BDRVCURLState *s)
            break;
        }
        if (!state) {
-            aio_poll(state->s->aio_context, true);
+            g_usleep(100);
+            curl_multi_do(s);
        }
    } while(!state);

-    if (!state->curl) {
-        state->curl = curl_easy_init();
-        if (!state->curl) {
-            return NULL;
-        }
-        curl_easy_setopt(state->curl, CURLOPT_URL, s->url);
-        curl_easy_setopt(state->curl, CURLOPT_SSL_VERIFYPEER,
-                         (long) s->sslverify);
-        curl_easy_setopt(state->curl, CURLOPT_TIMEOUT, 5);
-        curl_easy_setopt(state->curl, CURLOPT_WRITEFUNCTION,
-                         (void *)curl_read_cb);
-        curl_easy_setopt(state->curl, CURLOPT_WRITEDATA, (void *)state);
-        curl_easy_setopt(state->curl, CURLOPT_PRIVATE, (void *)state);
-        curl_easy_setopt(state->curl, CURLOPT_AUTOREFERER, 1);
-        curl_easy_setopt(state->curl, CURLOPT_FOLLOWLOCATION, 1);
-        curl_easy_setopt(state->curl, CURLOPT_NOSIGNAL, 1);
-        curl_easy_setopt(state->curl, CURLOPT_ERRORBUFFER, state->errmsg);
-        curl_easy_setopt(state->curl, CURLOPT_FAILONERROR, 1);
+    if (state->curl)
+        goto has_curl;

-        /* Restrict supported protocols to avoid security issues in the more
-         * obscure protocols.  For example, do not allow POP3/SMTP/IMAP see
-         * CVE-2013-0249.
-         *
-         * Restricting protocols is only supported from 7.19.4 upwards.
-         */
+    state->curl = curl_easy_init();
+    if (!state->curl)
+        return NULL;
+    curl_easy_setopt(state->curl, CURLOPT_URL, s->url);
+    curl_easy_setopt(state->curl, CURLOPT_TIMEOUT, 5);
+    curl_easy_setopt(state->curl, CURLOPT_WRITEFUNCTION, (void *)curl_read_cb);
+    curl_easy_setopt(state->curl, CURLOPT_WRITEDATA, (void *)state);
+    curl_easy_setopt(state->curl, CURLOPT_PRIVATE, (void *)state);
+    curl_easy_setopt(state->curl, CURLOPT_AUTOREFERER, 1);
+    curl_easy_setopt(state->curl, CURLOPT_FOLLOWLOCATION, 1);
+    curl_easy_setopt(state->curl, CURLOPT_NOSIGNAL, 1);
+    curl_easy_setopt(state->curl, CURLOPT_ERRORBUFFER, state->errmsg);
+    curl_easy_setopt(state->curl, CURLOPT_FAILONERROR, 1);
+
+    /* Restrict supported protocols to avoid security issues in the more
+     * obscure protocols.  For example, do not allow POP3/SMTP/IMAP see
+     * CVE-2013-0249.
+     *
+     * Restricting protocols is only supported from 7.19.4 upwards.
+     */
 #if LIBCURL_VERSION_NUM >= 0x071304
-        curl_easy_setopt(state->curl, CURLOPT_PROTOCOLS, PROTOCOLS);
-        curl_easy_setopt(state->curl, CURLOPT_REDIR_PROTOCOLS, PROTOCOLS);
+    curl_easy_setopt(state->curl, CURLOPT_PROTOCOLS, PROTOCOLS);
+    curl_easy_setopt(state->curl, CURLOPT_REDIR_PROTOCOLS, PROTOCOLS);
 #endif

 #ifdef DEBUG_VERBOSE
-        curl_easy_setopt(state->curl, CURLOPT_VERBOSE, 1);
+    curl_easy_setopt(state->curl, CURLOPT_VERBOSE, 1);
 #endif
-    }
+
+has_curl:

    state->s = s;

@@ -424,50 +391,43 @@ static void curl_clean_state(CURLState *s)
 static void curl_parse_filename(const char *filename, QDict *options,
                                Error **errp)
 {
-    qdict_put(options, CURL_BLOCK_OPT_URL, qstring_from_str(filename));
-}

-static void curl_detach_aio_context(BlockDriverState *bs)
-{
-    BDRVCURLState *s = bs->opaque;
-    int i;
+    #define RA_OPTSTR ":readahead="
+    char *file;
+    char *ra;
+    const char *ra_val;
+    int parse_state = 0;

-    for (i = 0; i < CURL_NUM_STATES; i++) {
-        if (s->states[i].in_use) {
-            curl_clean_state(&s->states[i]);
+    file = g_strdup(filename);
+
+    /* Parse a trailing ":readahead=#:" param, if present. */
+    ra = file + strlen(file) - 1;
+    while (ra >= file) {
+        if (parse_state == 0) {
+            if (*ra == ':') {
+                parse_state++;
+            } else {
+                break;
+            }
+        } else if (parse_state == 1) {
+            if (*ra > '9' || *ra < '0') {
+                char *opt_start = ra - strlen(RA_OPTSTR) + 1;
+                if (opt_start > file &&
+                    strncmp(opt_start, RA_OPTSTR, strlen(RA_OPTSTR)) == 0) {
+                    ra_val = ra + 1;
+                    ra -= strlen(RA_OPTSTR) - 1;
+                    *ra = '\0';
+                    qdict_put(options, "readahead", qstring_from_str(ra_val));
+                }
+                break;
+            }
        }
-        if (s->states[i].curl) {
-            curl_easy_cleanup(s->states[i].curl);
-            s->states[i].curl = NULL;
-        }
-        g_free(s->states[i].orig_buf);
-        s->states[i].orig_buf = NULL;
-    }
-    if (s->multi) {
-        curl_multi_cleanup(s->multi);
-        s->multi = NULL;
+        ra--;
    }

-    timer_del(&s->timer);
-}
+    qdict_put(options, "url", qstring_from_str(file));

-static void curl_attach_aio_context(BlockDriverState *bs,
-                                    AioContext *new_context)
-{
-    BDRVCURLState *s = bs->opaque;
-
-    aio_timer_init(new_context, &s->timer,
-                   QEMU_CLOCK_REALTIME, SCALE_NS,
-                   curl_multi_timeout_do, s);
-
-    assert(!s->multi);
-    s->multi = curl_multi_init();
-    s->aio_context = new_context;
-    curl_multi_setopt(s->multi, CURLMOPT_SOCKETFUNCTION, curl_sock_cb);
-#ifdef NEED_CURL_TIMER_CALLBACK
-    curl_multi_setopt(s->multi, CURLMOPT_TIMERDATA, s);
-    curl_multi_setopt(s->multi, CURLMOPT_TIMERFUNCTION, curl_timer_cb);
-#endif
+    g_free(file);
 }

 static QemuOptsList runtime_opts = {
@@ -475,20 +435,15 @@ static QemuOptsList runtime_opts = {
    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
    .desc = {
        {
-            .name = CURL_BLOCK_OPT_URL,
+            .name = "url",
            .type = QEMU_OPT_STRING,
            .help = "URL to open",
        },
        {
-            .name = CURL_BLOCK_OPT_READAHEAD,
+            .name = "readahead",
            .type = QEMU_OPT_SIZE,
            .help = "Readahead size",
        },
-        {
-            .name = CURL_BLOCK_OPT_SSLVERIFY,
-            .type = QEMU_OPT_BOOL,
-            .help = "Verify SSL certificate"
-        },
        { /* end of list */ }
    },
 };
@@ -506,30 +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, CURL_BLOCK_OPT_READAHEAD,
-                                          READ_AHEAD_DEFAULT);
+    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;
    }

-    s->sslverify = qemu_opt_get_bool(opts, CURL_BLOCK_OPT_SSLVERIFY, true);
-
-    file = qemu_opt_get(opts, CURL_BLOCK_OPT_URL);
+    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;
    }

@@ -539,7 +494,6 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
    }

    DPRINTF("CURL: Opening %s\n", file);
-    s->aio_context = bdrv_get_aio_context(bs);
    s->url = g_strdup(file);
    state = curl_init_state(s);
    if (!state)
@@ -572,13 +526,27 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
    curl_easy_cleanup(state->curl);
    state->curl = NULL;

-    curl_attach_aio_context(bs, bdrv_get_aio_context(bs));
+    aio_timer_init(bdrv_get_aio_context(bs), &s->timer,
+                   QEMU_CLOCK_REALTIME, SCALE_NS,
+                   curl_multi_timeout_do, s);
+
+    // Now we know the file exists and its size, so let's
+    // initialize the multi interface!
+
+    s->multi = curl_multi_init();
+    curl_multi_setopt(s->multi, CURLMOPT_SOCKETDATA, s);
+    curl_multi_setopt(s->multi, CURLMOPT_SOCKETFUNCTION, curl_sock_cb);
+#ifdef NEED_CURL_TIMER_CALLBACK
+    curl_multi_setopt(s->multi, CURLMOPT_TIMERDATA, s);
+    curl_multi_setopt(s->multi, CURLMOPT_TIMERFUNCTION, curl_timer_cb);
+#endif
+    curl_multi_do(s);

    qemu_opts_del(opts);
    return 0;

 out:
-    error_setg(errp, "CURL: Error opening file: %s", state->errmsg);
+    fprintf(stderr, "CURL: Error opening file: %s\n", state->errmsg);
    curl_easy_cleanup(state->curl);
    state->curl = NULL;
 out_noclean:
@@ -601,7 +569,6 @@ static const AIOCBInfo curl_aiocb_info = {
 static void curl_readv_bh_cb(void *p)
 {
    CURLState *state;
-    int running;

    CURLAIOCB *acb = p;
    BDRVCURLState *s = acb->common.bs->opaque;
@@ -636,7 +603,8 @@ static void curl_readv_bh_cb(void *p)
    acb->end = (acb->nb_sectors * SECTOR_SIZE);

    state->buf_off = 0;
-    g_free(state->orig_buf);
+    if (state->orig_buf)
+        g_free(state->orig_buf);
    state->buf_start = start;
    state->buf_len = acb->end + s->readahead_size;
    end = MIN(start + state->buf_len, s->len) - 1;
@@ -649,9 +617,8 @@ static void curl_readv_bh_cb(void *p)
    curl_easy_setopt(state->curl, CURLOPT_RANGE, state->range);

    curl_multi_add_handle(s->multi, state->curl);
+    curl_multi_do(s);

-    /* Tell curl it needs to kick things off */
-    curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
 }

 static BlockDriverAIOCB *curl_aio_readv(BlockDriverState *bs,
@@ -666,7 +633,7 @@ static BlockDriverAIOCB *curl_aio_readv(BlockDriverState *bs,
    acb->sector_num = sector_num;
    acb->nb_sectors = nb_sectors;

-    acb->bh = aio_bh_new(bdrv_get_aio_context(bs), curl_readv_bh_cb, acb);
+    acb->bh = qemu_bh_new(curl_readv_bh_cb, acb);
    qemu_bh_schedule(acb->bh);
    return &acb->common;
 }
@@ -674,9 +641,25 @@ static BlockDriverAIOCB *curl_aio_readv(BlockDriverState *bs,
 static void curl_close(BlockDriverState *bs)
 {
    BDRVCURLState *s = bs->opaque;
+    int i;

    DPRINTF("CURL: Close\n");
-    curl_detach_aio_context(bs);
+    for (i=0; i<CURL_NUM_STATES; i++) {
+        if (s->states[i].in_use)
+            curl_clean_state(&s->states[i]);
+        if (s->states[i].curl) {
+            curl_easy_cleanup(s->states[i].curl);
+            s->states[i].curl = NULL;
+        }
+        if (s->states[i].orig_buf) {
+            g_free(s->states[i].orig_buf);
+            s->states[i].orig_buf = NULL;
+        }
+    }
+    if (s->multi)
+        curl_multi_cleanup(s->multi);
+
+    timer_del(&s->timer);

    g_free(s->url);
 }
@@ -688,83 +671,68 @@ static int64_t curl_getlength(BlockDriverState *bs)
 }

 static BlockDriver bdrv_http = {
-    .format_name                = "http",
-    .protocol_name              = "http",
+    .format_name            = "http",
+    .protocol_name          = "http",

-    .instance_size              = sizeof(BDRVCURLState),
-    .bdrv_parse_filename        = curl_parse_filename,
-    .bdrv_file_open             = curl_open,
-    .bdrv_close                 = curl_close,
-    .bdrv_getlength             = curl_getlength,
+    .instance_size          = sizeof(BDRVCURLState),
+    .bdrv_parse_filename    = curl_parse_filename,
+    .bdrv_file_open         = curl_open,
+    .bdrv_close             = curl_close,
+    .bdrv_getlength         = curl_getlength,

-    .bdrv_aio_readv             = curl_aio_readv,
-
-    .bdrv_detach_aio_context    = curl_detach_aio_context,
-    .bdrv_attach_aio_context    = curl_attach_aio_context,
+    .bdrv_aio_readv         = curl_aio_readv,
 };

 static BlockDriver bdrv_https = {
-    .format_name                = "https",
-    .protocol_name              = "https",
+    .format_name            = "https",
+    .protocol_name          = "https",

-    .instance_size              = sizeof(BDRVCURLState),
-    .bdrv_parse_filename        = curl_parse_filename,
-    .bdrv_file_open             = curl_open,
-    .bdrv_close                 = curl_close,
-    .bdrv_getlength             = curl_getlength,
+    .instance_size          = sizeof(BDRVCURLState),
+    .bdrv_parse_filename    = curl_parse_filename,
+    .bdrv_file_open         = curl_open,
+    .bdrv_close             = curl_close,
+    .bdrv_getlength         = curl_getlength,

-    .bdrv_aio_readv             = curl_aio_readv,
-
-    .bdrv_detach_aio_context    = curl_detach_aio_context,
-    .bdrv_attach_aio_context    = curl_attach_aio_context,
+    .bdrv_aio_readv         = curl_aio_readv,
 };

 static BlockDriver bdrv_ftp = {
-    .format_name                = "ftp",
-    .protocol_name              = "ftp",
+    .format_name            = "ftp",
+    .protocol_name          = "ftp",

-    .instance_size              = sizeof(BDRVCURLState),
-    .bdrv_parse_filename        = curl_parse_filename,
-    .bdrv_file_open             = curl_open,
-    .bdrv_close                 = curl_close,
-    .bdrv_getlength             = curl_getlength,
+    .instance_size          = sizeof(BDRVCURLState),
+    .bdrv_parse_filename    = curl_parse_filename,
+    .bdrv_file_open         = curl_open,
+    .bdrv_close             = curl_close,
+    .bdrv_getlength         = curl_getlength,

-    .bdrv_aio_readv             = curl_aio_readv,
-
-    .bdrv_detach_aio_context    = curl_detach_aio_context,
-    .bdrv_attach_aio_context    = curl_attach_aio_context,
+    .bdrv_aio_readv         = curl_aio_readv,
 };

 static BlockDriver bdrv_ftps = {
-    .format_name                = "ftps",
-    .protocol_name              = "ftps",
+    .format_name            = "ftps",
+    .protocol_name          = "ftps",

-    .instance_size              = sizeof(BDRVCURLState),
-    .bdrv_parse_filename        = curl_parse_filename,
-    .bdrv_file_open             = curl_open,
-    .bdrv_close                 = curl_close,
-    .bdrv_getlength             = curl_getlength,
+    .instance_size          = sizeof(BDRVCURLState),
+    .bdrv_parse_filename    = curl_parse_filename,
+    .bdrv_file_open         = curl_open,
+    .bdrv_close             = curl_close,
+    .bdrv_getlength         = curl_getlength,

-    .bdrv_aio_readv             = curl_aio_readv,
-
-    .bdrv_detach_aio_context    = curl_detach_aio_context,
-    .bdrv_attach_aio_context    = curl_attach_aio_context,
+    .bdrv_aio_readv         = curl_aio_readv,
 };

 static BlockDriver bdrv_tftp = {
-    .format_name                = "tftp",
-    .protocol_name              = "tftp",
+    .format_name            = "tftp",
+    .protocol_name          = "tftp",

-    .instance_size              = sizeof(BDRVCURLState),
-    .bdrv_parse_filename        = curl_parse_filename,
-    .bdrv_file_open             = curl_open,
-    .bdrv_close                 = curl_close,
-    .bdrv_getlength             = curl_getlength,
+    .instance_size          = sizeof(BDRVCURLState),
+    .bdrv_parse_filename    = curl_parse_filename,
+    .bdrv_file_open         = curl_open,
+    .bdrv_close             = curl_close,
+    .bdrv_getlength         = curl_getlength,

-    .bdrv_aio_readv             = curl_aio_readv,
-
-    .bdrv_detach_aio_context    = curl_detach_aio_context,
-    .bdrv_attach_aio_context    = curl_attach_aio_context,
+    .bdrv_aio_readv         = curl_aio_readv,
 };

 static void curl_block_init(void)
@@ -248,8 +248,8 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
                offset += 8;

                if (s->sectorcounts[i] > DMG_SECTORCOUNTS_MAX) {
-                    error_report("sector count %" PRIu64 " for chunk %" PRIu32
-                                 " is larger than max (%u)",
+                    error_report("sector count %" PRIu64 " for chunk %u is "
+                                 "larger than max (%u)",
                                 s->sectorcounts[i], i, DMG_SECTORCOUNTS_MAX);
                    ret = -EINVAL;
                    goto fail;
@@ -269,8 +269,8 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
                offset += 8;

                if (s->lengths[i] > DMG_LENGTHS_MAX) {
-                    error_report("length %" PRIu64 " for chunk %" PRIu32
-                                 " is larger than max (%u)",
+                    error_report("length %" PRIu64 " for chunk %u is larger "
+                                 "than max (%u)",
                                 s->lengths[i], i, DMG_LENGTHS_MAX);
                    ret = -EINVAL;
                    goto fail;
@@ -3,27 +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;
-    AioContext *aio_context;
 } 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;
@@ -34,13 +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)
@@ -81,7 +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.
 *
@@ -118,7 +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");
@@ -154,7 +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;
    }

@@ -166,8 +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;
@@ -175,8 +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;
    }
@@ -203,16 +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);
-
-        /* glfs_init sometimes doesn't set errno although docs suggest that */
-        if (errno == 0)
-            errno = EINVAL;
-
+        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;
@@ -226,32 +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 = aio_bh_new(acb->aio_context, 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 */
@@ -268,57 +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);
@@ -334,181 +356,26 @@ 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();
-    acb->aio_context = bdrv_get_aio_context(bs);
-
-    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,
-                               QemuOpts *opts, Error **errp)
+        QEMUOptionParameter *options, Error **errp)
 {
    struct glfs *glfs;
    struct glfs_fd *fd;
    int ret = 0;
-    int prealloc = 0;
    int64_t total_size = 0;
-    char *tmp = NULL;
    GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));

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

-    total_size =
-        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / BDRV_SECTOR_SIZE;
-
-    tmp = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
-    if (!tmp || !strcmp(tmp, "off")) {
-        prealloc = 0;
-    } else if (!strcmp(tmp, "full") &&
-               gluster_supports_zerofill()) {
-        prealloc = 1;
-    } else {
-        error_setg(errp, "Invalid preallocation mode: '%s'"
-            " or GlusterFS doesn't support zerofill API",
-            tmp);
-        ret = -EINVAL;
-        goto out;
+    while (options && options->name) {
+        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+            total_size = options->value.n / BDRV_SECTOR_SIZE;
+        }
+        options++;
    }

    fd = glfs_creat(glfs, gconf->image,
@@ -516,21 +383,14 @@ 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;
        }
    }
 out:
-    g_free(tmp);
    qemu_gluster_gconf_free(gconf);
    if (glfs) {
        glfs_fini(glfs);
@@ -538,19 +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->aio_context = bdrv_get_aio_context(bs);
+    acb->finished = NULL;

    if (write) {
        ret = glfs_pwritev_async(s->fd, qiov->iov, qiov->niov, offset, 0,
@@ -561,16 +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)
@@ -586,70 +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->aio_context = bdrv_get_aio_context(bs);
+    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->aio_context = bdrv_get_aio_context(bs);
+    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

@@ -684,6 +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;
@@ -697,22 +598,13 @@ static int qemu_gluster_has_zero_init(BlockDriverState *bs)
    return 0;
 }

-static QemuOptsList qemu_gluster_create_opts = {
-    .name = "qemu-gluster-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(qemu_gluster_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        {
-            .name = BLOCK_OPT_PREALLOC,
-            .type = QEMU_OPT_STRING,
-            .help = "Preallocation mode (allowed values: off, full)"
-        },
-        { /* end of list */ }
-    }
+static QEMUOptionParameter qemu_gluster_create_options[] = {
+    {
+        .name = BLOCK_OPT_SIZE,
+        .type = OPT_SIZE,
+        .help = "Virtual disk size"
+    },
+    { NULL }
 };

 static BlockDriver bdrv_gluster = {
@@ -721,25 +613,19 @@ 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,
+    .bdrv_aio_discard             = qemu_gluster_aio_discard,
 #endif
-#ifdef CONFIG_GLUSTERFS_ZEROFILL
-    .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
-#endif
-    .create_opts                  = &qemu_gluster_create_opts,
+    .create_options               = qemu_gluster_create_options,
 };

 static BlockDriver bdrv_gluster_tcp = {
@@ -748,25 +634,19 @@ 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,
+    .bdrv_aio_discard             = qemu_gluster_aio_discard,
 #endif
-#ifdef CONFIG_GLUSTERFS_ZEROFILL
-    .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
-#endif
-    .create_opts                  = &qemu_gluster_create_opts,
+    .create_options               = qemu_gluster_create_options,
 };

 static BlockDriver bdrv_gluster_unix = {
@@ -775,25 +655,19 @@ 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,
+    .bdrv_aio_discard             = qemu_gluster_aio_discard,
 #endif
-#ifdef CONFIG_GLUSTERFS_ZEROFILL
-    .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
-#endif
-    .create_opts                  = &qemu_gluster_create_opts,
+    .create_options               = qemu_gluster_create_options,
 };

 static BlockDriver bdrv_gluster_rdma = {
@@ -802,25 +676,19 @@ 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,
+    .bdrv_aio_discard             = qemu_gluster_aio_discard,
 #endif
-#ifdef CONFIG_GLUSTERFS_ZEROFILL
-    .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
-#endif
-    .create_opts                  = &qemu_gluster_create_opts,
+    .create_options               = qemu_gluster_create_options,
 };

 static void bdrv_gluster_init(void)
@@ -25,8 +25,6 @@
 */
 #define MAX_EVENTS 128

-#define MAX_QUEUED_IO  128
-
 struct qemu_laiocb {
    BlockDriverAIOCB common;
    struct qemu_laio_state *ctx;
@@ -38,19 +36,9 @@ struct qemu_laiocb {
    QLIST_ENTRY(qemu_laiocb) node;
 };

-typedef struct {
-    struct iocb *iocbs[MAX_QUEUED_IO];
-    int plugged;
-    unsigned int size;
-    unsigned int idx;
-} LaioQueue;
-
 struct qemu_laio_state {
    io_context_t ctx;
    EventNotifier e;
-
-    /* io queue for submit at batch */
-    LaioQueue io_q;
 };

 static inline ssize_t io_event_ret(struct io_event *ev)
@@ -147,79 +135,6 @@ static const AIOCBInfo laio_aiocb_info = {
    .cancel             = laio_cancel,
 };

-static void ioq_init(LaioQueue *io_q)
-{
-    io_q->size = MAX_QUEUED_IO;
-    io_q->idx = 0;
-    io_q->plugged = 0;
-}
-
-static int ioq_submit(struct qemu_laio_state *s)
-{
-    int ret, i = 0;
-    int len = s->io_q.idx;
-
-    do {
-        ret = io_submit(s->ctx, len, s->io_q.iocbs);
-    } while (i++ < 3 && ret == -EAGAIN);
-
-    /* empty io queue */
-    s->io_q.idx = 0;
-
-    if (ret < 0) {
-        i = 0;
-    } else {
-        i = ret;
-    }
-
-    for (; i < len; i++) {
-        struct qemu_laiocb *laiocb =
-            container_of(s->io_q.iocbs[i], struct qemu_laiocb, iocb);
-
-        laiocb->ret = (ret < 0) ? ret : -EIO;
-        qemu_laio_process_completion(s, laiocb);
-    }
-    return ret;
-}
-
-static void ioq_enqueue(struct qemu_laio_state *s, struct iocb *iocb)
-{
-    unsigned int idx = s->io_q.idx;
-
-    s->io_q.iocbs[idx++] = iocb;
-    s->io_q.idx = idx;
-
-    /* submit immediately if queue is full */
-    if (idx == s->io_q.size) {
-        ioq_submit(s);
-    }
-}
-
-void laio_io_plug(BlockDriverState *bs, void *aio_ctx)
-{
-    struct qemu_laio_state *s = aio_ctx;
-
-    s->io_q.plugged++;
-}
-
-int laio_io_unplug(BlockDriverState *bs, void *aio_ctx, bool unplug)
-{
-    struct qemu_laio_state *s = aio_ctx;
-    int ret = 0;
-
-    assert(s->io_q.plugged > 0 || !unplug);
-
-    if (unplug && --s->io_q.plugged > 0) {
-        return 0;
-    }
-
-    if (s->io_q.idx > 0) {
-        ret = ioq_submit(s);
-    }
-
-    return ret;
-}
-
 BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
        BlockDriverCompletionFunc *cb, void *opaque, int type)
@@ -253,13 +168,8 @@ BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
    }
    io_set_eventfd(&laiocb->iocb, event_notifier_get_fd(&s->e));

-    if (!s->io_q.plugged) {
-        if (io_submit(s->ctx, 1, &iocbs) < 0) {
-            goto out_free_aiocb;
-        }
-    } else {
-        ioq_enqueue(s, iocbs);
-    }
+    if (io_submit(s->ctx, 1, &iocbs) < 0)
+        goto out_free_aiocb;
    return &laiocb->common;

 out_free_aiocb:
@@ -267,20 +177,6 @@ out_free_aiocb:
    return NULL;
 }

-void laio_detach_aio_context(void *s_, AioContext *old_context)
-{
-    struct qemu_laio_state *s = s_;
-
-    aio_set_event_notifier(old_context, &s->e, NULL);
-}
-
-void laio_attach_aio_context(void *s_, AioContext *new_context)
-{
-    struct qemu_laio_state *s = s_;
-
-    aio_set_event_notifier(new_context, &s->e, qemu_laio_completion_cb);
-}
-
 void *laio_init(void)
 {
    struct qemu_laio_state *s;
@@ -294,7 +190,7 @@ void *laio_init(void)
        goto out_close_efd;
    }

-    ioq_init(&s->io_q);
+    qemu_aio_set_event_notifier(&s->e, qemu_laio_completion_cb);

    return s;

@@ -304,16 +200,3 @@ out_free_state:
    g_free(s);
    return NULL;
 }
-
-void laio_cleanup(void *s_)
-{
-    struct qemu_laio_state *s = s_;
-
-    event_notifier_cleanup(&s->e);
-
-    if (io_destroy(s->ctx) != 0) {
-        fprintf(stderr, "%s: destroy AIO context %p failed\n",
-                        __func__, &s->ctx);
-    }
-    g_free(s);
-}
@@ -31,14 +31,7 @@ typedef struct MirrorBlockJob {
    BlockJob common;
    RateLimit limit;
    BlockDriverState *target;
-    BlockDriverState *base;
-    /* The name of the graph node to replace */
-    char *replaces;
-    /* The BDS to replace */
-    BlockDriverState *to_replace;
-    /* Used to block operations on the drive-mirror-replace target */
-    Error *replace_blocker;
-    bool is_none_mode;
+    MirrorSyncMode mode;
    BlockdevOnError on_source_error, on_target_error;
    bool synced;
    bool should_complete;
@@ -46,7 +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;
@@ -102,7 +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
@@ -124,7 +115,7 @@ static void mirror_write_complete(void *opaque, int ret)

        bdrv_set_dirty(source, op->sector_num, op->nb_sectors);
        action = mirror_error_action(s, false, -ret);
-        if (action == BLOCK_ERROR_ACTION_REPORT && s->ret >= 0) {
+        if (action == BDRV_ACTION_REPORT && s->ret >= 0) {
            s->ret = ret;
        }
    }
@@ -141,7 +132,7 @@ static void mirror_read_complete(void *opaque, int ret)

        bdrv_set_dirty(source, op->sector_num, op->nb_sectors);
        action = mirror_error_action(s, true, -ret);
-        if (action == BLOCK_ERROR_ACTION_REPORT && s->ret >= 0) {
+        if (action == BDRV_ACTION_REPORT && s->ret >= 0) {
            s->ret = ret;
        }

@@ -162,10 +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);
    }

@@ -201,7 +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;
@@ -265,17 +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);
        }

@@ -332,21 +319,12 @@ 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_event_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 = DIV_ROUND_UP(s->common.len, s->granularity);
+    length = (bdrv_getlength(bs) + s->granularity - 1) / s->granularity;
    s->in_flight_bitmap = bitmap_new(length);

    /* If we have no backing file yet in the destination, we cannot let
@@ -356,10 +334,7 @@ static void coroutine_fn mirror_run(void *opaque)
    bdrv_get_backing_filename(s->target, backing_filename,
                              sizeof(backing_filename));
    if (backing_filename[0] && !s->target->backing_hd) {
-        ret = bdrv_get_info(s->target, &bdi);
-        if (ret < 0) {
-            goto immediate_exit;
-        }
+        bdrv_get_info(s->target, &bdi);
        if (s->granularity < bdi.cluster_size) {
            s->buf_size = MAX(s->buf_size, bdi.cluster_size);
            s->cow_bitmap = bitmap_new(length);
@@ -371,9 +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,
@@ -393,7 +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;
@@ -405,7 +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.
@@ -432,8 +408,7 @@ static void coroutine_fn mirror_run(void *opaque)
            trace_mirror_before_flush(s);
            ret = bdrv_flush(s->target);
            if (ret < 0) {
-                if (mirror_error_action(s, false, -ret) ==
-                    BLOCK_ERROR_ACTION_REPORT) {
+                if (mirror_error_action(s, false, -ret) == BDRV_ACTION_REPORT) {
                    goto immediate_exit;
                }
            } else {
@@ -444,13 +419,13 @@ static void coroutine_fn mirror_run(void *opaque)
                 */
                s->common.offset = end * BDRV_SECTOR_SIZE;
                if (!s->synced) {
-                    block_job_event_ready(&s->common);
+                    block_job_ready(&s->common);
                    s->synced = true;
                }

                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);
            }
        }

@@ -465,7 +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;
@@ -505,31 +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) {
-        BlockDriverState *to_replace = s->common.bs;
-        if (s->to_replace) {
-            to_replace = s->to_replace;
-        }
-        if (bdrv_get_flags(s->target) != bdrv_get_flags(to_replace)) {
-            bdrv_reopen(s->target, bdrv_get_flags(to_replace), NULL);
-        }
-        bdrv_swap(s->target, to_replace);
-        if (s->common.driver->job_type == BLOCK_JOB_TYPE_COMMIT) {
-            /* drop the bs loop chain formed by the swap: break the loop then
-             * trigger the unref from the top one */
-            BlockDriverState *p = s->base->backing_hd;
-            bdrv_set_backing_hd(s->base, NULL);
-            bdrv_unref(p);
+        if (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->to_replace) {
-        bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
-        error_free(s->replace_blocker);
-        bdrv_unref(s->to_replace);
-    }
-    g_free(s->replaces);
+    bdrv_close(s->target);
    bdrv_unref(s->target);
    block_job_completed(&s->common, ret);
 }
@@ -560,6 +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;
    }
@@ -568,20 +530,6 @@ static void mirror_complete(BlockJob *job, Error **errp)
        return;
    }

-    /* check the target bs is not blocked and block all operations on it */
-    if (s->replaces) {
-        s->to_replace = check_to_replace_node(s->replaces, &local_err);
-        if (!s->to_replace) {
-            error_propagate(errp, local_err);
-            return;
-        }
-
-        error_setg(&s->replace_blocker,
-                   "block device is in use by block-job-complete");
-        bdrv_op_block_all(s->to_replace, s->replace_blocker);
-        bdrv_ref(s->to_replace);
-    }
-
    s->should_complete = true;
    block_job_resume(job);
 }
@@ -594,25 +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,
-                             const char *replaces,
-                             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;

@@ -637,25 +572,19 @@ 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;
    }

-    s->replaces = g_strdup(replaces);
    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, errp);
-    if (!s->dirty_bitmap) {
-        return;
-    }
+    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);
@@ -663,82 +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,
-                  const char *replaces,
-                  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, replaces,
-                     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, NULL, speed, 0, 0,
-                     on_error, on_error, cb, opaque, &local_err,
-                     &commit_active_job_driver, false, base);
-    if (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;
-}
@@ -1,404 +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);
-
-    nbd_client_session_detach_aio_context(client);
-    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)
-{
-    AioContext *aio_context;
-    int rc, ret;
-
-    qemu_co_mutex_lock(&s->send_mutex);
-    s->send_coroutine = qemu_coroutine_self();
-    aio_context = bdrv_get_aio_context(s->bs);
-    aio_set_fd_handler(aio_context, s->sock,
-                       nbd_reply_ready, nbd_restart_write, s);
-    if (qiov) {
-        if (!s->is_unix) {
-            socket_set_cork(s->sock, 1);
-        }
-        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);
-    }
-    aio_set_fd_handler(aio_context, s->sock, nbd_reply_ready, NULL, s);
-    s->send_coroutine = NULL;
-    qemu_co_mutex_unlock(&s->send_mutex);
-    return rc;
-}
-
-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_detach_aio_context(NbdClientSession *client)
-{
-    aio_set_fd_handler(bdrv_get_aio_context(client->bs), client->sock,
-                       NULL, NULL, NULL);
-}
-
-void nbd_client_session_attach_aio_context(NbdClientSession *client,
-                                           AioContext *new_context)
-{
-    aio_set_fd_handler(new_context, client->sock,
-                       nbd_reply_ready, NULL, client);
-}
-
-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);
-    nbd_client_session_attach_aio_context(client, bdrv_get_aio_context(bs));
-
-    logout("Established connection with NBD server\n");
-    return 0;
-}
@@ -1,54 +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);
-
-void nbd_client_session_detach_aio_context(NbdClientSession *client);
-void nbd_client_session_attach_aio_context(NbdClientSession *client,
-                                           AioContext *new_context);
-
-#endif /* NBD_CLIENT_H */
@@ -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)
@@ -175,7 +204,7 @@ static void nbd_parse_filename(const char *filename, QDict *options,
        InetSocketAddress *addr = NULL;

        addr = inet_parse(host_spec, errp);
-        if (!addr) {
+        if (error_is_set(errp)) {
            goto out;
        }

@@ -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);
        }
@@ -242,148 +417,268 @@ 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;
-}
-
-static void nbd_detach_aio_context(BlockDriverState *bs)
-{
-    BDRVNBDState *s = bs->opaque;
-
-    nbd_client_session_detach_aio_context(&s->client);
-}
-
-static void nbd_attach_aio_context(BlockDriverState *bs,
-                                   AioContext *new_context)
-{
-    BDRVNBDState *s = bs->opaque;
-
-    nbd_client_session_attach_aio_context(&s->client, new_context);
+    return s->size;
 }

 static BlockDriver bdrv_nbd = {
-    .format_name                = "nbd",
-    .protocol_name              = "nbd",
-    .instance_size              = sizeof(BDRVNBDState),
-    .bdrv_parse_filename        = nbd_parse_filename,
-    .bdrv_file_open             = nbd_open,
-    .bdrv_co_readv              = nbd_co_readv,
-    .bdrv_co_writev             = nbd_co_writev,
-    .bdrv_close                 = nbd_close,
-    .bdrv_co_flush_to_os        = nbd_co_flush,
-    .bdrv_co_discard            = nbd_co_discard,
-    .bdrv_getlength             = nbd_getlength,
-    .bdrv_detach_aio_context    = nbd_detach_aio_context,
-    .bdrv_attach_aio_context    = nbd_attach_aio_context,
+    .format_name         = "nbd",
+    .protocol_name       = "nbd",
+    .instance_size       = sizeof(BDRVNBDState),
+    .bdrv_parse_filename = nbd_parse_filename,
+    .bdrv_file_open      = nbd_open,
+    .bdrv_co_readv       = nbd_co_readv,
+    .bdrv_co_writev      = nbd_co_writev,
+    .bdrv_close          = nbd_close,
+    .bdrv_co_flush_to_os = nbd_co_flush,
+    .bdrv_co_discard     = nbd_co_discard,
+    .bdrv_getlength      = nbd_getlength,
 };

 static BlockDriver bdrv_nbd_tcp = {
-    .format_name                = "nbd",
-    .protocol_name              = "nbd+tcp",
-    .instance_size              = sizeof(BDRVNBDState),
-    .bdrv_parse_filename        = nbd_parse_filename,
-    .bdrv_file_open             = nbd_open,
-    .bdrv_co_readv              = nbd_co_readv,
-    .bdrv_co_writev             = nbd_co_writev,
-    .bdrv_close                 = nbd_close,
-    .bdrv_co_flush_to_os        = nbd_co_flush,
-    .bdrv_co_discard            = nbd_co_discard,
-    .bdrv_getlength             = nbd_getlength,
-    .bdrv_detach_aio_context    = nbd_detach_aio_context,
-    .bdrv_attach_aio_context    = nbd_attach_aio_context,
+    .format_name         = "nbd",
+    .protocol_name       = "nbd+tcp",
+    .instance_size       = sizeof(BDRVNBDState),
+    .bdrv_parse_filename = nbd_parse_filename,
+    .bdrv_file_open      = nbd_open,
+    .bdrv_co_readv       = nbd_co_readv,
+    .bdrv_co_writev      = nbd_co_writev,
+    .bdrv_close          = nbd_close,
+    .bdrv_co_flush_to_os = nbd_co_flush,
+    .bdrv_co_discard     = nbd_co_discard,
+    .bdrv_getlength      = nbd_getlength,
 };

 static BlockDriver bdrv_nbd_unix = {
-    .format_name                = "nbd",
-    .protocol_name              = "nbd+unix",
-    .instance_size              = sizeof(BDRVNBDState),
-    .bdrv_parse_filename        = nbd_parse_filename,
-    .bdrv_file_open             = nbd_open,
-    .bdrv_co_readv              = nbd_co_readv,
-    .bdrv_co_writev             = nbd_co_writev,
-    .bdrv_close                 = nbd_close,
-    .bdrv_co_flush_to_os        = nbd_co_flush,
-    .bdrv_co_discard            = nbd_co_discard,
-    .bdrv_getlength             = nbd_getlength,
-    .bdrv_detach_aio_context    = nbd_detach_aio_context,
-    .bdrv_attach_aio_context    = nbd_attach_aio_context,
+    .format_name         = "nbd",
+    .protocol_name       = "nbd+unix",
+    .instance_size       = sizeof(BDRVNBDState),
+    .bdrv_parse_filename = nbd_parse_filename,
+    .bdrv_file_open      = nbd_open,
+    .bdrv_co_readv       = nbd_co_readv,
+    .bdrv_co_writev      = nbd_co_writev,
+    .bdrv_close          = nbd_close,
+    .bdrv_co_flush_to_os = nbd_co_flush,
+    .bdrv_co_discard     = nbd_co_discard,
+    .bdrv_getlength      = nbd_getlength,
 };

 static void bdrv_nbd_init(void)
@@ -1,500 +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;
-    AioContext *aio_context;
-} NFSClient;
-
-typedef struct NFSRPC {
-    int ret;
-    int complete;
-    QEMUIOVector *iov;
-    struct stat *st;
-    Coroutine *co;
-    QEMUBH *bh;
-    NFSClient *client;
-} 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) {
-        aio_set_fd_handler(client->aio_context,
-                           nfs_get_fd(client->context),
-                           (ev & POLLIN) ? nfs_process_read : NULL,
-                           (ev & POLLOUT) ? nfs_process_write : NULL,
-                           client);
-
-    }
-    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(),
-        .client         = client,
-    };
-}
-
-static void nfs_co_generic_bh_cb(void *opaque)
-{
-    NFSRPC *task = opaque;
-    task->complete = 1;
-    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->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 = aio_bh_new(task->client->aio_context,
-                              nfs_co_generic_bh_cb, task);
-        qemu_bh_schedule(task->bh);
-    } else {
-        task->complete = 1;
-    }
-}
-
-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_detach_aio_context(BlockDriverState *bs)
-{
-    NFSClient *client = bs->opaque;
-
-    aio_set_fd_handler(client->aio_context,
-                       nfs_get_fd(client->context),
-                       NULL, NULL, NULL);
-    client->events = 0;
-}
-
-static void nfs_attach_aio_context(BlockDriverState *bs,
-                                   AioContext *new_context)
-{
-    NFSClient *client = bs->opaque;
-
-    client->aio_context = new_context;
-    nfs_set_events(client);
-}
-
-static void nfs_client_close(NFSClient *client)
-{
-    if (client->context) {
-        if (client->fh) {
-            nfs_close(client->context, client->fh);
-        }
-        aio_set_fd_handler(client->aio_context,
-                           nfs_get_fd(client->context),
-                           NULL, NULL, NULL);
-        nfs_destroy_context(client->context);
-    }
-    memset(client, 0, sizeof(NFSClient));
-}
-
-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;
-    }
-    if (!uri->server) {
-        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++) {
-        unsigned long long val;
-        if (!qp->p[i].value) {
-            error_setg(errp, "Value for NFS parameter expected: %s",
-                       qp->p[i].name);
-            goto fail;
-        }
-        if (parse_uint_full(qp->p[i].value, &val, 0)) {
-            error_setg(errp, "Illegal value for NFS parameter: %s",
-                       qp->p[i].name);
-            goto fail;
-        }
-        if (!strcmp(qp->p[i].name, "uid")) {
-            nfs_set_uid(client->context, val);
-        } else if (!strcmp(qp->p[i].name, "gid")) {
-            nfs_set_gid(client->context, val);
-        } else if (!strcmp(qp->p[i].name, "tcp-syncnt")) {
-            nfs_set_tcp_syncnt(client->context, val);
-#ifdef LIBNFS_FEATURE_READAHEAD
-        } else if (!strcmp(qp->p[i].name, "readahead")) {
-            nfs_set_readahead(client->context, val);
-#endif
-        } 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;
-
-    client->aio_context = bdrv_get_aio_context(bs);
-
-    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (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 QemuOptsList nfs_create_opts = {
-    .name = "nfs-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(nfs_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        { /* end of list */ }
-    }
-};
-
-static int nfs_file_create(const char *url, QemuOpts *opts, Error **errp)
-{
-    int ret = 0;
-    int64_t total_size = 0;
-    NFSClient *client = g_malloc0(sizeof(NFSClient));
-
-    client->aio_context = qemu_get_aio_context();
-
-    /* Read out options */
-    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
-
-    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);
-        aio_poll(client->aio_context, true);
-    }
-
-    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,
-    .create_opts                    = &nfs_create_opts,
-
-    .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,
-
-    .bdrv_detach_aio_context        = nfs_detach_aio_context,
-    .bdrv_attach_aio_context        = nfs_attach_aio_context,
-};
-
-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;
    }

@@ -29,61 +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);
-    info->detect_zeroes = bs->detect_zeroes;
-
-    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
@@ -259,20 +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;
            }
@@ -293,7 +294,7 @@ void bdrv_query_info(BlockDriverState *bs,
    qapi_free_BlockInfo(info);
 }

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

@@ -320,11 +321,6 @@ static 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;
 }

@@ -337,7 +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;
        }
@@ -360,11 +356,7 @@ BlockStatsList *qmp_query_blockstats(Error **errp)

     while ((bs = bdrv_next(bs))) {
        BlockStatsList *info = g_malloc0(sizeof(*info));
-        AioContext *ctx = bdrv_get_aio_context(bs);
-
-        aio_context_acquire(ctx);
        info->value = bdrv_query_stats(bs);
-        aio_context_release(ctx);

        *p_next = info;
        p_next = &info->next;
@@ -538,11 +530,12 @@ static void dump_qdict(fprintf_function func_fprintf, void *f, int indentation,
 void bdrv_image_info_specific_dump(fprintf_function func_fprintf, void *f,
                                   ImageInfoSpecific *info_spec)
 {
+    Error *local_err = NULL;
    QmpOutputVisitor *ov = qmp_output_visitor_new();
    QObject *obj, *data;

    visit_type_ImageInfoSpecific(qmp_output_get_visitor(ov), &info_spec, NULL,
-                                 &error_abort);
+                                 &local_err);
    obj = qmp_output_get_qobject(ov);
    assert(qobject_type(obj) == QTYPE_QDICT);
    data = qdict_get(qobject_to_qdict(obj), "data");
@@ -115,16 +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 %" PRIu32,
-                 header.version);
-        error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
-                  bs->device_name, "qcow", version);
+        snprintf(version, sizeof(version), "QCOW version %d", header.version);
+        qerror_report(QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+            bs->device_name, "qcow", version);
        ret = -ENOTSUP;
        goto fail;
    }
@@ -149,7 +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;
    }
@@ -693,37 +690,43 @@ static void qcow_close(BlockDriverState *bs)
    error_free(s->migration_blocker);
 }

-static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
+static int qcow_create(const char *filename, QEMUOptionParameter *options,
+                       Error **errp)
 {
    int header_size, backing_filename_len, l1_size, shift, i;
    QCowHeader header;
    uint8_t *tmp;
    int64_t total_size = 0;
-    char *backing_file = NULL;
+    const char *backing_file = NULL;
    int flags = 0;
    Error *local_err = NULL;
    int ret;
    BlockDriverState *qcow_bs;

    /* Read out options */
-    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
-    backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
-    if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ENCRYPT, false)) {
-        flags |= BLOCK_FLAG_ENCRYPT;
+    while (options && options->name) {
+        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+            total_size = options->value.n / 512;
+        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
+            backing_file = options->value.s;
+        } else if (!strcmp(options->name, BLOCK_OPT_ENCRYPT)) {
+            flags |= options->value.n ? BLOCK_FLAG_ENCRYPT : 0;
+        }
+        options++;
    }

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

    ret = bdrv_truncate(qcow_bs, 0);
@@ -748,7 +751,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
            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 */
@@ -794,8 +797,6 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
    ret = 0;
 exit:
    bdrv_unref(qcow_bs);
-cleanup:
-    g_free(backing_file);
    return ret;
 }

@@ -908,28 +909,24 @@ static int qcow_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
    return 0;
 }

-static QemuOptsList qcow_create_opts = {
-    .name = "qcow-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(qcow_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        {
-            .name = BLOCK_OPT_BACKING_FILE,
-            .type = QEMU_OPT_STRING,
-            .help = "File name of a base image"
-        },
-        {
-            .name = BLOCK_OPT_ENCRYPT,
-            .type = QEMU_OPT_BOOL,
-            .help = "Encrypt the image",
-            .def_value_str = "off"
-        },
-        { /* end of list */ }
-    }
+
+static QEMUOptionParameter qcow_create_options[] = {
+    {
+        .name = BLOCK_OPT_SIZE,
+        .type = OPT_SIZE,
+        .help = "Virtual disk size"
+    },
+    {
+        .name = BLOCK_OPT_BACKING_FILE,
+        .type = OPT_STRING,
+        .help = "File name of a base image"
+    },
+    {
+        .name = BLOCK_OPT_ENCRYPT,
+        .type = OPT_FLAG,
+        .help = "Encrypt the image"
+    },
+    { NULL }
 };

 static BlockDriver bdrv_qcow = {
@@ -938,10 +935,9 @@ static BlockDriver bdrv_qcow = {
    .bdrv_probe		= qcow_probe,
    .bdrv_open		= qcow_open,
    .bdrv_close		= qcow_close,
-    .bdrv_reopen_prepare    = qcow_reopen_prepare,
-    .bdrv_create            = qcow_create,
+    .bdrv_reopen_prepare = qcow_reopen_prepare,
+    .bdrv_create	= qcow_create,
    .bdrv_has_zero_init     = bdrv_has_zero_init_1,
-    .supports_backing       = true,

    .bdrv_co_readv          = qcow_co_readv,
    .bdrv_co_writev         = qcow_co_writev,
@@ -952,7 +948,7 @@ static BlockDriver bdrv_qcow = {
    .bdrv_write_compressed  = qcow_write_compressed,
    .bdrv_get_info          = qcow_get_info,

-    .create_opts            = &qcow_create_opts,
+    .create_options = qcow_create_options,
 };

 static void bdrv_qcow_init(void)
@@ -42,13 +42,6 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
    if (min_size <= s->l1_size)
        return 0;

-    /* Do a sanity check on min_size before trying to calculate new_l1_size
-     * (this prevents overflows during the while loop for the calculation of
-     * new_l1_size) */
-    if (min_size > INT_MAX / sizeof(uint64_t)) {
-        return -EFBIG;
-    }
-
    if (exact_size) {
        new_l1_size = min_size;
    } else {
@@ -158,14 +151,12 @@ static int l2_load(BlockDriverState *bs, uint64_t l2_offset,
 int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index)
 {
    BDRVQcowState *s = bs->opaque;
-    uint64_t buf[L1_ENTRIES_PER_SECTOR] = { 0 };
+    uint64_t buf[L1_ENTRIES_PER_SECTOR];
    int l1_start_index;
    int i, ret;

    l1_start_index = l1_index & ~(L1_ENTRIES_PER_SECTOR - 1);
-    for (i = 0; i < L1_ENTRIES_PER_SECTOR && l1_start_index + i < s->l1_size;
-         i++)
-    {
+    for (i = 0; i < L1_ENTRIES_PER_SECTOR; i++) {
        buf[i] = cpu_to_be64(s->l1_table[l1_start_index + i]);
    }

@@ -380,11 +371,6 @@ static int coroutine_fn copy_sectors(BlockDriverState *bs,

    BLKDBG_EVENT(bs->file, BLKDBG_COW_READ);

-    if (!bs->drv) {
-        ret = -ENOMEDIUM;
-        goto out;
-    }
-
    /* 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.
@@ -501,7 +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,
@@ -1188,7 +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;
@@ -1196,13 +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 = (uint64_t)*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;
@@ -1288,7 +1275,7 @@ again:
        }
    }

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

@@ -1370,47 +1357,19 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
    nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);

    for (i = 0; i < nb_clusters; i++) {
-        uint64_t old_l2_entry;
+        uint64_t old_offset;

-        old_l2_entry = 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.
-         */
-        switch (qcow2_get_cluster_type(old_l2_entry)) {
-            case QCOW2_CLUSTER_UNALLOCATED:
-                if (!bs->backing_hd) {
-                    continue;
-                }
-                break;
-
-            case QCOW2_CLUSTER_ZERO:
-                continue;
-
-            case QCOW2_CLUSTER_NORMAL:
-            case QCOW2_CLUSTER_COMPRESSED:
-                break;
-
-            default:
-                abort();
+        old_offset = be64_to_cpu(l2_table[l2_index + i]);
+        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_l2_entry, 1, type);
+        qcow2_free_any_clusters(bs, old_offset, 1, type);
    }

    ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
@@ -1433,7 +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;
@@ -1645,7 +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,
@@ -27,7 +27,6 @@
 #include "block/qcow2.h"
 #include "qemu/range.h"
 #include "qapi/qmp/types.h"
-#include "qapi-event.h"

 static int64_t alloc_clusters_noref(BlockDriverState *bs, uint64_t size);
 static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
@@ -99,8 +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;

@@ -525,8 +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)
    {
@@ -654,15 +652,6 @@ retry:
            goto retry;
        }
    }
-
-    /* Make sure that all offsets in the "allocated" range are representable
-     * in an int64_t */
-    if (s->free_cluster_index > 0 &&
-        s->free_cluster_index - 1 > (INT64_MAX >> s->cluster_bits))
-    {
-        return -EFBIG;
-    }
-
 #ifdef DEBUG_ALLOC2
    fprintf(stderr, "alloc_clusters: size=%" PRId64 " -> %" PRId64 "\n",
            size,
@@ -750,7 +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;
@@ -758,7 +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 {
@@ -766,7 +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;
@@ -1035,8 +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;
@@ -1143,7 +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++;
@@ -1215,7 +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++;
@@ -1397,7 +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)
@@ -1413,14 +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
@@ -1431,7 +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 */
@@ -1439,37 +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;
 }

@@ -1490,11 +1477,6 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
    int ret;

    size = bdrv_getlength(bs->file);
-    if (size < 0) {
-        res->check_errors++;
-        return size;
-    }
-
    nb_clusters = size_to_clusters(s, size);
    if (nb_clusters > INT_MAX) {
        res->check_errors++;
@@ -1540,7 +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++;
@@ -1808,6 +1790,7 @@ int qcow2_pre_write_overlap_check(BlockDriverState *bs, int ign, int64_t offset,
    } else if (ret > 0) {
        int metadata_ol_bitnr = ffs(ret) - 1;
        char *message;
+        QObject *data;

        assert(metadata_ol_bitnr < QCOW2_OL_MAX_BITNR);

@@ -1816,14 +1799,12 @@ int qcow2_pre_write_overlap_check(BlockDriverState *bs, int ign, int64_t offset,
                metadata_ol_names[metadata_ol_bitnr]);
        message = g_strdup_printf("Prevented %s overwrite",
                metadata_ol_names[metadata_ol_bitnr]);
-        qapi_event_send_block_image_corrupted(bdrv_get_device_name(bs),
-                                              message,
-                                              true,
-                                              offset,
-                                              true,
-                                              size,
-                                              &error_abort);
+        data = qobject_from_jsonf("{ 'device': %s, 'msg': %s, 'offset': %"
+                PRId64 ", 'size': %" PRId64 " }", bs->device_name, message,
+                offset, size);
+        monitor_protocol_event(QEVENT_BLOCK_IMAGE_CORRUPTED, data);
        g_free(message);
+        qobject_decref(data);

        qcow2_mark_corrupt(bs);
        bs->drv = NULL; /* make BDS unusable */
@@ -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;
    }
@@ -31,7 +31,6 @@
 #include "qapi/qmp/qerror.h"
 #include "qapi/qmp/qbool.h"
 #include "trace.h"
-#include "qemu/option_int.h"

 /*
  Differences with QCOW:
@@ -114,7 +113,7 @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset,
 #ifdef DEBUG_EXT
        printf("ext.magic = 0x%x\n", ext.magic);
 #endif
-        if (offset > end_offset || ext.len > end_offset - offset) {
+        if (ext.len > end_offset - offset) {
            error_setg(errp, "Header extension too large");
            return -EINVAL;
        }
@@ -125,9 +124,8 @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset,

        case QCOW2_EXT_MAGIC_BACKING_FORMAT:
            if (ext.len >= sizeof(bs->backing_format)) {
-                error_setg(errp, "ERROR: ext_backing_format: len=%" PRIu32
-                           " too large (>=%zu)", ext.len,
-                           sizeof(bs->backing_format));
+                error_setg(errp, "ERROR: ext_backing_format: len=%u too large"
+                           " (>=%zu)", ext.len, sizeof(bs->backing_format));
                return 2;
            }
            ret = bdrv_pread(bs->file, offset, bs->backing_format, ext.len);
@@ -210,31 +208,20 @@ static void GCC_FMT_ATTR(3, 4) report_unsupported(BlockDriverState *bs,
 static void report_unsupported_feature(BlockDriverState *bs,
    Error **errp, Qcow2Feature *table, uint64_t mask)
 {
-    char *features = g_strdup("");
-    char *old;
-
    while (table && table->name[0] != '\0') {
        if (table->type == QCOW2_FEAT_TYPE_INCOMPATIBLE) {
-            if (mask & (1ULL << table->bit)) {
-                old = features;
-                features = g_strdup_printf("%s%s%.46s", old, *old ? ", " : "",
-                                           table->name);
-                g_free(old);
-                mask &= ~(1ULL << table->bit);
+            if (mask & (1 << table->bit)) {
+                report_unsupported(bs, errp, "%.46s", table->name);
+                mask &= ~(1 << table->bit);
            }
        }
        table++;
    }

    if (mask) {
-        old = features;
-        features = g_strdup_printf("%s%sUnknown incompatible feature: %" PRIx64,
-                                   old, *old ? ", " : "", mask);
-        g_free(old);
+        report_unsupported(bs, errp, "Unknown incompatible feature: %" PRIx64,
+                           mask);
    }
-
-    report_unsupported(bs, errp, "%s", features);
-    g_free(features);
 }

 /*
@@ -492,11 +479,11 @@ 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) {
-        report_unsupported(bs, errp, "QCOW version %" PRIu32, header.version);
+        report_unsupported(bs, errp, "QCOW version %d", header.version);
        ret = -ENOTSUP;
        goto fail;
    }
@@ -506,8 +493,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
    /* Initialise cluster size */
    if (header.cluster_bits < MIN_CLUSTER_BITS ||
        header.cluster_bits > MAX_CLUSTER_BITS) {
-        error_setg(errp, "Unsupported cluster size: 2^%" PRIu32,
-                   header.cluster_bits);
+        error_setg(errp, "Unsupported cluster size: 2^%i", header.cluster_bits);
        ret = -EINVAL;
        goto fail;
    }
@@ -580,7 +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;
    }

@@ -605,7 +590,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
    s->refcount_order = header.refcount_order;

    if (header.crypt_method > QCOW_CRYPT_AES) {
-        error_setg(errp, "Unsupported encryption method: %" PRIu32,
+        error_setg(errp, "Unsupported encryption method: %i",
                   header.crypt_method);
        ret = -EINVAL;
        goto fail;
@@ -757,7 +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) {
@@ -770,7 +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};

@@ -782,9 +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;
@@ -858,21 +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 void qcow2_refresh_limits(BlockDriverState *bs, Error **errp)
-{
-    BDRVQcowState *s = bs->opaque;
-
-    bs->bl.write_zeroes_alignment = s->cluster_sectors;
-}
-
 static int qcow2_set_key(BlockDriverState *bs, const char *key)
 {
    BDRVQcowState *s = bs->opaque;
@@ -1029,20 +1004,11 @@ static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
                n1 = qcow2_backing_read1(bs->backing_hd, &hd_qiov,
                    sector_num, cur_nr_sectors);
                if (n1 > 0) {
-                    QEMUIOVector local_qiov;
-
-                    qemu_iovec_init(&local_qiov, hd_qiov.niov);
-                    qemu_iovec_concat(&local_qiov, &hd_qiov, 0,
-                                      n1 * BDRV_SECTOR_SIZE);
-
                    BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING_AIO);
                    qemu_co_mutex_unlock(&s->lock);
                    ret = bdrv_co_readv(bs->backing_hd, sector_num,
-                                        n1, &local_qiov);
+                                        n1, &hd_qiov);
                    qemu_co_mutex_lock(&s->lock);
-
-                    qemu_iovec_destroy(&local_qiov);
-
                    if (ret < 0) {
                        goto fail;
                    }
@@ -1137,6 +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;
@@ -1160,16 +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;
        }
@@ -1274,25 +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)) {
-        int ret1, ret2;
+    qcow2_cache_flush(bs, s->l2_table_cache);
+    qcow2_cache_flush(bs, s->refcount_block_cache);

-        ret1 = qcow2_cache_flush(bs, s->l2_table_cache);
-        ret2 = qcow2_cache_flush(bs, s->refcount_block_cache);
-
-        if (ret1) {
-            error_report("Failed to flush the L2 table cache: %s",
-                         strerror(-ret1));
-        }
-        if (ret2) {
-            error_report("Failed to flush the refcount block cache: %s",
-                         strerror(-ret2));
-        }
-
-        if (!ret1 && !ret2) {
-            qcow2_mark_clean(bs);
-        }
-    }
+    qcow2_mark_clean(bs);

    qcow2_cache_destroy(bs, s->l2_table_cache);
    qcow2_cache_destroy(bs, s->refcount_block_cache);
@@ -1306,7 +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;
@@ -1314,8 +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,
@@ -1330,26 +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;
@@ -1570,39 +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;
    }

    /*
@@ -1611,10 +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;
        }
@@ -1626,7 +1556,7 @@ static int preallocate(BlockDriverState *bs)
 static int qcow2_create2(const char *filename, int64_t total_size,
                         const char *backing_file, const char *backing_format,
                         int flags, size_t cluster_size, int prealloc,
-                         QemuOpts *opts, int version,
+                         QEMUOptionParameter *options, int version,
                         Error **errp)
 {
    /* Calculate cluster_bits */
@@ -1658,15 +1588,13 @@ static int qcow2_create2(const char *filename, int64_t total_size,
    Error *local_err = NULL;
    int ret;

-    ret = bdrv_create_file(filename, opts, &local_err);
+    ret = bdrv_create_file(filename, options, &local_err);
    if (ret < 0) {
        error_propagate(errp, local_err);
        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;
@@ -1717,17 +1645,17 @@ 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
     * refcount of the cluster that is occupied by the header and the refcount
     * table)
     */
-    ret = bdrv_open(&bs, filename, NULL, NULL,
-                    BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH,
-                    &bdrv_qcow2, &local_err);
+    BlockDriver* drv = bdrv_find_format("qcow2");
+    assert(drv != 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);
        goto out;
@@ -1773,31 +1701,28 @@ 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,
-                    &bdrv_qcow2, &local_err);
-    if (local_err) {
+                    drv, &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;
 }

-static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
+static int qcow2_create(const char *filename, QEMUOptionParameter *options,
+                        Error **errp)
 {
-    char *backing_file = NULL;
-    char *backing_fmt = NULL;
-    char *buf = NULL;
+    const char *backing_file = NULL;
+    const char *backing_fmt = NULL;
    uint64_t sectors = 0;
    int flags = 0;
    size_t cluster_size = DEFAULT_CLUSTER_SIZE;
@@ -1807,71 +1732,89 @@ static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
    int ret;

    /* Read out options */
-    sectors = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
-    backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
-    backing_fmt = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FMT);
-    if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ENCRYPT, false)) {
-        flags |= BLOCK_FLAG_ENCRYPT;
-    }
-    cluster_size = qemu_opt_get_size_del(opts, BLOCK_OPT_CLUSTER_SIZE,
-                                         DEFAULT_CLUSTER_SIZE);
-    buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
-    if (!buf || !strcmp(buf, "off")) {
-        prealloc = 0;
-    } else if (!strcmp(buf, "metadata")) {
-        prealloc = 1;
-    } else {
-        error_setg(errp, "Invalid preallocation mode: '%s'", buf);
-        ret = -EINVAL;
-        goto finish;
-    }
-    g_free(buf);
-    buf = qemu_opt_get_del(opts, BLOCK_OPT_COMPAT_LEVEL);
-    if (!buf) {
-        /* keep the default */
-    } else if (!strcmp(buf, "0.10")) {
-        version = 2;
-    } else if (!strcmp(buf, "1.1")) {
-        version = 3;
-    } else {
-        error_setg(errp, "Invalid compatibility level: '%s'", buf);
-        ret = -EINVAL;
-        goto finish;
-    }
-
-    if (qemu_opt_get_bool_del(opts, BLOCK_OPT_LAZY_REFCOUNTS, false)) {
-        flags |= BLOCK_FLAG_LAZY_REFCOUNTS;
+    while (options && options->name) {
+        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+            sectors = options->value.n / 512;
+        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
+            backing_file = options->value.s;
+        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FMT)) {
+            backing_fmt = options->value.s;
+        } else if (!strcmp(options->name, BLOCK_OPT_ENCRYPT)) {
+            flags |= options->value.n ? BLOCK_FLAG_ENCRYPT : 0;
+        } else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) {
+            if (options->value.n) {
+                cluster_size = options->value.n;
+            }
+        } 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, "metadata")) {
+                prealloc = 1;
+            } else {
+                error_setg(errp, "Invalid preallocation mode: '%s'",
+                           options->value.s);
+                return -EINVAL;
+            }
+        } else if (!strcmp(options->name, BLOCK_OPT_COMPAT_LEVEL)) {
+            if (!options->value.s) {
+                /* keep the default */
+            } else if (!strcmp(options->value.s, "0.10")) {
+                version = 2;
+            } else if (!strcmp(options->value.s, "1.1")) {
+                version = 3;
+            } else {
+                error_setg(errp, "Invalid compatibility level: '%s'",
+                           options->value.s);
+                return -EINVAL;
+            }
+        } else if (!strcmp(options->name, BLOCK_OPT_LAZY_REFCOUNTS)) {
+            flags |= options->value.n ? BLOCK_FLAG_LAZY_REFCOUNTS : 0;
+        }
+        options++;
    }

    if (backing_file && prealloc) {
        error_setg(errp, "Backing file and preallocation cannot be used at "
                   "the same time");
-        ret = -EINVAL;
-        goto finish;
+        return -EINVAL;
    }

    if (version < 3 && (flags & BLOCK_FLAG_LAZY_REFCOUNTS)) {
        error_setg(errp, "Lazy refcounts only supported with compatibility "
                   "level 1.1 and above (use compat=1.1 or greater)");
-        ret = -EINVAL;
-        goto finish;
+        return -EINVAL;
    }

    ret = qcow2_create2(filename, sectors, backing_file, backing_fmt, flags,
-                        cluster_size, prealloc, opts, version, &local_err);
-    if (local_err) {
+                        cluster_size, prealloc, options, version, &local_err);
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
    }
-
-finish:
-    g_free(backing_file);
-    g_free(backing_fmt);
-    g_free(buf);
    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;
@@ -1960,7 +1903,8 @@ static int qcow2_write_compressed(BlockDriverState *bs, int64_t sector_num,
           sector based I/Os */
        cluster_offset = bdrv_getlength(bs->file);
        cluster_offset = (cluster_offset + 511) & ~511;
-        return bdrv_truncate(bs->file, cluster_offset);
+        bdrv_truncate(bs->file, cluster_offset);
+        return 0;
    }

    if (nb_sectors != s->cluster_sectors) {
@@ -2066,8 +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;
@@ -2230,72 +2172,64 @@ static int qcow2_downgrade(BlockDriverState *bs, int target_version)
    return 0;
 }

-static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts)
+static int qcow2_amend_options(BlockDriverState *bs,
+                               QEMUOptionParameter *options)
 {
    BDRVQcowState *s = bs->opaque;
    int old_version = s->qcow_version, new_version = old_version;
    uint64_t new_size = 0;
    const char *backing_file = NULL, *backing_format = NULL;
    bool lazy_refcounts = s->use_lazy_refcounts;
-    const char *compat = NULL;
-    uint64_t cluster_size = s->cluster_size;
-    bool encrypt;
    int ret;
-    QemuOptDesc *desc = opts->list->desc;
+    int i;

-    while (desc && desc->name) {
-        if (!qemu_opt_find(opts, desc->name)) {
+    for (i = 0; options[i].name; i++)
+    {
+        if (!options[i].assigned) {
            /* only change explicitly defined options */
-            desc++;
            continue;
        }

-        if (!strcmp(desc->name, "compat")) {
-            compat = qemu_opt_get(opts, "compat");
-            if (!compat) {
+        if (!strcmp(options[i].name, "compat")) {
+            if (!options[i].value.s) {
                /* preserve default */
-            } else if (!strcmp(compat, "0.10")) {
+            } else if (!strcmp(options[i].value.s, "0.10")) {
                new_version = 2;
-            } else if (!strcmp(compat, "1.1")) {
+            } else if (!strcmp(options[i].value.s, "1.1")) {
                new_version = 3;
            } else {
-                fprintf(stderr, "Unknown compatibility level %s.\n", compat);
+                fprintf(stderr, "Unknown compatibility level %s.\n",
+                        options[i].value.s);
                return -EINVAL;
            }
-        } else if (!strcmp(desc->name, "preallocation")) {
+        } else if (!strcmp(options[i].name, "preallocation")) {
            fprintf(stderr, "Cannot change preallocation mode.\n");
            return -ENOTSUP;
-        } else if (!strcmp(desc->name, "size")) {
-            new_size = qemu_opt_get_size(opts, "size", 0);
-        } else if (!strcmp(desc->name, "backing_file")) {
-            backing_file = qemu_opt_get(opts, "backing_file");
-        } else if (!strcmp(desc->name, "backing_fmt")) {
-            backing_format = qemu_opt_get(opts, "backing_fmt");
-        } else if (!strcmp(desc->name, "encryption")) {
-            encrypt = qemu_opt_get_bool(opts, "encryption", s->crypt_method);
-            if (encrypt != !!s->crypt_method) {
+        } else if (!strcmp(options[i].name, "size")) {
+            new_size = options[i].value.n;
+        } else if (!strcmp(options[i].name, "backing_file")) {
+            backing_file = options[i].value.s;
+        } else if (!strcmp(options[i].name, "backing_fmt")) {
+            backing_format = options[i].value.s;
+        } else if (!strcmp(options[i].name, "encryption")) {
+            if ((options[i].value.n != !!s->crypt_method)) {
                fprintf(stderr, "Changing the encryption flag is not "
                        "supported.\n");
                return -ENOTSUP;
            }
-        } else if (!strcmp(desc->name, "cluster_size")) {
-            cluster_size = qemu_opt_get_size(opts, "cluster_size",
-                                             cluster_size);
-            if (cluster_size != s->cluster_size) {
+        } else if (!strcmp(options[i].name, "cluster_size")) {
+            if (options[i].value.n != s->cluster_size) {
                fprintf(stderr, "Changing the cluster size is not "
                        "supported.\n");
                return -ENOTSUP;
            }
-        } else if (!strcmp(desc->name, "lazy_refcounts")) {
-            lazy_refcounts = qemu_opt_get_bool(opts, "lazy_refcounts",
-                                               lazy_refcounts);
+        } else if (!strcmp(options[i].name, "lazy_refcounts")) {
+            lazy_refcounts = options[i].value.n;
        } else {
            /* if this assertion fails, this probably means a new option was
             * added without having it covered here */
            assert(false);
        }
-
-        desc++;
    }

    if (new_version != old_version) {
@@ -2364,58 +2298,52 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts)
    return 0;
 }

-static QemuOptsList qcow2_create_opts = {
-    .name = "qcow2-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(qcow2_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        {
-            .name = BLOCK_OPT_COMPAT_LEVEL,
-            .type = QEMU_OPT_STRING,
-            .help = "Compatibility level (0.10 or 1.1)"
-        },
-        {
-            .name = BLOCK_OPT_BACKING_FILE,
-            .type = QEMU_OPT_STRING,
-            .help = "File name of a base image"
-        },
-        {
-            .name = BLOCK_OPT_BACKING_FMT,
-            .type = QEMU_OPT_STRING,
-            .help = "Image format of the base image"
-        },
-        {
-            .name = BLOCK_OPT_ENCRYPT,
-            .type = QEMU_OPT_BOOL,
-            .help = "Encrypt the image",
-            .def_value_str = "off"
-        },
-        {
-            .name = BLOCK_OPT_CLUSTER_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "qcow2 cluster size",
-            .def_value_str = stringify(DEFAULT_CLUSTER_SIZE)
-        },
-        {
-            .name = BLOCK_OPT_PREALLOC,
-            .type = QEMU_OPT_STRING,
-            .help = "Preallocation mode (allowed values: off, metadata)"
-        },
-        {
-            .name = BLOCK_OPT_LAZY_REFCOUNTS,
-            .type = QEMU_OPT_BOOL,
-            .help = "Postpone refcount updates",
-            .def_value_str = "off"
-        },
-        { /* end of list */ }
-    }
+static QEMUOptionParameter qcow2_create_options[] = {
+    {
+        .name = BLOCK_OPT_SIZE,
+        .type = OPT_SIZE,
+        .help = "Virtual disk size"
+    },
+    {
+        .name = BLOCK_OPT_COMPAT_LEVEL,
+        .type = OPT_STRING,
+        .help = "Compatibility level (0.10 or 1.1)"
+    },
+    {
+        .name = BLOCK_OPT_BACKING_FILE,
+        .type = OPT_STRING,
+        .help = "File name of a base image"
+    },
+    {
+        .name = BLOCK_OPT_BACKING_FMT,
+        .type = OPT_STRING,
+        .help = "Image format of the base image"
+    },
+    {
+        .name = BLOCK_OPT_ENCRYPT,
+        .type = OPT_FLAG,
+        .help = "Encrypt the image"
+    },
+    {
+        .name = BLOCK_OPT_CLUSTER_SIZE,
+        .type = OPT_SIZE,
+        .help = "qcow2 cluster size",
+        .value = { .n = DEFAULT_CLUSTER_SIZE },
+    },
+    {
+        .name = BLOCK_OPT_PREALLOC,
+        .type = OPT_STRING,
+        .help = "Preallocation mode (allowed values: off, metadata)"
+    },
+    {
+        .name = BLOCK_OPT_LAZY_REFCOUNTS,
+        .type = OPT_FLAG,
+        .help = "Postpone refcount updates",
+    },
+    { NULL }
 };

-BlockDriver bdrv_qcow2 = {
+static BlockDriver bdrv_qcow2 = {
    .format_name        = "qcow2",
    .instance_size      = sizeof(BDRVQcowState),
    .bdrv_probe         = qcow2_probe,
@@ -2426,6 +2354,7 @@ 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,
@@ -2440,22 +2369,20 @@ BlockDriver bdrv_qcow2 = {
    .bdrv_snapshot_goto     = qcow2_snapshot_goto,
    .bdrv_snapshot_delete   = qcow2_snapshot_delete,
    .bdrv_snapshot_list     = qcow2_snapshot_list,
-    .bdrv_snapshot_load_tmp = qcow2_snapshot_load_tmp,
-    .bdrv_get_info          = qcow2_get_info,
+    .bdrv_snapshot_load_tmp     = qcow2_snapshot_load_tmp,
+    .bdrv_get_info      = qcow2_get_info,
    .bdrv_get_specific_info = qcow2_get_specific_info,

    .bdrv_save_vmstate    = qcow2_save_vmstate,
    .bdrv_load_vmstate    = qcow2_load_vmstate,

-    .supports_backing           = true,
    .bdrv_change_backing_file   = qcow2_change_backing_file,

-    .bdrv_refresh_limits        = qcow2_refresh_limits,
    .bdrv_invalidate_cache      = qcow2_invalidate_cache,

-    .create_opts         = &qcow2_create_opts,
-    .bdrv_check          = qcow2_check,
-    .bdrv_amend_options  = qcow2_amend_options,
+    .create_options = qcow2_create_options,
+    .bdrv_check = qcow2_check,
+    .bdrv_amend_options = qcow2_amend_options,
 };

 static void bdrv_qcow2_init(void)
@@ -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);
@@ -173,7 +173,7 @@ int qed_read_l1_table_sync(BDRVQEDState *s)
    qed_read_table(s, s->header.l1_table_offset,
                   s->l1_table, qed_sync_cb, &ret);
    while (ret == -EINPROGRESS) {
-        aio_poll(bdrv_get_aio_context(s->bs), true);
+        qemu_aio_wait();
    }

    return ret;
@@ -194,7 +194,7 @@ int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index,

    qed_write_l1_table(s, index, n, qed_sync_cb, &ret);
    while (ret == -EINPROGRESS) {
-        aio_poll(bdrv_get_aio_context(s->bs), true);
+        qemu_aio_wait();
    }

    return ret;
@@ -267,7 +267,7 @@ int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request, uint64_t offset

    qed_read_l2_table(s, request, offset, qed_sync_cb, &ret);
    while (ret == -EINPROGRESS) {
-        aio_poll(bdrv_get_aio_context(s->bs), true);
+        qemu_aio_wait();
    }

    return ret;
@@ -289,7 +289,7 @@ int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request,

    qed_write_l2_table(s, request, index, n, flush, qed_sync_cb, &ret);
    while (ret == -EINPROGRESS) {
-        aio_poll(bdrv_get_aio_context(s->bs), true);
+        qemu_aio_wait();
    }

    return ret;
@@ -21,13 +21,12 @@
 static void qed_aio_cancel(BlockDriverAIOCB *blockacb)
 {
    QEDAIOCB *acb = (QEDAIOCB *)blockacb;
-    AioContext *aio_context = bdrv_get_aio_context(blockacb->bs);
    bool finished = false;

    /* Wait for the request to finish */
    acb->finished = &finished;
    while (!finished) {
-        aio_poll(aio_context, true);
+        qemu_aio_wait();
    }
 }

@@ -374,27 +373,6 @@ static void bdrv_qed_rebind(BlockDriverState *bs)
    s->bs = bs;
 }

-static void bdrv_qed_detach_aio_context(BlockDriverState *bs)
-{
-    BDRVQEDState *s = bs->opaque;
-
-    qed_cancel_need_check_timer(s);
-    timer_free(s->need_check_timer);
-}
-
-static void bdrv_qed_attach_aio_context(BlockDriverState *bs,
-                                        AioContext *new_context)
-{
-    BDRVQEDState *s = bs->opaque;
-
-    s->need_check_timer = aio_timer_new(new_context,
-                                        QEMU_CLOCK_VIRTUAL, SCALE_NS,
-                                        qed_need_check_timer_cb, s);
-    if (s->header.features & QED_F_NEED_CHECK) {
-        qed_start_need_check_timer(s);
-    }
-}
-
 static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
                         Error **errp)
 {
@@ -413,15 +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;
    }
@@ -518,7 +495,8 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
        }
    }

-    bdrv_qed_attach_aio_context(bs, bdrv_get_aio_context(bs));
+    s->need_check_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
+                                            qed_need_check_timer_cb, s);

 out:
    if (ret) {
@@ -528,13 +506,6 @@ out:
    return ret;
 }

-static void bdrv_qed_refresh_limits(BlockDriverState *bs, Error **errp)
-{
-    BDRVQEDState *s = bs->opaque;
-
-    bs->bl.write_zeroes_alignment = s->header.cluster_size >> BDRV_SECTOR_BITS;
-}
-
 /* We have nothing to do for QED reopen, stubs just return
 * success */
 static int bdrv_qed_reopen_prepare(BDRVReopenState *state,
@@ -547,7 +518,8 @@ static void bdrv_qed_close(BlockDriverState *bs)
 {
    BDRVQEDState *s = bs->opaque;

-    bdrv_qed_detach_aio_context(bs);
+    qed_cancel_need_check_timer(s);
+    timer_free(s->need_check_timer);

    /* Ensure writes reach stable storage */
    bdrv_flush(bs->file);
@@ -564,8 +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,
-                      QemuOpts *opts, Error **errp)
+                      const char *backing_file, const char *backing_fmt)
 {
    QEDHeader header = {
        .magic = QED_MAGIC,
@@ -582,20 +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, opts, &local_err);
+    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;
    }

@@ -639,53 +610,53 @@ out:
    return ret;
 }

-static int bdrv_qed_create(const char *filename, QemuOpts *opts, Error **errp)
+static int bdrv_qed_create(const char *filename, QEMUOptionParameter *options,
+                           Error **errp)
 {
    uint64_t image_size = 0;
    uint32_t cluster_size = QED_DEFAULT_CLUSTER_SIZE;
    uint32_t table_size = QED_DEFAULT_TABLE_SIZE;
-    char *backing_file = NULL;
-    char *backing_fmt = NULL;
-    int ret;
+    const char *backing_file = NULL;
+    const char *backing_fmt = NULL;

-    image_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
-    backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
-    backing_fmt = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FMT);
-    cluster_size = qemu_opt_get_size_del(opts,
-                                         BLOCK_OPT_CLUSTER_SIZE,
-                                         QED_DEFAULT_CLUSTER_SIZE);
-    table_size = qemu_opt_get_size_del(opts, BLOCK_OPT_TABLE_SIZE,
-                                       QED_DEFAULT_TABLE_SIZE);
+    while (options && options->name) {
+        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+            image_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_BACKING_FMT)) {
+            backing_fmt = options->value.s;
+        } else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) {
+            if (options->value.n) {
+                cluster_size = options->value.n;
+            }
+        } else if (!strcmp(options->name, BLOCK_OPT_TABLE_SIZE)) {
+            if (options->value.n) {
+                table_size = options->value.n;
+            }
+        }
+        options++;
+    }

    if (!qed_is_cluster_size_valid(cluster_size)) {
-        error_setg(errp, "QED cluster size must be within range [%u, %u] "
-                         "and power of 2",
-                   QED_MIN_CLUSTER_SIZE, QED_MAX_CLUSTER_SIZE);
-        ret = -EINVAL;
-        goto finish;
+        fprintf(stderr, "QED cluster size must be within range [%u, %u] and power of 2\n",
+                QED_MIN_CLUSTER_SIZE, QED_MAX_CLUSTER_SIZE);
+        return -EINVAL;
    }
    if (!qed_is_table_size_valid(table_size)) {
-        error_setg(errp, "QED table size must be within range [%u, %u] "
-                         "and power of 2",
-                   QED_MIN_TABLE_SIZE, QED_MAX_TABLE_SIZE);
-        ret = -EINVAL;
-        goto finish;
+        fprintf(stderr, "QED table size must be within range [%u, %u] and power of 2\n",
+                QED_MIN_TABLE_SIZE, QED_MAX_TABLE_SIZE);
+        return -EINVAL;
    }
    if (!qed_is_image_size_valid(image_size, cluster_size, table_size)) {
-        error_setg(errp, "QED image size must be a non-zero multiple of "
-                         "cluster size and less than %" PRIu64 " bytes",
-                   qed_max_image_size(cluster_size, table_size));
-        ret = -EINVAL;
-        goto finish;
+        fprintf(stderr, "QED image size must be a non-zero multiple of "
+                        "cluster size and less than %" PRIu64 " bytes\n",
+                qed_max_image_size(cluster_size, table_size));
+        return -EINVAL;
    }

-    ret = qed_create(filename, cluster_size, image_size, table_size,
-                     backing_file, backing_fmt, opts, errp);
-
-finish:
-    g_free(backing_file);
-    g_free(backing_fmt);
-    return ret;
+    return qed_create(filename, cluster_size, image_size, table_size,
+                      backing_file, backing_fmt);
 }

 typedef struct {
@@ -751,6 +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;
@@ -759,19 +735,17 @@ static BDRVQEDState *acb_to_s(QEDAIOCB *acb)
 /**
 * Read from the backing file or zero-fill if no backing file
 *
- * @s:              QED state
- * @pos:            Byte position in device
- * @qiov:           Destination I/O vector
- * @backing_qiov:   Possibly shortened copy of qiov, to be allocated here
- * @cb:             Completion function
- * @opaque:         User data for completion function
+ * @s:          QED state
+ * @pos:        Byte position in device
+ * @qiov:       Destination I/O vector
+ * @cb:         Completion function
+ * @opaque:     User data for completion function
 *
 * This function reads qiov->size bytes starting at pos from the backing file.
 * If there is no backing file then zeroes are read.
 */
 static void qed_read_backing_file(BDRVQEDState *s, uint64_t pos,
                                  QEMUIOVector *qiov,
-                                  QEMUIOVector **backing_qiov,
                                  BlockDriverCompletionFunc *cb, void *opaque)
 {
    uint64_t backing_length = 0;
@@ -804,21 +778,15 @@ static void qed_read_backing_file(BDRVQEDState *s, uint64_t pos,
    /* If the read straddles the end of the backing file, shorten it */
    size = MIN((uint64_t)backing_length - pos, qiov->size);

-    assert(*backing_qiov == NULL);
-    *backing_qiov = g_new(QEMUIOVector, 1);
-    qemu_iovec_init(*backing_qiov, qiov->niov);
-    qemu_iovec_concat(*backing_qiov, qiov, 0, size);
-
    BLKDBG_EVENT(s->bs->file, BLKDBG_READ_BACKING_AIO);
    bdrv_aio_readv(s->bs->backing_hd, pos / BDRV_SECTOR_SIZE,
-                   *backing_qiov, size / BDRV_SECTOR_SIZE, cb, opaque);
+                   qiov, size / BDRV_SECTOR_SIZE, cb, opaque);
 }

 typedef struct {
    GenericCB gencb;
    BDRVQEDState *s;
    QEMUIOVector qiov;
-    QEMUIOVector *backing_qiov;
    struct iovec iov;
    uint64_t offset;
 } CopyFromBackingFileCB;
@@ -835,12 +803,6 @@ static void qed_copy_from_backing_file_write(void *opaque, int ret)
    CopyFromBackingFileCB *copy_cb = opaque;
    BDRVQEDState *s = copy_cb->s;

-    if (copy_cb->backing_qiov) {
-        qemu_iovec_destroy(copy_cb->backing_qiov);
-        g_free(copy_cb->backing_qiov);
-        copy_cb->backing_qiov = NULL;
-    }
-
    if (ret) {
        qed_copy_from_backing_file_cb(copy_cb, ret);
        return;
@@ -878,12 +840,11 @@ static void qed_copy_from_backing_file(BDRVQEDState *s, uint64_t pos,
    copy_cb = gencb_alloc(sizeof(*copy_cb), cb, opaque);
    copy_cb->s = s;
    copy_cb->offset = offset;
-    copy_cb->backing_qiov = NULL;
    copy_cb->iov.iov_base = qemu_blockalign(s->bs, len);
    copy_cb->iov.iov_len = len;
    qemu_iovec_init_external(&copy_cb->qiov, &copy_cb->iov, 1);

-    qed_read_backing_file(s, pos, &copy_cb->qiov, &copy_cb->backing_qiov,
+    qed_read_backing_file(s, pos, &copy_cb->qiov,
                          qed_copy_from_backing_file_write, copy_cb);
 }

@@ -950,8 +911,7 @@ static void qed_aio_complete(QEDAIOCB *acb, int ret)

    /* Arrange for a bh to invoke the completion function */
    acb->bh_ret = ret;
-    acb->bh = aio_bh_new(bdrv_get_aio_context(acb->common.bs),
-                         qed_aio_complete_bh, acb);
+    acb->bh = qemu_bh_new(qed_aio_complete_bh, acb);
    qemu_bh_schedule(acb->bh);

    /* Start next allocating write request waiting behind this one.  Note that
@@ -1326,7 +1286,7 @@ static void qed_aio_read_data(void *opaque, int ret,
        return;
    } else if (ret != QED_CLUSTER_FOUND) {
        qed_read_backing_file(s, acb->cur_pos, &acb->cur_qiov,
-                              &acb->backing_qiov, qed_aio_next_io, acb);
+                              qed_aio_next_io, acb);
        return;
    }

@@ -1352,12 +1312,6 @@ static void qed_aio_next_io(void *opaque, int ret)

    trace_qed_aio_next_io(s, acb, ret, acb->cur_pos + acb->cur_qiov.size);

-    if (acb->backing_qiov) {
-        qemu_iovec_destroy(acb->backing_qiov);
-        g_free(acb->backing_qiov);
-        acb->backing_qiov = NULL;
-    }
-
    /* Handle I/O error */
    if (ret) {
        qed_aio_complete(acb, ret);
@@ -1397,7 +1351,6 @@ static BlockDriverAIOCB *qed_aio_setup(BlockDriverState *bs,
    acb->qiov_offset = 0;
    acb->cur_pos = (uint64_t)sector_num * BDRV_SECTOR_SIZE;
    acb->end_pos = acb->cur_pos + nb_sectors * BDRV_SECTOR_SIZE;
-    acb->backing_qiov = NULL;
    acb->request.l2_table = NULL;
    qemu_iovec_init(&acb->cur_qiov, qiov->niov);

@@ -1444,8 +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;
@@ -1522,8 +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;
 }

@@ -1599,31 +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,
@@ -1634,45 +1566,36 @@ static int bdrv_qed_check(BlockDriverState *bs, BdrvCheckResult *result,
    return qed_check(s, result, !!fix);
 }

-static QemuOptsList qed_create_opts = {
-    .name = "qed-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(qed_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        {
-            .name = BLOCK_OPT_BACKING_FILE,
-            .type = QEMU_OPT_STRING,
-            .help = "File name of a base image"
-        },
-        {
-            .name = BLOCK_OPT_BACKING_FMT,
-            .type = QEMU_OPT_STRING,
-            .help = "Image format of the base image"
-        },
-        {
-            .name = BLOCK_OPT_CLUSTER_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Cluster size (in bytes)",
-            .def_value_str = stringify(QED_DEFAULT_CLUSTER_SIZE)
-        },
-        {
-            .name = BLOCK_OPT_TABLE_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "L1/L2 table size (in clusters)"
-        },
-        { /* end of list */ }
-    }
+static QEMUOptionParameter qed_create_options[] = {
+    {
+        .name = BLOCK_OPT_SIZE,
+        .type = OPT_SIZE,
+        .help = "Virtual disk size (in bytes)"
+    }, {
+        .name = BLOCK_OPT_BACKING_FILE,
+        .type = OPT_STRING,
+        .help = "File name of a base image"
+    }, {
+        .name = BLOCK_OPT_BACKING_FMT,
+        .type = OPT_STRING,
+        .help = "Image format of the base image"
+    }, {
+        .name = BLOCK_OPT_CLUSTER_SIZE,
+        .type = OPT_SIZE,
+        .help = "Cluster size (in bytes)",
+        .value = { .n = QED_DEFAULT_CLUSTER_SIZE },
+    }, {
+        .name = BLOCK_OPT_TABLE_SIZE,
+        .type = OPT_SIZE,
+        .help = "L1/L2 table size (in clusters)"
+    },
+    { /* end of list */ }
 };

 static BlockDriver bdrv_qed = {
    .format_name              = "qed",
    .instance_size            = sizeof(BDRVQEDState),
-    .create_opts              = &qed_create_opts,
-    .supports_backing         = true,
+    .create_options           = qed_create_options,

    .bdrv_probe               = bdrv_qed_probe,
    .bdrv_rebind              = bdrv_qed_rebind,
@@ -1682,18 +1605,16 @@ 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,
-    .bdrv_detach_aio_context  = bdrv_qed_detach_aio_context,
-    .bdrv_attach_aio_context  = bdrv_qed_attach_aio_context,
 };

 static void bdrv_qed_init(void)
@@ -43,7 +43,7 @@
 *
 * All fields are little-endian on disk.
 */
-#define  QED_DEFAULT_CLUSTER_SIZE  65536
+
 enum {
    QED_MAGIC = 'Q' | 'E' << 8 | 'D' << 16 | '\0' << 24,

@@ -69,6 +69,7 @@ enum {
     */
    QED_MIN_CLUSTER_SIZE = 4 * 1024, /* in bytes */
    QED_MAX_CLUSTER_SIZE = 64 * 1024 * 1024,
+    QED_DEFAULT_CLUSTER_SIZE = 64 * 1024,

    /* Allocated clusters are tracked using a 2-level pagetable.  Table size is
     * a multiple of clusters so large maximum image sizes can be supported
@@ -142,7 +143,6 @@ typedef struct QEDAIOCB {

    /* Current cluster scatter-gather list */
    QEMUIOVector cur_qiov;
-    QEMUIOVector *backing_qiov;
    uint64_t cur_pos;               /* position on block device, in bytes */
    uint64_t cur_cluster;           /* cluster offset in image file */
    unsigned int cur_nclusters;     /* number of clusters being accessed */
@@ -1,977 +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"
-#include "qapi-event.h"
-
-#define HASH_LENGTH 32
-
-#define QUORUM_OPT_VOTE_THRESHOLD "vote-threshold"
-#define QUORUM_OPT_BLKVERIFY      "blkverify"
-#define QUORUM_OPT_REWRITE        "rewrite-corrupted"
-
-/* 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.
-                            */
-    bool rewrite_corrupted;/* true if the driver must rewrite-on-read corrupted
-                            * block if Quorum is reached.
-                            */
-} 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 */
-
-    int rewrite_count;          /* number of replica to rewrite: count down to
-                                 * zero once writes are fired
-                                 */
-
-    QuorumVotes votes;
-
-    bool is_read;
-    int vote_ret;
-};
-
-static bool 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->rewrite_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)
-{
-    const char *msg = NULL;
-    if (ret < 0) {
-        msg = strerror(-ret);
-    }
-    qapi_event_send_quorum_report_bad(!!msg, msg, node_name,
-                                      acb->sector_num, acb->nb_sectors, &error_abort);
-}
-
-static void quorum_report_failure(QuorumAIOCB *acb)
-{
-    const char *reference = acb->common.bs->device_name[0] ?
-                            acb->common.bs->device_name :
-                            acb->common.bs->node_name;
-
-    qapi_event_send_quorum_failure(reference, acb->sector_num,
-                                   acb->nb_sectors, &error_abort);
-}
-
-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_rewrite_aio_cb(void *opaque, int ret)
-{
-    QuorumAIOCB *acb = opaque;
-
-    /* one less rewrite to do */
-    acb->rewrite_count--;
-
-    /* wait until all rewrite callbacks have completed */
-    if (acb->rewrite_count) {
-        return;
-    }
-
-    quorum_aio_finalize(acb);
-}
-
-static void quorum_aio_cb(void *opaque, int ret)
-{
-    QuorumChildRequest *sacb = opaque;
-    QuorumAIOCB *acb = sacb->parent;
-    BDRVQuorumState *s = acb->common.bs->opaque;
-    bool rewrite = false;
-
-    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) {
-        rewrite = quorum_vote(acb);
-    } else {
-        quorum_has_too_much_io_failed(acb);
-    }
-
-    /* if no rewrite is done the code will finish right away */
-    if (!rewrite) {
-        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 bool quorum_rewrite_bad_versions(BDRVQuorumState *s, QuorumAIOCB *acb,
-                                        QuorumVoteValue *value)
-{
-    QuorumVoteVersion *version;
-    QuorumVoteItem *item;
-    int count = 0;
-
-    /* first count the number of bad versions: done first to avoid concurrency
-     * issues.
-     */
-    QLIST_FOREACH(version, &acb->votes.vote_list, next) {
-        if (acb->votes.compare(&version->value, value)) {
-            continue;
-        }
-        QLIST_FOREACH(item, &version->items, next) {
-            count++;
-        }
-    }
-
-    /* quorum_rewrite_aio_cb will count down this to zero */
-    acb->rewrite_count = count;
-
-    /* now fire the correcting rewrites */
-    QLIST_FOREACH(version, &acb->votes.vote_list, next) {
-        if (acb->votes.compare(&version->value, value)) {
-            continue;
-        }
-        QLIST_FOREACH(item, &version->items, next) {
-            bdrv_aio_writev(s->bs[item->index], acb->sector_num, acb->qiov,
-                            acb->nb_sectors, quorum_rewrite_aio_cb, acb);
-        }
-    }
-
-    /* return true if any rewrite is done else false */
-    return count;
-}
-
-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 bool quorum_vote(QuorumAIOCB *acb)
-{
-    bool quorum = true;
-    bool rewrite = false;
-    int i, j, ret;
-    QuorumVoteValue hash;
-    BDRVQuorumState *s = acb->common.bs->opaque;
-    QuorumVoteVersion *winner;
-
-    if (quorum_has_too_much_io_failed(acb)) {
-        return false;
-    }
-
-    /* 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 false;
-    }
-
-    /* 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);
-
-    /* corruption correction is enabled */
-    if (s->rewrite_corrupted) {
-        rewrite = quorum_rewrite_bad_versions(s, acb, &winner->value);
-    }
-
-free_exit:
-    /* free lists */
-    quorum_free_vote_list(&acb->votes);
-    return rewrite;
-}
-
-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",
-        },
-        {
-            .name = QUORUM_OPT_REWRITE,
-            .type = QEMU_OPT_BOOL,
-            .help = "Rewrite corrupted block on read quorum",
-        },
-        { /* 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 (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");
-    }
-
-    s->rewrite_corrupted = qemu_opt_get_bool(opts, QUORUM_OPT_REWRITE, false);
-    if (s->rewrite_corrupted && s->is_blkverify) {
-        error_setg(&local_err,
-                   "rewrite-corrupted=on cannot be used with blkverify=on");
-        ret = -EINVAL;
-        goto exit;
-    }
-
-    /* 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 (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 void quorum_detach_aio_context(BlockDriverState *bs)
-{
-    BDRVQuorumState *s = bs->opaque;
-    int i;
-
-    for (i = 0; i < s->num_children; i++) {
-        bdrv_detach_aio_context(s->bs[i]);
-    }
-}
-
-static void quorum_attach_aio_context(BlockDriverState *bs,
-                                      AioContext *new_context)
-{
-    BDRVQuorumState *s = bs->opaque;
-    int i;
-
-    for (i = 0; i < s->num_children; i++) {
-        bdrv_attach_aio_context(s->bs[i], new_context);
-    }
-}
-
-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,
-
-    .bdrv_detach_aio_context            = quorum_detach_aio_context,
-    .bdrv_attach_aio_context            = quorum_attach_aio_context,
-
-    .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
@@ -34,29 +33,19 @@
 /* linux-aio.c - Linux native implementation */
 #ifdef CONFIG_LINUX_AIO
 void *laio_init(void);
-void laio_cleanup(void *s);
 BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
        BlockDriverCompletionFunc *cb, void *opaque, int type);
-void laio_detach_aio_context(void *s, AioContext *old_context);
-void laio_attach_aio_context(void *s, AioContext *new_context);
-void laio_io_plug(BlockDriverState *bs, void *aio_ctx);
-int laio_io_unplug(BlockDriverState *bs, void *aio_ctx, bool unplug);
 #endif

 #ifdef _WIN32
 typedef struct QEMUWin32AIOState QEMUWin32AIOState;
 QEMUWin32AIOState *win32_aio_init(void);
-void win32_aio_cleanup(QEMUWin32AIOState *aio);
 int win32_aio_attach(QEMUWin32AIOState *aio, HANDLE hfile);
 BlockDriverAIOCB *win32_aio_submit(BlockDriverState *bs,
        QEMUWin32AIOState *aio, HANDLE hfile,
        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
        BlockDriverCompletionFunc *cb, void *opaque, int type);
-void win32_aio_detach_aio_context(QEMUWin32AIOState *aio,
-                                  AioContext *old_context);
-void win32_aio_attach_aio_context(QEMUWin32AIOState *aio,
-                                  AioContext *new_context);
 #endif

 #endif /* QEMU_RAW_AIO_H */
@@ -36,6 +36,8 @@
 #define FTYPE_CD     1
 #define FTYPE_HARDDISK 2

+static QEMUWin32AIOState *aio;
+
 typedef struct RawWin32AIOData {
    BlockDriverState *bs;
    HANDLE hfile;
@@ -200,54 +202,6 @@ static int set_sparse(int fd)
 				 NULL, 0, NULL, 0, &returned, NULL);
 }

-static void raw_detach_aio_context(BlockDriverState *bs)
-{
-    BDRVRawState *s = bs->opaque;
-
-    if (s->aio) {
-        win32_aio_detach_aio_context(s->aio, bdrv_get_aio_context(bs));
-    }
-}
-
-static void raw_attach_aio_context(BlockDriverState *bs,
-                                   AioContext *new_context)
-{
-    BDRVRawState *s = bs->opaque;
-
-    if (s->aio) {
-        win32_aio_attach_aio_context(s->aio, new_context);
-    }
-}
-
-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);
@@ -268,17 +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),
@@ -305,9 +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;
@@ -317,15 +260,13 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,

    raw_parse_flags(flags, &access_flags, &overlapped);

-    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]);
+    if ((flags & BDRV_O_NATIVE_AIO) && aio == NULL) {
+        aio = win32_aio_init();
+        if (aio == NULL) {
+            error_setg(errp, "Could not initialize AIO");
+            ret = -EINVAL;
+            goto fail;
+        }
    }

    s->hfile = CreateFile(filename, access_flags,
@@ -343,26 +284,15 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
    }

    if (flags & BDRV_O_NATIVE_AIO) {
-        s->aio = win32_aio_init();
-        if (s->aio == NULL) {
-            CloseHandle(s->hfile);
-            error_setg(errp, "Could not initialize AIO");
-            ret = -EINVAL;
-            goto fail;
-        }
-
-        ret = win32_aio_attach(s->aio, s->hfile);
+        ret = win32_aio_attach(aio, s->hfile);
        if (ret < 0) {
-            win32_aio_cleanup(s->aio);
            CloseHandle(s->hfile);
            error_setg_errno(errp, -ret, "Could not enable AIO");
            goto fail;
        }
-
-        win32_aio_attach_aio_context(s->aio, bdrv_get_aio_context(bs));
+        s->aio = aio;
    }

-    raw_probe_alignment(bs);
    ret = 0;
 fail:
    qemu_opts_del(opts);
@@ -407,17 +337,7 @@ static BlockDriverAIOCB *raw_aio_flush(BlockDriverState *bs,
 static void raw_close(BlockDriverState *bs)
 {
    BDRVRawState *s = bs->opaque;
-
-    if (s->aio) {
-        win32_aio_detach_aio_context(s->aio, bdrv_get_aio_context(bs));
-        win32_aio_cleanup(s->aio);
-        s->aio = NULL;
-    }
-
    CloseHandle(s->hfile);
-    if (bs->open_flags & BDRV_O_TEMPORARY) {
-        unlink(bs->filename);
-    }
 }

 static int raw_truncate(BlockDriverState *bs, int64_t offset)
@@ -503,16 +423,19 @@ static int64_t raw_get_allocated_file_size(BlockDriverState *bs)
    return st.st_size;
 }

-static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
+static int raw_create(const char *filename, QEMUOptionParameter *options,
+                      Error **errp)
 {
    int fd;
    int64_t total_size = 0;

-    strstart(filename, "file:", &filename);
-
    /* Read out options */
-    total_size =
-        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
+    while (options && options->name) {
+        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+            total_size = options->value.n / 512;
+        }
+        options++;
+    }

    fd = qemu_open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
                   0644);
@@ -526,29 +449,23 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
    return 0;
 }

-
-static QemuOptsList raw_create_opts = {
-    .name = "raw-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(raw_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        { /* end of list */ }
-    }
+static QEMUOptionParameter raw_create_options[] = {
+    {
+        .name = BLOCK_OPT_SIZE,
+        .type = OPT_SIZE,
+        .help = "Virtual disk size"
+    },
+    { NULL }
 };

-BlockDriver bdrv_file = {
+static BlockDriver bdrv_file = {
    .format_name	= "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,
+    .bdrv_file_open	= raw_open,
+    .bdrv_close		= raw_close,
+    .bdrv_create	= raw_create,
    .bdrv_has_zero_init = bdrv_has_zero_init_1,

    .bdrv_aio_readv     = raw_aio_readv,
@@ -560,7 +477,7 @@ BlockDriver bdrv_file = {
    .bdrv_get_allocated_file_size
                        = raw_get_allocated_file_size,

-    .create_opts        = &raw_create_opts,
+    .create_options = raw_create_options,
 };

 /***********************************************/
@@ -621,15 +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)
 {
@@ -642,10 +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;
@@ -700,7 +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,
@@ -709,9 +615,6 @@ static BlockDriver bdrv_host_device = {
    .bdrv_aio_writev    = raw_aio_writev,
    .bdrv_aio_flush     = raw_aio_flush,

-    .bdrv_detach_aio_context = raw_detach_aio_context,
-    .bdrv_attach_aio_context = raw_attach_aio_context,
-
    .bdrv_getlength      = raw_getlength,
    .has_variable_length = true,

@@ -29,17 +29,13 @@
 #include "block/block_int.h"
 #include "qemu/option.h"

-static QemuOptsList raw_create_opts = {
-    .name = "raw-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(raw_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        { /* end of list */ }
-    }
+static QEMUOptionParameter raw_create_options[] = {
+    {
+        .name = BLOCK_OPT_SIZE,
+        .type = OPT_SIZE,
+        .help = "Virtual disk size"
+    },
+    { 0 }
 };

 static int raw_reopen_prepare(BDRVReopenState *reopen_state,
@@ -72,10 +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,
@@ -94,11 +89,6 @@ static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
    return bdrv_get_info(bs->file, bdi);
 }

-static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
-{
-    bs->bl = bs->file->bl;
-}
-
 static int raw_truncate(BlockDriverState *bs, int64_t offset)
 {
    return bdrv_truncate(bs->file, offset);
@@ -142,13 +132,14 @@ static int raw_has_zero_init(BlockDriverState *bs)
    return bdrv_has_zero_init(bs->file);
 }

-static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
+static int raw_create(const char *filename, QEMUOptionParameter *options,
+                      Error **errp)
 {
    Error *local_err = NULL;
    int ret;

-    ret = bdrv_create_file(filename, opts, &local_err);
-    if (local_err) {
+    ret = bdrv_create_file(filename, options, &local_err);
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
    }
    return ret;
@@ -173,7 +164,7 @@ static int raw_probe(const uint8_t *buf, int buf_size, const char *filename)
    return 1;
 }

-BlockDriver bdrv_raw = {
+static BlockDriver bdrv_raw = {
    .format_name          = "raw",
    .bdrv_probe           = &raw_probe,
    .bdrv_reopen_prepare  = &raw_reopen_prepare,
@@ -189,14 +180,13 @@ 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,
    .bdrv_lock_medium     = &raw_lock_medium,
    .bdrv_ioctl           = &raw_ioctl,
    .bdrv_aio_ioctl       = &raw_aio_ioctl,
-    .create_opts          = &raw_create_opts,
+    .create_options       = &raw_create_options[0],
    .bdrv_has_zero_init   = &raw_has_zero_init
 };

@@ -95,17 +95,22 @@ 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,
-                             char **p, Error **errp)
+                             char **p)
 {
    int l;
    char *end;
@@ -128,10 +133,10 @@ static int qemu_rbd_next_tok(char *dst, int dst_len,
    }
    l = strlen(src);
    if (l >= dst_len) {
-        error_setg(errp, "%s too long", name);
+        error_report("%s too long", name);
        return -EINVAL;
    } else if (l == 0) {
-        error_setg(errp, "%s too short", name);
+        error_report("%s too short", name);
        return -EINVAL;
    }

@@ -157,15 +162,13 @@ static int qemu_rbd_parsename(const char *filename,
                              char *pool, int pool_len,
                              char *snap, int snap_len,
                              char *name, int name_len,
-                              char *conf, int conf_len,
-                              Error **errp)
+                              char *conf, int conf_len)
 {
    const char *start;
    char *p, *buf;
    int ret;

    if (!strstart(filename, "rbd:", &start)) {
-        error_setg(errp, "File name must start with 'rbd:'");
        return -EINVAL;
    }

@@ -174,8 +177,7 @@ static int qemu_rbd_parsename(const char *filename,
    *snap = '\0';
    *conf = '\0';

-    ret = qemu_rbd_next_tok(pool, pool_len, p,
-                            '/', "pool name", &p, errp);
+    ret = qemu_rbd_next_tok(pool, pool_len, p, '/', "pool name", &p);
    if (ret < 0 || !p) {
        ret = -EINVAL;
        goto done;
@@ -183,25 +185,21 @@ static int qemu_rbd_parsename(const char *filename,
    qemu_rbd_unescape(pool);

    if (strchr(p, '@')) {
-        ret = qemu_rbd_next_tok(name, name_len, p,
-                                '@', "object name", &p, errp);
+        ret = qemu_rbd_next_tok(name, name_len, p, '@', "object name", &p);
        if (ret < 0) {
            goto done;
        }
-        ret = qemu_rbd_next_tok(snap, snap_len, p,
-                                ':', "snap name", &p, errp);
+        ret = qemu_rbd_next_tok(snap, snap_len, p, ':', "snap name", &p);
        qemu_rbd_unescape(snap);
    } else {
-        ret = qemu_rbd_next_tok(name, name_len, p,
-                                ':', "object name", &p, errp);
+        ret = qemu_rbd_next_tok(name, name_len, p, ':', "object name", &p);
    }
    qemu_rbd_unescape(name);
    if (ret < 0 || !p) {
        goto done;
    }

-    ret = qemu_rbd_next_tok(conf, conf_len, p,
-                            '\0', "configuration", &p, errp);
+    ret = qemu_rbd_next_tok(conf, conf_len, p, '\0', "configuration", &p);

 done:
    g_free(buf);
@@ -236,7 +234,7 @@ static char *qemu_rbd_parse_clientname(const char *conf, char *clientname)
    return NULL;
 }

-static int qemu_rbd_set_conf(rados_t cluster, const char *conf, Error **errp)
+static int qemu_rbd_set_conf(rados_t cluster, const char *conf)
 {
    char *p, *buf;
    char name[RBD_MAX_CONF_NAME_SIZE];
@@ -248,20 +246,20 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf, Error **errp)

    while (p) {
        ret = qemu_rbd_next_tok(name, sizeof(name), p,
-                                '=', "conf option name", &p, errp);
+                                '=', "conf option name", &p);
        if (ret < 0) {
            break;
        }
        qemu_rbd_unescape(name);

        if (!p) {
-            error_setg(errp, "conf option %s has no value", name);
+            error_report("conf option %s has no value", name);
            ret = -EINVAL;
            break;
        }

        ret = qemu_rbd_next_tok(value, sizeof(value), p,
-                                ':', "conf option value", &p, errp);
+                                ':', "conf option value", &p);
        if (ret < 0) {
            break;
        }
@@ -270,7 +268,7 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf, Error **errp)
        if (strcmp(name, "conf") == 0) {
            ret = rados_conf_read_file(cluster, value);
            if (ret < 0) {
-                error_setg(errp, "error reading conf file %s", value);
+                error_report("error reading conf file %s", value);
                break;
            }
        } else if (strcmp(name, "id") == 0) {
@@ -278,7 +276,7 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf, Error **errp)
        } else {
            ret = rados_conf_set(cluster, name, value);
            if (ret < 0) {
-                error_setg(errp, "invalid conf option %s", name);
+                error_report("invalid conf option %s", name);
                ret = -EINVAL;
                break;
            }
@@ -289,9 +287,9 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf, Error **errp)
    return ret;
 }

-static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
+static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options,
+                           Error **errp)
 {
-    Error *local_err = NULL;
    int64_t bytes = 0;
    int64_t objsize;
    int obj_order = 0;
@@ -308,29 +306,34 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
    if (qemu_rbd_parsename(filename, pool, sizeof(pool),
                           snap_buf, sizeof(snap_buf),
                           name, sizeof(name),
-                           conf, sizeof(conf), &local_err) < 0) {
-        error_propagate(errp, local_err);
+                           conf, sizeof(conf)) < 0) {
        return -EINVAL;
    }

    /* Read out options */
-    bytes = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
-    objsize = qemu_opt_get_size_del(opts, BLOCK_OPT_CLUSTER_SIZE, 0);
-    if (objsize) {
-        if ((objsize - 1) & objsize) {    /* not a power of 2? */
-            error_setg(errp, "obj size needs to be power of 2");
-            return -EINVAL;
+    while (options && options->name) {
+        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+            bytes = options->value.n;
+        } else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) {
+            if (options->value.n) {
+                objsize = options->value.n;
+                if ((objsize - 1) & objsize) {    /* not a power of 2? */
+                    error_report("obj size needs to be power of 2");
+                    return -EINVAL;
+                }
+                if (objsize < 4096) {
+                    error_report("obj size too small");
+                    return -EINVAL;
+                }
+                obj_order = ffs(objsize) - 1;
+            }
        }
-        if (objsize < 4096) {
-            error_setg(errp, "obj size too small");
-            return -EINVAL;
-        }
-        obj_order = ffs(objsize) - 1;
+        options++;
    }

    clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
    if (rados_create(&cluster, clientname) < 0) {
-        error_setg(errp, "error initializing");
+        error_report("error initializing");
        return -EIO;
    }

@@ -340,20 +343,20 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
    }

    if (conf[0] != '\0' &&
-        qemu_rbd_set_conf(cluster, conf, &local_err) < 0) {
+        qemu_rbd_set_conf(cluster, conf) < 0) {
+        error_report("error setting config options");
        rados_shutdown(cluster);
-        error_propagate(errp, local_err);
        return -EIO;
    }

    if (rados_connect(cluster) < 0) {
-        error_setg(errp, "error connecting");
+        error_report("error connecting");
        rados_shutdown(cluster);
        return -EIO;
    }

    if (rados_ioctx_create(cluster, pool, &io_ctx) < 0) {
-        error_setg(errp, "error opening pool %s", pool);
+        error_report("error opening pool %s", pool);
        rados_shutdown(cluster);
        return -EIO;
    }
@@ -366,8 +369,9 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
 }

 /*
- * 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)
 {
@@ -397,19 +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 */
@@ -440,10 +461,11 @@ 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) {
-        error_propagate(errp, local_err);
+    if (error_is_set(&local_err)) {
+        qerror_report_err(local_err);
+        error_free(local_err);
        qemu_opts_del(opts);
        return -EINVAL;
    }
@@ -453,7 +475,7 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
    if (qemu_rbd_parsename(filename, pool, sizeof(pool),
                           snap_buf, sizeof(snap_buf),
                           s->name, sizeof(s->name),
-                           conf, sizeof(conf), errp) < 0) {
+                           conf, sizeof(conf)) < 0) {
        r = -EINVAL;
        goto failed_opts;
    }
@@ -461,7 +483,7 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
    clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
    r = rados_create(&s->cluster, clientname);
    if (r < 0) {
-        error_setg(&local_err, "error initializing");
+        error_report("error initializing");
        goto failed_opts;
    }

@@ -489,35 +511,50 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
    }

    if (conf[0] != '\0') {
-        r = qemu_rbd_set_conf(s->cluster, conf, errp);
+        r = qemu_rbd_set_conf(s->cluster, conf);
        if (r < 0) {
+            error_report("error setting config options");
            goto failed_shutdown;
        }
    }

    r = rados_connect(s->cluster);
    if (r < 0) {
-        error_setg(&local_err, "error connecting");
+        error_report("error connecting");
        goto failed_shutdown;
    }

    r = rados_ioctx_create(s->cluster, pool, &s->io_ctx);
    if (r < 0) {
-        error_setg(&local_err, "error opening pool %s", pool);
+        error_report("error opening pool %s", pool);
        goto failed_shutdown;
    }

    r = rbd_open(s->io_ctx, s->name, &s->image, s->snap);
    if (r < 0) {
-        error_setg(&local_err, "error reading header from %s", s->name);
+        error_report("error reading header from %s", s->name);
        goto failed_open;
    }

    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);
@@ -548,7 +589,7 @@ static void qemu_rbd_aio_cancel(BlockDriverAIOCB *blockacb)
    acb->cancelled = 1;

    while (acb->status == -EINPROGRESS) {
-        aio_poll(bdrv_get_aio_context(acb->common.bs), true);
+        qemu_aio_wait();
    }

    qemu_aio_release(acb);
@@ -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;
 }

 /*
@@ -571,19 +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 = aio_bh_new(bdrv_get_aio_context(acb->common.bs),
-                         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,
@@ -678,16 +763,13 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
    }

    if (r < 0) {
-        goto failed_completion;
+        goto failed;
    }

    return &acb->common;

-failed_completion:
-    rbd_aio_release(c);
 failed:
    g_free(rcb);
-    qemu_vfree(acb->bounce);
    qemu_aio_release(acb);
    return NULL;
 }
@@ -904,22 +986,18 @@ static BlockDriverAIOCB* qemu_rbd_aio_discard(BlockDriverState *bs,
 }
 #endif

-static QemuOptsList qemu_rbd_create_opts = {
-    .name = "rbd-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(qemu_rbd_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        {
-            .name = BLOCK_OPT_CLUSTER_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "RBD object size"
-        },
-        { /* end of list */ }
-    }
+static QEMUOptionParameter qemu_rbd_create_options[] = {
+    {
+     .name = BLOCK_OPT_SIZE,
+     .type = OPT_SIZE,
+     .help = "Virtual disk size"
+    },
+    {
+     .name = BLOCK_OPT_CLUSTER_SIZE,
+     .type = OPT_SIZE,
+     .help = "RBD object size"
+    },
+    {NULL}
 };

 static BlockDriver bdrv_rbd = {
@@ -931,7 +1009,7 @@ static BlockDriver bdrv_rbd = {
    .bdrv_create        = qemu_rbd_create,
    .bdrv_has_zero_init = bdrv_has_zero_init_1,
    .bdrv_get_info      = qemu_rbd_getinfo,
-    .create_opts        = &qemu_rbd_create_opts,
+    .create_options     = qemu_rbd_create_options,
    .bdrv_getlength     = qemu_rbd_getlength,
    .bdrv_truncate      = qemu_rbd_truncate,
    .protocol_name      = "rbd",
@@ -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
@@ -236,10 +218,6 @@ int bdrv_snapshot_delete(BlockDriverState *bs,
        error_setg(errp, "snapshot_id and name are both NULL");
        return -EINVAL;
    }
-
-    /* drain all pending i/o before deleting snapshot */
-    bdrv_drain_all();
-
    if (drv->bdrv_snapshot_delete) {
        return drv->bdrv_snapshot_delete(bs, snapshot_id, name, errp);
    }
@@ -287,71 +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;
-}
@@ -106,59 +106,30 @@ static void ssh_state_free(BDRVSSHState *s)
    }
 }

-static void GCC_FMT_ATTR(3, 4)
-session_error_setg(Error **errp, BDRVSSHState *s, const char *fs, ...)
+/* Wrappers around error_report which make sure to dump as much
+ * information from libssh2 as possible.
+ */
+static void GCC_FMT_ATTR(2, 3)
+session_error_report(BDRVSSHState *s, const char *fs, ...)
 {
    va_list args;
-    char *msg;

    va_start(args, fs);
-    msg = g_strdup_vprintf(fs, args);
-    va_end(args);
+    error_vprintf(fs, args);

-    if (s->session) {
+    if ((s)->session) {
        char *ssh_err;
        int ssh_err_code;

+        libssh2_session_last_error((s)->session, &ssh_err, NULL, 0);
        /* This is not an errno.  See <libssh2.h>. */
-        ssh_err_code = libssh2_session_last_error(s->session,
-                                                  &ssh_err, NULL, 0);
-        error_setg(errp, "%s: %s (libssh2 error code: %d)",
-                   msg, ssh_err, ssh_err_code);
-    } else {
-        error_setg(errp, "%s", msg);
+        ssh_err_code = libssh2_session_last_errno((s)->session);
+
+        error_printf(": %s (libssh2 error code: %d)", ssh_err, ssh_err_code);
    }
-    g_free(msg);
-}

-static void GCC_FMT_ATTR(3, 4)
-sftp_error_setg(Error **errp, BDRVSSHState *s, const char *fs, ...)
-{
-    va_list args;
-    char *msg;
-
-    va_start(args, fs);
-    msg = g_strdup_vprintf(fs, args);
    va_end(args);
-
-    if (s->sftp) {
-        char *ssh_err;
-        int ssh_err_code;
-        unsigned long sftp_err_code;
-
-        /* This is not an errno.  See <libssh2.h>. */
-        ssh_err_code = libssh2_session_last_error(s->session,
-                                                  &ssh_err, NULL, 0);
-        /* See <libssh2_sftp.h>. */
-        sftp_err_code = libssh2_sftp_last_error((s)->sftp);
-
-        error_setg(errp,
-                   "%s: %s (libssh2 error code: %d, sftp error code: %lu)",
-                   msg, ssh_err, ssh_err_code, sftp_err_code);
-    } else {
-        error_setg(errp, "%s", msg);
-    }
-    g_free(msg);
+    error_printf("\n");
 }

 static void GCC_FMT_ATTR(2, 3)
@@ -174,9 +145,9 @@ sftp_error_report(BDRVSSHState *s, const char *fs, ...)
        int ssh_err_code;
        unsigned long sftp_err_code;

+        libssh2_session_last_error((s)->session, &ssh_err, NULL, 0);
        /* This is not an errno.  See <libssh2.h>. */
-        ssh_err_code = libssh2_session_last_error(s->session,
-                                                  &ssh_err, NULL, 0);
+        ssh_err_code = libssh2_session_last_errno((s)->session);
        /* See <libssh2_sftp.h>. */
        sftp_err_code = libssh2_sftp_last_error((s)->sftp);

@@ -272,7 +243,7 @@ static void ssh_parse_filename(const char *filename, QDict *options,
 }

 static int check_host_key_knownhosts(BDRVSSHState *s,
-                                     const char *host, int port, Error **errp)
+                                     const char *host, int port)
 {
    const char *home;
    char *knh_file = NULL;
@@ -286,15 +257,14 @@ static int check_host_key_knownhosts(BDRVSSHState *s,
    hostkey = libssh2_session_hostkey(s->session, &len, &type);
    if (!hostkey) {
        ret = -EINVAL;
-        session_error_setg(errp, s, "failed to read remote host key");
+        session_error_report(s, "failed to read remote host key");
        goto out;
    }

    knh = libssh2_knownhost_init(s->session);
    if (!knh) {
        ret = -EINVAL;
-        session_error_setg(errp, s,
-                           "failed to initialize known hosts support");
+        session_error_report(s, "failed to initialize known hosts support");
        goto out;
    }

@@ -319,23 +289,21 @@ static int check_host_key_knownhosts(BDRVSSHState *s,
        break;
    case LIBSSH2_KNOWNHOST_CHECK_MISMATCH:
        ret = -EINVAL;
-        session_error_setg(errp, s,
-                      "host key does not match the one in known_hosts"
-                      " (found key %s)", found->key);
+        session_error_report(s, "host key does not match the one in known_hosts (found key %s)",
+                             found->key);
        goto out;
    case LIBSSH2_KNOWNHOST_CHECK_NOTFOUND:
        ret = -EINVAL;
-        session_error_setg(errp, s, "no host key was found in known_hosts");
+        session_error_report(s, "no host key was found in known_hosts");
        goto out;
    case LIBSSH2_KNOWNHOST_CHECK_FAILURE:
        ret = -EINVAL;
-        session_error_setg(errp, s,
-                      "failure matching the host key with known_hosts");
+        session_error_report(s, "failure matching the host key with known_hosts");
        goto out;
    default:
        ret = -EINVAL;
-        session_error_setg(errp, s, "unknown error matching the host key"
-                      " with known_hosts (%d)", r);
+        session_error_report(s, "unknown error matching the host key with known_hosts (%d)",
+                             r);
        goto out;
    }

@@ -390,20 +358,20 @@ static int compare_fingerprint(const unsigned char *fingerprint, size_t len,

 static int
 check_host_key_hash(BDRVSSHState *s, const char *hash,
-                    int hash_type, size_t fingerprint_len, Error **errp)
+                    int hash_type, size_t fingerprint_len)
 {
    const char *fingerprint;

    fingerprint = libssh2_hostkey_hash(s->session, hash_type);
    if (!fingerprint) {
-        session_error_setg(errp, s, "failed to read remote host key");
+        session_error_report(s, "failed to read remote host key");
        return -EINVAL;
    }

    if(compare_fingerprint((unsigned char *) fingerprint, fingerprint_len,
                           hash) != 0) {
-        error_setg(errp, "remote host key does not match host_key_check '%s'",
-                   hash);
+        error_report("remote host key does not match host_key_check '%s'",
+                     hash);
        return -EPERM;
    }

@@ -411,7 +379,7 @@ check_host_key_hash(BDRVSSHState *s, const char *hash,
 }

 static int check_host_key(BDRVSSHState *s, const char *host, int port,
-                          const char *host_key_check, Error **errp)
+                          const char *host_key_check)
 {
    /* host_key_check=no */
    if (strcmp(host_key_check, "no") == 0) {
@@ -421,25 +389,25 @@ static int check_host_key(BDRVSSHState *s, const char *host, int port,
    /* host_key_check=md5:xx:yy:zz:... */
    if (strncmp(host_key_check, "md5:", 4) == 0) {
        return check_host_key_hash(s, &host_key_check[4],
-                                   LIBSSH2_HOSTKEY_HASH_MD5, 16, errp);
+                                   LIBSSH2_HOSTKEY_HASH_MD5, 16);
    }

    /* host_key_check=sha1:xx:yy:zz:... */
    if (strncmp(host_key_check, "sha1:", 5) == 0) {
        return check_host_key_hash(s, &host_key_check[5],
-                                   LIBSSH2_HOSTKEY_HASH_SHA1, 20, errp);
+                                   LIBSSH2_HOSTKEY_HASH_SHA1, 20);
    }

    /* host_key_check=yes */
    if (strcmp(host_key_check, "yes") == 0) {
-        return check_host_key_knownhosts(s, host, port, errp);
+        return check_host_key_knownhosts(s, host, port);
    }

-    error_setg(errp, "unknown host_key_check setting (%s)", host_key_check);
+    error_report("unknown host_key_check setting (%s)", host_key_check);
    return -EINVAL;
 }

-static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
+static int authenticate(BDRVSSHState *s, const char *user)
 {
    int r, ret;
    const char *userauthlist;
@@ -450,8 +418,7 @@ static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
    userauthlist = libssh2_userauth_list(s->session, user, strlen(user));
    if (strstr(userauthlist, "publickey") == NULL) {
        ret = -EPERM;
-        error_setg(errp,
-                "remote server does not support \"publickey\" authentication");
+        error_report("remote server does not support \"publickey\" authentication");
        goto out;
    }

@@ -459,18 +426,17 @@ static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
    agent = libssh2_agent_init(s->session);
    if (!agent) {
        ret = -EINVAL;
-        session_error_setg(errp, s, "failed to initialize ssh-agent support");
+        session_error_report(s, "failed to initialize ssh-agent support");
        goto out;
    }
    if (libssh2_agent_connect(agent)) {
        ret = -ECONNREFUSED;
-        session_error_setg(errp, s, "failed to connect to ssh-agent");
+        session_error_report(s, "failed to connect to ssh-agent");
        goto out;
    }
    if (libssh2_agent_list_identities(agent)) {
        ret = -EINVAL;
-        session_error_setg(errp, s,
-                           "failed requesting identities from ssh-agent");
+        session_error_report(s, "failed requesting identities from ssh-agent");
        goto out;
    }

@@ -481,8 +447,7 @@ static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
        }
        if (r < 0) {
            ret = -EINVAL;
-            session_error_setg(errp, s,
-                               "failed to obtain identity from ssh-agent");
+            session_error_report(s, "failed to obtain identity from ssh-agent");
            goto out;
        }
        r = libssh2_agent_userauth(agent, user, identity);
@@ -496,8 +461,8 @@ static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
    }

    ret = -EPERM;
-    error_setg(errp, "failed to authenticate using publickey authentication "
-               "and the identities held by your ssh-agent");
+    error_report("failed to authenticate using publickey authentication "
+                 "and the identities held by your ssh-agent");

 out:
    if (agent != NULL) {
@@ -511,9 +476,10 @@ static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
 }

 static int connect_to_ssh(BDRVSSHState *s, QDict *options,
-                          int ssh_flags, int creat_mode, Error **errp)
+                          int ssh_flags, int creat_mode)
 {
    int r, ret;
+    Error *err = NULL;
    const char *host, *user, *path, *host_key_check;
    int port;

@@ -532,7 +498,6 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
    } else {
        user = g_get_user_name();
        if (!user) {
-            error_setg_errno(errp, errno, "Can't get user name");
            ret = -errno;
            goto err;
        }
@@ -549,9 +514,11 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
    s->hostport = g_strdup_printf("%s:%d", host, port);

    /* Open the socket and connect. */
-    s->sock = inet_connect(s->hostport, errp);
-    if (s->sock < 0) {
+    s->sock = inet_connect(s->hostport, &err);
+    if (err != NULL) {
        ret = -errno;
+        qerror_report_err(err);
+        error_free(err);
        goto err;
    }

@@ -559,7 +526,7 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
    s->session = libssh2_session_init();
    if (!s->session) {
        ret = -EINVAL;
-        session_error_setg(errp, s, "failed to initialize libssh2 session");
+        session_error_report(s, "failed to initialize libssh2 session");
        goto err;
    }

@@ -570,18 +537,18 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
    r = libssh2_session_handshake(s->session, s->sock);
    if (r != 0) {
        ret = -EINVAL;
-        session_error_setg(errp, s, "failed to establish SSH session");
+        session_error_report(s, "failed to establish SSH session");
        goto err;
    }

    /* Check the remote host's key against known_hosts. */
-    ret = check_host_key(s, host, port, host_key_check, errp);
+    ret = check_host_key(s, host, port, host_key_check);
    if (ret < 0) {
        goto err;
    }

    /* Authenticate. */
-    ret = authenticate(s, user, errp);
+    ret = authenticate(s, user);
    if (ret < 0) {
        goto err;
    }
@@ -589,7 +556,7 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
    /* Start SFTP. */
    s->sftp = libssh2_sftp_init(s->session);
    if (!s->sftp) {
-        session_error_setg(errp, s, "failed to initialize sftp handle");
+        session_error_report(s, "failed to initialize sftp handle");
        ret = -EINVAL;
        goto err;
    }
@@ -599,14 +566,14 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
            path, ssh_flags, creat_mode);
    s->sftp_handle = libssh2_sftp_open(s->sftp, path, ssh_flags, creat_mode);
    if (!s->sftp_handle) {
-        session_error_setg(errp, s, "failed to open remote file '%s'", path);
+        session_error_report(s, "failed to open remote file '%s'", path);
        ret = -EINVAL;
        goto err;
    }

    r = libssh2_sftp_fstat(s->sftp_handle, &s->attrs);
    if (r < 0) {
-        sftp_error_setg(errp, s, "failed to read file attributes");
+        sftp_error_report(s, "failed to read file attributes");
        return -EINVAL;
    }

@@ -656,7 +623,7 @@ static int ssh_file_open(BlockDriverState *bs, QDict *options, int bdrv_flags,
    }

    /* Start up SSH. */
-    ret = connect_to_ssh(s, options, ssh_flags, 0, errp);
+    ret = connect_to_ssh(s, options, ssh_flags, 0);
    if (ret < 0) {
        goto err;
    }
@@ -675,22 +642,20 @@ static int ssh_file_open(BlockDriverState *bs, QDict *options, int bdrv_flags,
    return ret;
 }

-static QemuOptsList ssh_create_opts = {
-    .name = "ssh-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(ssh_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        { /* end of list */ }
-    }
+static QEMUOptionParameter ssh_create_options[] = {
+    {
+        .name = BLOCK_OPT_SIZE,
+        .type = OPT_SIZE,
+        .help = "Virtual disk size"
+    },
+    { NULL }
 };

-static int ssh_create(const char *filename, QemuOpts *opts, Error **errp)
+static int ssh_create(const char *filename, QEMUOptionParameter *options,
+                      Error **errp)
 {
    int r, ret;
+    Error *local_err = NULL;
    int64_t total_size = 0;
    QDict *uri_options = NULL;
    BDRVSSHState s;
@@ -700,20 +665,26 @@ static int ssh_create(const char *filename, QemuOpts *opts, Error **errp)
    ssh_state_init(&s);

    /* Get desired file size. */
-    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    while (options && options->name) {
+        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+            total_size = options->value.n;
+        }
+        options++;
+    }
    DPRINTF("total_size=%" PRIi64, total_size);

    uri_options = qdict_new();
-    r = parse_uri(filename, uri_options, errp);
+    r = parse_uri(filename, uri_options, &local_err);
    if (r < 0) {
+        qerror_report_err(local_err);
+        error_free(local_err);
        ret = r;
        goto out;
    }

    r = connect_to_ssh(&s, uri_options,
                       LIBSSH2_FXF_READ|LIBSSH2_FXF_WRITE|
-                       LIBSSH2_FXF_CREAT|LIBSSH2_FXF_TRUNC,
-                       0644, errp);
+                       LIBSSH2_FXF_CREAT|LIBSSH2_FXF_TRUNC, 0644);
    if (r < 0) {
        ret = r;
        goto out;
@@ -723,7 +694,7 @@ static int ssh_create(const char *filename, QemuOpts *opts, Error **errp)
        libssh2_sftp_seek64(s.sftp_handle, total_size-1);
        r2 = libssh2_sftp_write(s.sftp_handle, c, 1);
        if (r2 < 0) {
-            sftp_error_setg(errp, &s, "truncate failed");
+            sftp_error_report(&s, "truncate failed");
            ret = -EINVAL;
            goto out;
        }
@@ -771,7 +742,7 @@ static void restart_coroutine(void *opaque)
    qemu_coroutine_enter(co, NULL);
 }

-static coroutine_fn void set_fd_handler(BDRVSSHState *s, BlockDriverState *bs)
+static coroutine_fn void set_fd_handler(BDRVSSHState *s)
 {
    int r;
    IOHandler *rd_handler = NULL, *wr_handler = NULL;
@@ -789,26 +760,24 @@ static coroutine_fn void set_fd_handler(BDRVSSHState *s, BlockDriverState *bs)
    DPRINTF("s->sock=%d rd_handler=%p wr_handler=%p", s->sock,
            rd_handler, wr_handler);

-    aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock,
-                       rd_handler, wr_handler, co);
+    qemu_aio_set_fd_handler(s->sock, rd_handler, wr_handler, co);
 }

-static coroutine_fn void clear_fd_handler(BDRVSSHState *s,
-                                          BlockDriverState *bs)
+static coroutine_fn void clear_fd_handler(BDRVSSHState *s)
 {
    DPRINTF("s->sock=%d", s->sock);
-    aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock, NULL, NULL, NULL);
+    qemu_aio_set_fd_handler(s->sock, NULL, NULL, NULL);
 }

 /* A non-blocking call returned EAGAIN, so yield, ensuring the
 * handlers are set up so that we'll be rescheduled when there is an
 * interesting event on the socket.
 */
-static coroutine_fn void co_yield(BDRVSSHState *s, BlockDriverState *bs)
+static coroutine_fn void co_yield(BDRVSSHState *s)
 {
-    set_fd_handler(s, bs);
+    set_fd_handler(s);
    qemu_coroutine_yield();
-    clear_fd_handler(s, bs);
+    clear_fd_handler(s);
 }

 /* SFTP has a function `libssh2_sftp_seek64' which seeks to a position
@@ -838,7 +807,7 @@ static void ssh_seek(BDRVSSHState *s, int64_t offset, int flags)
    }
 }

-static coroutine_fn int ssh_read(BDRVSSHState *s, BlockDriverState *bs,
+static coroutine_fn int ssh_read(BDRVSSHState *s,
                                 int64_t offset, size_t size,
                                 QEMUIOVector *qiov)
 {
@@ -871,7 +840,7 @@ static coroutine_fn int ssh_read(BDRVSSHState *s, BlockDriverState *bs,
        DPRINTF("sftp_read returned %zd", r);

        if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
-            co_yield(s, bs);
+            co_yield(s);
            goto again;
        }
        if (r < 0) {
@@ -906,14 +875,14 @@ static coroutine_fn int ssh_co_readv(BlockDriverState *bs,
    int ret;

    qemu_co_mutex_lock(&s->lock);
-    ret = ssh_read(s, bs, sector_num * BDRV_SECTOR_SIZE,
+    ret = ssh_read(s, sector_num * BDRV_SECTOR_SIZE,
                   nb_sectors * BDRV_SECTOR_SIZE, qiov);
    qemu_co_mutex_unlock(&s->lock);

    return ret;
 }

-static int ssh_write(BDRVSSHState *s, BlockDriverState *bs,
+static int ssh_write(BDRVSSHState *s,
                     int64_t offset, size_t size,
                     QEMUIOVector *qiov)
 {
@@ -941,7 +910,7 @@ static int ssh_write(BDRVSSHState *s, BlockDriverState *bs,
        DPRINTF("sftp_write returned %zd", r);

        if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
-            co_yield(s, bs);
+            co_yield(s);
            goto again;
        }
        if (r < 0) {
@@ -960,7 +929,7 @@ static int ssh_write(BDRVSSHState *s, BlockDriverState *bs,
         */
        if (r == 0) {
            ssh_seek(s, offset + written, SSH_SEEK_WRITE|SSH_SEEK_FORCE);
-            co_yield(s, bs);
+            co_yield(s);
            goto again;
        }

@@ -988,7 +957,7 @@ static coroutine_fn int ssh_co_writev(BlockDriverState *bs,
    int ret;

    qemu_co_mutex_lock(&s->lock);
-    ret = ssh_write(s, bs, sector_num * BDRV_SECTOR_SIZE,
+    ret = ssh_write(s, sector_num * BDRV_SECTOR_SIZE,
                    nb_sectors * BDRV_SECTOR_SIZE, qiov);
    qemu_co_mutex_unlock(&s->lock);

@@ -1009,7 +978,7 @@ static void unsafe_flush_warning(BDRVSSHState *s, const char *what)

 #ifdef HAS_LIBSSH2_SFTP_FSYNC

-static coroutine_fn int ssh_flush(BDRVSSHState *s, BlockDriverState *bs)
+static coroutine_fn int ssh_flush(BDRVSSHState *s)
 {
    int r;

@@ -1017,7 +986,7 @@ static coroutine_fn int ssh_flush(BDRVSSHState *s, BlockDriverState *bs)
 again:
    r = libssh2_sftp_fsync(s->sftp_handle);
    if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
-        co_yield(s, bs);
+        co_yield(s);
        goto again;
    }
    if (r == LIBSSH2_ERROR_SFTP_PROTOCOL &&
@@ -1039,7 +1008,7 @@ static coroutine_fn int ssh_co_flush(BlockDriverState *bs)
    int ret;

    qemu_co_mutex_lock(&s->lock);
-    ret = ssh_flush(s, bs);
+    ret = ssh_flush(s);
    qemu_co_mutex_unlock(&s->lock);

    return ret;
@@ -1082,7 +1051,7 @@ static BlockDriver bdrv_ssh = {
    .bdrv_co_writev               = ssh_co_writev,
    .bdrv_getlength               = ssh_getlength,
    .bdrv_co_flush_to_disk        = ssh_co_flush,
-    .create_opts                  = &ssh_create_opts,
+    .create_options               = ssh_create_options,
 };

 static void bdrv_ssh_init(void)
@@ -32,7 +32,7 @@ typedef struct StreamBlockJob {
    RateLimit limit;
    BlockDriverState *base;
    BlockdevOnError on_error;
-    char *backing_file_str;
+    char backing_file_id[1024];
 } StreamBlockJob;

 static int coroutine_fn stream_populate(BlockDriverState *bs,
@@ -60,7 +60,7 @@ static void close_unused_images(BlockDriverState *top, BlockDriverState *base,
    /* Must assign before bdrv_delete() to prevent traversing dangling pointer
     * while we delete backing image instances.
     */
-    bdrv_set_backing_hd(top, base);
+    top->backing_hd = base;

    while (intermediate) {
        BlockDriverState *unused;
@@ -72,11 +72,9 @@ static void close_unused_images(BlockDriverState *top, BlockDriverState *base,

        unused = intermediate;
        intermediate = intermediate->backing_hd;
-        bdrv_set_backing_hd(unused, NULL);
+        unused->backing_hd = NULL;
        bdrv_unref(unused);
    }
-
-    bdrv_refresh_limits(top, NULL);
 }

 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);
@@ -159,14 +152,14 @@ wait:
            BlockErrorAction action =
                block_job_error_action(&s->common, s->common.bs, s->on_error,
                                       true, -ret);
-            if (action == BLOCK_ERROR_ACTION_STOP) {
+            if (action == BDRV_ACTION_STOP) {
                n = 0;
                continue;
            }
            if (error == 0) {
                error = ret;
            }
-            if (action == BLOCK_ERROR_ACTION_REPORT) {
+            if (action == BDRV_ACTION_REPORT) {
                break;
            }
        }
@@ -186,7 +179,7 @@ wait:
    if (!block_job_is_cancelled(&s->common) && sector_num == end && ret == 0) {
        const char *base_id = NULL, *base_fmt = NULL;
        if (base) {
-            base_id = s->backing_file_str;
+            base_id = s->backing_file_id;
            if (base->drv) {
                base_fmt = base->drv->format_name;
            }
@@ -196,7 +189,6 @@ wait:
    }

    qemu_vfree(buf);
-    g_free(s->backing_file_str);
    block_job_completed(&s->common, ret);
 }

@@ -218,7 +210,7 @@ static const BlockJobDriver stream_job_driver = {
 };

 void stream_start(BlockDriverState *bs, BlockDriverState *base,
-                  const char *backing_file_str, int64_t speed,
+                  const char *base_id, int64_t speed,
                  BlockdevOnError on_error,
                  BlockDriverCompletionFunc *cb,
                  void *opaque, Error **errp)
@@ -238,7 +230,9 @@ void stream_start(BlockDriverState *bs, BlockDriverState *base,
    }

    s->base = base;
-    s->backing_file_str = g_strdup(backing_file_str);
+    if (base_id) {
+        pstrcpy(s->backing_file_id, sizeof(s->backing_file_id), base_id);
+    }

    s->on_error = on_error;
    s->common.co = qemu_coroutine_create(stream_run);
@@ -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
@@ -53,13 +53,6 @@
 #include "block/block_int.h"
 #include "qemu/module.h"
 #include "migration/migration.h"
-#ifdef __linux__
-#include <linux/fs.h>
-#include <sys/ioctl.h>
-#ifndef FS_NOCOW_FL
-#define FS_NOCOW_FL                     0x00800000 /* Do not cow file */
-#endif
-#endif

 #if defined(CONFIG_UUID)
 #include <uuid/uuid.h>
@@ -246,6 +239,7 @@ static void vdi_header_to_le(VdiHeader *header)
    cpu_to_le32s(&header->block_extra);
    cpu_to_le32s(&header->blocks_in_image);
    cpu_to_le32s(&header->blocks_allocated);
+    cpu_to_le32s(&header->blocks_allocated);
    uuid_convert(header->uuid_image);
    uuid_convert(header->uuid_last_snap);
    uuid_convert(header->uuid_link);
@@ -342,7 +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;
 }

@@ -397,9 +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;
    }
@@ -414,57 +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 %08" PRIx32
-                   ")", 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 %" PRIu32 ".%" PRIu32
-                   ")", 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%" PRIx32 ")", 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%"
-                   PRIx32 ")", 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 %" PRIu32
-                   " 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 %" PRIu32
-                   " 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;
    }
@@ -679,7 +662,8 @@ static int vdi_co_write(BlockDriverState *bs,
    return ret;
 }

-static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
+static int vdi_create(const char *filename, QEMUOptionParameter *options,
+                      Error **errp)
 {
    int fd;
    int result = 0;
@@ -690,30 +674,35 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
    VdiHeader header;
    size_t i;
    size_t bmap_size;
-    bool nocow = false;

    logout("\n");

    /* Read out options. */
-    bytes = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    while (options && options->name) {
+        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+            bytes = options->value.n;
 #if defined(CONFIG_VDI_BLOCK_SIZE)
-    /* TODO: Additional checks (SECTOR_SIZE * 2^n, ...). */
-    block_size = qemu_opt_get_size_del(opts,
-                                       BLOCK_OPT_CLUSTER_SIZE,
-                                       DEFAULT_CLUSTER_SIZE);
+        } else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) {
+            if (options->value.n) {
+                /* TODO: Additional checks (SECTOR_SIZE * 2^n, ...). */
+                block_size = options->value.n;
+            }
 #endif
 #if defined(CONFIG_VDI_STATIC_IMAGE)
-    if (qemu_opt_get_bool_del(opts, BLOCK_OPT_STATIC, false)) {
-        image_type = VDI_TYPE_STATIC;
-    }
+        } else if (!strcmp(options->name, BLOCK_OPT_STATIC)) {
+            if (options->value.n) {
+                image_type = VDI_TYPE_STATIC;
+            }
 #endif
-    nocow = qemu_opt_get_bool_del(opts, BLOCK_OPT_NOCOW, false);
+        }
+        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;
    }

@@ -725,21 +714,6 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
        goto exit;
    }

-    if (nocow) {
-#ifdef __linux__
-        /* Set NOCOW flag to solve performance issue on fs like btrfs.
-         * This is an optimisation. The FS_IOC_SETFLAGS ioctl return value will
-         * be ignored since any failure of this operation should not block the
-         * left work.
-         */
-        int attr;
-        if (ioctl(fd, FS_IOC_GETFLAGS, &attr) == 0) {
-            attr |= FS_NOCOW_FL;
-            ioctl(fd, FS_IOC_SETFLAGS, &attr);
-        }
-#endif
-    }
-
    /* We need enough blocks to store the given disk size,
       so always round up. */
    blocks = (bytes + block_size - 1) / block_size;
@@ -771,7 +745,6 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
    vdi_header_to_le(&header);
    if (write(fd, &header, sizeof(header)) < 0) {
        result = -errno;
-        goto close_and_exit;
    }

    if (bmap_size > 0) {
@@ -785,8 +758,6 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
        }
        if (write(fd, bmap, bmap_size) < 0) {
            result = -errno;
-            g_free(bmap);
-            goto close_and_exit;
        }
        g_free(bmap);
    }
@@ -794,12 +765,10 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
    if (image_type == VDI_TYPE_STATIC) {
        if (ftruncate(fd, sizeof(header) + bmap_size + blocks * block_size)) {
            result = -errno;
-            goto close_and_exit;
        }
    }

-close_and_exit:
-    if ((close(fd) < 0) && !result) {
+    if (close(fd) < 0) {
        result = -errno;
    }

@@ -817,39 +786,29 @@ static void vdi_close(BlockDriverState *bs)
    error_free(s->migration_blocker);
 }

-static QemuOptsList vdi_create_opts = {
-    .name = "vdi-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(vdi_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
+static QEMUOptionParameter vdi_create_options[] = {
+    {
+        .name = BLOCK_OPT_SIZE,
+        .type = OPT_SIZE,
+        .help = "Virtual disk size"
+    },
 #if defined(CONFIG_VDI_BLOCK_SIZE)
-        {
-            .name = BLOCK_OPT_CLUSTER_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "VDI cluster (block) size",
-            .def_value_str = stringify(DEFAULT_CLUSTER_SIZE)
-        },
+    {
+        .name = BLOCK_OPT_CLUSTER_SIZE,
+        .type = OPT_SIZE,
+        .help = "VDI cluster (block) size",
+        .value = { .n = DEFAULT_CLUSTER_SIZE },
+    },
 #endif
 #if defined(CONFIG_VDI_STATIC_IMAGE)
-        {
-            .name = BLOCK_OPT_STATIC,
-            .type = QEMU_OPT_BOOL,
-            .help = "VDI static (pre-allocated) image",
-            .def_value_str = "off"
-        },
+    {
+        .name = BLOCK_OPT_STATIC,
+        .type = OPT_FLAG,
+        .help = "VDI static (pre-allocated) image"
+    },
 #endif
-        {
-            .name = BLOCK_OPT_NOCOW,
-            .type = QEMU_OPT_BOOL,
-            .help = "Turn off copy-on-write (valid only on btrfs)"
-        },
-        /* TODO: An additional option to set UUID values might be useful. */
-        { /* end of list */ }
-    }
+    /* TODO: An additional option to set UUID values might be useful. */
+    { NULL }
 };

 static BlockDriver bdrv_vdi = {
@@ -871,7 +830,7 @@ static BlockDriver bdrv_vdi = {

    .bdrv_get_info = vdi_get_info,

-    .create_opts = &vdi_create_opts,
+    .create_options = vdi_create_options,
    .bdrv_check = vdi_check,
 };

@@ -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
@@ -473,29 +473,27 @@ static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s,
        } else if (h2_seq > h1_seq) {
            s->curr_header = 1;
        } else {
-            /* The Microsoft Disk2VHD tool will create 2 identical
-             * headers, with identical sequence numbers.  If the headers are
-             * identical, don't consider the file corrupt */
-            if (!memcmp(header1, header2, sizeof(VHDXHeader))) {
-                s->curr_header = 0;
-            } else {
-                goto fail;
-            }
+            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;
 }


@@ -888,7 +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;
@@ -911,14 +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;
    }
@@ -1054,18 +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)
@@ -1723,7 +1708,8 @@ exit:
 *    .---- ~ ----------- ~ ------------ ~ ---------------- ~ -----------.
 *   1MB
 */
-static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
+static int vhdx_create(const char *filename, QEMUOptionParameter *options,
+                       Error **errp)
 {
    int ret = 0;
    uint64_t image_size = (uint64_t) 2 * GiB;
@@ -1736,15 +1722,24 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
    gunichar2 *creator = NULL;
    glong creator_items;
    BlockDriverState *bs;
-    char *type = NULL;
+    const char *type = NULL;
    VHDXImageType image_type;
    Error *local_err = NULL;

-    image_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
-    log_size = qemu_opt_get_size_del(opts, VHDX_BLOCK_OPT_LOG_SIZE, 0);
-    block_size = qemu_opt_get_size_del(opts, VHDX_BLOCK_OPT_BLOCK_SIZE, 0);
-    type = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT);
-    use_zero_blocks = qemu_opt_get_bool_del(opts, VHDX_BLOCK_OPT_ZERO, false);
+    while (options && options->name) {
+        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+            image_size = options->value.n;
+        } else if (!strcmp(options->name, VHDX_BLOCK_OPT_LOG_SIZE)) {
+            log_size = options->value.n;
+        } else if (!strcmp(options->name, VHDX_BLOCK_OPT_BLOCK_SIZE)) {
+            block_size = options->value.n;
+        } else if (!strcmp(options->name, BLOCK_OPT_SUBFMT)) {
+            type = options->value.s;
+        } else if (!strcmp(options->name, VHDX_BLOCK_OPT_ZERO)) {
+            use_zero_blocks = options->value.n != 0;
+        }
+        options++;
+    }

    if (image_size > VHDX_MAX_IMAGE_SIZE) {
        error_setg_errno(errp, EINVAL, "Image size too large; max of 64TB");
@@ -1753,7 +1748,7 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
    }

    if (type == NULL) {
-        type = g_strdup("dynamic");
+        type = "dynamic";
    }

    if (!strcmp(type, "dynamic")) {
@@ -1793,15 +1788,13 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
    block_size = block_size > VHDX_BLOCK_SIZE_MAX ? VHDX_BLOCK_SIZE_MAX :
                                                    block_size;

-    ret = bdrv_create_file(filename, opts, &local_err);
+    ret = bdrv_create_file(filename, options, &local_err);
    if (ret < 0) {
        error_propagate(errp, local_err);
        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;
@@ -1814,13 +1807,13 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
    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;
        }
@@ -1853,64 +1846,41 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
 delete_and_exit:
    bdrv_unref(bs);
 exit:
-    g_free(type);
    g_free(creator);
    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 QemuOptsList vhdx_create_opts = {
-    .name = "vhdx-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(vhdx_create_opts.head),
-    .desc = {
-        {
-           .name = BLOCK_OPT_SIZE,
-           .type = QEMU_OPT_SIZE,
-           .help = "Virtual disk size; max of 64TB."
-       },
-       {
-           .name = VHDX_BLOCK_OPT_LOG_SIZE,
-           .type = QEMU_OPT_SIZE,
-           .def_value_str = stringify(DEFAULT_LOG_SIZE),
-           .help = "Log size; min 1MB."
-       },
-       {
-           .name = VHDX_BLOCK_OPT_BLOCK_SIZE,
-           .type = QEMU_OPT_SIZE,
-           .def_value_str = stringify(0),
-           .help = "Block Size; min 1MB, max 256MB. " \
-                   "0 means auto-calculate based on image size."
-       },
-       {
-           .name = BLOCK_OPT_SUBFMT,
-           .type = QEMU_OPT_STRING,
-           .help = "VHDX format type, can be either 'dynamic' or 'fixed'. "\
-                   "Default is 'dynamic'."
-       },
-       {
-           .name = VHDX_BLOCK_OPT_ZERO,
-           .type = QEMU_OPT_BOOL,
-           .help = "Force use of payload blocks of type 'ZERO'.  Non-standard."
-       },
-       { NULL }
-    }
+static QEMUOptionParameter vhdx_create_options[] = {
+    {
+        .name = BLOCK_OPT_SIZE,
+        .type = OPT_SIZE,
+        .help = "Virtual disk size; max of 64TB."
+    },
+    {
+        .name = VHDX_BLOCK_OPT_LOG_SIZE,
+        .type = OPT_SIZE,
+        .value.n = 1 * MiB,
+        .help = "Log size; min 1MB."
+    },
+    {
+        .name = VHDX_BLOCK_OPT_BLOCK_SIZE,
+        .type = OPT_SIZE,
+        .value.n = 0,
+        .help = "Block Size; min 1MB, max 256MB. " \
+                "0 means auto-calculate based on image size."
+    },
+    {
+        .name = BLOCK_OPT_SUBFMT,
+        .type = OPT_STRING,
+        .help = "VHDX format type, can be either 'dynamic' or 'fixed'. "\
+                "Default is 'dynamic'."
+    },
+    {
+        .name = VHDX_BLOCK_OPT_ZERO,
+        .type = OPT_FLAG,
+        .help = "Force use of payload blocks of type 'ZERO'.  Non-standard."
+    },
+    { NULL }
 };

 static BlockDriver bdrv_vhdx = {
@@ -1923,10 +1893,8 @@ 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_opts            = &vhdx_create_opts,
+    .create_options         = vhdx_create_options,
 };

 static void bdrv_vhdx_init(void)
@@ -23,7 +23,6 @@
 #define GiB            (MiB * 1024)
 #define TiB ((uint64_t) GiB * 1024)

-#define DEFAULT_LOG_SIZE 1048576 /* 1MiB */
 /* Structures and fields present in the VHDX file */

 /* The header section has the following blocks,
@@ -62,7 +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
@@ -239,7 +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 ---- */
@@ -248,7 +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;
@@ -395,8 +394,6 @@ typedef struct BDRVVHDXState {

    Error *migration_blocker;

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

@@ -411,8 +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);
@@ -262,7 +262,7 @@ static uint32_t vmdk_read_cid(BlockDriverState *bs, int parent)
    p_name = strstr(desc, cid_str);
    if (p_name != NULL) {
        p_name += cid_str_size;
-        sscanf(p_name, "%" SCNx32, &cid);
+        sscanf(p_name, "%x", &cid);
    }

    return cid;
@@ -290,7 +290,7 @@ static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid)
    p_name = strstr(desc, "CID");
    if (p_name != NULL) {
        p_name += sizeof("CID");
-        snprintf(p_name, sizeof(desc) - (p_name - desc), "%" PRIx32 "\n", cid);
+        snprintf(p_name, sizeof(desc) - (p_name - desc), "%x\n", cid);
        pstrcat(desc, sizeof(desc), tmp_desc);
    }

@@ -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 %" PRId32,
+        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;
    }

@@ -669,14 +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 %" PRId64 " bytes",
-                   (int64_t)(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,
@@ -691,10 +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;
@@ -735,12 +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);
@@ -749,8 +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;
    }
 }
@@ -787,14 +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;
        }

@@ -807,9 +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;
        }
@@ -826,14 +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;
            }
@@ -856,16 +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") &&
@@ -881,37 +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) {
@@ -926,32 +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 void vmdk_refresh_limits(BlockDriverState *bs, Error **errp)
-{
-    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);
-        }
-    }
-}
-
 static int get_whole_cluster(BlockDriverState *bs,
                VmdkExtent *extent,
                uint64_t cluster_offset,
@@ -1183,7 +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;
        }

@@ -1386,8 +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;
@@ -1494,23 +1417,9 @@ static coroutine_fn int vmdk_co_write(BlockDriverState *bs, int64_t sector_num,
    return ret;
 }

-static int vmdk_write_compressed(BlockDriverState *bs,
-                                 int64_t sector_num,
-                                 const uint8_t *buf,
-                                 int nb_sectors)
-{
-    BDRVVmdkState *s = bs->opaque;
-    if (s->num_extents == 1 && s->extents[0].compressed) {
-        return vmdk_write(bs, sector_num, buf, nb_sectors, false, false);
-    } else {
-        return -ENOTSUP;
-    }
-}
-
 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;
@@ -1526,35 +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,
-                              QemuOpts *opts, Error **errp)
+                              bool flat, bool compress, bool zeroed_grain)
 {
    int ret, i;
-    BlockDriverState *bs = NULL;
+    int fd = 0;
    VMDK4Header header;
-    Error *local_err = NULL;
-    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, opts, &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;
    }
@@ -1565,23 +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);
@@ -1601,55 +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;
 }

@@ -1693,20 +1584,19 @@ static int filename_decompose(const char *filename, char *path, char *prefix,
    return VMDK_OK;
 }

-static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
+static int vmdk_create(const char *filename, QEMUOptionParameter *options,
+                       Error **errp)
 {
-    int idx = 0;
-    BlockDriverState *new_bs = NULL;
-    Error *local_err = NULL;
-    char *desc = NULL;
+    int fd, idx = 0;
+    char desc[BUF_SIZE];
    int64_t total_size = 0, filesize;
-    char *adapter_type = NULL;
-    char *backing_file = NULL;
-    char *fmt = NULL;
+    const char *adapter_type = NULL;
+    const char *backing_file = NULL;
+    const char *fmt = NULL;
    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;
@@ -1714,12 +1604,11 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
    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"
-        "CID=%" PRIx32 "\n"
-        "parentCID=%" PRIx32 "\n"
+        "CID=%x\n"
+        "parentCID=%x\n"
        "createType=\"%s\"\n"
        "%s"
        "\n"
@@ -1731,37 +1620,38 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
        "\n"
        "ddb.virtualHWVersion = \"%d\"\n"
        "ddb.geometry.cylinders = \"%" PRId64 "\"\n"
-        "ddb.geometry.heads = \"%" PRIu32 "\"\n"
+        "ddb.geometry.heads = \"%d\"\n"
        "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 */
-    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
-    adapter_type = qemu_opt_get_del(opts, BLOCK_OPT_ADAPTER_TYPE);
-    backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
-    if (qemu_opt_get_bool_del(opts, BLOCK_OPT_COMPAT6, false)) {
-        flags |= BLOCK_FLAG_COMPAT6;
+    while (options && options->name) {
+        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+            total_size = options->value.n;
+        } else if (!strcmp(options->name, BLOCK_OPT_ADAPTER_TYPE)) {
+            adapter_type = options->value.s;
+        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
+            backing_file = options->value.s;
+        } else if (!strcmp(options->name, BLOCK_OPT_COMPAT6)) {
+            flags |= options->value.n ? BLOCK_FLAG_COMPAT6 : 0;
+        } else if (!strcmp(options->name, BLOCK_OPT_SUBFMT)) {
+            fmt = options->value.s;
+        } else if (!strcmp(options->name, BLOCK_OPT_ZEROED_GRAIN)) {
+            zeroed_grain |= options->value.n;
+        }
+        options++;
    }
-    fmt = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT);
-    if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ZEROED_GRAIN, false)) {
-        zeroed_grain = true;
-    }
-
    if (!adapter_type) {
-        adapter_type = g_strdup("ide");
+        adapter_type = "ide";
    } else if (strcmp(adapter_type, "ide") &&
               strcmp(adapter_type, "buslogic") &&
               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
@@ -1770,15 +1660,14 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
    }
    if (!fmt) {
        /* Default format to monolithicSparse */
-        fmt = g_strdup("monolithicSparse");
+        fmt = "monolithicSparse";
    } else if (strcmp(fmt, "monolithicFlat") &&
               strcmp(fmt, "monolithicSparse") &&
               strcmp(fmt, "twoGbMaxExtentSparse") &&
               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"));
@@ -1786,31 +1675,28 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
             strcmp(fmt, "twoGbMaxExtentFlat"));
    compress = !strcmp(fmt, "streamOptimized");
    if (flat) {
-        desc_extent_line = "RW %" PRId64 " FLAT \"%s\" 0\n";
+        desc_extent_line = "RW %lld FLAT \"%s\" 0\n";
    } else {
-        desc_extent_line = "RW %" PRId64 " SPARSE \"%s\"\n";
+        desc_extent_line = "RW %lld SPARSE \"%s\"\n";
    }
    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);
@@ -1843,69 +1729,51 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
                path, desc_filename);

        if (vmdk_create_extent(ext_filename, size,
-                               flat, compress, zeroed_grain, opts, 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,
-                           (uint32_t)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, opts, &local_err);
-        if (ret < 0) {
-            error_propagate(errp, local_err);
-            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_propagate(errp, local_err);
+    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(adapter_type);
-    g_free(backing_file);
-    g_free(fmt);
-    g_free(desc);
-    g_string_free(ext_desc_lines, true);
+    qemu_close(fd);
    return ret;
 }

@@ -1993,53 +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;
@@ -2071,88 +1892,41 @@ static ImageInfoSpecific *vmdk_get_specific_info(BlockDriverState *bs)
    return spec_info;
 }

-static int vmdk_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
-{
-    int i;
-    BDRVVmdkState *s = bs->opaque;
-    assert(s->num_extents);
-    bdi->needs_compressed_writes = s->extents[0].compressed;
-    if (!s->extents[0].flat) {
-        bdi->cluster_size = s->extents[0].cluster_sectors << BDRV_SECTOR_BITS;
-    }
-    /* See if we have multiple extents but they have different cases */
-    for (i = 1; i < s->num_extents; i++) {
-        if (bdi->needs_compressed_writes != s->extents[i].compressed ||
-            (bdi->cluster_size && bdi->cluster_size !=
-                s->extents[i].cluster_sectors << BDRV_SECTOR_BITS)) {
-            return -ENOTSUP;
-        }
-    }
-    return 0;
-}
-
-static void vmdk_detach_aio_context(BlockDriverState *bs)
-{
-    BDRVVmdkState *s = bs->opaque;
-    int i;
-
-    for (i = 0; i < s->num_extents; i++) {
-        bdrv_detach_aio_context(s->extents[i].file);
-    }
-}
-
-static void vmdk_attach_aio_context(BlockDriverState *bs,
-                                    AioContext *new_context)
-{
-    BDRVVmdkState *s = bs->opaque;
-    int i;
-
-    for (i = 0; i < s->num_extents; i++) {
-        bdrv_attach_aio_context(s->extents[i].file, new_context);
-    }
-}
-
-static QemuOptsList vmdk_create_opts = {
-    .name = "vmdk-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(vmdk_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        {
-            .name = BLOCK_OPT_ADAPTER_TYPE,
-            .type = QEMU_OPT_STRING,
-            .help = "Virtual adapter type, can be one of "
-                    "ide (default), lsilogic, buslogic or legacyESX"
-        },
-        {
-            .name = BLOCK_OPT_BACKING_FILE,
-            .type = QEMU_OPT_STRING,
-            .help = "File name of a base image"
-        },
-        {
-            .name = BLOCK_OPT_COMPAT6,
-            .type = QEMU_OPT_BOOL,
-            .help = "VMDK version 6 image",
-            .def_value_str = "off"
-        },
-        {
-            .name = BLOCK_OPT_SUBFMT,
-            .type = QEMU_OPT_STRING,
-            .help =
-                "VMDK flat extent format, can be one of "
-                "{monolithicSparse (default) | monolithicFlat | twoGbMaxExtentSparse | twoGbMaxExtentFlat | streamOptimized} "
-        },
-        {
-            .name = BLOCK_OPT_ZEROED_GRAIN,
-            .type = QEMU_OPT_BOOL,
-            .help = "Enable efficient zero writes "
-                    "using the zeroed-grain GTE feature"
-        },
-        { /* end of list */ }
-    }
+static QEMUOptionParameter vmdk_create_options[] = {
+    {
+        .name = BLOCK_OPT_SIZE,
+        .type = OPT_SIZE,
+        .help = "Virtual disk size"
+    },
+    {
+        .name = BLOCK_OPT_ADAPTER_TYPE,
+        .type = OPT_STRING,
+        .help = "Virtual adapter type, can be one of "
+                "ide (default), lsilogic, buslogic or legacyESX"
+    },
+    {
+        .name = BLOCK_OPT_BACKING_FILE,
+        .type = OPT_STRING,
+        .help = "File name of a base image"
+    },
+    {
+        .name = BLOCK_OPT_COMPAT6,
+        .type = OPT_FLAG,
+        .help = "VMDK version 6 image"
+    },
+    {
+        .name = BLOCK_OPT_SUBFMT,
+        .type = OPT_STRING,
+        .help =
+            "VMDK flat extent format, can be one of "
+            "{monolithicSparse (default) | monolithicFlat | twoGbMaxExtentSparse | twoGbMaxExtentFlat | streamOptimized} "
+    },
+    {
+        .name = BLOCK_OPT_ZEROED_GRAIN,
+        .type = OPT_FLAG,
+        .help = "Enable efficient zero writes using the zeroed-grain GTE feature"
+    },
+    { NULL }
 };

 static BlockDriver bdrv_vmdk = {
@@ -2160,11 +1934,9 @@ 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,
-    .bdrv_write_compressed        = vmdk_write_compressed,
    .bdrv_co_write_zeroes         = vmdk_co_write_zeroes,
    .bdrv_close                   = vmdk_close,
    .bdrv_create                  = vmdk_create,
@@ -2173,13 +1945,8 @@ 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,
-    .bdrv_get_info                = vmdk_get_info,
-    .bdrv_detach_aio_context      = vmdk_detach_aio_context,
-    .bdrv_attach_aio_context      = vmdk_attach_aio_context,

-    .supports_backing             = true,
-    .create_opts                  = &vmdk_create_opts,
+    .create_options               = vmdk_create_options,
 };

 static void bdrv_vmdk_init(void)
@@ -29,13 +29,6 @@
 #if defined(CONFIG_UUID)
 #include <uuid/uuid.h>
 #endif
-#ifdef __linux__
-#include <linux/fs.h>
-#include <sys/ioctl.h>
-#ifndef FS_NOCOW_FL
-#define FS_NOCOW_FL                     0x00800000 /* Do not cow file */
-#endif
-#endif

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

@@ -200,8 +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;
@@ -487,19 +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)
 {
@@ -745,11 +724,12 @@ static int create_fixed_disk(int fd, uint8_t *buf, int64_t total_size)
    return ret;
 }

-static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
+static int vpc_create(const char *filename, QEMUOptionParameter *options,
+                      Error **errp)
 {
    uint8_t buf[1024];
    VHDFooter *footer = (VHDFooter *) buf;
-    char *disk_type_param;
+    QEMUOptionParameter *disk_type_param;
    int fd, i;
    uint16_t cyls = 0;
    uint8_t heads = 0;
@@ -758,45 +738,27 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
    int64_t total_size;
    int disk_type;
    int ret = -EIO;
-    bool nocow = false;

    /* Read out options */
-    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
-    disk_type_param = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT);
-    if (disk_type_param) {
-        if (!strcmp(disk_type_param, "dynamic")) {
+    total_size = get_option_parameter(options, BLOCK_OPT_SIZE)->value.n;
+
+    disk_type_param = get_option_parameter(options, BLOCK_OPT_SUBFMT);
+    if (disk_type_param && disk_type_param->value.s) {
+        if (!strcmp(disk_type_param->value.s, "dynamic")) {
            disk_type = VHD_DYNAMIC;
-        } else if (!strcmp(disk_type_param, "fixed")) {
+        } else if (!strcmp(disk_type_param->value.s, "fixed")) {
            disk_type = VHD_FIXED;
        } else {
-            ret = -EINVAL;
-            goto out;
+            return -EINVAL;
        }
    } else {
        disk_type = VHD_DYNAMIC;
    }
-    nocow = qemu_opt_get_bool_del(opts, BLOCK_OPT_NOCOW, false);

    /* Create the file */
    fd = qemu_open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, 0644);
    if (fd < 0) {
-        ret = -EIO;
-        goto out;
-    }
-
-    if (nocow) {
-#ifdef __linux__
-        /* Set NOCOW flag to solve performance issue on fs like btrfs.
-         * This is an optimisation. The FS_IOC_SETFLAGS ioctl return value will
-         * be ignored since any failure of this operation should not block the
-         * left work.
-         */
-        int attr;
-        if (ioctl(fd, FS_IOC_GETFLAGS, &attr) == 0) {
-            attr |= FS_NOCOW_FL;
-            ioctl(fd, FS_IOC_SETFLAGS, &attr);
-        }
-#endif
+        return -EIO;
    }

    /*
@@ -861,10 +823,8 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
        ret = create_fixed_disk(fd, buf, total_size);
    }

-fail:
+ fail:
    qemu_close(fd);
-out:
-    g_free(disk_type_param);
    return ret;
 }

@@ -892,29 +852,20 @@ static void vpc_close(BlockDriverState *bs)
    error_free(s->migration_blocker);
 }

-static QemuOptsList vpc_create_opts = {
-    .name = "vpc-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(vpc_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        {
-            .name = BLOCK_OPT_SUBFMT,
-            .type = QEMU_OPT_STRING,
-            .help =
-                "Type of virtual hard disk format. Supported formats are "
-                "{dynamic (default) | fixed} "
-        },
-        {
-            .name = BLOCK_OPT_NOCOW,
-            .type = QEMU_OPT_BOOL,
-            .help = "Turn off copy-on-write (valid only on btrfs)"
-        },
-        { /* end of list */ }
-    }
+static QEMUOptionParameter vpc_create_options[] = {
+    {
+        .name = BLOCK_OPT_SIZE,
+        .type = OPT_SIZE,
+        .help = "Virtual disk size"
+    },
+    {
+        .name = BLOCK_OPT_SUBFMT,
+        .type = OPT_STRING,
+        .help =
+            "Type of virtual hard disk format. Supported formats are "
+            "{dynamic (default) | fixed} "
+    },
+    { NULL }
 };

 static BlockDriver bdrv_vpc = {
@@ -930,9 +881,7 @@ static BlockDriver bdrv_vpc = {
    .bdrv_read              = vpc_co_read,
    .bdrv_write             = vpc_co_write,

-    .bdrv_get_info          = vpc_get_info,
-
-    .create_opts            = &vpc_create_opts,
+    .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--) {
@@ -833,8 +834,7 @@ static inline off_t cluster2sector(BDRVVVFATState* s, uint32_t cluster_num)
 }

 static int init_directories(BDRVVVFATState* s,
-                            const char *dirname, int heads, int secs,
-                            Error **errp)
+                            const char *dirname, int heads, int secs)
 {
    bootsector_t* bootsector;
    mapping_t* mapping;
@@ -863,7 +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 */
@@ -895,8 +896,8 @@ static int init_directories(BDRVVVFATState* s,
        if (mapping->mode & MODE_DIRECTORY) {
 	    mapping->begin = cluster;
 	    if(read_directory(s, i)) {
-                error_setg(errp, "Could not read directory %s",
-                           mapping->path);
+		fprintf(stderr, "Could not read directory %s\n",
+			mapping->path);
 		return -1;
 	    }
 	    mapping = array_get(&(s->mapping), i);
@@ -922,10 +923,9 @@ static int init_directories(BDRVVVFATState* s,
 	cluster = mapping->end;

 	if(cluster > s->cluster_count) {
-            error_setg(errp,
-                       "Directory does not fit in FAT%d (capacity %.2f MB)",
-                       s->fat_type, s->sector_count / 2000.0);
-            return -1;
+	    fprintf(stderr,"Directory does not fit in FAT%d (capacity %.2f MB)\n",
+		    s->fat_type, s->sector_count / 2000.0);
+	    return -EINVAL;
 	}

 	/* fix fat for entry */
@@ -983,7 +983,7 @@ static int init_directories(BDRVVVFATState* s,
 static BDRVVVFATState *vvv = NULL;
 #endif

-static int enable_write_target(BDRVVVFATState *s, Error **errp);
+static int enable_write_target(BDRVVVFATState *s);
 static int is_consistent(BDRVVVFATState *s);

 static void vvfat_rebind(BlockDriverState *bs)
@@ -1087,17 +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;
    }
@@ -1123,7 +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;
@@ -1138,7 +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;
    }
@@ -1151,6 +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;
@@ -1164,7 +1167,7 @@ DLOG(if (stderr == NULL) {
    s->sector_count = cyls * heads * secs - (s->first_sectors_number - 1);

    if (qemu_opt_get_bool(opts, "rw", false)) {
-        ret = enable_write_target(s, errp);
+        ret = enable_write_target(s);
        if (ret < 0) {
            goto fail;
        }
@@ -1173,7 +1176,7 @@ DLOG(if (stderr == NULL) {

    bs->total_sectors = cyls * heads * secs;

-    if (init_directories(s, dirname, heads, secs, errp)) {
+    if (init_directories(s, dirname, heads, secs)) {
        ret = -EIO;
        goto fail;
    }
@@ -1590,20 +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';
@@ -2908,10 +2908,11 @@ static BlockDriver vvfat_write_target = {
    .bdrv_close         = write_target_close,
 };

-static int enable_write_target(BDRVVVFATState *s, Error **errp)
+static int enable_write_target(BDRVVVFATState *s)
 {
-    BlockDriver *bdrv_qcow = NULL;
-    QemuOpts *opts = NULL;
+    BlockDriver *bdrv_qcow;
+    QEMUOptionParameter *options;
+    Error *local_err = NULL;
    int ret;
    int size = sector2cluster(s, s->sector_count);
    s->used_clusters = calloc(size, 1);
@@ -2921,32 +2922,30 @@ static int enable_write_target(BDRVVVFATState *s, Error **errp)
    s->qcow_filename = g_malloc(1024);
    ret = get_tmp_filename(s->qcow_filename, 1024);
    if (ret < 0) {
-        error_setg_errno(errp, -ret, "can't create temporary file");
        goto err;
    }

    bdrv_qcow = bdrv_find_format("qcow");
-    if (!bdrv_qcow) {
-        error_setg(errp, "Failed to locate qcow driver");
-        ret = -ENOENT;
+    options = parse_option_parameters("", bdrv_qcow->create_options, NULL);
+    set_option_parameter_int(options, BLOCK_OPT_SIZE, s->sector_count * 512);
+    set_option_parameter(options, BLOCK_OPT_BACKING_FILE, "fat:");
+
+    ret = bdrv_create(bdrv_qcow, s->qcow_filename, options, &local_err);
+    if (ret < 0) {
+        qerror_report_err(local_err);
+        error_free(local_err);
        goto err;
    }

-    opts = qemu_opts_create(bdrv_qcow->create_opts, NULL, 0, &error_abort);
-    qemu_opt_set_number(opts, BLOCK_OPT_SIZE, s->sector_count * 512);
-    qemu_opt_set(opts, BLOCK_OPT_BACKING_FILE, "fat:");
+    s->qcow = bdrv_new("");

-    ret = bdrv_create(bdrv_qcow, s->qcow_filename, opts, errp);
-    qemu_opts_del(opts);
-    if (ret < 0) {
-        goto err;
-    }
-
-    s->qcow = NULL;
-    ret = bdrv_open(&s->qcow, s->qcow_filename, NULL, NULL,
-                    BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH,
-                    bdrv_qcow, errp);
+    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;
    }

@@ -2954,7 +2953,7 @@ static int enable_write_target(BDRVVVFATState *s, Error **errp)
    unlink(s->qcow_filename);
 #endif

-    bdrv_set_backing_hd(s->bs, bdrv_new("", &error_abort));
+    s->bs->backing_hd = bdrv_new("");
    s->bs->backing_hd->drv = &vvfat_write_target;
    s->bs->backing_hd->opaque = g_malloc(sizeof(void*));
    *(void**)s->bs->backing_hd->opaque = s;
@@ -40,7 +40,6 @@ struct QEMUWin32AIOState {
    HANDLE hIOCP;
    EventNotifier e;
    int count;
-    bool is_aio_context_attached;
 };

 typedef struct QEMUWin32AIOCB {
@@ -115,7 +114,7 @@ static void win32_aio_cancel(BlockDriverAIOCB *blockacb)
     * wait for completion.
     */
    while (!HasOverlappedIoCompleted(&waiocb->ov)) {
-        aio_poll(bdrv_get_aio_context(blockacb->bs), true);
+        qemu_aio_wait();
    }
 }

@@ -181,20 +180,6 @@ int win32_aio_attach(QEMUWin32AIOState *aio, HANDLE hfile)
    }
 }

-void win32_aio_detach_aio_context(QEMUWin32AIOState *aio,
-                                  AioContext *old_context)
-{
-    aio_set_event_notifier(old_context, &aio->e, NULL);
-    aio->is_aio_context_attached = false;
-}
-
-void win32_aio_attach_aio_context(QEMUWin32AIOState *aio,
-                                  AioContext *new_context)
-{
-    aio->is_aio_context_attached = true;
-    aio_set_event_notifier(new_context, &aio->e, win32_aio_completion_cb);
-}
-
 QEMUWin32AIOState *win32_aio_init(void)
 {
    QEMUWin32AIOState *s;
@@ -209,6 +194,8 @@ QEMUWin32AIOState *win32_aio_init(void)
        goto out_close_efd;
    }

+    qemu_aio_set_event_notifier(&s->e, win32_aio_completion_cb);
+
    return s;

 out_close_efd:
@@ -217,11 +204,3 @@ out_free_state:
    g_free(s);
    return NULL;
 }
-
-void win32_aio_cleanup(QEMUWin32AIOState *aio)
-{
-    assert(!aio->is_aio_context_attached);
-    CloseHandle(aio->hIOCP);
-    event_notifier_cleanup(&aio->e);
-    g_free(aio);
-}
@@ -26,6 +26,7 @@
 #include "config-host.h"
 #include "qemu-common.h"
 #include "trace.h"
+#include "monitor/monitor.h"
 #include "block/block.h"
 #include "block/blockjob.h"
 #include "block/block_int.h"
@@ -33,7 +34,6 @@
 #include "block/coroutine.h"
 #include "qmp-commands.h"
 #include "qemu/timer.h"
-#include "qapi-event.h"

 void *block_job_create(const BlockJobDriver *driver, BlockDriverState *bs,
                       int64_t speed, BlockDriverCompletionFunc *cb,
@@ -41,16 +41,14 @@ void *block_job_create(const BlockJobDriver *driver, BlockDriverState *bs,
 {
    BlockJob *job;

-    if (bs->job) {
+    if (bs->job || bdrv_in_use(bs)) {
        error_set(errp, QERR_DEVICE_IN_USE, bdrv_get_device_name(bs));
        return NULL;
    }
    bdrv_ref(bs);
-    job = g_malloc0(driver->instance_size);
-    error_setg(&job->blocker, "block device is in use by block job: %s",
-               BlockJobType_lookup[driver->job_type]);
-    bdrv_op_block_all(bs, job->blocker);
+    bdrv_set_in_use(bs, 1);

+    job = g_malloc0(driver->instance_size);
    job->driver        = driver;
    job->bs            = bs;
    job->cb            = cb;
@@ -63,11 +61,10 @@ 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;
-            bdrv_op_unblock_all(bs, job->blocker);
-            error_free(job->blocker);
            g_free(job);
+            bdrv_set_in_use(bs, 0);
            error_propagate(errp, local_err);
            return NULL;
        }
@@ -82,9 +79,8 @@ void block_job_completed(BlockJob *job, int ret)
    assert(bs->job == job);
    job->cb(job->opaque, ret);
    bs->job = NULL;
-    bdrv_op_unblock_all(bs, job->blocker);
-    error_free(job->blocker);
    g_free(job);
+    bdrv_set_in_use(bs, 0);
 }

 void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)
@@ -92,11 +88,11 @@ void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)
    Error *local_err = NULL;

    if (!job->driver->set_speed) {
-        error_set(errp, QERR_UNSUPPORTED);
+        error_set(errp, QERR_NOT_SUPPORTED);
        return;
    }
    job->driver->set_speed(job, speed, &local_err);
-    if (local_err) {
+    if (error_is_set(&local_err)) {
        error_propagate(errp, local_err);
        return;
    }
@@ -187,7 +183,7 @@ int block_job_cancel_sync(BlockJob *job)
    job->opaque = &data;
    block_job_cancel(job);
    while (data.ret == -EINPROGRESS) {
-        aio_poll(bdrv_get_aio_context(bs), true);
+        qemu_aio_wait();
    }
    return (data.cancelled && data.ret == 0) ? -ECANCELED : data.ret;
 }
@@ -210,20 +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);
@@ -246,35 +228,26 @@ static void block_job_iostatus_set_err(BlockJob *job, int error)
    }
 }

-void block_job_event_cancelled(BlockJob *job)
+
+QObject *qobject_from_block_job(BlockJob *job)
 {
-    qapi_event_send_block_job_cancelled(job->driver->job_type,
-                                        bdrv_get_device_name(job->bs),
-                                        job->len,
-                                        job->offset,
-                                        job->speed,
-                                        &error_abort);
+    return qobject_from_jsonf("{ 'type': %s,"
+                              "'device': %s,"
+                              "'len': %" PRId64 ","
+                              "'offset': %" PRId64 ","
+                              "'speed': %" PRId64 " }",
+                              BlockJobType_lookup[job->driver->job_type],
+                              bdrv_get_device_name(job->bs),
+                              job->len,
+                              job->offset,
+                              job->speed);
 }

-void block_job_event_completed(BlockJob *job, const char *msg)
+void block_job_ready(BlockJob *job)
 {
-    qapi_event_send_block_job_completed(job->driver->job_type,
-                                        bdrv_get_device_name(job->bs),
-                                        job->len,
-                                        job->offset,
-                                        job->speed,
-                                        !!msg,
-                                        msg,
-                                        &error_abort);
-}
-
-void block_job_event_ready(BlockJob *job)
-{
-    qapi_event_send_block_job_ready(job->driver->job_type,
-                                    bdrv_get_device_name(job->bs),
-                                    job->len,
-                                    job->offset,
-                                    job->speed, &error_abort);
+    QObject *data = qobject_from_block_job(job);
+    monitor_protocol_event(QEVENT_BLOCK_JOB_READY, data);
+    qobject_decref(data);
 }

 BlockErrorAction block_job_error_action(BlockJob *job, BlockDriverState *bs,
@@ -285,26 +258,22 @@ BlockErrorAction block_job_error_action(BlockJob *job, BlockDriverState *bs,

    switch (on_err) {
    case BLOCKDEV_ON_ERROR_ENOSPC:
-        action = (error == ENOSPC) ?
-                 BLOCK_ERROR_ACTION_STOP : BLOCK_ERROR_ACTION_REPORT;
+        action = (error == ENOSPC) ? BDRV_ACTION_STOP : BDRV_ACTION_REPORT;
        break;
    case BLOCKDEV_ON_ERROR_STOP:
-        action = BLOCK_ERROR_ACTION_STOP;
+        action = BDRV_ACTION_STOP;
        break;
    case BLOCKDEV_ON_ERROR_REPORT:
-        action = BLOCK_ERROR_ACTION_REPORT;
+        action = BDRV_ACTION_REPORT;
        break;
    case BLOCKDEV_ON_ERROR_IGNORE:
-        action = BLOCK_ERROR_ACTION_IGNORE;
+        action = BDRV_ACTION_IGNORE;
        break;
    default:
        abort();
    }
-    qapi_event_send_block_job_error(bdrv_get_device_name(job->bs),
-                                    is_read ? IO_OPERATION_TYPE_READ :
-                                    IO_OPERATION_TYPE_WRITE,
-                                    action, &error_abort);
-    if (action == BLOCK_ERROR_ACTION_STOP) {
+    bdrv_emit_qmp_error_event(job->bs, QEVENT_BLOCK_JOB_ERROR, action, is_read);
+    if (action == BDRV_ACTION_STOP) {
        block_job_pause(job);
        block_job_iostatus_set_err(job, error);
        if (bs != job->bs) {
@@ -1,37 +1,7 @@
-/*
- *  FreeBSD strace list
- *
- *
- *  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/>.
- */
-
-{ TARGET_FREEBSD_NR___acl_aclcheck_fd, "__acl_aclcheck_fd", "%s(%d, %d, %#x)", NULL, NULL },
-{ TARGET_FREEBSD_NR___acl_aclcheck_file, "__acl_aclcheck_file", "%s(\"%s\", %d, %#x)", NULL, NULL },
-{ TARGET_FREEBSD_NR___acl_aclcheck_link, "__acl_aclcheck_link", "%s(\"%s\", %d, %#x)", NULL, NULL },
-{ TARGET_FREEBSD_NR___acl_delete_fd, "__acl_delete_fd", "%s(%d, %d)", NULL, NULL },
-{ TARGET_FREEBSD_NR___acl_delete_file, "__acl_delete_file", "%s(\"%s\", %d)", NULL, NULL },
-{ TARGET_FREEBSD_NR___acl_delete_link, "__acl_delete_link", "%s(\"%s\", %d)", NULL, NULL },
-{ TARGET_FREEBSD_NR___acl_get_fd, "__acl_get_fd", "%s(%d, %d, %#x)", NULL, NULL },
-{ TARGET_FREEBSD_NR___acl_get_file, "__acl_get_file", "%s(\"%s\", %d, %#x)", NULL, NULL },
-{ TARGET_FREEBSD_NR___acl_get_link, "__acl_get_link", "%s(\"%s\", %d, %#x)", NULL, NULL },
-{ TARGET_FREEBSD_NR___acl_set_fd, "__acl_set_fd", "%s(%d, %d, %#x)", NULL, NULL },
-{ TARGET_FREEBSD_NR___acl_set_file, "__acl_set_file", "%s(\"%s\", %d, %#x)", NULL, NULL },
-{ TARGET_FREEBSD_NR___acl_set_link, "__acl_set_link", "%s(\"%s\", %d, %#x)", NULL, NULL },
+{ TARGET_FREEBSD_NR___getcwd, "__getcwd", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR___semctl, "__semctl", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR___syscall, "__syscall", NULL, NULL, NULL },
-{ TARGET_FREEBSD_NR___sysctl, "__sysctl", NULL, print_sysctl, NULL },
-{ TARGET_FREEBSD_NR__umtx_op, "_umtx_op", "%s(%#x, %d, %d, %#x, %#x)", NULL, NULL },
+{ TARGET_FREEBSD_NR___sysctl, "__sysctl", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_accept, "accept", "%s(%d,%#x,%#x)", NULL, NULL },
 { TARGET_FREEBSD_NR_access, "access", "%s(\"%s\",%#o)", NULL, NULL },
 { TARGET_FREEBSD_NR_acct, "acct", NULL, NULL, NULL },
@@ -50,41 +20,24 @@
 { TARGET_FREEBSD_NR_connect, "connect", "%s(%d,%#x,%d)", NULL, NULL },
 { TARGET_FREEBSD_NR_dup, "dup", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_dup2, "dup2", NULL, NULL, NULL },
-{ TARGET_FREEBSD_NR_eaccess, "eaccess", "%s(\"%s\",%#x)", NULL, NULL },
 { TARGET_FREEBSD_NR_execve, "execve", NULL, print_execve, NULL },
 { TARGET_FREEBSD_NR_exit, "exit", "%s(%d)\n", NULL, NULL },
-{ TARGET_FREEBSD_NR_extattrctl, "extattrctl", "%s(\"%s\", %d, \"%s\", %d, \"%s\"", NULL, NULL },
-{ TARGET_FREEBSD_NR_extattr_delete_fd, "extattr_delete_fd", "%s(%d, %d, \"%s\")", NULL, NULL },
-{ TARGET_FREEBSD_NR_extattr_delete_file, "extattr_delete_file", "%s(\"%s\", %d, \"%s\")", NULL, NULL },
-{ TARGET_FREEBSD_NR_extattr_delete_link, "extattr_delete_link", "%s(\"%s\", %d, \"%s\")", NULL, NULL },
-{ TARGET_FREEBSD_NR_extattr_get_fd, "extattr_get_fd", "%s(%d, %d, \"%s\", %#x, %d)", NULL, NULL },
-{ TARGET_FREEBSD_NR_extattr_get_file, "extattr_get_file", "%s(\"%s\", %d, \"%s\", %#x, %d)", NULL, NULL },
-{ TARGET_FREEBSD_NR_extattr_get_file, "extattr_get_link", "%s(\"%s\", %d, \"%s\", %#x, %d)", NULL, NULL },
-{ TARGET_FREEBSD_NR_extattr_list_fd, "extattr_list_fd", "%s(%d, %d, %#x, %d)", NULL, NULL },
-{ TARGET_FREEBSD_NR_extattr_list_file, "extattr_list_file", "%s(\"%s\", %d, %#x, %d)", NULL, NULL },
-{ TARGET_FREEBSD_NR_extattr_list_link, "extattr_list_link", "%s(\"%s\", %d, %#x, %d)", NULL, NULL },
-{ TARGET_FREEBSD_NR_extattr_set_fd, "extattr_set_fd", "%s(%d, %d, \"%s\", %#x, %d)", NULL, NULL },
-{ TARGET_FREEBSD_NR_extattr_set_file, "extattr_set_file", "%s(\"%s\", %d, \"%s\", %#x, %d)", NULL, NULL },
-{ TARGET_FREEBSD_NR_extattr_set_link, "extattr_set_link", "%s(\"%s\", %d, \"%s\", %#x, %d)", NULL, NULL },
 { TARGET_FREEBSD_NR_fchdir, "fchdir", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_fchflags, "fchflags", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_fchmod, "fchmod", "%s(%d,%#o)", NULL, NULL },
-{ TARGET_FREEBSD_NR_fchown, "fchown", "%s(%d,%d,%d)", NULL, NULL },
+{ TARGET_FREEBSD_NR_fchown, "fchown", "%s(\"%s\",%d,%d)", NULL, NULL },
 { TARGET_FREEBSD_NR_fcntl, "fcntl", NULL, NULL, NULL },
-{ TARGET_FREEBSD_NR_fexecve, "fexecve", NULL, print_execve, NULL },
 { TARGET_FREEBSD_NR_fhopen, "fhopen", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_fhstat, "fhstat", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_fhstatfs, "fhstatfs", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_flock, "flock", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_fork, "fork", "%s()", NULL, NULL },
 { TARGET_FREEBSD_NR_fpathconf, "fpathconf", NULL, NULL, NULL },
-{ TARGET_FREEBSD_NR_fstat, "fstat", "%s(%d,%#x)", NULL, NULL },
-{ TARGET_FREEBSD_NR_fstatat, "fstatat", "%s(%d,\"%s\", %#x, %d)", NULL, NULL },
-{ TARGET_FREEBSD_NR_fstatfs, "fstatfs", "%s(%d,%#x)", NULL, NULL },
+{ TARGET_FREEBSD_NR_fstat, "fstat", "%s(%d,%p)", NULL, NULL },
+{ TARGET_FREEBSD_NR_fstatfs, "fstatfs", "%s(%d,%p)", NULL, NULL },
 { TARGET_FREEBSD_NR_fsync, "fsync", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_ftruncate, "ftruncate", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_futimes, "futimes", NULL, NULL, NULL },
-{ TARGET_FREEBSD_NR_getcontext, "getcontext", "%s(%#x)", NULL, NULL },
 { TARGET_FREEBSD_NR_getdirentries, "getdirentries", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_freebsd6_mmap, "freebsd6_mmap", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_getegid, "getegid", "%s()", NULL, NULL },
@@ -110,7 +63,7 @@
 { TARGET_FREEBSD_NR_getsockopt, "getsockopt", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_gettimeofday, "gettimeofday", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_getuid, "getuid", "%s()", NULL, NULL },
-{ TARGET_FREEBSD_NR_ioctl, "ioctl", NULL, print_ioctl, NULL },
+{ TARGET_FREEBSD_NR_ioctl, "ioctl", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_issetugid, "issetugid", "%s()", NULL, NULL },
 { TARGET_FREEBSD_NR_kevent, "kevent", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_kill, "kill", NULL, NULL, NULL },
@@ -119,7 +72,6 @@
 { TARGET_FREEBSD_NR_lchown, "lchown", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_link, "link", "%s(\"%s\",\"%s\")", NULL, NULL },
 { TARGET_FREEBSD_NR_listen, "listen", NULL, NULL, NULL },
-{ TARGET_FREEBSD_NR_lpathconf, "lpathconf", "%s(\"%s\", %d)", NULL, NULL },
 { TARGET_FREEBSD_NR_lseek, "lseek", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_lstat, "lstat", "%s(\"%s\",%p)", NULL, NULL },
 { TARGET_FREEBSD_NR_madvise, "madvise", NULL, NULL, NULL },
@@ -144,8 +96,7 @@
 { TARGET_FREEBSD_NR_nanosleep, "nanosleep", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_nfssvc, "nfssvc", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_open, "open", "%s(\"%s\",%#x,%#o)", NULL, NULL },
-{ TARGET_FREEBSD_NR_openat, "openat", "%s(%d, \"%s\",%#x,%#o)", NULL, NULL },
-{ TARGET_FREEBSD_NR_pathconf, "pathconf", "%s(\"%s\", %d)", NULL, NULL },
+{ TARGET_FREEBSD_NR_pathconf, "pathconf", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_pipe, "pipe", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_poll, "poll", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_pread, "pread", NULL, NULL, NULL },
@@ -165,7 +116,6 @@
 { TARGET_FREEBSD_NR_revoke, "revoke", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_rfork, "rfork", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_rmdir, "rmdir", NULL, NULL, NULL },
-{ TARGET_FREEBSD_NR_rtprio_thread, "rtprio_thread", "%s(%d, %d, %p)", NULL, NULL },
 { TARGET_FREEBSD_NR_sbrk, "sbrk", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_sched_yield, "sched_yield", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_select, "select", NULL, NULL, NULL },
@@ -173,7 +123,6 @@
 { TARGET_FREEBSD_NR_semop, "semop", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_sendmsg, "sendmsg", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_sendto, "sendto", NULL, NULL, NULL },
-{ TARGET_FREEBSD_NR_setcontext, "setcontext", "%s(%#x)", NULL, NULL },
 { TARGET_FREEBSD_NR_setegid, "setegid", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_seteuid, "seteuid", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_setgid, "setgid", NULL, NULL, NULL },
@@ -202,7 +151,7 @@
 { TARGET_FREEBSD_NR_sigprocmask, "sigprocmask", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_sigreturn, "sigreturn", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_sigsuspend, "sigsuspend", NULL, NULL, NULL },
-{ TARGET_FREEBSD_NR_socket, "socket", "%s(%d,%d,%d)", NULL, NULL },
+{ TARGET_FREEBSD_NR_socket, "socket", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_socketpair, "socketpair", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_sstk, "sstk", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_stat, "stat", "%s(\"%s\",%p)", NULL, NULL },
@@ -211,15 +160,6 @@
 { TARGET_FREEBSD_NR_sync, "sync", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_sysarch, "sysarch", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_syscall, "syscall", NULL, NULL, NULL },
-{ TARGET_FREEBSD_NR_thr_create, "thr_create", "%s(%#x, %#x, %d)", NULL, NULL },
-{ TARGET_FREEBSD_NR_thr_exit, "thr_exit", "%s(%#x)", NULL, NULL },
-{ TARGET_FREEBSD_NR_thr_kill, "thr_kill", "%s(%d, %#x)", NULL, NULL },
-{ TARGET_FREEBSD_NR_thr_kill2, "thr_kill2", "%s(%d, %d, %d)", NULL, NULL },
-{ TARGET_FREEBSD_NR_thr_new, "thr_new", "%s(%#x, %d)", NULL, NULL },
-{ TARGET_FREEBSD_NR_thr_self, "thr_self", "%s(%#x)", NULL, NULL },
-{ TARGET_FREEBSD_NR_thr_set_name, "thr_set_name", "%s(%d, \"%s\")", NULL, NULL },
-{ TARGET_FREEBSD_NR_thr_suspend, "thr_suspend", "%s(%d, %#x)", NULL, NULL },
-{ TARGET_FREEBSD_NR_thr_wake, "thr_wake", "%s(%d)", NULL, NULL },
 { TARGET_FREEBSD_NR_truncate, "truncate", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_umask, "umask", "%s(%#o)", NULL, NULL },
 { TARGET_FREEBSD_NR_unlink, "unlink", "%s(\"%s\")", NULL, NULL },
@@ -1,450 +1,373 @@
 /*
 * System call numbers.
 *
- * created from FreeBSD: releng/9.1/sys/kern/syscalls.master 229723
- * 2012-01-06 19:29:16Z jhb
+ * $FreeBSD: src/sys/sys/syscall.h,v 1.224 2008/08/24 21:23:08 rwatson Exp $
+ * created from FreeBSD: head/sys/kern/syscalls.master 182123 2008-08-24 21:20:35Z rwatson
 */

-#define TARGET_FREEBSD_NR_syscall   0
-#define TARGET_FREEBSD_NR_exit  1
-#define TARGET_FREEBSD_NR_fork  2
-#define TARGET_FREEBSD_NR_read  3
-#define TARGET_FREEBSD_NR_write 4
-#define TARGET_FREEBSD_NR_open  5
-#define TARGET_FREEBSD_NR_close 6
-#define TARGET_FREEBSD_NR_wait4 7
-                /* 8 is old creat */
-#define TARGET_FREEBSD_NR_link  9
-#define TARGET_FREEBSD_NR_unlink    10
-                /* 11 is obsolete execv */
-#define TARGET_FREEBSD_NR_chdir 12
-#define TARGET_FREEBSD_NR_fchdir    13
-#define TARGET_FREEBSD_NR_mknod 14
-#define TARGET_FREEBSD_NR_chmod 15
-#define TARGET_FREEBSD_NR_chown 16
-#define TARGET_FREEBSD_NR_break 17
-#define TARGET_FREEBSD_NR_freebsd4_getfsstat    18
-                /* 19 is old lseek */
-#define TARGET_FREEBSD_NR_getpid    20
-#define TARGET_FREEBSD_NR_mount 21
-#define TARGET_FREEBSD_NR_unmount   22
-#define TARGET_FREEBSD_NR_setuid    23
-#define TARGET_FREEBSD_NR_getuid    24
-#define TARGET_FREEBSD_NR_geteuid   25
-#define TARGET_FREEBSD_NR_ptrace    26
-#define TARGET_FREEBSD_NR_recvmsg   27
-#define TARGET_FREEBSD_NR_sendmsg   28
-#define TARGET_FREEBSD_NR_recvfrom  29
-#define TARGET_FREEBSD_NR_accept    30
-#define TARGET_FREEBSD_NR_getpeername   31
-#define TARGET_FREEBSD_NR_getsockname   32
-#define TARGET_FREEBSD_NR_access    33
-#define TARGET_FREEBSD_NR_chflags   34
-#define TARGET_FREEBSD_NR_fchflags  35
-#define TARGET_FREEBSD_NR_sync  36
-#define TARGET_FREEBSD_NR_kill  37
-                /* 38 is old stat */
-#define TARGET_FREEBSD_NR_getppid   39
-                /* 40 is old lstat */
-#define TARGET_FREEBSD_NR_dup   41
-#define TARGET_FREEBSD_NR_pipe  42
-#define TARGET_FREEBSD_NR_getegid   43
-#define TARGET_FREEBSD_NR_profil    44
-#define TARGET_FREEBSD_NR_ktrace    45
-                /* 46 is old sigaction */
-#define TARGET_FREEBSD_NR_getgid    47
-                /* 48 is old sigprocmask */
-#define TARGET_FREEBSD_NR_getlogin  49
-#define TARGET_FREEBSD_NR_setlogin  50
-#define TARGET_FREEBSD_NR_acct  51
-                /* 52 is old sigpending */
-#define TARGET_FREEBSD_NR_sigaltstack   53
-#define TARGET_FREEBSD_NR_ioctl 54
-#define TARGET_FREEBSD_NR_reboot    55
-#define TARGET_FREEBSD_NR_revoke    56
-#define TARGET_FREEBSD_NR_symlink   57
-#define TARGET_FREEBSD_NR_readlink  58
-#define TARGET_FREEBSD_NR_execve    59
-#define TARGET_FREEBSD_NR_umask 60
-#define TARGET_FREEBSD_NR_chroot    61
-                /* 62 is old fstat */
-                /* 63 is old getkerninfo */
-                /* 64 is old getpagesize */
-#define TARGET_FREEBSD_NR_msync 65
-#define TARGET_FREEBSD_NR_vfork 66
-                /* 67 is obsolete vread */
-                /* 68 is obsolete vwrite */
-#define TARGET_FREEBSD_NR_sbrk  69
-#define TARGET_FREEBSD_NR_sstk  70
-                /* 71 is old mmap */
-#define TARGET_FREEBSD_NR_vadvise   72
-#define TARGET_FREEBSD_NR_munmap    73
-#define TARGET_FREEBSD_NR_mprotect  74
-#define TARGET_FREEBSD_NR_madvise   75
-                /* 76 is obsolete vhangup */
-                /* 77 is obsolete vlimit */
-#define TARGET_FREEBSD_NR_mincore   78
-#define TARGET_FREEBSD_NR_getgroups 79
-#define TARGET_FREEBSD_NR_setgroups 80
-#define TARGET_FREEBSD_NR_getpgrp   81
-#define TARGET_FREEBSD_NR_setpgid   82
-#define TARGET_FREEBSD_NR_setitimer 83
-                /* 84 is old wait */
-#define TARGET_FREEBSD_NR_swapon    85
-#define TARGET_FREEBSD_NR_getitimer 86
-                /* 87 is old gethostname */
-                /* 88 is old sethostname */
-#define TARGET_FREEBSD_NR_getdtablesize 89
-#define TARGET_FREEBSD_NR_dup2  90
-#define TARGET_FREEBSD_NR_fcntl 92
-#define TARGET_FREEBSD_NR_select    93
-#define TARGET_FREEBSD_NR_fsync 95
-#define TARGET_FREEBSD_NR_setpriority   96
-#define TARGET_FREEBSD_NR_socket    97
-#define TARGET_FREEBSD_NR_connect   98
-                /* 99 is old accept */
-#define TARGET_FREEBSD_NR_getpriority   100
-                /* 101 is old send */
-                /* 102 is old recv */
-                /* 103 is old sigreturn */
-#define TARGET_FREEBSD_NR_bind  104
-#define TARGET_FREEBSD_NR_setsockopt    105
-#define TARGET_FREEBSD_NR_listen    106
-                /* 107 is obsolete vtimes */
-                /* 108 is old sigvec */
-                /* 109 is old sigblock */
-                /* 110 is old sigsetmask */
-                /* 111 is old sigsuspend */
-                /* 112 is old sigstack */
-                /* 113 is old recvmsg */
-                /* 114 is old sendmsg */
-                /* 115 is obsolete vtrace */
-#define TARGET_FREEBSD_NR_gettimeofday  116
-#define TARGET_FREEBSD_NR_getrusage 117
-#define TARGET_FREEBSD_NR_getsockopt    118
-#define TARGET_FREEBSD_NR_readv 120
-#define TARGET_FREEBSD_NR_writev    121
-#define TARGET_FREEBSD_NR_settimeofday  122
-#define TARGET_FREEBSD_NR_fchown    123
-#define TARGET_FREEBSD_NR_fchmod    124
-                /* 125 is old recvfrom */
-#define TARGET_FREEBSD_NR_setreuid  126
-#define TARGET_FREEBSD_NR_setregid  127
-#define TARGET_FREEBSD_NR_rename    128
-                /* 129 is old truncate */
-                /* 130 is old ftruncate */
-#define TARGET_FREEBSD_NR_flock 131
-#define TARGET_FREEBSD_NR_mkfifo    132
-#define TARGET_FREEBSD_NR_sendto    133
-#define TARGET_FREEBSD_NR_shutdown  134
-#define TARGET_FREEBSD_NR_socketpair    135
-#define TARGET_FREEBSD_NR_mkdir 136
-#define TARGET_FREEBSD_NR_rmdir 137
-#define TARGET_FREEBSD_NR_utimes    138
-                /* 139 is obsolete 4.2 sigreturn */
-#define TARGET_FREEBSD_NR_adjtime   140
-                /* 141 is old getpeername */
-                /* 142 is old gethostid */
-                /* 143 is old sethostid */
-                /* 144 is old getrlimit */
-                /* 145 is old setrlimit */
-                /* 146 is old killpg */
-#define TARGET_FREEBSD_NR_killpg    146 /* COMPAT */
-#define TARGET_FREEBSD_NR_setsid    147
-#define TARGET_FREEBSD_NR_quotactl  148
-                /* 149 is old quota */
-                /* 150 is old getsockname */
-#define TARGET_FREEBSD_NR_nlm_syscall   154
-#define TARGET_FREEBSD_NR_nfssvc    155
-                /* 156 is old getdirentries */
-#define TARGET_FREEBSD_NR_freebsd4_statfs   157
-#define TARGET_FREEBSD_NR_freebsd4_fstatfs  158
-#define TARGET_FREEBSD_NR_lgetfh    160
-#define TARGET_FREEBSD_NR_getfh 161
-#define TARGET_FREEBSD_NR_freebsd4_getdomainname    162
-#define TARGET_FREEBSD_NR_freebsd4_setdomainname    163
-#define TARGET_FREEBSD_NR_freebsd4_uname    164
-#define TARGET_FREEBSD_NR_sysarch   165
-#define TARGET_FREEBSD_NR_rtprio    166
-#define TARGET_FREEBSD_NR_semsys    169
-#define TARGET_FREEBSD_NR_msgsys    170
-#define TARGET_FREEBSD_NR_shmsys    171
-#define TARGET_FREEBSD_NR_freebsd6_pread    173
-#define TARGET_FREEBSD_NR_freebsd6_pwrite   174
-#define TARGET_FREEBSD_NR_setfib    175
-#define TARGET_FREEBSD_NR_ntp_adjtime   176
-#define TARGET_FREEBSD_NR_setgid    181
-#define TARGET_FREEBSD_NR_setegid   182
-#define TARGET_FREEBSD_NR_seteuid   183
-#define TARGET_FREEBSD_NR_stat  188
-#define TARGET_FREEBSD_NR_fstat 189
-#define TARGET_FREEBSD_NR_lstat 190
-#define TARGET_FREEBSD_NR_pathconf  191
-#define TARGET_FREEBSD_NR_fpathconf 192
-#define TARGET_FREEBSD_NR_getrlimit 194
-#define TARGET_FREEBSD_NR_setrlimit 195
-#define TARGET_FREEBSD_NR_getdirentries 196
-#define TARGET_FREEBSD_NR_freebsd6_mmap 197
-#define TARGET_FREEBSD_NR___syscall 198
-#define TARGET_FREEBSD_NR_freebsd6_lseek    199
-#define TARGET_FREEBSD_NR_freebsd6_truncate 200
-#define TARGET_FREEBSD_NR_freebsd6_ftruncate    201
-#define TARGET_FREEBSD_NR___sysctl  202
-#define TARGET_FREEBSD_NR_mlock 203
-#define TARGET_FREEBSD_NR_munlock   204
-#define TARGET_FREEBSD_NR_undelete  205
-#define TARGET_FREEBSD_NR_futimes   206
-#define TARGET_FREEBSD_NR_getpgid   207
-#define TARGET_FREEBSD_NR_poll  209
-#define TARGET_FREEBSD_NR_freebsd7___semctl 220
-#define TARGET_FREEBSD_NR_semget    221
-#define TARGET_FREEBSD_NR_semop 222
-#define TARGET_FREEBSD_NR_freebsd7_msgctl   224
-#define TARGET_FREEBSD_NR_msgget    225
-#define TARGET_FREEBSD_NR_msgsnd    226
-#define TARGET_FREEBSD_NR_msgrcv    227
-#define TARGET_FREEBSD_NR_shmat 228
-#define TARGET_FREEBSD_NR_freebsd7_shmctl   229
-#define TARGET_FREEBSD_NR_shmdt 230
-#define TARGET_FREEBSD_NR_shmget    231
-#define TARGET_FREEBSD_NR_clock_gettime 232
-#define TARGET_FREEBSD_NR_clock_settime 233
-#define TARGET_FREEBSD_NR_clock_getres  234
-#define TARGET_FREEBSD_NR_ktimer_create 235
-#define TARGET_FREEBSD_NR_ktimer_delete 236
-#define TARGET_FREEBSD_NR_ktimer_settime    237
-#define TARGET_FREEBSD_NR_ktimer_gettime    238
-#define TARGET_FREEBSD_NR_ktimer_getoverrun 239
-#define TARGET_FREEBSD_NR_nanosleep 240
-#define TARGET_FREEBSD_NR_ntp_gettime   248
-#define TARGET_FREEBSD_NR_minherit  250
-#define TARGET_FREEBSD_NR_rfork 251
-#define TARGET_FREEBSD_NR_openbsd_poll  252
-#define TARGET_FREEBSD_NR_issetugid 253
-#define TARGET_FREEBSD_NR_lchown    254
-#define TARGET_FREEBSD_NR_aio_read  255
-#define TARGET_FREEBSD_NR_aio_write 256
-#define TARGET_FREEBSD_NR_lio_listio    257
-#define TARGET_FREEBSD_NR_getdents  272
-#define TARGET_FREEBSD_NR_lchmod    274
-#define TARGET_FREEBSD_NR_netbsd_lchown 275
-#define TARGET_FREEBSD_NR_lutimes   276
-#define TARGET_FREEBSD_NR_netbsd_msync  277
-#define TARGET_FREEBSD_NR_nstat 278
-#define TARGET_FREEBSD_NR_nfstat    279
-#define TARGET_FREEBSD_NR_nlstat    280
-#define TARGET_FREEBSD_NR_preadv    289
-#define TARGET_FREEBSD_NR_pwritev   290
-#define TARGET_FREEBSD_NR_freebsd4_fhstatfs 297
-#define TARGET_FREEBSD_NR_fhopen    298
-#define TARGET_FREEBSD_NR_fhstat    299
-#define TARGET_FREEBSD_NR_modnext   300
-#define TARGET_FREEBSD_NR_modstat   301
-#define TARGET_FREEBSD_NR_modfnext  302
-#define TARGET_FREEBSD_NR_modfind   303
-#define TARGET_FREEBSD_NR_kldload   304
-#define TARGET_FREEBSD_NR_kldunload 305
-#define TARGET_FREEBSD_NR_kldfind   306
-#define TARGET_FREEBSD_NR_kldnext   307
-#define TARGET_FREEBSD_NR_kldstat   308
-#define TARGET_FREEBSD_NR_kldfirstmod   309
-#define TARGET_FREEBSD_NR_getsid    310
-#define TARGET_FREEBSD_NR_setresuid 311
-#define TARGET_FREEBSD_NR_setresgid 312
-                /* 313 is obsolete signanosleep */
-#define TARGET_FREEBSD_NR_aio_return    314
-#define TARGET_FREEBSD_NR_aio_suspend   315
-#define TARGET_FREEBSD_NR_aio_cancel    316
-#define TARGET_FREEBSD_NR_aio_error 317
-#define TARGET_FREEBSD_NR_oaio_read 318
-#define TARGET_FREEBSD_NR_oaio_write    319
-#define TARGET_FREEBSD_NR_olio_listio   320
-#define TARGET_FREEBSD_NR_yield 321
-                /* 322 is obsolete thr_sleep */
-                /* 323 is obsolete thr_wakeup */
-#define TARGET_FREEBSD_NR_mlockall  324
-#define TARGET_FREEBSD_NR_munlockall    325
-#define TARGET_FREEBSD_NR___getcwd  326
-#define TARGET_FREEBSD_NR_sched_setparam    327
-#define TARGET_FREEBSD_NR_sched_getparam    328
-#define TARGET_FREEBSD_NR_sched_setscheduler    329
-#define TARGET_FREEBSD_NR_sched_getscheduler    330
-#define TARGET_FREEBSD_NR_sched_yield   331
-#define TARGET_FREEBSD_NR_sched_get_priority_max    332
-#define TARGET_FREEBSD_NR_sched_get_priority_min    333
-#define TARGET_FREEBSD_NR_sched_rr_get_interval 334
-#define TARGET_FREEBSD_NR_utrace    335
-#define TARGET_FREEBSD_NR_freebsd4_sendfile 336
-#define TARGET_FREEBSD_NR_kldsym    337
-#define TARGET_FREEBSD_NR_jail  338
-#define TARGET_FREEBSD_NR_nnpfs_syscall 339
-#define TARGET_FREEBSD_NR_sigprocmask   340
-#define TARGET_FREEBSD_NR_sigsuspend    341
-#define TARGET_FREEBSD_NR_freebsd4_sigaction    342
-#define TARGET_FREEBSD_NR_sigpending    343
-#define TARGET_FREEBSD_NR_freebsd4_sigreturn    344
-#define TARGET_FREEBSD_NR_sigtimedwait  345
-#define TARGET_FREEBSD_NR_sigwaitinfo   346
-#define TARGET_FREEBSD_NR___acl_get_file    347
-#define TARGET_FREEBSD_NR___acl_set_file    348
-#define TARGET_FREEBSD_NR___acl_get_fd  349
-#define TARGET_FREEBSD_NR___acl_set_fd  350
-#define TARGET_FREEBSD_NR___acl_delete_file 351
-#define TARGET_FREEBSD_NR___acl_delete_fd   352
-#define TARGET_FREEBSD_NR___acl_aclcheck_file   353
-#define TARGET_FREEBSD_NR___acl_aclcheck_fd 354
-#define TARGET_FREEBSD_NR_extattrctl    355
-#define TARGET_FREEBSD_NR_extattr_set_file  356
-#define TARGET_FREEBSD_NR_extattr_get_file  357
-#define TARGET_FREEBSD_NR_extattr_delete_file   358
-#define TARGET_FREEBSD_NR_aio_waitcomplete  359
-#define TARGET_FREEBSD_NR_getresuid 360
-#define TARGET_FREEBSD_NR_getresgid 361
-#define TARGET_FREEBSD_NR_kqueue    362
-#define TARGET_FREEBSD_NR_kevent    363
-#define TARGET_FREEBSD_NR_extattr_set_fd    371
-#define TARGET_FREEBSD_NR_extattr_get_fd    372
-#define TARGET_FREEBSD_NR_extattr_delete_fd 373
-#define TARGET_FREEBSD_NR___setugid 374
-#define TARGET_FREEBSD_NR_eaccess   376
-#define TARGET_FREEBSD_NR_afs3_syscall  377
-#define TARGET_FREEBSD_NR_nmount    378
-#define TARGET_FREEBSD_NR___mac_get_proc    384
-#define TARGET_FREEBSD_NR___mac_set_proc    385
-#define TARGET_FREEBSD_NR___mac_get_fd  386
-#define TARGET_FREEBSD_NR___mac_get_file    387
-#define TARGET_FREEBSD_NR___mac_set_fd  388
-#define TARGET_FREEBSD_NR___mac_set_file    389
-#define TARGET_FREEBSD_NR_kenv  390
-#define TARGET_FREEBSD_NR_lchflags  391
-#define TARGET_FREEBSD_NR_uuidgen   392
-#define TARGET_FREEBSD_NR_sendfile  393
-#define TARGET_FREEBSD_NR_mac_syscall   394
-#define TARGET_FREEBSD_NR_getfsstat 395
-#define TARGET_FREEBSD_NR_statfs    396
-#define TARGET_FREEBSD_NR_fstatfs   397
-#define TARGET_FREEBSD_NR_fhstatfs  398
-#define TARGET_FREEBSD_NR_ksem_close    400
-#define TARGET_FREEBSD_NR_ksem_post 401
-#define TARGET_FREEBSD_NR_ksem_wait 402
-#define TARGET_FREEBSD_NR_ksem_trywait  403
-#define TARGET_FREEBSD_NR_ksem_init 404
-#define TARGET_FREEBSD_NR_ksem_open 405
-#define TARGET_FREEBSD_NR_ksem_unlink   406
-#define TARGET_FREEBSD_NR_ksem_getvalue 407
-#define TARGET_FREEBSD_NR_ksem_destroy  408
-#define TARGET_FREEBSD_NR___mac_get_pid 409
-#define TARGET_FREEBSD_NR___mac_get_link    410
-#define TARGET_FREEBSD_NR___mac_set_link    411
-#define TARGET_FREEBSD_NR_extattr_set_link  412
-#define TARGET_FREEBSD_NR_extattr_get_link  413
-#define TARGET_FREEBSD_NR_extattr_delete_link   414
-#define TARGET_FREEBSD_NR___mac_execve  415
-#define TARGET_FREEBSD_NR_sigaction 416
-#define TARGET_FREEBSD_NR_sigreturn 417
-#define TARGET_FREEBSD_NR_getcontext    421
-#define TARGET_FREEBSD_NR_setcontext    422
-#define TARGET_FREEBSD_NR_swapcontext   423
-#define TARGET_FREEBSD_NR_swapoff   424
-#define TARGET_FREEBSD_NR___acl_get_link    425
-#define TARGET_FREEBSD_NR___acl_set_link    426
-#define TARGET_FREEBSD_NR___acl_delete_link 427
-#define TARGET_FREEBSD_NR___acl_aclcheck_link   428
-#define TARGET_FREEBSD_NR_sigwait   429
-#define TARGET_FREEBSD_NR_thr_create    430
-#define TARGET_FREEBSD_NR_thr_exit  431
-#define TARGET_FREEBSD_NR_thr_self  432
-#define TARGET_FREEBSD_NR_thr_kill  433
-#define TARGET_FREEBSD_NR__umtx_lock    434
-#define TARGET_FREEBSD_NR__umtx_unlock  435
-#define TARGET_FREEBSD_NR_jail_attach   436
-#define TARGET_FREEBSD_NR_extattr_list_fd   437
-#define TARGET_FREEBSD_NR_extattr_list_file 438
-#define TARGET_FREEBSD_NR_extattr_list_link 439
-#define TARGET_FREEBSD_NR_ksem_timedwait    441
-#define TARGET_FREEBSD_NR_thr_suspend   442
-#define TARGET_FREEBSD_NR_thr_wake  443
-#define TARGET_FREEBSD_NR_kldunloadf    444
-#define TARGET_FREEBSD_NR_audit 445
-#define TARGET_FREEBSD_NR_auditon   446
-#define TARGET_FREEBSD_NR_getauid   447
-#define TARGET_FREEBSD_NR_setauid   448
-#define TARGET_FREEBSD_NR_getaudit  449
-#define TARGET_FREEBSD_NR_setaudit  450
-#define TARGET_FREEBSD_NR_getaudit_addr 451
-#define TARGET_FREEBSD_NR_setaudit_addr 452
-#define TARGET_FREEBSD_NR_auditctl  453
-#define TARGET_FREEBSD_NR__umtx_op  454
-#define TARGET_FREEBSD_NR_thr_new   455
-#define TARGET_FREEBSD_NR_sigqueue  456
-#define TARGET_FREEBSD_NR_kmq_open  457
-#define TARGET_FREEBSD_NR_kmq_setattr   458
-#define TARGET_FREEBSD_NR_kmq_timedreceive  459
-#define TARGET_FREEBSD_NR_kmq_timedsend 460
-#define TARGET_FREEBSD_NR_kmq_notify    461
-#define TARGET_FREEBSD_NR_kmq_unlink    462
-#define TARGET_FREEBSD_NR_abort2    463
-#define TARGET_FREEBSD_NR_thr_set_name  464
-#define TARGET_FREEBSD_NR_aio_fsync 465
-#define TARGET_FREEBSD_NR_rtprio_thread 466
-#define TARGET_FREEBSD_NR_sctp_peeloff  471
-#define TARGET_FREEBSD_NR_sctp_generic_sendmsg  472
-#define TARGET_FREEBSD_NR_sctp_generic_sendmsg_iov  473
-#define TARGET_FREEBSD_NR_sctp_generic_recvmsg  474
-#define TARGET_FREEBSD_NR_pread 475
-#define TARGET_FREEBSD_NR_pwrite    476
-#define TARGET_FREEBSD_NR_mmap  477
-#define TARGET_FREEBSD_NR_lseek 478
-#define TARGET_FREEBSD_NR_truncate  479
-#define TARGET_FREEBSD_NR_ftruncate 480
-#define TARGET_FREEBSD_NR_thr_kill2 481
-#define TARGET_FREEBSD_NR_shm_open  482
-#define TARGET_FREEBSD_NR_shm_unlink    483
-#define TARGET_FREEBSD_NR_cpuset    484
-#define TARGET_FREEBSD_NR_cpuset_setid  485
-#define TARGET_FREEBSD_NR_cpuset_getid  486
-#define TARGET_FREEBSD_NR_cpuset_getaffinity    487
-#define TARGET_FREEBSD_NR_cpuset_setaffinity    488
-#define TARGET_FREEBSD_NR_faccessat 489
-#define TARGET_FREEBSD_NR_fchmodat  490
-#define TARGET_FREEBSD_NR_fchownat  491
-#define TARGET_FREEBSD_NR_fexecve   492
-#define TARGET_FREEBSD_NR_fstatat   493
-#define TARGET_FREEBSD_NR_futimesat 494
-#define TARGET_FREEBSD_NR_linkat    495
-#define TARGET_FREEBSD_NR_mkdirat   496
-#define TARGET_FREEBSD_NR_mkfifoat  497
-#define TARGET_FREEBSD_NR_mknodat   498
-#define TARGET_FREEBSD_NR_openat    499
-#define TARGET_FREEBSD_NR_readlinkat    500
-#define TARGET_FREEBSD_NR_renameat  501
-#define TARGET_FREEBSD_NR_symlinkat 502
-#define TARGET_FREEBSD_NR_unlinkat  503
-#define TARGET_FREEBSD_NR_posix_openpt  504
-#define TARGET_FREEBSD_NR_gssd_syscall  505
-#define TARGET_FREEBSD_NR_jail_get  506
-#define TARGET_FREEBSD_NR_jail_set  507
-#define TARGET_FREEBSD_NR_jail_remove   508
-#define TARGET_FREEBSD_NR_closefrom 509
-#define TARGET_FREEBSD_NR___semctl  510
-#define TARGET_FREEBSD_NR_msgctl    511
-#define TARGET_FREEBSD_NR_shmctl    512
-#define TARGET_FREEBSD_NR_lpathconf 513
-#define TARGET_FREEBSD_NR_cap_new   514
-#define TARGET_FREEBSD_NR_cap_getrights 515
-#define TARGET_FREEBSD_NR_cap_enter 516
-#define TARGET_FREEBSD_NR_cap_getmode   517
-#define TARGET_FREEBSD_NR_pdfork    518
-#define TARGET_FREEBSD_NR_pdkill    519
-#define TARGET_FREEBSD_NR_pdgetpid  520
-#define TARGET_FREEBSD_NR_pselect   522
-#define TARGET_FREEBSD_NR_getloginclass 523
-#define TARGET_FREEBSD_NR_setloginclass 524
-#define TARGET_FREEBSD_NR_rctl_get_racct    525
-#define TARGET_FREEBSD_NR_rctl_get_rules    526
-#define TARGET_FREEBSD_NR_rctl_get_limits   527
-#define TARGET_FREEBSD_NR_rctl_add_rule 528
-#define TARGET_FREEBSD_NR_rctl_remove_rule  529
-#define TARGET_FREEBSD_NR_posix_fallocate   530
-#define TARGET_FREEBSD_NR_posix_fadvise 531
-#define TARGET_FREEBSD_NR_MAXSYSCALL    532
+#define TARGET_FREEBSD_NR_syscall     0
+#define TARGET_FREEBSD_NR_exit        1
+#define TARGET_FREEBSD_NR_fork        2
+#define TARGET_FREEBSD_NR_read        3
+#define TARGET_FREEBSD_NR_write       4
+#define TARGET_FREEBSD_NR_open        5
+#define TARGET_FREEBSD_NR_close       6
+#define TARGET_FREEBSD_NR_wait4       7
+#define TARGET_FREEBSD_NR_link        9
+#define TARGET_FREEBSD_NR_unlink      10
+#define TARGET_FREEBSD_NR_chdir       12
+#define TARGET_FREEBSD_NR_fchdir      13
+#define TARGET_FREEBSD_NR_mknod       14
+#define TARGET_FREEBSD_NR_chmod       15
+#define TARGET_FREEBSD_NR_chown       16
+#define TARGET_FREEBSD_NR_break       17
+#define TARGET_FREEBSD_NR_freebsd4_getfsstat  18
+#define TARGET_FREEBSD_NR_getpid      20
+#define TARGET_FREEBSD_NR_mount       21
+#define TARGET_FREEBSD_NR_unmount     22
+#define TARGET_FREEBSD_NR_setuid      23
+#define TARGET_FREEBSD_NR_getuid      24
+#define TARGET_FREEBSD_NR_geteuid     25
+#define TARGET_FREEBSD_NR_ptrace      26
+#define TARGET_FREEBSD_NR_recvmsg     27
+#define TARGET_FREEBSD_NR_sendmsg     28
+#define TARGET_FREEBSD_NR_recvfrom    29
+#define TARGET_FREEBSD_NR_accept      30
+#define TARGET_FREEBSD_NR_getpeername 31
+#define TARGET_FREEBSD_NR_getsockname 32
+#define TARGET_FREEBSD_NR_access      33
+#define TARGET_FREEBSD_NR_chflags     34
+#define TARGET_FREEBSD_NR_fchflags    35
+#define TARGET_FREEBSD_NR_sync        36
+#define TARGET_FREEBSD_NR_kill        37
+#define TARGET_FREEBSD_NR_getppid     39
+#define TARGET_FREEBSD_NR_dup 41
+#define TARGET_FREEBSD_NR_pipe        42
+#define TARGET_FREEBSD_NR_getegid     43
+#define TARGET_FREEBSD_NR_profil      44
+#define TARGET_FREEBSD_NR_ktrace      45
+#define TARGET_FREEBSD_NR_getgid      47
+#define TARGET_FREEBSD_NR_getlogin    49
+#define TARGET_FREEBSD_NR_setlogin    50
+#define TARGET_FREEBSD_NR_acct        51
+#define TARGET_FREEBSD_NR_sigaltstack 53
+#define TARGET_FREEBSD_NR_ioctl       54
+#define TARGET_FREEBSD_NR_reboot      55
+#define TARGET_FREEBSD_NR_revoke      56
+#define TARGET_FREEBSD_NR_symlink     57
+#define TARGET_FREEBSD_NR_readlink    58
+#define TARGET_FREEBSD_NR_execve      59
+#define TARGET_FREEBSD_NR_umask       60
+#define TARGET_FREEBSD_NR_chroot      61
+#define TARGET_FREEBSD_NR_msync       65
+#define TARGET_FREEBSD_NR_vfork       66
+#define TARGET_FREEBSD_NR_sbrk        69
+#define TARGET_FREEBSD_NR_sstk        70
+#define TARGET_FREEBSD_NR_vadvise     72
+#define TARGET_FREEBSD_NR_munmap      73
+#define TARGET_FREEBSD_NR_mprotect    74
+#define TARGET_FREEBSD_NR_madvise     75
+#define TARGET_FREEBSD_NR_mincore     78
+#define TARGET_FREEBSD_NR_getgroups   79
+#define TARGET_FREEBSD_NR_setgroups   80
+#define TARGET_FREEBSD_NR_getpgrp     81
+#define TARGET_FREEBSD_NR_setpgid     82
+#define TARGET_FREEBSD_NR_setitimer   83
+#define TARGET_FREEBSD_NR_swapon      85
+#define TARGET_FREEBSD_NR_getitimer   86
+#define TARGET_FREEBSD_NR_getdtablesize       89
+#define TARGET_FREEBSD_NR_dup2        90
+#define TARGET_FREEBSD_NR_fcntl       92
+#define TARGET_FREEBSD_NR_select      93
+#define TARGET_FREEBSD_NR_fsync       95
+#define TARGET_FREEBSD_NR_setpriority 96
+#define TARGET_FREEBSD_NR_socket      97
+#define TARGET_FREEBSD_NR_connect     98
+#define TARGET_FREEBSD_NR_getpriority 100
+#define TARGET_FREEBSD_NR_bind        104
+#define TARGET_FREEBSD_NR_setsockopt  105
+#define TARGET_FREEBSD_NR_listen      106
+#define TARGET_FREEBSD_NR_gettimeofday        116
+#define TARGET_FREEBSD_NR_getrusage   117
+#define TARGET_FREEBSD_NR_getsockopt  118
+#define TARGET_FREEBSD_NR_readv       120
+#define TARGET_FREEBSD_NR_writev      121
+#define TARGET_FREEBSD_NR_settimeofday        122
+#define TARGET_FREEBSD_NR_fchown      123
+#define TARGET_FREEBSD_NR_fchmod      124
+#define TARGET_FREEBSD_NR_setreuid    126
+#define TARGET_FREEBSD_NR_setregid    127
+#define TARGET_FREEBSD_NR_rename      128
+#define TARGET_FREEBSD_NR_flock       131
+#define TARGET_FREEBSD_NR_mkfifo      132
+#define TARGET_FREEBSD_NR_sendto      133
+#define TARGET_FREEBSD_NR_shutdown    134
+#define TARGET_FREEBSD_NR_socketpair  135
+#define TARGET_FREEBSD_NR_mkdir       136
+#define TARGET_FREEBSD_NR_rmdir       137
+#define TARGET_FREEBSD_NR_utimes      138
+#define TARGET_FREEBSD_NR_adjtime     140
+#define TARGET_FREEBSD_NR_setsid      147
+#define TARGET_FREEBSD_NR_quotactl    148
+#define TARGET_FREEBSD_NR_nlm_syscall 154
+#define TARGET_FREEBSD_NR_nfssvc      155
+#define TARGET_FREEBSD_NR_freebsd4_statfs     157
+#define TARGET_FREEBSD_NR_freebsd4_fstatfs    158
+#define TARGET_FREEBSD_NR_lgetfh      160
+#define TARGET_FREEBSD_NR_getfh       161
+#define TARGET_FREEBSD_NR_getdomainname       162
+#define TARGET_FREEBSD_NR_setdomainname       163
+#define TARGET_FREEBSD_NR_uname       164
+#define TARGET_FREEBSD_NR_sysarch     165
+#define TARGET_FREEBSD_NR_rtprio      166
+#define TARGET_FREEBSD_NR_semsys      169
+#define TARGET_FREEBSD_NR_msgsys      170
+#define TARGET_FREEBSD_NR_shmsys      171
+#define TARGET_FREEBSD_NR_freebsd6_pread      173
+#define TARGET_FREEBSD_NR_freebsd6_pwrite     174
+#define TARGET_FREEBSD_NR_setfib      175
+#define TARGET_FREEBSD_NR_ntp_adjtime 176
+#define TARGET_FREEBSD_NR_setgid      181
+#define TARGET_FREEBSD_NR_setegid     182
+#define TARGET_FREEBSD_NR_seteuid     183
+#define TARGET_FREEBSD_NR_stat        188
+#define TARGET_FREEBSD_NR_fstat       189
+#define TARGET_FREEBSD_NR_lstat       190
+#define TARGET_FREEBSD_NR_pathconf    191
+#define TARGET_FREEBSD_NR_fpathconf   192
+#define TARGET_FREEBSD_NR_getrlimit   194
+#define TARGET_FREEBSD_NR_setrlimit   195
+#define TARGET_FREEBSD_NR_getdirentries       196
+#define TARGET_FREEBSD_NR_freebsd6_mmap       197
+#define TARGET_FREEBSD_NR___syscall   198
+#define TARGET_FREEBSD_NR_freebsd6_lseek      199
+#define TARGET_FREEBSD_NR_freebsd6_truncate   200
+#define TARGET_FREEBSD_NR_freebsd6_ftruncate  201
+#define TARGET_FREEBSD_NR___sysctl    202
+#define TARGET_FREEBSD_NR_mlock       203
+#define TARGET_FREEBSD_NR_munlock     204
+#define TARGET_FREEBSD_NR_undelete    205
+#define TARGET_FREEBSD_NR_futimes     206
+#define TARGET_FREEBSD_NR_getpgid     207
+#define TARGET_FREEBSD_NR_poll        209
+#define TARGET_FREEBSD_NR___semctl    220
+#define TARGET_FREEBSD_NR_semget      221
+#define TARGET_FREEBSD_NR_semop       222
+#define TARGET_FREEBSD_NR_msgctl      224
+#define TARGET_FREEBSD_NR_msgget      225
+#define TARGET_FREEBSD_NR_msgsnd      226
+#define TARGET_FREEBSD_NR_msgrcv      227
+#define TARGET_FREEBSD_NR_shmat       228
+#define TARGET_FREEBSD_NR_shmctl      229
+#define TARGET_FREEBSD_NR_shmdt       230
+#define TARGET_FREEBSD_NR_shmget      231
+#define TARGET_FREEBSD_NR_clock_gettime       232
+#define TARGET_FREEBSD_NR_clock_settime       233
+#define TARGET_FREEBSD_NR_clock_getres        234
+#define TARGET_FREEBSD_NR_ktimer_create       235
+#define TARGET_FREEBSD_NR_ktimer_delete       236
+#define TARGET_FREEBSD_NR_ktimer_settime      237
+#define TARGET_FREEBSD_NR_ktimer_gettime      238
+#define TARGET_FREEBSD_NR_ktimer_getoverrun   239
+#define TARGET_FREEBSD_NR_nanosleep   240
+#define TARGET_FREEBSD_NR_ntp_gettime 248
+#define TARGET_FREEBSD_NR_minherit    250
+#define TARGET_FREEBSD_NR_rfork       251
+#define TARGET_FREEBSD_NR_openbsd_poll        252
+#define TARGET_FREEBSD_NR_issetugid   253
+#define TARGET_FREEBSD_NR_lchown      254
+#define TARGET_FREEBSD_NR_aio_read    255
+#define TARGET_FREEBSD_NR_aio_write   256
+#define TARGET_FREEBSD_NR_lio_listio  257
+#define TARGET_FREEBSD_NR_getdents    272
+#define TARGET_FREEBSD_NR_lchmod      274
+#define TARGET_FREEBSD_NR_netbsd_lchown       275
+#define TARGET_FREEBSD_NR_lutimes     276
+#define TARGET_FREEBSD_NR_netbsd_msync        277
+#define TARGET_FREEBSD_NR_nstat       278
+#define TARGET_FREEBSD_NR_nfstat      279
+#define TARGET_FREEBSD_NR_nlstat      280
+#define TARGET_FREEBSD_NR_preadv      289
+#define TARGET_FREEBSD_NR_pwritev     290
+#define TARGET_FREEBSD_NR_freebsd4_fhstatfs   297
+#define TARGET_FREEBSD_NR_fhopen      298
+#define TARGET_FREEBSD_NR_fhstat      299
+#define TARGET_FREEBSD_NR_modnext     300
+#define TARGET_FREEBSD_NR_modstat     301
+#define TARGET_FREEBSD_NR_modfnext    302
+#define TARGET_FREEBSD_NR_modfind     303
+#define TARGET_FREEBSD_NR_kldload     304
+#define TARGET_FREEBSD_NR_kldunload   305
+#define TARGET_FREEBSD_NR_kldfind     306
+#define TARGET_FREEBSD_NR_kldnext     307
+#define TARGET_FREEBSD_NR_kldstat     308
+#define TARGET_FREEBSD_NR_kldfirstmod 309
+#define TARGET_FREEBSD_NR_getsid      310
+#define TARGET_FREEBSD_NR_setresuid   311
+#define TARGET_FREEBSD_NR_setresgid   312
+#define TARGET_FREEBSD_NR_aio_return  314
+#define TARGET_FREEBSD_NR_aio_suspend 315
+#define TARGET_FREEBSD_NR_aio_cancel  316
+#define TARGET_FREEBSD_NR_aio_error   317
+#define TARGET_FREEBSD_NR_oaio_read   318
+#define TARGET_FREEBSD_NR_oaio_write  319
+#define TARGET_FREEBSD_NR_olio_listio 320
+#define TARGET_FREEBSD_NR_yield       321
+#define TARGET_FREEBSD_NR_mlockall    324
+#define TARGET_FREEBSD_NR_munlockall  325
+#define TARGET_FREEBSD_NR___getcwd    326
+#define TARGET_FREEBSD_NR_sched_setparam      327
+#define TARGET_FREEBSD_NR_sched_getparam      328
+#define TARGET_FREEBSD_NR_sched_setscheduler  329
+#define TARGET_FREEBSD_NR_sched_getscheduler  330
+#define TARGET_FREEBSD_NR_sched_yield 331
+#define TARGET_FREEBSD_NR_sched_get_priority_max      332
+#define TARGET_FREEBSD_NR_sched_get_priority_min      333
+#define TARGET_FREEBSD_NR_sched_rr_get_interval       334
+#define TARGET_FREEBSD_NR_utrace      335
+#define TARGET_FREEBSD_NR_freebsd4_sendfile   336
+#define TARGET_FREEBSD_NR_kldsym      337
+#define TARGET_FREEBSD_NR_jail        338
+#define TARGET_FREEBSD_NR_sigprocmask 340
+#define TARGET_FREEBSD_NR_sigsuspend  341
+#define TARGET_FREEBSD_NR_freebsd4_sigaction  342
+#define TARGET_FREEBSD_NR_sigpending  343
+#define TARGET_FREEBSD_NR_freebsd4_sigreturn  344
+#define TARGET_FREEBSD_NR_sigtimedwait        345
+#define TARGET_FREEBSD_NR_sigwaitinfo 346
+#define TARGET_FREEBSD_NR___acl_get_file      347
+#define TARGET_FREEBSD_NR___acl_set_file      348
+#define TARGET_FREEBSD_NR___acl_get_fd        349
+#define TARGET_FREEBSD_NR___acl_set_fd        350
+#define TARGET_FREEBSD_NR___acl_delete_file   351
+#define TARGET_FREEBSD_NR___acl_delete_fd     352
+#define TARGET_FREEBSD_NR___acl_aclcheck_file 353
+#define TARGET_FREEBSD_NR___acl_aclcheck_fd   354
+#define TARGET_FREEBSD_NR_extattrctl  355
+#define TARGET_FREEBSD_NR_extattr_set_file    356
+#define TARGET_FREEBSD_NR_extattr_get_file    357
+#define TARGET_FREEBSD_NR_extattr_delete_file 358
+#define TARGET_FREEBSD_NR_aio_waitcomplete    359
+#define TARGET_FREEBSD_NR_getresuid   360
+#define TARGET_FREEBSD_NR_getresgid   361
+#define TARGET_FREEBSD_NR_kqueue      362
+#define TARGET_FREEBSD_NR_kevent      363
+#define TARGET_FREEBSD_NR_extattr_set_fd      371
+#define TARGET_FREEBSD_NR_extattr_get_fd      372
+#define TARGET_FREEBSD_NR_extattr_delete_fd   373
+#define TARGET_FREEBSD_NR___setugid   374
+#define TARGET_FREEBSD_NR_nfsclnt     375
+#define TARGET_FREEBSD_NR_eaccess     376
+#define TARGET_FREEBSD_NR_nmount      378
+#define TARGET_FREEBSD_NR___mac_get_proc      384
+#define TARGET_FREEBSD_NR___mac_set_proc      385
+#define TARGET_FREEBSD_NR___mac_get_fd        386
+#define TARGET_FREEBSD_NR___mac_get_file      387
+#define TARGET_FREEBSD_NR___mac_set_fd        388
+#define TARGET_FREEBSD_NR___mac_set_file      389
+#define TARGET_FREEBSD_NR_kenv        390
+#define TARGET_FREEBSD_NR_lchflags    391
+#define TARGET_FREEBSD_NR_uuidgen     392
+#define TARGET_FREEBSD_NR_sendfile    393
+#define TARGET_FREEBSD_NR_mac_syscall 394
+#define TARGET_FREEBSD_NR_getfsstat   395
+#define TARGET_FREEBSD_NR_statfs      396
+#define TARGET_FREEBSD_NR_fstatfs     397
+#define TARGET_FREEBSD_NR_fhstatfs    398
+#define TARGET_FREEBSD_NR_ksem_close  400
+#define TARGET_FREEBSD_NR_ksem_post   401
+#define TARGET_FREEBSD_NR_ksem_wait   402
+#define TARGET_FREEBSD_NR_ksem_trywait        403
+#define TARGET_FREEBSD_NR_ksem_init   404
+#define TARGET_FREEBSD_NR_ksem_open   405
+#define TARGET_FREEBSD_NR_ksem_unlink 406
+#define TARGET_FREEBSD_NR_ksem_getvalue       407
+#define TARGET_FREEBSD_NR_ksem_destroy        408
+#define TARGET_FREEBSD_NR___mac_get_pid       409
+#define TARGET_FREEBSD_NR___mac_get_link      410
+#define TARGET_FREEBSD_NR___mac_set_link      411
+#define TARGET_FREEBSD_NR_extattr_set_link    412
+#define TARGET_FREEBSD_NR_extattr_get_link    413
+#define TARGET_FREEBSD_NR_extattr_delete_link 414
+#define TARGET_FREEBSD_NR___mac_execve        415
+#define TARGET_FREEBSD_NR_sigaction   416
+#define TARGET_FREEBSD_NR_sigreturn   417
+#define TARGET_FREEBSD_NR_getcontext  421
+#define TARGET_FREEBSD_NR_setcontext  422
+#define TARGET_FREEBSD_NR_swapcontext 423
+#define TARGET_FREEBSD_NR_swapoff     424
+#define TARGET_FREEBSD_NR___acl_get_link      425
+#define TARGET_FREEBSD_NR___acl_set_link      426
+#define TARGET_FREEBSD_NR___acl_delete_link   427
+#define TARGET_FREEBSD_NR___acl_aclcheck_link 428
+#define TARGET_FREEBSD_NR_sigwait     429
+#define TARGET_FREEBSD_NR_thr_create  430
+#define TARGET_FREEBSD_NR_thr_exit    431
+#define TARGET_FREEBSD_NR_thr_self    432
+#define TARGET_FREEBSD_NR_thr_kill    433
+#define TARGET_FREEBSD_NR__umtx_lock  434
+#define TARGET_FREEBSD_NR__umtx_unlock        435
+#define TARGET_FREEBSD_NR_jail_attach 436
+#define TARGET_FREEBSD_NR_extattr_list_fd     437
+#define TARGET_FREEBSD_NR_extattr_list_file   438
+#define TARGET_FREEBSD_NR_extattr_list_link   439
+#define TARGET_FREEBSD_NR_ksem_timedwait      441
+#define TARGET_FREEBSD_NR_thr_suspend 442
+#define TARGET_FREEBSD_NR_thr_wake    443
+#define TARGET_FREEBSD_NR_kldunloadf  444
+#define TARGET_FREEBSD_NR_audit       445
+#define TARGET_FREEBSD_NR_auditon     446
+#define TARGET_FREEBSD_NR_getauid     447
+#define TARGET_FREEBSD_NR_setauid     448
+#define TARGET_FREEBSD_NR_getaudit    449
+#define TARGET_FREEBSD_NR_setaudit    450
+#define TARGET_FREEBSD_NR_getaudit_addr       451
+#define TARGET_FREEBSD_NR_setaudit_addr       452
+#define TARGET_FREEBSD_NR_auditctl    453
+#define TARGET_FREEBSD_NR__umtx_op    454
+#define TARGET_FREEBSD_NR_thr_new     455
+#define TARGET_FREEBSD_NR_sigqueue    456
+#define TARGET_FREEBSD_NR_kmq_open    457
+#define TARGET_FREEBSD_NR_kmq_setattr 458
+#define TARGET_FREEBSD_NR_kmq_timedreceive    459
+#define TARGET_FREEBSD_NR_kmq_timedsend       460
+#define TARGET_FREEBSD_NR_kmq_notify  461
+#define TARGET_FREEBSD_NR_kmq_unlink  462
+#define TARGET_FREEBSD_NR_abort2      463
+#define TARGET_FREEBSD_NR_thr_set_name        464
+#define TARGET_FREEBSD_NR_aio_fsync   465
+#define TARGET_FREEBSD_NR_rtprio_thread       466
+#define TARGET_FREEBSD_NR_sctp_peeloff        471
+#define TARGET_FREEBSD_NR_sctp_generic_sendmsg        472
+#define TARGET_FREEBSD_NR_sctp_generic_sendmsg_iov    473
+#define TARGET_FREEBSD_NR_sctp_generic_recvmsg        474
+#define TARGET_FREEBSD_NR_pread       475
+#define TARGET_FREEBSD_NR_pwrite      476
+#define TARGET_FREEBSD_NR_mmap        477
+#define TARGET_FREEBSD_NR_lseek       478
+#define TARGET_FREEBSD_NR_truncate    479
+#define TARGET_FREEBSD_NR_ftruncate   480
+#define TARGET_FREEBSD_NR_thr_kill2   481
+#define TARGET_FREEBSD_NR_shm_open    482
+#define TARGET_FREEBSD_NR_shm_unlink  483
+#define TARGET_FREEBSD_NR_cpuset      484
+#define TARGET_FREEBSD_NR_cpuset_setid        485
+#define TARGET_FREEBSD_NR_cpuset_getid        486
+#define TARGET_FREEBSD_NR_cpuset_getaffinity  487
+#define TARGET_FREEBSD_NR_cpuset_setaffinity  488
+#define TARGET_FREEBSD_NR_faccessat   489
+#define TARGET_FREEBSD_NR_fchmodat    490
+#define TARGET_FREEBSD_NR_fchownat    491
+#define TARGET_FREEBSD_NR_fexecve     492
+#define TARGET_FREEBSD_NR_fstatat     493
+#define TARGET_FREEBSD_NR_futimesat   494
+#define TARGET_FREEBSD_NR_linkat      495
+#define TARGET_FREEBSD_NR_mkdirat     496
+#define TARGET_FREEBSD_NR_mkfifoat    497
+#define TARGET_FREEBSD_NR_mknodat     498
+#define TARGET_FREEBSD_NR_openat      499
+#define TARGET_FREEBSD_NR_readlinkat  500
+#define TARGET_FREEBSD_NR_renameat    501
+#define TARGET_FREEBSD_NR_symlinkat   502
+#define TARGET_FREEBSD_NR_unlinkat    503
+#define TARGET_FREEBSD_NR_posix_openpt        504
@@ -43,7 +43,7 @@ unsigned long reserved_va;
 #endif

 static const char *interp_prefix = CONFIG_QEMU_INTERP_PREFIX;
-const char *qemu_uname_release;
+const char *qemu_uname_release = CONFIG_UNAME_RELEASE;
 extern char **environ;
 enum BSDType bsd_type;

@@ -1000,11 +1000,13 @@ 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);
+
    env->cr[0] = CR0_PG_MASK | CR0_WP_MASK | CR0_PE_MASK;
-    env->hflags |= HF_PE_MASK | HF_CPL_MASK;
+    env->hflags |= HF_PE_MASK;
    if (env->features[FEAT_1_EDX] & CPUID_SSE) {
        env->cr[4] |= CR4_OSFXSR_MASK;
        env->hflags |= HF_OSFXSR_MASK;
@@ -74,6 +74,66 @@ void mmap_unlock(void)
 }
 #endif

+static void *bsd_vmalloc(size_t size)
+{
+    void *p;
+    mmap_lock();
+    /* Use map and mark the pages as used.  */
+    p = mmap(NULL, size, PROT_READ | PROT_WRITE,
+             MAP_PRIVATE | MAP_ANON, -1, 0);
+
+    if (h2g_valid(p)) {
+        /* Allocated region overlaps guest address space.
+           This may recurse.  */
+        abi_ulong addr = h2g(p);
+        page_set_flags(addr & TARGET_PAGE_MASK, TARGET_PAGE_ALIGN(addr + size),
+                       PAGE_RESERVED);
+    }
+
+    mmap_unlock();
+    return p;
+}
+
+void *g_malloc(size_t size)
+{
+    char * p;
+    size += 16;
+    p = bsd_vmalloc(size);
+    *(size_t *)p = size;
+    return p + 16;
+}
+
+/* We use map, which is always zero initialized.  */
+void * g_malloc0(size_t size)
+{
+    return g_malloc(size);
+}
+
+void g_free(void *ptr)
+{
+    /* FIXME: We should unmark the reserved pages here.  However this gets
+       complicated when one target page spans multiple host pages, so we
+       don't bother.  */
+    size_t *p;
+    p = (size_t *)((char *)ptr - 16);
+    munmap(p, *p);
+}
+
+void *g_realloc(void *ptr, size_t size)
+{
+    size_t old_size, copy;
+    void *new_ptr;
+
+    if (!ptr)
+        return g_malloc(size);
+    old_size = *(size_t *)((char *)ptr - 16);
+    copy = old_size < size ? old_size : size;
+    new_ptr = g_malloc(size);
+    memcpy(new_ptr, ptr, copy);
+    g_free(ptr);
+    return new_ptr;
+}
+
 /* NOTE: all the constants are the HOST ones, but addresses are target. */
 int target_mprotect(abi_ulong start, abi_ulong len, int prot)
 {
@@ -1,19 +1,3 @@
-/*
- *  qemu bsd user mode definition
- *
- *  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/>.
- */
 #ifndef QEMU_H
 #define QEMU_H

@@ -21,7 +5,6 @@
 #include <string.h>

 #include "cpu.h"
-#include "exec/cpu_ldst.h"

 #undef DEBUG_REMAP
 #ifdef DEBUG_REMAP
@@ -166,16 +149,6 @@ void fork_end(int child);
 #include "qemu/log.h"

 /* strace.c */
-struct syscallname {
-    int nr;
-    const char *name;
-    const char *format;
-    void (*call)(const struct syscallname *,
-                 abi_long, abi_long, abi_long,
-                 abi_long, abi_long, abi_long);
-    void (*result)(const struct syscallname *, abi_long);
-};
-
 void
 print_freebsd_syscall(int num,
                      abi_long arg1, abi_long arg2, abi_long arg3,
@@ -1,71 +1,37 @@
-/*
- *  System call tracing and debugging
- *
- *
- *  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 <stdio.h>
 #include <errno.h>
 #include <sys/select.h>
 #include <sys/types.h>
 #include <unistd.h>
 #include <sys/syscall.h>
-#include <sys/ioccom.h>
-#include <ctype.h>
-
 #include "qemu.h"

-int do_strace;
+int do_strace=0;
+
+struct syscallname {
+    int nr;
+    const char *name;
+    const char *format;
+    void (*call)(const struct syscallname *,
+                 abi_long, abi_long, abi_long,
+                 abi_long, abi_long, abi_long);
+    void (*result)(const struct syscallname *, abi_long);
+};

 /*
 * Utility functions
 */

-static void print_sysctl(const struct syscallname *name, abi_long arg1,
-        abi_long arg2, abi_long arg3, abi_long arg4, abi_long arg5,
-        abi_long arg6)
-{
-    uint32_t i;
-    int32_t *namep;
-
-    gemu_log("%s({ ", name->name);
-    namep = lock_user(VERIFY_READ, arg1, sizeof(int32_t) * arg2, 1);
-    if (namep) {
-        int32_t *p = namep;
-
-        for (i = 0; i < (uint32_t)arg2; i++) {
-            gemu_log("%d ", tswap32(*p++));
-        }
-        unlock_user(namep, arg1, 0);
-    }
-    gemu_log("}, %u, 0x" TARGET_ABI_FMT_lx ", 0x" TARGET_ABI_FMT_lx ", 0x"
-        TARGET_ABI_FMT_lx ", 0x" TARGET_ABI_FMT_lx ")",
-        (uint32_t)arg2, arg3, arg4, arg5, arg6);
-}
-
-static void print_execve(const struct syscallname *name, abi_long arg1,
-        abi_long arg2, abi_long arg3, abi_long arg4, abi_long arg5,
-        abi_long arg6)
+static void
+print_execve(const struct syscallname *name,
+             abi_long arg1, abi_long arg2, abi_long arg3,
+             abi_long arg4, abi_long arg5, abi_long arg6)
 {
    abi_ulong arg_ptr_addr;
    char *s;

-    s = lock_user_string(arg1);
-    if (s == NULL) {
+    if (!(s = lock_user_string(arg1)))
        return;
-    }
    gemu_log("%s(\"%s\",{", name->name, s);
    unlock_user(s, arg1, 0);

@@ -73,48 +39,29 @@ static void print_execve(const struct syscallname *name, abi_long arg1,
        abi_ulong *arg_ptr, arg_addr;

        arg_ptr = lock_user(VERIFY_READ, arg_ptr_addr, sizeof(abi_ulong), 1);
-        if (!arg_ptr) {
+        if (!arg_ptr)
            return;
-        }
        arg_addr = tswapl(*arg_ptr);
        unlock_user(arg_ptr, arg_ptr_addr, 0);
-        if (!arg_addr) {
+        if (!arg_addr)
            break;
-        }
        if ((s = lock_user_string(arg_addr))) {
            gemu_log("\"%s\",", s);
            unlock_user(s, arg_addr, 0);
        }
    }
-    gemu_log("NULL})");
-}

-static void print_ioctl(const struct syscallname *name,
-        abi_long arg1, abi_long arg2, abi_long arg3, abi_long arg4,
-        abi_long arg5, abi_long arg6)
-{
-    /* Decode the ioctl request */
-    gemu_log("%s(%d, 0x%0lx { IO%s%s GRP:0x%x('%c') CMD:%d LEN:%d }, 0x"
-            TARGET_ABI_FMT_lx ", ...)",
-            name->name,
-            (int)arg1,
-            (unsigned long)arg2,
-            arg2 & IOC_OUT ? "R" : "",
-            arg2 & IOC_IN ? "W" : "",
-            (unsigned)IOCGROUP(arg2),
-            isprint(IOCGROUP(arg2)) ? (char)IOCGROUP(arg2) : '?',
-            (int)arg2 & 0xFF,
-            (int)IOCPARM_LEN(arg2),
-            arg3);
+    gemu_log("NULL})");
 }

 /*
 * Variants for the return value output function
 */

-static void print_syscall_ret_addr(const struct syscallname *name, abi_long ret)
+static void
+print_syscall_ret_addr(const struct syscallname *name, abi_long ret)
 {
-    if (ret == -1) {
+if( ret == -1 ) {
        gemu_log(" = -1 errno=%d (%s)\n", errno, strerror(errno));
    } else {
        gemu_log(" = 0x" TARGET_ABI_FMT_lx "\n", ret);
@@ -143,9 +90,10 @@ static const struct syscallname openbsd_scnames[] = {
 #include "openbsd/strace.list"
 };

-static void print_syscall(int num, const struct syscallname *scnames,
-        unsigned int nscnames, abi_long arg1, abi_long arg2, abi_long arg3,
-        abi_long arg4, abi_long arg5, abi_long arg6)
+static void
+print_syscall(int num, const struct syscallname *scnames, unsigned int nscnames,
+              abi_long arg1, abi_long arg2, abi_long arg3,
+              abi_long arg4, abi_long arg5, abi_long arg6)
 {
    unsigned int i;
    const char *format="%s(" TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld ","
@@ -154,37 +102,36 @@ static void print_syscall(int num, const struct syscallname *scnames,

    gemu_log("%d ", getpid() );

-    for (i = 0; i < nscnames; i++) {
+    for (i = 0; i < nscnames; i++)
        if (scnames[i].nr == num) {
            if (scnames[i].call != NULL) {
                scnames[i].call(&scnames[i], arg1, arg2, arg3, arg4, arg5,
-                        arg6);
+                                arg6);
            } else {
                /* XXX: this format system is broken because it uses
                   host types and host pointers for strings */
-                if (scnames[i].format != NULL) {
+                if (scnames[i].format != NULL)
                    format = scnames[i].format;
-                }
-                gemu_log(format, scnames[i].name, arg1, arg2, arg3, arg4, arg5,
-                        arg6);
+                gemu_log(format, scnames[i].name, arg1, arg2, arg3, arg4,
+                         arg5, arg6);
            }
            return;
        }
-    }
    gemu_log("Unknown syscall %d\n", num);
 }

-static void print_syscall_ret(int num, abi_long ret,
-        const struct syscallname *scnames, unsigned int nscnames)
+static void
+print_syscall_ret(int num, abi_long ret, const struct syscallname *scnames,
+                  unsigned int nscnames)
 {
    unsigned int i;

-    for (i = 0; i < nscnames; i++) {
+    for (i = 0; i < nscnames; i++)
        if (scnames[i].nr == num) {
            if (scnames[i].result != NULL) {
                scnames[i].result(&scnames[i], ret);
            } else {
-                if (ret < 0) {
+                if( ret < 0 ) {
                    gemu_log(" = -1 errno=" TARGET_ABI_FMT_ld " (%s)\n", -ret,
                             strerror(-ret));
                } else {
@@ -193,50 +140,52 @@ static void print_syscall_ret(int num, abi_long ret,
            }
            break;
        }
-    }
 }

 /*
 * The public interface to this module.
 */
-void print_freebsd_syscall(int num, abi_long arg1, abi_long arg2, abi_long arg3,
-        abi_long arg4, abi_long arg5, abi_long arg6)
+void
+print_freebsd_syscall(int num,
+                      abi_long arg1, abi_long arg2, abi_long arg3,
+                      abi_long arg4, abi_long arg5, abi_long arg6)
 {
-
-    print_syscall(num, freebsd_scnames, ARRAY_SIZE(freebsd_scnames), arg1, arg2,
-            arg3, arg4, arg5, arg6);
+    print_syscall(num, freebsd_scnames, ARRAY_SIZE(freebsd_scnames),
+                  arg1, arg2, arg3, arg4, arg5, arg6);
 }

-void print_freebsd_syscall_ret(int num, abi_long ret)
+void
+print_freebsd_syscall_ret(int num, abi_long ret)
 {
-
    print_syscall_ret(num, ret, freebsd_scnames, ARRAY_SIZE(freebsd_scnames));
 }

-void print_netbsd_syscall(int num, abi_long arg1, abi_long arg2, abi_long arg3,
-        abi_long arg4, abi_long arg5, abi_long arg6)
+void
+print_netbsd_syscall(int num,
+                      abi_long arg1, abi_long arg2, abi_long arg3,
+                      abi_long arg4, abi_long arg5, abi_long arg6)
 {
-
    print_syscall(num, netbsd_scnames, ARRAY_SIZE(netbsd_scnames),
                  arg1, arg2, arg3, arg4, arg5, arg6);
 }

-void print_netbsd_syscall_ret(int num, abi_long ret)
+void
+print_netbsd_syscall_ret(int num, abi_long ret)
 {
-
    print_syscall_ret(num, ret, netbsd_scnames, ARRAY_SIZE(netbsd_scnames));
 }

-void print_openbsd_syscall(int num, abi_long arg1, abi_long arg2, abi_long arg3,
-        abi_long arg4, abi_long arg5, abi_long arg6)
+void
+print_openbsd_syscall(int num,
+                      abi_long arg1, abi_long arg2, abi_long arg3,
+                      abi_long arg4, abi_long arg5, abi_long arg6)
 {
-
-    print_syscall(num, openbsd_scnames, ARRAY_SIZE(openbsd_scnames), arg1, arg2,
-            arg3, arg4, arg5, arg6);
+    print_syscall(num, openbsd_scnames, ARRAY_SIZE(openbsd_scnames),
+                  arg1, arg2, arg3, arg4, arg5, arg6);
 }

-void print_openbsd_syscall_ret(int num, abi_long ret)
+void
+print_openbsd_syscall_ret(int num, abi_long ret)
 {
-
    print_syscall_ret(num, ret, openbsd_scnames, ARRAY_SIZE(openbsd_scnames));
 }
@@ -30,14 +30,20 @@ typedef struct {
    CoroutineAction action;
 } CoroutineGThread;

-static CompatGMutex coroutine_lock;
-static CompatGCond coroutine_cond;
+static GStaticMutex coroutine_lock = G_STATIC_MUTEX_INIT;

 /* GLib 2.31 and beyond deprecated various parts of the thread API,
 * but the new interfaces are not available in older GLib versions
 * so we have to cope with both.
 */
 #if GLIB_CHECK_VERSION(2, 31, 0)
+/* Default zero-initialisation is sufficient for 2.31+ GCond */
+static GCond the_coroutine_cond;
+static GCond *coroutine_cond = &the_coroutine_cond;
+static inline void init_coroutine_cond(void)
+{
+}
+
 /* Awkwardly, the GPrivate API doesn't provide a way to update the
 * GDestroyNotify handler for the coroutine key dynamically. So instead
 * we track whether or not the CoroutineGThread should be freed on
@@ -78,6 +84,11 @@ static inline GThread *create_thread(GThreadFunc func, gpointer data)
 #else

 /* Handle older GLib versions */
+static GCond *coroutine_cond;
+static inline void init_coroutine_cond(void)
+{
+    coroutine_cond = g_cond_new();
+}

 static GStaticPrivate coroutine_key = G_STATIC_PRIVATE_INIT;

@@ -104,25 +115,30 @@ static inline GThread *create_thread(GThreadFunc func, gpointer data)

 static void __attribute__((constructor)) coroutine_init(void)
 {
-#if !GLIB_CHECK_VERSION(2, 31, 0)
    if (!g_thread_supported()) {
+#if !GLIB_CHECK_VERSION(2, 31, 0)
        g_thread_init(NULL);
-    }
+#else
+        fprintf(stderr, "glib threading failed to initialize.\n");
+        exit(1);
 #endif
+    }
+
+    init_coroutine_cond();
 }

 static void coroutine_wait_runnable_locked(CoroutineGThread *co)
 {
    while (!co->runnable) {
-        g_cond_wait(&coroutine_cond, &coroutine_lock);
+        g_cond_wait(coroutine_cond, g_static_mutex_get_mutex(&coroutine_lock));
    }
 }

 static void coroutine_wait_runnable(CoroutineGThread *co)
 {
-    g_mutex_lock(&coroutine_lock);
+    g_static_mutex_lock(&coroutine_lock);
    coroutine_wait_runnable_locked(co);
-    g_mutex_unlock(&coroutine_lock);
+    g_static_mutex_unlock(&coroutine_lock);
 }

 static gpointer coroutine_thread(gpointer opaque)
@@ -164,17 +180,17 @@ CoroutineAction qemu_coroutine_switch(Coroutine *from_,
    CoroutineGThread *from = DO_UPCAST(CoroutineGThread, base, from_);
    CoroutineGThread *to = DO_UPCAST(CoroutineGThread, base, to_);

-    g_mutex_lock(&coroutine_lock);
+    g_static_mutex_lock(&coroutine_lock);
    from->runnable = false;
    from->action = action;
    to->runnable = true;
    to->action = action;
-    g_cond_broadcast(&coroutine_cond);
+    g_cond_broadcast(coroutine_cond);

    if (action != COROUTINE_TERMINATE) {
        coroutine_wait_runnable_locked(from);
    }
-    g_mutex_unlock(&coroutine_lock);
+    g_static_mutex_unlock(&coroutine_lock);
    return from->action;
 }

@@ -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) || \
@@ -331,38 +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);
-                    }
-#endif
-#if defined(TARGET_I386)
-                    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);
-                    }
-#else
-                    if (interrupt_request & CPU_INTERRUPT_RESET) {
-                        cpu_reset(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_SIPI) {
-                            do_cpu_sipi(x86_cpu);
+                    if (interrupt_request & CPU_INTERRUPT_INIT) {
+                            cpu_svm_check_intercept_param(env, SVM_EXIT_INIT,
+                                                          0);
+                            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_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)) {
@@ -399,10 +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;
@@ -411,6 +383,9 @@ int cpu_exec(CPUArchState *env)
                        }
                    }
 #elif defined(TARGET_PPC)
+                    if ((interrupt_request & CPU_INTERRUPT_RESET)) {
+                        cpu_reset(cpu);
+                    }
                    if (interrupt_request & CPU_INTERRUPT_HARD) {
                        ppc_hw_interrupt(env);
                        if (env->pending_interrupts == 0) {
@@ -421,7 +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;
                    }
@@ -430,7 +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;
                    }
@@ -438,7 +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;
@@ -455,7 +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;
                        }
@@ -470,7 +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;
                            }
@@ -478,8 +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;
                    }
@@ -494,15 +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;
                    }
@@ -537,7 +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;
@@ -547,7 +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;
                    }
@@ -559,7 +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;
                        }
@@ -573,7 +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;
                    }
@@ -585,7 +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;
                    }
@@ -601,11 +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 */
@@ -627,7 +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
@@ -657,25 +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;
                    }
@@ -696,13 +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(;;) */

@@ -26,7 +26,6 @@
 #include "config-host.h"

 #include "monitor/monitor.h"
-#include "qapi/qmp/qerror.h"
 #include "sysemu/sysemu.h"
 #include "exec/gdbstub.h"
 #include "sysemu/dma.h"
@@ -39,7 +38,6 @@
 #include "qemu/main-loop.h"
 #include "qemu/bitmap.h"
 #include "qemu/seqlock.h"
-#include "qapi-event.h"

 #ifndef _WIN32
 #include "qemu/compatfd.h"
@@ -78,7 +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;
    }
@@ -141,10 +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);
 }
@@ -349,7 +348,7 @@ void qtest_clock_warp(int64_t dest)
    assert(qtest_enabled());
    while (clock < dest) {
        int64_t deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL);
-        int64_t warp = qemu_soonest_timeout(dest - clock, deadline);
+        int64_t warp = MIN(dest - clock, deadline);
        seqlock_write_lock(&timers_state.vm_clock_seqlock);
        qemu_icount_bias += warp;
        seqlock_write_unlock(&timers_state.vm_clock_seqlock);
@@ -432,7 +431,8 @@ static const VMStateDescription vmstate_timers = {
    .name = "timer",
    .version_id = 2,
    .minimum_version_id = 1,
-    .fields = (VMStateField[]) {
+    .minimum_version_id_old = 1,
+    .fields      = (VMStateField[]) {
        VMSTATE_INT64(cpu_ticks_offset, TimersState),
        VMSTATE_INT64(dummy, TimersState),
        VMSTATE_INT64_V(cpu_clock_offset, TimersState, 2),
@@ -523,15 +523,6 @@ void cpu_synchronize_all_post_init(void)
    }
 }

-void cpu_clean_all_dirty(void)
-{
-    CPUState *cpu;
-
-    CPU_FOREACH(cpu) {
-        cpu_clean_state(cpu);
-    }
-}
-
 static int do_vm_stop(RunState state)
 {
    int ret = 0;
@@ -541,7 +532,7 @@ static int do_vm_stop(RunState state)
        pause_all_vcpus();
        runstate_set(state);
        vm_state_notify(0, state);
-        qapi_event_send_stop(&error_abort);
+        monitor_protocol_event(QEVENT_STOP, NULL);
    }

    bdrv_drain_all();
@@ -1126,25 +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
@@ -1160,15 +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);
    }
@@ -1176,14 +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);
@@ -1217,7 +1191,6 @@ void cpu_stop_current(void)
 int vm_stop(RunState state)
 {
    if (qemu_in_vcpu_thread()) {
-        qemu_system_vmstop_request_prepare();
        qemu_system_vmstop_request(state);
        /*
         * FIXME: should not return to device code in case
@@ -1246,7 +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;
@@ -1259,9 +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
@@ -1277,8 +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
@@ -1287,9 +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;
 }
@@ -1324,6 +1297,20 @@ static void tcg_exec_all(void)
    exit_request = 0;
 }

+void set_numa_modes(void)
+{
+    CPUState *cpu;
+    int i;
+
+    CPU_FOREACH(cpu) {
+        for (i = 0; i < nb_numa_nodes; i++) {
+            if (test_bit(cpu->cpu_index, node_cpumask[i])) {
+                cpu->numa_node = i;
+            }
+        }
+    }
+}
+
 void list_cpus(FILE *f, fprintf_function cpu_fprintf, const char *optarg)
 {
    /* XXX: implement xxx_cpu_list for targets that still miss it */
@@ -1451,7 +1438,7 @@ void qmp_pmemsave(int64_t addr, int64_t size, const char *filename,
        l = sizeof(buf);
        if (l > size)
            l = size;
-        cpu_physical_memory_read(addr, buf, l);
+        cpu_physical_memory_rw(addr, buf, l, 0);
        if (fwrite(buf, 1, l, f) != l) {
            error_set(errp, QERR_IO_ERROR);
            goto exit;
@@ -1471,11 +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)
@@ -22,13 +22,10 @@
 #include "exec/exec-all.h"
 #include "exec/memory.h"
 #include "exec/address-spaces.h"
-#include "exec/cpu_ldst.h"

 #include "exec/cputlb.h"

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

 //#define DEBUG_TLB
 //#define DEBUG_TLB_CHECK
@@ -36,6 +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
@@ -48,9 +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");
@@ -59,8 +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;
@@ -75,13 +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;

@@ -95,7 +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
@@ -108,23 +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)
@@ -223,11 +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;
@@ -242,7 +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);

@@ -263,7 +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);
@@ -287,8 +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;
@@ -308,7 +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);
@@ -317,14 +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);
        }
    }
@@ -332,21 +343,6 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr)
    return qemu_ram_addr_from_host_nofail(p);
 }

-#define MMUSUFFIX _mmu
-
-#define SHIFT 0
-#include "softmmu_template.h"
-
-#define SHIFT 1
-#include "softmmu_template.h"
-
-#define SHIFT 2
-#include "softmmu_template.h"
-
-#define SHIFT 3
-#include "softmmu_template.h"
-#undef MMUSUFFIX
-
 #define MMUSUFFIX _cmmu
 #undef GETPC_ADJ
 #define GETPC_ADJ 0
@@ -355,13 +351,15 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr)
 #define SOFTMMU_CODE_ACCESS

 #define SHIFT 0
-#include "softmmu_template.h"
+#include "exec/softmmu_template.h"

 #define SHIFT 1
-#include "softmmu_template.h"
+#include "exec/softmmu_template.h"

 #define SHIFT 2
-#include "softmmu_template.h"
+#include "exec/softmmu_template.h"

 #define SHIFT 3
-#include "softmmu_template.h"
+#include "exec/softmmu_template.h"
+
+#undef env
@@ -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
@@ -44,4 +44,3 @@ CONFIG_APIC=y
 CONFIG_IOAPIC=y
 CONFIG_ICC_BUS=y
 CONFIG_PVPANIC=y
-CONFIG_MEM_HOTPLUG=y
@@ -1,2 +1 @@
 # Default configuration for ppc-linux-user
-CONFIG_LIBDECNUMBER=y
@@ -41,12 +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
-CONFIG_LIBDECNUMBER=y
--- a/Show More
+++ b/Show More
@@ -1 +1 @@
 .1.3
 .7.2