Update VERSION for 1.6.1 release

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>

.gitignore

@@ -1,67 +1,65 @@
-/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/qmp-commands.txt
+test-coroutine
+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 +73,34 @@
 *.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

.gitmodules

@@ -1,33 +1,27 @@
 [submodule "roms/vgabios"]
 	path = roms/vgabios
-	url = git://git.qemu-project.org/vgabios.git/
+	url = git://git.qemu.org/vgabios.git/
 [submodule "roms/seabios"]
 	path = roms/seabios
-	url = git://git.qemu-project.org/seabios.git/
+	url = git://git.qemu.org/seabios.git/
 [submodule "roms/SLOF"]
 	path = roms/SLOF
-	url = git://git.qemu-project.org/SLOF.git
+	url = git://git.qemu.org/SLOF.git
 [submodule "roms/ipxe"]
 	path = roms/ipxe
-	url = git://git.qemu-project.org/ipxe.git
+	url = git://git.qemu.org/ipxe.git
 [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
+	url = git://git.qemu.org/openbios.git
 [submodule "roms/qemu-palcode"]
 	path = roms/qemu-palcode
 	url = git://github.com/rth7680/qemu-palcode.git
 [submodule "roms/sgabios"]
 	path = roms/sgabios
-	url = git://git.qemu-project.org/sgabios.git
+	url = git://git.qemu.org/sgabios.git
 [submodule "pixman"]
 	path = pixman
 	url = git://anongit.freedesktop.org/pixman
 [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
+	url = git://git.qemu.org/dtc.git

.mailmap

@@ -2,8 +2,7 @@
 # into proper addresses so that they are counted properly in git shortlog output.
 #
 Andrzej Zaborowski <balrogg@gmail.com> balrog <balrog@c046a42c-6fe2-441c-8c8c-71466251a162>
-Anthony Liguori <anthony@codemonkey.ws> aliguori <aliguori@c046a42c-6fe2-441c-8c8c-71466251a162>
-Anthony Liguori <anthony@codemonkey.ws> Anthony Liguori <aliguori@us.ibm.com>
+Anthony Liguori <aliguori@us.ibm.com> aliguori <aliguori@c046a42c-6fe2-441c-8c8c-71466251a162>
 Aurelien Jarno <aurelien@aurel32.net> aurel32 <aurel32@c046a42c-6fe2-441c-8c8c-71466251a162>
 Blue Swirl <blauwirbel@gmail.com> blueswir1 <blueswir1@c046a42c-6fe2-441c-8c8c-71466251a162>
 Edgar E. Iglesias <edgar.iglesias@gmail.com> edgar_igl <edgar_igl@c046a42c-6fe2-441c-8c8c-71466251a162>

.travis.yml

@@ -1,81 +0,0 @@
-language: c
-python:
-  - "2.4"
-compiler:
-  - gcc
-  - clang
-notifications:
-  irc:
-    channels:
-      - "irc.oftc.net#qemu"
-    on_success: change
-    on_failure: always
-env:
-  global:
-    - TEST_CMD="make check"
-    - EXTRA_CONFIG=""
-    # Development packages, EXTRA_PKGS saved for additional builds
-    - CORE_PKGS="libusb-1.0-0-dev libiscsi-dev librados-dev libncurses5-dev"
-    - NET_PKGS="libseccomp-dev libgnutls-dev libssh2-1-dev  libspice-server-dev libspice-protocol-dev libnss3-dev"
-    - 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
-before_install:
-  - git submodule update --init --recursive
-  - sudo apt-get update -qq
-  - sudo apt-get install -qq ${CORE_PKGS} ${NET_PKGS} ${GUI_PKGS} ${EXTRA_PKGS}
-script: "./configure --target-list=${TARGETS} ${EXTRA_CONFIG} && make && ${TEST_CMD}"
-matrix:
-  # We manually include a number of additional build for non-standard bits
-  include:
-    # Debug related options
-    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-debug"
-      compiler: gcc
-    - 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"
-      compiler: gcc
-    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_PKGS="sparse"
-           EXTRA_CONFIG="--enable-sparse"
-      compiler: gcc
-    # All the trace backends (apart from dtrace)
-    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-trace-backends=stderr"
-      compiler: gcc
-    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-trace-backends=simple"
-      compiler: gcc
-    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-trace-backends=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

CODING_STYLE

@@ -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.

Changelog

@@ -1,6 +1,6 @@
 This file documents changes for QEMU releases 0.12 and earlier.
 For changelog information for later releases, see
-http://wiki.qemu-project.org/ChangeLog or look at the git history for
+http://wiki.qemu.org/ChangeLog or look at the git history for
 more detailed information.
 
 

MAINTAINERS

@@ -50,14 +50,8 @@ Descriptions of section entries:
 
 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
+M: Anthony Liguori <aliguori@us.ibm.com>
+M: Paul Brook <paul@codesourcery.com>
 
 Guest CPU cores (TCG):
 ----------------------
@@ -68,6 +62,7 @@ F: target-alpha/
 F: hw/alpha/
 
 ARM
+M: Paul Brook <paul@codesourcery.com>
 M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
 F: target-arm/
@@ -88,7 +83,8 @@ F: hw/lm32/
 F: hw/char/lm32_*
 
 M68K
-S: Orphan
+M: Paul Brook <paul@codesourcery.com>
+S: Odd Fixes
 F: target-m68k/
 F: hw/m68k/
 
@@ -165,6 +161,7 @@ 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 +173,18 @@ 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 +222,6 @@ 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 +231,11 @@ 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
@@ -271,6 +248,7 @@ F: hw/*/imx*
 F: hw/arm/kzm.c
 
 Integrator CP
+M: Paul Brook <paul@codesourcery.com>
 M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
 F: hw/arm/integratorcp.c
@@ -296,6 +274,7 @@ S: Maintained
 F: hw/arm/palm.c
 
 Real View
+M: Paul Brook <paul@codesourcery.com>
 M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
 F: hw/arm/realview*
@@ -306,17 +285,19 @@ S: Maintained
 F: hw/arm/spitz.c
 
 Stellaris
+M: Paul Brook <paul@codesourcery.com>
 M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
 F: hw/*/stellaris*
 
 Versatile PB
+M: Paul Brook <paul@codesourcery.com>
 M: Peter Maydell <peter.maydell@linaro.org>
 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
@@ -346,15 +327,18 @@ F: hw/lm32/milkymist.c
 M68K Machines
 -------------
 an5206
-S: Orphan
+M: Paul Brook <paul@codesourcery.com>
+S: Maintained
 F: hw/m68k/an5206.c
 
 dummy_m68k
-S: Orphan
+M: Paul Brook <paul@codesourcery.com>
+S: Maintained
 F: hw/m68k/dummy_m68k.c
 
 mcf5208
-S: Orphan
+M: Paul Brook <paul@codesourcery.com>
+S: Maintained
 F: hw/m68k/mcf5208.c
 
 MicroBlaze Machines
@@ -365,7 +349,7 @@ 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 +492,10 @@ 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
@@ -528,24 +509,10 @@ F: hw/unicore32/
 X86 Machines
 ------------
 PC
-M: Anthony Liguori <aliguori@amazon.com>
-M: Michael S. Tsirkin <mst@redhat.com>
+M: Anthony Liguori <aliguori@us.ibm.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 +530,6 @@ 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/
@@ -601,11 +567,12 @@ F: hw/scsi/*
 T: git git://github.com/bonzini/qemu.git scsi-next
 
 LSI53C895A
-S: Orphan
+M: Paul Brook <paul@codesourcery.com>
+S: Odd Fixes
 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 +581,6 @@ 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>
@@ -627,8 +593,7 @@ S: Supported
 F: hw/*/*vhost*
 
 virtio
-M: Anthony Liguori <aliguori@amazon.com>
-M: Michael S. Tsirkin <mst@redhat.com>
+M: Anthony Liguori <aliguori@us.ibm.com>
 S: Supported
 F: hw/*/virtio*
 
@@ -637,7 +602,6 @@ 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 +612,6 @@ 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 +626,9 @@ 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_*
@@ -682,13 +638,9 @@ Subsystems
 ----------
 Audio
 M: Vassili Karpov (malc) <av1474@comtv.ru>
-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>
@@ -697,13 +649,9 @@ 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
 
 Character Devices
-M: Anthony Liguori <aliguori@amazon.com>
+M: Anthony Liguori <aliguori@us.ibm.com>
 S: Maintained
 F: qemu-char.c
 
@@ -721,7 +669,7 @@ 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 +680,6 @@ 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
@@ -751,45 +689,34 @@ F: audio/spiceaudio.c
 F: hw/display/qxl*
 
 Graphics
-M: Anthony Liguori <aliguori@amazon.com>
-M: Gerd Hoffmann <kraxel@redhat.com>
-S: Odd Fixes
+M: Anthony Liguori <aliguori@us.ibm.com>
+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
 
 Main loop
-M: Anthony Liguori <aliguori@amazon.com>
+M: Anthony Liguori <aliguori@us.ibm.com>
 S: Supported
 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
-T: git git://repo.or.cz/qemu/qmp-unstable.git queue/qmp
 
 Network device layer
-M: Anthony Liguori <aliguori@amazon.com>
+M: Anthony Liguori <aliguori@us.ibm.com>
 M: Stefan Hajnoczi <stefanha@redhat.com>
 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
@@ -801,9 +728,8 @@ 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
 
 QAPI Schema
 M: Eric Blake <eblake@redhat.com>
@@ -811,27 +737,14 @@ M: Luiz Capitulino <lcapitulino@redhat.com>
 M: Markus Armbruster <armbru@redhat.com>
 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
 F: QMP/
-T: git git://repo.or.cz/qemu/qmp-unstable.git queue/qmp
 
 SLIRP
 M: Jan Kiszka <jan.kiszka@siemens.com>
@@ -853,12 +766,6 @@ M: Blue Swirl <blauwirbel@gmail.com>
 S: Odd Fixes
 F: scripts/checkpatch.pl
 
-Seccomp
-M: Eduardo Otubo <eduardo.otubo@profitbricks.com>
-S: Supported
-F: qemu-seccomp.c
-F: include/sysemu/seccomp.h
-
 Usermode Emulation
 ------------------
 BSD user
@@ -890,6 +797,11 @@ M: Andrzej Zaborowski <balrogg@gmail.com>
 S: Maintained
 F: tcg/arm/
 
+HPPA target
+M: Richard Henderson <rth@twiddle.net>
+S: Maintained
+F: tcg/hppa/
+
 i386 target
 M: qemu-devel@nongnu.org
 S: Maintained
@@ -930,73 +842,25 @@ TCI target
 M: Stefan Weil <sw@weilnetz.de>
 S: Maintained
 F: tcg/tci/
-F: tci.c
 
 Stable branches
 ---------------
 Stable 1.0
 L: qemu-stable@nongnu.org
-T: git git://git.qemu-project.org/qemu-stable-1.0.git
+T: git git://git.qemu.org/qemu-stable-1.0.git
 S: Orphan
 
 Stable 0.15
 L: qemu-stable@nongnu.org
-M: Andreas Färber <afaerber@suse.de>
-T: git git://git.qemu-project.org/qemu-stable-0.15.git
-S: Supported
+T: git git://git.qemu.org/qemu-stable-0.15.git
+S: Orphan
 
 Stable 0.14
 L: qemu-stable@nongnu.org
-T: git git://git.qemu-project.org/qemu-stable-0.14.git
+T: git git://git.qemu.org/qemu-stable-0.14.git
 S: Orphan
 
 Stable 0.10
 L: qemu-stable@nongnu.org
-T: git git://git.qemu-project.org/qemu-stable-0.10.git
+T: git git://git.qemu.org/qemu-stable-0.10.git
 S: Orphan
-
-Block drivers
--------------
-VMDK
-M: Fam Zheng <famz@redhat.com>
-S: Supported
-F: block/vmdk.c
-
-RBD
-M: Josh Durgin <josh.durgin@inktank.com>
-S: Supported
-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
-
-VHDX
-M: Jeff Cody <jcody@redhat.com>
-S: Supported
-F: block/vhdx*
-
-VDI
-M: Stefan Weil <sw@weilnetz.de>
-S: Maintained
-F: block/vdi.c
-
-iSCSI
-M: Ronnie Sahlberg <ronniesahlberg@gmail.com>
-M: Paolo Bonzini <pbonzini@redhat.com>
-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
-F: block/ssh.c

Makefile

@@ -28,14 +28,7 @@ CONFIG_ALL=y
 include $(SRC_PATH)/rules.mak
 config-host.mak: $(SRC_PATH)/configure
 	@echo $@ is out-of-date, running configure
-	@# TODO: The next lines include code which supports a smooth
-	@# transition from old configurations without config.status.
-	@# This code can be removed after QEMU 1.7.
-	@if test -x config.status; then \
-	    ./config.status; \
-        else \
-	    sed -n "/.*Configured with/s/[^:]*: //p" $@ | sh; \
-	fi
+	@sed -n "/.*Configured with/s/[^:]*: //p" $@ | sh
 else
 config-host.mak:
 ifneq ($(filter-out %clean,$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
@@ -45,23 +38,18 @@ 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: ;
@@ -77,7 +65,7 @@ LIBS+=-lz $(LIBS_TOOLS)
 HELPERS-$(CONFIG_LINUX) = qemu-bridge-helper$(EXESUF)
 
 ifdef BUILD_DOCS
-DOCS=qemu-doc.html qemu-tech.html qemu.1 qemu-img.1 qemu-nbd.8 qmp-commands.txt
+DOCS=qemu-doc.html qemu-tech.html qemu.1 qemu-img.1 qemu-nbd.8 QMP/qmp-commands.txt
 ifdef CONFIG_VIRTFS
 DOCS+=fsdev/virtfs-proxy-helper.1
 endif
@@ -127,26 +115,13 @@ 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 +131,6 @@ 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-%:
@@ -191,10 +165,10 @@ 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
-	$(call quiet-command,$(WINDRES) -I$(BUILD_DIR) -o $@ $<,"  RC    version.lo")
 
 Makefile: $(version-obj-y) $(version-lobj-y)
 
@@ -202,10 +176,7 @@ 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 +203,23 @@ 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)
@@ -281,10 +231,10 @@ 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 {} +
-	rm -f $(filter-out %.tlb,$(TOOLS)) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
-	rm -f fsdev/*.pod
-	rm -rf .libs */.libs
+	find . -name '*.[oda]' -type f -exec rm -f {} +
+	find . -name '*.l[oa]' -type f -exec rm -f {} +
+	rm -f $(TOOLS) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
+	rm -Rf .libs
 	rm -f qemu-img-cmds.h
 	@# May not be present in GENERATED_HEADERS
 	rm -f trace/generated-tracers-dtrace.dtrace*
@@ -293,6 +243,7 @@ clean:
 	rm -f $(foreach f,$(GENERATED_SOURCES),$(f) $(f)-timestamp)
 	rm -rf qapi-generated
 	rm -rf qga/qapi-generated
+	$(MAKE) -C tests/tcg clean
 	for d in $(ALL_SUBDIRS); do \
 	if test -d $$d; then $(MAKE) -C $$d $@ || exit 1; fi; \
 	rm -f $$d/qemu-options.def; \
@@ -308,7 +259,6 @@ qemu-%.tar.bz2:
 distclean: clean
 	rm -f config-host.mak config-host.h* config-host.ld $(DOCS) qemu-options.texi qemu-img-cmds.texi qemu-monitor.texi
 	rm -f config-all-devices.mak config-all-disas.mak
-	rm -f po/*.mo
 	rm -f roms/seabios/config.mak roms/vgabios/config.mak
 	rm -f qemu-doc.info qemu-doc.aux qemu-doc.cp qemu-doc.cps qemu-doc.dvi
 	rm -f qemu-doc.fn qemu-doc.fns qemu-doc.info qemu-doc.ky qemu-doc.kys
@@ -320,20 +270,19 @@ distclean: clean
 	for d in $(TARGET_DIRS); do \
 	rm -rf $$d || exit 1 ; \
         done
-	rm -Rf .sdk
 	if test -f pixman/config.log; then make -C pixman distclean; fi
 	if test -f dtc/version_gen.h; then make $(DTC_MAKE_ARGS) clean; fi
 
 KEYMAPS=da     en-gb  et  fr     fr-ch  is  lt  modifiers  no  pt-br  sv \
 ar      de     en-us  fi  fr-be  hr     it  lv  nl         pl  ru     th \
 common  de-ch  es     fo  fr-ca  hu     ja  mk  nl-be      pt  sl     tr \
-bepo    cz
+bepo
 
 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 \
 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 +293,7 @@ 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
@@ -353,7 +301,7 @@ endif
 install-doc: $(DOCS)
 	$(INSTALL_DIR) "$(DESTDIR)$(qemu_docdir)"
 	$(INSTALL_DATA) qemu-doc.html  qemu-tech.html "$(DESTDIR)$(qemu_docdir)"
-	$(INSTALL_DATA) qmp-commands.txt "$(DESTDIR)$(qemu_docdir)"
+	$(INSTALL_DATA) QMP/qmp-commands.txt "$(DESTDIR)$(qemu_docdir)"
 ifdef CONFIG_POSIX
 	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man1"
 	$(INSTALL_DATA) qemu.1 "$(DESTDIR)$(mandir)/man1"
@@ -386,19 +334,13 @@ 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) "$$t"; \
-	done
+	$(INSTALL_PROG) $(STRIP_OPT) $(TOOLS) "$(DESTDIR)$(bindir)"
 endif
 ifneq ($(HELPERS-y),)
-	$(call install-prog,$(HELPERS-y),$(DESTDIR)$(libexecdir))
+	$(INSTALL_DIR) "$(DESTDIR)$(libexecdir)"
+	$(INSTALL_PROG) $(STRIP_OPT) $(HELPERS-y) "$(DESTDIR)$(libexecdir)"
 endif
 ifneq ($(BLOBS),)
 	set -e; for x in $(BLOBS); do \
@@ -413,7 +355,7 @@ endif
 		$(INSTALL_DATA) $(SRC_PATH)/pc-bios/keymaps/$$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
@@ -453,7 +395,7 @@ qemu-options.texi: $(SRC_PATH)/qemu-options.hx
 qemu-monitor.texi: $(SRC_PATH)/hmp-commands.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"  GEN   $@")
 
-qmp-commands.txt: $(SRC_PATH)/qmp-commands.hx
+QMP/qmp-commands.txt: $(SRC_PATH)/qmp-commands.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -q < $< > $@,"  GEN   $@")
 
 qemu-img-cmds.texi: $(SRC_PATH)/qemu-img-cmds.hx

Makefile.objs

@@ -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-$(CONFIG_SLIRP) += slirp/
@@ -112,4 +109,17 @@ version-lobj-$(CONFIG_WIN32) += $(BUILD_DIR)/version.lo
 # FIXME: a few definitions from qapi-types.o/qapi-visit.o are needed
 # by libqemuutil.a.  These should be moved to a separate .json schema.
 qga-obj-y = qga/ qapi-types.o qapi-visit.o
-qga-vss-dll-obj-y = qga/
+
+vl.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
+
+vl.o: QEMU_CFLAGS+=$(SDL_CFLAGS)
+
+QEMU_CFLAGS+=$(GLIB_CFLAGS)
+
+nested-vars += \
+	stub-obj-y \
+	util-obj-y \
+	qga-obj-y \
+	block-obj-y \
+	common-obj-y
+dummy := $(call unnest-vars)

Makefile.target

@@ -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) \
@@ -73,6 +70,10 @@ all: $(PROGS) stap
 # Dummy command so that make thinks it has done something
 	@true
 
+CONFIG_NO_PCI = $(if $(subst n,,$(CONFIG_PCI)),n,y)
+CONFIG_NO_KVM = $(if $(subst n,,$(CONFIG_KVM)),n,y)
+CONFIG_NO_XEN = $(if $(subst n,,$(CONFIG_XEN)),n,y)
+
 #########################################################
 # cpu emulator library
 obj-y = exec.o translate-all.o cpu-exec.o
@@ -82,14 +83,8 @@ obj-$(CONFIG_TCG_INTERPRETER) += disas/tci.o
 obj-y += fpu/softfloat.o
 obj-y += target-$(TARGET_BASE_ARCH)/
 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-$(CONFIG_LIBDECNUMBER) += libdecnumber/dpd/decimal128.o
+obj-$(CONFIG_GDBSTUB_XML) += gdbstub-xml.o
+obj-$(CONFIG_NO_KVM) += kvm-stub.o
 
 #########################################################
 # Linux user emulator target
@@ -108,8 +103,7 @@ 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 +113,7 @@ 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-$(CONFIG_FDT) += device_tree.o
@@ -130,10 +124,8 @@ obj-y += dump.o
 LIBS+=$(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-$(CONFIG_XEN) += xen-all.o xen-mapcache.o
+obj-$(CONFIG_NO_XEN) += xen-stub.o
 
 # Hardware support
 ifeq ($(TARGET_NAME), sparc64)
@@ -142,6 +134,8 @@ else
 obj-y += hw/$(TARGET_BASE_ARCH)/
 endif
 
+main.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
+
 GENERATED_HEADERS += hmp-commands.h qmp-commands-old.h
 
 endif # CONFIG_SOFTMMU
@@ -149,23 +143,28 @@ 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 +185,10 @@ 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"

QMP/README

@@ -0,0 +1,88 @@
+                          QEMU Monitor Protocol
+                          =====================
+
+Introduction
+-------------
+
+The QEMU Monitor Protocol (QMP) allows applications to communicate with
+QEMU's Monitor.
+
+QMP is JSON[1] based and currently has the following features:
+
+- Lightweight, text-based, easy to parse data format
+- Asynchronous messages support (ie. events)
+- Capabilities Negotiation
+
+For detailed information on QMP's usage, please, refer to the following files:
+
+o qmp-spec.txt      QEMU Monitor Protocol current specification
+o qmp-commands.txt  QMP supported commands (auto-generated at build-time)
+o qmp-events.txt    List of available asynchronous events
+
+There is also a simple Python script called 'qmp-shell' available.
+
+IMPORTANT: It's strongly recommended to read the 'Stability Considerations'
+section in the qmp-commands.txt file before making any serious use of QMP.
+
+
+[1] http://www.json.org
+
+Usage
+-----
+
+To enable QMP, you need a QEMU monitor instance in "control mode". There are
+two ways of doing this.
+
+The simplest one is using the '-qmp' command-line option. The following
+example makes QMP available on localhost port 4444:
+
+  $ qemu [...] -qmp tcp:localhost:4444,server
+
+However, in order to have more complex combinations, like multiple monitors,
+the '-mon' command-line option should be used along with the '-chardev' one.
+For instance, the following example creates one user monitor on stdio and one
+QMP monitor on localhost port 4444.
+
+   $ qemu [...] -chardev stdio,id=mon0 -mon chardev=mon0,mode=readline \
+                -chardev socket,id=mon1,host=localhost,port=4444,server \
+                -mon chardev=mon1,mode=control
+
+Please, refer to QEMU's manpage for more information.
+
+Simple Testing
+--------------
+
+To manually test QMP one can connect with telnet and issue commands by hand:
+
+$ telnet localhost 4444
+Trying 127.0.0.1...
+Connected to localhost.
+Escape character is '^]'.
+{"QMP": {"version": {"qemu": {"micro": 50, "minor": 13, "major": 0}, "package": ""}, "capabilities": []}}
+{ "execute": "qmp_capabilities" }
+{"return": {}}
+{ "execute": "query-version" }
+{"return": {"qemu": {"micro": 50, "minor": 13, "major": 0}, "package": ""}}
+
+Development Process
+-------------------
+
+When changing QMP's interface (by adding new commands, events or modifying
+existing ones) it's mandatory to update the relevant documentation, which is
+one (or more) of the files listed in the 'Introduction' section*.
+
+Also, it's strongly recommended to send the documentation patch first, before
+doing any code change. This is so because:
+
+  1. Avoids the code dictating the interface
+
+  2. Review can improve your interface.  Letting that happen before
+     you implement it can save you work.
+
+* The qmp-commands.txt file is generated from the qmp-commands.hx one, which
+  is the file that should be edited.
+
+Homepage
+--------
+
+http://wiki.qemu.org/QMP

QMP/qemu-ga-client

@@ -33,7 +33,7 @@
 # $ qemu-ga-client fsfreeze freeze
 # 2 filesystems frozen
 #
-# See also: http://wiki.qemu-project.org/Features/QAPI/GuestAgent
+# See also: http://wiki.qemu.org/Features/QAPI/GuestAgent
 #
 
 import base64
@@ -267,9 +267,7 @@ def main(address, cmd, args):
             print('Hint: qemu is not running?')
         sys.exit(1)
 
-    if cmd == 'fsfreeze' and args[0] == 'freeze':
-        client.sync(60)
-    elif cmd != 'ping':
+    if cmd != 'ping':
         client.sync()
 
     globals()['_cmd_' + cmd](client, args)

QMP/qmp-events.txt

@@ -1,16 +1,6 @@
-                   QEMU Machine Protocol Events
+                   QEMU Monitor Protocol Events
                    ============================
 
-ACPI_DEVICE_OST
----------------
-
-Emitted when guest executes ACPI _OST method.
-
- - data: ACPIOSTInfo type as described in qapi-schema.json
-
-{ "event": "ACPI_DEVICE_OST",
-     "data": { "device": "d1", "slot": "0", "slot-type": "DIMM", "source": 1, "status": 0 } }
-
 BALLOON_CHANGE
 --------------
 
@@ -28,28 +18,6 @@ Example:
     "data": { "actual": 944766976 },
     "timestamp": { "seconds": 1267020223, "microseconds": 435656 } }
 
-BLOCK_IMAGE_CORRUPTED
----------------------
-
-Emitted when a disk image is being marked corrupt.
-
-Data:
-
-- "device": Device name (json-string)
-- "msg":    Informative message (e.g., reason for the corruption) (json-string)
-- "offset": If the corruption resulted from an image access, this is the access
-            offset into the image (json-int)
-- "size":   If the corruption resulted from an image access, this is the access
-            size (json-int)
-
-Example:
-
-{ "event": "BLOCK_IMAGE_CORRUPTED",
-    "data": { "device": "ide0-hd0",
-        "msg": "Prevented active L1 table overwrite", "offset": 196608,
-        "size": 65536 },
-    "timestamp": { "seconds": 1378126126, "microseconds": 966463 } }
-
 BLOCK_IO_ERROR
 --------------
 
@@ -62,7 +30,7 @@ Data:
 - "action": action that has been taken, it's one of the following (json-string):
     "ignore": error has been ignored
     "report": error has been reported to the device
-    "stop": the VM is going to stop because of the error
+    "stop": error caused VM to be stopped
 
 Example:
 
@@ -157,27 +125,19 @@ Emitted when a block job is ready to complete.
 
 Data:
 
-- "type":     Job type (json-string; "stream" for image streaming
-                                     "commit" for block commit)
-- "device":   Device name (json-string)
-- "len":      Maximum progress value (json-int)
-- "offset":   Current progress value (json-int)
-              On success this is equal to len.
-              On failure this is less than len.
-- "speed":    Rate limit, bytes per second (json-int)
+- "device": device name (json-string)
 
 Example:
 
 { "event": "BLOCK_JOB_READY",
-    "data": { "device": "drive0", "type": "mirror", "speed": 0,
-              "len": 2097152, "offset": 2097152 }
+    "data": { "device": "ide0-hd1" },
     "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
 
 Note: The "ready to complete" status is always reset by a BLOCK_JOB_ERROR
 event.
 
 DEVICE_DELETED
---------------
+-----------------
 
 Emitted whenever the device removal completion is acknowledged
 by the guest.
@@ -212,22 +172,8 @@ Data:
   },
   "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
 
-GUEST_PANICKED
---------------
-
-Emitted when guest OS panic is detected.
-
-Data:
-
-- "action": Action that has been taken (json-string, currently always "pause").
-
-Example:
-
-{ "event": "GUEST_PANICKED",
-     "data": { "action": "pause" } }
-
 NIC_RX_FILTER_CHANGED
----------------------
+-----------------
 
 The event is emitted once until the query command is executed,
 the first event will always be emitted.
@@ -243,62 +189,10 @@ Data:
   "timestamp": { "seconds": 1368697518, "microseconds": 326866 } }
 }
 
-POWERDOWN
----------
-
-Emitted when the Virtual Machine is powered down through the power
-control system, such as via ACPI.
-
-Data: None.
-
-Example:
-
-{ "event": "POWERDOWN",
-    "timestamp": { "seconds": 1267040730, "microseconds": 682951 } }
-
-QUORUM_FAILURE
---------------
-
-Emitted by the Quorum block driver if it fails to establish a quorum.
-
-Data:
-
-- "reference":     device name if defined else node name.
-- "sector-num":    Number of the first sector of the failed read operation.
-- "sectors-count": Failed read operation sector count.
-
-Example:
-
-{ "event": "QUORUM_FAILURE",
-     "data": { "reference": "usr1", "sector-num": 345435, "sectors-count": 5 },
-     "timestamp": { "seconds": 1344522075, "microseconds": 745528 } }
-
-QUORUM_REPORT_BAD
------------------
-
-Emitted to report a corruption of a Quorum file.
-
-Data:
-
-- "error":         Error message (json-string, optional)
-                   Only present on failure.  This field contains a human-readable
-                   error message.  There are no semantics other than that the
-                   block layer reported an error and clients should not try to
-                   interpret the error string.
-- "node-name":     The graph node name of the block driver state.
-- "sector-num":    Number of the first sector of the failed read operation.
-- "sectors-count": Failed read operation sector count.
-
-Example:
-
-{ "event": "QUORUM_REPORT_BAD",
-     "data": { "node-name": "1.raw", "sector-num": 345435, "sectors-count": 5 },
-     "timestamp": { "seconds": 1344522075, "microseconds": 745528 } }
-
 RESET
 -----
 
-Emitted when the Virtual Machine is reset.
+Emitted when the Virtual Machine is reseted.
 
 Data: None.
 
@@ -338,8 +232,7 @@ Example:
 SHUTDOWN
 --------
 
-Emitted when the Virtual Machine has shut down, indicating that qemu
-is about to exit.
+Emitted when the Virtual Machine is powered down.
 
 Data: None.
 
@@ -351,10 +244,10 @@ Example:
 Note: If the command-line option "-no-shutdown" has been specified, a STOP
 event will eventually follow the SHUTDOWN event.
 
-SPICE_CONNECTED
----------------
+SPICE_CONNECTED, SPICE_DISCONNECTED
+-----------------------------------
 
-Emitted when a SPICE client connects.
+Emitted when a SPICE client connects or disconnects.
 
 Data:
 
@@ -376,36 +269,11 @@ Example:
     "client": {"port": "52873", "family": "ipv4", "host": "127.0.0.1"}
 }}
 
-SPICE_DISCONNECTED
-------------------
-
-Emitted when a SPICE client disconnects.
-
-Data:
-
-- "server": Server information (json-object)
-  - "host": IP address (json-string)
-  - "port": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-- "client": Client information (json-object)
-  - "host": IP address (json-string)
-  - "port": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-
-Example:
-
-{ "timestamp": {"seconds": 1290688046, "microseconds": 388707},
-  "event": "SPICE_DISCONNECTED",
-  "data": {
-    "server": { "port": "5920", "family": "ipv4", "host": "127.0.0.1"},
-    "client": {"port": "52873", "family": "ipv4", "host": "127.0.0.1"}
-}}
-
 SPICE_INITIALIZED
 -----------------
 
 Emitted after initial handshake and authentication takes place (if any)
-and the SPICE channel is up and running
+and the SPICE channel is up'n'running
 
 Data:
 
@@ -438,19 +306,6 @@ Example:
                       "channel-id": 0, "tls": true}
 }}
 
-SPICE_MIGRATE_COMPLETED
------------------------
-
-Emitted when SPICE migration has completed
-
-Data: None.
-
-Example:
-
-{ "timestamp": {"seconds": 1290688046, "microseconds": 417172},
-  "event": "SPICE_MIGRATE_COMPLETED" }
-
-
 STOP
 ----
 
@@ -579,22 +434,6 @@ Example:
                     "host": "127.0.0.1", "sasl_username": "luiz" } },
         "timestamp": { "seconds": 1263475302, "microseconds": 150772 } }
 
-VSERPORT_CHANGE
----------------
-
-Emitted when the guest opens or closes a virtio-serial port.
-
-Data:
-
-- "id": device identifier of the virtio-serial port (json-string)
-- "open": true if the guest has opened the virtio-serial port (json-bool)
-
-Example:
-
-{ "event": "VSERPORT_CHANGE",
-    "data": { "id": "channel0", "open": true },
-    "timestamp": { "seconds": 1401385907, "microseconds": 422329 } }
-
 WAKEUP
 ------
 
@@ -604,7 +443,7 @@ Data: None.
 
 Example:
 
-{ "event": "WAKEUP",
+{ "event": "WATCHDOG",
      "timestamp": { "seconds": 1344522075, "microseconds": 745528 } }
 
 WATCHDOG
@@ -625,3 +464,17 @@ Example:
 
 Note: If action is "reset", "shutdown", or "pause" the WATCHDOG event is
 followed respectively by the RESET, SHUTDOWN, or STOP events.
+
+GUEST_PANICKED
+--------------
+
+Emitted when guest OS panic is detected.
+
+Data:
+
+- "action": Action that has been taken (json-string, currently always "pause").
+
+Example:
+
+{ "event": "GUEST_PANICKED",
+     "data": { "action": "pause" } }

QMP/qmp-shell

@@ -31,7 +31,6 @@
 # (QEMU)
 
 import qmp
-import json
 import readline
 import sys
 import pprint
@@ -92,7 +91,7 @@ class QMPShell(qmp.QEMUMonitorProtocol):
         """
         Build a QMP input object from a user provided command-line in the
         following format:
-
+    
             < command-name > [ arg-name1=arg1 ] ... [ arg-nameN=argN ]
         """
         cmdargs = cmdline.split()
@@ -108,33 +107,15 @@ class QMPShell(qmp.QEMUMonitorProtocol):
                     value = True
                 elif opt[1] == 'false':
                     value = False
-                elif opt[1].startswith('{'):
-                    value = json.loads(opt[1])
                 else:
                     value = opt[1]
-            optpath = opt[0].split('.')
-            parent = qmpcmd['arguments']
-            curpath = []
-            for p in optpath[:-1]:
-                curpath.append(p)
-                d = parent.get(p, {})
-                if type(d) is not dict:
-                    raise QMPShellError('Cannot use "%s" as both leaf and non-leaf key' % '.'.join(curpath))
-                parent[p] = d
-                parent = d
-            if optpath[-1] in parent:
-                if type(parent[optpath[-1]]) is dict:
-                    raise QMPShellError('Cannot use "%s" as both leaf and non-leaf key' % '.'.join(curpath))
-                else:
-                    raise QMPShellError('Cannot set "%s" multiple times' % opt[0])
-            parent[optpath[-1]] = value
+            qmpcmd['arguments'][opt[0]] = value
         return qmpcmd
 
     def _execute_cmd(self, cmdline):
         try:
             qmpcmd = self.__build_cmd(cmdline)
-        except Exception, e:
-            print 'Error while parsing command line: %s' % e
+        except:
             print 'command format: <command-name> ',
             print '[arg-name1=arg1] ... [arg-nameN=argN]'
             return True

QMP/qmp-spec.txt

@@ -1,17 +1,21 @@
-                      QEMU Machine Protocol Specification
+           QEMU Monitor Protocol Specification - Version 0.1
 
 1. Introduction
 ===============
 
-This document specifies the QEMU Machine Protocol (QMP), a JSON-based protocol
-which is available for applications to operate QEMU at the machine-level.
+This document specifies the QEMU Monitor Protocol (QMP), a JSON-based protocol
+which is available for applications to control QEMU at the machine-level.
+
+To enable QMP support, QEMU has to be run in "control mode". This is done by
+starting QEMU with the appropriate command-line options. Please, refer to the
+QEMU manual page for more information.
 
 2. Protocol Specification
 =========================
 
 This section details the protocol format. For the purpose of this document
-"Client" is any application which is using QMP to communicate with QEMU and
-"Server" is QEMU itself.
+"Client" is any application which is communicating with QEMU in control mode,
+and "Server" is QEMU itself.
 
 JSON data structures, when mentioned in this document, are always in the
 following format:
@@ -43,14 +47,14 @@ that the connection has been successfully established and that the Server is
 ready for capabilities negotiation (for more information refer to section
 '4. Capabilities Negotiation').
 
-The greeting message format is:
+The format is:
 
 { "QMP": { "version": json-object, "capabilities": json-array } }
 
  Where,
 
 - The "version" member contains the Server's version information (the format
-  is the same of the query-version command)
+  is the same of the 'query-version' command)
 - The "capabilities" member specify the availability of features beyond the
   baseline specification
 
@@ -79,7 +83,10 @@ of a command execution: success or error.
 2.4.1 success
 -------------
 
-The format of a success response is:
+The success response is issued when the command execution has finished
+without errors.
+
+The format is:
 
 { "return": json-object, "id": json-value }
 
@@ -89,12 +96,15 @@ The format of a success response is:
   in a per-command basis or an empty json-object if the command does not
   return data
 - The "id" member contains the transaction identification associated
-  with the command execution if issued by the Client
+  with the command execution (if issued by the Client)
 
 2.4.2 error
 -----------
 
-The format of an error response is:
+The error response is issued when the command execution could not be
+completed because of an error condition.
+
+The format is:
 
 { "error": { "class": json-string, "desc": json-string }, "id": json-value }
 
@@ -104,7 +114,7 @@ The format of an error response is:
 - The "desc" member is a human-readable error message. Clients should
   not attempt to parse this message.
 - The "id" member contains the transaction identification associated with
-  the command execution if issued by the Client
+  the command execution (if issued by the Client)
 
 NOTE: Some errors can occur before the Server is able to read the "id" member,
 in these cases the "id" member will not be part of the error response, even
@@ -114,9 +124,9 @@ if provided by the client.
 -----------------------
 
 As a result of state changes, the Server may send messages unilaterally
-to the Client at any time. They are called "asynchronous events".
+to the Client at any time. They are called 'asynchronous events'.
 
-The format of asynchronous events is:
+The format is:
 
 { "event": json-string, "data": json-object,
   "timestamp": { "seconds": json-number, "microseconds": json-number } }
@@ -137,37 +147,36 @@ qmp-events.txt file.
 ===============
 
 This section provides some examples of real QMP usage, in all of them
-"C" stands for "Client" and "S" stands for "Server".
+'C' stands for 'Client' and 'S' stands for 'Server'.
 
 3.1 Server greeting
 -------------------
 
-S: { "QMP": { "version": { "qemu": { "micro": 50, "minor": 6, "major": 1 },
-     "package": ""}, "capabilities": []}}
+S: {"QMP": {"version": {"qemu": "0.12.50", "package": ""}, "capabilities": []}}
 
 3.2 Simple 'stop' execution
 ---------------------------
 
 C: { "execute": "stop" }
-S: { "return": {} }
+S: {"return": {}}
 
 3.3 KVM information
 -------------------
 
 C: { "execute": "query-kvm", "id": "example" }
-S: { "return": { "enabled": true, "present": true }, "id": "example"}
+S: {"return": {"enabled": true, "present": true}, "id": "example"}
 
 3.4 Parsing error
 ------------------
 
 C: { "execute": }
-S: { "error": { "class": "GenericError", "desc": "Invalid JSON syntax" } }
+S: {"error": {"class": "GenericError", "desc": "Invalid JSON syntax" } }
 
 3.5 Powerdown event
 -------------------
 
-S: { "timestamp": { "seconds": 1258551470, "microseconds": 802384 },
-    "event": "POWERDOWN" }
+S: {"timestamp": {"seconds": 1258551470, "microseconds": 802384}, "event":
+"POWERDOWN"}
 
 4. Capabilities Negotiation
 ----------------------------
@@ -175,17 +184,17 @@ S: { "timestamp": { "seconds": 1258551470, "microseconds": 802384 },
 When a Client successfully establishes a connection, the Server is in
 Capabilities Negotiation mode.
 
-In this mode only the qmp_capabilities command is allowed to run, all
-other commands will return the CommandNotFound error. Asynchronous
-messages are not delivered either.
+In this mode only the 'qmp_capabilities' command is allowed to run, all
+other commands will return the CommandNotFound error. Asynchronous messages
+are not delivered either.
 
-Clients should use the qmp_capabilities command to enable capabilities
+Clients should use the 'qmp_capabilities' command to enable capabilities
 advertised in the Server's greeting (section '2.2 Server Greeting') they
 support.
 
-When the qmp_capabilities command is issued, and if it does not return an
+When the 'qmp_capabilities' command is issued, and if it does not return an
 error, the Server enters in Command mode where capabilities changes take
-effect, all commands (except qmp_capabilities) are allowed and asynchronous
+effect, all commands (except 'qmp_capabilities') are allowed and asynchronous
 messages are delivered.
 
 5 Compatibility Considerations
@@ -236,7 +245,7 @@ arguments, errors, asynchronous events, and so forth.
 
 Any new names downstream wishes to add must begin with '__'.  To
 ensure compatibility with other downstreams, it is strongly
-recommended that you prefix your downstream names with '__RFQDN_' where
+recommended that you prefix your downstram names with '__RFQDN_' where
 RFQDN is a valid, reverse fully qualified domain name which you
 control.  For example, a qemu-kvm specific monitor command would be:
 

QMP/qmp.py

@@ -1,5 +1,5 @@
 # QEMU Monitor Protocol Python class
-#
+# 
 # Copyright (C) 2009, 2010 Red Hat Inc.
 #
 # Authors:
@@ -171,12 +171,7 @@ class QEMUMonitorProtocol:
                 pass
         self.__sock.setblocking(1)
         if not self.__events and wait:
-            ret = self.__json_read(only_event=True)
-            if ret == None:
-                # We are in blocking mode, if don't get anything, something
-                # went wrong
-                raise QMPConnectError("Error while reading from socket")
-
+            self.__json_read(only_event=True)
         return self.__events
 
     def clear_events(self):
@@ -193,9 +188,3 @@ class QEMUMonitorProtocol:
 
     def settimeout(self, timeout):
         self.__sock.settimeout(timeout)
-
-    def get_sock_fd(self):
-        return self.__sock.fileno()
-
-    def is_scm_available(self):
-        return self.__sock.family == socket.AF_UNIX

README

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

VERSION

@@ -1 +1 @@
-2.1.2
+1.6.1

aio-posix.c

@@ -23,6 +23,7 @@ struct AioHandler
     GPollFD pfd;
     IOHandler *io_read;
     IOHandler *io_write;
+    AioFlushHandler *io_flush;
     int deleted;
     int pollfds_idx;
     void *opaque;
@@ -46,6 +47,7 @@ void aio_set_fd_handler(AioContext *ctx,
                         int fd,
                         IOHandler *io_read,
                         IOHandler *io_write,
+                        AioFlushHandler *io_flush,
                         void *opaque)
 {
     AioHandler *node;
@@ -82,6 +84,7 @@ void aio_set_fd_handler(AioContext *ctx,
         /* Update handler with latest information */
         node->io_read = io_read;
         node->io_write = io_write;
+        node->io_flush = io_flush;
         node->opaque = opaque;
         node->pollfds_idx = -1;
 
@@ -94,10 +97,12 @@ void aio_set_fd_handler(AioContext *ctx,
 
 void aio_set_event_notifier(AioContext *ctx,
                             EventNotifier *notifier,
-                            EventNotifierHandler *io_read)
+                            EventNotifierHandler *io_read,
+                            AioFlushEventNotifierHandler *io_flush)
 {
     aio_set_fd_handler(ctx, event_notifier_get_fd(notifier),
-                       (IOHandler *)io_read, NULL, notifier);
+                       (IOHandler *)io_read, NULL,
+                       (AioFlushHandler *)io_flush, notifier);
 }
 
 bool aio_pending(AioContext *ctx)
@@ -125,7 +130,7 @@ 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);
@@ -142,11 +147,7 @@ static bool aio_dispatch(AioContext *ctx)
             (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) &&
             node->io_read) {
             node->io_read(node->opaque);
-
-            /* aio_notify() does not count as progress */
-            if (node->opaque != &ctx->notifier) {
-                progress = true;
-            }
+            progress = true;
         }
         if (!node->deleted &&
             (revents & (G_IO_OUT | G_IO_ERR)) &&
@@ -165,66 +166,33 @@ static bool aio_dispatch(AioContext *ctx)
             g_free(tmp);
         }
     }
-
-    /* Run our timers */
-    progress |= timerlistgroup_run_timers(&ctx->tlg);
-
     return progress;
 }
 
 bool aio_poll(AioContext *ctx, bool blocking)
 {
     AioHandler *node;
-    bool was_dispatching;
     int ret;
-    bool progress;
+    bool busy, 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++;
@@ -232,8 +200,20 @@ bool aio_poll(AioContext *ctx, bool blocking)
     g_array_set_size(ctx->pollfds, 0);
 
     /* fill pollfds */
+    busy = false;
     QLIST_FOREACH(node, &ctx->aio_handlers, node) {
         node->pollfds_idx = -1;
+
+        /* If there aren't pending AIO operations, don't invoke callbacks.
+         * Otherwise, if there are no AIO requests, qemu_aio_wait() would
+         * wait indefinitely.
+         */
+        if (!node->deleted && node->io_flush) {
+            if (node->io_flush(node->opaque) == 0) {
+                continue;
+            }
+            busy = true;
+        }
         if (!node->deleted && node->pfd.events) {
             GPollFD pfd = {
                 .fd = node->pfd.fd,
@@ -246,10 +226,15 @@ bool aio_poll(AioContext *ctx, bool blocking)
 
     ctx->walking_handlers--;
 
+    /* No AIO operations?  Get us out of here */
+    if (!busy) {
+        return progress;
+    }
+
     /* wait until next event */
-    ret = qemu_poll_ns((GPollFD *)ctx->pollfds->data,
-                         ctx->pollfds->len,
-                         blocking ? timerlistgroup_deadline_ns(&ctx->tlg) : 0);
+    ret = g_poll((GPollFD *)ctx->pollfds->data,
+                 ctx->pollfds->len,
+                 blocking ? -1 : 0);
 
     /* if we have any readable fds, dispatch event */
     if (ret > 0) {
@@ -260,15 +245,11 @@ bool aio_poll(AioContext *ctx, bool blocking)
                 node->pfd.revents = pfd->revents;
             }
         }
+        if (aio_dispatch(ctx)) {
+            progress = true;
+        }
     }
 
-    /* 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;
+    assert(progress || busy);
+    return true;
 }

aio-win32.c

@@ -23,6 +23,7 @@
 struct AioHandler {
     EventNotifier *e;
     EventNotifierHandler *io_notify;
+    AioFlushEventNotifierHandler *io_flush;
     GPollFD pfd;
     int deleted;
     QLIST_ENTRY(AioHandler) node;
@@ -30,7 +31,8 @@ struct AioHandler {
 
 void aio_set_event_notifier(AioContext *ctx,
                             EventNotifier *e,
-                            EventNotifierHandler *io_notify)
+                            EventNotifierHandler *io_notify,
+                            AioFlushEventNotifierHandler *io_flush)
 {
     AioHandler *node;
 
@@ -71,6 +73,7 @@ void aio_set_event_notifier(AioContext *ctx,
         }
         /* Update handler with latest information */
         node->io_notify = io_notify;
+        node->io_flush = io_flush;
     }
 
     aio_notify(ctx);
@@ -93,29 +96,25 @@ bool aio_poll(AioContext *ctx, bool blocking)
 {
     AioHandler *node;
     HANDLE events[MAXIMUM_WAIT_OBJECTS + 1];
-    bool progress;
+    bool busy, progress;
     int count;
-    int timeout;
 
     progress = false;
 
     /*
      * 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;
         progress = true;
     }
 
-    /* Run timers */
-    progress |= timerlistgroup_run_timers(&ctx->tlg);
-
     /*
      * 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);
@@ -127,11 +126,7 @@ bool aio_poll(AioContext *ctx, bool blocking)
         if (node->pfd.revents && node->io_notify) {
             node->pfd.revents = 0;
             node->io_notify(node->e);
-
-            /* aio_notify() does not count as progress */
-            if (node->e != &ctx->notifier) {
-                progress = true;
-            }
+            progress = true;
         }
 
         tmp = node;
@@ -152,8 +147,19 @@ bool aio_poll(AioContext *ctx, bool blocking)
     ctx->walking_handlers++;
 
     /* fill fd sets */
+    busy = false;
     count = 0;
     QLIST_FOREACH(node, &ctx->aio_handlers, node) {
+        /* If there aren't pending AIO operations, don't invoke callbacks.
+         * Otherwise, if there are no AIO requests, qemu_aio_wait() would
+         * wait indefinitely.
+         */
+        if (!node->deleted && node->io_flush) {
+            if (node->io_flush(node->e) == 0) {
+                continue;
+            }
+            busy = true;
+        }
         if (!node->deleted && node->io_notify) {
             events[count++] = event_notifier_get_handle(node->e);
         }
@@ -161,13 +167,15 @@ bool aio_poll(AioContext *ctx, bool blocking)
 
     ctx->walking_handlers--;
 
+    /* No AIO operations?  Get us out of here */
+    if (!busy) {
+        return progress;
+    }
+
     /* wait until next event */
     while (count > 0) {
-        int ret;
-
-        timeout = blocking ?
-            qemu_timeout_ns_to_ms(timerlistgroup_deadline_ns(&ctx->tlg)) : 0;
-        ret = WaitForMultipleObjects(count, events, FALSE, timeout);
+        int timeout = blocking ? INFINITE : 0;
+        int ret = WaitForMultipleObjects(count, events, FALSE, timeout);
 
         /* if we have any signaled events, dispatch event */
         if ((DWORD) (ret - WAIT_OBJECT_0) >= count) {
@@ -177,7 +185,7 @@ 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;
@@ -188,11 +196,7 @@ bool aio_poll(AioContext *ctx, bool blocking)
                 event_notifier_get_handle(node->e) == events[ret - WAIT_OBJECT_0] &&
                 node->io_notify) {
                 node->io_notify(node->e);
-
-                /* aio_notify() does not count as progress */
-                if (node->e != &ctx->notifier) {
-                    progress = true;
-                }
+                progress = true;
             }
 
             tmp = node;
@@ -210,14 +214,6 @@ bool aio_poll(AioContext *ctx, bool blocking)
         events[ret - WAIT_OBJECT_0] = events[--count];
     }
 
-    if (blocking) {
-        /* Run the timers a second time. We do this because otherwise aio_wait
-         * will not note progress - and will stop a drain early - if we have
-         * a timer that was not ready to run entering g_poll but is ready
-         * after g_poll. This will only do anything if a timer has expired.
-         */
-        progress |= timerlistgroup_run_timers(&ctx->tlg);
-    }
-
-    return progress;
+    assert(progress || busy);
+    return true;
 }

async.c

@@ -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) */
@@ -118,21 +117,15 @@ void qemu_bh_schedule_idle(QEMUBH *bh)
 
 void qemu_bh_schedule(QEMUBH *bh)
 {
-    AioContext *ctx;
-
     if (bh->scheduled)
         return;
-    ctx = bh->ctx;
     bh->idle = 0;
-    /* Make sure that:
-     * 1. idle & any writes needed by the callback are done before the
-     *    locations are read in the aio_bh_poll.
-     * 2. ctx is loaded before scheduled is set and the callback has a chance
-     *    to execute.
+    /* Make sure that idle & any writes needed by the callback are done
+     * before the locations are read in the aio_bh_poll.
      */
-    smp_mb();
+    smp_wmb();
     bh->scheduled = 1;
-    aio_notify(ctx);
+    aio_notify(bh->ctx);
 }
 
 
@@ -157,10 +150,7 @@ aio_ctx_prepare(GSource *source, gint    *timeout)
 {
     AioContext *ctx = (AioContext *) source;
     QEMUBH *bh;
-    int deadline;
 
-    /* We assume there is no timeout already supplied */
-    *timeout = -1;
     for (bh = ctx->first_bh; bh; bh = bh->next) {
         if (!bh->deleted && bh->scheduled) {
             if (bh->idle) {
@@ -176,14 +166,6 @@ aio_ctx_prepare(GSource *source, gint    *timeout)
         }
     }
 
-    deadline = qemu_timeout_ns_to_ms(timerlistgroup_deadline_ns(&ctx->tlg));
-    if (deadline == 0) {
-        *timeout = 0;
-        return true;
-    } else {
-        *timeout = qemu_soonest_timeout(*timeout, deadline);
-    }
-
     return false;
 }
 
@@ -198,7 +180,7 @@ aio_ctx_check(GSource *source)
             return true;
 	}
     }
-    return aio_pending(ctx) || (timerlistgroup_deadline_ns(&ctx->tlg) == 0);
+    return aio_pending(ctx);
 }
 
 static gboolean
@@ -219,12 +201,10 @@ aio_ctx_finalize(GSource     *source)
     AioContext *ctx = (AioContext *) source;
 
     thread_pool_free(ctx->thread_pool);
-    aio_set_event_notifier(ctx, &ctx->notifier, NULL);
+    aio_set_event_notifier(ctx, &ctx->notifier, NULL, 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);
 }
 
 static GSourceFuncs aio_source_funcs = {
@@ -248,36 +228,9 @@ 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);
-    }
-}
-
-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);
+    event_notifier_set(&ctx->notifier);
 }
 
 AioContext *aio_context_new(void)
@@ -287,12 +240,10 @@ 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 *)
-                           event_notifier_test_and_clear);
-    timerlistgroup_init(&ctx->tlg, aio_timerlist_notify, ctx);
+                           event_notifier_test_and_clear, NULL);
 
     return ctx;
 }
@@ -306,13 +257,3 @@ 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);
-}

audio/Makefile.objs

@@ -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)

audio/alsaaudio.c

@@ -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)

audio/audio.c

@@ -95,7 +95,7 @@ static struct {
         }
     },
 
-    .period = { .hertz = 100 },
+    .period = { .hertz = 250 },
     .plive = 0,
     .log_to_monitor = 0,
     .try_poll_in = 1,
@@ -1124,11 +1124,10 @@ static int audio_is_timer_needed (void)
 static void audio_reset_timer (AudioState *s)
 {
     if (audio_is_timer_needed ()) {
-        timer_mod (s->ts,
-            qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + conf.period.ticks);
+        qemu_mod_timer (s->ts, qemu_get_clock_ns (vm_clock) + 1);
     }
     else {
-        timer_del (s->ts);
+        qemu_del_timer (s->ts);
     }
 }
 
@@ -1812,7 +1811,8 @@ 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()
     }
 };
@@ -1834,7 +1834,7 @@ static void audio_init (void)
     QLIST_INIT (&s->cap_head);
     atexit (audio_atexit);
 
-    s->ts = timer_new_ns(QEMU_CLOCK_VIRTUAL, audio_timer, s);
+    s->ts = qemu_new_timer_ns (vm_clock, audio_timer, s);
     if (!s->ts) {
         hw_error("Could not create audio timer\n");
     }

audio/audio_template.h

@@ -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)

audio/mixeng.c

@@ -348,6 +348,7 @@ void mixeng_clear (struct st_sample *buf, int len)
 
 void mixeng_volume (struct st_sample *buf, int len, struct mixeng_volume *vol)
 {
+#ifdef CONFIG_MIXEMU
     if (vol->mute) {
         mixeng_clear (buf, len);
         return;
@@ -363,4 +364,9 @@ void mixeng_volume (struct st_sample *buf, int len, struct mixeng_volume *vol)
 #endif
         buf += 1;
     }
+#else
+    (void) buf;
+    (void) len;
+    (void) vol;
+#endif
 }

audio/mixeng_template.h

@@ -35,7 +35,7 @@
 #define IN_T glue (glue (ITYPE, BSIZE), _t)
 
 #ifdef FLOAT_MIXENG
-static inline mixeng_real glue (conv_, ET) (IN_T v)
+static mixeng_real inline glue (conv_, ET) (IN_T v)
 {
     IN_T nv = ENDIAN_CONVERT (v);
 
@@ -54,7 +54,7 @@ static inline mixeng_real glue (conv_, ET) (IN_T v)
 #endif
 }
 
-static inline IN_T glue (clip_, ET) (mixeng_real v)
+static IN_T inline glue (clip_, ET) (mixeng_real v)
 {
     if (v >= 0.5) {
         return IN_MAX;

audio/noaudio.c

@@ -46,7 +46,7 @@ static int no_run_out (HWVoiceOut *hw, int live)
     int64_t ticks;
     int64_t bytes;
 
-    now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+    now = qemu_get_clock_ns (vm_clock);
     ticks = now - no->old_ticks;
     bytes = muldiv64 (ticks, hw->info.bytes_per_second, get_ticks_per_sec ());
     bytes = audio_MIN (bytes, INT_MAX);
@@ -102,7 +102,7 @@ static int no_run_in (HWVoiceIn *hw)
     int samples = 0;
 
     if (dead) {
-        int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+        int64_t now = qemu_get_clock_ns (vm_clock);
         int64_t ticks = now - no->old_ticks;
         int64_t bytes =
             muldiv64 (ticks, hw->info.bytes_per_second, get_ticks_per_sec ());

audio/ossaudio.c

@@ -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)
@@ -847,10 +849,6 @@ static int oss_ctl_in (HWVoiceIn *hw, int cmd, ...)
 
 static void *oss_audio_init (void)
 {
-    if (access(conf.devpath_in, R_OK | W_OK) < 0 ||
-        access(conf.devpath_out, R_OK | W_OK) < 0) {
-        return NULL;
-    }
     return &conf;
 }
 

audio/paaudio.c

@@ -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;
 

audio/spiceaudio.c

@@ -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;
@@ -90,7 +81,7 @@ static void spice_audio_fini (void *opaque)
 static void rate_start (SpiceRateCtl *rate)
 {
     memset (rate, 0, sizeof (*rate));
-    rate->start_ticks = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+    rate->start_ticks = qemu_get_clock_ns (vm_clock);
 }
 
 static int rate_get_samples (struct audio_pcm_info *info, SpiceRateCtl *rate)
@@ -100,12 +91,12 @@ static int rate_get_samples (struct audio_pcm_info *info, SpiceRateCtl *rate)
     int64_t bytes;
     int64_t samples;
 
-    now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+    now = qemu_get_clock_ns (vm_clock);
     ticks = now - rate->start_ticks;
     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;
 }
 

audio/wavaudio.c

@@ -52,7 +52,7 @@ static int wav_run_out (HWVoiceOut *hw, int live)
     int rpos, decr, samples;
     uint8_t *dst;
     struct st_sample *src;
-    int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+    int64_t now = qemu_get_clock_ns (vm_clock);
     int64_t ticks = now - wav->old_ticks;
     int64_t bytes =
         muldiv64 (ticks, hw->info.bytes_per_second, get_ticks_per_sec ());

audio/wavcapture.c

@@ -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));
         }
     }
 

backends/Makefile.objs

@@ -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

backends/baum.c

@@ -314,9 +314,9 @@ static int baum_eat_packet(BaumDriverState *baum, const uint8_t *buf, int len)
             return 0; \
         if (*cur++ != ESC) { \
             DPRINTF("Broken packet %#2x, tossing\n", req); \
-            if (timer_pending(baum->cellCount_timer)) {    \
-                timer_del(baum->cellCount_timer);     \
-                baum_cellCount_timer_cb(baum);             \
+		if (qemu_timer_pending(baum->cellCount_timer)) { \
+                qemu_del_timer(baum->cellCount_timer); \
+                baum_cellCount_timer_cb(baum); \
             } \
             return (cur - 2 - buf); \
         } \
@@ -334,7 +334,7 @@ static int baum_eat_packet(BaumDriverState *baum, const uint8_t *buf, int len)
         int i;
 
         /* Allow 100ms to complete the DisplayData packet */
-        timer_mod(baum->cellCount_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
+        qemu_mod_timer(baum->cellCount_timer, qemu_get_clock_ns(vm_clock) +
                        get_ticks_per_sec() / 10);
         for (i = 0; i < baum->x * baum->y ; i++) {
             EAT(c);
@@ -348,7 +348,7 @@ static int baum_eat_packet(BaumDriverState *baum, const uint8_t *buf, int len)
                 c = '?';
             text[i] = c;
         }
-        timer_del(baum->cellCount_timer);
+        qemu_del_timer(baum->cellCount_timer);
 
         memset(zero, 0, sizeof(zero));
 
@@ -553,7 +553,7 @@ static void baum_close(struct CharDriverState *chr)
 {
     BaumDriverState *baum = chr->opaque;
 
-    timer_free(baum->cellCount_timer);
+    qemu_free_timer(baum->cellCount_timer);
     if (baum->brlapi) {
         brlapi__closeConnection(baum->brlapi);
         g_free(baum->brlapi);
@@ -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;
@@ -590,21 +588,19 @@ CharDriverState *chr_baum_init(void)
         goto fail_handle;
     }
 
-    baum->cellCount_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, baum_cellCount_timer_cb, baum);
+    baum->cellCount_timer = qemu_new_timer_ns(vm_clock, baum_cellCount_timer_cb, baum);
 
     if (brlapi__getDisplaySize(handle, &baum->x, &baum->y) == -1) {
         brlapi_perror("baum_init: brlapi_getDisplaySize");
         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;
 
@@ -618,7 +614,7 @@ CharDriverState *chr_baum_init(void)
     return chr;
 
 fail:
-    timer_free(baum->cellCount_timer);
+    qemu_free_timer(baum->cellCount_timer);
     brlapi__closeConnection(handle);
 fail_handle:
     g_free(handle);

backends/hostmem-file.c

@@ -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);

backends/hostmem-ram.c

@@ -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);

backends/hostmem.c

@@ -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);

backends/msmouse.c

@@ -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;

backends/rng-egd.c

@@ -91,14 +91,12 @@ static int rng_egd_chr_can_read(void *opaque)
 static void rng_egd_chr_read(void *opaque, const uint8_t *buf, int size)
 {
     RngEgd *s = RNG_EGD(opaque);
-    size_t buf_offset = 0;
 
     while (size > 0 && s->requests) {
         RngRequest *req = s->requests->data;
         int len = MIN(size, req->size - req->offset);
 
-        memcpy(req->data + req->offset, buf + buf_offset, len);
-        buf_offset += len;
+        memcpy(req->data + req->offset, buf, len);
         req->offset += len;
         size -= len;
 

backends/rng-random.c

@@ -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);
     }
 

backends/rng.c

@@ -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)

backends/tpm.c

@@ -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)

balloon.c

@@ -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;

block-migration.c

@@ -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);
     }
 }
 
@@ -362,9 +336,8 @@ 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_ref(bs);
+        drive_get_ref(drive_get_by_blockdev(bs));
+        bdrv_set_in_use(bs, 1);
 
         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;
@@ -596,14 +569,13 @@ 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_unref(bmds->bs);
+        bdrv_set_in_use(bmds->bs, 0);
+        drive_put_ref(drive_get_by_blockdev(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);
@@ -814,8 +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);
@@ -861,7 +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,

block/Makefile.objs

@@ -1,9 +1,8 @@
-block-obj-y += raw_bsd.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o
+block-obj-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o
 block-obj-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
 block-obj-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
 block-obj-y += qed-check.o
-block-obj-$(CONFIG_VHDX) += vhdx.o vhdx-endian.o vhdx-log.o
-block-obj-$(CONFIG_QUORUM) += quorum.o
+block-obj-y += vhdx.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)

block/backup.c

@@ -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)
@@ -208,9 +202,9 @@ static void backup_iostatus_reset(BlockJob *job)
     bdrv_iostatus_reset(s->target);
 }
 
-static const BlockJobDriver backup_job_driver = {
+static const BlockJobType backup_job_type = {
     .instance_size  = sizeof(BackupBlockJob),
-    .job_type       = BLOCK_JOB_TYPE_BACKUP,
+    .job_type       = "backup",
     .set_speed      = backup_set_speed,
     .iostatus_reset = backup_iostatus_reset,
 };
@@ -278,9 +272,9 @@ static void coroutine_fn backup_run(void *opaque)
                 uint64_t delay_ns = ratelimit_calculate_delay(
                         &job->limit, job->sectors_read);
                 job->sectors_read = 0;
-                block_job_sleep_ns(&job->common, QEMU_CLOCK_REALTIME, delay_ns);
+                block_job_sleep_ns(&job->common, rt_clock, delay_ns);
             } else {
-                block_job_sleep_ns(&job->common, QEMU_CLOCK_REALTIME, 0);
+                block_job_sleep_ns(&job->common, rt_clock, 0);
             }
 
             if (block_job_is_cancelled(&job->common)) {
@@ -295,19 +289,19 @@ static void coroutine_fn backup_run(void *opaque)
                  * backing file. */
 
                 for (i = 0; i < BACKUP_SECTORS_PER_CLUSTER;) {
-                    /* bdrv_is_allocated() only returns true/false based
-                     * on the first set of sectors it comes across that
+                    /* bdrv_co_is_allocated() only returns true/false based
+                     * on the first set of sectors it comes accross that
                      * are are all in the same state.
                      * For that reason we must verify each sector in the
                      * backup cluster length.  We end up copying more than
                      * needed but at some point that is always the case. */
                     alloced =
-                        bdrv_is_allocated(bs,
+                        bdrv_co_is_allocated(bs,
                                 start * BACKUP_SECTORS_PER_CLUSTER + i,
                                 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--;
@@ -344,7 +338,7 @@ static void coroutine_fn backup_run(void *opaque)
     hbitmap_free(job->bitmap);
 
     bdrv_iostatus_disable(target);
-    bdrv_unref(target);
+    bdrv_delete(target);
 
     block_job_completed(&job->common, ret);
 }
@@ -376,7 +370,7 @@ void backup_start(BlockDriverState *bs, BlockDriverState *target,
         return;
     }
 
-    BackupBlockJob *job = block_job_create(&backup_job_driver, bs, speed,
+    BackupBlockJob *job = block_job_create(&backup_job_type, bs, speed,
                                            cb, opaque, errp);
     if (!job) {
         return;

block/blkdebug.c

@@ -168,7 +168,6 @@ static const char *event_names[BLKDBG_EVENT_MAX] = {
 
     [BLKDBG_REFTABLE_LOAD]                  = "reftable_load",
     [BLKDBG_REFTABLE_GROW]                  = "reftable_grow",
-    [BLKDBG_REFTABLE_UPDATE]                = "reftable_update",
 
     [BLKDBG_REFBLOCK_LOAD]                  = "refblock_load",
     [BLKDBG_REFBLOCK_UPDATE]                = "refblock_update",
@@ -186,14 +185,6 @@ 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 +270,19 @@ 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 +297,7 @@ 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 +309,7 @@ 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;
     }
 
@@ -372,68 +345,53 @@ 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 */ }
     },
 };
 
-static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
-                         Error **errp)
+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) {
-        error_propagate(errp, local_err);
+    if (error_is_set(&local_err)) {
+        qerror_report_err(local_err);
+        error_free(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) {
+            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) {
+        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);
+    if (ret < 0) {
+        goto fail;
     }
 
     ret = 0;
-    goto out;
-
-fail_unref:
-    bdrv_unref(bs->file);
-out:
+fail:
     qemu_opts_del(opts);
     return ret;
 }
@@ -449,10 +407,6 @@ 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 +429,7 @@ 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);
 
@@ -636,9 +590,9 @@ 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;
@@ -647,31 +601,6 @@ 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)
 {
@@ -706,8 +635,6 @@ static BlockDriver bdrv_blkdebug = {
 
     .bdrv_debug_event           = blkdebug_debug_event,
     .bdrv_debug_breakpoint      = blkdebug_debug_breakpoint,
-    .bdrv_debug_remove_breakpoint
-                                = blkdebug_debug_remove_breakpoint,
     .bdrv_debug_resume          = blkdebug_debug_resume,
     .bdrv_debug_is_suspended    = blkdebug_debug_is_suspended,
 };

block/blkverify.c

@@ -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;
     }
 
@@ -119,37 +116,46 @@ static QemuOptsList runtime_opts = {
     },
 };
 
-static int blkverify_open(BlockDriverState *bs, QDict *options, int flags,
-                          Error **errp)
+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) {
-        error_propagate(errp, local_err);
+    if (error_is_set(&local_err)) {
+        qerror_report_err(local_err);
+        error_free(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) {
+        ret = -EINVAL;
+        goto fail;
+    }
+
+    ret = bdrv_file_open(&bs->file, raw, NULL, flags);
     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) {
+        ret = -EINVAL;
+        goto fail;
+    }
+
+    s->test_file = bdrv_new("");
+    ret = bdrv_open(s->test_file, filename, NULL, flags, NULL);
     if (ret < 0) {
-        error_propagate(errp, local_err);
+        bdrv_delete(s->test_file);
         s->test_file = NULL;
         goto fail;
     }
@@ -163,7 +169,7 @@ static void blkverify_close(BlockDriverState *bs)
 {
     BDRVBlkverifyState *s = bs->opaque;
 
-    bdrv_unref(s->test_file);
+    bdrv_delete(s->test_file);
     s->test_file = NULL;
 }
 
@@ -174,6 +180,110 @@ 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 +339,7 @@ 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 +347,7 @@ 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 +365,7 @@ 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 +399,19 @@ 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_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_aio_readv         = blkverify_aio_readv,
+    .bdrv_aio_writev        = blkverify_aio_writev,
+    .bdrv_aio_flush         = blkverify_aio_flush,
 };
 
 static void bdrv_blkverify_init(void)

block/bochs.c

@@ -39,41 +39,56 @@
 // not allocated: 0xffffffff
 
 // always little-endian
-struct bochs_header {
-    char magic[32];     /* "Bochs Virtual HD Image" */
-    char type[16];      /* "Redolog" */
-    char subtype[16];   /* "Undoable" / "Volatile" / "Growing" */
+struct bochs_header_v1 {
+    char magic[32]; // "Bochs Virtual HD Image"
+    char type[16]; // "Redolog"
+    char subtype[16]; // "Undoable" / "Volatile" / "Growing"
     uint32_t version;
-    uint32_t header;    /* size of header */
-
-    uint32_t catalog;   /* num of entries */
-    uint32_t bitmap;    /* bitmap size */
-    uint32_t extent;    /* extent size */
+    uint32_t header; // size of header
 
     union {
-        struct {
-            uint32_t reserved;  /* for ??? */
-            uint64_t disk;      /* disk size */
-            char padding[HEADER_SIZE - 64 - 20 - 12];
-        } QEMU_PACKED redolog;
-        struct {
-            uint64_t disk;      /* disk size */
-            char padding[HEADER_SIZE - 64 - 20 - 8];
-        } QEMU_PACKED redolog_v1;
-        char padding[HEADER_SIZE - 64 - 20];
+	struct {
+	    uint32_t catalog; // num of entries
+	    uint32_t bitmap; // bitmap size
+	    uint32_t extent; // extent size
+	    uint64_t disk; // disk size
+	    char padding[HEADER_SIZE - 64 - 8 - 20];
+	} redolog;
+	char padding[HEADER_SIZE - 64 - 8];
     } extra;
-} QEMU_PACKED;
+};
+
+// always little-endian
+struct bochs_header {
+    char magic[32]; // "Bochs Virtual HD Image"
+    char type[16]; // "Redolog"
+    char subtype[16]; // "Undoable" / "Volatile" / "Growing"
+    uint32_t version;
+    uint32_t header; // size of header
+
+    union {
+	struct {
+	    uint32_t catalog; // num of entries
+	    uint32_t bitmap; // bitmap size
+	    uint32_t extent; // extent size
+	    uint32_t reserved; // for ???
+	    uint64_t disk; // disk size
+	    char padding[HEADER_SIZE - 64 - 8 - 24];
+	} redolog;
+	char padding[HEADER_SIZE - 64 - 8];
+    } extra;
+};
 
 typedef struct BDRVBochsState {
     CoMutex lock;
     uint32_t *catalog_bitmap;
-    uint32_t catalog_size;
+    int catalog_size;
 
-    uint32_t data_offset;
+    int data_offset;
 
-    uint32_t bitmap_blocks;
-    uint32_t extent_blocks;
-    uint32_t extent_size;
+    int bitmap_blocks;
+    int extent_blocks;
+    int extent_size;
 } BDRVBochsState;
 
 static int bochs_probe(const uint8_t *buf, int buf_size, const char *filename)
@@ -93,12 +108,12 @@ static int bochs_probe(const uint8_t *buf, int buf_size, const char *filename)
     return 0;
 }
 
-static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
-                      Error **errp)
+static int bochs_open(BlockDriverState *bs, QDict *options, int flags)
 {
     BDRVBochsState *s = bs->opaque;
-    uint32_t i;
+    int i;
     struct bochs_header bochs;
+    struct bochs_header_v1 header_v1;
     int ret;
 
     bs->read_only = 1; // no write support yet
@@ -113,24 +128,17 @@ 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) {
-        bs->total_sectors = le64_to_cpu(bochs.extra.redolog_v1.disk) / 512;
+      memcpy(&header_v1, &bochs, sizeof(bochs));
+      bs->total_sectors = le64_to_cpu(header_v1.extra.redolog.disk) / 512;
     } else {
-        bs->total_sectors = le64_to_cpu(bochs.extra.redolog.disk) / 512;
-    }
-
-    /* Limit to 1M entries to avoid unbounded allocation. This is what is
-     * needed for the largest image that bximage can create (~8 TB). */
-    s->catalog_size = le32_to_cpu(bochs.catalog);
-    if (s->catalog_size > 0x100000) {
-        error_setg(errp, "Catalog size is too large");
-        return -EFBIG;
+      bs->total_sectors = le64_to_cpu(bochs.extra.redolog.disk) / 512;
     }
 
+    s->catalog_size = le32_to_cpu(bochs.extra.redolog.catalog);
     s->catalog_bitmap = g_malloc(s->catalog_size * 4);
 
     ret = bdrv_pread(bs->file, le32_to_cpu(bochs.header), s->catalog_bitmap,
@@ -144,34 +152,10 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
 
     s->data_offset = le32_to_cpu(bochs.header) + (s->catalog_size * 4);
 
-    s->bitmap_blocks = 1 + (le32_to_cpu(bochs.bitmap) - 1) / 512;
-    s->extent_blocks = 1 + (le32_to_cpu(bochs.extent) - 1) / 512;
+    s->bitmap_blocks = 1 + (le32_to_cpu(bochs.extra.redolog.bitmap) - 1) / 512;
+    s->extent_blocks = 1 + (le32_to_cpu(bochs.extra.redolog.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;
-    } else if (s->extent_size > 0x800000) {
-        error_setg(errp, "Extent size %" PRIu32 " is too large",
-                   s->extent_size);
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    if (s->catalog_size < DIV_ROUND_UP(bs->total_sectors,
-                                       s->extent_size / BDRV_SECTOR_SIZE))
-    {
-        error_setg(errp, "Catalog size is too small for this disk size");
-        ret = -EINVAL;
-        goto fail;
-    }
+    s->extent_size = le32_to_cpu(bochs.extra.redolog.extent);
 
     qemu_co_mutex_init(&s->lock);
     return 0;
@@ -184,32 +168,29 @@ fail:
 static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)
 {
     BDRVBochsState *s = bs->opaque;
-    uint64_t offset = sector_num * 512;
-    uint64_t extent_index, extent_offset, bitmap_offset;
+    int64_t offset = sector_num * 512;
+    int64_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 +
-        (512 * (uint64_t) s->catalog_bitmap[extent_index] *
-        (s->extent_blocks + s->bitmap_blocks));
+    bitmap_offset = s->data_offset + (512 * s->catalog_bitmap[extent_index] *
+	(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 +203,13 @@ 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;

block/cloop.c

@@ -26,9 +26,6 @@
 #include "qemu/module.h"
 #include <zlib.h>
 
-/* Maximum compressed block size */
-#define MAX_BLOCK_SIZE (64 * 1024 * 1024)
-
 typedef struct BDRVCloopState {
     CoMutex lock;
     uint32_t block_size;
@@ -56,8 +53,7 @@ static int cloop_probe(const uint8_t *buf, int buf_size, const char *filename)
     return 0;
 }
 
-static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
-                      Error **errp)
+static int cloop_open(BlockDriverState *bs, QDict *options, int flags)
 {
     BDRVCloopState *s = bs->opaque;
     uint32_t offsets_size, max_compressed_block_size = 1, i;
@@ -71,26 +67,6 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
         return ret;
     }
     s->block_size = be32_to_cpu(s->block_size);
-    if (s->block_size % 512) {
-        error_setg(errp, "block_size %" PRIu32 " must be a multiple of 512",
-                   s->block_size);
-        return -EINVAL;
-    }
-    if (s->block_size == 0) {
-        error_setg(errp, "block_size cannot be zero");
-        return -EINVAL;
-    }
-
-    /* cloop's create_compressed_fs.c warns about block sizes beyond 256 KB but
-     * we can accept more.  Prevent ridiculous values like 4 GB - 1 since we
-     * need a buffer this big.
-     */
-    if (s->block_size > MAX_BLOCK_SIZE) {
-        error_setg(errp, "block_size %" PRIu32 " must be %u MB or less",
-                   s->block_size,
-                   MAX_BLOCK_SIZE / (1024 * 1024));
-        return -EINVAL;
-    }
 
     ret = bdrv_pread(bs->file, 128 + 4, &s->n_blocks, 4);
     if (ret < 0) {
@@ -99,23 +75,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
     s->n_blocks = be32_to_cpu(s->n_blocks);
 
     /* 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",
-                   s->n_blocks,
-                   (UINT32_MAX - 1) / sizeof(uint64_t));
-        return -EINVAL;
-    }
-    offsets_size = (s->n_blocks + 1) * sizeof(uint64_t);
-    if (offsets_size > 512 * 1024 * 1024) {
-        /* Prevent ridiculous offsets_size which causes memory allocation to
-         * fail or overflows bdrv_pread() size.  In practice the 512 MB
-         * offsets[] limit supports 16 TB images at 256 KB block size.
-         */
-        error_setg(errp, "image requires too many offsets, "
-                   "try increasing block size");
-        return -EINVAL;
-    }
+    offsets_size = s->n_blocks * sizeof(uint64_t);
     s->offsets = g_malloc(offsets_size);
 
     ret = bdrv_pread(bs->file, 128 + 4 + 4, s->offsets, offsets_size);
@@ -123,37 +83,13 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
 
-    for (i = 0; i < s->n_blocks + 1; i++) {
-        uint64_t size;
-
+    for(i=0;i<s->n_blocks;i++) {
         s->offsets[i] = be64_to_cpu(s->offsets[i]);
-        if (i == 0) {
-            continue;
-        }
-
-        if (s->offsets[i] < s->offsets[i - 1]) {
-            error_setg(errp, "offsets not monotonically increasing at "
-                       "index %" PRIu32 ", image file is corrupt", i);
-            ret = -EINVAL;
-            goto fail;
-        }
-
-        size = s->offsets[i] - s->offsets[i - 1];
-
-        /* Compressed blocks should be smaller than the uncompressed block size
-         * but maybe compression performed poorly so the compressed block is
-         * actually bigger.  Clamp down on unrealistic values to prevent
-         * ridiculous s->compressed_block allocation.
-         */
-        if (size > 2 * MAX_BLOCK_SIZE) {
-            error_setg(errp, "invalid compressed block size at index %" PRIu32
-                       ", image file is corrupt", i);
-            ret = -EINVAL;
-            goto fail;
-        }
-
-        if (size > max_compressed_block_size) {
-            max_compressed_block_size = size;
+        if (i > 0) {
+            uint32_t size = s->offsets[i] - s->offsets[i - 1];
+            if (size > max_compressed_block_size) {
+                max_compressed_block_size = size;
+            }
         }
     }
 
@@ -243,7 +179,9 @@ static coroutine_fn int cloop_co_read(BlockDriverState *bs, int64_t sector_num,
 static void cloop_close(BlockDriverState *bs)
 {
     BDRVCloopState *s = bs->opaque;
-    g_free(s->offsets);
+    if (s->n_blocks > 0) {
+        g_free(s->offsets);
+    }
     g_free(s->compressed_block);
     g_free(s->uncompressed_block);
     inflateEnd(&s->zstream);

block/commit.c

@@ -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,
@@ -104,14 +103,14 @@ wait:
         /* Note that even when no rate limit is applied we need to yield
          * with no pending I/O here so that bdrv_drain_all() returns.
          */
-        block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, delay_ns);
+        block_job_sleep_ns(&s->common, rt_clock, delay_ns);
         if (block_job_is_cancelled(&s->common)) {
             break;
         }
         /* Copy if allocated above the base */
-        ret = bdrv_is_allocated_above(top, base, sector_num,
-                                      COMMIT_BUFFER_SIZE / BDRV_SECTOR_SIZE,
-                                      &n);
+        ret = bdrv_co_is_allocated_above(top, base, sector_num,
+                                         COMMIT_BUFFER_SIZE / BDRV_SECTOR_SIZE,
+                                         &n);
         copy = (ret == 1);
         trace_commit_one_iteration(s, sector_num, n, ret);
         if (copy) {
@@ -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);
 }
 
@@ -174,16 +173,16 @@ static void commit_set_speed(BlockJob *job, int64_t speed, Error **errp)
     ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
 }
 
-static const BlockJobDriver commit_job_driver = {
+static const BlockJobType commit_job_type = {
     .instance_size = sizeof(CommitBlockJob),
-    .job_type      = BLOCK_JOB_TYPE_COMMIT,
+    .job_type      = "commit",
     .set_speed     = commit_set_speed,
 };
 
 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;
@@ -233,7 +238,7 @@ void commit_start(BlockDriverState *bs, BlockDriverState *base,
     }
 
 
-    s = block_job_create(&commit_job_driver, bs, speed, cb, opaque, errp);
+    s = block_job_create(&commit_job_type, bs, speed, cb, opaque, errp);
     if (!s) {
         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);
 

block/cow.c

@@ -58,8 +58,7 @@ static int cow_probe(const uint8_t *buf, int buf_size, const char *filename)
         return 0;
 }
 
-static int cow_open(BlockDriverState *bs, QDict *options, int flags,
-                    Error **errp)
+static int cow_open(BlockDriverState *bs, QDict *options, int flags)
 {
     BDRVCowState *s = bs->opaque;
     struct cow_header_v2 cow_header;
@@ -74,16 +73,15 @@ 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;
@@ -104,45 +102,42 @@ 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)
 {
-    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;
     }
+
+    bitmap |= (1 << (bitnum % 8));
+
+    ret = bdrv_pwrite_sync(bs->file, offset, &bitmap, sizeof(bitmap));
+    if (ret < 0) {
+       return ret;
+    }
+    return 0;
 }
 
-#define BITS_PER_BITMAP_SECTOR (512 * 8)
-
-/* Cannot use bitmap.c on big-endian machines.  */
-static int cow_test_bit(int64_t bitnum, const uint8_t *bitmap)
+static inline int is_bit_set(BlockDriverState *bs, int64_t bitnum)
 {
-    return (bitmap[bitnum / 8] & (1 << (bitnum & 7))) != 0;
-}
+    uint64_t offset = sizeof(struct cow_header_v2) + bitnum / 8;
+    uint8_t bitmap;
+    int ret;
 
-static int cow_find_streak(const uint8_t *bitmap, int value, int start, int nb_sectors)
-{
-    int streak_value = value ? 0xFF : 0;
-    int last = MIN(start + nb_sectors, BITS_PER_BITMAP_SECTOR);
-    int bitnum = start;
-    while (bitnum < last) {
-        if ((bitnum & 7) == 0 && bitmap[bitnum / 8] == streak_value) {
-            bitnum += 8;
-            continue;
-        }
-        if (cow_test_bit(bitnum, bitmap) == value) {
-            bitnum++;
-            continue;
-        }
-        break;
+    ret = bdrv_pread(bs->file, offset, &bitmap, sizeof(bitmap));
+    if (ret < 0) {
+       return ret;
     }
-    return MIN(bitnum, last) - start;
+
+    return !!(bitmap & (1 << (bitnum % 8)));
 }
 
 /* Return true if first block has been changed (ie. current version is
@@ -151,100 +146,40 @@ static int cow_find_streak(const uint8_t *bitmap, int value, int start, int nb_s
 static int coroutine_fn cow_co_is_allocated(BlockDriverState *bs,
         int64_t sector_num, int nb_sectors, int *num_same)
 {
-    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;
+    int changed;
 
-    do {
-        int ret;
-        uint8_t bitmap[BDRV_SECTOR_SIZE];
-
-        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;
-    return changed;
-}
-
-static int64_t coroutine_fn cow_co_get_block_status(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *num_same)
-{
-    BDRVCowState *s = bs->opaque;
-    int ret = cow_co_is_allocated(bs, sector_num, nb_sectors, num_same);
-    int64_t offset = s->cow_sectors_offset + (sector_num << BDRV_SECTOR_BITS);
-    if (ret < 0) {
-        return ret;
+    if (nb_sectors == 0) {
+	*num_same = nb_sectors;
+	return 0;
     }
-    return (ret ? BDRV_BLOCK_DATA : 0) | offset | BDRV_BLOCK_OFFSET_VALID;
+
+    changed = is_bit_set(bs, sector_num);
+    if (changed < 0) {
+        return 0; /* XXX: how to return I/O errors? */
+    }
+
+    for (*num_same = 1; *num_same < nb_sectors; (*num_same)++) {
+	if (is_bit_set(bs, sector_num + *num_same) != changed)
+	    break;
+    }
+
+    return changed;
 }
 
 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;
-    bool first = true;
-    int sector_bits;
+    int error = 0;
+    int i;
 
-    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);
+        if (error) {
+            break;
         }
     }
 
-    return 0;
+    return error;
 }
 
 static int coroutine_fn cow_read(BlockDriverState *bs, int64_t sector_num,
@@ -254,7 +189,7 @@ static int coroutine_fn cow_read(BlockDriverState *bs, int64_t sector_num,
     int ret, n;
 
     while (nb_sectors > 0) {
-        ret = cow_co_is_allocated(bs, sector_num, nb_sectors, &n);
+        ret = bdrv_co_is_allocated(bs, sector_num, nb_sectors, &n);
         if (ret < 0) {
             return ret;
         }
@@ -324,31 +259,33 @@ 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)
 {
     struct cow_header_v2 cow_header;
     struct stat st;
     int64_t image_sectors = 0;
-    char *image_filename = NULL;
-    Error *local_err = NULL;
+    const char *image_filename = 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);
     if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto exit;
+        return ret;
+    }
+
+    ret = bdrv_file_open(&cow_bs, filename, NULL, BDRV_O_RDWR);
+    if (ret < 0) {
+        return ret;
     }
 
     memset(&cow_header, 0, sizeof(cow_header));
@@ -381,29 +318,22 @@ static int cow_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
 exit:
-    g_free(image_filename);
-    if (cow_bs) {
-        bdrv_unref(cow_bs);
-    }
+    bdrv_delete(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 +345,12 @@ 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,
+    .bdrv_co_is_allocated   = cow_co_is_allocated,
 
-    .create_opts    = &cow_create_opts,
+    .create_options = cow_create_options,
 };
 
 static void bdrv_cow_init(void)

block/curl.c

@@ -23,7 +23,6 @@
  */
 #include "qemu-common.h"
 #include "block/block_int.h"
-#include "qapi/qmp/qbool.h"
 #include <curl/curl.h>
 
 // #define DEBUG
@@ -35,26 +34,6 @@
 #define DPRINTF(fmt, ...) do { } while (0)
 #endif
 
-#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 | \
                    CURLPROTO_FTP | CURLPROTO_FTPS | \
                    CURLPROTO_TFTP)
@@ -62,16 +41,12 @@ 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 +66,6 @@ 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;
@@ -103,61 +77,34 @@ typedef struct CURLState
 
 typedef struct BDRVCURLState {
     CURLM *multi;
-    QEMUTimer timer;
     size_t len;
     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)
-{
-    BDRVCURLState *s = opaque;
-
-    DPRINTF("CURL: timer callback timeout_ms %ld\n", timeout_ms);
-    if (timeout_ms == -1) {
-        timer_del(&s->timer);
-    } else {
-        int64_t timeout_ns = (int64_t)timeout_ms * 1000 * 1000;
-        timer_mod(&s->timer,
-                  qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + timeout_ns);
-    }
-    return 0;
-}
-#endif
+static int curl_aio_flush(void *opaque);
 
 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, curl_aio_flush, 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, curl_aio_flush, 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,
+                                    curl_aio_flush, 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, NULL);
             break;
     }
 
@@ -187,13 +134,8 @@ 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 */
-        return 0;
-    }
-    realsize = MIN(realsize, s->buf_len - s->buf_off);
     memcpy(s->orig_buf + s->buf_off, ptr, realsize);
     s->buf_off += realsize;
 
@@ -212,6 +154,7 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
         }
     }
 
+read_end:
     return realsize;
 }
 
@@ -246,8 +189,7 @@ 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))
@@ -269,87 +211,61 @@ 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_do(void *arg)
 {
+    BDRVCURLState *s = (BDRVCURLState *)arg;
+    int running;
+    int r;
     int msgs_in_queue;
 
+    if (!s->multi)
+        return;
+
+    do {
+        r = curl_multi_socket_all(s->multi, &running);
+    } while(r == CURLM_CALL_MULTI_PERFORM);
+
     /* 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;
         }
-    }
-}
-
-static void curl_multi_do(void *arg)
-{
-    CURLState *s = (CURLState *)arg;
-    int running;
-    int r;
-
-    if (!s->s->multi) {
-        return;
-    }
-
-    do {
-        r = curl_multi_socket_action(s->s->multi, s->sock_fd, 0, &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);
-}
-
-static void curl_multi_timeout_do(void *arg)
-{
-#ifdef NEED_CURL_TIMER_CALLBACK
-    BDRVCURLState *s = (BDRVCURLState *)arg;
-    int running;
-
-    if (!s->multi) {
-        return;
-    }
-
-    curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
-
-    curl_multi_check_completion(s);
-#else
-    abort();
-#endif
+    } while(msgs_in_queue);
 }
 
 static CURLState *curl_init_state(BDRVCURLState *s)
@@ -370,44 +286,44 @@ 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 +340,43 @@ 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 = {
@@ -475,26 +384,20 @@ 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 */ }
     },
 };
 
-static int curl_open(BlockDriverState *bs, QDict *options, int flags,
-                     Error **errp)
+static int curl_open(BlockDriverState *bs, QDict *options, int flags)
 {
     BDRVCURLState *s = bs->opaque;
     CURLState *state = NULL;
@@ -506,30 +409,30 @@ 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 +442,6 @@ 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 +474,19 @@ 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));
+    // 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);
+    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:
@@ -587,6 +495,21 @@ out_noclean:
     return -EINVAL;
 }
 
+static int curl_aio_flush(void *opaque)
+{
+    BDRVCURLState *s = opaque;
+    int i, j;
+
+    for (i=0; i < CURL_NUM_STATES; i++) {
+        for(j=0; j < CURL_NUM_ACB; j++) {
+            if (s->states[i].acb[j]) {
+                return 1;
+            }
+        }
+    }
+    return 0;
+}
+
 static void curl_aio_cancel(BlockDriverAIOCB *blockacb)
 {
     // Do we have to implement canceling? Seems to work without...
@@ -601,7 +524,6 @@ 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 +558,8 @@ 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 +572,8 @@ 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 +588,13 @@ 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);
+
+    if (!acb->bh) {
+        DPRINTF("CURL: qemu_bh_new failed\n");
+        return NULL;
+    }
+
     qemu_bh_schedule(acb->bh);
     return &acb->common;
 }
@@ -674,10 +602,23 @@ 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);
     g_free(s->url);
 }
 
@@ -688,83 +629,68 @@ 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)

block/dmg.c

@@ -27,14 +27,6 @@
 #include "qemu/module.h"
 #include <zlib.h>
 
-enum {
-    /* Limit chunk sizes to prevent unreasonable amounts of memory being used
-     * or truncating when converting to 32-bit types
-     */
-    DMG_LENGTHS_MAX = 64 * 1024 * 1024, /* 64 MB */
-    DMG_SECTORCOUNTS_MAX = DMG_LENGTHS_MAX / 512,
-};
-
 typedef struct BDRVDMGState {
     CoMutex lock;
     /* each chunk contains a certain number of sectors,
@@ -100,44 +92,12 @@ static int read_uint32(BlockDriverState *bs, int64_t offset, uint32_t *result)
     return 0;
 }
 
-/* Increase max chunk sizes, if necessary.  This function is used to calculate
- * the buffer sizes needed for compressed/uncompressed chunk I/O.
- */
-static void update_max_chunk_size(BDRVDMGState *s, uint32_t chunk,
-                                  uint32_t *max_compressed_size,
-                                  uint32_t *max_sectors_per_chunk)
-{
-    uint32_t compressed_size = 0;
-    uint32_t uncompressed_sectors = 0;
-
-    switch (s->types[chunk]) {
-    case 0x80000005: /* zlib compressed */
-        compressed_size = s->lengths[chunk];
-        uncompressed_sectors = s->sectorcounts[chunk];
-        break;
-    case 1: /* copy */
-        uncompressed_sectors = (s->lengths[chunk] + 511) / 512;
-        break;
-    case 2: /* zero */
-        uncompressed_sectors = s->sectorcounts[chunk];
-        break;
-    }
-
-    if (compressed_size > *max_compressed_size) {
-        *max_compressed_size = compressed_size;
-    }
-    if (uncompressed_sectors > *max_sectors_per_chunk) {
-        *max_sectors_per_chunk = uncompressed_sectors;
-    }
-}
-
-static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
-                    Error **errp)
+static int dmg_open(BlockDriverState *bs, QDict *options, int flags)
 {
     BDRVDMGState *s = bs->opaque;
-    uint64_t info_begin, info_end, last_in_offset, last_out_offset;
+    uint64_t info_begin,info_end,last_in_offset,last_out_offset;
     uint32_t count, tmp;
-    uint32_t max_compressed_size = 1, max_sectors_per_chunk = 1, i;
+    uint32_t max_compressed_size=1,max_sectors_per_chunk=1,i;
     int64_t offset;
     int ret;
 
@@ -199,40 +159,37 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
             goto fail;
         }
 
-        if (type == 0x6d697368 && count >= 244) {
-            size_t new_size;
-            uint32_t chunk_count;
+	if (type == 0x6d697368 && count >= 244) {
+	    int new_size, chunk_count;
 
             offset += 4;
             offset += 200;
 
-            chunk_count = (count - 204) / 40;
-            new_size = sizeof(uint64_t) * (s->n_chunks + chunk_count);
-            s->types = g_realloc(s->types, new_size / 2);
-            s->offsets = g_realloc(s->offsets, new_size);
-            s->lengths = g_realloc(s->lengths, new_size);
-            s->sectors = g_realloc(s->sectors, new_size);
-            s->sectorcounts = g_realloc(s->sectorcounts, new_size);
+	    chunk_count = (count-204)/40;
+	    new_size = sizeof(uint64_t) * (s->n_chunks + chunk_count);
+	    s->types = g_realloc(s->types, new_size/2);
+	    s->offsets = g_realloc(s->offsets, new_size);
+	    s->lengths = g_realloc(s->lengths, new_size);
+	    s->sectors = g_realloc(s->sectors, new_size);
+	    s->sectorcounts = g_realloc(s->sectorcounts, new_size);
 
             for (i = s->n_chunks; i < s->n_chunks + chunk_count; i++) {
                 ret = read_uint32(bs, offset, &s->types[i]);
                 if (ret < 0) {
                     goto fail;
                 }
-                offset += 4;
-                if (s->types[i] != 0x80000005 && s->types[i] != 1 &&
-                    s->types[i] != 2) {
-                    if (s->types[i] == 0xffffffff && i > 0) {
-                        last_in_offset = s->offsets[i - 1] + s->lengths[i - 1];
-                        last_out_offset = s->sectors[i - 1] +
-                                          s->sectorcounts[i - 1];
-                    }
-                    chunk_count--;
-                    i--;
-                    offset += 36;
-                    continue;
-                }
-                offset += 4;
+		offset += 4;
+		if(s->types[i]!=0x80000005 && s->types[i]!=1 && s->types[i]!=2) {
+		    if(s->types[i]==0xffffffff) {
+			last_in_offset = s->offsets[i-1]+s->lengths[i-1];
+			last_out_offset = s->sectors[i-1]+s->sectorcounts[i-1];
+		    }
+		    chunk_count--;
+		    i--;
+		    offset += 36;
+		    continue;
+		}
+		offset += 4;
 
                 ret = read_uint64(bs, offset, &s->sectors[i]);
                 if (ret < 0) {
@@ -247,14 +204,6 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
                 }
                 offset += 8;
 
-                if (s->sectorcounts[i] > DMG_SECTORCOUNTS_MAX) {
-                    error_report("sector count %" PRIu64 " for chunk %" PRIu32
-                                 " is larger than max (%u)",
-                                 s->sectorcounts[i], i, DMG_SECTORCOUNTS_MAX);
-                    ret = -EINVAL;
-                    goto fail;
-                }
-
                 ret = read_uint64(bs, offset, &s->offsets[i]);
                 if (ret < 0) {
                     goto fail;
@@ -268,25 +217,19 @@ 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)",
-                                 s->lengths[i], i, DMG_LENGTHS_MAX);
-                    ret = -EINVAL;
-                    goto fail;
-                }
-
-                update_max_chunk_size(s, i, &max_compressed_size,
-                                      &max_sectors_per_chunk);
-            }
-            s->n_chunks += chunk_count;
-        }
+		if(s->lengths[i]>max_compressed_size)
+		    max_compressed_size = s->lengths[i];
+		if(s->sectorcounts[i]>max_sectors_per_chunk)
+		    max_sectors_per_chunk = s->sectorcounts[i];
+	    }
+	    s->n_chunks+=chunk_count;
+	}
     }
 
     /* initialize zlib engine */
-    s->compressed_chunk = g_malloc(max_compressed_size + 1);
-    s->uncompressed_chunk = g_malloc(512 * max_sectors_per_chunk);
-    if (inflateInit(&s->zstream) != Z_OK) {
+    s->compressed_chunk = g_malloc(max_compressed_size+1);
+    s->uncompressed_chunk = g_malloc(512*max_sectors_per_chunk);
+    if(inflateInit(&s->zstream) != Z_OK) {
         ret = -EINVAL;
         goto fail;
     }
@@ -308,82 +251,83 @@ fail:
 }
 
 static inline int is_sector_in_chunk(BDRVDMGState* s,
-                uint32_t chunk_num, uint64_t sector_num)
+		uint32_t chunk_num,int sector_num)
 {
-    if (chunk_num >= s->n_chunks || s->sectors[chunk_num] > sector_num ||
-            s->sectors[chunk_num] + s->sectorcounts[chunk_num] <= sector_num) {
-        return 0;
-    } else {
-        return -1;
-    }
+    if(chunk_num>=s->n_chunks || s->sectors[chunk_num]>sector_num ||
+	    s->sectors[chunk_num]+s->sectorcounts[chunk_num]<=sector_num)
+	return 0;
+    else
+	return -1;
 }
 
-static inline uint32_t search_chunk(BDRVDMGState *s, uint64_t sector_num)
+static inline uint32_t search_chunk(BDRVDMGState* s,int sector_num)
 {
     /* binary search */
-    uint32_t chunk1 = 0, chunk2 = s->n_chunks, chunk3;
-    while (chunk1 != chunk2) {
-        chunk3 = (chunk1 + chunk2) / 2;
-        if (s->sectors[chunk3] > sector_num) {
-            chunk2 = chunk3;
-        } else if (s->sectors[chunk3] + s->sectorcounts[chunk3] > sector_num) {
-            return chunk3;
-        } else {
-            chunk1 = chunk3;
-        }
+    uint32_t chunk1=0,chunk2=s->n_chunks,chunk3;
+    while(chunk1!=chunk2) {
+	chunk3 = (chunk1+chunk2)/2;
+	if(s->sectors[chunk3]>sector_num)
+	    chunk2 = chunk3;
+	else if(s->sectors[chunk3]+s->sectorcounts[chunk3]>sector_num)
+	    return chunk3;
+	else
+	    chunk1 = chunk3;
     }
     return s->n_chunks; /* error */
 }
 
-static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num)
+static inline int dmg_read_chunk(BlockDriverState *bs, int sector_num)
 {
     BDRVDMGState *s = bs->opaque;
 
-    if (!is_sector_in_chunk(s, s->current_chunk, sector_num)) {
-        int ret;
-        uint32_t chunk = search_chunk(s, sector_num);
+    if(!is_sector_in_chunk(s,s->current_chunk,sector_num)) {
+	int ret;
+	uint32_t chunk = search_chunk(s,sector_num);
 
-        if (chunk >= s->n_chunks) {
-            return -1;
-        }
+	if(chunk>=s->n_chunks)
+	    return -1;
 
-        s->current_chunk = s->n_chunks;
-        switch (s->types[chunk]) {
-        case 0x80000005: { /* zlib compressed */
-            /* we need to buffer, because only the chunk as whole can be
-             * inflated. */
-            ret = bdrv_pread(bs->file, s->offsets[chunk],
-                             s->compressed_chunk, s->lengths[chunk]);
-            if (ret != s->lengths[chunk]) {
-                return -1;
-            }
+	s->current_chunk = s->n_chunks;
+	switch(s->types[chunk]) {
+	case 0x80000005: { /* zlib compressed */
+	    int i;
 
-            s->zstream.next_in = s->compressed_chunk;
-            s->zstream.avail_in = s->lengths[chunk];
-            s->zstream.next_out = s->uncompressed_chunk;
-            s->zstream.avail_out = 512 * s->sectorcounts[chunk];
-            ret = inflateReset(&s->zstream);
-            if (ret != Z_OK) {
-                return -1;
-            }
-            ret = inflate(&s->zstream, Z_FINISH);
-            if (ret != Z_STREAM_END ||
-                s->zstream.total_out != 512 * s->sectorcounts[chunk]) {
-                return -1;
-            }
-            break; }
-        case 1: /* copy */
-            ret = bdrv_pread(bs->file, s->offsets[chunk],
+	    /* we need to buffer, because only the chunk as whole can be
+	     * inflated. */
+	    i=0;
+	    do {
+                ret = bdrv_pread(bs->file, s->offsets[chunk] + i,
+                                 s->compressed_chunk+i, s->lengths[chunk]-i);
+		if(ret<0 && errno==EINTR)
+		    ret=0;
+		i+=ret;
+	    } while(ret>=0 && ret+i<s->lengths[chunk]);
+
+	    if (ret != s->lengths[chunk])
+		return -1;
+
+	    s->zstream.next_in = s->compressed_chunk;
+	    s->zstream.avail_in = s->lengths[chunk];
+	    s->zstream.next_out = s->uncompressed_chunk;
+	    s->zstream.avail_out = 512*s->sectorcounts[chunk];
+	    ret = inflateReset(&s->zstream);
+	    if(ret != Z_OK)
+		return -1;
+	    ret = inflate(&s->zstream, Z_FINISH);
+	    if(ret != Z_STREAM_END || s->zstream.total_out != 512*s->sectorcounts[chunk])
+		return -1;
+	    break; }
+	case 1: /* copy */
+	    ret = bdrv_pread(bs->file, s->offsets[chunk],
                              s->uncompressed_chunk, s->lengths[chunk]);
-            if (ret != s->lengths[chunk]) {
-                return -1;
-            }
-            break;
-        case 2: /* zero */
-            memset(s->uncompressed_chunk, 0, 512 * s->sectorcounts[chunk]);
-            break;
-        }
-        s->current_chunk = chunk;
+	    if (ret != s->lengths[chunk])
+		return -1;
+	    break;
+	case 2: /* zero */
+	    memset(s->uncompressed_chunk, 0, 512*s->sectorcounts[chunk]);
+	    break;
+	}
+	s->current_chunk = chunk;
     }
     return 0;
 }
@@ -394,14 +338,12 @@ static int dmg_read(BlockDriverState *bs, int64_t sector_num,
     BDRVDMGState *s = bs->opaque;
     int i;
 
-    for (i = 0; i < nb_sectors; i++) {
-        uint32_t sector_offset_in_chunk;
-        if (dmg_read_chunk(bs, sector_num + i) != 0) {
-            return -1;
-        }
-        sector_offset_in_chunk = sector_num + i - s->sectors[s->current_chunk];
-        memcpy(buf + i * 512,
-               s->uncompressed_chunk + sector_offset_in_chunk * 512, 512);
+    for(i=0;i<nb_sectors;i++) {
+	uint32_t sector_offset_in_chunk;
+	if(dmg_read_chunk(bs, sector_num+i) != 0)
+	    return -1;
+	sector_offset_in_chunk = sector_num+i-s->sectors[s->current_chunk];
+	memcpy(buf+i*512,s->uncompressed_chunk+sector_offset_in_chunk*512,512);
     }
     return 0;
 }
@@ -433,12 +375,12 @@ static void dmg_close(BlockDriverState *bs)
 }
 
 static BlockDriver bdrv_dmg = {
-    .format_name    = "dmg",
-    .instance_size  = sizeof(BDRVDMGState),
-    .bdrv_probe     = dmg_probe,
-    .bdrv_open      = dmg_open,
-    .bdrv_read      = dmg_co_read,
-    .bdrv_close     = dmg_close,
+    .format_name	= "dmg",
+    .instance_size	= sizeof(BDRVDMGState),
+    .bdrv_probe		= dmg_probe,
+    .bdrv_open		= dmg_open,
+    .bdrv_read          = dmg_co_read,
+    .bdrv_close		= dmg_close,
 };
 
 static void bdrv_dmg_init(void)

block/gluster.c

@@ -3,27 +3,43 @@
  *
  * 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 qemu_aio_count;
+    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 +50,11 @@ 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 +95,7 @@ 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 +132,7 @@ 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 +168,7 @@ 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 +180,7 @@ 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 +188,8 @@ 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 +216,9 @@ 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 +232,54 @@ 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);
+    s->qemu_aio_count--;
+    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);
+}
+
+static int qemu_gluster_aio_flush_cb(void *opaque)
+{
+    BDRVGlusterState *s = opaque;
+
+    return (s->qemu_aio_count > 0);
 }
 
 /* TODO Convert to fine grained options */
@@ -268,57 +296,60 @@ 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)
+                             int bdrv_flags)
 {
     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, qemu_gluster_aio_flush_cb, s);
+
 out:
     qemu_opts_del(opts);
     qemu_gluster_gconf_free(gconf);
@@ -334,181 +365,26 @@ 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)
 {
     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 +392,14 @@ 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 +407,72 @@ 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.
+         *
+         * Complete this IO request and make the disk inaccessible for
+         * subsequent reads and writes.
+         */
+        error_report("Gluster failed to notify QEMU about IO completion");
+
+        qemu_mutex_lock_iothread(); /* We are in gluster thread context */
+        acb->common.cb(acb->common.opaque, -EIO);
+        qemu_aio_release(acb);
+        s->qemu_aio_count--;
+        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,
+            NULL);
+        bs->drv = NULL; /* Make the disk inaccessible */
+        qemu_mutex_unlock_iothread();
+    }
+}
+
+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;
+    s->qemu_aio_count++;
+
+    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 +483,14 @@ 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;
+    s->qemu_aio_count--;
+    qemu_aio_release(acb);
+    return NULL;
 }
 
 static int qemu_gluster_truncate(BlockDriverState *bs, int64_t offset)
@@ -586,70 +506,75 @@ 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;
+    s->qemu_aio_count++;
 
     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;
+    s->qemu_aio_count--;
+    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;
+    s->qemu_aio_count++;
 
     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;
+    s->qemu_aio_count--;
+    qemu_aio_release(acb);
+    return NULL;
 }
 #endif
 
@@ -684,6 +609,10 @@ 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, NULL);
+
     if (s->fd) {
         glfs_close(s->fd);
         s->fd = NULL;
@@ -697,130 +626,93 @@ 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 = {
     .format_name                  = "gluster",
     .protocol_name                = "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 = {
     .format_name                  = "gluster",
     .protocol_name                = "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 = {
     .format_name                  = "gluster",
     .protocol_name                = "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 = {
     .format_name                  = "gluster",
     .protocol_name                = "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)

block/linux-aio.c

@@ -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 +36,10 @@ 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;
+    int count;
 };
 
 static inline ssize_t io_event_ret(struct io_event *ev)
@@ -66,6 +55,8 @@ static void qemu_laio_process_completion(struct qemu_laio_state *s,
 {
     int ret;
 
+    s->count--;
+
     ret = laiocb->ret;
     if (ret != -ECANCELED) {
         if (ret == laiocb->nbytes) {
@@ -110,6 +101,13 @@ static void qemu_laio_completion_cb(EventNotifier *e)
     }
 }
 
+static int qemu_laio_flush_cb(EventNotifier *e)
+{
+    struct qemu_laio_state *s = container_of(e, struct qemu_laio_state, e);
+
+    return (s->count > 0) ? 1 : 0;
+}
+
 static void laio_cancel(BlockDriverAIOCB *blockacb)
 {
     struct qemu_laiocb *laiocb = (struct qemu_laiocb *)blockacb;
@@ -147,79 +145,6 @@ 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)
@@ -252,35 +177,19 @@ BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
         goto out_free_aiocb;
     }
     io_set_eventfd(&laiocb->iocb, event_notifier_get_fd(&s->e));
+    s->count++;
 
-    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_dec_count;
     return &laiocb->common;
 
+out_dec_count:
+    s->count--;
 out_free_aiocb:
     qemu_aio_release(laiocb);
     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 +203,8 @@ void *laio_init(void)
         goto out_close_efd;
     }
 
-    ioq_init(&s->io_q);
+    qemu_aio_set_event_notifier(&s->e, qemu_laio_completion_cb,
+                                qemu_laio_flush_cb);
 
     return s;
 
@@ -304,16 +214,3 @@ 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);
-}

block/mirror.c

@@ -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;
@@ -102,16 +94,8 @@ 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
-     * rate-limit itself.  The coroutine will eventually resume since there is
-     * a sleep timeout so don't wake it early.
-     */
-    if (s->common.busy) {
-        qemu_coroutine_enter(s->common.co, NULL);
-    }
+    qemu_coroutine_enter(s->common.co, NULL);
 }
 
 static void mirror_write_complete(void *opaque, int ret)
@@ -124,7 +108,7 @@ 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 +125,7 @@ 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;
         }
 
@@ -152,20 +136,18 @@ static void mirror_read_complete(void *opaque, int ret)
                     mirror_write_complete, op);
 }
 
-static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
+static void coroutine_fn mirror_iteration(MirrorBlockJob *s)
 {
     BlockDriverState *source = s->common.bs;
     int nb_sectors, sectors_per_chunk, nb_chunks;
     int64_t end, sector_num, next_chunk, next_sector, hbitmap_next_sector;
-    uint64_t delay_ns;
     MirrorOp *op;
 
     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 +183,7 @@ 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;
@@ -245,12 +227,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
         nb_chunks += added_chunks;
         next_sector += added_sectors;
         next_chunk += added_chunks;
-        if (!s->synced && s->common.speed) {
-            delay_ns = ratelimit_calculate_delay(&s->limit, added_sectors);
-        } else {
-            delay_ns = 0;
-        }
-    } while (delay_ns == 0 && next_sector < end);
+    } while (next_sector < end);
 
     /* Allocate a MirrorOp that is used as an AIO callback.  */
     op = g_slice_new(MirrorOp);
@@ -265,17 +242,14 @@ 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);
         }
 
@@ -289,7 +263,6 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
     trace_mirror_one_iteration(s, sector_num, nb_sectors);
     bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors,
                    mirror_read_complete, op);
-    return delay_ns;
 }
 
 static void mirror_free_init(MirrorBlockJob *s)
@@ -332,21 +305,12 @@ 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 +320,7 @@ 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);
@@ -371,13 +332,14 @@ 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,
-                                          sector_num, next - sector_num, &n);
+            ret = bdrv_co_is_allocated_above(bs, base,
+                                             sector_num, next - sector_num, &n);
 
             if (ret < 0) {
                 goto immediate_exit;
@@ -393,10 +355,10 @@ static void coroutine_fn mirror_run(void *opaque)
         }
     }
 
-    bdrv_dirty_iter_init(bs, s->dirty_bitmap, &s->hbi);
-    last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
+    bdrv_dirty_iter_init(bs, &s->hbi);
+    last_pause_ns = qemu_get_clock_ns(rt_clock);
     for (;;) {
-        uint64_t delay_ns = 0;
+        uint64_t delay_ns;
         int64_t cnt;
         bool should_complete;
 
@@ -405,14 +367,14 @@ 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.
          * We do so every SLICE_TIME nanoseconds, or when there is an error,
          * or when the source is clean, whichever comes first.
          */
-        if (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - last_pause_ns < SLICE_TIME &&
+        if (qemu_get_clock_ns(rt_clock) - last_pause_ns < SLICE_TIME &&
             s->common.iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
             if (s->in_flight == MAX_IN_FLIGHT || s->buf_free_count == 0 ||
                 (cnt == 0 && s->in_flight > 0)) {
@@ -420,10 +382,8 @@ static void coroutine_fn mirror_run(void *opaque)
                 qemu_coroutine_yield();
                 continue;
             } else if (cnt != 0) {
-                delay_ns = mirror_iteration(s);
-                if (delay_ns == 0) {
-                    continue;
-                }
+                mirror_iteration(s);
+                continue;
             }
         }
 
@@ -432,8 +392,7 @@ 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 +403,13 @@ 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);
             }
         }
 
@@ -465,21 +424,28 @@ 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;
-        trace_mirror_before_sleep(s, cnt, s->synced, delay_ns);
+        trace_mirror_before_sleep(s, cnt, s->synced);
         if (!s->synced) {
             /* Publish progress */
             s->common.offset = (end - cnt) * BDRV_SECTOR_SIZE;
-            block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, delay_ns);
+
+            if (s->common.speed) {
+                delay_ns = ratelimit_calculate_delay(&s->limit, sectors_per_chunk);
+            } else {
+                delay_ns = 0;
+            }
+
+            block_job_sleep_ns(&s->common, rt_clock, delay_ns);
             if (block_job_is_cancelled(&s->common)) {
                 break;
             }
         } else if (!should_complete) {
             delay_ns = (s->in_flight == 0 && cnt == 0 ? SLICE_TIME : 0);
-            block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, delay_ns);
+            block_job_sleep_ns(&s->common, rt_clock, delay_ns);
         } else if (cnt == 0) {
             /* The two disks are in sync.  Exit and report successful
              * completion.
@@ -488,7 +454,7 @@ static void coroutine_fn mirror_run(void *opaque)
             s->common.cancelled = false;
             break;
         }
-        last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
+        last_pause_ns = qemu_get_clock_ns(rt_clock);
     }
 
 immediate_exit:
@@ -505,32 +471,16 @@ 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_unref(s->target);
+    bdrv_close(s->target);
+    bdrv_delete(s->target);
     block_job_completed(&s->common, ret);
 }
 
@@ -555,12 +505,14 @@ static void mirror_iostatus_reset(BlockJob *job)
 static void mirror_complete(BlockJob *job, Error **errp)
 {
     MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
-    Error *local_err = NULL;
     int ret;
 
-    ret = bdrv_open_backing_file(s->target, NULL, &local_err);
+    ret = bdrv_open_backing_file(s->target, NULL);
     if (ret < 0) {
-        error_propagate(errp, local_err);
+        char backing_filename[PATH_MAX];
+        bdrv_get_full_backing_filename(s->target, backing_filename,
+                                       sizeof(backing_filename));
+        error_setg_file_open(errp, -ret, backing_filename);
         return;
     }
     if (!s->synced) {
@@ -568,51 +520,24 @@ 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);
 }
 
-static const BlockJobDriver mirror_job_driver = {
+static const BlockJobType mirror_job_type = {
     .instance_size = sizeof(MirrorBlockJob),
-    .job_type      = BLOCK_JOB_TYPE_MIRROR,
+    .job_type      = "mirror",
     .set_speed     = mirror_set_speed,
     .iostatus_reset= mirror_iostatus_reset,
     .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 +562,19 @@ 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_type, 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 +582,3 @@ 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;
-}

block/nbd-client.c

@@ -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;
-}

block/nbd-client.h

@@ -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 */

block/nbd.c

@@ -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 +217,204 @@ 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 int nbd_have_request(void *opaque)
+{
+    BDRVNBDState *s = opaque;
+
+    return s->in_flight > 0;
+}
+
+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,
+                            nbd_have_request, 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,
+                            nbd_have_request, 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 +426,268 @@ 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,
+                            nbd_have_request, s);
+
+    s->sock = sock;
+    s->size = size;
+    s->blocksize = blocksize;
+
+    logout("Established connection with NBD server\n");
+    return 0;
 }
 
-static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
-                    Error **errp)
+static void nbd_teardown_connection(BlockDriverState *bs)
 {
     BDRVNBDState *s = bs->opaque;
-    char *export = NULL;
-    int result, sock;
-    Error *local_err = NULL;
+    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, NULL);
+    closesocket(s->sock);
+}
+
+static int nbd_open(BlockDriverState *bs, QDict *options, int flags)
+{
+    BDRVNBDState *s = bs->opaque;
+    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)

block/nfs.c

@@ -1,485 +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 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,
-    .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);

block/parallels.c

@@ -49,9 +49,9 @@ typedef struct BDRVParallelsState {
     CoMutex lock;
 
     uint32_t *catalog_bitmap;
-    unsigned int catalog_size;
+    int catalog_size;
 
-    unsigned int tracks;
+    int tracks;
 } BDRVParallelsState;
 
 static int parallels_probe(const uint8_t *buf, int buf_size, const char *filename)
@@ -68,8 +68,7 @@ static int parallels_probe(const uint8_t *buf, int buf_size, const char *filenam
     return 0;
 }
 
-static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
-                          Error **errp)
+static int parallels_open(BlockDriverState *bs, QDict *options, int flags)
 {
     BDRVParallelsState *s = bs->opaque;
     int i;
@@ -85,26 +84,15 @@ 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;
     }
 
     bs->total_sectors = le32_to_cpu(ph.nb_sectors);
 
     s->tracks = le32_to_cpu(ph.tracks);
-    if (s->tracks == 0) {
-        error_setg(errp, "Invalid image: Zero sectors per track");
-        ret = -EINVAL;
-        goto fail;
-    }
 
     s->catalog_size = le32_to_cpu(ph.catalog_entries);
-    if (s->catalog_size > INT_MAX / 4) {
-        error_setg(errp, "Catalog too large");
-        ret = -EFBIG;
-        goto fail;
-    }
     s->catalog_bitmap = g_malloc(s->catalog_size * 4);
 
     ret = bdrv_pread(bs->file, 64, s->catalog_bitmap, s->catalog_size * 4);

block/qapi.c

@@ -25,64 +25,6 @@
 #include "block/qapi.h"
 #include "block/block_int.h"
 #include "qmp-commands.h"
-#include "qapi-visit.h"
-#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
@@ -192,9 +134,6 @@ void bdrv_query_image_info(BlockDriverState *bs,
         info->dirty_flag = bdi.is_dirty;
         info->has_dirty_flag = true;
     }
-    info->format_specific     = bdrv_get_specific_info(bs);
-    info->has_format_specific = info->format_specific != NULL;
-
     backing_filename = bs->backing_file;
     if (backing_filename[0] != '\0') {
         info->backing_filename = g_strdup(backing_filename);
@@ -259,20 +198,50 @@ 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) {
+            info->inserted->bps =
+                           bs->io_limits.bps[BLOCK_IO_LIMIT_TOTAL];
+            info->inserted->bps_rd =
+                           bs->io_limits.bps[BLOCK_IO_LIMIT_READ];
+            info->inserted->bps_wr =
+                           bs->io_limits.bps[BLOCK_IO_LIMIT_WRITE];
+            info->inserted->iops =
+                           bs->io_limits.iops[BLOCK_IO_LIMIT_TOTAL];
+            info->inserted->iops_rd =
+                           bs->io_limits.iops[BLOCK_IO_LIMIT_READ];
+            info->inserted->iops_wr =
+                           bs->io_limits.iops[BLOCK_IO_LIMIT_WRITE];
+        }
 
         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 +262,7 @@ 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 +289,6 @@ 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 +301,7 @@ 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 +324,7 @@ 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;
@@ -437,119 +397,6 @@ void bdrv_snapshot_dump(fprintf_function func_fprintf, void *f,
     }
 }
 
-static void dump_qdict(fprintf_function func_fprintf, void *f, int indentation,
-                       QDict *dict);
-static void dump_qlist(fprintf_function func_fprintf, void *f, int indentation,
-                       QList *list);
-
-static void dump_qobject(fprintf_function func_fprintf, void *f,
-                         int comp_indent, QObject *obj)
-{
-    switch (qobject_type(obj)) {
-        case QTYPE_QINT: {
-            QInt *value = qobject_to_qint(obj);
-            func_fprintf(f, "%" PRId64, qint_get_int(value));
-            break;
-        }
-        case QTYPE_QSTRING: {
-            QString *value = qobject_to_qstring(obj);
-            func_fprintf(f, "%s", qstring_get_str(value));
-            break;
-        }
-        case QTYPE_QDICT: {
-            QDict *value = qobject_to_qdict(obj);
-            dump_qdict(func_fprintf, f, comp_indent, value);
-            break;
-        }
-        case QTYPE_QLIST: {
-            QList *value = qobject_to_qlist(obj);
-            dump_qlist(func_fprintf, f, comp_indent, value);
-            break;
-        }
-        case QTYPE_QFLOAT: {
-            QFloat *value = qobject_to_qfloat(obj);
-            func_fprintf(f, "%g", qfloat_get_double(value));
-            break;
-        }
-        case QTYPE_QBOOL: {
-            QBool *value = qobject_to_qbool(obj);
-            func_fprintf(f, "%s", qbool_get_int(value) ? "true" : "false");
-            break;
-        }
-        case QTYPE_QERROR: {
-            QString *value = qerror_human((QError *)obj);
-            func_fprintf(f, "%s", qstring_get_str(value));
-            QDECREF(value);
-            break;
-        }
-        case QTYPE_NONE:
-            break;
-        case QTYPE_MAX:
-        default:
-            abort();
-    }
-}
-
-static void dump_qlist(fprintf_function func_fprintf, void *f, int indentation,
-                       QList *list)
-{
-    const QListEntry *entry;
-    int i = 0;
-
-    for (entry = qlist_first(list); entry; entry = qlist_next(entry), i++) {
-        qtype_code type = qobject_type(entry->value);
-        bool composite = (type == QTYPE_QDICT || type == QTYPE_QLIST);
-        const char *format = composite ? "%*s[%i]:\n" : "%*s[%i]: ";
-
-        func_fprintf(f, format, indentation * 4, "", i);
-        dump_qobject(func_fprintf, f, indentation + 1, entry->value);
-        if (!composite) {
-            func_fprintf(f, "\n");
-        }
-    }
-}
-
-static void dump_qdict(fprintf_function func_fprintf, void *f, int indentation,
-                       QDict *dict)
-{
-    const QDictEntry *entry;
-
-    for (entry = qdict_first(dict); entry; entry = qdict_next(dict, entry)) {
-        qtype_code type = qobject_type(entry->value);
-        bool composite = (type == QTYPE_QDICT || type == QTYPE_QLIST);
-        const char *format = composite ? "%*s%s:\n" : "%*s%s: ";
-        char key[strlen(entry->key) + 1];
-        int i;
-
-        /* replace dashes with spaces in key (variable) names */
-        for (i = 0; entry->key[i]; i++) {
-            key[i] = entry->key[i] == '-' ? ' ' : entry->key[i];
-        }
-        key[i] = 0;
-
-        func_fprintf(f, format, indentation * 4, "", key);
-        dump_qobject(func_fprintf, f, indentation + 1, entry->value);
-        if (!composite) {
-            func_fprintf(f, "\n");
-        }
-    }
-}
-
-void bdrv_image_info_specific_dump(fprintf_function func_fprintf, void *f,
-                                   ImageInfoSpecific *info_spec)
-{
-    QmpOutputVisitor *ov = qmp_output_visitor_new();
-    QObject *obj, *data;
-
-    visit_type_ImageInfoSpecific(qmp_output_get_visitor(ov), &info_spec, NULL,
-                                 &error_abort);
-    obj = qmp_output_get_qobject(ov);
-    assert(qobject_type(obj) == QTYPE_QDICT);
-    data = qdict_get(qobject_to_qdict(obj), "data");
-    dump_qobject(func_fprintf, f, 1, data);
-    qmp_output_visitor_cleanup(ov);
-}
-
 void bdrv_image_info_dump(fprintf_function func_fprintf, void *f,
                           ImageInfo *info)
 {
@@ -620,9 +467,4 @@ void bdrv_image_info_dump(fprintf_function func_fprintf, void *f,
             func_fprintf(f, "\n");
         }
     }
-
-    if (info->has_format_specific) {
-        func_fprintf(f, "Format specific information:\n");
-        bdrv_image_info_specific_dump(func_fprintf, f, info->format_specific);
-    }
 }

block/qcow.c

@@ -48,10 +48,9 @@ typedef struct QCowHeader {
     uint64_t size; /* in bytes */
     uint8_t cluster_bits;
     uint8_t l2_bits;
-    uint16_t padding;
     uint32_t crypt_method;
     uint64_t l1_table_offset;
-} QEMU_PACKED QCowHeader;
+} QCowHeader;
 
 #define L2_CACHE_SIZE 16
 
@@ -61,7 +60,7 @@ typedef struct BDRVQcowState {
     int cluster_sectors;
     int l2_bits;
     int l2_size;
-    unsigned int l1_size;
+    int l1_size;
     uint64_t cluster_offset_mask;
     uint64_t l1_table_offset;
     uint64_t *l1_table;
@@ -93,12 +92,10 @@ static int qcow_probe(const uint8_t *buf, int buf_size, const char *filename)
         return 0;
 }
 
-static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
-                     Error **errp)
+static int qcow_open(BlockDriverState *bs, QDict *options, int flags)
 {
     BDRVQcowState *s = bs->opaque;
-    unsigned int len, i, shift;
-    int ret;
+    int len, i, shift, ret;
     QCowHeader header;
 
     ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
@@ -115,41 +112,23 @@ 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;
     }
 
-    if (header.size <= 1) {
-        error_setg(errp, "Image size is too small (must be at least 2 bytes)");
+    if (header.size <= 1 || header.cluster_bits < 9) {
         ret = -EINVAL;
         goto fail;
     }
-    if (header.cluster_bits < 9 || header.cluster_bits > 16) {
-        error_setg(errp, "Cluster size must be between 512 and 64k");
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    /* l2_bits specifies number of entries; storing a uint64_t in each entry,
-     * so bytes = num_entries << 3. */
-    if (header.l2_bits < 9 - 3 || header.l2_bits > 16 - 3) {
-        error_setg(errp, "L2 table size must be between 512 and 64k");
-        ret = -EINVAL;
-        goto fail;
-    }
-
     if (header.crypt_method > QCOW_CRYPT_AES) {
-        error_setg(errp, "invalid encryption method in qcow header");
         ret = -EINVAL;
         goto fail;
     }
@@ -167,19 +146,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
 
     /* read the level 1 table */
     shift = s->cluster_bits + s->l2_bits;
-    if (header.size > UINT64_MAX - (1LL << shift)) {
-        error_setg(errp, "Image too large");
-        ret = -EINVAL;
-        goto fail;
-    } else {
-        uint64_t l1_size = (header.size + (1LL << shift) - 1) >> shift;
-        if (l1_size > INT_MAX / sizeof(uint64_t)) {
-            error_setg(errp, "Image too large");
-            ret = -EINVAL;
-            goto fail;
-        }
-        s->l1_size = l1_size;
-    }
+    s->l1_size = (header.size + (1LL << shift) - 1) >> shift;
 
     s->l1_table_offset = header.l1_table_offset;
     s->l1_table = g_malloc(s->l1_size * sizeof(uint64_t));
@@ -203,9 +170,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
     if (header.backing_file_offset != 0) {
         len = header.backing_file_size;
         if (len > 1023) {
-            error_setg(errp, "Backing file name too long");
-            ret = -EINVAL;
-            goto fail;
+            len = 1023;
         }
         ret = bdrv_pread(bs->file, header.backing_file_offset,
                    bs->backing_file, len);
@@ -430,7 +395,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
     return cluster_offset;
 }
 
-static int64_t coroutine_fn qcow_co_get_block_status(BlockDriverState *bs,
+static int coroutine_fn qcow_co_is_allocated(BlockDriverState *bs,
         int64_t sector_num, int nb_sectors, int *pnum)
 {
     BDRVQcowState *s = bs->opaque;
@@ -445,14 +410,7 @@ static int64_t coroutine_fn qcow_co_get_block_status(BlockDriverState *bs,
     if (n > nb_sectors)
         n = nb_sectors;
     *pnum = n;
-    if (!cluster_offset) {
-        return 0;
-    }
-    if ((cluster_offset & QCOW_OFLAG_COMPRESSED) || s->crypt_method) {
-        return BDRV_BLOCK_DATA;
-    }
-    cluster_offset |= (index_in_cluster << BDRV_SECTOR_BITS);
-    return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | cluster_offset;
+    return (cluster_offset != 0);
 }
 
 static int decompress_buffer(uint8_t *out_buf, int out_buf_size,
@@ -693,37 +651,37 @@ 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)
 {
     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);
     if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto cleanup;
+        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);
     if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto cleanup;
+        return ret;
     }
 
     ret = bdrv_truncate(qcow_bs, 0);
@@ -748,7 +706,7 @@ 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 */
@@ -793,9 +751,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
     g_free(tmp);
     ret = 0;
 exit:
-    bdrv_unref(qcow_bs);
-cleanup:
-    g_free(backing_file);
+    bdrv_delete(qcow_bs);
     return ret;
 }
 
@@ -908,28 +864,24 @@ 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 = {
@@ -938,21 +890,20 @@ 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,
-    .bdrv_co_get_block_status   = qcow_co_get_block_status,
+    .bdrv_co_is_allocated   = qcow_co_is_allocated,
 
     .bdrv_set_key           = qcow_set_key,
     .bdrv_make_empty        = qcow_make_empty,
     .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)

block/qcow2-cache.c

@@ -114,21 +114,6 @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)
         return ret;
     }
 
-    if (c == s->refcount_block_cache) {
-        ret = qcow2_pre_write_overlap_check(bs, QCOW2_OL_REFCOUNT_BLOCK,
-                c->entries[i].offset, s->cluster_size);
-    } else if (c == s->l2_table_cache) {
-        ret = qcow2_pre_write_overlap_check(bs, QCOW2_OL_ACTIVE_L2,
-                c->entries[i].offset, s->cluster_size);
-    } else {
-        ret = qcow2_pre_write_overlap_check(bs, 0,
-                c->entries[i].offset, s->cluster_size);
-    }
-
-    if (ret < 0) {
-        return ret;
-    }
-
     if (c == s->refcount_block_cache) {
         BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_UPDATE_PART);
     } else if (c == s->l2_table_cache) {
@@ -200,24 +185,6 @@ void qcow2_cache_depends_on_flush(Qcow2Cache *c)
     c->depends_on_flush = true;
 }
 
-int qcow2_cache_empty(BlockDriverState *bs, Qcow2Cache *c)
-{
-    int ret, i;
-
-    ret = qcow2_cache_flush(bs, c);
-    if (ret < 0) {
-        return ret;
-    }
-
-    for (i = 0; i < c->size; i++) {
-        assert(c->entries[i].ref == 0);
-        c->entries[i].offset = 0;
-        c->entries[i].cache_hits = 0;
-    }
-
-    return 0;
-}
-
 static int qcow2_cache_find_entry_to_replace(Qcow2Cache *c)
 {
     int i;

block/qcow2-cluster.c

@@ -35,20 +35,12 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
     BDRVQcowState *s = bs->opaque;
     int new_l1_size2, ret, i;
     uint64_t *new_l1_table;
-    int64_t old_l1_table_offset, old_l1_size;
     int64_t new_l1_table_offset, new_l1_size;
     uint8_t data[12];
 
     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 {
@@ -62,7 +54,7 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
         }
     }
 
-    if (new_l1_size > INT_MAX / sizeof(uint64_t)) {
+    if (new_l1_size > INT_MAX) {
         return -EFBIG;
     }
 
@@ -88,14 +80,6 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
         goto fail;
     }
 
-    /* the L1 position has not yet been updated, so these clusters must
-     * indeed be completely free */
-    ret = qcow2_pre_write_overlap_check(bs, 0, new_l1_table_offset,
-                                        new_l1_size2);
-    if (ret < 0) {
-        goto fail;
-    }
-
     BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_WRITE_TABLE);
     for(i = 0; i < s->l1_size; i++)
         new_l1_table[i] = cpu_to_be64(new_l1_table[i]);
@@ -108,19 +92,17 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
     /* set new table */
     BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_ACTIVATE_TABLE);
     cpu_to_be32w((uint32_t*)data, new_l1_size);
-    stq_be_p(data + 4, new_l1_table_offset);
+    cpu_to_be64wu((uint64_t*)(data + 4), new_l1_table_offset);
     ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, l1_size), data,sizeof(data));
     if (ret < 0) {
         goto fail;
     }
     g_free(s->l1_table);
-    old_l1_table_offset = s->l1_table_offset;
+    qcow2_free_clusters(bs, s->l1_table_offset, s->l1_size * sizeof(uint64_t),
+                        QCOW2_DISCARD_OTHER);
     s->l1_table_offset = new_l1_table_offset;
     s->l1_table = new_l1_table;
-    old_l1_size = s->l1_size;
     s->l1_size = new_l1_size;
-    qcow2_free_clusters(bs, old_l1_table_offset, old_l1_size * sizeof(uint64_t),
-                        QCOW2_DISCARD_OTHER);
     return 0;
  fail:
     g_free(new_l1_table);
@@ -155,7 +137,7 @@ static int l2_load(BlockDriverState *bs, uint64_t l2_offset,
  * and we really don't want bdrv_pread to perform a read-modify-write)
  */
 #define L1_ENTRIES_PER_SECTOR (512 / 8)
-int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index)
+static int write_l1_entry(BlockDriverState *bs, int l1_index)
 {
     BDRVQcowState *s = bs->opaque;
     uint64_t buf[L1_ENTRIES_PER_SECTOR];
@@ -167,12 +149,6 @@ int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index)
         buf[i] = cpu_to_be64(s->l1_table[l1_start_index + i]);
     }
 
-    ret = qcow2_pre_write_overlap_check(bs, QCOW2_OL_ACTIVE_L1,
-            s->l1_table_offset + 8 * l1_start_index, sizeof(buf));
-    if (ret < 0) {
-        return ret;
-    }
-
     BLKDBG_EVENT(bs->file, BLKDBG_L1_UPDATE);
     ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset + 8 * l1_start_index,
         buf, sizeof(buf));
@@ -197,7 +173,7 @@ static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table)
 {
     BDRVQcowState *s = bs->opaque;
     uint64_t old_l2_offset;
-    uint64_t *l2_table = NULL;
+    uint64_t *l2_table;
     int64_t l2_offset;
     int ret;
 
@@ -209,8 +185,7 @@ static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table)
 
     l2_offset = qcow2_alloc_clusters(bs, s->l2_size * sizeof(uint64_t));
     if (l2_offset < 0) {
-        ret = l2_offset;
-        goto fail;
+        return l2_offset;
     }
 
     ret = qcow2_cache_flush(bs, s->refcount_block_cache);
@@ -223,7 +198,7 @@ static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table)
     trace_qcow2_l2_allocate_get_empty(bs, l1_index);
     ret = qcow2_cache_get_empty(bs, s->l2_table_cache, l2_offset, (void**) table);
     if (ret < 0) {
-        goto fail;
+        return ret;
     }
 
     l2_table = *table;
@@ -264,7 +239,7 @@ static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table)
     /* update the L1 entry */
     trace_qcow2_l2_allocate_write_l1(bs, l1_index);
     s->l1_table[l1_index] = l2_offset | QCOW_OFLAG_COPIED;
-    ret = qcow2_write_l1_entry(bs, l1_index);
+    ret = write_l1_entry(bs, l1_index);
     if (ret < 0) {
         goto fail;
     }
@@ -275,14 +250,8 @@ static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table)
 
 fail:
     trace_qcow2_l2_allocate_done(bs, l1_index, ret);
-    if (l2_table != NULL) {
-        qcow2_cache_put(bs, s->l2_table_cache, (void**) table);
-    }
+    qcow2_cache_put(bs, s->l2_table_cache, (void**) table);
     s->l1_table[l1_index] = old_l2_offset;
-    if (l2_offset > 0) {
-        qcow2_free_clusters(bs, l2_offset, s->l2_size * sizeof(uint64_t),
-                            QCOW2_DISCARD_ALWAYS);
-    }
     return ret;
 }
 
@@ -294,26 +263,23 @@ fail:
  * cluster which may require a different handling)
  */
 static int count_contiguous_clusters(uint64_t nb_clusters, int cluster_size,
-        uint64_t *l2_table, uint64_t stop_flags)
+        uint64_t *l2_table, uint64_t start, uint64_t stop_flags)
 {
     int i;
-    uint64_t mask = stop_flags | L2E_OFFSET_MASK | QCOW_OFLAG_COMPRESSED;
-    uint64_t first_entry = be64_to_cpu(l2_table[0]);
-    uint64_t offset = first_entry & mask;
+    uint64_t mask = stop_flags | L2E_OFFSET_MASK;
+    uint64_t offset = be64_to_cpu(l2_table[0]) & mask;
 
     if (!offset)
         return 0;
 
-    assert(qcow2_get_cluster_type(first_entry) != QCOW2_CLUSTER_COMPRESSED);
-
-    for (i = 0; i < nb_clusters; i++) {
+    for (i = start; i < start + nb_clusters; i++) {
         uint64_t l2_entry = be64_to_cpu(l2_table[i]) & mask;
         if (offset + (uint64_t) i * cluster_size != l2_entry) {
             break;
         }
     }
 
-	return i;
+	return (i - start);
 }
 
 static int count_contiguous_free_clusters(uint64_t nb_clusters, uint64_t *l2_table)
@@ -366,6 +332,15 @@ static int coroutine_fn copy_sectors(BlockDriverState *bs,
     struct iovec iov;
     int n, ret;
 
+    /*
+     * If this is the last cluster and it is only partially used, we must only
+     * copy until the end of the image, or bdrv_check_request will fail for the
+     * bdrv_read/write calls below.
+     */
+    if (start_sect + n_end > bs->total_sectors) {
+        n_end = bs->total_sectors - start_sect;
+    }
+
     n = n_end - n_start;
     if (n <= 0) {
         return 0;
@@ -378,11 +353,6 @@ 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.
@@ -398,12 +368,6 @@ static int coroutine_fn copy_sectors(BlockDriverState *bs,
                         &s->aes_encrypt_key);
     }
 
-    ret = qcow2_pre_write_overlap_check(bs, 0,
-            cluster_offset + n_start * BDRV_SECTOR_SIZE, n * BDRV_SECTOR_SIZE);
-    if (ret < 0) {
-        goto out;
-    }
-
     BLKDBG_EVENT(bs->file, BLKDBG_COW_WRITE);
     ret = bdrv_co_writev(bs->file, (cluster_offset >> 9) + n_start, n, &qiov);
     if (ret < 0) {
@@ -499,11 +463,11 @@ 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,
-                &l2_table[l2_index], QCOW_OFLAG_ZERO);
+                &l2_table[l2_index], 0,
+                QCOW_OFLAG_COMPRESSED | QCOW_OFLAG_ZERO);
         *cluster_offset = 0;
         break;
     case QCOW2_CLUSTER_UNALLOCATED:
@@ -514,7 +478,8 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
     case QCOW2_CLUSTER_NORMAL:
         /* how many allocated clusters ? */
         c = count_contiguous_clusters(nb_clusters, s->cluster_size,
-                &l2_table[l2_index], QCOW_OFLAG_ZERO);
+                &l2_table[l2_index], 0,
+                QCOW_OFLAG_COMPRESSED | QCOW_OFLAG_ZERO);
         *cluster_offset &= L2E_OFFSET_MASK;
         break;
     default:
@@ -730,7 +695,6 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
     }
     qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
 
-    assert(l2_index + m->nb_clusters <= s->l2_size);
     for (i = 0; i < m->nb_clusters; i++) {
         /* if two concurrent writes happen to the same unallocated cluster
 	 * each write allocates separate cluster and writes data concurrently.
@@ -944,7 +908,7 @@ static int handle_copied(BlockDriverState *bs, uint64_t guest_offset,
         /* We keep all QCOW_OFLAG_COPIED clusters */
         keep_clusters =
             count_contiguous_clusters(nb_clusters, s->cluster_size,
-                                      &l2_table[l2_index],
+                                      &l2_table[l2_index], 0,
                                       QCOW_OFLAG_COPIED | QCOW_OFLAG_ZERO);
         assert(keep_clusters <= nb_clusters);
 
@@ -1186,7 +1150,7 @@ 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;
@@ -1194,13 +1158,15 @@ int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
     uint64_t cur_bytes;
     int ret;
 
-    trace_qcow2_alloc_clusters_offset(qemu_coroutine_self(), offset, *num);
+    trace_qcow2_alloc_clusters_offset(qemu_coroutine_self(), offset,
+                                      n_start, n_end);
 
-    assert((offset & ~BDRV_SECTOR_MASK) == 0);
+    assert(n_start * BDRV_SECTOR_SIZE == offset_into_cluster(s, offset));
+    offset = start_of_cluster(s, offset);
 
 again:
-    start = offset;
-    remaining = *num << BDRV_SECTOR_BITS;
+    start = offset + (n_start << BDRV_SECTOR_BITS);
+    remaining = (n_end - n_start) << BDRV_SECTOR_BITS;
     cluster_offset = 0;
     *host_offset = 0;
     cur_bytes = 0;
@@ -1286,7 +1252,7 @@ again:
         }
     }
 
-    *num -= remaining >> BDRV_SECTOR_BITS;
+    *num = (n_end - n_start) - (remaining >> BDRV_SECTOR_BITS);
     assert(*num > 0);
     assert(*host_offset != 0);
 
@@ -1351,7 +1317,7 @@ int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
  * clusters.
  */
 static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
-    unsigned int nb_clusters, enum qcow2_discard_type type)
+    unsigned int nb_clusters)
 {
     BDRVQcowState *s = bs->opaque;
     uint64_t *l2_table;
@@ -1368,47 +1334,19 @@ 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, QCOW2_DISCARD_REQUEST);
     }
 
     ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
@@ -1420,7 +1358,7 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
 }
 
 int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
-    int nb_sectors, enum qcow2_discard_type type)
+    int nb_sectors)
 {
     BDRVQcowState *s = bs->opaque;
     uint64_t end_offset;
@@ -1431,7 +1369,7 @@ 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;
@@ -1443,7 +1381,7 @@ int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
 
     /* Each L2 table is handled by its own loop iteration */
     while (nb_clusters > 0) {
-        ret = discard_single_l2(bs, offset, nb_clusters, type);
+        ret = discard_single_l2(bs, offset, nb_clusters);
         if (ret < 0) {
             goto fail;
         }
@@ -1538,255 +1476,3 @@ fail:
 
     return ret;
 }
-
-/*
- * Expands all zero clusters in a specific L1 table (or deallocates them, for
- * non-backed non-pre-allocated zero clusters).
- *
- * expanded_clusters is a bitmap where every bit corresponds to one cluster in
- * the image file; a bit gets set if the corresponding cluster has been used for
- * zero expansion (i.e., has been filled with zeroes and is referenced from an
- * L2 table). nb_clusters contains the total cluster count of the image file,
- * i.e., the number of bits in expanded_clusters.
- */
-static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
-                                      int l1_size, uint8_t **expanded_clusters,
-                                      uint64_t *nb_clusters)
-{
-    BDRVQcowState *s = bs->opaque;
-    bool is_active_l1 = (l1_table == s->l1_table);
-    uint64_t *l2_table = NULL;
-    int ret;
-    int i, j;
-
-    if (!is_active_l1) {
-        /* inactive L2 tables require a buffer to be stored in when loading
-         * them from disk */
-        l2_table = qemu_blockalign(bs, s->cluster_size);
-    }
-
-    for (i = 0; i < l1_size; i++) {
-        uint64_t l2_offset = l1_table[i] & L1E_OFFSET_MASK;
-        bool l2_dirty = false;
-
-        if (!l2_offset) {
-            /* unallocated */
-            continue;
-        }
-
-        if (is_active_l1) {
-            /* get active L2 tables from cache */
-            ret = qcow2_cache_get(bs, s->l2_table_cache, l2_offset,
-                    (void **)&l2_table);
-        } else {
-            /* load inactive L2 tables from disk */
-            ret = bdrv_read(bs->file, l2_offset / BDRV_SECTOR_SIZE,
-                    (void *)l2_table, s->cluster_sectors);
-        }
-        if (ret < 0) {
-            goto fail;
-        }
-
-        for (j = 0; j < s->l2_size; j++) {
-            uint64_t l2_entry = be64_to_cpu(l2_table[j]);
-            int64_t offset = l2_entry & L2E_OFFSET_MASK, cluster_index;
-            int cluster_type = qcow2_get_cluster_type(l2_entry);
-            bool preallocated = offset != 0;
-
-            if (cluster_type == QCOW2_CLUSTER_NORMAL) {
-                cluster_index = offset >> s->cluster_bits;
-                assert((cluster_index >= 0) && (cluster_index < *nb_clusters));
-                if ((*expanded_clusters)[cluster_index / 8] &
-                    (1 << (cluster_index % 8))) {
-                    /* Probably a shared L2 table; this cluster was a zero
-                     * cluster which has been expanded, its refcount
-                     * therefore most likely requires an update. */
-                    ret = qcow2_update_cluster_refcount(bs, cluster_index, 1,
-                                                        QCOW2_DISCARD_NEVER);
-                    if (ret < 0) {
-                        goto fail;
-                    }
-                    /* Since we just increased the refcount, the COPIED flag may
-                     * no longer be set. */
-                    l2_table[j] = cpu_to_be64(l2_entry & ~QCOW_OFLAG_COPIED);
-                    l2_dirty = true;
-                }
-                continue;
-            }
-            else if (qcow2_get_cluster_type(l2_entry) != QCOW2_CLUSTER_ZERO) {
-                continue;
-            }
-
-            if (!preallocated) {
-                if (!bs->backing_hd) {
-                    /* not backed; therefore we can simply deallocate the
-                     * cluster */
-                    l2_table[j] = 0;
-                    l2_dirty = true;
-                    continue;
-                }
-
-                offset = qcow2_alloc_clusters(bs, s->cluster_size);
-                if (offset < 0) {
-                    ret = offset;
-                    goto fail;
-                }
-            }
-
-            ret = qcow2_pre_write_overlap_check(bs, 0, offset, s->cluster_size);
-            if (ret < 0) {
-                if (!preallocated) {
-                    qcow2_free_clusters(bs, offset, s->cluster_size,
-                                        QCOW2_DISCARD_ALWAYS);
-                }
-                goto fail;
-            }
-
-            ret = bdrv_write_zeroes(bs->file, offset / BDRV_SECTOR_SIZE,
-                                    s->cluster_sectors, 0);
-            if (ret < 0) {
-                if (!preallocated) {
-                    qcow2_free_clusters(bs, offset, s->cluster_size,
-                                        QCOW2_DISCARD_ALWAYS);
-                }
-                goto fail;
-            }
-
-            l2_table[j] = cpu_to_be64(offset | QCOW_OFLAG_COPIED);
-            l2_dirty = true;
-
-            cluster_index = offset >> s->cluster_bits;
-
-            if (cluster_index >= *nb_clusters) {
-                uint64_t old_bitmap_size = (*nb_clusters + 7) / 8;
-                uint64_t new_bitmap_size;
-                /* The offset may lie beyond the old end of the underlying image
-                 * file for growable files only */
-                assert(bs->file->growable);
-                *nb_clusters = size_to_clusters(s, bs->file->total_sectors *
-                                                BDRV_SECTOR_SIZE);
-                new_bitmap_size = (*nb_clusters + 7) / 8;
-                *expanded_clusters = g_realloc(*expanded_clusters,
-                                               new_bitmap_size);
-                /* clear the newly allocated space */
-                memset(&(*expanded_clusters)[old_bitmap_size], 0,
-                       new_bitmap_size - old_bitmap_size);
-            }
-
-            assert((cluster_index >= 0) && (cluster_index < *nb_clusters));
-            (*expanded_clusters)[cluster_index / 8] |= 1 << (cluster_index % 8);
-        }
-
-        if (is_active_l1) {
-            if (l2_dirty) {
-                qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
-                qcow2_cache_depends_on_flush(s->l2_table_cache);
-            }
-            ret = qcow2_cache_put(bs, s->l2_table_cache, (void **)&l2_table);
-            if (ret < 0) {
-                l2_table = NULL;
-                goto fail;
-            }
-        } else {
-            if (l2_dirty) {
-                ret = qcow2_pre_write_overlap_check(bs,
-                        QCOW2_OL_INACTIVE_L2 | QCOW2_OL_ACTIVE_L2, l2_offset,
-                        s->cluster_size);
-                if (ret < 0) {
-                    goto fail;
-                }
-
-                ret = bdrv_write(bs->file, l2_offset / BDRV_SECTOR_SIZE,
-                        (void *)l2_table, s->cluster_sectors);
-                if (ret < 0) {
-                    goto fail;
-                }
-            }
-        }
-    }
-
-    ret = 0;
-
-fail:
-    if (l2_table) {
-        if (!is_active_l1) {
-            qemu_vfree(l2_table);
-        } else {
-            if (ret < 0) {
-                qcow2_cache_put(bs, s->l2_table_cache, (void **)&l2_table);
-            } else {
-                ret = qcow2_cache_put(bs, s->l2_table_cache,
-                        (void **)&l2_table);
-            }
-        }
-    }
-    return ret;
-}
-
-/*
- * For backed images, expands all zero clusters on the image. For non-backed
- * images, deallocates all non-pre-allocated zero clusters (and claims the
- * allocation for pre-allocated ones). This is important for downgrading to a
- * qcow2 version which doesn't yet support metadata zero clusters.
- */
-int qcow2_expand_zero_clusters(BlockDriverState *bs)
-{
-    BDRVQcowState *s = bs->opaque;
-    uint64_t *l1_table = NULL;
-    uint64_t nb_clusters;
-    uint8_t *expanded_clusters;
-    int ret;
-    int i, j;
-
-    nb_clusters = size_to_clusters(s, bs->file->total_sectors *
-                                   BDRV_SECTOR_SIZE);
-    expanded_clusters = g_malloc0((nb_clusters + 7) / 8);
-
-    ret = expand_zero_clusters_in_l1(bs, s->l1_table, s->l1_size,
-                                     &expanded_clusters, &nb_clusters);
-    if (ret < 0) {
-        goto fail;
-    }
-
-    /* Inactive L1 tables may point to active L2 tables - therefore it is
-     * necessary to flush the L2 table cache before trying to access the L2
-     * tables pointed to by inactive L1 entries (else we might try to expand
-     * zero clusters that have already been expanded); furthermore, it is also
-     * necessary to empty the L2 table cache, since it may contain tables which
-     * are now going to be modified directly on disk, bypassing the cache.
-     * qcow2_cache_empty() does both for us. */
-    ret = qcow2_cache_empty(bs, s->l2_table_cache);
-    if (ret < 0) {
-        goto fail;
-    }
-
-    for (i = 0; i < s->nb_snapshots; i++) {
-        int l1_sectors = (s->snapshots[i].l1_size * sizeof(uint64_t) +
-                BDRV_SECTOR_SIZE - 1) / BDRV_SECTOR_SIZE;
-
-        l1_table = g_realloc(l1_table, l1_sectors * BDRV_SECTOR_SIZE);
-
-        ret = bdrv_read(bs->file, s->snapshots[i].l1_table_offset /
-                BDRV_SECTOR_SIZE, (void *)l1_table, l1_sectors);
-        if (ret < 0) {
-            goto fail;
-        }
-
-        for (j = 0; j < s->snapshots[i].l1_size; j++) {
-            be64_to_cpus(&l1_table[j]);
-        }
-
-        ret = expand_zero_clusters_in_l1(bs, l1_table, s->snapshots[i].l1_size,
-                                         &expanded_clusters, &nb_clusters);
-        if (ret < 0) {
-            goto fail;
-        }
-    }
-
-    ret = 0;
-
-fail:
-    g_free(expanded_clusters);
-    g_free(l1_table);
-    return ret;
-}

block/qcow2-snapshot.c

@@ -26,6 +26,31 @@
 #include "block/block_int.h"
 #include "block/qcow2.h"
 
+typedef struct QEMU_PACKED QCowSnapshotHeader {
+    /* header is 8 byte aligned */
+    uint64_t l1_table_offset;
+
+    uint32_t l1_size;
+    uint16_t id_str_size;
+    uint16_t name_size;
+
+    uint32_t date_sec;
+    uint32_t date_nsec;
+
+    uint64_t vm_clock_nsec;
+
+    uint32_t vm_state_size;
+    uint32_t extra_data_size; /* for extension */
+    /* extra data follows */
+    /* id_str follows */
+    /* name follows  */
+} QCowSnapshotHeader;
+
+typedef struct QEMU_PACKED QCowSnapshotExtraData {
+    uint64_t vm_state_size_large;
+    uint64_t disk_size;
+} QCowSnapshotExtraData;
+
 void qcow2_free_snapshots(BlockDriverState *bs)
 {
     BDRVQcowState *s = bs->opaque;
@@ -116,14 +141,8 @@ 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 +163,7 @@ 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 */
@@ -156,36 +175,20 @@ 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 */
     snapshots_offset = qcow2_alloc_clusters(bs, snapshots_size);
     offset = snapshots_offset;
     if (offset < 0) {
-        ret = offset;
-        goto fail;
+        return offset;
     }
     ret = bdrv_flush(bs);
     if (ret < 0) {
-        goto fail;
+        return ret;
     }
 
-    /* The snapshot list position has not yet been updated, so these clusters
-     * must indeed be completely free */
-    ret = qcow2_pre_write_overlap_check(bs, 0, offset, snapshots_size);
-    if (ret < 0) {
-        goto fail;
-    }
-
-
     /* Write all snapshots to the new list */
     for(i = 0; i < s->nb_snapshots; i++) {
         sn = s->snapshots + i;
@@ -208,7 +211,6 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
 
         id_str_size = strlen(sn->id_str);
         name_size = strlen(sn->name);
-        assert(id_str_size <= UINT16_MAX && name_size <= UINT16_MAX);
         h.id_str_size = cpu_to_be16(id_str_size);
         h.name_size = cpu_to_be16(name_size);
         offset = align_offset(offset, 8);
@@ -267,10 +269,6 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
     return 0;
 
 fail:
-    if (snapshots_offset > 0) {
-        qcow2_free_clusters(bs, snapshots_offset, snapshots_size,
-                            QCOW2_DISCARD_ALWAYS);
-    }
     return ret;
 }
 
@@ -279,8 +277,7 @@ static void find_new_snapshot_id(BlockDriverState *bs,
 {
     BDRVQcowState *s = bs->opaque;
     QCowSnapshot *sn;
-    int i;
-    unsigned long id, id_max = 0;
+    int i, id, id_max = 0;
 
     for(i = 0; i < s->nb_snapshots; i++) {
         sn = s->snapshots + i;
@@ -288,50 +285,34 @@ static void find_new_snapshot_id(BlockDriverState *bs,
         if (id > id_max)
             id_max = id;
     }
-    snprintf(id_str, id_str_size, "%lu", id_max + 1);
+    snprintf(id_str, id_str_size, "%d", id_max + 1);
 }
 
-static int find_snapshot_by_id_and_name(BlockDriverState *bs,
-                                        const char *id,
-                                        const char *name)
+static int find_snapshot_by_id(BlockDriverState *bs, const char *id_str)
 {
     BDRVQcowState *s = bs->opaque;
     int i;
 
-    if (id && name) {
-        for (i = 0; i < s->nb_snapshots; i++) {
-            if (!strcmp(s->snapshots[i].id_str, id) &&
-                !strcmp(s->snapshots[i].name, name)) {
-                return i;
-            }
-        }
-    } else if (id) {
-        for (i = 0; i < s->nb_snapshots; i++) {
-            if (!strcmp(s->snapshots[i].id_str, id)) {
-                return i;
-            }
-        }
-    } else if (name) {
-        for (i = 0; i < s->nb_snapshots; i++) {
-            if (!strcmp(s->snapshots[i].name, name)) {
-                return i;
-            }
-        }
+    for(i = 0; i < s->nb_snapshots; i++) {
+        if (!strcmp(s->snapshots[i].id_str, id_str))
+            return i;
     }
-
     return -1;
 }
 
-static int find_snapshot_by_id_or_name(BlockDriverState *bs,
-                                       const char *id_or_name)
+static int find_snapshot_by_id_or_name(BlockDriverState *bs, const char *name)
 {
-    int ret;
+    BDRVQcowState *s = bs->opaque;
+    int i, ret;
 
-    ret = find_snapshot_by_id_and_name(bs, id_or_name, NULL);
-    if (ret >= 0) {
+    ret = find_snapshot_by_id(bs, name);
+    if (ret >= 0)
         return ret;
+    for(i = 0; i < s->nb_snapshots; i++) {
+        if (!strcmp(s->snapshots[i].name, name))
+            return i;
     }
-    return find_snapshot_by_id_and_name(bs, NULL, id_or_name);
+    return -1;
 }
 
 /* if no id is provided, a new one is constructed */
@@ -345,10 +326,6 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
     uint64_t *l1_table = NULL;
     int64_t l1_table_offset;
 
-    if (s->nb_snapshots >= QCOW_MAX_SNAPSHOTS) {
-        return -EFBIG;
-    }
-
     memset(sn, 0, sizeof(*sn));
 
     /* Generate an ID if it wasn't passed */
@@ -357,7 +334,7 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
     }
 
     /* Check that the ID is unique */
-    if (find_snapshot_by_id_and_name(bs, sn_info->id_str, NULL) >= 0) {
+    if (find_snapshot_by_id(bs, sn_info->id_str) >= 0) {
         return -EEXIST;
     }
 
@@ -386,12 +363,6 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
         l1_table[i] = cpu_to_be64(s->l1_table[i]);
     }
 
-    ret = qcow2_pre_write_overlap_check(bs, 0, sn->l1_table_offset,
-                                        s->l1_size * sizeof(uint64_t));
-    if (ret < 0) {
-        goto fail;
-    }
-
     ret = bdrv_pwrite(bs->file, sn->l1_table_offset, l1_table,
                       s->l1_size * sizeof(uint64_t));
     if (ret < 0) {
@@ -425,19 +396,11 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
     if (ret < 0) {
         g_free(s->snapshots);
         s->snapshots = old_snapshot_list;
-        s->nb_snapshots--;
         goto fail;
     }
 
     g_free(old_snapshot_list);
 
-    /* The VM state isn't needed any more in the active L1 table; in fact, it
-     * hurts by causing expensive COW for the next snapshot. */
-    qcow2_discard_clusters(bs, qcow2_vm_state_offset(s),
-                           align_offset(sn->vm_state_size, s->cluster_size)
-                                >> BDRV_SECTOR_BITS,
-                           QCOW2_DISCARD_NEVER);
-
 #ifdef DEBUG_ALLOC
     {
       BdrvCheckResult result = {0};
@@ -512,12 +475,6 @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
         goto fail;
     }
 
-    ret = qcow2_pre_write_overlap_check(bs, QCOW2_OL_ACTIVE_L1,
-                                        s->l1_table_offset, cur_l1_bytes);
-    if (ret < 0) {
-        goto fail;
-    }
-
     ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset, sn_l1_table,
                            cur_l1_bytes);
     if (ret < 0) {
@@ -574,19 +531,15 @@ fail:
     return ret;
 }
 
-int qcow2_snapshot_delete(BlockDriverState *bs,
-                          const char *snapshot_id,
-                          const char *name,
-                          Error **errp)
+int qcow2_snapshot_delete(BlockDriverState *bs, const char *snapshot_id)
 {
     BDRVQcowState *s = bs->opaque;
     QCowSnapshot sn;
     int snapshot_index, ret;
 
     /* 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_id);
     if (snapshot_index < 0) {
-        error_setg(errp, "Can't find the snapshot");
         return -ENOENT;
     }
     sn = s->snapshots[snapshot_index];
@@ -598,8 +551,6 @@ 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");
         return ret;
     }
 
@@ -617,7 +568,6 @@ 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");
         return ret;
     }
     qcow2_free_clusters(bs, sn.l1_table_offset, sn.l1_size * sizeof(uint64_t),
@@ -626,8 +576,6 @@ 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");
         return ret;
     }
 
@@ -669,10 +617,7 @@ 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;
@@ -684,25 +629,18 @@ 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");
-        return -EFBIG;
-    }
-    new_l1_bytes = sn->l1_size * sizeof(uint64_t);
+    new_l1_bytes = s->l1_size * sizeof(uint64_t);
     new_l1_table = g_malloc0(align_offset(new_l1_bytes, 512));
 
     ret = bdrv_pread(bs->file, sn->l1_table_offset, new_l1_table, new_l1_bytes);
     if (ret < 0) {
-        error_setg(errp, "Failed to read l1 table for snapshot");
         g_free(new_l1_table);
         return ret;
     }

block/qcow2.h

@@ -38,26 +38,13 @@
 #define QCOW_CRYPT_AES  1
 
 #define QCOW_MAX_CRYPT_CLUSTERS 32
-#define QCOW_MAX_SNAPSHOTS 65536
-
-/* 8 MB refcount table is enough for 2 PB images at 64k cluster size
- * (128 GB for 512 byte clusters, 2 EB for 2 MB clusters) */
-#define QCOW_MAX_REFTABLE_SIZE 0x800000
-
-/* 32 MB L1 table is enough for 2 PB images at 64k cluster size
- * (128 GB for 512 byte clusters, 2 EB for 2 MB clusters) */
-#define QCOW_MAX_L1_SIZE 0x2000000
-
-/* Allow for an average of 1k per snapshot table entry, should be plenty of
- * space for snapshot names and IDs */
-#define QCOW_MAX_SNAPSHOTS_SIZE (1024 * QCOW_MAX_SNAPSHOTS)
 
 /* indicate that the refcount of the referenced cluster is exactly one. */
-#define QCOW_OFLAG_COPIED     (1ULL << 63)
+#define QCOW_OFLAG_COPIED     (1LL << 63)
 /* indicate that the cluster is compressed (they never have the copied flag) */
-#define QCOW_OFLAG_COMPRESSED (1ULL << 62)
+#define QCOW_OFLAG_COMPRESSED (1LL << 62)
 /* The cluster reads as all zeros */
-#define QCOW_OFLAG_ZERO (1ULL << 0)
+#define QCOW_OFLAG_ZERO (1LL << 0)
 
 #define REFCOUNT_SHIFT 1 /* refcount size is 2 bytes */
 
@@ -76,15 +63,6 @@
 #define QCOW2_OPT_DISCARD_REQUEST "pass-discard-request"
 #define QCOW2_OPT_DISCARD_SNAPSHOT "pass-discard-snapshot"
 #define QCOW2_OPT_DISCARD_OTHER "pass-discard-other"
-#define QCOW2_OPT_OVERLAP "overlap-check"
-#define QCOW2_OPT_OVERLAP_MAIN_HEADER "overlap-check.main-header"
-#define QCOW2_OPT_OVERLAP_ACTIVE_L1 "overlap-check.active-l1"
-#define QCOW2_OPT_OVERLAP_ACTIVE_L2 "overlap-check.active-l2"
-#define QCOW2_OPT_OVERLAP_REFCOUNT_TABLE "overlap-check.refcount-table"
-#define QCOW2_OPT_OVERLAP_REFCOUNT_BLOCK "overlap-check.refcount-block"
-#define QCOW2_OPT_OVERLAP_SNAPSHOT_TABLE "overlap-check.snapshot-table"
-#define QCOW2_OPT_OVERLAP_INACTIVE_L1 "overlap-check.inactive-l1"
-#define QCOW2_OPT_OVERLAP_INACTIVE_L2 "overlap-check.inactive-l2"
 
 typedef struct QCowHeader {
     uint32_t magic;
@@ -108,33 +86,7 @@ typedef struct QCowHeader {
 
     uint32_t refcount_order;
     uint32_t header_length;
-} QEMU_PACKED QCowHeader;
-
-typedef struct QEMU_PACKED QCowSnapshotHeader {
-    /* header is 8 byte aligned */
-    uint64_t l1_table_offset;
-
-    uint32_t l1_size;
-    uint16_t id_str_size;
-    uint16_t name_size;
-
-    uint32_t date_sec;
-    uint32_t date_nsec;
-
-    uint64_t vm_clock_nsec;
-
-    uint32_t vm_state_size;
-    uint32_t extra_data_size; /* for extension */
-    /* extra data follows */
-    /* id_str follows */
-    /* name follows  */
-} QCowSnapshotHeader;
-
-typedef struct QEMU_PACKED QCowSnapshotExtraData {
-    uint64_t vm_state_size_large;
-    uint64_t disk_size;
-} QCowSnapshotExtraData;
-
+} QCowHeader;
 
 typedef struct QCowSnapshot {
     uint64_t l1_table_offset;
@@ -167,12 +119,9 @@ enum {
 /* Incompatible feature bits */
 enum {
     QCOW2_INCOMPAT_DIRTY_BITNR   = 0,
-    QCOW2_INCOMPAT_CORRUPT_BITNR = 1,
     QCOW2_INCOMPAT_DIRTY         = 1 << QCOW2_INCOMPAT_DIRTY_BITNR,
-    QCOW2_INCOMPAT_CORRUPT       = 1 << QCOW2_INCOMPAT_CORRUPT_BITNR,
 
-    QCOW2_INCOMPAT_MASK          = QCOW2_INCOMPAT_DIRTY
-                                 | QCOW2_INCOMPAT_CORRUPT,
+    QCOW2_INCOMPAT_MASK          = QCOW2_INCOMPAT_DIRTY,
 };
 
 /* Compatible feature bits */
@@ -230,8 +179,8 @@ typedef struct BDRVQcowState {
     uint64_t *refcount_table;
     uint64_t refcount_table_offset;
     uint32_t refcount_table_size;
-    uint64_t free_cluster_index;
-    uint64_t free_byte_offset;
+    int64_t free_cluster_index;
+    int64_t free_byte_offset;
 
     CoMutex lock;
 
@@ -241,18 +190,15 @@ typedef struct BDRVQcowState {
     AES_KEY aes_decrypt_key;
     uint64_t snapshots_offset;
     int snapshots_size;
-    unsigned int nb_snapshots;
+    int nb_snapshots;
     QCowSnapshot *snapshots;
 
     int flags;
     int qcow_version;
     bool use_lazy_refcounts;
-    int refcount_order;
 
     bool discard_passthrough[QCOW2_DISCARD_MAX];
 
-    int overlap_check; /* bitmask of Qcow2MetadataOverlap values */
-
     uint64_t incompatible_features;
     uint64_t compatible_features;
     uint64_t autoclear_features;
@@ -340,50 +286,11 @@ enum {
     QCOW2_CLUSTER_ZERO
 };
 
-typedef enum QCow2MetadataOverlap {
-    QCOW2_OL_MAIN_HEADER_BITNR    = 0,
-    QCOW2_OL_ACTIVE_L1_BITNR      = 1,
-    QCOW2_OL_ACTIVE_L2_BITNR      = 2,
-    QCOW2_OL_REFCOUNT_TABLE_BITNR = 3,
-    QCOW2_OL_REFCOUNT_BLOCK_BITNR = 4,
-    QCOW2_OL_SNAPSHOT_TABLE_BITNR = 5,
-    QCOW2_OL_INACTIVE_L1_BITNR    = 6,
-    QCOW2_OL_INACTIVE_L2_BITNR    = 7,
-
-    QCOW2_OL_MAX_BITNR            = 8,
-
-    QCOW2_OL_NONE           = 0,
-    QCOW2_OL_MAIN_HEADER    = (1 << QCOW2_OL_MAIN_HEADER_BITNR),
-    QCOW2_OL_ACTIVE_L1      = (1 << QCOW2_OL_ACTIVE_L1_BITNR),
-    QCOW2_OL_ACTIVE_L2      = (1 << QCOW2_OL_ACTIVE_L2_BITNR),
-    QCOW2_OL_REFCOUNT_TABLE = (1 << QCOW2_OL_REFCOUNT_TABLE_BITNR),
-    QCOW2_OL_REFCOUNT_BLOCK = (1 << QCOW2_OL_REFCOUNT_BLOCK_BITNR),
-    QCOW2_OL_SNAPSHOT_TABLE = (1 << QCOW2_OL_SNAPSHOT_TABLE_BITNR),
-    QCOW2_OL_INACTIVE_L1    = (1 << QCOW2_OL_INACTIVE_L1_BITNR),
-    /* NOTE: Checking overlaps with inactive L2 tables will result in bdrv
-     * reads. */
-    QCOW2_OL_INACTIVE_L2    = (1 << QCOW2_OL_INACTIVE_L2_BITNR),
-} QCow2MetadataOverlap;
-
-/* Perform all overlap checks which can be done in constant time */
-#define QCOW2_OL_CONSTANT \
-    (QCOW2_OL_MAIN_HEADER | QCOW2_OL_ACTIVE_L1 | QCOW2_OL_REFCOUNT_TABLE | \
-     QCOW2_OL_SNAPSHOT_TABLE)
-
-/* Perform all overlap checks which don't require disk access */
-#define QCOW2_OL_CACHED \
-    (QCOW2_OL_CONSTANT | QCOW2_OL_ACTIVE_L2 | QCOW2_OL_REFCOUNT_BLOCK | \
-     QCOW2_OL_INACTIVE_L1)
-
-/* Perform all overlap checks */
-#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)
 {
@@ -417,16 +324,6 @@ static inline int64_t align_offset(int64_t offset, int n)
     return offset;
 }
 
-static inline int64_t qcow2_vm_state_offset(BDRVQcowState *s)
-{
-    return (int64_t)s->l1_vm_state_index << (s->cluster_bits + s->l2_bits);
-}
-
-static inline uint64_t qcow2_max_refcount_clusters(BDRVQcowState *s)
-{
-    return QCOW_MAX_REFTABLE_SIZE >> s->cluster_bits;
-}
-
 static inline int qcow2_get_cluster_type(uint64_t l2_entry)
 {
     if (l2_entry & QCOW_OFLAG_COMPRESSED) {
@@ -464,18 +361,13 @@ int qcow2_backing_read1(BlockDriverState *bs, QEMUIOVector *qiov,
                   int64_t sector_num, int nb_sectors);
 
 int qcow2_mark_dirty(BlockDriverState *bs);
-int qcow2_mark_corrupt(BlockDriverState *bs);
-int qcow2_mark_consistent(BlockDriverState *bs);
 int qcow2_update_header(BlockDriverState *bs);
 
 /* qcow2-refcount.c functions */
 int qcow2_refcount_init(BlockDriverState *bs);
 void qcow2_refcount_close(BlockDriverState *bs);
 
-int qcow2_update_cluster_refcount(BlockDriverState *bs, int64_t cluster_index,
-                                  int addend, enum qcow2_discard_type type);
-
-int64_t qcow2_alloc_clusters(BlockDriverState *bs, uint64_t size);
+int64_t qcow2_alloc_clusters(BlockDriverState *bs, int64_t size);
 int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
     int nb_clusters);
 int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size);
@@ -493,15 +385,9 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
 
 void qcow2_process_discards(BlockDriverState *bs, int ret);
 
-int qcow2_check_metadata_overlap(BlockDriverState *bs, int ign, int64_t offset,
-                                 int64_t size);
-int qcow2_pre_write_overlap_check(BlockDriverState *bs, int ign, int64_t offset,
-                                  int64_t size);
-
 /* qcow2-cluster.c functions */
 int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
                         bool exact_size);
-int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index);
 void qcow2_l2_cache_reset(BlockDriverState *bs);
 int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset);
 void qcow2_encrypt_sectors(BDRVQcowState *s, int64_t sector_num,
@@ -512,30 +398,22 @@ 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);
 
 int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m);
 int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
-    int nb_sectors, enum qcow2_discard_type type);
+    int nb_sectors);
 int qcow2_zero_clusters(BlockDriverState *bs, uint64_t offset, int nb_sectors);
 
-int qcow2_expand_zero_clusters(BlockDriverState *bs);
-
 /* qcow2-snapshot.c functions */
 int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info);
 int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id);
-int qcow2_snapshot_delete(BlockDriverState *bs,
-                          const char *snapshot_id,
-                          const char *name,
-                          Error **errp);
+int qcow2_snapshot_delete(BlockDriverState *bs, const char *snapshot_id);
 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);
@@ -550,8 +428,6 @@ int qcow2_cache_set_dependency(BlockDriverState *bs, Qcow2Cache *c,
     Qcow2Cache *dependency);
 void qcow2_cache_depends_on_flush(Qcow2Cache *c);
 
-int qcow2_cache_empty(BlockDriverState *bs, Qcow2Cache *c);
-
 int qcow2_cache_get(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset,
     void **table);
 int qcow2_cache_get_empty(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset,

block/qed-table.c

@@ -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;

block/qed.c

@@ -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();
     }
 }
 
@@ -354,10 +353,10 @@ static void qed_start_need_check_timer(BDRVQEDState *s)
 {
     trace_qed_start_need_check_timer(s);
 
-    /* Use QEMU_CLOCK_VIRTUAL so we don't alter the image file while suspended for
+    /* Use vm_clock so we don't alter the image file while suspended for
      * migration.
      */
-    timer_mod(s->need_check_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
+    qemu_mod_timer(s->need_check_timer, qemu_get_clock_ns(vm_clock) +
                    get_ticks_per_sec() * QED_NEED_CHECK_TIMEOUT);
 }
 
@@ -365,7 +364,7 @@ static void qed_start_need_check_timer(BDRVQEDState *s)
 static void qed_cancel_need_check_timer(BDRVQEDState *s)
 {
     trace_qed_cancel_need_check_timer(s);
-    timer_del(s->need_check_timer);
+    qemu_del_timer(s->need_check_timer);
 }
 
 static void bdrv_qed_rebind(BlockDriverState *bs)
@@ -374,29 +373,7 @@ 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)
+static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags)
 {
     BDRVQEDState *s = bs->opaque;
     QEDHeader le_header;
@@ -413,15 +390,14 @@ 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 +494,8 @@ 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 = qemu_new_timer_ns(vm_clock,
+                                            qed_need_check_timer_cb, s);
 
 out:
     if (ret) {
@@ -528,13 +505,6 @@ 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 +517,8 @@ static void bdrv_qed_close(BlockDriverState *bs)
 {
     BDRVQEDState *s = bs->opaque;
 
-    bdrv_qed_detach_aio_context(bs);
+    qed_cancel_need_check_timer(s);
+    qemu_free_timer(s->need_check_timer);
 
     /* Ensure writes reach stable storage */
     bdrv_flush(bs->file);
@@ -564,8 +535,7 @@ 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,
@@ -580,22 +550,16 @@ static int qed_create(const char *filename, uint32_t cluster_size,
     QEDHeader le_header;
     uint8_t *l1_table = NULL;
     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);
     if (ret < 0) {
-        error_propagate(errp, 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);
     if (ret < 0) {
-        error_propagate(errp, local_err);
         return ret;
     }
 
@@ -635,120 +599,103 @@ static int qed_create(const char *filename, uint32_t cluster_size,
     ret = 0; /* success */
 out:
     g_free(l1_table);
-    bdrv_unref(bs);
+    bdrv_delete(bs);
     return ret;
 }
 
-static int bdrv_qed_create(const char *filename, QemuOpts *opts, Error **errp)
+static int bdrv_qed_create(const char *filename, QEMUOptionParameter *options)
 {
     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 {
-    BlockDriverState *bs;
     Coroutine *co;
-    uint64_t pos;
-    int64_t status;
+    int is_allocated;
     int *pnum;
 } QEDIsAllocatedCB;
 
 static void qed_is_allocated_cb(void *opaque, int ret, uint64_t offset, size_t len)
 {
     QEDIsAllocatedCB *cb = opaque;
-    BDRVQEDState *s = cb->bs->opaque;
     *cb->pnum = len / BDRV_SECTOR_SIZE;
-    switch (ret) {
-    case QED_CLUSTER_FOUND:
-        offset |= qed_offset_into_cluster(s, cb->pos);
-        cb->status = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | offset;
-        break;
-    case QED_CLUSTER_ZERO:
-        cb->status = BDRV_BLOCK_ZERO;
-        break;
-    case QED_CLUSTER_L2:
-    case QED_CLUSTER_L1:
-        cb->status = 0;
-        break;
-    default:
-        assert(ret < 0);
-        cb->status = ret;
-        break;
-    }
-
+    cb->is_allocated = (ret == QED_CLUSTER_FOUND || ret == QED_CLUSTER_ZERO);
     if (cb->co) {
         qemu_coroutine_enter(cb->co, NULL);
     }
 }
 
-static int64_t coroutine_fn bdrv_qed_co_get_block_status(BlockDriverState *bs,
+static int coroutine_fn bdrv_qed_co_is_allocated(BlockDriverState *bs,
                                                  int64_t sector_num,
                                                  int nb_sectors, int *pnum)
 {
     BDRVQEDState *s = bs->opaque;
+    uint64_t pos = (uint64_t)sector_num * BDRV_SECTOR_SIZE;
     size_t len = (size_t)nb_sectors * BDRV_SECTOR_SIZE;
     QEDIsAllocatedCB cb = {
-        .bs = bs,
-        .pos = (uint64_t)sector_num * BDRV_SECTOR_SIZE,
-        .status = BDRV_BLOCK_OFFSET_MASK,
+        .is_allocated = -1,
         .pnum = pnum,
     };
     QEDRequest request = { .l2_table = NULL };
 
-    qed_find_cluster(s, &request, cb.pos, len, qed_is_allocated_cb, &cb);
+    qed_find_cluster(s, &request, pos, len, qed_is_allocated_cb, &cb);
 
     /* Now sleep if the callback wasn't invoked immediately */
-    while (cb.status == BDRV_BLOCK_OFFSET_MASK) {
+    while (cb.is_allocated == -1) {
         cb.co = qemu_coroutine_self();
         qemu_coroutine_yield();
     }
 
     qed_unref_l2_cache_entry(request.l2_table);
 
-    return cb.status;
+    return cb.is_allocated;
+}
+
+static int bdrv_qed_make_empty(BlockDriverState *bs)
+{
+    return -ENOTSUP;
 }
 
 static BDRVQEDState *acb_to_s(QEDAIOCB *acb)
@@ -759,19 +706,17 @@ 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 +749,15 @@ 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 +774,6 @@ 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 +811,11 @@ 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 +882,7 @@ 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 +1257,7 @@ 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 +1283,6 @@ 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 +1322,6 @@ 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 +1368,7 @@ 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 +1445,6 @@ 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 +1520,13 @@ 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);
 }
 
 static int bdrv_qed_check(BlockDriverState *bs, BdrvCheckResult *result,
@@ -1634,45 +1537,36 @@ 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,
@@ -1681,19 +1575,17 @@ static BlockDriver bdrv_qed = {
     .bdrv_reopen_prepare      = bdrv_qed_reopen_prepare,
     .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_co_is_allocated     = bdrv_qed_co_is_allocated,
+    .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)

block/qed.h

@@ -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
@@ -99,7 +100,7 @@ typedef struct {
     /* if (features & QED_F_BACKING_FILE) */
     uint32_t backing_filename_offset; /* in bytes from start of header */
     uint32_t backing_filename_size;   /* in bytes */
-} QEMU_PACKED QEDHeader;
+} QEDHeader;
 
 typedef struct {
     uint64_t offsets[0];            /* in bytes */
@@ -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 */

block/quorum.c

@@ -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);

block/raw-aio.h

@@ -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 */

block/raw-win32.c

@@ -36,6 +36,8 @@
 #define FTYPE_CD     1
 #define FTYPE_HARDDISK 2
 
+static QEMUWin32AIOState *aio;
+
 typedef struct RawWin32AIOData {
     BlockDriverState *bs;
     HANDLE hfile;
@@ -83,7 +85,6 @@ static size_t handle_aiocb_rw(RawWin32AIOData *aiocb)
             ret_count = 0;
         }
         if (ret_count != len) {
-            offset += ret_count;
             break;
         }
         offset += len;
@@ -200,54 +201,6 @@ 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 +221,6 @@ 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),
@@ -292,8 +234,7 @@ static QemuOptsList raw_runtime_opts = {
     },
 };
 
-static int raw_open(BlockDriverState *bs, QDict *options, int flags,
-                    Error **errp)
+static int raw_open(BlockDriverState *bs, QDict *options, int flags)
 {
     BDRVRawState *s = bs->opaque;
     int access_flags;
@@ -305,10 +246,11 @@ 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) {
-        error_propagate(errp, local_err);
+    if (error_is_set(&local_err)) {
+        qerror_report_err(local_err);
+        error_free(local_err);
         ret = -EINVAL;
         goto fail;
     }
@@ -317,15 +259,12 @@ 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) {
+            ret = -EINVAL;
+            goto fail;
+        }
     }
 
     s->hfile = CreateFile(filename, access_flags,
@@ -343,26 +282,14 @@ 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 +334,7 @@ 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)
@@ -503,52 +420,45 @@ 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)
 {
     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);
-    if (fd < 0) {
-        error_setg_errno(errp, errno, "Could not create file");
+    if (fd < 0)
         return -EIO;
-    }
     set_sparse(fd);
     ftruncate(fd, total_size * 512);
     qemu_close(fd);
     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 }
 };
 
 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 +470,7 @@ static BlockDriver bdrv_file = {
     .bdrv_get_allocated_file_size
                         = raw_get_allocated_file_size,
 
-    .create_opts        = &raw_create_opts,
+    .create_options = raw_create_options,
 };
 
 /***********************************************/
@@ -621,17 +531,7 @@ 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)
+static int hdev_open(BlockDriverState *bs, QDict *options, int flags)
 {
     BDRVRawState *s = bs->opaque;
     int access_flags, create_flags;
@@ -642,11 +542,11 @@ 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) {
-        error_propagate(errp, local_err);
+    if (error_is_set(&local_err)) {
+        qerror_report_err(local_err);
+        error_free(local_err);
         ret = -EINVAL;
         goto done;
     }
@@ -655,7 +555,6 @@ static int hdev_open(BlockDriverState *bs, QDict *options, int flags,
 
     if (strstart(filename, "/dev/cdrom", NULL)) {
         if (find_cdrom(device_name, sizeof(device_name)) < 0) {
-            error_setg(errp, "Could not open CD-ROM drive");
             ret = -ENOENT;
             goto done;
         }
@@ -684,9 +583,8 @@ static int hdev_open(BlockDriverState *bs, QDict *options, int flags,
         if (err == ERROR_ACCESS_DENIED) {
             ret = -EACCES;
         } else {
-            ret = -EINVAL;
+            ret = -1;
         }
-        error_setg_errno(errp, -ret, "Could not open device");
         goto done;
     }
 
@@ -699,8 +597,6 @@ static BlockDriver bdrv_host_device = {
     .format_name	= "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,
@@ -709,12 +605,7 @@ 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,
-
+    .bdrv_getlength	= raw_getlength,
     .bdrv_get_allocated_file_size
                         = raw_get_allocated_file_size,
 };

block/raw.c

@@ -0,0 +1,192 @@
+/*
+ * Block driver for RAW format
+ *
+ * Copyright (c) 2006 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "qemu-common.h"
+#include "block/block_int.h"
+#include "qemu/module.h"
+
+static int raw_open(BlockDriverState *bs, QDict *options, int flags)
+{
+    bs->sg = bs->file->sg;
+    return 0;
+}
+
+/* We have nothing to do for raw reopen, stubs just return
+ * success */
+static int raw_reopen_prepare(BDRVReopenState *state,
+                              BlockReopenQueue *queue,  Error **errp)
+{
+    return 0;
+}
+
+static int coroutine_fn raw_co_readv(BlockDriverState *bs, int64_t sector_num,
+                                     int nb_sectors, QEMUIOVector *qiov)
+{
+    BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
+    return bdrv_co_readv(bs->file, sector_num, nb_sectors, qiov);
+}
+
+static int coroutine_fn raw_co_writev(BlockDriverState *bs, int64_t sector_num,
+                                      int nb_sectors, QEMUIOVector *qiov)
+{
+    BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
+    return bdrv_co_writev(bs->file, sector_num, nb_sectors, qiov);
+}
+
+static void raw_close(BlockDriverState *bs)
+{
+}
+
+static int coroutine_fn raw_co_is_allocated(BlockDriverState *bs,
+                                            int64_t sector_num,
+                                            int nb_sectors, int *pnum)
+{
+    return bdrv_co_is_allocated(bs->file, sector_num, nb_sectors, pnum);
+}
+
+static int coroutine_fn raw_co_write_zeroes(BlockDriverState *bs,
+                                            int64_t sector_num,
+                                            int nb_sectors)
+{
+    return bdrv_co_write_zeroes(bs->file, sector_num, nb_sectors);
+}
+
+static int64_t raw_getlength(BlockDriverState *bs)
+{
+    return bdrv_getlength(bs->file);
+}
+
+static int raw_truncate(BlockDriverState *bs, int64_t offset)
+{
+    return bdrv_truncate(bs->file, offset);
+}
+
+static int raw_probe(const uint8_t *buf, int buf_size, const char *filename)
+{
+   return 1; /* everything can be opened as raw image */
+}
+
+static int coroutine_fn raw_co_discard(BlockDriverState *bs,
+                                       int64_t sector_num, int nb_sectors)
+{
+    return bdrv_co_discard(bs->file, sector_num, nb_sectors);
+}
+
+static int raw_is_inserted(BlockDriverState *bs)
+{
+    return bdrv_is_inserted(bs->file);
+}
+
+static int raw_media_changed(BlockDriverState *bs)
+{
+    return bdrv_media_changed(bs->file);
+}
+
+static void raw_eject(BlockDriverState *bs, bool eject_flag)
+{
+    bdrv_eject(bs->file, eject_flag);
+}
+
+static void raw_lock_medium(BlockDriverState *bs, bool locked)
+{
+    bdrv_lock_medium(bs->file, locked);
+}
+
+static int raw_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
+{
+   return bdrv_ioctl(bs->file, req, buf);
+}
+
+static BlockDriverAIOCB *raw_aio_ioctl(BlockDriverState *bs,
+        unsigned long int req, void *buf,
+        BlockDriverCompletionFunc *cb, void *opaque)
+{
+   return bdrv_aio_ioctl(bs->file, req, buf, cb, opaque);
+}
+
+static int raw_create(const char *filename, QEMUOptionParameter *options)
+{
+    return bdrv_create_file(filename, options);
+}
+
+static QEMUOptionParameter raw_create_options[] = {
+    {
+        .name = BLOCK_OPT_SIZE,
+        .type = OPT_SIZE,
+        .help = "Virtual disk size"
+    },
+    { NULL }
+};
+
+static int raw_has_zero_init(BlockDriverState *bs)
+{
+    return bdrv_has_zero_init(bs->file);
+}
+
+static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
+{
+    return bdrv_get_info(bs->file, bdi);
+}
+
+static BlockDriver bdrv_raw = {
+    .format_name        = "raw",
+
+    /* It's really 0, but we need to make g_malloc() happy */
+    .instance_size      = 1,
+
+    .bdrv_open          = raw_open,
+    .bdrv_close         = raw_close,
+
+    .bdrv_reopen_prepare  = raw_reopen_prepare,
+
+    .bdrv_co_readv          = raw_co_readv,
+    .bdrv_co_writev         = raw_co_writev,
+    .bdrv_co_is_allocated   = raw_co_is_allocated,
+    .bdrv_co_write_zeroes   = raw_co_write_zeroes,
+    .bdrv_co_discard        = raw_co_discard,
+
+    .bdrv_probe         = raw_probe,
+    .bdrv_getlength     = raw_getlength,
+    .bdrv_get_info      = raw_get_info,
+    .bdrv_truncate      = raw_truncate,
+
+    .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,
+
+    .bdrv_create        = raw_create,
+    .create_options     = raw_create_options,
+    .bdrv_has_zero_init = raw_has_zero_init,
+};
+
+static void bdrv_raw_init(void)
+{
+    bdrv_register(&bdrv_raw);
+}
+
+block_init(bdrv_raw_init);

block/raw_bsd.c

@@ -1,208 +0,0 @@
-/* BlockDriver implementation for "raw"
- *
- * Copyright (C) 2010, 2013, Red Hat, Inc.
- * Copyright (C) 2010, Blue Swirl <blauwirbel@gmail.com>
- * Copyright (C) 2009, Anthony Liguori <aliguori@us.ibm.com>
- *
- * Author:
- *   Laszlo Ersek <lersek@redhat.com>
- *
- * 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 "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 int raw_reopen_prepare(BDRVReopenState *reopen_state,
-                              BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
-}
-
-static int coroutine_fn raw_co_readv(BlockDriverState *bs, int64_t sector_num,
-                                     int nb_sectors, QEMUIOVector *qiov)
-{
-    BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
-    return bdrv_co_readv(bs->file, sector_num, nb_sectors, qiov);
-}
-
-static int coroutine_fn raw_co_writev(BlockDriverState *bs, int64_t sector_num,
-                                      int nb_sectors, QEMUIOVector *qiov)
-{
-    BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
-    return bdrv_co_writev(bs->file, sector_num, nb_sectors, qiov);
-}
-
-static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs,
-                                            int64_t sector_num,
-                                            int nb_sectors, int *pnum)
-{
-    *pnum = nb_sectors;
-    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID | BDRV_BLOCK_DATA |
-           (sector_num << BDRV_SECTOR_BITS);
-}
-
-static int coroutine_fn raw_co_write_zeroes(BlockDriverState *bs,
-                                            int64_t sector_num, int nb_sectors,
-                                            BdrvRequestFlags flags)
-{
-    return bdrv_co_write_zeroes(bs->file, sector_num, nb_sectors, flags);
-}
-
-static int coroutine_fn raw_co_discard(BlockDriverState *bs,
-                                       int64_t sector_num, int nb_sectors)
-{
-    return bdrv_co_discard(bs->file, sector_num, nb_sectors);
-}
-
-static int64_t raw_getlength(BlockDriverState *bs)
-{
-    return bdrv_getlength(bs->file);
-}
-
-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);
-}
-
-static int raw_is_inserted(BlockDriverState *bs)
-{
-    return bdrv_is_inserted(bs->file);
-}
-
-static int raw_media_changed(BlockDriverState *bs)
-{
-    return bdrv_media_changed(bs->file);
-}
-
-static void raw_eject(BlockDriverState *bs, bool eject_flag)
-{
-    bdrv_eject(bs->file, eject_flag);
-}
-
-static void raw_lock_medium(BlockDriverState *bs, bool locked)
-{
-    bdrv_lock_medium(bs->file, locked);
-}
-
-static int raw_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
-{
-    return bdrv_ioctl(bs->file, req, buf);
-}
-
-static BlockDriverAIOCB *raw_aio_ioctl(BlockDriverState *bs,
-                                       unsigned long int req, void *buf,
-                                       BlockDriverCompletionFunc *cb,
-                                       void *opaque)
-{
-    return bdrv_aio_ioctl(bs->file, req, buf, cb, opaque);
-}
-
-static int raw_has_zero_init(BlockDriverState *bs)
-{
-    return bdrv_has_zero_init(bs->file);
-}
-
-static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
-{
-    Error *local_err = NULL;
-    int ret;
-
-    ret = bdrv_create_file(filename, opts, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-    }
-    return ret;
-}
-
-static int raw_open(BlockDriverState *bs, QDict *options, int flags,
-                    Error **errp)
-{
-    bs->sg = bs->file->sg;
-    return 0;
-}
-
-static void raw_close(BlockDriverState *bs)
-{
-}
-
-static int raw_probe(const uint8_t *buf, int buf_size, const char *filename)
-{
-    /* smallest possible positive score so that raw is used if and only if no
-     * other block driver works
-     */
-    return 1;
-}
-
-static BlockDriver bdrv_raw = {
-    .format_name          = "raw",
-    .bdrv_probe           = &raw_probe,
-    .bdrv_reopen_prepare  = &raw_reopen_prepare,
-    .bdrv_open            = &raw_open,
-    .bdrv_close           = &raw_close,
-    .bdrv_create          = &raw_create,
-    .bdrv_co_readv        = &raw_co_readv,
-    .bdrv_co_writev       = &raw_co_writev,
-    .bdrv_co_write_zeroes = &raw_co_write_zeroes,
-    .bdrv_co_discard      = &raw_co_discard,
-    .bdrv_co_get_block_status = &raw_co_get_block_status,
-    .bdrv_truncate        = &raw_truncate,
-    .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,
-    .bdrv_has_zero_init   = &raw_has_zero_init
-};
-
-static void bdrv_raw_init(void)
-{
-    bdrv_register(&bdrv_raw);
-}
-
-block_init(bdrv_raw_init);

block/rbd.c

@@ -95,17 +95,23 @@ 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];
+    int qemu_aio_count;
     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 +134,10 @@ 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 +163,13 @@ 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 +178,7 @@ 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 +186,21 @@ 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 +235,7 @@ static char *qemu_rbd_parse_clientname(const char *conf, char *clientname)
     return NULL;
 }
 
-static int qemu_rbd_set_conf(rados_t cluster, const char *conf, 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 +247,20 @@ 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 +269,7 @@ 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 +277,7 @@ 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 +288,8 @@ 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 *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 +401,44 @@ 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);
+                s->qemu_aio_count--;
+            }
+        }
+    } while (ret < 0 && errno == EINTR);
+}
+
+static int qemu_rbd_aio_flush_cb(void *opaque)
+{
+    BDRVRBDState *s = opaque;
+
+    return (s->qemu_aio_count > 0);
 }
 
 /* TODO Convert to fine grained options */
@@ -426,8 +455,7 @@ static QemuOptsList runtime_opts = {
     },
 };
 
-static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
-                         Error **errp)
+static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags)
 {
     BDRVRBDState *s = bs->opaque;
     char pool[RBD_MAX_POOL_NAME_SIZE];
@@ -440,10 +468,11 @@ 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 +482,7 @@ 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 +490,7 @@ 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 +518,50 @@ 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, qemu_rbd_aio_flush_cb, s);
+
+
     qemu_opts_del(opts);
     return 0;
 
+failed:
+    rbd_close(s->image);
 failed_open:
     rados_ioctx_destroy(s->io_ctx);
 failed_shutdown:
@@ -532,6 +576,10 @@ 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, NULL);
+
     rbd_close(s->image);
     rados_ioctx_destroy(s->io_ctx);
     g_free(s->snap);
@@ -548,7 +596,7 @@ 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 +607,34 @@ 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 +642,40 @@ 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,
@@ -649,6 +741,8 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
     off = sector_num * BDRV_SECTOR_SIZE;
     size = nb_sectors * BDRV_SECTOR_SIZE;
 
+    s->qemu_aio_count++; /* All the RADOSCB */
+
     rcb = g_malloc(sizeof(RADOSCB));
     rcb->done = 0;
     rcb->acb = acb;
@@ -678,16 +772,14 @@ 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);
+    s->qemu_aio_count--;
     qemu_aio_release(acb);
     return NULL;
 }
@@ -811,31 +903,12 @@ static int qemu_rbd_snap_create(BlockDriverState *bs,
 }
 
 static int qemu_rbd_snap_remove(BlockDriverState *bs,
-                                const char *snapshot_id,
-                                const char *snapshot_name,
-                                Error **errp)
+                                const char *snapshot_name)
 {
     BDRVRBDState *s = bs->opaque;
     int r;
 
-    if (!snapshot_name) {
-        error_setg(errp, "rbd need a valid snapshot name");
-        return -EINVAL;
-    }
-
-    /* If snapshot_id is specified, it must be equal to name, see
-       qemu_rbd_snap_list() */
-    if (snapshot_id && strcmp(snapshot_id, snapshot_name)) {
-        error_setg(errp,
-                   "rbd do not support snapshot id, it should be NULL or "
-                   "equal to snapshot name");
-        return -EINVAL;
-    }
-
     r = rbd_snap_remove(s->image, snapshot_name);
-    if (r < 0) {
-        error_setg_errno(errp, -r, "Failed to remove the snapshot");
-    }
     return r;
 }
 
@@ -904,34 +977,29 @@ 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 = {
     .format_name        = "rbd",
     .instance_size      = sizeof(BDRVRBDState),
-    .bdrv_needs_filename = true,
     .bdrv_file_open     = qemu_rbd_open,
     .bdrv_close         = qemu_rbd_close,
     .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",

block/snapshot.c

@@ -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)
 {
@@ -66,79 +48,6 @@ int bdrv_snapshot_find(BlockDriverState *bs, QEMUSnapshotInfo *sn_info,
     return ret;
 }
 
-/**
- * Look up an internal snapshot by @id and @name.
- * @bs: block device to search
- * @id: unique snapshot ID, or NULL
- * @name: snapshot name, or NULL
- * @sn_info: location to store information on the snapshot found
- * @errp: location to store error, will be set only for exception
- *
- * This function will traverse snapshot list in @bs to search the matching
- * one, @id and @name are the matching condition:
- * If both @id and @name are specified, find the first one with id @id and
- * name @name.
- * If only @id is specified, find the first one with id @id.
- * If only @name is specified, find the first one with name @name.
- * if none is specified, abort().
- *
- * Returns: true when a snapshot is found and @sn_info will be filled, false
- * when error or not found. If all operation succeed but no matching one is
- * found, @errp will NOT be set.
- */
-bool bdrv_snapshot_find_by_id_and_name(BlockDriverState *bs,
-                                       const char *id,
-                                       const char *name,
-                                       QEMUSnapshotInfo *sn_info,
-                                       Error **errp)
-{
-    QEMUSnapshotInfo *sn_tab, *sn;
-    int nb_sns, i;
-    bool ret = false;
-
-    assert(id || name);
-
-    nb_sns = bdrv_snapshot_list(bs, &sn_tab);
-    if (nb_sns < 0) {
-        error_setg_errno(errp, -nb_sns, "Failed to get a snapshot list");
-        return false;
-    } else if (nb_sns == 0) {
-        return false;
-    }
-
-    if (id && name) {
-        for (i = 0; i < nb_sns; i++) {
-            sn = &sn_tab[i];
-            if (!strcmp(sn->id_str, id) && !strcmp(sn->name, name)) {
-                *sn_info = *sn;
-                ret = true;
-                break;
-            }
-        }
-    } else if (id) {
-        for (i = 0; i < nb_sns; i++) {
-            sn = &sn_tab[i];
-            if (!strcmp(sn->id_str, id)) {
-                *sn_info = *sn;
-                ret = true;
-                break;
-            }
-        }
-    } else if (name) {
-        for (i = 0; i < nb_sns; i++) {
-            sn = &sn_tab[i];
-            if (!strcmp(sn->name, name)) {
-                *sn_info = *sn;
-                ret = true;
-                break;
-            }
-        }
-    }
-
-    g_free(sn_tab);
-    return ret;
-}
-
 int bdrv_can_snapshot(BlockDriverState *bs)
 {
     BlockDriver *drv = bs->drv;
@@ -188,9 +97,9 @@ int bdrv_snapshot_goto(BlockDriverState *bs,
     if (bs->file) {
         drv->bdrv_close(bs);
         ret = bdrv_snapshot_goto(bs->file, snapshot_id);
-        open_ret = drv->bdrv_open(bs, NULL, bs->open_flags, NULL);
+        open_ret = drv->bdrv_open(bs, NULL, bs->open_flags);
         if (open_ret < 0) {
-            bdrv_unref(bs->file);
+            bdrv_delete(bs->file);
             bs->drv = NULL;
             return open_ret;
         }
@@ -200,73 +109,21 @@ int bdrv_snapshot_goto(BlockDriverState *bs,
     return -ENOTSUP;
 }
 
-/**
- * Delete 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, delete the first one with
- * id @snapshot_id and name @name.
- * 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.
- *
- * 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
- * does not support internal snapshot deletion, return -ENOTSUP. If @bs does
- * not support parameter @snapshot_id or @name, or one of them is not correctly
- * specified, return -EINVAL. If @bs can't find one matching @id and @name,
- * return -ENOENT. If @errp != NULL, it will always be filled with error
- * message on failure.
- */
-int bdrv_snapshot_delete(BlockDriverState *bs,
-                         const char *snapshot_id,
-                         const char *name,
-                         Error **errp)
+int bdrv_snapshot_delete(BlockDriverState *bs, const char *snapshot_id)
 {
     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 (drv->bdrv_snapshot_delete) {
-        return drv->bdrv_snapshot_delete(bs, snapshot_id, name, errp);
+        return drv->bdrv_snapshot_delete(bs, snapshot_id);
     }
     if (bs->file) {
-        return bdrv_snapshot_delete(bs->file, snapshot_id, name, errp);
+        return bdrv_snapshot_delete(bs->file, snapshot_id);
     }
-    error_set(errp, QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
-              drv->format_name, bdrv_get_device_name(bs),
-              "internal snapshot deletion");
     return -ENOTSUP;
 }
 
-void bdrv_snapshot_delete_by_id_or_name(BlockDriverState *bs,
-                                        const char *id_or_name,
-                                        Error **errp)
-{
-    int ret;
-    Error *local_err = NULL;
-
-    ret = bdrv_snapshot_delete(bs, id_or_name, NULL, &local_err);
-    if (ret == -ENOENT || ret == -EINVAL) {
-        error_free(local_err);
-        local_err = NULL;
-        ret = bdrv_snapshot_delete(bs, NULL, id_or_name, &local_err);
-    }
-
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-    }
-}
-
 int bdrv_snapshot_list(BlockDriverState *bs,
                        QEMUSnapshotInfo **psn_info)
 {
@@ -283,71 +140,18 @@ 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;
-}

block/ssh.c

@@ -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;
     }
 
@@ -641,8 +608,7 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
     return ret;
 }
 
-static int ssh_file_open(BlockDriverState *bs, QDict *options, int bdrv_flags,
-                         Error **errp)
+static int ssh_file_open(BlockDriverState *bs, QDict *options, int bdrv_flags)
 {
     BDRVSSHState *s = bs->opaque;
     int ret;
@@ -656,7 +622,7 @@ 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 +641,19 @@ 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)
 {
     int r, ret;
+    Error *local_err = NULL;
     int64_t total_size = 0;
     QDict *uri_options = NULL;
     BDRVSSHState s;
@@ -700,20 +663,26 @@ 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 +692,7 @@ 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 +740,15 @@ static void restart_coroutine(void *opaque)
     qemu_coroutine_enter(co, NULL);
 }
 
-static coroutine_fn void set_fd_handler(BDRVSSHState *s, BlockDriverState *bs)
+/* Always true because when we have called set_fd_handler there is
+ * always a request being processed.
+ */
+static int return_true(void *opaque)
+{
+    return 1;
+}
+
+static coroutine_fn void set_fd_handler(BDRVSSHState *s)
 {
     int r;
     IOHandler *rd_handler = NULL, *wr_handler = NULL;
@@ -789,26 +766,24 @@ 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, return_true, 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, 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 +813,7 @@ 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 +846,7 @@ 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 +881,14 @@ 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 +916,7 @@ 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 +935,7 @@ 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 +963,7 @@ 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 +984,7 @@ 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 +992,7 @@ 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 +1014,7 @@ 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 +1057,7 @@ 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)

block/stream.c

@@ -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,
@@ -57,11 +57,6 @@ static void close_unused_images(BlockDriverState *top, BlockDriverState *base,
     BlockDriverState *intermediate;
     intermediate = top->backing_hd;
 
-    /* Must assign before bdrv_delete() to prevent traversing dangling pointer
-     * while we delete backing image instances.
-     */
-    bdrv_set_backing_hd(top, base);
-
     while (intermediate) {
         BlockDriverState *unused;
 
@@ -72,11 +67,10 @@ static void close_unused_images(BlockDriverState *top, BlockDriverState *base,
 
         unused = intermediate;
         intermediate = intermediate->backing_hd;
-        bdrv_set_backing_hd(unused, NULL);
-        bdrv_unref(unused);
+        unused->backing_hd = NULL;
+        bdrv_delete(unused);
     }
-
-    bdrv_refresh_limits(top, NULL);
+    top->backing_hd = base;
 }
 
 static void coroutine_fn stream_run(void *opaque)
@@ -90,11 +84,6 @@ 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);
@@ -121,22 +110,21 @@ wait:
         /* Note that even when no rate limit is applied we need to yield
          * with no pending I/O here so that bdrv_drain_all() returns.
          */
-        block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, delay_ns);
+        block_job_sleep_ns(&s->common, rt_clock, delay_ns);
         if (block_job_is_cancelled(&s->common)) {
             break;
         }
 
-        copy = false;
-
-        ret = bdrv_is_allocated(bs, sector_num,
-                                STREAM_BUFFER_SIZE / BDRV_SECTOR_SIZE, &n);
+        ret = bdrv_co_is_allocated(bs, sector_num,
+                                   STREAM_BUFFER_SIZE / BDRV_SECTOR_SIZE, &n);
         if (ret == 1) {
             /* Allocated in the top, no need to copy.  */
+            copy = false;
         } else if (ret >= 0) {
             /* Copy if allocated in the intermediate images.  Limit to the
              * known-unallocated area [sector_num, sector_num+n).  */
-            ret = bdrv_is_allocated_above(bs->backing_hd, base,
-                                          sector_num, n, &n);
+            ret = bdrv_co_is_allocated_above(bs->backing_hd, base,
+                                             sector_num, n, &n);
 
             /* Finish early if end of backing file has been reached */
             if (ret == 0 && n == 0) {
@@ -146,7 +134,7 @@ wait:
             copy = (ret == 1);
         }
         trace_stream_one_iteration(s, sector_num, n, ret);
-        if (copy) {
+        if (ret >= 0 && copy) {
             if (s->common.speed) {
                 delay_ns = ratelimit_calculate_delay(&s->limit, n);
                 if (delay_ns > 0) {
@@ -159,14 +147,14 @@ 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 +174,7 @@ 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 +184,6 @@ wait:
     }
 
     qemu_vfree(buf);
-    g_free(s->backing_file_str);
     block_job_completed(&s->common, ret);
 }
 
@@ -211,14 +198,14 @@ static void stream_set_speed(BlockJob *job, int64_t speed, Error **errp)
     ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
 }
 
-static const BlockJobDriver stream_job_driver = {
+static const BlockJobType stream_job_type = {
     .instance_size = sizeof(StreamBlockJob),
-    .job_type      = BLOCK_JOB_TYPE_STREAM,
+    .job_type      = "stream",
     .set_speed     = stream_set_speed,
 };
 
 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)
@@ -232,13 +219,15 @@ void stream_start(BlockDriverState *bs, BlockDriverState *base,
         return;
     }
 
-    s = block_job_create(&stream_job_driver, bs, speed, cb, opaque, errp);
+    s = block_job_create(&stream_job_type, bs, speed, cb, opaque, errp);
     if (!s) {
         return;
     }
 
     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);

block/vdi.c

@@ -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>
@@ -127,11 +120,6 @@ typedef unsigned char uuid_t[16];
 
 #define VDI_IS_ALLOCATED(X) ((X) < VDI_DISCARDED)
 
-/* max blocks in image is (0xffffffff / 4) */
-#define VDI_BLOCKS_IN_IMAGE_MAX  0x3fffffff
-#define VDI_DISK_SIZE_MAX        ((uint64_t)VDI_BLOCKS_IN_IMAGE_MAX * \
-                                  (uint64_t)DEFAULT_CLUSTER_SIZE)
-
 #if !defined(CONFIG_UUID)
 static inline void uuid_generate(uuid_t out)
 {
@@ -177,7 +165,7 @@ typedef struct {
     uuid_t uuid_link;
     uuid_t uuid_parent;
     uint64_t unused2[7];
-} QEMU_PACKED VdiHeader;
+} VdiHeader;
 
 typedef struct {
     /* The block map entries are little endian (even in memory). */
@@ -246,6 +234,7 @@ 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 +331,6 @@ 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;
 }
 
@@ -376,8 +364,7 @@ static int vdi_probe(const uint8_t *buf, int buf_size, const char *filename)
     return result;
 }
 
-static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
-                    Error **errp)
+static int vdi_open(BlockDriverState *bs, QDict *options, int flags)
 {
     BDRVVdiState *s = bs->opaque;
     VdiHeader header;
@@ -396,14 +383,6 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
     vdi_header_print(&header);
 #endif
 
-    if (header.disk_size > VDI_DISK_SIZE_MAX) {
-        error_setg(errp, "Unsupported VDI image size (size is 0x%" PRIx64
-                          ", max supported is 0x%" PRIx64 ")",
-                          header.disk_size, VDI_DISK_SIZE_MAX);
-        ret = -ENOTSUP;
-        goto fail;
-    }
-
     if (header.disk_size % SECTOR_SIZE != 0) {
         /* 'VBoxManage convertfromraw' can create images with odd disk sizes.
            We accept them but round the disk size to the next multiple of
@@ -414,57 +393,43 @@ 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);
+    } else if (header.block_size != 1 * MiB) {
+        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)");
-        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("parent uuid != 0, unsupported\n");
         ret = -ENOTSUP;
         goto fail;
     }
@@ -505,7 +470,7 @@ static int vdi_reopen_prepare(BDRVReopenState *state,
     return 0;
 }
 
-static int64_t coroutine_fn vdi_co_get_block_status(BlockDriverState *bs,
+static int coroutine_fn vdi_co_is_allocated(BlockDriverState *bs,
         int64_t sector_num, int nb_sectors, int *pnum)
 {
     /* TODO: Check for too large sector_num (in bdrv_is_allocated or here). */
@@ -514,23 +479,12 @@ static int64_t coroutine_fn vdi_co_get_block_status(BlockDriverState *bs,
     size_t sector_in_block = sector_num % s->block_sectors;
     int n_sectors = s->block_sectors - sector_in_block;
     uint32_t bmap_entry = le32_to_cpu(s->bmap[bmap_index]);
-    uint64_t offset;
-    int result;
-
     logout("%p, %" PRId64 ", %d, %p\n", bs, sector_num, nb_sectors, pnum);
     if (n_sectors > nb_sectors) {
         n_sectors = nb_sectors;
     }
     *pnum = n_sectors;
-    result = VDI_IS_ALLOCATED(bmap_entry);
-    if (!result) {
-        return 0;
-    }
-
-    offset = s->header.offset_data +
-                              (uint64_t)bmap_entry * s->block_size +
-                              sector_in_block * SECTOR_SIZE;
-    return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | offset;
+    return VDI_IS_ALLOCATED(bmap_entry);
 }
 
 static int vdi_co_read(BlockDriverState *bs,
@@ -679,7 +633,7 @@ 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)
 {
     int fd;
     int result = 0;
@@ -690,54 +644,35 @@ 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);
-
-    if (bytes > VDI_DISK_SIZE_MAX) {
-        result = -ENOTSUP;
-        error_setg(errp, "Unsupported VDI image size (size is 0x%" PRIx64
-                          ", max supported is 0x%" PRIx64 ")",
-                          bytes, VDI_DISK_SIZE_MAX);
-        goto exit;
+        }
+        options++;
     }
 
     fd = qemu_open(filename,
                    O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
                    0644);
     if (fd < 0) {
-        result = -errno;
-        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
+        return -errno;
     }
 
     /* We need enough blocks to store the given disk size,
@@ -771,7 +706,6 @@ 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 +719,6 @@ 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);
     }
@@ -794,16 +726,13 @@ 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;
     }
 
-exit:
     return result;
 }
 
@@ -817,39 +746,29 @@ 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 = {
@@ -861,7 +780,7 @@ static BlockDriver bdrv_vdi = {
     .bdrv_reopen_prepare = vdi_reopen_prepare,
     .bdrv_create = vdi_create,
     .bdrv_has_zero_init = bdrv_has_zero_init_1,
-    .bdrv_co_get_block_status = vdi_co_get_block_status,
+    .bdrv_co_is_allocated = vdi_co_is_allocated,
     .bdrv_make_empty = vdi_make_empty,
 
     .bdrv_read = vdi_co_read,
@@ -871,7 +790,7 @@ static BlockDriver bdrv_vdi = {
 
     .bdrv_get_info = vdi_get_info,
 
-    .create_opts = &vdi_create_opts,
+    .create_options = vdi_create_options,
     .bdrv_check = vdi_check,
 };
 

block/vhdx-endian.c

@@ -1,216 +0,0 @@
-/*
- * Block driver for Hyper-V VHDX Images
- *
- * Copyright (c) 2013 Red Hat, Inc.,
- *
- * Authors:
- *  Jeff Cody <jcody@redhat.com>
- *
- *  This is based on the "VHDX Format Specification v1.00", published 8/25/2012
- *  by Microsoft:
- *      https://www.microsoft.com/en-us/download/details.aspx?id=34750
- *
- * This work is licensed under the terms of the GNU LGPL, version 2 or later.
- * See the COPYING.LIB file in the top-level directory.
- *
- */
-
-#include "qemu-common.h"
-#include "block/block_int.h"
-#include "block/vhdx.h"
-
-#include <uuid/uuid.h>
-
-
-/*
- * All the VHDX formats on disk are little endian - the following
- * are helper import/export functions to correctly convert
- * endianness from disk read to native cpu format, and back again.
- */
-
-
-/* VHDX File Header */
-
-
-void vhdx_header_le_import(VHDXHeader *h)
-{
-    assert(h != NULL);
-
-    le32_to_cpus(&h->signature);
-    le32_to_cpus(&h->checksum);
-    le64_to_cpus(&h->sequence_number);
-
-    leguid_to_cpus(&h->file_write_guid);
-    leguid_to_cpus(&h->data_write_guid);
-    leguid_to_cpus(&h->log_guid);
-
-    le16_to_cpus(&h->log_version);
-    le16_to_cpus(&h->version);
-    le32_to_cpus(&h->log_length);
-    le64_to_cpus(&h->log_offset);
-}
-
-void vhdx_header_le_export(VHDXHeader *orig_h, VHDXHeader *new_h)
-{
-    assert(orig_h != NULL);
-    assert(new_h != NULL);
-
-    new_h->signature       = cpu_to_le32(orig_h->signature);
-    new_h->checksum        = cpu_to_le32(orig_h->checksum);
-    new_h->sequence_number = cpu_to_le64(orig_h->sequence_number);
-
-    new_h->file_write_guid = orig_h->file_write_guid;
-    new_h->data_write_guid = orig_h->data_write_guid;
-    new_h->log_guid        = orig_h->log_guid;
-
-    cpu_to_leguids(&new_h->file_write_guid);
-    cpu_to_leguids(&new_h->data_write_guid);
-    cpu_to_leguids(&new_h->log_guid);
-
-    new_h->log_version     = cpu_to_le16(orig_h->log_version);
-    new_h->version         = cpu_to_le16(orig_h->version);
-    new_h->log_length      = cpu_to_le32(orig_h->log_length);
-    new_h->log_offset      = cpu_to_le64(orig_h->log_offset);
-}
-
-
-/* VHDX Log Headers */
-
-
-void vhdx_log_desc_le_import(VHDXLogDescriptor *d)
-{
-    assert(d != NULL);
-
-    le32_to_cpus(&d->signature);
-    le32_to_cpus(&d->trailing_bytes);
-    le64_to_cpus(&d->leading_bytes);
-    le64_to_cpus(&d->file_offset);
-    le64_to_cpus(&d->sequence_number);
-}
-
-void vhdx_log_desc_le_export(VHDXLogDescriptor *d)
-{
-    assert(d != NULL);
-
-    cpu_to_le32s(&d->signature);
-    cpu_to_le32s(&d->trailing_bytes);
-    cpu_to_le64s(&d->leading_bytes);
-    cpu_to_le64s(&d->file_offset);
-    cpu_to_le64s(&d->sequence_number);
-}
-
-void vhdx_log_data_le_export(VHDXLogDataSector *d)
-{
-    assert(d != NULL);
-
-    cpu_to_le32s(&d->data_signature);
-    cpu_to_le32s(&d->sequence_high);
-    cpu_to_le32s(&d->sequence_low);
-}
-
-void vhdx_log_entry_hdr_le_import(VHDXLogEntryHeader *hdr)
-{
-    assert(hdr != NULL);
-
-    le32_to_cpus(&hdr->signature);
-    le32_to_cpus(&hdr->checksum);
-    le32_to_cpus(&hdr->entry_length);
-    le32_to_cpus(&hdr->tail);
-    le64_to_cpus(&hdr->sequence_number);
-    le32_to_cpus(&hdr->descriptor_count);
-    leguid_to_cpus(&hdr->log_guid);
-    le64_to_cpus(&hdr->flushed_file_offset);
-    le64_to_cpus(&hdr->last_file_offset);
-}
-
-void vhdx_log_entry_hdr_le_export(VHDXLogEntryHeader *hdr)
-{
-    assert(hdr != NULL);
-
-    cpu_to_le32s(&hdr->signature);
-    cpu_to_le32s(&hdr->checksum);
-    cpu_to_le32s(&hdr->entry_length);
-    cpu_to_le32s(&hdr->tail);
-    cpu_to_le64s(&hdr->sequence_number);
-    cpu_to_le32s(&hdr->descriptor_count);
-    cpu_to_leguids(&hdr->log_guid);
-    cpu_to_le64s(&hdr->flushed_file_offset);
-    cpu_to_le64s(&hdr->last_file_offset);
-}
-
-
-/* Region table entries */
-void vhdx_region_header_le_import(VHDXRegionTableHeader *hdr)
-{
-    assert(hdr != NULL);
-
-    le32_to_cpus(&hdr->signature);
-    le32_to_cpus(&hdr->checksum);
-    le32_to_cpus(&hdr->entry_count);
-}
-
-void vhdx_region_header_le_export(VHDXRegionTableHeader *hdr)
-{
-    assert(hdr != NULL);
-
-    cpu_to_le32s(&hdr->signature);
-    cpu_to_le32s(&hdr->checksum);
-    cpu_to_le32s(&hdr->entry_count);
-}
-
-void vhdx_region_entry_le_import(VHDXRegionTableEntry *e)
-{
-    assert(e != NULL);
-
-    leguid_to_cpus(&e->guid);
-    le64_to_cpus(&e->file_offset);
-    le32_to_cpus(&e->length);
-    le32_to_cpus(&e->data_bits);
-}
-
-void vhdx_region_entry_le_export(VHDXRegionTableEntry *e)
-{
-    assert(e != NULL);
-
-    cpu_to_leguids(&e->guid);
-    cpu_to_le64s(&e->file_offset);
-    cpu_to_le32s(&e->length);
-    cpu_to_le32s(&e->data_bits);
-}
-
-
-/* Metadata headers & table */
-void vhdx_metadata_header_le_import(VHDXMetadataTableHeader *hdr)
-{
-    assert(hdr != NULL);
-
-    le64_to_cpus(&hdr->signature);
-    le16_to_cpus(&hdr->entry_count);
-}
-
-void vhdx_metadata_header_le_export(VHDXMetadataTableHeader *hdr)
-{
-    assert(hdr != NULL);
-
-    cpu_to_le64s(&hdr->signature);
-    cpu_to_le16s(&hdr->entry_count);
-}
-
-void vhdx_metadata_entry_le_import(VHDXMetadataTableEntry *e)
-{
-    assert(e != NULL);
-
-    leguid_to_cpus(&e->item_id);
-    le32_to_cpus(&e->offset);
-    le32_to_cpus(&e->length);
-    le32_to_cpus(&e->data_bits);
-}
-void vhdx_metadata_entry_le_export(VHDXMetadataTableEntry *e)
-{
-    assert(e != NULL);
-
-    cpu_to_leguids(&e->item_id);
-    cpu_to_le32s(&e->offset);
-    cpu_to_le32s(&e->length);
-    cpu_to_le32s(&e->data_bits);
-}

block/vhdx.h

@@ -6,9 +6,9 @@
  * Authors:
  *  Jeff Cody <jcody@redhat.com>
  *
- *  This is based on the "VHDX Format Specification v1.00", published 8/25/2012
+ *  This is based on the "VHDX Format Specification v0.95", published 4/12/2012
  *  by Microsoft:
- *      https://www.microsoft.com/en-us/download/details.aspx?id=34750
+ *      https://www.microsoft.com/en-us/download/details.aspx?id=29681
  *
  * This work is licensed under the terms of the GNU LGPL, version 2 or later.
  * See the COPYING.LIB file in the top-level directory.
@@ -18,12 +18,6 @@
 #ifndef BLOCK_VHDX_H
 #define BLOCK_VHDX_H
 
-#define KiB              (1 * 1024)
-#define MiB            (KiB * 1024)
-#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,
@@ -36,15 +30,14 @@
  * 0.........64KB...........128KB........192KB..........256KB................1MB
  */
 
-#define VHDX_HEADER_BLOCK_SIZE      (64 * 1024)
+#define VHDX_HEADER_BLOCK_SIZE      (64*1024)
 
 #define VHDX_FILE_ID_OFFSET         0
-#define VHDX_HEADER1_OFFSET         (VHDX_HEADER_BLOCK_SIZE * 1)
-#define VHDX_HEADER2_OFFSET         (VHDX_HEADER_BLOCK_SIZE * 2)
-#define VHDX_REGION_TABLE_OFFSET    (VHDX_HEADER_BLOCK_SIZE * 3)
-#define VHDX_REGION_TABLE2_OFFSET   (VHDX_HEADER_BLOCK_SIZE * 4)
+#define VHDX_HEADER1_OFFSET         (VHDX_HEADER_BLOCK_SIZE*1)
+#define VHDX_HEADER2_OFFSET         (VHDX_HEADER_BLOCK_SIZE*2)
+#define VHDX_REGION_TABLE_OFFSET    (VHDX_HEADER_BLOCK_SIZE*3)
+
 
-#define VHDX_HEADER_SECTION_END     (1 * MiB)
 /*
  * A note on the use of MS-GUID fields.  For more details on the GUID,
  * please see: https://en.wikipedia.org/wiki/Globally_unique_identifier.
@@ -62,11 +55,10 @@
 /* These structures are ones that are defined in the VHDX specification
  * document */
 
-#define VHDX_FILE_SIGNATURE 0x656C696678646876ULL  /* "vhdxfile" in ASCII */
 typedef struct VHDXFileIdentifier {
     uint64_t    signature;              /* "vhdxfile" in ASCII */
     uint16_t    creator[256];           /* optional; utf-16 string to identify
-                                           the vhdx file creator.  Diagnostic
+                                           the vhdx file creator.  Diagnotistic
                                            only */
 } VHDXFileIdentifier;
 
@@ -75,7 +67,7 @@ typedef struct VHDXFileIdentifier {
  * Microsoft is not just 16 bytes though - it is a structure that is defined,
  * so we need to follow it here so that endianness does not trip us up */
 
-typedef struct QEMU_PACKED MSGUID {
+typedef struct MSGUID {
     uint32_t  data1;
     uint16_t  data2;
     uint16_t  data3;
@@ -85,15 +77,14 @@ typedef struct QEMU_PACKED MSGUID {
 #define guid_eq(a, b) \
     (memcmp(&(a), &(b), sizeof(MSGUID)) == 0)
 
-#define VHDX_HEADER_SIZE (4 * 1024)   /* although the vhdx_header struct in disk
-                                         is only 582 bytes, for purposes of crc
-                                         the header is the first 4KB of the 64KB
-                                         block */
+#define VHDX_HEADER_SIZE (4*1024)   /* although the vhdx_header struct in disk
+                                       is only 582 bytes, for purposes of crc
+                                       the header is the first 4KB of the 64KB
+                                       block */
 
 /* The full header is 4KB, although the actual header data is much smaller.
  * But for the checksum calculation, it is over the entire 4KB structure,
  * not just the defined portion of it */
-#define VHDX_HEADER_SIGNATURE 0x64616568
 typedef struct QEMU_PACKED VHDXHeader {
     uint32_t    signature;              /* "head" in ASCII */
     uint32_t    checksum;               /* CRC-32C hash of the whole header */
@@ -101,7 +92,7 @@ typedef struct QEMU_PACKED VHDXHeader {
                                            VHDX file has 2 of these headers,
                                            and only the header with the highest
                                            sequence number is valid */
-    MSGUID      file_write_guid;        /* 128 bit unique identifier. Must be
+    MSGUID      file_write_guid;       /* 128 bit unique identifier. Must be
                                            updated to new, unique value before
                                            the first modification is made to
                                            file */
@@ -123,9 +114,9 @@ typedef struct QEMU_PACKED VHDXHeader {
                                            there is no valid log. If non-zero,
                                            log entries with this guid are
                                            valid. */
-    uint16_t    log_version;            /* version of the log format. Must be
-                                           set to zero */
-    uint16_t    version;                /* version of the vhdx file.  Currently,
+    uint16_t    log_version;            /* version of the log format. Mustn't be
+                                           zero, unless log_guid is also zero */
+    uint16_t    version;                /* version of th evhdx file.  Currently,
                                            only supported version is "1" */
     uint32_t    log_length;             /* length of the log.  Must be multiple
                                            of 1MB */
@@ -134,7 +125,6 @@ typedef struct QEMU_PACKED VHDXHeader {
 } VHDXHeader;
 
 /* Header for the region table block */
-#define VHDX_REGION_SIGNATURE  0x69676572  /* "regi" in ASCII */
 typedef struct QEMU_PACKED VHDXRegionTableHeader {
     uint32_t    signature;              /* "regi" in ASCII */
     uint32_t    checksum;               /* CRC-32C hash of the 64KB table */
@@ -161,10 +151,7 @@ typedef struct QEMU_PACKED VHDXRegionTableEntry {
 
 
 /* ---- LOG ENTRY STRUCTURES ---- */
-#define VHDX_LOG_MIN_SIZE (1024 * 1024)
-#define VHDX_LOG_SECTOR_SIZE 4096
 #define VHDX_LOG_HDR_SIZE 64
-#define VHDX_LOG_SIGNATURE 0x65676f6c
 typedef struct QEMU_PACKED VHDXLogEntryHeader {
     uint32_t    signature;              /* "loge" in ASCII */
     uint32_t    checksum;               /* CRC-32C hash of the 64KB table */
@@ -187,8 +174,7 @@ typedef struct QEMU_PACKED VHDXLogEntryHeader {
 } VHDXLogEntryHeader;
 
 #define VHDX_LOG_DESC_SIZE 32
-#define VHDX_LOG_DESC_SIGNATURE 0x63736564
-#define VHDX_LOG_ZERO_SIGNATURE 0x6f72657a
+
 typedef struct QEMU_PACKED VHDXLogDescriptor {
     uint32_t    signature;              /* "zero" or "desc" in ASCII */
     union  {
@@ -208,7 +194,6 @@ typedef struct QEMU_PACKED VHDXLogDescriptor {
                                            vhdx_log_entry_header */
 } VHDXLogDescriptor;
 
-#define VHDX_LOG_DATA_SIGNATURE 0x61746164
 typedef struct QEMU_PACKED VHDXLogDataSector {
     uint32_t    data_signature;         /* "data" in ASCII */
     uint32_t    sequence_high;          /* 4 MSB of 8 byte sequence_number */
@@ -227,19 +212,19 @@ typedef struct QEMU_PACKED VHDXLogDataSector {
 #define PAYLOAD_BLOCK_UNDEFINED         1
 #define PAYLOAD_BLOCK_ZERO              2
 #define PAYLOAD_BLOCK_UNMAPPED          5
-#define PAYLOAD_BLOCK_FULLY_PRESENT     6
+#define PAYLOAD_BLOCK_FULL_PRESENT      6
 #define PAYLOAD_BLOCK_PARTIALLY_PRESENT 7
 
 #define SB_BLOCK_NOT_PRESENT    0
 #define SB_BLOCK_PRESENT        6
 
 /* per the spec */
-#define VHDX_MAX_SECTORS_PER_BLOCK  (1 << 23)
+#define VHDX_MAX_SECTORS_PER_BLOCK  (1<<23)
 
 /* 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_BITS (64-44)
 typedef uint64_t VHDXBatEntry;
 
 /* ---- METADATA REGION STRUCTURES ---- */
@@ -248,7 +233,6 @@ 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 */
 typedef struct QEMU_PACKED VHDXMetadataTableHeader {
     uint64_t    signature;              /* "metadata" in ASCII */
     uint16_t    reserved;
@@ -268,8 +252,8 @@ typedef struct QEMU_PACKED VHDXMetadataTableEntry {
                                            metadata region */
                                         /* note: if length = 0, so is offset */
     uint32_t    length;                 /* length of metadata. <= 1MB. */
-    uint32_t    data_bits;              /* least-significant 3 bits are flags,
-                                           the rest are reserved (see above) */
+    uint32_t    data_bits;      /* least-significant 3 bits are flags, the
+                                   rest are reserved (see above) */
     uint32_t    reserved2;
 } VHDXMetadataTableEntry;
 
@@ -278,16 +262,13 @@ typedef struct QEMU_PACKED VHDXMetadataTableEntry {
                                                    If set indicates a fixed
                                                    size VHDX file */
 #define VHDX_PARAMS_HAS_PARENT           0x02    /* has parent / backing file */
-#define VHDX_BLOCK_SIZE_MIN             (1   * MiB)
-#define VHDX_BLOCK_SIZE_MAX             (256 * MiB)
 typedef struct QEMU_PACKED VHDXFileParameters {
     uint32_t    block_size;             /* size of each payload block, always
                                            power of 2, <= 256MB and >= 1MB. */
-    uint32_t data_bits;                 /* least-significant 2 bits are flags,
-                                           the rest are reserved (see above) */
+    uint32_t data_bits;     /* least-significant 2 bits are flags, the rest
+                               are reserved (see above) */
 } VHDXFileParameters;
 
-#define VHDX_MAX_IMAGE_SIZE  ((uint64_t) 64 * TiB)
 typedef struct QEMU_PACKED VHDXVirtualDiskSize {
     uint64_t    virtual_disk_size;      /* Size of the virtual disk, in bytes.
                                            Must be multiple of the sector size,
@@ -295,7 +276,7 @@ typedef struct QEMU_PACKED VHDXVirtualDiskSize {
 } VHDXVirtualDiskSize;
 
 typedef struct QEMU_PACKED VHDXPage83Data {
-    MSGUID      page_83_data;           /* unique id for scsi devices that
+    MSGUID      page_83_data[16];       /* unique id for scsi devices that
                                            support page 0x83 */
 } VHDXPage83Data;
 
@@ -310,7 +291,7 @@ typedef struct QEMU_PACKED VHDXVirtualDiskPhysicalSectorSize {
 } VHDXVirtualDiskPhysicalSectorSize;
 
 typedef struct QEMU_PACKED VHDXParentLocatorHeader {
-    MSGUID      locator_type;           /* type of the parent virtual disk. */
+    MSGUID      locator_type[16];       /* type of the parent virtual disk. */
     uint16_t    reserved;
     uint16_t    key_value_count;        /* number of key/value pairs for this
                                            locator */
@@ -327,125 +308,18 @@ typedef struct QEMU_PACKED VHDXParentLocatorEntry {
 
 /* ----- END VHDX SPECIFICATION STRUCTURES ---- */
 
-typedef struct VHDXMetadataEntries {
-    VHDXMetadataTableEntry file_parameters_entry;
-    VHDXMetadataTableEntry virtual_disk_size_entry;
-    VHDXMetadataTableEntry page83_data_entry;
-    VHDXMetadataTableEntry logical_sector_size_entry;
-    VHDXMetadataTableEntry phys_sector_size_entry;
-    VHDXMetadataTableEntry parent_locator_entry;
-    uint16_t present;
-} VHDXMetadataEntries;
 
-typedef struct VHDXLogEntries {
-    uint64_t offset;
-    uint64_t length;
-    uint32_t write;
-    uint32_t read;
-    VHDXLogEntryHeader *hdr;
-    void *desc_buffer;
-    uint64_t sequence;
-    uint32_t tail;
-} VHDXLogEntries;
-
-typedef struct VHDXRegionEntry {
-    uint64_t start;
-    uint64_t end;
-    QLIST_ENTRY(VHDXRegionEntry) entries;
-} VHDXRegionEntry;
-
-typedef struct BDRVVHDXState {
-    CoMutex lock;
-
-    int curr_header;
-    VHDXHeader *headers[2];
-
-    VHDXRegionTableHeader rt;
-    VHDXRegionTableEntry bat_rt;         /* region table for the BAT */
-    VHDXRegionTableEntry metadata_rt;    /* region table for the metadata */
-
-    VHDXMetadataTableHeader metadata_hdr;
-    VHDXMetadataEntries metadata_entries;
-
-    VHDXFileParameters params;
-    uint32_t block_size;
-    uint32_t block_size_bits;
-    uint32_t sectors_per_block;
-    uint32_t sectors_per_block_bits;
-
-    uint64_t virtual_disk_size;
-    uint32_t logical_sector_size;
-    uint32_t physical_sector_size;
-
-    uint64_t chunk_ratio;
-    uint32_t chunk_ratio_bits;
-    uint32_t logical_sector_size_bits;
-
-    uint32_t bat_entries;
-    VHDXBatEntry *bat;
-    uint64_t bat_offset;
-
-    bool first_visible_write;
-    MSGUID session_guid;
-
-    VHDXLogEntries log;
-
-    VHDXParentLocatorHeader parent_header;
-    VHDXParentLocatorEntry *parent_entries;
-
-    Error *migration_blocker;
-
-    bool log_replayed_on_open;
-
-    QLIST_HEAD(VHDXRegionHead, VHDXRegionEntry) regions;
-} BDRVVHDXState;
-
-void vhdx_guid_generate(MSGUID *guid);
-
-int vhdx_update_headers(BlockDriverState *bs, BDRVVHDXState *s, bool rw,
-                        MSGUID *log_guid);
-
-uint32_t vhdx_update_checksum(uint8_t *buf, size_t size, int crc_offset);
 uint32_t vhdx_checksum_calc(uint32_t crc, uint8_t *buf, size_t size,
                             int crc_offset);
 
 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_log_write_and_flush(BlockDriverState *bs, BDRVVHDXState *s,
-                             void *data, uint32_t length, uint64_t offset);
-
-static inline void leguid_to_cpus(MSGUID *guid)
+static void leguid_to_cpus(MSGUID *guid)
 {
     le32_to_cpus(&guid->data1);
     le16_to_cpus(&guid->data2);
     le16_to_cpus(&guid->data3);
 }
 
-static inline void cpu_to_leguids(MSGUID *guid)
-{
-    cpu_to_le32s(&guid->data1);
-    cpu_to_le16s(&guid->data2);
-    cpu_to_le16s(&guid->data3);
-}
-
-void vhdx_header_le_import(VHDXHeader *h);
-void vhdx_header_le_export(VHDXHeader *orig_h, VHDXHeader *new_h);
-void vhdx_log_desc_le_import(VHDXLogDescriptor *d);
-void vhdx_log_desc_le_export(VHDXLogDescriptor *d);
-void vhdx_log_data_le_export(VHDXLogDataSector *d);
-void vhdx_log_entry_hdr_le_import(VHDXLogEntryHeader *hdr);
-void vhdx_log_entry_hdr_le_export(VHDXLogEntryHeader *hdr);
-void vhdx_region_header_le_import(VHDXRegionTableHeader *hdr);
-void vhdx_region_header_le_export(VHDXRegionTableHeader *hdr);
-void vhdx_region_entry_le_import(VHDXRegionTableEntry *e);
-void vhdx_region_entry_le_export(VHDXRegionTableEntry *e);
-void vhdx_metadata_header_le_import(VHDXMetadataTableHeader *hdr);
-void vhdx_metadata_header_le_export(VHDXMetadataTableHeader *hdr);
-void vhdx_metadata_entry_le_import(VHDXMetadataTableEntry *e);
-void vhdx_metadata_entry_le_export(VHDXMetadataTableEntry *e);
-int vhdx_user_visible_write(BlockDriverState *bs, BDRVVHDXState *s);
-
 #endif

block/vpc.c

@@ -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
 
 /**************************************************************/
 
@@ -52,10 +45,8 @@ enum vhd_type {
 // Seconds since Jan 1, 2000 0:00:00 (UTC)
 #define VHD_TIMESTAMP_BASE 946684800
 
-#define VHD_MAX_SECTORS       (65535LL * 255 * 255)
-
 // always big-endian
-typedef struct vhd_footer {
+struct vhd_footer {
     char        creator[8]; // "conectix"
     uint32_t    features;
     uint32_t    version;
@@ -88,9 +79,9 @@ typedef struct vhd_footer {
     uint8_t     uuid[16];
 
     uint8_t     in_saved_state;
-} QEMU_PACKED VHDFooter;
+};
 
-typedef struct vhd_dyndisk_header {
+struct vhd_dyndisk_header {
     char        magic[8]; // "cxsparse"
 
     // Offset of next header structure, 0xFFFFFFFF if none
@@ -120,7 +111,7 @@ typedef struct vhd_dyndisk_header {
         uint32_t    reserved;
         uint64_t    data_offset;
     } parent_locator[8];
-} QEMU_PACKED VHDDynDiskHeader;
+};
 
 typedef struct BDRVVPCState {
     CoMutex lock;
@@ -164,16 +155,14 @@ static int vpc_probe(const uint8_t *buf, int buf_size, const char *filename)
     return 0;
 }
 
-static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
-                    Error **errp)
+static int vpc_open(BlockDriverState *bs, QDict *options, int flags)
 {
     BDRVVPCState *s = bs->opaque;
     int i;
-    VHDFooter *footer;
-    VHDDynDiskHeader *dyndisk_header;
+    struct vhd_footer* footer;
+    struct vhd_dyndisk_header* dyndisk_header;
     uint8_t buf[HEADER_SIZE];
     uint32_t checksum;
-    uint64_t computed_size;
     int disk_type = VHD_DYNAMIC;
     int ret;
 
@@ -182,7 +171,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
 
-    footer = (VHDFooter *) s->footer_buf;
+    footer = (struct vhd_footer*) s->footer_buf;
     if (strncmp(footer->creator, "conectix", 8)) {
         int64_t offset = bdrv_getlength(bs->file);
         if (offset < 0) {
@@ -200,8 +189,7 @@ 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;
@@ -222,17 +210,8 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
     bs->total_sectors = (int64_t)
         be16_to_cpu(footer->cyls) * footer->heads * footer->secs_per_cyl;
 
-    /* images created with disk2vhd report a far higher virtual size
-     * than expected with the cyls * heads * sectors_per_cyl formula.
-     * use the footer->size instead if the image was created with
-     * disk2vhd.
-     */
-    if (!strncmp(footer->creator_app, "d2v", 4)) {
-        bs->total_sectors = be64_to_cpu(footer->size) / BDRV_SECTOR_SIZE;
-    }
-
     /* Allow a maximum disk size of approximately 2 TB */
-    if (bs->total_sectors >= VHD_MAX_SECTORS) {
+    if (bs->total_sectors >= 65535LL * 255 * 255) {
         ret = -EFBIG;
         goto fail;
     }
@@ -244,7 +223,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
             goto fail;
         }
 
-        dyndisk_header = (VHDDynDiskHeader *) buf;
+        dyndisk_header = (struct vhd_dyndisk_header *) buf;
 
         if (strncmp(dyndisk_header->magic, "cxsparse", 8)) {
             ret = -EINVAL;
@@ -252,31 +231,10 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
         }
 
         s->block_size = be32_to_cpu(dyndisk_header->block_size);
-        if (!is_power_of_2(s->block_size) || s->block_size < BDRV_SECTOR_SIZE) {
-            error_setg(errp, "Invalid block size %" PRIu32, s->block_size);
-            ret = -EINVAL;
-            goto fail;
-        }
         s->bitmap_size = ((s->block_size / (8 * 512)) + 511) & ~511;
 
         s->max_table_entries = be32_to_cpu(dyndisk_header->max_table_entries);
-
-        if ((bs->total_sectors * 512) / s->block_size > 0xffffffffU) {
-            ret = -EINVAL;
-            goto fail;
-        }
-        if (s->max_table_entries > (VHD_MAX_SECTORS * 512) / s->block_size) {
-            ret = -EINVAL;
-            goto fail;
-        }
-
-        computed_size = (uint64_t) s->max_table_entries * s->block_size;
-        if (computed_size < bs->total_sectors * 512) {
-            ret = -EINVAL;
-            goto fail;
-        }
-
-        s->pagetable = qemu_blockalign(bs, s->max_table_entries * 4);
+        s->pagetable = g_malloc(s->max_table_entries * 4);
 
         s->bat_offset = be64_to_cpu(dyndisk_header->table_offset);
 
@@ -301,13 +259,6 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
             }
         }
 
-        if (s->free_data_block_offset > bdrv_getlength(bs->file)) {
-            error_setg(errp, "block-vpc: free_data_block_offset points after "
-                             "the end of file. The image has been truncated.");
-            ret = -EINVAL;
-            goto fail;
-        }
-
         s->last_bitmap_offset = (int64_t) -1;
 
 #ifdef CACHE
@@ -329,7 +280,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
     return 0;
 
 fail:
-    qemu_vfree(s->pagetable);
+    g_free(s->pagetable);
 #ifdef CACHE
     g_free(s->pageentry_u8);
 #endif
@@ -487,19 +438,6 @@ 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)
 {
@@ -507,7 +445,7 @@ static int vpc_read(BlockDriverState *bs, int64_t sector_num,
     int ret;
     int64_t offset;
     int64_t sectors, sectors_per_block;
-    VHDFooter *footer = (VHDFooter *) s->footer_buf;
+    struct vhd_footer *footer = (struct vhd_footer *) s->footer_buf;
 
     if (cpu_to_be32(footer->type) == VHD_FIXED) {
         return bdrv_read(bs->file, sector_num, buf, nb_sectors);
@@ -556,7 +494,7 @@ static int vpc_write(BlockDriverState *bs, int64_t sector_num,
     int64_t offset;
     int64_t sectors, sectors_per_block;
     int ret;
-    VHDFooter *footer =  (VHDFooter *) s->footer_buf;
+    struct vhd_footer *footer =  (struct vhd_footer *) s->footer_buf;
 
     if (cpu_to_be32(footer->type) == VHD_FIXED) {
         return bdrv_write(bs->file, sector_num, buf, nb_sectors);
@@ -658,8 +596,8 @@ static int calculate_geometry(int64_t total_sectors, uint16_t* cyls,
 
 static int create_dynamic_disk(int fd, uint8_t *buf, int64_t total_sectors)
 {
-    VHDDynDiskHeader *dyndisk_header =
-        (VHDDynDiskHeader *) buf;
+    struct vhd_dyndisk_header* dyndisk_header =
+        (struct vhd_dyndisk_header*) buf;
     size_t block_size, num_bat_entries;
     int i;
     int ret = -EIO;
@@ -745,11 +683,11 @@ 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)
 {
     uint8_t buf[1024];
-    VHDFooter *footer = (VHDFooter *) buf;
-    char *disk_type_param;
+    struct vhd_footer *footer = (struct vhd_footer *) buf;
+    QEMUOptionParameter *disk_type_param;
     int fd, i;
     uint16_t cyls = 0;
     uint8_t heads = 0;
@@ -758,45 +696,27 @@ 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;
     }
 
     /*
@@ -861,17 +781,15 @@ 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;
 }
 
 static int vpc_has_zero_init(BlockDriverState *bs)
 {
     BDRVVPCState *s = bs->opaque;
-    VHDFooter *footer =  (VHDFooter *) s->footer_buf;
+    struct vhd_footer *footer =  (struct vhd_footer *) s->footer_buf;
 
     if (cpu_to_be32(footer->type) == VHD_FIXED) {
         return bdrv_has_zero_init(bs->file);
@@ -883,7 +801,7 @@ static int vpc_has_zero_init(BlockDriverState *bs)
 static void vpc_close(BlockDriverState *bs)
 {
     BDRVVPCState *s = bs->opaque;
-    qemu_vfree(s->pagetable);
+    g_free(s->pagetable);
 #ifdef CACHE
     g_free(s->pageentry_u8);
 #endif
@@ -892,29 +810,20 @@ 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 +839,7 @@ 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,
 };