update VERSION for 1.1.2

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

.exrc

@@ -1,7 +0,0 @@
-"VIM settings to match QEMU coding style.  They are activated by adding the
-"following settings (without the " symbol) as last two lines in $HOME/.vimrc:
-"set secure
-"set exrc
-set expandtab
-set shiftwidth=4
-set smarttab

.gitignore

@@ -1,21 +1,19 @@
 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
+trace.h
+trace.c
+trace-dtrace.h
+trace-dtrace.dtrace
 *-timestamp
 *-softmmu
 *-darwin-user
 *-linux-user
 *-bsd-user
 libdis*
+libhw32
+libhw64
 libuser
 linux-headers/asm
 qapi-generated
@@ -43,15 +41,12 @@ 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
@@ -73,34 +68,22 @@ fsdev/virtfs-proxy-helper.pod
 *.tp
 *.vr
 *.d
-!scripts/qemu-guest-agent/fsfreeze-hook.d
 *.o
-*.lo
-*.la
-*.pc
-.libs
 *.swp
 *.orig
 .pc
-*.gcda
-*.gcno
 patches
 pc-bios/bios-pq/status
 pc-bios/vgabios-pq/status
-pc-bios/optionrom/linuxboot.asm
 pc-bios/optionrom/linuxboot.bin
 pc-bios/optionrom/linuxboot.raw
 pc-bios/optionrom/linuxboot.img
-pc-bios/optionrom/multiboot.asm
 pc-bios/optionrom/multiboot.bin
 pc-bios/optionrom/multiboot.raw
 pc-bios/optionrom/multiboot.img
-pc-bios/optionrom/kvmvapic.asm
 pc-bios/optionrom/kvmvapic.bin
 pc-bios/optionrom/kvmvapic.raw
 pc-bios/optionrom/kvmvapic.img
-pc-bios/s390-ccw/s390-ccw.elf
-pc-bios/s390-ccw/s390-ccw.img
 .stgit-*
 cscope.*
 tags

.gitmodules

@@ -15,13 +15,7 @@
 	url = git://git.qemu.org/openbios.git
 [submodule "roms/qemu-palcode"]
 	path = roms/qemu-palcode
-	url = git://github.com/rth7680/qemu-palcode.git
+	url = git://repo.or.cz/qemu-palcode.git
 [submodule "roms/sgabios"]
 	path = roms/sgabios
 	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.org/dtc.git

HACKING

@@ -32,7 +32,7 @@ mandatory for VMState fields.
 
 Don't use Linux kernel internal types like u32, __u32 or __le32.
 
-Use hwaddr for guest physical addresses except pcibus_t
+Use target_phys_addr_t for guest physical addresses except pcibus_t
 for PCI addresses.  In addition, ram_addr_t is a QEMU internal address
 space that maps guest RAM physical addresses into an intermediate
 address space that can map to host virtual address spaces.  Generally
@@ -40,23 +40,8 @@ speaking, the size of guest memory can always fit into ram_addr_t but
 it would not be correct to store an actual guest physical address in a
 ram_addr_t.
 
-For CPU virtual addresses there are several possible types.
-vaddr is the best type to use to hold a CPU virtual address in
-target-independent code. It is guaranteed to be large enough to hold a
-virtual address for any target, and it does not change size from target
-to target. It is always unsigned.
-target_ulong is a type the size of a virtual address on the CPU; this means
-it may be 32 or 64 bits depending on which target is being built. It should
-therefore be used only in target-specific code, and in some
-performance-critical built-per-target core code such as the TLB code.
-There is also a signed version, target_long.
-abi_ulong is for the *-user targets, and represents a type the size of
-'void *' in that target's ABI. (This may not be the same as the size of a
-full CPU virtual address in the case of target ABIs which use 32 bit pointers
-on 64 bit CPUs, like sparc32plus.) Definitions of structures that must match
-the target's ABI must use this type for anything that on the target is defined
-to be an 'unsigned long' or a pointer type.
-There is also a signed version, abi_long.
+Use target_ulong (or abi_ulong) for CPU virtual addresses, however
+devices should not need to use target_ulong.
 
 Of course, take all of the above with a grain of salt.  If you're about
 to use some system interface that requires a type like size_t, pid_t or
@@ -93,23 +78,23 @@ avoided.
 Use of the malloc/free/realloc/calloc/valloc/memalign/posix_memalign
 APIs is not allowed in the QEMU codebase. Instead of these routines,
 use the GLib memory allocation routines g_malloc/g_malloc0/g_new/
-g_new0/g_realloc/g_free or QEMU's qemu_memalign/qemu_blockalign/qemu_vfree
+g_new0/g_realloc/g_free or QEMU's qemu_vmalloc/qemu_memalign/qemu_vfree
 APIs.
 
 Please note that g_malloc will exit on allocation failure, so there
 is no need to test for failure (as you would have to with malloc).
 Calling g_malloc with a zero size is valid and will return NULL.
 
-Memory allocated by qemu_memalign or qemu_blockalign must be freed with
-qemu_vfree, since breaking this will cause problems on Win32.
+Memory allocated by qemu_vmalloc or qemu_memalign must be freed with
+qemu_vfree, since breaking this will cause problems on Win32 and user
+emulators.
 
 4. String manipulation
 
-Do not use the strncpy function.  As mentioned in the man page, it does *not*
-guarantee a NULL-terminated buffer, which makes it extremely dangerous to use.
-It also zeros trailing destination bytes out to the specified length.  Instead,
-use this similar function when possible, but note its different signature:
-void pstrcpy(char *dest, int dest_buf_size, const char *src)
+Do not use the strncpy function.  According to the man page, it does
+*not* guarantee a NULL-terminated buffer, which makes it extremely dangerous
+to use.  Instead, use functionally equivalent function:
+void pstrcpy(char *buf, int buf_size, const char *str)
 
 Don't use strcat because it can't check for buffer overflows, but:
 char *pstrcat(char *buf, int buf_size, const char *s)
@@ -137,23 +122,3 @@ gcc's printf attribute directive in the prototype.
 This makes it so gcc's -Wformat and -Wformat-security options can do
 their jobs and cross-check format strings with the number and types
 of arguments.
-
-6. C standard, implementation defined and undefined behaviors
-
-C code in QEMU should be written to the C99 language specification. A copy
-of the final version of the C99 standard with corrigenda TC1, TC2, and TC3
-included, formatted as a draft, can be downloaded from:
- http://www.open-std.org/jtc1/sc22/WG14/www/docs/n1256.pdf
-
-The C language specification defines regions of undefined behavior and
-implementation defined behavior (to give compiler authors enough leeway to
-produce better code).  In general, code in QEMU should follow the language
-specification and avoid both undefined and implementation defined
-constructs. ("It works fine on the gcc I tested it with" is not a valid
-argument...) However there are a few areas where we allow ourselves to
-assume certain behaviors because in practice all the platforms we care about
-behave in the same way and writing strictly conformant code would be
-painful. These are:
- * you may assume that integers are 2s complement representation
- * you may assume that right shift of a signed integer duplicates
-   the sign bit (ie it is an arithmetic shift, not a logical shift)

MAINTAINERS

@@ -59,120 +59,86 @@ Alpha
 M: Richard Henderson <rth@twiddle.net>
 S: Maintained
 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/
-F: hw/arm/
-F: hw/cpu/a*mpcore.c
 
 CRIS
 M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
 S: Maintained
 F: target-cris/
-F: hw/cris/
 
 LM32
 M: Michael Walle <michael@walle.cc>
 S: Maintained
 F: target-lm32/
-F: hw/lm32/
-F: hw/char/lm32_*
 
 M68K
 M: Paul Brook <paul@codesourcery.com>
 S: Odd Fixes
 F: target-m68k/
-F: hw/m68k/
 
 MicroBlaze
 M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
 S: Maintained
 F: target-microblaze/
-F: hw/microblaze/
 
 MIPS
 M: Aurelien Jarno <aurelien@aurel32.net>
 S: Odd Fixes
 F: target-mips/
-F: hw/mips/
-
-Moxie
-M: Anthony Green <green@moxielogic.com>
-S: Maintained
-F: target-moxie/
-
-OpenRISC
-M: Jia Liu <proljc@gmail.com>
-S: Maintained
-F: target-openrisc/
-F: hw/openrisc/
 
 PowerPC
 M: Alexander Graf <agraf@suse.de>
 L: qemu-ppc@nongnu.org
 S: Maintained
 F: target-ppc/
-F: hw/ppc/
 
 S390
-M: Richard Henderson <rth@twiddle.net>
 M: Alexander Graf <agraf@suse.de>
 S: Maintained
 F: target-s390x/
-F: hw/s390x/
 
 SH4
 M: Aurelien Jarno <aurelien@aurel32.net>
 S: Odd Fixes
 F: target-sh4/
-F: hw/sh4/
 
 SPARC
 M: Blue Swirl <blauwirbel@gmail.com>
 S: Maintained
 F: target-sparc/
-F: hw/sparc/
-F: hw/sparc64/
 
 UniCore32
 M: Guan Xuetao <gxt@mprc.pku.edu.cn>
 S: Maintained
 F: target-unicore32/
-F: hw/unicore32/
 
 X86
 M: qemu-devel@nongnu.org
 S: Odd Fixes
 F: target-i386/
-F: hw/i386/
 
 Xtensa
 M: Max Filippov <jcmvbkbc@gmail.com>
 W: http://wiki.osll.spb.ru/doku.php?id=etc:users:jcmvbkbc:qemu-target-xtensa
 S: Maintained
 F: target-xtensa/
-F: hw/xtensa/
 
 Guest CPU Cores (KVM):
 ----------------------
 
 Overall
-M: Gleb Natapov <gleb@redhat.com>
-M: Paolo Bonzini <pbonzini@redhat.com>
+M: Avi Kivity <avi@redhat.com>
+M: Marcelo Tosatti <mtosatti@redhat.com>
 L: kvm@vger.kernel.org
 S: Supported
 F: kvm-*
 F: */kvm.*
 
-ARM
-M: Peter Maydell <peter.maydell@linaro.org>
-S: Maintained
-F: target-arm/kvm.c
-
 PPC
 M: Alexander Graf <agraf@suse.de>
 S: Maintained
@@ -184,7 +150,7 @@ S: Maintained
 F: target-s390x/kvm.c
 
 X86
-M: Gleb Natapov <gleb@redhat.com>
+M: Avi Kivity <avi@redhat.com>
 M: Marcelo Tosatti <mtosatti@redhat.com>
 L: kvm@vger.kernel.org
 S: Supported
@@ -225,377 +191,273 @@ ARM Machines
 Exynos
 M: Evgeny Voevodin <e.voevodin@samsung.com>
 M: Maksim Kozlov <m.kozlov@samsung.com>
-M: Igor Mitsyanko <i.mitsyanko@gmail.com>
+M: Igor Mitsyanko <i.mitsyanko@samsung.com>
 M: Dmitry Solodkiy <d.solodkiy@samsung.com>
 S: Maintained
-F: hw/*/exynos*
+F: hw/exynos*
 
 Calxeda Highbank
 M: Mark Langsdorf <mark.langsdorf@calxeda.com>
 S: Supported
-F: hw/arm/highbank.c
-F: hw/net/xgmac.c
+F: hw/highbank.c
+F: hw/xgmac.c
 
 Gumstix
 M: qemu-devel@nongnu.org
 S: Orphan
-F: hw/arm/gumstix.c
-
-i.MX31
-M: Peter Chubb <peter.chubb@nicta.com.au>
-S: Odd fixes
-F: hw/*/imx*
-F: hw/arm/kzm.c
+F: hw/gumstix.c
 
 Integrator CP
 M: Paul Brook <paul@codesourcery.com>
 M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
-F: hw/arm/integratorcp.c
+F: hw/integratorcp.c
 
 Mainstone
 M: qemu-devel@nongnu.org
 S: Orphan
-F: hw/arm/mainstone.c
+F: hw/mainstone.c
 
 Musicpal
 M: Jan Kiszka <jan.kiszka@web.de>
 S: Maintained
-F: hw/arm/musicpal.c
+F: hw/musicpal.c
 
 nSeries
 M: Andrzej Zaborowski <balrogg@gmail.com>
 S: Maintained
-F: hw/arm/nseries.c
+F: hw/nseries.c
 
 Palm
 M: Andrzej Zaborowski <balrogg@gmail.com>
 S: Maintained
-F: hw/arm/palm.c
+F: hw/palm.c
 
 Real View
 M: Paul Brook <paul@codesourcery.com>
 M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
-F: hw/arm/realview*
+F: hw/realview*
 
 Spitz
 M: Andrzej Zaborowski <balrogg@gmail.com>
 S: Maintained
-F: hw/arm/spitz.c
+F: hw/spitz.c
 
 Stellaris
 M: Paul Brook <paul@codesourcery.com>
 M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
-F: hw/*/stellaris*
+F: hw/stellaris.c
 
 Versatile PB
 M: Paul Brook <paul@codesourcery.com>
 M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
-F: hw/*/versatile*
+F: hw/versatilepb.c
 
 Xilinx Zynq
 M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
 S: Maintained
-F: hw/arm/xilinx_zynq.c
-F: hw/misc/zynq_slcr.c
-F: hw/*/cadence_*
-F: hw/ssi/xilinx_spips.c
+F: hw/xilinx_zynq.c
+F: hw/zynq_slcr.c
+F: hw/cadence_*
 
 CRIS Machines
 -------------
 Axis Dev88
 M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
 S: Maintained
-F: hw/cris/axis_dev88.c
-F: hw/*/etraxfs_*.c
+F: hw/axis_dev88.c
+
+etraxfs
+M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
+S: Maintained
+F: hw/etraxfs.c
 
 LM32 Machines
 -------------
 EVR32 and uclinux BSP
 M: Michael Walle <michael@walle.cc>
 S: Maintained
-F: hw/lm32/lm32_boards.c
+F: hw/lm32_boards.c
 
 milkymist
 M: Michael Walle <michael@walle.cc>
 S: Maintained
-F: hw/lm32/milkymist.c
+F: hw/milkymist.c
 
 M68K Machines
 -------------
 an5206
 M: Paul Brook <paul@codesourcery.com>
 S: Maintained
-F: hw/m68k/an5206.c
+F: hw/an5206.c
 
 dummy_m68k
 M: Paul Brook <paul@codesourcery.com>
 S: Maintained
-F: hw/m68k/dummy_m68k.c
+F: hw/dummy_m68k.c
 
 mcf5208
 M: Paul Brook <paul@codesourcery.com>
 S: Maintained
-F: hw/m68k/mcf5208.c
+F: hw/mcf5208.c
 
 MicroBlaze Machines
 -------------------
 petalogix_s3adsp1800
 M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
 S: Maintained
-F: hw/microblaze/petalogix_s3adsp1800_mmu.c
-
-petalogix_ml605
-M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
-S: Maintained
-F: hw/microblaze/petalogix_ml605_mmu.c
+F: hw/petalogix_s3adsp1800.c
 
 MIPS Machines
 -------------
 Jazz
 M: Hervé Poussineau <hpoussin@reactos.org>
 S: Maintained
-F: hw/mips/mips_jazz.c
+F: hw/mips_jazz.c
 
 Malta
 M: Aurelien Jarno <aurelien@aurel32.net>
 S: Maintained
-F: hw/mips/mips_malta.c
+F: hw/mips_malta.c
 
 Mipssim
 M: qemu-devel@nongnu.org
 S: Orphan
-F: hw/mips/mips_mipssim.c
+F: hw/mips_mipssim.c
 
 R4000
 M: Aurelien Jarno <aurelien@aurel32.net>
 S: Maintained
-F: hw/mips/mips_r4k.c
-
-OpenRISC Machines
------------------
-or1k-sim
-M: Jia Liu <proljc@gmail.com>
-S: Maintained
-F: hw/openrisc/openrisc_sim.c
+F: hw/mips_r4k.c
 
 PowerPC Machines
 ----------------
 405
 M: Alexander Graf <agraf@suse.de>
 L: qemu-ppc@nongnu.org
-S: Odd Fixes
-F: hw/ppc/ppc405_boards.c
-
-Bamboo
-M: Alexander Graf <agraf@suse.de>
-L: qemu-ppc@nongnu.org
-S: Odd Fixes
-F: hw/ppc/ppc440_bamboo.c
-
-e500
-M: Alexander Graf <agraf@suse.de>
-M: Scott Wood <scottwood@freescale.com>
-L: qemu-ppc@nongnu.org
-S: Supported
-F: hw/ppc/e500.[hc]
-F: hw/ppc/e500plat.c
-
-mpc8544ds
-M: Alexander Graf <agraf@suse.de>
-M: Scott Wood <scottwood@freescale.com>
-L: qemu-ppc@nongnu.org
-S: Supported
-F: hw/ppc/mpc8544ds.c
-F: hw/ppc/mpc8544_guts.c
+S: Maintained
+F: hw/ppc405_boards.c
 
 New World
 M: Alexander Graf <agraf@suse.de>
 L: qemu-ppc@nongnu.org
 S: Maintained
-F: hw/ppc/mac_newworld.c
-F: hw/pci-host/uninorth.c
-F: hw/pci-bridge/dec.[hc]
-F: hw/misc/macio/
+F: hw/ppc_newworld.c
+F: hw/unin_pci.c
+F: hw/dec_pci.[hc]
 
 Old World
 M: Alexander Graf <agraf@suse.de>
 L: qemu-ppc@nongnu.org
 S: Maintained
-F: hw/ppc/mac_oldworld.c
-F: hw/pci-host/grackle.c
-F: hw/misc/macio/
+F: hw/ppc_oldworld.c
+F: hw/grackle_pci.c
 
 PReP
 M: Andreas Färber <andreas.faerber@web.de>
 L: qemu-ppc@nongnu.org
 S: Odd Fixes
-F: hw/ppc/prep.c
-F: hw/pci-host/prep.[hc]
-F: hw/isa/pc87312.[hc]
-
-sPAPR
-M: Alexander Graf <agraf@suse.de>
-L: qemu-ppc@nongnu.org
-S: Supported
-F: hw/*/spapr*
-F: include/hw/*/spapr*
-F: hw/*/xics*
-F: include/hw/*/xics*
-F: pc-bios/spapr-rtas/*
-
-virtex_ml507
-M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
-L: qemu-ppc@nongnu.org
-S: Odd Fixes
-F: hw/ppc/virtex_ml507.c
+F: hw/ppc_prep.c
+F: hw/prep_pci.[hc]
 
 SH4 Machines
 ------------
 R2D
 M: Magnus Damm <magnus.damm@gmail.com>
 S: Maintained
-F: hw/sh4/r2d.c
+F: hw/r2d.c
 
 Shix
 M: Magnus Damm <magnus.damm@gmail.com>
 S: Orphan
-F: hw/sh4/shix.c
+F: hw/shix.c
 
 SPARC Machines
 --------------
 Sun4m
 M: Blue Swirl <blauwirbel@gmail.com>
 S: Maintained
-F: hw/sparc/sun4m.c
+F: hw/sun4m.c
 
 Sun4u
 M: Blue Swirl <blauwirbel@gmail.com>
 S: Maintained
-F: hw/sparc64/sun4u.c
-
-Leon3
-M: Fabien Chouteau <chouteau@adacore.com>
-S: Maintained
-F: hw/sparc/leon3.c
-F: hw/*/grlib*
+F: hw/sun4u.c
 
 S390 Machines
 -------------
 S390 Virtio
 M: Alexander Graf <agraf@suse.de>
 S: Maintained
-F: hw/s390x/s390-*.c
-
-S390 Virtio-ccw
-M: Cornelia Huck <cornelia.huck@de.ibm.com>
-M: Alexander Graf <agraf@suse.de>
-S: Supported
-F: hw/s390x/s390-virtio-ccw.c
-F: hw/s390x/css.[hc]
-T: git git://github.com/cohuck/qemu virtio-ccw-upstr
-
-UniCore32 Machines
--------------
-PKUnity-3 SoC initramfs-with-busybox
-M: Guan Xuetao <gxt@mprc.pku.edu.cn>
-S: Maintained
-F: hw/*/puv3*
-F: hw/unicore32/
+F: hw/s390-*.c
 
 X86 Machines
 ------------
 PC
 M: Anthony Liguori <aliguori@us.ibm.com>
 S: Supported
-F: hw/i386/pc.[ch]
-F: hw/i386/pc_piix.c
+F: hw/pc.[ch]
+F: hw/pc_piix.c
 
 Xtensa Machines
 ---------------
 sim
 M: Max Filippov <jcmvbkbc@gmail.com>
 S: Maintained
-F: hw/xtensa/xtensa_sim.c
+F: hw/xtensa_sim.c
 
 Avnet LX60
 M: Max Filippov <jcmvbkbc@gmail.com>
 S: Maintained
-F: hw/xtensa/xtensa_lx60.c
+F: hw/xtensa_lx60.c
 
 Devices
 -------
 IDE
 M: Kevin Wolf <kwolf@redhat.com>
 S: Odd Fixes
-F: include/hw/ide.h
 F: hw/ide/
 
 OMAP
 M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
-F: hw/*/omap*
+F: hw/omap*
 
 PCI
 M: Michael S. Tsirkin <mst@redhat.com>
 S: Supported
-F: include/hw/pci/*
-F: hw/pci/*
-F: hw/acpi/*
-
-ppc4xx
-M: Alexander Graf <agraf@suse.de>
-L: qemu-ppc@nongnu.org
-S: Odd Fixes
-F: hw/ppc/ppc4*.c
-
-ppce500
-M: Alexander Graf <agraf@suse.de>
-M: Scott Wood <scottwood@freescale.com>
-L: qemu-ppc@nongnu.org
-S: Supported
-F: hw/ppc/e500*
+F: hw/pci*
+F: hw/piix*
 
 SCSI
 M: Paolo Bonzini <pbonzini@redhat.com>
 S: Supported
-F: include/hw/scsi*
-F: hw/scsi/*
+F: hw/virtio-scsi.*
+F: hw/scsi*
 T: git git://github.com/bonzini/qemu.git scsi-next
 
 LSI53C895A
 M: Paul Brook <paul@codesourcery.com>
 S: Odd Fixes
-F: hw/scsi/lsi53c895a.c
-
-SSI
-M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
-S: Maintained
-F: hw/ssi/*
-F: hw/block/m25p80.c
+F: hw/lsi53c895a.c
 
 USB
 M: Gerd Hoffmann <kraxel@redhat.com>
 S: Maintained
-F: hw/usb/*
-
-VFIO
-M: Alex Williamson <alex.williamson@redhat.com>
-S: Supported
-F: hw/misc/vfio.c
+F: hw/usb*
 
 vhost
 M: Michael S. Tsirkin <mst@redhat.com>
 S: Supported
-F: hw/*/*vhost*
+F: hw/vhost*
 
 virtio
 M: Anthony Liguori <aliguori@us.ibm.com>
 S: Supported
-F: hw/*/virtio*
+F: hw/virtio*
 
 virtio-9p
 M: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
@@ -606,33 +468,14 @@ T: git git://github.com/kvaneesh/QEMU.git
 
 virtio-blk
 M: Kevin Wolf <kwolf@redhat.com>
-M: Stefan Hajnoczi <stefanha@redhat.com>
 S: Supported
-F: hw/block/virtio-blk.c
-
-virtio-ccw
-M: Cornelia Huck <cornelia.huck@de.ibm.com>
-S: Supported
-F: hw/s390x/virtio-ccw.[hc]
-T: git git://github.com/cohuck/qemu virtio-ccw-upstr
+F: hw/virtio-blk*
 
 virtio-serial
 M: Amit Shah <amit.shah@redhat.com>
 S: Supported
-F: hw/char/virtio-serial-bus.c
-F: hw/char/virtio-console.c
-
-nvme
-M: Keith Busch <keith.busch@intel.com>
-S: Supported
-F: hw/block/nvme*
-
-Xilinx EDK
-M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
-M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
-S: Maintained
-F: hw/*/xilinx_*
-F: include/hw/xilinx.h
+F: hw/virtio-serial*
+F: hw/virtio-console*
 
 Subsystems
 ----------
@@ -640,40 +483,18 @@ Audio
 M: Vassili Karpov (malc) <av1474@comtv.ru>
 S: Maintained
 F: audio/
-F: hw/audio/
 
 Block
 M: Kevin Wolf <kwolf@redhat.com>
-M: Stefan Hajnoczi <stefanha@redhat.com>
 S: Supported
 F: block*
 F: block/
-F: hw/block/
 
 Character Devices
 M: Anthony Liguori <aliguori@us.ibm.com>
 S: Maintained
 F: qemu-char.c
 
-CPU
-M: Andreas Färber <afaerber@suse.de>
-S: Supported
-F: qom/cpu.c
-F: include/qom/cpu.h
-F: target-i386/cpu.c
-
-ICC Bus
-M: Igor Mammedov <imammedo@redhat.com>
-S: Supported
-F: include/hw/cpu/icc_bus.h
-F: hw/cpu/icc_bus.c
-
-Device Tree
-M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
-M: Alexander Graf <agraf@suse.de>
-S: Maintained
-F: device_tree.[ch]
-
 GDB stub
 M: qemu-devel@nongnu.org
 S: Odd Fixes
@@ -683,10 +504,10 @@ F: gdb-xml/
 SPICE
 M: Gerd Hoffmann <kraxel@redhat.com>
 S: Supported
-F: include/ui/qemu-spice.h
+F: ui/qemu-spice.h
 F: ui/spice-*.c
 F: audio/spiceaudio.c
-F: hw/display/qxl*
+F: hw/qxl*
 
 Graphics
 M: Anthony Liguori <aliguori@us.ibm.com>
@@ -703,19 +524,17 @@ M: Anthony Liguori <aliguori@us.ibm.com>
 S: Supported
 F: vl.c
 
-Human Monitor (HMP)
+Monitor (QMP/HMP)
 M: Luiz Capitulino <lcapitulino@redhat.com>
+M: Markus Armbruster <armbru@redhat.com>
 S: Supported
 F: monitor.c
-F: hmp.c
-F: hmp-commands.hx
 
 Network device layer
 M: Anthony Liguori <aliguori@us.ibm.com>
-M: Stefan Hajnoczi <stefanha@redhat.com>
+M: Mark McLoughlin <markmc@redhat.com>
 S: Maintained
 F: net/
-T: git git://github.com/stefanha/qemu.git net
 
 Network Block Device (NBD)
 M: Paolo Bonzini <pbonzini@redhat.com>
@@ -725,27 +544,6 @@ F: nbd.*
 F: qemu-nbd.c
 T: git git://github.com/bonzini/qemu.git nbd-next
 
-QAPI
-M: Luiz Capitulino <lcapitulino@redhat.com>
-M: Michael Roth <mdroth@linux.vnet.ibm.com>
-S: Supported
-F: qapi/
-
-QAPI Schema
-M: Eric Blake <eblake@redhat.com>
-M: Luiz Capitulino <lcapitulino@redhat.com>
-M: Markus Armbruster <armbru@redhat.com>
-S: Supported
-F: qapi-schema.json
-
-QMP
-M: Luiz Capitulino <lcapitulino@redhat.com>
-S: Supported
-F: qmp.c
-F: monitor.c
-F: qmp-commands.hx
-F: QMP/
-
 SLIRP
 M: Jan Kiszka <jan.kiszka@siemens.com>
 S: Maintained
@@ -753,7 +551,7 @@ F: slirp/
 T: git git://git.kiszka.org/qemu.git queues/slirp
 
 Tracing
-M: Stefan Hajnoczi <stefanha@redhat.com>
+M: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
 S: Maintained
 F: trace/
 F: scripts/tracetool.py
@@ -782,16 +580,9 @@ Tiny Code Generator (TCG)
 -------------------------
 Common code
 M: qemu-devel@nongnu.org
-M: Richard Henderson <rth@twiddle.net>
 S: Maintained
 F: tcg/
 
-AArch64 target
-M: Claudio Fontana <claudio.fontana@huawei.com>
-M: Claudio Fontana <claudio.fontana@gmail.com>
-S: Maintained
-F: tcg/aarch64/
-
 ARM target
 M: Andrzej Zaborowski <balrogg@gmail.com>
 S: Maintained

Makefile

@@ -6,49 +6,24 @@ BUILD_DIR=$(CURDIR)
 # All following code might depend on configuration variables
 ifneq ($(wildcard config-host.mak),)
 # Put the all: rule here so that config-host.mak can contain dependencies.
-all:
+all: build-all
 include config-host.mak
-
-# Check that we're not trying to do an out-of-tree build from
-# a tree that's been used for an in-tree build.
-ifneq ($(realpath $(SRC_PATH)),$(realpath .))
-ifneq ($(wildcard $(SRC_PATH)/config-host.mak),)
-$(error This is an out of tree build but your source tree ($(SRC_PATH)) \
-seems to have been used for an in-tree build. You can fix this by running \
-"make distclean && rm -rf *-linux-user *-softmmu" in your source tree)
-endif
-endif
-
-CONFIG_SOFTMMU := $(if $(filter %-softmmu,$(TARGET_DIRS)),y)
-CONFIG_USER_ONLY := $(if $(filter %-user,$(TARGET_DIRS)),y)
-CONFIG_ALL=y
--include config-all-devices.mak
--include config-all-disas.mak
-
 include $(SRC_PATH)/rules.mak
 config-host.mak: $(SRC_PATH)/configure
 	@echo $@ is out-of-date, running configure
 	@sed -n "/.*Configured with/s/[^:]*: //p" $@ | sh
 else
 config-host.mak:
-ifneq ($(filter-out %clean,$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
 	@echo "Please call configure before running make!"
 	@exit 1
 endif
-endif
 
-GENERATED_HEADERS = config-host.h qemu-options.def
-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
+GENERATED_HEADERS = config-host.h trace.h qemu-options.def
 ifeq ($(TRACE_BACKEND),dtrace)
-GENERATED_HEADERS += trace/generated-tracers-dtrace.h
+GENERATED_HEADERS += trace-dtrace.h
 endif
-GENERATED_SOURCES += trace/generated-tracers.c
+GENERATED_HEADERS += qmp-commands.h qapi-types.h qapi-visit.h
+GENERATED_SOURCES += qmp-marshal.c qapi-types.c qapi-visit.c trace.c
 
 # Don't try to regenerate Makefile or configure
 # We don't generate any of them
@@ -56,9 +31,9 @@ Makefile: ;
 configure: ;
 
 .PHONY: all clean cscope distclean dvi html info install install-doc \
-	pdf recurse-all speed test dist
+	pdf recurse-all speed tar tarbin test build-all
 
-$(call set-vpath, $(SRC_PATH))
+$(call set-vpath, $(SRC_PATH):$(SRC_PATH)/hw)
 
 LIBS+=-lz $(LIBS_TOOLS)
 
@@ -75,18 +50,10 @@ endif
 
 SUBDIR_MAKEFLAGS=$(if $(V),,--no-print-directory) BUILD_DIR=$(BUILD_DIR)
 SUBDIR_DEVICES_MAK=$(patsubst %, %/config-devices.mak, $(TARGET_DIRS))
-SUBDIR_DEVICES_MAK_DEP=$(patsubst %, %-config-devices.mak.d, $(TARGET_DIRS))
+SUBDIR_DEVICES_MAK_DEP=$(patsubst %, %/config-devices.mak.d, $(TARGET_DIRS))
 
-ifeq ($(SUBDIR_DEVICES_MAK),)
-config-all-devices.mak:
-	$(call quiet-command,echo '# no devices' > $@,"  GEN   $@")
-else
 config-all-devices.mak: $(SUBDIR_DEVICES_MAK)
-	$(call quiet-command, sed -n \
-             's|^\([^=]*\)=\(.*\)$$|\1:=$$(findstring y,$$(\1)\2)|p' \
-             $(SUBDIR_DEVICES_MAK) | sort -u > $@, \
-             "  GEN   $@")
-endif
+	$(call quiet-command,cat $(SUBDIR_DEVICES_MAK) | grep =y | sort -u > $@,"  GEN   $@")
 
 -include $(SUBDIR_DEVICES_MAK_DEP)
 
@@ -113,15 +80,9 @@ endif
 defconfig:
 	rm -f config-all-devices.mak $(SUBDIR_DEVICES_MAK)
 
-ifneq ($(wildcard config-host.mak),)
-include $(SRC_PATH)/Makefile.objs
-include $(SRC_PATH)/tests/Makefile
-endif
-ifeq ($(CONFIG_SMARTCARD_NSS),y)
-include $(SRC_PATH)/libcacard/Makefile
-endif
+-include config-all-devices.mak
 
-all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all
+build-all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all
 
 config-host.h: config-host.h-timestamp
 config-host.h-timestamp: config-host.mak
@@ -129,33 +90,20 @@ qemu-options.def: $(SRC_PATH)/qemu-options.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $@")
 
 SUBDIR_RULES=$(patsubst %,subdir-%, $(TARGET_DIRS))
-SOFTMMU_SUBDIR_RULES=$(filter %-softmmu,$(SUBDIR_RULES))
 
-$(SOFTMMU_SUBDIR_RULES): config-all-devices.mak
-
-subdir-%:
+subdir-%: $(GENERATED_HEADERS)
 	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C $* V="$(V)" TARGET_DIR="$*/" all,)
 
-subdir-pixman: pixman/Makefile
-	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C pixman V="$(V)" all,)
+ifneq ($(wildcard config-host.mak),)
+include $(SRC_PATH)/Makefile.objs
+endif
 
-pixman/Makefile: $(SRC_PATH)/pixman/configure
-	(cd pixman; CFLAGS="$(CFLAGS) -fPIC $(extra_cflags) $(extra_ldflags)" $(SRC_PATH)/pixman/configure $(AUTOCONF_HOST) --disable-gtk --disable-shared --enable-static)
+$(universal-obj-y) $(common-obj-y): $(GENERATED_HEADERS)
+subdir-libcacard: $(oslib-obj-y) $(trace-obj-y) qemu-timer-common.o
 
-$(SRC_PATH)/pixman/configure:
-	(cd $(SRC_PATH)/pixman; autoreconf -v --install)
+$(filter %-softmmu,$(SUBDIR_RULES)): $(universal-obj-y) $(trace-obj-y) $(common-obj-y) subdir-libdis
 
-DTC_MAKE_ARGS=-I$(SRC_PATH)/dtc VPATH=$(SRC_PATH)/dtc -C dtc V="$(V)" LIBFDT_srcdir=$(SRC_PATH)/dtc/libfdt
-DTC_CFLAGS=$(CFLAGS) $(QEMU_CFLAGS)
-DTC_CPPFLAGS=-I$(BUILD_DIR)/dtc -I$(SRC_PATH)/dtc -I$(SRC_PATH)/dtc/libfdt
-
-subdir-dtc:dtc/libfdt dtc/tests
-	$(call quiet-command,$(MAKE) $(DTC_MAKE_ARGS) CPPFLAGS="$(DTC_CPPFLAGS)" CFLAGS="$(DTC_CFLAGS)" LDFLAGS="$(LDFLAGS)" ARFLAGS="$(ARFLAGS)" CC="$(CC)" AR="$(AR)" LD="$(LD)" $(SUBDIR_MAKEFLAGS) libfdt/libfdt.a,)
-
-dtc/%:
-	mkdir -p $@
-
-$(SUBDIR_RULES): libqemuutil.a libqemustub.a $(common-obj-y)
+$(filter %-user,$(SUBDIR_RULES)): $(GENERATED_HEADERS) $(universal-obj-y) $(trace-obj-y) subdir-libdis-user subdir-libuser
 
 ROMSUBDIR_RULES=$(patsubst %,romsubdir-%, $(ROMS))
 romsubdir-%:
@@ -165,103 +113,128 @@ ALL_SUBDIRS=$(TARGET_DIRS) $(patsubst %,pc-bios/%, $(ROMS))
 
 recurse-all: $(SUBDIR_RULES) $(ROMSUBDIR_RULES)
 
+audio/audio.o audio/fmodaudio.o: QEMU_CFLAGS += $(FMOD_CFLAGS)
+
+QEMU_CFLAGS+=$(CURL_CFLAGS)
+
+QEMU_CFLAGS += -I$(SRC_PATH)/include
+
+ui/cocoa.o: ui/cocoa.m
+
+ui/sdl.o audio/sdlaudio.o ui/sdl_zoom.o baum.o: QEMU_CFLAGS += $(SDL_CFLAGS)
+
+ui/vnc.o: QEMU_CFLAGS += $(VNC_TLS_CFLAGS)
+
 bt-host.o: QEMU_CFLAGS += $(BLUEZ_CFLAGS)
 
-version.o: $(SRC_PATH)/version.rc config-host.h | version.lo
-version.lo: $(SRC_PATH)/version.rc config-host.h
+version.o: $(SRC_PATH)/version.rc config-host.h
+	$(call quiet-command,$(WINDRES) -I. -o $@ $<,"  RC    $(TARGET_DIR)$@")
 
 version-obj-$(CONFIG_WIN32) += version.o
-version-lobj-$(CONFIG_WIN32) += version.lo
-
-Makefile: $(version-obj-y) $(version-lobj-y)
-
 ######################################################################
-# Build libraries
+# Support building shared library libcacard
 
-libqemustub.a: $(stub-obj-y)
-libqemuutil.a: $(util-obj-y) qapi-types.o qapi-visit.o
+.PHONY: libcacard.la install-libcacard
+ifeq ($(LIBTOOL),)
+libcacard.la:
+	@echo "libtool is missing, please install and rerun configure"; exit 1
 
+install-libcacard:
+	@echo "libtool is missing, please install and rerun configure"; exit 1
+else
+libcacard.la: $(GENERATED_HEADERS) $(oslib-obj-y) qemu-timer-common.o $(addsuffix .lo, $(basename $(trace-obj-y)))
+	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C libcacard V="$(V)" TARGET_DIR="$*/" libcacard.la,)
+
+install-libcacard: libcacard.la
+	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C libcacard V="$(V)" TARGET_DIR="$*/" install-libcacard,)
+endif
 ######################################################################
 
 qemu-img.o: qemu-img-cmds.h
+qemu-img.o qemu-tool.o qemu-nbd.o qemu-io.o cmd.o qemu-ga.o: $(GENERATED_HEADERS)
 
-qemu-img$(EXESUF): qemu-img.o $(block-obj-y) libqemuutil.a libqemustub.a
-qemu-nbd$(EXESUF): qemu-nbd.o $(block-obj-y) libqemuutil.a libqemustub.a
-qemu-io$(EXESUF): qemu-io.o $(block-obj-y) libqemuutil.a libqemustub.a
+tools-obj-y = $(oslib-obj-y) $(trace-obj-y) qemu-tool.o qemu-timer.o \
+	qemu-timer-common.o main-loop.o notify.o iohandler.o cutils.o async.o
+tools-obj-$(CONFIG_POSIX) += compatfd.o
+
+qemu-img$(EXESUF): qemu-img.o $(tools-obj-y) $(block-obj-y)
+qemu-nbd$(EXESUF): qemu-nbd.o $(tools-obj-y) $(block-obj-y)
+qemu-io$(EXESUF): qemu-io.o cmd.o $(tools-obj-y) $(block-obj-y)
 
 qemu-bridge-helper$(EXESUF): qemu-bridge-helper.o
+qemu-bridge-helper.o: $(GENERATED_HEADERS)
 
-fsdev/virtfs-proxy-helper$(EXESUF): fsdev/virtfs-proxy-helper.o fsdev/virtio-9p-marshal.o libqemuutil.a libqemustub.a
+fsdev/virtfs-proxy-helper$(EXESUF): fsdev/virtfs-proxy-helper.o fsdev/virtio-9p-marshal.o oslib-posix.o $(trace-obj-y)
 fsdev/virtfs-proxy-helper$(EXESUF): LIBS += -lcap
 
 qemu-img-cmds.h: $(SRC_PATH)/qemu-img-cmds.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $@")
 
+$(qapi-obj-y): $(GENERATED_HEADERS)
+qapi-dir := $(BUILD_DIR)/qapi-generated
 qemu-ga$(EXESUF): LIBS = $(LIBS_QGA)
-qemu-ga$(EXESUF): QEMU_CFLAGS += -I qga/qapi-generated
+qemu-ga$(EXESUF): QEMU_CFLAGS += -I $(qapi-dir)
 
 gen-out-type = $(subst .,-,$(suffix $@))
 
-qapi-py = $(SRC_PATH)/scripts/qapi.py $(SRC_PATH)/scripts/ordereddict.py
+ifneq ($(wildcard config-host.mak),)
+include $(SRC_PATH)/tests/Makefile
+endif
 
-qga/qapi-generated/qga-qapi-types.c qga/qapi-generated/qga-qapi-types.h :\
-$(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py $(gen-out-type) -o qga/qapi-generated -p "qga-" < $<, "  GEN   $@")
-qga/qapi-generated/qga-qapi-visit.c qga/qapi-generated/qga-qapi-visit.h :\
-$(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-visit.py $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py $(gen-out-type) -o qga/qapi-generated -p "qga-" < $<, "  GEN   $@")
-qga/qapi-generated/qga-qmp-commands.h qga/qapi-generated/qga-qmp-marshal.c :\
-$(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py $(gen-out-type) -o qga/qapi-generated -p "qga-" < $<, "  GEN   $@")
+$(qapi-dir)/qga-qapi-types.c $(qapi-dir)/qga-qapi-types.h :\
+$(SRC_PATH)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-types.py
+	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py $(gen-out-type) -o "$(qapi-dir)" -p "qga-" < $<, "  GEN   $@")
+$(qapi-dir)/qga-qapi-visit.c $(qapi-dir)/qga-qapi-visit.h :\
+$(SRC_PATH)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-visit.py
+	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py $(gen-out-type) -o "$(qapi-dir)" -p "qga-" < $<, "  GEN   $@")
+$(qapi-dir)/qga-qmp-commands.h $(qapi-dir)/qga-qmp-marshal.c :\
+$(SRC_PATH)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-commands.py
+	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py $(gen-out-type) -o "$(qapi-dir)" -p "qga-" < $<, "  GEN   $@")
 
 qapi-types.c qapi-types.h :\
-$(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   $@")
+$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-types.py
+	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py $(gen-out-type) -o "." < $<, "  GEN   $@")
 qapi-visit.c qapi-visit.h :\
-$(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   $@")
+$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-visit.py
+	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py $(gen-out-type) -o "."  < $<, "  GEN   $@")
 qmp-commands.h qmp-marshal.c :\
-$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
+$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.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: $(QGALIB_GEN)
+QGALIB_OBJ=$(addprefix $(qapi-dir)/, qga-qapi-types.o qga-qapi-visit.o qga-qmp-marshal.o)
+QGALIB_GEN=$(addprefix $(qapi-dir)/, qga-qapi-types.h qga-qapi-visit.h qga-qmp-commands.h)
+$(QGALIB_OBJ): $(QGALIB_GEN) $(GENERATED_HEADERS)
+$(qga-obj-y) qemu-ga.o: $(QGALIB_GEN) $(GENERATED_HEADERS)
 
-qemu-ga$(EXESUF): $(qga-obj-y) libqemuutil.a libqemustub.a
-	$(call LINK, $^)
+qemu-ga$(EXESUF): qemu-ga.o $(qga-obj-y) $(tools-obj-y) $(qapi-obj-y) $(qobject-obj-y) $(version-obj-y) $(QGALIB_OBJ)
+
+QEMULIBS=libhw32 libhw64 libuser libdis libdis-user
 
 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 '*.[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 -f *.o *.d *.a *.lo $(TOOLS) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
 	rm -Rf .libs
+	rm -f slirp/*.o slirp/*.d audio/*.o audio/*.d block/*.o block/*.d net/*.o net/*.d fsdev/*.o fsdev/*.d ui/*.o ui/*.d qapi/*.o qapi/*.d qga/*.o qga/*.d
+	rm -f qom/*.o qom/*.d
 	rm -f qemu-img-cmds.h
+	rm -f trace/*.o trace/*.d
+	rm -f trace-dtrace.dtrace trace-dtrace.dtrace-timestamp
 	@# May not be present in GENERATED_HEADERS
-	rm -f trace/generated-tracers-dtrace.dtrace*
-	rm -f trace/generated-tracers-dtrace.h*
+	rm -f trace-dtrace.h trace-dtrace.h-timestamp
 	rm -f $(foreach f,$(GENERATED_HEADERS),$(f) $(f)-timestamp)
 	rm -f $(foreach f,$(GENERATED_SOURCES),$(f) $(f)-timestamp)
-	rm -rf qapi-generated
-	rm -rf qga/qapi-generated
+	rm -rf $(qapi-dir)
 	$(MAKE) -C tests/tcg clean
-	for d in $(ALL_SUBDIRS); do \
+	for d in $(ALL_SUBDIRS) $(QEMULIBS) libcacard; do \
 	if test -d $$d; then $(MAKE) -C $$d $@ || exit 1; fi; \
 	rm -f $$d/qemu-options.def; \
         done
 
-VERSION ?= $(shell cat VERSION)
-
-dist: qemu-$(VERSION).tar.bz2
-
-qemu-%.tar.bz2:
-	$(SRC_PATH)/scripts/make-release "$(SRC_PATH)" "$(patsubst qemu-%.tar.bz2,%,$@)"
-
 distclean: clean
 	rm -f config-host.mak config-host.h* config-host.ld $(DOCS) qemu-options.texi qemu-img-cmds.texi qemu-monitor.texi
-	rm -f config-all-devices.mak config-all-disas.mak
+	rm -f config-all-devices.mak
 	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
@@ -270,31 +243,25 @@ distclean: clean
 	rm -f config.log
 	rm -f linux-headers/asm
 	rm -f qemu-tech.info qemu-tech.aux qemu-tech.cp qemu-tech.dvi qemu-tech.fn qemu-tech.info qemu-tech.ky qemu-tech.log qemu-tech.pdf qemu-tech.pg qemu-tech.toc qemu-tech.tp qemu-tech.vr
-	for d in $(TARGET_DIRS); do \
+	for d in $(TARGET_DIRS) $(QEMULIBS); do \
 	rm -rf $$d || exit 1 ; \
         done
-	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
+common  de-ch  es     fo  fr-ca  hu     ja  mk  nl-be      pt  sl     tr
 
 ifdef INSTALL_BLOBS
 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 \
 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 \
-efi-pcnet.rom efi-rtl8139.rom efi-virtio.rom \
-qemu-icon.bmp qemu_logo_no_text.svg \
+qemu-icon.bmp \
 bamboo.dtb petalogix-s3adsp1800.dtb petalogix-ml605.dtb \
+mpc8544ds.dtb \
 multiboot.bin linuxboot.bin kvmvapic.bin \
 s390-zipl.rom \
-s390-ccw.img \
 spapr-rtas.bin slof.bin \
 palcode-clipper
 else
@@ -307,13 +274,10 @@ install-doc: $(DOCS)
 	$(INSTALL_DATA) QMP/qmp-commands.txt "$(DESTDIR)$(qemu_docdir)"
 ifdef CONFIG_POSIX
 	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man1"
-	$(INSTALL_DATA) qemu.1 "$(DESTDIR)$(mandir)/man1"
-ifneq ($(TOOLS),)
-	$(INSTALL_DATA) qemu-img.1 "$(DESTDIR)$(mandir)/man1"
+	$(INSTALL_DATA) qemu.1 qemu-img.1 "$(DESTDIR)$(mandir)/man1"
 	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man8"
 	$(INSTALL_DATA) qemu-nbd.8 "$(DESTDIR)$(mandir)/man8"
 endif
-endif
 ifdef CONFIG_VIRTFS
 	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man1"
 	$(INSTALL_DATA) fsdev/virtfs-proxy-helper.1 "$(DESTDIR)$(mandir)/man1"
@@ -322,21 +286,14 @@ endif
 install-datadir:
 	$(INSTALL_DIR) "$(DESTDIR)$(qemu_datadir)"
 
-install-localstatedir:
-ifdef CONFIG_POSIX
-ifneq (,$(findstring qemu-ga,$(TOOLS)))
-	$(INSTALL_DIR) "$(DESTDIR)$(qemu_localstatedir)"/run
-endif
-endif
-
 install-confdir:
 	$(INSTALL_DIR) "$(DESTDIR)$(qemu_confdir)"
 
 install-sysconfig: install-datadir install-confdir
 	$(INSTALL_DATA) $(SRC_PATH)/sysconfigs/target/target-x86_64.conf "$(DESTDIR)$(qemu_confdir)"
+	$(INSTALL_DATA) $(SRC_PATH)/sysconfigs/target/cpus-x86_64.conf "$(DESTDIR)$(qemu_datadir)"
 
-install: all $(if $(BUILD_DOCS),install-doc) install-sysconfig \
-install-datadir install-localstatedir
+install: all $(if $(BUILD_DOCS),install-doc) install-sysconfig install-datadir
 	$(INSTALL_DIR) "$(DESTDIR)$(bindir)"
 ifneq ($(TOOLS),)
 	$(INSTALL_PROG) $(STRIP_OPT) $(TOOLS) "$(DESTDIR)$(bindir)"
@@ -349,9 +306,6 @@ ifneq ($(BLOBS),)
 	set -e; for x in $(BLOBS); do \
 		$(INSTALL_DATA) $(SRC_PATH)/pc-bios/$$x "$(DESTDIR)$(qemu_datadir)"; \
 	done
-endif
-ifeq ($(CONFIG_GTK),y)
-	$(MAKE) -C po $@
 endif
 	$(INSTALL_DIR) "$(DESTDIR)$(qemu_datadir)/keymaps"
 	set -e; for x in $(KEYMAPS); do \
@@ -367,8 +321,7 @@ test speed: all
 
 .PHONY: TAGS
 TAGS:
-	rm -f $@
-	find "$(SRC_PATH)" -name '*.[hc]' -exec etags --append {} +
+	find "$(SRC_PATH)" -name '*.[hc]' -print0 | xargs -0 etags
 
 cscope:
 	rm -f ./cscope.*
@@ -437,67 +390,15 @@ qemu-doc.dvi qemu-doc.html qemu-doc.info qemu-doc.pdf: \
 	qemu-img.texi qemu-nbd.texi qemu-options.texi \
 	qemu-monitor.texi qemu-img-cmds.texi
 
-ifdef CONFIG_WIN32
+VERSION ?= $(shell cat VERSION)
+FILE = qemu-$(VERSION)
 
-INSTALLER = qemu-setup-$(VERSION)$(EXESUF)
-
-nsisflags = -V2 -NOCD
-
-ifneq ($(wildcard $(SRC_PATH)/dll),)
-ifeq ($(ARCH),x86_64)
-# 64 bit executables
-DLL_PATH = $(SRC_PATH)/dll/w64
-nsisflags += -DW64
-else
-# 32 bit executables
-DLL_PATH = $(SRC_PATH)/dll/w32
-endif
-endif
-
-.PHONY: installer
-installer: $(INSTALLER)
-
-INSTDIR=/tmp/qemu-nsis
-
-$(INSTALLER): $(SRC_PATH)/qemu.nsi
-	make install prefix=${INSTDIR}
-ifdef SIGNCODE
-	(cd ${INSTDIR}; \
-         for i in *.exe; do \
-           $(SIGNCODE) $${i}; \
-         done \
-        )
-endif # SIGNCODE
-	(cd ${INSTDIR}; \
-         for i in qemu-system-*.exe; do \
-           arch=$${i%.exe}; \
-           arch=$${arch#qemu-system-}; \
-           echo Section \"$$arch\" Section_$$arch; \
-           echo SetOutPath \"\$$INSTDIR\"; \
-           echo File \"\$${BINDIR}\\$$i\"; \
-           echo SectionEnd; \
-         done \
-        ) >${INSTDIR}/system-emulations.nsh
-	makensis $(nsisflags) \
-                $(if $(BUILD_DOCS),-DCONFIG_DOCUMENTATION="y") \
-                $(if $(CONFIG_GTK),-DCONFIG_GTK="y") \
-                -DBINDIR="${INSTDIR}" \
-                $(if $(DLL_PATH),-DDLLDIR="$(DLL_PATH)") \
-                -DSRCDIR="$(SRC_PATH)" \
-                -DOUTFILE="$(INSTALLER)" \
-                $(SRC_PATH)/qemu.nsi
-	rm -r ${INSTDIR}
-ifdef SIGNCODE
-	$(SIGNCODE) $(INSTALLER)
-endif # SIGNCODE
-endif # CONFIG_WIN
-
-# Add a dependency on the generated files, so that they are always
-# rebuilt before other object files
-ifneq ($(filter-out %clean,$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
-Makefile: $(GENERATED_HEADERS)
-endif
+# tar release (use 'make -k tar' on a checkouted tree)
+tar:
+	rm -rf /tmp/$(FILE)
+	cp -r . /tmp/$(FILE)
+	cd /tmp && tar zcvf ~/$(FILE).tar.gz $(FILE) --exclude CVS --exclude .git --exclude .svn
+	rm -rf /tmp/$(FILE)
 
 # Include automatically generated dependency files
-# Dependencies in Makefile.objs files come from our recursive subdir rules
--include $(wildcard *.d tests/*.d)
+-include $(wildcard *.d audio/*.d slirp/*.d block/*.d net/*.d ui/*.d qapi/*.d qga/*.d)

Makefile.dis

@@ -0,0 +1,23 @@
+# Makefile for disassemblers.
+
+include ../config-host.mak
+include config.mak
+include $(SRC_PATH)/rules.mak
+
+.PHONY: all
+
+$(call set-vpath, $(SRC_PATH))
+
+QEMU_CFLAGS+=-I..
+
+include $(SRC_PATH)/Makefile.objs
+
+all: $(libdis-y)
+# Dummy command so that make thinks it has done something
+	@true
+
+clean:
+	rm -f *.o *.d *.a *~
+
+# Include automatically generated dependency files
+-include $(wildcard *.d */*.d)

Makefile.hw

@@ -0,0 +1,25 @@
+# Makefile for qemu target independent devices.
+
+include ../config-host.mak
+include ../config-all-devices.mak
+include config.mak
+include $(SRC_PATH)/rules.mak
+
+.PHONY: all
+
+$(call set-vpath, $(SRC_PATH):$(SRC_PATH)/hw)
+
+QEMU_CFLAGS+=-I..
+QEMU_CFLAGS += -I$(SRC_PATH)/include
+
+include $(SRC_PATH)/Makefile.objs
+
+all: $(hw-obj-y)
+# Dummy command so that make thinks it has done something
+	@true
+
+clean:
+	rm -f *.o */*.o *.d */*.d *.a */*.a *~ */*~
+
+# Include automatically generated dependency files
+-include $(wildcard *.d */*.d)

Makefile.objs

@@ -1,109 +1,471 @@
 #######################################################################
-# Common libraries for tools and emulators
-stub-obj-y = stubs/
-util-obj-y = util/ qobject/ qapi/ trace/
+# Target-independent parts used in system and user emulation
+universal-obj-y =
+
+#######################################################################
+# QObject
+qobject-obj-y = qint.o qstring.o qdict.o qlist.o qfloat.o qbool.o
+qobject-obj-y += qjson.o json-lexer.o json-streamer.o json-parser.o
+qobject-obj-y += qerror.o error.o qemu-error.o
+
+universal-obj-y += $(qobject-obj-y)
+
+#######################################################################
+# QOM
+include $(SRC_PATH)/qom/Makefile
+qom-obj-y = $(addprefix qom/, $(qom-y))
+qom-obj-twice-y = $(addprefix qom/, $(qom-twice-y))
+
+universal-obj-y += $(qom-obj-y)
+
+#######################################################################
+# oslib-obj-y is code depending on the OS (win32 vs posix)
+oslib-obj-y = osdep.o
+oslib-obj-$(CONFIG_WIN32) += oslib-win32.o qemu-thread-win32.o
+oslib-obj-$(CONFIG_POSIX) += oslib-posix.o qemu-thread-posix.o
+
+#######################################################################
+# coroutines
+coroutine-obj-y = qemu-coroutine.o qemu-coroutine-lock.o qemu-coroutine-io.o
+coroutine-obj-y += qemu-coroutine-sleep.o
+ifeq ($(CONFIG_UCONTEXT_COROUTINE),y)
+coroutine-obj-$(CONFIG_POSIX) += coroutine-ucontext.o
+else
+ifeq ($(CONFIG_SIGALTSTACK_COROUTINE),y)
+coroutine-obj-$(CONFIG_POSIX) += coroutine-sigaltstack.o
+else
+coroutine-obj-$(CONFIG_POSIX) += coroutine-gthread.o
+endif
+endif
+coroutine-obj-$(CONFIG_WIN32) += coroutine-win32.o
 
 #######################################################################
 # block-obj-y is code used by both qemu system emulation and qemu-img
 
-block-obj-y = async.o thread-pool.o
-block-obj-y += nbd.o block.o blockjob.o
-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
-block-obj-y += qemu-io-cmds.o
+block-obj-y = cutils.o cache-utils.o qemu-option.o module.o async.o
+block-obj-y += nbd.o block.o aio.o aes.o qemu-config.o qemu-progress.o qemu-sockets.o
+block-obj-y += $(coroutine-obj-y) $(qobject-obj-y) $(version-obj-y)
+block-obj-$(CONFIG_POSIX) += posix-aio-compat.o
+block-obj-$(CONFIG_LINUX_AIO) += linux-aio.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-$(CONFIG_COROUTINE_BACKEND).o
+block-nested-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o
+block-nested-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
+block-nested-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
+block-nested-y += qed-check.o
+block-nested-y += parallels.o nbd.o blkdebug.o sheepdog.o blkverify.o
+block-nested-y += stream.o
+block-nested-$(CONFIG_WIN32) += raw-win32.o
+block-nested-$(CONFIG_POSIX) += raw-posix.o
+block-nested-$(CONFIG_LIBISCSI) += iscsi.o
+block-nested-$(CONFIG_CURL) += curl.o
+block-nested-$(CONFIG_RBD) += rbd.o
+
+block-obj-y +=  $(addprefix block/, $(block-nested-y))
+
+net-obj-y = net.o
+net-nested-y = queue.o checksum.o util.o
+net-nested-y += socket.o
+net-nested-y += dump.o
+net-nested-$(CONFIG_POSIX) += tap.o
+net-nested-$(CONFIG_LINUX) += tap-linux.o
+net-nested-$(CONFIG_WIN32) += tap-win32.o
+net-nested-$(CONFIG_BSD) += tap-bsd.o
+net-nested-$(CONFIG_SOLARIS) += tap-solaris.o
+net-nested-$(CONFIG_AIX) += tap-aix.o
+net-nested-$(CONFIG_HAIKU) += tap-haiku.o
+net-nested-$(CONFIG_SLIRP) += slirp.o
+net-nested-$(CONFIG_VDE) += vde.o
+net-obj-y += $(addprefix net/, $(net-nested-y))
 
 ifeq ($(CONFIG_VIRTIO)$(CONFIG_VIRTFS)$(CONFIG_PCI),yyy)
 # Lots of the fsdev/9pcode is pulled in by vl.c via qemu_fsdev_add.
 # only pull in the actual virtio-9p device if we also enabled virtio.
 CONFIG_REALLY_VIRTFS=y
+fsdev-nested-y = qemu-fsdev.o virtio-9p-marshal.o
+else
+fsdev-nested-y = qemu-fsdev-dummy.o
 endif
-
-######################################################################
-# smartcard
-
-libcacard-y += libcacard/cac.o libcacard/event.o
-libcacard-y += libcacard/vcard.o libcacard/vreader.o
-libcacard-y += libcacard/vcard_emul_nss.o
-libcacard-y += libcacard/vcard_emul_type.o
-libcacard-y += libcacard/card_7816.o
-libcacard-y += libcacard/vcardt.o
+fsdev-obj-$(CONFIG_VIRTFS) += $(addprefix fsdev/, $(fsdev-nested-y))
 
 ######################################################################
 # Target independent part of system emulation. The long term path is to
 # suppress *all* target specific code in case of system emulation, i.e. a
 # single QEMU executable should support all CPUs and machines.
 
-ifeq ($(CONFIG_SOFTMMU),y)
-common-obj-y = $(block-obj-y) blockdev.o blockdev-nbd.o block/
-common-obj-y += net/
-common-obj-y += readline.o
-common-obj-y += qdev-monitor.o device-hotplug.o
+common-obj-y = $(block-obj-y) blockdev.o
+common-obj-y += $(net-obj-y)
+common-obj-y += $(qom-obj-twice-y)
+common-obj-$(CONFIG_LINUX) += $(fsdev-obj-$(CONFIG_LINUX))
+common-obj-y += readline.o console.o cursor.o
+common-obj-y += $(oslib-obj-y)
 common-obj-$(CONFIG_WIN32) += os-win32.o
 common-obj-$(CONFIG_POSIX) += os-posix.o
 
-common-obj-$(CONFIG_LINUX) += fsdev/
-
-common-obj-y += migration.o migration-tcp.o
-common-obj-$(CONFIG_RDMA) += migration-rdma.o
+common-obj-y += tcg-runtime.o host-utils.o main-loop.o
+common-obj-y += irq.o input.o
+common-obj-$(CONFIG_PTIMER) += ptimer.o
+common-obj-$(CONFIG_MAX7310) += max7310.o
+common-obj-$(CONFIG_WM8750) += wm8750.o
+common-obj-$(CONFIG_TWL92230) += twl92230.o
+common-obj-$(CONFIG_TSC2005) += tsc2005.o
+common-obj-$(CONFIG_LM832X) += lm832x.o
+common-obj-$(CONFIG_TMP105) += tmp105.o
+common-obj-$(CONFIG_STELLARIS_INPUT) += stellaris_input.o
+common-obj-$(CONFIG_SSD0303) += ssd0303.o
+common-obj-$(CONFIG_SSD0323) += ssd0323.o
+common-obj-$(CONFIG_ADS7846) += ads7846.o
+common-obj-$(CONFIG_MAX111X) += max111x.o
+common-obj-$(CONFIG_DS1338) += ds1338.o
+common-obj-y += i2c.o smbus.o smbus_eeprom.o
+common-obj-y += eeprom93xx.o
+common-obj-y += scsi-disk.o cdrom.o
+common-obj-y += scsi-generic.o scsi-bus.o
+common-obj-y += hid.o
+common-obj-y += usb/core.o usb/bus.o usb/desc.o usb/dev-hub.o
+common-obj-y += usb/host-$(HOST_USB).o
+common-obj-y += usb/dev-hid.o usb/dev-storage.o usb/dev-wacom.o
+common-obj-y += usb/dev-serial.o usb/dev-network.o usb/dev-audio.o
+common-obj-$(CONFIG_SSI) += ssi.o
+common-obj-$(CONFIG_SSI_SD) += ssi-sd.o
+common-obj-$(CONFIG_SD) += sd.o
+common-obj-y += bt.o bt-host.o bt-vhci.o bt-l2cap.o bt-sdp.o bt-hci.o bt-hid.o
+common-obj-y += bt-hci-csr.o usb/dev-bluetooth.o
+common-obj-y += buffered_file.o migration.o migration-tcp.o
 common-obj-y += qemu-char.o #aio.o
-common-obj-y += block-migration.o
-common-obj-y += page_cache.o xbzrle.o
+common-obj-y += msmouse.o ps2.o
+common-obj-y += qdev.o qdev-properties.o qdev-monitor.o
+common-obj-y += block-migration.o iohandler.o
+common-obj-y += pflib.o
+common-obj-y += bitmap.o bitops.o
 
+common-obj-$(CONFIG_BRLAPI) += baum.o
 common-obj-$(CONFIG_POSIX) += migration-exec.o migration-unix.o migration-fd.o
+common-obj-$(CONFIG_WIN32) += version.o
 
-common-obj-$(CONFIG_SPICE) += spice-qemu-char.o
+common-obj-$(CONFIG_SPICE) += ui/spice-core.o ui/spice-input.o ui/spice-display.o spice-qemu-char.o
 
-common-obj-y += audio/
-common-obj-y += hw/
+audio-obj-y = audio.o noaudio.o wavaudio.o mixeng.o
+audio-obj-$(CONFIG_SDL) += sdlaudio.o
+audio-obj-$(CONFIG_OSS) += ossaudio.o
+audio-obj-$(CONFIG_SPICE) += spiceaudio.o
+audio-obj-$(CONFIG_COREAUDIO) += coreaudio.o
+audio-obj-$(CONFIG_ALSA) += alsaaudio.o
+audio-obj-$(CONFIG_DSOUND) += dsoundaudio.o
+audio-obj-$(CONFIG_FMOD) += fmodaudio.o
+audio-obj-$(CONFIG_ESD) += esdaudio.o
+audio-obj-$(CONFIG_PA) += paaudio.o
+audio-obj-$(CONFIG_WINWAVE) += winwaveaudio.o
+audio-obj-$(CONFIG_AUDIO_PT_INT) += audio_pt_int.o
+audio-obj-$(CONFIG_AUDIO_WIN_INT) += audio_win_int.o
+audio-obj-y += wavcapture.o
+common-obj-y += $(addprefix audio/, $(audio-obj-y))
 
-common-obj-y += ui/
-common-obj-y += bt-host.o bt-vhci.o
+ui-obj-y += keymaps.o
+ui-obj-$(CONFIG_SDL) += sdl.o sdl_zoom.o x_keymap.o
+ui-obj-$(CONFIG_COCOA) += cocoa.o
+ui-obj-$(CONFIG_CURSES) += curses.o
+vnc-obj-y += vnc.o d3des.o
+vnc-obj-y += vnc-enc-zlib.o vnc-enc-hextile.o
+vnc-obj-y += vnc-enc-tight.o vnc-palette.o
+vnc-obj-y += vnc-enc-zrle.o
+vnc-obj-$(CONFIG_VNC_TLS) += vnc-tls.o vnc-auth-vencrypt.o
+vnc-obj-$(CONFIG_VNC_SASL) += vnc-auth-sasl.o
+ifdef CONFIG_VNC_THREAD
+vnc-obj-y += vnc-jobs-async.o
+else
+vnc-obj-y += vnc-jobs-sync.o
+endif
+common-obj-y += $(addprefix ui/, $(ui-obj-y))
+common-obj-$(CONFIG_VNC) += $(addprefix ui/, $(vnc-obj-y))
 
-common-obj-y += dma-helpers.o
-common-obj-y += vl.o
-common-obj-y += tpm.o
+common-obj-y += iov.o acl.o
+common-obj-$(CONFIG_POSIX) += compatfd.o
+common-obj-y += notify.o event_notifier.o
+common-obj-y += qemu-timer.o qemu-timer-common.o
 
-common-obj-$(CONFIG_SLIRP) += slirp/
+slirp-obj-y = cksum.o if.o ip_icmp.o ip_input.o ip_output.o
+slirp-obj-y += slirp.o mbuf.o misc.o sbuf.o socket.o tcp_input.o tcp_output.o
+slirp-obj-y += tcp_subr.o tcp_timer.o udp.o bootp.o tftp.o arp_table.o
+common-obj-$(CONFIG_SLIRP) += $(addprefix slirp/, $(slirp-obj-y))
 
-common-obj-y += backends/
+# xen backend driver support
+common-obj-$(CONFIG_XEN_BACKEND) += xen_backend.o xen_devconfig.o
+common-obj-$(CONFIG_XEN_BACKEND) += xen_console.o xenfb.o xen_disk.o xen_nic.o
 
-common-obj-$(CONFIG_SECCOMP) += qemu-seccomp.o
+######################################################################
+# libuser
 
-common-obj-$(CONFIG_SMARTCARD_NSS) += $(libcacard-y)
+user-obj-y =
+user-obj-y += envlist.o path.o
+user-obj-y += tcg-runtime.o host-utils.o
+user-obj-y += cutils.o cache-utils.o
+user-obj-y += module.o
+user-obj-y += qemu-user.o
+user-obj-y += $(trace-obj-y)
+user-obj-y += $(qom-obj-twice-y)
+
+######################################################################
+# libhw
+
+hw-obj-y =
+hw-obj-y += vl.o loader.o
+hw-obj-$(CONFIG_VIRTIO) += virtio-console.o
+hw-obj-y += usb/libhw.o
+hw-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.o
+hw-obj-y += fw_cfg.o
+hw-obj-$(CONFIG_PCI) += pci.o pci_bridge.o pci_bridge_dev.o
+hw-obj-$(CONFIG_PCI) += msix.o msi.o
+hw-obj-$(CONFIG_PCI) += shpc.o
+hw-obj-$(CONFIG_PCI) += slotid_cap.o
+hw-obj-$(CONFIG_PCI) += pci_host.o pcie_host.o
+hw-obj-$(CONFIG_PCI) += ioh3420.o xio3130_upstream.o xio3130_downstream.o
+hw-obj-y += watchdog.o
+hw-obj-$(CONFIG_ISA_MMIO) += isa_mmio.o
+hw-obj-$(CONFIG_ECC) += ecc.o
+hw-obj-$(CONFIG_NAND) += nand.o
+hw-obj-$(CONFIG_PFLASH_CFI01) += pflash_cfi01.o
+hw-obj-$(CONFIG_PFLASH_CFI02) += pflash_cfi02.o
+
+hw-obj-$(CONFIG_M48T59) += m48t59.o
+hw-obj-$(CONFIG_ESCC) += escc.o
+hw-obj-$(CONFIG_EMPTY_SLOT) += empty_slot.o
+
+hw-obj-$(CONFIG_SERIAL) += serial.o
+hw-obj-$(CONFIG_PARALLEL) += parallel.o
+hw-obj-$(CONFIG_I8254) += i8254_common.o i8254.o
+hw-obj-$(CONFIG_PCSPK) += pcspk.o
+hw-obj-$(CONFIG_PCKBD) += pckbd.o
+hw-obj-$(CONFIG_USB_UHCI) += usb/hcd-uhci.o
+hw-obj-$(CONFIG_USB_OHCI) += usb/hcd-ohci.o
+hw-obj-$(CONFIG_USB_EHCI) += usb/hcd-ehci.o
+hw-obj-$(CONFIG_USB_XHCI) += usb/hcd-xhci.o
+hw-obj-$(CONFIG_FDC) += fdc.o
+hw-obj-$(CONFIG_ACPI) += acpi.o acpi_piix4.o
+hw-obj-$(CONFIG_APM) += pm_smbus.o apm.o
+hw-obj-$(CONFIG_DMA) += dma.o
+hw-obj-$(CONFIG_I82374) += i82374.o
+hw-obj-$(CONFIG_HPET) += hpet.o
+hw-obj-$(CONFIG_APPLESMC) += applesmc.o
+hw-obj-$(CONFIG_SMARTCARD) += usb/dev-smartcard-reader.o ccid-card-passthru.o
+hw-obj-$(CONFIG_SMARTCARD_NSS) += ccid-card-emulated.o
+hw-obj-$(CONFIG_USB_REDIR) += usb/redirect.o
+hw-obj-$(CONFIG_I8259) += i8259_common.o i8259.o
+
+# PPC devices
+hw-obj-$(CONFIG_PREP_PCI) += prep_pci.o
+hw-obj-$(CONFIG_I82378) += i82378.o
+# Mac shared devices
+hw-obj-$(CONFIG_MACIO) += macio.o
+hw-obj-$(CONFIG_CUDA) += cuda.o
+hw-obj-$(CONFIG_ADB) += adb.o
+hw-obj-$(CONFIG_MAC_NVRAM) += mac_nvram.o
+hw-obj-$(CONFIG_MAC_DBDMA) += mac_dbdma.o
+# OldWorld PowerMac
+hw-obj-$(CONFIG_HEATHROW_PIC) += heathrow_pic.o
+hw-obj-$(CONFIG_GRACKLE_PCI) += grackle_pci.o
+# NewWorld PowerMac
+hw-obj-$(CONFIG_UNIN_PCI) += unin_pci.o
+hw-obj-$(CONFIG_DEC_PCI) += dec_pci.o
+# PowerPC E500 boards
+hw-obj-$(CONFIG_PPCE500_PCI) += ppce500_pci.o
+
+# MIPS devices
+hw-obj-$(CONFIG_PIIX4) += piix4.o
+hw-obj-$(CONFIG_G364FB) += g364fb.o
+hw-obj-$(CONFIG_JAZZ_LED) += jazz_led.o
+
+# PCI watchdog devices
+hw-obj-$(CONFIG_PCI) += wdt_i6300esb.o
+
+hw-obj-$(CONFIG_PCI) += pcie.o pcie_aer.o pcie_port.o
+
+# PCI network cards
+hw-obj-$(CONFIG_NE2000_PCI) += ne2000.o
+hw-obj-$(CONFIG_EEPRO100_PCI) += eepro100.o
+hw-obj-$(CONFIG_PCNET_PCI) += pcnet-pci.o
+hw-obj-$(CONFIG_PCNET_COMMON) += pcnet.o
+hw-obj-$(CONFIG_E1000_PCI) += e1000.o
+hw-obj-$(CONFIG_RTL8139_PCI) += rtl8139.o
+
+hw-obj-$(CONFIG_SMC91C111) += smc91c111.o
+hw-obj-$(CONFIG_LAN9118) += lan9118.o
+hw-obj-$(CONFIG_NE2000_ISA) += ne2000-isa.o
+hw-obj-$(CONFIG_OPENCORES_ETH) += opencores_eth.o
+
+# IDE
+hw-obj-$(CONFIG_IDE_CORE) += ide/core.o ide/atapi.o
+hw-obj-$(CONFIG_IDE_QDEV) += ide/qdev.o
+hw-obj-$(CONFIG_IDE_PCI) += ide/pci.o
+hw-obj-$(CONFIG_IDE_ISA) += ide/isa.o
+hw-obj-$(CONFIG_IDE_PIIX) += ide/piix.o
+hw-obj-$(CONFIG_IDE_CMD646) += ide/cmd646.o
+hw-obj-$(CONFIG_IDE_MACIO) += ide/macio.o
+hw-obj-$(CONFIG_IDE_VIA) += ide/via.o
+hw-obj-$(CONFIG_AHCI) += ide/ahci.o
+hw-obj-$(CONFIG_AHCI) += ide/ich.o
+
+# SCSI layer
+hw-obj-$(CONFIG_LSI_SCSI_PCI) += lsi53c895a.o
+hw-obj-$(CONFIG_ESP) += esp.o
+
+hw-obj-y += dma-helpers.o sysbus.o isa-bus.o
+hw-obj-y += qdev-addr.o
+
+# VGA
+hw-obj-$(CONFIG_VGA_PCI) += vga-pci.o
+hw-obj-$(CONFIG_VGA_ISA) += vga-isa.o
+hw-obj-$(CONFIG_VGA_ISA_MM) += vga-isa-mm.o
+hw-obj-$(CONFIG_VMWARE_VGA) += vmware_vga.o
+hw-obj-$(CONFIG_VMMOUSE) += vmmouse.o
+hw-obj-$(CONFIG_VGA_CIRRUS) += cirrus_vga.o
+
+hw-obj-$(CONFIG_RC4030) += rc4030.o
+hw-obj-$(CONFIG_DP8393X) += dp8393x.o
+hw-obj-$(CONFIG_DS1225Y) += ds1225y.o
+hw-obj-$(CONFIG_MIPSNET) += mipsnet.o
+
+hw-obj-y += qtest.o
+
+# Sound
+sound-obj-y =
+sound-obj-$(CONFIG_SB16) += sb16.o
+sound-obj-$(CONFIG_ES1370) += es1370.o
+sound-obj-$(CONFIG_AC97) += ac97.o
+sound-obj-$(CONFIG_ADLIB) += fmopl.o adlib.o
+sound-obj-$(CONFIG_GUS) += gus.o gusemu_hal.o gusemu_mixer.o
+sound-obj-$(CONFIG_CS4231A) += cs4231a.o
+sound-obj-$(CONFIG_HDA) += intel-hda.o hda-audio.o
+
+adlib.o fmopl.o: QEMU_CFLAGS += -DBUILD_Y8950=0
+hw-obj-$(CONFIG_SOUND) += $(sound-obj-y)
+
+9pfs-nested-$(CONFIG_VIRTFS)  = virtio-9p.o
+9pfs-nested-$(CONFIG_VIRTFS) += virtio-9p-local.o virtio-9p-xattr.o
+9pfs-nested-$(CONFIG_VIRTFS) += virtio-9p-xattr-user.o virtio-9p-posix-acl.o
+9pfs-nested-$(CONFIG_VIRTFS) += virtio-9p-coth.o cofs.o codir.o cofile.o
+9pfs-nested-$(CONFIG_VIRTFS) += coxattr.o virtio-9p-synth.o
+9pfs-nested-$(CONFIG_OPEN_BY_HANDLE) +=  virtio-9p-handle.o
+9pfs-nested-$(CONFIG_VIRTFS) += virtio-9p-proxy.o
+
+hw-obj-$(CONFIG_REALLY_VIRTFS) += $(addprefix 9pfs/, $(9pfs-nested-y))
+
+######################################################################
+# libdis
+# NOTE: the disassembler code is only needed for debugging
+
+libdis-y =
+libdis-$(CONFIG_ALPHA_DIS) += alpha-dis.o
+libdis-$(CONFIG_ARM_DIS) += arm-dis.o
+libdis-$(CONFIG_CRIS_DIS) += cris-dis.o
+libdis-$(CONFIG_HPPA_DIS) += hppa-dis.o
+libdis-$(CONFIG_I386_DIS) += i386-dis.o
+libdis-$(CONFIG_IA64_DIS) += ia64-dis.o
+libdis-$(CONFIG_M68K_DIS) += m68k-dis.o
+libdis-$(CONFIG_MICROBLAZE_DIS) += microblaze-dis.o
+libdis-$(CONFIG_MIPS_DIS) += mips-dis.o
+libdis-$(CONFIG_PPC_DIS) += ppc-dis.o
+libdis-$(CONFIG_S390_DIS) += s390-dis.o
+libdis-$(CONFIG_SH4_DIS) += sh4-dis.o
+libdis-$(CONFIG_SPARC_DIS) += sparc-dis.o
+libdis-$(CONFIG_LM32_DIS) += lm32-dis.o
+
+######################################################################
+# trace
+
+ifeq ($(TRACE_BACKEND),dtrace)
+TRACE_H_EXTRA_DEPS=trace-dtrace.h
+endif
+trace.h: trace.h-timestamp $(TRACE_H_EXTRA_DEPS)
+trace.h-timestamp: $(SRC_PATH)/trace-events $(BUILD_DIR)/config-host.mak
+	$(call quiet-command,$(TRACETOOL) \
+		--format=h \
+		--backend=$(TRACE_BACKEND) \
+		< $< > $@,"  GEN   trace.h")
+	@cmp -s $@ trace.h || cp $@ trace.h
+
+trace.c: trace.c-timestamp
+trace.c-timestamp: $(SRC_PATH)/trace-events $(BUILD_DIR)/config-host.mak
+	$(call quiet-command,$(TRACETOOL) \
+		--format=c \
+		--backend=$(TRACE_BACKEND) \
+		< $< > $@,"  GEN   trace.c")
+	@cmp -s $@ trace.c || cp $@ trace.c
+
+trace.o: trace.c $(GENERATED_HEADERS)
+
+trace-dtrace.h: trace-dtrace.dtrace
+	$(call quiet-command,dtrace -o $@ -h -s $<, "  GEN   trace-dtrace.h")
+
+# Normal practice is to name DTrace probe file with a '.d' extension
+# but that gets picked up by QEMU's Makefile as an external dependency
+# rule file. So we use '.dtrace' instead
+trace-dtrace.dtrace: trace-dtrace.dtrace-timestamp
+trace-dtrace.dtrace-timestamp: $(SRC_PATH)/trace-events $(BUILD_DIR)/config-host.mak
+	$(call quiet-command,$(TRACETOOL) \
+		--format=d \
+		--backend=$(TRACE_BACKEND) \
+		< $< > $@,"  GEN   trace-dtrace.dtrace")
+	@cmp -s $@ trace-dtrace.dtrace || cp $@ trace-dtrace.dtrace
+
+trace-dtrace.o: trace-dtrace.dtrace $(GENERATED_HEADERS)
+	$(call quiet-command,dtrace -o $@ -G -s $<, "  GEN   trace-dtrace.o")
+
+ifeq ($(LIBTOOL),)
+trace-dtrace.lo: trace-dtrace.dtrace
+	@echo "missing libtool. please install and rerun configure."; exit 1
+else
+trace-dtrace.lo: trace-dtrace.dtrace
+	$(call quiet-command,$(LIBTOOL) --mode=compile --tag=CC dtrace -o $@ -G -s $<, "  lt GEN trace-dtrace.o")
+endif
+
+trace/simple.o: trace/simple.c $(GENERATED_HEADERS)
+
+trace-obj-$(CONFIG_TRACE_DTRACE) += trace-dtrace.o
+ifneq ($(TRACE_BACKEND),dtrace)
+trace-obj-y = trace.o
+endif
+
+trace-nested-$(CONFIG_TRACE_DEFAULT) += default.o
+
+trace-nested-$(CONFIG_TRACE_SIMPLE) += simple.o
+trace-obj-$(CONFIG_TRACE_SIMPLE) += qemu-timer-common.o
+
+trace-nested-$(CONFIG_TRACE_STDERR) += stderr.o
+
+trace-nested-y += control.o
+
+trace-obj-y += $(addprefix trace/, $(trace-nested-y))
+
+$(trace-obj-y): $(GENERATED_HEADERS)
+
+######################################################################
+# smartcard
+
+libcacard-y = cac.o event.o vcard.o vreader.o vcard_emul_nss.o vcard_emul_type.o card_7816.o
 
 ######################################################################
 # qapi
 
-common-obj-y += qmp-marshal.o
+qapi-nested-y = qapi-visit-core.o qapi-dealloc-visitor.o qmp-input-visitor.o
+qapi-nested-y += qmp-output-visitor.o qmp-registry.o qmp-dispatch.o
+qapi-nested-y += string-input-visitor.o string-output-visitor.o
+qapi-obj-y = $(addprefix qapi/, $(qapi-nested-y))
+
+common-obj-y += qmp-marshal.o qapi-visit.o qapi-types.o
 common-obj-y += qmp.o hmp.o
-endif
 
-######################################################################
-# some qapi visitors are used by both system and user emulation:
-
-common-obj-y += qapi-visit.o qapi-types.o
-
-#######################################################################
-# Target-independent parts used in system and user emulation
-common-obj-y += qemu-log.o
-common-obj-y += tcg-runtime.o
-common-obj-y += hw/
-common-obj-y += qom/
-common-obj-y += disas/
+universal-obj-y += $(qapi-obj-y)
 
 ######################################################################
 # guest agent
 
-# 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-nested-y = commands.o guest-agent-command-state.o
+qga-nested-$(CONFIG_POSIX) += commands-posix.o channel-posix.o
+qga-nested-$(CONFIG_WIN32) += commands-win32.o channel-win32.o service-win32.o
+qga-obj-y = $(addprefix qga/, $(qga-nested-y))
+qga-obj-y += qemu-ga.o module.o
+qga-obj-$(CONFIG_WIN32) += oslib-win32.o
+qga-obj-$(CONFIG_POSIX) += oslib-posix.o qemu-sockets.o qemu-option.o
 
 vl.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
 
@@ -111,10 +473,3 @@ 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

@@ -1,28 +1,39 @@
 # -*- Mode: makefile -*-
 
-include ../config-host.mak
-include config-target.mak
-include config-devices.mak
-include $(SRC_PATH)/rules.mak
+GENERATED_HEADERS = config-target.h
+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)
 
-$(call set-vpath, $(SRC_PATH))
+include ../config-host.mak
+include config-devices.mak
+include config-target.mak
+include $(SRC_PATH)/rules.mak
+ifneq ($(HWDIR),)
+include $(HWDIR)/config.mak
+endif
+
+TARGET_PATH=$(SRC_PATH)/target-$(TARGET_BASE_ARCH)
+$(call set-vpath, $(SRC_PATH):$(TARGET_PATH):$(SRC_PATH)/hw)
 ifdef CONFIG_LINUX
 QEMU_CFLAGS += -I../linux-headers
 endif
-QEMU_CFLAGS += -I.. -I$(SRC_PATH)/target-$(TARGET_BASE_ARCH) -DNEED_CPU_H
+QEMU_CFLAGS += -I.. -I$(TARGET_PATH) -DNEED_CPU_H
+
+include $(SRC_PATH)/Makefile.objs
 
 QEMU_CFLAGS+=-I$(SRC_PATH)/include
 
 ifdef CONFIG_USER_ONLY
 # user emulator name
-QEMU_PROG=qemu-$(TARGET_NAME)
+QEMU_PROG=qemu-$(TARGET_ARCH2)
 else
 # system emulator name
-ifneq (,$(findstring -mwindows,$(libs_softmmu)))
+ifneq (,$(findstring -mwindows,$(LIBS)))
 # Terminate program name with a 'w' because the linker builds a windows executable.
-QEMU_PROGW=qemu-system-$(TARGET_NAME)w$(EXESUF)
+QEMU_PROGW=qemu-system-$(TARGET_ARCH2)w$(EXESUF)
 endif # windows executable
-QEMU_PROG=qemu-system-$(TARGET_NAME)$(EXESUF)
+QEMU_PROG=qemu-system-$(TARGET_ARCH2)$(EXESUF)
 endif
 
 PROGS=$(QEMU_PROG)
@@ -31,11 +42,15 @@ PROGS+=$(QEMU_PROGW)
 endif
 STPFILES=
 
+ifndef CONFIG_HAIKU
+LIBS+=-lm
+endif
+
 config-target.h: config-target.h-timestamp
 config-target.h-timestamp: config-target.mak
 
 ifdef CONFIG_TRACE_SYSTEMTAP
-stap: $(QEMU_PROG).stp-installed $(QEMU_PROG).stp
+stap: $(QEMU_PROG).stp
 
 ifdef CONFIG_USER_ONLY
 TARGET_TYPE=user
@@ -43,24 +58,14 @@ else
 TARGET_TYPE=system
 endif
 
-$(QEMU_PROG).stp-installed: $(SRC_PATH)/trace-events
-	$(call quiet-command,$(TRACETOOL) \
-		--format=stap \
-		--backend=$(TRACE_BACKEND) \
-		--binary=$(bindir)/$(QEMU_PROG) \
-		--target-name=$(TARGET_NAME) \
-		--target-type=$(TARGET_TYPE) \
-		< $< > $@,"  GEN   $(TARGET_DIR)$(QEMU_PROG).stp-installed")
-
 $(QEMU_PROG).stp: $(SRC_PATH)/trace-events
 	$(call quiet-command,$(TRACETOOL) \
 		--format=stap \
 		--backend=$(TRACE_BACKEND) \
-		--binary=$(realpath .)/$(QEMU_PROG) \
-		--target-name=$(TARGET_NAME) \
+		--binary=$(bindir)/$(QEMU_PROG) \
+		--target-arch=$(TARGET_ARCH) \
 		--target-type=$(TARGET_TYPE) \
-		< $< > $@,"  GEN   $(TARGET_DIR)$(QEMU_PROG).stp")
-
+		< $< > $@,"  GEN   $(QEMU_PROG).stp")
 else
 stap:
 endif
@@ -70,31 +75,80 @@ 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
-obj-y += tcg/tcg.o tcg/optimize.o
-obj-$(CONFIG_TCG_INTERPRETER) += tci.o
-obj-$(CONFIG_TCG_INTERPRETER) += disas/tci.o
-obj-y += fpu/softfloat.o
-obj-y += target-$(TARGET_BASE_ARCH)/
-obj-y += disas.o
-obj-$(CONFIG_GDBSTUB_XML) += gdbstub-xml.o
-obj-$(CONFIG_NO_KVM) += kvm-stub.o
+libobj-y = exec.o translate-all.o cpu-exec.o translate.o
+libobj-y += tcg/tcg.o tcg/optimize.o
+libobj-$(CONFIG_TCG_INTERPRETER) += tci.o
+libobj-y += fpu/softfloat.o
+ifneq ($(TARGET_BASE_ARCH), sparc)
+ifneq ($(TARGET_BASE_ARCH), alpha)
+libobj-y += op_helper.o
+endif
+endif
+libobj-y += helper.o
+ifneq ($(TARGET_BASE_ARCH), ppc)
+libobj-y += cpu.o
+endif
+libobj-$(TARGET_SPARC64) += vis_helper.o
+libobj-$(CONFIG_NEED_MMU) += mmu.o
+libobj-$(TARGET_ARM) += neon_helper.o iwmmxt_helper.o
+ifeq ($(TARGET_BASE_ARCH), sparc)
+libobj-y += fop_helper.o cc_helper.o win_helper.o mmu_helper.o ldst_helper.o
+endif
+libobj-$(TARGET_SPARC) += int32_helper.o
+libobj-$(TARGET_SPARC64) += int64_helper.o
+libobj-$(TARGET_ALPHA) += int_helper.o fpu_helper.o sys_helper.o mem_helper.o
+
+libobj-y += disas.o
+libobj-$(CONFIG_TCI_DIS) += tci-dis.o
+
+tci-dis.o: QEMU_CFLAGS += -I$(SRC_PATH)/tcg -I$(SRC_PATH)/tcg/tci
+
+$(libobj-y): $(GENERATED_HEADERS)
+
+# HELPER_CFLAGS is used for all the legacy code compiled with static register
+# variables
+ifneq ($(TARGET_BASE_ARCH), sparc)
+op_helper.o: QEMU_CFLAGS += $(HELPER_CFLAGS)
+endif
+user-exec.o: QEMU_CFLAGS += $(HELPER_CFLAGS)
+
+# Note: this is a workaround. The real fix is to avoid compiling
+# cpu_signal_handler() in user-exec.c.
+signal.o: QEMU_CFLAGS += $(HELPER_CFLAGS)
 
 #########################################################
 # Linux user emulator target
 
 ifdef CONFIG_LINUX_USER
 
-QEMU_CFLAGS+=-I$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR) -I$(SRC_PATH)/linux-user
+$(call set-vpath, $(SRC_PATH)/linux-user:$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR))
 
-obj-y += linux-user/
-obj-y += gdbstub.o thunk.o user-exec.o
+QEMU_CFLAGS+=-I$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR) -I$(SRC_PATH)/linux-user
+obj-y = main.o syscall.o strace.o mmap.o signal.o thunk.o \
+      elfload.o linuxload.o uaccess.o gdbstub.o cpu-uname.o \
+      user-exec.o $(oslib-obj-y)
+
+obj-$(TARGET_HAS_BFLT) += flatload.o
+
+obj-$(TARGET_I386) += vm86.o
+
+obj-i386-y += ioport-user.o
+
+nwfpe-obj-y = fpa11.o fpa11_cpdo.o fpa11_cpdt.o fpa11_cprt.o fpopcode.o
+nwfpe-obj-y += single_cpdo.o double_cpdo.o extended_cpdo.o
+obj-arm-y +=  $(addprefix nwfpe/, $(nwfpe-obj-y))
+obj-arm-y += arm-semi.o
+
+obj-m68k-y += m68k-sim.o m68k-semi.o
+
+$(obj-y) $(obj-$(TARGET_BASE_ARCH)-y): $(GENERATED_HEADERS)
+
+obj-y += $(addprefix ../, $(universal-obj-y))
+obj-y += $(addprefix ../libuser/, $(user-obj-y))
+obj-y += $(addprefix ../libdis-user/, $(libdis-y))
+obj-y += $(libobj-y)
 
 endif #CONFIG_LINUX_USER
 
@@ -103,66 +157,269 @@ endif #CONFIG_LINUX_USER
 
 ifdef CONFIG_BSD_USER
 
-QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ABI_DIR)
+$(call set-vpath, $(SRC_PATH)/bsd-user)
 
-obj-y += bsd-user/
-obj-y += gdbstub.o user-exec.o
+QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ARCH)
+
+obj-y = main.o bsdload.o elfload.o mmap.o signal.o strace.o syscall.o \
+        gdbstub.o uaccess.o user-exec.o
+
+obj-i386-y += ioport-user.o
+
+$(obj-y) $(obj-$(TARGET_BASE_ARCH)-y): $(GENERATED_HEADERS)
+
+obj-y += $(addprefix ../, $(universal-obj-y))
+obj-y += $(addprefix ../libuser/, $(user-obj-y))
+obj-y += $(addprefix ../libdis-user/, $(libdis-y))
+obj-y += $(libobj-y)
 
 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
-obj-y += qtest.o
-obj-y += hw/
-obj-$(CONFIG_FDT) += device_tree.o
-obj-$(CONFIG_KVM) += kvm-all.o
+
+obj-y = arch_init.o cpus.o monitor.o machine.o gdbstub.o balloon.o ioport.o
+# virtio has to be here due to weird dependency between PCI and virtio-net.
+# need to fix this properly
+obj-$(CONFIG_NO_PCI) += pci-stub.o
+obj-$(CONFIG_VIRTIO) += virtio.o virtio-blk.o virtio-balloon.o virtio-net.o virtio-serial-bus.o
+obj-$(CONFIG_VIRTIO) += virtio-scsi.o
+obj-y += vhost_net.o
+obj-$(CONFIG_VHOST_NET) += vhost.o
+obj-$(CONFIG_REALLY_VIRTFS) += 9pfs/virtio-9p-device.o
+obj-$(CONFIG_KVM) += kvm.o kvm-all.o
+obj-$(CONFIG_NO_KVM) += kvm-stub.o
+obj-$(CONFIG_VGA) += vga.o
 obj-y += memory.o savevm.o cputlb.o
-obj-y += memory_mapping.o
-obj-y += dump.o
-LIBS+=$(libs_softmmu)
+LIBS+=-lz
+
+obj-i386-$(CONFIG_KVM) += hyperv.o
+
+QEMU_CFLAGS += $(VNC_TLS_CFLAGS)
+QEMU_CFLAGS += $(VNC_SASL_CFLAGS)
+QEMU_CFLAGS += $(VNC_JPEG_CFLAGS)
+QEMU_CFLAGS += $(VNC_PNG_CFLAGS)
 
 # xen support
-obj-$(CONFIG_XEN) += xen-all.o xen-mapcache.o
+obj-$(CONFIG_XEN) += xen-all.o xen_machine_pv.o xen_domainbuild.o xen-mapcache.o
 obj-$(CONFIG_NO_XEN) += xen-stub.o
 
-# Hardware support
-ifeq ($(TARGET_NAME), sparc64)
-obj-y += hw/sparc64/
-else
-obj-y += hw/$(TARGET_BASE_ARCH)/
+obj-i386-$(CONFIG_XEN) += xen_platform.o xen_apic.o
+
+# Inter-VM PCI shared memory
+CONFIG_IVSHMEM =
+ifeq ($(CONFIG_KVM), y)
+  ifeq ($(CONFIG_PCI), y)
+    CONFIG_IVSHMEM = y
+  endif
 endif
+obj-$(CONFIG_IVSHMEM) += ivshmem.o
+
+# Generic hotplugging
+obj-y += device-hotplug.o
+
+# Hardware support
+obj-i386-y += mc146818rtc.o pc.o
+obj-i386-y += apic_common.o apic.o kvmvapic.o
+obj-i386-y += sga.o ioapic_common.o ioapic.o piix_pci.o
+obj-i386-y += vmport.o
+obj-i386-y += pci-hotplug.o smbios.o wdt_ib700.o
+obj-i386-y += debugcon.o multiboot.o
+obj-i386-y += pc_piix.o
+obj-i386-y += pc_sysfw.o
+obj-i386-$(CONFIG_KVM) += kvm/clock.o kvm/apic.o kvm/i8259.o kvm/ioapic.o kvm/i8254.o
+obj-i386-$(CONFIG_SPICE) += qxl.o qxl-logger.o qxl-render.o
+
+# shared objects
+obj-ppc-y = ppc.o ppc_booke.o
+# PREP target
+obj-ppc-y += mc146818rtc.o
+obj-ppc-y += ppc_prep.o
+# OldWorld PowerMac
+obj-ppc-y += ppc_oldworld.o
+# NewWorld PowerMac
+obj-ppc-y += ppc_newworld.o
+# IBM pSeries (sPAPR)
+obj-ppc-$(CONFIG_PSERIES) += spapr.o spapr_hcall.o spapr_rtas.o spapr_vio.o
+obj-ppc-$(CONFIG_PSERIES) += xics.o spapr_vty.o spapr_llan.o spapr_vscsi.o
+obj-ppc-$(CONFIG_PSERIES) += spapr_pci.o device-hotplug.o pci-hotplug.o
+# PowerPC 4xx boards
+obj-ppc-y += ppc4xx_devs.o ppc4xx_pci.o ppc405_uc.o ppc405_boards.o
+obj-ppc-y += ppc440_bamboo.o
+# PowerPC E500 boards
+obj-ppc-y += ppce500_mpc8544ds.o mpc8544_guts.o ppce500_spin.o
+# PowerPC 440 Xilinx ML507 reference board.
+obj-ppc-y += virtex_ml507.o
+obj-ppc-$(CONFIG_KVM) += kvm_ppc.o
+obj-ppc-$(CONFIG_FDT) += device_tree.o
+# PowerPC OpenPIC
+obj-ppc-y += openpic.o
+
+# Xilinx PPC peripherals
+obj-ppc-y += xilinx_intc.o
+obj-ppc-y += xilinx_timer.o
+obj-ppc-y += xilinx_uartlite.o
+obj-ppc-y += xilinx_ethlite.o
+
+# LM32 boards
+obj-lm32-y += lm32_boards.o
+obj-lm32-y += milkymist.o
+
+# LM32 peripherals
+obj-lm32-y += lm32_pic.o
+obj-lm32-y += lm32_juart.o
+obj-lm32-y += lm32_timer.o
+obj-lm32-y += lm32_uart.o
+obj-lm32-y += lm32_sys.o
+obj-lm32-y += milkymist-ac97.o
+obj-lm32-y += milkymist-hpdmc.o
+obj-lm32-y += milkymist-memcard.o
+obj-lm32-y += milkymist-minimac2.o
+obj-lm32-y += milkymist-pfpu.o
+obj-lm32-y += milkymist-softusb.o
+obj-lm32-y += milkymist-sysctl.o
+obj-lm32-$(CONFIG_OPENGL) += milkymist-tmu2.o
+obj-lm32-y += milkymist-uart.o
+obj-lm32-y += milkymist-vgafb.o
+obj-lm32-y += framebuffer.o
+
+obj-mips-y = mips_r4k.o mips_jazz.o mips_malta.o mips_mipssim.o
+obj-mips-y += mips_addr.o mips_timer.o mips_int.o
+obj-mips-y += gt64xxx.o mc146818rtc.o
+obj-mips-$(CONFIG_FULONG) += bonito.o vt82c686.o mips_fulong2e.o
+
+obj-microblaze-y = petalogix_s3adsp1800_mmu.o
+obj-microblaze-y += petalogix_ml605_mmu.o
+obj-microblaze-y += microblaze_boot.o
+
+obj-microblaze-y += microblaze_pic_cpu.o
+obj-microblaze-y += xilinx_intc.o
+obj-microblaze-y += xilinx_timer.o
+obj-microblaze-y += xilinx_uartlite.o
+obj-microblaze-y += xilinx_ethlite.o
+obj-microblaze-y += xilinx_axidma.o
+obj-microblaze-y += xilinx_axienet.o
+
+obj-microblaze-$(CONFIG_FDT) += device_tree.o
+
+# Boards
+obj-cris-y = cris_pic_cpu.o
+obj-cris-y += cris-boot.o
+obj-cris-y += axis_dev88.o
+
+# IO blocks
+obj-cris-y += etraxfs_dma.o
+obj-cris-y += etraxfs_pic.o
+obj-cris-y += etraxfs_eth.o
+obj-cris-y += etraxfs_timer.o
+obj-cris-y += etraxfs_ser.o
+
+ifeq ($(TARGET_ARCH), sparc64)
+obj-sparc-y = sun4u.o apb_pci.o
+obj-sparc-y += mc146818rtc.o
+else
+obj-sparc-y = sun4m.o lance.o tcx.o sun4m_iommu.o slavio_intctl.o
+obj-sparc-y += slavio_timer.o slavio_misc.o sparc32_dma.o
+obj-sparc-y += cs4231.o eccmemctl.o sbi.o sun4c_intctl.o leon3.o
+
+# GRLIB
+obj-sparc-y += grlib_gptimer.o grlib_irqmp.o grlib_apbuart.o
+endif
+
+obj-arm-y = integratorcp.o versatilepb.o arm_pic.o arm_timer.o
+obj-arm-y += arm_boot.o pl011.o pl031.o pl050.o pl080.o pl110.o pl181.o pl190.o
+obj-arm-y += versatile_pci.o
+obj-arm-y += versatile_i2c.o
+obj-arm-y += cadence_uart.o
+obj-arm-y += cadence_ttc.o
+obj-arm-y += cadence_gem.o
+obj-arm-y += xilinx_zynq.o zynq_slcr.o
+obj-arm-y += arm_gic.o
+obj-arm-y += realview_gic.o realview.o arm_sysctl.o arm11mpcore.o a9mpcore.o
+obj-arm-y += exynos4210_gic.o exynos4210_combiner.o exynos4210.o
+obj-arm-y += exynos4_boards.o exynos4210_uart.o exynos4210_pwm.o
+obj-arm-y += exynos4210_pmu.o exynos4210_mct.o exynos4210_fimd.o
+obj-arm-y += arm_l2x0.o
+obj-arm-y += arm_mptimer.o a15mpcore.o
+obj-arm-y += armv7m.o armv7m_nvic.o stellaris.o pl022.o stellaris_enet.o
+obj-arm-y += highbank.o
+obj-arm-y += pl061.o
+obj-arm-y += xgmac.o
+obj-arm-y += arm-semi.o
+obj-arm-y += pxa2xx.o pxa2xx_pic.o pxa2xx_gpio.o pxa2xx_timer.o pxa2xx_dma.o
+obj-arm-y += pxa2xx_lcd.o pxa2xx_mmci.o pxa2xx_pcmcia.o pxa2xx_keypad.o
+obj-arm-y += gumstix.o
+obj-arm-y += zaurus.o ide/microdrive.o spitz.o tosa.o tc6393xb.o
+obj-arm-y += omap1.o omap_lcdc.o omap_dma.o omap_clk.o omap_mmc.o omap_i2c.o \
+		omap_gpio.o omap_intc.o omap_uart.o
+obj-arm-y += omap2.o omap_dss.o soc_dma.o omap_gptimer.o omap_synctimer.o \
+		omap_gpmc.o omap_sdrc.o omap_spi.o omap_tap.o omap_l4.o
+obj-arm-y += omap_sx1.o palm.o tsc210x.o
+obj-arm-y += nseries.o blizzard.o onenand.o cbus.o tusb6010.o usb/hcd-musb.o
+obj-arm-y += mst_fpga.o mainstone.o
+obj-arm-y += z2.o
+obj-arm-y += musicpal.o bitbang_i2c.o marvell_88w8618_audio.o
+obj-arm-y += framebuffer.o
+obj-arm-y += vexpress.o
+obj-arm-y += strongarm.o
+obj-arm-y += collie.o
+obj-arm-y += pl041.o lm4549.o
+obj-arm-$(CONFIG_FDT) += device_tree.o
+
+obj-sh4-y = shix.o r2d.o sh7750.o sh7750_regnames.o tc58128.o
+obj-sh4-y += sh_timer.o sh_serial.o sh_intc.o sh_pci.o sm501.o
+obj-sh4-y += ide/mmio.o
+
+obj-m68k-y = an5206.o mcf5206.o mcf_uart.o mcf_intc.o mcf5208.o mcf_fec.o
+obj-m68k-y += m68k-semi.o dummy_m68k.o
+
+obj-s390x-y = s390-virtio-bus.o s390-virtio.o
+
+obj-alpha-y = mc146818rtc.o
+obj-alpha-y += alpha_pci.o alpha_dp264.o alpha_typhoon.o
+
+obj-xtensa-y += xtensa_pic.o
+obj-xtensa-y += xtensa_sim.o
+obj-xtensa-y += xtensa_lx60.o
+obj-xtensa-y += xtensa-semi.o
+obj-xtensa-y += core-dc232b.o
+obj-xtensa-y += core-dc233c.o
+obj-xtensa-y += core-fsf.o
 
 main.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
 
-GENERATED_HEADERS += hmp-commands.h qmp-commands-old.h
+monitor.o: hmp-commands.h qmp-commands-old.h
+
+$(obj-y) $(obj-$(TARGET_BASE_ARCH)-y): $(GENERATED_HEADERS)
+
+obj-y += $(addprefix ../, $(universal-obj-y))
+obj-y += $(addprefix ../, $(common-obj-y))
+obj-y += $(addprefix ../libdis/, $(libdis-y))
+obj-y += $(libobj-y)
+obj-y += $(addprefix $(HWDIR)/, $(hw-obj-y))
+obj-y += $(addprefix ../, $(trace-obj-y))
 
 endif # CONFIG_SOFTMMU
 
-# Workaround for http://gcc.gnu.org/PR55489, see configure.
-%/translate.o: QEMU_CFLAGS += $(TRANSLATE_OPT_CFLAGS)
+ifndef CONFIG_LINUX_USER
+ifndef CONFIG_BSD_USER
+# libcacard needs qemu-thread support, and besides is only needed by devices
+# so not requires with linux-user / bsd-user targets
+obj-$(CONFIG_SMARTCARD_NSS) += $(addprefix ../libcacard/, $(libcacard-y))
+endif # CONFIG_BSD_USER
+endif # CONFIG_LINUX_USER
 
-nested-vars += obj-y
-
-# This resolves all nested paths, so it must come last
-include $(SRC_PATH)/Makefile.objs
-
-all-obj-y = $(obj-y)
-all-obj-y += $(addprefix ../, $(common-obj-y))
-
-ifndef CONFIG_HAIKU
-LIBS+=-lm
-endif
+obj-$(CONFIG_GDBSTUB_XML) += gdbstub-xml.o
 
 ifdef QEMU_PROGW
 # The linker builds a windows executable. Make also a console executable.
-$(QEMU_PROGW): $(all-obj-y) ../libqemuutil.a ../libqemustub.a
+$(QEMU_PROGW): $(obj-y) $(obj-$(TARGET_BASE_ARCH)-y)
 	$(call LINK,$^)
 $(QEMU_PROG): $(QEMU_PROGW)
 	$(call quiet-command,$(OBJCOPY) --subsystem console $(QEMU_PROGW) $(QEMU_PROG),"  GEN   $(TARGET_DIR)$(QEMU_PROG)")
 else
-$(QEMU_PROG): $(all-obj-y) ../libqemuutil.a ../libqemustub.a
+$(QEMU_PROG): $(obj-y) $(obj-$(TARGET_BASE_ARCH)-y)
 	$(call LINK,$^)
 endif
 
@@ -176,8 +433,8 @@ qmp-commands-old.h: $(SRC_PATH)/qmp-commands.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $(TARGET_DIR)$@")
 
 clean:
-	rm -f *.a *~ $(PROGS)
-	rm -f $(shell find . -name '*.[od]')
+	rm -f *.o *.a *~ $(PROGS) nwfpe/*.o fpu/*.o
+	rm -f *.d */*.d tcg/*.o ide/*.o 9pfs/*.o kvm/*.o
 	rm -f hmp-commands.h qmp-commands-old.h gdbstub-xml.c
 ifdef CONFIG_TRACE_SYSTEMTAP
 	rm -f *.stp
@@ -192,8 +449,8 @@ endif
 endif
 ifdef CONFIG_TRACE_SYSTEMTAP
 	$(INSTALL_DIR) "$(DESTDIR)$(qemu_datadir)/../systemtap/tapset"
-	$(INSTALL_DATA) $(QEMU_PROG).stp-installed "$(DESTDIR)$(qemu_datadir)/../systemtap/tapset/$(QEMU_PROG).stp"
+	$(INSTALL_DATA) $(QEMU_PROG).stp "$(DESTDIR)$(qemu_datadir)/../systemtap/tapset"
 endif
 
-GENERATED_HEADERS += config-target.h
-Makefile: $(GENERATED_HEADERS)
+# Include automatically generated dependency files
+-include $(wildcard *.d */*.d)

Makefile.user

@@ -0,0 +1,26 @@
+# Makefile for qemu target independent user files.
+
+include ../config-host.mak
+include $(SRC_PATH)/rules.mak
+-include config.mak
+
+.PHONY: all
+
+$(call set-vpath, $(SRC_PATH))
+
+QEMU_CFLAGS+=-I..
+QEMU_CFLAGS += -I$(SRC_PATH)/include
+
+include $(SRC_PATH)/Makefile.objs
+
+all: $(user-obj-y)
+# Dummy command so that make thinks it has done something
+	@true
+
+clean:
+	for d in . trace; do \
+	rm -f $$d/*.o $$d/*.d $$d/*.a $$d/*~; \
+	done
+
+# Include automatically generated dependency files
+-include $(wildcard *.d */*.d)

QMP/qemu-ga-client

@@ -1,299 +0,0 @@
-#!/usr/bin/python
-
-# QEMU Guest Agent Client
-#
-# Copyright (C) 2012 Ryota Ozaki <ozaki.ryota@gmail.com>
-#
-# This work is licensed under the terms of the GNU GPL, version 2.  See
-# the COPYING file in the top-level directory.
-#
-# Usage:
-#
-# Start QEMU with:
-#
-# # qemu [...] -chardev socket,path=/tmp/qga.sock,server,nowait,id=qga0 \
-#   -device virtio-serial -device virtserialport,chardev=qga0,name=org.qemu.guest_agent.0
-#
-# Run the script:
-#
-# $ qemu-ga-client --address=/tmp/qga.sock <command> [args...]
-#
-# or
-#
-# $ export QGA_CLIENT_ADDRESS=/tmp/qga.sock
-# $ qemu-ga-client <command> [args...]
-#
-# For example:
-#
-# $ qemu-ga-client cat /etc/resolv.conf
-# # Generated by NetworkManager
-# nameserver 10.0.2.3
-# $ qemu-ga-client fsfreeze status
-# thawed
-# $ qemu-ga-client fsfreeze freeze
-# 2 filesystems frozen
-#
-# See also: http://wiki.qemu.org/Features/QAPI/GuestAgent
-#
-
-import base64
-import random
-
-import qmp
-
-
-class QemuGuestAgent(qmp.QEMUMonitorProtocol):
-    def __getattr__(self, name):
-        def wrapper(**kwds):
-            return self.command('guest-' + name.replace('_', '-'), **kwds)
-        return wrapper
-
-
-class QemuGuestAgentClient:
-    error = QemuGuestAgent.error
-
-    def __init__(self, address):
-        self.qga = QemuGuestAgent(address)
-        self.qga.connect(negotiate=False)
-
-    def sync(self, timeout=3):
-        # Avoid being blocked forever
-        if not self.ping(timeout):
-            raise EnvironmentError('Agent seems not alive')
-        uid = random.randint(0, (1 << 32) - 1)
-        while True:
-            ret = self.qga.sync(id=uid)
-            if isinstance(ret, int) and int(ret) == uid:
-                break
-
-    def __file_read_all(self, handle):
-        eof = False
-        data = ''
-        while not eof:
-            ret = self.qga.file_read(handle=handle, count=1024)
-            _data = base64.b64decode(ret['buf-b64'])
-            data += _data
-            eof = ret['eof']
-        return data
-
-    def read(self, path):
-        handle = self.qga.file_open(path=path)
-        try:
-            data = self.__file_read_all(handle)
-        finally:
-            self.qga.file_close(handle=handle)
-        return data
-
-    def info(self):
-        info = self.qga.info()
-
-        msgs = []
-        msgs.append('version: ' + info['version'])
-        msgs.append('supported_commands:')
-        enabled = [c['name'] for c in info['supported_commands'] if c['enabled']]
-        msgs.append('\tenabled: ' + ', '.join(enabled))
-        disabled = [c['name'] for c in info['supported_commands'] if not c['enabled']]
-        msgs.append('\tdisabled: ' + ', '.join(disabled))
-
-        return '\n'.join(msgs)
-
-    def __gen_ipv4_netmask(self, prefixlen):
-        mask = int('1' * prefixlen + '0' * (32 - prefixlen), 2)
-        return '.'.join([str(mask >> 24),
-                         str((mask >> 16) & 0xff),
-                         str((mask >> 8) & 0xff),
-                         str(mask & 0xff)])
-
-    def ifconfig(self):
-        nifs = self.qga.network_get_interfaces()
-
-        msgs = []
-        for nif in nifs:
-            msgs.append(nif['name'] + ':')
-            if 'ip-addresses' in nif:
-                for ipaddr in nif['ip-addresses']:
-                    if ipaddr['ip-address-type'] == 'ipv4':
-                        addr = ipaddr['ip-address']
-                        mask = self.__gen_ipv4_netmask(int(ipaddr['prefix']))
-                        msgs.append("\tinet %s  netmask %s" % (addr, mask))
-                    elif ipaddr['ip-address-type'] == 'ipv6':
-                        addr = ipaddr['ip-address']
-                        prefix = ipaddr['prefix']
-                        msgs.append("\tinet6 %s  prefixlen %s" % (addr, prefix))
-            if nif['hardware-address'] != '00:00:00:00:00:00':
-                msgs.append("\tether " + nif['hardware-address'])
-
-        return '\n'.join(msgs)
-
-    def ping(self, timeout):
-        self.qga.settimeout(timeout)
-        try:
-            self.qga.ping()
-        except self.qga.timeout:
-            return False
-        return True
-
-    def fsfreeze(self, cmd):
-        if cmd not in ['status', 'freeze', 'thaw']:
-            raise StandardError('Invalid command: ' + cmd)
-
-        return getattr(self.qga, 'fsfreeze' + '_' + cmd)()
-
-    def fstrim(self, minimum=0):
-        return getattr(self.qga, 'fstrim')(minimum=minimum)
-
-    def suspend(self, mode):
-        if mode not in ['disk', 'ram', 'hybrid']:
-            raise StandardError('Invalid mode: ' + mode)
-
-        try:
-            getattr(self.qga, 'suspend' + '_' + mode)()
-            # On error exception will raise
-        except self.qga.timeout:
-            # On success command will timed out
-            return
-
-    def shutdown(self, mode='powerdown'):
-        if mode not in ['powerdown', 'halt', 'reboot']:
-            raise StandardError('Invalid mode: ' + mode)
-
-        try:
-            self.qga.shutdown(mode=mode)
-        except self.qga.timeout:
-            return
-
-
-def _cmd_cat(client, args):
-    if len(args) != 1:
-        print('Invalid argument')
-        print('Usage: cat <file>')
-        sys.exit(1)
-    print(client.read(args[0]))
-
-
-def _cmd_fsfreeze(client, args):
-    usage = 'Usage: fsfreeze status|freeze|thaw'
-    if len(args) != 1:
-        print('Invalid argument')
-        print(usage)
-        sys.exit(1)
-    if args[0] not in ['status', 'freeze', 'thaw']:
-        print('Invalid command: ' + args[0])
-        print(usage)
-        sys.exit(1)
-    cmd = args[0]
-    ret = client.fsfreeze(cmd)
-    if cmd == 'status':
-        print(ret)
-    elif cmd == 'freeze':
-        print("%d filesystems frozen" % ret)
-    else:
-        print("%d filesystems thawed" % ret)
-
-
-def _cmd_fstrim(client, args):
-    if len(args) == 0:
-        minimum = 0
-    else:
-        minimum = int(args[0])
-    print(client.fstrim(minimum))
-
-
-def _cmd_ifconfig(client, args):
-    print(client.ifconfig())
-
-
-def _cmd_info(client, args):
-    print(client.info())
-
-
-def _cmd_ping(client, args):
-    if len(args) == 0:
-        timeout = 3
-    else:
-        timeout = float(args[0])
-    alive = client.ping(timeout)
-    if not alive:
-        print("Not responded in %s sec" % args[0])
-        sys.exit(1)
-
-
-def _cmd_suspend(client, args):
-    usage = 'Usage: suspend disk|ram|hybrid'
-    if len(args) != 1:
-        print('Less argument')
-        print(usage)
-        sys.exit(1)
-    if args[0] not in ['disk', 'ram', 'hybrid']:
-        print('Invalid command: ' + args[0])
-        print(usage)
-        sys.exit(1)
-    client.suspend(args[0])
-
-
-def _cmd_shutdown(client, args):
-    client.shutdown()
-_cmd_powerdown = _cmd_shutdown
-
-
-def _cmd_halt(client, args):
-    client.shutdown('halt')
-
-
-def _cmd_reboot(client, args):
-    client.shutdown('reboot')
-
-
-commands = [m.replace('_cmd_', '') for m in dir() if '_cmd_' in m]
-
-
-def main(address, cmd, args):
-    if not os.path.exists(address):
-        print('%s not found' % address)
-        sys.exit(1)
-
-    if cmd not in commands:
-        print('Invalid command: ' + cmd)
-        print('Available commands: ' + ', '.join(commands))
-        sys.exit(1)
-
-    try:
-        client = QemuGuestAgentClient(address)
-    except QemuGuestAgent.error, e:
-        import errno
-
-        print(e)
-        if e.errno == errno.ECONNREFUSED:
-            print('Hint: qemu is not running?')
-        sys.exit(1)
-
-    if cmd != 'ping':
-        client.sync()
-
-    globals()['_cmd_' + cmd](client, args)
-
-
-if __name__ == '__main__':
-    import sys
-    import os
-    import optparse
-
-    address = os.environ['QGA_CLIENT_ADDRESS'] if 'QGA_CLIENT_ADDRESS' in os.environ else None
-
-    usage = "%prog [--address=<unix_path>|<ipv4_address>] <command> [args...]\n"
-    usage += '<command>: ' + ', '.join(commands)
-    parser = optparse.OptionParser(usage=usage)
-    parser.add_option('--address', action='store', type='string',
-                      default=address, help='Specify a ip:port pair or a unix socket path')
-    options, args = parser.parse_args()
-
-    address = options.address
-    if address is None:
-        parser.error('address is not specified')
-        sys.exit(1)
-
-    if len(args) == 0:
-        parser.error('Less argument')
-        sys.exit(1)
-
-    main(address, args[0], args[1:])

QMP/qmp-events.txt

@@ -1,23 +1,6 @@
                    QEMU Monitor Protocol Events
                    ============================
 
-BALLOON_CHANGE
---------------
-
-Emitted when the guest changes the actual BALLOON level. This
-value is equivalent to the 'actual' field return by the
-'query-balloon' command
-
-Data:
-
-- "actual": actual level of the guest memory balloon in bytes (json-number)
-
-Example:
-
-{ "event": "BALLOON_CHANGE",
-    "data": { "actual": 944766976 },
-    "timestamp": { "seconds": 1267020223, "microseconds": 435656 } }
-
 BLOCK_IO_ERROR
 --------------
 
@@ -43,117 +26,6 @@ Example:
 Note: If action is "stop", a STOP event will eventually follow the
 BLOCK_IO_ERROR event.
 
-BLOCK_JOB_CANCELLED
--------------------
-
-Emitted when a block job has been cancelled.
-
-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)
-
-Example:
-
-{ "event": "BLOCK_JOB_CANCELLED",
-     "data": { "type": "stream", "device": "virtio-disk0",
-               "len": 10737418240, "offset": 134217728,
-               "speed": 0 },
-     "timestamp": { "seconds": 1267061043, "microseconds": 959568 } }
-
-BLOCK_JOB_COMPLETED
--------------------
-
-Emitted when a block job has completed.
-
-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)
-- "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 streaming
-              has failed and clients should not try to interpret the error
-              string.
-
-Example:
-
-{ "event": "BLOCK_JOB_COMPLETED",
-     "data": { "type": "stream", "device": "virtio-disk0",
-               "len": 10737418240, "offset": 10737418240,
-               "speed": 0 },
-     "timestamp": { "seconds": 1267061043, "microseconds": 959568 } }
-
-BLOCK_JOB_ERROR
----------------
-
-Emitted when a block job encounters an error.
-
-Data:
-
-- "device": device name (json-string)
-- "operation": I/O operation (json-string, "read" or "write")
-- "action": action that has been taken, it's one of the following (json-string):
-    "ignore": error has been ignored, the job may fail later
-    "report": error will be reported and the job canceled
-    "stop": error caused job to be paused
-
-Example:
-
-{ "event": "BLOCK_JOB_ERROR",
-    "data": { "device": "ide0-hd1",
-              "operation": "write",
-              "action": "stop" },
-    "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
-
-BLOCK_JOB_READY
----------------
-
-Emitted when a block job is ready to complete.
-
-Data:
-
-- "device": device name (json-string)
-
-Example:
-
-{ "event": "BLOCK_JOB_READY",
-    "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.
-At this point, it's safe to reuse the specified device ID.
-Device removal can be initiated by the guest or by HMP/QMP commands.
-
-Data:
-
-- "device": device name (json-string, optional)
-- "path": device path (json-string)
-
-{ "event": "DEVICE_DELETED",
-  "data": { "device": "virtio-net-pci-0",
-            "path": "/machine/peripheral/virtio-net-pci-0" },
-  "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
-
 DEVICE_TRAY_MOVED
 -----------------
 
@@ -172,23 +44,6 @@ Data:
   },
   "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
 
-NIC_RX_FILTER_CHANGED
------------------
-
-The event is emitted once until the query command is executed,
-the first event will always be emitted.
-
-Data:
-
-- "name": net client name (json-string)
-- "path": device path (json-string)
-
-{ "event": "NIC_RX_FILTER_CHANGED",
-  "data": { "name": "vnet0",
-            "path": "/machine/peripheral/vnet0/virtio-backend" },
-  "timestamp": { "seconds": 1368697518, "microseconds": 326866 } }
-}
-
 RESET
 -----
 
@@ -220,8 +75,7 @@ Emitted when the guest changes the RTC time.
 
 Data:
 
-- "offset": Offset between base RTC clock (as specified by -rtc base), and
-new RTC clock value (json-number)
+- "offset": delta against the host UTC in seconds (json-number)
 
 Example:
 
@@ -244,68 +98,6 @@ Example:
 Note: If the command-line option "-no-shutdown" has been specified, a STOP
 event will eventually follow the SHUTDOWN event.
 
-SPICE_CONNECTED, SPICE_DISCONNECTED
------------------------------------
-
-Emitted when a SPICE client connects or 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_CONNECTED",
-  "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'n'running
-
-Data:
-
-- "server": Server information (json-object)
-  - "host": IP address (json-string)
-  - "port": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-  - "auth": authentication method (json-string, optional)
-- "client": Client information (json-object)
-  - "host": IP address (json-string)
-  - "port": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-  - "connection-id": spice connection id.  All channels with the same id
-                     belong to the same spice session (json-int)
-  - "channel-type": channel type.  "1" is the main control channel, filter for
-                    this one if you want track spice sessions only (json-int)
-  - "channel-id": channel id.  Usually "0", might be different needed when
-                  multiple channels of the same type exist, such as multiple
-                  display channels in a multihead setup (json-int)
-  - "tls": whevener the channel is encrypted (json-bool)
-
-Example:
-
-{ "timestamp": {"seconds": 1290688046, "microseconds": 417172},
-  "event": "SPICE_INITIALIZED",
-  "data": {"server": {"auth": "spice", "port": "5921",
-                      "family": "ipv4", "host": "127.0.0.1"},
-           "client": {"port": "49004", "family": "ipv4", "channel-type": 3,
-                      "connection-id": 1804289383, "host": "127.0.0.1",
-                      "channel-id": 0, "tls": true}
-}}
-
 STOP
 ----
 
@@ -318,32 +110,6 @@ Example:
 { "event": "STOP",
     "timestamp": { "seconds": 1267041730, "microseconds": 281295 } }
 
-SUSPEND
--------
-
-Emitted when guest enters S3 state.
-
-Data: None.
-
-Example:
-
-{ "event": "SUSPEND",
-     "timestamp": { "seconds": 1344456160, "microseconds": 309119 } }
-
-SUSPEND_DISK
-------------
-
-Emitted when the guest makes a request to enter S4 state.
-
-Data: None.
-
-Example:
-
-{ "event": "SUSPEND_DISK",
-     "timestamp": { "seconds": 1344456160, "microseconds": 309119 } }
-
-Note: QEMU shuts down when entering S4 state.
-
 VNC_CONNECTED
 -------------
 
@@ -434,17 +200,69 @@ Example:
                     "host": "127.0.0.1", "sasl_username": "luiz" } },
         "timestamp": { "seconds": 1263475302, "microseconds": 150772 } }
 
-WAKEUP
-------
+SPICE_CONNECTED, SPICE_DISCONNECTED
+-----------------------------------
 
-Emitted when the guest has woken up from S3 and is running.
+Emitted when a SPICE client connects or disconnects.
 
-Data: None.
+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:
 
-{ "event": "WATCHDOG",
-     "timestamp": { "seconds": 1344522075, "microseconds": 745528 } }
+{ "timestamp": {"seconds": 1290688046, "microseconds": 388707},
+  "event": "SPICE_CONNECTED",
+  "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'n'running
+
+Data:
+
+- "server": Server information (json-object)
+  - "host": IP address (json-string)
+  - "port": port number (json-string)
+  - "family": address family (json-string, "ipv4" or "ipv6")
+  - "auth": authentication method (json-string, optional)
+- "client": Client information (json-object)
+  - "host": IP address (json-string)
+  - "port": port number (json-string)
+  - "family": address family (json-string, "ipv4" or "ipv6")
+  - "connection-id": spice connection id.  All channels with the same id
+                     belong to the same spice session (json-int)
+  - "channel-type": channel type.  "1" is the main control channel, filter for
+                    this one if you want track spice sessions only (json-int)
+  - "channel-id": channel id.  Usually "0", might be different needed when
+                  multiple channels of the same type exist, such as multiple
+                  display channels in a multihead setup (json-int)
+  - "tls": whevener the channel is encrypted (json-bool)
+
+Example:
+
+{ "timestamp": {"seconds": 1290688046, "microseconds": 417172},
+  "event": "SPICE_INITIALIZED",
+  "data": {"server": {"auth": "spice", "port": "5921",
+                      "family": "ipv4", "host": "127.0.0.1"},
+           "client": {"port": "49004", "family": "ipv4", "channel-type": 3,
+                      "connection-id": 1804289383, "host": "127.0.0.1",
+                      "channel-id": 0, "tls": true}
+}}
+
 
 WATCHDOG
 --------
@@ -465,16 +283,55 @@ 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.
+BLOCK_JOB_COMPLETED
+-------------------
+
+Emitted when a block job has completed.
 
 Data:
 
-- "action": Action that has been taken (json-string, currently always "pause").
+- "type":     Job type ("stream" for image streaming, json-string)
+- "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)
+- "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 streaming
+              has failed and clients should not try to interpret the error
+              string.
 
 Example:
 
-{ "event": "GUEST_PANICKED",
-     "data": { "action": "pause" } }
+{ "event": "BLOCK_JOB_COMPLETED",
+     "data": { "type": "stream", "device": "virtio-disk0",
+               "len": 10737418240, "offset": 10737418240,
+               "speed": 0 },
+     "timestamp": { "seconds": 1267061043, "microseconds": 959568 } }
+
+
+BLOCK_JOB_CANCELLED
+-------------------
+
+Emitted when a block job has been cancelled.
+
+Data:
+
+- "type":     Job type ("stream" for image streaming, json-string)
+- "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)
+
+Example:
+
+{ "event": "BLOCK_JOB_CANCELLED",
+     "data": { "type": "stream", "device": "virtio-disk0",
+               "len": 10737418240, "offset": 134217728,
+               "speed": 0 },
+     "timestamp": { "seconds": 1267061043, "microseconds": 959568 } }

QMP/qmp-shell

@@ -33,7 +33,6 @@
 import qmp
 import readline
 import sys
-import pprint
 
 class QMPCompleter(list):
     def complete(self, text, state):
@@ -53,11 +52,10 @@ class QMPShellBadPort(QMPShellError):
 # TODO: QMPShell's interface is a bit ugly (eg. _fill_completion() and
 #       _execute_cmd()). Let's design a better one.
 class QMPShell(qmp.QEMUMonitorProtocol):
-    def __init__(self, address, pp=None):
+    def __init__(self, address):
         qmp.QEMUMonitorProtocol.__init__(self, self.__get_address(address))
         self._greeting = None
         self._completer = None
-        self._pp = pp
 
     def __get_address(self, arg):
         """
@@ -99,16 +97,9 @@ class QMPShell(qmp.QEMUMonitorProtocol):
         for arg in cmdargs[1:]:
             opt = arg.split('=')
             try:
-                if(len(opt) > 2):
-                    opt[1] = '='.join(opt[1:])
                 value = int(opt[1])
             except ValueError:
-                if opt[1] == 'true':
-                    value = True
-                elif opt[1] == 'false':
-                    value = False
-                else:
-                    value = opt[1]
+                value = opt[1]
             qmpcmd['arguments'][opt[0]] = value
         return qmpcmd
 
@@ -123,11 +114,7 @@ class QMPShell(qmp.QEMUMonitorProtocol):
         if resp is None:
             print 'Disconnected'
             return False
-
-        if self._pp is not None:
-            self._pp.pprint(resp)
-        else:
-            print resp
+        print resp
         return True
 
     def connect(self):
@@ -235,36 +222,22 @@ def die(msg):
 def fail_cmdline(option=None):
     if option:
         sys.stderr.write('ERROR: bad command-line option \'%s\'\n' % option)
-    sys.stderr.write('qemu-shell [ -p ] [ -H ] < UNIX socket path> | < TCP address:port >\n')
+    sys.stderr.write('qemu-shell [ -H ] < UNIX socket path> | < TCP address:port >\n')
     sys.exit(1)
 
 def main():
     addr = ''
-    qemu = None
-    hmp = False
-    pp = None
-
     try:
-        for arg in sys.argv[1:]:
-            if arg == "-H":
-                if qemu is not None:
-                    fail_cmdline(arg)
-                hmp = True
-            elif arg == "-p":
-                if pp is not None:
-                    fail_cmdline(arg)
-                pp = pprint.PrettyPrinter(indent=4)
-            else:
-                if qemu is not None:
-                    fail_cmdline(arg)
-                if hmp:
-                    qemu = HMPShell(arg)
-                else:
-                    qemu = QMPShell(arg, pp)
-                addr = arg
-
-        if qemu is None:
-            fail_cmdline()
+        if len(sys.argv) == 2:
+            qemu = QMPShell(sys.argv[1])
+            addr = sys.argv[1]
+        elif len(sys.argv) == 3:
+            if sys.argv[1] != '-H':
+                fail_cmdline(sys.argv[1])
+            qemu = HMPShell(sys.argv[2])
+            addr = sys.argv[2]
+        else:
+                fail_cmdline()
     except QMPShellBadPort:
         die('bad port number in command-line')
 

QMP/qmp-spec.txt

@@ -106,11 +106,14 @@ completed because of an error condition.
 
 The format is:
 
-{ "error": { "class": json-string, "desc": json-string }, "id": json-value }
+{ "error": { "class": json-string, "data": json-object, "desc": json-string },
+  "id": json-value }
 
  Where,
 
-- The "class" member contains the error class name (eg. "GenericError")
+- The "class" member contains the error class name (eg. "ServiceUnavailable")
+- The "data" member contains specific error data and is defined in a
+  per-command basis, it will be an empty json-object if the error has no data
 - 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
@@ -170,7 +173,8 @@ S: {"return": {"enabled": true, "present": true}, "id": "example"}
 ------------------
 
 C: { "execute": }
-S: {"error": {"class": "GenericError", "desc": "Invalid JSON syntax" } }
+S: {"error": {"class": "JSONParsing", "desc": "Invalid JSON syntax", "data":
+{}}}
 
 3.5 Powerdown event
 -------------------

QMP/qmp.py

@@ -49,6 +49,7 @@ class QEMUMonitorProtocol:
         return socket.socket(family, socket.SOCK_STREAM)
 
     def __negotiate_capabilities(self):
+        self.__sockfile = self.__sock.makefile()
         greeting = self.__json_read()
         if greeting is None or not greeting.has_key('QMP'):
             raise QMPConnectError
@@ -72,7 +73,7 @@ class QEMUMonitorProtocol:
 
     error = socket.error
 
-    def connect(self, negotiate=True):
+    def connect(self):
         """
         Connect to the QMP Monitor and perform capabilities negotiation.
 
@@ -82,9 +83,7 @@ class QEMUMonitorProtocol:
         @raise QMPCapabilitiesError if fails to negotiate capabilities
         """
         self.__sock.connect(self.__address)
-        self.__sockfile = self.__sock.makefile()
-        if negotiate:
-            return self.__negotiate_capabilities()
+        return self.__negotiate_capabilities()
 
     def accept(self):
         """
@@ -96,7 +95,6 @@ class QEMUMonitorProtocol:
         @raise QMPCapabilitiesError if fails to negotiate capabilities
         """
         self.__sock, _ = self.__sock.accept()
-        self.__sockfile = self.__sock.makefile()
         return self.__negotiate_capabilities()
 
     def cmd_obj(self, qmp_cmd):
@@ -136,26 +134,6 @@ class QEMUMonitorProtocol:
             raise Exception(ret['error']['desc'])
         return ret['return']
 
-    def pull_event(self, wait=False):
-        """
-        Get and delete the first available QMP event.
-
-        @param wait: block until an event is available (bool)
-        """
-        self.__sock.setblocking(0)
-        try:
-            self.__json_read()
-        except socket.error, err:
-            if err[0] == errno.EAGAIN:
-                # No data available
-                pass
-        self.__sock.setblocking(1)
-        if not self.__events and wait:
-            self.__json_read(only_event=True)
-        event = self.__events[0]
-        del self.__events[0]
-        return event
-
     def get_events(self, wait=False):
         """
         Get a list of available QMP events.
@@ -183,8 +161,3 @@ class QEMUMonitorProtocol:
     def close(self):
         self.__sock.close()
         self.__sockfile.close()
-
-    timeout = socket.timeout
-
-    def settimeout(self, timeout):
-        self.__sock.settimeout(timeout)

TODO

@@ -0,0 +1,37 @@
+General:
+-------
+- cycle counter for all archs
+- cpu_interrupt() win32/SMP fix
+- merge PIC spurious interrupt patch
+- warning for OS/2: must not use 128 MB memory (merge bochs cmos patch ?)
+- config file (at least for windows/Mac OS X)
+- update doc: PCI infos.
+- basic VGA optimizations
+- better code fetch
+- do not resize vga if invalid size.
+- TLB code protection support for PPC
+- disable SMC handling for ARM/SPARC/PPC (not finished)
+- see undefined flags for BTx insn
+- keyboard output buffer filling timing emulation
+- tests for each target CPU
+- fix all remaining thread lock issues (must put TBs in a specific invalid
+  state, find a solution for tb_flush()).
+
+ppc specific:
+------------
+- TLB invalidate not needed if msr_pr changes
+- enable shift optimizations ?
+
+linux-user specific:
+-------------------
+- remove threading support as it cannot work at this point
+- improve IPC syscalls
+- more syscalls (in particular all 64 bit ones, IPCs, fix 64 bit
+  issues, fix 16 bit uid issues)
+- use kernel traps for unaligned accesses on ARM ?
+
+
+lower priority:
+--------------
+- int15 ah=86: use better timing
+- use -msoft-float on ARM

VERSION

@@ -1 +1 @@
-1.5.92
+1.1.2

a.out.h

@@ -0,0 +1,430 @@
+/* a.out.h
+
+   Copyright 1997, 1998, 1999, 2001 Red Hat, Inc.
+
+This file is part of Cygwin.
+
+This software is a copyrighted work licensed under the terms of the
+Cygwin license.  Please consult the file "CYGWIN_LICENSE" for
+details. */
+
+#ifndef _A_OUT_H_
+#define _A_OUT_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+#define COFF_IMAGE_WITH_PE
+#define COFF_LONG_SECTION_NAMES
+
+/*** coff information for Intel 386/486.  */
+
+
+/********************** FILE HEADER **********************/
+
+struct external_filehdr {
+  short f_magic;	/* magic number			*/
+  short f_nscns;	/* number of sections		*/
+  host_ulong f_timdat;	/* time & date stamp		*/
+  host_ulong f_symptr;	/* file pointer to symtab	*/
+  host_ulong f_nsyms;	/* number of symtab entries	*/
+  short f_opthdr;	/* sizeof(optional hdr)		*/
+  short f_flags;	/* flags			*/
+};
+
+/* Bits for f_flags:
+ *	F_RELFLG	relocation info stripped from file
+ *	F_EXEC		file is executable (no unresolved external references)
+ *	F_LNNO		line numbers stripped from file
+ *	F_LSYMS		local symbols stripped from file
+ *	F_AR32WR	file has byte ordering of an AR32WR machine (e.g. vax)
+ */
+
+#define F_RELFLG	(0x0001)
+#define F_EXEC		(0x0002)
+#define F_LNNO		(0x0004)
+#define F_LSYMS		(0x0008)
+
+
+
+#define	I386MAGIC	0x14c
+#define I386PTXMAGIC	0x154
+#define I386AIXMAGIC	0x175
+
+/* This is Lynx's all-platform magic number for executables. */
+
+#define LYNXCOFFMAGIC	0415
+
+#define I386BADMAG(x) (((x).f_magic != I386MAGIC) \
+		       && (x).f_magic != I386AIXMAGIC \
+		       && (x).f_magic != I386PTXMAGIC \
+		       && (x).f_magic != LYNXCOFFMAGIC)
+
+#define	FILHDR	struct external_filehdr
+#define	FILHSZ	20
+
+
+/********************** AOUT "OPTIONAL HEADER"=
+ **********************/
+
+
+typedef struct
+{
+  unsigned short magic;		/* type of file				*/
+  unsigned short vstamp;	/* version stamp			*/
+  host_ulong	tsize;		/* text size in bytes, padded to FW bdry*/
+  host_ulong	dsize;		/* initialized data "  "		*/
+  host_ulong	bsize;		/* uninitialized data "   "		*/
+  host_ulong	entry;		/* entry pt.				*/
+  host_ulong text_start;	/* base of text used for this file */
+  host_ulong data_start;	/* base of data used for this file=
+ */
+}
+AOUTHDR;
+
+#define AOUTSZ 28
+#define AOUTHDRSZ 28
+
+#define OMAGIC          0404    /* object files, eg as output */
+#define ZMAGIC          0413    /* demand load format, eg normal ld output */
+#define STMAGIC		0401	/* target shlib */
+#define SHMAGIC		0443	/* host   shlib */
+
+
+/* define some NT default values */
+/*  #define NT_IMAGE_BASE        0x400000 moved to internal.h */
+#define NT_SECTION_ALIGNMENT 0x1000
+#define NT_FILE_ALIGNMENT    0x200
+#define NT_DEF_RESERVE       0x100000
+#define NT_DEF_COMMIT        0x1000
+
+/********************** SECTION HEADER **********************/
+
+
+struct external_scnhdr {
+  char		s_name[8];	/* section name			*/
+  host_ulong	s_paddr;	/* physical address, offset
+				   of last addr in scn */
+  host_ulong	s_vaddr;	/* virtual address		*/
+  host_ulong	s_size;		/* section size			*/
+  host_ulong	s_scnptr;	/* file ptr to raw data for section */
+  host_ulong	s_relptr;	/* file ptr to relocation	*/
+  host_ulong	s_lnnoptr;	/* file ptr to line numbers	*/
+  unsigned short s_nreloc;	/* number of relocation entries	*/
+  unsigned short s_nlnno;	/* number of line number entries*/
+  host_ulong	s_flags;	/* flags			*/
+};
+
+#define	SCNHDR	struct external_scnhdr
+#define	SCNHSZ	40
+
+/*
+ * names of "special" sections
+ */
+#define _TEXT	".text"
+#define _DATA	".data"
+#define _BSS	".bss"
+#define _COMMENT ".comment"
+#define _LIB ".lib"
+
+/********************** LINE NUMBERS **********************/
+
+/* 1 line number entry for every "breakpointable" source line in a section.
+ * Line numbers are grouped on a per function basis; first entry in a function
+ * grouping will have l_lnno = 0 and in place of physical address will be the
+ * symbol table index of the function name.
+ */
+struct external_lineno {
+  union {
+    host_ulong l_symndx; /* function name symbol index, iff l_lnno 0 */
+    host_ulong l_paddr;	/* (physical) address of line number	*/
+  } l_addr;
+  unsigned short l_lnno;	/* line number		*/
+};
+
+#define	LINENO	struct external_lineno
+#define	LINESZ	6
+
+/********************** SYMBOLS **********************/
+
+#define E_SYMNMLEN	8	/* # characters in a symbol name	*/
+#define E_FILNMLEN	14	/* # characters in a file name		*/
+#define E_DIMNUM	4	/* # array dimensions in auxiliary entry */
+
+struct QEMU_PACKED external_syment
+{
+  union {
+    char e_name[E_SYMNMLEN];
+    struct {
+      host_ulong e_zeroes;
+      host_ulong e_offset;
+    } e;
+  } e;
+  host_ulong e_value;
+  unsigned short e_scnum;
+  unsigned short e_type;
+  char e_sclass[1];
+  char e_numaux[1];
+};
+
+#define N_BTMASK	(0xf)
+#define N_TMASK		(0x30)
+#define N_BTSHFT	(4)
+#define N_TSHIFT	(2)
+
+union external_auxent {
+  struct {
+    host_ulong x_tagndx;	/* str, un, or enum tag indx */
+    union {
+      struct {
+	unsigned short  x_lnno; /* declaration line number */
+	unsigned short  x_size; /* str/union/array size */
+      } x_lnsz;
+      host_ulong x_fsize;	/* size of function */
+    } x_misc;
+    union {
+      struct {			/* if ISFCN, tag, or .bb */
+	host_ulong x_lnnoptr;/* ptr to fcn line # */
+	host_ulong x_endndx;	/* entry ndx past block end */
+      } x_fcn;
+      struct {			/* if ISARY, up to 4 dimen. */
+	char x_dimen[E_DIMNUM][2];
+      } x_ary;
+    } x_fcnary;
+    unsigned short x_tvndx;	/* tv index */
+  } x_sym;
+
+  union {
+    char x_fname[E_FILNMLEN];
+    struct {
+      host_ulong x_zeroes;
+      host_ulong x_offset;
+    } x_n;
+  } x_file;
+
+  struct {
+    host_ulong x_scnlen;	/* section length */
+    unsigned short x_nreloc;	/* # relocation entries */
+    unsigned short x_nlinno;	/* # line numbers */
+    host_ulong x_checksum;	/* section COMDAT checksum */
+    unsigned short x_associated;/* COMDAT associated section index */
+    char x_comdat[1];		/* COMDAT selection number */
+  } x_scn;
+
+  struct {
+    host_ulong x_tvfill;	/* tv fill value */
+    unsigned short x_tvlen;	/* length of .tv */
+    char x_tvran[2][2];		/* tv range */
+  } x_tv;	/* info about .tv section (in auxent of symbol .tv)) */
+
+};
+
+#define	SYMENT	struct external_syment
+#define	SYMESZ	18
+#define	AUXENT	union external_auxent
+#define	AUXESZ	18
+
+#define _ETEXT	"etext"
+
+/********************** RELOCATION DIRECTIVES **********************/
+
+struct external_reloc {
+  char r_vaddr[4];
+  char r_symndx[4];
+  char r_type[2];
+};
+
+#define RELOC struct external_reloc
+#define RELSZ 10
+
+/* end of coff/i386.h */
+
+/* PE COFF header information */
+
+#ifndef _PE_H
+#define _PE_H
+
+/* NT specific file attributes */
+#define IMAGE_FILE_RELOCS_STRIPPED           0x0001
+#define IMAGE_FILE_EXECUTABLE_IMAGE          0x0002
+#define IMAGE_FILE_LINE_NUMS_STRIPPED        0x0004
+#define IMAGE_FILE_LOCAL_SYMS_STRIPPED       0x0008
+#define IMAGE_FILE_BYTES_REVERSED_LO         0x0080
+#define IMAGE_FILE_32BIT_MACHINE             0x0100
+#define IMAGE_FILE_DEBUG_STRIPPED            0x0200
+#define IMAGE_FILE_SYSTEM                    0x1000
+#define IMAGE_FILE_DLL                       0x2000
+#define IMAGE_FILE_BYTES_REVERSED_HI         0x8000
+
+/* additional flags to be set for section headers to allow the NT loader to
+   read and write to the section data (to replace the addresses of data in
+   dlls for one thing); also to execute the section in .text's case=
+ */
+#define IMAGE_SCN_MEM_DISCARDABLE 0x02000000
+#define IMAGE_SCN_MEM_EXECUTE     0x20000000
+#define IMAGE_SCN_MEM_READ        0x40000000
+#define IMAGE_SCN_MEM_WRITE       0x80000000
+
+/*
+ * Section characteristics added for ppc-nt
+ */
+
+#define IMAGE_SCN_TYPE_NO_PAD                0x00000008  /* Reserved.  */
+
+#define IMAGE_SCN_CNT_CODE                   0x00000020  /* Section contains code. */
+#define IMAGE_SCN_CNT_INITIALIZED_DATA       0x00000040  /* Section contains initialized data. */
+#define IMAGE_SCN_CNT_UNINITIALIZED_DATA     0x00000080  /* Section contains uninitialized data. */
+
+#define IMAGE_SCN_LNK_OTHER                  0x00000100  /* Reserved.  */
+#define IMAGE_SCN_LNK_INFO                   0x00000200  /* Section contains comments or some other type of information. */
+#define IMAGE_SCN_LNK_REMOVE                 0x00000800  /* Section contents will not become part of image. */
+#define IMAGE_SCN_LNK_COMDAT                 0x00001000  /* Section contents comdat. */
+
+#define IMAGE_SCN_MEM_FARDATA                0x00008000
+
+#define IMAGE_SCN_MEM_PURGEABLE              0x00020000
+#define IMAGE_SCN_MEM_16BIT                  0x00020000
+#define IMAGE_SCN_MEM_LOCKED                 0x00040000
+#define IMAGE_SCN_MEM_PRELOAD                0x00080000
+
+#define IMAGE_SCN_ALIGN_1BYTES               0x00100000
+#define IMAGE_SCN_ALIGN_2BYTES               0x00200000
+#define IMAGE_SCN_ALIGN_4BYTES               0x00300000
+#define IMAGE_SCN_ALIGN_8BYTES               0x00400000
+#define IMAGE_SCN_ALIGN_16BYTES              0x00500000  /* Default alignment if no others are specified. */
+#define IMAGE_SCN_ALIGN_32BYTES              0x00600000
+#define IMAGE_SCN_ALIGN_64BYTES              0x00700000
+
+
+#define IMAGE_SCN_LNK_NRELOC_OVFL            0x01000000  /* Section contains extended relocations. */
+#define IMAGE_SCN_MEM_NOT_CACHED             0x04000000  /* Section is not cachable.               */
+#define IMAGE_SCN_MEM_NOT_PAGED              0x08000000  /* Section is not pageable.               */
+#define IMAGE_SCN_MEM_SHARED                 0x10000000  /* Section is shareable.                  */
+
+/* COMDAT selection codes.  */
+
+#define IMAGE_COMDAT_SELECT_NODUPLICATES     (1) /* Warn if duplicates.  */
+#define IMAGE_COMDAT_SELECT_ANY		     (2) /* No warning.  */
+#define IMAGE_COMDAT_SELECT_SAME_SIZE	     (3) /* Warn if different size.  */
+#define IMAGE_COMDAT_SELECT_EXACT_MATCH	     (4) /* Warn if different.  */
+#define IMAGE_COMDAT_SELECT_ASSOCIATIVE	     (5) /* Base on other section.  */
+
+/* Magic values that are true for all dos/nt implementations */
+#define DOSMAGIC       0x5a4d
+#define NT_SIGNATURE   0x00004550
+
+/* NT allows long filenames, we want to accommodate this.  This may break
+     some of the bfd functions */
+#undef  FILNMLEN
+#define FILNMLEN	18	/* # characters in a file name		*/
+
+
+#ifdef COFF_IMAGE_WITH_PE
+/* The filehdr is only weired in images */
+
+#undef FILHDR
+struct external_PE_filehdr
+{
+  /* DOS header fields */
+  unsigned short e_magic;	/* Magic number, 0x5a4d */
+  unsigned short e_cblp;	/* Bytes on last page of file, 0x90 */
+  unsigned short e_cp;		/* Pages in file, 0x3 */
+  unsigned short e_crlc;	/* Relocations, 0x0 */
+  unsigned short e_cparhdr;	/* Size of header in paragraphs, 0x4 */
+  unsigned short e_minalloc;	/* Minimum extra paragraphs needed, 0x0 */
+  unsigned short e_maxalloc;	/* Maximum extra paragraphs needed, 0xFFFF */
+  unsigned short e_ss;		/* Initial (relative) SS value, 0x0 */
+  unsigned short e_sp;		/* Initial SP value, 0xb8 */
+  unsigned short e_csum;	/* Checksum, 0x0 */
+  unsigned short e_ip;		/* Initial IP value, 0x0 */
+  unsigned short e_cs;		/* Initial (relative) CS value, 0x0 */
+  unsigned short e_lfarlc;	/* File address of relocation table, 0x40 */
+  unsigned short e_ovno;	/* Overlay number, 0x0 */
+  char e_res[4][2];		/* Reserved words, all 0x0 */
+  unsigned short e_oemid;	/* OEM identifier (for e_oeminfo), 0x0 */
+  unsigned short e_oeminfo;	/* OEM information; e_oemid specific, 0x0 */
+  char e_res2[10][2];		/* Reserved words, all 0x0 */
+  host_ulong e_lfanew;	/* File address of new exe header, 0x80 */
+  char dos_message[16][4];	/* other stuff, always follow DOS header */
+  unsigned int nt_signature;	/* required NT signature, 0x4550 */
+
+  /* From standard header */
+
+  unsigned short f_magic;	/* magic number			*/
+  unsigned short f_nscns;	/* number of sections		*/
+  host_ulong f_timdat;	/* time & date stamp		*/
+  host_ulong f_symptr;	/* file pointer to symtab	*/
+  host_ulong f_nsyms;	/* number of symtab entries	*/
+  unsigned short f_opthdr;	/* sizeof(optional hdr)		*/
+  unsigned short f_flags;	/* flags			*/
+};
+
+
+#define FILHDR struct external_PE_filehdr
+#undef FILHSZ
+#define FILHSZ 152
+
+#endif
+
+typedef struct
+{
+  unsigned short magic;		/* type of file				*/
+  unsigned short vstamp;	/* version stamp			*/
+  host_ulong	tsize;		/* text size in bytes, padded to FW bdry*/
+  host_ulong	dsize;		/* initialized data "  "		*/
+  host_ulong	bsize;		/* uninitialized data "   "		*/
+  host_ulong	entry;		/* entry pt.				*/
+  host_ulong text_start;	/* base of text used for this file */
+  host_ulong data_start;	/* base of all data used for this file */
+
+  /* NT extra fields; see internal.h for descriptions */
+  host_ulong  ImageBase;
+  host_ulong  SectionAlignment;
+  host_ulong  FileAlignment;
+  unsigned short  MajorOperatingSystemVersion;
+  unsigned short  MinorOperatingSystemVersion;
+  unsigned short  MajorImageVersion;
+  unsigned short  MinorImageVersion;
+  unsigned short  MajorSubsystemVersion;
+  unsigned short  MinorSubsystemVersion;
+  char  Reserved1[4];
+  host_ulong  SizeOfImage;
+  host_ulong  SizeOfHeaders;
+  host_ulong  CheckSum;
+  unsigned short Subsystem;
+  unsigned short DllCharacteristics;
+  host_ulong  SizeOfStackReserve;
+  host_ulong  SizeOfStackCommit;
+  host_ulong  SizeOfHeapReserve;
+  host_ulong  SizeOfHeapCommit;
+  host_ulong  LoaderFlags;
+  host_ulong  NumberOfRvaAndSizes;
+  /* IMAGE_DATA_DIRECTORY DataDirectory[IMAGE_NUMBEROF_DIRECTORY_ENTRIES]; */
+  char  DataDirectory[16][2][4]; /* 16 entries, 2 elements/entry, 4 chars */
+
+} PEAOUTHDR;
+
+
+#undef AOUTSZ
+#define AOUTSZ (AOUTHDRSZ + 196)
+
+#undef  E_FILNMLEN
+#define E_FILNMLEN	18	/* # characters in a file name		*/
+#endif
+
+/* end of coff/pe.h */
+
+#define DT_NON		(0)	/* no derived type */
+#define DT_PTR		(1)	/* pointer */
+#define DT_FCN		(2)	/* function */
+#define DT_ARY		(3)	/* array */
+
+#define ISPTR(x)	(((x) & N_TMASK) == (DT_PTR << N_BTSHFT))
+#define ISFCN(x)	(((x) & N_TMASK) == (DT_FCN << N_BTSHFT))
+#define ISARY(x)	(((x) & N_TMASK) == (DT_ARY << N_BTSHFT))
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _A_OUT_H_ */

acl.c

@@ -24,7 +24,7 @@
 
 
 #include "qemu-common.h"
-#include "qemu/acl.h"
+#include "acl.h"
 
 #ifdef CONFIG_FNMATCH
 #include <fnmatch.h>
@@ -103,8 +103,8 @@ void qemu_acl_reset(qemu_acl *acl)
     acl->defaultDeny = 1;
     QTAILQ_FOREACH_SAFE(entry, &acl->entries, next, next_entry) {
         QTAILQ_REMOVE(&acl->entries, entry, next);
-        g_free(entry->match);
-        g_free(entry);
+        free(entry->match);
+        free(entry);
     }
     acl->nentries = 0;
 }
@@ -138,9 +138,9 @@ int qemu_acl_insert(qemu_acl *acl,
 
     if (index <= 0)
         return -1;
-    if (index > acl->nentries) {
+    if (index >= acl->nentries)
         return qemu_acl_append(acl, deny, match);
-    }
+
 
     entry = g_malloc(sizeof(*entry));
     entry->match = g_strdup(match);
@@ -168,9 +168,6 @@ int qemu_acl_remove(qemu_acl *acl,
         i++;
         if (strcmp(entry->match, match) == 0) {
             QTAILQ_REMOVE(&acl->entries, entry, next);
-            acl->nentries--;
-            g_free(entry->match);
-            g_free(entry);
             return i;
         }
     }

acl.h

@@ -25,7 +25,7 @@
 #ifndef __QEMU_ACL_H__
 #define __QEMU_ACL_H__
 
-#include "qemu/queue.h"
+#include "qemu-queue.h"
 
 typedef struct qemu_acl_entry qemu_acl_entry;
 typedef struct qemu_acl qemu_acl;

aes.c

@@ -28,9 +28,14 @@
  * EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 #include "qemu-common.h"
-#include "qemu/aes.h"
+#include "aes.h"
+
+#ifndef NDEBUG
+#define NDEBUG
+#endif
 
 typedef uint32_t u32;
+typedef uint16_t u16;
 typedef uint8_t u8;
 
 /* This controls loop-unrolling in aes_core.c */
@@ -39,20 +44,20 @@ typedef uint8_t u8;
 # define PUTU32(ct, st) { (ct)[0] = (u8)((st) >> 24); (ct)[1] = (u8)((st) >> 16); (ct)[2] = (u8)((st) >>  8); (ct)[3] = (u8)(st); }
 
 /*
-AES_Te0[x] = S [x].[02, 01, 01, 03];
-AES_Te1[x] = S [x].[03, 02, 01, 01];
-AES_Te2[x] = S [x].[01, 03, 02, 01];
-AES_Te3[x] = S [x].[01, 01, 03, 02];
-AES_Te4[x] = S [x].[01, 01, 01, 01];
+Te0[x] = S [x].[02, 01, 01, 03];
+Te1[x] = S [x].[03, 02, 01, 01];
+Te2[x] = S [x].[01, 03, 02, 01];
+Te3[x] = S [x].[01, 01, 03, 02];
+Te4[x] = S [x].[01, 01, 01, 01];
 
-AES_Td0[x] = Si[x].[0e, 09, 0d, 0b];
-AES_Td1[x] = Si[x].[0b, 0e, 09, 0d];
-AES_Td2[x] = Si[x].[0d, 0b, 0e, 09];
-AES_Td3[x] = Si[x].[09, 0d, 0b, 0e];
-AES_Td4[x] = Si[x].[01, 01, 01, 01];
+Td0[x] = Si[x].[0e, 09, 0d, 0b];
+Td1[x] = Si[x].[0b, 0e, 09, 0d];
+Td2[x] = Si[x].[0d, 0b, 0e, 09];
+Td3[x] = Si[x].[09, 0d, 0b, 0e];
+Td4[x] = Si[x].[01, 01, 01, 01];
 */
 
-const uint32_t AES_Te0[256] = {
+static const u32 Te0[256] = {
     0xc66363a5U, 0xf87c7c84U, 0xee777799U, 0xf67b7b8dU,
     0xfff2f20dU, 0xd66b6bbdU, 0xde6f6fb1U, 0x91c5c554U,
     0x60303050U, 0x02010103U, 0xce6767a9U, 0x562b2b7dU,
@@ -118,7 +123,7 @@ const uint32_t AES_Te0[256] = {
     0x824141c3U, 0x299999b0U, 0x5a2d2d77U, 0x1e0f0f11U,
     0x7bb0b0cbU, 0xa85454fcU, 0x6dbbbbd6U, 0x2c16163aU,
 };
-const uint32_t AES_Te1[256] = {
+static const u32 Te1[256] = {
     0xa5c66363U, 0x84f87c7cU, 0x99ee7777U, 0x8df67b7bU,
     0x0dfff2f2U, 0xbdd66b6bU, 0xb1de6f6fU, 0x5491c5c5U,
     0x50603030U, 0x03020101U, 0xa9ce6767U, 0x7d562b2bU,
@@ -184,7 +189,7 @@ const uint32_t AES_Te1[256] = {
     0xc3824141U, 0xb0299999U, 0x775a2d2dU, 0x111e0f0fU,
     0xcb7bb0b0U, 0xfca85454U, 0xd66dbbbbU, 0x3a2c1616U,
 };
-const uint32_t AES_Te2[256] = {
+static const u32 Te2[256] = {
     0x63a5c663U, 0x7c84f87cU, 0x7799ee77U, 0x7b8df67bU,
     0xf20dfff2U, 0x6bbdd66bU, 0x6fb1de6fU, 0xc55491c5U,
     0x30506030U, 0x01030201U, 0x67a9ce67U, 0x2b7d562bU,
@@ -250,7 +255,7 @@ const uint32_t AES_Te2[256] = {
     0x41c38241U, 0x99b02999U, 0x2d775a2dU, 0x0f111e0fU,
     0xb0cb7bb0U, 0x54fca854U, 0xbbd66dbbU, 0x163a2c16U,
 };
-const uint32_t AES_Te3[256] = {
+static const u32 Te3[256] = {
 
     0x6363a5c6U, 0x7c7c84f8U, 0x777799eeU, 0x7b7b8df6U,
     0xf2f20dffU, 0x6b6bbdd6U, 0x6f6fb1deU, 0xc5c55491U,
@@ -317,7 +322,7 @@ const uint32_t AES_Te3[256] = {
     0x4141c382U, 0x9999b029U, 0x2d2d775aU, 0x0f0f111eU,
     0xb0b0cb7bU, 0x5454fca8U, 0xbbbbd66dU, 0x16163a2cU,
 };
-const uint32_t AES_Te4[256] = {
+static const u32 Te4[256] = {
     0x63636363U, 0x7c7c7c7cU, 0x77777777U, 0x7b7b7b7bU,
     0xf2f2f2f2U, 0x6b6b6b6bU, 0x6f6f6f6fU, 0xc5c5c5c5U,
     0x30303030U, 0x01010101U, 0x67676767U, 0x2b2b2b2bU,
@@ -383,7 +388,7 @@ const uint32_t AES_Te4[256] = {
     0x41414141U, 0x99999999U, 0x2d2d2d2dU, 0x0f0f0f0fU,
     0xb0b0b0b0U, 0x54545454U, 0xbbbbbbbbU, 0x16161616U,
 };
-const uint32_t AES_Td0[256] = {
+static const u32 Td0[256] = {
     0x51f4a750U, 0x7e416553U, 0x1a17a4c3U, 0x3a275e96U,
     0x3bab6bcbU, 0x1f9d45f1U, 0xacfa58abU, 0x4be30393U,
     0x2030fa55U, 0xad766df6U, 0x88cc7691U, 0xf5024c25U,
@@ -449,7 +454,7 @@ const uint32_t AES_Td0[256] = {
     0x39a80171U, 0x080cb3deU, 0xd8b4e49cU, 0x6456c190U,
     0x7bcb8461U, 0xd532b670U, 0x486c5c74U, 0xd0b85742U,
 };
-const uint32_t AES_Td1[256] = {
+static const u32 Td1[256] = {
     0x5051f4a7U, 0x537e4165U, 0xc31a17a4U, 0x963a275eU,
     0xcb3bab6bU, 0xf11f9d45U, 0xabacfa58U, 0x934be303U,
     0x552030faU, 0xf6ad766dU, 0x9188cc76U, 0x25f5024cU,
@@ -515,7 +520,7 @@ const uint32_t AES_Td1[256] = {
     0x7139a801U, 0xde080cb3U, 0x9cd8b4e4U, 0x906456c1U,
     0x617bcb84U, 0x70d532b6U, 0x74486c5cU, 0x42d0b857U,
 };
-const uint32_t AES_Td2[256] = {
+static const u32 Td2[256] = {
     0xa75051f4U, 0x65537e41U, 0xa4c31a17U, 0x5e963a27U,
     0x6bcb3babU, 0x45f11f9dU, 0x58abacfaU, 0x03934be3U,
     0xfa552030U, 0x6df6ad76U, 0x769188ccU, 0x4c25f502U,
@@ -582,7 +587,7 @@ const uint32_t AES_Td2[256] = {
     0x017139a8U, 0xb3de080cU, 0xe49cd8b4U, 0xc1906456U,
     0x84617bcbU, 0xb670d532U, 0x5c74486cU, 0x5742d0b8U,
 };
-const uint32_t AES_Td3[256] = {
+static const u32 Td3[256] = {
     0xf4a75051U, 0x4165537eU, 0x17a4c31aU, 0x275e963aU,
     0xab6bcb3bU, 0x9d45f11fU, 0xfa58abacU, 0xe303934bU,
     0x30fa5520U, 0x766df6adU, 0xcc769188U, 0x024c25f5U,
@@ -648,7 +653,7 @@ const uint32_t AES_Td3[256] = {
     0xa8017139U, 0x0cb3de08U, 0xb4e49cd8U, 0x56c19064U,
     0xcb84617bU, 0x32b670d5U, 0x6c5c7448U, 0xb85742d0U,
 };
-const uint32_t AES_Td4[256] = {
+static const u32 Td4[256] = {
     0x52525252U, 0x09090909U, 0x6a6a6a6aU, 0xd5d5d5d5U,
     0x30303030U, 0x36363636U, 0xa5a5a5a5U, 0x38383838U,
     0xbfbfbfbfU, 0x40404040U, 0xa3a3a3a3U, 0x9e9e9e9eU,
@@ -752,10 +757,10 @@ int AES_set_encrypt_key(const unsigned char *userKey, const int bits,
 		while (1) {
 			temp  = rk[3];
 			rk[4] = rk[0] ^
-                                (AES_Te4[(temp >> 16) & 0xff] & 0xff000000) ^
-                                (AES_Te4[(temp >>  8) & 0xff] & 0x00ff0000) ^
-                                (AES_Te4[(temp      ) & 0xff] & 0x0000ff00) ^
-                                (AES_Te4[(temp >> 24)       ] & 0x000000ff) ^
+				(Te4[(temp >> 16) & 0xff] & 0xff000000) ^
+				(Te4[(temp >>  8) & 0xff] & 0x00ff0000) ^
+				(Te4[(temp      ) & 0xff] & 0x0000ff00) ^
+				(Te4[(temp >> 24)       ] & 0x000000ff) ^
 				rcon[i];
 			rk[5] = rk[1] ^ rk[4];
 			rk[6] = rk[2] ^ rk[5];
@@ -772,10 +777,10 @@ int AES_set_encrypt_key(const unsigned char *userKey, const int bits,
 		while (1) {
 			temp = rk[ 5];
 			rk[ 6] = rk[ 0] ^
-                                (AES_Te4[(temp >> 16) & 0xff] & 0xff000000) ^
-                                (AES_Te4[(temp >>  8) & 0xff] & 0x00ff0000) ^
-                                (AES_Te4[(temp      ) & 0xff] & 0x0000ff00) ^
-                                (AES_Te4[(temp >> 24)       ] & 0x000000ff) ^
+				(Te4[(temp >> 16) & 0xff] & 0xff000000) ^
+				(Te4[(temp >>  8) & 0xff] & 0x00ff0000) ^
+				(Te4[(temp      ) & 0xff] & 0x0000ff00) ^
+				(Te4[(temp >> 24)       ] & 0x000000ff) ^
 				rcon[i];
 			rk[ 7] = rk[ 1] ^ rk[ 6];
 			rk[ 8] = rk[ 2] ^ rk[ 7];
@@ -794,10 +799,10 @@ int AES_set_encrypt_key(const unsigned char *userKey, const int bits,
 		while (1) {
 			temp = rk[ 7];
 			rk[ 8] = rk[ 0] ^
-                                (AES_Te4[(temp >> 16) & 0xff] & 0xff000000) ^
-                                (AES_Te4[(temp >>  8) & 0xff] & 0x00ff0000) ^
-                                (AES_Te4[(temp      ) & 0xff] & 0x0000ff00) ^
-                                (AES_Te4[(temp >> 24)       ] & 0x000000ff) ^
+				(Te4[(temp >> 16) & 0xff] & 0xff000000) ^
+				(Te4[(temp >>  8) & 0xff] & 0x00ff0000) ^
+				(Te4[(temp      ) & 0xff] & 0x0000ff00) ^
+				(Te4[(temp >> 24)       ] & 0x000000ff) ^
 				rcon[i];
 			rk[ 9] = rk[ 1] ^ rk[ 8];
 			rk[10] = rk[ 2] ^ rk[ 9];
@@ -807,10 +812,10 @@ int AES_set_encrypt_key(const unsigned char *userKey, const int bits,
 			}
 			temp = rk[11];
 			rk[12] = rk[ 4] ^
-                                (AES_Te4[(temp >> 24)       ] & 0xff000000) ^
-                                (AES_Te4[(temp >> 16) & 0xff] & 0x00ff0000) ^
-                                (AES_Te4[(temp >>  8) & 0xff] & 0x0000ff00) ^
-                                (AES_Te4[(temp      ) & 0xff] & 0x000000ff);
+				(Te4[(temp >> 24)       ] & 0xff000000) ^
+				(Te4[(temp >> 16) & 0xff] & 0x00ff0000) ^
+				(Te4[(temp >>  8) & 0xff] & 0x0000ff00) ^
+				(Te4[(temp      ) & 0xff] & 0x000000ff);
 			rk[13] = rk[ 5] ^ rk[12];
 			rk[14] = rk[ 6] ^ rk[13];
 			rk[15] = rk[ 7] ^ rk[14];
@@ -849,25 +854,25 @@ int AES_set_decrypt_key(const unsigned char *userKey, const int bits,
 	for (i = 1; i < (key->rounds); i++) {
 		rk += 4;
 		rk[0] =
-                        AES_Td0[AES_Te4[(rk[0] >> 24)       ] & 0xff] ^
-                        AES_Td1[AES_Te4[(rk[0] >> 16) & 0xff] & 0xff] ^
-                        AES_Td2[AES_Te4[(rk[0] >>  8) & 0xff] & 0xff] ^
-                        AES_Td3[AES_Te4[(rk[0]      ) & 0xff] & 0xff];
+			Td0[Te4[(rk[0] >> 24)       ] & 0xff] ^
+			Td1[Te4[(rk[0] >> 16) & 0xff] & 0xff] ^
+			Td2[Te4[(rk[0] >>  8) & 0xff] & 0xff] ^
+			Td3[Te4[(rk[0]      ) & 0xff] & 0xff];
 		rk[1] =
-                        AES_Td0[AES_Te4[(rk[1] >> 24)       ] & 0xff] ^
-                        AES_Td1[AES_Te4[(rk[1] >> 16) & 0xff] & 0xff] ^
-                        AES_Td2[AES_Te4[(rk[1] >>  8) & 0xff] & 0xff] ^
-                        AES_Td3[AES_Te4[(rk[1]      ) & 0xff] & 0xff];
+			Td0[Te4[(rk[1] >> 24)       ] & 0xff] ^
+			Td1[Te4[(rk[1] >> 16) & 0xff] & 0xff] ^
+			Td2[Te4[(rk[1] >>  8) & 0xff] & 0xff] ^
+			Td3[Te4[(rk[1]      ) & 0xff] & 0xff];
 		rk[2] =
-                        AES_Td0[AES_Te4[(rk[2] >> 24)       ] & 0xff] ^
-                        AES_Td1[AES_Te4[(rk[2] >> 16) & 0xff] & 0xff] ^
-                        AES_Td2[AES_Te4[(rk[2] >>  8) & 0xff] & 0xff] ^
-                        AES_Td3[AES_Te4[(rk[2]      ) & 0xff] & 0xff];
+			Td0[Te4[(rk[2] >> 24)       ] & 0xff] ^
+			Td1[Te4[(rk[2] >> 16) & 0xff] & 0xff] ^
+			Td2[Te4[(rk[2] >>  8) & 0xff] & 0xff] ^
+			Td3[Te4[(rk[2]      ) & 0xff] & 0xff];
 		rk[3] =
-                        AES_Td0[AES_Te4[(rk[3] >> 24)       ] & 0xff] ^
-                        AES_Td1[AES_Te4[(rk[3] >> 16) & 0xff] & 0xff] ^
-                        AES_Td2[AES_Te4[(rk[3] >>  8) & 0xff] & 0xff] ^
-                        AES_Td3[AES_Te4[(rk[3]      ) & 0xff] & 0xff];
+			Td0[Te4[(rk[3] >> 24)       ] & 0xff] ^
+			Td1[Te4[(rk[3] >> 16) & 0xff] & 0xff] ^
+			Td2[Te4[(rk[3] >>  8) & 0xff] & 0xff] ^
+			Td3[Te4[(rk[3]      ) & 0xff] & 0xff];
 	}
 	return 0;
 }
@@ -899,72 +904,72 @@ void AES_encrypt(const unsigned char *in, unsigned char *out,
 	s3 = GETU32(in + 12) ^ rk[3];
 #ifdef FULL_UNROLL
 	/* round 1: */
-        t0 = AES_Te0[s0 >> 24] ^ AES_Te1[(s1 >> 16) & 0xff] ^ AES_Te2[(s2 >>  8) & 0xff] ^ AES_Te3[s3 & 0xff] ^ rk[ 4];
-        t1 = AES_Te0[s1 >> 24] ^ AES_Te1[(s2 >> 16) & 0xff] ^ AES_Te2[(s3 >>  8) & 0xff] ^ AES_Te3[s0 & 0xff] ^ rk[ 5];
-        t2 = AES_Te0[s2 >> 24] ^ AES_Te1[(s3 >> 16) & 0xff] ^ AES_Te2[(s0 >>  8) & 0xff] ^ AES_Te3[s1 & 0xff] ^ rk[ 6];
-        t3 = AES_Te0[s3 >> 24] ^ AES_Te1[(s0 >> 16) & 0xff] ^ AES_Te2[(s1 >>  8) & 0xff] ^ AES_Te3[s2 & 0xff] ^ rk[ 7];
+   	t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >>  8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[ 4];
+   	t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >>  8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[ 5];
+   	t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >>  8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[ 6];
+   	t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >>  8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[ 7];
    	/* round 2: */
-        s0 = AES_Te0[t0 >> 24] ^ AES_Te1[(t1 >> 16) & 0xff] ^ AES_Te2[(t2 >>  8) & 0xff] ^ AES_Te3[t3 & 0xff] ^ rk[ 8];
-        s1 = AES_Te0[t1 >> 24] ^ AES_Te1[(t2 >> 16) & 0xff] ^ AES_Te2[(t3 >>  8) & 0xff] ^ AES_Te3[t0 & 0xff] ^ rk[ 9];
-        s2 = AES_Te0[t2 >> 24] ^ AES_Te1[(t3 >> 16) & 0xff] ^ AES_Te2[(t0 >>  8) & 0xff] ^ AES_Te3[t1 & 0xff] ^ rk[10];
-        s3 = AES_Te0[t3 >> 24] ^ AES_Te1[(t0 >> 16) & 0xff] ^ AES_Te2[(t1 >>  8) & 0xff] ^ AES_Te3[t2 & 0xff] ^ rk[11];
+   	s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >>  8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[ 8];
+   	s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >>  8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[ 9];
+   	s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >>  8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[10];
+   	s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >>  8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[11];
 	/* round 3: */
-        t0 = AES_Te0[s0 >> 24] ^ AES_Te1[(s1 >> 16) & 0xff] ^ AES_Te2[(s2 >>  8) & 0xff] ^ AES_Te3[s3 & 0xff] ^ rk[12];
-        t1 = AES_Te0[s1 >> 24] ^ AES_Te1[(s2 >> 16) & 0xff] ^ AES_Te2[(s3 >>  8) & 0xff] ^ AES_Te3[s0 & 0xff] ^ rk[13];
-        t2 = AES_Te0[s2 >> 24] ^ AES_Te1[(s3 >> 16) & 0xff] ^ AES_Te2[(s0 >>  8) & 0xff] ^ AES_Te3[s1 & 0xff] ^ rk[14];
-        t3 = AES_Te0[s3 >> 24] ^ AES_Te1[(s0 >> 16) & 0xff] ^ AES_Te2[(s1 >>  8) & 0xff] ^ AES_Te3[s2 & 0xff] ^ rk[15];
+   	t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >>  8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[12];
+   	t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >>  8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[13];
+   	t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >>  8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[14];
+   	t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >>  8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[15];
    	/* round 4: */
-        s0 = AES_Te0[t0 >> 24] ^ AES_Te1[(t1 >> 16) & 0xff] ^ AES_Te2[(t2 >>  8) & 0xff] ^ AES_Te3[t3 & 0xff] ^ rk[16];
-        s1 = AES_Te0[t1 >> 24] ^ AES_Te1[(t2 >> 16) & 0xff] ^ AES_Te2[(t3 >>  8) & 0xff] ^ AES_Te3[t0 & 0xff] ^ rk[17];
-        s2 = AES_Te0[t2 >> 24] ^ AES_Te1[(t3 >> 16) & 0xff] ^ AES_Te2[(t0 >>  8) & 0xff] ^ AES_Te3[t1 & 0xff] ^ rk[18];
-        s3 = AES_Te0[t3 >> 24] ^ AES_Te1[(t0 >> 16) & 0xff] ^ AES_Te2[(t1 >>  8) & 0xff] ^ AES_Te3[t2 & 0xff] ^ rk[19];
+   	s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >>  8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[16];
+   	s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >>  8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[17];
+   	s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >>  8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[18];
+   	s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >>  8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[19];
 	/* round 5: */
-        t0 = AES_Te0[s0 >> 24] ^ AES_Te1[(s1 >> 16) & 0xff] ^ AES_Te2[(s2 >>  8) & 0xff] ^ AES_Te3[s3 & 0xff] ^ rk[20];
-        t1 = AES_Te0[s1 >> 24] ^ AES_Te1[(s2 >> 16) & 0xff] ^ AES_Te2[(s3 >>  8) & 0xff] ^ AES_Te3[s0 & 0xff] ^ rk[21];
-        t2 = AES_Te0[s2 >> 24] ^ AES_Te1[(s3 >> 16) & 0xff] ^ AES_Te2[(s0 >>  8) & 0xff] ^ AES_Te3[s1 & 0xff] ^ rk[22];
-        t3 = AES_Te0[s3 >> 24] ^ AES_Te1[(s0 >> 16) & 0xff] ^ AES_Te2[(s1 >>  8) & 0xff] ^ AES_Te3[s2 & 0xff] ^ rk[23];
+   	t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >>  8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[20];
+   	t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >>  8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[21];
+   	t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >>  8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[22];
+   	t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >>  8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[23];
    	/* round 6: */
-        s0 = AES_Te0[t0 >> 24] ^ AES_Te1[(t1 >> 16) & 0xff] ^ AES_Te2[(t2 >>  8) & 0xff] ^ AES_Te3[t3 & 0xff] ^ rk[24];
-        s1 = AES_Te0[t1 >> 24] ^ AES_Te1[(t2 >> 16) & 0xff] ^ AES_Te2[(t3 >>  8) & 0xff] ^ AES_Te3[t0 & 0xff] ^ rk[25];
-        s2 = AES_Te0[t2 >> 24] ^ AES_Te1[(t3 >> 16) & 0xff] ^ AES_Te2[(t0 >>  8) & 0xff] ^ AES_Te3[t1 & 0xff] ^ rk[26];
-        s3 = AES_Te0[t3 >> 24] ^ AES_Te1[(t0 >> 16) & 0xff] ^ AES_Te2[(t1 >>  8) & 0xff] ^ AES_Te3[t2 & 0xff] ^ rk[27];
+   	s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >>  8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[24];
+   	s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >>  8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[25];
+   	s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >>  8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[26];
+   	s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >>  8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[27];
 	/* round 7: */
-        t0 = AES_Te0[s0 >> 24] ^ AES_Te1[(s1 >> 16) & 0xff] ^ AES_Te2[(s2 >>  8) & 0xff] ^ AES_Te3[s3 & 0xff] ^ rk[28];
-        t1 = AES_Te0[s1 >> 24] ^ AES_Te1[(s2 >> 16) & 0xff] ^ AES_Te2[(s3 >>  8) & 0xff] ^ AES_Te3[s0 & 0xff] ^ rk[29];
-        t2 = AES_Te0[s2 >> 24] ^ AES_Te1[(s3 >> 16) & 0xff] ^ AES_Te2[(s0 >>  8) & 0xff] ^ AES_Te3[s1 & 0xff] ^ rk[30];
-        t3 = AES_Te0[s3 >> 24] ^ AES_Te1[(s0 >> 16) & 0xff] ^ AES_Te2[(s1 >>  8) & 0xff] ^ AES_Te3[s2 & 0xff] ^ rk[31];
+   	t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >>  8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[28];
+   	t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >>  8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[29];
+   	t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >>  8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[30];
+   	t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >>  8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[31];
    	/* round 8: */
-        s0 = AES_Te0[t0 >> 24] ^ AES_Te1[(t1 >> 16) & 0xff] ^ AES_Te2[(t2 >>  8) & 0xff] ^ AES_Te3[t3 & 0xff] ^ rk[32];
-        s1 = AES_Te0[t1 >> 24] ^ AES_Te1[(t2 >> 16) & 0xff] ^ AES_Te2[(t3 >>  8) & 0xff] ^ AES_Te3[t0 & 0xff] ^ rk[33];
-        s2 = AES_Te0[t2 >> 24] ^ AES_Te1[(t3 >> 16) & 0xff] ^ AES_Te2[(t0 >>  8) & 0xff] ^ AES_Te3[t1 & 0xff] ^ rk[34];
-        s3 = AES_Te0[t3 >> 24] ^ AES_Te1[(t0 >> 16) & 0xff] ^ AES_Te2[(t1 >>  8) & 0xff] ^ AES_Te3[t2 & 0xff] ^ rk[35];
+   	s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >>  8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[32];
+   	s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >>  8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[33];
+   	s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >>  8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[34];
+   	s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >>  8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[35];
 	/* round 9: */
-        t0 = AES_Te0[s0 >> 24] ^ AES_Te1[(s1 >> 16) & 0xff] ^ AES_Te2[(s2 >>  8) & 0xff] ^ AES_Te3[s3 & 0xff] ^ rk[36];
-        t1 = AES_Te0[s1 >> 24] ^ AES_Te1[(s2 >> 16) & 0xff] ^ AES_Te2[(s3 >>  8) & 0xff] ^ AES_Te3[s0 & 0xff] ^ rk[37];
-        t2 = AES_Te0[s2 >> 24] ^ AES_Te1[(s3 >> 16) & 0xff] ^ AES_Te2[(s0 >>  8) & 0xff] ^ AES_Te3[s1 & 0xff] ^ rk[38];
-        t3 = AES_Te0[s3 >> 24] ^ AES_Te1[(s0 >> 16) & 0xff] ^ AES_Te2[(s1 >>  8) & 0xff] ^ AES_Te3[s2 & 0xff] ^ rk[39];
+   	t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >>  8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[36];
+   	t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >>  8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[37];
+   	t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >>  8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[38];
+   	t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >>  8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[39];
     if (key->rounds > 10) {
         /* round 10: */
-        s0 = AES_Te0[t0 >> 24] ^ AES_Te1[(t1 >> 16) & 0xff] ^ AES_Te2[(t2 >>  8) & 0xff] ^ AES_Te3[t3 & 0xff] ^ rk[40];
-        s1 = AES_Te0[t1 >> 24] ^ AES_Te1[(t2 >> 16) & 0xff] ^ AES_Te2[(t3 >>  8) & 0xff] ^ AES_Te3[t0 & 0xff] ^ rk[41];
-        s2 = AES_Te0[t2 >> 24] ^ AES_Te1[(t3 >> 16) & 0xff] ^ AES_Te2[(t0 >>  8) & 0xff] ^ AES_Te3[t1 & 0xff] ^ rk[42];
-        s3 = AES_Te0[t3 >> 24] ^ AES_Te1[(t0 >> 16) & 0xff] ^ AES_Te2[(t1 >>  8) & 0xff] ^ AES_Te3[t2 & 0xff] ^ rk[43];
+        s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >>  8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[40];
+        s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >>  8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[41];
+        s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >>  8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[42];
+        s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >>  8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[43];
         /* round 11: */
-        t0 = AES_Te0[s0 >> 24] ^ AES_Te1[(s1 >> 16) & 0xff] ^ AES_Te2[(s2 >>  8) & 0xff] ^ AES_Te3[s3 & 0xff] ^ rk[44];
-        t1 = AES_Te0[s1 >> 24] ^ AES_Te1[(s2 >> 16) & 0xff] ^ AES_Te2[(s3 >>  8) & 0xff] ^ AES_Te3[s0 & 0xff] ^ rk[45];
-        t2 = AES_Te0[s2 >> 24] ^ AES_Te1[(s3 >> 16) & 0xff] ^ AES_Te2[(s0 >>  8) & 0xff] ^ AES_Te3[s1 & 0xff] ^ rk[46];
-        t3 = AES_Te0[s3 >> 24] ^ AES_Te1[(s0 >> 16) & 0xff] ^ AES_Te2[(s1 >>  8) & 0xff] ^ AES_Te3[s2 & 0xff] ^ rk[47];
+        t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >>  8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[44];
+        t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >>  8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[45];
+        t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >>  8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[46];
+        t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >>  8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[47];
         if (key->rounds > 12) {
             /* round 12: */
-            s0 = AES_Te0[t0 >> 24] ^ AES_Te1[(t1 >> 16) & 0xff] ^ AES_Te2[(t2 >>  8) & 0xff] ^ AES_Te3[t3 & 0xff] ^ rk[48];
-            s1 = AES_Te0[t1 >> 24] ^ AES_Te1[(t2 >> 16) & 0xff] ^ AES_Te2[(t3 >>  8) & 0xff] ^ AES_Te3[t0 & 0xff] ^ rk[49];
-            s2 = AES_Te0[t2 >> 24] ^ AES_Te1[(t3 >> 16) & 0xff] ^ AES_Te2[(t0 >>  8) & 0xff] ^ AES_Te3[t1 & 0xff] ^ rk[50];
-            s3 = AES_Te0[t3 >> 24] ^ AES_Te1[(t0 >> 16) & 0xff] ^ AES_Te2[(t1 >>  8) & 0xff] ^ AES_Te3[t2 & 0xff] ^ rk[51];
+            s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >>  8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[48];
+            s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >>  8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[49];
+            s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >>  8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[50];
+            s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >>  8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[51];
             /* round 13: */
-            t0 = AES_Te0[s0 >> 24] ^ AES_Te1[(s1 >> 16) & 0xff] ^ AES_Te2[(s2 >>  8) & 0xff] ^ AES_Te3[s3 & 0xff] ^ rk[52];
-            t1 = AES_Te0[s1 >> 24] ^ AES_Te1[(s2 >> 16) & 0xff] ^ AES_Te2[(s3 >>  8) & 0xff] ^ AES_Te3[s0 & 0xff] ^ rk[53];
-            t2 = AES_Te0[s2 >> 24] ^ AES_Te1[(s3 >> 16) & 0xff] ^ AES_Te2[(s0 >>  8) & 0xff] ^ AES_Te3[s1 & 0xff] ^ rk[54];
-            t3 = AES_Te0[s3 >> 24] ^ AES_Te1[(s0 >> 16) & 0xff] ^ AES_Te2[(s1 >>  8) & 0xff] ^ AES_Te3[s2 & 0xff] ^ rk[55];
+            t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >>  8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[52];
+            t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >>  8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[53];
+            t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >>  8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[54];
+            t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >>  8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[55];
         }
     }
     rk += key->rounds << 2;
@@ -975,28 +980,28 @@ void AES_encrypt(const unsigned char *in, unsigned char *out,
     r = key->rounds >> 1;
     for (;;) {
         t0 =
-            AES_Te0[(s0 >> 24)       ] ^
-            AES_Te1[(s1 >> 16) & 0xff] ^
-            AES_Te2[(s2 >>  8) & 0xff] ^
-            AES_Te3[(s3      ) & 0xff] ^
+            Te0[(s0 >> 24)       ] ^
+            Te1[(s1 >> 16) & 0xff] ^
+            Te2[(s2 >>  8) & 0xff] ^
+            Te3[(s3      ) & 0xff] ^
             rk[4];
         t1 =
-            AES_Te0[(s1 >> 24)       ] ^
-            AES_Te1[(s2 >> 16) & 0xff] ^
-            AES_Te2[(s3 >>  8) & 0xff] ^
-            AES_Te3[(s0      ) & 0xff] ^
+            Te0[(s1 >> 24)       ] ^
+            Te1[(s2 >> 16) & 0xff] ^
+            Te2[(s3 >>  8) & 0xff] ^
+            Te3[(s0      ) & 0xff] ^
             rk[5];
         t2 =
-            AES_Te0[(s2 >> 24)       ] ^
-            AES_Te1[(s3 >> 16) & 0xff] ^
-            AES_Te2[(s0 >>  8) & 0xff] ^
-            AES_Te3[(s1      ) & 0xff] ^
+            Te0[(s2 >> 24)       ] ^
+            Te1[(s3 >> 16) & 0xff] ^
+            Te2[(s0 >>  8) & 0xff] ^
+            Te3[(s1      ) & 0xff] ^
             rk[6];
         t3 =
-            AES_Te0[(s3 >> 24)       ] ^
-            AES_Te1[(s0 >> 16) & 0xff] ^
-            AES_Te2[(s1 >>  8) & 0xff] ^
-            AES_Te3[(s2      ) & 0xff] ^
+            Te0[(s3 >> 24)       ] ^
+            Te1[(s0 >> 16) & 0xff] ^
+            Te2[(s1 >>  8) & 0xff] ^
+            Te3[(s2      ) & 0xff] ^
             rk[7];
 
         rk += 8;
@@ -1005,28 +1010,28 @@ void AES_encrypt(const unsigned char *in, unsigned char *out,
         }
 
         s0 =
-            AES_Te0[(t0 >> 24)       ] ^
-            AES_Te1[(t1 >> 16) & 0xff] ^
-            AES_Te2[(t2 >>  8) & 0xff] ^
-            AES_Te3[(t3      ) & 0xff] ^
+            Te0[(t0 >> 24)       ] ^
+            Te1[(t1 >> 16) & 0xff] ^
+            Te2[(t2 >>  8) & 0xff] ^
+            Te3[(t3      ) & 0xff] ^
             rk[0];
         s1 =
-            AES_Te0[(t1 >> 24)       ] ^
-            AES_Te1[(t2 >> 16) & 0xff] ^
-            AES_Te2[(t3 >>  8) & 0xff] ^
-            AES_Te3[(t0      ) & 0xff] ^
+            Te0[(t1 >> 24)       ] ^
+            Te1[(t2 >> 16) & 0xff] ^
+            Te2[(t3 >>  8) & 0xff] ^
+            Te3[(t0      ) & 0xff] ^
             rk[1];
         s2 =
-            AES_Te0[(t2 >> 24)       ] ^
-            AES_Te1[(t3 >> 16) & 0xff] ^
-            AES_Te2[(t0 >>  8) & 0xff] ^
-            AES_Te3[(t1      ) & 0xff] ^
+            Te0[(t2 >> 24)       ] ^
+            Te1[(t3 >> 16) & 0xff] ^
+            Te2[(t0 >>  8) & 0xff] ^
+            Te3[(t1      ) & 0xff] ^
             rk[2];
         s3 =
-            AES_Te0[(t3 >> 24)       ] ^
-            AES_Te1[(t0 >> 16) & 0xff] ^
-            AES_Te2[(t1 >>  8) & 0xff] ^
-            AES_Te3[(t2      ) & 0xff] ^
+            Te0[(t3 >> 24)       ] ^
+            Te1[(t0 >> 16) & 0xff] ^
+            Te2[(t1 >>  8) & 0xff] ^
+            Te3[(t2      ) & 0xff] ^
             rk[3];
     }
 #endif /* ?FULL_UNROLL */
@@ -1035,31 +1040,31 @@ void AES_encrypt(const unsigned char *in, unsigned char *out,
 	 * map cipher state to byte array block:
 	 */
 	s0 =
-                (AES_Te4[(t0 >> 24)       ] & 0xff000000) ^
-                (AES_Te4[(t1 >> 16) & 0xff] & 0x00ff0000) ^
-                (AES_Te4[(t2 >>  8) & 0xff] & 0x0000ff00) ^
-                (AES_Te4[(t3      ) & 0xff] & 0x000000ff) ^
+		(Te4[(t0 >> 24)       ] & 0xff000000) ^
+		(Te4[(t1 >> 16) & 0xff] & 0x00ff0000) ^
+		(Te4[(t2 >>  8) & 0xff] & 0x0000ff00) ^
+		(Te4[(t3      ) & 0xff] & 0x000000ff) ^
 		rk[0];
 	PUTU32(out     , s0);
 	s1 =
-                (AES_Te4[(t1 >> 24)       ] & 0xff000000) ^
-                (AES_Te4[(t2 >> 16) & 0xff] & 0x00ff0000) ^
-                (AES_Te4[(t3 >>  8) & 0xff] & 0x0000ff00) ^
-                (AES_Te4[(t0      ) & 0xff] & 0x000000ff) ^
+		(Te4[(t1 >> 24)       ] & 0xff000000) ^
+		(Te4[(t2 >> 16) & 0xff] & 0x00ff0000) ^
+		(Te4[(t3 >>  8) & 0xff] & 0x0000ff00) ^
+		(Te4[(t0      ) & 0xff] & 0x000000ff) ^
 		rk[1];
 	PUTU32(out +  4, s1);
 	s2 =
-                (AES_Te4[(t2 >> 24)       ] & 0xff000000) ^
-                (AES_Te4[(t3 >> 16) & 0xff] & 0x00ff0000) ^
-                (AES_Te4[(t0 >>  8) & 0xff] & 0x0000ff00) ^
-                (AES_Te4[(t1      ) & 0xff] & 0x000000ff) ^
+		(Te4[(t2 >> 24)       ] & 0xff000000) ^
+		(Te4[(t3 >> 16) & 0xff] & 0x00ff0000) ^
+		(Te4[(t0 >>  8) & 0xff] & 0x0000ff00) ^
+		(Te4[(t1      ) & 0xff] & 0x000000ff) ^
 		rk[2];
 	PUTU32(out +  8, s2);
 	s3 =
-                (AES_Te4[(t3 >> 24)       ] & 0xff000000) ^
-                (AES_Te4[(t0 >> 16) & 0xff] & 0x00ff0000) ^
-                (AES_Te4[(t1 >>  8) & 0xff] & 0x0000ff00) ^
-                (AES_Te4[(t2      ) & 0xff] & 0x000000ff) ^
+		(Te4[(t3 >> 24)       ] & 0xff000000) ^
+		(Te4[(t0 >> 16) & 0xff] & 0x00ff0000) ^
+		(Te4[(t1 >>  8) & 0xff] & 0x0000ff00) ^
+		(Te4[(t2      ) & 0xff] & 0x000000ff) ^
 		rk[3];
 	PUTU32(out + 12, s3);
 }
@@ -1090,72 +1095,72 @@ void AES_decrypt(const unsigned char *in, unsigned char *out,
     s3 = GETU32(in + 12) ^ rk[3];
 #ifdef FULL_UNROLL
     /* round 1: */
-    t0 = AES_Td0[s0 >> 24] ^ AES_Td1[(s3 >> 16) & 0xff] ^ AES_Td2[(s2 >>  8) & 0xff] ^ AES_Td3[s1 & 0xff] ^ rk[ 4];
-    t1 = AES_Td0[s1 >> 24] ^ AES_Td1[(s0 >> 16) & 0xff] ^ AES_Td2[(s3 >>  8) & 0xff] ^ AES_Td3[s2 & 0xff] ^ rk[ 5];
-    t2 = AES_Td0[s2 >> 24] ^ AES_Td1[(s1 >> 16) & 0xff] ^ AES_Td2[(s0 >>  8) & 0xff] ^ AES_Td3[s3 & 0xff] ^ rk[ 6];
-    t3 = AES_Td0[s3 >> 24] ^ AES_Td1[(s2 >> 16) & 0xff] ^ AES_Td2[(s1 >>  8) & 0xff] ^ AES_Td3[s0 & 0xff] ^ rk[ 7];
+    t0 = Td0[s0 >> 24] ^ Td1[(s3 >> 16) & 0xff] ^ Td2[(s2 >>  8) & 0xff] ^ Td3[s1 & 0xff] ^ rk[ 4];
+    t1 = Td0[s1 >> 24] ^ Td1[(s0 >> 16) & 0xff] ^ Td2[(s3 >>  8) & 0xff] ^ Td3[s2 & 0xff] ^ rk[ 5];
+    t2 = Td0[s2 >> 24] ^ Td1[(s1 >> 16) & 0xff] ^ Td2[(s0 >>  8) & 0xff] ^ Td3[s3 & 0xff] ^ rk[ 6];
+    t3 = Td0[s3 >> 24] ^ Td1[(s2 >> 16) & 0xff] ^ Td2[(s1 >>  8) & 0xff] ^ Td3[s0 & 0xff] ^ rk[ 7];
     /* round 2: */
-    s0 = AES_Td0[t0 >> 24] ^ AES_Td1[(t3 >> 16) & 0xff] ^ AES_Td2[(t2 >>  8) & 0xff] ^ AES_Td3[t1 & 0xff] ^ rk[ 8];
-    s1 = AES_Td0[t1 >> 24] ^ AES_Td1[(t0 >> 16) & 0xff] ^ AES_Td2[(t3 >>  8) & 0xff] ^ AES_Td3[t2 & 0xff] ^ rk[ 9];
-    s2 = AES_Td0[t2 >> 24] ^ AES_Td1[(t1 >> 16) & 0xff] ^ AES_Td2[(t0 >>  8) & 0xff] ^ AES_Td3[t3 & 0xff] ^ rk[10];
-    s3 = AES_Td0[t3 >> 24] ^ AES_Td1[(t2 >> 16) & 0xff] ^ AES_Td2[(t1 >>  8) & 0xff] ^ AES_Td3[t0 & 0xff] ^ rk[11];
+    s0 = Td0[t0 >> 24] ^ Td1[(t3 >> 16) & 0xff] ^ Td2[(t2 >>  8) & 0xff] ^ Td3[t1 & 0xff] ^ rk[ 8];
+    s1 = Td0[t1 >> 24] ^ Td1[(t0 >> 16) & 0xff] ^ Td2[(t3 >>  8) & 0xff] ^ Td3[t2 & 0xff] ^ rk[ 9];
+    s2 = Td0[t2 >> 24] ^ Td1[(t1 >> 16) & 0xff] ^ Td2[(t0 >>  8) & 0xff] ^ Td3[t3 & 0xff] ^ rk[10];
+    s3 = Td0[t3 >> 24] ^ Td1[(t2 >> 16) & 0xff] ^ Td2[(t1 >>  8) & 0xff] ^ Td3[t0 & 0xff] ^ rk[11];
     /* round 3: */
-    t0 = AES_Td0[s0 >> 24] ^ AES_Td1[(s3 >> 16) & 0xff] ^ AES_Td2[(s2 >>  8) & 0xff] ^ AES_Td3[s1 & 0xff] ^ rk[12];
-    t1 = AES_Td0[s1 >> 24] ^ AES_Td1[(s0 >> 16) & 0xff] ^ AES_Td2[(s3 >>  8) & 0xff] ^ AES_Td3[s2 & 0xff] ^ rk[13];
-    t2 = AES_Td0[s2 >> 24] ^ AES_Td1[(s1 >> 16) & 0xff] ^ AES_Td2[(s0 >>  8) & 0xff] ^ AES_Td3[s3 & 0xff] ^ rk[14];
-    t3 = AES_Td0[s3 >> 24] ^ AES_Td1[(s2 >> 16) & 0xff] ^ AES_Td2[(s1 >>  8) & 0xff] ^ AES_Td3[s0 & 0xff] ^ rk[15];
+    t0 = Td0[s0 >> 24] ^ Td1[(s3 >> 16) & 0xff] ^ Td2[(s2 >>  8) & 0xff] ^ Td3[s1 & 0xff] ^ rk[12];
+    t1 = Td0[s1 >> 24] ^ Td1[(s0 >> 16) & 0xff] ^ Td2[(s3 >>  8) & 0xff] ^ Td3[s2 & 0xff] ^ rk[13];
+    t2 = Td0[s2 >> 24] ^ Td1[(s1 >> 16) & 0xff] ^ Td2[(s0 >>  8) & 0xff] ^ Td3[s3 & 0xff] ^ rk[14];
+    t3 = Td0[s3 >> 24] ^ Td1[(s2 >> 16) & 0xff] ^ Td2[(s1 >>  8) & 0xff] ^ Td3[s0 & 0xff] ^ rk[15];
     /* round 4: */
-    s0 = AES_Td0[t0 >> 24] ^ AES_Td1[(t3 >> 16) & 0xff] ^ AES_Td2[(t2 >>  8) & 0xff] ^ AES_Td3[t1 & 0xff] ^ rk[16];
-    s1 = AES_Td0[t1 >> 24] ^ AES_Td1[(t0 >> 16) & 0xff] ^ AES_Td2[(t3 >>  8) & 0xff] ^ AES_Td3[t2 & 0xff] ^ rk[17];
-    s2 = AES_Td0[t2 >> 24] ^ AES_Td1[(t1 >> 16) & 0xff] ^ AES_Td2[(t0 >>  8) & 0xff] ^ AES_Td3[t3 & 0xff] ^ rk[18];
-    s3 = AES_Td0[t3 >> 24] ^ AES_Td1[(t2 >> 16) & 0xff] ^ AES_Td2[(t1 >>  8) & 0xff] ^ AES_Td3[t0 & 0xff] ^ rk[19];
+    s0 = Td0[t0 >> 24] ^ Td1[(t3 >> 16) & 0xff] ^ Td2[(t2 >>  8) & 0xff] ^ Td3[t1 & 0xff] ^ rk[16];
+    s1 = Td0[t1 >> 24] ^ Td1[(t0 >> 16) & 0xff] ^ Td2[(t3 >>  8) & 0xff] ^ Td3[t2 & 0xff] ^ rk[17];
+    s2 = Td0[t2 >> 24] ^ Td1[(t1 >> 16) & 0xff] ^ Td2[(t0 >>  8) & 0xff] ^ Td3[t3 & 0xff] ^ rk[18];
+    s3 = Td0[t3 >> 24] ^ Td1[(t2 >> 16) & 0xff] ^ Td2[(t1 >>  8) & 0xff] ^ Td3[t0 & 0xff] ^ rk[19];
     /* round 5: */
-    t0 = AES_Td0[s0 >> 24] ^ AES_Td1[(s3 >> 16) & 0xff] ^ AES_Td2[(s2 >>  8) & 0xff] ^ AES_Td3[s1 & 0xff] ^ rk[20];
-    t1 = AES_Td0[s1 >> 24] ^ AES_Td1[(s0 >> 16) & 0xff] ^ AES_Td2[(s3 >>  8) & 0xff] ^ AES_Td3[s2 & 0xff] ^ rk[21];
-    t2 = AES_Td0[s2 >> 24] ^ AES_Td1[(s1 >> 16) & 0xff] ^ AES_Td2[(s0 >>  8) & 0xff] ^ AES_Td3[s3 & 0xff] ^ rk[22];
-    t3 = AES_Td0[s3 >> 24] ^ AES_Td1[(s2 >> 16) & 0xff] ^ AES_Td2[(s1 >>  8) & 0xff] ^ AES_Td3[s0 & 0xff] ^ rk[23];
+    t0 = Td0[s0 >> 24] ^ Td1[(s3 >> 16) & 0xff] ^ Td2[(s2 >>  8) & 0xff] ^ Td3[s1 & 0xff] ^ rk[20];
+    t1 = Td0[s1 >> 24] ^ Td1[(s0 >> 16) & 0xff] ^ Td2[(s3 >>  8) & 0xff] ^ Td3[s2 & 0xff] ^ rk[21];
+    t2 = Td0[s2 >> 24] ^ Td1[(s1 >> 16) & 0xff] ^ Td2[(s0 >>  8) & 0xff] ^ Td3[s3 & 0xff] ^ rk[22];
+    t3 = Td0[s3 >> 24] ^ Td1[(s2 >> 16) & 0xff] ^ Td2[(s1 >>  8) & 0xff] ^ Td3[s0 & 0xff] ^ rk[23];
     /* round 6: */
-    s0 = AES_Td0[t0 >> 24] ^ AES_Td1[(t3 >> 16) & 0xff] ^ AES_Td2[(t2 >>  8) & 0xff] ^ AES_Td3[t1 & 0xff] ^ rk[24];
-    s1 = AES_Td0[t1 >> 24] ^ AES_Td1[(t0 >> 16) & 0xff] ^ AES_Td2[(t3 >>  8) & 0xff] ^ AES_Td3[t2 & 0xff] ^ rk[25];
-    s2 = AES_Td0[t2 >> 24] ^ AES_Td1[(t1 >> 16) & 0xff] ^ AES_Td2[(t0 >>  8) & 0xff] ^ AES_Td3[t3 & 0xff] ^ rk[26];
-    s3 = AES_Td0[t3 >> 24] ^ AES_Td1[(t2 >> 16) & 0xff] ^ AES_Td2[(t1 >>  8) & 0xff] ^ AES_Td3[t0 & 0xff] ^ rk[27];
+    s0 = Td0[t0 >> 24] ^ Td1[(t3 >> 16) & 0xff] ^ Td2[(t2 >>  8) & 0xff] ^ Td3[t1 & 0xff] ^ rk[24];
+    s1 = Td0[t1 >> 24] ^ Td1[(t0 >> 16) & 0xff] ^ Td2[(t3 >>  8) & 0xff] ^ Td3[t2 & 0xff] ^ rk[25];
+    s2 = Td0[t2 >> 24] ^ Td1[(t1 >> 16) & 0xff] ^ Td2[(t0 >>  8) & 0xff] ^ Td3[t3 & 0xff] ^ rk[26];
+    s3 = Td0[t3 >> 24] ^ Td1[(t2 >> 16) & 0xff] ^ Td2[(t1 >>  8) & 0xff] ^ Td3[t0 & 0xff] ^ rk[27];
     /* round 7: */
-    t0 = AES_Td0[s0 >> 24] ^ AES_Td1[(s3 >> 16) & 0xff] ^ AES_Td2[(s2 >>  8) & 0xff] ^ AES_Td3[s1 & 0xff] ^ rk[28];
-    t1 = AES_Td0[s1 >> 24] ^ AES_Td1[(s0 >> 16) & 0xff] ^ AES_Td2[(s3 >>  8) & 0xff] ^ AES_Td3[s2 & 0xff] ^ rk[29];
-    t2 = AES_Td0[s2 >> 24] ^ AES_Td1[(s1 >> 16) & 0xff] ^ AES_Td2[(s0 >>  8) & 0xff] ^ AES_Td3[s3 & 0xff] ^ rk[30];
-    t3 = AES_Td0[s3 >> 24] ^ AES_Td1[(s2 >> 16) & 0xff] ^ AES_Td2[(s1 >>  8) & 0xff] ^ AES_Td3[s0 & 0xff] ^ rk[31];
+    t0 = Td0[s0 >> 24] ^ Td1[(s3 >> 16) & 0xff] ^ Td2[(s2 >>  8) & 0xff] ^ Td3[s1 & 0xff] ^ rk[28];
+    t1 = Td0[s1 >> 24] ^ Td1[(s0 >> 16) & 0xff] ^ Td2[(s3 >>  8) & 0xff] ^ Td3[s2 & 0xff] ^ rk[29];
+    t2 = Td0[s2 >> 24] ^ Td1[(s1 >> 16) & 0xff] ^ Td2[(s0 >>  8) & 0xff] ^ Td3[s3 & 0xff] ^ rk[30];
+    t3 = Td0[s3 >> 24] ^ Td1[(s2 >> 16) & 0xff] ^ Td2[(s1 >>  8) & 0xff] ^ Td3[s0 & 0xff] ^ rk[31];
     /* round 8: */
-    s0 = AES_Td0[t0 >> 24] ^ AES_Td1[(t3 >> 16) & 0xff] ^ AES_Td2[(t2 >>  8) & 0xff] ^ AES_Td3[t1 & 0xff] ^ rk[32];
-    s1 = AES_Td0[t1 >> 24] ^ AES_Td1[(t0 >> 16) & 0xff] ^ AES_Td2[(t3 >>  8) & 0xff] ^ AES_Td3[t2 & 0xff] ^ rk[33];
-    s2 = AES_Td0[t2 >> 24] ^ AES_Td1[(t1 >> 16) & 0xff] ^ AES_Td2[(t0 >>  8) & 0xff] ^ AES_Td3[t3 & 0xff] ^ rk[34];
-    s3 = AES_Td0[t3 >> 24] ^ AES_Td1[(t2 >> 16) & 0xff] ^ AES_Td2[(t1 >>  8) & 0xff] ^ AES_Td3[t0 & 0xff] ^ rk[35];
+    s0 = Td0[t0 >> 24] ^ Td1[(t3 >> 16) & 0xff] ^ Td2[(t2 >>  8) & 0xff] ^ Td3[t1 & 0xff] ^ rk[32];
+    s1 = Td0[t1 >> 24] ^ Td1[(t0 >> 16) & 0xff] ^ Td2[(t3 >>  8) & 0xff] ^ Td3[t2 & 0xff] ^ rk[33];
+    s2 = Td0[t2 >> 24] ^ Td1[(t1 >> 16) & 0xff] ^ Td2[(t0 >>  8) & 0xff] ^ Td3[t3 & 0xff] ^ rk[34];
+    s3 = Td0[t3 >> 24] ^ Td1[(t2 >> 16) & 0xff] ^ Td2[(t1 >>  8) & 0xff] ^ Td3[t0 & 0xff] ^ rk[35];
     /* round 9: */
-    t0 = AES_Td0[s0 >> 24] ^ AES_Td1[(s3 >> 16) & 0xff] ^ AES_Td2[(s2 >>  8) & 0xff] ^ AES_Td3[s1 & 0xff] ^ rk[36];
-    t1 = AES_Td0[s1 >> 24] ^ AES_Td1[(s0 >> 16) & 0xff] ^ AES_Td2[(s3 >>  8) & 0xff] ^ AES_Td3[s2 & 0xff] ^ rk[37];
-    t2 = AES_Td0[s2 >> 24] ^ AES_Td1[(s1 >> 16) & 0xff] ^ AES_Td2[(s0 >>  8) & 0xff] ^ AES_Td3[s3 & 0xff] ^ rk[38];
-    t3 = AES_Td0[s3 >> 24] ^ AES_Td1[(s2 >> 16) & 0xff] ^ AES_Td2[(s1 >>  8) & 0xff] ^ AES_Td3[s0 & 0xff] ^ rk[39];
+    t0 = Td0[s0 >> 24] ^ Td1[(s3 >> 16) & 0xff] ^ Td2[(s2 >>  8) & 0xff] ^ Td3[s1 & 0xff] ^ rk[36];
+    t1 = Td0[s1 >> 24] ^ Td1[(s0 >> 16) & 0xff] ^ Td2[(s3 >>  8) & 0xff] ^ Td3[s2 & 0xff] ^ rk[37];
+    t2 = Td0[s2 >> 24] ^ Td1[(s1 >> 16) & 0xff] ^ Td2[(s0 >>  8) & 0xff] ^ Td3[s3 & 0xff] ^ rk[38];
+    t3 = Td0[s3 >> 24] ^ Td1[(s2 >> 16) & 0xff] ^ Td2[(s1 >>  8) & 0xff] ^ Td3[s0 & 0xff] ^ rk[39];
     if (key->rounds > 10) {
         /* round 10: */
-        s0 = AES_Td0[t0 >> 24] ^ AES_Td1[(t3 >> 16) & 0xff] ^ AES_Td2[(t2 >>  8) & 0xff] ^ AES_Td3[t1 & 0xff] ^ rk[40];
-        s1 = AES_Td0[t1 >> 24] ^ AES_Td1[(t0 >> 16) & 0xff] ^ AES_Td2[(t3 >>  8) & 0xff] ^ AES_Td3[t2 & 0xff] ^ rk[41];
-        s2 = AES_Td0[t2 >> 24] ^ AES_Td1[(t1 >> 16) & 0xff] ^ AES_Td2[(t0 >>  8) & 0xff] ^ AES_Td3[t3 & 0xff] ^ rk[42];
-        s3 = AES_Td0[t3 >> 24] ^ AES_Td1[(t2 >> 16) & 0xff] ^ AES_Td2[(t1 >>  8) & 0xff] ^ AES_Td3[t0 & 0xff] ^ rk[43];
+        s0 = Td0[t0 >> 24] ^ Td1[(t3 >> 16) & 0xff] ^ Td2[(t2 >>  8) & 0xff] ^ Td3[t1 & 0xff] ^ rk[40];
+        s1 = Td0[t1 >> 24] ^ Td1[(t0 >> 16) & 0xff] ^ Td2[(t3 >>  8) & 0xff] ^ Td3[t2 & 0xff] ^ rk[41];
+        s2 = Td0[t2 >> 24] ^ Td1[(t1 >> 16) & 0xff] ^ Td2[(t0 >>  8) & 0xff] ^ Td3[t3 & 0xff] ^ rk[42];
+        s3 = Td0[t3 >> 24] ^ Td1[(t2 >> 16) & 0xff] ^ Td2[(t1 >>  8) & 0xff] ^ Td3[t0 & 0xff] ^ rk[43];
         /* round 11: */
-        t0 = AES_Td0[s0 >> 24] ^ AES_Td1[(s3 >> 16) & 0xff] ^ AES_Td2[(s2 >>  8) & 0xff] ^ AES_Td3[s1 & 0xff] ^ rk[44];
-        t1 = AES_Td0[s1 >> 24] ^ AES_Td1[(s0 >> 16) & 0xff] ^ AES_Td2[(s3 >>  8) & 0xff] ^ AES_Td3[s2 & 0xff] ^ rk[45];
-        t2 = AES_Td0[s2 >> 24] ^ AES_Td1[(s1 >> 16) & 0xff] ^ AES_Td2[(s0 >>  8) & 0xff] ^ AES_Td3[s3 & 0xff] ^ rk[46];
-        t3 = AES_Td0[s3 >> 24] ^ AES_Td1[(s2 >> 16) & 0xff] ^ AES_Td2[(s1 >>  8) & 0xff] ^ AES_Td3[s0 & 0xff] ^ rk[47];
+        t0 = Td0[s0 >> 24] ^ Td1[(s3 >> 16) & 0xff] ^ Td2[(s2 >>  8) & 0xff] ^ Td3[s1 & 0xff] ^ rk[44];
+        t1 = Td0[s1 >> 24] ^ Td1[(s0 >> 16) & 0xff] ^ Td2[(s3 >>  8) & 0xff] ^ Td3[s2 & 0xff] ^ rk[45];
+        t2 = Td0[s2 >> 24] ^ Td1[(s1 >> 16) & 0xff] ^ Td2[(s0 >>  8) & 0xff] ^ Td3[s3 & 0xff] ^ rk[46];
+        t3 = Td0[s3 >> 24] ^ Td1[(s2 >> 16) & 0xff] ^ Td2[(s1 >>  8) & 0xff] ^ Td3[s0 & 0xff] ^ rk[47];
         if (key->rounds > 12) {
             /* round 12: */
-            s0 = AES_Td0[t0 >> 24] ^ AES_Td1[(t3 >> 16) & 0xff] ^ AES_Td2[(t2 >>  8) & 0xff] ^ AES_Td3[t1 & 0xff] ^ rk[48];
-            s1 = AES_Td0[t1 >> 24] ^ AES_Td1[(t0 >> 16) & 0xff] ^ AES_Td2[(t3 >>  8) & 0xff] ^ AES_Td3[t2 & 0xff] ^ rk[49];
-            s2 = AES_Td0[t2 >> 24] ^ AES_Td1[(t1 >> 16) & 0xff] ^ AES_Td2[(t0 >>  8) & 0xff] ^ AES_Td3[t3 & 0xff] ^ rk[50];
-            s3 = AES_Td0[t3 >> 24] ^ AES_Td1[(t2 >> 16) & 0xff] ^ AES_Td2[(t1 >>  8) & 0xff] ^ AES_Td3[t0 & 0xff] ^ rk[51];
+            s0 = Td0[t0 >> 24] ^ Td1[(t3 >> 16) & 0xff] ^ Td2[(t2 >>  8) & 0xff] ^ Td3[t1 & 0xff] ^ rk[48];
+            s1 = Td0[t1 >> 24] ^ Td1[(t0 >> 16) & 0xff] ^ Td2[(t3 >>  8) & 0xff] ^ Td3[t2 & 0xff] ^ rk[49];
+            s2 = Td0[t2 >> 24] ^ Td1[(t1 >> 16) & 0xff] ^ Td2[(t0 >>  8) & 0xff] ^ Td3[t3 & 0xff] ^ rk[50];
+            s3 = Td0[t3 >> 24] ^ Td1[(t2 >> 16) & 0xff] ^ Td2[(t1 >>  8) & 0xff] ^ Td3[t0 & 0xff] ^ rk[51];
             /* round 13: */
-            t0 = AES_Td0[s0 >> 24] ^ AES_Td1[(s3 >> 16) & 0xff] ^ AES_Td2[(s2 >>  8) & 0xff] ^ AES_Td3[s1 & 0xff] ^ rk[52];
-            t1 = AES_Td0[s1 >> 24] ^ AES_Td1[(s0 >> 16) & 0xff] ^ AES_Td2[(s3 >>  8) & 0xff] ^ AES_Td3[s2 & 0xff] ^ rk[53];
-            t2 = AES_Td0[s2 >> 24] ^ AES_Td1[(s1 >> 16) & 0xff] ^ AES_Td2[(s0 >>  8) & 0xff] ^ AES_Td3[s3 & 0xff] ^ rk[54];
-            t3 = AES_Td0[s3 >> 24] ^ AES_Td1[(s2 >> 16) & 0xff] ^ AES_Td2[(s1 >>  8) & 0xff] ^ AES_Td3[s0 & 0xff] ^ rk[55];
+            t0 = Td0[s0 >> 24] ^ Td1[(s3 >> 16) & 0xff] ^ Td2[(s2 >>  8) & 0xff] ^ Td3[s1 & 0xff] ^ rk[52];
+            t1 = Td0[s1 >> 24] ^ Td1[(s0 >> 16) & 0xff] ^ Td2[(s3 >>  8) & 0xff] ^ Td3[s2 & 0xff] ^ rk[53];
+            t2 = Td0[s2 >> 24] ^ Td1[(s1 >> 16) & 0xff] ^ Td2[(s0 >>  8) & 0xff] ^ Td3[s3 & 0xff] ^ rk[54];
+            t3 = Td0[s3 >> 24] ^ Td1[(s2 >> 16) & 0xff] ^ Td2[(s1 >>  8) & 0xff] ^ Td3[s0 & 0xff] ^ rk[55];
         }
     }
 	rk += key->rounds << 2;
@@ -1166,28 +1171,28 @@ void AES_decrypt(const unsigned char *in, unsigned char *out,
     r = key->rounds >> 1;
     for (;;) {
         t0 =
-            AES_Td0[(s0 >> 24)       ] ^
-            AES_Td1[(s3 >> 16) & 0xff] ^
-            AES_Td2[(s2 >>  8) & 0xff] ^
-            AES_Td3[(s1      ) & 0xff] ^
+            Td0[(s0 >> 24)       ] ^
+            Td1[(s3 >> 16) & 0xff] ^
+            Td2[(s2 >>  8) & 0xff] ^
+            Td3[(s1      ) & 0xff] ^
             rk[4];
         t1 =
-            AES_Td0[(s1 >> 24)       ] ^
-            AES_Td1[(s0 >> 16) & 0xff] ^
-            AES_Td2[(s3 >>  8) & 0xff] ^
-            AES_Td3[(s2      ) & 0xff] ^
+            Td0[(s1 >> 24)       ] ^
+            Td1[(s0 >> 16) & 0xff] ^
+            Td2[(s3 >>  8) & 0xff] ^
+            Td3[(s2      ) & 0xff] ^
             rk[5];
         t2 =
-            AES_Td0[(s2 >> 24)       ] ^
-            AES_Td1[(s1 >> 16) & 0xff] ^
-            AES_Td2[(s0 >>  8) & 0xff] ^
-            AES_Td3[(s3      ) & 0xff] ^
+            Td0[(s2 >> 24)       ] ^
+            Td1[(s1 >> 16) & 0xff] ^
+            Td2[(s0 >>  8) & 0xff] ^
+            Td3[(s3      ) & 0xff] ^
             rk[6];
         t3 =
-            AES_Td0[(s3 >> 24)       ] ^
-            AES_Td1[(s2 >> 16) & 0xff] ^
-            AES_Td2[(s1 >>  8) & 0xff] ^
-            AES_Td3[(s0      ) & 0xff] ^
+            Td0[(s3 >> 24)       ] ^
+            Td1[(s2 >> 16) & 0xff] ^
+            Td2[(s1 >>  8) & 0xff] ^
+            Td3[(s0      ) & 0xff] ^
             rk[7];
 
         rk += 8;
@@ -1196,28 +1201,28 @@ void AES_decrypt(const unsigned char *in, unsigned char *out,
         }
 
         s0 =
-            AES_Td0[(t0 >> 24)       ] ^
-            AES_Td1[(t3 >> 16) & 0xff] ^
-            AES_Td2[(t2 >>  8) & 0xff] ^
-            AES_Td3[(t1      ) & 0xff] ^
+            Td0[(t0 >> 24)       ] ^
+            Td1[(t3 >> 16) & 0xff] ^
+            Td2[(t2 >>  8) & 0xff] ^
+            Td3[(t1      ) & 0xff] ^
             rk[0];
         s1 =
-            AES_Td0[(t1 >> 24)       ] ^
-            AES_Td1[(t0 >> 16) & 0xff] ^
-            AES_Td2[(t3 >>  8) & 0xff] ^
-            AES_Td3[(t2      ) & 0xff] ^
+            Td0[(t1 >> 24)       ] ^
+            Td1[(t0 >> 16) & 0xff] ^
+            Td2[(t3 >>  8) & 0xff] ^
+            Td3[(t2      ) & 0xff] ^
             rk[1];
         s2 =
-            AES_Td0[(t2 >> 24)       ] ^
-            AES_Td1[(t1 >> 16) & 0xff] ^
-            AES_Td2[(t0 >>  8) & 0xff] ^
-            AES_Td3[(t3      ) & 0xff] ^
+            Td0[(t2 >> 24)       ] ^
+            Td1[(t1 >> 16) & 0xff] ^
+            Td2[(t0 >>  8) & 0xff] ^
+            Td3[(t3      ) & 0xff] ^
             rk[2];
         s3 =
-            AES_Td0[(t3 >> 24)       ] ^
-            AES_Td1[(t2 >> 16) & 0xff] ^
-            AES_Td2[(t1 >>  8) & 0xff] ^
-            AES_Td3[(t0      ) & 0xff] ^
+            Td0[(t3 >> 24)       ] ^
+            Td1[(t2 >> 16) & 0xff] ^
+            Td2[(t1 >>  8) & 0xff] ^
+            Td3[(t0      ) & 0xff] ^
             rk[3];
     }
 #endif /* ?FULL_UNROLL */
@@ -1226,31 +1231,31 @@ void AES_decrypt(const unsigned char *in, unsigned char *out,
 	 * map cipher state to byte array block:
 	 */
    	s0 =
-                (AES_Td4[(t0 >> 24)       ] & 0xff000000) ^
-                (AES_Td4[(t3 >> 16) & 0xff] & 0x00ff0000) ^
-                (AES_Td4[(t2 >>  8) & 0xff] & 0x0000ff00) ^
-                (AES_Td4[(t1      ) & 0xff] & 0x000000ff) ^
+   		(Td4[(t0 >> 24)       ] & 0xff000000) ^
+   		(Td4[(t3 >> 16) & 0xff] & 0x00ff0000) ^
+   		(Td4[(t2 >>  8) & 0xff] & 0x0000ff00) ^
+   		(Td4[(t1      ) & 0xff] & 0x000000ff) ^
    		rk[0];
 	PUTU32(out     , s0);
    	s1 =
-                (AES_Td4[(t1 >> 24)       ] & 0xff000000) ^
-                (AES_Td4[(t0 >> 16) & 0xff] & 0x00ff0000) ^
-                (AES_Td4[(t3 >>  8) & 0xff] & 0x0000ff00) ^
-                (AES_Td4[(t2      ) & 0xff] & 0x000000ff) ^
+   		(Td4[(t1 >> 24)       ] & 0xff000000) ^
+   		(Td4[(t0 >> 16) & 0xff] & 0x00ff0000) ^
+   		(Td4[(t3 >>  8) & 0xff] & 0x0000ff00) ^
+   		(Td4[(t2      ) & 0xff] & 0x000000ff) ^
    		rk[1];
 	PUTU32(out +  4, s1);
    	s2 =
-                (AES_Td4[(t2 >> 24)       ] & 0xff000000) ^
-                (AES_Td4[(t1 >> 16) & 0xff] & 0x00ff0000) ^
-                (AES_Td4[(t0 >>  8) & 0xff] & 0x0000ff00) ^
-                (AES_Td4[(t3      ) & 0xff] & 0x000000ff) ^
+   		(Td4[(t2 >> 24)       ] & 0xff000000) ^
+   		(Td4[(t1 >> 16) & 0xff] & 0x00ff0000) ^
+   		(Td4[(t0 >>  8) & 0xff] & 0x0000ff00) ^
+   		(Td4[(t3      ) & 0xff] & 0x000000ff) ^
    		rk[2];
 	PUTU32(out +  8, s2);
    	s3 =
-                (AES_Td4[(t3 >> 24)       ] & 0xff000000) ^
-                (AES_Td4[(t2 >> 16) & 0xff] & 0x00ff0000) ^
-                (AES_Td4[(t1 >>  8) & 0xff] & 0x0000ff00) ^
-                (AES_Td4[(t0      ) & 0xff] & 0x000000ff) ^
+   		(Td4[(t3 >> 24)       ] & 0xff000000) ^
+   		(Td4[(t2 >> 16) & 0xff] & 0x00ff0000) ^
+   		(Td4[(t1 >>  8) & 0xff] & 0x0000ff00) ^
+   		(Td4[(t0      ) & 0xff] & 0x000000ff) ^
    		rk[3];
 	PUTU32(out + 12, s3);
 }

aes.h

@@ -23,23 +23,4 @@ void AES_cbc_encrypt(const unsigned char *in, unsigned char *out,
 		     const unsigned long length, const AES_KEY *key,
 		     unsigned char *ivec, const int enc);
 
-/*
-AES_Te0[x] = S [x].[02, 01, 01, 03];
-AES_Te1[x] = S [x].[03, 02, 01, 01];
-AES_Te2[x] = S [x].[01, 03, 02, 01];
-AES_Te3[x] = S [x].[01, 01, 03, 02];
-AES_Te4[x] = S [x].[01, 01, 01, 01];
-
-AES_Td0[x] = Si[x].[0e, 09, 0d, 0b];
-AES_Td1[x] = Si[x].[0b, 0e, 09, 0d];
-AES_Td2[x] = Si[x].[0d, 0b, 0e, 09];
-AES_Td3[x] = Si[x].[09, 0d, 0b, 0e];
-AES_Td4[x] = Si[x].[01, 01, 01, 01];
-*/
-
-extern const uint32_t AES_Te0[256], AES_Te1[256], AES_Te2[256],
-                      AES_Te3[256], AES_Te4[256];
-extern const uint32_t AES_Td0[256], AES_Td1[256], AES_Td2[256],
-                      AES_Td3[256], AES_Td4[256];
-
 #endif

aio-posix.c

@@ -1,255 +0,0 @@
-/*
- * QEMU aio implementation
- *
- * Copyright IBM, Corp. 2008
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.ibm.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 "qemu-common.h"
-#include "block/block.h"
-#include "qemu/queue.h"
-#include "qemu/sockets.h"
-
-struct AioHandler
-{
-    GPollFD pfd;
-    IOHandler *io_read;
-    IOHandler *io_write;
-    AioFlushHandler *io_flush;
-    int deleted;
-    int pollfds_idx;
-    void *opaque;
-    QLIST_ENTRY(AioHandler) node;
-};
-
-static AioHandler *find_aio_handler(AioContext *ctx, int fd)
-{
-    AioHandler *node;
-
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        if (node->pfd.fd == fd)
-            if (!node->deleted)
-                return node;
-    }
-
-    return NULL;
-}
-
-void aio_set_fd_handler(AioContext *ctx,
-                        int fd,
-                        IOHandler *io_read,
-                        IOHandler *io_write,
-                        AioFlushHandler *io_flush,
-                        void *opaque)
-{
-    AioHandler *node;
-
-    node = find_aio_handler(ctx, fd);
-
-    /* Are we deleting the fd handler? */
-    if (!io_read && !io_write) {
-        if (node) {
-            g_source_remove_poll(&ctx->source, &node->pfd);
-
-            /* If the lock is held, just mark the node as deleted */
-            if (ctx->walking_handlers) {
-                node->deleted = 1;
-                node->pfd.revents = 0;
-            } else {
-                /* Otherwise, delete it for real.  We can't just mark it as
-                 * deleted because deleted nodes are only cleaned up after
-                 * releasing the walking_handlers lock.
-                 */
-                QLIST_REMOVE(node, node);
-                g_free(node);
-            }
-        }
-    } else {
-        if (node == NULL) {
-            /* Alloc and insert if it's not already there */
-            node = g_malloc0(sizeof(AioHandler));
-            node->pfd.fd = fd;
-            QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
-
-            g_source_add_poll(&ctx->source, &node->pfd);
-        }
-        /* 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;
-
-        node->pfd.events = (io_read ? G_IO_IN | G_IO_HUP | G_IO_ERR : 0);
-        node->pfd.events |= (io_write ? G_IO_OUT | G_IO_ERR : 0);
-    }
-
-    aio_notify(ctx);
-}
-
-void aio_set_event_notifier(AioContext *ctx,
-                            EventNotifier *notifier,
-                            EventNotifierHandler *io_read,
-                            AioFlushEventNotifierHandler *io_flush)
-{
-    aio_set_fd_handler(ctx, event_notifier_get_fd(notifier),
-                       (IOHandler *)io_read, NULL,
-                       (AioFlushHandler *)io_flush, notifier);
-}
-
-bool aio_pending(AioContext *ctx)
-{
-    AioHandler *node;
-
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        int revents;
-
-        revents = node->pfd.revents & node->pfd.events;
-        if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR) && node->io_read) {
-            return true;
-        }
-        if (revents & (G_IO_OUT | G_IO_ERR) && node->io_write) {
-            return true;
-        }
-    }
-
-    return false;
-}
-
-static bool aio_dispatch(AioContext *ctx)
-{
-    AioHandler *node;
-    bool progress = false;
-
-    /*
-     * 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);
-    while (node) {
-        AioHandler *tmp;
-        int revents;
-
-        ctx->walking_handlers++;
-
-        revents = node->pfd.revents & node->pfd.events;
-        node->pfd.revents = 0;
-
-        if (!node->deleted &&
-            (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) &&
-            node->io_read) {
-            node->io_read(node->opaque);
-            progress = true;
-        }
-        if (!node->deleted &&
-            (revents & (G_IO_OUT | G_IO_ERR)) &&
-            node->io_write) {
-            node->io_write(node->opaque);
-            progress = true;
-        }
-
-        tmp = node;
-        node = QLIST_NEXT(node, node);
-
-        ctx->walking_handlers--;
-
-        if (!ctx->walking_handlers && tmp->deleted) {
-            QLIST_REMOVE(tmp, node);
-            g_free(tmp);
-        }
-    }
-    return progress;
-}
-
-bool aio_poll(AioContext *ctx, bool blocking)
-{
-    AioHandler *node;
-    int ret;
-    bool busy, progress;
-
-    progress = false;
-
-    /*
-     * 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 qemu_aio_wait loops).
-     */
-    if (aio_bh_poll(ctx)) {
-        blocking = false;
-        progress = true;
-    }
-
-    if (aio_dispatch(ctx)) {
-        progress = true;
-    }
-
-    if (progress && !blocking) {
-        return true;
-    }
-
-    ctx->walking_handlers++;
-
-    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,
-                .events = node->pfd.events,
-            };
-            node->pollfds_idx = ctx->pollfds->len;
-            g_array_append_val(ctx->pollfds, pfd);
-        }
-    }
-
-    ctx->walking_handlers--;
-
-    /* No AIO operations?  Get us out of here */
-    if (!busy) {
-        return progress;
-    }
-
-    /* wait until next event */
-    ret = g_poll((GPollFD *)ctx->pollfds->data,
-                 ctx->pollfds->len,
-                 blocking ? -1 : 0);
-
-    /* if we have any readable fds, dispatch event */
-    if (ret > 0) {
-        QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-            if (node->pollfds_idx != -1) {
-                GPollFD *pfd = &g_array_index(ctx->pollfds, GPollFD,
-                                              node->pollfds_idx);
-                node->pfd.revents = pfd->revents;
-            }
-        }
-        if (aio_dispatch(ctx)) {
-            progress = true;
-        }
-    }
-
-    assert(progress || busy);
-    return true;
-}

aio-win32.c

@@ -1,219 +0,0 @@
-/*
- * QEMU aio implementation
- *
- * Copyright IBM Corp., 2008
- * Copyright Red Hat Inc., 2012
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.ibm.com>
- *  Paolo Bonzini     <pbonzini@redhat.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 "qemu-common.h"
-#include "block/block.h"
-#include "qemu/queue.h"
-#include "qemu/sockets.h"
-
-struct AioHandler {
-    EventNotifier *e;
-    EventNotifierHandler *io_notify;
-    AioFlushEventNotifierHandler *io_flush;
-    GPollFD pfd;
-    int deleted;
-    QLIST_ENTRY(AioHandler) node;
-};
-
-void aio_set_event_notifier(AioContext *ctx,
-                            EventNotifier *e,
-                            EventNotifierHandler *io_notify,
-                            AioFlushEventNotifierHandler *io_flush)
-{
-    AioHandler *node;
-
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        if (node->e == e && !node->deleted) {
-            break;
-        }
-    }
-
-    /* Are we deleting the fd handler? */
-    if (!io_notify) {
-        if (node) {
-            g_source_remove_poll(&ctx->source, &node->pfd);
-
-            /* If the lock is held, just mark the node as deleted */
-            if (ctx->walking_handlers) {
-                node->deleted = 1;
-                node->pfd.revents = 0;
-            } else {
-                /* Otherwise, delete it for real.  We can't just mark it as
-                 * deleted because deleted nodes are only cleaned up after
-                 * releasing the walking_handlers lock.
-                 */
-                QLIST_REMOVE(node, node);
-                g_free(node);
-            }
-        }
-    } else {
-        if (node == NULL) {
-            /* Alloc and insert if it's not already there */
-            node = g_malloc0(sizeof(AioHandler));
-            node->e = e;
-            node->pfd.fd = (uintptr_t)event_notifier_get_handle(e);
-            node->pfd.events = G_IO_IN;
-            QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
-
-            g_source_add_poll(&ctx->source, &node->pfd);
-        }
-        /* Update handler with latest information */
-        node->io_notify = io_notify;
-        node->io_flush = io_flush;
-    }
-
-    aio_notify(ctx);
-}
-
-bool aio_pending(AioContext *ctx)
-{
-    AioHandler *node;
-
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        if (node->pfd.revents && node->io_notify) {
-            return true;
-        }
-    }
-
-    return false;
-}
-
-bool aio_poll(AioContext *ctx, bool blocking)
-{
-    AioHandler *node;
-    HANDLE events[MAXIMUM_WAIT_OBJECTS + 1];
-    bool busy, progress;
-    int count;
-
-    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 qemu_aio_wait loops).
-     */
-    if (aio_bh_poll(ctx)) {
-        blocking = false;
-        progress = true;
-    }
-
-    /*
-     * Then dispatch any pending callbacks from the GSource.
-     *
-     * 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);
-    while (node) {
-        AioHandler *tmp;
-
-        ctx->walking_handlers++;
-
-        if (node->pfd.revents && node->io_notify) {
-            node->pfd.revents = 0;
-            node->io_notify(node->e);
-            progress = true;
-        }
-
-        tmp = node;
-        node = QLIST_NEXT(node, node);
-
-        ctx->walking_handlers--;
-
-        if (!ctx->walking_handlers && tmp->deleted) {
-            QLIST_REMOVE(tmp, node);
-            g_free(tmp);
-        }
-    }
-
-    if (progress && !blocking) {
-        return true;
-    }
-
-    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);
-        }
-    }
-
-    ctx->walking_handlers--;
-
-    /* No AIO operations?  Get us out of here */
-    if (!busy) {
-        return progress;
-    }
-
-    /* wait until next event */
-    while (count > 0) {
-        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) {
-            break;
-        }
-
-        blocking = false;
-
-        /* 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);
-        while (node) {
-            AioHandler *tmp;
-
-            ctx->walking_handlers++;
-
-            if (!node->deleted &&
-                event_notifier_get_handle(node->e) == events[ret - WAIT_OBJECT_0] &&
-                node->io_notify) {
-                node->io_notify(node->e);
-                progress = true;
-            }
-
-            tmp = node;
-            node = QLIST_NEXT(node, node);
-
-            ctx->walking_handlers--;
-
-            if (!ctx->walking_handlers && tmp->deleted) {
-                QLIST_REMOVE(tmp, node);
-                g_free(tmp);
-            }
-        }
-
-        /* Try again, but only call each handler once.  */
-        events[ret - WAIT_OBJECT_0] = events[--count];
-    }
-
-    assert(progress || busy);
-    return true;
-}

aio.c

@@ -0,0 +1,194 @@
+/*
+ * QEMU aio implementation
+ *
+ * Copyright IBM, Corp. 2008
+ *
+ * Authors:
+ *  Anthony Liguori   <aliguori@us.ibm.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 "qemu-common.h"
+#include "block.h"
+#include "qemu-queue.h"
+#include "qemu_socket.h"
+
+typedef struct AioHandler AioHandler;
+
+/* The list of registered AIO handlers */
+static QLIST_HEAD(, AioHandler) aio_handlers;
+
+/* This is a simple lock used to protect the aio_handlers list.  Specifically,
+ * it's used to ensure that no callbacks are removed while we're walking and
+ * dispatching callbacks.
+ */
+static int walking_handlers;
+
+struct AioHandler
+{
+    int fd;
+    IOHandler *io_read;
+    IOHandler *io_write;
+    AioFlushHandler *io_flush;
+    int deleted;
+    void *opaque;
+    QLIST_ENTRY(AioHandler) node;
+};
+
+static AioHandler *find_aio_handler(int fd)
+{
+    AioHandler *node;
+
+    QLIST_FOREACH(node, &aio_handlers, node) {
+        if (node->fd == fd)
+            if (!node->deleted)
+                return node;
+    }
+
+    return NULL;
+}
+
+int qemu_aio_set_fd_handler(int fd,
+                            IOHandler *io_read,
+                            IOHandler *io_write,
+                            AioFlushHandler *io_flush,
+                            void *opaque)
+{
+    AioHandler *node;
+
+    node = find_aio_handler(fd);
+
+    /* Are we deleting the fd handler? */
+    if (!io_read && !io_write) {
+        if (node) {
+            /* If the lock is held, just mark the node as deleted */
+            if (walking_handlers)
+                node->deleted = 1;
+            else {
+                /* Otherwise, delete it for real.  We can't just mark it as
+                 * deleted because deleted nodes are only cleaned up after
+                 * releasing the walking_handlers lock.
+                 */
+                QLIST_REMOVE(node, node);
+                g_free(node);
+            }
+        }
+    } else {
+        if (node == NULL) {
+            /* Alloc and insert if it's not already there */
+            node = g_malloc0(sizeof(AioHandler));
+            node->fd = fd;
+            QLIST_INSERT_HEAD(&aio_handlers, node, node);
+        }
+        /* Update handler with latest information */
+        node->io_read = io_read;
+        node->io_write = io_write;
+        node->io_flush = io_flush;
+        node->opaque = opaque;
+    }
+
+    qemu_set_fd_handler2(fd, NULL, io_read, io_write, opaque);
+
+    return 0;
+}
+
+void qemu_aio_flush(void)
+{
+    while (qemu_aio_wait());
+}
+
+bool qemu_aio_wait(void)
+{
+    AioHandler *node;
+    fd_set rdfds, wrfds;
+    int max_fd = -1;
+    int ret;
+    bool busy;
+
+    /*
+     * 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 qemu_aio_wait loops).
+     */
+    if (qemu_bh_poll()) {
+        return true;
+    }
+
+    walking_handlers = 1;
+
+    FD_ZERO(&rdfds);
+    FD_ZERO(&wrfds);
+
+    /* fill fd sets */
+    busy = false;
+    QLIST_FOREACH(node, &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->io_flush) {
+            if (node->io_flush(node->opaque) == 0) {
+                continue;
+            }
+            busy = true;
+        }
+        if (!node->deleted && node->io_read) {
+            FD_SET(node->fd, &rdfds);
+            max_fd = MAX(max_fd, node->fd + 1);
+        }
+        if (!node->deleted && node->io_write) {
+            FD_SET(node->fd, &wrfds);
+            max_fd = MAX(max_fd, node->fd + 1);
+        }
+    }
+
+    walking_handlers = 0;
+
+    /* No AIO operations?  Get us out of here */
+    if (!busy) {
+        return false;
+    }
+
+    /* wait until next event */
+    ret = select(max_fd, &rdfds, &wrfds, NULL, NULL);
+
+    /* if we have any readable fds, dispatch event */
+    if (ret > 0) {
+        walking_handlers = 1;
+
+        /* we have to walk very carefully in case
+         * qemu_aio_set_fd_handler is called while we're walking */
+        node = QLIST_FIRST(&aio_handlers);
+        while (node) {
+            AioHandler *tmp;
+
+            if (!node->deleted &&
+                FD_ISSET(node->fd, &rdfds) &&
+                node->io_read) {
+                node->io_read(node->opaque);
+            }
+            if (!node->deleted &&
+                FD_ISSET(node->fd, &wrfds) &&
+                node->io_write) {
+                node->io_write(node->opaque);
+            }
+
+            tmp = node;
+            node = QLIST_NEXT(node, node);
+
+            if (tmp->deleted) {
+                QLIST_REMOVE(tmp, node);
+                g_free(tmp);
+            }
+        }
+
+        walking_handlers = 0;
+    }
+
+    return true;
+}

alpha-dis.c

@@ -20,7 +20,7 @@ along with this file; see the file COPYING.  If not, see
 <http://www.gnu.org/licenses/>. */
 
 #include <stdio.h>
-#include "disas/bfd.h"
+#include "dis-asm.h"
 
 /* MAX is redefined below, so remove any previous definition. */
 #undef MAX

alpha.ld

@@ -0,0 +1,127 @@
+OUTPUT_FORMAT("elf64-alpha", "elf64-alpha",
+	      "elf64-alpha")
+OUTPUT_ARCH(alpha)
+ENTRY(__start)
+SECTIONS
+{
+  /* Read-only sections, merged into text segment: */
+  . = 0x60000000 + SIZEOF_HEADERS;
+  .interp     : { *(.interp) 	}
+  .hash          : { *(.hash)		}
+  .dynsym        : { *(.dynsym)		}
+  .dynstr        : { *(.dynstr)		}
+  .gnu.version   : { *(.gnu.version)	}
+  .gnu.version_d   : { *(.gnu.version_d)	}
+  .gnu.version_r   : { *(.gnu.version_r)	}
+  .rel.text      :
+    { *(.rel.text) *(.rel.gnu.linkonce.t*) }
+  .rela.text     :
+    { *(.rela.text) *(.rela.gnu.linkonce.t*) }
+  .rel.data      :
+    { *(.rel.data) *(.rel.gnu.linkonce.d*) }
+  .rela.data     :
+    { *(.rela.data) *(.rela.gnu.linkonce.d*) }
+  .rel.rodata    :
+    { *(.rel.rodata) *(.rel.gnu.linkonce.r*) }
+  .rela.rodata   :
+    { *(.rela.rodata) *(.rela.gnu.linkonce.r*) }
+  .rel.got       : { *(.rel.got)		}
+  .rela.got      : { *(.rela.got)		}
+  .rel.ctors     : { *(.rel.ctors)	}
+  .rela.ctors    : { *(.rela.ctors)	}
+  .rel.dtors     : { *(.rel.dtors)	}
+  .rela.dtors    : { *(.rela.dtors)	}
+  .rel.init      : { *(.rel.init)	}
+  .rela.init     : { *(.rela.init)	}
+  .rel.fini      : { *(.rel.fini)	}
+  .rela.fini     : { *(.rela.fini)	}
+  .rel.bss       : { *(.rel.bss)		}
+  .rela.bss      : { *(.rela.bss)		}
+  .rel.plt       : { *(.rel.plt)		}
+  .rela.plt      : { *(.rela.plt)		}
+  .init          : { *(.init)	} =0x47ff041f
+  .text      :
+  {
+    *(.text)
+    /* .gnu.warning sections are handled specially by elf32.em.  */
+    *(.gnu.warning)
+    *(.gnu.linkonce.t*)
+  } =0x47ff041f
+  _etext = .;
+  PROVIDE (etext = .);
+  .fini      : { *(.fini)    } =0x47ff041f
+  .rodata    : { *(.rodata) *(.gnu.linkonce.r*) }
+  .rodata1   : { *(.rodata1) }
+  .reginfo : { *(.reginfo) }
+  /* Adjust the address for the data segment.  We want to adjust up to
+     the same address within the page on the next page up.  */
+  . = ALIGN(0x100000) + (. & (0x100000 - 1));
+  .data    :
+  {
+    *(.data)
+    *(.gnu.linkonce.d*)
+    CONSTRUCTORS
+  }
+  .data1   : { *(.data1) }
+  .ctors         :
+  {
+    *(.ctors)
+  }
+  .dtors         :
+  {
+    *(.dtors)
+  }
+  .plt      : { *(.plt)	}
+  .got           : { *(.got.plt) *(.got) }
+  .dynamic       : { *(.dynamic) }
+  /* We want the small data sections together, so single-instruction offsets
+     can access them all, and initialized data all before uninitialized, so
+     we can shorten the on-disk segment size.  */
+  .sdata     : { *(.sdata) }
+  _edata  =  .;
+  PROVIDE (edata = .);
+  __bss_start = .;
+  .sbss      : { *(.sbss) *(.scommon) }
+  .bss       :
+  {
+   *(.dynbss)
+   *(.bss)
+   *(COMMON)
+  }
+  _end = . ;
+  PROVIDE (end = .);
+  /* Stabs debugging sections.  */
+  .stab 0 : { *(.stab) }
+  .stabstr 0 : { *(.stabstr) }
+  .stab.excl 0 : { *(.stab.excl) }
+  .stab.exclstr 0 : { *(.stab.exclstr) }
+  .stab.index 0 : { *(.stab.index) }
+  .stab.indexstr 0 : { *(.stab.indexstr) }
+  .comment 0 : { *(.comment) }
+  /* DWARF debug sections.
+     Symbols in the DWARF debugging sections are relative to the beginning
+     of the section so we begin them at 0.  */
+  /* DWARF 1 */
+  .debug          0 : { *(.debug) }
+  .line           0 : { *(.line) }
+  /* GNU DWARF 1 extensions */
+  .debug_srcinfo  0 : { *(.debug_srcinfo) }
+  .debug_sfnames  0 : { *(.debug_sfnames) }
+  /* DWARF 1.1 and DWARF 2 */
+  .debug_aranges  0 : { *(.debug_aranges) }
+  .debug_pubnames 0 : { *(.debug_pubnames) }
+  /* DWARF 2 */
+  .debug_info     0 : { *(.debug_info) }
+  .debug_abbrev   0 : { *(.debug_abbrev) }
+  .debug_line     0 : { *(.debug_line) }
+  .debug_frame    0 : { *(.debug_frame) }
+  .debug_str      0 : { *(.debug_str) }
+  .debug_loc      0 : { *(.debug_loc) }
+  .debug_macinfo  0 : { *(.debug_macinfo) }
+  /* SGI/MIPS DWARF 2 extensions */
+  .debug_weaknames 0 : { *(.debug_weaknames) }
+  .debug_funcnames 0 : { *(.debug_funcnames) }
+  .debug_typenames 0 : { *(.debug_typenames) }
+  .debug_varnames  0 : { *(.debug_varnames) }
+  /* These must appear regardless of  .  */
+}

arch_init.h

@@ -1,9 +1,6 @@
 #ifndef QEMU_ARCH_INIT_H
 #define QEMU_ARCH_INIT_H
 
-#include "qmp-commands.h"
-#include "qemu/option.h"
-
 enum {
     QEMU_ARCH_ALL = -1,
     QEMU_ARCH_ALPHA = 1,
@@ -19,22 +16,18 @@ enum {
     QEMU_ARCH_SH4 = 1024,
     QEMU_ARCH_SPARC = 2048,
     QEMU_ARCH_XTENSA = 4096,
-    QEMU_ARCH_OPENRISC = 8192,
-    QEMU_ARCH_UNICORE32 = 0x4000,
-    QEMU_ARCH_MOXIE = 0x8000,
 };
 
 extern const uint32_t arch_type;
 
 void select_soundhw(const char *optarg);
-void do_acpitable_option(const QemuOpts *opts);
+void do_acpitable_option(const char *optarg);
 void do_smbios_option(const char *optarg);
 void cpudef_init(void);
-void audio_init(void);
+int audio_available(void);
+void audio_init(ISABus *isa_bus, PCIBus *pci_bus);
 int tcg_available(void);
 int kvm_available(void);
 int xen_available(void);
 
-CpuDefinitionInfoList *arch_query_cpu_definitions(Error **errp);
-
 #endif

arm-dis.c

@@ -22,7 +22,7 @@
 /* Start of qemu specific additions.  Mostly this is stub definitions
    for things we don't care about.  */
 
-#include "disas/bfd.h"
+#include "dis-asm.h"
 #define ATTRIBUTE_UNUSED __attribute__((unused))
 #define ISSPACE(x) ((x) == ' ' || (x) == '\t' || (x) == '\n')
 
@@ -819,10 +819,6 @@ static const struct opcode32 arm_opcodes[] =
   {ARM_EXT_V3M, 0x00800090, 0x0fa000f0, "%22?sumull%20's%c\t%12-15r, %16-19r, %0-3r, %8-11r"},
   {ARM_EXT_V3M, 0x00a00090, 0x0fa000f0, "%22?sumlal%20's%c\t%12-15r, %16-19r, %0-3r, %8-11r"},
 
-  /* IDIV instructions.  */
-  {ARM_EXT_DIV, 0x0710f010, 0x0ff0f0f0, "sdiv%c\t%16-19r, %0-3r, %8-11r"},
-  {ARM_EXT_DIV, 0x0730f010, 0x0ff0f0f0, "udiv%c\t%16-19r, %0-3r, %8-11r"},
-
   /* V7 instructions.  */
   {ARM_EXT_V7, 0xf450f000, 0xfd70f000, "pli\t%P"},
   {ARM_EXT_V7, 0x0320f0f0, 0x0ffffff0, "dbg%c\t#%0-3d"},

arm-semi.c

@@ -33,8 +33,8 @@
 #define ARM_ANGEL_HEAP_SIZE (128 * 1024 * 1024)
 #else
 #include "qemu-common.h"
-#include "exec/gdbstub.h"
-#include "hw/arm/arm.h"
+#include "gdbstub.h"
+#include "hw/arm-misc.h"
 #endif
 
 #define TARGET_SYS_OPEN        0x01
@@ -113,7 +113,7 @@ static inline uint32_t set_swi_errno(CPUARMState *env, uint32_t code)
     return code;
 }
 
-#include "exec/softmmu-semi.h"
+#include "softmmu-semi.h"
 #endif
 
 static target_ulong arm_semi_syscall_len;
@@ -122,10 +122,8 @@ static target_ulong arm_semi_syscall_len;
 static target_ulong syscall_err;
 #endif
 
-static void arm_semi_cb(CPUState *cs, target_ulong ret, target_ulong err)
+static void arm_semi_cb(CPUARMState *env, target_ulong ret, target_ulong err)
 {
-    ARMCPU *cpu = ARM_CPU(cs);
-    CPUARMState *env = &cpu->env;
 #ifdef CONFIG_USER_ONLY
     TaskState *ts = env->opaque;
 #endif
@@ -154,14 +152,12 @@ static void arm_semi_cb(CPUState *cs, target_ulong ret, target_ulong err)
     }
 }
 
-static void arm_semi_flen_cb(CPUState *cs, target_ulong ret, target_ulong err)
+static void arm_semi_flen_cb(CPUARMState *env, target_ulong ret, target_ulong err)
 {
-    ARMCPU *cpu = ARM_CPU(cs);
-    CPUARMState *env = &cpu->env;
     /* The size is always stored in big-endian order, extract
        the value. We assume the size always fit in 32 bits.  */
     uint32_t size;
-    cpu_memory_rw_debug(cs, env->regs[13]-64+32, (uint8_t *)&size, 4, 0);
+    cpu_memory_rw_debug(env, env->regs[13]-64+32, (uint8_t *)&size, 4, 0);
     env->regs[0] = be32_to_cpu(size);
 #ifdef CONFIG_USER_ONLY
     ((TaskState *)env->opaque)->swi_errno = err;
@@ -170,21 +166,17 @@ static void arm_semi_flen_cb(CPUState *cs, target_ulong ret, target_ulong err)
 #endif
 }
 
-/* Read the input value from the argument block; fail the semihosting
- * call if the memory read fails.
- */
-#define GET_ARG(n) do {                                 \
-    if (get_user_ual(arg ## n, args + (n) * 4)) {       \
-        return (uint32_t)-1;                            \
-    }                                                   \
-} while (0)
-
+#define ARG(n)					\
+({						\
+    target_ulong __arg;				\
+    /* FIXME - handle get_user() failure */	\
+    get_user_ual(__arg, args + (n) * 4);	\
+    __arg;					\
+})
 #define SET_ARG(n, val) put_user_ual(val, args + (n) * 4)
 uint32_t do_arm_semihosting(CPUARMState *env)
 {
-    ARMCPU *cpu = arm_env_get_cpu(env);
     target_ulong args;
-    target_ulong arg0, arg1, arg2, arg3;
     char * s;
     int nr;
     uint32_t ret;
@@ -199,39 +191,33 @@ uint32_t do_arm_semihosting(CPUARMState *env)
     args = env->regs[1];
     switch (nr) {
     case TARGET_SYS_OPEN:
-        GET_ARG(0);
-        GET_ARG(1);
-        GET_ARG(2);
-        s = lock_user_string(arg0);
-        if (!s) {
+        if (!(s = lock_user_string(ARG(0))))
             /* FIXME - should this error code be -TARGET_EFAULT ? */
             return (uint32_t)-1;
-        }
-        if (arg1 >= 12) {
-            unlock_user(s, arg0, 0);
+        if (ARG(1) >= 12) {
+            unlock_user(s, ARG(0), 0);
             return (uint32_t)-1;
         }
         if (strcmp(s, ":tt") == 0) {
-            int result_fileno = arg1 < 4 ? STDIN_FILENO : STDOUT_FILENO;
-            unlock_user(s, arg0, 0);
+            int result_fileno = ARG(1) < 4 ? STDIN_FILENO : STDOUT_FILENO;
+            unlock_user(s, ARG(0), 0);
             return result_fileno;
         }
         if (use_gdb_syscalls()) {
-            gdb_do_syscall(arm_semi_cb, "open,%s,%x,1a4", arg0,
-                           (int)arg2+1, gdb_open_modeflags[arg1]);
+            gdb_do_syscall(arm_semi_cb, "open,%s,%x,1a4", ARG(0),
+			   (int)ARG(2)+1, gdb_open_modeflags[ARG(1)]);
             ret = env->regs[0];
         } else {
-            ret = set_swi_errno(ts, open(s, open_modeflags[arg1], 0644));
+            ret = set_swi_errno(ts, open(s, open_modeflags[ARG(1)], 0644));
         }
-        unlock_user(s, arg0, 0);
+        unlock_user(s, ARG(0), 0);
         return ret;
     case TARGET_SYS_CLOSE:
-        GET_ARG(0);
         if (use_gdb_syscalls()) {
-            gdb_do_syscall(arm_semi_cb, "close,%x", arg0);
+            gdb_do_syscall(arm_semi_cb, "close,%x", ARG(0));
             return env->regs[0];
         } else {
-            return set_swi_errno(ts, close(arg0));
+            return set_swi_errno(ts, close(ARG(0)));
         }
     case TARGET_SYS_WRITEC:
         {
@@ -262,81 +248,67 @@ uint32_t do_arm_semihosting(CPUARMState *env)
         unlock_user(s, args, 0);
         return ret;
     case TARGET_SYS_WRITE:
-        GET_ARG(0);
-        GET_ARG(1);
-        GET_ARG(2);
-        len = arg2;
+        len = ARG(2);
         if (use_gdb_syscalls()) {
             arm_semi_syscall_len = len;
-            gdb_do_syscall(arm_semi_cb, "write,%x,%x,%x", arg0, arg1, len);
+            gdb_do_syscall(arm_semi_cb, "write,%x,%x,%x", ARG(0), ARG(1), len);
             return env->regs[0];
         } else {
-            s = lock_user(VERIFY_READ, arg1, len, 1);
-            if (!s) {
+            if (!(s = lock_user(VERIFY_READ, ARG(1), len, 1)))
                 /* FIXME - should this error code be -TARGET_EFAULT ? */
                 return (uint32_t)-1;
-            }
-            ret = set_swi_errno(ts, write(arg0, s, len));
-            unlock_user(s, arg1, 0);
+            ret = set_swi_errno(ts, write(ARG(0), s, len));
+            unlock_user(s, ARG(1), 0);
             if (ret == (uint32_t)-1)
                 return -1;
             return len - ret;
         }
     case TARGET_SYS_READ:
-        GET_ARG(0);
-        GET_ARG(1);
-        GET_ARG(2);
-        len = arg2;
+        len = ARG(2);
         if (use_gdb_syscalls()) {
             arm_semi_syscall_len = len;
-            gdb_do_syscall(arm_semi_cb, "read,%x,%x,%x", arg0, arg1, len);
+            gdb_do_syscall(arm_semi_cb, "read,%x,%x,%x", ARG(0), ARG(1), len);
             return env->regs[0];
         } else {
-            s = lock_user(VERIFY_WRITE, arg1, len, 0);
-            if (!s) {
+            if (!(s = lock_user(VERIFY_WRITE, ARG(1), len, 0)))
                 /* FIXME - should this error code be -TARGET_EFAULT ? */
                 return (uint32_t)-1;
-            }
-            do {
-                ret = set_swi_errno(ts, read(arg0, s, len));
-            } while (ret == -1 && errno == EINTR);
-            unlock_user(s, arg1, len);
+            do
+              ret = set_swi_errno(ts, read(ARG(0), s, len));
+            while (ret == -1 && errno == EINTR);
+            unlock_user(s, ARG(1), len);
             if (ret == (uint32_t)-1)
                 return -1;
             return len - ret;
         }
     case TARGET_SYS_READC:
-       /* XXX: Read from debug console. Not implemented.  */
+       /* XXX: Read from debug cosole. Not implemented.  */
         return 0;
     case TARGET_SYS_ISTTY:
-        GET_ARG(0);
         if (use_gdb_syscalls()) {
-            gdb_do_syscall(arm_semi_cb, "isatty,%x", arg0);
+            gdb_do_syscall(arm_semi_cb, "isatty,%x", ARG(0));
             return env->regs[0];
         } else {
-            return isatty(arg0);
+            return isatty(ARG(0));
         }
     case TARGET_SYS_SEEK:
-        GET_ARG(0);
-        GET_ARG(1);
         if (use_gdb_syscalls()) {
-            gdb_do_syscall(arm_semi_cb, "lseek,%x,%x,0", arg0, arg1);
+            gdb_do_syscall(arm_semi_cb, "lseek,%x,%x,0", ARG(0), ARG(1));
             return env->regs[0];
         } else {
-            ret = set_swi_errno(ts, lseek(arg0, arg1, SEEK_SET));
+            ret = set_swi_errno(ts, lseek(ARG(0), ARG(1), SEEK_SET));
             if (ret == (uint32_t)-1)
               return -1;
             return 0;
         }
     case TARGET_SYS_FLEN:
-        GET_ARG(0);
         if (use_gdb_syscalls()) {
             gdb_do_syscall(arm_semi_flen_cb, "fstat,%x,%x",
-                           arg0, env->regs[13]-64);
+			   ARG(0), env->regs[13]-64);
             return env->regs[0];
         } else {
             struct stat buf;
-            ret = set_swi_errno(ts, fstat(arg0, &buf));
+            ret = set_swi_errno(ts, fstat(ARG(0), &buf));
             if (ret == (uint32_t)-1)
                 return -1;
             return buf.st_size;
@@ -345,43 +317,35 @@ uint32_t do_arm_semihosting(CPUARMState *env)
         /* XXX: Not implemented.  */
         return -1;
     case TARGET_SYS_REMOVE:
-        GET_ARG(0);
-        GET_ARG(1);
         if (use_gdb_syscalls()) {
-            gdb_do_syscall(arm_semi_cb, "unlink,%s", arg0, (int)arg1+1);
+            gdb_do_syscall(arm_semi_cb, "unlink,%s", ARG(0), (int)ARG(1)+1);
             ret = env->regs[0];
         } else {
-            s = lock_user_string(arg0);
-            if (!s) {
+            if (!(s = lock_user_string(ARG(0))))
                 /* FIXME - should this error code be -TARGET_EFAULT ? */
                 return (uint32_t)-1;
-            }
             ret =  set_swi_errno(ts, remove(s));
-            unlock_user(s, arg0, 0);
+            unlock_user(s, ARG(0), 0);
         }
         return ret;
     case TARGET_SYS_RENAME:
-        GET_ARG(0);
-        GET_ARG(1);
-        GET_ARG(2);
-        GET_ARG(3);
         if (use_gdb_syscalls()) {
             gdb_do_syscall(arm_semi_cb, "rename,%s,%s",
-                           arg0, (int)arg1+1, arg2, (int)arg3+1);
+                           ARG(0), (int)ARG(1)+1, ARG(2), (int)ARG(3)+1);
             return env->regs[0];
         } else {
             char *s2;
-            s = lock_user_string(arg0);
-            s2 = lock_user_string(arg2);
+            s = lock_user_string(ARG(0));
+            s2 = lock_user_string(ARG(2));
             if (!s || !s2)
                 /* FIXME - should this error code be -TARGET_EFAULT ? */
                 ret = (uint32_t)-1;
             else
                 ret = set_swi_errno(ts, rename(s, s2));
             if (s2)
-                unlock_user(s2, arg2, 0);
+                unlock_user(s2, ARG(2), 0);
             if (s)
-                unlock_user(s, arg0, 0);
+                unlock_user(s, ARG(0), 0);
             return ret;
         }
     case TARGET_SYS_CLOCK:
@@ -389,19 +353,15 @@ uint32_t do_arm_semihosting(CPUARMState *env)
     case TARGET_SYS_TIME:
         return set_swi_errno(ts, time(NULL));
     case TARGET_SYS_SYSTEM:
-        GET_ARG(0);
-        GET_ARG(1);
         if (use_gdb_syscalls()) {
-            gdb_do_syscall(arm_semi_cb, "system,%s", arg0, (int)arg1+1);
+            gdb_do_syscall(arm_semi_cb, "system,%s", ARG(0), (int)ARG(1)+1);
             return env->regs[0];
         } else {
-            s = lock_user_string(arg0);
-            if (!s) {
+            if (!(s = lock_user_string(ARG(0))))
                 /* FIXME - should this error code be -TARGET_EFAULT ? */
                 return (uint32_t)-1;
-            }
             ret = set_swi_errno(ts, system(s));
-            unlock_user(s, arg0, 0);
+            unlock_user(s, ARG(0), 0);
             return ret;
         }
     case TARGET_SYS_ERRNO:
@@ -415,24 +375,22 @@ uint32_t do_arm_semihosting(CPUARMState *env)
             /* Build a command-line from the original argv.
              *
              * The inputs are:
-             *     * arg0, pointer to a buffer of at least the size
-             *               specified in arg1.
-             *     * arg1, size of the buffer pointed to by arg0 in
+             *     * ARG(0), pointer to a buffer of at least the size
+             *               specified in ARG(1).
+             *     * ARG(1), size of the buffer pointed to by ARG(0) in
              *               bytes.
              *
              * The outputs are:
-             *     * arg0, pointer to null-terminated string of the
+             *     * ARG(0), pointer to null-terminated string of the
              *               command line.
-             *     * arg1, length of the string pointed to by arg0.
+             *     * ARG(1), length of the string pointed to by ARG(0).
              */
 
             char *output_buffer;
-            size_t input_size;
+            size_t input_size = ARG(1);
             size_t output_size;
             int status = 0;
-            GET_ARG(0);
-            GET_ARG(1);
-            input_size = arg1;
+
             /* Compute the size of the output string.  */
 #if !defined(CONFIG_USER_ONLY)
             output_size = strlen(ts->boot_info->kernel_filename)
@@ -456,13 +414,10 @@ uint32_t do_arm_semihosting(CPUARMState *env)
             }
 
             /* Adjust the command-line length.  */
-            if (SET_ARG(1, output_size - 1)) {
-                /* Couldn't write back to argument block */
-                return -1;
-            }
+            SET_ARG(1, output_size - 1);
 
             /* Lock the buffer on the ARM side.  */
-            output_buffer = lock_user(VERIFY_WRITE, arg0, output_size, 0);
+            output_buffer = lock_user(VERIFY_WRITE, ARG(0), output_size, 0);
             if (!output_buffer) {
                 return -1;
             }
@@ -494,7 +449,7 @@ uint32_t do_arm_semihosting(CPUARMState *env)
         out:
 #endif
             /* Unlock the buffer on the ARM side.  */
-            unlock_user(output_buffer, arg0, output_size);
+            unlock_user(output_buffer, ARG(0), output_size);
 
             return status;
         }
@@ -502,7 +457,6 @@ uint32_t do_arm_semihosting(CPUARMState *env)
         {
             uint32_t *ptr;
             uint32_t limit;
-            GET_ARG(0);
 
 #ifdef CONFIG_USER_ONLY
             /* Some C libraries assume the heap immediately follows .bss, so
@@ -523,29 +477,25 @@ uint32_t do_arm_semihosting(CPUARMState *env)
                 ts->heap_limit = limit;
             }
 
-            ptr = lock_user(VERIFY_WRITE, arg0, 16, 0);
-            if (!ptr) {
+            if (!(ptr = lock_user(VERIFY_WRITE, ARG(0), 16, 0)))
                 /* FIXME - should this error code be -TARGET_EFAULT ? */
                 return (uint32_t)-1;
-            }
             ptr[0] = tswap32(ts->heap_base);
             ptr[1] = tswap32(ts->heap_limit);
             ptr[2] = tswap32(ts->stack_base);
             ptr[3] = tswap32(0); /* Stack limit.  */
-            unlock_user(ptr, arg0, 16);
+            unlock_user(ptr, ARG(0), 16);
 #else
             limit = ram_size;
-            ptr = lock_user(VERIFY_WRITE, arg0, 16, 0);
-            if (!ptr) {
+            if (!(ptr = lock_user(VERIFY_WRITE, ARG(0), 16, 0)))
                 /* FIXME - should this error code be -TARGET_EFAULT ? */
                 return (uint32_t)-1;
-            }
             /* TODO: Make this use the limit of the loaded application.  */
             ptr[0] = tswap32(limit / 2);
             ptr[1] = tswap32(limit);
             ptr[2] = tswap32(limit); /* Stack base */
             ptr[3] = tswap32(0); /* Stack limit.  */
-            unlock_user(ptr, arg0, 16);
+            unlock_user(ptr, ARG(0), 16);
 #endif
             return 0;
         }
@@ -554,7 +504,7 @@ uint32_t do_arm_semihosting(CPUARMState *env)
         exit(0);
     default:
         fprintf(stderr, "qemu: Unsupported SemiHosting SWI 0x%02x\n", nr);
-        cpu_dump_state(CPU(cpu), stderr, fprintf, 0);
+        cpu_dump_state(env, stderr, fprintf, 0);
         abort();
     }
 }

arm.ld

@@ -0,0 +1,153 @@
+OUTPUT_FORMAT("elf32-littlearm", "elf32-littlearm",
+	      "elf32-littlearm")
+OUTPUT_ARCH(arm)
+ENTRY(_start)
+SECTIONS
+{
+  /* Read-only sections, merged into text segment: */
+  . = 0x60000000 + SIZEOF_HEADERS;
+  .interp     : { *(.interp) 	}
+  .hash          : { *(.hash)		}
+  .dynsym        : { *(.dynsym)		}
+  .dynstr        : { *(.dynstr)		}
+  .gnu.version   : { *(.gnu.version)	}
+  .gnu.version_d   : { *(.gnu.version_d)	}
+  .gnu.version_r   : { *(.gnu.version_r)	}
+  .rel.text      :
+    { *(.rel.text) *(.rel.gnu.linkonce.t*) }
+  .rela.text     :
+    { *(.rela.text) *(.rela.gnu.linkonce.t*) }
+  .rel.data      :
+    { *(.rel.data) *(.rel.gnu.linkonce.d*) }
+  .rela.data     :
+    { *(.rela.data) *(.rela.gnu.linkonce.d*) }
+  .rel.rodata    :
+    { *(.rel.rodata) *(.rel.gnu.linkonce.r*) }
+  .rela.rodata   :
+    { *(.rela.rodata) *(.rela.gnu.linkonce.r*) }
+  .rel.got       : { *(.rel.got)		}
+  .rela.got      : { *(.rela.got)		}
+  .rel.ctors     : { *(.rel.ctors)	}
+  .rela.ctors    : { *(.rela.ctors)	}
+  .rel.dtors     : { *(.rel.dtors)	}
+  .rela.dtors    : { *(.rela.dtors)	}
+  .rel.init      : { *(.rel.init)	}
+  .rela.init     : { *(.rela.init)	}
+  .rel.fini      : { *(.rel.fini)	}
+  .rela.fini     : { *(.rela.fini)	}
+  .rel.bss       : { *(.rel.bss)		}
+  .rela.bss      : { *(.rela.bss)		}
+  .rel.plt       : { *(.rel.plt)		}
+  .rela.plt      : { *(.rela.plt)		}
+  .init          : { *(.init)	} =0x47ff041f
+  .text      :
+  {
+    *(.text)
+    /* .gnu.warning sections are handled specially by elf32.em.  */
+    *(.gnu.warning)
+    *(.gnu.linkonce.t*)
+  } =0x47ff041f
+  _etext = .;
+  PROVIDE (etext = .);
+  .fini      : { *(.fini)    } =0x47ff041f
+  .rodata    : { *(.rodata) *(.gnu.linkonce.r*) }
+  .rodata1   : { *(.rodata1) }
+  .ARM.extab   : { *(.ARM.extab* .gnu.linkonce.armextab.*) }
+   __exidx_start = .;
+  .ARM.exidx   : { *(.ARM.exidx* .gnu.linkonce.armexidx.*) }
+   __exidx_end = .;
+  .reginfo : { *(.reginfo) }
+  /* Adjust the address for the data segment.  We want to adjust up to
+     the same address within the page on the next page up.  */
+  . = ALIGN(0x100000) + (. & (0x100000 - 1));
+  .data    :
+  {
+    *(.gen_code)
+    *(.data)
+    *(.gnu.linkonce.d*)
+    CONSTRUCTORS
+  }
+  .tbss           : { *(.tbss .tbss.* .gnu.linkonce.tb.*) *(.tcommon) }
+  .data1   : { *(.data1) }
+  .preinit_array     :
+  {
+    PROVIDE (__preinit_array_start = .);
+    KEEP (*(.preinit_array))
+    PROVIDE (__preinit_array_end = .);
+  }
+  .init_array     :
+  {
+     PROVIDE (__init_array_start = .);
+     KEEP (*(SORT(.init_array.*)))
+     KEEP (*(.init_array))
+     PROVIDE (__init_array_end = .);
+  }
+  .fini_array     :
+  {
+    PROVIDE (__fini_array_start = .);
+    KEEP (*(.fini_array))
+    KEEP (*(SORT(.fini_array.*)))
+    PROVIDE (__fini_array_end = .);
+  }
+  .ctors         :
+  {
+    *(.ctors)
+  }
+  .dtors         :
+  {
+    *(.dtors)
+  }
+  .plt      : { *(.plt)	}
+  .got           : { *(.got.plt) *(.got) }
+  .dynamic       : { *(.dynamic) }
+  /* We want the small data sections together, so single-instruction offsets
+     can access them all, and initialized data all before uninitialized, so
+     we can shorten the on-disk segment size.  */
+  .sdata     : { *(.sdata) }
+  _edata  =  .;
+  PROVIDE (edata = .);
+  __bss_start = .;
+  .sbss      : { *(.sbss) *(.scommon) }
+  .bss       :
+  {
+   *(.dynbss)
+   *(.bss)
+   *(COMMON)
+  }
+  _end = . ;
+  PROVIDE (end = .);
+  /* Stabs debugging sections.  */
+  .stab 0 : { *(.stab) }
+  .stabstr 0 : { *(.stabstr) }
+  .stab.excl 0 : { *(.stab.excl) }
+  .stab.exclstr 0 : { *(.stab.exclstr) }
+  .stab.index 0 : { *(.stab.index) }
+  .stab.indexstr 0 : { *(.stab.indexstr) }
+  .comment 0 : { *(.comment) }
+  /* DWARF debug sections.
+     Symbols in the DWARF debugging sections are relative to the beginning
+     of the section so we begin them at 0.  */
+  /* DWARF 1 */
+  .debug          0 : { *(.debug) }
+  .line           0 : { *(.line) }
+  /* GNU DWARF 1 extensions */
+  .debug_srcinfo  0 : { *(.debug_srcinfo) }
+  .debug_sfnames  0 : { *(.debug_sfnames) }
+  /* DWARF 1.1 and DWARF 2 */
+  .debug_aranges  0 : { *(.debug_aranges) }
+  .debug_pubnames 0 : { *(.debug_pubnames) }
+  /* DWARF 2 */
+  .debug_info     0 : { *(.debug_info) }
+  .debug_abbrev   0 : { *(.debug_abbrev) }
+  .debug_line     0 : { *(.debug_line) }
+  .debug_frame    0 : { *(.debug_frame) }
+  .debug_str      0 : { *(.debug_str) }
+  .debug_loc      0 : { *(.debug_loc) }
+  .debug_macinfo  0 : { *(.debug_macinfo) }
+  /* SGI/MIPS DWARF 2 extensions */
+  .debug_weaknames 0 : { *(.debug_weaknames) }
+  .debug_funcnames 0 : { *(.debug_funcnames) }
+  .debug_typenames 0 : { *(.debug_typenames) }
+  .debug_varnames  0 : { *(.debug_varnames) }
+  /* These must appear regardless of  .  */
+}

async.c

@@ -23,15 +23,16 @@
  */
 
 #include "qemu-common.h"
-#include "block/aio.h"
-#include "block/thread-pool.h"
-#include "qemu/main-loop.h"
+#include "qemu-aio.h"
+#include "main-loop.h"
+
+/* Anchor of the list of Bottom Halves belonging to the context */
+static struct QEMUBH *first_bh;
 
 /***********************************************************/
 /* bottom halves (can be seen as timers which expire ASAP) */
 
 struct QEMUBH {
-    AioContext *ctx;
     QEMUBHFunc *cb;
     void *opaque;
     QEMUBH *next;
@@ -40,41 +41,30 @@ struct QEMUBH {
     bool deleted;
 };
 
-QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
+QEMUBH *qemu_bh_new(QEMUBHFunc *cb, void *opaque)
 {
     QEMUBH *bh;
     bh = g_malloc0(sizeof(QEMUBH));
-    bh->ctx = ctx;
     bh->cb = cb;
     bh->opaque = opaque;
-    qemu_mutex_lock(&ctx->bh_lock);
-    bh->next = ctx->first_bh;
-    /* Make sure that the members are ready before putting bh into list */
-    smp_wmb();
-    ctx->first_bh = bh;
-    qemu_mutex_unlock(&ctx->bh_lock);
+    bh->next = first_bh;
+    first_bh = bh;
     return bh;
 }
 
-/* Multiple occurrences of aio_bh_poll cannot be called concurrently */
-int aio_bh_poll(AioContext *ctx)
+int qemu_bh_poll(void)
 {
     QEMUBH *bh, **bhp, *next;
     int ret;
+    static int nesting = 0;
 
-    ctx->walking_bh++;
+    nesting++;
 
     ret = 0;
-    for (bh = ctx->first_bh; bh; bh = next) {
-        /* Make sure that fetching bh happens before accessing its members */
-        smp_read_barrier_depends();
+    for (bh = first_bh; bh; bh = next) {
         next = bh->next;
         if (!bh->deleted && bh->scheduled) {
             bh->scheduled = 0;
-            /* Paired with write barrier in bh schedule to ensure reading for
-             * idle & callbacks coming after bh's scheduling.
-             */
-            smp_rmb();
             if (!bh->idle)
                 ret = 1;
             bh->idle = 0;
@@ -82,12 +72,11 @@ int aio_bh_poll(AioContext *ctx)
         }
     }
 
-    ctx->walking_bh--;
+    nesting--;
 
     /* remove deleted bhs */
-    if (!ctx->walking_bh) {
-        qemu_mutex_lock(&ctx->bh_lock);
-        bhp = &ctx->first_bh;
+    if (!nesting) {
+        bhp = &first_bh;
         while (*bhp) {
             bh = *bhp;
             if (bh->deleted) {
@@ -97,7 +86,6 @@ int aio_bh_poll(AioContext *ctx)
                 bhp = &bh->next;
             }
         }
-        qemu_mutex_unlock(&ctx->bh_lock);
     }
 
     return ret;
@@ -107,153 +95,48 @@ void qemu_bh_schedule_idle(QEMUBH *bh)
 {
     if (bh->scheduled)
         return;
-    bh->idle = 1;
-    /* Make sure that idle & any writes needed by the callback are done
-     * before the locations are read in the aio_bh_poll.
-     */
-    smp_wmb();
     bh->scheduled = 1;
+    bh->idle = 1;
 }
 
 void qemu_bh_schedule(QEMUBH *bh)
 {
     if (bh->scheduled)
         return;
-    bh->idle = 0;
-    /* Make sure that idle & any writes needed by the callback are done
-     * before the locations are read in the aio_bh_poll.
-     */
-    smp_wmb();
     bh->scheduled = 1;
-    aio_notify(bh->ctx);
+    bh->idle = 0;
+    /* stop the currently executing CPU to execute the BH ASAP */
+    qemu_notify_event();
 }
 
-
-/* This func is async.
- */
 void qemu_bh_cancel(QEMUBH *bh)
 {
     bh->scheduled = 0;
 }
 
-/* This func is async.The bottom half will do the delete action at the finial
- * end.
- */
 void qemu_bh_delete(QEMUBH *bh)
 {
     bh->scheduled = 0;
     bh->deleted = 1;
 }
 
-static gboolean
-aio_ctx_prepare(GSource *source, gint    *timeout)
+void qemu_bh_update_timeout(uint32_t *timeout)
 {
-    AioContext *ctx = (AioContext *) source;
     QEMUBH *bh;
 
-    for (bh = ctx->first_bh; bh; bh = bh->next) {
+    for (bh = first_bh; bh; bh = bh->next) {
         if (!bh->deleted && bh->scheduled) {
             if (bh->idle) {
                 /* idle bottom halves will be polled at least
                  * every 10ms */
-                *timeout = 10;
+                *timeout = MIN(10, *timeout);
             } else {
                 /* non-idle bottom halves will be executed
                  * immediately */
                 *timeout = 0;
-                return true;
+                break;
             }
         }
     }
-
-    return false;
 }
 
-static gboolean
-aio_ctx_check(GSource *source)
-{
-    AioContext *ctx = (AioContext *) source;
-    QEMUBH *bh;
-
-    for (bh = ctx->first_bh; bh; bh = bh->next) {
-        if (!bh->deleted && bh->scheduled) {
-            return true;
-	}
-    }
-    return aio_pending(ctx);
-}
-
-static gboolean
-aio_ctx_dispatch(GSource     *source,
-                 GSourceFunc  callback,
-                 gpointer     user_data)
-{
-    AioContext *ctx = (AioContext *) source;
-
-    assert(callback == NULL);
-    aio_poll(ctx, false);
-    return true;
-}
-
-static void
-aio_ctx_finalize(GSource     *source)
-{
-    AioContext *ctx = (AioContext *) source;
-
-    thread_pool_free(ctx->thread_pool);
-    aio_set_event_notifier(ctx, &ctx->notifier, NULL, NULL);
-    event_notifier_cleanup(&ctx->notifier);
-    qemu_mutex_destroy(&ctx->bh_lock);
-    g_array_free(ctx->pollfds, TRUE);
-}
-
-static GSourceFuncs aio_source_funcs = {
-    aio_ctx_prepare,
-    aio_ctx_check,
-    aio_ctx_dispatch,
-    aio_ctx_finalize
-};
-
-GSource *aio_get_g_source(AioContext *ctx)
-{
-    g_source_ref(&ctx->source);
-    return &ctx->source;
-}
-
-ThreadPool *aio_get_thread_pool(AioContext *ctx)
-{
-    if (!ctx->thread_pool) {
-        ctx->thread_pool = thread_pool_new(ctx);
-    }
-    return ctx->thread_pool;
-}
-
-void aio_notify(AioContext *ctx)
-{
-    event_notifier_set(&ctx->notifier);
-}
-
-AioContext *aio_context_new(void)
-{
-    AioContext *ctx;
-    ctx = (AioContext *) g_source_new(&aio_source_funcs, sizeof(AioContext));
-    ctx->pollfds = g_array_new(FALSE, FALSE, sizeof(GPollFD));
-    ctx->thread_pool = NULL;
-    qemu_mutex_init(&ctx->bh_lock);
-    event_notifier_init(&ctx->notifier, false);
-    aio_set_event_notifier(ctx, &ctx->notifier, 
-                           (EventNotifierHandler *)
-                           event_notifier_test_and_clear, NULL);
-
-    return ctx;
-}
-
-void aio_context_ref(AioContext *ctx)
-{
-    g_source_ref(&ctx->source);
-}
-
-void aio_context_unref(AioContext *ctx)
-{
-    g_source_unref(&ctx->source);
-}

audio/Makefile.objs

@@ -1,17 +0,0 @@
-common-obj-y = audio.o noaudio.o wavaudio.o mixeng.o
-common-obj-$(CONFIG_SDL) += sdlaudio.o
-common-obj-$(CONFIG_OSS) += ossaudio.o
-common-obj-$(CONFIG_SPICE) += spiceaudio.o
-common-obj-$(CONFIG_COREAUDIO) += coreaudio.o
-common-obj-$(CONFIG_ALSA) += alsaaudio.o
-common-obj-$(CONFIG_DSOUND) += dsoundaudio.o
-common-obj-$(CONFIG_FMOD) += fmodaudio.o
-common-obj-$(CONFIG_ESD) += esdaudio.o
-common-obj-$(CONFIG_PA) += paaudio.o
-common-obj-$(CONFIG_WINWAVE) += winwaveaudio.o
-common-obj-$(CONFIG_AUDIO_PT_INT) += audio_pt_int.o
-common-obj-$(CONFIG_AUDIO_WIN_INT) += audio_win_int.o
-common-obj-y += wavcapture.o
-
-$(obj)/audio.o $(obj)/fmodaudio.o: QEMU_CFLAGS += $(FMOD_CFLAGS)
-$(obj)/sdlaudio.o: QEMU_CFLAGS += $(SDL_CFLAGS)

audio/alsaaudio.c

@@ -23,7 +23,7 @@
  */
 #include <alsa/asoundlib.h>
 #include "qemu-common.h"
-#include "qemu/main-loop.h"
+#include "qemu-char.h"
 #include "audio.h"
 
 #if QEMU_GNUC_PREREQ(4, 3)

audio/audio.c

@@ -23,9 +23,9 @@
  */
 #include "hw/hw.h"
 #include "audio.h"
-#include "monitor/monitor.h"
-#include "qemu/timer.h"
-#include "sysemu/sysemu.h"
+#include "monitor.h"
+#include "qemu-timer.h"
+#include "sysemu.h"
 
 #define AUDIO_CAP "audio"
 #include "audio_int.h"
@@ -818,7 +818,6 @@ static int audio_attach_capture (HWVoiceOut *hw)
         sw->active = hw->enabled;
         sw->conv = noop_conv;
         sw->ratio = ((int64_t) hw_cap->info.freq << 32) / sw->info.freq;
-        sw->vol = nominal_volume;
         sw->rate = st_rate_start (sw->info.freq, hw_cap->info.freq);
         if (!sw->rate) {
             dolog ("Could not start rate conversion for `%s'\n", SW_NAME (sw));
@@ -828,9 +827,8 @@ static int audio_attach_capture (HWVoiceOut *hw)
         QLIST_INSERT_HEAD (&hw_cap->sw_head, sw, entries);
         QLIST_INSERT_HEAD (&hw->cap_head, sc, entries);
 #ifdef DEBUG_CAPTURE
-        sw->name = g_strdup_printf ("for %p %d,%d,%d",
-                                    hw, sw->info.freq, sw->info.bits,
-                                    sw->info.nchannels);
+        asprintf (&sw->name, "for %p %d,%d,%d",
+                  hw, sw->info.freq, sw->info.bits, sw->info.nchannels);
         dolog ("Added %s active = %d\n", sw->name, sw->active);
 #endif
         if (sw->active) {

audio/audio.h

@@ -25,7 +25,7 @@
 #define QEMU_AUDIO_H
 
 #include "config-host.h"
-#include "qemu/queue.h"
+#include "qemu-queue.h"
 
 typedef void (*audio_callback_fn) (void *opaque, int avail);
 

audio/audio_int.h

@@ -243,13 +243,38 @@ static inline int audio_ring_dist (int dst, int src, int len)
     return (dst >= src) ? (dst - src) : (len - src + dst);
 }
 
-#define dolog(fmt, ...) AUD_log(AUDIO_CAP, fmt, ## __VA_ARGS__)
+static void GCC_ATTR dolog (const char *fmt, ...)
+{
+    va_list ap;
+
+    va_start (ap, fmt);
+    AUD_vlog (AUDIO_CAP, fmt, ap);
+    va_end (ap);
+}
 
 #ifdef DEBUG
-#define ldebug(fmt, ...) AUD_log(AUDIO_CAP, fmt, ## __VA_ARGS__)
+static void GCC_ATTR ldebug (const char *fmt, ...)
+{
+    va_list ap;
+
+    va_start (ap, fmt);
+    AUD_vlog (AUDIO_CAP, fmt, ap);
+    va_end (ap);
+}
 #else
-#define ldebug(fmt, ...) (void)0
+#if defined NDEBUG && defined __GNUC__
+#define ldebug(...)
+#elif defined NDEBUG && defined _MSC_VER
+#define ldebug __noop
+#else
+static void GCC_ATTR ldebug (const char *fmt, ...)
+{
+    (void) fmt;
+}
 #endif
+#endif
+
+#undef GCC_ATTR
 
 #define AUDIO_STRINGIFY_(n) #n
 #define AUDIO_STRINGIFY(n) AUDIO_STRINGIFY_(n)

audio/audio_template.h

@@ -410,15 +410,15 @@ SW *glue (AUD_open_, TYPE) (
     SW *old_sw = NULL;
 #endif
 
+    ldebug ("open %s, freq %d, nchannels %d, fmt %d\n",
+            name, as->freq, as->nchannels, as->fmt);
+
     if (audio_bug (AUDIO_FUNC, !card || !name || !callback_fn || !as)) {
         dolog ("card=%p name=%p callback_fn=%p as=%p\n",
                card, name, callback_fn, as);
         goto fail;
     }
 
-    ldebug ("open %s, freq %d, nchannels %d, fmt %d\n",
-            name, as->freq, as->nchannels, as->fmt);
-
     if (audio_bug (AUDIO_FUNC, audio_validate_settings (as))) {
         audio_print_settings (as);
         goto fail;

audio/audio_win_int.c

@@ -1,6 +1,7 @@
 /* public domain */
 
 #include "qemu-common.h"
+#include "audio.h"
 
 #define AUDIO_CAP "win-int"
 #include <windows.h>

audio/noaudio.c

@@ -23,7 +23,7 @@
  */
 #include "qemu-common.h"
 #include "audio.h"
-#include "qemu/timer.h"
+#include "qemu-timer.h"
 
 #define AUDIO_CAP "noaudio"
 #include "audio_int.h"

audio/ossaudio.c

@@ -25,10 +25,14 @@
 #include <sys/mman.h>
 #include <sys/types.h>
 #include <sys/ioctl.h>
+#ifdef __OpenBSD__
+#include <soundcard.h>
+#else
 #include <sys/soundcard.h>
+#endif
 #include "qemu-common.h"
-#include "qemu/main-loop.h"
-#include "qemu/host-utils.h"
+#include "host-utils.h"
+#include "qemu-char.h"
 #include "audio.h"
 
 #define AUDIO_CAP "oss"

audio/spiceaudio.c

@@ -18,7 +18,7 @@
  */
 
 #include "hw/hw.h"
-#include "qemu/timer.h"
+#include "qemu-timer.h"
 #include "ui/qemu-spice.h"
 
 #define AUDIO_CAP "spice"

audio/wavaudio.c

@@ -22,7 +22,7 @@
  * THE SOFTWARE.
  */
 #include "hw/hw.h"
-#include "qemu/timer.h"
+#include "qemu-timer.h"
 #include "audio.h"
 
 #define AUDIO_CAP "wav"

audio/wavcapture.c

@@ -1,5 +1,5 @@
 #include "hw/hw.h"
-#include "monitor/monitor.h"
+#include "monitor.h"
 #include "audio.h"
 
 typedef struct {

audio/winwaveaudio.c

@@ -1,7 +1,7 @@
 /* public domain */
 
 #include "qemu-common.h"
-#include "sysemu/sysemu.h"
+#include "sysemu.h"
 #include "audio.h"
 
 #define AUDIO_CAP "winwave"
@@ -72,7 +72,7 @@ static void winwave_log_mmresult (MMRESULT mr)
         break;
 
     case MMSYSERR_NOMEM:
-        str = "Unable to allocate or lock memory";
+        str = "Unable to allocate or locl memory";
         break;
 
     case WAVERR_SYNC:

backends/Makefile.objs

@@ -1,8 +0,0 @@
-common-obj-y += rng.o rng-egd.o
-common-obj-$(CONFIG_POSIX) += rng-random.o
-
-common-obj-y += msmouse.o
-common-obj-$(CONFIG_BRLAPI) += baum.o
-$(obj)/baum.o: QEMU_CFLAGS += $(SDL_CFLAGS) 
-
-common-obj-$(CONFIG_TPM) += tpm.o

backends/rng-egd.c

@@ -1,230 +0,0 @@
-/*
- * QEMU Random Number Generator Backend
- *
- * Copyright IBM, Corp. 2012
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.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.
- */
-
-#include "sysemu/rng.h"
-#include "sysemu/char.h"
-#include "qapi/qmp/qerror.h"
-#include "hw/qdev.h" /* just for DEFINE_PROP_CHR */
-
-#define TYPE_RNG_EGD "rng-egd"
-#define RNG_EGD(obj) OBJECT_CHECK(RngEgd, (obj), TYPE_RNG_EGD)
-
-typedef struct RngEgd
-{
-    RngBackend parent;
-
-    CharDriverState *chr;
-    char *chr_name;
-
-    GSList *requests;
-} RngEgd;
-
-typedef struct RngRequest
-{
-    EntropyReceiveFunc *receive_entropy;
-    uint8_t *data;
-    void *opaque;
-    size_t offset;
-    size_t size;
-} RngRequest;
-
-static void rng_egd_request_entropy(RngBackend *b, size_t size,
-                                    EntropyReceiveFunc *receive_entropy,
-                                    void *opaque)
-{
-    RngEgd *s = RNG_EGD(b);
-    RngRequest *req;
-
-    req = g_malloc(sizeof(*req));
-
-    req->offset = 0;
-    req->size = size;
-    req->receive_entropy = receive_entropy;
-    req->opaque = opaque;
-    req->data = g_malloc(req->size);
-
-    while (size > 0) {
-        uint8_t header[2];
-        uint8_t len = MIN(size, 255);
-
-        /* synchronous entropy request */
-        header[0] = 0x02;
-        header[1] = len;
-
-        qemu_chr_fe_write(s->chr, header, sizeof(header));
-
-        size -= len;
-    }
-
-    s->requests = g_slist_append(s->requests, req);
-}
-
-static void rng_egd_free_request(RngRequest *req)
-{
-    g_free(req->data);
-    g_free(req);
-}
-
-static int rng_egd_chr_can_read(void *opaque)
-{
-    RngEgd *s = RNG_EGD(opaque);
-    GSList *i;
-    int size = 0;
-
-    for (i = s->requests; i; i = i->next) {
-        RngRequest *req = i->data;
-        size += req->size - req->offset;
-    }
-
-    return size;
-}
-
-static void rng_egd_chr_read(void *opaque, const uint8_t *buf, int size)
-{
-    RngEgd *s = RNG_EGD(opaque);
-
-    while (size > 0 && s->requests) {
-        RngRequest *req = s->requests->data;
-        int len = MIN(size, req->size - req->offset);
-
-        memcpy(req->data + req->offset, buf, len);
-        req->offset += len;
-        size -= len;
-
-        if (req->offset == req->size) {
-            s->requests = g_slist_remove_link(s->requests, s->requests);
-
-            req->receive_entropy(req->opaque, req->data, req->size);
-
-            rng_egd_free_request(req);
-        }
-    }
-}
-
-static void rng_egd_free_requests(RngEgd *s)
-{
-    GSList *i;
-
-    for (i = s->requests; i; i = i->next) {
-        rng_egd_free_request(i->data);
-    }
-
-    g_slist_free(s->requests);
-    s->requests = NULL;
-}
-
-static void rng_egd_cancel_requests(RngBackend *b)
-{
-    RngEgd *s = RNG_EGD(b);
-
-    /* We simply delete the list of pending requests.  If there is data in the 
-     * queue waiting to be read, this is okay, because there will always be
-     * more data than we requested originally
-     */
-    rng_egd_free_requests(s);
-}
-
-static void rng_egd_opened(RngBackend *b, Error **errp)
-{
-    RngEgd *s = RNG_EGD(b);
-
-    if (s->chr_name == NULL) {
-        error_set(errp, QERR_INVALID_PARAMETER_VALUE,
-                  "chardev", "a valid character device");
-        return;
-    }
-
-    s->chr = qemu_chr_find(s->chr_name);
-    if (s->chr == NULL) {
-        error_set(errp, QERR_DEVICE_NOT_FOUND, s->chr_name);
-        return;
-    }
-
-    if (qemu_chr_fe_claim(s->chr) != 0) {
-        error_set(errp, QERR_DEVICE_IN_USE, s->chr_name);
-        return;
-    }
-
-    /* FIXME we should resubmit pending requests when the CDS reconnects. */
-    qemu_chr_add_handlers(s->chr, rng_egd_chr_can_read, rng_egd_chr_read,
-                          NULL, s);
-}
-
-static void rng_egd_set_chardev(Object *obj, const char *value, Error **errp)
-{
-    RngBackend *b = RNG_BACKEND(obj);
-    RngEgd *s = RNG_EGD(b);
-
-    if (b->opened) {
-        error_set(errp, QERR_PERMISSION_DENIED);
-    } else {
-        g_free(s->chr_name);
-        s->chr_name = g_strdup(value);
-    }
-}
-
-static char *rng_egd_get_chardev(Object *obj, Error **errp)
-{
-    RngEgd *s = RNG_EGD(obj);
-
-    if (s->chr && s->chr->label) {
-        return g_strdup(s->chr->label);
-    }
-
-    return NULL;
-}
-
-static void rng_egd_init(Object *obj)
-{
-    object_property_add_str(obj, "chardev",
-                            rng_egd_get_chardev, rng_egd_set_chardev,
-                            NULL);
-}
-
-static void rng_egd_finalize(Object *obj)
-{
-    RngEgd *s = RNG_EGD(obj);
-
-    if (s->chr) {
-        qemu_chr_add_handlers(s->chr, NULL, NULL, NULL, NULL);
-        qemu_chr_fe_release(s->chr);
-    }
-
-    g_free(s->chr_name);
-
-    rng_egd_free_requests(s);
-}
-
-static void rng_egd_class_init(ObjectClass *klass, void *data)
-{
-    RngBackendClass *rbc = RNG_BACKEND_CLASS(klass);
-
-    rbc->request_entropy = rng_egd_request_entropy;
-    rbc->cancel_requests = rng_egd_cancel_requests;
-    rbc->opened = rng_egd_opened;
-}
-
-static const TypeInfo rng_egd_info = {
-    .name = TYPE_RNG_EGD,
-    .parent = TYPE_RNG_BACKEND,
-    .instance_size = sizeof(RngEgd),
-    .class_init = rng_egd_class_init,
-    .instance_init = rng_egd_init,
-    .instance_finalize = rng_egd_finalize,
-};
-
-static void register_types(void)
-{
-    type_register_static(&rng_egd_info);
-}
-
-type_init(register_types);

backends/rng-random.c

@@ -1,163 +0,0 @@
-/*
- * QEMU Random Number Generator Backend
- *
- * Copyright IBM, Corp. 2012
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.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.
- */
-
-#include "sysemu/rng-random.h"
-#include "sysemu/rng.h"
-#include "qapi/qmp/qerror.h"
-#include "qemu/main-loop.h"
-
-struct RndRandom
-{
-    RngBackend parent;
-
-    int fd;
-    char *filename;
-
-    EntropyReceiveFunc *receive_func;
-    void *opaque;
-    size_t size;
-};
-
-/**
- * A simple and incomplete backend to request entropy from /dev/random.
- *
- * This backend exposes an additional "filename" property that can be used to
- * set the filename to use to open the backend.
- */
-
-static void entropy_available(void *opaque)
-{
-    RndRandom *s = RNG_RANDOM(opaque);
-    uint8_t buffer[s->size];
-    ssize_t len;
-
-    len = read(s->fd, buffer, s->size);
-    if (len < 0 && errno == EAGAIN) {
-        return;
-    }
-    g_assert(len != -1);
-
-    s->receive_func(s->opaque, buffer, len);
-    s->receive_func = NULL;
-
-    qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
-}
-
-static void rng_random_request_entropy(RngBackend *b, size_t size,
-                                        EntropyReceiveFunc *receive_entropy,
-                                        void *opaque)
-{
-    RndRandom *s = RNG_RANDOM(b);
-
-    if (s->receive_func) {
-        s->receive_func(s->opaque, NULL, 0);
-    }
-
-    s->receive_func = receive_entropy;
-    s->opaque = opaque;
-    s->size = size;
-
-    qemu_set_fd_handler(s->fd, entropy_available, NULL, s);
-}
-
-static void rng_random_opened(RngBackend *b, Error **errp)
-{
-    RndRandom *s = RNG_RANDOM(b);
-
-    if (s->filename == NULL) {
-        error_set(errp, QERR_INVALID_PARAMETER_VALUE,
-                  "filename", "a valid filename");
-    } else {
-        s->fd = qemu_open(s->filename, O_RDONLY | O_NONBLOCK);
-        if (s->fd == -1) {
-            error_setg_file_open(errp, errno, s->filename);
-        }
-    }
-}
-
-static char *rng_random_get_filename(Object *obj, Error **errp)
-{
-    RndRandom *s = RNG_RANDOM(obj);
-
-    if (s->filename) {
-        return g_strdup(s->filename);
-    }
-
-    return NULL;
-}
-
-static void rng_random_set_filename(Object *obj, const char *filename,
-                                 Error **errp)
-{
-    RngBackend *b = RNG_BACKEND(obj);
-    RndRandom *s = RNG_RANDOM(obj);
-
-    if (b->opened) {
-        error_set(errp, QERR_PERMISSION_DENIED);
-        return;
-    }
-
-    if (s->filename) {
-        g_free(s->filename);
-    }
-
-    s->filename = g_strdup(filename);
-}
-
-static void rng_random_init(Object *obj)
-{
-    RndRandom *s = RNG_RANDOM(obj);
-
-    object_property_add_str(obj, "filename",
-                            rng_random_get_filename,
-                            rng_random_set_filename,
-                            NULL);
-
-    s->filename = g_strdup("/dev/random");
-}
-
-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_close(s->fd);
-    }
-
-    g_free(s->filename);
-}
-
-static void rng_random_class_init(ObjectClass *klass, void *data)
-{
-    RngBackendClass *rbc = RNG_BACKEND_CLASS(klass);
-
-    rbc->request_entropy = rng_random_request_entropy;
-    rbc->opened = rng_random_opened;
-}
-
-static const TypeInfo rng_random_info = {
-    .name = TYPE_RNG_RANDOM,
-    .parent = TYPE_RNG_BACKEND,
-    .instance_size = sizeof(RndRandom),
-    .class_init = rng_random_class_init,
-    .instance_init = rng_random_init,
-    .instance_finalize = rng_random_finalize,
-};
-
-static void register_types(void)
-{
-    type_register_static(&rng_random_info);
-}
-
-type_init(register_types);

backends/rng.c

@@ -1,93 +0,0 @@
-/*
- * QEMU Random Number Generator Backend
- *
- * Copyright IBM, Corp. 2012
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.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.
- */
-
-#include "sysemu/rng.h"
-#include "qapi/qmp/qerror.h"
-
-void rng_backend_request_entropy(RngBackend *s, size_t size,
-                                 EntropyReceiveFunc *receive_entropy,
-                                 void *opaque)
-{
-    RngBackendClass *k = RNG_BACKEND_GET_CLASS(s);
-
-    if (k->request_entropy) {
-        k->request_entropy(s, size, receive_entropy, opaque);
-    }
-}
-
-void rng_backend_cancel_requests(RngBackend *s)
-{
-    RngBackendClass *k = RNG_BACKEND_GET_CLASS(s);
-
-    if (k->cancel_requests) {
-        k->cancel_requests(s);
-    }
-}
-
-static bool rng_backend_prop_get_opened(Object *obj, Error **errp)
-{
-    RngBackend *s = RNG_BACKEND(obj);
-
-    return s->opened;
-}
-
-void rng_backend_open(RngBackend *s, Error **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);
-
-    if (value == s->opened) {
-        return;
-    }
-
-    if (!value && s->opened) {
-        error_set(errp, QERR_PERMISSION_DENIED);
-        return;
-    }
-
-    if (k->opened) {
-        k->opened(s, errp);
-    }
-
-    if (!error_is_set(errp)) {
-        s->opened = value;
-    }
-}
-
-static void rng_backend_init(Object *obj)
-{
-    object_property_add_bool(obj, "opened",
-                             rng_backend_prop_get_opened,
-                             rng_backend_prop_set_opened,
-                             NULL);
-}
-
-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),
-    .abstract = true,
-};
-
-static void register_types(void)
-{
-    type_register_static(&rng_backend_info);
-}
-
-type_init(register_types);

backends/tpm.c

@@ -1,190 +0,0 @@
-/*
- * QEMU TPM Backend
- *
- * Copyright IBM, Corp. 2013
- *
- * Authors:
- *  Stefan Berger   <stefanb@us.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.
- *
- * Based on backends/rng.c by Anthony Liguori
- */
-
-#include "sysemu/tpm_backend.h"
-#include "qapi/qmp/qerror.h"
-#include "sysemu/tpm.h"
-#include "qemu/thread.h"
-#include "sysemu/tpm_backend_int.h"
-
-enum TpmType tpm_backend_get_type(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->type;
-}
-
-const char *tpm_backend_get_desc(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->desc();
-}
-
-void tpm_backend_destroy(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->destroy(s);
-}
-
-int tpm_backend_init(TPMBackend *s, TPMState *state,
-                     TPMRecvDataCB *datacb)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->init(s, state, datacb);
-}
-
-int tpm_backend_startup_tpm(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->startup_tpm(s);
-}
-
-bool tpm_backend_had_startup_error(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->had_startup_error(s);
-}
-
-size_t tpm_backend_realloc_buffer(TPMBackend *s, TPMSizedBuffer *sb)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->realloc_buffer(sb);
-}
-
-void tpm_backend_deliver_request(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    k->ops->deliver_request(s);
-}
-
-void tpm_backend_reset(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    k->ops->reset(s);
-}
-
-void tpm_backend_cancel_cmd(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    k->ops->cancel_cmd(s);
-}
-
-bool tpm_backend_get_tpm_established_flag(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->get_tpm_established_flag(s);
-}
-
-static bool tpm_backend_prop_get_opened(Object *obj, Error **errp)
-{
-    TPMBackend *s = TPM_BACKEND(obj);
-
-    return s->opened;
-}
-
-void tpm_backend_open(TPMBackend *s, Error **errp)
-{
-    object_property_set_bool(OBJECT(s), true, "opened", errp);
-}
-
-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);
-
-    if (value == s->opened) {
-        return;
-    }
-
-    if (!value && s->opened) {
-        error_set(errp, QERR_PERMISSION_DENIED);
-        return;
-    }
-
-    if (k->opened) {
-        k->opened(s, errp);
-    }
-
-    if (!error_is_set(errp)) {
-        s->opened = value;
-    }
-}
-
-static void tpm_backend_instance_init(Object *obj)
-{
-    object_property_add_bool(obj, "opened",
-                             tpm_backend_prop_get_opened,
-                             tpm_backend_prop_set_opened,
-                             NULL);
-}
-
-void tpm_backend_thread_deliver_request(TPMBackendThread *tbt)
-{
-   g_thread_pool_push(tbt->pool, (gpointer)TPM_BACKEND_CMD_PROCESS_CMD, NULL);
-}
-
-void tpm_backend_thread_create(TPMBackendThread *tbt,
-                               GFunc func, gpointer user_data)
-{
-    if (!tbt->pool) {
-        tbt->pool = g_thread_pool_new(func, user_data, 1, TRUE, NULL);
-        g_thread_pool_push(tbt->pool, (gpointer)TPM_BACKEND_CMD_INIT, NULL);
-    }
-}
-
-void tpm_backend_thread_end(TPMBackendThread *tbt)
-{
-    if (tbt->pool) {
-        g_thread_pool_push(tbt->pool, (gpointer)TPM_BACKEND_CMD_END, NULL);
-        g_thread_pool_free(tbt->pool, FALSE, TRUE);
-        tbt->pool = NULL;
-    }
-}
-
-void tpm_backend_thread_tpm_reset(TPMBackendThread *tbt,
-                                  GFunc func, gpointer user_data)
-{
-    if (!tbt->pool) {
-        tpm_backend_thread_create(tbt, func, user_data);
-    } else {
-        g_thread_pool_push(tbt->pool, (gpointer)TPM_BACKEND_CMD_TPM_RESET,
-                           NULL);
-    }
-}
-
-static const TypeInfo tpm_backend_info = {
-    .name = TYPE_TPM_BACKEND,
-    .parent = TYPE_OBJECT,
-    .instance_size = sizeof(TPMBackend),
-    .instance_init = tpm_backend_instance_init,
-    .class_size = sizeof(TPMBackendClass),
-    .abstract = true,
-};
-
-static void register_types(void)
-{
-    type_register_static(&tpm_backend_info);
-}
-
-type_init(register_types);

balloon.c

@@ -24,13 +24,12 @@
  * THE SOFTWARE.
  */
 
-#include "monitor/monitor.h"
-#include "exec/cpu-common.h"
-#include "sysemu/kvm.h"
-#include "sysemu/balloon.h"
+#include "monitor.h"
+#include "cpu-common.h"
+#include "kvm.h"
+#include "balloon.h"
 #include "trace.h"
 #include "qmp-commands.h"
-#include "qapi/qmp/qjson.h"
 
 static QEMUBalloonEvent *balloon_event_fn;
 static QEMUBalloonStatus *balloon_stat_fn;
@@ -81,19 +80,6 @@ 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;

balloon.h

@@ -14,7 +14,7 @@
 #ifndef _QEMU_BALLOON_H
 #define _QEMU_BALLOON_H
 
-#include "monitor/monitor.h"
+#include "monitor.h"
 #include "qapi-types.h"
 
 typedef void (QEMUBalloonEvent)(void *opaque, ram_addr_t target);
@@ -24,6 +24,4 @@ int qemu_add_balloon_handler(QEMUBalloonEvent *event_func,
 			     QEMUBalloonStatus *stat_func, void *opaque);
 void qemu_remove_balloon_handler(void *opaque);
 
-void qemu_balloon_changed(int64_t actual);
-
 #endif

bitmap.c

@@ -9,8 +9,8 @@
  * Version 2.
  */
 
-#include "qemu/bitops.h"
-#include "qemu/bitmap.h"
+#include "bitops.h"
+#include "bitmap.h"
 
 /*
  * bitmaps provide an array of bits, implemented using an an

bitmap.h

@@ -13,7 +13,7 @@
 #define BITMAP_H
 
 #include "qemu-common.h"
-#include "qemu/bitops.h"
+#include "bitops.h"
 
 /*
  * The available bitmap operations and their rough meaning in the

bitops.c

@@ -11,7 +11,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#include "qemu/bitops.h"
+#include "bitops.h"
 
 #define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
 
@@ -42,23 +42,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
         size -= BITS_PER_LONG;
         result += BITS_PER_LONG;
     }
-    while (size >= 4*BITS_PER_LONG) {
-        unsigned long d1, d2, d3;
-        tmp = *p;
-        d1 = *(p+1);
-        d2 = *(p+2);
-        d3 = *(p+3);
-        if (tmp) {
-            goto found_middle;
-        }
-        if (d1 | d2 | d3) {
-            break;
-        }
-        p += 4;
-        result += 4*BITS_PER_LONG;
-        size -= 4*BITS_PER_LONG;
-    }
-    while (size >= BITS_PER_LONG) {
+    while (size & ~(BITS_PER_LONG-1)) {
         if ((tmp = *(p++))) {
             goto found_middle;
         }
@@ -76,7 +60,7 @@ found_first:
         return result + size;	/* Nope. */
     }
 found_middle:
-    return result + ctzl(tmp);
+    return result + bitops_ffsl(tmp);
 }
 
 /*
@@ -125,7 +109,7 @@ found_first:
         return result + size;	/* Nope. */
     }
 found_middle:
-    return result + ctzl(~tmp);
+    return result + ffz(tmp);
 }
 
 unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
@@ -149,7 +133,7 @@ unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
         tmp = addr[--words];
         if (tmp) {
         found:
-            return words * BITS_PER_LONG + BITS_PER_LONG - 1 - clzl(tmp);
+            return words * BITS_PER_LONG + bitops_flsl(tmp);
         }
     }
 

bitops.h

@@ -0,0 +1,272 @@
+/*
+ * Bitops Module
+ *
+ * Copyright (C) 2010 Corentin Chary <corentin.chary@gmail.com>
+ *
+ * Mostly inspired by (stolen from) linux/bitmap.h and linux/bitops.h
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+
+#ifndef BITOPS_H
+#define BITOPS_H
+
+#include "qemu-common.h"
+
+#define BITS_PER_BYTE           CHAR_BIT
+#define BITS_PER_LONG           (sizeof (unsigned long) * BITS_PER_BYTE)
+
+#define BIT(nr)			(1UL << (nr))
+#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
+#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
+#define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
+
+/**
+ * bitops_ffs - find first bit in word.
+ * @word: The word to search
+ *
+ * Undefined if no bit exists, so code should check against 0 first.
+ */
+static unsigned long bitops_ffsl(unsigned long word)
+{
+	int num = 0;
+
+#if LONG_MAX > 0x7FFFFFFF
+	if ((word & 0xffffffff) == 0) {
+		num += 32;
+		word >>= 32;
+	}
+#endif
+	if ((word & 0xffff) == 0) {
+		num += 16;
+		word >>= 16;
+	}
+	if ((word & 0xff) == 0) {
+		num += 8;
+		word >>= 8;
+	}
+	if ((word & 0xf) == 0) {
+		num += 4;
+		word >>= 4;
+	}
+	if ((word & 0x3) == 0) {
+		num += 2;
+		word >>= 2;
+	}
+	if ((word & 0x1) == 0) {
+		num += 1;
+        }
+	return num;
+}
+
+/**
+ * bitops_fls - find last (most-significant) set bit in a long word
+ * @word: the word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+static inline unsigned long bitops_flsl(unsigned long word)
+{
+	int num = BITS_PER_LONG - 1;
+
+#if LONG_MAX > 0x7FFFFFFF
+	if (!(word & (~0ul << 32))) {
+		num -= 32;
+		word <<= 32;
+	}
+#endif
+	if (!(word & (~0ul << (BITS_PER_LONG-16)))) {
+		num -= 16;
+		word <<= 16;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-8)))) {
+		num -= 8;
+		word <<= 8;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-4)))) {
+		num -= 4;
+		word <<= 4;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-2)))) {
+		num -= 2;
+
+		word <<= 2;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-1))))
+		num -= 1;
+	return num;
+}
+
+/**
+ * ffz - find first zero in word.
+ * @word: The word to search
+ *
+ * Undefined if no zero exists, so code should check against ~0UL first.
+ */
+static inline unsigned long ffz(unsigned long word)
+{
+    return bitops_ffsl(~word);
+}
+
+/**
+ * set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ */
+static inline void set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p  |= mask;
+}
+
+/**
+ * clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ */
+static inline void clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p &= ~mask;
+}
+
+/**
+ * change_bit - Toggle a bit in memory
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ */
+static inline void change_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p ^= mask;
+}
+
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ */
+static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old | mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ */
+static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old & ~mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ */
+static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old ^ mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static inline int test_bit(int nr, const volatile unsigned long *addr)
+{
+	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+}
+
+/**
+ * find_last_bit - find the last set bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum size to search
+ *
+ * Returns the bit number of the first set bit, or size.
+ */
+unsigned long find_last_bit(const unsigned long *addr,
+                            unsigned long size);
+
+/**
+ * find_next_bit - find the next set bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The bitmap size in bits
+ */
+unsigned long find_next_bit(const unsigned long *addr,
+				   unsigned long size, unsigned long offset);
+
+/**
+ * find_next_zero_bit - find the next cleared bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The bitmap size in bits
+ */
+
+unsigned long find_next_zero_bit(const unsigned long *addr,
+                                 unsigned long size,
+                                 unsigned long offset);
+
+/**
+ * find_first_bit - find the first set bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum size to search
+ *
+ * Returns the bit number of the first set bit.
+ */
+static inline unsigned long find_first_bit(const unsigned long *addr,
+                                           unsigned long size)
+{
+    return find_next_bit(addr, size, 0);
+}
+
+/**
+ * find_first_zero_bit - find the first cleared bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum size to search
+ *
+ * Returns the bit number of the first cleared bit.
+ */
+static inline unsigned long find_first_zero_bit(const unsigned long *addr,
+                                                unsigned long size)
+{
+    return find_next_zero_bit(addr, size, 0);
+}
+
+static inline unsigned long hweight_long(unsigned long w)
+{
+    unsigned long count;
+
+    for (count = 0; w; w >>= 1) {
+        count += w & 1;
+    }
+    return count;
+}
+
+#endif

block-migration.c

@@ -14,22 +14,20 @@
  */
 
 #include "qemu-common.h"
-#include "block/block_int.h"
+#include "block_int.h"
 #include "hw/hw.h"
-#include "qemu/queue.h"
-#include "qemu/timer.h"
-#include "migration/block.h"
-#include "migration/migration.h"
-#include "sysemu/blockdev.h"
+#include "qemu-queue.h"
+#include "qemu-timer.h"
+#include "block-migration.h"
+#include "migration.h"
+#include "blockdev.h"
 #include <assert.h>
 
-#define BLOCK_SIZE                       (1 << 20)
-#define BDRV_SECTORS_PER_DIRTY_CHUNK     (BLOCK_SIZE >> BDRV_SECTOR_BITS)
+#define BLOCK_SIZE (BDRV_SECTORS_PER_DIRTY_CHUNK << BDRV_SECTOR_BITS)
 
 #define BLK_MIG_FLAG_DEVICE_BLOCK       0x01
 #define BLK_MIG_FLAG_EOS                0x02
 #define BLK_MIG_FLAG_PROGRESS           0x04
-#define BLK_MIG_FLAG_ZERO_BLOCK         0x08
 
 #define MAX_IS_ALLOCATED_SEARCH 65536
 
@@ -44,24 +42,19 @@
 #endif
 
 typedef struct BlkMigDevState {
-    /* Written during setup phase.  Can be read without a lock.  */
     BlockDriverState *bs;
-    int shared_base;
-    int64_t total_sectors;
-    QSIMPLEQ_ENTRY(BlkMigDevState) entry;
-
-    /* Only used by migration thread.  Does not need a lock.  */
     int bulk_completed;
+    int shared_base;
     int64_t cur_sector;
     int64_t cur_dirty;
-
-    /* Protected by block migration lock.  */
-    unsigned long *aio_bitmap;
     int64_t completed_sectors;
+    int64_t total_sectors;
+    int64_t dirty;
+    QSIMPLEQ_ENTRY(BlkMigDevState) entry;
+    unsigned long *aio_bitmap;
 } BlkMigDevState;
 
 typedef struct BlkMigBlock {
-    /* Only used by migration thread.  */
     uint8_t *buf;
     BlkMigDevState *bmds;
     int64_t sector;
@@ -69,77 +62,41 @@ typedef struct BlkMigBlock {
     struct iovec iov;
     QEMUIOVector qiov;
     BlockDriverAIOCB *aiocb;
-
-    /* Protected by block migration lock.  */
     int ret;
     QSIMPLEQ_ENTRY(BlkMigBlock) entry;
 } BlkMigBlock;
 
 typedef struct BlkMigState {
-    /* Written during setup phase.  Can be read without a lock.  */
     int blk_enable;
     int shared_base;
     QSIMPLEQ_HEAD(bmds_list, BlkMigDevState) bmds_list;
-    int64_t total_sector_sum;
-    bool zero_blocks;
-
-    /* Protected by lock.  */
     QSIMPLEQ_HEAD(blk_list, BlkMigBlock) blk_list;
     int submitted;
     int read_done;
-
-    /* Only used by migration thread.  Does not need a lock.  */
     int transferred;
+    int64_t total_sector_sum;
     int prev_progress;
     int bulk_completed;
-
-    /* Lock must be taken _inside_ the iothread lock.  */
-    QemuMutex lock;
+    long double total_time;
+    long double prev_time_offset;
+    int reads;
 } BlkMigState;
 
 static BlkMigState block_mig_state;
 
-static void blk_mig_lock(void)
-{
-    qemu_mutex_lock(&block_mig_state.lock);
-}
-
-static void blk_mig_unlock(void)
-{
-    qemu_mutex_unlock(&block_mig_state.lock);
-}
-
-/* Must run outside of the iothread lock during the bulk phase,
- * or the VM will stall.
- */
-
 static void blk_send(QEMUFile *f, BlkMigBlock * blk)
 {
     int len;
-    uint64_t flags = BLK_MIG_FLAG_DEVICE_BLOCK;
-
-    if (block_mig_state.zero_blocks &&
-        buffer_is_zero(blk->buf, BLOCK_SIZE)) {
-        flags |= BLK_MIG_FLAG_ZERO_BLOCK;
-    }
 
     /* sector number and flags */
     qemu_put_be64(f, (blk->sector << BDRV_SECTOR_BITS)
-                     | flags);
+                     | BLK_MIG_FLAG_DEVICE_BLOCK);
 
     /* device name */
     len = strlen(blk->bmds->bs->device_name);
     qemu_put_byte(f, len);
     qemu_put_buffer(f, (uint8_t *)blk->bmds->bs->device_name, len);
 
-    /* if a block is zero we need to flush here since the network
-     * bandwidth is now a lot higher than the storage device bandwidth.
-     * thus if we queue zero blocks we slow down the migration */
-    if (flags & BLK_MIG_FLAG_ZERO_BLOCK) {
-        qemu_fflush(f);
-        return;
-    }
-
     qemu_put_buffer(f, blk->buf, BLOCK_SIZE);
 }
 
@@ -153,11 +110,9 @@ uint64_t blk_mig_bytes_transferred(void)
     BlkMigDevState *bmds;
     uint64_t sum = 0;
 
-    blk_mig_lock();
     QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
         sum += bmds->completed_sectors;
     }
-    blk_mig_unlock();
     return sum << BDRV_SECTOR_BITS;
 }
 
@@ -177,8 +132,11 @@ uint64_t blk_mig_bytes_total(void)
     return sum << BDRV_SECTOR_BITS;
 }
 
-
-/* Called with migration lock held.  */
+static inline long double compute_read_bwidth(void)
+{
+    assert(block_mig_state.total_time != 0);
+    return (block_mig_state.reads / block_mig_state.total_time) * BLOCK_SIZE;
+}
 
 static int bmds_aio_inflight(BlkMigDevState *bmds, int64_t sector)
 {
@@ -192,8 +150,6 @@ static int bmds_aio_inflight(BlkMigDevState *bmds, int64_t sector)
     }
 }
 
-/* Called with migration lock held.  */
-
 static void bmds_set_aio_inflight(BlkMigDevState *bmds, int64_t sector_num,
                              int nb_sectors, int set)
 {
@@ -228,26 +184,25 @@ static void alloc_aio_bitmap(BlkMigDevState *bmds)
     bmds->aio_bitmap = g_malloc0(bitmap_size);
 }
 
-/* Never hold migration lock when yielding to the main loop!  */
-
 static void blk_mig_read_cb(void *opaque, int ret)
 {
+    long double curr_time = qemu_get_clock_ns(rt_clock);
     BlkMigBlock *blk = opaque;
 
-    blk_mig_lock();
     blk->ret = ret;
 
+    block_mig_state.reads++;
+    block_mig_state.total_time += (curr_time - block_mig_state.prev_time_offset);
+    block_mig_state.prev_time_offset = curr_time;
+
     QSIMPLEQ_INSERT_TAIL(&block_mig_state.blk_list, blk, entry);
     bmds_set_aio_inflight(blk->bmds, blk->sector, blk->nr_sectors, 0);
 
     block_mig_state.submitted--;
     block_mig_state.read_done++;
     assert(block_mig_state.submitted >= 0);
-    blk_mig_unlock();
 }
 
-/* Called with no lock taken.  */
-
 static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds)
 {
     int64_t total_sectors = bmds->total_sectors;
@@ -257,13 +212,11 @@ static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds)
     int nr_sectors;
 
     if (bmds->shared_base) {
-        qemu_mutex_lock_iothread();
         while (cur_sector < total_sectors &&
                !bdrv_is_allocated(bs, cur_sector, MAX_IS_ALLOCATED_SEARCH,
                                   &nr_sectors)) {
             cur_sector += nr_sectors;
         }
-        qemu_mutex_unlock_iothread();
     }
 
     if (cur_sector >= total_sectors) {
@@ -292,29 +245,26 @@ static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds)
     blk->iov.iov_len = nr_sectors * BDRV_SECTOR_SIZE;
     qemu_iovec_init_external(&blk->qiov, &blk->iov, 1);
 
-    blk_mig_lock();
-    block_mig_state.submitted++;
-    blk_mig_unlock();
+    if (block_mig_state.submitted == 0) {
+        block_mig_state.prev_time_offset = qemu_get_clock_ns(rt_clock);
+    }
 
-    qemu_mutex_lock_iothread();
     blk->aiocb = bdrv_aio_readv(bs, cur_sector, &blk->qiov,
                                 nr_sectors, blk_mig_read_cb, blk);
+    block_mig_state.submitted++;
 
     bdrv_reset_dirty(bs, cur_sector, nr_sectors);
-    qemu_mutex_unlock_iothread();
-
     bmds->cur_sector = cur_sector + nr_sectors;
+
     return (bmds->cur_sector >= total_sectors);
 }
 
-/* Called with iothread lock taken.  */
-
 static void set_dirty_tracking(int enable)
 {
     BlkMigDevState *bmds;
 
     QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
-        bdrv_set_dirty_tracking(bmds->bs, enable ? BLOCK_SIZE : 0);
+        bdrv_set_dirty_tracking(bmds->bs, enable);
     }
 }
 
@@ -360,13 +310,12 @@ static void init_blk_migration(QEMUFile *f)
     block_mig_state.total_sector_sum = 0;
     block_mig_state.prev_progress = -1;
     block_mig_state.bulk_completed = 0;
-    block_mig_state.zero_blocks = migrate_zero_blocks();
+    block_mig_state.total_time = 0;
+    block_mig_state.reads = 0;
 
     bdrv_iterate(init_blk_migration_it, NULL);
 }
 
-/* Called with no lock taken.  */
-
 static int blk_mig_save_bulked_block(QEMUFile *f)
 {
     int64_t completed_sector_sum = 0;
@@ -413,8 +362,6 @@ static void blk_mig_reset_dirty_cursor(void)
     }
 }
 
-/* Called with iothread lock taken.  */
-
 static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
                                  int is_async)
 {
@@ -425,12 +372,8 @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
     int ret = -EIO;
 
     for (sector = bmds->cur_dirty; sector < bmds->total_sectors;) {
-        blk_mig_lock();
         if (bmds_aio_inflight(bmds, sector)) {
-            blk_mig_unlock();
             bdrv_drain_all();
-        } else {
-            blk_mig_unlock();
         }
         if (bdrv_get_dirty(bmds->bs, sector)) {
 
@@ -450,13 +393,14 @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
                 blk->iov.iov_len = nr_sectors * BDRV_SECTOR_SIZE;
                 qemu_iovec_init_external(&blk->qiov, &blk->iov, 1);
 
+                if (block_mig_state.submitted == 0) {
+                    block_mig_state.prev_time_offset = qemu_get_clock_ns(rt_clock);
+                }
+
                 blk->aiocb = bdrv_aio_readv(bmds->bs, sector, &blk->qiov,
                                             nr_sectors, blk_mig_read_cb, blk);
-
-                blk_mig_lock();
                 block_mig_state.submitted++;
                 bmds_set_aio_inflight(bmds, sector, nr_sectors, 1);
-                blk_mig_unlock();
             } else {
                 ret = bdrv_read(bmds->bs, sector, blk->buf, nr_sectors);
                 if (ret < 0) {
@@ -479,25 +423,20 @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
 
 error:
     DPRINTF("Error reading sector %" PRId64 "\n", sector);
+    qemu_file_set_error(f, ret);
     g_free(blk->buf);
     g_free(blk);
-    return ret;
+    return 0;
 }
 
-/* Called with iothread lock taken.
- *
- * return value:
- * 0: too much data for max_downtime
- * 1: few enough data for max_downtime
-*/
 static int blk_mig_save_dirty_block(QEMUFile *f, int is_async)
 {
     BlkMigDevState *bmds;
-    int ret = 1;
+    int ret = 0;
 
     QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
-        ret = mig_save_device_dirty(f, bmds, is_async);
-        if (ret <= 0) {
+        if (mig_save_device_dirty(f, bmds, is_async) == 0) {
+            ret = 1;
             break;
         }
     }
@@ -505,32 +444,25 @@ static int blk_mig_save_dirty_block(QEMUFile *f, int is_async)
     return ret;
 }
 
-/* Called with no locks taken.  */
-
-static int flush_blks(QEMUFile *f)
+static void flush_blks(QEMUFile* f)
 {
     BlkMigBlock *blk;
-    int ret = 0;
 
     DPRINTF("%s Enter submitted %d read_done %d transferred %d\n",
             __FUNCTION__, block_mig_state.submitted, block_mig_state.read_done,
             block_mig_state.transferred);
 
-    blk_mig_lock();
     while ((blk = QSIMPLEQ_FIRST(&block_mig_state.blk_list)) != NULL) {
         if (qemu_file_rate_limit(f)) {
             break;
         }
         if (blk->ret < 0) {
-            ret = blk->ret;
+            qemu_file_set_error(f, blk->ret);
             break;
         }
+        blk_send(f, blk);
 
         QSIMPLEQ_REMOVE_HEAD(&block_mig_state.blk_list, entry);
-        blk_mig_unlock();
-        blk_send(f, blk);
-        blk_mig_lock();
-
         g_free(blk->buf);
         g_free(blk);
 
@@ -538,16 +470,12 @@ static int flush_blks(QEMUFile *f)
         block_mig_state.transferred++;
         assert(block_mig_state.read_done >= 0);
     }
-    blk_mig_unlock();
 
     DPRINTF("%s Exit submitted %d read_done %d transferred %d\n", __FUNCTION__,
             block_mig_state.submitted, block_mig_state.read_done,
             block_mig_state.transferred);
-    return ret;
 }
 
-/* Called with iothread lock taken.  */
-
 static int64_t get_remaining_dirty(void)
 {
     BlkMigDevState *bmds;
@@ -557,21 +485,42 @@ static int64_t get_remaining_dirty(void)
         dirty += bdrv_get_dirty_count(bmds->bs);
     }
 
-    return dirty << BDRV_SECTOR_BITS;
+    return dirty * BLOCK_SIZE;
 }
 
-/* Called with iothread lock taken.  */
+static int is_stage2_completed(void)
+{
+    int64_t remaining_dirty;
+    long double bwidth;
+
+    if (block_mig_state.bulk_completed == 1) {
+
+        remaining_dirty = get_remaining_dirty();
+        if (remaining_dirty == 0) {
+            return 1;
+        }
+
+        bwidth = compute_read_bwidth();
+
+        if ((remaining_dirty / bwidth) <=
+            migrate_max_downtime()) {
+            /* finish stage2 because we think that we can finish remaining work
+               below max_downtime */
+
+            return 1;
+        }
+    }
+
+    return 0;
+}
 
 static void blk_mig_cleanup(void)
 {
     BlkMigDevState *bmds;
     BlkMigBlock *blk;
 
-    bdrv_drain_all();
-
     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_set_in_use(bmds->bs, 0);
@@ -585,151 +534,93 @@ static void blk_mig_cleanup(void)
         g_free(blk->buf);
         g_free(blk);
     }
-    blk_mig_unlock();
 }
 
-static void block_migration_cancel(void *opaque)
-{
-    blk_mig_cleanup();
-}
-
-static int block_save_setup(QEMUFile *f, void *opaque)
+static int block_save_live(QEMUFile *f, int stage, void *opaque)
 {
     int ret;
 
-    DPRINTF("Enter save live setup submitted %d transferred %d\n",
-            block_mig_state.submitted, block_mig_state.transferred);
+    DPRINTF("Enter save live stage %d submitted %d transferred %d\n",
+            stage, block_mig_state.submitted, block_mig_state.transferred);
 
-    qemu_mutex_lock_iothread();
-    init_blk_migration(f);
+    if (stage < 0) {
+        blk_mig_cleanup();
+        return 0;
+    }
 
-    /* start track dirty blocks */
-    set_dirty_tracking(1);
-    qemu_mutex_unlock_iothread();
+    if (block_mig_state.blk_enable != 1) {
+        /* no need to migrate storage */
+        qemu_put_be64(f, BLK_MIG_FLAG_EOS);
+        return 1;
+    }
 
-    ret = flush_blks(f);
-    blk_mig_reset_dirty_cursor();
-    qemu_put_be64(f, BLK_MIG_FLAG_EOS);
+    if (stage == 1) {
+        init_blk_migration(f);
 
-    return ret;
-}
+        /* start track dirty blocks */
+        set_dirty_tracking(1);
+    }
 
-static int block_save_iterate(QEMUFile *f, void *opaque)
-{
-    int ret;
-    int64_t last_ftell = qemu_ftell(f);
+    flush_blks(f);
 
-    DPRINTF("Enter save live iterate submitted %d transferred %d\n",
-            block_mig_state.submitted, block_mig_state.transferred);
-
-    ret = flush_blks(f);
+    ret = qemu_file_get_error(f);
     if (ret) {
+        blk_mig_cleanup();
         return ret;
     }
 
     blk_mig_reset_dirty_cursor();
 
-    /* control the rate of transfer */
-    blk_mig_lock();
-    while ((block_mig_state.submitted +
-            block_mig_state.read_done) * BLOCK_SIZE <
-           qemu_file_get_rate_limit(f)) {
-        blk_mig_unlock();
-        if (block_mig_state.bulk_completed == 0) {
-            /* first finish the bulk phase */
-            if (blk_mig_save_bulked_block(f) == 0) {
-                /* finished saving bulk on all devices */
-                block_mig_state.bulk_completed = 1;
+    if (stage == 2) {
+        /* control the rate of transfer */
+        while ((block_mig_state.submitted +
+                block_mig_state.read_done) * BLOCK_SIZE <
+               qemu_file_get_rate_limit(f)) {
+            if (block_mig_state.bulk_completed == 0) {
+                /* first finish the bulk phase */
+                if (blk_mig_save_bulked_block(f) == 0) {
+                    /* finished saving bulk on all devices */
+                    block_mig_state.bulk_completed = 1;
+                }
+            } else {
+                if (blk_mig_save_dirty_block(f, 1) == 0) {
+                    /* no more dirty blocks */
+                    break;
+                }
             }
-            ret = 0;
-        } else {
-            /* Always called with iothread lock taken for
-             * simplicity, block_save_complete also calls it.
-             */
-            qemu_mutex_lock_iothread();
-            ret = blk_mig_save_dirty_block(f, 1);
-            qemu_mutex_unlock_iothread();
         }
-        if (ret < 0) {
+
+        flush_blks(f);
+
+        ret = qemu_file_get_error(f);
+        if (ret) {
+            blk_mig_cleanup();
             return ret;
         }
-        blk_mig_lock();
-        if (ret != 0) {
-            /* no more dirty blocks */
-            break;
-        }
     }
-    blk_mig_unlock();
 
-    ret = flush_blks(f);
-    if (ret) {
-        return ret;
+    if (stage == 3) {
+        /* we know for sure that save bulk is completed and
+           all async read completed */
+        assert(block_mig_state.submitted == 0);
+
+        while (blk_mig_save_dirty_block(f, 0) != 0);
+        blk_mig_cleanup();
+
+        /* report completion */
+        qemu_put_be64(f, (100 << BDRV_SECTOR_BITS) | BLK_MIG_FLAG_PROGRESS);
+
+        ret = qemu_file_get_error(f);
+        if (ret) {
+            return ret;
+        }
+
+        DPRINTF("Block migration completed\n");
     }
 
     qemu_put_be64(f, BLK_MIG_FLAG_EOS);
-    return qemu_ftell(f) - last_ftell;
-}
 
-/* Called with iothread lock taken.  */
-
-static int block_save_complete(QEMUFile *f, void *opaque)
-{
-    int ret;
-
-    DPRINTF("Enter save live complete submitted %d transferred %d\n",
-            block_mig_state.submitted, block_mig_state.transferred);
-
-    ret = flush_blks(f);
-    if (ret) {
-        return ret;
-    }
-
-    blk_mig_reset_dirty_cursor();
-
-    /* we know for sure that save bulk is completed and
-       all async read completed */
-    blk_mig_lock();
-    assert(block_mig_state.submitted == 0);
-    blk_mig_unlock();
-
-    do {
-        ret = blk_mig_save_dirty_block(f, 0);
-        if (ret < 0) {
-            return ret;
-        }
-    } while (ret == 0);
-
-    /* report completion */
-    qemu_put_be64(f, (100 << BDRV_SECTOR_BITS) | BLK_MIG_FLAG_PROGRESS);
-
-    DPRINTF("Block migration completed\n");
-
-    qemu_put_be64(f, BLK_MIG_FLAG_EOS);
-
-    blk_mig_cleanup();
-    return 0;
-}
-
-static uint64_t block_save_pending(QEMUFile *f, void *opaque, uint64_t max_size)
-{
-    /* Estimate pending number of bytes to send */
-    uint64_t pending;
-
-    qemu_mutex_lock_iothread();
-    blk_mig_lock();
-    pending = get_remaining_dirty() +
-                       block_mig_state.submitted * BLOCK_SIZE +
-                       block_mig_state.read_done * BLOCK_SIZE;
-
-    /* Report at least one block pending during bulk phase */
-    if (pending == 0 && !block_mig_state.bulk_completed) {
-        pending = BLOCK_SIZE;
-    }
-    blk_mig_unlock();
-    qemu_mutex_unlock_iothread();
-
-    DPRINTF("Enter save live pending  %" PRIu64 "\n", pending);
-    return pending;
+    return ((stage == 2) && is_stage2_completed());
 }
 
 static int block_load(QEMUFile *f, void *opaque, int version_id)
@@ -779,15 +670,12 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
                 nr_sectors = BDRV_SECTORS_PER_DIRTY_CHUNK;
             }
 
-            if (flags & BLK_MIG_FLAG_ZERO_BLOCK) {
-                ret = bdrv_write_zeroes(bs, addr, nr_sectors);
-            } else {
-                buf = g_malloc(BLOCK_SIZE);
-                qemu_get_buffer(f, buf, BLOCK_SIZE);
-                ret = bdrv_write(bs, addr, buf, nr_sectors);
-                g_free(buf);
-            }
+            buf = g_malloc(BLOCK_SIZE);
 
+            qemu_get_buffer(f, buf, BLOCK_SIZE);
+            ret = bdrv_write(bs, addr, buf, nr_sectors);
+
+            g_free(buf);
             if (ret < 0) {
                 return ret;
             }
@@ -800,7 +688,7 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
                    (addr == 100) ? '\n' : '\r');
             fflush(stdout);
         } else if (!(flags & BLK_MIG_FLAG_EOS)) {
-            fprintf(stderr, "Unknown block migration flags: %#x\n", flags);
+            fprintf(stderr, "Unknown flags\n");
             return -EINVAL;
         }
         ret = qemu_file_get_error(f);
@@ -812,37 +700,20 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
     return 0;
 }
 
-static void block_set_params(const MigrationParams *params, void *opaque)
+static void block_set_params(int blk_enable, int shared_base, void *opaque)
 {
-    block_mig_state.blk_enable = params->blk;
-    block_mig_state.shared_base = params->shared;
+    block_mig_state.blk_enable = blk_enable;
+    block_mig_state.shared_base = shared_base;
 
     /* shared base means that blk_enable = 1 */
-    block_mig_state.blk_enable |= params->shared;
+    block_mig_state.blk_enable |= shared_base;
 }
 
-static bool block_is_active(void *opaque)
-{
-    return block_mig_state.blk_enable == 1;
-}
-
-SaveVMHandlers savevm_block_handlers = {
-    .set_params = block_set_params,
-    .save_live_setup = block_save_setup,
-    .save_live_iterate = block_save_iterate,
-    .save_live_complete = block_save_complete,
-    .save_live_pending = block_save_pending,
-    .load_state = block_load,
-    .cancel = block_migration_cancel,
-    .is_active = block_is_active,
-};
-
 void blk_mig_init(void)
 {
     QSIMPLEQ_INIT(&block_mig_state.bmds_list);
     QSIMPLEQ_INIT(&block_mig_state.blk_list);
-    qemu_mutex_init(&block_mig_state.lock);
 
-    register_savevm_live(NULL, "block", 0, 1, &savevm_block_handlers,
-                         &block_mig_state);
+    register_savevm_live(NULL, "block", 0, 1, block_set_params,
+                         block_save_live, NULL, block_load, &block_mig_state);
 }

block.h

@@ -1,16 +1,14 @@
 #ifndef BLOCK_H
 #define BLOCK_H
 
-#include "block/aio.h"
+#include "qemu-aio.h"
 #include "qemu-common.h"
-#include "qemu/option.h"
-#include "block/coroutine.h"
-#include "qapi/qmp/qobject.h"
-#include "qapi-types.h"
+#include "qemu-option.h"
+#include "qemu-coroutine.h"
+#include "qobject.h"
 
 /* block.c */
 typedef struct BlockDriver BlockDriver;
-typedef struct BlockJob BlockJob;
 
 typedef struct BlockDriverInfo {
     /* in bytes, 0 if irrelevant */
@@ -24,9 +22,19 @@ typedef struct BlockFragInfo {
     uint64_t allocated_clusters;
     uint64_t total_clusters;
     uint64_t fragmented_clusters;
-    uint64_t compressed_clusters;
 } BlockFragInfo;
 
+typedef struct QEMUSnapshotInfo {
+    char id_str[128]; /* unique snapshot id */
+    /* the following fields are informative. They are not needed for
+       the consistency of the snapshot */
+    char name[256]; /* user chosen name */
+    uint64_t vm_state_size; /* VM state info size */
+    uint32_t date_sec; /* UTC date of the snapshot */
+    uint32_t date_nsec;
+    uint64_t vm_clock_nsec; /* VM clock relative to boot */
+} QEMUSnapshotInfo;
+
 /* Callbacks for block device models */
 typedef struct BlockDevOps {
     /*
@@ -71,9 +79,6 @@ typedef struct BlockDevOps {
 #define BDRV_O_NO_FLUSH    0x0200 /* disable flushing on this disk */
 #define BDRV_O_COPY_ON_READ 0x0400 /* copy read backing sectors into image */
 #define BDRV_O_INCOMING    0x0800  /* consistency hint for incoming migration */
-#define BDRV_O_CHECK       0x1000  /* open solely for consistency check */
-#define BDRV_O_ALLOW_RDWR  0x2000  /* allow reopen to change from r/o to r/w */
-#define BDRV_O_UNMAP       0x4000  /* execute guest UNMAP/TRIM operations */
 
 #define BDRV_O_CACHE_MASK  (BDRV_O_NOCACHE | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH)
 
@@ -82,23 +87,21 @@ typedef struct BlockDevOps {
 #define BDRV_SECTOR_MASK   ~(BDRV_SECTOR_SIZE - 1)
 
 typedef enum {
-    BDRV_ACTION_REPORT, BDRV_ACTION_IGNORE, BDRV_ACTION_STOP
+    BLOCK_ERR_REPORT, BLOCK_ERR_IGNORE, BLOCK_ERR_STOP_ENOSPC,
+    BLOCK_ERR_STOP_ANY
 } BlockErrorAction;
 
-typedef QSIMPLEQ_HEAD(BlockReopenQueue, BlockReopenQueueEntry) BlockReopenQueue;
-
-typedef struct BDRVReopenState {
-    BlockDriverState *bs;
-    int flags;
-    void *opaque;
-} BDRVReopenState;
-
+typedef enum {
+    BDRV_ACTION_REPORT, BDRV_ACTION_IGNORE, BDRV_ACTION_STOP
+} BlockQMPEventAction;
 
 void bdrv_iostatus_enable(BlockDriverState *bs);
 void bdrv_iostatus_reset(BlockDriverState *bs);
 void bdrv_iostatus_disable(BlockDriverState *bs);
 bool bdrv_iostatus_is_enabled(const BlockDriverState *bs);
 void bdrv_iostatus_set_err(BlockDriverState *bs, int error);
+void bdrv_emit_qmp_error_event(const BlockDriverState *bdrv,
+                               BlockQMPEventAction action, int is_read);
 void bdrv_info_print(Monitor *mon, const QObject *data);
 void bdrv_info(Monitor *mon, QObject **ret_data);
 void bdrv_stats_print(Monitor *mon, const QObject *data);
@@ -111,36 +114,21 @@ bool bdrv_io_limits_enabled(BlockDriverState *bs);
 
 void bdrv_init(void);
 void bdrv_init_with_whitelist(void);
-BlockDriver *bdrv_find_protocol(const char *filename,
-                                bool allow_protocol_prefix);
+BlockDriver *bdrv_find_protocol(const char *filename);
 BlockDriver *bdrv_find_format(const char *format_name);
-BlockDriver *bdrv_find_whitelisted_format(const char *format_name,
-                                          bool readonly);
+BlockDriver *bdrv_find_whitelisted_format(const char *format_name);
 int bdrv_create(BlockDriver *drv, const char* filename,
     QEMUOptionParameter *options);
 int bdrv_create_file(const char* filename, QEMUOptionParameter *options);
 BlockDriverState *bdrv_new(const char *device_name);
 void bdrv_make_anon(BlockDriverState *bs);
-void bdrv_swap(BlockDriverState *bs_new, BlockDriverState *bs_old);
 void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top);
 void bdrv_delete(BlockDriverState *bs);
 int bdrv_parse_cache_flags(const char *mode, int *flags);
-int bdrv_parse_discard_flags(const char *mode, int *flags);
-int bdrv_file_open(BlockDriverState **pbs, const char *filename,
-                   QDict *options, int flags);
-int bdrv_open_backing_file(BlockDriverState *bs, QDict *options);
-int bdrv_open(BlockDriverState *bs, const char *filename, QDict *options,
-              int flags, BlockDriver *drv);
-BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
-                                    BlockDriverState *bs, int flags);
-int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp);
-int bdrv_reopen(BlockDriverState *bs, int bdrv_flags, Error **errp);
-int bdrv_reopen_prepare(BDRVReopenState *reopen_state,
-                        BlockReopenQueue *queue, Error **errp);
-void bdrv_reopen_commit(BDRVReopenState *reopen_state);
-void bdrv_reopen_abort(BDRVReopenState *reopen_state);
+int bdrv_file_open(BlockDriverState **pbs, const char *filename, int flags);
+int bdrv_open(BlockDriverState *bs, const char *filename, int flags,
+              BlockDriver *drv);
 void bdrv_close(BlockDriverState *bs);
-void bdrv_add_close_notifier(BlockDriverState *bs, Notifier *notify);
 int bdrv_attach_dev(BlockDriverState *bs, void *dev);
 void bdrv_attach_dev_nofail(BlockDriverState *bs, void *dev);
 void bdrv_detach_dev(BlockDriverState *bs, void *dev);
@@ -153,18 +141,12 @@ bool bdrv_dev_is_tray_open(BlockDriverState *bs);
 bool bdrv_dev_is_medium_locked(BlockDriverState *bs);
 int bdrv_read(BlockDriverState *bs, int64_t sector_num,
               uint8_t *buf, int nb_sectors);
-int bdrv_read_unthrottled(BlockDriverState *bs, int64_t sector_num,
-                          uint8_t *buf, int nb_sectors);
 int bdrv_write(BlockDriverState *bs, int64_t sector_num,
                const uint8_t *buf, int nb_sectors);
-int bdrv_write_zeroes(BlockDriverState *bs, int64_t sector_num,
-               int nb_sectors);
-int bdrv_writev(BlockDriverState *bs, int64_t sector_num, QEMUIOVector *qiov);
 int bdrv_pread(BlockDriverState *bs, int64_t offset,
                void *buf, int count);
 int bdrv_pwrite(BlockDriverState *bs, int64_t offset,
                 const void *buf, int count);
-int bdrv_pwritev(BlockDriverState *bs, int64_t offset, QEMUIOVector *qiov);
 int bdrv_pwrite_sync(BlockDriverState *bs, int64_t offset,
     const void *buf, int count);
 int coroutine_fn bdrv_co_readv(BlockDriverState *bs, int64_t sector_num,
@@ -183,45 +165,28 @@ int coroutine_fn bdrv_co_write_zeroes(BlockDriverState *bs, int64_t sector_num,
     int nb_sectors);
 int coroutine_fn bdrv_co_is_allocated(BlockDriverState *bs, int64_t sector_num,
     int nb_sectors, int *pnum);
-int coroutine_fn bdrv_co_is_allocated_above(BlockDriverState *top,
-                                            BlockDriverState *base,
-                                            int64_t sector_num,
-                                            int nb_sectors, int *pnum);
 BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
     const char *backing_file);
-int bdrv_get_backing_file_depth(BlockDriverState *bs);
 int bdrv_truncate(BlockDriverState *bs, int64_t offset);
 int64_t bdrv_getlength(BlockDriverState *bs);
 int64_t bdrv_get_allocated_file_size(BlockDriverState *bs);
 void bdrv_get_geometry(BlockDriverState *bs, uint64_t *nb_sectors_ptr);
+void bdrv_guess_geometry(BlockDriverState *bs, int *pcyls, int *pheads, int *psecs);
 int bdrv_commit(BlockDriverState *bs);
 int bdrv_commit_all(void);
 int bdrv_change_backing_file(BlockDriverState *bs,
     const char *backing_file, const char *backing_fmt);
 void bdrv_register(BlockDriver *bdrv);
-int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top,
-                           BlockDriverState *base);
-BlockDriverState *bdrv_find_overlay(BlockDriverState *active,
-                                    BlockDriverState *bs);
-BlockDriverState *bdrv_find_base(BlockDriverState *bs);
 
 
 typedef struct BdrvCheckResult {
     int corruptions;
     int leaks;
     int check_errors;
-    int corruptions_fixed;
-    int leaks_fixed;
-    int64_t image_end_offset;
     BlockFragInfo bfi;
 } BdrvCheckResult;
 
-typedef enum {
-    BDRV_FIX_LEAKS    = 1,
-    BDRV_FIX_ERRORS   = 2,
-} BdrvCheckMode;
-
-int bdrv_check(BlockDriverState *bs, BdrvCheckResult *res, BdrvCheckMode fix);
+int bdrv_check(BlockDriverState *bs, BdrvCheckResult *res);
 
 /* async block I/O */
 typedef void BlockDriverDirtyHandler(BlockDriverState *bs, int64_t sector,
@@ -269,34 +234,57 @@ void bdrv_clear_incoming_migration_all(void);
 /* Ensure contents are flushed to disk.  */
 int bdrv_flush(BlockDriverState *bs);
 int coroutine_fn bdrv_co_flush(BlockDriverState *bs);
-int bdrv_flush_all(void);
+void bdrv_flush_all(void);
 void bdrv_close_all(void);
 void bdrv_drain_all(void);
 
 int bdrv_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors);
 int bdrv_co_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors);
-int bdrv_has_zero_init_1(BlockDriverState *bs);
 int bdrv_has_zero_init(BlockDriverState *bs);
 int bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
                       int *pnum);
-int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base,
-                            int64_t sector_num, int nb_sectors, int *pnum);
 
-void bdrv_set_on_error(BlockDriverState *bs, BlockdevOnError on_read_error,
-                       BlockdevOnError on_write_error);
-BlockdevOnError bdrv_get_on_error(BlockDriverState *bs, bool is_read);
-BlockErrorAction bdrv_get_error_action(BlockDriverState *bs, bool is_read, int error);
-void bdrv_error_action(BlockDriverState *bs, BlockErrorAction action,
-                       bool is_read, int error);
+#define BIOS_ATA_TRANSLATION_AUTO   0
+#define BIOS_ATA_TRANSLATION_NONE   1
+#define BIOS_ATA_TRANSLATION_LBA    2
+#define BIOS_ATA_TRANSLATION_LARGE  3
+#define BIOS_ATA_TRANSLATION_RECHS  4
+
+void bdrv_set_geometry_hint(BlockDriverState *bs,
+                            int cyls, int heads, int secs);
+void bdrv_set_translation_hint(BlockDriverState *bs, int translation);
+void bdrv_get_geometry_hint(BlockDriverState *bs,
+                            int *pcyls, int *pheads, int *psecs);
+typedef enum FDriveType {
+    FDRIVE_DRV_144  = 0x00,   /* 1.44 MB 3"5 drive      */
+    FDRIVE_DRV_288  = 0x01,   /* 2.88 MB 3"5 drive      */
+    FDRIVE_DRV_120  = 0x02,   /* 1.2  MB 5"25 drive     */
+    FDRIVE_DRV_NONE = 0x03,   /* No drive connected     */
+} FDriveType;
+
+typedef enum FDriveRate {
+    FDRIVE_RATE_500K = 0x00,  /* 500 Kbps */
+    FDRIVE_RATE_300K = 0x01,  /* 300 Kbps */
+    FDRIVE_RATE_250K = 0x02,  /* 250 Kbps */
+    FDRIVE_RATE_1M   = 0x03,  /*   1 Mbps */
+} FDriveRate;
+
+void bdrv_get_floppy_geometry_hint(BlockDriverState *bs, int *nb_heads,
+                                   int *max_track, int *last_sect,
+                                   FDriveType drive_in, FDriveType *drive,
+                                   FDriveRate *rate);
+int bdrv_get_translation_hint(BlockDriverState *bs);
+void bdrv_set_on_error(BlockDriverState *bs, BlockErrorAction on_read_error,
+                       BlockErrorAction on_write_error);
+BlockErrorAction bdrv_get_on_error(BlockDriverState *bs, int is_read);
 int bdrv_is_read_only(BlockDriverState *bs);
 int bdrv_is_sg(BlockDriverState *bs);
 int bdrv_enable_write_cache(BlockDriverState *bs);
-void bdrv_set_enable_write_cache(BlockDriverState *bs, bool wce);
 int bdrv_is_inserted(BlockDriverState *bs);
 int bdrv_media_changed(BlockDriverState *bs);
 void bdrv_lock_medium(BlockDriverState *bs, bool locked);
 void bdrv_eject(BlockDriverState *bs, bool eject_flag);
-const char *bdrv_get_format_name(BlockDriverState *bs);
+void bdrv_get_format(BlockDriverState *bs, char *buf, int buf_size);
 BlockDriverState *bdrv_find(const char *name);
 BlockDriverState *bdrv_next(BlockDriverState *bs);
 void bdrv_iterate(void (*it)(void *opaque, BlockDriverState *bs),
@@ -308,49 +296,54 @@ int bdrv_query_missing_keys(void);
 void bdrv_iterate_format(void (*it)(void *opaque, const char *name),
                          void *opaque);
 const char *bdrv_get_device_name(BlockDriverState *bs);
-int bdrv_get_flags(BlockDriverState *bs);
 int bdrv_write_compressed(BlockDriverState *bs, int64_t sector_num,
                           const uint8_t *buf, int nb_sectors);
 int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi);
-void bdrv_round_to_clusters(BlockDriverState *bs,
-                            int64_t sector_num, int nb_sectors,
-                            int64_t *cluster_sector_num,
-                            int *cluster_nb_sectors);
 
 const char *bdrv_get_encrypted_filename(BlockDriverState *bs);
 void bdrv_get_backing_filename(BlockDriverState *bs,
                                char *filename, int filename_size);
 void bdrv_get_full_backing_filename(BlockDriverState *bs,
                                     char *dest, size_t sz);
+int bdrv_can_snapshot(BlockDriverState *bs);
 int bdrv_is_snapshot(BlockDriverState *bs);
+BlockDriverState *bdrv_snapshots(void);
+int bdrv_snapshot_create(BlockDriverState *bs,
+                         QEMUSnapshotInfo *sn_info);
+int bdrv_snapshot_goto(BlockDriverState *bs,
+                       const char *snapshot_id);
+int bdrv_snapshot_delete(BlockDriverState *bs, const char *snapshot_id);
+int bdrv_snapshot_list(BlockDriverState *bs,
+                       QEMUSnapshotInfo **psn_info);
+int bdrv_snapshot_load_tmp(BlockDriverState *bs,
+                           const char *snapshot_name);
+char *bdrv_snapshot_dump(char *buf, int buf_size, QEMUSnapshotInfo *sn);
 
+char *get_human_readable_size(char *buf, int buf_size, int64_t size);
 int path_is_absolute(const char *path);
 void path_combine(char *dest, int dest_size,
                   const char *base_path,
                   const char *filename);
 
-int bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos);
 int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
                       int64_t pos, int size);
 
 int bdrv_load_vmstate(BlockDriverState *bs, uint8_t *buf,
                       int64_t pos, int size);
 
-void bdrv_img_create(const char *filename, const char *fmt,
-                     const char *base_filename, const char *base_fmt,
-                     char *options, uint64_t img_size, int flags,
-                     Error **errp, bool quiet);
+int bdrv_img_create(const char *filename, const char *fmt,
+                    const char *base_filename, const char *base_fmt,
+                    char *options, uint64_t img_size, int flags);
 
 void bdrv_set_buffer_alignment(BlockDriverState *bs, int align);
 void *qemu_blockalign(BlockDriverState *bs, size_t size);
-bool bdrv_qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov);
 
-struct HBitmapIter;
-void bdrv_set_dirty_tracking(BlockDriverState *bs, int granularity);
+#define BDRV_SECTORS_PER_DIRTY_CHUNK 2048
+
+void bdrv_set_dirty_tracking(BlockDriverState *bs, int enable);
 int bdrv_get_dirty(BlockDriverState *bs, int64_t sector);
-void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector, int nr_sectors);
-void bdrv_reset_dirty(BlockDriverState *bs, int64_t cur_sector, int nr_sectors);
-void bdrv_dirty_iter_init(BlockDriverState *bs, struct HBitmapIter *hbi);
+void bdrv_reset_dirty(BlockDriverState *bs, int64_t cur_sector,
+                      int nr_sectors);
 int64_t bdrv_get_dirty_count(BlockDriverState *bs);
 
 void bdrv_enable_copy_on_read(BlockDriverState *bs);
@@ -359,15 +352,6 @@ void bdrv_disable_copy_on_read(BlockDriverState *bs);
 void bdrv_set_in_use(BlockDriverState *bs, int in_use);
 int bdrv_in_use(BlockDriverState *bs);
 
-#ifdef CONFIG_LINUX_AIO
-int raw_get_aio_fd(BlockDriverState *bs);
-#else
-static inline int raw_get_aio_fd(BlockDriverState *bs)
-{
-    return -ENOTSUP;
-}
-#endif
-
 enum BlockAcctType {
     BDRV_ACCT_READ,
     BDRV_ACCT_WRITE,
@@ -398,7 +382,9 @@ typedef enum {
     BLKDBG_L2_ALLOC_COW_READ,
     BLKDBG_L2_ALLOC_WRITE,
 
+    BLKDBG_READ,
     BLKDBG_READ_AIO,
+    BLKDBG_READ_BACKING,
     BLKDBG_READ_BACKING_AIO,
     BLKDBG_READ_COMPRESSED,
 
@@ -428,18 +414,49 @@ typedef enum {
     BLKDBG_CLUSTER_ALLOC_BYTES,
     BLKDBG_CLUSTER_FREE,
 
-    BLKDBG_FLUSH_TO_OS,
-    BLKDBG_FLUSH_TO_DISK,
-
     BLKDBG_EVENT_MAX,
 } BlkDebugEvent;
 
 #define BLKDBG_EVENT(bs, evt) bdrv_debug_event(bs, evt)
 void bdrv_debug_event(BlockDriverState *bs, BlkDebugEvent event);
 
-int bdrv_debug_breakpoint(BlockDriverState *bs, const char *event,
-                           const char *tag);
-int bdrv_debug_resume(BlockDriverState *bs, const char *tag);
-bool bdrv_debug_is_suspended(BlockDriverState *bs, const char *tag);
+
+/* Convenience for block device models */
+
+typedef struct BlockConf {
+    BlockDriverState *bs;
+    uint16_t physical_block_size;
+    uint16_t logical_block_size;
+    uint16_t min_io_size;
+    uint32_t opt_io_size;
+    int32_t bootindex;
+    uint32_t discard_granularity;
+} BlockConf;
+
+static inline unsigned int get_physical_block_exp(BlockConf *conf)
+{
+    unsigned int exp = 0, size;
+
+    for (size = conf->physical_block_size;
+        size > conf->logical_block_size;
+        size >>= 1) {
+        exp++;
+    }
+
+    return exp;
+}
+
+#define DEFINE_BLOCK_PROPERTIES(_state, _conf)                          \
+    DEFINE_PROP_DRIVE("drive", _state, _conf.bs),                       \
+    DEFINE_PROP_BLOCKSIZE("logical_block_size", _state,                 \
+                          _conf.logical_block_size, 512),               \
+    DEFINE_PROP_BLOCKSIZE("physical_block_size", _state,                \
+                          _conf.physical_block_size, 512),              \
+    DEFINE_PROP_UINT16("min_io_size", _state, _conf.min_io_size, 0),  \
+    DEFINE_PROP_UINT32("opt_io_size", _state, _conf.opt_io_size, 0),    \
+    DEFINE_PROP_INT32("bootindex", _state, _conf.bootindex, -1),        \
+    DEFINE_PROP_UINT32("discard_granularity", _state, \
+                       _conf.discard_granularity, 0)
 
 #endif
+

block/Makefile.objs

@@ -1,26 +0,0 @@
-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-y += vhdx.o
-block-obj-y += parallels.o blkdebug.o blkverify.o
-block-obj-y += snapshot.o qapi.o
-block-obj-$(CONFIG_WIN32) += raw-win32.o win32-aio.o
-block-obj-$(CONFIG_POSIX) += raw-posix.o
-block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
-
-ifeq ($(CONFIG_POSIX),y)
-block-obj-y += nbd.o sheepdog.o
-block-obj-$(CONFIG_LIBISCSI) += iscsi.o
-block-obj-$(CONFIG_CURL) += curl.o
-block-obj-$(CONFIG_RBD) += rbd.o
-block-obj-$(CONFIG_GLUSTERFS) += gluster.o
-block-obj-$(CONFIG_LIBSSH2) += ssh.o
-endif
-
-common-obj-y += stream.o
-common-obj-y += commit.o
-common-obj-y += mirror.o
-common-obj-y += backup.o
-
-$(obj)/curl.o: QEMU_CFLAGS+=$(CURL_CFLAGS)

block/backup.c

@@ -1,386 +0,0 @@
-/*
- * QEMU backup
- *
- * Copyright (C) 2013 Proxmox Server Solutions
- *
- * Authors:
- *  Dietmar Maurer (dietmar@proxmox.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 <stdio.h>
-#include <errno.h>
-#include <unistd.h>
-
-#include "trace.h"
-#include "block/block.h"
-#include "block/block_int.h"
-#include "block/blockjob.h"
-#include "qemu/ratelimit.h"
-
-#define BACKUP_CLUSTER_BITS 16
-#define BACKUP_CLUSTER_SIZE (1 << BACKUP_CLUSTER_BITS)
-#define BACKUP_SECTORS_PER_CLUSTER (BACKUP_CLUSTER_SIZE / BDRV_SECTOR_SIZE)
-
-#define SLICE_TIME 100000000ULL /* ns */
-
-typedef struct CowRequest {
-    int64_t start;
-    int64_t end;
-    QLIST_ENTRY(CowRequest) list;
-    CoQueue wait_queue; /* coroutines blocked on this request */
-} CowRequest;
-
-typedef struct BackupBlockJob {
-    BlockJob common;
-    BlockDriverState *target;
-    MirrorSyncMode sync_mode;
-    RateLimit limit;
-    BlockdevOnError on_source_error;
-    BlockdevOnError on_target_error;
-    CoRwlock flush_rwlock;
-    uint64_t sectors_read;
-    HBitmap *bitmap;
-    QLIST_HEAD(, CowRequest) inflight_reqs;
-} BackupBlockJob;
-
-/* See if in-flight requests overlap and wait for them to complete */
-static void coroutine_fn wait_for_overlapping_requests(BackupBlockJob *job,
-                                                       int64_t start,
-                                                       int64_t end)
-{
-    CowRequest *req;
-    bool retry;
-
-    do {
-        retry = false;
-        QLIST_FOREACH(req, &job->inflight_reqs, list) {
-            if (end > req->start && start < req->end) {
-                qemu_co_queue_wait(&req->wait_queue);
-                retry = true;
-                break;
-            }
-        }
-    } while (retry);
-}
-
-/* Keep track of an in-flight request */
-static void cow_request_begin(CowRequest *req, BackupBlockJob *job,
-                                     int64_t start, int64_t end)
-{
-    req->start = start;
-    req->end = end;
-    qemu_co_queue_init(&req->wait_queue);
-    QLIST_INSERT_HEAD(&job->inflight_reqs, req, list);
-}
-
-/* Forget about a completed request */
-static void cow_request_end(CowRequest *req)
-{
-    QLIST_REMOVE(req, list);
-    qemu_co_queue_restart_all(&req->wait_queue);
-}
-
-static int coroutine_fn backup_do_cow(BlockDriverState *bs,
-                                      int64_t sector_num, int nb_sectors,
-                                      bool *error_is_read)
-{
-    BackupBlockJob *job = (BackupBlockJob *)bs->job;
-    CowRequest cow_request;
-    struct iovec iov;
-    QEMUIOVector bounce_qiov;
-    void *bounce_buffer = NULL;
-    int ret = 0;
-    int64_t start, end;
-    int n;
-
-    qemu_co_rwlock_rdlock(&job->flush_rwlock);
-
-    start = sector_num / BACKUP_SECTORS_PER_CLUSTER;
-    end = DIV_ROUND_UP(sector_num + nb_sectors, BACKUP_SECTORS_PER_CLUSTER);
-
-    trace_backup_do_cow_enter(job, start, sector_num, nb_sectors);
-
-    wait_for_overlapping_requests(job, start, end);
-    cow_request_begin(&cow_request, job, start, end);
-
-    for (; start < end; start++) {
-        if (hbitmap_get(job->bitmap, start)) {
-            trace_backup_do_cow_skip(job, start);
-            continue; /* already copied */
-        }
-
-        trace_backup_do_cow_process(job, start);
-
-        n = MIN(BACKUP_SECTORS_PER_CLUSTER,
-                job->common.len / BDRV_SECTOR_SIZE -
-                start * BACKUP_SECTORS_PER_CLUSTER);
-
-        if (!bounce_buffer) {
-            bounce_buffer = qemu_blockalign(bs, BACKUP_CLUSTER_SIZE);
-        }
-        iov.iov_base = bounce_buffer;
-        iov.iov_len = n * BDRV_SECTOR_SIZE;
-        qemu_iovec_init_external(&bounce_qiov, &iov, 1);
-
-        ret = bdrv_co_readv(bs, start * BACKUP_SECTORS_PER_CLUSTER, n,
-                            &bounce_qiov);
-        if (ret < 0) {
-            trace_backup_do_cow_read_fail(job, start, ret);
-            if (error_is_read) {
-                *error_is_read = true;
-            }
-            goto out;
-        }
-
-        if (buffer_is_zero(iov.iov_base, iov.iov_len)) {
-            ret = bdrv_co_write_zeroes(job->target,
-                                       start * BACKUP_SECTORS_PER_CLUSTER, n);
-        } else {
-            ret = bdrv_co_writev(job->target,
-                                 start * BACKUP_SECTORS_PER_CLUSTER, n,
-                                 &bounce_qiov);
-        }
-        if (ret < 0) {
-            trace_backup_do_cow_write_fail(job, start, ret);
-            if (error_is_read) {
-                *error_is_read = false;
-            }
-            goto out;
-        }
-
-        hbitmap_set(job->bitmap, start, 1);
-
-        /* Publish progress, guest I/O counts as progress too.  Note that the
-         * offset field is an opaque progress value, it is not a disk offset.
-         */
-        job->sectors_read += n;
-        job->common.offset += n * BDRV_SECTOR_SIZE;
-    }
-
-out:
-    if (bounce_buffer) {
-        qemu_vfree(bounce_buffer);
-    }
-
-    cow_request_end(&cow_request);
-
-    trace_backup_do_cow_return(job, sector_num, nb_sectors, ret);
-
-    qemu_co_rwlock_unlock(&job->flush_rwlock);
-
-    return ret;
-}
-
-static int coroutine_fn backup_before_write_notify(
-        NotifierWithReturn *notifier,
-        void *opaque)
-{
-    BdrvTrackedRequest *req = opaque;
-
-    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)
-{
-    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
-
-    if (speed < 0) {
-        error_set(errp, QERR_INVALID_PARAMETER, "speed");
-        return;
-    }
-    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
-}
-
-static void backup_iostatus_reset(BlockJob *job)
-{
-    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
-
-    bdrv_iostatus_reset(s->target);
-}
-
-static const BlockJobType backup_job_type = {
-    .instance_size  = sizeof(BackupBlockJob),
-    .job_type       = "backup",
-    .set_speed      = backup_set_speed,
-    .iostatus_reset = backup_iostatus_reset,
-};
-
-static BlockErrorAction backup_error_action(BackupBlockJob *job,
-                                            bool read, int error)
-{
-    if (read) {
-        return block_job_error_action(&job->common, job->common.bs,
-                                      job->on_source_error, true, error);
-    } else {
-        return block_job_error_action(&job->common, job->target,
-                                      job->on_target_error, false, error);
-    }
-}
-
-static void coroutine_fn backup_run(void *opaque)
-{
-    BackupBlockJob *job = opaque;
-    BlockDriverState *bs = job->common.bs;
-    BlockDriverState *target = job->target;
-    BlockdevOnError on_target_error = job->on_target_error;
-    NotifierWithReturn before_write = {
-        .notify = backup_before_write_notify,
-    };
-    int64_t start, end;
-    int ret = 0;
-
-    QLIST_INIT(&job->inflight_reqs);
-    qemu_co_rwlock_init(&job->flush_rwlock);
-
-    start = 0;
-    end = DIV_ROUND_UP(job->common.len / BDRV_SECTOR_SIZE,
-                       BACKUP_SECTORS_PER_CLUSTER);
-
-    job->bitmap = hbitmap_alloc(end, 0);
-
-    bdrv_set_enable_write_cache(target, true);
-    bdrv_set_on_error(target, on_target_error, on_target_error);
-    bdrv_iostatus_enable(target);
-
-    bdrv_add_before_write_notifier(bs, &before_write);
-
-    if (job->sync_mode == MIRROR_SYNC_MODE_NONE) {
-        while (!block_job_is_cancelled(&job->common)) {
-            /* Yield until the job is cancelled.  We just let our before_write
-             * notify callback service CoW requests. */
-            job->common.busy = false;
-            qemu_coroutine_yield();
-            job->common.busy = true;
-        }
-    } else {
-        /* Both FULL and TOP SYNC_MODE's require copying.. */
-        for (; start < end; start++) {
-            bool error_is_read;
-
-            if (block_job_is_cancelled(&job->common)) {
-                break;
-            }
-
-            /* we need to yield so that qemu_aio_flush() returns.
-             * (without, VM does not reboot)
-             */
-            if (job->common.speed) {
-                uint64_t delay_ns = ratelimit_calculate_delay(
-                        &job->limit, job->sectors_read);
-                job->sectors_read = 0;
-                block_job_sleep_ns(&job->common, rt_clock, delay_ns);
-            } else {
-                block_job_sleep_ns(&job->common, rt_clock, 0);
-            }
-
-            if (block_job_is_cancelled(&job->common)) {
-                break;
-            }
-
-            if (job->sync_mode == MIRROR_SYNC_MODE_TOP) {
-                int i, n;
-                int alloced = 0;
-
-                /* Check to see if these blocks are already in the
-                 * backing file. */
-
-                for (i = 0; i < BACKUP_SECTORS_PER_CLUSTER;) {
-                    /* 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_co_is_allocated(bs,
-                                start * BACKUP_SECTORS_PER_CLUSTER + i,
-                                BACKUP_SECTORS_PER_CLUSTER - i, &n);
-                    i += n;
-
-                    if (alloced == 1) {
-                        break;
-                    }
-                }
-
-                /* If the above loop never found any sectors that are in
-                 * the topmost image, skip this backup. */
-                if (alloced == 0) {
-                    continue;
-                }
-            }
-            /* FULL sync mode we copy the whole drive. */
-            ret = backup_do_cow(bs, start * BACKUP_SECTORS_PER_CLUSTER,
-                    BACKUP_SECTORS_PER_CLUSTER, &error_is_read);
-            if (ret < 0) {
-                /* Depending on error action, fail now or retry cluster */
-                BlockErrorAction action =
-                    backup_error_action(job, error_is_read, -ret);
-                if (action == BDRV_ACTION_REPORT) {
-                    break;
-                } else {
-                    start--;
-                    continue;
-                }
-            }
-        }
-    }
-
-    notifier_with_return_remove(&before_write);
-
-    /* wait until pending backup_do_cow() calls have completed */
-    qemu_co_rwlock_wrlock(&job->flush_rwlock);
-    qemu_co_rwlock_unlock(&job->flush_rwlock);
-
-    hbitmap_free(job->bitmap);
-
-    bdrv_iostatus_disable(target);
-    bdrv_delete(target);
-
-    block_job_completed(&job->common, ret);
-}
-
-void backup_start(BlockDriverState *bs, BlockDriverState *target,
-                  int64_t speed, MirrorSyncMode sync_mode,
-                  BlockdevOnError on_source_error,
-                  BlockdevOnError on_target_error,
-                  BlockDriverCompletionFunc *cb, void *opaque,
-                  Error **errp)
-{
-    int64_t len;
-
-    assert(bs);
-    assert(target);
-    assert(cb);
-
-    if ((on_source_error == BLOCKDEV_ON_ERROR_STOP ||
-         on_source_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        !bdrv_iostatus_is_enabled(bs)) {
-        error_set(errp, QERR_INVALID_PARAMETER, "on-source-error");
-        return;
-    }
-
-    len = bdrv_getlength(bs);
-    if (len < 0) {
-        error_setg_errno(errp, -len, "unable to get length for '%s'",
-                         bdrv_get_device_name(bs));
-        return;
-    }
-
-    BackupBlockJob *job = block_job_create(&backup_job_type, bs, speed,
-                                           cb, opaque, errp);
-    if (!job) {
-        return;
-    }
-
-    job->on_source_error = on_source_error;
-    job->on_target_error = on_target_error;
-    job->target = target;
-    job->sync_mode = sync_mode;
-    job->common.len = len;
-    job->common.co = qemu_coroutine_create(backup_run);
-    qemu_coroutine_enter(job->common.co, job);
-}

block/blkdebug.c

@@ -23,17 +23,27 @@
  */
 
 #include "qemu-common.h"
-#include "qemu/config-file.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
+
+typedef struct BlkdebugVars {
+    int state;
+
+    /* If inject_errno != 0, an error is injected for requests */
+    int inject_errno;
+
+    /* Decides if all future requests fail (false) or only the next one and
+     * after the next request inject_errno is reset to 0 (true) */
+    bool inject_once;
+
+    /* Decides if aio_readv/writev fails right away (true) or returns an error
+     * return value only in the callback (false) */
+    bool inject_immediately;
+} BlkdebugVars;
 
 typedef struct BDRVBlkdebugState {
-    int state;
-    int new_state;
-
-    QLIST_HEAD(, BlkdebugRule) rules[BLKDBG_EVENT_MAX];
-    QSIMPLEQ_HEAD(, BlkdebugRule) active_rules;
-    QLIST_HEAD(, BlkdebugSuspendedReq) suspended_reqs;
+    BlkdebugVars vars;
+    QLIST_HEAD(list, BlkdebugRule) rules[BLKDBG_EVENT_MAX];
 } BDRVBlkdebugState;
 
 typedef struct BlkdebugAIOCB {
@@ -42,15 +52,9 @@ typedef struct BlkdebugAIOCB {
     int ret;
 } BlkdebugAIOCB;
 
-typedef struct BlkdebugSuspendedReq {
-    Coroutine *co;
-    char *tag;
-    QLIST_ENTRY(BlkdebugSuspendedReq) next;
-} BlkdebugSuspendedReq;
-
 static void blkdebug_aio_cancel(BlockDriverAIOCB *blockacb);
 
-static const AIOCBInfo blkdebug_aiocb_info = {
+static AIOPool blkdebug_aio_pool = {
     .aiocb_size = sizeof(BlkdebugAIOCB),
     .cancel     = blkdebug_aio_cancel,
 };
@@ -58,7 +62,6 @@ static const AIOCBInfo blkdebug_aiocb_info = {
 enum {
     ACTION_INJECT_ERROR,
     ACTION_SET_STATE,
-    ACTION_SUSPEND,
 };
 
 typedef struct BlkdebugRule {
@@ -70,17 +73,12 @@ typedef struct BlkdebugRule {
             int error;
             int immediately;
             int once;
-            int64_t sector;
         } inject;
         struct {
             int new_state;
         } set_state;
-        struct {
-            char *tag;
-        } suspend;
     } options;
     QLIST_ENTRY(BlkdebugRule) next;
-    QSIMPLEQ_ENTRY(BlkdebugRule) active_next;
 } BlkdebugRule;
 
 static QemuOptsList inject_error_opts = {
@@ -99,10 +97,6 @@ static QemuOptsList inject_error_opts = {
             .name = "errno",
             .type = QEMU_OPT_NUMBER,
         },
-        {
-            .name = "sector",
-            .type = QEMU_OPT_NUMBER,
-        },
         {
             .name = "once",
             .type = QEMU_OPT_BOOL,
@@ -153,7 +147,9 @@ static const char *event_names[BLKDBG_EVENT_MAX] = {
     [BLKDBG_L2_ALLOC_COW_READ]              = "l2_alloc.cow_read",
     [BLKDBG_L2_ALLOC_WRITE]                 = "l2_alloc.write",
 
+    [BLKDBG_READ]                           = "read",
     [BLKDBG_READ_AIO]                       = "read_aio",
+    [BLKDBG_READ_BACKING]                   = "read_backing",
     [BLKDBG_READ_BACKING_AIO]               = "read_backing_aio",
     [BLKDBG_READ_COMPRESSED]                = "read_compressed",
 
@@ -182,9 +178,6 @@ static const char *event_names[BLKDBG_EVENT_MAX] = {
     [BLKDBG_CLUSTER_ALLOC]                  = "cluster_alloc",
     [BLKDBG_CLUSTER_ALLOC_BYTES]            = "cluster_alloc_bytes",
     [BLKDBG_CLUSTER_FREE]                   = "cluster_free",
-
-    [BLKDBG_FLUSH_TO_OS]                    = "flush_to_os",
-    [BLKDBG_FLUSH_TO_DISK]                  = "flush_to_disk",
 };
 
 static int get_event_by_name(const char *name, BlkDebugEvent *event)
@@ -235,18 +228,12 @@ static int add_rule(QemuOpts *opts, void *opaque)
         rule->options.inject.once  = qemu_opt_get_bool(opts, "once", 0);
         rule->options.inject.immediately =
             qemu_opt_get_bool(opts, "immediately", 0);
-        rule->options.inject.sector = qemu_opt_get_number(opts, "sector", -1);
         break;
 
     case ACTION_SET_STATE:
         rule->options.set_state.new_state =
             qemu_opt_get_number(opts, "new_state", 0);
         break;
-
-    case ACTION_SUSPEND:
-        rule->options.suspend.tag =
-            g_strdup(qemu_opt_get(opts, "tag"));
-        break;
     };
 
     /* Add the rule */
@@ -255,21 +242,6 @@ static int add_rule(QemuOpts *opts, void *opaque)
     return 0;
 }
 
-static void remove_rule(BlkdebugRule *rule)
-{
-    switch (rule->action) {
-    case ACTION_INJECT_ERROR:
-    case ACTION_SET_STATE:
-        break;
-    case ACTION_SUSPEND:
-        g_free(rule->options.suspend.tag);
-        break;
-    }
-
-    QLIST_REMOVE(rule, next);
-    g_free(rule);
-}
-
 static int read_config(BDRVBlkdebugState *s, const char *filename)
 {
     FILE *f;
@@ -302,98 +274,43 @@ fail:
 }
 
 /* Valid blkdebug filenames look like blkdebug:path/to/config:path/to/image */
-static void blkdebug_parse_filename(const char *filename, QDict *options,
-                                    Error **errp)
-{
-    const char *c;
-
-    /* Parse the blkdebug: prefix */
-    if (!strstart(filename, "blkdebug:", &filename)) {
-        error_setg(errp, "File name string must start with 'blkdebug:'");
-        return;
-    }
-
-    /* Parse config file path */
-    c = strchr(filename, ':');
-    if (c == NULL) {
-        error_setg(errp, "blkdebug requires both config file and image path");
-        return;
-    }
-
-    if (c != filename) {
-        QString *config_path;
-        config_path = qstring_from_substr(filename, 0, c - filename - 1);
-        qdict_put(options, "config", config_path);
-    }
-
-    /* TODO Allow multi-level nesting and set file.filename here */
-    filename = c + 1;
-    qdict_put(options, "x-image", qstring_from_str(filename));
-}
-
-static QemuOptsList runtime_opts = {
-    .name = "blkdebug",
-    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
-    .desc = {
-        {
-            .name = "config",
-            .type = QEMU_OPT_STRING,
-            .help = "Path to the configuration file",
-        },
-        {
-            .name = "x-image",
-            .type = QEMU_OPT_STRING,
-            .help = "[internal use only, will be removed]",
-        },
-        { /* end of list */ }
-    },
-};
-
-static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags)
+static int blkdebug_open(BlockDriverState *bs, const char *filename, int flags)
 {
     BDRVBlkdebugState *s = bs->opaque;
-    QemuOpts *opts;
-    Error *local_err = NULL;
-    const char *filename, *config;
     int ret;
+    char *config, *c;
 
-    opts = qemu_opts_create_nofail(&runtime_opts);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (error_is_set(&local_err)) {
-        qerror_report_err(local_err);
-        error_free(local_err);
-        ret = -EINVAL;
-        goto fail;
+    /* Parse the blkdebug: prefix */
+    if (strncmp(filename, "blkdebug:", strlen("blkdebug:"))) {
+        return -EINVAL;
     }
+    filename += strlen("blkdebug:");
 
     /* Read rules from config file */
-    config = qemu_opt_get(opts, "config");
-    if (config) {
-        ret = read_config(s, config);
-        if (ret < 0) {
-            goto fail;
-        }
+    c = strchr(filename, ':');
+    if (c == NULL) {
+        return -EINVAL;
     }
 
+    config = g_strdup(filename);
+    config[c - filename] = '\0';
+    ret = read_config(s, config);
+    g_free(config);
+    if (ret < 0) {
+        return ret;
+    }
+    filename = c + 1;
+
     /* Set initial state */
-    s->state = 1;
+    s->vars.state = 1;
 
     /* Open the backing file */
-    filename = qemu_opt_get(opts, "x-image");
-    if (filename == NULL) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    ret = bdrv_file_open(&bs->file, filename, NULL, flags);
+    ret = bdrv_file_open(&bs->file, filename, flags);
     if (ret < 0) {
-        goto fail;
+        return ret;
     }
 
-    ret = 0;
-fail:
-    qemu_opts_del(opts);
-    return ret;
+    return 0;
 }
 
 static void error_callback_bh(void *opaque)
@@ -411,22 +328,22 @@ static void blkdebug_aio_cancel(BlockDriverAIOCB *blockacb)
 }
 
 static BlockDriverAIOCB *inject_error(BlockDriverState *bs,
-    BlockDriverCompletionFunc *cb, void *opaque, BlkdebugRule *rule)
+    BlockDriverCompletionFunc *cb, void *opaque)
 {
     BDRVBlkdebugState *s = bs->opaque;
-    int error = rule->options.inject.error;
+    int error = s->vars.inject_errno;
     struct BlkdebugAIOCB *acb;
     QEMUBH *bh;
 
-    if (rule->options.inject.once) {
-        QSIMPLEQ_INIT(&s->active_rules);
+    if (s->vars.inject_once) {
+        s->vars.inject_errno = 0;
     }
 
-    if (rule->options.inject.immediately) {
+    if (s->vars.inject_immediately) {
         return NULL;
     }
 
-    acb = qemu_aio_get(&blkdebug_aiocb_info, bs, cb, opaque);
+    acb = qemu_aio_get(&blkdebug_aio_pool, bs, cb, opaque);
     acb->ret = -error;
 
     bh = qemu_bh_new(error_callback_bh, acb);
@@ -441,21 +358,14 @@ static BlockDriverAIOCB *blkdebug_aio_readv(BlockDriverState *bs,
     BlockDriverCompletionFunc *cb, void *opaque)
 {
     BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugRule *rule = NULL;
 
-    QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
-        if (rule->options.inject.sector == -1 ||
-            (rule->options.inject.sector >= sector_num &&
-             rule->options.inject.sector < sector_num + nb_sectors)) {
-            break;
-        }
+    if (s->vars.inject_errno) {
+        return inject_error(bs, cb, opaque);
     }
 
-    if (rule && rule->options.inject.error) {
-        return inject_error(bs, cb, opaque, rule);
-    }
-
-    return bdrv_aio_readv(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
+    BlockDriverAIOCB *acb =
+        bdrv_aio_readv(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
+    return acb;
 }
 
 static BlockDriverAIOCB *blkdebug_aio_writev(BlockDriverState *bs,
@@ -463,24 +373,16 @@ static BlockDriverAIOCB *blkdebug_aio_writev(BlockDriverState *bs,
     BlockDriverCompletionFunc *cb, void *opaque)
 {
     BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugRule *rule = NULL;
 
-    QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
-        if (rule->options.inject.sector == -1 ||
-            (rule->options.inject.sector >= sector_num &&
-             rule->options.inject.sector < sector_num + nb_sectors)) {
-            break;
-        }
+    if (s->vars.inject_errno) {
+        return inject_error(bs, cb, opaque);
     }
 
-    if (rule && rule->options.inject.error) {
-        return inject_error(bs, cb, opaque, rule);
-    }
-
-    return bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
+    BlockDriverAIOCB *acb =
+        bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
+    return acb;
 }
 
-
 static void blkdebug_close(BlockDriverState *bs)
 {
     BDRVBlkdebugState *s = bs->opaque;
@@ -489,154 +391,63 @@ static void blkdebug_close(BlockDriverState *bs)
 
     for (i = 0; i < BLKDBG_EVENT_MAX; i++) {
         QLIST_FOREACH_SAFE(rule, &s->rules[i], next, next) {
-            remove_rule(rule);
+            QLIST_REMOVE(rule, next);
+            g_free(rule);
         }
     }
 }
 
-static void suspend_request(BlockDriverState *bs, BlkdebugRule *rule)
-{
-    BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugSuspendedReq r;
-
-    r = (BlkdebugSuspendedReq) {
-        .co         = qemu_coroutine_self(),
-        .tag        = g_strdup(rule->options.suspend.tag),
-    };
-
-    remove_rule(rule);
-    QLIST_INSERT_HEAD(&s->suspended_reqs, &r, next);
-
-    printf("blkdebug: Suspended request '%s'\n", r.tag);
-    qemu_coroutine_yield();
-    printf("blkdebug: Resuming request '%s'\n", r.tag);
-
-    QLIST_REMOVE(&r, next);
-    g_free(r.tag);
-}
-
-static bool process_rule(BlockDriverState *bs, struct BlkdebugRule *rule,
-    bool injected)
+static void process_rule(BlockDriverState *bs, struct BlkdebugRule *rule,
+    BlkdebugVars *old_vars)
 {
     BDRVBlkdebugState *s = bs->opaque;
+    BlkdebugVars *vars = &s->vars;
 
     /* Only process rules for the current state */
-    if (rule->state && rule->state != s->state) {
-        return injected;
+    if (rule->state && rule->state != old_vars->state) {
+        return;
     }
 
     /* Take the action */
     switch (rule->action) {
     case ACTION_INJECT_ERROR:
-        if (!injected) {
-            QSIMPLEQ_INIT(&s->active_rules);
-            injected = true;
-        }
-        QSIMPLEQ_INSERT_HEAD(&s->active_rules, rule, active_next);
+        vars->inject_errno       = rule->options.inject.error;
+        vars->inject_once        = rule->options.inject.once;
+        vars->inject_immediately = rule->options.inject.immediately;
         break;
 
     case ACTION_SET_STATE:
-        s->new_state = rule->options.set_state.new_state;
-        break;
-
-    case ACTION_SUSPEND:
-        suspend_request(bs, rule);
+        vars->state              = rule->options.set_state.new_state;
         break;
     }
-    return injected;
 }
 
 static void blkdebug_debug_event(BlockDriverState *bs, BlkDebugEvent event)
 {
     BDRVBlkdebugState *s = bs->opaque;
-    struct BlkdebugRule *rule, *next;
-    bool injected;
+    struct BlkdebugRule *rule;
+    BlkdebugVars old_vars = s->vars;
 
     assert((int)event >= 0 && event < BLKDBG_EVENT_MAX);
 
-    injected = false;
-    s->new_state = s->state;
-    QLIST_FOREACH_SAFE(rule, &s->rules[event], next, next) {
-        injected = process_rule(bs, rule, injected);
+    QLIST_FOREACH(rule, &s->rules[event], next) {
+        process_rule(bs, rule, &old_vars);
     }
-    s->state = s->new_state;
-}
-
-static int blkdebug_debug_breakpoint(BlockDriverState *bs, const char *event,
-                                     const char *tag)
-{
-    BDRVBlkdebugState *s = bs->opaque;
-    struct BlkdebugRule *rule;
-    BlkDebugEvent blkdebug_event;
-
-    if (get_event_by_name(event, &blkdebug_event) < 0) {
-        return -ENOENT;
-    }
-
-
-    rule = g_malloc(sizeof(*rule));
-    *rule = (struct BlkdebugRule) {
-        .event  = blkdebug_event,
-        .action = ACTION_SUSPEND,
-        .state  = 0,
-        .options.suspend.tag = g_strdup(tag),
-    };
-
-    QLIST_INSERT_HEAD(&s->rules[blkdebug_event], rule, next);
-
-    return 0;
-}
-
-static int blkdebug_debug_resume(BlockDriverState *bs, const char *tag)
-{
-    BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugSuspendedReq *r;
-
-    QLIST_FOREACH(r, &s->suspended_reqs, next) {
-        if (!strcmp(r->tag, tag)) {
-            qemu_coroutine_enter(r->co, NULL);
-            return 0;
-        }
-    }
-    return -ENOENT;
-}
-
-
-static bool blkdebug_debug_is_suspended(BlockDriverState *bs, const char *tag)
-{
-    BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugSuspendedReq *r;
-
-    QLIST_FOREACH(r, &s->suspended_reqs, next) {
-        if (!strcmp(r->tag, tag)) {
-            return true;
-        }
-    }
-    return false;
-}
-
-static int64_t blkdebug_getlength(BlockDriverState *bs)
-{
-    return bdrv_getlength(bs->file);
 }
 
 static BlockDriver bdrv_blkdebug = {
-    .format_name            = "blkdebug",
-    .protocol_name          = "blkdebug",
-    .instance_size          = sizeof(BDRVBlkdebugState),
+    .format_name        = "blkdebug",
+    .protocol_name      = "blkdebug",
 
-    .bdrv_parse_filename    = blkdebug_parse_filename,
-    .bdrv_file_open         = blkdebug_open,
-    .bdrv_close             = blkdebug_close,
-    .bdrv_getlength         = blkdebug_getlength,
+    .instance_size      = sizeof(BDRVBlkdebugState),
 
-    .bdrv_aio_readv         = blkdebug_aio_readv,
-    .bdrv_aio_writev        = blkdebug_aio_writev,
+    .bdrv_file_open     = blkdebug_open,
+    .bdrv_close         = blkdebug_close,
 
-    .bdrv_debug_event           = blkdebug_debug_event,
-    .bdrv_debug_breakpoint      = blkdebug_debug_breakpoint,
-    .bdrv_debug_resume          = blkdebug_debug_resume,
-    .bdrv_debug_is_suspended    = blkdebug_debug_is_suspended,
+    .bdrv_aio_readv     = blkdebug_aio_readv,
+    .bdrv_aio_writev    = blkdebug_aio_writev,
+
+    .bdrv_debug_event   = blkdebug_debug_event,
 };
 
 static void bdrv_blkdebug_init(void)

block/blkverify.c

@@ -8,8 +8,8 @@
  */
 
 #include <stdarg.h>
-#include "qemu/sockets.h" /* for EINPROGRESS on Windows */
-#include "block/block_int.h"
+#include "qemu_socket.h" /* for EINPROGRESS on Windows */
+#include "block_int.h"
 
 typedef struct {
     BlockDriverState *test_file;
@@ -48,7 +48,7 @@ static void blkverify_aio_cancel(BlockDriverAIOCB *blockacb)
     }
 }
 
-static const AIOCBInfo blkverify_aiocb_info = {
+static AIOPool blkverify_aio_pool = {
     .aiocb_size         = sizeof(BlkverifyAIOCB),
     .cancel             = blkverify_aio_cancel,
 };
@@ -69,100 +69,43 @@ static void GCC_FMT_ATTR(2, 3) blkverify_err(BlkverifyAIOCB *acb,
 }
 
 /* Valid blkverify filenames look like blkverify:path/to/raw_image:path/to/image */
-static void blkverify_parse_filename(const char *filename, QDict *options,
-                                     Error **errp)
+static int blkverify_open(BlockDriverState *bs, const char *filename, int flags)
 {
-    const char *c;
-    QString *raw_path;
-
+    BDRVBlkverifyState *s = bs->opaque;
+    int ret;
+    char *raw, *c;
 
     /* Parse the blkverify: prefix */
-    if (!strstart(filename, "blkverify:", &filename)) {
-        error_setg(errp, "File name string must start with 'blkverify:'");
-        return;
+    if (strncmp(filename, "blkverify:", strlen("blkverify:"))) {
+        return -EINVAL;
     }
+    filename += strlen("blkverify:");
 
     /* Parse the raw image filename */
     c = strchr(filename, ':');
     if (c == NULL) {
-        error_setg(errp, "blkverify requires raw copy and original image path");
-        return;
+        return -EINVAL;
     }
 
-    /* TODO Implement option pass-through and set raw.filename here */
-    raw_path = qstring_from_substr(filename, 0, c - filename - 1);
-    qdict_put(options, "x-raw", raw_path);
-
-    /* TODO Allow multi-level nesting and set file.filename here */
-    filename = c + 1;
-    qdict_put(options, "x-image", qstring_from_str(filename));
-}
-
-static QemuOptsList runtime_opts = {
-    .name = "blkverify",
-    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
-    .desc = {
-        {
-            .name = "x-raw",
-            .type = QEMU_OPT_STRING,
-            .help = "[internal use only, will be removed]",
-        },
-        {
-            .name = "x-image",
-            .type = QEMU_OPT_STRING,
-            .help = "[internal use only, will be removed]",
-        },
-        { /* end of list */ }
-    },
-};
-
-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_nofail(&runtime_opts);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (error_is_set(&local_err)) {
-        qerror_report_err(local_err);
-        error_free(local_err);
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    /* 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);
+    raw = g_strdup(filename);
+    raw[c - filename] = '\0';
+    ret = bdrv_file_open(&bs->file, raw, flags);
+    g_free(raw);
     if (ret < 0) {
-        goto fail;
+        return ret;
     }
+    filename = c + 1;
 
     /* Open the test file */
-    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);
+    ret = bdrv_open(s->test_file, filename, flags, NULL);
     if (ret < 0) {
         bdrv_delete(s->test_file);
         s->test_file = NULL;
-        goto fail;
+        return ret;
     }
 
-    ret = 0;
-fail:
-    return ret;
+    return 0;
 }
 
 static void blkverify_close(BlockDriverState *bs)
@@ -290,7 +233,7 @@ static BlkverifyAIOCB *blkverify_aio_get(BlockDriverState *bs, bool is_write,
                                          BlockDriverCompletionFunc *cb,
                                          void *opaque)
 {
-    BlkverifyAIOCB *acb = qemu_aio_get(&blkverify_aiocb_info, bs, cb, opaque);
+    BlkverifyAIOCB *acb = qemu_aio_get(&blkverify_aio_pool, bs, cb, opaque);
 
     acb->bh = NULL;
     acb->is_write = is_write;
@@ -400,18 +343,19 @@ static BlockDriverAIOCB *blkverify_aio_flush(BlockDriverState *bs,
 }
 
 static BlockDriver bdrv_blkverify = {
-    .format_name            = "blkverify",
-    .protocol_name          = "blkverify",
-    .instance_size          = sizeof(BDRVBlkverifyState),
+    .format_name        = "blkverify",
+    .protocol_name      = "blkverify",
 
-    .bdrv_parse_filename    = blkverify_parse_filename,
-    .bdrv_file_open         = blkverify_open,
-    .bdrv_close             = blkverify_close,
-    .bdrv_getlength         = blkverify_getlength,
+    .instance_size      = sizeof(BDRVBlkverifyState),
 
-    .bdrv_aio_readv         = blkverify_aio_readv,
-    .bdrv_aio_writev        = blkverify_aio_writev,
-    .bdrv_aio_flush         = blkverify_aio_flush,
+    .bdrv_getlength     = blkverify_getlength,
+
+    .bdrv_file_open     = blkverify_open,
+    .bdrv_close         = blkverify_close,
+
+    .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

@@ -23,8 +23,8 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
 
 /**************************************************************/
 
@@ -108,19 +108,17 @@ 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)
+static int bochs_open(BlockDriverState *bs, int flags)
 {
     BDRVBochsState *s = bs->opaque;
     int i;
     struct bochs_header bochs;
     struct bochs_header_v1 header_v1;
-    int ret;
 
     bs->read_only = 1; // no write support yet
 
-    ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs));
-    if (ret < 0) {
-        return ret;
+    if (bdrv_pread(bs->file, 0, &bochs, sizeof(bochs)) != sizeof(bochs)) {
+        goto fail;
     }
 
     if (strcmp(bochs.magic, HEADER_MAGIC) ||
@@ -128,7 +126,7 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags)
         strcmp(bochs.subtype, GROWING_TYPE) ||
 	((le32_to_cpu(bochs.version) != HEADER_VERSION) &&
 	(le32_to_cpu(bochs.version) != HEADER_V1))) {
-        return -EMEDIUMTYPE;
+        goto fail;
     }
 
     if (le32_to_cpu(bochs.version) == HEADER_V1) {
@@ -140,13 +138,9 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags)
 
     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,
-                     s->catalog_size * 4);
-    if (ret < 0) {
-        goto fail;
-    }
-
+    if (bdrv_pread(bs->file, le32_to_cpu(bochs.header), s->catalog_bitmap,
+                   s->catalog_size * 4) != s->catalog_size * 4)
+	goto fail;
     for (i = 0; i < s->catalog_size; i++)
 	le32_to_cpus(&s->catalog_bitmap[i]);
 
@@ -159,10 +153,8 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags)
 
     qemu_co_mutex_init(&s->lock);
     return 0;
-
-fail:
-    g_free(s->catalog_bitmap);
-    return ret;
+ fail:
+    return -1;
 }
 
 static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)

block/cloop.c

@@ -22,8 +22,8 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
 #include <zlib.h>
 
 typedef struct BDRVCloopState {
@@ -53,36 +53,31 @@ 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)
+static int cloop_open(BlockDriverState *bs, int flags)
 {
     BDRVCloopState *s = bs->opaque;
     uint32_t offsets_size, max_compressed_block_size = 1, i;
-    int ret;
 
     bs->read_only = 1;
 
     /* read header */
-    ret = bdrv_pread(bs->file, 128, &s->block_size, 4);
-    if (ret < 0) {
-        return ret;
+    if (bdrv_pread(bs->file, 128, &s->block_size, 4) < 4) {
+        goto cloop_close;
     }
     s->block_size = be32_to_cpu(s->block_size);
 
-    ret = bdrv_pread(bs->file, 128 + 4, &s->n_blocks, 4);
-    if (ret < 0) {
-        return ret;
+    if (bdrv_pread(bs->file, 128 + 4, &s->n_blocks, 4) < 4) {
+        goto cloop_close;
     }
     s->n_blocks = be32_to_cpu(s->n_blocks);
 
     /* read offsets */
     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);
-    if (ret < 0) {
-        goto fail;
+    if (bdrv_pread(bs->file, 128 + 4 + 4, s->offsets, offsets_size) <
+            offsets_size) {
+        goto cloop_close;
     }
-
     for(i=0;i<s->n_blocks;i++) {
         s->offsets[i] = be64_to_cpu(s->offsets[i]);
         if (i > 0) {
@@ -97,8 +92,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags)
     s->compressed_block = g_malloc(max_compressed_block_size + 1);
     s->uncompressed_block = g_malloc(s->block_size);
     if (inflateInit(&s->zstream) != Z_OK) {
-        ret = -EINVAL;
-        goto fail;
+        goto cloop_close;
     }
     s->current_block = s->n_blocks;
 
@@ -107,11 +101,8 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags)
     qemu_co_mutex_init(&s->lock);
     return 0;
 
-fail:
-    g_free(s->offsets);
-    g_free(s->compressed_block);
-    g_free(s->uncompressed_block);
-    return ret;
+cloop_close:
+    return -1;
 }
 
 static inline int cloop_read_block(BlockDriverState *bs, int block_num)

block/commit.c

@@ -1,258 +0,0 @@
-/*
- * Live block commit
- *
- * Copyright Red Hat, Inc. 2012
- *
- * Authors:
- *  Jeff Cody   <jcody@redhat.com>
- *  Based on stream.c by Stefan Hajnoczi
- *
- * 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 "trace.h"
-#include "block/block_int.h"
-#include "block/blockjob.h"
-#include "qemu/ratelimit.h"
-
-enum {
-    /*
-     * Size of data buffer for populating the image file.  This should be large
-     * enough to process multiple clusters in a single call, so that populating
-     * contiguous regions of the image is efficient.
-     */
-    COMMIT_BUFFER_SIZE = 512 * 1024, /* in bytes */
-};
-
-#define SLICE_TIME 100000000ULL /* ns */
-
-typedef struct CommitBlockJob {
-    BlockJob common;
-    RateLimit limit;
-    BlockDriverState *active;
-    BlockDriverState *top;
-    BlockDriverState *base;
-    BlockdevOnError on_error;
-    int base_flags;
-    int orig_overlay_flags;
-} CommitBlockJob;
-
-static int coroutine_fn commit_populate(BlockDriverState *bs,
-                                        BlockDriverState *base,
-                                        int64_t sector_num, int nb_sectors,
-                                        void *buf)
-{
-    int ret = 0;
-
-    ret = bdrv_read(bs, sector_num, buf, nb_sectors);
-    if (ret) {
-        return ret;
-    }
-
-    ret = bdrv_write(base, sector_num, buf, nb_sectors);
-    if (ret) {
-        return ret;
-    }
-
-    return 0;
-}
-
-static void coroutine_fn commit_run(void *opaque)
-{
-    CommitBlockJob *s = opaque;
-    BlockDriverState *active = s->active;
-    BlockDriverState *top = s->top;
-    BlockDriverState *base = s->base;
-    BlockDriverState *overlay_bs;
-    int64_t sector_num, end;
-    int ret = 0;
-    int n = 0;
-    void *buf;
-    int bytes_written = 0;
-    int64_t base_len;
-
-    ret = s->common.len = bdrv_getlength(top);
-
-
-    if (s->common.len < 0) {
-        goto exit_restore_reopen;
-    }
-
-    ret = base_len = bdrv_getlength(base);
-    if (base_len < 0) {
-        goto exit_restore_reopen;
-    }
-
-    if (base_len < s->common.len) {
-        ret = bdrv_truncate(base, s->common.len);
-        if (ret) {
-            goto exit_restore_reopen;
-        }
-    }
-
-    end = s->common.len >> BDRV_SECTOR_BITS;
-    buf = qemu_blockalign(top, COMMIT_BUFFER_SIZE);
-
-    for (sector_num = 0; sector_num < end; sector_num += n) {
-        uint64_t delay_ns = 0;
-        bool copy;
-
-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, rt_clock, delay_ns);
-        if (block_job_is_cancelled(&s->common)) {
-            break;
-        }
-        /* Copy if allocated above the base */
-        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) {
-            if (s->common.speed) {
-                delay_ns = ratelimit_calculate_delay(&s->limit, n);
-                if (delay_ns > 0) {
-                    goto wait;
-                }
-            }
-            ret = commit_populate(top, base, sector_num, n, buf);
-            bytes_written += n * BDRV_SECTOR_SIZE;
-        }
-        if (ret < 0) {
-            if (s->on_error == BLOCKDEV_ON_ERROR_STOP ||
-                s->on_error == BLOCKDEV_ON_ERROR_REPORT||
-                (s->on_error == BLOCKDEV_ON_ERROR_ENOSPC && ret == -ENOSPC)) {
-                goto exit_free_buf;
-            } else {
-                n = 0;
-                continue;
-            }
-        }
-        /* Publish progress */
-        s->common.offset += n * BDRV_SECTOR_SIZE;
-    }
-
-    ret = 0;
-
-    if (!block_job_is_cancelled(&s->common) && sector_num == end) {
-        /* success */
-        ret = bdrv_drop_intermediate(active, top, base);
-    }
-
-exit_free_buf:
-    qemu_vfree(buf);
-
-exit_restore_reopen:
-    /* restore base open flags here if appropriate (e.g., change the base back
-     * to r/o). These reopens do not need to be atomic, since we won't abort
-     * even on failure here */
-    if (s->base_flags != bdrv_get_flags(base)) {
-        bdrv_reopen(base, s->base_flags, NULL);
-    }
-    overlay_bs = bdrv_find_overlay(active, top);
-    if (overlay_bs && s->orig_overlay_flags != bdrv_get_flags(overlay_bs)) {
-        bdrv_reopen(overlay_bs, s->orig_overlay_flags, NULL);
-    }
-
-    block_job_completed(&s->common, ret);
-}
-
-static void commit_set_speed(BlockJob *job, int64_t speed, Error **errp)
-{
-    CommitBlockJob *s = container_of(job, CommitBlockJob, common);
-
-    if (speed < 0) {
-        error_set(errp, QERR_INVALID_PARAMETER, "speed");
-        return;
-    }
-    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
-}
-
-static const BlockJobType commit_job_type = {
-    .instance_size = sizeof(CommitBlockJob),
-    .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, Error **errp)
-{
-    CommitBlockJob *s;
-    BlockReopenQueue *reopen_queue = NULL;
-    int orig_overlay_flags;
-    int orig_base_flags;
-    BlockDriverState *overlay_bs;
-    Error *local_err = NULL;
-
-    if ((on_error == BLOCKDEV_ON_ERROR_STOP ||
-         on_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        !bdrv_iostatus_is_enabled(bs)) {
-        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;
-    }
-
-    if (top == base) {
-        error_setg(errp, "Invalid files for merge: top and base are the same");
-        return;
-    }
-
-    overlay_bs = bdrv_find_overlay(bs, top);
-
-    if (overlay_bs == NULL) {
-        error_setg(errp, "Could not find overlay image for %s:", top->filename);
-        return;
-    }
-
-    orig_base_flags    = bdrv_get_flags(base);
-    orig_overlay_flags = bdrv_get_flags(overlay_bs);
-
-    /* convert base & overlay_bs to r/w, if necessary */
-    if (!(orig_base_flags & BDRV_O_RDWR)) {
-        reopen_queue = bdrv_reopen_queue(reopen_queue, base,
-                                         orig_base_flags | BDRV_O_RDWR);
-    }
-    if (!(orig_overlay_flags & BDRV_O_RDWR)) {
-        reopen_queue = bdrv_reopen_queue(reopen_queue, overlay_bs,
-                                         orig_overlay_flags | BDRV_O_RDWR);
-    }
-    if (reopen_queue) {
-        bdrv_reopen_multiple(reopen_queue, &local_err);
-        if (local_err != NULL) {
-            error_propagate(errp, local_err);
-            return;
-        }
-    }
-
-
-    s = block_job_create(&commit_job_type, bs, speed, cb, opaque, errp);
-    if (!s) {
-        return;
-    }
-
-    s->base   = base;
-    s->top    = top;
-    s->active = bs;
-
-    s->base_flags          = orig_base_flags;
-    s->orig_overlay_flags  = orig_overlay_flags;
-
-    s->on_error = on_error;
-    s->common.co = qemu_coroutine_create(commit_run);
-
-    trace_commit_start(bs, base, top, s, s->common.co, opaque);
-    qemu_coroutine_enter(s->common.co, s);
-}

block/cow.c

@@ -22,8 +22,8 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
 
 /**************************************************************/
 /* COW block driver using file system holes */
@@ -58,7 +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)
+static int cow_open(BlockDriverState *bs, int flags)
 {
     BDRVCowState *s = bs->opaque;
     struct cow_header_v2 cow_header;
@@ -73,7 +73,7 @@ static int cow_open(BlockDriverState *bs, QDict *options, int flags)
     }
 
     if (be32_to_cpu(cow_header.magic) != COW_MAGIC) {
-        ret = -EMEDIUMTYPE;
+        ret = -EINVAL;
         goto fail;
     }
 
@@ -279,7 +279,7 @@ static int cow_create(const char *filename, QEMUOptionParameter *options)
         return ret;
     }
 
-    ret = bdrv_file_open(&cow_bs, filename, NULL, BDRV_O_RDWR);
+    ret = bdrv_file_open(&cow_bs, filename, BDRV_O_RDWR);
     if (ret < 0) {
         return ret;
     }
@@ -340,7 +340,6 @@ static BlockDriver bdrv_cow = {
     .bdrv_open      = cow_open,
     .bdrv_close     = cow_close,
     .bdrv_create    = cow_create,
-    .bdrv_has_zero_init     = bdrv_has_zero_init_1,
 
     .bdrv_read              = cow_co_read,
     .bdrv_write             = cow_co_write,

block/curl.c

@@ -22,7 +22,7 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
+#include "block_int.h"
 #include <curl/curl.h>
 
 // #define DEBUG
@@ -34,10 +34,6 @@
 #define DPRINTF(fmt, ...) do { } while (0)
 #endif
 
-#define PROTOCOLS (CURLPROTO_HTTP | CURLPROTO_HTTPS | \
-                   CURLPROTO_FTP | CURLPROTO_FTPS | \
-                   CURLPROTO_TFTP)
-
 #define CURL_NUM_STATES 8
 #define CURL_NUM_ACB    8
 #define SECTOR_SIZE     512
@@ -81,7 +77,6 @@ typedef struct BDRVCURLState {
     CURLState states[CURL_NUM_STATES];
     char *url;
     size_t readahead_size;
-    bool accept_range;
 } BDRVCURLState;
 
 static void curl_clean_state(CURLState *s);
@@ -111,15 +106,14 @@ static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
     return 0;
 }
 
-static size_t curl_header_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
+static size_t curl_size_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
 {
-    BDRVCURLState *s = opaque;
+    CURLState *s = ((CURLState*)opaque);
     size_t realsize = size * nmemb;
-    const char *accept_line = "Accept-Ranges: bytes";
+    size_t fsize;
 
-    if (realsize >= strlen(accept_line)
-        && strncmp((char *)ptr, accept_line, strlen(accept_line)) == 0) {
-        s->accept_range = true;
+    if(sscanf(ptr, "Content-Length: %zd", &fsize) == 1) {
+        s->s->len = fsize;
     }
 
     return realsize;
@@ -146,8 +140,8 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
             continue;
 
         if ((s->buf_off >= acb->end)) {
-            qemu_iovec_from_buf(acb->qiov, 0, s->orig_buf + acb->start,
-                                acb->end - acb->start);
+            qemu_iovec_from_buffer(acb->qiov, s->orig_buf + acb->start,
+                                   acb->end - acb->start);
             acb->common.cb(acb->common.opaque, 0);
             qemu_aio_release(acb);
             s->acb[i] = NULL;
@@ -182,7 +176,7 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
         {
             char *buf = state->orig_buf + (start - state->buf_start);
 
-            qemu_iovec_from_buf(acb->qiov, 0, buf, len);
+            qemu_iovec_from_buffer(acb->qiov, buf, len);
             acb->common.cb(acb->common.opaque, 0);
 
             return FIND_RET_OK;
@@ -308,17 +302,6 @@ static CURLState *curl_init_state(BDRVCURLState *s)
     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);
-#endif
-
 #ifdef DEBUG_VERBOSE
     curl_easy_setopt(state->curl, CURLOPT_VERBOSE, 1);
 #endif
@@ -337,9 +320,11 @@ static void curl_clean_state(CURLState *s)
     s->in_use = 0;
 }
 
-static void curl_parse_filename(const char *filename, QDict *options,
-                                Error **errp)
+static int curl_open(BlockDriverState *bs, const char *filename, int flags)
 {
+    BDRVCURLState *s = bs->opaque;
+    CURLState *state = NULL;
+    double d;
 
     #define RA_OPTSTR ":readahead="
     char *file;
@@ -347,17 +332,19 @@ static void curl_parse_filename(const char *filename, QDict *options,
     const char *ra_val;
     int parse_state = 0;
 
+    static int inited = 0;
+
     file = g_strdup(filename);
+    s->readahead_size = READ_AHEAD_SIZE;
 
     /* Parse a trailing ":readahead=#:" param, if present. */
     ra = file + strlen(file) - 1;
     while (ra >= file) {
         if (parse_state == 0) {
-            if (*ra == ':') {
+            if (*ra == ':')
                 parse_state++;
-            } else {
+            else
                 break;
-            }
         } else if (parse_state == 1) {
             if (*ra > '9' || *ra < '0') {
                 char *opt_start = ra - strlen(RA_OPTSTR) + 1;
@@ -366,108 +353,46 @@ static void curl_parse_filename(const char *filename, QDict *options,
                     ra_val = ra + 1;
                     ra -= strlen(RA_OPTSTR) - 1;
                     *ra = '\0';
-                    qdict_put(options, "readahead", qstring_from_str(ra_val));
+                    s->readahead_size = atoi(ra_val);
+                    break;
+                } else {
+                    break;
                 }
-                break;
             }
         }
         ra--;
     }
 
-    qdict_put(options, "url", qstring_from_str(file));
-
-    g_free(file);
-}
-
-static QemuOptsList runtime_opts = {
-    .name = "curl",
-    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
-    .desc = {
-        {
-            .name = "url",
-            .type = QEMU_OPT_STRING,
-            .help = "URL to open",
-        },
-        {
-            .name = "readahead",
-            .type = QEMU_OPT_SIZE,
-            .help = "Readahead size",
-        },
-        { /* end of list */ }
-    },
-};
-
-static int curl_open(BlockDriverState *bs, QDict *options, int flags)
-{
-    BDRVCURLState *s = bs->opaque;
-    CURLState *state = NULL;
-    QemuOpts *opts;
-    Error *local_err = NULL;
-    const char *file;
-    double d;
-
-    static int inited = 0;
-
-    if (flags & BDRV_O_RDWR) {
-        qerror_report(ERROR_CLASS_GENERIC_ERROR,
-                      "curl block device does not support writes");
-        return -EROFS;
-    }
-
-    opts = qemu_opts_create_nofail(&runtime_opts);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (error_is_set(&local_err)) {
-        qerror_report_err(local_err);
-        error_free(local_err);
-        goto out_noclean;
-    }
-
-    s->readahead_size = qemu_opt_get_size(opts, "readahead", READ_AHEAD_SIZE);
     if ((s->readahead_size & 0x1ff) != 0) {
         fprintf(stderr, "HTTP_READAHEAD_SIZE %zd is not a multiple of 512\n",
                 s->readahead_size);
         goto out_noclean;
     }
 
-    file = qemu_opt_get(opts, "url");
-    if (file == NULL) {
-        qerror_report(ERROR_CLASS_GENERIC_ERROR, "curl block driver requires "
-                      "an 'url' option");
-        goto out_noclean;
-    }
-
     if (!inited) {
         curl_global_init(CURL_GLOBAL_ALL);
         inited = 1;
     }
 
     DPRINTF("CURL: Opening %s\n", file);
-    s->url = g_strdup(file);
+    s->url = file;
     state = curl_init_state(s);
     if (!state)
         goto out_noclean;
 
     // Get file size
 
-    s->accept_range = false;
     curl_easy_setopt(state->curl, CURLOPT_NOBODY, 1);
-    curl_easy_setopt(state->curl, CURLOPT_HEADERFUNCTION,
-                     curl_header_cb);
-    curl_easy_setopt(state->curl, CURLOPT_HEADERDATA, s);
+    curl_easy_setopt(state->curl, CURLOPT_WRITEFUNCTION, (void *)curl_size_cb);
     if (curl_easy_perform(state->curl))
         goto out;
     curl_easy_getinfo(state->curl, CURLINFO_CONTENT_LENGTH_DOWNLOAD, &d);
+    curl_easy_setopt(state->curl, CURLOPT_WRITEFUNCTION, (void *)curl_read_cb);
+    curl_easy_setopt(state->curl, CURLOPT_NOBODY, 0);
     if (d)
         s->len = (size_t)d;
     else if(!s->len)
         goto out;
-    if ((!strncasecmp(s->url, "http://", strlen("http://"))
-        || !strncasecmp(s->url, "https://", strlen("https://")))
-        && !s->accept_range) {
-        pstrcpy(state->errmsg, CURL_ERROR_SIZE,
-                "Server does not support 'range' (byte ranges).");
-        goto out;
-    }
     DPRINTF("CURL: Size = %zd\n", s->len);
 
     curl_clean_state(state);
@@ -478,11 +403,10 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags)
     // 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_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:
@@ -490,8 +414,7 @@ out:
     curl_easy_cleanup(state->curl);
     state->curl = NULL;
 out_noclean:
-    g_free(s->url);
-    qemu_opts_del(opts);
+    g_free(file);
     return -EINVAL;
 }
 
@@ -515,7 +438,7 @@ static void curl_aio_cancel(BlockDriverAIOCB *blockacb)
     // Do we have to implement canceling? Seems to work without...
 }
 
-static const AIOCBInfo curl_aiocb_info = {
+static AIOPool curl_aio_pool = {
     .aiocb_size         = sizeof(CURLAIOCB),
     .cancel             = curl_aio_cancel,
 };
@@ -582,7 +505,7 @@ static BlockDriverAIOCB *curl_aio_readv(BlockDriverState *bs,
 {
     CURLAIOCB *acb;
 
-    acb = qemu_aio_get(&curl_aiocb_info, bs, cb, opaque);
+    acb = qemu_aio_get(&curl_aio_pool, bs, cb, opaque);
 
     acb->qiov = qiov;
     acb->sector_num = sector_num;
@@ -619,7 +542,8 @@ static void curl_close(BlockDriverState *bs)
     }
     if (s->multi)
         curl_multi_cleanup(s->multi);
-    g_free(s->url);
+    if (s->url)
+        free(s->url);
 }
 
 static int64_t curl_getlength(BlockDriverState *bs)
@@ -629,68 +553,63 @@ 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_file_open  = curl_open,
+    .bdrv_close      = curl_close,
+    .bdrv_getlength  = curl_getlength,
 
-    .bdrv_aio_readv         = curl_aio_readv,
+    .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_file_open  = curl_open,
+    .bdrv_close      = curl_close,
+    .bdrv_getlength  = curl_getlength,
 
-    .bdrv_aio_readv         = curl_aio_readv,
+    .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_file_open  = curl_open,
+    .bdrv_close      = curl_close,
+    .bdrv_getlength  = curl_getlength,
 
-    .bdrv_aio_readv         = curl_aio_readv,
+    .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_file_open  = curl_open,
+    .bdrv_close      = curl_close,
+    .bdrv_getlength  = curl_getlength,
 
-    .bdrv_aio_readv         = curl_aio_readv,
+    .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_file_open  = curl_open,
+    .bdrv_close      = curl_close,
+    .bdrv_getlength  = curl_getlength,
 
-    .bdrv_aio_readv         = curl_aio_readv,
+    .bdrv_aio_readv  = curl_aio_readv,
 };
 
 static void curl_block_init(void)

block/dmg.c

@@ -22,9 +22,9 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/bswap.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "bswap.h"
+#include "module.h"
 #include <zlib.h>
 
 typedef struct BDRVDMGState {
@@ -51,55 +51,35 @@ typedef struct BDRVDMGState {
 
 static int dmg_probe(const uint8_t *buf, int buf_size, const char *filename)
 {
-    int len;
-
-    if (!filename) {
-        return 0;
-    }
-
-    len = strlen(filename);
-    if (len > 4 && !strcmp(filename + len - 4, ".dmg")) {
-        return 2;
-    }
+    int len=strlen(filename);
+    if(len>4 && !strcmp(filename+len-4,".dmg"))
+	return 2;
     return 0;
 }
 
-static int read_uint64(BlockDriverState *bs, int64_t offset, uint64_t *result)
+static off_t read_off(BlockDriverState *bs, int64_t offset)
 {
-    uint64_t buffer;
-    int ret;
-
-    ret = bdrv_pread(bs->file, offset, &buffer, 8);
-    if (ret < 0) {
-        return ret;
-    }
-
-    *result = be64_to_cpu(buffer);
-    return 0;
+	uint64_t buffer;
+	if (bdrv_pread(bs->file, offset, &buffer, 8) < 8)
+		return 0;
+	return be64_to_cpu(buffer);
 }
 
-static int read_uint32(BlockDriverState *bs, int64_t offset, uint32_t *result)
+static off_t read_uint32(BlockDriverState *bs, int64_t offset)
 {
-    uint32_t buffer;
-    int ret;
-
-    ret = bdrv_pread(bs->file, offset, &buffer, 4);
-    if (ret < 0) {
-        return ret;
-    }
-
-    *result = be32_to_cpu(buffer);
-    return 0;
+	uint32_t buffer;
+	if (bdrv_pread(bs->file, offset, &buffer, 4) < 4)
+		return 0;
+	return be32_to_cpu(buffer);
 }
 
-static int dmg_open(BlockDriverState *bs, QDict *options, int flags)
+static int dmg_open(BlockDriverState *bs, int flags)
 {
     BDRVDMGState *s = bs->opaque;
-    uint64_t info_begin,info_end,last_in_offset,last_out_offset;
-    uint32_t count, tmp;
+    off_t info_begin,info_end,last_in_offset,last_out_offset;
+    uint32_t count;
     uint32_t max_compressed_size=1,max_sectors_per_chunk=1,i;
     int64_t offset;
-    int ret;
 
     bs->read_only = 1;
     s->n_chunks = 0;
@@ -108,32 +88,21 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags)
     /* read offset of info blocks */
     offset = bdrv_getlength(bs->file);
     if (offset < 0) {
-        ret = offset;
         goto fail;
     }
     offset -= 0x1d8;
 
-    ret = read_uint64(bs, offset, &info_begin);
-    if (ret < 0) {
-        goto fail;
-    } else if (info_begin == 0) {
-        ret = -EINVAL;
+    info_begin = read_off(bs, offset);
+    if (info_begin == 0) {
+	goto fail;
+    }
+
+    if (read_uint32(bs, info_begin) != 0x100) {
         goto fail;
     }
 
-    ret = read_uint32(bs, info_begin, &tmp);
-    if (ret < 0) {
-        goto fail;
-    } else if (tmp != 0x100) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    ret = read_uint32(bs, info_begin + 4, &count);
-    if (ret < 0) {
-        goto fail;
-    } else if (count == 0) {
-        ret = -EINVAL;
+    count = read_uint32(bs, info_begin + 4);
+    if (count == 0) {
         goto fail;
     }
     info_end = info_begin + count;
@@ -145,20 +114,12 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags)
     while (offset < info_end) {
         uint32_t type;
 
-        ret = read_uint32(bs, offset, &count);
-        if (ret < 0) {
-            goto fail;
-        } else if (count == 0) {
-            ret = -EINVAL;
-            goto fail;
-        }
+	count = read_uint32(bs, offset);
+	if(count==0)
+	    goto fail;
         offset += 4;
 
-        ret = read_uint32(bs, offset, &type);
-        if (ret < 0) {
-            goto fail;
-        }
-
+	type = read_uint32(bs, offset);
 	if (type == 0x6d697368 && count >= 244) {
 	    int new_size, chunk_count;
 
@@ -173,11 +134,8 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags)
 	    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;
-                }
+	    for(i=s->n_chunks;i<s->n_chunks+chunk_count;i++) {
+		s->types[i] = read_uint32(bs, offset);
 		offset += 4;
 		if(s->types[i]!=0x80000005 && s->types[i]!=1 && s->types[i]!=2) {
 		    if(s->types[i]==0xffffffff) {
@@ -191,31 +149,17 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags)
 		}
 		offset += 4;
 
-                ret = read_uint64(bs, offset, &s->sectors[i]);
-                if (ret < 0) {
-                    goto fail;
-                }
-                s->sectors[i] += last_out_offset;
-                offset += 8;
+		s->sectors[i] = last_out_offset+read_off(bs, offset);
+		offset += 8;
 
-                ret = read_uint64(bs, offset, &s->sectorcounts[i]);
-                if (ret < 0) {
-                    goto fail;
-                }
-                offset += 8;
+		s->sectorcounts[i] = read_off(bs, offset);
+		offset += 8;
 
-                ret = read_uint64(bs, offset, &s->offsets[i]);
-                if (ret < 0) {
-                    goto fail;
-                }
-                s->offsets[i] += last_in_offset;
-                offset += 8;
+		s->offsets[i] = last_in_offset+read_off(bs, offset);
+		offset += 8;
 
-                ret = read_uint64(bs, offset, &s->lengths[i]);
-                if (ret < 0) {
-                    goto fail;
-                }
-                offset += 8;
+		s->lengths[i] = read_off(bs, offset);
+		offset += 8;
 
 		if(s->lengths[i]>max_compressed_size)
 		    max_compressed_size = s->lengths[i];
@@ -229,25 +173,15 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags)
     /* 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) {
-        ret = -EINVAL;
-        goto fail;
-    }
+    if(inflateInit(&s->zstream) != Z_OK)
+	goto fail;
 
     s->current_chunk = s->n_chunks;
 
     qemu_co_mutex_init(&s->lock);
     return 0;
-
 fail:
-    g_free(s->types);
-    g_free(s->offsets);
-    g_free(s->lengths);
-    g_free(s->sectors);
-    g_free(s->sectorcounts);
-    g_free(s->compressed_chunk);
-    g_free(s->uncompressed_chunk);
-    return ret;
+    return -1;
 }
 
 static inline int is_sector_in_chunk(BDRVDMGState* s,
@@ -362,15 +296,15 @@ static coroutine_fn int dmg_co_read(BlockDriverState *bs, int64_t sector_num,
 static void dmg_close(BlockDriverState *bs)
 {
     BDRVDMGState *s = bs->opaque;
-
-    g_free(s->types);
-    g_free(s->offsets);
-    g_free(s->lengths);
-    g_free(s->sectors);
-    g_free(s->sectorcounts);
-    g_free(s->compressed_chunk);
-    g_free(s->uncompressed_chunk);
-
+    if(s->n_chunks>0) {
+	free(s->types);
+	free(s->offsets);
+	free(s->lengths);
+	free(s->sectors);
+	free(s->sectorcounts);
+    }
+    free(s->compressed_chunk);
+    free(s->uncompressed_chunk);
     inflateEnd(&s->zstream);
 }
 

block/gluster.c

@@ -1,726 +0,0 @@
-/*
- * GlusterFS backend for QEMU
- *
- * Copyright (C) 2012 Bharata B Rao <bharata@linux.vnet.ibm.com>
- *
- * 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;
-} 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;
-    char *volname;
-    char *image;
-    char *transport;
-} GlusterConf;
-
-static void qemu_gluster_gconf_free(GlusterConf *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)
-{
-    char *p, *q;
-
-    if (!path) {
-        return -EINVAL;
-    }
-
-    /* volume */
-    p = q = path + strspn(path, "/");
-    p += strcspn(p, "/");
-    if (*p == '\0') {
-        return -EINVAL;
-    }
-    gconf->volname = g_strndup(q, p - q);
-
-    /* image */
-    p += strspn(p, "/");
-    if (*p == '\0') {
-        return -EINVAL;
-    }
-    gconf->image = g_strdup(p);
-    return 0;
-}
-
-/*
- * file=gluster[+transport]://[server[:port]]/volname/image[?socket=...]
- *
- * 'gluster' is the protocol.
- *
- * 'transport' specifies the transport type used to connect to gluster
- * management daemon (glusterd). Valid transport types are
- * tcp, unix and rdma. If a transport type isn't specified, then tcp
- * type is assumed.
- *
- * '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 specifed.
- * The 'socket' field needs to be populated with the path to unix domain
- * socket.
- *
- * 'port' is the port number on which glusterd is listening. This is optional
- * and if not specified, QEMU will send 0 which will make gluster to use the
- * default port. If the transport type is unix, then 'port' should not be
- * specified.
- *
- * 'volname' is the name of the gluster volume which contains the VM image.
- *
- * 'image' is the path to the actual VM image that resides on gluster volume.
- *
- * Examples:
- *
- * file=gluster://1.2.3.4/testvol/a.img
- * file=gluster+tcp://1.2.3.4/testvol/a.img
- * file=gluster+tcp://1.2.3.4:24007/testvol/dir/a.img
- * file=gluster+tcp://[1:2:3:4:5:6:7:8]/testvol/dir/a.img
- * file=gluster+tcp://[1:2:3:4:5:6:7:8]:24007/testvol/dir/a.img
- * file=gluster+tcp://server.domain.com:24007/testvol/dir/a.img
- * file=gluster+unix:///testvol/dir/a.img?socket=/tmp/glusterd.socket
- * file=gluster+rdma://1.2.3.4:24007/testvol/a.img
- */
-static int qemu_gluster_parseuri(GlusterConf *gconf, const char *filename)
-{
-    URI *uri;
-    QueryParams *qp = NULL;
-    bool is_unix = false;
-    int ret = 0;
-
-    uri = uri_parse(filename);
-    if (!uri) {
-        return -EINVAL;
-    }
-
-    /* transport */
-    if (!strcmp(uri->scheme, "gluster")) {
-        gconf->transport = g_strdup("tcp");
-    } else if (!strcmp(uri->scheme, "gluster+tcp")) {
-        gconf->transport = g_strdup("tcp");
-    } else if (!strcmp(uri->scheme, "gluster+unix")) {
-        gconf->transport = g_strdup("unix");
-        is_unix = true;
-    } else if (!strcmp(uri->scheme, "gluster+rdma")) {
-        gconf->transport = g_strdup("rdma");
-    } else {
-        ret = -EINVAL;
-        goto out;
-    }
-
-    ret = parse_volume_options(gconf, uri->path);
-    if (ret < 0) {
-        goto out;
-    }
-
-    qp = query_params_parse(uri->query);
-    if (qp->n > 1 || (is_unix && !qp->n) || (!is_unix && qp->n)) {
-        ret = -EINVAL;
-        goto out;
-    }
-
-    if (is_unix) {
-        if (uri->server || uri->port) {
-            ret = -EINVAL;
-            goto out;
-        }
-        if (strcmp(qp->p[0].name, "socket")) {
-            ret = -EINVAL;
-            goto out;
-        }
-        gconf->server = g_strdup(qp->p[0].value);
-    } else {
-        gconf->server = g_strdup(uri->server);
-        gconf->port = uri->port;
-    }
-
-out:
-    if (qp) {
-        query_params_free(qp);
-    }
-    uri_free(uri);
-    return ret;
-}
-
-static struct glfs *qemu_gluster_init(GlusterConf *gconf, const char *filename)
-{
-    struct glfs *glfs = NULL;
-    int ret;
-    int old_errno;
-
-    ret = qemu_gluster_parseuri(gconf, filename);
-    if (ret < 0) {
-        error_report("Usage: file=gluster[+transport]://[server[:port]]/"
-            "volname/image[?socket=...]");
-        errno = -ret;
-        goto out;
-    }
-
-    glfs = glfs_new(gconf->volname);
-    if (!glfs) {
-        goto out;
-    }
-
-    ret = glfs_set_volfile_server(glfs, gconf->transport, gconf->server,
-            gconf->port);
-    if (ret < 0) {
-        goto out;
-    }
-
-    /*
-     * TODO: Use GF_LOG_ERROR instead of hard code value of 4 here when
-     * GlusterFS makes GF_LOG_* macros available to libgfapi users.
-     */
-    ret = glfs_set_logging(glfs, "-", 4);
-    if (ret < 0) {
-        goto out;
-    }
-
-    ret = glfs_init(glfs);
-    if (ret) {
-        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;
-
-out:
-    if (glfs) {
-        old_errno = errno;
-        glfs_fini(glfs);
-        errno = old_errno;
-    }
-    return NULL;
-}
-
-static void qemu_gluster_complete_aio(GlusterAIOCB *acb, BDRVGlusterState *s)
-{
-    int ret;
-    bool *finished = acb->finished;
-    BlockDriverCompletionFunc *cb = acb->common.cb;
-    void *opaque = acb->common.opaque;
-
-    if (!acb->ret || acb->ret == acb->size) {
-        ret = 0; /* Success */
-    } else if (acb->ret < 0) {
-        ret = acb->ret; /* Read/Write failed */
-    } else {
-        ret = -EIO; /* Partial read/write - fail it */
-    }
-
-    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 */
-static QemuOptsList runtime_opts = {
-    .name = "gluster",
-    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
-    .desc = {
-        {
-            .name = "filename",
-            .type = QEMU_OPT_STRING,
-            .help = "URL to the gluster image",
-        },
-        { /* end of list */ }
-    },
-};
-
-static int qemu_gluster_open(BlockDriverState *bs,  QDict *options,
-                             int bdrv_flags)
-{
-    BDRVGlusterState *s = bs->opaque;
-    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_nofail(&runtime_opts);
-    qemu_opts_absorb_qdict(opts, options, &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);
-    if (!s->glfs) {
-        ret = -errno;
-        goto out;
-    }
-
-    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);
-    if (!ret) {
-        return ret;
-    }
-    if (s->fd) {
-        glfs_close(s->fd);
-    }
-    if (s->glfs) {
-        glfs_fini(s->glfs);
-    }
-    return ret;
-}
-
-static int qemu_gluster_create(const char *filename,
-        QEMUOptionParameter *options)
-{
-    struct glfs *glfs;
-    struct glfs_fd *fd;
-    int ret = 0;
-    int64_t total_size = 0;
-    GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
-
-    glfs = qemu_gluster_init(gconf, filename);
-    if (!glfs) {
-        ret = -errno;
-        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,
-        O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, S_IRUSR | S_IWUSR);
-    if (!fd) {
-        ret = -errno;
-    } else {
-        if (glfs_ftruncate(fd, total_size * BDRV_SECTOR_SIZE) != 0) {
-            ret = -errno;
-        }
-        if (glfs_close(fd) != 0) {
-            ret = -errno;
-        }
-    }
-out:
-    qemu_gluster_gconf_free(gconf);
-    if (glfs) {
-        glfs_fini(glfs);
-    }
-    return ret;
-}
-
-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;
-    BDRVGlusterState *s = bs->opaque;
-    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->finished = NULL;
-
-    if (write) {
-        ret = glfs_pwritev_async(s->fd, qiov->iov, qiov->niov, offset, 0,
-            &gluster_finish_aiocb, acb);
-    } else {
-        ret = glfs_preadv_async(s->fd, qiov->iov, qiov->niov, offset, 0,
-            &gluster_finish_aiocb, acb);
-    }
-
-    if (ret < 0) {
-        goto out;
-    }
-    return &acb->common;
-
-out:
-    s->qemu_aio_count--;
-    qemu_aio_release(acb);
-    return NULL;
-}
-
-static int qemu_gluster_truncate(BlockDriverState *bs, int64_t offset)
-{
-    int ret;
-    BDRVGlusterState *s = bs->opaque;
-
-    ret = glfs_ftruncate(s->fd, offset);
-    if (ret < 0) {
-        return -errno;
-    }
-
-    return 0;
-}
-
-static BlockDriverAIOCB *qemu_gluster_aio_readv(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque)
-{
-    return qemu_gluster_aio_rw(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
-}
-
-static BlockDriverAIOCB *qemu_gluster_aio_writev(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque)
-{
-    return qemu_gluster_aio_rw(bs, sector_num, qiov, nb_sectors, cb, opaque, 1);
-}
-
-static BlockDriverAIOCB *qemu_gluster_aio_flush(BlockDriverState *bs,
-        BlockDriverCompletionFunc *cb, void *opaque)
-{
-    int ret;
-    GlusterAIOCB *acb;
-    BDRVGlusterState *s = bs->opaque;
-
-    acb = qemu_aio_get(&gluster_aiocb_info, bs, cb, opaque);
-    acb->size = 0;
-    acb->ret = 0;
-    acb->finished = NULL;
-    s->qemu_aio_count++;
-
-    ret = glfs_fsync_async(s->fd, &gluster_finish_aiocb, acb);
-    if (ret < 0) {
-        goto out;
-    }
-    return &acb->common;
-
-out:
-    s->qemu_aio_count--;
-    qemu_aio_release(acb);
-    return NULL;
-}
-
-#ifdef CONFIG_GLUSTERFS_DISCARD
-static BlockDriverAIOCB *qemu_gluster_aio_discard(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, BlockDriverCompletionFunc *cb,
-        void *opaque)
-{
-    int ret;
-    GlusterAIOCB *acb;
-    BDRVGlusterState *s = bs->opaque;
-    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->finished = NULL;
-    s->qemu_aio_count++;
-
-    ret = glfs_discard_async(s->fd, offset, size, &gluster_finish_aiocb, acb);
-    if (ret < 0) {
-        goto out;
-    }
-    return &acb->common;
-
-out:
-    s->qemu_aio_count--;
-    qemu_aio_release(acb);
-    return NULL;
-}
-#endif
-
-static int64_t qemu_gluster_getlength(BlockDriverState *bs)
-{
-    BDRVGlusterState *s = bs->opaque;
-    int64_t ret;
-
-    ret = glfs_lseek(s->fd, 0, SEEK_END);
-    if (ret < 0) {
-        return -errno;
-    } else {
-        return ret;
-    }
-}
-
-static int64_t qemu_gluster_allocated_file_size(BlockDriverState *bs)
-{
-    BDRVGlusterState *s = bs->opaque;
-    struct stat st;
-    int ret;
-
-    ret = glfs_fstat(s->fd, &st);
-    if (ret < 0) {
-        return -errno;
-    } else {
-        return st.st_blocks * 512;
-    }
-}
-
-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;
-    }
-    glfs_fini(s->glfs);
-}
-
-static int qemu_gluster_has_zero_init(BlockDriverState *bs)
-{
-    /* GlusterFS volume could be backed by a block device */
-    return 0;
-}
-
-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_file_open               = qemu_gluster_open,
-    .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_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_aio_discard             = qemu_gluster_aio_discard,
-#endif
-    .create_options               = qemu_gluster_create_options,
-};
-
-static BlockDriver bdrv_gluster_tcp = {
-    .format_name                  = "gluster",
-    .protocol_name                = "gluster+tcp",
-    .instance_size                = sizeof(BDRVGlusterState),
-    .bdrv_file_open               = qemu_gluster_open,
-    .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_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_aio_discard             = qemu_gluster_aio_discard,
-#endif
-    .create_options               = qemu_gluster_create_options,
-};
-
-static BlockDriver bdrv_gluster_unix = {
-    .format_name                  = "gluster",
-    .protocol_name                = "gluster+unix",
-    .instance_size                = sizeof(BDRVGlusterState),
-    .bdrv_file_open               = qemu_gluster_open,
-    .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_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_aio_discard             = qemu_gluster_aio_discard,
-#endif
-    .create_options               = qemu_gluster_create_options,
-};
-
-static BlockDriver bdrv_gluster_rdma = {
-    .format_name                  = "gluster",
-    .protocol_name                = "gluster+rdma",
-    .instance_size                = sizeof(BDRVGlusterState),
-    .bdrv_file_open               = qemu_gluster_open,
-    .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_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_aio_discard             = qemu_gluster_aio_discard,
-#endif
-    .create_options               = qemu_gluster_create_options,
-};
-
-static void bdrv_gluster_init(void)
-{
-    bdrv_register(&bdrv_gluster_rdma);
-    bdrv_register(&bdrv_gluster_unix);
-    bdrv_register(&bdrv_gluster_tcp);
-    bdrv_register(&bdrv_gluster);
-}
-
-block_init(bdrv_gluster_init);

block/mirror.c

@@ -1,584 +0,0 @@
-/*
- * Image mirroring
- *
- * Copyright Red Hat, Inc. 2012
- *
- * Authors:
- *  Paolo Bonzini  <pbonzini@redhat.com>
- *
- * This work is licensed under the terms of the GNU LGPL, version 2 or later.
- * See the COPYING.LIB file in the top-level directory.
- *
- */
-
-#include "trace.h"
-#include "block/blockjob.h"
-#include "block/block_int.h"
-#include "qemu/ratelimit.h"
-#include "qemu/bitmap.h"
-
-#define SLICE_TIME    100000000ULL /* ns */
-#define MAX_IN_FLIGHT 16
-
-/* The mirroring buffer is a list of granularity-sized chunks.
- * Free chunks are organized in a list.
- */
-typedef struct MirrorBuffer {
-    QSIMPLEQ_ENTRY(MirrorBuffer) next;
-} MirrorBuffer;
-
-typedef struct MirrorBlockJob {
-    BlockJob common;
-    RateLimit limit;
-    BlockDriverState *target;
-    MirrorSyncMode mode;
-    BlockdevOnError on_source_error, on_target_error;
-    bool synced;
-    bool should_complete;
-    int64_t sector_num;
-    int64_t granularity;
-    size_t buf_size;
-    unsigned long *cow_bitmap;
-    HBitmapIter hbi;
-    uint8_t *buf;
-    QSIMPLEQ_HEAD(, MirrorBuffer) buf_free;
-    int buf_free_count;
-
-    unsigned long *in_flight_bitmap;
-    int in_flight;
-    int ret;
-} MirrorBlockJob;
-
-typedef struct MirrorOp {
-    MirrorBlockJob *s;
-    QEMUIOVector qiov;
-    int64_t sector_num;
-    int nb_sectors;
-} MirrorOp;
-
-static BlockErrorAction mirror_error_action(MirrorBlockJob *s, bool read,
-                                            int error)
-{
-    s->synced = false;
-    if (read) {
-        return block_job_error_action(&s->common, s->common.bs,
-                                      s->on_source_error, true, error);
-    } else {
-        return block_job_error_action(&s->common, s->target,
-                                      s->on_target_error, false, error);
-    }
-}
-
-static void mirror_iteration_done(MirrorOp *op, int ret)
-{
-    MirrorBlockJob *s = op->s;
-    struct iovec *iov;
-    int64_t chunk_num;
-    int i, nb_chunks, sectors_per_chunk;
-
-    trace_mirror_iteration_done(s, op->sector_num, op->nb_sectors, ret);
-
-    s->in_flight--;
-    iov = op->qiov.iov;
-    for (i = 0; i < op->qiov.niov; i++) {
-        MirrorBuffer *buf = (MirrorBuffer *) iov[i].iov_base;
-        QSIMPLEQ_INSERT_TAIL(&s->buf_free, buf, next);
-        s->buf_free_count++;
-    }
-
-    sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
-    chunk_num = op->sector_num / sectors_per_chunk;
-    nb_chunks = op->nb_sectors / sectors_per_chunk;
-    bitmap_clear(s->in_flight_bitmap, chunk_num, nb_chunks);
-    if (s->cow_bitmap && ret >= 0) {
-        bitmap_set(s->cow_bitmap, chunk_num, nb_chunks);
-    }
-
-    g_slice_free(MirrorOp, op);
-    qemu_coroutine_enter(s->common.co, NULL);
-}
-
-static void mirror_write_complete(void *opaque, int ret)
-{
-    MirrorOp *op = opaque;
-    MirrorBlockJob *s = op->s;
-    if (ret < 0) {
-        BlockDriverState *source = s->common.bs;
-        BlockErrorAction action;
-
-        bdrv_set_dirty(source, op->sector_num, op->nb_sectors);
-        action = mirror_error_action(s, false, -ret);
-        if (action == BDRV_ACTION_REPORT && s->ret >= 0) {
-            s->ret = ret;
-        }
-    }
-    mirror_iteration_done(op, ret);
-}
-
-static void mirror_read_complete(void *opaque, int ret)
-{
-    MirrorOp *op = opaque;
-    MirrorBlockJob *s = op->s;
-    if (ret < 0) {
-        BlockDriverState *source = s->common.bs;
-        BlockErrorAction action;
-
-        bdrv_set_dirty(source, op->sector_num, op->nb_sectors);
-        action = mirror_error_action(s, true, -ret);
-        if (action == BDRV_ACTION_REPORT && s->ret >= 0) {
-            s->ret = ret;
-        }
-
-        mirror_iteration_done(op, ret);
-        return;
-    }
-    bdrv_aio_writev(s->target, op->sector_num, &op->qiov, op->nb_sectors,
-                    mirror_write_complete, op);
-}
-
-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;
-    MirrorOp *op;
-
-    s->sector_num = hbitmap_iter_next(&s->hbi);
-    if (s->sector_num < 0) {
-        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));
-        assert(s->sector_num >= 0);
-    }
-
-    hbitmap_next_sector = s->sector_num;
-    sector_num = s->sector_num;
-    sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
-    end = s->common.len >> BDRV_SECTOR_BITS;
-
-    /* Extend the QEMUIOVector to include all adjacent blocks that will
-     * be copied in this operation.
-     *
-     * We have to do this if we have no backing file yet in the destination,
-     * and the cluster size is very large.  Then we need to do COW ourselves.
-     * The first time a cluster is copied, copy it entirely.  Note that,
-     * because both the granularity and the cluster size are powers of two,
-     * the number of sectors to copy cannot exceed one cluster.
-     *
-     * We also want to extend the QEMUIOVector to include more adjacent
-     * dirty blocks if possible, to limit the number of I/O operations and
-     * run efficiently even with a small granularity.
-     */
-    nb_chunks = 0;
-    nb_sectors = 0;
-    next_sector = sector_num;
-    next_chunk = sector_num / sectors_per_chunk;
-
-    /* Wait for I/O to this cluster (from a previous iteration) to be done.  */
-    while (test_bit(next_chunk, s->in_flight_bitmap)) {
-        trace_mirror_yield_in_flight(s, sector_num, s->in_flight);
-        qemu_coroutine_yield();
-    }
-
-    do {
-        int added_sectors, added_chunks;
-
-        if (!bdrv_get_dirty(source, next_sector) ||
-            test_bit(next_chunk, s->in_flight_bitmap)) {
-            assert(nb_sectors > 0);
-            break;
-        }
-
-        added_sectors = sectors_per_chunk;
-        if (s->cow_bitmap && !test_bit(next_chunk, s->cow_bitmap)) {
-            bdrv_round_to_clusters(s->target,
-                                   next_sector, added_sectors,
-                                   &next_sector, &added_sectors);
-
-            /* On the first iteration, the rounding may make us copy
-             * sectors before the first dirty one.
-             */
-            if (next_sector < sector_num) {
-                assert(nb_sectors == 0);
-                sector_num = next_sector;
-                next_chunk = next_sector / sectors_per_chunk;
-            }
-        }
-
-        added_sectors = MIN(added_sectors, end - (sector_num + nb_sectors));
-        added_chunks = (added_sectors + sectors_per_chunk - 1) / sectors_per_chunk;
-
-        /* When doing COW, it may happen that there is not enough space for
-         * a full cluster.  Wait if that is the case.
-         */
-        while (nb_chunks == 0 && s->buf_free_count < added_chunks) {
-            trace_mirror_yield_buf_busy(s, nb_chunks, s->in_flight);
-            qemu_coroutine_yield();
-        }
-        if (s->buf_free_count < nb_chunks + added_chunks) {
-            trace_mirror_break_buf_busy(s, nb_chunks, s->in_flight);
-            break;
-        }
-
-        /* We have enough free space to copy these sectors.  */
-        bitmap_set(s->in_flight_bitmap, next_chunk, added_chunks);
-
-        nb_sectors += added_sectors;
-        nb_chunks += added_chunks;
-        next_sector += added_sectors;
-        next_chunk += added_chunks;
-    } while (next_sector < end);
-
-    /* Allocate a MirrorOp that is used as an AIO callback.  */
-    op = g_slice_new(MirrorOp);
-    op->s = s;
-    op->sector_num = sector_num;
-    op->nb_sectors = nb_sectors;
-
-    /* Now make a QEMUIOVector taking enough granularity-sized chunks
-     * from s->buf_free.
-     */
-    qemu_iovec_init(&op->qiov, nb_chunks);
-    next_sector = sector_num;
-    while (nb_chunks-- > 0) {
-        MirrorBuffer *buf = QSIMPLEQ_FIRST(&s->buf_free);
-        QSIMPLEQ_REMOVE_HEAD(&s->buf_free, next);
-        s->buf_free_count--;
-        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, next_sector)) {
-            hbitmap_next_sector = hbitmap_iter_next(&s->hbi);
-        }
-
-        next_sector += sectors_per_chunk;
-    }
-
-    bdrv_reset_dirty(source, sector_num, nb_sectors);
-
-    /* Copy the dirty cluster.  */
-    s->in_flight++;
-    trace_mirror_one_iteration(s, sector_num, nb_sectors);
-    bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors,
-                   mirror_read_complete, op);
-}
-
-static void mirror_free_init(MirrorBlockJob *s)
-{
-    int granularity = s->granularity;
-    size_t buf_size = s->buf_size;
-    uint8_t *buf = s->buf;
-
-    assert(s->buf_free_count == 0);
-    QSIMPLEQ_INIT(&s->buf_free);
-    while (buf_size != 0) {
-        MirrorBuffer *cur = (MirrorBuffer *)buf;
-        QSIMPLEQ_INSERT_TAIL(&s->buf_free, cur, next);
-        s->buf_free_count++;
-        buf_size -= granularity;
-        buf += granularity;
-    }
-}
-
-static void mirror_drain(MirrorBlockJob *s)
-{
-    while (s->in_flight > 0) {
-        qemu_coroutine_yield();
-    }
-}
-
-static void coroutine_fn mirror_run(void *opaque)
-{
-    MirrorBlockJob *s = opaque;
-    BlockDriverState *bs = s->common.bs;
-    int64_t sector_num, end, sectors_per_chunk, length;
-    uint64_t last_pause_ns;
-    BlockDriverInfo bdi;
-    char backing_filename[1024];
-    int ret = 0;
-    int n;
-
-    if (block_job_is_cancelled(&s->common)) {
-        goto immediate_exit;
-    }
-
-    s->common.len = bdrv_getlength(bs);
-    if (s->common.len <= 0) {
-        block_job_completed(&s->common, s->common.len);
-        return;
-    }
-
-    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
-     * the destination do COW.  Instead, we copy sectors around the
-     * dirty data if needed.  We need a bitmap to do that.
-     */
-    bdrv_get_backing_filename(s->target, backing_filename,
-                              sizeof(backing_filename));
-    if (backing_filename[0] && !s->target->backing_hd) {
-        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);
-        }
-    }
-
-    end = s->common.len >> BDRV_SECTOR_BITS;
-    s->buf = qemu_blockalign(bs, s->buf_size);
-    sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
-    mirror_free_init(s);
-
-    if (s->mode != MIRROR_SYNC_MODE_NONE) {
-        /* First part, loop on the sectors and initialize the dirty bitmap.  */
-        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_co_is_allocated_above(bs, base,
-                                             sector_num, next - sector_num, &n);
-
-            if (ret < 0) {
-                goto immediate_exit;
-            }
-
-            assert(n > 0);
-            if (ret == 1) {
-                bdrv_set_dirty(bs, sector_num, n);
-                sector_num = next;
-            } else {
-                sector_num += n;
-            }
-        }
-    }
-
-    bdrv_dirty_iter_init(bs, &s->hbi);
-    last_pause_ns = qemu_get_clock_ns(rt_clock);
-    for (;;) {
-        uint64_t delay_ns;
-        int64_t cnt;
-        bool should_complete;
-
-        if (s->ret < 0) {
-            ret = s->ret;
-            goto immediate_exit;
-        }
-
-        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_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)) {
-                trace_mirror_yield(s, s->in_flight, s->buf_free_count, cnt);
-                qemu_coroutine_yield();
-                continue;
-            } else if (cnt != 0) {
-                mirror_iteration(s);
-                continue;
-            }
-        }
-
-        should_complete = false;
-        if (s->in_flight == 0 && cnt == 0) {
-            trace_mirror_before_flush(s);
-            ret = bdrv_flush(s->target);
-            if (ret < 0) {
-                if (mirror_error_action(s, false, -ret) == BDRV_ACTION_REPORT) {
-                    goto immediate_exit;
-                }
-            } else {
-                /* We're out of the streaming phase.  From now on, if the job
-                 * is cancelled we will actually complete all pending I/O and
-                 * report completion.  This way, block-job-cancel will leave
-                 * the target in a consistent state.
-                 */
-                s->common.offset = end * BDRV_SECTOR_SIZE;
-                if (!s->synced) {
-                    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);
-            }
-        }
-
-        if (cnt == 0 && should_complete) {
-            /* The dirty bitmap is not updated while operations are pending.
-             * If we're about to exit, wait for pending operations before
-             * calling bdrv_get_dirty_count(bs), or we may exit while the
-             * source has dirty data to copy!
-             *
-             * Note that I/O can be submitted by the guest while
-             * mirror_populate runs.
-             */
-            trace_mirror_before_drain(s, cnt);
-            bdrv_drain_all();
-            cnt = bdrv_get_dirty_count(bs);
-        }
-
-        ret = 0;
-        trace_mirror_before_sleep(s, cnt, s->synced);
-        if (!s->synced) {
-            /* Publish progress */
-            s->common.offset = (end - cnt) * BDRV_SECTOR_SIZE;
-
-            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, rt_clock, delay_ns);
-        } else if (cnt == 0) {
-            /* The two disks are in sync.  Exit and report successful
-             * completion.
-             */
-            assert(QLIST_EMPTY(&bs->tracked_requests));
-            s->common.cancelled = false;
-            break;
-        }
-        last_pause_ns = qemu_get_clock_ns(rt_clock);
-    }
-
-immediate_exit:
-    if (s->in_flight > 0) {
-        /* We get here only if something went wrong.  Either the job failed,
-         * or it was cancelled prematurely so that we do not guarantee that
-         * the target is a copy of the source.
-         */
-        assert(ret < 0 || (!s->synced && block_job_is_cancelled(&s->common)));
-        mirror_drain(s);
-    }
-
-    assert(s->in_flight == 0);
-    qemu_vfree(s->buf);
-    g_free(s->cow_bitmap);
-    g_free(s->in_flight_bitmap);
-    bdrv_set_dirty_tracking(bs, 0);
-    bdrv_iostatus_disable(s->target);
-    if (s->should_complete && ret == 0) {
-        if (bdrv_get_flags(s->target) != bdrv_get_flags(s->common.bs)) {
-            bdrv_reopen(s->target, bdrv_get_flags(s->common.bs), NULL);
-        }
-        bdrv_swap(s->target, s->common.bs);
-    }
-    bdrv_close(s->target);
-    bdrv_delete(s->target);
-    block_job_completed(&s->common, ret);
-}
-
-static void mirror_set_speed(BlockJob *job, int64_t speed, Error **errp)
-{
-    MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
-
-    if (speed < 0) {
-        error_set(errp, QERR_INVALID_PARAMETER, "speed");
-        return;
-    }
-    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
-}
-
-static void mirror_iostatus_reset(BlockJob *job)
-{
-    MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
-
-    bdrv_iostatus_reset(s->target);
-}
-
-static void mirror_complete(BlockJob *job, Error **errp)
-{
-    MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
-    int ret;
-
-    ret = bdrv_open_backing_file(s->target, NULL);
-    if (ret < 0) {
-        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) {
-        error_set(errp, QERR_BLOCK_JOB_NOT_READY, job->bs->device_name);
-        return;
-    }
-
-    s->should_complete = true;
-    block_job_resume(job);
-}
-
-static const BlockJobType mirror_job_type = {
-    .instance_size = sizeof(MirrorBlockJob),
-    .job_type      = "mirror",
-    .set_speed     = mirror_set_speed,
-    .iostatus_reset= mirror_iostatus_reset,
-    .complete      = mirror_complete,
-};
-
-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;
-
-    if (granularity == 0) {
-        /* Choose the default granularity based on the target file's cluster
-         * size, clamped between 4k and 64k.  */
-        BlockDriverInfo bdi;
-        if (bdrv_get_info(target, &bdi) >= 0 && bdi.cluster_size != 0) {
-            granularity = MAX(4096, bdi.cluster_size);
-            granularity = MIN(65536, granularity);
-        } else {
-            granularity = 65536;
-        }
-    }
-
-    assert ((granularity & (granularity - 1)) == 0);
-
-    if ((on_source_error == BLOCKDEV_ON_ERROR_STOP ||
-         on_source_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        !bdrv_iostatus_is_enabled(bs)) {
-        error_set(errp, QERR_INVALID_PARAMETER, "on-source-error");
-        return;
-    }
-
-    s = block_job_create(&mirror_job_type, bs, speed, cb, opaque, errp);
-    if (!s) {
-        return;
-    }
-
-    s->on_source_error = on_source_error;
-    s->on_target_error = on_target_error;
-    s->target = target;
-    s->mode = mode;
-    s->granularity = granularity;
-    s->buf_size = MAX(buf_size, granularity);
-
-    bdrv_set_dirty_tracking(bs, granularity);
-    bdrv_set_enable_write_cache(s->target, true);
-    bdrv_set_on_error(s->target, on_target_error, on_target_error);
-    bdrv_iostatus_enable(s->target);
-    s->common.co = qemu_coroutine_create(mirror_run);
-    trace_mirror_start(bs, s, s->common.co, opaque);
-    qemu_coroutine_enter(s->common.co, s);
-}

block/nbd.c

@@ -27,13 +27,10 @@
  */
 
 #include "qemu-common.h"
-#include "block/nbd.h"
-#include "qemu/uri.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
-#include "qemu/sockets.h"
-#include "qapi/qmp/qjson.h"
-#include "qapi/qmp/qint.h"
+#include "nbd.h"
+#include "block_int.h"
+#include "module.h"
+#include "qemu_socket.h"
 
 #include <sys/types.h>
 #include <unistd.h>
@@ -58,6 +55,7 @@ typedef struct BDRVNBDState {
     uint32_t nbdflags;
     off_t size;
     size_t blocksize;
+    char *export_name; /* An NBD server may export several devices */
 
     CoMutex send_mutex;
     CoMutex free_sema;
@@ -67,112 +65,19 @@ typedef struct BDRVNBDState {
     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 */
+    /* If it begins with  '/', this is a UNIX domain socket. Otherwise,
+     * it's a string of the form <hostname|ip4|\[ip6\]>:port
+     */
+    char *host_spec;
 } BDRVNBDState;
 
-static int nbd_parse_uri(const char *filename, QDict *options)
-{
-    URI *uri;
-    const char *p;
-    QueryParams *qp = NULL;
-    int ret = 0;
-    bool is_unix;
-
-    uri = uri_parse(filename);
-    if (!uri) {
-        return -EINVAL;
-    }
-
-    /* transport */
-    if (!strcmp(uri->scheme, "nbd")) {
-        is_unix = false;
-    } else if (!strcmp(uri->scheme, "nbd+tcp")) {
-        is_unix = false;
-    } else if (!strcmp(uri->scheme, "nbd+unix")) {
-        is_unix = true;
-    } else {
-        ret = -EINVAL;
-        goto out;
-    }
-
-    p = uri->path ? uri->path : "/";
-    p += strspn(p, "/");
-    if (p[0]) {
-        qdict_put(options, "export", qstring_from_str(p));
-    }
-
-    qp = query_params_parse(uri->query);
-    if (qp->n > 1 || (is_unix && !qp->n) || (!is_unix && qp->n)) {
-        ret = -EINVAL;
-        goto out;
-    }
-
-    if (is_unix) {
-        /* nbd+unix:///export?socket=path */
-        if (uri->server || uri->port || strcmp(qp->p[0].name, "socket")) {
-            ret = -EINVAL;
-            goto out;
-        }
-        qdict_put(options, "path", qstring_from_str(qp->p[0].value));
-    } else {
-        QString *host;
-        /* nbd[+tcp]://host[:port]/export */
-        if (!uri->server) {
-            ret = -EINVAL;
-            goto out;
-        }
-
-        /* strip braces from literal IPv6 address */
-        if (uri->server[0] == '[') {
-            host = qstring_from_substr(uri->server, 1,
-                                       strlen(uri->server) - 2);
-        } else {
-            host = qstring_from_str(uri->server);
-        }
-
-        qdict_put(options, "host", host);
-        if (uri->port) {
-            char* port_str = g_strdup_printf("%d", uri->port);
-            qdict_put(options, "port", qstring_from_str(port_str));
-            g_free(port_str);
-        }
-    }
-
-out:
-    if (qp) {
-        query_params_free(qp);
-    }
-    uri_free(uri);
-    return ret;
-}
-
-static void nbd_parse_filename(const char *filename, QDict *options,
-                               Error **errp)
+static int nbd_config(BDRVNBDState *s, const char *filename, int flags)
 {
     char *file;
     char *export_name;
     const char *host_spec;
     const char *unixpath;
-
-    if (qdict_haskey(options, "host")
-        || qdict_haskey(options, "port")
-        || qdict_haskey(options, "path"))
-    {
-        error_setg(errp, "host/port/path and a file name may not be specified "
-                         "at the same time");
-        return;
-    }
-
-    if (strstr(filename, "://")) {
-        int ret = nbd_parse_uri(filename, options);
-        if (ret < 0) {
-            error_setg(errp, "No valid URL specified");
-        }
-        return;
-    }
+    int err = -EINVAL;
 
     file = g_strdup(filename);
 
@@ -183,79 +88,35 @@ static void nbd_parse_filename(const char *filename, QDict *options,
         }
         export_name[0] = 0; /* truncate 'file' */
         export_name += strlen(EN_OPTSTR);
-
-        qdict_put(options, "export", qstring_from_str(export_name));
+        s->export_name = g_strdup(export_name);
     }
 
     /* extract the host_spec - fail if it's not nbd:... */
     if (!strstart(file, "nbd:", &host_spec)) {
-        error_setg(errp, "File name string for NBD must start with 'nbd:'");
-        goto out;
-    }
-
-    if (!*host_spec) {
         goto out;
     }
 
     /* are we a UNIX or TCP socket? */
     if (strstart(host_spec, "unix:", &unixpath)) {
-        qdict_put(options, "path", qstring_from_str(unixpath));
-    } else {
-        InetSocketAddress *addr = NULL;
-
-        addr = inet_parse(host_spec, errp);
-        if (error_is_set(errp)) {
+        if (unixpath[0] != '/') { /* We demand  an absolute path*/
             goto out;
         }
-
-        qdict_put(options, "host", qstring_from_str(addr->host));
-        qdict_put(options, "port", qstring_from_str(addr->port));
-        qapi_free_InetSocketAddress(addr);
+        s->host_spec = g_strdup(unixpath);
+    } else {
+        s->host_spec = g_strdup(host_spec);
     }
 
+    err = 0;
+
 out:
     g_free(file);
+    if (err != 0) {
+        g_free(s->export_name);
+        g_free(s->host_spec);
+    }
+    return err;
 }
 
-static int nbd_config(BDRVNBDState *s, QDict *options)
-{
-    Error *local_err = NULL;
-
-    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;
-        }
-        s->is_unix = true;
-    } else if (qdict_haskey(options, "host")) {
-        s->is_unix = false;
-    } else {
-        return -EINVAL;
-    }
-
-    s->socket_opts = qemu_opts_create_nofail(&socket_optslist);
-
-    qemu_opts_absorb_qdict(s->socket_opts, options, &local_err);
-    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);
-    }
-
-    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;
@@ -335,7 +196,7 @@ static void nbd_restart_write(void *opaque)
 }
 
 static int nbd_co_send_request(BDRVNBDState *s, struct nbd_request *request,
-                               QEMUIOVector *qiov, int offset)
+                               struct iovec *iov, int offset)
 {
     int rc, ret;
 
@@ -343,23 +204,12 @@ static int nbd_co_send_request(BDRVNBDState *s, struct nbd_request *request,
     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 && iov) {
+        ret = qemu_co_sendv(s->sock, iov, request->len, offset);
+        if (ret != request->len) {
+            return -EIO;
         }
-        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);
@@ -370,7 +220,7 @@ static int nbd_co_send_request(BDRVNBDState *s, struct nbd_request *request,
 
 static void nbd_co_receive_reply(BDRVNBDState *s, struct nbd_request *request,
                                  struct nbd_reply *reply,
-                                 QEMUIOVector *qiov, int offset)
+                                 struct iovec *iov, int offset)
 {
     int ret;
 
@@ -381,9 +231,8 @@ static void nbd_co_receive_reply(BDRVNBDState *s, struct nbd_request *request,
     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 (iov && reply->error == 0) {
+            ret = qemu_co_recvv(s->sock, iov, request->len, offset);
             if (ret != request->len) {
                 reply->error = EIO;
             }
@@ -411,13 +260,10 @@ static int nbd_establish_connection(BlockDriverState *bs)
     off_t size;
     size_t blocksize;
 
-    if (s->is_unix) {
-        sock = unix_socket_outgoing(qemu_opt_get(s->socket_opts, "path"));
+    if (s->host_spec[0] == '/') {
+        sock = unix_socket_outgoing(s->host_spec);
     } else {
-        sock = tcp_socket_outgoing_opts(s->socket_opts);
-        if (sock >= 0) {
-            socket_set_nodelay(sock);
-        }
+        sock = tcp_socket_outgoing_spec(s->host_spec);
     }
 
     /* Failed to establish connection */
@@ -437,7 +283,7 @@ static int nbd_establish_connection(BlockDriverState *bs)
 
     /* Now that we're connected, set the socket to be non-blocking and
      * kick the reply mechanism.  */
-    qemu_set_nonblock(sock);
+    socket_set_nonblock(sock);
     qemu_aio_set_fd_handler(sock, nbd_reply_ready, NULL,
                             nbd_have_request, s);
 
@@ -463,7 +309,7 @@ static void nbd_teardown_connection(BlockDriverState *bs)
     closesocket(s->sock);
 }
 
-static int nbd_open(BlockDriverState *bs, QDict *options, int flags)
+static int nbd_open(BlockDriverState *bs, const char* filename, int flags)
 {
     BDRVNBDState *s = bs->opaque;
     int result;
@@ -472,7 +318,7 @@ static int nbd_open(BlockDriverState *bs, QDict *options, int flags)
     qemu_co_mutex_init(&s->free_sema);
 
     /* Pop the config into our state object. Exit if invalid. */
-    result = nbd_config(s, options);
+    result = nbd_config(s, filename, flags);
     if (result != 0) {
         return result;
     }
@@ -503,7 +349,7 @@ static int nbd_co_readv_1(BlockDriverState *bs, int64_t sector_num,
     if (ret < 0) {
         reply.error = -ret;
     } else {
-        nbd_co_receive_reply(s, &request, &reply, qiov, offset);
+        nbd_co_receive_reply(s, &request, &reply, qiov->iov, offset);
     }
     nbd_coroutine_end(s, &request);
     return -reply.error;
@@ -528,7 +374,7 @@ static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num,
     request.len = nb_sectors * 512;
 
     nbd_coroutine_start(s, &request);
-    ret = nbd_co_send_request(s, &request, qiov, offset);
+    ret = nbd_co_send_request(s, &request, qiov->iov, offset);
     if (ret < 0) {
         reply.error = -ret;
     } else {
@@ -618,7 +464,7 @@ static int nbd_co_discard(BlockDriverState *bs, int64_t sector_num,
         return 0;
     }
     request.type = NBD_CMD_TRIM;
-    request.from = sector_num * 512;
+    request.from = sector_num * 512;;
     request.len = nb_sectors * 512;
 
     nbd_coroutine_start(s, &request);
@@ -636,7 +482,7 @@ static void nbd_close(BlockDriverState *bs)
 {
     BDRVNBDState *s = bs->opaque;
     g_free(s->export_name);
-    qemu_opts_del(s->socket_opts);
+    g_free(s->host_spec);
 
     nbd_teardown_connection(bs);
 }
@@ -650,51 +496,20 @@ static int64_t nbd_getlength(BlockDriverState *bs)
 
 static BlockDriver bdrv_nbd = {
     .format_name         = "nbd",
+    .instance_size       = sizeof(BDRVNBDState),
+    .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,
     .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,
-};
-
-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,
 };
 
 static void bdrv_nbd_init(void)
 {
     bdrv_register(&bdrv_nbd);
-    bdrv_register(&bdrv_nbd_tcp);
-    bdrv_register(&bdrv_nbd_unix);
 }
 
 block_init(bdrv_nbd_init);

block/parallels.c

@@ -24,8 +24,8 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
 
 /**************************************************************/
 
@@ -68,23 +68,19 @@ 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)
+static int parallels_open(BlockDriverState *bs, int flags)
 {
     BDRVParallelsState *s = bs->opaque;
     int i;
     struct parallels_header ph;
-    int ret;
 
     bs->read_only = 1; // no write support yet
 
-    ret = bdrv_pread(bs->file, 0, &ph, sizeof(ph));
-    if (ret < 0) {
+    if (bdrv_pread(bs->file, 0, &ph, sizeof(ph)) != sizeof(ph))
         goto fail;
-    }
 
     if (memcmp(ph.magic, HEADER_MAGIC, 16) ||
-        (le32_to_cpu(ph.version) != HEADER_VERSION)) {
-        ret = -EMEDIUMTYPE;
+	(le32_to_cpu(ph.version) != HEADER_VERSION)) {
         goto fail;
     }
 
@@ -94,21 +90,18 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags)
 
     s->catalog_size = le32_to_cpu(ph.catalog_entries);
     s->catalog_bitmap = g_malloc(s->catalog_size * 4);
-
-    ret = bdrv_pread(bs->file, 64, s->catalog_bitmap, s->catalog_size * 4);
-    if (ret < 0) {
-        goto fail;
-    }
-
+    if (bdrv_pread(bs->file, 64, s->catalog_bitmap, s->catalog_size * 4) !=
+	s->catalog_size * 4)
+	goto fail;
     for (i = 0; i < s->catalog_size; i++)
 	le32_to_cpus(&s->catalog_bitmap[i]);
 
     qemu_co_mutex_init(&s->lock);
     return 0;
-
 fail:
-    g_free(s->catalog_bitmap);
-    return ret;
+    if (s->catalog_bitmap)
+	g_free(s->catalog_bitmap);
+    return -1;
 }
 
 static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)

block/qapi.c

@@ -1,470 +0,0 @@
-/*
- * Block layer qmp and info dump related functions
- *
- * Copyright (c) 2003-2008 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 "block/qapi.h"
-#include "block/block_int.h"
-#include "qmp-commands.h"
-
-/*
- * Returns 0 on success, with *p_list either set to describe snapshot
- * information, or NULL because there are no snapshots.  Returns -errno on
- * error, with *p_list untouched.
- */
-int bdrv_query_snapshot_info_list(BlockDriverState *bs,
-                                  SnapshotInfoList **p_list,
-                                  Error **errp)
-{
-    int i, sn_count;
-    QEMUSnapshotInfo *sn_tab = NULL;
-    SnapshotInfoList *info_list, *cur_item = NULL, *head = NULL;
-    SnapshotInfo *info;
-
-    sn_count = bdrv_snapshot_list(bs, &sn_tab);
-    if (sn_count < 0) {
-        const char *dev = bdrv_get_device_name(bs);
-        switch (sn_count) {
-        case -ENOMEDIUM:
-            error_setg(errp, "Device '%s' is not inserted", dev);
-            break;
-        case -ENOTSUP:
-            error_setg(errp,
-                       "Device '%s' does not support internal snapshots",
-                       dev);
-            break;
-        default:
-            error_setg_errno(errp, -sn_count,
-                             "Can't list snapshots of device '%s'", dev);
-            break;
-        }
-        return sn_count;
-    }
-
-    for (i = 0; i < sn_count; i++) {
-        info = g_new0(SnapshotInfo, 1);
-        info->id            = g_strdup(sn_tab[i].id_str);
-        info->name          = g_strdup(sn_tab[i].name);
-        info->vm_state_size = sn_tab[i].vm_state_size;
-        info->date_sec      = sn_tab[i].date_sec;
-        info->date_nsec     = sn_tab[i].date_nsec;
-        info->vm_clock_sec  = sn_tab[i].vm_clock_nsec / 1000000000;
-        info->vm_clock_nsec = sn_tab[i].vm_clock_nsec % 1000000000;
-
-        info_list = g_new0(SnapshotInfoList, 1);
-        info_list->value = info;
-
-        /* XXX: waiting for the qapi to support qemu-queue.h types */
-        if (!cur_item) {
-            head = cur_item = info_list;
-        } else {
-            cur_item->next = info_list;
-            cur_item = info_list;
-        }
-
-    }
-
-    g_free(sn_tab);
-    *p_list = head;
-    return 0;
-}
-
-/**
- * bdrv_query_image_info:
- * @bs: block device to examine
- * @p_info: location to store image information
- * @errp: location to store error information
- *
- * Store "flat" image information in @p_info.
- *
- * "Flat" means it does *not* query backing image information,
- * i.e. (*pinfo)->has_backing_image will be set to false and
- * (*pinfo)->backing_image to NULL even when the image does in fact have
- * a backing image.
- *
- * @p_info will be set only on success. On error, store error in @errp.
- */
-void bdrv_query_image_info(BlockDriverState *bs,
-                           ImageInfo **p_info,
-                           Error **errp)
-{
-    uint64_t total_sectors;
-    const char *backing_filename;
-    char backing_filename2[1024];
-    BlockDriverInfo bdi;
-    int ret;
-    Error *err = NULL;
-    ImageInfo *info = g_new0(ImageInfo, 1);
-
-    bdrv_get_geometry(bs, &total_sectors);
-
-    info->filename        = g_strdup(bs->filename);
-    info->format          = g_strdup(bdrv_get_format_name(bs));
-    info->virtual_size    = total_sectors * 512;
-    info->actual_size     = bdrv_get_allocated_file_size(bs);
-    info->has_actual_size = info->actual_size >= 0;
-    if (bdrv_is_encrypted(bs)) {
-        info->encrypted = true;
-        info->has_encrypted = true;
-    }
-    if (bdrv_get_info(bs, &bdi) >= 0) {
-        if (bdi.cluster_size != 0) {
-            info->cluster_size = bdi.cluster_size;
-            info->has_cluster_size = true;
-        }
-        info->dirty_flag = bdi.is_dirty;
-        info->has_dirty_flag = true;
-    }
-    backing_filename = bs->backing_file;
-    if (backing_filename[0] != '\0') {
-        info->backing_filename = g_strdup(backing_filename);
-        info->has_backing_filename = true;
-        bdrv_get_full_backing_filename(bs, backing_filename2,
-                                       sizeof(backing_filename2));
-
-        if (strcmp(backing_filename, backing_filename2) != 0) {
-            info->full_backing_filename =
-                        g_strdup(backing_filename2);
-            info->has_full_backing_filename = true;
-        }
-
-        if (bs->backing_format[0]) {
-            info->backing_filename_format = g_strdup(bs->backing_format);
-            info->has_backing_filename_format = true;
-        }
-    }
-
-    ret = bdrv_query_snapshot_info_list(bs, &info->snapshots, &err);
-    switch (ret) {
-    case 0:
-        if (info->snapshots) {
-            info->has_snapshots = true;
-        }
-        break;
-    /* recoverable error */
-    case -ENOMEDIUM:
-    case -ENOTSUP:
-        error_free(err);
-        break;
-    default:
-        error_propagate(errp, err);
-        qapi_free_ImageInfo(info);
-        return;
-    }
-
-    *p_info = info;
-}
-
-/* @p_info will be set only on success. */
-void bdrv_query_info(BlockDriverState *bs,
-                     BlockInfo **p_info,
-                     Error **errp)
-{
-    BlockInfo *info = g_malloc0(sizeof(*info));
-    BlockDriverState *bs0;
-    ImageInfo **p_image_info;
-    Error *local_err = NULL;
-    info->device = g_strdup(bs->device_name);
-    info->type = g_strdup("unknown");
-    info->locked = bdrv_dev_is_medium_locked(bs);
-    info->removable = bdrv_dev_has_removable_media(bs);
-
-    if (bdrv_dev_has_removable_media(bs)) {
-        info->has_tray_open = true;
-        info->tray_open = bdrv_dev_is_tray_open(bs);
-    }
-
-    if (bdrv_iostatus_is_enabled(bs)) {
-        info->has_io_status = true;
-        info->io_status = bs->iostatus;
-    }
-
-    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 = 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 (error_is_set(&local_err)) {
-                error_propagate(errp, local_err);
-                goto err;
-            }
-            if (bs0->drv && bs0->backing_hd) {
-                bs0 = bs0->backing_hd;
-                (*p_image_info)->has_backing_image = true;
-                p_image_info = &((*p_image_info)->backing_image);
-            } else {
-                break;
-            }
-        }
-    }
-
-    *p_info = info;
-    return;
-
- err:
-    qapi_free_BlockInfo(info);
-}
-
-BlockStats *bdrv_query_stats(const BlockDriverState *bs)
-{
-    BlockStats *s;
-
-    s = g_malloc0(sizeof(*s));
-
-    if (bs->device_name[0]) {
-        s->has_device = true;
-        s->device = g_strdup(bs->device_name);
-    }
-
-    s->stats = g_malloc0(sizeof(*s->stats));
-    s->stats->rd_bytes = bs->nr_bytes[BDRV_ACCT_READ];
-    s->stats->wr_bytes = bs->nr_bytes[BDRV_ACCT_WRITE];
-    s->stats->rd_operations = bs->nr_ops[BDRV_ACCT_READ];
-    s->stats->wr_operations = bs->nr_ops[BDRV_ACCT_WRITE];
-    s->stats->wr_highest_offset = bs->wr_highest_sector * BDRV_SECTOR_SIZE;
-    s->stats->flush_operations = bs->nr_ops[BDRV_ACCT_FLUSH];
-    s->stats->wr_total_time_ns = bs->total_time_ns[BDRV_ACCT_WRITE];
-    s->stats->rd_total_time_ns = bs->total_time_ns[BDRV_ACCT_READ];
-    s->stats->flush_total_time_ns = bs->total_time_ns[BDRV_ACCT_FLUSH];
-
-    if (bs->file) {
-        s->has_parent = true;
-        s->parent = bdrv_query_stats(bs->file);
-    }
-
-    return s;
-}
-
-BlockInfoList *qmp_query_block(Error **errp)
-{
-    BlockInfoList *head = NULL, **p_next = &head;
-    BlockDriverState *bs = NULL;
-    Error *local_err = NULL;
-
-     while ((bs = bdrv_next(bs))) {
-        BlockInfoList *info = g_malloc0(sizeof(*info));
-        bdrv_query_info(bs, &info->value, &local_err);
-        if (error_is_set(&local_err)) {
-            error_propagate(errp, local_err);
-            goto err;
-        }
-
-        *p_next = info;
-        p_next = &info->next;
-    }
-
-    return head;
-
- err:
-    qapi_free_BlockInfoList(head);
-    return NULL;
-}
-
-BlockStatsList *qmp_query_blockstats(Error **errp)
-{
-    BlockStatsList *head = NULL, **p_next = &head;
-    BlockDriverState *bs = NULL;
-
-     while ((bs = bdrv_next(bs))) {
-        BlockStatsList *info = g_malloc0(sizeof(*info));
-        info->value = bdrv_query_stats(bs);
-
-        *p_next = info;
-        p_next = &info->next;
-    }
-
-    return head;
-}
-
-#define NB_SUFFIXES 4
-
-static char *get_human_readable_size(char *buf, int buf_size, int64_t size)
-{
-    static const char suffixes[NB_SUFFIXES] = "KMGT";
-    int64_t base;
-    int i;
-
-    if (size <= 999) {
-        snprintf(buf, buf_size, "%" PRId64, size);
-    } else {
-        base = 1024;
-        for (i = 0; i < NB_SUFFIXES; i++) {
-            if (size < (10 * base)) {
-                snprintf(buf, buf_size, "%0.1f%c",
-                         (double)size / base,
-                         suffixes[i]);
-                break;
-            } else if (size < (1000 * base) || i == (NB_SUFFIXES - 1)) {
-                snprintf(buf, buf_size, "%" PRId64 "%c",
-                         ((size + (base >> 1)) / base),
-                         suffixes[i]);
-                break;
-            }
-            base = base * 1024;
-        }
-    }
-    return buf;
-}
-
-void bdrv_snapshot_dump(fprintf_function func_fprintf, void *f,
-                        QEMUSnapshotInfo *sn)
-{
-    char buf1[128], date_buf[128], clock_buf[128];
-    struct tm tm;
-    time_t ti;
-    int64_t secs;
-
-    if (!sn) {
-        func_fprintf(f,
-                     "%-10s%-20s%7s%20s%15s",
-                     "ID", "TAG", "VM SIZE", "DATE", "VM CLOCK");
-    } else {
-        ti = sn->date_sec;
-        localtime_r(&ti, &tm);
-        strftime(date_buf, sizeof(date_buf),
-                 "%Y-%m-%d %H:%M:%S", &tm);
-        secs = sn->vm_clock_nsec / 1000000000;
-        snprintf(clock_buf, sizeof(clock_buf),
-                 "%02d:%02d:%02d.%03d",
-                 (int)(secs / 3600),
-                 (int)((secs / 60) % 60),
-                 (int)(secs % 60),
-                 (int)((sn->vm_clock_nsec / 1000000) % 1000));
-        func_fprintf(f,
-                     "%-10s%-20s%7s%20s%15s",
-                     sn->id_str, sn->name,
-                     get_human_readable_size(buf1, sizeof(buf1),
-                                             sn->vm_state_size),
-                     date_buf,
-                     clock_buf);
-    }
-}
-
-void bdrv_image_info_dump(fprintf_function func_fprintf, void *f,
-                          ImageInfo *info)
-{
-    char size_buf[128], dsize_buf[128];
-    if (!info->has_actual_size) {
-        snprintf(dsize_buf, sizeof(dsize_buf), "unavailable");
-    } else {
-        get_human_readable_size(dsize_buf, sizeof(dsize_buf),
-                                info->actual_size);
-    }
-    get_human_readable_size(size_buf, sizeof(size_buf), info->virtual_size);
-    func_fprintf(f,
-                 "image: %s\n"
-                 "file format: %s\n"
-                 "virtual size: %s (%" PRId64 " bytes)\n"
-                 "disk size: %s\n",
-                 info->filename, info->format, size_buf,
-                 info->virtual_size,
-                 dsize_buf);
-
-    if (info->has_encrypted && info->encrypted) {
-        func_fprintf(f, "encrypted: yes\n");
-    }
-
-    if (info->has_cluster_size) {
-        func_fprintf(f, "cluster_size: %" PRId64 "\n",
-                       info->cluster_size);
-    }
-
-    if (info->has_dirty_flag && info->dirty_flag) {
-        func_fprintf(f, "cleanly shut down: no\n");
-    }
-
-    if (info->has_backing_filename) {
-        func_fprintf(f, "backing file: %s", info->backing_filename);
-        if (info->has_full_backing_filename) {
-            func_fprintf(f, " (actual path: %s)", info->full_backing_filename);
-        }
-        func_fprintf(f, "\n");
-        if (info->has_backing_filename_format) {
-            func_fprintf(f, "backing file format: %s\n",
-                         info->backing_filename_format);
-        }
-    }
-
-    if (info->has_snapshots) {
-        SnapshotInfoList *elem;
-
-        func_fprintf(f, "Snapshot list:\n");
-        bdrv_snapshot_dump(func_fprintf, f, NULL);
-        func_fprintf(f, "\n");
-
-        /* Ideally bdrv_snapshot_dump() would operate on SnapshotInfoList but
-         * we convert to the block layer's native QEMUSnapshotInfo for now.
-         */
-        for (elem = info->snapshots; elem; elem = elem->next) {
-            QEMUSnapshotInfo sn = {
-                .vm_state_size = elem->value->vm_state_size,
-                .date_sec = elem->value->date_sec,
-                .date_nsec = elem->value->date_nsec,
-                .vm_clock_nsec = elem->value->vm_clock_sec * 1000000000ULL +
-                                 elem->value->vm_clock_nsec,
-            };
-
-            pstrcpy(sn.id_str, sizeof(sn.id_str), elem->value->id);
-            pstrcpy(sn.name, sizeof(sn.name), elem->value->name);
-            bdrv_snapshot_dump(func_fprintf, f, &sn);
-            func_fprintf(f, "\n");
-        }
-    }
-}

block/qcow.c

@@ -22,11 +22,11 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
 #include <zlib.h>
-#include "qemu/aes.h"
-#include "migration/migration.h"
+#include "aes.h"
+#include "migration.h"
 
 /**************************************************************/
 /* QEMU COW block driver with compression and encryption support */
@@ -92,7 +92,7 @@ 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)
+static int qcow_open(BlockDriverState *bs, int flags)
 {
     BDRVQcowState *s = bs->opaque;
     int len, i, shift, ret;
@@ -112,7 +112,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags)
     be64_to_cpus(&header.l1_table_offset);
 
     if (header.magic != QCOW_MAGIC) {
-        ret = -EMEDIUMTYPE;
+        ret = -EINVAL;
         goto fail;
     }
     if (header.version != QCOW_VERSION) {
@@ -197,15 +197,6 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags)
     return ret;
 }
 
-
-/* We have nothing to do for QCOW reopen, stubs just return
- * success */
-static int qcow_reopen_prepare(BDRVReopenState *state,
-                               BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
-}
-
 static int qcow_set_key(BlockDriverState *bs, const char *key)
 {
     BDRVQcowState *s = bs->opaque;
@@ -549,7 +540,7 @@ done:
     qemu_co_mutex_unlock(&s->lock);
 
     if (qiov->niov > 1) {
-        qemu_iovec_from_buf(qiov, 0, orig_buf, qiov->size);
+        qemu_iovec_from_buffer(qiov, orig_buf, qiov->size);
         qemu_vfree(orig_buf);
     }
 
@@ -578,7 +569,7 @@ static coroutine_fn int qcow_co_writev(BlockDriverState *bs, int64_t sector_num,
 
     if (qiov->niov > 1) {
         buf = orig_buf = qemu_blockalign(bs, qiov->size);
-        qemu_iovec_to_buf(qiov, 0, buf, qiov->size);
+        qemu_iovec_to_buffer(qiov, buf);
     } else {
         orig_buf = NULL;
         buf = (uint8_t *)qiov->iov->iov_base;
@@ -679,7 +670,7 @@ static int qcow_create(const char *filename, QEMUOptionParameter *options)
         return ret;
     }
 
-    ret = bdrv_file_open(&qcow_bs, filename, NULL, BDRV_O_RDWR);
+    ret = bdrv_file_open(&qcow_bs, filename, BDRV_O_RDWR);
     if (ret < 0) {
         return ret;
     }
@@ -787,21 +778,8 @@ static int qcow_write_compressed(BlockDriverState *bs, int64_t sector_num,
     uint8_t *out_buf;
     uint64_t cluster_offset;
 
-    if (nb_sectors != s->cluster_sectors) {
-        ret = -EINVAL;
-
-        /* Zero-pad last write if image size is not cluster aligned */
-        if (sector_num + nb_sectors == bs->total_sectors &&
-            nb_sectors < s->cluster_sectors) {
-            uint8_t *pad_buf = qemu_blockalign(bs, s->cluster_size);
-            memset(pad_buf, 0, s->cluster_size);
-            memcpy(pad_buf, buf, nb_sectors * BDRV_SECTOR_SIZE);
-            ret = qcow_write_compressed(bs, sector_num,
-                                        pad_buf, s->cluster_sectors);
-            qemu_vfree(pad_buf);
-        }
-        return ret;
-    }
+    if (nb_sectors != s->cluster_sectors)
+        return -EINVAL;
 
     out_buf = g_malloc(s->cluster_size + (s->cluster_size / 1000) + 128);
 
@@ -890,9 +868,7 @@ 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_has_zero_init     = bdrv_has_zero_init_1,
 
     .bdrv_co_readv          = qcow_co_readv,
     .bdrv_co_writev         = qcow_co_writev,

block/qcow2-cache.c

@@ -22,7 +22,7 @@
  * THE SOFTWARE.
  */
 
-#include "block/block_int.h"
+#include "block_int.h"
 #include "qemu-common.h"
 #include "qcow2.h"
 #include "trace.h"
@@ -40,9 +40,11 @@ struct Qcow2Cache {
     struct Qcow2Cache*      depends;
     int                     size;
     bool                    depends_on_flush;
+    bool                    writethrough;
 };
 
-Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables)
+Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables,
+    bool writethrough)
 {
     BDRVQcowState *s = bs->opaque;
     Qcow2Cache *c;
@@ -51,6 +53,7 @@ Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables)
     c = g_malloc0(sizeof(*c));
     c->size = num_tables;
     c->entries = g_malloc0(sizeof(*c->entries) * num_tables);
+    c->writethrough = writethrough;
 
     for (i = 0; i < c->size; i++) {
         c->entries[i].table = qemu_blockalign(bs, s->cluster_size);
@@ -304,7 +307,12 @@ found:
     *table = NULL;
 
     assert(c->entries[i].ref >= 0);
-    return 0;
+
+    if (c->writethrough) {
+        return qcow2_cache_entry_flush(bs, c, i);
+    } else {
+        return 0;
+    }
 }
 
 void qcow2_cache_entry_mark_dirty(Qcow2Cache *c, void *table)
@@ -321,3 +329,16 @@ void qcow2_cache_entry_mark_dirty(Qcow2Cache *c, void *table)
 found:
     c->entries[i].dirty = true;
 }
+
+bool qcow2_cache_set_writethrough(BlockDriverState *bs, Qcow2Cache *c,
+    bool enable)
+{
+    bool old = c->writethrough;
+
+    if (!old && enable) {
+        qcow2_cache_flush(bs, c);
+    }
+
+    c->writethrough = enable;
+    return old;
+}

block/qcow2-cluster.c

@@ -25,17 +25,16 @@
 #include <zlib.h>
 
 #include "qemu-common.h"
-#include "block/block_int.h"
+#include "block_int.h"
 #include "block/qcow2.h"
 #include "trace.h"
 
-int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
-                        bool exact_size)
+int qcow2_grow_l1_table(BlockDriverState *bs, int min_size, bool exact_size)
 {
     BDRVQcowState *s = bs->opaque;
-    int new_l1_size2, ret, i;
+    int new_l1_size, new_l1_size2, ret, i;
     uint64_t *new_l1_table;
-    int64_t new_l1_table_offset, new_l1_size;
+    int64_t new_l1_table_offset;
     uint8_t data[12];
 
     if (min_size <= s->l1_size)
@@ -54,13 +53,8 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
         }
     }
 
-    if (new_l1_size > INT_MAX) {
-        return -EFBIG;
-    }
-
 #ifdef DEBUG_ALLOC2
-    fprintf(stderr, "grow l1_table from %d to %" PRId64 "\n",
-            s->l1_size, new_l1_size);
+    fprintf(stderr, "grow l1_table from %d to %d\n", s->l1_size, new_l1_size);
 #endif
 
     new_l1_size2 = sizeof(uint64_t) * new_l1_size;
@@ -98,16 +92,14 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
         goto fail;
     }
     g_free(s->l1_table);
-    qcow2_free_clusters(bs, s->l1_table_offset, s->l1_size * sizeof(uint64_t),
-                        QCOW2_DISCARD_OTHER);
+    qcow2_free_clusters(bs, s->l1_table_offset, s->l1_size * sizeof(uint64_t));
     s->l1_table_offset = new_l1_table_offset;
     s->l1_table = new_l1_table;
     s->l1_size = new_l1_size;
     return 0;
  fail:
     g_free(new_l1_table);
-    qcow2_free_clusters(bs, new_l1_table_offset, new_l1_size2,
-                        QCOW2_DISCARD_OTHER);
+    qcow2_free_clusters(bs, new_l1_table_offset, new_l1_size2);
     return ret;
 }
 
@@ -399,8 +391,8 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
     int *num, uint64_t *cluster_offset)
 {
     BDRVQcowState *s = bs->opaque;
-    unsigned int l2_index;
-    uint64_t l1_index, l2_offset, *l2_table;
+    unsigned int l1_index, l2_index;
+    uint64_t l2_offset, *l2_table;
     int l1_bits, c;
     unsigned int index_in_cluster, nb_clusters;
     uint64_t nb_available, nb_needed;
@@ -462,9 +454,6 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
         *cluster_offset &= L2E_COMPRESSED_OFFSET_SIZE_MASK;
         break;
     case QCOW2_CLUSTER_ZERO:
-        if (s->qcow_version < 3) {
-            return -EIO;
-        }
         c = count_contiguous_clusters(nb_clusters, s->cluster_size,
                 &l2_table[l2_index], 0,
                 QCOW_OFLAG_COMPRESSED | QCOW_OFLAG_ZERO);
@@ -515,8 +504,8 @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset,
                              int *new_l2_index)
 {
     BDRVQcowState *s = bs->opaque;
-    unsigned int l2_index;
-    uint64_t l1_index, l2_offset;
+    unsigned int l1_index, l2_index;
+    uint64_t l2_offset;
     uint64_t *l2_table = NULL;
     int ret;
 
@@ -530,7 +519,6 @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset,
         }
     }
 
-    assert(l1_index < s->l1_size);
     l2_offset = s->l1_table[l1_index] & L1E_OFFSET_MASK;
 
     /* seek the l2 table of the given l2 offset */
@@ -550,9 +538,9 @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset,
 
         /* Then decrease the refcount of the old table */
         if (l2_offset) {
-            qcow2_free_clusters(bs, l2_offset, s->l2_size * sizeof(uint64_t),
-                                QCOW2_DISCARD_OTHER);
+            qcow2_free_clusters(bs, l2_offset, s->l2_size * sizeof(uint64_t));
         }
+        l2_offset = s->l1_table[l1_index] & L1E_OFFSET_MASK;
     }
 
     /* find the cluster offset for the given disk offset */
@@ -628,67 +616,55 @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
     return cluster_offset;
 }
 
-static int perform_cow(BlockDriverState *bs, QCowL2Meta *m, Qcow2COWRegion *r)
-{
-    BDRVQcowState *s = bs->opaque;
-    int ret;
-
-    if (r->nb_sectors == 0) {
-        return 0;
-    }
-
-    qemu_co_mutex_unlock(&s->lock);
-    ret = copy_sectors(bs, m->offset / BDRV_SECTOR_SIZE, m->alloc_offset,
-                       r->offset / BDRV_SECTOR_SIZE,
-                       r->offset / BDRV_SECTOR_SIZE + r->nb_sectors);
-    qemu_co_mutex_lock(&s->lock);
-
-    if (ret < 0) {
-        return ret;
-    }
-
-    /*
-     * Before we update the L2 table to actually point to the new cluster, we
-     * need to be sure that the refcounts have been increased and COW was
-     * handled.
-     */
-    qcow2_cache_depends_on_flush(s->l2_table_cache);
-
-    return 0;
-}
-
 int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
 {
     BDRVQcowState *s = bs->opaque;
     int i, j = 0, l2_index, ret;
-    uint64_t *old_cluster, *l2_table;
+    uint64_t *old_cluster, start_sect, *l2_table;
     uint64_t cluster_offset = m->alloc_offset;
+    bool cow = false;
 
     trace_qcow2_cluster_link_l2(qemu_coroutine_self(), m->nb_clusters);
-    assert(m->nb_clusters > 0);
+
+    if (m->nb_clusters == 0)
+        return 0;
 
     old_cluster = g_malloc(m->nb_clusters * sizeof(uint64_t));
 
     /* copy content of unmodified sectors */
-    ret = perform_cow(bs, m, &m->cow_start);
-    if (ret < 0) {
-        goto err;
+    start_sect = (m->offset & ~(s->cluster_size - 1)) >> 9;
+    if (m->n_start) {
+        cow = true;
+        qemu_co_mutex_unlock(&s->lock);
+        ret = copy_sectors(bs, start_sect, cluster_offset, 0, m->n_start);
+        qemu_co_mutex_lock(&s->lock);
+        if (ret < 0)
+            goto err;
     }
 
-    ret = perform_cow(bs, m, &m->cow_end);
-    if (ret < 0) {
-        goto err;
+    if (m->nb_available & (s->cluster_sectors - 1)) {
+        uint64_t end = m->nb_available & ~(uint64_t)(s->cluster_sectors - 1);
+        cow = true;
+        qemu_co_mutex_unlock(&s->lock);
+        ret = copy_sectors(bs, start_sect + end, cluster_offset + (end << 9),
+                m->nb_available - end, s->cluster_sectors);
+        qemu_co_mutex_lock(&s->lock);
+        if (ret < 0)
+            goto err;
     }
 
-    /* Update L2 table. */
-    if (s->use_lazy_refcounts) {
-        qcow2_mark_dirty(bs);
-    }
-    if (qcow2_need_accurate_refcounts(s)) {
-        qcow2_cache_set_dependency(bs, s->l2_table_cache,
-                                   s->refcount_block_cache);
+    /*
+     * Update L2 table.
+     *
+     * Before we update the L2 table to actually point to the new cluster, we
+     * need to be sure that the refcounts have been increased and COW was
+     * handled.
+     */
+    if (cow) {
+        qcow2_cache_depends_on_flush(s->l2_table_cache);
     }
 
+    qcow2_cache_set_dependency(bs, s->l2_table_cache, s->refcount_block_cache);
     ret = get_cluster_table(bs, m->offset, &l2_table, &l2_index);
     if (ret < 0) {
         goto err;
@@ -718,14 +694,10 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
     /*
      * If this was a COW, we need to decrease the refcount of the old cluster.
      * Also flush bs->file to get the right order for L2 and refcount update.
-     *
-     * Don't discard clusters that reach a refcount of 0 (e.g. compressed
-     * clusters), the next write will reuse them anyway.
      */
     if (j != 0) {
         for (i = 0; i < j; i++) {
-            qcow2_free_any_clusters(bs, be64_to_cpu(old_cluster[i]), 1,
-                                    QCOW2_DISCARD_NEVER);
+            qcow2_free_any_clusters(bs, be64_to_cpu(old_cluster[i]), 1);
         }
     }
 
@@ -769,175 +741,6 @@ out:
     return i;
 }
 
-/*
- * Check if there already is an AIO write request in flight which allocates
- * the same cluster. In this case we need to wait until the previous
- * request has completed and updated the L2 table accordingly.
- *
- * Returns:
- *   0       if there was no dependency. *cur_bytes indicates the number of
- *           bytes from guest_offset that can be read before the next
- *           dependency must be processed (or the request is complete)
- *
- *   -EAGAIN if we had to wait for another request, previously gathered
- *           information on cluster allocation may be invalid now. The caller
- *           must start over anyway, so consider *cur_bytes undefined.
- */
-static int handle_dependencies(BlockDriverState *bs, uint64_t guest_offset,
-    uint64_t *cur_bytes, QCowL2Meta **m)
-{
-    BDRVQcowState *s = bs->opaque;
-    QCowL2Meta *old_alloc;
-    uint64_t bytes = *cur_bytes;
-
-    QLIST_FOREACH(old_alloc, &s->cluster_allocs, next_in_flight) {
-
-        uint64_t start = guest_offset;
-        uint64_t end = start + bytes;
-        uint64_t old_start = l2meta_cow_start(old_alloc);
-        uint64_t old_end = l2meta_cow_end(old_alloc);
-
-        if (end <= old_start || start >= old_end) {
-            /* No intersection */
-        } else {
-            if (start < old_start) {
-                /* Stop at the start of a running allocation */
-                bytes = old_start - start;
-            } else {
-                bytes = 0;
-            }
-
-            /* Stop if already an l2meta exists. After yielding, it wouldn't
-             * be valid any more, so we'd have to clean up the old L2Metas
-             * and deal with requests depending on them before starting to
-             * gather new ones. Not worth the trouble. */
-            if (bytes == 0 && *m) {
-                *cur_bytes = 0;
-                return 0;
-            }
-
-            if (bytes == 0) {
-                /* Wait for the dependency to complete. We need to recheck
-                 * the free/allocated clusters when we continue. */
-                qemu_co_mutex_unlock(&s->lock);
-                qemu_co_queue_wait(&old_alloc->dependent_requests);
-                qemu_co_mutex_lock(&s->lock);
-                return -EAGAIN;
-            }
-        }
-    }
-
-    /* Make sure that existing clusters and new allocations are only used up to
-     * the next dependency if we shortened the request above */
-    *cur_bytes = bytes;
-
-    return 0;
-}
-
-/*
- * Checks how many already allocated clusters that don't require a copy on
- * write there are at the given guest_offset (up to *bytes). If
- * *host_offset is not zero, only physically contiguous clusters beginning at
- * this host offset are counted.
- *
- * Note that guest_offset may not be cluster aligned. In this case, the
- * returned *host_offset points to exact byte referenced by guest_offset and
- * therefore isn't cluster aligned as well.
- *
- * Returns:
- *   0:     if no allocated clusters are available at the given offset.
- *          *bytes is normally unchanged. It is set to 0 if the cluster
- *          is allocated and doesn't need COW, but doesn't have the right
- *          physical offset.
- *
- *   1:     if allocated clusters that don't require a COW are available at
- *          the requested offset. *bytes may have decreased and describes
- *          the length of the area that can be written to.
- *
- *  -errno: in error cases
- */
-static int handle_copied(BlockDriverState *bs, uint64_t guest_offset,
-    uint64_t *host_offset, uint64_t *bytes, QCowL2Meta **m)
-{
-    BDRVQcowState *s = bs->opaque;
-    int l2_index;
-    uint64_t cluster_offset;
-    uint64_t *l2_table;
-    unsigned int nb_clusters;
-    unsigned int keep_clusters;
-    int ret, pret;
-
-    trace_qcow2_handle_copied(qemu_coroutine_self(), guest_offset, *host_offset,
-                              *bytes);
-
-    assert(*host_offset == 0 ||    offset_into_cluster(s, guest_offset)
-                                == offset_into_cluster(s, *host_offset));
-
-    /*
-     * Calculate the number of clusters to look for. We stop at L2 table
-     * boundaries to keep things simple.
-     */
-    nb_clusters =
-        size_to_clusters(s, offset_into_cluster(s, guest_offset) + *bytes);
-
-    l2_index = offset_to_l2_index(s, guest_offset);
-    nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
-
-    /* Find L2 entry for the first involved cluster */
-    ret = get_cluster_table(bs, guest_offset, &l2_table, &l2_index);
-    if (ret < 0) {
-        return ret;
-    }
-
-    cluster_offset = be64_to_cpu(l2_table[l2_index]);
-
-    /* Check how many clusters are already allocated and don't need COW */
-    if (qcow2_get_cluster_type(cluster_offset) == QCOW2_CLUSTER_NORMAL
-        && (cluster_offset & QCOW_OFLAG_COPIED))
-    {
-        /* If a specific host_offset is required, check it */
-        bool offset_matches =
-            (cluster_offset & L2E_OFFSET_MASK) == *host_offset;
-
-        if (*host_offset != 0 && !offset_matches) {
-            *bytes = 0;
-            ret = 0;
-            goto out;
-        }
-
-        /* We keep all QCOW_OFLAG_COPIED clusters */
-        keep_clusters =
-            count_contiguous_clusters(nb_clusters, s->cluster_size,
-                                      &l2_table[l2_index], 0,
-                                      QCOW_OFLAG_COPIED | QCOW_OFLAG_ZERO);
-        assert(keep_clusters <= nb_clusters);
-
-        *bytes = MIN(*bytes,
-                 keep_clusters * s->cluster_size
-                 - offset_into_cluster(s, guest_offset));
-
-        ret = 1;
-    } else {
-        ret = 0;
-    }
-
-    /* Cleanup */
-out:
-    pret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
-    if (pret < 0) {
-        return pret;
-    }
-
-    /* Only return a host offset if we actually made progress. Otherwise we
-     * would make requirements for handle_alloc() that it can't fulfill */
-    if (ret) {
-        *host_offset = (cluster_offset & L2E_OFFSET_MASK)
-                     + offset_into_cluster(s, guest_offset);
-    }
-
-    return ret;
-}
-
 /*
  * Allocates new clusters for the given guest_offset.
  *
@@ -961,10 +764,48 @@ static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset,
     uint64_t *host_offset, unsigned int *nb_clusters)
 {
     BDRVQcowState *s = bs->opaque;
+    QCowL2Meta *old_alloc;
 
     trace_qcow2_do_alloc_clusters_offset(qemu_coroutine_self(), guest_offset,
                                          *host_offset, *nb_clusters);
 
+    /*
+     * Check if there already is an AIO write request in flight which allocates
+     * the same cluster. In this case we need to wait until the previous
+     * request has completed and updated the L2 table accordingly.
+     */
+    QLIST_FOREACH(old_alloc, &s->cluster_allocs, next_in_flight) {
+
+        uint64_t start = guest_offset >> s->cluster_bits;
+        uint64_t end = start + *nb_clusters;
+        uint64_t old_start = old_alloc->offset >> s->cluster_bits;
+        uint64_t old_end = old_start + old_alloc->nb_clusters;
+
+        if (end < old_start || start > old_end) {
+            /* No intersection */
+        } else {
+            if (start < old_start) {
+                /* Stop at the start of a running allocation */
+                *nb_clusters = old_start - start;
+            } else {
+                *nb_clusters = 0;
+            }
+
+            if (*nb_clusters == 0) {
+                /* Wait for the dependency to complete. We need to recheck
+                 * the free/allocated clusters when we continue. */
+                qemu_co_mutex_unlock(&s->lock);
+                qemu_co_queue_wait(&old_alloc->dependent_requests);
+                qemu_co_mutex_lock(&s->lock);
+                return -EAGAIN;
+            }
+        }
+    }
+
+    if (!*nb_clusters) {
+        abort();
+    }
+
     /* Allocate new clusters */
     trace_qcow2_cluster_alloc_phys(qemu_coroutine_self());
     if (*host_offset == 0) {
@@ -985,151 +826,6 @@ static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset,
     }
 }
 
-/*
- * Allocates new clusters for an area that either is yet unallocated or needs a
- * copy on write. If *host_offset is non-zero, clusters are only allocated if
- * the new allocation can match the specified host offset.
- *
- * Note that guest_offset may not be cluster aligned. In this case, the
- * returned *host_offset points to exact byte referenced by guest_offset and
- * therefore isn't cluster aligned as well.
- *
- * Returns:
- *   0:     if no clusters could be allocated. *bytes is set to 0,
- *          *host_offset is left unchanged.
- *
- *   1:     if new clusters were allocated. *bytes may be decreased if the
- *          new allocation doesn't cover all of the requested area.
- *          *host_offset is updated to contain the host offset of the first
- *          newly allocated cluster.
- *
- *  -errno: in error cases
- */
-static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset,
-    uint64_t *host_offset, uint64_t *bytes, QCowL2Meta **m)
-{
-    BDRVQcowState *s = bs->opaque;
-    int l2_index;
-    uint64_t *l2_table;
-    uint64_t entry;
-    unsigned int nb_clusters;
-    int ret;
-
-    uint64_t alloc_cluster_offset;
-
-    trace_qcow2_handle_alloc(qemu_coroutine_self(), guest_offset, *host_offset,
-                             *bytes);
-    assert(*bytes > 0);
-
-    /*
-     * Calculate the number of clusters to look for. We stop at L2 table
-     * boundaries to keep things simple.
-     */
-    nb_clusters =
-        size_to_clusters(s, offset_into_cluster(s, guest_offset) + *bytes);
-
-    l2_index = offset_to_l2_index(s, guest_offset);
-    nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
-
-    /* Find L2 entry for the first involved cluster */
-    ret = get_cluster_table(bs, guest_offset, &l2_table, &l2_index);
-    if (ret < 0) {
-        return ret;
-    }
-
-    entry = be64_to_cpu(l2_table[l2_index]);
-
-    /* For the moment, overwrite compressed clusters one by one */
-    if (entry & QCOW_OFLAG_COMPRESSED) {
-        nb_clusters = 1;
-    } else {
-        nb_clusters = count_cow_clusters(s, nb_clusters, l2_table, l2_index);
-    }
-
-    /* This function is only called when there were no non-COW clusters, so if
-     * we can't find any unallocated or COW clusters either, something is
-     * wrong with our code. */
-    assert(nb_clusters > 0);
-
-    ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
-    if (ret < 0) {
-        return ret;
-    }
-
-    /* Allocate, if necessary at a given offset in the image file */
-    alloc_cluster_offset = start_of_cluster(s, *host_offset);
-    ret = do_alloc_cluster_offset(bs, guest_offset, &alloc_cluster_offset,
-                                  &nb_clusters);
-    if (ret < 0) {
-        goto fail;
-    }
-
-    /* Can't extend contiguous allocation */
-    if (nb_clusters == 0) {
-        *bytes = 0;
-        return 0;
-    }
-
-    /*
-     * Save info needed for meta data update.
-     *
-     * requested_sectors: Number of sectors from the start of the first
-     * newly allocated cluster to the end of the (possibly shortened
-     * before) write request.
-     *
-     * avail_sectors: Number of sectors from the start of the first
-     * newly allocated to the end of the last newly allocated cluster.
-     *
-     * nb_sectors: The number of sectors from the start of the first
-     * newly allocated cluster to the end of the area that the write
-     * request actually writes to (excluding COW at the end)
-     */
-    int requested_sectors =
-        (*bytes + offset_into_cluster(s, guest_offset))
-        >> BDRV_SECTOR_BITS;
-    int avail_sectors = nb_clusters
-                        << (s->cluster_bits - BDRV_SECTOR_BITS);
-    int alloc_n_start = offset_into_cluster(s, guest_offset)
-                        >> BDRV_SECTOR_BITS;
-    int nb_sectors = MIN(requested_sectors, avail_sectors);
-    QCowL2Meta *old_m = *m;
-
-    *m = g_malloc0(sizeof(**m));
-
-    **m = (QCowL2Meta) {
-        .next           = old_m,
-
-        .alloc_offset   = alloc_cluster_offset,
-        .offset         = start_of_cluster(s, guest_offset),
-        .nb_clusters    = nb_clusters,
-        .nb_available   = nb_sectors,
-
-        .cow_start = {
-            .offset     = 0,
-            .nb_sectors = alloc_n_start,
-        },
-        .cow_end = {
-            .offset     = nb_sectors * BDRV_SECTOR_SIZE,
-            .nb_sectors = avail_sectors - nb_sectors,
-        },
-    };
-    qemu_co_queue_init(&(*m)->dependent_requests);
-    QLIST_INSERT_HEAD(&s->cluster_allocs, *m, next_in_flight);
-
-    *host_offset = alloc_cluster_offset + offset_into_cluster(s, guest_offset);
-    *bytes = MIN(*bytes, (nb_sectors * BDRV_SECTOR_SIZE)
-                         - offset_into_cluster(s, guest_offset));
-    assert(*bytes != 0);
-
-    return 1;
-
-fail:
-    if (*m && (*m)->nb_clusters > 0) {
-        QLIST_REMOVE(*m, next_in_flight);
-    }
-    return ret;
-}
-
 /*
  * alloc_cluster_offset
  *
@@ -1150,113 +846,143 @@ fail:
  * Return 0 on success and -errno in error cases
  */
 int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
-    int n_start, int n_end, int *num, uint64_t *host_offset, QCowL2Meta **m)
+    int n_start, int n_end, int *num, QCowL2Meta *m)
 {
     BDRVQcowState *s = bs->opaque;
-    uint64_t start, remaining;
+    int l2_index, ret, sectors;
+    uint64_t *l2_table;
+    unsigned int nb_clusters, keep_clusters;
     uint64_t cluster_offset;
-    uint64_t cur_bytes;
-    int ret;
 
     trace_qcow2_alloc_clusters_offset(qemu_coroutine_self(), offset,
                                       n_start, n_end);
 
-    assert(n_start * BDRV_SECTOR_SIZE == offset_into_cluster(s, offset));
-    offset = start_of_cluster(s, offset);
-
+    /* Find L2 entry for the first involved cluster */
 again:
-    start = offset + (n_start << BDRV_SECTOR_BITS);
-    remaining = (n_end - n_start) << BDRV_SECTOR_BITS;
-    cluster_offset = 0;
-    *host_offset = 0;
-    cur_bytes = 0;
-    *m = NULL;
+    ret = get_cluster_table(bs, offset, &l2_table, &l2_index);
+    if (ret < 0) {
+        return ret;
+    }
 
-    while (true) {
+    /*
+     * Calculate the number of clusters to look for. We stop at L2 table
+     * boundaries to keep things simple.
+     */
+    nb_clusters = MIN(size_to_clusters(s, n_end << BDRV_SECTOR_BITS),
+                      s->l2_size - l2_index);
 
-        if (!*host_offset) {
-            *host_offset = start_of_cluster(s, cluster_offset);
-        }
+    cluster_offset = be64_to_cpu(l2_table[l2_index]);
 
-        assert(remaining >= cur_bytes);
+    /*
+     * Check how many clusters are already allocated and don't need COW, and how
+     * many need a new allocation.
+     */
+    if (qcow2_get_cluster_type(cluster_offset) == QCOW2_CLUSTER_NORMAL
+        && (cluster_offset & QCOW_OFLAG_COPIED))
+    {
+        /* We keep all QCOW_OFLAG_COPIED clusters */
+        keep_clusters =
+            count_contiguous_clusters(nb_clusters, s->cluster_size,
+                                      &l2_table[l2_index], 0,
+                                      QCOW_OFLAG_COPIED | QCOW_OFLAG_ZERO);
+        assert(keep_clusters <= nb_clusters);
+        nb_clusters -= keep_clusters;
+    } else {
+        keep_clusters = 0;
+        cluster_offset = 0;
+    }
 
-        start           += cur_bytes;
-        remaining       -= cur_bytes;
-        cluster_offset  += cur_bytes;
-
-        if (remaining == 0) {
-            break;
-        }
-
-        cur_bytes = remaining;
-
-        /*
-         * Now start gathering as many contiguous clusters as possible:
-         *
-         * 1. Check for overlaps with in-flight allocations
-         *
-         *      a) Overlap not in the first cluster -> shorten this request and
-         *         let the caller handle the rest in its next loop iteration.
-         *
-         *      b) Real overlaps of two requests. Yield and restart the search
-         *         for contiguous clusters (the situation could have changed
-         *         while we were sleeping)
-         *
-         *      c) TODO: Request starts in the same cluster as the in-flight
-         *         allocation ends. Shorten the COW of the in-fight allocation,
-         *         set cluster_offset to write to the same cluster and set up
-         *         the right synchronisation between the in-flight request and
-         *         the new one.
-         */
-        ret = handle_dependencies(bs, start, &cur_bytes, m);
-        if (ret == -EAGAIN) {
-            /* Currently handle_dependencies() doesn't yield if we already had
-             * an allocation. If it did, we would have to clean up the L2Meta
-             * structs before starting over. */
-            assert(*m == NULL);
-            goto again;
-        } else if (ret < 0) {
-            return ret;
-        } else if (cur_bytes == 0) {
-            break;
+    if (nb_clusters > 0) {
+        /* For the moment, overwrite compressed clusters one by one */
+        uint64_t entry = be64_to_cpu(l2_table[l2_index + keep_clusters]);
+        if (entry & QCOW_OFLAG_COMPRESSED) {
+            nb_clusters = 1;
         } else {
-            /* handle_dependencies() may have decreased cur_bytes (shortened
-             * the allocations below) so that the next dependency is processed
-             * correctly during the next loop iteration. */
-        }
-
-        /*
-         * 2. Count contiguous COPIED clusters.
-         */
-        ret = handle_copied(bs, start, &cluster_offset, &cur_bytes, m);
-        if (ret < 0) {
-            return ret;
-        } else if (ret) {
-            continue;
-        } else if (cur_bytes == 0) {
-            break;
-        }
-
-        /*
-         * 3. If the request still hasn't completed, allocate new clusters,
-         *    considering any cluster_offset of steps 1c or 2.
-         */
-        ret = handle_alloc(bs, start, &cluster_offset, &cur_bytes, m);
-        if (ret < 0) {
-            return ret;
-        } else if (ret) {
-            continue;
-        } else {
-            assert(cur_bytes == 0);
-            break;
+            nb_clusters = count_cow_clusters(s, nb_clusters, l2_table,
+                                             l2_index + keep_clusters);
         }
     }
 
-    *num = (n_end - n_start) - (remaining >> BDRV_SECTOR_BITS);
-    assert(*num > 0);
-    assert(*host_offset != 0);
+    cluster_offset &= L2E_OFFSET_MASK;
+
+    /*
+     * The L2 table isn't used any more after this. As long as the cache works
+     * synchronously, it's important to release it before calling
+     * do_alloc_cluster_offset, which may yield if we need to wait for another
+     * request to complete. If we still had the reference, we could use up the
+     * whole cache with sleeping requests.
+     */
+    ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+    if (ret < 0) {
+        return ret;
+    }
+
+    /* If there is something left to allocate, do that now */
+    *m = (QCowL2Meta) {
+        .cluster_offset     = cluster_offset,
+        .nb_clusters        = 0,
+    };
+    qemu_co_queue_init(&m->dependent_requests);
+
+    if (nb_clusters > 0) {
+        uint64_t alloc_offset;
+        uint64_t alloc_cluster_offset;
+        uint64_t keep_bytes = keep_clusters * s->cluster_size;
+
+        /* Calculate start and size of allocation */
+        alloc_offset = offset + keep_bytes;
+
+        if (keep_clusters == 0) {
+            alloc_cluster_offset = 0;
+        } else {
+            alloc_cluster_offset = cluster_offset + keep_bytes;
+        }
+
+        /* Allocate, if necessary at a given offset in the image file */
+        ret = do_alloc_cluster_offset(bs, alloc_offset, &alloc_cluster_offset,
+                                      &nb_clusters);
+        if (ret == -EAGAIN) {
+            goto again;
+        } else if (ret < 0) {
+            goto fail;
+        }
+
+        /* save info needed for meta data update */
+        if (nb_clusters > 0) {
+            int requested_sectors = n_end - keep_clusters * s->cluster_sectors;
+            int avail_sectors = (keep_clusters + nb_clusters)
+                                << (s->cluster_bits - BDRV_SECTOR_BITS);
+
+            *m = (QCowL2Meta) {
+                .cluster_offset = keep_clusters == 0 ?
+                                  alloc_cluster_offset : cluster_offset,
+                .alloc_offset   = alloc_cluster_offset,
+                .offset         = alloc_offset,
+                .n_start        = keep_clusters == 0 ? n_start : 0,
+                .nb_clusters    = nb_clusters,
+                .nb_available   = MIN(requested_sectors, avail_sectors),
+            };
+            qemu_co_queue_init(&m->dependent_requests);
+            QLIST_INSERT_HEAD(&s->cluster_allocs, m, next_in_flight);
+        }
+    }
+
+    /* Some cleanup work */
+    sectors = (keep_clusters + nb_clusters) << (s->cluster_bits - 9);
+    if (sectors > n_end) {
+        sectors = n_end;
+    }
+
+    assert(sectors > n_start);
+    *num = sectors - n_start;
 
     return 0;
+
+fail:
+    if (m->nb_clusters > 0) {
+        QLIST_REMOVE(m, next_in_flight);
+    }
+    return ret;
 }
 
 static int decompress_buffer(uint8_t *out_buf, int out_buf_size,
@@ -1346,7 +1072,7 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
         l2_table[l2_index + i] = cpu_to_be64(0);
 
         /* Then decrease the refcount */
-        qcow2_free_any_clusters(bs, old_offset, 1, QCOW2_DISCARD_REQUEST);
+        qcow2_free_any_clusters(bs, old_offset, 1);
     }
 
     ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
@@ -1377,25 +1103,18 @@ int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
 
     nb_clusters = size_to_clusters(s, end_offset - offset);
 
-    s->cache_discards = true;
-
     /* Each L2 table is handled by its own loop iteration */
     while (nb_clusters > 0) {
         ret = discard_single_l2(bs, offset, nb_clusters);
         if (ret < 0) {
-            goto fail;
+            return ret;
         }
 
         nb_clusters -= ret;
         offset += (ret * s->cluster_size);
     }
 
-    ret = 0;
-fail:
-    s->cache_discards = false;
-    qcow2_process_discards(bs, ret);
-
-    return ret;
+    return 0;
 }
 
 /*
@@ -1429,7 +1148,7 @@ static int zero_single_l2(BlockDriverState *bs, uint64_t offset,
         qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
         if (old_offset & QCOW_OFLAG_COMPRESSED) {
             l2_table[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO);
-            qcow2_free_any_clusters(bs, old_offset, 1, QCOW2_DISCARD_REQUEST);
+            qcow2_free_any_clusters(bs, old_offset, 1);
         } else {
             l2_table[l2_index + i] |= cpu_to_be64(QCOW_OFLAG_ZERO);
         }
@@ -1457,22 +1176,15 @@ int qcow2_zero_clusters(BlockDriverState *bs, uint64_t offset, int nb_sectors)
     /* Each L2 table is handled by its own loop iteration */
     nb_clusters = size_to_clusters(s, nb_sectors << BDRV_SECTOR_BITS);
 
-    s->cache_discards = true;
-
     while (nb_clusters > 0) {
         ret = zero_single_l2(bs, offset, nb_clusters);
         if (ret < 0) {
-            goto fail;
+            return ret;
         }
 
         nb_clusters -= ret;
         offset += (ret * s->cluster_size);
     }
 
-    ret = 0;
-fail:
-    s->cache_discards = false;
-    qcow2_process_discards(bs, ret);
-
-    return ret;
+    return 0;
 }

block/qcow2-refcount.c

@@ -23,13 +23,13 @@
  */
 
 #include "qemu-common.h"
-#include "block/block_int.h"
+#include "block_int.h"
 #include "block/qcow2.h"
 
 static int64_t alloc_clusters_noref(BlockDriverState *bs, int64_t size);
 static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
                             int64_t offset, int64_t length,
-                            int addend, enum qcow2_discard_type type);
+                            int addend);
 
 
 /*********************************************************/
@@ -201,10 +201,7 @@ static int alloc_refcount_block(BlockDriverState *bs,
     *refcount_block = NULL;
 
     /* We write to the refcount table, so we might depend on L2 tables */
-    ret = qcow2_cache_flush(bs, s->l2_table_cache);
-    if (ret < 0) {
-        return ret;
-    }
+    qcow2_cache_flush(bs, s->l2_table_cache);
 
     /* Allocate the refcount block itself and mark it as used */
     int64_t new_block = alloc_clusters_noref(bs, s->cluster_size);
@@ -235,16 +232,12 @@ static int alloc_refcount_block(BlockDriverState *bs,
     } else {
         /* Described somewhere else. This can recurse at most twice before we
          * arrive at a block that describes itself. */
-        ret = update_refcount(bs, new_block, s->cluster_size, 1,
-                              QCOW2_DISCARD_NEVER);
+        ret = update_refcount(bs, new_block, s->cluster_size, 1);
         if (ret < 0) {
             goto fail_block;
         }
 
-        ret = qcow2_cache_flush(bs, s->refcount_block_cache);
-        if (ret < 0) {
-            goto fail_block;
-        }
+        bdrv_flush(bs->file);
 
         /* Initialize the new refcount block only after updating its refcount,
          * update_refcount uses the refcount cache itself */
@@ -308,8 +301,7 @@ static int alloc_refcount_block(BlockDriverState *bs,
     uint64_t last_table_size;
     uint64_t blocks_clusters;
     do {
-        uint64_t table_clusters =
-            size_to_clusters(s, table_size * sizeof(uint64_t));
+        uint64_t table_clusters = size_to_clusters(s, table_size);
         blocks_clusters = 1 +
             ((table_clusters + refcount_block_clusters - 1)
             / refcount_block_clusters);
@@ -400,8 +392,7 @@ static int alloc_refcount_block(BlockDriverState *bs,
 
     /* Free old table. Remember, we must not change free_cluster_index */
     uint64_t old_free_cluster_index = s->free_cluster_index;
-    qcow2_free_clusters(bs, old_table_offset, old_table_size * sizeof(uint64_t),
-                        QCOW2_DISCARD_OTHER);
+    qcow2_free_clusters(bs, old_table_offset, old_table_size * sizeof(uint64_t));
     s->free_cluster_index = old_free_cluster_index;
 
     ret = load_refcount_block(bs, new_block, (void**) refcount_block);
@@ -420,77 +411,9 @@ fail_block:
     return ret;
 }
 
-void qcow2_process_discards(BlockDriverState *bs, int ret)
-{
-    BDRVQcowState *s = bs->opaque;
-    Qcow2DiscardRegion *d, *next;
-
-    QTAILQ_FOREACH_SAFE(d, &s->discards, next, next) {
-        QTAILQ_REMOVE(&s->discards, d, next);
-
-        /* Discard is optional, ignore the return value */
-        if (ret >= 0) {
-            bdrv_discard(bs->file,
-                         d->offset >> BDRV_SECTOR_BITS,
-                         d->bytes >> BDRV_SECTOR_BITS);
-        }
-
-        g_free(d);
-    }
-}
-
-static void update_refcount_discard(BlockDriverState *bs,
-                                    uint64_t offset, uint64_t length)
-{
-    BDRVQcowState *s = bs->opaque;
-    Qcow2DiscardRegion *d, *p, *next;
-
-    QTAILQ_FOREACH(d, &s->discards, next) {
-        uint64_t new_start = MIN(offset, d->offset);
-        uint64_t new_end = MAX(offset + length, d->offset + d->bytes);
-
-        if (new_end - new_start <= length + d->bytes) {
-            /* There can't be any overlap, areas ending up here have no
-             * references any more and therefore shouldn't get freed another
-             * time. */
-            assert(d->bytes + length == new_end - new_start);
-            d->offset = new_start;
-            d->bytes = new_end - new_start;
-            goto found;
-        }
-    }
-
-    d = g_malloc(sizeof(*d));
-    *d = (Qcow2DiscardRegion) {
-        .bs     = bs,
-        .offset = offset,
-        .bytes  = length,
-    };
-    QTAILQ_INSERT_TAIL(&s->discards, d, next);
-
-found:
-    /* Merge discard requests if they are adjacent now */
-    QTAILQ_FOREACH_SAFE(p, &s->discards, next, next) {
-        if (p == d
-            || p->offset > d->offset + d->bytes
-            || d->offset > p->offset + p->bytes)
-        {
-            continue;
-        }
-
-        /* Still no overlap possible */
-        assert(p->offset == d->offset + d->bytes
-            || d->offset == p->offset + p->bytes);
-
-        QTAILQ_REMOVE(&s->discards, p, next);
-        d->offset = MIN(d->offset, p->offset);
-        d->bytes += p->bytes;
-    }
-}
-
 /* XXX: cache several refcount block clusters ? */
 static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
-    int64_t offset, int64_t length, int addend, enum qcow2_discard_type type)
+    int64_t offset, int64_t length, int addend)
 {
     BDRVQcowState *s = bs->opaque;
     int64_t start, last, cluster_offset;
@@ -556,18 +479,10 @@ static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
             s->free_cluster_index = cluster_index;
         }
         refcount_block[block_index] = cpu_to_be16(refcount);
-
-        if (refcount == 0 && s->discard_passthrough[type]) {
-            update_refcount_discard(bs, cluster_offset, s->cluster_size);
-        }
     }
 
     ret = 0;
 fail:
-    if (!s->cache_discards) {
-        qcow2_process_discards(bs, ret);
-    }
-
     /* Write last changed block to disk */
     if (refcount_block) {
         int wret;
@@ -584,8 +499,7 @@ fail:
      */
     if (ret < 0) {
         int dummy;
-        dummy = update_refcount(bs, offset, cluster_offset - offset, -addend,
-                                QCOW2_DISCARD_NEVER);
+        dummy = update_refcount(bs, offset, cluster_offset - offset, -addend);
         (void)dummy;
     }
 
@@ -601,18 +515,18 @@ fail:
  */
 static int update_cluster_refcount(BlockDriverState *bs,
                                    int64_t cluster_index,
-                                   int addend,
-                                   enum qcow2_discard_type type)
+                                   int addend)
 {
     BDRVQcowState *s = bs->opaque;
     int ret;
 
-    ret = update_refcount(bs, cluster_index << s->cluster_bits, 1, addend,
-                          type);
+    ret = update_refcount(bs, cluster_index << s->cluster_bits, 1, addend);
     if (ret < 0) {
         return ret;
     }
 
+    bdrv_flush(bs->file);
+
     return get_refcount(bs, cluster_index);
 }
 
@@ -660,7 +574,7 @@ int64_t qcow2_alloc_clusters(BlockDriverState *bs, int64_t size)
         return offset;
     }
 
-    ret = update_refcount(bs, offset, size, 1, QCOW2_DISCARD_NEVER);
+    ret = update_refcount(bs, offset, size, 1);
     if (ret < 0) {
         return ret;
     }
@@ -692,8 +606,7 @@ int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
     old_free_cluster_index = s->free_cluster_index;
     s->free_cluster_index = cluster_index + i;
 
-    ret = update_refcount(bs, offset, i << s->cluster_bits, 1,
-                          QCOW2_DISCARD_NEVER);
+    ret = update_refcount(bs, offset, i << s->cluster_bits, 1);
     if (ret < 0) {
         return ret;
     }
@@ -714,11 +627,10 @@ int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size)
     BLKDBG_EVENT(bs->file, BLKDBG_CLUSTER_ALLOC_BYTES);
     assert(size > 0 && size <= s->cluster_size);
     if (s->free_byte_offset == 0) {
-        offset = qcow2_alloc_clusters(bs, s->cluster_size);
-        if (offset < 0) {
-            return offset;
+        s->free_byte_offset = qcow2_alloc_clusters(bs, s->cluster_size);
+        if (s->free_byte_offset < 0) {
+            return s->free_byte_offset;
         }
-        s->free_byte_offset = offset;
     }
  redo:
     free_in_cluster = s->cluster_size -
@@ -731,8 +643,7 @@ int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size)
         if (free_in_cluster == 0)
             s->free_byte_offset = 0;
         if ((offset & (s->cluster_size - 1)) != 0)
-            update_cluster_refcount(bs, offset >> s->cluster_bits, 1,
-                                    QCOW2_DISCARD_NEVER);
+            update_cluster_refcount(bs, offset >> s->cluster_bits, 1);
     } else {
         offset = qcow2_alloc_clusters(bs, s->cluster_size);
         if (offset < 0) {
@@ -742,8 +653,7 @@ int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size)
         if ((cluster_offset + s->cluster_size) == offset) {
             /* we are lucky: contiguous data */
             offset = s->free_byte_offset;
-            update_cluster_refcount(bs, offset >> s->cluster_bits, 1,
-                                    QCOW2_DISCARD_NEVER);
+            update_cluster_refcount(bs, offset >> s->cluster_bits, 1);
             s->free_byte_offset += size;
         } else {
             s->free_byte_offset = offset;
@@ -751,22 +661,17 @@ int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size)
         }
     }
 
-    /* The cluster refcount was incremented, either by qcow2_alloc_clusters()
-     * or explicitly by update_cluster_refcount().  Refcount blocks must be
-     * flushed before the caller's L2 table updates.
-     */
-    qcow2_cache_set_dependency(bs, s->l2_table_cache, s->refcount_block_cache);
+    bdrv_flush(bs->file);
     return offset;
 }
 
 void qcow2_free_clusters(BlockDriverState *bs,
-                          int64_t offset, int64_t size,
-                          enum qcow2_discard_type type)
+                          int64_t offset, int64_t size)
 {
     int ret;
 
     BLKDBG_EVENT(bs->file, BLKDBG_CLUSTER_FREE);
-    ret = update_refcount(bs, offset, size, -1, type);
+    ret = update_refcount(bs, offset, size, -1);
     if (ret < 0) {
         fprintf(stderr, "qcow2_free_clusters failed: %s\n", strerror(-ret));
         /* TODO Remember the clusters to free them later and avoid leaking */
@@ -777,8 +682,8 @@ void qcow2_free_clusters(BlockDriverState *bs,
  * Free a cluster using its L2 entry (handles clusters of all types, e.g.
  * normal cluster, compressed cluster, etc.)
  */
-void qcow2_free_any_clusters(BlockDriverState *bs, uint64_t l2_entry,
-                             int nb_clusters, enum qcow2_discard_type type)
+void qcow2_free_any_clusters(BlockDriverState *bs,
+    uint64_t l2_entry, int nb_clusters)
 {
     BDRVQcowState *s = bs->opaque;
 
@@ -790,12 +695,12 @@ void qcow2_free_any_clusters(BlockDriverState *bs, uint64_t l2_entry,
                            s->csize_mask) + 1;
             qcow2_free_clusters(bs,
                 (l2_entry & s->cluster_offset_mask) & ~511,
-                nb_csectors * 512, type);
+                nb_csectors * 512);
         }
         break;
     case QCOW2_CLUSTER_NORMAL:
         qcow2_free_clusters(bs, l2_entry & L2E_OFFSET_MASK,
-                            nb_clusters << s->cluster_bits, type);
+                            nb_clusters << s->cluster_bits);
         break;
     case QCOW2_CLUSTER_UNALLOCATED:
     case QCOW2_CLUSTER_ZERO:
@@ -821,22 +726,32 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
     int64_t old_offset, old_l2_offset;
     int i, j, l1_modified = 0, nb_csectors, refcount;
     int ret;
+    bool old_l2_writethrough, old_refcount_writethrough;
+
+    /* Switch caches to writeback mode during update */
+    old_l2_writethrough =
+        qcow2_cache_set_writethrough(bs, s->l2_table_cache, false);
+    old_refcount_writethrough =
+        qcow2_cache_set_writethrough(bs, s->refcount_block_cache, false);
 
     l2_table = NULL;
     l1_table = NULL;
     l1_size2 = l1_size * sizeof(uint64_t);
 
-    s->cache_discards = true;
-
     /* WARNING: qcow2_snapshot_goto relies on this function not using the
      * l1_table_offset when it is the current s->l1_table_offset! Be careful
      * when changing this! */
     if (l1_table_offset != s->l1_table_offset) {
-        l1_table = g_malloc0(align_offset(l1_size2, 512));
+        if (l1_size2 != 0) {
+            l1_table = g_malloc0(align_offset(l1_size2, 512));
+        } else {
+            l1_table = NULL;
+        }
         l1_allocated = 1;
-
-        ret = bdrv_pread(bs->file, l1_table_offset, l1_table, l1_size2);
-        if (ret < 0) {
+        if (bdrv_pread(bs->file, l1_table_offset,
+                       l1_table, l1_size2) != l1_size2)
+        {
+            ret = -EIO;
             goto fail;
         }
 
@@ -872,25 +787,27 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
                             int ret;
                             ret = update_refcount(bs,
                                 (offset & s->cluster_offset_mask) & ~511,
-                                nb_csectors * 512, addend,
-                                QCOW2_DISCARD_SNAPSHOT);
+                                nb_csectors * 512, addend);
                             if (ret < 0) {
                                 goto fail;
                             }
+
+                            /* TODO Flushing once for the whole function should
+                             * be enough */
+                            bdrv_flush(bs->file);
                         }
                         /* compressed clusters are never modified */
                         refcount = 2;
                     } else {
                         uint64_t cluster_index = (offset & L2E_OFFSET_MASK) >> s->cluster_bits;
                         if (addend != 0) {
-                            refcount = update_cluster_refcount(bs, cluster_index, addend,
-                                                               QCOW2_DISCARD_SNAPSHOT);
+                            refcount = update_cluster_refcount(bs, cluster_index, addend);
                         } else {
                             refcount = get_refcount(bs, cluster_index);
                         }
 
                         if (refcount < 0) {
-                            ret = refcount;
+                            ret = -EIO;
                             goto fail;
                         }
                     }
@@ -916,13 +833,12 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
 
 
             if (addend != 0) {
-                refcount = update_cluster_refcount(bs, l2_offset >> s->cluster_bits, addend,
-                                                   QCOW2_DISCARD_SNAPSHOT);
+                refcount = update_cluster_refcount(bs, l2_offset >> s->cluster_bits, addend);
             } else {
                 refcount = get_refcount(bs, l2_offset >> s->cluster_bits);
             }
             if (refcount < 0) {
-                ret = refcount;
+                ret = -EIO;
                 goto fail;
             } else if (refcount == 1) {
                 l2_offset |= QCOW_OFLAG_COPIED;
@@ -934,26 +850,26 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
         }
     }
 
-    ret = bdrv_flush(bs);
+    ret = 0;
 fail:
     if (l2_table) {
         qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
     }
 
-    s->cache_discards = false;
-    qcow2_process_discards(bs, ret);
+    /* Enable writethrough cache mode again */
+    qcow2_cache_set_writethrough(bs, s->l2_table_cache, old_l2_writethrough);
+    qcow2_cache_set_writethrough(bs, s->refcount_block_cache,
+        old_refcount_writethrough);
 
     /* Update L1 only if it isn't deleted anyway (addend = -1) */
-    if (ret == 0 && addend >= 0 && l1_modified) {
-        for (i = 0; i < l1_size; i++) {
+    if (addend >= 0 && l1_modified) {
+        for(i = 0; i < l1_size; i++)
             cpu_to_be64s(&l1_table[i]);
-        }
-
-        ret = bdrv_pwrite_sync(bs->file, l1_table_offset, l1_table, l1_size2);
-
-        for (i = 0; i < l1_size; i++) {
+        if (bdrv_pwrite_sync(bs->file, l1_table_offset, l1_table,
+                        l1_size2) < 0)
+            goto fail;
+        for(i = 0; i < l1_size; i++)
             be64_to_cpus(&l1_table[i]);
-        }
     }
     if (l1_allocated)
         g_free(l1_table);
@@ -1012,12 +928,6 @@ static void inc_refcounts(BlockDriverState *bs,
     }
 }
 
-/* Flags for check_refcounts_l1() and check_refcounts_l2() */
-enum {
-    CHECK_OFLAG_COPIED = 0x1,   /* check QCOW_OFLAG_COPIED matches refcount */
-    CHECK_FRAG_INFO = 0x2,      /* update BlockFragInfo counters */
-};
-
 /*
  * Increases the refcount in the given refcount table for the all clusters
  * referenced in the L2 table. While doing so, performs some checks on L2
@@ -1028,11 +938,10 @@ enum {
  */
 static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res,
     uint16_t *refcount_table, int refcount_table_size, int64_t l2_offset,
-    int flags)
+    int check_copied)
 {
     BDRVQcowState *s = bs->opaque;
     uint64_t *l2_table, l2_entry;
-    uint64_t next_contiguous_offset = 0;
     int i, l2_size, nb_csectors, refcount;
 
     /* Read L2 table from disk */
@@ -1063,18 +972,6 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res,
             l2_entry &= s->cluster_offset_mask;
             inc_refcounts(bs, res, refcount_table, refcount_table_size,
                 l2_entry & ~511, nb_csectors * 512);
-
-            if (flags & CHECK_FRAG_INFO) {
-                res->bfi.allocated_clusters++;
-                res->bfi.compressed_clusters++;
-
-                /* Compressed clusters are fragmented by nature.  Since they
-                 * take up sub-sector space but we only have sector granularity
-                 * I/O we need to re-read the same sectors even for adjacent
-                 * compressed clusters.
-                 */
-                res->bfi.fragmented_clusters++;
-            }
             break;
 
         case QCOW2_CLUSTER_ZERO:
@@ -1088,7 +985,7 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res,
             /* QCOW_OFLAG_COPIED must be set iff refcount == 1 */
             uint64_t offset = l2_entry & L2E_OFFSET_MASK;
 
-            if (flags & CHECK_OFLAG_COPIED) {
+            if (check_copied) {
                 refcount = get_refcount(bs, offset >> s->cluster_bits);
                 if (refcount < 0) {
                     fprintf(stderr, "Can't get refcount for offset %"
@@ -1102,15 +999,6 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res,
                 }
             }
 
-            if (flags & CHECK_FRAG_INFO) {
-                res->bfi.allocated_clusters++;
-                if (next_contiguous_offset &&
-                    offset != next_contiguous_offset) {
-                    res->bfi.fragmented_clusters++;
-                }
-                next_contiguous_offset = offset + s->cluster_size;
-            }
-
             /* Mark cluster as used */
             inc_refcounts(bs, res, refcount_table,refcount_table_size,
                 offset, s->cluster_size);
@@ -1154,7 +1042,7 @@ static int check_refcounts_l1(BlockDriverState *bs,
                               uint16_t *refcount_table,
                               int refcount_table_size,
                               int64_t l1_table_offset, int l1_size,
-                              int flags)
+                              int check_copied)
 {
     BDRVQcowState *s = bs->opaque;
     uint64_t *l1_table, l2_offset, l1_size2;
@@ -1183,7 +1071,7 @@ static int check_refcounts_l1(BlockDriverState *bs,
         l2_offset = l1_table[i];
         if (l2_offset) {
             /* QCOW_OFLAG_COPIED must be set iff refcount == 1 */
-            if (flags & CHECK_OFLAG_COPIED) {
+            if (check_copied) {
                 refcount = get_refcount(bs, (l2_offset & ~QCOW_OFLAG_COPIED)
                     >> s->cluster_bits);
                 if (refcount < 0) {
@@ -1212,7 +1100,7 @@ static int check_refcounts_l1(BlockDriverState *bs,
 
             /* Process and check L2 entries */
             ret = check_refcounts_l2(bs, res, refcount_table,
-                                     refcount_table_size, l2_offset, flags);
+                refcount_table_size, l2_offset, check_copied);
             if (ret < 0) {
                 goto fail;
             }
@@ -1234,12 +1122,11 @@ fail:
  * Returns 0 if no errors are found, the number of errors in case the image is
  * detected as corrupted, and -errno when an internal error occurred.
  */
-int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
-                          BdrvCheckMode fix)
+int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res)
 {
     BDRVQcowState *s = bs->opaque;
-    int64_t size, i, highest_cluster;
-    int nb_clusters, refcount1, refcount2;
+    int64_t size;
+    int nb_clusters, refcount1, refcount2, i;
     QCowSnapshot *sn;
     uint16_t *refcount_table;
     int ret;
@@ -1248,17 +1135,13 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
     nb_clusters = size_to_clusters(s, size);
     refcount_table = g_malloc0(nb_clusters * sizeof(uint16_t));
 
-    res->bfi.total_clusters =
-        size_to_clusters(s, bs->total_sectors * BDRV_SECTOR_SIZE);
-
     /* header */
     inc_refcounts(bs, res, refcount_table, nb_clusters,
         0, s->cluster_size);
 
     /* current L1 table */
     ret = check_refcounts_l1(bs, res, refcount_table, nb_clusters,
-                             s->l1_table_offset, s->l1_size,
-                             CHECK_OFLAG_COPIED | CHECK_FRAG_INFO);
+                       s->l1_table_offset, s->l1_size, 1);
     if (ret < 0) {
         goto fail;
     }
@@ -1287,15 +1170,14 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
 
         /* Refcount blocks are cluster aligned */
         if (offset & (s->cluster_size - 1)) {
-            fprintf(stderr, "ERROR refcount block %" PRId64 " is not "
+            fprintf(stderr, "ERROR refcount block %d is not "
                 "cluster aligned; refcount table entry corrupted\n", i);
             res->corruptions++;
             continue;
         }
 
         if (cluster >= nb_clusters) {
-            fprintf(stderr, "ERROR refcount block %" PRId64
-                    " is outside image\n", i);
+            fprintf(stderr, "ERROR refcount block %d is outside image\n", i);
             res->corruptions++;
             continue;
         }
@@ -1304,8 +1186,7 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
             inc_refcounts(bs, res, refcount_table, nb_clusters,
                 offset, s->cluster_size);
             if (refcount_table[cluster] != 1) {
-                fprintf(stderr, "ERROR refcount block %" PRId64
-                    " refcount=%d\n",
+                fprintf(stderr, "ERROR refcount block %d refcount=%d\n",
                     i, refcount_table[cluster]);
                 res->corruptions++;
             }
@@ -1313,48 +1194,20 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
     }
 
     /* compare ref counts */
-    for (i = 0, highest_cluster = 0; i < nb_clusters; i++) {
+    for(i = 0; i < nb_clusters; i++) {
         refcount1 = get_refcount(bs, i);
         if (refcount1 < 0) {
-            fprintf(stderr, "Can't get refcount for cluster %" PRId64 ": %s\n",
+            fprintf(stderr, "Can't get refcount for cluster %d: %s\n",
                 i, strerror(-refcount1));
             res->check_errors++;
             continue;
         }
 
         refcount2 = refcount_table[i];
-
-        if (refcount1 > 0 || refcount2 > 0) {
-            highest_cluster = i;
-        }
-
         if (refcount1 != refcount2) {
-
-            /* Check if we're allowed to fix the mismatch */
-            int *num_fixed = NULL;
-            if (refcount1 > refcount2 && (fix & BDRV_FIX_LEAKS)) {
-                num_fixed = &res->leaks_fixed;
-            } else if (refcount1 < refcount2 && (fix & BDRV_FIX_ERRORS)) {
-                num_fixed = &res->corruptions_fixed;
-            }
-
-            fprintf(stderr, "%s cluster %" PRId64 " refcount=%d reference=%d\n",
-                   num_fixed != NULL     ? "Repairing" :
-                   refcount1 < refcount2 ? "ERROR" :
-                                           "Leaked",
+            fprintf(stderr, "%s cluster %d refcount=%d reference=%d\n",
+                   refcount1 < refcount2 ? "ERROR" : "Leaked",
                    i, refcount1, refcount2);
-
-            if (num_fixed) {
-                ret = update_refcount(bs, i << s->cluster_bits, 1,
-                                      refcount2 - refcount1,
-                                      QCOW2_DISCARD_ALWAYS);
-                if (ret >= 0) {
-                    (*num_fixed)++;
-                    continue;
-                }
-            }
-
-            /* And if we couldn't, print an error */
             if (refcount1 < refcount2) {
                 res->corruptions++;
             } else {
@@ -1363,7 +1216,6 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
         }
     }
 
-    res->image_end_offset = (highest_cluster + 1) * s->cluster_size;
     ret = 0;
 
 fail:

block/qcow2-snapshot.c

@@ -23,7 +23,7 @@
  */
 
 #include "qemu-common.h"
-#include "block/block_int.h"
+#include "block_int.h"
 #include "block/qcow2.h"
 
 typedef struct QEMU_PACKED QCowSnapshotHeader {
@@ -180,14 +180,11 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
 
     /* Allocate space for the new snapshot list */
     snapshots_offset = qcow2_alloc_clusters(bs, snapshots_size);
+    bdrv_flush(bs->file);
     offset = snapshots_offset;
     if (offset < 0) {
         return offset;
     }
-    ret = bdrv_flush(bs);
-    if (ret < 0) {
-        return ret;
-    }
 
     /* Write all snapshots to the new list */
     for(i = 0; i < s->nb_snapshots; i++) {
@@ -262,8 +259,7 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
     }
 
     /* free the old snapshot table */
-    qcow2_free_clusters(bs, s->snapshots_offset, s->snapshots_size,
-                        QCOW2_DISCARD_SNAPSHOT);
+    qcow2_free_clusters(bs, s->snapshots_offset, s->snapshots_size);
     s->snapshots_offset = snapshots_offset;
     s->snapshots_size = snapshots_size;
     return 0;
@@ -382,6 +378,11 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
         goto fail;
     }
 
+    ret = bdrv_flush(bs);
+    if (ret < 0) {
+        goto fail;
+    }
+
     /* Append the new snapshot to the snapshot list */
     new_snapshot_list = g_malloc((s->nb_snapshots + 1) * sizeof(QCowSnapshot));
     if (s->snapshots) {
@@ -404,7 +405,7 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
 #ifdef DEBUG_ALLOC
     {
       BdrvCheckResult result = {0};
-      qcow2_check_refcounts(bs, &result, 0);
+      qcow2_check_refcounts(bs, &result);
     }
 #endif
     return 0;
@@ -521,7 +522,7 @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
 #ifdef DEBUG_ALLOC
     {
         BdrvCheckResult result = {0};
-        qcow2_check_refcounts(bs, &result, 0);
+        qcow2_check_refcounts(bs, &result);
     }
 #endif
     return 0;
@@ -570,8 +571,7 @@ int qcow2_snapshot_delete(BlockDriverState *bs, const char *snapshot_id)
     if (ret < 0) {
         return ret;
     }
-    qcow2_free_clusters(bs, sn.l1_table_offset, sn.l1_size * sizeof(uint64_t),
-                        QCOW2_DISCARD_SNAPSHOT);
+    qcow2_free_clusters(bs, sn.l1_table_offset, sn.l1_size * sizeof(uint64_t));
 
     /* must update the copied flag on the current cluster offsets */
     ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 0);
@@ -582,7 +582,7 @@ int qcow2_snapshot_delete(BlockDriverState *bs, const char *snapshot_id)
 #ifdef DEBUG_ALLOC
     {
         BdrvCheckResult result = {0};
-        qcow2_check_refcounts(bs, &result, 0);
+        qcow2_check_refcounts(bs, &result);
     }
 #endif
     return 0;

block/qcow2.c

@@ -22,14 +22,13 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
 #include <zlib.h>
-#include "qemu/aes.h"
+#include "aes.h"
 #include "block/qcow2.h"
-#include "qemu/error-report.h"
-#include "qapi/qmp/qerror.h"
-#include "qapi/qmp/qbool.h"
+#include "qemu-error.h"
+#include "qerror.h"
 #include "trace.h"
 
 /*
@@ -53,7 +52,6 @@ typedef struct {
     uint32_t magic;
     uint32_t len;
 } QCowExtension;
-
 #define  QCOW2_EXT_MAGIC_END 0
 #define  QCOW2_EXT_MAGIC_BACKING_FORMAT 0xE2792ACA
 #define  QCOW2_EXT_MAGIC_FEATURE_TABLE 0x6803f857
@@ -216,114 +214,13 @@ static void report_unsupported_feature(BlockDriverState *bs,
     }
 }
 
-/*
- * Sets the dirty bit and flushes afterwards if necessary.
- *
- * The incompatible_features bit is only set if the image file header was
- * updated successfully.  Therefore it is not required to check the return
- * value of this function.
- */
-int qcow2_mark_dirty(BlockDriverState *bs)
-{
-    BDRVQcowState *s = bs->opaque;
-    uint64_t val;
-    int ret;
-
-    assert(s->qcow_version >= 3);
-
-    if (s->incompatible_features & QCOW2_INCOMPAT_DIRTY) {
-        return 0; /* already dirty */
-    }
-
-    val = cpu_to_be64(s->incompatible_features | QCOW2_INCOMPAT_DIRTY);
-    ret = bdrv_pwrite(bs->file, offsetof(QCowHeader, incompatible_features),
-                      &val, sizeof(val));
-    if (ret < 0) {
-        return ret;
-    }
-    ret = bdrv_flush(bs->file);
-    if (ret < 0) {
-        return ret;
-    }
-
-    /* Only treat image as dirty if the header was updated successfully */
-    s->incompatible_features |= QCOW2_INCOMPAT_DIRTY;
-    return 0;
-}
-
-/*
- * Clears the dirty bit and flushes before if necessary.  Only call this
- * function when there are no pending requests, it does not guard against
- * concurrent requests dirtying the image.
- */
-static int qcow2_mark_clean(BlockDriverState *bs)
-{
-    BDRVQcowState *s = bs->opaque;
-
-    if (s->incompatible_features & QCOW2_INCOMPAT_DIRTY) {
-        int ret = bdrv_flush(bs);
-        if (ret < 0) {
-            return ret;
-        }
-
-        s->incompatible_features &= ~QCOW2_INCOMPAT_DIRTY;
-        return qcow2_update_header(bs);
-    }
-    return 0;
-}
-
-static int qcow2_check(BlockDriverState *bs, BdrvCheckResult *result,
-                       BdrvCheckMode fix)
-{
-    int ret = qcow2_check_refcounts(bs, result, fix);
-    if (ret < 0) {
-        return ret;
-    }
-
-    if (fix && result->check_errors == 0 && result->corruptions == 0) {
-        return qcow2_mark_clean(bs);
-    }
-    return ret;
-}
-
-static QemuOptsList qcow2_runtime_opts = {
-    .name = "qcow2",
-    .head = QTAILQ_HEAD_INITIALIZER(qcow2_runtime_opts.head),
-    .desc = {
-        {
-            .name = QCOW2_OPT_LAZY_REFCOUNTS,
-            .type = QEMU_OPT_BOOL,
-            .help = "Postpone refcount updates",
-        },
-        {
-            .name = QCOW2_OPT_DISCARD_REQUEST,
-            .type = QEMU_OPT_BOOL,
-            .help = "Pass guest discard requests to the layer below",
-        },
-        {
-            .name = QCOW2_OPT_DISCARD_SNAPSHOT,
-            .type = QEMU_OPT_BOOL,
-            .help = "Generate discard requests when snapshot related space "
-                    "is freed",
-        },
-        {
-            .name = QCOW2_OPT_DISCARD_OTHER,
-            .type = QEMU_OPT_BOOL,
-            .help = "Generate discard requests when other clusters are freed",
-        },
-        { /* end of list */ }
-    },
-};
-
-static int qcow2_open(BlockDriverState *bs, QDict *options, int flags)
+static int qcow2_open(BlockDriverState *bs, int flags)
 {
     BDRVQcowState *s = bs->opaque;
     int len, i, ret = 0;
     QCowHeader header;
-    QemuOpts *opts;
-    Error *local_err = NULL;
     uint64_t ext_end;
-    uint64_t l1_vm_state_index;
+    bool writethrough;
 
     ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
     if (ret < 0) {
@@ -344,7 +241,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags)
     be32_to_cpus(&header.nb_snapshots);
 
     if (header.magic != QCOW_MAGIC) {
-        ret = -EMEDIUMTYPE;
+        ret = -EINVAL;
         goto fail;
     }
     if (header.version < 2 || header.version > 3) {
@@ -391,13 +288,12 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags)
     s->compatible_features      = header.compatible_features;
     s->autoclear_features       = header.autoclear_features;
 
-    if (s->incompatible_features & ~QCOW2_INCOMPAT_MASK) {
+    if (s->incompatible_features != 0) {
         void *feature_table = NULL;
         qcow2_read_extensions(bs, header.header_length, ext_end,
                               &feature_table);
         report_unsupported_feature(bs, feature_table,
-                                   s->incompatible_features &
-                                   ~QCOW2_INCOMPAT_MASK);
+                                   s->incompatible_features);
         ret = -ENOTSUP;
         goto fail;
     }
@@ -441,14 +337,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags)
 
     /* read the level 1 table */
     s->l1_size = header.l1_size;
-
-    l1_vm_state_index = size_to_l1(s, header.size);
-    if (l1_vm_state_index > INT_MAX) {
-        ret = -EFBIG;
-        goto fail;
-    }
-    s->l1_vm_state_index = l1_vm_state_index;
-
+    s->l1_vm_state_index = size_to_l1(s, header.size);
     /* the L1 table must contain at least enough entries to put
        header.size bytes */
     if (s->l1_size < s->l1_vm_state_index) {
@@ -470,8 +359,10 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags)
     }
 
     /* alloc L2 table/refcount block cache */
-    s->l2_table_cache = qcow2_cache_create(bs, L2_CACHE_SIZE);
-    s->refcount_block_cache = qcow2_cache_create(bs, REFCOUNT_CACHE_SIZE);
+    writethrough = ((flags & BDRV_O_CACHE_WB) == 0);
+    s->l2_table_cache = qcow2_cache_create(bs, L2_CACHE_SIZE, writethrough);
+    s->refcount_block_cache = qcow2_cache_create(bs, REFCOUNT_CACHE_SIZE,
+        writethrough);
 
     s->cluster_cache = g_malloc(s->cluster_size);
     /* one more sector for decompressed data alignment */
@@ -486,7 +377,6 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags)
     }
 
     QLIST_INIT(&s->cluster_allocs);
-    QTAILQ_INIT(&s->discards);
 
     /* read qcow2 extensions */
     if (qcow2_read_extensions(bs, header.header_length, ext_end, NULL)) {
@@ -525,53 +415,10 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags)
     /* Initialise locks */
     qemu_co_mutex_init(&s->lock);
 
-    /* Repair image if dirty */
-    if (!(flags & BDRV_O_CHECK) && !bs->read_only &&
-        (s->incompatible_features & QCOW2_INCOMPAT_DIRTY)) {
-        BdrvCheckResult result = {0};
-
-        ret = qcow2_check(bs, &result, BDRV_FIX_ERRORS);
-        if (ret < 0) {
-            goto fail;
-        }
-    }
-
-    /* Enable lazy_refcounts according to image and command line options */
-    opts = qemu_opts_create_nofail(&qcow2_runtime_opts);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (error_is_set(&local_err)) {
-        qerror_report_err(local_err);
-        error_free(local_err);
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    s->use_lazy_refcounts = qemu_opt_get_bool(opts, QCOW2_OPT_LAZY_REFCOUNTS,
-        (s->compatible_features & QCOW2_COMPAT_LAZY_REFCOUNTS));
-
-    s->discard_passthrough[QCOW2_DISCARD_NEVER] = false;
-    s->discard_passthrough[QCOW2_DISCARD_ALWAYS] = true;
-    s->discard_passthrough[QCOW2_DISCARD_REQUEST] =
-        qemu_opt_get_bool(opts, QCOW2_OPT_DISCARD_REQUEST,
-                          flags & BDRV_O_UNMAP);
-    s->discard_passthrough[QCOW2_DISCARD_SNAPSHOT] =
-        qemu_opt_get_bool(opts, QCOW2_OPT_DISCARD_SNAPSHOT, true);
-    s->discard_passthrough[QCOW2_DISCARD_OTHER] =
-        qemu_opt_get_bool(opts, QCOW2_OPT_DISCARD_OTHER, false);
-
-    qemu_opts_del(opts);
-
-    if (s->use_lazy_refcounts && s->qcow_version < 3) {
-        qerror_report(ERROR_CLASS_GENERIC_ERROR, "Lazy refcounts require "
-            "a qcow2 image with at least qemu 1.1 compatibility level");
-        ret = -EINVAL;
-        goto fail;
-    }
-
 #ifdef DEBUG_ALLOC
     {
         BdrvCheckResult result = {0};
-        qcow2_check_refcounts(bs, &result, 0);
+        qcow2_check_refcounts(bs, &result);
     }
 #endif
     return ret;
@@ -632,14 +479,6 @@ static int qcow2_set_key(BlockDriverState *bs, const char *key)
     return 0;
 }
 
-/* We have nothing to do for QCOW2 reopen, stubs just return
- * success */
-static int qcow2_reopen_prepare(BDRVReopenState *state,
-                                BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
-}
-
 static int coroutine_fn qcow2_co_is_allocated(BlockDriverState *bs,
         int64_t sector_num, int nb_sectors, int *pnum)
 {
@@ -657,7 +496,7 @@ static int coroutine_fn qcow2_co_is_allocated(BlockDriverState *bs,
         *pnum = 0;
     }
 
-    return (cluster_offset != 0) || (ret == QCOW2_CLUSTER_ZERO);
+    return (cluster_offset != 0);
 }
 
 /* handle reading after the end of the backing file */
@@ -672,7 +511,7 @@ int qcow2_backing_read1(BlockDriverState *bs, QEMUIOVector *qiov,
     else
         n1 = bs->total_sectors - sector_num;
 
-    qemu_iovec_memset(qiov, 512 * n1, 0, 512 * (nb_sectors - n1));
+    qemu_iovec_memset_skip(qiov, 0, 512 * (nb_sectors - n1), 512 * n1);
 
     return n1;
 }
@@ -711,7 +550,7 @@ static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
         index_in_cluster = sector_num & (s->cluster_sectors - 1);
 
         qemu_iovec_reset(&hd_qiov);
-        qemu_iovec_concat(&hd_qiov, qiov, bytes_done,
+        qemu_iovec_copy(&hd_qiov, qiov, bytes_done,
             cur_nr_sectors * 512);
 
         switch (ret) {
@@ -733,12 +572,16 @@ static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
                 }
             } else {
                 /* Note: in this case, no need to wait */
-                qemu_iovec_memset(&hd_qiov, 0, 0, 512 * cur_nr_sectors);
+                qemu_iovec_memset(&hd_qiov, 0, 512 * cur_nr_sectors);
             }
             break;
 
         case QCOW2_CLUSTER_ZERO:
-            qemu_iovec_memset(&hd_qiov, 0, 0, 512 * cur_nr_sectors);
+            if (s->qcow_version < 3) {
+                ret = -EIO;
+                goto fail;
+            }
+            qemu_iovec_memset(&hd_qiov, 0, 512 * cur_nr_sectors);
             break;
 
         case QCOW2_CLUSTER_COMPRESSED:
@@ -748,7 +591,7 @@ static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
                 goto fail;
             }
 
-            qemu_iovec_from_buf(&hd_qiov, 0,
+            qemu_iovec_from_buffer(&hd_qiov,
                 s->cluster_cache + index_in_cluster * 512,
                 512 * cur_nr_sectors);
             break;
@@ -788,8 +631,11 @@ static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
             if (s->crypt_method) {
                 qcow2_encrypt_sectors(s, sector_num,  cluster_data,
                     cluster_data, cur_nr_sectors, 0, &s->aes_decrypt_key);
-                qemu_iovec_from_buf(qiov, bytes_done,
-                    cluster_data, 512 * cur_nr_sectors);
+                qemu_iovec_reset(&hd_qiov);
+                qemu_iovec_copy(&hd_qiov, qiov, bytes_done,
+                    cur_nr_sectors * 512);
+                qemu_iovec_from_buffer(&hd_qiov, cluster_data,
+                    512 * cur_nr_sectors);
             }
             break;
 
@@ -814,6 +660,21 @@ fail:
     return ret;
 }
 
+static void run_dependent_requests(BDRVQcowState *s, QCowL2Meta *m)
+{
+    /* Take the request off the list of running requests */
+    if (m->nb_clusters != 0) {
+        QLIST_REMOVE(m, next_in_flight);
+    }
+
+    /* Restart all dependent requests */
+    if (!qemu_co_queue_empty(&m->dependent_requests)) {
+        qemu_co_mutex_unlock(&s->lock);
+        qemu_co_queue_restart_all(&m->dependent_requests);
+        qemu_co_mutex_lock(&s->lock);
+    }
+}
+
 static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
                            int64_t sector_num,
                            int remaining_sectors,
@@ -828,11 +689,15 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
     QEMUIOVector hd_qiov;
     uint64_t bytes_done = 0;
     uint8_t *cluster_data = NULL;
-    QCowL2Meta *l2meta = NULL;
+    QCowL2Meta l2meta = {
+        .nb_clusters = 0,
+    };
 
     trace_qcow2_writev_start_req(qemu_coroutine_self(), sector_num,
                                  remaining_sectors);
 
+    qemu_co_queue_init(&l2meta.dependent_requests);
+
     qemu_iovec_init(&hd_qiov, qiov->niov);
 
     s->cluster_cache_offset = -1; /* disable compressed cache */
@@ -841,8 +706,6 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
 
     while (remaining_sectors != 0) {
 
-        l2meta = NULL;
-
         trace_qcow2_writev_start_part(qemu_coroutine_self());
         index_in_cluster = sector_num & (s->cluster_sectors - 1);
         n_end = index_in_cluster + remaining_sectors;
@@ -852,15 +715,16 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
         }
 
         ret = qcow2_alloc_cluster_offset(bs, sector_num << 9,
-            index_in_cluster, n_end, &cur_nr_sectors, &cluster_offset, &l2meta);
+            index_in_cluster, n_end, &cur_nr_sectors, &l2meta);
         if (ret < 0) {
             goto fail;
         }
 
+        cluster_offset = l2meta.cluster_offset;
         assert((cluster_offset & 511) == 0);
 
         qemu_iovec_reset(&hd_qiov);
-        qemu_iovec_concat(&hd_qiov, qiov, bytes_done,
+        qemu_iovec_copy(&hd_qiov, qiov, bytes_done,
             cur_nr_sectors * 512);
 
         if (s->crypt_method) {
@@ -871,7 +735,7 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
 
             assert(hd_qiov.size <=
                    QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size);
-            qemu_iovec_to_buf(&hd_qiov, 0, cluster_data, hd_qiov.size);
+            qemu_iovec_to_buffer(&hd_qiov, cluster_data);
 
             qcow2_encrypt_sectors(s, sector_num, cluster_data,
                 cluster_data, cur_nr_sectors, 1, &s->aes_encrypt_key);
@@ -881,8 +745,8 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
                 cur_nr_sectors * 512);
         }
 
-        qemu_co_mutex_unlock(&s->lock);
         BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
+        qemu_co_mutex_unlock(&s->lock);
         trace_qcow2_writev_data(qemu_coroutine_self(),
                                 (cluster_offset >> 9) + index_in_cluster);
         ret = bdrv_co_writev(bs->file,
@@ -893,26 +757,13 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
             goto fail;
         }
 
-        while (l2meta != NULL) {
-            QCowL2Meta *next;
-
-            ret = qcow2_alloc_cluster_link_l2(bs, l2meta);
-            if (ret < 0) {
-                goto fail;
-            }
-
-            /* Take the request off the list of running requests */
-            if (l2meta->nb_clusters != 0) {
-                QLIST_REMOVE(l2meta, next_in_flight);
-            }
-
-            qemu_co_queue_restart_all(&l2meta->dependent_requests);
-
-            next = l2meta->next;
-            g_free(l2meta);
-            l2meta = next;
+        ret = qcow2_alloc_cluster_link_l2(bs, &l2meta);
+        if (ret < 0) {
+            goto fail;
         }
 
+        run_dependent_requests(s, &l2meta);
+
         remaining_sectors -= cur_nr_sectors;
         sector_num += cur_nr_sectors;
         bytes_done += cur_nr_sectors * 512;
@@ -921,21 +772,10 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
     ret = 0;
 
 fail:
+    run_dependent_requests(s, &l2meta);
+
     qemu_co_mutex_unlock(&s->lock);
 
-    while (l2meta != NULL) {
-        QCowL2Meta *next;
-
-        if (l2meta->nb_clusters != 0) {
-            QLIST_REMOVE(l2meta, next_in_flight);
-        }
-        qemu_co_queue_restart_all(&l2meta->dependent_requests);
-
-        next = l2meta->next;
-        g_free(l2meta);
-        l2meta = next;
-    }
-
     qemu_iovec_destroy(&hd_qiov);
     qemu_vfree(cluster_data);
     trace_qcow2_writev_done_req(qemu_coroutine_self(), ret);
@@ -951,8 +791,6 @@ static void qcow2_close(BlockDriverState *bs)
     qcow2_cache_flush(bs, s->l2_table_cache);
     qcow2_cache_flush(bs, s->refcount_block_cache);
 
-    qcow2_mark_clean(bs);
-
     qcow2_cache_destroy(bs, s->l2_table_cache);
     qcow2_cache_destroy(bs, s->refcount_block_cache);
 
@@ -972,7 +810,6 @@ static void qcow2_invalidate_cache(BlockDriverState *bs)
     AES_KEY aes_encrypt_key;
     AES_KEY aes_decrypt_key;
     uint32_t crypt_method = 0;
-    QDict *options;
 
     /*
      * Backing files are read-only which makes all of their metadata immutable,
@@ -987,14 +824,8 @@ static void qcow2_invalidate_cache(BlockDriverState *bs)
 
     qcow2_close(bs);
 
-    options = qdict_new();
-    qdict_put(options, QCOW2_OPT_LAZY_REFCOUNTS,
-              qbool_from_int(s->use_lazy_refcounts));
-
     memset(s, 0, sizeof(BDRVQcowState));
-    qcow2_open(bs, options, flags);
-
-    QDECREF(options);
+    qcow2_open(bs, flags);
 
     if (crypt_method) {
         s->crypt_method = crypt_method;
@@ -1124,16 +955,7 @@ int qcow2_update_header(BlockDriverState *bs)
 
     /* Feature table */
     Qcow2Feature features[] = {
-        {
-            .type = QCOW2_FEAT_TYPE_INCOMPATIBLE,
-            .bit  = QCOW2_INCOMPAT_DIRTY_BITNR,
-            .name = "dirty bit",
-        },
-        {
-            .type = QCOW2_FEAT_TYPE_COMPATIBLE,
-            .bit  = QCOW2_COMPAT_LAZY_REFCOUNTS_BITNR,
-            .name = "lazy refcounts",
-        },
+        /* no feature defined yet */
     };
 
     ret = header_ext_add(buf, QCOW2_EXT_MAGIC_FEATURE_TABLE,
@@ -1173,7 +995,6 @@ int qcow2_update_header(BlockDriverState *bs)
             goto fail;
         }
 
-        /* Using strncpy is ok here, since buf is not NUL-terminated. */
         strncpy(buf, bs->backing_file, buflen);
 
         header->backing_file_offset = cpu_to_be64(buf - ((char*) header));
@@ -1205,34 +1026,31 @@ static int preallocate(BlockDriverState *bs)
 {
     uint64_t nb_sectors;
     uint64_t offset;
-    uint64_t host_offset = 0;
     int num;
     int ret;
-    QCowL2Meta *meta;
+    QCowL2Meta meta;
 
     nb_sectors = bdrv_getlength(bs) >> 9;
     offset = 0;
+    qemu_co_queue_init(&meta.dependent_requests);
+    meta.cluster_offset = 0;
 
     while (nb_sectors) {
         num = MIN(nb_sectors, INT_MAX >> 9);
-        ret = qcow2_alloc_cluster_offset(bs, offset, 0, num, &num,
-                                         &host_offset, &meta);
+        ret = qcow2_alloc_cluster_offset(bs, offset, 0, num, &num, &meta);
         if (ret < 0) {
             return ret;
         }
 
-        ret = qcow2_alloc_cluster_link_l2(bs, meta);
+        ret = qcow2_alloc_cluster_link_l2(bs, &meta);
         if (ret < 0) {
-            qcow2_free_any_clusters(bs, meta->alloc_offset, meta->nb_clusters,
-                                    QCOW2_DISCARD_NEVER);
+            qcow2_free_any_clusters(bs, meta.cluster_offset, meta.nb_clusters);
             return ret;
         }
 
         /* There are no dependent requests, but we need to remove our request
          * from the list of in-flight requests */
-        if (meta != NULL) {
-            QLIST_REMOVE(meta, next_in_flight);
-        }
+        run_dependent_requests(bs->opaque, &meta);
 
         /* TODO Preallocate data if requested */
 
@@ -1245,10 +1063,10 @@ static int preallocate(BlockDriverState *bs)
      * all of the allocated clusters (otherwise we get failing reads after
      * EOF). Extend the image to the last allocated sector.
      */
-    if (host_offset != 0) {
+    if (meta.cluster_offset != 0) {
         uint8_t buf[512];
         memset(buf, 0, 512);
-        ret = bdrv_write(bs->file, (host_offset >> 9) + num - 1, buf, 1);
+        ret = bdrv_write(bs->file, (meta.cluster_offset >> 9) + num - 1, buf, 1);
         if (ret < 0) {
             return ret;
         }
@@ -1296,7 +1114,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
         return ret;
     }
 
-    ret = bdrv_file_open(&bs, filename, NULL, BDRV_O_RDWR);
+    ret = bdrv_file_open(&bs, filename, BDRV_O_RDWR);
     if (ret < 0) {
         return ret;
     }
@@ -1320,11 +1138,6 @@ static int qcow2_create2(const char *filename, int64_t total_size,
         header.crypt_method = cpu_to_be32(QCOW_CRYPT_NONE);
     }
 
-    if (flags & BLOCK_FLAG_LAZY_REFCOUNTS) {
-        header.compatible_features |=
-            cpu_to_be64(QCOW2_COMPAT_LAZY_REFCOUNTS);
-    }
-
     ret = bdrv_pwrite(bs, 0, &header, sizeof(header));
     if (ret < 0) {
         goto out;
@@ -1348,7 +1161,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
      */
     BlockDriver* drv = bdrv_find_format("qcow2");
     assert(drv != NULL);
-    ret = bdrv_open(bs, filename, NULL,
+    ret = bdrv_open(bs, filename,
         BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH, drv);
     if (ret < 0) {
         goto out;
@@ -1438,8 +1251,6 @@ static int qcow2_create(const char *filename, QEMUOptionParameter *options)
                     options->value.s);
                 return -EINVAL;
             }
-        } else if (!strcmp(options->name, BLOCK_OPT_LAZY_REFCOUNTS)) {
-            flags |= options->value.n ? BLOCK_FLAG_LAZY_REFCOUNTS : 0;
         }
         options++;
     }
@@ -1450,12 +1261,6 @@ static int qcow2_create(const char *filename, QEMUOptionParameter *options)
         return -EINVAL;
     }
 
-    if (version < 3 && (flags & BLOCK_FLAG_LAZY_REFCOUNTS)) {
-        fprintf(stderr, "Lazy refcounts only supported with compatibility "
-                "level 1.1 and above (use compat=1.1 or greater)\n");
-        return -EINVAL;
-    }
-
     return qcow2_create2(filename, sectors, backing_file, backing_fmt, flags,
                          cluster_size, prealloc, options, version);
 }
@@ -1516,8 +1321,7 @@ static coroutine_fn int qcow2_co_discard(BlockDriverState *bs,
 static int qcow2_truncate(BlockDriverState *bs, int64_t offset)
 {
     BDRVQcowState *s = bs->opaque;
-    int64_t new_l1_size;
-    int ret;
+    int ret, new_l1_size;
 
     if (offset & 511) {
         error_report("The new size must be a multiple of 512");
@@ -1574,21 +1378,8 @@ static int qcow2_write_compressed(BlockDriverState *bs, int64_t sector_num,
         return 0;
     }
 
-    if (nb_sectors != s->cluster_sectors) {
-        ret = -EINVAL;
-
-        /* Zero-pad last write if image size is not cluster aligned */
-        if (sector_num + nb_sectors == bs->total_sectors &&
-            nb_sectors < s->cluster_sectors) {
-            uint8_t *pad_buf = qemu_blockalign(bs, s->cluster_size);
-            memset(pad_buf, 0, s->cluster_size);
-            memcpy(pad_buf, buf, nb_sectors * BDRV_SECTOR_SIZE);
-            ret = qcow2_write_compressed(bs, sector_num,
-                                         pad_buf, s->cluster_sectors);
-            qemu_vfree(pad_buf);
-        }
-        return ret;
-    }
+    if (nb_sectors != s->cluster_sectors)
+        return -EINVAL;
 
     out_buf = g_malloc(s->cluster_size + (s->cluster_size / 1000) + 128);
 
@@ -1656,12 +1447,10 @@ static coroutine_fn int qcow2_co_flush_to_os(BlockDriverState *bs)
         return ret;
     }
 
-    if (qcow2_need_accurate_refcounts(s)) {
-        ret = qcow2_cache_flush(bs, s->refcount_block_cache);
-        if (ret < 0) {
-            qemu_co_mutex_unlock(&s->lock);
-            return ret;
-        }
+    ret = qcow2_cache_flush(bs, s->refcount_block_cache);
+    if (ret < 0) {
+        qemu_co_mutex_unlock(&s->lock);
+        return ret;
     }
     qemu_co_mutex_unlock(&s->lock);
 
@@ -1681,6 +1470,12 @@ static int qcow2_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
     return 0;
 }
 
+
+static int qcow2_check(BlockDriverState *bs, BdrvCheckResult *result)
+{
+    return qcow2_check_refcounts(bs, result);
+}
+
 #if 0
 static void dump_refcounts(BlockDriverState *bs)
 {
@@ -1702,8 +1497,8 @@ static void dump_refcounts(BlockDriverState *bs)
 }
 #endif
 
-static int qcow2_save_vmstate(BlockDriverState *bs, QEMUIOVector *qiov,
-                              int64_t pos)
+static int qcow2_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
+                              int64_t pos, int size)
 {
     BDRVQcowState *s = bs->opaque;
     int growable = bs->growable;
@@ -1711,7 +1506,7 @@ static int qcow2_save_vmstate(BlockDriverState *bs, QEMUIOVector *qiov,
 
     BLKDBG_EVENT(bs->file, BLKDBG_VMSTATE_SAVE);
     bs->growable = 1;
-    ret = bdrv_pwritev(bs, qcow2_vm_state_offset(s) + pos, qiov);
+    ret = bdrv_pwrite(bs, qcow2_vm_state_offset(s) + pos, buf, size);
     bs->growable = growable;
 
     return ret;
@@ -1769,11 +1564,6 @@ static QEMUOptionParameter qcow2_create_options[] = {
         .type = OPT_STRING,
         .help = "Preallocation mode (allowed values: off, metadata)"
     },
-    {
-        .name = BLOCK_OPT_LAZY_REFCOUNTS,
-        .type = OPT_FLAG,
-        .help = "Postpone refcount updates",
-    },
     { NULL }
 };
 
@@ -1783,9 +1573,7 @@ static BlockDriver bdrv_qcow2 = {
     .bdrv_probe         = qcow2_probe,
     .bdrv_open          = qcow2_open,
     .bdrv_close         = qcow2_close,
-    .bdrv_reopen_prepare  = qcow2_reopen_prepare,
     .bdrv_create        = qcow2_create,
-    .bdrv_has_zero_init = bdrv_has_zero_init_1,
     .bdrv_co_is_allocated = qcow2_co_is_allocated,
     .bdrv_set_key       = qcow2_set_key,
     .bdrv_make_empty    = qcow2_make_empty,

block/qcow2.h

@@ -25,8 +25,8 @@
 #ifndef BLOCK_QCOW2_H
 #define BLOCK_QCOW2_H
 
-#include "qemu/aes.h"
-#include "block/coroutine.h"
+#include "aes.h"
+#include "qemu-coroutine.h"
 
 //#define DEBUG_ALLOC
 //#define DEBUG_ALLOC2
@@ -58,12 +58,6 @@
 
 #define DEFAULT_CLUSTER_SIZE 65536
 
-
-#define QCOW2_OPT_LAZY_REFCOUNTS "lazy-refcounts"
-#define QCOW2_OPT_DISCARD_REQUEST "pass-discard-request"
-#define QCOW2_OPT_DISCARD_SNAPSHOT "pass-discard-snapshot"
-#define QCOW2_OPT_DISCARD_OTHER "pass-discard-other"
-
 typedef struct QCowHeader {
     uint32_t magic;
     uint32_t version;
@@ -116,44 +110,12 @@ enum {
     QCOW2_FEAT_TYPE_AUTOCLEAR       = 2,
 };
 
-/* Incompatible feature bits */
-enum {
-    QCOW2_INCOMPAT_DIRTY_BITNR   = 0,
-    QCOW2_INCOMPAT_DIRTY         = 1 << QCOW2_INCOMPAT_DIRTY_BITNR,
-
-    QCOW2_INCOMPAT_MASK          = QCOW2_INCOMPAT_DIRTY,
-};
-
-/* Compatible feature bits */
-enum {
-    QCOW2_COMPAT_LAZY_REFCOUNTS_BITNR = 0,
-    QCOW2_COMPAT_LAZY_REFCOUNTS       = 1 << QCOW2_COMPAT_LAZY_REFCOUNTS_BITNR,
-
-    QCOW2_COMPAT_FEAT_MASK            = QCOW2_COMPAT_LAZY_REFCOUNTS,
-};
-
-enum qcow2_discard_type {
-    QCOW2_DISCARD_NEVER = 0,
-    QCOW2_DISCARD_ALWAYS,
-    QCOW2_DISCARD_REQUEST,
-    QCOW2_DISCARD_SNAPSHOT,
-    QCOW2_DISCARD_OTHER,
-    QCOW2_DISCARD_MAX
-};
-
 typedef struct Qcow2Feature {
     uint8_t type;
     uint8_t bit;
     char    name[46];
 } QEMU_PACKED Qcow2Feature;
 
-typedef struct Qcow2DiscardRegion {
-    BlockDriverState *bs;
-    uint64_t offset;
-    uint64_t bytes;
-    QTAILQ_ENTRY(Qcow2DiscardRegion) next;
-} Qcow2DiscardRegion;
-
 typedef struct BDRVQcowState {
     int cluster_bits;
     int cluster_size;
@@ -195,9 +157,6 @@ typedef struct BDRVQcowState {
 
     int flags;
     int qcow_version;
-    bool use_lazy_refcounts;
-
-    bool discard_passthrough[QCOW2_DISCARD_MAX];
 
     uint64_t incompatible_features;
     uint64_t compatible_features;
@@ -206,8 +165,6 @@ typedef struct BDRVQcowState {
     size_t unknown_header_fields_size;
     void* unknown_header_fields;
     QLIST_HEAD(, Qcow2UnknownHeaderExtension) unknown_header_ext;
-    QTAILQ_HEAD (, Qcow2DiscardRegion) discards;
-    bool cache_discards;
 } BDRVQcowState;
 
 /* XXX: use std qcow open function ? */
@@ -223,59 +180,17 @@ typedef struct QCowCreateState {
 
 struct QCowAIOCB;
 
-typedef struct Qcow2COWRegion {
-    /**
-     * Offset of the COW region in bytes from the start of the first cluster
-     * touched by the request.
-     */
-    uint64_t    offset;
-
-    /** Number of sectors to copy */
-    int         nb_sectors;
-} Qcow2COWRegion;
-
-/**
- * Describes an in-flight (part of a) write request that writes to clusters
- * that are not referenced in their L2 table yet.
- */
+/* XXX This could be private for qcow2-cluster.c */
 typedef struct QCowL2Meta
 {
-    /** Guest offset of the first newly allocated cluster */
     uint64_t offset;
-
-    /** Host offset of the first newly allocated cluster */
+    uint64_t cluster_offset;
     uint64_t alloc_offset;
-
-    /**
-     * Number of sectors from the start of the first allocated cluster to
-     * the end of the (possibly shortened) request
-     */
+    int n_start;
     int nb_available;
-
-    /** Number of newly allocated clusters */
     int nb_clusters;
-
-    /**
-     * Requests that overlap with this allocation and wait to be restarted
-     * when the allocating request has completed.
-     */
     CoQueue dependent_requests;
 
-    /**
-     * The COW Region between the start of the first allocated cluster and the
-     * area the guest actually writes to.
-     */
-    Qcow2COWRegion cow_start;
-
-    /**
-     * The COW Region between the area the guest actually writes to and the
-     * end of the last allocated cluster.
-     */
-    Qcow2COWRegion cow_end;
-
-    /** Pointer to next L2Meta of the same write request */
-    struct QCowL2Meta *next;
-
     QLIST_ENTRY(QCowL2Meta) next_in_flight;
 } QCowL2Meta;
 
@@ -292,32 +207,17 @@ enum {
 
 #define REFT_OFFSET_MASK 0xffffffffffffff00ULL
 
-static inline int64_t start_of_cluster(BDRVQcowState *s, int64_t offset)
-{
-    return offset & ~(s->cluster_size - 1);
-}
-
-static inline int64_t offset_into_cluster(BDRVQcowState *s, int64_t offset)
-{
-    return offset & (s->cluster_size - 1);
-}
-
 static inline int size_to_clusters(BDRVQcowState *s, int64_t size)
 {
     return (size + (s->cluster_size - 1)) >> s->cluster_bits;
 }
 
-static inline int64_t size_to_l1(BDRVQcowState *s, int64_t size)
+static inline int size_to_l1(BDRVQcowState *s, int64_t size)
 {
     int shift = s->cluster_bits + s->l2_bits;
     return (size + (1ULL << shift) - 1) >> shift;
 }
 
-static inline int offset_to_l2_index(BDRVQcowState *s, int64_t offset)
-{
-    return (offset >> s->cluster_bits) & (s->l2_size - 1);
-}
-
 static inline int64_t align_offset(int64_t offset, int n)
 {
     offset = (offset + n - 1) & ~(n - 1);
@@ -337,30 +237,12 @@ static inline int qcow2_get_cluster_type(uint64_t l2_entry)
     }
 }
 
-/* Check whether refcounts are eager or lazy */
-static inline bool qcow2_need_accurate_refcounts(BDRVQcowState *s)
-{
-    return !(s->incompatible_features & QCOW2_INCOMPAT_DIRTY);
-}
-
-static inline uint64_t l2meta_cow_start(QCowL2Meta *m)
-{
-    return m->offset + m->cow_start.offset;
-}
-
-static inline uint64_t l2meta_cow_end(QCowL2Meta *m)
-{
-    return m->offset + m->cow_end.offset
-        + (m->cow_end.nb_sectors << BDRV_SECTOR_BITS);
-}
 
 // FIXME Need qcow2_ prefix to global functions
 
 /* qcow2.c functions */
 int qcow2_backing_read1(BlockDriverState *bs, QEMUIOVector *qiov,
                   int64_t sector_num, int nb_sectors);
-
-int qcow2_mark_dirty(BlockDriverState *bs);
 int qcow2_update_header(BlockDriverState *bs);
 
 /* qcow2-refcount.c functions */
@@ -372,22 +254,17 @@ int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
     int nb_clusters);
 int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size);
 void qcow2_free_clusters(BlockDriverState *bs,
-                          int64_t offset, int64_t size,
-                          enum qcow2_discard_type type);
-void qcow2_free_any_clusters(BlockDriverState *bs, uint64_t l2_entry,
-                             int nb_clusters, enum qcow2_discard_type type);
+    int64_t offset, int64_t size);
+void qcow2_free_any_clusters(BlockDriverState *bs,
+    uint64_t cluster_offset, int nb_clusters);
 
 int qcow2_update_snapshot_refcount(BlockDriverState *bs,
     int64_t l1_table_offset, int l1_size, int addend);
 
-int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
-                          BdrvCheckMode fix);
-
-void qcow2_process_discards(BlockDriverState *bs, int ret);
+int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res);
 
 /* qcow2-cluster.c functions */
-int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
-                        bool exact_size);
+int qcow2_grow_l1_table(BlockDriverState *bs, int min_size, bool exact_size);
 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,
@@ -398,7 +275,7 @@ void qcow2_encrypt_sectors(BDRVQcowState *s, int64_t sector_num,
 int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
     int *num, uint64_t *cluster_offset);
 int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
-    int n_start, int n_end, int *num, uint64_t *host_offset, QCowL2Meta **m);
+    int n_start, int n_end, int *num, QCowL2Meta *m);
 uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
                                          uint64_t offset,
                                          int compressed_size);
@@ -419,8 +296,11 @@ void qcow2_free_snapshots(BlockDriverState *bs);
 int qcow2_read_snapshots(BlockDriverState *bs);
 
 /* qcow2-cache.c functions */
-Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables);
+Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables,
+    bool writethrough);
 int qcow2_cache_destroy(BlockDriverState* bs, Qcow2Cache *c);
+bool qcow2_cache_set_writethrough(BlockDriverState *bs, Qcow2Cache *c,
+    bool enable);
 
 void qcow2_cache_entry_mark_dirty(Qcow2Cache *c, void *table);
 int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c);

block/qed-check.c

@@ -87,7 +87,6 @@ static unsigned int qed_check_l2_table(QEDCheck *check, QEDTable *table)
         if (!qed_check_cluster_offset(s, offset)) {
             if (check->fix) {
                 table->offsets[i] = 0;
-                check->result->corruptions_fixed++;
             } else {
                 check->result->corruptions++;
             }
@@ -128,7 +127,6 @@ static int qed_check_l1_table(QEDCheck *check, QEDTable *table)
             /* Clear invalid offset */
             if (check->fix) {
                 table->offsets[i] = 0;
-                check->result->corruptions_fixed++;
             } else {
                 check->result->corruptions++;
             }
@@ -194,28 +192,6 @@ static void qed_check_for_leaks(QEDCheck *check)
     }
 }
 
-/**
- * Mark an image clean once it passes check or has been repaired
- */
-static void qed_check_mark_clean(BDRVQEDState *s, BdrvCheckResult *result)
-{
-    /* Skip if there were unfixable corruptions or I/O errors */
-    if (result->corruptions > 0 || result->check_errors > 0) {
-        return;
-    }
-
-    /* Skip if image is already marked clean */
-    if (!(s->header.features & QED_F_NEED_CHECK)) {
-        return;
-    }
-
-    /* Ensure fixes reach storage before clearing check bit */
-    bdrv_flush(s->bs);
-
-    s->header.features &= ~QED_F_NEED_CHECK;
-    qed_write_header_sync(s);
-}
-
 int qed_check(BDRVQEDState *s, BdrvCheckResult *result, bool fix)
 {
     QEDCheck check = {
@@ -237,10 +213,6 @@ int qed_check(BDRVQEDState *s, BdrvCheckResult *result, bool fix)
     if (ret == 0) {
         /* Only check for leaks if entire image was scanned successfully */
         qed_check_for_leaks(&check);
-
-        if (fix) {
-            qed_check_mark_clean(s, result);
-        }
     }
 
     g_free(check.used_clusters);

block/qed-table.c

@@ -13,7 +13,7 @@
  */
 
 #include "trace.h"
-#include "qemu/sockets.h" /* for EINPROGRESS on Windows */
+#include "qemu_socket.h" /* for EINPROGRESS on Windows */
 #include "qed.h"
 
 typedef struct {
@@ -103,6 +103,7 @@ static void qed_write_table_cb(void *opaque, int ret)
 out:
     qemu_vfree(write_table_cb->table);
     gencb_complete(&write_table_cb->gencb, ret);
+    return;
 }
 
 /**

block/qed.c

@@ -12,11 +12,11 @@
  *
  */
 
-#include "qemu/timer.h"
+#include "qemu-timer.h"
 #include "trace.h"
 #include "qed.h"
-#include "qapi/qmp/qerror.h"
-#include "migration/migration.h"
+#include "qerror.h"
+#include "migration.h"
 
 static void qed_aio_cancel(BlockDriverAIOCB *blockacb)
 {
@@ -30,7 +30,7 @@ static void qed_aio_cancel(BlockDriverAIOCB *blockacb)
     }
 }
 
-static const AIOCBInfo qed_aiocb_info = {
+static AIOPool qed_aio_pool = {
     .aiocb_size         = sizeof(QEDAIOCB),
     .cancel             = qed_aio_cancel,
 };
@@ -89,7 +89,7 @@ static void qed_header_cpu_to_le(const QEDHeader *cpu, QEDHeader *le)
     le->backing_filename_size = cpu_to_le32(cpu->backing_filename_size);
 }
 
-int qed_write_header_sync(BDRVQEDState *s)
+static int qed_write_header_sync(BDRVQEDState *s)
 {
     QEDHeader le;
     int ret;
@@ -373,7 +373,7 @@ static void bdrv_qed_rebind(BlockDriverState *bs)
     s->bs = bs;
 }
 
-static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags)
+static int bdrv_qed_open(BlockDriverState *bs, int flags)
 {
     BDRVQEDState *s = bs->opaque;
     QEDHeader le_header;
@@ -390,7 +390,7 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags)
     qed_header_le_to_cpu(&le_header, &s->header);
 
     if (s->header.magic != QED_MAGIC) {
-        return -EMEDIUMTYPE;
+        return -EINVAL;
     }
     if (s->header.features & ~QED_FEATURE_MASK) {
         /* image uses unsupported feature bits */
@@ -477,7 +477,7 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags)
     }
 
     /* If image was not closed cleanly, check consistency */
-    if (!(flags & BDRV_O_CHECK) && (s->header.features & QED_F_NEED_CHECK)) {
+    if (s->header.features & QED_F_NEED_CHECK) {
         /* Read-only images cannot be fixed.  There is no risk of corruption
          * since write operations are not possible.  Therefore, allow
          * potentially inconsistent images to be opened read-only.  This can
@@ -491,6 +491,13 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags)
             if (ret) {
                 goto out;
             }
+            if (!result.corruptions && !result.check_errors) {
+                /* Ensure fixes reach storage before clearing check bit */
+                bdrv_flush(s->bs);
+
+                s->header.features &= ~QED_F_NEED_CHECK;
+                qed_write_header_sync(s);
+            }
         }
     }
 
@@ -505,14 +512,6 @@ out:
     return ret;
 }
 
-/* We have nothing to do for QED reopen, stubs just return
- * success */
-static int bdrv_qed_reopen_prepare(BDRVReopenState *state,
-                                   BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
-}
-
 static void bdrv_qed_close(BlockDriverState *bs)
 {
     BDRVQEDState *s = bs->opaque;
@@ -558,7 +557,7 @@ static int qed_create(const char *filename, uint32_t cluster_size,
         return ret;
     }
 
-    ret = bdrv_file_open(&bs, filename, NULL, BDRV_O_RDWR | BDRV_O_CACHE_WB);
+    ret = bdrv_file_open(&bs, filename, BDRV_O_RDWR | BDRV_O_CACHE_WB);
     if (ret < 0) {
         return ret;
     }
@@ -737,7 +736,7 @@ static void qed_read_backing_file(BDRVQEDState *s, uint64_t pos,
     /* Zero all sectors if reading beyond the end of the backing file */
     if (pos >= backing_length ||
         pos + qiov->size > backing_length) {
-        qemu_iovec_memset(qiov, 0, 0, qiov->size);
+        qemu_iovec_memset(qiov, 0, qiov->size);
     }
 
     /* Complete now if there are no backing file sectors to read */
@@ -749,7 +748,7 @@ 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);
 
-    BLKDBG_EVENT(s->bs->file, BLKDBG_READ_BACKING_AIO);
+    BLKDBG_EVENT(s->bs->file, BLKDBG_READ_BACKING);
     bdrv_aio_readv(s->bs->backing_hd, pos / BDRV_SECTOR_SIZE,
                    qiov, size / BDRV_SECTOR_SIZE, cb, opaque);
 }
@@ -1132,7 +1131,7 @@ static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len)
 
     acb->cur_nclusters = qed_bytes_to_clusters(s,
             qed_offset_into_cluster(s, acb->cur_pos) + len);
-    qemu_iovec_concat(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
+    qemu_iovec_copy(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
 
     if (acb->flags & QED_AIOCB_ZERO) {
         /* Skip ahead if the clusters are already zero */
@@ -1178,7 +1177,7 @@ static void qed_aio_write_inplace(QEDAIOCB *acb, uint64_t offset, size_t len)
 
     /* Calculate the I/O vector */
     acb->cur_cluster = offset;
-    qemu_iovec_concat(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
+    qemu_iovec_copy(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
 
     /* Do the actual write */
     qed_aio_write_main(acb, 0);
@@ -1248,11 +1247,11 @@ static void qed_aio_read_data(void *opaque, int ret,
         goto err;
     }
 
-    qemu_iovec_concat(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
+    qemu_iovec_copy(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
 
     /* Handle zero cluster and backing file reads */
     if (ret == QED_CLUSTER_ZERO) {
-        qemu_iovec_memset(&acb->cur_qiov, 0, 0, acb->cur_qiov.size);
+        qemu_iovec_memset(&acb->cur_qiov, 0, acb->cur_qiov.size);
         qed_aio_next_io(acb, 0);
         return;
     } else if (ret != QED_CLUSTER_FOUND) {
@@ -1311,7 +1310,7 @@ static BlockDriverAIOCB *qed_aio_setup(BlockDriverState *bs,
                                        BlockDriverCompletionFunc *cb,
                                        void *opaque, int flags)
 {
-    QEDAIOCB *acb = qemu_aio_get(&qed_aiocb_info, bs, cb, opaque);
+    QEDAIOCB *acb = qemu_aio_get(&qed_aio_pool, bs, cb, opaque);
 
     trace_qed_aio_setup(bs->opaque, acb, sector_num, nb_sectors,
                         opaque, flags);
@@ -1371,21 +1370,10 @@ static int coroutine_fn bdrv_qed_co_write_zeroes(BlockDriverState *bs,
                                                  int nb_sectors)
 {
     BlockDriverAIOCB *blockacb;
-    BDRVQEDState *s = bs->opaque;
     QEDWriteZeroesCB cb = { .done = false };
     QEMUIOVector qiov;
     struct iovec iov;
 
-    /* Refuse if there are untouched backing file sectors */
-    if (bs->backing_hd) {
-        if (qed_offset_into_cluster(s, sector_num * BDRV_SECTOR_SIZE) != 0) {
-            return -ENOTSUP;
-        }
-        if (qed_offset_into_cluster(s, nb_sectors * BDRV_SECTOR_SIZE) != 0) {
-            return -ENOTSUP;
-        }
-    }
-
     /* Zero writes start without an I/O buffer.  If a buffer becomes necessary
      * then it will be allocated during request processing.
      */
@@ -1526,15 +1514,14 @@ static void bdrv_qed_invalidate_cache(BlockDriverState *bs)
 
     bdrv_qed_close(bs);
     memset(s, 0, sizeof(BDRVQEDState));
-    bdrv_qed_open(bs, NULL, bs->open_flags);
+    bdrv_qed_open(bs, bs->open_flags);
 }
 
-static int bdrv_qed_check(BlockDriverState *bs, BdrvCheckResult *result,
-                          BdrvCheckMode fix)
+static int bdrv_qed_check(BlockDriverState *bs, BdrvCheckResult *result)
 {
     BDRVQEDState *s = bs->opaque;
 
-    return qed_check(s, result, !!fix);
+    return qed_check(s, result, false);
 }
 
 static QEMUOptionParameter qed_create_options[] = {
@@ -1572,9 +1559,7 @@ static BlockDriver bdrv_qed = {
     .bdrv_rebind              = bdrv_qed_rebind,
     .bdrv_open                = bdrv_qed_open,
     .bdrv_close               = bdrv_qed_close,
-    .bdrv_reopen_prepare      = bdrv_qed_reopen_prepare,
     .bdrv_create              = bdrv_qed_create,
-    .bdrv_has_zero_init       = bdrv_has_zero_init_1,
     .bdrv_co_is_allocated     = bdrv_qed_co_is_allocated,
     .bdrv_make_empty          = bdrv_qed_make_empty,
     .bdrv_aio_readv           = bdrv_qed_aio_readv,

block/qed.h

@@ -15,7 +15,7 @@
 #ifndef BLOCK_QED_H
 #define BLOCK_QED_H
 
-#include "block/block_int.h"
+#include "block_int.h"
 
 /* The layout of a QED file is as follows:
  *
@@ -210,11 +210,6 @@ typedef struct {
 void *gencb_alloc(size_t len, BlockDriverCompletionFunc *cb, void *opaque);
 void gencb_complete(void *opaque, int ret);
 
-/**
- * Header functions
- */
-int qed_write_header_sync(BDRVQEDState *s);
-
 /**
  * L2 cache functions
  */

block/raw-posix-aio.h

@@ -1,5 +1,5 @@
 /*
- * Declarations for AIO in the raw protocol
+ * QEMU Posix block I/O backend AIO support
  *
  * Copyright IBM, Corp. 2008
  *
@@ -12,40 +12,34 @@
  * Contributions after 2012-01-13 are licensed under the terms of the
  * GNU GPL, version 2 or (at your option) any later version.
  */
-#ifndef QEMU_RAW_AIO_H
-#define QEMU_RAW_AIO_H
+#ifndef QEMU_RAW_POSIX_AIO_H
+#define QEMU_RAW_POSIX_AIO_H
 
 /* AIO request types */
 #define QEMU_AIO_READ         0x0001
 #define QEMU_AIO_WRITE        0x0002
 #define QEMU_AIO_IOCTL        0x0004
 #define QEMU_AIO_FLUSH        0x0008
-#define QEMU_AIO_DISCARD      0x0010
 #define QEMU_AIO_TYPE_MASK \
-        (QEMU_AIO_READ|QEMU_AIO_WRITE|QEMU_AIO_IOCTL|QEMU_AIO_FLUSH| \
-         QEMU_AIO_DISCARD)
+	(QEMU_AIO_READ|QEMU_AIO_WRITE|QEMU_AIO_IOCTL|QEMU_AIO_FLUSH)
 
 /* AIO flags */
 #define QEMU_AIO_MISALIGNED   0x1000
-#define QEMU_AIO_BLKDEV       0x2000
 
 
+/* posix-aio-compat.c - thread pool based implementation */
+int paio_init(void);
+BlockDriverAIOCB *paio_submit(BlockDriverState *bs, int fd,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockDriverCompletionFunc *cb, void *opaque, int type);
+BlockDriverAIOCB *paio_ioctl(BlockDriverState *bs, int fd,
+        unsigned long int req, void *buf,
+        BlockDriverCompletionFunc *cb, void *opaque);
+
 /* linux-aio.c - Linux native implementation */
-#ifdef CONFIG_LINUX_AIO
 void *laio_init(void);
 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);
-#endif
 
-#ifdef _WIN32
-typedef struct QEMUWin32AIOState QEMUWin32AIOState;
-QEMUWin32AIOState *win32_aio_init(void);
-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);
-#endif
-
-#endif /* QEMU_RAW_AIO_H */
+#endif /* QEMU_RAW_POSIX_AIO_H */

block/raw-win32.c

@@ -22,13 +22,9 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "qemu/timer.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
-#include "raw-aio.h"
-#include "trace.h"
-#include "block/thread-pool.h"
-#include "qemu/iov.h"
+#include "qemu-timer.h"
+#include "block_int.h"
+#include "module.h"
 #include <windows.h>
 #include <winioctl.h>
 
@@ -36,132 +32,12 @@
 #define FTYPE_CD     1
 #define FTYPE_HARDDISK 2
 
-static QEMUWin32AIOState *aio;
-
-typedef struct RawWin32AIOData {
-    BlockDriverState *bs;
-    HANDLE hfile;
-    struct iovec *aio_iov;
-    int aio_niov;
-    size_t aio_nbytes;
-    off64_t aio_offset;
-    int aio_type;
-} RawWin32AIOData;
-
 typedef struct BDRVRawState {
     HANDLE hfile;
     int type;
     char drive_path[16]; /* format: "d:\" */
-    QEMUWin32AIOState *aio;
 } BDRVRawState;
 
-/*
- * Read/writes the data to/from a given linear buffer.
- *
- * Returns the number of bytes handles or -errno in case of an error. Short
- * reads are only returned if the end of the file is reached.
- */
-static size_t handle_aiocb_rw(RawWin32AIOData *aiocb)
-{
-    size_t offset = 0;
-    int i;
-
-    for (i = 0; i < aiocb->aio_niov; i++) {
-        OVERLAPPED ov;
-        DWORD ret, ret_count, len;
-
-        memset(&ov, 0, sizeof(ov));
-        ov.Offset = (aiocb->aio_offset + offset);
-        ov.OffsetHigh = (aiocb->aio_offset + offset) >> 32;
-        len = aiocb->aio_iov[i].iov_len;
-        if (aiocb->aio_type & QEMU_AIO_WRITE) {
-            ret = WriteFile(aiocb->hfile, aiocb->aio_iov[i].iov_base,
-                            len, &ret_count, &ov);
-        } else {
-            ret = ReadFile(aiocb->hfile, aiocb->aio_iov[i].iov_base,
-                           len, &ret_count, &ov);
-        }
-        if (!ret) {
-            ret_count = 0;
-        }
-        if (ret_count != len) {
-            break;
-        }
-        offset += len;
-    }
-
-    return offset;
-}
-
-static int aio_worker(void *arg)
-{
-    RawWin32AIOData *aiocb = arg;
-    ssize_t ret = 0;
-    size_t count;
-
-    switch (aiocb->aio_type & QEMU_AIO_TYPE_MASK) {
-    case QEMU_AIO_READ:
-        count = handle_aiocb_rw(aiocb);
-        if (count < aiocb->aio_nbytes && aiocb->bs->growable) {
-            /* A short read means that we have reached EOF. Pad the buffer
-             * with zeros for bytes after EOF. */
-            iov_memset(aiocb->aio_iov, aiocb->aio_niov, count,
-                      0, aiocb->aio_nbytes - count);
-
-            count = aiocb->aio_nbytes;
-        }
-        if (count == aiocb->aio_nbytes) {
-            ret = 0;
-        } else {
-            ret = -EINVAL;
-        }
-        break;
-    case QEMU_AIO_WRITE:
-        count = handle_aiocb_rw(aiocb);
-        if (count == aiocb->aio_nbytes) {
-            count = 0;
-        } else {
-            count = -EINVAL;
-        }
-        break;
-    case QEMU_AIO_FLUSH:
-        if (!FlushFileBuffers(aiocb->hfile)) {
-            return -EIO;
-        }
-        break;
-    default:
-        fprintf(stderr, "invalid aio request (0x%x)\n", aiocb->aio_type);
-        ret = -EINVAL;
-        break;
-    }
-
-    g_slice_free(RawWin32AIOData, aiocb);
-    return ret;
-}
-
-static BlockDriverAIOCB *paio_submit(BlockDriverState *bs, HANDLE hfile,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque, int type)
-{
-    RawWin32AIOData *acb = g_slice_new(RawWin32AIOData);
-    ThreadPool *pool;
-
-    acb->bs = bs;
-    acb->hfile = hfile;
-    acb->aio_type = type;
-
-    if (qiov) {
-        acb->aio_iov = qiov->iov;
-        acb->aio_niov = qiov->niov;
-    }
-    acb->aio_nbytes = nb_sectors * 512;
-    acb->aio_offset = sector_num * 512;
-
-    trace_paio_submit(acb, opaque, sector_num, nb_sectors, type);
-    pool = aio_get_thread_pool(bdrv_get_aio_context(bs));
-    return thread_pool_submit_aio(pool, aio_worker, acb, cb, opaque);
-}
-
 int qemu_ftruncate64(int fd, int64_t length)
 {
     LARGE_INTEGER li;
@@ -201,134 +77,91 @@ static int set_sparse(int fd)
 				 NULL, 0, NULL, 0, &returned, NULL);
 }
 
-static void raw_parse_flags(int flags, int *access_flags, DWORD *overlapped)
-{
-    assert(access_flags != NULL);
-    assert(overlapped != NULL);
-
-    if (flags & BDRV_O_RDWR) {
-        *access_flags = GENERIC_READ | GENERIC_WRITE;
-    } else {
-        *access_flags = GENERIC_READ;
-    }
-
-    *overlapped = FILE_ATTRIBUTE_NORMAL;
-    if (flags & BDRV_O_NATIVE_AIO) {
-        *overlapped |= FILE_FLAG_OVERLAPPED;
-    }
-    if (flags & BDRV_O_NOCACHE) {
-        *overlapped |= FILE_FLAG_NO_BUFFERING;
-    }
-}
-
-static QemuOptsList raw_runtime_opts = {
-    .name = "raw",
-    .head = QTAILQ_HEAD_INITIALIZER(raw_runtime_opts.head),
-    .desc = {
-        {
-            .name = "filename",
-            .type = QEMU_OPT_STRING,
-            .help = "File name of the image",
-        },
-        { /* end of list */ }
-    },
-};
-
-static int raw_open(BlockDriverState *bs, QDict *options, int flags)
+static int raw_open(BlockDriverState *bs, const char *filename, int flags)
 {
     BDRVRawState *s = bs->opaque;
     int access_flags;
     DWORD overlapped;
-    QemuOpts *opts;
-    Error *local_err = NULL;
-    const char *filename;
-    int ret;
 
     s->type = FTYPE_FILE;
 
-    opts = qemu_opts_create_nofail(&raw_runtime_opts);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (error_is_set(&local_err)) {
-        qerror_report_err(local_err);
-        error_free(local_err);
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    filename = qemu_opt_get(opts, "filename");
-
-    raw_parse_flags(flags, &access_flags, &overlapped);
-
-    if ((flags & BDRV_O_NATIVE_AIO) && aio == NULL) {
-        aio = win32_aio_init();
-        if (aio == NULL) {
-            ret = -EINVAL;
-            goto fail;
-        }
+    if (flags & BDRV_O_RDWR) {
+        access_flags = GENERIC_READ | GENERIC_WRITE;
+    } else {
+        access_flags = GENERIC_READ;
     }
 
+    overlapped = FILE_ATTRIBUTE_NORMAL;
+    if (flags & BDRV_O_NOCACHE)
+        overlapped |= FILE_FLAG_NO_BUFFERING;
+    if (!(flags & BDRV_O_CACHE_WB))
+        overlapped |= FILE_FLAG_WRITE_THROUGH;
     s->hfile = CreateFile(filename, access_flags,
                           FILE_SHARE_READ, NULL,
                           OPEN_EXISTING, overlapped, NULL);
     if (s->hfile == INVALID_HANDLE_VALUE) {
         int err = GetLastError();
 
-        if (err == ERROR_ACCESS_DENIED) {
-            ret = -EACCES;
-        } else {
-            ret = -EINVAL;
-        }
-        goto fail;
+        if (err == ERROR_ACCESS_DENIED)
+            return -EACCES;
+        return -1;
     }
-
-    if (flags & BDRV_O_NATIVE_AIO) {
-        ret = win32_aio_attach(aio, s->hfile);
-        if (ret < 0) {
-            CloseHandle(s->hfile);
-            goto fail;
-        }
-        s->aio = aio;
-    }
-
-    ret = 0;
-fail:
-    qemu_opts_del(opts);
-    return ret;
+    return 0;
 }
 
-static BlockDriverAIOCB *raw_aio_readv(BlockDriverState *bs,
-                         int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-                         BlockDriverCompletionFunc *cb, void *opaque)
+static int raw_read(BlockDriverState *bs, int64_t sector_num,
+                    uint8_t *buf, int nb_sectors)
 {
     BDRVRawState *s = bs->opaque;
-    if (s->aio) {
-        return win32_aio_submit(bs, s->aio, s->hfile, sector_num, qiov,
-                                nb_sectors, cb, opaque, QEMU_AIO_READ); 
-    } else {
-        return paio_submit(bs, s->hfile, sector_num, qiov, nb_sectors,
-                           cb, opaque, QEMU_AIO_READ);
-    }
+    OVERLAPPED ov;
+    DWORD ret_count;
+    int ret;
+    int64_t offset = sector_num * 512;
+    int count = nb_sectors * 512;
+
+    memset(&ov, 0, sizeof(ov));
+    ov.Offset = offset;
+    ov.OffsetHigh = offset >> 32;
+    ret = ReadFile(s->hfile, buf, count, &ret_count, &ov);
+    if (!ret)
+        return ret_count;
+    if (ret_count == count)
+        ret_count = 0;
+    return ret_count;
 }
 
-static BlockDriverAIOCB *raw_aio_writev(BlockDriverState *bs,
-                          int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-                          BlockDriverCompletionFunc *cb, void *opaque)
+static int raw_write(BlockDriverState *bs, int64_t sector_num,
+                     const uint8_t *buf, int nb_sectors)
 {
     BDRVRawState *s = bs->opaque;
-    if (s->aio) {
-        return win32_aio_submit(bs, s->aio, s->hfile, sector_num, qiov,
-                                nb_sectors, cb, opaque, QEMU_AIO_WRITE); 
-    } else {
-        return paio_submit(bs, s->hfile, sector_num, qiov, nb_sectors,
-                           cb, opaque, QEMU_AIO_WRITE);
-    }
+    OVERLAPPED ov;
+    DWORD ret_count;
+    int ret;
+    int64_t offset = sector_num * 512;
+    int count = nb_sectors * 512;
+
+    memset(&ov, 0, sizeof(ov));
+    ov.Offset = offset;
+    ov.OffsetHigh = offset >> 32;
+    ret = WriteFile(s->hfile, buf, count, &ret_count, &ov);
+    if (!ret)
+        return ret_count;
+    if (ret_count == count)
+        ret_count = 0;
+    return ret_count;
 }
 
-static BlockDriverAIOCB *raw_aio_flush(BlockDriverState *bs,
-                         BlockDriverCompletionFunc *cb, void *opaque)
+static int raw_flush(BlockDriverState *bs)
 {
     BDRVRawState *s = bs->opaque;
-    return paio_submit(bs, s->hfile, 0, NULL, 0, cb, opaque, QEMU_AIO_FLUSH);
+    int ret;
+
+    ret = FlushFileBuffers(s->hfile);
+    if (ret == 0) {
+        return -EIO;
+    }
+
+    return 0;
 }
 
 static void raw_close(BlockDriverState *bs)
@@ -341,24 +174,13 @@ static int raw_truncate(BlockDriverState *bs, int64_t offset)
 {
     BDRVRawState *s = bs->opaque;
     LONG low, high;
-    DWORD dwPtrLow;
 
     low = offset;
     high = offset >> 32;
-
-    /*
-     * An error has occurred if the return value is INVALID_SET_FILE_POINTER
-     * and GetLastError doesn't return NO_ERROR.
-     */
-    dwPtrLow = SetFilePointer(s->hfile, low, &high, FILE_BEGIN);
-    if (dwPtrLow == INVALID_SET_FILE_POINTER && GetLastError() != NO_ERROR) {
-        fprintf(stderr, "SetFilePointer error: %lu\n", GetLastError());
+    if (!SetFilePointer(s->hfile, low, &high, FILE_BEGIN))
+	return -EIO;
+    if (!SetEndOfFile(s->hfile))
         return -EIO;
-    }
-    if (SetEndOfFile(s->hfile) == 0) {
-        fprintf(stderr, "SetEndOfFile error: %lu\n", GetLastError());
-        return -EIO;
-    }
     return 0;
 }
 
@@ -433,13 +255,13 @@ static int raw_create(const char *filename, QEMUOptionParameter *options)
         options++;
     }
 
-    fd = qemu_open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
-                   0644);
+    fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
+              0644);
     if (fd < 0)
         return -EIO;
     set_sparse(fd);
     ftruncate(fd, total_size * 512);
-    qemu_close(fd);
+    close(fd);
     return 0;
 }
 
@@ -459,11 +281,10 @@ static BlockDriver bdrv_file = {
     .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,
-    .bdrv_aio_writev    = raw_aio_writev,
-    .bdrv_aio_flush     = raw_aio_flush,
+    .bdrv_read              = raw_read,
+    .bdrv_write             = raw_write,
+    .bdrv_co_flush_to_disk  = raw_flush,
 
     .bdrv_truncate	= raw_truncate,
     .bdrv_getlength	= raw_getlength,
@@ -531,13 +352,12 @@ static int hdev_probe_device(const char *filename)
     return 0;
 }
 
-static int hdev_open(BlockDriverState *bs, QDict *options, int flags)
+static int hdev_open(BlockDriverState *bs, const char *filename, int flags)
 {
     BDRVRawState *s = bs->opaque;
     int access_flags, create_flags;
     DWORD overlapped;
     char device_name[64];
-    const char *filename = qdict_get_str(options, "filename");
 
     if (strstart(filename, "/dev/cdrom", NULL)) {
         if (find_cdrom(device_name, sizeof(device_name)) < 0)
@@ -554,10 +374,18 @@ static int hdev_open(BlockDriverState *bs, QDict *options, int flags)
     }
     s->type = find_device_type(bs, filename);
 
-    raw_parse_flags(flags, &access_flags, &overlapped);
-
+    if (flags & BDRV_O_RDWR) {
+        access_flags = GENERIC_READ | GENERIC_WRITE;
+    } else {
+        access_flags = GENERIC_READ;
+    }
     create_flags = OPEN_EXISTING;
 
+    overlapped = FILE_ATTRIBUTE_NORMAL;
+    if (flags & BDRV_O_NOCACHE)
+        overlapped |= FILE_FLAG_NO_BUFFERING;
+    if (!(flags & BDRV_O_CACHE_WB))
+        overlapped |= FILE_FLAG_WRITE_THROUGH;
     s->hfile = CreateFile(filename, access_flags,
                           FILE_SHARE_READ, NULL,
                           create_flags, overlapped, NULL);
@@ -571,6 +399,11 @@ static int hdev_open(BlockDriverState *bs, QDict *options, int flags)
     return 0;
 }
 
+static int hdev_has_zero_init(BlockDriverState *bs)
+{
+    return 0;
+}
+
 static BlockDriver bdrv_host_device = {
     .format_name	= "host_device",
     .protocol_name	= "host_device",
@@ -578,10 +411,11 @@ static BlockDriver bdrv_host_device = {
     .bdrv_probe_device	= hdev_probe_device,
     .bdrv_file_open	= hdev_open,
     .bdrv_close		= raw_close,
+    .bdrv_has_zero_init = hdev_has_zero_init,
 
-    .bdrv_aio_readv     = raw_aio_readv,
-    .bdrv_aio_writev    = raw_aio_writev,
-    .bdrv_aio_flush     = raw_aio_flush,
+    .bdrv_read              = raw_read,
+    .bdrv_write             = raw_write,
+    .bdrv_co_flush_to_disk  = raw_flush,
 
     .bdrv_getlength	= raw_getlength,
     .bdrv_get_allocated_file_size

block/raw.c

@@ -1,33 +1,23 @@
 
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
 
-static int raw_open(BlockDriverState *bs, QDict *options, int flags)
+static int raw_open(BlockDriverState *bs, 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);
 }
 
@@ -35,20 +25,6 @@ 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);
@@ -121,11 +97,6 @@ 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",
 
@@ -135,17 +106,12 @@ static BlockDriver bdrv_raw = {
     .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,

block/rbd.c

@@ -14,8 +14,8 @@
 #include <inttypes.h>
 
 #include "qemu-common.h"
-#include "qemu/error-report.h"
-#include "block/block_int.h"
+#include "qemu-error.h"
+#include "block_int.h"
 
 #include <rbd/librbd.h>
 
@@ -63,14 +63,13 @@
 typedef enum {
     RBD_AIO_READ,
     RBD_AIO_WRITE,
-    RBD_AIO_DISCARD,
-    RBD_AIO_FLUSH
+    RBD_AIO_DISCARD
 } RBDAIOCmd;
 
 typedef struct RBDAIOCB {
     BlockDriverAIOCB common;
     QEMUBH *bh;
-    int64_t ret;
+    int ret;
     QEMUIOVector *qiov;
     char *bounce;
     RBDAIOCmd cmd;
@@ -78,7 +77,6 @@ typedef struct RBDAIOCB {
     int error;
     struct BDRVRBDState *s;
     int cancelled;
-    int status;
 } RBDAIOCB;
 
 typedef struct RADOSCB {
@@ -88,7 +86,7 @@ typedef struct RADOSCB {
     int done;
     int64_t size;
     char *buf;
-    int64_t ret;
+    int ret;
 } RADOSCB;
 
 #define RBD_FD_READ 0
@@ -378,9 +376,16 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
     RBDAIOCB *acb = rcb->acb;
     int64_t r;
 
+    if (acb->cancelled) {
+        qemu_vfree(acb->bounce);
+        qemu_aio_release(acb);
+        goto done;
+    }
+
     r = rcb->ret;
 
-    if (acb->cmd != RBD_AIO_READ) {
+    if (acb->cmd == RBD_AIO_WRITE ||
+        acb->cmd == RBD_AIO_DISCARD) {
         if (r < 0) {
             acb->ret = r;
             acb->error = 1;
@@ -404,6 +409,7 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
     /* 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);
+done:
     g_free(rcb);
 }
 
@@ -441,21 +447,7 @@ static int qemu_rbd_aio_flush_cb(void *opaque)
     return (s->qemu_aio_count > 0);
 }
 
-/* TODO Convert to fine grained options */
-static QemuOptsList runtime_opts = {
-    .name = "rbd",
-    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
-    .desc = {
-        {
-            .name = "filename",
-            .type = QEMU_OPT_STRING,
-            .help = "Specification of the rbd image",
-        },
-        { /* end of list */ }
-    },
-};
-
-static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags)
+static int qemu_rbd_open(BlockDriverState *bs, const char *filename, int flags)
 {
     BDRVRBDState *s = bs->opaque;
     char pool[RBD_MAX_POOL_NAME_SIZE];
@@ -463,35 +455,20 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags)
     char conf[RBD_MAX_CONF_SIZE];
     char clientname_buf[RBD_MAX_CONF_SIZE];
     char *clientname;
-    QemuOpts *opts;
-    Error *local_err = NULL;
-    const char *filename;
     int r;
 
-    opts = qemu_opts_create_nofail(&runtime_opts);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (error_is_set(&local_err)) {
-        qerror_report_err(local_err);
-        error_free(local_err);
-        qemu_opts_del(opts);
-        return -EINVAL;
-    }
-
-    filename = qemu_opt_get(opts, "filename");
-
     if (qemu_rbd_parsename(filename, pool, sizeof(pool),
                            snap_buf, sizeof(snap_buf),
                            s->name, sizeof(s->name),
                            conf, sizeof(conf)) < 0) {
-        r = -EINVAL;
-        goto failed_opts;
+        return -EINVAL;
     }
 
     clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
     r = rados_create(&s->cluster, clientname);
     if (r < 0) {
         error_report("error initializing");
-        goto failed_opts;
+        return r;
     }
 
     s->snap = NULL;
@@ -499,19 +476,6 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags)
         s->snap = g_strdup(snap_buf);
     }
 
-    /*
-     * Fallback to more conservative semantics if setting cache
-     * options fails. Ignore errors from setting rbd_cache because the
-     * only possible error is that the option does not exist, and
-     * librbd defaults to no caching. If write through caching cannot
-     * be set up, fall back to no caching.
-     */
-    if (flags & BDRV_O_NOCACHE) {
-        rados_conf_set(s->cluster, "rbd_cache", "false");
-    } else {
-        rados_conf_set(s->cluster, "rbd_cache", "true");
-    }
-
     if (strstr(conf, "conf=") == NULL) {
         /* try default location, but ignore failure */
         rados_conf_read_file(s->cluster, NULL);
@@ -557,7 +521,6 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags)
                             NULL, qemu_rbd_aio_flush_cb, s);
 
 
-    qemu_opts_del(opts);
     return 0;
 
 failed:
@@ -567,8 +530,6 @@ failed_open:
 failed_shutdown:
     rados_shutdown(s->cluster);
     g_free(s->snap);
-failed_opts:
-    qemu_opts_del(opts);
     return r;
 }
 
@@ -594,15 +555,9 @@ static void qemu_rbd_aio_cancel(BlockDriverAIOCB *blockacb)
 {
     RBDAIOCB *acb = (RBDAIOCB *) blockacb;
     acb->cancelled = 1;
-
-    while (acb->status == -EINPROGRESS) {
-        qemu_aio_wait();
-    }
-
-    qemu_aio_release(acb);
 }
 
-static const AIOCBInfo rbd_aiocb_info = {
+static AIOPool rbd_aio_pool = {
     .aiocb_size = sizeof(RBDAIOCB),
     .cancel = qemu_rbd_aio_cancel,
 };
@@ -665,17 +620,14 @@ 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_iovec_from_buffer(acb->qiov, 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);
-    }
+    qemu_aio_release(acb);
 }
 
 static int rbd_aio_discard_wrapper(rbd_image_t image,
@@ -690,16 +642,6 @@ static int rbd_aio_discard_wrapper(rbd_image_t image,
 #endif
 }
 
-static int rbd_aio_flush_wrapper(rbd_image_t image,
-                                 rbd_completion_t comp)
-{
-#ifdef LIBRBD_SUPPORTS_AIO_FLUSH
-    return rbd_aio_flush(image, comp);
-#else
-    return -ENOTSUP;
-#endif
-}
-
 static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
                                        int64_t sector_num,
                                        QEMUIOVector *qiov,
@@ -717,10 +659,10 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
 
     BDRVRBDState *s = bs->opaque;
 
-    acb = qemu_aio_get(&rbd_aiocb_info, bs, cb, opaque);
+    acb = qemu_aio_get(&rbd_aio_pool, bs, cb, opaque);
     acb->cmd = cmd;
     acb->qiov = qiov;
-    if (cmd == RBD_AIO_DISCARD || cmd == RBD_AIO_FLUSH) {
+    if (cmd == RBD_AIO_DISCARD) {
         acb->bounce = NULL;
     } else {
         acb->bounce = qemu_blockalign(bs, qiov->size);
@@ -730,10 +672,9 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
     acb->s = s;
     acb->cancelled = 0;
     acb->bh = NULL;
-    acb->status = -EINPROGRESS;
 
     if (cmd == RBD_AIO_WRITE) {
-        qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
+        qemu_iovec_to_buffer(acb->qiov, acb->bounce);
     }
 
     buf = acb->bounce;
@@ -764,9 +705,6 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
     case RBD_AIO_DISCARD:
         r = rbd_aio_discard_wrapper(s->image, off, size, c);
         break;
-    case RBD_AIO_FLUSH:
-        r = rbd_aio_flush_wrapper(s->image, c);
-        break;
     default:
         r = -EINVAL;
     }
@@ -806,16 +744,6 @@ static BlockDriverAIOCB *qemu_rbd_aio_writev(BlockDriverState *bs,
                          RBD_AIO_WRITE);
 }
 
-#ifdef LIBRBD_SUPPORTS_AIO_FLUSH
-static BlockDriverAIOCB *qemu_rbd_aio_flush(BlockDriverState *bs,
-                                            BlockDriverCompletionFunc *cb,
-                                            void *opaque)
-{
-    return rbd_start_aio(bs, 0, NULL, 0, cb, opaque, RBD_AIO_FLUSH);
-}
-
-#else
-
 static int qemu_rbd_co_flush(BlockDriverState *bs)
 {
 #if LIBRBD_VERSION_CODE >= LIBRBD_VERSION(0, 1, 1)
@@ -826,7 +754,6 @@ static int qemu_rbd_co_flush(BlockDriverState *bs)
     return 0;
 #endif
 }
-#endif
 
 static int qemu_rbd_getinfo(BlockDriverState *bs, BlockDriverInfo *bdi)
 {
@@ -996,7 +923,6 @@ static BlockDriver bdrv_rbd = {
     .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_options     = qemu_rbd_create_options,
     .bdrv_getlength     = qemu_rbd_getlength,
@@ -1005,12 +931,7 @@ static BlockDriver bdrv_rbd = {
 
     .bdrv_aio_readv         = qemu_rbd_aio_readv,
     .bdrv_aio_writev        = qemu_rbd_aio_writev,
-
-#ifdef LIBRBD_SUPPORTS_AIO_FLUSH
-    .bdrv_aio_flush         = qemu_rbd_aio_flush,
-#else
     .bdrv_co_flush_to_disk  = qemu_rbd_co_flush,
-#endif
 
 #ifdef LIBRBD_SUPPORTS_DISCARD
     .bdrv_aio_discard       = qemu_rbd_aio_discard,

block/snapshot.c

@@ -1,157 +0,0 @@
-/*
- * Block layer snapshot related functions
- *
- * Copyright (c) 2003-2008 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 "block/snapshot.h"
-#include "block/block_int.h"
-
-int bdrv_snapshot_find(BlockDriverState *bs, QEMUSnapshotInfo *sn_info,
-                       const char *name)
-{
-    QEMUSnapshotInfo *sn_tab, *sn;
-    int nb_sns, i, ret;
-
-    ret = -ENOENT;
-    nb_sns = bdrv_snapshot_list(bs, &sn_tab);
-    if (nb_sns < 0) {
-        return ret;
-    }
-    for (i = 0; i < nb_sns; i++) {
-        sn = &sn_tab[i];
-        if (!strcmp(sn->id_str, name) || !strcmp(sn->name, name)) {
-            *sn_info = *sn;
-            ret = 0;
-            break;
-        }
-    }
-    g_free(sn_tab);
-    return ret;
-}
-
-int bdrv_can_snapshot(BlockDriverState *bs)
-{
-    BlockDriver *drv = bs->drv;
-    if (!drv || !bdrv_is_inserted(bs) || bdrv_is_read_only(bs)) {
-        return 0;
-    }
-
-    if (!drv->bdrv_snapshot_create) {
-        if (bs->file != NULL) {
-            return bdrv_can_snapshot(bs->file);
-        }
-        return 0;
-    }
-
-    return 1;
-}
-
-int bdrv_snapshot_create(BlockDriverState *bs,
-                         QEMUSnapshotInfo *sn_info)
-{
-    BlockDriver *drv = bs->drv;
-    if (!drv) {
-        return -ENOMEDIUM;
-    }
-    if (drv->bdrv_snapshot_create) {
-        return drv->bdrv_snapshot_create(bs, sn_info);
-    }
-    if (bs->file) {
-        return bdrv_snapshot_create(bs->file, sn_info);
-    }
-    return -ENOTSUP;
-}
-
-int bdrv_snapshot_goto(BlockDriverState *bs,
-                       const char *snapshot_id)
-{
-    BlockDriver *drv = bs->drv;
-    int ret, open_ret;
-
-    if (!drv) {
-        return -ENOMEDIUM;
-    }
-    if (drv->bdrv_snapshot_goto) {
-        return drv->bdrv_snapshot_goto(bs, snapshot_id);
-    }
-
-    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);
-        if (open_ret < 0) {
-            bdrv_delete(bs->file);
-            bs->drv = NULL;
-            return open_ret;
-        }
-        return ret;
-    }
-
-    return -ENOTSUP;
-}
-
-int bdrv_snapshot_delete(BlockDriverState *bs, const char *snapshot_id)
-{
-    BlockDriver *drv = bs->drv;
-    if (!drv) {
-        return -ENOMEDIUM;
-    }
-    if (drv->bdrv_snapshot_delete) {
-        return drv->bdrv_snapshot_delete(bs, snapshot_id);
-    }
-    if (bs->file) {
-        return bdrv_snapshot_delete(bs->file, snapshot_id);
-    }
-    return -ENOTSUP;
-}
-
-int bdrv_snapshot_list(BlockDriverState *bs,
-                       QEMUSnapshotInfo **psn_info)
-{
-    BlockDriver *drv = bs->drv;
-    if (!drv) {
-        return -ENOMEDIUM;
-    }
-    if (drv->bdrv_snapshot_list) {
-        return drv->bdrv_snapshot_list(bs, psn_info);
-    }
-    if (bs->file) {
-        return bdrv_snapshot_list(bs->file, psn_info);
-    }
-    return -ENOTSUP;
-}
-
-int bdrv_snapshot_load_tmp(BlockDriverState *bs,
-        const char *snapshot_name)
-{
-    BlockDriver *drv = bs->drv;
-    if (!drv) {
-        return -ENOMEDIUM;
-    }
-    if (!bs->read_only) {
-        return -EINVAL;
-    }
-    if (drv->bdrv_snapshot_load_tmp) {
-        return drv->bdrv_snapshot_load_tmp(bs, snapshot_name);
-    }
-    return -ENOTSUP;
-}

block/stream.c

@@ -12,9 +12,7 @@
  */
 
 #include "trace.h"
-#include "block/block_int.h"
-#include "block/blockjob.h"
-#include "qemu/ratelimit.h"
+#include "block_int.h"
 
 enum {
     /*
@@ -27,11 +25,38 @@ enum {
 
 #define SLICE_TIME 100000000ULL /* ns */
 
+typedef struct {
+    int64_t next_slice_time;
+    uint64_t slice_quota;
+    uint64_t dispatched;
+} RateLimit;
+
+static int64_t ratelimit_calculate_delay(RateLimit *limit, uint64_t n)
+{
+    int64_t now = qemu_get_clock_ns(rt_clock);
+
+    if (limit->next_slice_time < now) {
+        limit->next_slice_time = now + SLICE_TIME;
+        limit->dispatched = 0;
+    }
+    if (limit->dispatched == 0 || limit->dispatched + n <= limit->slice_quota) {
+        limit->dispatched += n;
+        return 0;
+    } else {
+        limit->dispatched = n;
+        return limit->next_slice_time - now;
+    }
+}
+
+static void ratelimit_set_speed(RateLimit *limit, uint64_t speed)
+{
+    limit->slice_quota = speed / (1000000000ULL / SLICE_TIME);
+}
+
 typedef struct StreamBlockJob {
     BlockJob common;
     RateLimit limit;
     BlockDriverState *base;
-    BlockdevOnError on_error;
     char backing_file_id[1024];
 } StreamBlockJob;
 
@@ -73,20 +98,80 @@ static void close_unused_images(BlockDriverState *top, BlockDriverState *base,
     top->backing_hd = base;
 }
 
+/*
+ * Given an image chain: [BASE] -> [INTER1] -> [INTER2] -> [TOP]
+ *
+ * Return true if the given sector is allocated in top.
+ * Return false if the given sector is allocated in intermediate images.
+ * Return true otherwise.
+ *
+ * 'pnum' is set to the number of sectors (including and immediately following
+ *  the specified sector) that are known to be in the same
+ *  allocated/unallocated state.
+ *
+ */
+static int coroutine_fn is_allocated_base(BlockDriverState *top,
+                                          BlockDriverState *base,
+                                          int64_t sector_num,
+                                          int nb_sectors, int *pnum)
+{
+    BlockDriverState *intermediate;
+    int ret, n;
+
+    ret = bdrv_co_is_allocated(top, sector_num, nb_sectors, &n);
+    if (ret) {
+        *pnum = n;
+        return ret;
+    }
+
+    /*
+     * Is the unallocated chunk [sector_num, n] also
+     * unallocated between base and top?
+     */
+    intermediate = top->backing_hd;
+
+    while (intermediate != base) {
+        int pnum_inter;
+
+        ret = bdrv_co_is_allocated(intermediate, sector_num, nb_sectors,
+                                   &pnum_inter);
+        if (ret < 0) {
+            return ret;
+        } else if (ret) {
+            *pnum = pnum_inter;
+            return 0;
+        }
+
+        /*
+         * [sector_num, nb_sectors] is unallocated on top but intermediate
+         * might have
+         *
+         * [sector_num+x, nr_sectors] allocated.
+         */
+        if (n > pnum_inter) {
+            n = pnum_inter;
+        }
+
+        intermediate = intermediate->backing_hd;
+    }
+
+    *pnum = n;
+    return 1;
+}
+
 static void coroutine_fn stream_run(void *opaque)
 {
     StreamBlockJob *s = opaque;
     BlockDriverState *bs = s->common.bs;
     BlockDriverState *base = s->base;
     int64_t sector_num, end;
-    int error = 0;
     int ret = 0;
     int n = 0;
     void *buf;
 
     s->common.len = bdrv_getlength(bs);
     if (s->common.len < 0) {
-        block_job_completed(&s->common, s->common.len);
+        block_job_complete(&s->common, s->common.len);
         return;
     }
 
@@ -104,37 +189,20 @@ static void coroutine_fn stream_run(void *opaque)
 
     for (sector_num = 0; sector_num < end; sector_num += n) {
         uint64_t delay_ns = 0;
-        bool copy;
 
 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.
+         * with no pending I/O here so that qemu_aio_flush() returns.
          */
         block_job_sleep_ns(&s->common, rt_clock, delay_ns);
         if (block_job_is_cancelled(&s->common)) {
             break;
         }
 
-        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 {
-            /* Copy if allocated in the intermediate images.  Limit to the
-             * known-unallocated area [sector_num, sector_num+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) {
-                n = end - sector_num;
-            }
-
-            copy = (ret == 1);
-        }
+        ret = is_allocated_base(bs, base, sector_num,
+                                STREAM_BUFFER_SIZE / BDRV_SECTOR_SIZE, &n);
         trace_stream_one_iteration(s, sector_num, n, ret);
-        if (ret >= 0 && copy) {
+        if (ret == 0) {
             if (s->common.speed) {
                 delay_ns = ratelimit_calculate_delay(&s->limit, n);
                 if (delay_ns > 0) {
@@ -144,19 +212,7 @@ wait:
             ret = stream_populate(bs, sector_num, n, buf);
         }
         if (ret < 0) {
-            BlockErrorAction action =
-                block_job_error_action(&s->common, s->common.bs, s->on_error,
-                                       true, -ret);
-            if (action == BDRV_ACTION_STOP) {
-                n = 0;
-                continue;
-            }
-            if (error == 0) {
-                error = ret;
-            }
-            if (action == BDRV_ACTION_REPORT) {
-                break;
-            }
+            break;
         }
         ret = 0;
 
@@ -168,9 +224,6 @@ wait:
         bdrv_disable_copy_on_read(bs);
     }
 
-    /* Do not remove the backing file if an error was there but ignored.  */
-    ret = error;
-
     if (!block_job_is_cancelled(&s->common) && sector_num == end && ret == 0) {
         const char *base_id = NULL, *base_fmt = NULL;
         if (base) {
@@ -184,7 +237,7 @@ wait:
     }
 
     qemu_vfree(buf);
-    block_job_completed(&s->common, ret);
+    block_job_complete(&s->common, ret);
 }
 
 static void stream_set_speed(BlockJob *job, int64_t speed, Error **errp)
@@ -195,10 +248,10 @@ static void stream_set_speed(BlockJob *job, int64_t speed, Error **errp)
         error_set(errp, QERR_INVALID_PARAMETER, "speed");
         return;
     }
-    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
+    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE);
 }
 
-static const BlockJobType stream_job_type = {
+static BlockJobType stream_job_type = {
     .instance_size = sizeof(StreamBlockJob),
     .job_type      = "stream",
     .set_speed     = stream_set_speed,
@@ -206,19 +259,11 @@ static const BlockJobType stream_job_type = {
 
 void stream_start(BlockDriverState *bs, BlockDriverState *base,
                   const char *base_id, int64_t speed,
-                  BlockdevOnError on_error,
                   BlockDriverCompletionFunc *cb,
                   void *opaque, Error **errp)
 {
     StreamBlockJob *s;
 
-    if ((on_error == BLOCKDEV_ON_ERROR_STOP ||
-         on_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        !bdrv_iostatus_is_enabled(bs)) {
-        error_set(errp, QERR_INVALID_PARAMETER, "on-error");
-        return;
-    }
-
     s = block_job_create(&stream_job_type, bs, speed, cb, opaque, errp);
     if (!s) {
         return;
@@ -229,7 +274,6 @@ void stream_start(BlockDriverState *bs, BlockDriverState *base,
         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);
     trace_stream_start(bs, base, s, s->common.co, opaque);
     qemu_coroutine_enter(s->common.co, s);

block/vdi.c

@@ -50,16 +50,19 @@
  */
 
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
-#include "migration/migration.h"
+#include "block_int.h"
+#include "module.h"
+#include "migration.h"
 
 #if defined(CONFIG_UUID)
 #include <uuid/uuid.h>
 #else
 /* TODO: move uuid emulation to some central place in QEMU. */
-#include "sysemu/sysemu.h"     /* UUID_FMT */
+#include "sysemu.h"     /* UUID_FMT */
 typedef unsigned char uuid_t[16];
+void uuid_generate(uuid_t out);
+int uuid_is_null(const uuid_t uu);
+void uuid_unparse(const uuid_t uu, char *out);
 #endif
 
 /* Code configuration options. */
@@ -121,18 +124,18 @@ typedef unsigned char uuid_t[16];
 #define VDI_IS_ALLOCATED(X) ((X) < VDI_DISCARDED)
 
 #if !defined(CONFIG_UUID)
-static inline void uuid_generate(uuid_t out)
+void uuid_generate(uuid_t out)
 {
     memset(out, 0, sizeof(uuid_t));
 }
 
-static inline int uuid_is_null(const uuid_t uu)
+int uuid_is_null(const uuid_t uu)
 {
     uuid_t null_uuid = { 0 };
     return memcmp(uu, null_uuid, sizeof(uuid_t)) == 0;
 }
 
-static inline void uuid_unparse(const uuid_t uu, char *out)
+void uuid_unparse(const uuid_t uu, char *out)
 {
     snprintf(out, 37, UUID_FMT,
             uu[0], uu[1], uu[2], uu[3], uu[4], uu[5], uu[6], uu[7],
@@ -246,7 +249,7 @@ static void vdi_header_print(VdiHeader *header)
 {
     char uuid[37];
     logout("text        %s", header->text);
-    logout("signature   0x%08x\n", header->signature);
+    logout("signature   0x%04x\n", header->signature);
     logout("header size 0x%04x\n", header->header_size);
     logout("image type  0x%04x\n", header->image_type);
     logout("image flags 0x%04x\n", header->image_flags);
@@ -274,8 +277,7 @@ static void vdi_header_print(VdiHeader *header)
 }
 #endif
 
-static int vdi_check(BlockDriverState *bs, BdrvCheckResult *res,
-                     BdrvCheckMode fix)
+static int vdi_check(BlockDriverState *bs, BdrvCheckResult *res)
 {
     /* TODO: additional checks possible. */
     BDRVVdiState *s = (BDRVVdiState *)bs->opaque;
@@ -284,10 +286,6 @@ static int vdi_check(BlockDriverState *bs, BdrvCheckResult *res,
     uint32_t *bmap;
     logout("\n");
 
-    if (fix) {
-        return -ENOTSUP;
-    }
-
     bmap = g_malloc(s->header.blocks_in_image * sizeof(uint32_t));
     memset(bmap, 0xff, s->header.blocks_in_image * sizeof(uint32_t));
 
@@ -364,17 +362,15 @@ 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)
+static int vdi_open(BlockDriverState *bs, int flags)
 {
     BDRVVdiState *s = bs->opaque;
     VdiHeader header;
     size_t bmap_size;
-    int ret;
 
     logout("\n");
 
-    ret = bdrv_read(bs->file, 0, (uint8_t *)&header, 1);
-    if (ret < 0) {
+    if (bdrv_read(bs->file, 0, (uint8_t *)&header, 1) < 0) {
         goto fail;
     }
 
@@ -392,45 +388,33 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags)
         header.disk_size &= ~(SECTOR_SIZE - 1);
     }
 
-    if (header.signature != VDI_SIGNATURE) {
-        logout("bad vdi signature %08x\n", header.signature);
-        ret = -EMEDIUMTYPE;
-        goto fail;
-    } else if (header.version != VDI_VERSION_1_1) {
+    if (header.version != VDI_VERSION_1_1) {
         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. */
         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. */
         logout("unsupported data offset 0x%x B\n", header.offset_data);
-        ret = -ENOTSUP;
         goto fail;
     } else if (header.sector_size != SECTOR_SIZE) {
         logout("unsupported sector size %u B\n", header.sector_size);
-        ret = -ENOTSUP;
         goto fail;
     } 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) {
         logout("unsupported disk size %" PRIu64 " B\n", header.disk_size);
-        ret = -ENOTSUP;
         goto fail;
     } else if (!uuid_is_null(header.uuid_link)) {
         logout("link uuid != 0, unsupported\n");
-        ret = -ENOTSUP;
         goto fail;
     } else if (!uuid_is_null(header.uuid_parent)) {
         logout("parent uuid != 0, unsupported\n");
-        ret = -ENOTSUP;
         goto fail;
     }
 
@@ -443,9 +427,10 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags)
 
     bmap_size = header.blocks_in_image * sizeof(uint32_t);
     bmap_size = (bmap_size + SECTOR_SIZE - 1) / SECTOR_SIZE;
-    s->bmap = g_malloc(bmap_size * SECTOR_SIZE);
-    ret = bdrv_read(bs->file, s->bmap_sector, (uint8_t *)s->bmap, bmap_size);
-    if (ret < 0) {
+    if (bmap_size > 0) {
+        s->bmap = g_malloc(bmap_size * SECTOR_SIZE);
+    }
+    if (bdrv_read(bs->file, s->bmap_sector, (uint8_t *)s->bmap, bmap_size) < 0) {
         goto fail_free_bmap;
     }
 
@@ -461,13 +446,7 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags)
     g_free(s->bmap);
 
  fail:
-    return ret;
-}
-
-static int vdi_reopen_prepare(BDRVReopenState *state,
-                              BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
+    return -1;
 }
 
 static int coroutine_fn vdi_co_is_allocated(BlockDriverState *bs,
@@ -644,6 +623,7 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options)
     VdiHeader header;
     size_t i;
     size_t bmap_size;
+    uint32_t *bmap;
 
     logout("\n");
 
@@ -668,9 +648,8 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options)
         options++;
     }
 
-    fd = qemu_open(filename,
-                   O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
-                   0644);
+    fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
+              0644);
     if (fd < 0) {
         return -errno;
     }
@@ -708,21 +687,21 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options)
         result = -errno;
     }
 
+    bmap = NULL;
     if (bmap_size > 0) {
-        uint32_t *bmap = g_malloc0(bmap_size);
-        for (i = 0; i < blocks; i++) {
-            if (image_type == VDI_TYPE_STATIC) {
-                bmap[i] = i;
-            } else {
-                bmap[i] = VDI_UNALLOCATED;
-            }
-        }
-        if (write(fd, bmap, bmap_size) < 0) {
-            result = -errno;
-        }
-        g_free(bmap);
+        bmap = (uint32_t *)g_malloc0(bmap_size);
     }
-
+    for (i = 0; i < blocks; i++) {
+        if (image_type == VDI_TYPE_STATIC) {
+            bmap[i] = i;
+        } else {
+            bmap[i] = VDI_UNALLOCATED;
+        }
+    }
+    if (write(fd, bmap, bmap_size) < 0) {
+        result = -errno;
+    }
+    g_free(bmap);
     if (image_type == VDI_TYPE_STATIC) {
         if (ftruncate(fd, sizeof(header) + bmap_size + blocks * block_size)) {
             result = -errno;
@@ -777,9 +756,7 @@ static BlockDriver bdrv_vdi = {
     .bdrv_probe = vdi_probe,
     .bdrv_open = vdi_open,
     .bdrv_close = vdi_close,
-    .bdrv_reopen_prepare = vdi_reopen_prepare,
     .bdrv_create = vdi_create,
-    .bdrv_has_zero_init = bdrv_has_zero_init_1,
     .bdrv_co_is_allocated = vdi_co_is_allocated,
     .bdrv_make_empty = vdi_make_empty,
 

block/vhdx.c

@@ -1,972 +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 v0.95", published 4/12/2012
- *  by Microsoft:
- *      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.
- *
- */
-
-#include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
-#include "qemu/crc32c.h"
-#include "block/vhdx.h"
-
-
-/* Several metadata and region table data entries are identified by
- * guids in  a MS-specific GUID format. */
-
-
-/* ------- Known Region Table GUIDs ---------------------- */
-static const MSGUID bat_guid =      { .data1 = 0x2dc27766,
-                                      .data2 = 0xf623,
-                                      .data3 = 0x4200,
-                                      .data4 = { 0x9d, 0x64, 0x11, 0x5e,
-                                                 0x9b, 0xfd, 0x4a, 0x08} };
-
-static const MSGUID metadata_guid = { .data1 = 0x8b7ca206,
-                                      .data2 = 0x4790,
-                                      .data3 = 0x4b9a,
-                                      .data4 = { 0xb8, 0xfe, 0x57, 0x5f,
-                                                 0x05, 0x0f, 0x88, 0x6e} };
-
-
-
-/* ------- Known Metadata Entry GUIDs ---------------------- */
-static const MSGUID file_param_guid =   { .data1 = 0xcaa16737,
-                                          .data2 = 0xfa36,
-                                          .data3 = 0x4d43,
-                                          .data4 = { 0xb3, 0xb6, 0x33, 0xf0,
-                                                     0xaa, 0x44, 0xe7, 0x6b} };
-
-static const MSGUID virtual_size_guid = { .data1 = 0x2FA54224,
-                                          .data2 = 0xcd1b,
-                                          .data3 = 0x4876,
-                                          .data4 = { 0xb2, 0x11, 0x5d, 0xbe,
-                                                     0xd8, 0x3b, 0xf4, 0xb8} };
-
-static const MSGUID page83_guid =       { .data1 = 0xbeca12ab,
-                                          .data2 = 0xb2e6,
-                                          .data3 = 0x4523,
-                                          .data4 = { 0x93, 0xef, 0xc3, 0x09,
-                                                     0xe0, 0x00, 0xc7, 0x46} };
-
-
-static const MSGUID phys_sector_guid =  { .data1 = 0xcda348c7,
-                                          .data2 = 0x445d,
-                                          .data3 = 0x4471,
-                                          .data4 = { 0x9c, 0xc9, 0xe9, 0x88,
-                                                     0x52, 0x51, 0xc5, 0x56} };
-
-static const MSGUID parent_locator_guid = { .data1 = 0xa8d35f2d,
-                                            .data2 = 0xb30b,
-                                            .data3 = 0x454d,
-                                            .data4 = { 0xab, 0xf7, 0xd3,
-                                                       0xd8, 0x48, 0x34,
-                                                       0xab, 0x0c} };
-
-static const MSGUID logical_sector_guid = { .data1 = 0x8141bf1d,
-                                            .data2 = 0xa96f,
-                                            .data3 = 0x4709,
-                                            .data4 = { 0xba, 0x47, 0xf2,
-                                                       0x33, 0xa8, 0xfa,
-                                                       0xab, 0x5f} };
-
-/* Each parent type must have a valid GUID; this is for parent images
- * of type 'VHDX'.  If we were to allow e.g. a QCOW2 parent, we would
- * need to make up our own QCOW2 GUID type */
-static const MSGUID parent_vhdx_guid = { .data1 = 0xb04aefb7,
-                                         .data2 = 0xd19e,
-                                         .data3 = 0x4a81,
-                                         .data4 = { 0xb7, 0x89, 0x25, 0xb8,
-                                                    0xe9, 0x44, 0x59, 0x13} };
-
-
-#define META_FILE_PARAMETER_PRESENT      0x01
-#define META_VIRTUAL_DISK_SIZE_PRESENT   0x02
-#define META_PAGE_83_PRESENT             0x04
-#define META_LOGICAL_SECTOR_SIZE_PRESENT 0x08
-#define META_PHYS_SECTOR_SIZE_PRESENT    0x10
-#define META_PARENT_LOCATOR_PRESENT      0x20
-
-#define META_ALL_PRESENT    \
-    (META_FILE_PARAMETER_PRESENT | META_VIRTUAL_DISK_SIZE_PRESENT | \
-     META_PAGE_83_PRESENT | META_LOGICAL_SECTOR_SIZE_PRESENT | \
-     META_PHYS_SECTOR_SIZE_PRESENT)
-
-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 VHDXSectorInfo {
-    uint32_t bat_idx;       /* BAT entry index */
-    uint32_t sectors_avail; /* sectors available in payload block */
-    uint32_t bytes_left;    /* bytes left in the block after data to r/w */
-    uint32_t bytes_avail;   /* bytes available in payload block */
-    uint64_t file_offset;   /* absolute offset in bytes, in file */
-    uint64_t block_offset;  /* block offset, in bytes */
-} VHDXSectorInfo;
-
-
-
-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;
-
-    VHDXParentLocatorHeader parent_header;
-    VHDXParentLocatorEntry *parent_entries;
-
-} BDRVVHDXState;
-
-uint32_t vhdx_checksum_calc(uint32_t crc, uint8_t *buf, size_t size,
-                            int crc_offset)
-{
-    uint32_t crc_new;
-    uint32_t crc_orig;
-    assert(buf != NULL);
-
-    if (crc_offset > 0) {
-        memcpy(&crc_orig, buf + crc_offset, sizeof(crc_orig));
-        memset(buf + crc_offset, 0, sizeof(crc_orig));
-    }
-
-    crc_new = crc32c(crc, buf, size);
-    if (crc_offset > 0) {
-        memcpy(buf + crc_offset, &crc_orig, sizeof(crc_orig));
-    }
-
-    return crc_new;
-}
-
-/* Validates the checksum of the buffer, with an in-place CRC.
- *
- * Zero is substituted during crc calculation for the original crc field,
- * and the crc field is restored afterwards.  But the buffer will be modifed
- * during the calculation, so this may not be not suitable for multi-threaded
- * use.
- *
- * crc_offset: byte offset in buf of the buffer crc
- * buf: buffer pointer
- * size: size of buffer (must be > crc_offset+4)
- *
- * returns true if checksum is valid, false otherwise
- */
-bool vhdx_checksum_is_valid(uint8_t *buf, size_t size, int crc_offset)
-{
-    uint32_t crc_orig;
-    uint32_t crc;
-
-    assert(buf != NULL);
-    assert(size > (crc_offset + 4));
-
-    memcpy(&crc_orig, buf + crc_offset, sizeof(crc_orig));
-    crc_orig = le32_to_cpu(crc_orig);
-
-    crc = vhdx_checksum_calc(0xffffffff, buf, size, crc_offset);
-
-    return crc == crc_orig;
-}
-
-
-/*
- * Per the MS VHDX Specification, for every VHDX file:
- *      - The header section is fixed size - 1 MB
- *      - The header section is always the first "object"
- *      - The first 64KB of the header is the File Identifier
- *      - The first uint64 (8 bytes) is the VHDX Signature ("vhdxfile")
- *      - The following 512 bytes constitute a UTF-16 string identifiying the
- *        software that created the file, and is optional and diagnostic only.
- *
- *  Therefore, we probe by looking for the vhdxfile signature "vhdxfile"
- */
-static int vhdx_probe(const uint8_t *buf, int buf_size, const char *filename)
-{
-    if (buf_size >= 8 && !memcmp(buf, "vhdxfile", 8)) {
-        return 100;
-    }
-    return 0;
-}
-
-/* All VHDX structures on disk are little endian */
-static 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);
-}
-
-
-/* opens the specified header block from the VHDX file header section */
-static int vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s)
-{
-    int ret = 0;
-    VHDXHeader *header1;
-    VHDXHeader *header2;
-    bool h1_valid = false;
-    bool h2_valid = false;
-    uint64_t h1_seq = 0;
-    uint64_t h2_seq = 0;
-    uint8_t *buffer;
-
-    header1 = qemu_blockalign(bs, sizeof(VHDXHeader));
-    header2 = qemu_blockalign(bs, sizeof(VHDXHeader));
-
-    buffer = qemu_blockalign(bs, VHDX_HEADER_SIZE);
-
-    s->headers[0] = header1;
-    s->headers[1] = header2;
-
-    /* We have to read the whole VHDX_HEADER_SIZE instead of
-     * sizeof(VHDXHeader), because the checksum is over the whole
-     * region */
-    ret = bdrv_pread(bs->file, VHDX_HEADER1_OFFSET, buffer, VHDX_HEADER_SIZE);
-    if (ret < 0) {
-        goto fail;
-    }
-    /* copy over just the relevant portion that we need */
-    memcpy(header1, buffer, sizeof(VHDXHeader));
-    vhdx_header_le_import(header1);
-
-    if (vhdx_checksum_is_valid(buffer, VHDX_HEADER_SIZE, 4) &&
-        !memcmp(&header1->signature, "head", 4)             &&
-        header1->version == 1) {
-        h1_seq = header1->sequence_number;
-        h1_valid = true;
-    }
-
-    ret = bdrv_pread(bs->file, VHDX_HEADER2_OFFSET, buffer, VHDX_HEADER_SIZE);
-    if (ret < 0) {
-        goto fail;
-    }
-    /* copy over just the relevant portion that we need */
-    memcpy(header2, buffer, sizeof(VHDXHeader));
-    vhdx_header_le_import(header2);
-
-    if (vhdx_checksum_is_valid(buffer, VHDX_HEADER_SIZE, 4) &&
-        !memcmp(&header2->signature, "head", 4)             &&
-        header2->version == 1) {
-        h2_seq = header2->sequence_number;
-        h2_valid = true;
-    }
-
-    /* If there is only 1 valid header (or no valid headers), we
-     * don't care what the sequence numbers are */
-    if (h1_valid && !h2_valid) {
-        s->curr_header = 0;
-    } else if (!h1_valid && h2_valid) {
-        s->curr_header = 1;
-    } else if (!h1_valid && !h2_valid) {
-        ret = -EINVAL;
-        goto fail;
-    } else {
-        /* If both headers are valid, then we choose the active one by the
-         * highest sequence number.  If the sequence numbers are equal, that is
-         * invalid */
-        if (h1_seq > h2_seq) {
-            s->curr_header = 0;
-        } else if (h2_seq > h1_seq) {
-            s->curr_header = 1;
-        } else {
-            ret = -EINVAL;
-            goto fail;
-        }
-    }
-
-    ret = 0;
-
-    goto exit;
-
-fail:
-    qerror_report(ERROR_CLASS_GENERIC_ERROR, "No valid VHDX header found");
-    qemu_vfree(header1);
-    qemu_vfree(header2);
-    s->headers[0] = NULL;
-    s->headers[1] = NULL;
-exit:
-    qemu_vfree(buffer);
-    return ret;
-}
-
-
-static int vhdx_open_region_tables(BlockDriverState *bs, BDRVVHDXState *s)
-{
-    int ret = 0;
-    uint8_t *buffer;
-    int offset = 0;
-    VHDXRegionTableEntry rt_entry;
-    uint32_t i;
-    bool bat_rt_found = false;
-    bool metadata_rt_found = false;
-
-    /* We have to read the whole 64KB block, because the crc32 is over the
-     * whole block */
-    buffer = qemu_blockalign(bs, VHDX_HEADER_BLOCK_SIZE);
-
-    ret = bdrv_pread(bs->file, VHDX_REGION_TABLE_OFFSET, buffer,
-                     VHDX_HEADER_BLOCK_SIZE);
-    if (ret < 0) {
-        goto fail;
-    }
-    memcpy(&s->rt, buffer, sizeof(s->rt));
-    le32_to_cpus(&s->rt.signature);
-    le32_to_cpus(&s->rt.checksum);
-    le32_to_cpus(&s->rt.entry_count);
-    le32_to_cpus(&s->rt.reserved);
-    offset += sizeof(s->rt);
-
-    if (!vhdx_checksum_is_valid(buffer, VHDX_HEADER_BLOCK_SIZE, 4) ||
-        memcmp(&s->rt.signature, "regi", 4)) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    /* Per spec, maximum region table entry count is 2047 */
-    if (s->rt.entry_count > 2047) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    for (i = 0; i < s->rt.entry_count; i++) {
-        memcpy(&rt_entry, buffer + offset, sizeof(rt_entry));
-        offset += sizeof(rt_entry);
-
-        leguid_to_cpus(&rt_entry.guid);
-        le64_to_cpus(&rt_entry.file_offset);
-        le32_to_cpus(&rt_entry.length);
-        le32_to_cpus(&rt_entry.data_bits);
-
-        /* see if we recognize the entry */
-        if (guid_eq(rt_entry.guid, bat_guid)) {
-            /* must be unique; if we have already found it this is invalid */
-            if (bat_rt_found) {
-                ret = -EINVAL;
-                goto fail;
-            }
-            bat_rt_found = true;
-            s->bat_rt = rt_entry;
-            continue;
-        }
-
-        if (guid_eq(rt_entry.guid, metadata_guid)) {
-            /* must be unique; if we have already found it this is invalid */
-            if (metadata_rt_found) {
-                ret = -EINVAL;
-                goto fail;
-            }
-            metadata_rt_found = true;
-            s->metadata_rt = rt_entry;
-            continue;
-        }
-
-        if (rt_entry.data_bits & VHDX_REGION_ENTRY_REQUIRED) {
-            /* cannot read vhdx file - required region table entry that
-             * we do not understand.  per spec, we must fail to open */
-            ret = -ENOTSUP;
-            goto fail;
-        }
-    }
-    ret = 0;
-
-fail:
-    qemu_vfree(buffer);
-    return ret;
-}
-
-
-
-/* Metadata initial parser
- *
- * This loads all the metadata entry fields.  This may cause additional
- * fields to be processed (e.g. parent locator, etc..).
- *
- * There are 5 Metadata items that are always required:
- *      - File Parameters (block size, has a parent)
- *      - Virtual Disk Size (size, in bytes, of the virtual drive)
- *      - Page 83 Data (scsi page 83 guid)
- *      - Logical Sector Size (logical sector size in bytes, either 512 or
- *                             4096.  We only support 512 currently)
- *      - Physical Sector Size (512 or 4096)
- *
- * Also, if the File Parameters indicate this is a differencing file,
- * we must also look for the Parent Locator metadata item.
- */
-static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s)
-{
-    int ret = 0;
-    uint8_t *buffer;
-    int offset = 0;
-    uint32_t i = 0;
-    VHDXMetadataTableEntry md_entry;
-
-    buffer = qemu_blockalign(bs, VHDX_METADATA_TABLE_MAX_SIZE);
-
-    ret = bdrv_pread(bs->file, s->metadata_rt.file_offset, buffer,
-                     VHDX_METADATA_TABLE_MAX_SIZE);
-    if (ret < 0) {
-        goto exit;
-    }
-    memcpy(&s->metadata_hdr, buffer, sizeof(s->metadata_hdr));
-    offset += sizeof(s->metadata_hdr);
-
-    le64_to_cpus(&s->metadata_hdr.signature);
-    le16_to_cpus(&s->metadata_hdr.reserved);
-    le16_to_cpus(&s->metadata_hdr.entry_count);
-
-    if (memcmp(&s->metadata_hdr.signature, "metadata", 8)) {
-        ret = -EINVAL;
-        goto exit;
-    }
-
-    s->metadata_entries.present = 0;
-
-    if ((s->metadata_hdr.entry_count * sizeof(md_entry)) >
-        (VHDX_METADATA_TABLE_MAX_SIZE - offset)) {
-        ret = -EINVAL;
-        goto exit;
-    }
-
-    for (i = 0; i < s->metadata_hdr.entry_count; i++) {
-        memcpy(&md_entry, buffer + offset, sizeof(md_entry));
-        offset += sizeof(md_entry);
-
-        leguid_to_cpus(&md_entry.item_id);
-        le32_to_cpus(&md_entry.offset);
-        le32_to_cpus(&md_entry.length);
-        le32_to_cpus(&md_entry.data_bits);
-        le32_to_cpus(&md_entry.reserved2);
-
-        if (guid_eq(md_entry.item_id, file_param_guid)) {
-            if (s->metadata_entries.present & META_FILE_PARAMETER_PRESENT) {
-                ret = -EINVAL;
-                goto exit;
-            }
-            s->metadata_entries.file_parameters_entry = md_entry;
-            s->metadata_entries.present |= META_FILE_PARAMETER_PRESENT;
-            continue;
-        }
-
-        if (guid_eq(md_entry.item_id, virtual_size_guid)) {
-            if (s->metadata_entries.present & META_VIRTUAL_DISK_SIZE_PRESENT) {
-                ret = -EINVAL;
-                goto exit;
-            }
-            s->metadata_entries.virtual_disk_size_entry = md_entry;
-            s->metadata_entries.present |= META_VIRTUAL_DISK_SIZE_PRESENT;
-            continue;
-        }
-
-        if (guid_eq(md_entry.item_id, page83_guid)) {
-            if (s->metadata_entries.present & META_PAGE_83_PRESENT) {
-                ret = -EINVAL;
-                goto exit;
-            }
-            s->metadata_entries.page83_data_entry = md_entry;
-            s->metadata_entries.present |= META_PAGE_83_PRESENT;
-            continue;
-        }
-
-        if (guid_eq(md_entry.item_id, logical_sector_guid)) {
-            if (s->metadata_entries.present &
-                META_LOGICAL_SECTOR_SIZE_PRESENT) {
-                ret = -EINVAL;
-                goto exit;
-            }
-            s->metadata_entries.logical_sector_size_entry = md_entry;
-            s->metadata_entries.present |= META_LOGICAL_SECTOR_SIZE_PRESENT;
-            continue;
-        }
-
-        if (guid_eq(md_entry.item_id, phys_sector_guid)) {
-            if (s->metadata_entries.present & META_PHYS_SECTOR_SIZE_PRESENT) {
-                ret = -EINVAL;
-                goto exit;
-            }
-            s->metadata_entries.phys_sector_size_entry = md_entry;
-            s->metadata_entries.present |= META_PHYS_SECTOR_SIZE_PRESENT;
-            continue;
-        }
-
-        if (guid_eq(md_entry.item_id, parent_locator_guid)) {
-            if (s->metadata_entries.present & META_PARENT_LOCATOR_PRESENT) {
-                ret = -EINVAL;
-                goto exit;
-            }
-            s->metadata_entries.parent_locator_entry = md_entry;
-            s->metadata_entries.present |= META_PARENT_LOCATOR_PRESENT;
-            continue;
-        }
-
-        if (md_entry.data_bits & VHDX_META_FLAGS_IS_REQUIRED) {
-            /* cannot read vhdx file - required region table entry that
-             * we do not understand.  per spec, we must fail to open */
-            ret = -ENOTSUP;
-            goto exit;
-        }
-    }
-
-    if (s->metadata_entries.present != META_ALL_PRESENT) {
-        ret = -ENOTSUP;
-        goto exit;
-    }
-
-    ret = bdrv_pread(bs->file,
-                     s->metadata_entries.file_parameters_entry.offset
-                                         + s->metadata_rt.file_offset,
-                     &s->params,
-                     sizeof(s->params));
-
-    if (ret < 0) {
-        goto exit;
-    }
-
-    le32_to_cpus(&s->params.block_size);
-    le32_to_cpus(&s->params.data_bits);
-
-
-    /* We now have the file parameters, so we can tell if this is a
-     * differencing file (i.e.. has_parent), is dynamic or fixed
-     * sized (leave_blocks_allocated), and the block size */
-
-    /* The parent locator required iff the file parameters has_parent set */
-    if (s->params.data_bits & VHDX_PARAMS_HAS_PARENT) {
-        if (s->metadata_entries.present & META_PARENT_LOCATOR_PRESENT) {
-            /* TODO: parse  parent locator fields */
-            ret = -ENOTSUP; /* temp, until differencing files are supported */
-            goto exit;
-        } else {
-            /* if has_parent is set, but there is not parent locator present,
-             * then that is an invalid combination */
-            ret = -EINVAL;
-            goto exit;
-        }
-    }
-
-    /* determine virtual disk size, logical sector size,
-     * and phys sector size */
-
-    ret = bdrv_pread(bs->file,
-                     s->metadata_entries.virtual_disk_size_entry.offset
-                                           + s->metadata_rt.file_offset,
-                     &s->virtual_disk_size,
-                     sizeof(uint64_t));
-    if (ret < 0) {
-        goto exit;
-    }
-    ret = bdrv_pread(bs->file,
-                     s->metadata_entries.logical_sector_size_entry.offset
-                                             + s->metadata_rt.file_offset,
-                     &s->logical_sector_size,
-                     sizeof(uint32_t));
-    if (ret < 0) {
-        goto exit;
-    }
-    ret = bdrv_pread(bs->file,
-                     s->metadata_entries.phys_sector_size_entry.offset
-                                          + s->metadata_rt.file_offset,
-                     &s->physical_sector_size,
-                     sizeof(uint32_t));
-    if (ret < 0) {
-        goto exit;
-    }
-
-    le64_to_cpus(&s->virtual_disk_size);
-    le32_to_cpus(&s->logical_sector_size);
-    le32_to_cpus(&s->physical_sector_size);
-
-    if (s->logical_sector_size == 0 || s->params.block_size == 0) {
-        ret = -EINVAL;
-        goto exit;
-    }
-
-    /* both block_size and sector_size are guaranteed powers of 2 */
-    s->sectors_per_block = s->params.block_size / s->logical_sector_size;
-    s->chunk_ratio = (VHDX_MAX_SECTORS_PER_BLOCK) *
-                     (uint64_t)s->logical_sector_size /
-                     (uint64_t)s->params.block_size;
-
-    /* These values are ones we will want to use for division / multiplication
-     * later on, and they are all guaranteed (per the spec) to be powers of 2,
-     * so we can take advantage of that for shift operations during
-     * reads/writes */
-    if (s->logical_sector_size & (s->logical_sector_size - 1)) {
-        ret = -EINVAL;
-        goto exit;
-    }
-    if (s->sectors_per_block & (s->sectors_per_block - 1)) {
-        ret = -EINVAL;
-        goto exit;
-    }
-    if (s->chunk_ratio & (s->chunk_ratio - 1)) {
-        ret = -EINVAL;
-        goto exit;
-    }
-    s->block_size = s->params.block_size;
-    if (s->block_size & (s->block_size - 1)) {
-        ret = -EINVAL;
-        goto exit;
-    }
-
-    s->logical_sector_size_bits = 31 - clz32(s->logical_sector_size);
-    s->sectors_per_block_bits =   31 - clz32(s->sectors_per_block);
-    s->chunk_ratio_bits =         63 - clz64(s->chunk_ratio);
-    s->block_size_bits =          31 - clz32(s->block_size);
-
-    ret = 0;
-
-exit:
-    qemu_vfree(buffer);
-    return ret;
-}
-
-/* Parse the replay log.  Per the VHDX spec, if the log is present
- * it must be replayed prior to opening the file, even read-only.
- *
- * If read-only, we must replay the log in RAM (or refuse to open
- * a dirty VHDX file read-only */
-static int vhdx_parse_log(BlockDriverState *bs, BDRVVHDXState *s)
-{
-    int ret = 0;
-    int i;
-    VHDXHeader *hdr;
-
-    hdr = s->headers[s->curr_header];
-
-    /* either the log guid, or log length is zero,
-     * then a replay log is present */
-    for (i = 0; i < sizeof(hdr->log_guid.data4); i++) {
-        ret |= hdr->log_guid.data4[i];
-    }
-    if (hdr->log_guid.data1 == 0 &&
-        hdr->log_guid.data2 == 0 &&
-        hdr->log_guid.data3 == 0 &&
-        ret == 0) {
-        goto exit;
-    }
-
-    /* per spec, only log version of 0 is supported */
-    if (hdr->log_version != 0) {
-        ret = -EINVAL;
-        goto exit;
-    }
-
-    if (hdr->log_length == 0) {
-        goto exit;
-    }
-
-    /* We currently do not support images with logs to replay */
-    ret = -ENOTSUP;
-
-exit:
-    return ret;
-}
-
-
-static int vhdx_open(BlockDriverState *bs, QDict *options, int flags)
-{
-    BDRVVHDXState *s = bs->opaque;
-    int ret = 0;
-    uint32_t i;
-    uint64_t signature;
-    uint32_t data_blocks_cnt, bitmap_blocks_cnt;
-
-
-    s->bat = NULL;
-
-    qemu_co_mutex_init(&s->lock);
-
-    /* validate the file signature */
-    ret = bdrv_pread(bs->file, 0, &signature, sizeof(uint64_t));
-    if (ret < 0) {
-        goto fail;
-    }
-    if (memcmp(&signature, "vhdxfile", 8)) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    ret = vhdx_parse_header(bs, s);
-    if (ret) {
-        goto fail;
-    }
-
-    ret = vhdx_parse_log(bs, s);
-    if (ret) {
-        goto fail;
-    }
-
-    ret = vhdx_open_region_tables(bs, s);
-    if (ret) {
-        goto fail;
-    }
-
-    ret = vhdx_parse_metadata(bs, s);
-    if (ret) {
-        goto fail;
-    }
-    s->block_size = s->params.block_size;
-
-    /* the VHDX spec dictates that virtual_disk_size is always a multiple of
-     * logical_sector_size */
-    bs->total_sectors = s->virtual_disk_size >> s->logical_sector_size_bits;
-
-    data_blocks_cnt = s->virtual_disk_size >> s->block_size_bits;
-    if (s->virtual_disk_size - (data_blocks_cnt << s->block_size_bits)) {
-        data_blocks_cnt++;
-    }
-    bitmap_blocks_cnt = data_blocks_cnt >> s->chunk_ratio_bits;
-    if (data_blocks_cnt - (bitmap_blocks_cnt << s->chunk_ratio_bits)) {
-        bitmap_blocks_cnt++;
-    }
-
-    if (s->parent_entries) {
-        s->bat_entries = bitmap_blocks_cnt * (s->chunk_ratio + 1);
-    } else {
-        s->bat_entries = data_blocks_cnt +
-                         ((data_blocks_cnt - 1) >> s->chunk_ratio_bits);
-    }
-
-    s->bat_offset = s->bat_rt.file_offset;
-
-    if (s->bat_entries > s->bat_rt.length / sizeof(VHDXBatEntry)) {
-        /* BAT allocation is not large enough for all entries */
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    s->bat = qemu_blockalign(bs, s->bat_rt.length);
-
-    ret = bdrv_pread(bs->file, s->bat_offset, s->bat, s->bat_rt.length);
-    if (ret < 0) {
-        goto fail;
-    }
-
-    for (i = 0; i < s->bat_entries; i++) {
-        le64_to_cpus(&s->bat[i]);
-    }
-
-    if (flags & BDRV_O_RDWR) {
-        ret = -ENOTSUP;
-        goto fail;
-    }
-
-    /* TODO: differencing files, write */
-
-    return 0;
-fail:
-    qemu_vfree(s->headers[0]);
-    qemu_vfree(s->headers[1]);
-    qemu_vfree(s->bat);
-    qemu_vfree(s->parent_entries);
-    return ret;
-}
-
-static int vhdx_reopen_prepare(BDRVReopenState *state,
-                               BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
-}
-
-
-/*
- * Perform sector to block offset translations, to get various
- * sector and file offsets into the image.  See VHDXSectorInfo
- */
-static void vhdx_block_translate(BDRVVHDXState *s, int64_t sector_num,
-                                 int nb_sectors, VHDXSectorInfo *sinfo)
-{
-    uint32_t block_offset;
-
-    sinfo->bat_idx = sector_num >> s->sectors_per_block_bits;
-    /* effectively a modulo - this gives us the offset into the block
-     * (in sector sizes) for our sector number */
-    block_offset = sector_num - (sinfo->bat_idx << s->sectors_per_block_bits);
-    /* the chunk ratio gives us the interleaving of the sector
-     * bitmaps, so we need to advance our page block index by the
-     * sector bitmaps entry number */
-    sinfo->bat_idx += sinfo->bat_idx >> s->chunk_ratio_bits;
-
-    /* the number of sectors we can read/write in this cycle */
-    sinfo->sectors_avail = s->sectors_per_block - block_offset;
-
-    sinfo->bytes_left = sinfo->sectors_avail << s->logical_sector_size_bits;
-
-    if (sinfo->sectors_avail > nb_sectors) {
-        sinfo->sectors_avail = nb_sectors;
-    }
-
-    sinfo->bytes_avail = sinfo->sectors_avail << s->logical_sector_size_bits;
-
-    sinfo->file_offset = s->bat[sinfo->bat_idx] >> VHDX_BAT_FILE_OFF_BITS;
-
-    sinfo->block_offset = block_offset << s->logical_sector_size_bits;
-
-    /* The file offset must be past the header section, so must be > 0 */
-    if (sinfo->file_offset == 0) {
-        return;
-    }
-
-    /* block offset is the offset in vhdx logical sectors, in
-     * the payload data block. Convert that to a byte offset
-     * in the block, and add in the payload data block offset
-     * in the file, in bytes, to get the final read address */
-
-    sinfo->file_offset <<= 20;  /* now in bytes, rather than 1MB units */
-    sinfo->file_offset += sinfo->block_offset;
-}
-
-
-
-static coroutine_fn int vhdx_co_readv(BlockDriverState *bs, int64_t sector_num,
-                                      int nb_sectors, QEMUIOVector *qiov)
-{
-    BDRVVHDXState *s = bs->opaque;
-    int ret = 0;
-    VHDXSectorInfo sinfo;
-    uint64_t bytes_done = 0;
-    QEMUIOVector hd_qiov;
-
-    qemu_iovec_init(&hd_qiov, qiov->niov);
-
-    qemu_co_mutex_lock(&s->lock);
-
-    while (nb_sectors > 0) {
-        /* We are a differencing file, so we need to inspect the sector bitmap
-         * to see if we have the data or not */
-        if (s->params.data_bits & VHDX_PARAMS_HAS_PARENT) {
-            /* not supported yet */
-            ret = -ENOTSUP;
-            goto exit;
-        } else {
-            vhdx_block_translate(s, sector_num, nb_sectors, &sinfo);
-
-            qemu_iovec_reset(&hd_qiov);
-            qemu_iovec_concat(&hd_qiov, qiov,  bytes_done, sinfo.bytes_avail);
-
-            /* check the payload block state */
-            switch (s->bat[sinfo.bat_idx] & VHDX_BAT_STATE_BIT_MASK) {
-            case PAYLOAD_BLOCK_NOT_PRESENT: /* fall through */
-            case PAYLOAD_BLOCK_UNDEFINED:   /* fall through */
-            case PAYLOAD_BLOCK_UNMAPPED:    /* fall through */
-            case PAYLOAD_BLOCK_ZERO:
-                /* return zero */
-                qemu_iovec_memset(&hd_qiov, 0, 0, sinfo.bytes_avail);
-                break;
-            case PAYLOAD_BLOCK_FULL_PRESENT:
-                qemu_co_mutex_unlock(&s->lock);
-                ret = bdrv_co_readv(bs->file,
-                                    sinfo.file_offset >> BDRV_SECTOR_BITS,
-                                    sinfo.sectors_avail, &hd_qiov);
-                qemu_co_mutex_lock(&s->lock);
-                if (ret < 0) {
-                    goto exit;
-                }
-                break;
-            case PAYLOAD_BLOCK_PARTIALLY_PRESENT:
-                /* we don't yet support difference files, fall through
-                 * to error */
-            default:
-                ret = -EIO;
-                goto exit;
-                break;
-            }
-            nb_sectors -= sinfo.sectors_avail;
-            sector_num += sinfo.sectors_avail;
-            bytes_done += sinfo.bytes_avail;
-        }
-    }
-    ret = 0;
-exit:
-    qemu_co_mutex_unlock(&s->lock);
-    qemu_iovec_destroy(&hd_qiov);
-    return ret;
-}
-
-
-
-static coroutine_fn int vhdx_co_writev(BlockDriverState *bs, int64_t sector_num,
-                                      int nb_sectors, QEMUIOVector *qiov)
-{
-    return -ENOTSUP;
-}
-
-
-static void vhdx_close(BlockDriverState *bs)
-{
-    BDRVVHDXState *s = bs->opaque;
-    qemu_vfree(s->headers[0]);
-    qemu_vfree(s->headers[1]);
-    qemu_vfree(s->bat);
-    qemu_vfree(s->parent_entries);
-}
-
-static BlockDriver bdrv_vhdx = {
-    .format_name            = "vhdx",
-    .instance_size          = sizeof(BDRVVHDXState),
-    .bdrv_probe             = vhdx_probe,
-    .bdrv_open              = vhdx_open,
-    .bdrv_close             = vhdx_close,
-    .bdrv_reopen_prepare    = vhdx_reopen_prepare,
-    .bdrv_co_readv          = vhdx_co_readv,
-    .bdrv_co_writev         = vhdx_co_writev,
-};
-
-static void bdrv_vhdx_init(void)
-{
-    bdrv_register(&bdrv_vhdx);
-}
-
-block_init(bdrv_vhdx_init);