This is the delta between the qemu and qemu-kvm v0.15.1 versions

Signed-off-by: Bruce Rogers <brogers@suse.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

@@ -12,13 +12,10 @@ trace-dtrace.dtrace
 *-linux-user
 *-bsd-user
 libdis*
+libhw32
+libhw64
 libuser
-linux-headers/asm
 qapi-generated
-qapi-types.[ch]
-qapi-visit.[ch]
-qmp-commands.h
-qmp-marshal.c
 qemu-doc.html
 qemu-tech.html
 qemu-doc.info
@@ -37,18 +34,8 @@ qemu-img-cmds.texi
 qemu-img-cmds.h
 qemu-io
 qemu-ga
-qemu-bridge-helper
 qemu-monitor.texi
-vscclient
 QMP/qmp-commands.txt
-test-coroutine
-test-qmp-input-visitor
-test-qmp-output-visitor
-test-string-input-visitor
-test-string-output-visitor
-test-visitor-serialization
-fsdev/virtfs-proxy-helper.1
-fsdev/virtfs-proxy-helper.pod
 .gdbinit
 *.a
 *.aux
@@ -69,10 +56,6 @@ fsdev/virtfs-proxy-helper.pod
 *.vr
 *.d
 *.o
-*.lo
-*.la
-*.pc
-.libs
 *.swp
 *.orig
 .pc
@@ -80,14 +63,10 @@ patches
 pc-bios/bios-pq/status
 pc-bios/vgabios-pq/status
 pc-bios/optionrom/linuxboot.bin
-pc-bios/optionrom/linuxboot.raw
-pc-bios/optionrom/linuxboot.img
 pc-bios/optionrom/multiboot.bin
 pc-bios/optionrom/multiboot.raw
-pc-bios/optionrom/multiboot.img
-pc-bios/optionrom/kvmvapic.bin
-pc-bios/optionrom/kvmvapic.raw
-pc-bios/optionrom/kvmvapic.img
+pc-bios/optionrom/extboot.bin
+pc-bios/optionrom/vapic.bin
 .stgit-*
 cscope.*
 tags

.gitmodules

@@ -1,6 +1,6 @@
 [submodule "roms/vgabios"]
 	path = roms/vgabios
-	url = git://git.qemu.org/vgabios.git/
+	url = git://git.kernel.org/pub/scm/virt/kvm/vgabios.git/
 [submodule "roms/seabios"]
 	path = roms/seabios
 	url = git://git.qemu.org/seabios.git/
@@ -10,15 +10,3 @@
 [submodule "roms/ipxe"]
 	path = roms/ipxe
 	url = git://git.qemu.org/ipxe.git
-[submodule "roms/openbios"]
-	path = roms/openbios
-	url = git://git.qemu.org/openbios.git
-[submodule "roms/qemu-palcode"]
-	path = roms/qemu-palcode
-	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

.mailmap

@@ -1,16 +0,0 @@
-# This mailmap just translates the weird addresses from the original import into git
-# into proper addresses so that they are counted properly in git shortlog output.
-#
-Andrzej Zaborowski <balrogg@gmail.com> balrog <balrog@c046a42c-6fe2-441c-8c8c-71466251a162>
-Anthony Liguori <aliguori@us.ibm.com> aliguori <aliguori@c046a42c-6fe2-441c-8c8c-71466251a162>
-Aurelien Jarno <aurelien@aurel32.net> aurel32 <aurel32@c046a42c-6fe2-441c-8c8c-71466251a162>
-Blue Swirl <blauwirbel@gmail.com> blueswir1 <blueswir1@c046a42c-6fe2-441c-8c8c-71466251a162>
-Edgar E. Iglesias <edgar.iglesias@gmail.com> edgar_igl <edgar_igl@c046a42c-6fe2-441c-8c8c-71466251a162>
-Fabrice Bellard <fabrice@bellard.org> bellard <bellard@c046a42c-6fe2-441c-8c8c-71466251a162>
-Jocelyn Mayer <l_indien@magic.fr> j_mayer <j_mayer@c046a42c-6fe2-441c-8c8c-71466251a162>
-Paul Brook <paul@codesourcery.com> pbrook <pbrook@c046a42c-6fe2-441c-8c8c-71466251a162>
-Thiemo Seufer <ths@networkno.de> ths <ths@c046a42c-6fe2-441c-8c8c-71466251a162>
-malc <av1474@comtv.ru> malc <malc@c046a42c-6fe2-441c-8c8c-71466251a162>
-# There is also a:
-#    (no author) <(no author)@c046a42c-6fe2-441c-8c8c-71466251a162>
-# for the cvs2svn initialization commit e63c3dc74bf.

CODING_STYLE

@@ -1,4 +1,4 @@
-QEMU Coding Style
+Qemu Coding Style
 =================
 
 Please use the script checkpatch.pl in the scripts directory to check
@@ -44,8 +44,7 @@ Rationale:
 3. Naming
 
 Variables are lower_case_with_underscores; easy to type and read.  Structured
-type names are in CamelCase; harder to type but standing out.  Enum type
-names and function type names should also be in CamelCase.  Scalar type
+type names are in CamelCase; harder to type but standing out.  Scalar type
 names are lower_case_with_underscores_ending_with_a_t, like the POSIX
 uint64_t and family.  Note that this last convention contradicts POSIX
 and is therefore likely to be changed.
@@ -69,10 +68,6 @@ keyword.  Example:
         printf("a was something else entirely.\n");
     }
 
-Note that 'else if' is considered a single statement; otherwise a long if/
-else if/else if/.../else sequence would need an indent for every else
-statement.
-
 An exception is the opening brace for a function; for reasons of tradition
 and clarity it comes on a line by itself:
 

Changelog

@@ -78,7 +78,7 @@ version 0.10.2:
 
   - fix savevm/loadvm (Anthony Liguori)
   - live migration: fix dirty tracking windows (Glauber Costa)
-  - live migration: improve error propagation (Glauber Costa)
+  - live migration: improve error propogation (Glauber Costa)
   - qcow2: fix image creation for > ~2TB images (Chris Wright)
   - hotplug: fix error handling for if= parameter (Eduardo Habkost)
   - qcow2: fix data corruption (Nolan Leake)
@@ -386,7 +386,7 @@ version 0.5.3:
   - support of CD-ROM change
   - multiple network interface support
   - initial x86-64 host support (Gwenole Beauchesne)
-  - lret to outer privilege fix (OS/2 install fix)
+  - lret to outer priviledge fix (OS/2 install fix)
   - task switch fixes (SkyOS boot)
   - VM save/restore commands
   - new timer API
@@ -447,7 +447,7 @@ version 0.5.0:
   - multi-target build
   - fixed: no error code in hardware interrupts
   - fixed: pop ss, mov ss, x and sti disable hardware irqs for the next insn
-  - correct single stepping through string operations
+  - correct single stepping thru string operations
   - preliminary SPARC target support (Thomas M. Ogrisegg)
   - tun-fd option (Rusty Russell)
   - automatic IDE geometry detection

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
@@ -77,13 +77,11 @@ 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_vmalloc/qemu_memalign/qemu_vfree
-APIs.
+use the replacement qemu_malloc/qemu_mallocz/qemu_realloc/qemu_free or
+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.
+Please note that NULL check for the qemu_malloc result is redundant and
+that qemu_malloc() call with zero size is not allowed.
 
 Memory allocated by qemu_vmalloc or qemu_memalign must be freed with
 qemu_vfree, since breaking this will cause problems on Win32 and user
@@ -91,11 +89,10 @@ 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)
@@ -111,7 +108,7 @@ int qemu_strnlen(const char *s, int max_len)
 There are also replacement character processing macros for isxyz and toxyz,
 so instead of e.g. isalnum you should use qemu_isalnum.
 
-Because of the memory management rules, you must use g_strdup/g_strndup
+Because of the memory management rules, you must use qemu_strdup/qemu_strndup
 instead of plain strdup/strndup.
 
 5. Printf-style functions

LICENSE

@@ -6,7 +6,9 @@ The following points clarify the QEMU license:
 GNU General Public License. Hence each source file contains its own
 licensing information.
 
-Many hardware device emulation sources are released under the BSD license.
+In particular, the QEMU virtual CPU core library (libqemu.a) is
+released under the GNU Lesser General Public License. Many hardware
+device emulation sources are released under the BSD license.
 
 3) The Tiny Code Generator (TCG) is released under the BSD license
    (see license headers in files).

MAINTAINERS

@@ -20,7 +20,7 @@ Descriptions of section entries:
 	   Supported:	Someone is actually paid to look after this.
 	   Maintained:	Someone actually looks after it.
 	   Odd Fixes:	It has a maintainer but they don't have time to do
-			much other than throw the odd patch in. See below.
+			much other than throw the odd patch in. See below..
 	   Orphan:	No current maintainer [but maybe you could take the
 			role as you write your new code].
 	   Obsolete:	Old code. Something tagged obsolete generally means
@@ -62,7 +62,6 @@ F: target-alpha/
 
 ARM
 M: Paul Brook <paul@codesourcery.com>
-M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
 F: target-arm/
 
@@ -78,7 +77,7 @@ F: target-lm32/
 
 M68K
 M: Paul Brook <paul@codesourcery.com>
-S: Odd Fixes
+S: Maintained
 F: target-m68k/
 
 MicroBlaze
@@ -88,12 +87,11 @@ F: target-microblaze/
 
 MIPS
 M: Aurelien Jarno <aurelien@aurel32.net>
-S: Odd Fixes
+S: Maintained
 F: target-mips/
 
 PowerPC
 M: Alexander Graf <agraf@suse.de>
-L: qemu-ppc@nongnu.org
 S: Maintained
 F: target-ppc/
 
@@ -104,7 +102,7 @@ F: target-s390x/
 
 SH4
 M: Aurelien Jarno <aurelien@aurel32.net>
-S: Odd Fixes
+S: Maintained
 F: target-sh4/
 
 SPARC
@@ -112,22 +110,11 @@ M: Blue Swirl <blauwirbel@gmail.com>
 S: Maintained
 F: target-sparc/
 
-UniCore32
-M: Guan Xuetao <gxt@mprc.pku.edu.cn>
-S: Maintained
-F: target-unicore32/
-
 X86
 M: qemu-devel@nongnu.org
 S: Odd Fixes
 F: target-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/
-
 Guest CPU Cores (KVM):
 ----------------------
 
@@ -156,66 +143,15 @@ L: kvm@vger.kernel.org
 S: Supported
 F: target-i386/kvm.c
 
-Guest CPU Cores (Xen):
-----------------------
-
-X86
-M: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
-L: xen-devel@lists.xensource.com
-S: Supported
-F: xen-*
-F: */xen*
-
-Hosts:
-------
-
-LINUX
-L: qemu-devel@nongnu.org
-S: Maintained
-F: linux-*
-F: linux-headers/
-
-POSIX
-L: qemu-devel@nongnu.org
-S: Maintained
-F: *posix*
-
-W32, W64
-L: qemu-devel@nongnu.org
-M: Stefan Weil <sw@weilnetz.de>
-S: Maintained
-F: *win32*
-
 ARM Machines
 ------------
-Exynos
-M: Evgeny Voevodin <e.voevodin@samsung.com>
-M: Maksim Kozlov <m.kozlov@samsung.com>
-M: Igor Mitsyanko <i.mitsyanko@samsung.com>
-M: Dmitry Solodkiy <d.solodkiy@samsung.com>
-S: Maintained
-F: hw/exynos*
-
-Calxeda Highbank
-M: Mark Langsdorf <mark.langsdorf@calxeda.com>
-S: Supported
-F: hw/highbank.c
-F: hw/xgmac.c
-
 Gumstix
 M: qemu-devel@nongnu.org
 S: Orphan
 F: hw/gumstix.c
 
-i.MX31
-M: Peter Chubb <peter.chubb@nicta.com.au>
-S: Odd fixes
-F: hw/imx*
-F: hw/kzm.c
-
 Integrator CP
 M: Paul Brook <paul@codesourcery.com>
-M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
 F: hw/integratorcp.c
 
@@ -241,7 +177,6 @@ F: hw/palm.c
 
 Real View
 M: Paul Brook <paul@codesourcery.com>
-M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
 F: hw/realview*
 
@@ -252,24 +187,14 @@ F: hw/spitz.c
 
 Stellaris
 M: Paul Brook <paul@codesourcery.com>
-M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
 F: hw/stellaris.c
 
 Versatile PB
 M: Paul Brook <paul@codesourcery.com>
-M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
 F: hw/versatilepb.c
 
-Xilinx Zynq
-M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
-S: Maintained
-F: hw/xilinx_zynq.c
-F: hw/zynq_slcr.c
-F: hw/cadence_*
-F: hw/xilinx_spips.c
-
 CRIS Machines
 -------------
 Axis Dev88
@@ -318,11 +243,6 @@ M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
 S: Maintained
 F: hw/petalogix_s3adsp1800.c
 
-petalogix_ml605
-M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
-S: Maintained
-F: hw/petalogix_ml605_mmu.c
-
 MIPS Machines
 -------------
 Jazz
@@ -349,66 +269,23 @@ PowerPC Machines
 ----------------
 405
 M: Alexander Graf <agraf@suse.de>
-L: qemu-ppc@nongnu.org
-S: Odd Fixes
+S: Maintained
 F: hw/ppc405_boards.c
 
-Bamboo
-M: Alexander Graf <agraf@suse.de>
-L: qemu-ppc@nongnu.org
-S: Odd Fixes
-F: hw/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/mpc8544_guts.c
-
 New World
 M: Alexander Graf <agraf@suse.de>
-L: qemu-ppc@nongnu.org
 S: Maintained
 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_oldworld.c
-F: hw/grackle_pci.c
 
-PReP
-M: Andreas Färber <andreas.faerber@web.de>
-L: qemu-ppc@nongnu.org
-S: Odd Fixes
+Prep
+M: qemu-devel@nongnu.org
+S: Orphan
 F: hw/ppc_prep.c
-F: hw/prep_pci.[hc]
-
-sPAPR
-M: David Gibson <david@gibson.dropbear.id.au>
-M: Alexander Graf <agraf@suse.de>
-L: qemu-ppc@nongnu.org
-S: Supported
-F: hw/spapr*
-
-virtex_ml507
-M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
-L: qemu-ppc@nongnu.org
-S: Odd Fixes
-F: hw/virtex_ml507.c
 
 SH4 Machines
 ------------
@@ -434,12 +311,6 @@ M: Blue Swirl <blauwirbel@gmail.com>
 S: Maintained
 F: hw/sun4u.c
 
-Leon3
-M: Fabien Chouteau <chouteau@adacore.com>
-S: Maintained
-F: hw/leon3.c
-F: hw/grlib*
-
 S390 Machines
 -------------
 S390 Virtio
@@ -447,33 +318,12 @@ M: Alexander Graf <agraf@suse.de>
 S: Maintained
 F: hw/s390-*.c
 
-UniCore32 Machines
--------------
-PKUnity-3 SoC initramfs-with-busybox
-M: Guan Xuetao <gxt@mprc.pku.edu.cn>
-S: Maintained
-F: hw/puv3*
-F: hw/unicore32/
-
 X86 Machines
 ------------
 PC
 M: Anthony Liguori <aliguori@us.ibm.com>
 S: Supported
-F: hw/pc.[ch]
-F: hw/pc_piix.c
-
-Xtensa Machines
----------------
-sim
-M: Max Filippov <jcmvbkbc@gmail.com>
-S: Maintained
-F: hw/xtensa_sim.c
-
-Avnet LX60
-M: Max Filippov <jcmvbkbc@gmail.com>
-S: Maintained
-F: hw/xtensa_lx60.c
+F: hw/pc.[ch] hw/pc_piix.c
 
 Devices
 -------
@@ -482,58 +332,24 @@ M: Kevin Wolf <kwolf@redhat.com>
 S: Odd Fixes
 F: hw/ide/
 
-OMAP
-M: Peter Maydell <peter.maydell@linaro.org>
-S: Maintained
-F: hw/omap*
-
 PCI
 M: Michael S. Tsirkin <mst@redhat.com>
 S: Supported
 F: hw/pci*
 F: hw/piix*
 
-ppc4xx
-M: Alexander Graf <agraf@suse.de>
-L: qemu-ppc@nongnu.org
-S: Odd Fixes
-F: hw/ppc4xx*.[hc]
-
-ppce500
-M: Alexander Graf <agraf@suse.de>
-M: Scott Wood <scottwood@freescale.com>
-L: qemu-ppc@nongnu.org
-S: Supported
-F: hw/ppce500_*
-
 SCSI
-M: Paolo Bonzini <pbonzini@redhat.com>
-S: Supported
-F: hw/virtio-scsi.*
-F: hw/scsi*
-T: git git://github.com/bonzini/qemu.git scsi-next
-
-LSI53C895A
 M: Paul Brook <paul@codesourcery.com>
+M: Kevin Wolf <kwolf@redhat.com>
 S: Odd Fixes
 F: hw/lsi53c895a.c
-
-SSI
-M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
-S: Maintained
-F: hw/ssi.*
-F: hw/m25p80.c
+F: hw/scsi*
 
 USB
 M: Gerd Hoffmann <kraxel@redhat.com>
 S: Maintained
 F: hw/usb*
 
-VFIO
-M: Alex Williamson <alex.williamson@redhat.com>
-S: Supported
-F: hw/vfio*
-
 vhost
 M: Michael S. Tsirkin <mst@redhat.com>
 S: Supported
@@ -545,15 +361,12 @@ S: Supported
 F: hw/virtio*
 
 virtio-9p
-M: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+M: Venkateswararao Jujjuri (JV) <jvrao@linux.vnet.ibm.com>
 S: Supported
-F: hw/9pfs/
-F: fsdev/
-T: git git://github.com/kvaneesh/QEMU.git
+F: hw/virtio-9p*
 
 virtio-blk
 M: Kevin Wolf <kwolf@redhat.com>
-M: Stefan Hajnoczi <stefanha@redhat.com>
 S: Supported
 F: hw/virtio-blk*
 
@@ -563,18 +376,6 @@ S: Supported
 F: hw/virtio-serial*
 F: hw/virtio-console*
 
-Xilinx EDK
-M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
-M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
-S: Maintained
-F: hw/xilinx_axi*
-F: hw/xilinx_uartlite.c
-F: hw/xilinx_intc.c
-F: hw/xilinx_ethlite.c
-F: hw/xilinx_timer.c
-F: hw/xilinx.h
-F: hw/xilinx_spi.c
-
 Subsystems
 ----------
 Audio
@@ -584,7 +385,6 @@ F: audio/
 
 Block
 M: Kevin Wolf <kwolf@redhat.com>
-M: Stefan Hajnoczi <stefanha@redhat.com>
 S: Supported
 F: block*
 F: block/
@@ -594,18 +394,6 @@ 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/qemu/cpu.h
-
-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
@@ -625,11 +413,6 @@ M: Anthony Liguori <aliguori@us.ibm.com>
 S: Maintained
 F: ui/
 
-Cocoa graphics
-M: Andreas Färber <andreas.faerber@web.de>
-S: Odd Fixes
-F: ui/cocoa.m
-
 Main loop
 M: Anthony Liguori <aliguori@us.ibm.com>
 S: Supported
@@ -643,38 +426,14 @@ F: monitor.c
 
 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>
-S: Odd Fixes
-F: block/nbd.c
-F: nbd.*
-F: qemu-nbd.c
-T: git git://github.com/bonzini/qemu.git nbd-next
 
 SLIRP
-M: Jan Kiszka <jan.kiszka@siemens.com>
-S: Maintained
+M: qemu-devel@nongnu.org
+S: Orphan
 F: slirp/
-T: git git://git.kiszka.org/qemu.git queues/slirp
-
-Tracing
-M: Stefan Hajnoczi <stefanha@redhat.com>
-S: Maintained
-F: trace/
-F: scripts/tracetool.py
-F: scripts/tracetool/
-F: docs/tracing.txt
-T: git git://github.com/stefanha/qemu.git tracing
-
-Checkpatch
-M: Blue Swirl <blauwirbel@gmail.com>
-S: Odd Fixes
-F: scripts/checkpatch.pl
 
 Usermode Emulation
 ------------------
@@ -683,6 +442,11 @@ M: Blue Swirl <blauwirbel@gmail.com>
 S: Maintained
 F: bsd-user/
 
+Darwin user
+M: qemu-devel@nongnu.org
+S: Orphan
+F: darwin-user/
+
 Linux user
 M: Riku Voipio <riku.voipio@iki.fi>
 S: Maintained
@@ -740,30 +504,3 @@ SPARC target
 M: Blue Swirl <blauwirbel@gmail.com>
 S: Maintained
 F: tcg/sparc/
-
-TCI target
-M: Stefan Weil <sw@weilnetz.de>
-S: Maintained
-F: tcg/tci/
-
-Stable branches
----------------
-Stable 1.0
-L: qemu-stable@nongnu.org
-T: git git://git.qemu.org/qemu-stable-1.0.git
-S: Orphan
-
-Stable 0.15
-L: qemu-stable@nongnu.org
-T: git git://git.qemu.org/qemu-stable-0.15.git
-S: Orphan
-
-Stable 0.14
-L: qemu-stable@nongnu.org
-T: git git://git.qemu.org/qemu-stable-0.14.git
-S: Orphan
-
-Stable 0.10
-L: qemu-stable@nongnu.org
-T: git git://git.qemu.org/qemu-stable-0.10.git
-S: Orphan

Makefile

@@ -1,42 +1,23 @@
 # Makefile for QEMU.
 
-# Always point to the root of the build tree (needs GNU make).
-BUILD_DIR=$(CURDIR)
+GENERATED_HEADERS = config-host.h trace.h qemu-options.def
+ifeq ($(TRACE_BACKEND),dtrace)
+GENERATED_HEADERS += trace-dtrace.h
+endif
 
-# 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
-
 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 $(MAKECMDGOALS),,fail))
 	@echo "Please call configure before running make!"
 	@exit 1
 endif
-endif
-
-GENERATED_HEADERS = config-host.h trace.h qemu-options.def
-ifeq ($(TRACE_BACKEND),dtrace)
-GENERATED_HEADERS += trace-dtrace.h
-endif
-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
@@ -44,34 +25,24 @@ 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)
 
-HELPERS-$(CONFIG_LINUX) = qemu-bridge-helper$(EXESUF)
-
 ifdef BUILD_DOCS
 DOCS=qemu-doc.html qemu-tech.html qemu.1 qemu-img.1 qemu-nbd.8 QMP/qmp-commands.txt
-ifdef CONFIG_VIRTFS
-DOCS+=fsdev/virtfs-proxy-helper.1
-endif
 else
 DOCS=
 endif
 
-SUBDIR_MAKEFLAGS=$(if $(V),,--no-print-directory) BUILD_DIR=$(BUILD_DIR)
+SUBDIR_MAKEFLAGS=$(if $(V),,--no-print-directory)
 SUBDIR_DEVICES_MAK=$(patsubst %, %/config-devices.mak, $(TARGET_DIRS))
 SUBDIR_DEVICES_MAK_DEP=$(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,cat $(SUBDIR_DEVICES_MAK) | grep =y | sort -u > $@,"  GEN   $@")
-endif
 
 -include $(SUBDIR_DEVICES_MAK_DEP)
 
@@ -100,7 +71,7 @@ defconfig:
 
 -include config-all-devices.mak
 
-all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all
+build-all: $(DOCS) $(TOOLS) recurse-all
 
 config-host.h: config-host.h-timestamp
 config-host.h-timestamp: config-host.mak
@@ -109,29 +80,19 @@ qemu-options.def: $(SRC_PATH)/qemu-options.hx
 
 SUBDIR_RULES=$(patsubst %,subdir-%, $(TARGET_DIRS))
 
-subdir-%:
+subdir-%: $(GENERATED_HEADERS)
 	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C $* V="$(V)" TARGET_DIR="$*/" all,)
 
 ifneq ($(wildcard config-host.mak),)
 include $(SRC_PATH)/Makefile.objs
 endif
 
-subdir-libcacard: $(oslib-obj-y) $(trace-obj-y) qemu-timer-common.o
+$(common-obj-y): $(GENERATED_HEADERS)
+subdir-libcacard: $(oslib-obj-y) $(trace-obj-y) qemu-malloc.o qemu-timer-common.o
 
-subdir-pixman: pixman/Makefile
-	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C pixman V="$(V)" all,)
+$(filter %-softmmu,$(SUBDIR_RULES)): $(trace-obj-y) $(common-obj-y) subdir-libdis
 
-pixman/Makefile: $(SRC_PATH)/pixman/configure
-	(cd pixman; CFLAGS="$(CFLAGS) -fPIC" $(SRC_PATH)/pixman/configure $(AUTOCONF_HOST) --disable-gtk --disable-shared --enable-static)
-
-$(SRC_PATH)/pixman/configure:
-	(cd $(SRC_PATH)/pixman; autoreconf -v --install)
-
-$(SUBDIR_RULES): libqemustub.a
-
-$(filter %-softmmu,$(SUBDIR_RULES)): $(universal-obj-y) $(trace-obj-y) $(common-obj-y) $(extra-obj-y) subdir-libdis
-
-$(filter %-user,$(SUBDIR_RULES)): $(universal-obj-y) $(trace-obj-y) subdir-libdis-user subdir-libuser
+$(filter %-user,$(SUBDIR_RULES)): $(GENERATED_HEADERS) $(trace-obj-y) subdir-libdis-user subdir-libuser
 
 ROMSUBDIR_RULES=$(patsubst %,romsubdir-%, $(ROMS))
 romsubdir-%:
@@ -145,26 +106,20 @@ audio/audio.o audio/fmodaudio.o: QEMU_CFLAGS += $(FMOD_CFLAGS)
 
 QEMU_CFLAGS+=$(CURL_CFLAGS)
 
-QEMU_CFLAGS += -I$(SRC_PATH)/include
+QEMU_CFLAGS+=$(GLIB_CFLAGS)
 
 ui/cocoa.o: ui/cocoa.m
 
-ui/sdl.o audio/sdlaudio.o ui/sdl_zoom.o hw/baum.o: QEMU_CFLAGS += $(SDL_CFLAGS)
+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.o: $(SRC_PATH)/version.rc config-host.mak
 	$(call quiet-command,$(WINDRES) -I. -o $@ $<,"  RC    $(TARGET_DIR)$@")
 
 version-obj-$(CONFIG_WIN32) += version.o
-
-######################################################################
-# Build library with stubs
-
-libqemustub.a: $(stub-obj-y)
-
 ######################################################################
 # Support building shared library libcacard
 
@@ -176,102 +131,93 @@ libcacard.la:
 install-libcacard:
 	@echo "libtool is missing, please install and rerun configure"; exit 1
 else
-libcacard.la: $(oslib-obj-y) qemu-timer-common.o $(addsuffix .lo, $(basename $(trace-obj-y)))
+libcacard.la: $(GENERATED_HEADERS) $(oslib-obj-y) qemu-malloc.o 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)
 
-tools-obj-y = $(oslib-obj-y) $(trace-obj-y) qemu-tool.o qemu-timer.o \
-	main-loop.o iohandler.o error.o
-tools-obj-$(CONFIG_POSIX) += compatfd.o
+qemu-img$(EXESUF): qemu-img.o qemu-tool.o qemu-error.o $(oslib-obj-y) $(trace-obj-y) $(block-obj-y) $(qobject-obj-y) $(version-obj-y) qemu-timer-common.o
 
-qemu-img$(EXESUF): qemu-img.o $(tools-obj-y) $(block-obj-y) libqemustub.a
-qemu-nbd$(EXESUF): qemu-nbd.o $(tools-obj-y) $(block-obj-y) libqemustub.a
-qemu-io$(EXESUF): qemu-io.o cmd.o $(tools-obj-y) $(block-obj-y) libqemustub.a
+qemu-nbd$(EXESUF): qemu-nbd.o qemu-tool.o qemu-error.o $(oslib-obj-y) $(trace-obj-y) $(block-obj-y) $(qobject-obj-y) $(version-obj-y) qemu-timer-common.o
 
-qemu-bridge-helper$(EXESUF): qemu-bridge-helper.o
-
-vscclient$(EXESUF): $(libcacard-y) $(oslib-obj-y) $(trace-obj-y) libcacard/vscclient.o libqemustub.a
-	$(call quiet-command,$(CC) $(LDFLAGS) -o $@ $^ $(libcacard_libs) $(LIBS),"  LINK  $@")
-
-fsdev/virtfs-proxy-helper$(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-io$(EXESUF): qemu-io.o cmd.o qemu-tool.o qemu-error.o $(oslib-obj-y) $(trace-obj-y) $(block-obj-y) $(qobject-obj-y) $(version-obj-y) qemu-timer-common.o
 
 qemu-img-cmds.h: $(SRC_PATH)/qemu-img-cmds.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $@")
 
-qemu-ga$(EXESUF): LIBS = $(LIBS_QGA)
-qemu-ga$(EXESUF): QEMU_CFLAGS += -I qga/qapi-generated
+check-qint.o check-qstring.o check-qdict.o check-qlist.o check-qfloat.o check-qjson.o: $(GENERATED_HEADERS)
 
-gen-out-type = $(subst .,-,$(suffix $@))
+CHECK_PROG_DEPS = qemu-malloc.o $(oslib-obj-y) $(trace-obj-y) qemu-tool.o
 
-ifneq ($(wildcard config-host.mak),)
-include $(SRC_PATH)/tests/Makefile
-endif
+check-qint: check-qint.o qint.o $(CHECK_PROG_DEPS)
+check-qstring: check-qstring.o qstring.o $(CHECK_PROG_DEPS)
+check-qdict: check-qdict.o qdict.o qfloat.o qint.o qstring.o qbool.o qlist.o $(CHECK_PROG_DEPS)
+check-qlist: check-qlist.o qlist.o qint.o $(CHECK_PROG_DEPS)
+check-qfloat: check-qfloat.o qfloat.o $(CHECK_PROG_DEPS)
+check-qjson: check-qjson.o qfloat.o qint.o qdict.o qstring.o qlist.o qbool.o qjson.o json-streamer.o json-lexer.o json-parser.o error.o qerror.o qemu-error.o $(CHECK_PROG_DEPS)
 
-qapi-py = $(SRC_PATH)/scripts/qapi.py $(SRC_PATH)/scripts/ordereddict.py
+$(qapi-obj-y): $(GENERATED_HEADERS)
+qapi-dir := qapi-generated
+test-visitor.o test-qmp-commands.o qemu-ga$(EXESUF): QEMU_CFLAGS += -I $(qapi-dir)
 
-qga/qapi-generated/qga-qapi-types.c qga/qapi-generated/qga-qapi-types.h :\
-$(SRC_PATH)/qapi-schema-guest.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)/qapi-schema-guest.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)/qapi-schema-guest.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)/test-qapi-types.c: $(qapi-dir)/test-qapi-types.h
+$(qapi-dir)/test-qapi-types.h: $(SRC_PATH)/qapi-schema-test.json $(SRC_PATH)/scripts/qapi-types.py
+	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py -o "$(qapi-dir)" -p "test-" < $<, "  GEN   $@")
+$(qapi-dir)/test-qapi-visit.c: $(qapi-dir)/test-qapi-visit.h
+$(qapi-dir)/test-qapi-visit.h: $(SRC_PATH)/qapi-schema-test.json $(SRC_PATH)/scripts/qapi-visit.py
+	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py -o "$(qapi-dir)" -p "test-" < $<, "  GEN   $@")
+$(qapi-dir)/test-qmp-commands.h: $(qapi-dir)/test-qmp-marshal.c
+$(qapi-dir)/test-qmp-marshal.c: $(SRC_PATH)/qapi-schema-test.json $(SRC_PATH)/scripts/qapi-commands.py
+	    $(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py -o "$(qapi-dir)" -p "test-" < $<, "  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 "." < $<, "  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 "."  < $<, "  GEN   $@")
-qmp-commands.h qmp-marshal.c :\
-$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py $(gen-out-type) -m -o "." < $<, "  GEN   $@")
+$(qapi-dir)/qga-qapi-types.c: $(qapi-dir)/qga-qapi-types.h
+$(qapi-dir)/qga-qapi-types.h: $(SRC_PATH)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-types.py
+	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py -o "$(qapi-dir)" -p "qga-" < $<, "  GEN   $@")
+$(qapi-dir)/qga-qapi-visit.c: $(qapi-dir)/qga-qapi-visit.h
+$(qapi-dir)/qga-qapi-visit.h: $(SRC_PATH)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-visit.py
+	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py -o "$(qapi-dir)" -p "qga-" < $<, "  GEN   $@")
+$(qapi-dir)/qga-qmp-marshal.c: $(SRC_PATH)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-commands.py
+	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py -o "$(qapi-dir)" -p "qga-" < $<, "  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)
+test-visitor.o: $(addprefix $(qapi-dir)/, test-qapi-types.c test-qapi-types.h test-qapi-visit.c test-qapi-visit.h) $(qapi-obj-y)
+test-visitor: test-visitor.o qfloat.o qint.o qdict.o qstring.o qlist.o qbool.o $(qapi-obj-y) error.o osdep.o qemu-malloc.o $(oslib-obj-y) qjson.o json-streamer.o json-lexer.o json-parser.o qerror.o qemu-error.o qemu-tool.o $(qapi-dir)/test-qapi-visit.o $(qapi-dir)/test-qapi-types.o
 
-qemu-ga$(EXESUF): qemu-ga.o $(qga-obj-y) $(oslib-obj-y) $(trace-obj-y) $(qapi-obj-y) $(qobject-obj-y) $(version-obj-y) libqemustub.a
+test-qmp-commands.o: $(addprefix $(qapi-dir)/, test-qapi-types.c test-qapi-types.h test-qapi-visit.c test-qapi-visit.h test-qmp-marshal.c test-qmp-commands.h) $(qapi-obj-y)
+test-qmp-commands: test-qmp-commands.o qfloat.o qint.o qdict.o qstring.o qlist.o qbool.o $(qapi-obj-y) error.o osdep.o qemu-malloc.o $(oslib-obj-y) qjson.o json-streamer.o json-lexer.o json-parser.o qerror.o qemu-error.o qemu-tool.o $(qapi-dir)/test-qapi-visit.o $(qapi-dir)/test-qapi-types.o $(qapi-dir)/test-qmp-marshal.o module.o
 
-QEMULIBS=libuser libdis libdis-user
+QGALIB=qga/guest-agent-command-state.o qga/guest-agent-commands.o
+QGALIB_GEN=$(addprefix $(qapi-dir)/, qga-qapi-types.c qga-qapi-types.h qga-qapi-visit.c qga-qmp-marshal.c)
+
+$(QGALIB_GEN): $(GENERATED_HEADERS)
+$(QGALIB) qemu-ga.o: $(QGALIB_GEN) $(qapi-obj-y)
+qemu-ga$(EXESUF): qemu-ga.o $(QGALIB) qemu-tool.o qemu-error.o error.o $(oslib-obj-y) $(trace-obj-y) $(block-obj-y) $(qobject-obj-y) $(version-obj-y) $(qapi-obj-y) qemu-timer-common.o qemu-sockets.o module.o qapi/qmp-dispatch.o qapi/qmp-registry.o $(qapi-dir)/qga-qapi-visit.o $(qapi-dir)/qga-qapi-types.o $(qapi-dir)/qga-qmp-marshal.o
+
+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 '*.[od]' -exec rm -f {} +
-	rm -f *.a *.lo $(TOOLS) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
+	rm -f *.o *.d *.a *.lo $(TOOLS) 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 qemu-img-cmds.h
+	rm -f trace.c trace.h trace.c-timestamp trace.h-timestamp
 	rm -f trace-dtrace.dtrace trace-dtrace.dtrace-timestamp
-	@# May not be present in GENERATED_HEADERS
 	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
-	$(MAKE) -C tests/tcg clean
+	rm -rf $(qapi-dir)
+	$(MAKE) -C tests clean
 	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
@@ -280,76 +226,65 @@ distclean: clean
 	rm -f qemu-doc.fn qemu-doc.fns qemu-doc.info qemu-doc.ky qemu-doc.kys
 	rm -f qemu-doc.log qemu-doc.pdf qemu-doc.pg qemu-doc.toc qemu-doc.tp
 	rm -f qemu-doc.vr
-	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) $(QEMULIBS); do \
 	rm -rf $$d || exit 1 ; \
         done
-	if test -f pixman/config.log; then make -C pixman distclean; 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 \
+BLOBS=bios.bin vgabios.bin vgabios-cirrus.bin \
 vgabios-stdvga.bin vgabios-vmware.bin vgabios-qxl.bin \
 ppc_rom.bin openbios-sparc32 openbios-sparc64 openbios-ppc \
 pxe-e1000.rom pxe-eepro100.rom pxe-ne2k_pci.rom \
 pxe-pcnet.rom pxe-rtl8139.rom pxe-virtio.rom \
-qemu-icon.bmp \
 bamboo.dtb petalogix-s3adsp1800.dtb petalogix-ml605.dtb \
-multiboot.bin linuxboot.bin kvmvapic.bin \
+mpc8544ds.dtb \
+multiboot.bin linuxboot.bin \
 s390-zipl.rom \
-spapr-rtas.bin slof.bin \
-palcode-clipper
+spapr-rtas.bin slof.bin
+BLOBS += extboot.bin
+BLOBS += vapic.bin
 else
 BLOBS=
 endif
 
 install-doc: $(DOCS)
-	$(INSTALL_DIR) "$(DESTDIR)$(qemu_docdir)"
-	$(INSTALL_DATA) qemu-doc.html  qemu-tech.html "$(DESTDIR)$(qemu_docdir)"
-	$(INSTALL_DATA) QMP/qmp-commands.txt "$(DESTDIR)$(qemu_docdir)"
+	$(INSTALL_DIR) "$(DESTDIR)$(docdir)"
+	$(INSTALL_DATA) qemu-doc.html  qemu-tech.html "$(DESTDIR)$(docdir)"
 ifdef CONFIG_POSIX
 	$(INSTALL_DIR) "$(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
-ifdef CONFIG_VIRTFS
-	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man1"
-	$(INSTALL_DATA) fsdev/virtfs-proxy-helper.1 "$(DESTDIR)$(mandir)/man1"
-endif
 
-install-datadir:
-	$(INSTALL_DIR) "$(DESTDIR)$(qemu_datadir)"
+install-sysconfig:
+	$(INSTALL_DIR) "$(DESTDIR)$(sysconfdir)/qemu"
+	$(INSTALL_DATA) $(SRC_PATH)/sysconfigs/target/target-x86_64.conf "$(DESTDIR)$(sysconfdir)/qemu"
 
-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: all $(if $(BUILD_DOCS),install-doc) install-sysconfig install-datadir
+install: all $(if $(BUILD_DOCS),install-doc) install-sysconfig
 	$(INSTALL_DIR) "$(DESTDIR)$(bindir)"
 ifneq ($(TOOLS),)
 	$(INSTALL_PROG) $(STRIP_OPT) $(TOOLS) "$(DESTDIR)$(bindir)"
 endif
-ifneq ($(HELPERS-y),)
-	$(INSTALL_DIR) "$(DESTDIR)$(libexecdir)"
-	$(INSTALL_PROG) $(STRIP_OPT) $(HELPERS-y) "$(DESTDIR)$(libexecdir)"
-endif
 ifneq ($(BLOBS),)
+	$(INSTALL_DIR) "$(DESTDIR)$(datadir)"
 	set -e; for x in $(BLOBS); do \
-		$(INSTALL_DATA) $(SRC_PATH)/pc-bios/$$x "$(DESTDIR)$(qemu_datadir)"; \
+	    if [ -f $(SRC_PATH)/pc-bios/$$x ];then \
+		$(INSTALL_DATA) $(SRC_PATH)/pc-bios/$$x "$(DESTDIR)$(datadir)"; \
+	    fi \
+	    ; if [ -f pc-bios/optionrom/$$x ];then \
+		$(INSTALL_DATA) pc-bios/optionrom/$$x "$(DESTDIR)$(datadir)"; \
+	    fi \
 	done
 endif
-	$(INSTALL_DIR) "$(DESTDIR)$(qemu_datadir)/keymaps"
+	$(INSTALL_DIR) "$(DESTDIR)$(datadir)/keymaps"
 	set -e; for x in $(KEYMAPS); do \
-		$(INSTALL_DATA) $(SRC_PATH)/pc-bios/keymaps/$$x "$(DESTDIR)$(qemu_datadir)/keymaps"; \
+		$(INSTALL_DATA) $(SRC_PATH)/pc-bios/keymaps/$$x "$(DESTDIR)$(datadir)/keymaps"; \
 	done
 	for d in $(TARGET_DIRS); do \
 	$(MAKE) -C $$d $@ || exit 1 ; \
@@ -357,7 +292,7 @@ endif
 
 # various test targets
 test speed: all
-	$(MAKE) -C tests/tcg $@
+	$(MAKE) -C tests $@
 
 .PHONY: TAGS
 TAGS:
@@ -365,7 +300,7 @@ TAGS:
 
 cscope:
 	rm -f ./cscope.*
-	find "$(SRC_PATH)" -name "*.[chsS]" -print | sed 's,^\./,,' > ./cscope.files
+	find . -name "*.[ch]" -print | sed 's,^\./,,' > ./cscope.files
 	cscope -b
 
 # documentation
@@ -376,7 +311,7 @@ TEXIFLAG=$(if $(V),,--quiet)
 	$(call quiet-command,texi2dvi $(TEXIFLAG) -I . $<,"  GEN   $@")
 
 %.html: %.texi
-	$(call quiet-command,LC_ALL=C $(MAKEINFO) $(MAKEINFOFLAGS) --html $< -o $@, \
+	$(call quiet-command,$(MAKEINFO) $(MAKEINFOFLAGS) --html $< -o $@, \
 	"  GEN   $@")
 
 %.info: %.texi
@@ -400,25 +335,19 @@ qemu-img-cmds.texi: $(SRC_PATH)/qemu-img-cmds.hx
 qemu.1: qemu-doc.texi qemu-options.texi qemu-monitor.texi
 	$(call quiet-command, \
 	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< qemu.pod && \
-	  $(POD2MAN) --section=1 --center=" " --release=" " qemu.pod > $@, \
+	  pod2man --section=1 --center=" " --release=" " qemu.pod > $@, \
 	  "  GEN   $@")
 
 qemu-img.1: qemu-img.texi qemu-img-cmds.texi
 	$(call quiet-command, \
 	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< qemu-img.pod && \
-	  $(POD2MAN) --section=1 --center=" " --release=" " qemu-img.pod > $@, \
-	  "  GEN   $@")
-
-fsdev/virtfs-proxy-helper.1: fsdev/virtfs-proxy-helper.texi
-	$(call quiet-command, \
-	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< fsdev/virtfs-proxy-helper.pod && \
-	  $(POD2MAN) --section=1 --center=" " --release=" " fsdev/virtfs-proxy-helper.pod > $@, \
+	  pod2man --section=1 --center=" " --release=" " qemu-img.pod > $@, \
 	  "  GEN   $@")
 
 qemu-nbd.8: qemu-nbd.texi
 	$(call quiet-command, \
 	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< qemu-nbd.pod && \
-	  $(POD2MAN) --section=8 --center=" " --release=" " qemu-nbd.pod > $@, \
+	  pod2man --section=8 --center=" " --release=" " qemu-nbd.pod > $@, \
 	  "  GEN   $@")
 
 dvi: qemu-doc.dvi qemu-tech.dvi
@@ -430,12 +359,53 @@ 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
 
-# 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
+VERSION ?= $(shell cat VERSION)
+FILE = qemu-$(VERSION)
+
+# 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)
+
+SYSTEM_TARGETS=$(filter %-softmmu,$(TARGET_DIRS))
+SYSTEM_PROGS=$(patsubst qemu-system-i386,qemu, \
+             $(patsubst %-softmmu,qemu-system-%, \
+             $(SYSTEM_TARGETS)))
+
+USER_TARGETS=$(filter %-user,$(TARGET_DIRS))
+USER_PROGS=$(patsubst %-bsd-user,qemu-%, \
+           $(patsubst %-darwin-user,qemu-%, \
+           $(patsubst %-linux-user,qemu-%, \
+           $(USER_TARGETS))))
+
+# generate a binary distribution
+tarbin:
+	cd / && tar zcvf ~/qemu-$(VERSION)-$(ARCH).tar.gz \
+	$(patsubst %,$(bindir)/%, $(SYSTEM_PROGS)) \
+	$(patsubst %,$(bindir)/%, $(USER_PROGS)) \
+	$(bindir)/qemu-img \
+	$(bindir)/qemu-nbd \
+	$(datadir)/bios.bin \
+	$(datadir)/vgabios.bin \
+	$(datadir)/vgabios-cirrus.bin \
+	$(datadir)/ppc_rom.bin \
+	$(datadir)/openbios-sparc32 \
+	$(datadir)/openbios-sparc64 \
+	$(datadir)/openbios-ppc \
+	$(datadir)/pxe-e1000.rom \
+	$(datadir)/pxe-eepro100.rom \
+	$(datadir)/pxe-ne2k_pci.rom \
+	$(datadir)/pxe-pcnet.rom \
+	$(datadir)/pxe-rtl8139.rom \
+	$(datadir)/pxe-virtio.rom \
+	$(datadir)/extboot.bin \
+	$(docdir)/qemu-doc.html \
+	$(docdir)/qemu-tech.html \
+	$(mandir)/man1/qemu.1 \
+	$(mandir)/man1/qemu-img.1 \
+	$(mandir)/man8/qemu-nbd.8
 
 # 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

@@ -18,3 +18,6 @@ all: $(libdis-y)
 
 clean:
 	rm -f *.o *.d *.a *~
+
+# Include automatically generated dependency files
+-include $(wildcard *.d */*.d)

Makefile.hw

@@ -0,0 +1,24 @@
+# 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.. -I$(SRC_PATH)/fpu
+
+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

@@ -1,116 +1,163 @@
-#######################################################################
-# Stub library, linked in tools
-stub-obj-y = stubs/
-
-#######################################################################
-# Target-independent parts used in system and user emulation
-universal-obj-y =
-universal-obj-y += qemu-log.o
-
 #######################################################################
 # 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
-qom-obj-y = qom/
-
-universal-obj-y += $(qom-obj-y)
+qobject-obj-y += qerror.o error.o
 
 #######################################################################
 # oslib-obj-y is code depending on the OS (win32 vs posix)
-oslib-obj-y = osdep.o cutils.o qemu-timer-common.o
+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 = iov.o cache-utils.o qemu-option.o module.o async.o
-block-obj-y += nbd.o block.o blockjob.o aes.o qemu-config.o
-block-obj-y += thread-pool.o qemu-progress.o qemu-sockets.o uri.o notify.o
-block-obj-y += $(coroutine-obj-y) $(qobject-obj-y) $(version-obj-y)
-block-obj-$(CONFIG_POSIX) += event_notifier-posix.o aio-posix.o
-block-obj-$(CONFIG_WIN32) += event_notifier-win32.o aio-win32.o
-block-obj-y += block/
-block-obj-y += $(qapi-obj-y) qapi-types.o qapi-visit.o
+block-obj-y = cutils.o cache-utils.o qemu-malloc.o qemu-option.o module.o async.o
+block-obj-y += nbd.o block.o aio.o aes.o qemu-config.o qemu-progress.o qemu-sockets.o
+block-obj-$(CONFIG_POSIX) += posix-aio-compat.o
+block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
+block-obj-$(CONFIG_POSIX) += compatfd.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-$(CONFIG_WIN32) += raw-win32.o
+block-nested-$(CONFIG_POSIX) += raw-posix.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)$(CONFIG_PCI),yyy)
 # Lots of the fsdev/9pcode is pulled in by vl.c via qemu_fsdev_add.
 # only pull in the actual virtio-9p device if we also enabled virtio.
 CONFIG_REALLY_VIRTFS=y
+fsdev-nested-y = qemu-fsdev.o
+else
+fsdev-nested-y = qemu-fsdev-dummy.o
 endif
+fsdev-obj-$(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.
+# libqemu_common.a: 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.
 
-common-obj-y = $(block-obj-y) blockdev.o blockdev-nbd.o block/
-common-obj-y += net.o net/
-common-obj-y += qom/
-common-obj-y += readline.o console.o cursor.o
-common-obj-y += qemu-pixman.o
+common-obj-y = $(block-obj-y) blockdev.o
+common-obj-y += $(net-obj-y)
+common-obj-y += $(qobject-obj-y)
+common-obj-$(CONFIG_LINUX) += $(fsdev-obj-$(CONFIG_LINUX))
+common-obj-y += readline.o console.o cursor.o qemu-error.o
 common-obj-y += $(oslib-obj-y)
 common-obj-$(CONFIG_WIN32) += os-win32.o
 common-obj-$(CONFIG_POSIX) += os-posix.o
 
-common-obj-$(CONFIG_LINUX) += fsdev/
-extra-obj-$(CONFIG_LINUX) += fsdev/
-
-common-obj-y += tcg-runtime.o host-utils.o main-loop.o
-common-obj-y += input.o
+common-obj-y += tcg-runtime.o host-utils.o
+common-obj-y += irq.o ioport.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-$(CONFIG_DS1338) += ds1338.o
+common-obj-y += i2c.o smbus.o smbus_eeprom.o
+common-obj-y += eeprom93xx.o
+common-obj-y += scsi-disk.o cdrom.o
+common-obj-y += scsi-generic.o scsi-bus.o
+common-obj-y += usb.o usb-hub.o usb-$(HOST_USB).o usb-hid.o usb-msd.o usb-wacom.o
+common-obj-y += usb-serial.o usb-net.o usb-bus.o usb-desc.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 usb-bt.o
+common-obj-y += bt-hci-csr.o
 common-obj-y += buffered_file.o migration.o migration-tcp.o
-common-obj-y += qemu-char.o #aio.o
+common-obj-y += qemu-char.o savevm.o #aio.o
+common-obj-y += msmouse.o ps2.o
+common-obj-y += qdev.o qdev-properties.o
 common-obj-y += block-migration.o iohandler.o
+common-obj-y += pflib.o
 common-obj-y += bitmap.o bitops.o
-common-obj-y += page_cache.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/
-common-obj-y += ui/
-common-obj-y += bt-host.o bt-vhci.o
+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 += dma-helpers.o
-common-obj-y += acl.o
-common-obj-$(CONFIG_POSIX) += compatfd.o
-common-obj-y += qemu-timer.o qemu-timer-common.o
-common-obj-y += qtest.o
-common-obj-y += vl.o
-
-common-obj-$(CONFIG_SLIRP) += slirp/
-
-common-obj-y += backends/
-
-######################################################################
-# libseccomp
-ifeq ($(CONFIG_SECCOMP),y)
-common-obj-y += qemu-seccomp.o
+ui-obj-y += keymaps.o
+ui-obj-$(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/, $(vnc-obj-y))
+
+common-obj-y += iov.o acl.o
+#common-obj-$(CONFIG_POSIX) += compatfd.o
+common-obj-y += notify.o event_notifier.o
+common-obj-y += qemu-timer.o qemu-timer-common.o
+
+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
+common-obj-$(CONFIG_SLIRP) += $(addprefix slirp/, $(slirp-obj-y))
+
+# xen backend driver support
+common-obj-$(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
 
 ######################################################################
 # libuser
@@ -118,11 +165,139 @@ endif
 user-obj-y =
 user-obj-y += envlist.o path.o
 user-obj-y += tcg-runtime.o host-utils.o
-user-obj-y += cache-utils.o
-user-obj-y += module.o
-user-obj-y += qemu-user.o
-user-obj-y += $(trace-obj-y)
-user-obj-y += qom/
+user-obj-y += cutils.o cache-utils.o
+
+######################################################################
+# libhw
+
+hw-obj-y =
+hw-obj-y += loader.o
+hw-obj-$(CONFIG_VIRTIO) += virtio-console.o
+hw-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.o
+hw-obj-y += fw_cfg.o
+hw-obj-$(CONFIG_PCI) += pci_bridge.o
+hw-obj-$(CONFIG_PCI) += msix.o msi.o
+hw-obj-$(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-$(CONFIG_PARALLEL) += parallel.o
+# Moved back to Makefile.target due to #include qemu-kvm.h:
+#hw-obj-$(CONFIG_I8254) += i8254.o
+#hw-obj-$(CONFIG_PCSPK) += pcspk.o
+hw-obj-$(CONFIG_PCKBD) += pckbd.o
+hw-obj-$(CONFIG_USB_UHCI) += usb-uhci.o
+hw-obj-$(CONFIG_USB_OHCI) += usb-ohci.o
+hw-obj-$(CONFIG_USB_EHCI) += usb-ehci.o
+hw-obj-$(CONFIG_FDC) += fdc.o
+# needs fixes for cpu hotplug, so moved to Makefile.target:
+# 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_HPET) += hpet.o
+hw-obj-$(CONFIG_APPLESMC) += applesmc.o
+hw-obj-$(CONFIG_SMARTCARD) += usb-ccid.o ccid-card-passthru.o
+hw-obj-$(CONFIG_SMARTCARD_NSS) += ccid-card-emulated.o
+hw-obj-$(CONFIG_USB_REDIR) += usb-redir.o
+
+# PPC devices
+hw-obj-$(CONFIG_OPENPIC) += openpic.o
+hw-obj-$(CONFIG_PREP_PCI) += prep_pci.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-$(CONFIG_PIIX4) += piix4.o
+
+# PCI watchdog devices
+hw-obj-$(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
+
+# 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_RC4030) += rc4030.o
+hw-obj-$(CONFIG_DP8393X) += dp8393x.o
+hw-obj-$(CONFIG_DS1225Y) += ds1225y.o
+hw-obj-$(CONFIG_MIPSNET) += mipsnet.o
+
+# Sound
+sound-obj-y =
+sound-obj-$(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 virtio-9p-debug.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
+
+hw-obj-$(CONFIG_REALLY_VIRTFS) += $(addprefix 9pfs/, $(9pfs-nested-y))
+
 
 ######################################################################
 # libdis
@@ -142,28 +317,22 @@ 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
+trace.h: trace.h-timestamp trace-dtrace.h
+else
+trace.h: trace.h-timestamp
 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")
+trace.h-timestamp: $(SRC_PATH)/trace-events config-host.mak
+	$(call quiet-command,sh $(SRC_PATH)/scripts/tracetool --$(TRACE_BACKEND) -h < $< > $@,"  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")
+trace.c-timestamp: $(SRC_PATH)/trace-events config-host.mak
+	$(call quiet-command,sh $(SRC_PATH)/scripts/tracetool --$(TRACE_BACKEND) -c < $< > $@,"  GEN   trace.c")
 	@cmp -s $@ trace.c || cp $@ trace.c
 
 trace.o: trace.c $(GENERATED_HEADERS)
@@ -175,80 +344,47 @@ trace-dtrace.h: trace-dtrace.dtrace
 # 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")
+trace-dtrace.dtrace-timestamp: $(SRC_PATH)/trace-events config-host.mak
+	$(call quiet-command,sh $(SRC_PATH)/scripts/tracetool --$(TRACE_BACKEND) -d < $< > $@,"  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")
+	$(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")
+	$(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)
+simpletrace.o: simpletrace.c $(GENERATED_HEADERS)
 
-trace-obj-$(CONFIG_TRACE_DTRACE) += trace-dtrace.o
-ifneq ($(TRACE_BACKEND),dtrace)
+ifeq ($(TRACE_BACKEND),dtrace)
+trace-obj-y = trace-dtrace.o
+else
 trace-obj-y = trace.o
+ifeq ($(TRACE_BACKEND),simple)
+trace-obj-y += simpletrace.o
+user-obj-y += qemu-timer-common.o
+endif
 endif
-
-trace-obj-$(CONFIG_TRACE_DEFAULT) += trace/default.o
-trace-obj-$(CONFIG_TRACE_SIMPLE) += trace/simple.o
-trace-obj-$(CONFIG_TRACE_SIMPLE) += qemu-timer-common.o
-trace-obj-$(CONFIG_TRACE_STDERR) += trace/stderr.o
-trace-obj-y += trace/control.o
-
-$(trace-obj-y): $(GENERATED_HEADERS)
 
 ######################################################################
 # 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
-
-common-obj-$(CONFIG_SMARTCARD_NSS) += $(libcacard-y)
+libcacard-y = cac.o event.o vcard.o vreader.o vcard_emul_nss.o vcard_emul_type.o card_7816.o
 
 ######################################################################
 # qapi
 
-qapi-obj-y = qapi/
-qapi-obj-y += qapi-types.o qapi-visit.o
-
-common-obj-y += qmp-marshal.o qapi-visit.o qapi-types.o
-common-obj-y += qmp.o hmp.o
-
-universal-obj-y += $(qapi-obj-y)
-
-######################################################################
-# guest agent
-
-qga-obj-y = qga/ qemu-ga.o module.o qemu-tool.o
-qga-obj-$(CONFIG_POSIX) += qemu-sockets.o qemu-option.o
+qapi-nested-y = qapi-visit-core.o qmp-input-visitor.o qmp-output-visitor.o qapi-dealloc-visitor.o
+qapi-nested-y += qmp-registry.o qmp-dispatch.o
+qapi-obj-y = $(addprefix qapi/, $(qapi-nested-y))
 
 vl.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
 
 vl.o: QEMU_CFLAGS+=$(SDL_CFLAGS)
 
-QEMU_CFLAGS+=$(GLIB_CFLAGS)
-
-nested-vars += \
-	stub-obj-y \
-	qga-obj-y \
-	qom-obj-y \
-	qapi-obj-y \
-	block-obj-y \
-	user-obj-y \
-	common-obj-y \
-	extra-obj-y
-dummy := $(call unnest-vars)
+vl.o: QEMU_CFLAGS+=$(GLIB_CFLAGS)

Makefile.target

@@ -1,34 +1,40 @@
 # -*- Mode: makefile -*-
 
+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)
+
 include ../config-host.mak
 include config-devices.mak
 include config-target.mak
 include $(SRC_PATH)/rules.mak
+ifneq ($(HWDIR),)
+include $(HWDIR)/config.mak
+endif
 
-$(call set-vpath, $(SRC_PATH))
+TARGET_PATH=$(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
 
-QEMU_CFLAGS+=-I$(SRC_PATH)/include
+include $(SRC_PATH)/Makefile.objs
 
 ifdef CONFIG_USER_ONLY
 # user emulator name
 QEMU_PROG=qemu-$(TARGET_ARCH2)
 else
 # system emulator name
-ifneq (,$(findstring -mwindows,$(LIBS)))
-# Terminate program name with a 'w' because the linker builds a windows executable.
-QEMU_PROGW=qemu-system-$(TARGET_ARCH2)w$(EXESUF)
-endif # windows executable
+ifeq ($(TARGET_ARCH), i386)
+QEMU_PROG=qemu$(EXESUF)
+else
 QEMU_PROG=qemu-system-$(TARGET_ARCH2)$(EXESUF)
 endif
+endif
 
 PROGS=$(QEMU_PROG)
-ifdef QEMU_PROGW
-PROGS+=$(QEMU_PROGW)
-endif
 STPFILES=
 
 ifndef CONFIG_HAIKU
@@ -38,7 +44,7 @@ endif
 config-target.h: config-target.h-timestamp
 config-target.h-timestamp: config-target.mak
 
-ifdef CONFIG_TRACE_SYSTEMTAP
+ifdef CONFIG_SYSTEMTAP_TRACE
 stap: $(QEMU_PROG).stp
 
 ifdef CONFIG_USER_ONLY
@@ -47,14 +53,13 @@ else
 TARGET_TYPE=system
 endif
 
-$(QEMU_PROG).stp: $(SRC_PATH)/trace-events
-	$(call quiet-command,$(TRACETOOL) \
-		--format=stap \
-		--backend=$(TRACE_BACKEND) \
-		--binary=$(bindir)/$(QEMU_PROG) \
-		--target-arch=$(TARGET_ARCH) \
-		--target-type=$(TARGET_TYPE) \
-		< $< > $@,"  GEN   $(QEMU_PROG).stp")
+$(QEMU_PROG).stp:
+	$(call quiet-command,sh $(SRC_PATH)/scripts/tracetool \
+		--$(TRACE_BACKEND) \
+		--binary $(bindir)/$(QEMU_PROG) \
+		--target-arch $(TARGET_ARCH) \
+		--target-type $(TARGET_TYPE) \
+		--stap < $(SRC_PATH)/trace-events > $(QEMU_PROG).stp,"  GEN   $(QEMU_PROG).stp")
 else
 stap:
 endif
@@ -66,110 +71,359 @@ all: $(PROGS) stap
 
 #########################################################
 # cpu emulator library
-obj-y = exec.o translate-all.o cpu-exec.o
-obj-y += tcg/tcg.o tcg/optimize.o
-obj-$(CONFIG_TCG_INTERPRETER) += tci.o
-obj-y += fpu/softfloat.o
-obj-y += disas.o
-obj-$(CONFIG_TCI_DIS) += tci-dis.o
-obj-y += target-$(TARGET_BASE_ARCH)/
-obj-$(CONFIG_GDBSTUB_XML) += gdbstub-xml.o
+libobj-y = exec.o cpu-exec.o
+libobj-$(CONFIG_NO_CPU_EMULATION) += fake-exec.o
+libobj-$(CONFIG_CPU_EMULATION) += translate-all.o translate.o
+libobj-$(CONFIG_CPU_EMULATION) += tcg/tcg.o
+libobj-y += fpu/softfloat.o
+libobj-y += op_helper.o helper.o
+ifeq ($(TARGET_BASE_ARCH), i386)
+libobj-y += cpuid.o
+endif
+libobj-$(CONFIG_NEED_MMU) += mmu.o
 
-tci-dis.o: QEMU_CFLAGS += -I$(SRC_PATH)/tcg -I$(SRC_PATH)/tcg/tci
+libobj-$(CONFIG_KVM) += kvm-tpr-opt.o
+
+libobj-$(TARGET_ARM) += neon_helper.o iwmmxt_helper.o
+
+libobj-y += disas.o
+
+$(libobj-y): $(GENERATED_HEADERS)
+
+# libqemu
+
+translate.o: translate.c cpu.h
+
+translate-all.o: translate-all.c cpu.h
+
+tcg/tcg.o: cpu.h
+
+# HELPER_CFLAGS is used for all the code compiled with static register
+# variables
+op_helper.o 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 $(oslib-obj-y)
+QEMU_CFLAGS+=-I$(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 \
+      qemu-malloc.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 ../libuser/, $(user-obj-y))
+obj-y += $(addprefix ../libdis-user/, $(libdis-y))
+obj-y += $(libobj-y)
 
 endif #CONFIG_LINUX_USER
 
+#########################################################
+# Darwin user emulator target
+
+ifdef CONFIG_DARWIN_USER
+
+$(call set-vpath, $(SRC_PATH)/darwin-user)
+
+QEMU_CFLAGS+=-I$(SRC_PATH)/darwin-user -I$(SRC_PATH)/darwin-user/$(TARGET_ARCH)
+
+# Leave some space for the regular program loading zone
+LDFLAGS+=-Wl,-segaddr,__STD_PROG_ZONE,0x1000 -image_base 0x0e000000
+
+LIBS+=-lmx
+
+obj-y = main.o commpage.o machload.o mmap.o signal.o syscall.o thunk.o \
+        gdbstub.o user-exec.o
+
+obj-i386-y += ioport-user.o
+
+$(obj-y) $(obj-$(TARGET_BASE_ARCH)-y): $(GENERATED_HEADERS)
+
+obj-y += $(addprefix ../libuser/, $(user-obj-y))
+obj-y += $(addprefix ../libdis-user/, $(libdis-y))
+obj-y += $(libobj-y)
+
+endif #CONFIG_DARWIN_USER
+
 #########################################################
 # BSD user emulator target
 
 ifdef CONFIG_BSD_USER
 
+$(call set-vpath, $(SRC_PATH)/bsd-user)
+
 QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ARCH)
 
-obj-y += bsd-user/
-obj-y += gdbstub.o user-exec.o $(oslib-obj-y)
+obj-y = main.o bsdload.o elfload.o mmap.o signal.o strace.o syscall.o \
+        gdbstub.o uaccess.o user-exec.o
+
+obj-i386-y += ioport-user.o
+
+$(obj-y) $(obj-$(TARGET_BASE_ARCH)-y): $(GENERATED_HEADERS)
+
+obj-y += $(addprefix ../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
-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)
-CONFIG_NO_GET_MEMORY_MAPPING = $(if $(subst n,,$(CONFIG_HAVE_GET_MEMORY_MAPPING)),n,y)
-CONFIG_NO_CORE_DUMP = $(if $(subst n,,$(CONFIG_HAVE_CORE_DUMP)),n,y)
 
-obj-y += arch_init.o cpus.o monitor.o gdbstub.o balloon.o ioport.o
-obj-y += hw/
-obj-$(CONFIG_KVM) += kvm-all.o
+obj-y = arch_init.o cpus.o monitor.o machine.o gdbstub.o vl.o balloon.o
+# virtio has to be here due to weird dependency between PCI and virtio-net.
+# need to fix this properly
+obj-$(CONFIG_NO_PCI) += pci-stub.o
+obj-$(CONFIG_PCI) += pci.o
+obj-$(CONFIG_VIRTIO) += virtio.o virtio-blk.o virtio-balloon.o virtio-net.o virtio-serial-bus.o
+obj-y += vhost_net.o
+obj-$(CONFIG_VHOST_NET) += vhost.o
+obj-$(CONFIG_REALLY_VIRTFS) += 9pfs/virtio-9p-device.o
+obj-y += rwhandler.o
+obj-$(CONFIG_KVM) += kvm.o kvm-all.o
 obj-$(CONFIG_NO_KVM) += kvm-stub.o
-obj-y += memory.o savevm.o cputlb.o
-obj-$(CONFIG_HAVE_GET_MEMORY_MAPPING) += memory_mapping.o
-obj-$(CONFIG_HAVE_CORE_DUMP) += dump.o
-obj-$(CONFIG_NO_GET_MEMORY_MAPPING) += memory_mapping-stub.o
-obj-$(CONFIG_NO_CORE_DUMP) += dump-stub.o
 LIBS+=-lz
 
 QEMU_CFLAGS += $(VNC_TLS_CFLAGS)
 QEMU_CFLAGS += $(VNC_SASL_CFLAGS)
 QEMU_CFLAGS += $(VNC_JPEG_CFLAGS)
 QEMU_CFLAGS += $(VNC_PNG_CFLAGS)
+QEMU_CFLAGS += $(GLIB_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
 
+obj-i386-$(CONFIG_XEN) += xen_platform.o
+
+# Inter-VM PCI shared memory
+CONFIG_IVSHMEM =
+ifeq ($(CONFIG_KVM), y)
+  ifeq ($(CONFIG_PCI), y)
+    CONFIG_IVSHMEM = y
+  endif
+endif
+obj-$(CONFIG_IVSHMEM) += ivshmem.o
+
 # Hardware support
+obj-i386-y += vga.o
+obj-i386-y += mc146818rtc.o i8259.o pc.o
+obj-i386-y += cirrus_vga.o sga.o apic.o ioapic.o piix_pci.o
+obj-i386-y += vmport.o
+obj-i386-y += device-hotplug.o pci-hotplug.o smbios.o wdt_ib700.o
+obj-i386-y += extboot.o
+obj-i386-y += debugcon.o multiboot.o
+obj-i386-y += pc_piix.o
+obj-i386-$(CONFIG_KVM) += kvmclock.o
+obj-i386-$(CONFIG_SPICE) += qxl.o qxl-logger.o qxl-render.o
+obj-i386-y += testdev.o
+obj-i386-y += acpi.o acpi_piix4.o
+
+obj-i386-y += pcspk.o i8254.o
+obj-i386-$(CONFIG_KVM_PIT) += i8254-kvm.o
+obj-i386-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += device-assignment.o
+
+# Hardware support
+obj-ia64-y += ide.o pckbd.o vga.o $(SOUND_HW) dma.o $(AUDIODRV)
+obj-ia64-y += fdc.o mc146818rtc.o serial.o i8259.o ipf.o
+obj-ia64-y += cirrus_vga.o parallel.o acpi.o piix_pci.o
+obj-ia64-y += usb-uhci.o
+obj-ia64-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += device-assignment.o
+
+# shared objects
+obj-ppc-y = ppc.o
+obj-ppc-y += vga.o
+# PREP target
+obj-ppc-y += i8259.o 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)
+ifeq ($(CONFIG_FDT)$(TARGET_PPC64),yy)
+obj-ppc-y += spapr.o spapr_hcall.o spapr_rtas.o spapr_vio.o
+obj-ppc-y += xics.o spapr_vty.o spapr_llan.o spapr_vscsi.o
+endif
+# PowerPC 4xx boards
+obj-ppc-y += ppc4xx_devs.o ppc4xx_pci.o ppc405_uc.o ppc405_boards.o
+obj-ppc-y += ppc440.o ppc440_bamboo.o
+# PowerPC E500 boards
+obj-ppc-y += ppce500_mpc8544ds.o mpc8544_guts.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
+
+# 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-$(CONFIG_OPENGL) += milkymist-tmu2.o
+obj-lm32-y += milkymist-uart.o
+obj-lm32-y += milkymist-vgafb.o
+obj-lm32-y += framebuffer.o
+
+obj-mips-y = mips_r4k.o mips_jazz.o mips_malta.o mips_mipssim.o
+obj-mips-y += pcspk.o i8254.o
+obj-mips-y += acpi.o acpi_piix4.o
+obj-mips-y += mips_addr.o mips_timer.o mips_int.o
+obj-mips-y += vga.o i8259.o
+obj-mips-y += g364fb.o jazz_led.o
+obj-mips-y += gt64xxx.o mc146818rtc.o
+obj-mips-y += cirrus_vga.o
+obj-mips-$(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_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-$(CONFIG_FDT) += device_tree.o
+
+# Boards
+obj-cris-y = cris_pic_cpu.o
+obj-cris-y += cris-boot.o
+obj-cris-y += etraxfs.o axis_dev88.o
+obj-cris-y += axis_dev88.o
+
+# IO blocks
+obj-cris-y += etraxfs_dma.o
+obj-cris-y += etraxfs_pic.o
+obj-cris-y += etraxfs_eth.o
+obj-cris-y += etraxfs_timer.o
+obj-cris-y += etraxfs_ser.o
+
 ifeq ($(TARGET_ARCH), sparc64)
-obj-y += hw/sparc64/
+obj-sparc-y = sun4u.o apb_pci.o
+obj-sparc-y += vga.o
+obj-sparc-y += mc146818rtc.o
+obj-sparc-y += cirrus_vga.o
 else
-obj-y += hw/$(TARGET_BASE_ARCH)/
+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 += realview_gic.o realview.o arm_sysctl.o arm11mpcore.o a9mpcore.o
+obj-arm-y += armv7m.o armv7m_nvic.o stellaris.o pl022.o stellaris_enet.o
+obj-arm-y += pl061.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 vga.o cbus.o tusb6010.o usb-musb.o
+obj-arm-y += mst_fpga.o mainstone.o
+obj-arm-y += musicpal.o bitbang_i2c.o marvell_88w8618_audio.o
+obj-arm-y += framebuffer.o
+obj-arm-y += syborg.o syborg_fb.o syborg_interrupt.o syborg_keyboard.o
+obj-arm-y += syborg_serial.o syborg_timer.o syborg_pointer.o syborg_rtc.o
+obj-arm-y += syborg_virtio.o
+obj-arm-y += vexpress.o
+obj-arm-y += strongarm.o
+obj-arm-y += collie.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 = i8259.o mc146818rtc.o
+obj-alpha-y += vga.o cirrus_vga.o
+
+ifeq ($(TARGET_ARCH), ia64)
+firmware.o: firmware.c
+	$(CC) $(HELPER_CFLAGS) $(CPPFLAGS) $(BASE_CFLAGS) -c -o $@ $<
 endif
 
 main.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
 
-GENERATED_HEADERS += hmp-commands.h qmp-commands-old.h
+monitor.o: hmp-commands.h qmp-commands.h
+
+$(obj-y) $(obj-$(TARGET_BASE_ARCH)-y): $(GENERATED_HEADERS)
+
+obj-y += $(addprefix ../, $(common-obj-y))
+obj-y += $(addprefix ../libdis/, $(libdis-y))
+obj-y += $(libobj-y)
+obj-y += $(addprefix $(HWDIR)/, $(hw-obj-y))
 
 endif # CONFIG_SOFTMMU
 
-nested-vars += obj-y
+ifndef CONFIG_LINUX_USER
+# libcacard needs qemu-thread support, and besides is only needed by devices
+# so not requires with linux-user targets
+obj-$(CONFIG_SMARTCARD_NSS) += $(addprefix ../libcacard/, $(libcacard-y))
+endif # CONFIG_LINUX_USER
 
-# This resolves all nested paths, so it must come last
-include $(SRC_PATH)/Makefile.objs
+obj-y += $(addprefix ../, $(trace-obj-y))
+obj-$(CONFIG_GDBSTUB_XML) += gdbstub-xml.o
 
-all-obj-y = $(obj-y)
-all-obj-y += $(addprefix ../, $(universal-obj-y))
+$(QEMU_PROG): $(obj-y) $(obj-$(TARGET_BASE_ARCH)-y)
+	$(call LINK,$(obj-y) $(obj-$(TARGET_BASE_ARCH)-y))
 
-ifdef CONFIG_SOFTMMU
-all-obj-y += $(addprefix ../, $(common-obj-y))
-all-obj-y += $(addprefix ../libdis/, $(libdis-y))
-all-obj-y += $(addprefix ../, $(trace-obj-y))
-else
-all-obj-y += $(addprefix ../libuser/, $(user-obj-y))
-all-obj-y += $(addprefix ../libdis-user/, $(libdis-y))
-endif #CONFIG_LINUX_USER
-
-ifdef QEMU_PROGW
-# The linker builds a windows executable. Make also a console executable.
-$(QEMU_PROGW): $(all-obj-y) ../libqemustub.a
-	$(call LINK,$^)
-$(QEMU_PROG): $(QEMU_PROGW)
-	$(call quiet-command,$(OBJCOPY) --subsystem console $(QEMU_PROGW) $(QEMU_PROG),"  GEN   $(TARGET_DIR)$(QEMU_PROG)")
-else
-$(QEMU_PROG): $(all-obj-y) ../libqemustub.a
-	$(call LINK,$^)
-endif
 
 gdbstub-xml.c: $(TARGET_XML_FILES) $(SRC_PATH)/scripts/feature_to_c.sh
 	$(call quiet-command,rm -f $@ && $(SHELL) $(SRC_PATH)/scripts/feature_to_c.sh $@ $(TARGET_XML_FILES),"  GEN   $(TARGET_DIR)$@")
@@ -177,14 +431,14 @@ gdbstub-xml.c: $(TARGET_XML_FILES) $(SRC_PATH)/scripts/feature_to_c.sh
 hmp-commands.h: $(SRC_PATH)/hmp-commands.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $(TARGET_DIR)$@")
 
-qmp-commands-old.h: $(SRC_PATH)/qmp-commands.hx
+qmp-commands.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 hmp-commands.h qmp-commands-old.h gdbstub-xml.c
-ifdef CONFIG_TRACE_SYSTEMTAP
+	rm -f *.o *.a *~ $(PROGS) nwfpe/*.o fpu/*.o
+	rm -f *.d */*.d tcg/*.o ide/*.o 9pfs/*.o
+	rm -f hmp-commands.h qmp-commands.h gdbstub-xml.c
+ifdef CONFIG_SYSTEMTAP_TRACE
 	rm -f *.stp
 endif
 
@@ -195,10 +449,10 @@ ifneq ($(STRIP),)
 	$(STRIP) $(patsubst %,"$(DESTDIR)$(bindir)/%",$(PROGS))
 endif
 endif
-ifdef CONFIG_TRACE_SYSTEMTAP
-	$(INSTALL_DIR) "$(DESTDIR)$(qemu_datadir)/../systemtap/tapset"
-	$(INSTALL_DATA) $(QEMU_PROG).stp "$(DESTDIR)$(qemu_datadir)/../systemtap/tapset"
+ifdef CONFIG_SYSTEMTAP_TRACE
+	$(INSTALL_DIR) "$(DESTDIR)$(datadir)/../systemtap/tapset"
+	$(INSTALL_DATA) $(QEMU_PROG).stp "$(DESTDIR)$(datadir)/../systemtap/tapset"
 endif
 
-GENERATED_HEADERS += config-target.h
-Makefile: $(GENERATED_HEADERS)
+# Include automatically generated dependency files
+-include $(wildcard *.d */*.d)

Makefile.user

@@ -9,8 +9,6 @@ include $(SRC_PATH)/rules.mak
 $(call set-vpath, $(SRC_PATH))
 
 QEMU_CFLAGS+=-I..
-QEMU_CFLAGS += -I$(SRC_PATH)/include
-QEMU_CFLAGS += -DCONFIG_USER_ONLY
 
 include $(SRC_PATH)/Makefile.objs
 
@@ -19,6 +17,7 @@ all: $(user-obj-y)
 	@true
 
 clean:
-	for d in . trace; do \
-	rm -f $$d/*.o $$d/*.d $$d/*.a $$d/*~; \
-	done
+	rm -f *.o *.d *.a *~
+
+# 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

@@ -1,126 +0,0 @@
-#!/usr/bin/python
-#
-# QMP command line tool
-#
-# Copyright IBM, Corp. 2011
-#
-# Authors:
-#  Anthony Liguori <aliguori@us.ibm.com>
-#
-# This work is licensed under the terms of the GNU GPLv2 or later.
-# See the COPYING file in the top-level directory.
-
-import sys, os
-from qmp import QEMUMonitorProtocol
-
-def print_response(rsp, prefix=[]):
-    if type(rsp) == list:
-        i = 0
-        for item in rsp:
-            if prefix == []:
-                prefix = ['item']
-            print_response(item, prefix[:-1] + ['%s[%d]' % (prefix[-1], i)])
-            i += 1
-    elif type(rsp) == dict:
-        for key in rsp.keys():
-            print_response(rsp[key], prefix + [key])
-    else:
-        if len(prefix):
-            print '%s: %s' % ('.'.join(prefix), rsp)
-        else:
-            print '%s' % (rsp)
-
-def main(args):
-    path = None
-
-    # Use QMP_PATH if it's set
-    if os.environ.has_key('QMP_PATH'):
-        path = os.environ['QMP_PATH']
-
-    while len(args):
-        arg = args[0]
-
-        if arg.startswith('--'):
-            arg = arg[2:]
-            if arg.find('=') == -1:
-                value = True
-            else:
-                arg, value = arg.split('=', 1)
-
-            if arg in ['path']:
-                if type(value) == str:
-                    path = value
-            elif arg in ['help']:
-                os.execlp('man', 'man', 'qmp')
-            else:
-                print 'Unknown argument "%s"' % arg
-
-            args = args[1:]
-        else:
-            break
-
-    if not path:
-        print "QMP path isn't set, use --path=qmp-monitor-address or set QMP_PATH"
-        return 1
-
-    if len(args):
-        command, args = args[0], args[1:]
-    else:
-        print 'No command found'
-        print 'Usage: "qmp [--path=qmp-monitor-address] qmp-cmd arguments"'
-        return 1
-
-    if command in ['help']:
-        os.execlp('man', 'man', 'qmp')
-
-    srv = QEMUMonitorProtocol(path)
-    srv.connect()
-
-    def do_command(srv, cmd, **kwds):
-        rsp = srv.cmd(cmd, kwds)
-        if rsp.has_key('error'):
-            raise Exception(rsp['error']['desc'])
-        return rsp['return']
-
-    commands = map(lambda x: x['name'], do_command(srv, 'query-commands'))
-
-    srv.close()
-
-    if command not in commands:
-        fullcmd = 'qmp-%s' % command
-        try:
-            os.environ['QMP_PATH'] = path
-            os.execvp(fullcmd, [fullcmd] + args)
-        except OSError, (errno, msg):
-            if errno == 2:
-                print 'Command "%s" not found.' % (fullcmd)
-                return 1
-            raise
-        return 0
-
-    srv = QEMUMonitorProtocol(path)
-    srv.connect()
-
-    arguments = {}
-    for arg in args:
-        if not arg.startswith('--'):
-            print 'Unknown argument "%s"' % arg
-            return 1
-
-        arg = arg[2:]
-        if arg.find('=') == -1:
-            value = True
-        else:
-            arg, value = arg.split('=', 1)
-
-        if arg in ['help']:
-            os.execlp('man', 'man', 'qmp-%s' % command)
-            return 1
-
-        arguments[arg] = value
-
-    rsp = do_command(srv, command, **arguments)
-    print_response(rsp)
-
-if __name__ == '__main__':
-    sys.exit(main(sys.argv[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_TRAY_MOVED
------------------
-
-It's emitted whenever the tray of a removable device is moved by the guest
-or by HMP/QMP commands.
-
-Data:
-
-- "device": device name (json-string)
-- "tray-open": true if the tray has been opened or false if it has been closed
-               (json-bool)
-
-{ "event": "DEVICE_TRAY_MOVED",
-  "data": { "device": "ide1-cd0",
-            "tray-open": true
-  },
-  "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
-
 RESET
 -----
 
@@ -208,68 +80,6 @@ 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
 ----
 
@@ -282,32 +92,6 @@ 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
 -------------
 
@@ -342,7 +126,7 @@ the authentication ID is not provided.
 VNC_DISCONNECTED
 ----------------
 
-Emitted when the connection is closed.
+Emitted when the conection is closed.
 
 Data:
 
@@ -398,17 +182,69 @@ 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
 --------

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):
         """
@@ -116,11 +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):
@@ -228,36 +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
 -------------------
@@ -205,27 +209,13 @@ incompatible way are disabled by default and will be advertised by the
 capabilities array (section '2.2 Server Greeting'). Thus, Clients can check
 that array and enable the capabilities they support.
 
-The QMP Server performs a type check on the arguments to a command.  It
-generates an error if a value does not have the expected type for its
-key, or if it does not understand a key that the Client included.  The
-strictness of the Server catches wrong assumptions of Clients about
-the Server's schema.  Clients can assume that, when such validation
-errors occur, they will be reported before the command generated any
-side effect.
+Additionally, Clients must not assume any particular:
 
-However, Clients must not assume any particular:
-
-- Length of json-arrays
-- Size of json-objects; in particular, future versions of QEMU may add
-  new keys and Clients should be able to ignore them.
+- Size of json-objects or length of json-arrays
 - Order of json-object members or json-array elements
 - Amount of errors generated by a command, that is, new errors can be added
   to any existing command in newer versions of the Server
 
-Of course, the Server does guarantee to send valid JSON.  But apart from
-this, a Client should be "conservative in what they send, and liberal in
-what they accept".
-
 6. Downstream extension of QMP
 ------------------------------
 

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):
@@ -130,32 +128,6 @@ class QEMUMonitorProtocol:
             qmp_cmd['id'] = id
         return self.cmd_obj(qmp_cmd)
 
-    def command(self, cmd, **kwds):
-        ret = self.cmd(cmd, kwds)
-        if ret.has_key('error'):
-            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 +155,3 @@ class QEMUMonitorProtocol:
     def close(self):
         self.__sock.close()
         self.__sockfile.close()
-
-    timeout = socket.timeout
-
-    def settimeout(self, timeout):
-        self.__sock.settimeout(timeout)

QMP/qom-fuse

@@ -1,138 +0,0 @@
-#!/usr/bin/python
-##
-# QEMU Object Model test tools
-#
-# 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.
-##
-
-import fuse, stat
-from fuse import Fuse
-import os, posix
-from errno import *
-from qmp import QEMUMonitorProtocol
-
-fuse.fuse_python_api = (0, 2)
-
-class QOMFS(Fuse):
-    def __init__(self, qmp, *args, **kwds):
-        Fuse.__init__(self, *args, **kwds)
-        self.qmp = qmp
-        self.qmp.connect()
-        self.ino_map = {}
-        self.ino_count = 1
-
-    def get_ino(self, path):
-        if self.ino_map.has_key(path):
-            return self.ino_map[path]
-        self.ino_map[path] = self.ino_count
-        self.ino_count += 1
-        return self.ino_map[path]
-
-    def is_object(self, path):
-        try:
-            items = self.qmp.command('qom-list', path=path)
-            return True
-        except:
-            return False
-
-    def is_property(self, path):
-        try:
-            path, prop = path.rsplit('/', 1)
-            for item in self.qmp.command('qom-list', path=path):
-                if item['name'] == prop:
-                    return True
-            return False
-        except:
-            return False
-
-    def is_link(self, path):
-        try:
-            path, prop = path.rsplit('/', 1)
-            for item in self.qmp.command('qom-list', path=path):
-                if item['name'] == prop:
-                    if item['type'].startswith('link<'):
-                        return True
-                    return False
-            return False
-        except:
-            return False
-
-    def read(self, path, length, offset):
-        if not self.is_property(path):
-            return -ENOENT
-
-        path, prop = path.rsplit('/', 1)
-        try:
-            data = str(self.qmp.command('qom-get', path=path, property=prop))
-            data += '\n' # make values shell friendly
-        except:
-            return -EPERM
-
-        if offset > len(data):
-            return ''
-
-        return str(data[offset:][:length])
-
-    def readlink(self, path):
-        if not self.is_link(path):
-            return False
-        path, prop = path.rsplit('/', 1)
-        prefix = '/'.join(['..'] * (len(path.split('/')) - 1))
-        return prefix + str(self.qmp.command('qom-get', path=path,
-                                             property=prop))
-
-    def getattr(self, path):
-        if self.is_link(path):
-            value = posix.stat_result((0755 | stat.S_IFLNK,
-                                       self.get_ino(path),
-                                       0,
-                                       2,
-                                       1000,
-                                       1000,
-                                       4096,
-                                       0,
-                                       0,
-                                       0))
-        elif self.is_object(path):
-            value = posix.stat_result((0755 | stat.S_IFDIR,
-                                       self.get_ino(path),
-                                       0,
-                                       2,
-                                       1000,
-                                       1000,
-                                       4096,
-                                       0,
-                                       0,
-                                       0))
-        elif self.is_property(path):
-            value = posix.stat_result((0644 | stat.S_IFREG,
-                                       self.get_ino(path),
-                                       0,
-                                       1,
-                                       1000,
-                                       1000,
-                                       4096,
-                                       0,
-                                       0,
-                                       0))
-        else:
-            value = -ENOENT
-        return value
-
-    def readdir(self, path, offset):
-        yield fuse.Direntry('.')
-        yield fuse.Direntry('..')
-        for item in self.qmp.command('qom-list', path=path):
-            yield fuse.Direntry(str(item['name']))
-
-if __name__ == '__main__':
-    import sys, os
-
-    fs = QOMFS(QEMUMonitorProtocol(os.environ['QMP_SOCKET']))
-    fs.main(sys.argv)

QMP/qom-get

@@ -1,67 +0,0 @@
-#!/usr/bin/python
-##
-# QEMU Object Model test tools
-#
-# Copyright IBM, Corp. 2011
-#
-# 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.
-##
-
-import sys
-import os
-from qmp import QEMUMonitorProtocol
-
-cmd, args = sys.argv[0], sys.argv[1:]
-socket_path = None
-path = None
-prop = None
-
-def usage():
-    return '''environment variables:
-    QMP_SOCKET=<path | addr:port>
-usage:
-    %s [-h] [-s <QMP socket path | addr:port>] <path>.<property>
-''' % cmd
-
-def usage_error(error_msg = "unspecified error"):
-    sys.stderr.write('%s\nERROR: %s\n' % (usage(), error_msg))
-    exit(1)
-
-if len(args) > 0:
-    if args[0] == "-h":
-        print usage()
-        exit(0);
-    elif args[0] == "-s":
-        try:
-            socket_path = args[1]
-        except:
-            usage_error("missing argument: QMP socket path or address");
-        args = args[2:]
-
-if not socket_path:
-    if os.environ.has_key('QMP_SOCKET'):
-        socket_path = os.environ['QMP_SOCKET']
-    else:
-        usage_error("no QMP socket path or address given");
-
-if len(args) > 0:
-    try:
-        path, prop = args[0].rsplit('.', 1)
-    except:
-        usage_error("invalid format for path/property/value")
-else:
-    usage_error("not enough arguments")
-
-srv = QEMUMonitorProtocol(socket_path)
-srv.connect()
-
-rsp = srv.command('qom-get', path=path, property=prop)
-if type(rsp) == dict:
-    for i in rsp.keys():
-        print '%s: %s' % (i, rsp[i])
-else:
-    print rsp

QMP/qom-list

@@ -1,64 +0,0 @@
-#!/usr/bin/python
-##
-# QEMU Object Model test tools
-#
-# Copyright IBM, Corp. 2011
-#
-# 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.
-##
-
-import sys
-import os
-from qmp import QEMUMonitorProtocol
-
-cmd, args = sys.argv[0], sys.argv[1:]
-socket_path = None
-path = None
-prop = None
-
-def usage():
-    return '''environment variables:
-    QMP_SOCKET=<path | addr:port>
-usage:
-    %s [-h] [-s <QMP socket path | addr:port>] [<path>]
-''' % cmd
-
-def usage_error(error_msg = "unspecified error"):
-    sys.stderr.write('%s\nERROR: %s\n' % (usage(), error_msg))
-    exit(1)
-
-if len(args) > 0:
-    if args[0] == "-h":
-        print usage()
-        exit(0);
-    elif args[0] == "-s":
-        try:
-            socket_path = args[1]
-        except:
-            usage_error("missing argument: QMP socket path or address");
-        args = args[2:]
-
-if not socket_path:
-    if os.environ.has_key('QMP_SOCKET'):
-        socket_path = os.environ['QMP_SOCKET']
-    else:
-        usage_error("no QMP socket path or address given");
-
-srv = QEMUMonitorProtocol(socket_path)
-srv.connect()
-
-if len(args) == 0:
-    print '/'
-    sys.exit(0)
-
-for item in srv.command('qom-list', path=args[0]):
-    if item['type'].startswith('child<'):
-        print '%s/' % item['name']
-    elif item['type'].startswith('link<'):
-        print '@%s/' % item['name']
-    else:
-        print '%s' % item['name']

QMP/qom-set

@@ -1,64 +0,0 @@
-#!/usr/bin/python
-##
-# QEMU Object Model test tools
-#
-# Copyright IBM, Corp. 2011
-#
-# 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.
-##
-
-import sys
-import os
-from qmp import QEMUMonitorProtocol
-
-cmd, args = sys.argv[0], sys.argv[1:]
-socket_path = None
-path = None
-prop = None
-value = None
-
-def usage():
-    return '''environment variables:
-    QMP_SOCKET=<path | addr:port>
-usage:
-    %s [-h] [-s <QMP socket path | addr:port>] <path>.<property> <value>
-''' % cmd
-
-def usage_error(error_msg = "unspecified error"):
-    sys.stderr.write('%s\nERROR: %s\n' % (usage(), error_msg))
-    exit(1)
-
-if len(args) > 0:
-    if args[0] == "-h":
-        print usage()
-        exit(0);
-    elif args[0] == "-s":
-        try:
-            socket_path = args[1]
-        except:
-            usage_error("missing argument: QMP socket path or address");
-        args = args[2:]
-
-if not socket_path:
-    if os.environ.has_key('QMP_SOCKET'):
-        socket_path = os.environ['QMP_SOCKET']
-    else:
-        usage_error("no QMP socket path or address given");
-
-if len(args) > 1:
-    try:
-        path, prop = args[0].rsplit('.', 1)
-    except:
-        usage_error("invalid format for path/property/value")
-    value = args[1]
-else:
-    usage_error("not enough arguments")
-
-srv = QEMUMonitorProtocol(socket_path)
-srv.connect()
-
-print srv.command('qom-set', path=path, property=prop, value=sys.argv[2])

README

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

VERSION

@@ -1 +1 @@
-1.2.91
+0.15.1

a.out.h

@@ -151,7 +151,7 @@ struct external_lineno {
 #define E_FILNMLEN	14	/* # characters in a file name		*/
 #define E_DIMNUM	4	/* # array dimensions in auxiliary entry */
 
-struct QEMU_PACKED external_syment
+struct __attribute__((packed)) external_syment
 {
   union {
     char e_name[E_SYMNMLEN];

acl.c

@@ -55,8 +55,8 @@ qemu_acl *qemu_acl_init(const char *aclname)
     if (acl)
         return acl;
 
-    acl = g_malloc(sizeof(*acl));
-    acl->aclname = g_strdup(aclname);
+    acl = qemu_malloc(sizeof(*acl));
+    acl->aclname = qemu_strdup(aclname);
     /* Deny by default, so there is no window of "open
      * access" between QEMU starting, and the user setting
      * up ACLs in the monitor */
@@ -65,7 +65,7 @@ qemu_acl *qemu_acl_init(const char *aclname)
     acl->nentries = 0;
     QTAILQ_INIT(&acl->entries);
 
-    acls = g_realloc(acls, sizeof(*acls) * (nacls +1));
+    acls = qemu_realloc(acls, sizeof(*acls) * (nacls +1));
     acls[nacls] = acl;
     nacls++;
 
@@ -95,13 +95,13 @@ int qemu_acl_party_is_allowed(qemu_acl *acl,
 
 void qemu_acl_reset(qemu_acl *acl)
 {
-    qemu_acl_entry *entry, *next_entry;
+    qemu_acl_entry *entry;
 
     /* Put back to deny by default, so there is no window
      * of "open access" while the user re-initializes the
      * access control list */
     acl->defaultDeny = 1;
-    QTAILQ_FOREACH_SAFE(entry, &acl->entries, next, next_entry) {
+    QTAILQ_FOREACH(entry, &acl->entries, next) {
         QTAILQ_REMOVE(&acl->entries, entry, next);
         free(entry->match);
         free(entry);
@@ -116,8 +116,8 @@ int qemu_acl_append(qemu_acl *acl,
 {
     qemu_acl_entry *entry;
 
-    entry = g_malloc(sizeof(*entry));
-    entry->match = g_strdup(match);
+    entry = qemu_malloc(sizeof(*entry));
+    entry->match = qemu_strdup(match);
     entry->deny = deny;
 
     QTAILQ_INSERT_TAIL(&acl->entries, entry, next);
@@ -142,8 +142,8 @@ int qemu_acl_insert(qemu_acl *acl,
         return qemu_acl_append(acl, deny, match);
 
 
-    entry = g_malloc(sizeof(*entry));
-    entry->match = g_strdup(match);
+    entry = qemu_malloc(sizeof(*entry));
+    entry->match = qemu_strdup(match);
     entry->deny = deny;
 
     QTAILQ_FOREACH(tmp, &acl->entries, next) {

aio-posix.c

@@ -1,268 +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.h"
-#include "qemu-queue.h"
-#include "qemu_socket.h"
-
-struct AioHandler
-{
-    GPollFD pfd;
-    IOHandler *io_read;
-    IOHandler *io_write;
-    AioFlushHandler *io_flush;
-    int deleted;
-    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->pfd.events = (io_read ? G_IO_IN | G_IO_HUP : 0);
-        node->pfd.events |= (io_write ? G_IO_OUT : 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;
-
-        /*
-         * FIXME: right now we cannot get G_IO_HUP and G_IO_ERR because
-         * main-loop.c is still select based (due to the slirp legacy).
-         * If main-loop.c ever switches to poll, G_IO_ERR should be
-         * tested too.  Dispatching G_IO_ERR to both handlers should be
-         * okay, since handlers need to be ready for spurious wakeups.
-         */
-        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;
-}
-
-bool aio_poll(AioContext *ctx, bool blocking)
-{
-    static struct timeval tv0;
-    AioHandler *node;
-    fd_set rdfds, wrfds;
-    int max_fd = -1;
-    int ret;
-    bool busy, progress;
-
-    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;
-        int revents;
-
-        ctx->walking_handlers++;
-
-        revents = node->pfd.revents & node->pfd.events;
-        node->pfd.revents = 0;
-
-        /* See comment in aio_pending.  */
-        if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR) && node->io_read) {
-            node->io_read(node->opaque);
-            progress = true;
-        }
-        if (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);
-        }
-    }
-
-    if (progress && !blocking) {
-        return true;
-    }
-
-    ctx->walking_handlers++;
-
-    FD_ZERO(&rdfds);
-    FD_ZERO(&wrfds);
-
-    /* fill fd sets */
-    busy = false;
-    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->opaque) == 0) {
-                continue;
-            }
-            busy = true;
-        }
-        if (!node->deleted && node->io_read) {
-            FD_SET(node->pfd.fd, &rdfds);
-            max_fd = MAX(max_fd, node->pfd.fd + 1);
-        }
-        if (!node->deleted && node->io_write) {
-            FD_SET(node->pfd.fd, &wrfds);
-            max_fd = MAX(max_fd, node->pfd.fd + 1);
-        }
-    }
-
-    ctx->walking_handlers--;
-
-    /* No AIO operations?  Get us out of here */
-    if (!busy) {
-        return progress;
-    }
-
-    /* wait until next event */
-    ret = select(max_fd, &rdfds, &wrfds, NULL, blocking ? NULL : &tv0);
-
-    /* if we have any readable fds, dispatch event */
-    if (ret > 0) {
-        /* 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 &&
-                FD_ISSET(node->pfd.fd, &rdfds) &&
-                node->io_read) {
-                node->io_read(node->opaque);
-                progress = true;
-            }
-            if (!node->deleted &&
-                FD_ISSET(node->pfd.fd, &wrfds) &&
-                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;
-}

aio-win32.c

@@ -1,218 +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.h"
-#include "qemu-queue.h"
-#include "qemu_socket.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];
-    }
-
-    return progress;
-}

aio.c

@@ -0,0 +1,230 @@
+/*
+ * 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.
+ *
+ */
+
+#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;
+    AioProcessQueue *io_process_queue;
+    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,
+                            AioProcessQueue *io_process_queue,
+                            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);
+                qemu_free(node);
+            }
+        }
+    } else {
+        if (node == NULL) {
+            /* Alloc and insert if it's not already there */
+            node = qemu_mallocz(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->io_process_queue = io_process_queue;
+        node->opaque = opaque;
+    }
+
+    qemu_set_fd_handler2(fd, NULL, io_read, io_write, opaque);
+
+    return 0;
+}
+
+void qemu_aio_flush(void)
+{
+    AioHandler *node;
+    int ret;
+
+    do {
+        ret = 0;
+
+	/*
+	 * If there are pending emulated aio start them now so flush
+	 * will be able to return 1.
+	 */
+        qemu_aio_wait();
+
+        QLIST_FOREACH(node, &aio_handlers, node) {
+            if (node->io_flush) {
+                ret |= node->io_flush(node->opaque);
+            }
+        }
+    } while (qemu_bh_poll() || ret > 0);
+}
+
+int qemu_aio_process_queue(void)
+{
+    AioHandler *node;
+    int ret = 0;
+
+    walking_handlers = 1;
+
+    QLIST_FOREACH(node, &aio_handlers, node) {
+        if (node->io_process_queue) {
+            if (node->io_process_queue(node->opaque)) {
+                ret = 1;
+            }
+        }
+    }
+
+    walking_handlers = 0;
+
+    return ret;
+}
+
+void qemu_aio_wait(void)
+{
+    int ret;
+
+    if (qemu_bh_poll())
+        return;
+
+    /*
+     * If there are callbacks left that have been queued, we need to call then.
+     * Return afterwards to avoid waiting needlessly in select().
+     */
+    if (qemu_aio_process_queue())
+        return;
+
+    do {
+        AioHandler *node;
+        fd_set rdfds, wrfds;
+        int max_fd = -1;
+
+        walking_handlers = 1;
+
+        FD_ZERO(&rdfds);
+        FD_ZERO(&wrfds);
+
+        /* fill fd sets */
+        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 && node->io_flush(node->opaque) == 0)
+                continue;
+
+            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 (max_fd == -1)
+            break;
+
+        /* wait until next event */
+        ret = select(max_fd, &rdfds, &wrfds, NULL, NULL);
+        if (ret == -1 && errno == EINTR)
+            continue;
+
+        /* 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);
+                    qemu_free(tmp);
+                }
+            }
+
+            walking_handlers = 0;
+        }
+    } while (ret == 0);
+}

arch_init.c

@@ -31,8 +31,6 @@
 #include "config.h"
 #include "monitor.h"
 #include "sysemu.h"
-#include "bitops.h"
-#include "bitmap.h"
 #include "arch_init.h"
 #include "audio/audio.h"
 #include "hw/pc.h"
@@ -43,19 +41,6 @@
 #include "net.h"
 #include "gdbstub.h"
 #include "hw/smbios.h"
-#include "exec-memory.h"
-#include "hw/pcspk.h"
-#include "qemu/page_cache.h"
-#include "qmp-commands.h"
-#include "trace.h"
-
-#ifdef DEBUG_ARCH_INIT
-#define DPRINTF(fmt, ...) \
-    do { fprintf(stdout, "arch_init: " fmt, ## __VA_ARGS__); } while (0)
-#else
-#define DPRINTF(fmt, ...) \
-    do { } while (0)
-#endif
 
 #ifdef TARGET_SPARC
 int graphic_width = 1024;
@@ -67,6 +52,7 @@ int graphic_height = 600;
 int graphic_depth = 15;
 #endif
 
+const char arch_config_name[] = CONFIG_QEMU_CONFDIR "/target-" TARGET_ARCH ".conf";
 
 #if defined(TARGET_ALPHA)
 #define QEMU_ARCH QEMU_ARCH_ALPHA
@@ -84,8 +70,6 @@ int graphic_depth = 15;
 #define QEMU_ARCH QEMU_ARCH_MICROBLAZE
 #elif defined(TARGET_MIPS)
 #define QEMU_ARCH QEMU_ARCH_MIPS
-#elif defined(TARGET_OPENRISC)
-#define QEMU_ARCH QEMU_ARCH_OPENRISC
 #elif defined(TARGET_PPC)
 #define QEMU_ARCH QEMU_ARCH_PPC
 #elif defined(TARGET_S390X)
@@ -94,10 +78,6 @@ int graphic_depth = 15;
 #define QEMU_ARCH QEMU_ARCH_SH4
 #elif defined(TARGET_SPARC)
 #define QEMU_ARCH QEMU_ARCH_SPARC
-#elif defined(TARGET_XTENSA)
-#define QEMU_ARCH QEMU_ARCH_XTENSA
-#elif defined(TARGET_UNICORE32)
-#define QEMU_ARCH QEMU_ARCH_UNICORE32
 #endif
 
 const uint32_t arch_type = QEMU_ARCH;
@@ -111,66 +91,15 @@ const uint32_t arch_type = QEMU_ARCH;
 #define RAM_SAVE_FLAG_PAGE     0x08
 #define RAM_SAVE_FLAG_EOS      0x10
 #define RAM_SAVE_FLAG_CONTINUE 0x20
-#define RAM_SAVE_FLAG_XBZRLE   0x40
 
-#ifdef __ALTIVEC__
-#include <altivec.h>
-#define VECTYPE        vector unsigned char
-#define SPLAT(p)       vec_splat(vec_ld(0, p), 0)
-#define ALL_EQ(v1, v2) vec_all_eq(v1, v2)
-/* altivec.h may redefine the bool macro as vector type.
- * Reset it to POSIX semantics. */
-#undef bool
-#define bool _Bool
-#elif defined __SSE2__
-#include <emmintrin.h>
-#define VECTYPE        __m128i
-#define SPLAT(p)       _mm_set1_epi8(*(p))
-#define ALL_EQ(v1, v2) (_mm_movemask_epi8(_mm_cmpeq_epi8(v1, v2)) == 0xFFFF)
-#else
-#define VECTYPE        unsigned long
-#define SPLAT(p)       (*(p) * (~0UL / 255))
-#define ALL_EQ(v1, v2) ((v1) == (v2))
-#endif
-
-
-static struct defconfig_file {
-    const char *filename;
-    /* Indicates it is an user config file (disabled by -no-user-config) */
-    bool userconfig;
-} default_config_files[] = {
-    { CONFIG_QEMU_CONFDIR "/qemu.conf",                   true },
-    { CONFIG_QEMU_CONFDIR "/target-" TARGET_ARCH ".conf", true },
-    { NULL }, /* end of list */
-};
-
-
-int qemu_read_default_config_files(bool userconfig)
+static int is_dup_page(uint8_t *page, uint8_t ch)
 {
-    int ret;
-    struct defconfig_file *f;
-
-    for (f = default_config_files; f->filename; f++) {
-        if (!userconfig && f->userconfig) {
-            continue;
-        }
-        ret = qemu_read_config_file(f->filename);
-        if (ret < 0 && ret != -ENOENT) {
-            return ret;
-        }
-    }
-    
-    return 0;
-}
-
-static int is_dup_page(uint8_t *page)
-{
-    VECTYPE *p = (VECTYPE *)page;
-    VECTYPE val = SPLAT(page);
+    uint32_t val = ch << 24 | ch << 16 | ch << 8 | ch;
+    uint32_t *array = (uint32_t *)page;
     int i;
 
-    for (i = 0; i < TARGET_PAGE_SIZE / sizeof(VECTYPE); i++) {
-        if (!ALL_EQ(val, p[i])) {
+    for (i = 0; i < (TARGET_PAGE_SIZE / 4); i++) {
+        if (array[i] != val) {
             return 0;
         }
     }
@@ -178,287 +107,53 @@ static int is_dup_page(uint8_t *page)
     return 1;
 }
 
-/* struct contains XBZRLE cache and a static page
-   used by the compression */
-static struct {
-    /* buffer used for XBZRLE encoding */
-    uint8_t *encoded_buf;
-    /* buffer for storing page content */
-    uint8_t *current_buf;
-    /* buffer used for XBZRLE decoding */
-    uint8_t *decoded_buf;
-    /* Cache for XBZRLE */
-    PageCache *cache;
-} XBZRLE = {
-    .encoded_buf = NULL,
-    .current_buf = NULL,
-    .decoded_buf = NULL,
-    .cache = NULL,
-};
-
-
-int64_t xbzrle_cache_resize(int64_t new_size)
-{
-    if (XBZRLE.cache != NULL) {
-        return cache_resize(XBZRLE.cache, new_size / TARGET_PAGE_SIZE) *
-            TARGET_PAGE_SIZE;
-    }
-    return pow2floor(new_size);
-}
-
-/* accounting for migration statistics */
-typedef struct AccountingInfo {
-    uint64_t dup_pages;
-    uint64_t norm_pages;
-    uint64_t iterations;
-    uint64_t xbzrle_bytes;
-    uint64_t xbzrle_pages;
-    uint64_t xbzrle_cache_miss;
-    uint64_t xbzrle_overflows;
-} AccountingInfo;
-
-static AccountingInfo acct_info;
-
-static void acct_clear(void)
-{
-    memset(&acct_info, 0, sizeof(acct_info));
-}
-
-uint64_t dup_mig_bytes_transferred(void)
-{
-    return acct_info.dup_pages * TARGET_PAGE_SIZE;
-}
-
-uint64_t dup_mig_pages_transferred(void)
-{
-    return acct_info.dup_pages;
-}
-
-uint64_t norm_mig_bytes_transferred(void)
-{
-    return acct_info.norm_pages * TARGET_PAGE_SIZE;
-}
-
-uint64_t norm_mig_pages_transferred(void)
-{
-    return acct_info.norm_pages;
-}
-
-uint64_t xbzrle_mig_bytes_transferred(void)
-{
-    return acct_info.xbzrle_bytes;
-}
-
-uint64_t xbzrle_mig_pages_transferred(void)
-{
-    return acct_info.xbzrle_pages;
-}
-
-uint64_t xbzrle_mig_pages_cache_miss(void)
-{
-    return acct_info.xbzrle_cache_miss;
-}
-
-uint64_t xbzrle_mig_pages_overflow(void)
-{
-    return acct_info.xbzrle_overflows;
-}
-
-static void save_block_hdr(QEMUFile *f, RAMBlock *block, ram_addr_t offset,
-        int cont, int flag)
-{
-        qemu_put_be64(f, offset | cont | flag);
-        if (!cont) {
-                qemu_put_byte(f, strlen(block->idstr));
-                qemu_put_buffer(f, (uint8_t *)block->idstr,
-                                strlen(block->idstr));
-        }
-
-}
-
-#define ENCODING_FLAG_XBZRLE 0x1
-
-static int save_xbzrle_page(QEMUFile *f, uint8_t *current_data,
-                            ram_addr_t current_addr, RAMBlock *block,
-                            ram_addr_t offset, int cont, bool last_stage)
-{
-    int encoded_len = 0, bytes_sent = -1;
-    uint8_t *prev_cached_page;
-
-    if (!cache_is_cached(XBZRLE.cache, current_addr)) {
-        if (!last_stage) {
-            cache_insert(XBZRLE.cache, current_addr,
-                         g_memdup(current_data, TARGET_PAGE_SIZE));
-        }
-        acct_info.xbzrle_cache_miss++;
-        return -1;
-    }
-
-    prev_cached_page = get_cached_data(XBZRLE.cache, current_addr);
-
-    /* save current buffer into memory */
-    memcpy(XBZRLE.current_buf, current_data, TARGET_PAGE_SIZE);
-
-    /* XBZRLE encoding (if there is no overflow) */
-    encoded_len = xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_buf,
-                                       TARGET_PAGE_SIZE, XBZRLE.encoded_buf,
-                                       TARGET_PAGE_SIZE);
-    if (encoded_len == 0) {
-        DPRINTF("Skipping unmodified page\n");
-        return 0;
-    } else if (encoded_len == -1) {
-        DPRINTF("Overflow\n");
-        acct_info.xbzrle_overflows++;
-        /* update data in the cache */
-        memcpy(prev_cached_page, current_data, TARGET_PAGE_SIZE);
-        return -1;
-    }
-
-    /* we need to update the data in the cache, in order to get the same data */
-    if (!last_stage) {
-        memcpy(prev_cached_page, XBZRLE.current_buf, TARGET_PAGE_SIZE);
-    }
-
-    /* Send XBZRLE based compressed page */
-    save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_XBZRLE);
-    qemu_put_byte(f, ENCODING_FLAG_XBZRLE);
-    qemu_put_be16(f, encoded_len);
-    qemu_put_buffer(f, XBZRLE.encoded_buf, encoded_len);
-    bytes_sent = encoded_len + 1 + 2;
-    acct_info.xbzrle_pages++;
-    acct_info.xbzrle_bytes += bytes_sent;
-
-    return bytes_sent;
-}
-
 static RAMBlock *last_block;
 static ram_addr_t last_offset;
-static unsigned long *migration_bitmap;
-static uint64_t migration_dirty_pages;
 
-static inline bool migration_bitmap_test_and_reset_dirty(MemoryRegion *mr,
-                                                         ram_addr_t offset)
-{
-    bool ret;
-    int nr = (mr->ram_addr + offset) >> TARGET_PAGE_BITS;
-
-    ret = test_and_clear_bit(nr, migration_bitmap);
-
-    if (ret) {
-        migration_dirty_pages--;
-    }
-    return ret;
-}
-
-static inline bool migration_bitmap_set_dirty(MemoryRegion *mr,
-                                              ram_addr_t offset)
-{
-    bool ret;
-    int nr = (mr->ram_addr + offset) >> TARGET_PAGE_BITS;
-
-    ret = test_and_set_bit(nr, migration_bitmap);
-
-    if (!ret) {
-        migration_dirty_pages++;
-    }
-    return ret;
-}
-
-static void migration_bitmap_sync(void)
-{
-    RAMBlock *block;
-    ram_addr_t addr;
-    uint64_t num_dirty_pages_init = migration_dirty_pages;
-    MigrationState *s = migrate_get_current();
-    static int64_t start_time;
-    static int64_t num_dirty_pages_period;
-    int64_t end_time;
-
-    if (!start_time) {
-        start_time = qemu_get_clock_ms(rt_clock);
-    }
-
-    trace_migration_bitmap_sync_start();
-    memory_global_sync_dirty_bitmap(get_system_memory());
-
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
-        for (addr = 0; addr < block->length; addr += TARGET_PAGE_SIZE) {
-            if (memory_region_get_dirty(block->mr, addr, TARGET_PAGE_SIZE,
-                                        DIRTY_MEMORY_MIGRATION)) {
-                migration_bitmap_set_dirty(block->mr, addr);
-            }
-        }
-        memory_region_reset_dirty(block->mr, 0, block->length,
-                                  DIRTY_MEMORY_MIGRATION);
-    }
-    trace_migration_bitmap_sync_end(migration_dirty_pages
-                                    - num_dirty_pages_init);
-    num_dirty_pages_period += migration_dirty_pages - num_dirty_pages_init;
-    end_time = qemu_get_clock_ms(rt_clock);
-
-    /* more than 1 second = 1000 millisecons */
-    if (end_time > start_time + 1000) {
-        s->dirty_pages_rate = num_dirty_pages_period * 1000
-            / (end_time - start_time);
-        start_time = end_time;
-        num_dirty_pages_period = 0;
-    }
-}
-
-
-/*
- * ram_save_block: Writes a page of memory to the stream f
- *
- * Returns:  0: if the page hasn't changed
- *          -1: if there are no more dirty pages
- *           n: the amount of bytes written in other case
- */
-
-static int ram_save_block(QEMUFile *f, bool last_stage)
+static int ram_save_block(QEMUFile *f)
 {
     RAMBlock *block = last_block;
     ram_addr_t offset = last_offset;
-    int bytes_sent = -1;
-    MemoryRegion *mr;
     ram_addr_t current_addr;
+    int bytes_sent = 0;
 
     if (!block)
         block = QLIST_FIRST(&ram_list.blocks);
 
+    current_addr = block->offset + offset;
+
     do {
-        mr = block->mr;
-        if (migration_bitmap_test_and_reset_dirty(mr, offset)) {
+        if (cpu_physical_memory_get_dirty(current_addr, MIGRATION_DIRTY_FLAG)) {
             uint8_t *p;
             int cont = (block == last_block) ? RAM_SAVE_FLAG_CONTINUE : 0;
 
-            p = memory_region_get_ram_ptr(mr) + offset;
+            cpu_physical_memory_reset_dirty(current_addr,
+                                            current_addr + TARGET_PAGE_SIZE,
+                                            MIGRATION_DIRTY_FLAG);
 
-            if (is_dup_page(p)) {
-                acct_info.dup_pages++;
-                save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_COMPRESS);
+            p = block->host + offset;
+
+            if (is_dup_page(p, *p)) {
+                qemu_put_be64(f, offset | cont | RAM_SAVE_FLAG_COMPRESS);
+                if (!cont) {
+                    qemu_put_byte(f, strlen(block->idstr));
+                    qemu_put_buffer(f, (uint8_t *)block->idstr,
+                                    strlen(block->idstr));
+                }
                 qemu_put_byte(f, *p);
                 bytes_sent = 1;
-            } else if (migrate_use_xbzrle()) {
-                current_addr = block->offset + offset;
-                bytes_sent = save_xbzrle_page(f, p, current_addr, block,
-                                              offset, cont, last_stage);
-                if (!last_stage) {
-                    p = get_cached_data(XBZRLE.cache, current_addr);
+            } else {
+                qemu_put_be64(f, offset | cont | RAM_SAVE_FLAG_PAGE);
+                if (!cont) {
+                    qemu_put_byte(f, strlen(block->idstr));
+                    qemu_put_buffer(f, (uint8_t *)block->idstr,
+                                    strlen(block->idstr));
                 }
-            }
-
-            /* either we didn't send yet (we may have had XBZRLE overflow) */
-            if (bytes_sent == -1) {
-                save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_PAGE);
                 qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
                 bytes_sent = TARGET_PAGE_SIZE;
-                acct_info.norm_pages++;
             }
 
-            /* if page is unmodified, continue to the next */
-            if (bytes_sent != 0) {
-                break;
-            }
+            break;
         }
 
         offset += TARGET_PAGE_SIZE;
@@ -468,7 +163,10 @@ static int ram_save_block(QEMUFile *f, bool last_stage)
             if (!block)
                 block = QLIST_FIRST(&ram_list.blocks);
         }
-    } while (block != last_block || offset != last_offset);
+
+        current_addr = block->offset + offset;
+
+    } while (current_addr != last_block->offset + last_offset);
 
     last_block = block;
     last_offset = offset;
@@ -480,7 +178,20 @@ static uint64_t bytes_transferred;
 
 static ram_addr_t ram_save_remaining(void)
 {
-    return migration_dirty_pages;
+    RAMBlock *block;
+    ram_addr_t count = 0;
+
+    QLIST_FOREACH(block, &ram_list.blocks, next) {
+        ram_addr_t addr;
+        for (addr = block->offset; addr < block->offset + block->length;
+             addr += TARGET_PAGE_SIZE) {
+            if (cpu_physical_memory_get_dirty(addr, MIGRATION_DIRTY_FLAG)) {
+                count++;
+            }
+        }
+    }
+
+    return count;
 }
 
 uint64_t ram_bytes_remaining(void)
@@ -508,8 +219,12 @@ static int block_compar(const void *a, const void *b)
 {
     RAMBlock * const *ablock = a;
     RAMBlock * const *bblock = b;
-
-    return strcmp((*ablock)->idstr, (*bblock)->idstr);
+    if ((*ablock)->offset < (*bblock)->offset) {
+        return -1;
+    } else if ((*ablock)->offset > (*bblock)->offset) {
+        return 1;
+    }
+    return 0;
 }
 
 static void sort_ram_list(void)
@@ -520,7 +235,7 @@ static void sort_ram_list(void)
     QLIST_FOREACH(block, &ram_list.blocks, next) {
         ++n;
     }
-    blocks = g_malloc(n * sizeof *blocks);
+    blocks = qemu_malloc(n * sizeof *blocks);
     n = 0;
     QLIST_FOREACH_SAFE(block, &ram_list.blocks, next, nblock) {
         blocks[n++] = block;
@@ -530,214 +245,94 @@ static void sort_ram_list(void)
     while (--n >= 0) {
         QLIST_INSERT_HEAD(&ram_list.blocks, blocks[n], next);
     }
-    g_free(blocks);
+    qemu_free(blocks);
 }
 
-static void migration_end(void)
-{
-    memory_global_dirty_log_stop();
-
-    if (migrate_use_xbzrle()) {
-        cache_fini(XBZRLE.cache);
-        g_free(XBZRLE.cache);
-        g_free(XBZRLE.encoded_buf);
-        g_free(XBZRLE.current_buf);
-        g_free(XBZRLE.decoded_buf);
-        XBZRLE.cache = NULL;
-    }
-}
-
-static void ram_migration_cancel(void *opaque)
-{
-    migration_end();
-}
-
-
-static void reset_ram_globals(void)
-{
-    last_block = NULL;
-    last_offset = 0;
-    sort_ram_list();
-}
-
-#define MAX_WAIT 50 /* ms, half buffered_file limit */
-
-static int ram_save_setup(QEMUFile *f, void *opaque)
-{
-    RAMBlock *block;
-    int64_t ram_pages = last_ram_offset() >> TARGET_PAGE_BITS;
-
-    migration_bitmap = bitmap_new(ram_pages);
-    bitmap_set(migration_bitmap, 1, ram_pages);
-    migration_dirty_pages = ram_pages;
-
-    bytes_transferred = 0;
-    reset_ram_globals();
-
-    if (migrate_use_xbzrle()) {
-        XBZRLE.cache = cache_init(migrate_xbzrle_cache_size() /
-                                  TARGET_PAGE_SIZE,
-                                  TARGET_PAGE_SIZE);
-        if (!XBZRLE.cache) {
-            DPRINTF("Error creating cache\n");
-            return -1;
-        }
-        XBZRLE.encoded_buf = g_malloc0(TARGET_PAGE_SIZE);
-        XBZRLE.current_buf = g_malloc(TARGET_PAGE_SIZE);
-        acct_clear();
-    }
-
-    memory_global_dirty_log_start();
-    migration_bitmap_sync();
-
-    qemu_put_be64(f, ram_bytes_total() | RAM_SAVE_FLAG_MEM_SIZE);
-
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
-        qemu_put_byte(f, strlen(block->idstr));
-        qemu_put_buffer(f, (uint8_t *)block->idstr, strlen(block->idstr));
-        qemu_put_be64(f, block->length);
-    }
-
-    qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
-
-    return 0;
-}
-
-static int ram_save_iterate(QEMUFile *f, void *opaque)
+int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
 {
+    ram_addr_t addr;
     uint64_t bytes_transferred_last;
     double bwidth = 0;
-    int ret;
-    int i;
-    uint64_t expected_downtime;
-    MigrationState *s = migrate_get_current();
+    uint64_t expected_time = 0;
+
+    if (stage < 0) {
+        cpu_physical_memory_set_dirty_tracking(0);
+        return 0;
+    }
+
+    if (cpu_physical_sync_dirty_bitmap(0, TARGET_PHYS_ADDR_MAX) != 0) {
+        qemu_file_set_error(f);
+        return 0;
+    }
+
+    if (stage == 1) {
+        RAMBlock *block;
+        bytes_transferred = 0;
+        last_block = NULL;
+        last_offset = 0;
+        sort_ram_list();
+
+        /* Make sure all dirty bits are set */
+        QLIST_FOREACH(block, &ram_list.blocks, next) {
+            for (addr = block->offset; addr < block->offset + block->length;
+                 addr += TARGET_PAGE_SIZE) {
+                if (!cpu_physical_memory_get_dirty(addr,
+                                                   MIGRATION_DIRTY_FLAG)) {
+                    cpu_physical_memory_set_dirty(addr);
+                }
+            }
+        }
+
+        /* Enable dirty memory tracking */
+        cpu_physical_memory_set_dirty_tracking(1);
+
+        qemu_put_be64(f, ram_bytes_total() | RAM_SAVE_FLAG_MEM_SIZE);
+
+        QLIST_FOREACH(block, &ram_list.blocks, next) {
+            qemu_put_byte(f, strlen(block->idstr));
+            qemu_put_buffer(f, (uint8_t *)block->idstr, strlen(block->idstr));
+            qemu_put_be64(f, block->length);
+        }
+    }
 
     bytes_transferred_last = bytes_transferred;
     bwidth = qemu_get_clock_ns(rt_clock);
 
-    i = 0;
-    while ((ret = qemu_file_rate_limit(f)) == 0) {
+    while (!qemu_file_rate_limit(f)) {
         int bytes_sent;
 
-        bytes_sent = ram_save_block(f, false);
-        /* no more blocks to sent */
-        if (bytes_sent < 0) {
+        bytes_sent = ram_save_block(f);
+        bytes_transferred += bytes_sent;
+        if (bytes_sent == 0) { /* no more blocks */
             break;
         }
-        bytes_transferred += bytes_sent;
-        acct_info.iterations++;
-        /* we want to check in the 1st loop, just in case it was the 1st time
-           and we had to sync the dirty bitmap.
-           qemu_get_clock_ns() is a bit expensive, so we only check each some
-           iterations
-        */
-        if ((i & 63) == 0) {
-            uint64_t t1 = (qemu_get_clock_ns(rt_clock) - bwidth) / 1000000;
-            if (t1 > MAX_WAIT) {
-                DPRINTF("big wait: %" PRIu64 " milliseconds, %d iterations\n",
-                        t1, i);
-                break;
-            }
-        }
-        i++;
-    }
-
-    if (ret < 0) {
-        return ret;
     }
 
     bwidth = qemu_get_clock_ns(rt_clock) - bwidth;
     bwidth = (bytes_transferred - bytes_transferred_last) / bwidth;
 
-    /* if we haven't transferred anything this round, force
-     * expected_downtime to a very high value, but without
-     * crashing */
+    /* if we haven't transferred anything this round, force expected_time to a
+     * a very high value, but without crashing */
     if (bwidth == 0) {
         bwidth = 0.000001;
     }
 
-    qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
-
-    expected_downtime = ram_save_remaining() * TARGET_PAGE_SIZE / bwidth;
-    DPRINTF("ram_save_live: expected(%" PRIu64 ") <= max(" PRIu64 ")?\n",
-            expected_downtime, migrate_max_downtime());
-
-    if (expected_downtime <= migrate_max_downtime()) {
-        migration_bitmap_sync();
-        expected_downtime = ram_save_remaining() * TARGET_PAGE_SIZE / bwidth;
-        s->expected_downtime = expected_downtime / 1000000; /* ns -> ms */
-
-        return expected_downtime <= migrate_max_downtime();
-    }
-    return 0;
-}
-
-static int ram_save_complete(QEMUFile *f, void *opaque)
-{
-    migration_bitmap_sync();
-
     /* try transferring iterative blocks of memory */
-
-    /* flush all remaining blocks regardless of rate limiting */
-    while (true) {
+    if (stage == 3) {
         int bytes_sent;
 
-        bytes_sent = ram_save_block(f, true);
-        /* no more blocks to sent */
-        if (bytes_sent < 0) {
-            break;
+        /* flush all remaining blocks regardless of rate limiting */
+        while ((bytes_sent = ram_save_block(f)) != 0) {
+            bytes_transferred += bytes_sent;
         }
-        bytes_transferred += bytes_sent;
+        cpu_physical_memory_set_dirty_tracking(0);
     }
-    memory_global_dirty_log_stop();
 
     qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
 
-    g_free(migration_bitmap);
-    migration_bitmap = NULL;
+    expected_time = ram_save_remaining() * TARGET_PAGE_SIZE / bwidth;
 
-    return 0;
-}
-
-static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
-{
-    int ret, rc = 0;
-    unsigned int xh_len;
-    int xh_flags;
-
-    if (!XBZRLE.decoded_buf) {
-        XBZRLE.decoded_buf = g_malloc(TARGET_PAGE_SIZE);
-    }
-
-    /* extract RLE header */
-    xh_flags = qemu_get_byte(f);
-    xh_len = qemu_get_be16(f);
-
-    if (xh_flags != ENCODING_FLAG_XBZRLE) {
-        fprintf(stderr, "Failed to load XBZRLE page - wrong compression!\n");
-        return -1;
-    }
-
-    if (xh_len > TARGET_PAGE_SIZE) {
-        fprintf(stderr, "Failed to load XBZRLE page - len overflow!\n");
-        return -1;
-    }
-    /* load data and decode */
-    qemu_get_buffer(f, XBZRLE.decoded_buf, xh_len);
-
-    /* decode RLE */
-    ret = xbzrle_decode_buffer(XBZRLE.decoded_buf, xh_len, host,
-                               TARGET_PAGE_SIZE);
-    if (ret == -1) {
-        fprintf(stderr, "Failed to load XBZRLE page - decode error!\n");
-        rc = -1;
-    } else  if (ret > TARGET_PAGE_SIZE) {
-        fprintf(stderr, "Failed to load XBZRLE page - size %d exceeds %d!\n",
-                ret, TARGET_PAGE_SIZE);
-        abort();
-    }
-
-    return rc;
+    return (stage == 2) && (expected_time <= migrate_max_downtime());
 }
 
 static inline void *host_from_stream_offset(QEMUFile *f,
@@ -754,7 +349,7 @@ static inline void *host_from_stream_offset(QEMUFile *f,
             return NULL;
         }
 
-        return memory_region_get_ram_ptr(block->mr) + offset;
+        return block->host + offset;
     }
 
     len = qemu_get_byte(f);
@@ -763,23 +358,19 @@ static inline void *host_from_stream_offset(QEMUFile *f,
 
     QLIST_FOREACH(block, &ram_list.blocks, next) {
         if (!strncmp(id, block->idstr, sizeof(id)))
-            return memory_region_get_ram_ptr(block->mr) + offset;
+            return block->host + offset;
     }
 
     fprintf(stderr, "Can't find block %s!\n", id);
     return NULL;
 }
 
-static int ram_load(QEMUFile *f, void *opaque, int version_id)
+int ram_load(QEMUFile *f, void *opaque, int version_id)
 {
     ram_addr_t addr;
-    int flags, ret = 0;
-    int error;
-    static uint64_t seq_iter;
+    int flags;
 
-    seq_iter++;
-
-    if (version_id < 4 || version_id > 4) {
+    if (version_id < 3 || version_id > 4) {
         return -EINVAL;
     }
 
@@ -790,7 +381,11 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
         addr &= TARGET_PAGE_MASK;
 
         if (flags & RAM_SAVE_FLAG_MEM_SIZE) {
-            if (version_id == 4) {
+            if (version_id == 3) {
+                if (addr != ram_bytes_total()) {
+                    return -EINVAL;
+                }
+            } else {
                 /* Synchronize RAM block list */
                 char id[256];
                 ram_addr_t length;
@@ -807,10 +402,8 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
 
                     QLIST_FOREACH(block, &ram_list.blocks, next) {
                         if (!strncmp(id, block->idstr, sizeof(id))) {
-                            if (block->length != length) {
-                                ret =  -EINVAL;
-                                goto done;
-                            }
+                            if (block->length != length)
+                                return -EINVAL;
                             break;
                         }
                     }
@@ -818,8 +411,7 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
                     if (!block) {
                         fprintf(stderr, "Unknown ramblock \"%s\", cannot "
                                 "accept migration\n", id);
-                        ret = -EINVAL;
-                        goto done;
+                        return -EINVAL;
                     }
 
                     total_ram_bytes -= length;
@@ -831,7 +423,10 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
             void *host;
             uint8_t ch;
 
-            host = host_from_stream_offset(f, addr, flags);
+            if (version_id == 3)
+                host = qemu_get_ram_ptr(addr);
+            else
+                host = host_from_stream_offset(f, addr, flags);
             if (!host) {
                 return -EINVAL;
             }
@@ -847,46 +442,25 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
         } else if (flags & RAM_SAVE_FLAG_PAGE) {
             void *host;
 
-            host = host_from_stream_offset(f, addr, flags);
-            if (!host) {
-                return -EINVAL;
-            }
+            if (version_id == 3)
+                host = qemu_get_ram_ptr(addr);
+            else
+                host = host_from_stream_offset(f, addr, flags);
 
             qemu_get_buffer(f, host, TARGET_PAGE_SIZE);
-        } else if (flags & RAM_SAVE_FLAG_XBZRLE) {
-            if (!migrate_use_xbzrle()) {
-                return -EINVAL;
-            }
-            void *host = host_from_stream_offset(f, addr, flags);
-            if (!host) {
-                return -EINVAL;
-            }
-
-            if (load_xbzrle(f, addr, host) < 0) {
-                ret = -EINVAL;
-                goto done;
-            }
         }
-        error = qemu_file_get_error(f);
-        if (error) {
-            ret = error;
-            goto done;
+        if (qemu_file_has_error(f)) {
+            return -EIO;
         }
     } while (!(flags & RAM_SAVE_FLAG_EOS));
 
-done:
-    DPRINTF("Completed load of VM with exit code %d seq iteration "
-            "%" PRIu64 "\n", ret, seq_iter);
-    return ret;
+    return 0;
 }
 
-SaveVMHandlers savevm_ram_handlers = {
-    .save_live_setup = ram_save_setup,
-    .save_live_iterate = ram_save_iterate,
-    .save_live_complete = ram_save_complete,
-    .load_state = ram_load,
-    .cancel = ram_migration_cancel,
-};
+void qemu_service_io(void)
+{
+    qemu_notify_event();
+}
 
 #ifdef HAS_AUDIO
 struct soundhw {
@@ -895,14 +469,14 @@ struct soundhw {
     int enabled;
     int isa;
     union {
-        int (*init_isa) (ISABus *bus);
+        int (*init_isa) (qemu_irq *pic);
         int (*init_pci) (PCIBus *bus);
     } init;
 };
 
 static struct soundhw soundhw[] = {
 #ifdef HAS_AUDIO_CHOICE
-#ifdef CONFIG_PCSPK
+#if defined(TARGET_I386) || defined(TARGET_MIPS)
     {
         "pcspk",
         "PC speaker",
@@ -995,20 +569,15 @@ void select_soundhw(const char *optarg)
 {
     struct soundhw *c;
 
-    if (is_help_option(optarg)) {
+    if (*optarg == '?') {
     show_valid_cards:
 
-#ifdef HAS_AUDIO_CHOICE
         printf("Valid sound card names (comma separated):\n");
         for (c = soundhw; c->name; ++c) {
             printf ("%-11s %s\n", c->name, c->descr);
         }
         printf("\n-soundhw all will enable all of the above\n");
-#else
-        printf("Machine has no user-selectable audio hardware "
-               "(it may or may not have always-present audio hardware).\n");
-#endif
-        exit(!is_help_option(optarg));
+        exit(*optarg != '?');
     }
     else {
         size_t l;
@@ -1055,15 +624,15 @@ void select_soundhw(const char *optarg)
     }
 }
 
-void audio_init(ISABus *isa_bus, PCIBus *pci_bus)
+void audio_init(qemu_irq *isa_pic, PCIBus *pci_bus)
 {
     struct soundhw *c;
 
     for (c = soundhw; c->name; ++c) {
         if (c->enabled) {
             if (c->isa) {
-                if (isa_bus) {
-                    c->init.init_isa(isa_bus);
+                if (isa_pic) {
+                    c->init.init_isa(isa_pic);
                 }
             } else {
                 if (pci_bus) {
@@ -1077,7 +646,7 @@ void audio_init(ISABus *isa_bus, PCIBus *pci_bus)
 void select_soundhw(const char *optarg)
 {
 }
-void audio_init(ISABus *isa_bus, PCIBus *pci_bus)
+void audio_init(qemu_irq *isa_pic, PCIBus *pci_bus)
 {
 }
 #endif
@@ -1162,13 +731,3 @@ int xen_available(void)
     return 0;
 #endif
 }
-
-
-TargetInfo *qmp_query_target(Error **errp)
-{
-    TargetInfo *info = g_malloc0(sizeof(*info));
-
-    info->arch = TARGET_TYPE;
-
-    return info;
-}

arch_init.h

@@ -1,7 +1,7 @@
 #ifndef QEMU_ARCH_INIT_H
 #define QEMU_ARCH_INIT_H
 
-#include "qmp-commands.h"
+extern const char arch_config_name[];
 
 enum {
     QEMU_ARCH_ALL = -1,
@@ -17,9 +17,6 @@ enum {
     QEMU_ARCH_S390X = 512,
     QEMU_ARCH_SH4 = 1024,
     QEMU_ARCH_SPARC = 2048,
-    QEMU_ARCH_XTENSA = 4096,
-    QEMU_ARCH_OPENRISC = 8192,
-    QEMU_ARCH_UNICORE32 = 0x4000,
 };
 
 extern const uint32_t arch_type;
@@ -29,11 +26,9 @@ void do_acpitable_option(const char *optarg);
 void do_smbios_option(const char *optarg);
 void cpudef_init(void);
 int audio_available(void);
-void audio_init(ISABus *isa_bus, PCIBus *pci_bus);
+void audio_init(qemu_irq *isa_pic, 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

@@ -1624,7 +1624,7 @@ arm_decode_shift (long given, fprintf_function func, void *stream,
 }
 
 /* Print one coprocessor instruction on INFO->STREAM.
-   Return true if the instruction matched, false if this is not a
+   Return true if the instuction matched, false if this is not a
    recognised coprocessor instruction.  */
 
 static bfd_boolean
@@ -2214,7 +2214,7 @@ print_arm_address (bfd_vma pc, struct disassemble_info *info, long given)
 }
 
 /* Print one neon instruction on INFO->STREAM.
-   Return true if the instruction matched, false if this is not a
+   Return true if the instuction matched, false if this is not a
    recognised neon instruction.  */
 
 static bfd_boolean
@@ -3927,7 +3927,7 @@ print_insn_arm (bfd_vma pc, struct disassemble_info *info)
 	    n = last_mapping_sym - 1;
 
 	  /* No mapping symbol found at this address.  Look backwards
-	     for a preceding one.  */
+	     for a preceeding one.  */
 	  for (; n >= 0; n--)
 	    {
 	      if (get_sym_code_type (info, n, &type))

arm-semi.c

@@ -37,26 +37,26 @@
 #include "hw/arm-misc.h"
 #endif
 
-#define TARGET_SYS_OPEN        0x01
-#define TARGET_SYS_CLOSE       0x02
-#define TARGET_SYS_WRITEC      0x03
-#define TARGET_SYS_WRITE0      0x04
-#define TARGET_SYS_WRITE       0x05
-#define TARGET_SYS_READ        0x06
-#define TARGET_SYS_READC       0x07
-#define TARGET_SYS_ISTTY       0x09
-#define TARGET_SYS_SEEK        0x0a
-#define TARGET_SYS_FLEN        0x0c
-#define TARGET_SYS_TMPNAM      0x0d
-#define TARGET_SYS_REMOVE      0x0e
-#define TARGET_SYS_RENAME      0x0f
-#define TARGET_SYS_CLOCK       0x10
-#define TARGET_SYS_TIME        0x11
-#define TARGET_SYS_SYSTEM      0x12
-#define TARGET_SYS_ERRNO       0x13
-#define TARGET_SYS_GET_CMDLINE 0x15
-#define TARGET_SYS_HEAPINFO    0x16
-#define TARGET_SYS_EXIT        0x18
+#define SYS_OPEN        0x01
+#define SYS_CLOSE       0x02
+#define SYS_WRITEC      0x03
+#define SYS_WRITE0      0x04
+#define SYS_WRITE       0x05
+#define SYS_READ        0x06
+#define SYS_READC       0x07
+#define SYS_ISTTY       0x09
+#define SYS_SEEK        0x0a
+#define SYS_FLEN        0x0c
+#define SYS_TMPNAM      0x0d
+#define SYS_REMOVE      0x0e
+#define SYS_RENAME      0x0f
+#define SYS_CLOCK       0x10
+#define SYS_TIME        0x11
+#define SYS_SYSTEM      0x12
+#define SYS_ERRNO       0x13
+#define SYS_GET_CMDLINE 0x15
+#define SYS_HEAPINFO    0x16
+#define SYS_EXIT        0x18
 
 #ifndef O_BINARY
 #define O_BINARY 0
@@ -108,7 +108,7 @@ static inline uint32_t set_swi_errno(TaskState *ts, uint32_t code)
     return code;
 }
 #else
-static inline uint32_t set_swi_errno(CPUARMState *env, uint32_t code)
+static inline uint32_t set_swi_errno(CPUState *env, uint32_t code)
 {
     return code;
 }
@@ -122,7 +122,7 @@ static target_ulong arm_semi_syscall_len;
 static target_ulong syscall_err;
 #endif
 
-static void arm_semi_cb(CPUARMState *env, target_ulong ret, target_ulong err)
+static void arm_semi_cb(CPUState *env, target_ulong ret, target_ulong err)
 {
 #ifdef CONFIG_USER_ONLY
     TaskState *ts = env->opaque;
@@ -138,11 +138,11 @@ static void arm_semi_cb(CPUARMState *env, target_ulong ret, target_ulong err)
     } else {
         /* Fixup syscalls that use nonstardard return conventions.  */
         switch (env->regs[0]) {
-        case TARGET_SYS_WRITE:
-        case TARGET_SYS_READ:
+        case SYS_WRITE:
+        case SYS_READ:
             env->regs[0] = arm_semi_syscall_len - ret;
             break;
-        case TARGET_SYS_SEEK:
+        case SYS_SEEK:
             env->regs[0] = 0;
             break;
         default:
@@ -152,7 +152,7 @@ static void arm_semi_cb(CPUARMState *env, target_ulong ret, target_ulong err)
     }
 }
 
-static void arm_semi_flen_cb(CPUARMState *env, target_ulong ret, target_ulong err)
+static void arm_semi_flen_cb(CPUState *env, target_ulong ret, target_ulong err)
 {
     /* The size is always stored in big-endian order, extract
        the value. We assume the size always fit in 32 bits.  */
@@ -166,20 +166,17 @@ static void arm_semi_flen_cb(CPUARMState *env, target_ulong ret, target_ulong er
 #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)
+uint32_t do_arm_semihosting(CPUState *env)
 {
     target_ulong args;
-    target_ulong arg0, arg1, arg2, arg3;
     char * s;
     int nr;
     uint32_t ret;
@@ -187,48 +184,41 @@ uint32_t do_arm_semihosting(CPUARMState *env)
 #ifdef CONFIG_USER_ONLY
     TaskState *ts = env->opaque;
 #else
-    CPUARMState *ts = env;
+    CPUState *ts = env;
 #endif
 
     nr = env->regs[0];
     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) {
+    case SYS_OPEN:
+        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)
             return (uint32_t)-1;
-        }
         if (strcmp(s, ":tt") == 0) {
-            int result_fileno = arg1 < 4 ? STDIN_FILENO : STDOUT_FILENO;
-            unlock_user(s, arg0, 0);
-            return result_fileno;
+            if (ARG(1) < 4)
+                return STDIN_FILENO;
+            else
+                return STDOUT_FILENO;
         }
         if (use_gdb_syscalls()) {
-            gdb_do_syscall(arm_semi_cb, "open,%s,%x,1a4", arg0,
-                           (int)arg2+1, gdb_open_modeflags[arg1]);
-            ret = env->regs[0];
-        } else {
-            ret = set_swi_errno(ts, open(s, open_modeflags[arg1], 0644));
-        }
-        unlock_user(s, arg0, 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, "open,%s,%x,1a4", ARG(0),
+			   (int)ARG(2)+1, gdb_open_modeflags[ARG(1)]);
             return env->regs[0];
         } else {
-            return set_swi_errno(ts, close(arg0));
+            ret = set_swi_errno(ts, open(s, open_modeflags[ARG(1)], 0644));
         }
-    case TARGET_SYS_WRITEC:
+        unlock_user(s, ARG(0), 0);
+        return ret;
+    case SYS_CLOSE:
+        if (use_gdb_syscalls()) {
+            gdb_do_syscall(arm_semi_cb, "close,%x", ARG(0));
+            return env->regs[0];
+        } else {
+            return set_swi_errno(ts, close(ARG(0)));
+        }
+    case SYS_WRITEC:
         {
           char c;
 
@@ -243,7 +233,7 @@ uint32_t do_arm_semihosting(CPUARMState *env)
                 return write(STDERR_FILENO, &c, 1);
           }
         }
-    case TARGET_SYS_WRITE0:
+    case SYS_WRITE0:
         if (!(s = lock_user_string(args)))
             /* FIXME - should this error code be -TARGET_EFAULT ? */
             return (uint32_t)-1;
@@ -256,178 +246,150 @@ 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;
+    case SYS_WRITE:
+        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;
+    case SYS_READ:
+        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.  */
+    case SYS_READC:
+       /* XXX: Read from debug cosole. Not implemented.  */
         return 0;
-    case TARGET_SYS_ISTTY:
-        GET_ARG(0);
+    case SYS_ISTTY:
         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);
+    case SYS_SEEK:
         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);
+    case SYS_FLEN:
         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;
         }
-    case TARGET_SYS_TMPNAM:
+    case SYS_TMPNAM:
         /* XXX: Not implemented.  */
         return -1;
-    case TARGET_SYS_REMOVE:
-        GET_ARG(0);
-        GET_ARG(1);
+    case SYS_REMOVE:
         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);
+    case SYS_RENAME:
         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:
+    case SYS_CLOCK:
         return clock() / (CLOCKS_PER_SEC / 100);
-    case TARGET_SYS_TIME:
+    case SYS_TIME:
         return set_swi_errno(ts, time(NULL));
-    case TARGET_SYS_SYSTEM:
-        GET_ARG(0);
-        GET_ARG(1);
+    case SYS_SYSTEM:
         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:
+    case SYS_ERRNO:
 #ifdef CONFIG_USER_ONLY
         return ts->swi_errno;
 #else
         return syscall_err;
 #endif
-    case TARGET_SYS_GET_CMDLINE:
+    case SYS_GET_CMDLINE:
         {
             /* 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)
@@ -451,13 +413,10 @@ 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;
             }
@@ -489,15 +448,14 @@ 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;
         }
-    case TARGET_SYS_HEAPINFO:
+    case SYS_HEAPINFO:
         {
             uint32_t *ptr;
             uint32_t limit;
-            GET_ARG(0);
 
 #ifdef CONFIG_USER_ONLY
             /* Some C libraries assume the heap immediately follows .bss, so
@@ -518,33 +476,29 @@ 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;
         }
-    case TARGET_SYS_EXIT:
+    case SYS_EXIT:
         gdb_exit(env, 0);
         exit(0);
     default:

async.c

@@ -24,42 +24,124 @@
 
 #include "qemu-common.h"
 #include "qemu-aio.h"
-#include "main-loop.h"
+
+/*
+ * An AsyncContext protects the callbacks of AIO requests and Bottom Halves
+ * against interfering with each other. A typical example is qcow2 that accepts
+ * asynchronous requests, but relies for manipulation of its metadata on
+ * synchronous bdrv_read/write that doesn't trigger any callbacks.
+ *
+ * However, these functions are often emulated using AIO which means that AIO
+ * callbacks must be run - but at the same time we must not run callbacks of
+ * other requests as they might start to modify metadata and corrupt the
+ * internal state of the caller of bdrv_read/write.
+ *
+ * To achieve the desired semantics we switch into a new AsyncContext.
+ * Callbacks must only be run if they belong to the current AsyncContext.
+ * Otherwise they need to be queued until their own context is active again.
+ * This is how you can make qemu_aio_wait() wait only for your own callbacks.
+ *
+ * The AsyncContexts form a stack. When you leave a AsyncContexts, you always
+ * return to the old ("parent") context.
+ */
+struct AsyncContext {
+    /* Consecutive number of the AsyncContext (position in the stack) */
+    int id;
+
+    /* Anchor of the list of Bottom Halves belonging to the context */
+    struct QEMUBH *first_bh;
+
+    /* Link to parent context */
+    struct AsyncContext *parent;
+};
+
+/* The currently active AsyncContext */
+static struct AsyncContext *async_context = &(struct AsyncContext) { 0 };
+
+/*
+ * Enter a new AsyncContext. Already scheduled Bottom Halves and AIO callbacks
+ * won't be called until this context is left again.
+ */
+void async_context_push(void)
+{
+    struct AsyncContext *new = qemu_mallocz(sizeof(*new));
+    new->parent = async_context;
+    new->id = async_context->id + 1;
+    async_context = new;
+}
+
+/* Run queued AIO completions and destroy Bottom Half */
+static void bh_run_aio_completions(void *opaque)
+{
+    QEMUBH **bh = opaque;
+    qemu_bh_delete(*bh);
+    qemu_free(bh);
+    qemu_aio_process_queue();
+}
+/*
+ * Leave the currently active AsyncContext. All Bottom Halves belonging to the
+ * old context are executed before changing the context.
+ */
+void async_context_pop(void)
+{
+    struct AsyncContext *old = async_context;
+    QEMUBH **bh;
+
+    /* Flush the bottom halves, we don't want to lose them */
+    while (qemu_bh_poll());
+
+    /* Switch back to the parent context */
+    async_context = async_context->parent;
+    qemu_free(old);
+
+    if (async_context == NULL) {
+        abort();
+    }
+
+    /* Schedule BH to run any queued AIO completions as soon as possible */
+    bh = qemu_malloc(sizeof(*bh));
+    *bh = qemu_bh_new(bh_run_aio_completions, bh);
+    qemu_bh_schedule(*bh);
+}
+
+/*
+ * Returns the ID of the currently active AsyncContext
+ */
+int get_async_context_id(void)
+{
+    return async_context->id;
+}
 
 /***********************************************************/
 /* bottom halves (can be seen as timers which expire ASAP) */
 
 struct QEMUBH {
-    AioContext *ctx;
     QEMUBHFunc *cb;
     void *opaque;
+    int scheduled;
+    int idle;
+    int deleted;
     QEMUBH *next;
-    bool scheduled;
-    bool idle;
-    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 = qemu_mallocz(sizeof(QEMUBH));
     bh->cb = cb;
     bh->opaque = opaque;
-    bh->next = ctx->first_bh;
-    ctx->first_bh = bh;
+    bh->next = async_context->first_bh;
+    async_context->first_bh = bh;
     return bh;
 }
 
-int aio_bh_poll(AioContext *ctx)
+int qemu_bh_poll(void)
 {
     QEMUBH *bh, **bhp, *next;
     int ret;
 
-    ctx->walking_bh++;
-
     ret = 0;
-    for (bh = ctx->first_bh; bh; bh = next) {
+    for (bh = async_context->first_bh; bh; bh = next) {
         next = bh->next;
         if (!bh->deleted && bh->scheduled) {
             bh->scheduled = 0;
@@ -70,20 +152,15 @@ int aio_bh_poll(AioContext *ctx)
         }
     }
 
-    ctx->walking_bh--;
-
     /* remove deleted bhs */
-    if (!ctx->walking_bh) {
-        bhp = &ctx->first_bh;
-        while (*bhp) {
-            bh = *bhp;
-            if (bh->deleted) {
-                *bhp = bh->next;
-                g_free(bh);
-            } else {
-                bhp = &bh->next;
-            }
-        }
+    bhp = &async_context->first_bh;
+    while (*bhp) {
+        bh = *bhp;
+        if (bh->deleted) {
+            *bhp = bh->next;
+            qemu_free(bh);
+        } else
+            bhp = &bh->next;
     }
 
     return ret;
@@ -103,7 +180,8 @@ void qemu_bh_schedule(QEMUBH *bh)
         return;
     bh->scheduled = 1;
     bh->idle = 0;
-    aio_notify(bh->ctx);
+    /* stop the currently executing CPU to execute the BH ASAP */
+    qemu_notify_event();
 }
 
 void qemu_bh_cancel(QEMUBH *bh)
@@ -117,106 +195,23 @@ void qemu_bh_delete(QEMUBH *bh)
     bh->deleted = 1;
 }
 
-static gboolean
-aio_ctx_prepare(GSource *source, gint    *timeout)
+void qemu_bh_update_timeout(int *timeout)
 {
-    AioContext *ctx = (AioContext *) source;
     QEMUBH *bh;
 
-    for (bh = ctx->first_bh; bh; bh = bh->next) {
+    for (bh = async_context->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;
-
-    aio_set_event_notifier(ctx, &ctx->notifier, NULL, NULL);
-    event_notifier_cleanup(&ctx->notifier);
-}
-
-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;
-}
-
-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));
-    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);
-}
-
-void aio_flush(AioContext *ctx)
-{
-    while (aio_poll(ctx, true));
-}

audio/Makefile.objs

@@ -1,14 +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

audio/alsaaudio.c

@@ -136,7 +136,7 @@ static void alsa_fini_poll (struct pollhlp *hlp)
         for (i = 0; i < hlp->count; ++i) {
             qemu_set_fd_handler (pfds[i].fd, NULL, NULL, NULL);
         }
-        g_free (pfds);
+        qemu_free (pfds);
     }
     hlp->pfds = NULL;
     hlp->count = 0;
@@ -260,7 +260,7 @@ static int alsa_poll_helper (snd_pcm_t *handle, struct pollhlp *hlp, int mask)
     if (err < 0) {
         alsa_logerr (err, "Could not initialize poll mode\n"
                      "Could not obtain poll descriptors\n");
-        g_free (pfds);
+        qemu_free (pfds);
         return -1;
     }
 
@@ -288,7 +288,7 @@ static int alsa_poll_helper (snd_pcm_t *handle, struct pollhlp *hlp, int mask)
             while (i--) {
                 qemu_set_fd_handler (pfds[i].fd, NULL, NULL, NULL);
             }
-            g_free (pfds);
+            qemu_free (pfds);
             return -1;
         }
     }
@@ -816,7 +816,7 @@ static void alsa_fini_out (HWVoiceOut *hw)
     alsa_anal_close (&alsa->handle, &alsa->pollhlp);
 
     if (alsa->pcm_buf) {
-        g_free (alsa->pcm_buf);
+        qemu_free (alsa->pcm_buf);
         alsa->pcm_buf = NULL;
     }
 }
@@ -979,7 +979,7 @@ static void alsa_fini_in (HWVoiceIn *hw)
     alsa_anal_close (&alsa->handle, &alsa->pollhlp);
 
     if (alsa->pcm_buf) {
-        g_free (alsa->pcm_buf);
+        qemu_free (alsa->pcm_buf);
         alsa->pcm_buf = NULL;
     }
 }

audio/audio.c

@@ -196,7 +196,7 @@ void *audio_calloc (const char *funcname, int nmemb, size_t size)
         return NULL;
     }
 
-    return g_malloc0 (len);
+    return qemu_mallocz (len);
 }
 
 static char *audio_alloc_prefix (const char *s)
@@ -210,7 +210,7 @@ static char *audio_alloc_prefix (const char *s)
     }
 
     len = strlen (s);
-    r = g_malloc (len + sizeof (qemu_prefix));
+    r = qemu_malloc (len + sizeof (qemu_prefix));
 
     u = r + sizeof (qemu_prefix) - 1;
 
@@ -425,7 +425,7 @@ static void audio_print_options (const char *prefix,
         printf ("    %s\n", opt->descr);
     }
 
-    g_free (uprefix);
+    qemu_free (uprefix);
 }
 
 static void audio_process_options (const char *prefix,
@@ -462,7 +462,7 @@ static void audio_process_options (const char *prefix,
          * (includes trailing zero) + zero + underscore (on behalf of
          * sizeof) */
         optlen = len + preflen + sizeof (qemu_prefix) + 1;
-        optname = g_malloc (optlen);
+        optname = qemu_malloc (optlen);
 
         pstrcpy (optname, optlen, qemu_prefix);
 
@@ -507,7 +507,7 @@ static void audio_process_options (const char *prefix,
             opt->overriddenp = &opt->overridden;
         }
         *opt->overriddenp = !def;
-        g_free (optname);
+        qemu_free (optname);
     }
 }
 
@@ -585,20 +585,17 @@ static int audio_pcm_info_eq (struct audio_pcm_info *info, struct audsettings *a
     switch (as->fmt) {
     case AUD_FMT_S8:
         sign = 1;
-        /* fall through */
     case AUD_FMT_U8:
         break;
 
     case AUD_FMT_S16:
         sign = 1;
-        /* fall through */
     case AUD_FMT_U16:
         bits = 16;
         break;
 
     case AUD_FMT_S32:
         sign = 1;
-        /* fall through */
     case AUD_FMT_U32:
         bits = 32;
         break;
@@ -781,7 +778,7 @@ static void audio_detach_capture (HWVoiceOut *hw)
 
         QLIST_REMOVE (sw, entries);
         QLIST_REMOVE (sc, entries);
-        g_free (sc);
+        qemu_free (sc);
         if (was_active) {
             /* We have removed soft voice from the capture:
                this might have changed the overall status of the capture
@@ -818,11 +815,10 @@ 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));
-            g_free (sw);
+            qemu_free (sw);
             return -1;
         }
         QLIST_INSERT_HEAD (&hw_cap->sw_head, sw, entries);
@@ -958,9 +954,7 @@ int audio_pcm_sw_read (SWVoiceIn *sw, void *buf, int size)
         total += isamp;
     }
 
-    if (!(hw->ctl_caps & VOICE_VOLUME_CAP)) {
-        mixeng_volume (sw->buf, ret, &sw->vol);
-    }
+    mixeng_volume (sw->buf, ret, &sw->vol);
 
     sw->clip (buf, sw->buf, ret);
     sw->total_hw_samples_acquired += total;
@@ -1044,10 +1038,7 @@ int audio_pcm_sw_write (SWVoiceOut *sw, void *buf, int size)
     swlim = audio_MIN (swlim, samples);
     if (swlim) {
         sw->conv (sw->buf, buf, swlim);
-
-        if (!(sw->hw->ctl_caps & VOICE_VOLUME_CAP)) {
-            mixeng_volume (sw->buf, swlim, &sw->vol);
-        }
+        mixeng_volume (sw->buf, swlim, &sw->vol);
     }
 
     while (swlim) {
@@ -1674,7 +1665,7 @@ static void audio_pp_nb_voices (const char *typ, int nb)
         printf ("Theoretically supports many %s voices\n", typ);
         break;
     default:
-        printf ("Theoretically supports up to %d %s voices\n", nb, typ);
+        printf ("Theoretically supports upto %d %s voices\n", nb, typ);
         break;
     }
 
@@ -1752,7 +1743,7 @@ static int audio_driver_init (AudioState *s, struct audio_driver *drv)
 }
 
 static void audio_vm_change_state_handler (void *opaque, int running,
-                                           RunState state)
+                                           int reason)
 {
     AudioState *s = opaque;
     HWVoiceOut *hwo = NULL;
@@ -1776,12 +1767,10 @@ static void audio_atexit (void)
     HWVoiceOut *hwo = NULL;
     HWVoiceIn *hwi = NULL;
 
-    while ((hwo = audio_pcm_hw_find_any_out (hwo))) {
+    while ((hwo = audio_pcm_hw_find_any_enabled_out (hwo))) {
         SWVoiceCap *sc;
 
-        if (hwo->enabled) {
-            hwo->pcm_ops->ctl_out (hwo, VOICE_DISABLE);
-        }
+        hwo->pcm_ops->ctl_out (hwo, VOICE_DISABLE);
         hwo->pcm_ops->fini_out (hwo);
 
         for (sc = hwo->cap_head.lh_first; sc; sc = sc->entries.le_next) {
@@ -1794,10 +1783,8 @@ static void audio_atexit (void)
         }
     }
 
-    while ((hwi = audio_pcm_hw_find_any_in (hwi))) {
-        if (hwi->enabled) {
-            hwi->pcm_ops->ctl_in (hwi, VOICE_DISABLE);
-        }
+    while ((hwi = audio_pcm_hw_find_any_enabled_in (hwi))) {
+        hwi->pcm_ops->ctl_in (hwi, VOICE_DISABLE);
         hwi->pcm_ops->fini_in (hwi);
     }
 
@@ -1920,7 +1907,7 @@ static void audio_init (void)
 void AUD_register_card (const char *name, QEMUSoundCard *card)
 {
     audio_init ();
-    card->name = g_strdup (name);
+    card->name = qemu_strdup (name);
     memset (&card->entries, 0, sizeof (card->entries));
     QLIST_INSERT_HEAD (&glob_audio_state.card_head, card, entries);
 }
@@ -1928,7 +1915,7 @@ void AUD_register_card (const char *name, QEMUSoundCard *card)
 void AUD_remove_card (QEMUSoundCard *card)
 {
     QLIST_REMOVE (card, entries);
-    g_free (card->name);
+    qemu_free (card->name);
 }
 
 
@@ -2013,11 +2000,11 @@ CaptureVoiceOut *AUD_add_capture (
         return cap;
 
     err3:
-        g_free (cap->hw.mix_buf);
+        qemu_free (cap->hw.mix_buf);
     err2:
-        g_free (cap);
+        qemu_free (cap);
     err1:
-        g_free (cb);
+        qemu_free (cb);
     err0:
         return NULL;
     }
@@ -2031,7 +2018,7 @@ void AUD_del_capture (CaptureVoiceOut *cap, void *cb_opaque)
         if (cb->opaque == cb_opaque) {
             cb->ops.destroy (cb_opaque);
             QLIST_REMOVE (cb, entries);
-            g_free (cb);
+            qemu_free (cb);
 
             if (!cap->cb_head.lh_first) {
                 SWVoiceOut *sw = cap->hw.sw_head.lh_first, *sw1;
@@ -2049,11 +2036,11 @@ void AUD_del_capture (CaptureVoiceOut *cap, void *cb_opaque)
                     }
                     QLIST_REMOVE (sw, entries);
                     QLIST_REMOVE (sc, entries);
-                    g_free (sc);
+                    qemu_free (sc);
                     sw = sw1;
                 }
                 QLIST_REMOVE (cap, entries);
-                g_free (cap);
+                qemu_free (cap);
             }
             return;
         }
@@ -2063,29 +2050,17 @@ void AUD_del_capture (CaptureVoiceOut *cap, void *cb_opaque)
 void AUD_set_volume_out (SWVoiceOut *sw, int mute, uint8_t lvol, uint8_t rvol)
 {
     if (sw) {
-        HWVoiceOut *hw = sw->hw;
-
         sw->vol.mute = mute;
         sw->vol.l = nominal_volume.l * lvol / 255;
         sw->vol.r = nominal_volume.r * rvol / 255;
-
-        if (hw->pcm_ops->ctl_out) {
-            hw->pcm_ops->ctl_out (hw, VOICE_VOLUME, sw);
-        }
     }
 }
 
 void AUD_set_volume_in (SWVoiceIn *sw, int mute, uint8_t lvol, uint8_t rvol)
 {
     if (sw) {
-        HWVoiceIn *hw = sw->hw;
-
         sw->vol.mute = mute;
         sw->vol.l = nominal_volume.l * lvol / 255;
         sw->vol.r = nominal_volume.r * rvol / 255;
-
-        if (hw->pcm_ops->ctl_in) {
-            hw->pcm_ops->ctl_in (hw, VOICE_VOLUME, sw);
-        }
     }
 }

audio/audio_int.h

@@ -82,7 +82,6 @@ typedef struct HWVoiceOut {
     int samples;
     QLIST_HEAD (sw_out_listhead, SWVoiceOut) sw_head;
     QLIST_HEAD (sw_cap_listhead, SWVoiceCap) cap_head;
-    int ctl_caps;
     struct audio_pcm_ops *pcm_ops;
     QLIST_ENTRY (HWVoiceOut) entries;
 } HWVoiceOut;
@@ -102,7 +101,6 @@ typedef struct HWVoiceIn {
 
     int samples;
     QLIST_HEAD (sw_in_listhead, SWVoiceIn) sw_head;
-    int ctl_caps;
     struct audio_pcm_ops *pcm_ops;
     QLIST_ENTRY (HWVoiceIn) entries;
 } HWVoiceIn;
@@ -152,7 +150,6 @@ struct audio_driver {
     int max_voices_in;
     int voice_size_out;
     int voice_size_in;
-    int ctl_caps;
 };
 
 struct audio_pcm_ops {
@@ -234,9 +231,6 @@ void audio_run (const char *msg);
 
 #define VOICE_ENABLE 1
 #define VOICE_DISABLE 2
-#define VOICE_VOLUME 3
-
-#define VOICE_VOLUME_CAP (1 << VOICE_VOLUME)
 
 static inline int audio_ring_dist (int dst, int src, int len)
 {

audio/audio_pt_int.c

@@ -1,4 +1,3 @@
-/* public domain */
 #include "qemu-common.h"
 #include "audio.h"
 

audio/audio_template.h

@@ -72,7 +72,7 @@ static void glue (audio_init_nb_voices_, TYPE) (struct audio_driver *drv)
 static void glue (audio_pcm_hw_free_resources_, TYPE) (HW *hw)
 {
     if (HWBUF) {
-        g_free (HWBUF);
+        qemu_free (HWBUF);
     }
 
     HWBUF = NULL;
@@ -93,7 +93,7 @@ static int glue (audio_pcm_hw_alloc_resources_, TYPE) (HW *hw)
 static void glue (audio_pcm_sw_free_resources_, TYPE) (SW *sw)
 {
     if (sw->buf) {
-        g_free (sw->buf);
+        qemu_free (sw->buf);
     }
 
     if (sw->rate) {
@@ -123,7 +123,7 @@ static int glue (audio_pcm_sw_alloc_resources_, TYPE) (SW *sw)
     sw->rate = st_rate_start (sw->hw->info.freq, sw->info.freq);
 #endif
     if (!sw->rate) {
-        g_free (sw->buf);
+        qemu_free (sw->buf);
         sw->buf = NULL;
         return -1;
     }
@@ -160,10 +160,10 @@ static int glue (audio_pcm_sw_init_, TYPE) (
         [sw->info.swap_endianness]
         [audio_bits_to_index (sw->info.bits)];
 
-    sw->name = g_strdup (name);
+    sw->name = qemu_strdup (name);
     err = glue (audio_pcm_sw_alloc_resources_, TYPE) (sw);
     if (err) {
-        g_free (sw->name);
+        qemu_free (sw->name);
         sw->name = NULL;
     }
     return err;
@@ -173,7 +173,7 @@ static void glue (audio_pcm_sw_fini_, TYPE) (SW *sw)
 {
     glue (audio_pcm_sw_free_resources_, TYPE) (sw);
     if (sw->name) {
-        g_free (sw->name);
+        qemu_free (sw->name);
         sw->name = NULL;
     }
 }
@@ -201,7 +201,7 @@ static void glue (audio_pcm_hw_gc_, TYPE) (HW **hwp)
         glue (s->nb_hw_voices_, TYPE) += 1;
         glue (audio_pcm_hw_free_resources_ ,TYPE) (hw);
         glue (hw->pcm_ops->fini_, TYPE) (hw);
-        g_free (hw);
+        qemu_free (hw);
         *hwp = NULL;
     }
 }
@@ -263,8 +263,6 @@ static HW *glue (audio_pcm_hw_add_new_, TYPE) (struct audsettings *as)
     }
 
     hw->pcm_ops = drv->pcm_ops;
-    hw->ctl_caps = drv->ctl_caps;
-
     QLIST_INIT (&hw->sw_head);
 #ifdef DAC
     QLIST_INIT (&hw->cap_head);
@@ -302,7 +300,7 @@ static HW *glue (audio_pcm_hw_add_new_, TYPE) (struct audsettings *as)
  err1:
     glue (hw->pcm_ops->fini_, TYPE) (hw);
  err0:
-    g_free (hw);
+    qemu_free (hw);
     return NULL;
 }
 
@@ -370,7 +368,7 @@ err3:
     glue (audio_pcm_hw_del_sw_, TYPE) (sw);
     glue (audio_pcm_hw_gc_, TYPE) (&hw);
 err2:
-    g_free (sw);
+    qemu_free (sw);
 err1:
     return NULL;
 }
@@ -380,7 +378,7 @@ static void glue (audio_close_, TYPE) (SW *sw)
     glue (audio_pcm_sw_fini_, TYPE) (sw);
     glue (audio_pcm_hw_del_sw_, TYPE) (sw);
     glue (audio_pcm_hw_gc_, TYPE) (&sw->hw);
-    g_free (sw);
+    qemu_free (sw);
 }
 
 void glue (AUD_close_, TYPE) (QEMUSoundCard *card, SW *sw)
@@ -410,15 +408,15 @@ 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/esdaudio.c

@@ -201,7 +201,7 @@ static int qesd_init_out (HWVoiceOut *hw, struct audsettings *as)
     case AUD_FMT_S32:
     case AUD_FMT_U32:
         dolog ("Will use 16 instead of 32 bit samples\n");
-        /* fall through */
+
     case AUD_FMT_S16:
     case AUD_FMT_U16:
     deffmt:
@@ -246,7 +246,7 @@ static int qesd_init_out (HWVoiceOut *hw, struct audsettings *as)
     esd->fd = -1;
 
  fail1:
-    g_free (esd->pcm_buf);
+    qemu_free (esd->pcm_buf);
     esd->pcm_buf = NULL;
     return -1;
 }
@@ -270,7 +270,7 @@ static void qesd_fini_out (HWVoiceOut *hw)
 
     audio_pt_fini (&esd->pt, AUDIO_FUNC);
 
-    g_free (esd->pcm_buf);
+    qemu_free (esd->pcm_buf);
     esd->pcm_buf = NULL;
 }
 
@@ -453,7 +453,7 @@ static int qesd_init_in (HWVoiceIn *hw, struct audsettings *as)
     esd->fd = -1;
 
  fail1:
-    g_free (esd->pcm_buf);
+    qemu_free (esd->pcm_buf);
     esd->pcm_buf = NULL;
     return -1;
 }
@@ -477,7 +477,7 @@ static void qesd_fini_in (HWVoiceIn *hw)
 
     audio_pt_fini (&esd->pt, AUDIO_FUNC);
 
-    g_free (esd->pcm_buf);
+    qemu_free (esd->pcm_buf);
     esd->pcm_buf = NULL;
 }
 

audio/fmodaudio.c

@@ -343,7 +343,7 @@ static void fmod_fini_out (HWVoiceOut *hw)
 
 static int fmod_init_out (HWVoiceOut *hw, struct audsettings *as)
 {
-    int mode, channel;
+    int bits16, mode, channel;
     FMODVoiceOut *fmd = (FMODVoiceOut *) hw;
     struct audsettings obt_as = *as;
 
@@ -374,6 +374,7 @@ static int fmod_init_out (HWVoiceOut *hw, struct audsettings *as)
     /* FMOD always operates on little endian frames? */
     obt_as.endianness = 0;
     audio_pcm_init_info (&hw->info, &obt_as);
+    bits16 = (mode & FSOUND_16BITS) != 0;
     hw->samples = conf.nb_samples;
     return 0;
 }
@@ -404,7 +405,7 @@ static int fmod_ctl_out (HWVoiceOut *hw, int cmd, ...)
 
 static int fmod_init_in (HWVoiceIn *hw, struct audsettings *as)
 {
-    int mode;
+    int bits16, mode;
     FMODVoiceIn *fmd = (FMODVoiceIn *) hw;
     struct audsettings obt_as = *as;
 
@@ -431,6 +432,7 @@ static int fmod_init_in (HWVoiceIn *hw, struct audsettings *as)
     /* FMOD always operates on little endian frames? */
     obt_as.endianness = 0;
     audio_pcm_init_info (&hw->info, &obt_as);
+    bits16 = (mode & FSOUND_16BITS) != 0;
     hw->samples = conf.nb_samples;
     return 0;
 }

audio/mixeng.c

@@ -33,8 +33,7 @@
 #define ENDIAN_CONVERT(v) (v)
 
 /* Signed 8 bit */
-#define BSIZE 8
-#define ITYPE int
+#define IN_T int8_t
 #define IN_MIN SCHAR_MIN
 #define IN_MAX SCHAR_MAX
 #define SIGNED
@@ -43,29 +42,25 @@
 #undef SIGNED
 #undef IN_MAX
 #undef IN_MIN
-#undef BSIZE
-#undef ITYPE
+#undef IN_T
 #undef SHIFT
 
 /* Unsigned 8 bit */
-#define BSIZE 8
-#define ITYPE uint
+#define IN_T uint8_t
 #define IN_MIN 0
 #define IN_MAX UCHAR_MAX
 #define SHIFT 8
 #include "mixeng_template.h"
 #undef IN_MAX
 #undef IN_MIN
-#undef BSIZE
-#undef ITYPE
+#undef IN_T
 #undef SHIFT
 
 #undef ENDIAN_CONVERT
 #undef ENDIAN_CONVERSION
 
 /* Signed 16 bit */
-#define BSIZE 16
-#define ITYPE int
+#define IN_T int16_t
 #define IN_MIN SHRT_MIN
 #define IN_MAX SHRT_MAX
 #define SIGNED
@@ -83,13 +78,11 @@
 #undef SIGNED
 #undef IN_MAX
 #undef IN_MIN
-#undef BSIZE
-#undef ITYPE
+#undef IN_T
 #undef SHIFT
 
 /* Unsigned 16 bit */
-#define BSIZE 16
-#define ITYPE uint
+#define IN_T uint16_t
 #define IN_MIN 0
 #define IN_MAX USHRT_MAX
 #define SHIFT 16
@@ -105,13 +98,11 @@
 #undef ENDIAN_CONVERSION
 #undef IN_MAX
 #undef IN_MIN
-#undef BSIZE
-#undef ITYPE
+#undef IN_T
 #undef SHIFT
 
 /* Signed 32 bit */
-#define BSIZE 32
-#define ITYPE int
+#define IN_T int32_t
 #define IN_MIN INT32_MIN
 #define IN_MAX INT32_MAX
 #define SIGNED
@@ -129,13 +120,11 @@
 #undef SIGNED
 #undef IN_MAX
 #undef IN_MIN
-#undef BSIZE
-#undef ITYPE
+#undef IN_T
 #undef SHIFT
 
 /* Unsigned 32 bit */
-#define BSIZE 32
-#define ITYPE uint
+#define IN_T uint32_t
 #define IN_MIN 0
 #define IN_MAX UINT32_MAX
 #define SHIFT 32
@@ -151,8 +140,7 @@
 #undef ENDIAN_CONVERSION
 #undef IN_MAX
 #undef IN_MIN
-#undef BSIZE
-#undef ITYPE
+#undef IN_T
 #undef SHIFT
 
 t_sample *mixeng_conv[2][2][2][3] = {
@@ -338,7 +326,7 @@ void *st_rate_start (int inrate, int outrate)
 
 void st_rate_stop (void *opaque)
 {
-    g_free (opaque);
+    qemu_free (opaque);
 }
 
 void mixeng_clear (struct st_sample *buf, int len)

audio/mixeng_template.h

@@ -31,8 +31,7 @@
 #define HALF (IN_MAX >> 1)
 #endif
 
-#define ET glue (ENDIAN_CONVERSION, glue (glue (glue (_, ITYPE), BSIZE), _t))
-#define IN_T glue (glue (ITYPE, BSIZE), _t)
+#define ET glue (ENDIAN_CONVERSION, glue (_, IN_T))
 
 #ifdef FLOAT_MIXENG
 static mixeng_real inline glue (conv_, ET) (IN_T v)
@@ -151,4 +150,3 @@ static void glue (glue (clip_, ET), _from_mono)
 
 #undef ET
 #undef HALF
-#undef IN_T

audio/ossaudio.c

@@ -508,7 +508,7 @@ static void oss_fini_out (HWVoiceOut *hw)
             }
         }
         else {
-            g_free (oss->pcm_buf);
+            qemu_free (oss->pcm_buf);
         }
         oss->pcm_buf = NULL;
     }
@@ -741,7 +741,7 @@ static void oss_fini_in (HWVoiceIn *hw)
     oss_anal_close (&oss->fd);
 
     if (oss->pcm_buf) {
-        g_free (oss->pcm_buf);
+        qemu_free (oss->pcm_buf);
         oss->pcm_buf = NULL;
     }
 }

audio/paaudio.c

@@ -2,7 +2,8 @@
 #include "qemu-common.h"
 #include "audio.h"
 
-#include <pulse/pulseaudio.h>
+#include <pulse/simple.h>
+#include <pulse/error.h>
 
 #define AUDIO_CAP "pulseaudio"
 #include "audio_int.h"
@@ -14,7 +15,7 @@ typedef struct {
     int live;
     int decr;
     int rpos;
-    pa_stream *stream;
+    pa_simple *s;
     void *pcm_buf;
     struct audio_pt pt;
 } PAVoiceOut;
@@ -25,23 +26,17 @@ typedef struct {
     int dead;
     int incr;
     int wpos;
-    pa_stream *stream;
+    pa_simple *s;
     void *pcm_buf;
     struct audio_pt pt;
-    const void *read_data;
-    size_t read_index, read_length;
 } PAVoiceIn;
 
-typedef struct {
+static struct {
     int samples;
     char *server;
     char *sink;
     char *source;
-    pa_threaded_mainloop *mainloop;
-    pa_context *context;
-} paaudio;
-
-static paaudio glob_paaudio = {
+} conf = {
     .samples = 4096,
 };
 
@@ -56,146 +51,6 @@ static void GCC_FMT_ATTR (2, 3) qpa_logerr (int err, const char *fmt, ...)
     AUD_log (AUDIO_CAP, "Reason: %s\n", pa_strerror (err));
 }
 
-#ifndef PA_CONTEXT_IS_GOOD
-static inline int PA_CONTEXT_IS_GOOD(pa_context_state_t x)
-{
-    return
-        x == PA_CONTEXT_CONNECTING ||
-        x == PA_CONTEXT_AUTHORIZING ||
-        x == PA_CONTEXT_SETTING_NAME ||
-        x == PA_CONTEXT_READY;
-}
-#endif
-
-#ifndef PA_STREAM_IS_GOOD
-static inline int PA_STREAM_IS_GOOD(pa_stream_state_t x)
-{
-    return
-        x == PA_STREAM_CREATING ||
-        x == PA_STREAM_READY;
-}
-#endif
-
-#define CHECK_SUCCESS_GOTO(c, rerror, expression, label)        \
-    do {                                                        \
-        if (!(expression)) {                                    \
-            if (rerror) {                                       \
-                *(rerror) = pa_context_errno ((c)->context);    \
-            }                                                   \
-            goto label;                                         \
-        }                                                       \
-    } while (0);
-
-#define CHECK_DEAD_GOTO(c, stream, rerror, label)                       \
-    do {                                                                \
-        if (!(c)->context || !PA_CONTEXT_IS_GOOD (pa_context_get_state((c)->context)) || \
-            !(stream) || !PA_STREAM_IS_GOOD (pa_stream_get_state ((stream)))) { \
-            if (((c)->context && pa_context_get_state ((c)->context) == PA_CONTEXT_FAILED) || \
-                ((stream) && pa_stream_get_state ((stream)) == PA_STREAM_FAILED)) { \
-                if (rerror) {                                           \
-                    *(rerror) = pa_context_errno ((c)->context);        \
-                }                                                       \
-            } else {                                                    \
-                if (rerror) {                                           \
-                    *(rerror) = PA_ERR_BADSTATE;                        \
-                }                                                       \
-            }                                                           \
-            goto label;                                                 \
-        }                                                               \
-    } while (0);
-
-static int qpa_simple_read (PAVoiceIn *p, void *data, size_t length, int *rerror)
-{
-    paaudio *g = &glob_paaudio;
-
-    pa_threaded_mainloop_lock (g->mainloop);
-
-    CHECK_DEAD_GOTO (g, p->stream, rerror, unlock_and_fail);
-
-    while (length > 0) {
-        size_t l;
-
-        while (!p->read_data) {
-            int r;
-
-            r = pa_stream_peek (p->stream, &p->read_data, &p->read_length);
-            CHECK_SUCCESS_GOTO (g, rerror, r == 0, unlock_and_fail);
-
-            if (!p->read_data) {
-                pa_threaded_mainloop_wait (g->mainloop);
-                CHECK_DEAD_GOTO (g, p->stream, rerror, unlock_and_fail);
-            } else {
-                p->read_index = 0;
-            }
-        }
-
-        l = p->read_length < length ? p->read_length : length;
-        memcpy (data, (const uint8_t *) p->read_data+p->read_index, l);
-
-        data = (uint8_t *) data + l;
-        length -= l;
-
-        p->read_index += l;
-        p->read_length -= l;
-
-        if (!p->read_length) {
-            int r;
-
-            r = pa_stream_drop (p->stream);
-            p->read_data = NULL;
-            p->read_length = 0;
-            p->read_index = 0;
-
-            CHECK_SUCCESS_GOTO (g, rerror, r == 0, unlock_and_fail);
-        }
-    }
-
-    pa_threaded_mainloop_unlock (g->mainloop);
-    return 0;
-
-unlock_and_fail:
-    pa_threaded_mainloop_unlock (g->mainloop);
-    return -1;
-}
-
-static int qpa_simple_write (PAVoiceOut *p, const void *data, size_t length, int *rerror)
-{
-    paaudio *g = &glob_paaudio;
-
-    pa_threaded_mainloop_lock (g->mainloop);
-
-    CHECK_DEAD_GOTO (g, p->stream, rerror, unlock_and_fail);
-
-    while (length > 0) {
-        size_t l;
-        int r;
-
-        while (!(l = pa_stream_writable_size (p->stream))) {
-            pa_threaded_mainloop_wait (g->mainloop);
-            CHECK_DEAD_GOTO (g, p->stream, rerror, unlock_and_fail);
-        }
-
-        CHECK_SUCCESS_GOTO (g, rerror, l != (size_t) -1, unlock_and_fail);
-
-        if (l > length) {
-            l = length;
-        }
-
-        r = pa_stream_write (p->stream, data, l, NULL, 0LL, PA_SEEK_RELATIVE);
-        CHECK_SUCCESS_GOTO (g, rerror, r >= 0, unlock_and_fail);
-
-        data = (const uint8_t *) data + l;
-        length -= l;
-    }
-
-    pa_threaded_mainloop_unlock (g->mainloop);
-    return 0;
-
-unlock_and_fail:
-    pa_threaded_mainloop_unlock (g->mainloop);
-    return -1;
-}
-
 static void *qpa_thread_out (void *arg)
 {
     PAVoiceOut *pa = arg;
@@ -222,7 +77,7 @@ static void *qpa_thread_out (void *arg)
             }
         }
 
-        decr = to_mix = audio_MIN (pa->live, glob_paaudio.samples >> 2);
+        decr = to_mix = audio_MIN (pa->live, conf.samples >> 2);
         rpos = pa->rpos;
 
         if (audio_pt_unlock (&pa->pt, AUDIO_FUNC)) {
@@ -236,8 +91,8 @@ static void *qpa_thread_out (void *arg)
 
             hw->clip (pa->pcm_buf, src, chunk);
 
-            if (qpa_simple_write (pa, pa->pcm_buf,
-                                  chunk << hw->info.shift, &error) < 0) {
+            if (pa_simple_write (pa->s, pa->pcm_buf,
+                                 chunk << hw->info.shift, &error) < 0) {
                 qpa_logerr (error, "pa_simple_write failed\n");
                 return NULL;
             }
@@ -314,7 +169,7 @@ static void *qpa_thread_in (void *arg)
             }
         }
 
-        incr = to_grab = audio_MIN (pa->dead, glob_paaudio.samples >> 2);
+        incr = to_grab = audio_MIN (pa->dead, conf.samples >> 2);
         wpos = pa->wpos;
 
         if (audio_pt_unlock (&pa->pt, AUDIO_FUNC)) {
@@ -326,8 +181,8 @@ static void *qpa_thread_in (void *arg)
             int chunk = audio_MIN (to_grab, hw->samples - wpos);
             void *buf = advance (pa->pcm_buf, wpos);
 
-            if (qpa_simple_read (pa, buf,
-                                 chunk << hw->info.shift, &error) < 0) {
+            if (pa_simple_read (pa->s, buf,
+                                chunk << hw->info.shift, &error) < 0) {
                 qpa_logerr (error, "pa_simple_read failed\n");
                 return NULL;
             }
@@ -428,112 +283,6 @@ static audfmt_e pa_to_audfmt (pa_sample_format_t fmt, int *endianness)
     }
 }
 
-static void context_state_cb (pa_context *c, void *userdata)
-{
-    paaudio *g = &glob_paaudio;
-
-    switch (pa_context_get_state(c)) {
-    case PA_CONTEXT_READY:
-    case PA_CONTEXT_TERMINATED:
-    case PA_CONTEXT_FAILED:
-        pa_threaded_mainloop_signal (g->mainloop, 0);
-        break;
-
-    case PA_CONTEXT_UNCONNECTED:
-    case PA_CONTEXT_CONNECTING:
-    case PA_CONTEXT_AUTHORIZING:
-    case PA_CONTEXT_SETTING_NAME:
-        break;
-    }
-}
-
-static void stream_state_cb (pa_stream *s, void * userdata)
-{
-    paaudio *g = &glob_paaudio;
-
-    switch (pa_stream_get_state (s)) {
-
-    case PA_STREAM_READY:
-    case PA_STREAM_FAILED:
-    case PA_STREAM_TERMINATED:
-        pa_threaded_mainloop_signal (g->mainloop, 0);
-        break;
-
-    case PA_STREAM_UNCONNECTED:
-    case PA_STREAM_CREATING:
-        break;
-    }
-}
-
-static void stream_request_cb (pa_stream *s, size_t length, void *userdata)
-{
-    paaudio *g = &glob_paaudio;
-
-    pa_threaded_mainloop_signal (g->mainloop, 0);
-}
-
-static pa_stream *qpa_simple_new (
-        const char *server,
-        const char *name,
-        pa_stream_direction_t dir,
-        const char *dev,
-        const char *stream_name,
-        const pa_sample_spec *ss,
-        const pa_channel_map *map,
-        const pa_buffer_attr *attr,
-        int *rerror)
-{
-    paaudio *g = &glob_paaudio;
-    int r;
-    pa_stream *stream;
-
-    pa_threaded_mainloop_lock (g->mainloop);
-
-    stream = pa_stream_new (g->context, name, ss, map);
-    if (!stream) {
-        goto fail;
-    }
-
-    pa_stream_set_state_callback (stream, stream_state_cb, g);
-    pa_stream_set_read_callback (stream, stream_request_cb, g);
-    pa_stream_set_write_callback (stream, stream_request_cb, g);
-
-    if (dir == PA_STREAM_PLAYBACK) {
-        r = pa_stream_connect_playback (stream, dev, attr,
-                                        PA_STREAM_INTERPOLATE_TIMING
-#ifdef PA_STREAM_ADJUST_LATENCY
-                                        |PA_STREAM_ADJUST_LATENCY
-#endif
-                                        |PA_STREAM_AUTO_TIMING_UPDATE, NULL, NULL);
-    } else {
-        r = pa_stream_connect_record (stream, dev, attr,
-                                      PA_STREAM_INTERPOLATE_TIMING
-#ifdef PA_STREAM_ADJUST_LATENCY
-                                      |PA_STREAM_ADJUST_LATENCY
-#endif
-                                      |PA_STREAM_AUTO_TIMING_UPDATE);
-    }
-
-    if (r < 0) {
-      goto fail;
-    }
-
-    pa_threaded_mainloop_unlock (g->mainloop);
-
-    return stream;
-
-fail:
-    pa_threaded_mainloop_unlock (g->mainloop);
-
-    if (stream) {
-        pa_stream_unref (stream);
-    }
-
-    *rerror = pa_context_errno (g->context);
-
-    return NULL;
-}
-
 static int qpa_init_out (HWVoiceOut *hw, struct audsettings *as)
 {
     int error;
@@ -557,24 +306,24 @@ static int qpa_init_out (HWVoiceOut *hw, struct audsettings *as)
 
     obt_as.fmt = pa_to_audfmt (ss.format, &obt_as.endianness);
 
-    pa->stream = qpa_simple_new (
-        glob_paaudio.server,
+    pa->s = pa_simple_new (
+        conf.server,
         "qemu",
         PA_STREAM_PLAYBACK,
-        glob_paaudio.sink,
+        conf.sink,
         "pcm.playback",
         &ss,
         NULL,                   /* channel map */
         &ba,                    /* buffering attributes */
         &error
         );
-    if (!pa->stream) {
+    if (!pa->s) {
         qpa_logerr (error, "pa_simple_new for playback failed\n");
         goto fail1;
     }
 
     audio_pcm_init_info (&hw->info, &obt_as);
-    hw->samples = glob_paaudio.samples;
+    hw->samples = conf.samples;
     pa->pcm_buf = audio_calloc (AUDIO_FUNC, hw->samples, 1 << hw->info.shift);
     pa->rpos = hw->rpos;
     if (!pa->pcm_buf) {
@@ -590,13 +339,11 @@ static int qpa_init_out (HWVoiceOut *hw, struct audsettings *as)
     return 0;
 
  fail3:
-    g_free (pa->pcm_buf);
+    qemu_free (pa->pcm_buf);
     pa->pcm_buf = NULL;
  fail2:
-    if (pa->stream) {
-        pa_stream_unref (pa->stream);
-        pa->stream = NULL;
-    }
+    pa_simple_free (pa->s);
+    pa->s = NULL;
  fail1:
     return -1;
 }
@@ -614,24 +361,24 @@ static int qpa_init_in (HWVoiceIn *hw, struct audsettings *as)
 
     obt_as.fmt = pa_to_audfmt (ss.format, &obt_as.endianness);
 
-    pa->stream = qpa_simple_new (
-        glob_paaudio.server,
+    pa->s = pa_simple_new (
+        conf.server,
         "qemu",
         PA_STREAM_RECORD,
-        glob_paaudio.source,
+        conf.source,
         "pcm.capture",
         &ss,
         NULL,                   /* channel map */
         NULL,                   /* buffering attributes */
         &error
         );
-    if (!pa->stream) {
+    if (!pa->s) {
         qpa_logerr (error, "pa_simple_new for capture failed\n");
         goto fail1;
     }
 
     audio_pcm_init_info (&hw->info, &obt_as);
-    hw->samples = glob_paaudio.samples;
+    hw->samples = conf.samples;
     pa->pcm_buf = audio_calloc (AUDIO_FUNC, hw->samples, 1 << hw->info.shift);
     pa->wpos = hw->wpos;
     if (!pa->pcm_buf) {
@@ -647,13 +394,11 @@ static int qpa_init_in (HWVoiceIn *hw, struct audsettings *as)
     return 0;
 
  fail3:
-    g_free (pa->pcm_buf);
+    qemu_free (pa->pcm_buf);
     pa->pcm_buf = NULL;
  fail2:
-    if (pa->stream) {
-        pa_stream_unref (pa->stream);
-        pa->stream = NULL;
-    }
+    pa_simple_free (pa->s);
+    pa->s = NULL;
  fail1:
     return -1;
 }
@@ -668,13 +413,13 @@ static void qpa_fini_out (HWVoiceOut *hw)
     audio_pt_unlock_and_signal (&pa->pt, AUDIO_FUNC);
     audio_pt_join (&pa->pt, &ret, AUDIO_FUNC);
 
-    if (pa->stream) {
-        pa_stream_unref (pa->stream);
-        pa->stream = NULL;
+    if (pa->s) {
+        pa_simple_free (pa->s);
+        pa->s = NULL;
     }
 
     audio_pt_fini (&pa->pt, AUDIO_FUNC);
-    g_free (pa->pcm_buf);
+    qemu_free (pa->pcm_buf);
     pa->pcm_buf = NULL;
 }
 
@@ -688,225 +433,64 @@ static void qpa_fini_in (HWVoiceIn *hw)
     audio_pt_unlock_and_signal (&pa->pt, AUDIO_FUNC);
     audio_pt_join (&pa->pt, &ret, AUDIO_FUNC);
 
-    if (pa->stream) {
-        pa_stream_unref (pa->stream);
-        pa->stream = NULL;
+    if (pa->s) {
+        pa_simple_free (pa->s);
+        pa->s = NULL;
     }
 
     audio_pt_fini (&pa->pt, AUDIO_FUNC);
-    g_free (pa->pcm_buf);
+    qemu_free (pa->pcm_buf);
     pa->pcm_buf = NULL;
 }
 
 static int qpa_ctl_out (HWVoiceOut *hw, int cmd, ...)
 {
-    PAVoiceOut *pa = (PAVoiceOut *) hw;
-    pa_operation *op;
-    pa_cvolume v;
-    paaudio *g = &glob_paaudio;
-
-#ifdef PA_CHECK_VERSION    /* macro is present in 0.9.16+ */
-    pa_cvolume_init (&v);  /* function is present in 0.9.13+ */
-#endif
-
-    switch (cmd) {
-    case VOICE_VOLUME:
-        {
-            SWVoiceOut *sw;
-            va_list ap;
-
-            va_start (ap, cmd);
-            sw = va_arg (ap, SWVoiceOut *);
-            va_end (ap);
-
-            v.channels = 2;
-            v.values[0] = ((PA_VOLUME_NORM - PA_VOLUME_MUTED) * sw->vol.l) / UINT32_MAX;
-            v.values[1] = ((PA_VOLUME_NORM - PA_VOLUME_MUTED) * sw->vol.r) / UINT32_MAX;
-
-            pa_threaded_mainloop_lock (g->mainloop);
-
-            op = pa_context_set_sink_input_volume (g->context,
-                pa_stream_get_index (pa->stream),
-                &v, NULL, NULL);
-            if (!op)
-                qpa_logerr (pa_context_errno (g->context),
-                            "set_sink_input_volume() failed\n");
-            else
-                pa_operation_unref (op);
-
-            op = pa_context_set_sink_input_mute (g->context,
-                pa_stream_get_index (pa->stream),
-               sw->vol.mute, NULL, NULL);
-            if (!op) {
-                qpa_logerr (pa_context_errno (g->context),
-                            "set_sink_input_mute() failed\n");
-            } else {
-                pa_operation_unref (op);
-            }
-
-            pa_threaded_mainloop_unlock (g->mainloop);
-        }
-    }
+    (void) hw;
+    (void) cmd;
     return 0;
 }
 
 static int qpa_ctl_in (HWVoiceIn *hw, int cmd, ...)
 {
-    PAVoiceIn *pa = (PAVoiceIn *) hw;
-    pa_operation *op;
-    pa_cvolume v;
-    paaudio *g = &glob_paaudio;
-
-#ifdef PA_CHECK_VERSION
-    pa_cvolume_init (&v);
-#endif
-
-    switch (cmd) {
-    case VOICE_VOLUME:
-        {
-            SWVoiceIn *sw;
-            va_list ap;
-
-            va_start (ap, cmd);
-            sw = va_arg (ap, SWVoiceIn *);
-            va_end (ap);
-
-            v.channels = 2;
-            v.values[0] = ((PA_VOLUME_NORM - PA_VOLUME_MUTED) * sw->vol.l) / UINT32_MAX;
-            v.values[1] = ((PA_VOLUME_NORM - PA_VOLUME_MUTED) * sw->vol.r) / UINT32_MAX;
-
-            pa_threaded_mainloop_lock (g->mainloop);
-
-            /* FIXME: use the upcoming "set_source_output_{volume,mute}" */
-            op = pa_context_set_source_volume_by_index (g->context,
-                pa_stream_get_device_index (pa->stream),
-                &v, NULL, NULL);
-            if (!op) {
-                qpa_logerr (pa_context_errno (g->context),
-                            "set_source_volume() failed\n");
-            } else {
-                pa_operation_unref(op);
-            }
-
-            op = pa_context_set_source_mute_by_index (g->context,
-                pa_stream_get_index (pa->stream),
-                sw->vol.mute, NULL, NULL);
-            if (!op) {
-                qpa_logerr (pa_context_errno (g->context),
-                            "set_source_mute() failed\n");
-            } else {
-                pa_operation_unref (op);
-            }
-
-            pa_threaded_mainloop_unlock (g->mainloop);
-        }
-    }
+    (void) hw;
+    (void) cmd;
     return 0;
 }
 
 /* common */
 static void *qpa_audio_init (void)
 {
-    paaudio *g = &glob_paaudio;
-
-    g->mainloop = pa_threaded_mainloop_new ();
-    if (!g->mainloop) {
-        goto fail;
-    }
-
-    g->context = pa_context_new (pa_threaded_mainloop_get_api (g->mainloop), glob_paaudio.server);
-    if (!g->context) {
-        goto fail;
-    }
-
-    pa_context_set_state_callback (g->context, context_state_cb, g);
-
-    if (pa_context_connect (g->context, glob_paaudio.server, 0, NULL) < 0) {
-        qpa_logerr (pa_context_errno (g->context),
-                    "pa_context_connect() failed\n");
-        goto fail;
-    }
-
-    pa_threaded_mainloop_lock (g->mainloop);
-
-    if (pa_threaded_mainloop_start (g->mainloop) < 0) {
-        goto unlock_and_fail;
-    }
-
-    for (;;) {
-        pa_context_state_t state;
-
-        state = pa_context_get_state (g->context);
-
-        if (state == PA_CONTEXT_READY) {
-            break;
-        }
-
-        if (!PA_CONTEXT_IS_GOOD (state)) {
-            qpa_logerr (pa_context_errno (g->context),
-                        "Wrong context state\n");
-            goto unlock_and_fail;
-        }
-
-        /* Wait until the context is ready */
-        pa_threaded_mainloop_wait (g->mainloop);
-    }
-
-    pa_threaded_mainloop_unlock (g->mainloop);
-
-    return &glob_paaudio;
-
-unlock_and_fail:
-    pa_threaded_mainloop_unlock (g->mainloop);
-fail:
-    AUD_log (AUDIO_CAP, "Failed to initialize PA context");
-    return NULL;
+    return &conf;
 }
 
 static void qpa_audio_fini (void *opaque)
 {
-    paaudio *g = opaque;
-
-    if (g->mainloop) {
-        pa_threaded_mainloop_stop (g->mainloop);
-    }
-
-    if (g->context) {
-        pa_context_disconnect (g->context);
-        pa_context_unref (g->context);
-        g->context = NULL;
-    }
-
-    if (g->mainloop) {
-        pa_threaded_mainloop_free (g->mainloop);
-    }
-
-    g->mainloop = NULL;
+    (void) opaque;
 }
 
 struct audio_option qpa_options[] = {
     {
         .name  = "SAMPLES",
         .tag   = AUD_OPT_INT,
-        .valp  = &glob_paaudio.samples,
+        .valp  = &conf.samples,
         .descr = "buffer size in samples"
     },
     {
         .name  = "SERVER",
         .tag   = AUD_OPT_STR,
-        .valp  = &glob_paaudio.server,
+        .valp  = &conf.server,
         .descr = "server address"
     },
     {
         .name  = "SINK",
         .tag   = AUD_OPT_STR,
-        .valp  = &glob_paaudio.sink,
+        .valp  = &conf.sink,
         .descr = "sink device name"
     },
     {
         .name  = "SOURCE",
         .tag   = AUD_OPT_STR,
-        .valp  = &glob_paaudio.source,
+        .valp  = &conf.source,
         .descr = "source device name"
     },
     { /* End of list */ }
@@ -937,6 +521,5 @@ struct audio_driver pa_audio_driver = {
     .max_voices_out = INT_MAX,
     .max_voices_in  = INT_MAX,
     .voice_size_out = sizeof (PAVoiceOut),
-    .voice_size_in  = sizeof (PAVoiceIn),
-    .ctl_caps       = VOICE_VOLUME_CAP
+    .voice_size_in  = sizeof (PAVoiceIn)
 };

audio/spiceaudio.c

@@ -202,26 +202,7 @@ static int line_out_ctl (HWVoiceOut *hw, int cmd, ...)
         }
         spice_server_playback_stop (&out->sin);
         break;
-    case VOICE_VOLUME:
-        {
-#if ((SPICE_INTERFACE_PLAYBACK_MAJOR >= 1) && (SPICE_INTERFACE_PLAYBACK_MINOR >= 2))
-            SWVoiceOut *sw;
-            va_list ap;
-            uint16_t vol[2];
-
-            va_start (ap, cmd);
-            sw = va_arg (ap, SWVoiceOut *);
-            va_end (ap);
-
-            vol[0] = sw->vol.l / ((1ULL << 16) + 1);
-            vol[1] = sw->vol.r / ((1ULL << 16) + 1);
-            spice_server_playback_set_volume (&out->sin, 2, vol);
-            spice_server_playback_set_mute (&out->sin, sw->vol.mute);
-#endif
-            break;
-        }
     }
-
     return 0;
 }
 
@@ -323,26 +304,7 @@ static int line_in_ctl (HWVoiceIn *hw, int cmd, ...)
         in->active = 0;
         spice_server_record_stop (&in->sin);
         break;
-    case VOICE_VOLUME:
-        {
-#if ((SPICE_INTERFACE_RECORD_MAJOR >= 2) && (SPICE_INTERFACE_RECORD_MINOR >= 2))
-            SWVoiceIn *sw;
-            va_list ap;
-            uint16_t vol[2];
-
-            va_start (ap, cmd);
-            sw = va_arg (ap, SWVoiceIn *);
-            va_end (ap);
-
-            vol[0] = sw->vol.l / ((1ULL << 16) + 1);
-            vol[1] = sw->vol.r / ((1ULL << 16) + 1);
-            spice_server_record_set_volume (&in->sin, 2, vol);
-            spice_server_record_set_mute (&in->sin, sw->vol.mute);
-#endif
-            break;
-        }
     }
-
     return 0;
 }
 
@@ -375,9 +337,6 @@ struct audio_driver spice_audio_driver = {
     .max_voices_in  = 1,
     .voice_size_out = sizeof (SpiceVoiceOut),
     .voice_size_in  = sizeof (SpiceVoiceIn),
-#if ((SPICE_INTERFACE_PLAYBACK_MAJOR >= 1) && (SPICE_INTERFACE_PLAYBACK_MINOR >= 2))
-    .ctl_caps       = VOICE_VOLUME_CAP
-#endif
 };
 
 void qemu_spice_audio_init (void)

audio/wavaudio.c

@@ -30,7 +30,7 @@
 
 typedef struct WAVVoiceOut {
     HWVoiceOut hw;
-    FILE *f;
+    QEMUFile *f;
     int64_t old_ticks;
     void *pcm_buf;
     int total_samples;
@@ -76,10 +76,7 @@ static int wav_run_out (HWVoiceOut *hw, int live)
         dst = advance (wav->pcm_buf, rpos << hw->info.shift);
 
         hw->clip (dst, src, convert_samples);
-        if (fwrite (dst, convert_samples << hw->info.shift, 1, wav->f) != 1) {
-            dolog ("wav_run_out: fwrite of %d bytes failed\nReaons: %s\n",
-                   convert_samples << hw->info.shift, strerror (errno));
-        }
+        qemu_put_buffer (wav->f, dst, convert_samples << hw->info.shift);
 
         rpos = (rpos + convert_samples) % hw->samples;
         samples -= convert_samples;
@@ -155,20 +152,16 @@ static int wav_init_out (HWVoiceOut *hw, struct audsettings *as)
     le_store (hdr + 28, hw->info.freq << (bits16 + stereo), 4);
     le_store (hdr + 32, 1 << (bits16 + stereo), 2);
 
-    wav->f = fopen (conf.wav_path, "wb");
+    wav->f = qemu_fopen (conf.wav_path, "wb");
     if (!wav->f) {
         dolog ("Failed to open wave file `%s'\nReason: %s\n",
                conf.wav_path, strerror (errno));
-        g_free (wav->pcm_buf);
+        qemu_free (wav->pcm_buf);
         wav->pcm_buf = NULL;
         return -1;
     }
 
-    if (fwrite (hdr, sizeof (hdr), 1, wav->f) != 1) {
-        dolog ("wav_init_out: failed to write header\nReason: %s\n",
-               strerror(errno));
-        return -1;
-    }
+    qemu_put_buffer (wav->f, hdr, sizeof (hdr));
     return 0;
 }
 
@@ -187,35 +180,16 @@ static void wav_fini_out (HWVoiceOut *hw)
     le_store (rlen, rifflen, 4);
     le_store (dlen, datalen, 4);
 
-    if (fseek (wav->f, 4, SEEK_SET)) {
-        dolog ("wav_fini_out: fseek to rlen failed\nReason: %s\n",
-               strerror(errno));
-        goto doclose;
-    }
-    if (fwrite (rlen, 4, 1, wav->f) != 1) {
-        dolog ("wav_fini_out: failed to write rlen\nReason: %s\n",
-               strerror (errno));
-        goto doclose;
-    }
-    if (fseek (wav->f, 32, SEEK_CUR)) {
-        dolog ("wav_fini_out: fseek to dlen failed\nReason: %s\n",
-               strerror (errno));
-        goto doclose;
-    }
-    if (fwrite (dlen, 4, 1, wav->f) != 1) {
-        dolog ("wav_fini_out: failed to write dlen\nReaons: %s\n",
-               strerror (errno));
-        goto doclose;
-    }
+    qemu_fseek (wav->f, 4, SEEK_SET);
+    qemu_put_buffer (wav->f, rlen, 4);
 
- doclose:
-    if (fclose (wav->f))  {
-        dolog ("wav_fini_out: fclose %p failed\nReason: %s\n",
-               wav->f, strerror (errno));
-    }
+    qemu_fseek (wav->f, 32, SEEK_CUR);
+    qemu_put_buffer (wav->f, dlen, 4);
+
+    qemu_fclose (wav->f);
     wav->f = NULL;
 
-    g_free (wav->pcm_buf);
+    qemu_free (wav->pcm_buf);
     wav->pcm_buf = NULL;
 }
 

audio/wavcapture.c

@@ -1,10 +1,9 @@
-/* public domain */
 #include "hw/hw.h"
 #include "monitor.h"
 #include "audio.h"
 
 typedef struct {
-    FILE *f;
+    QEMUFile *f;
     int bytes;
     char *path;
     int freq;
@@ -36,50 +35,27 @@ static void wav_destroy (void *opaque)
     uint8_t dlen[4];
     uint32_t datalen = wav->bytes;
     uint32_t rifflen = datalen + 36;
-    Monitor *mon = cur_mon;
 
     if (wav->f) {
         le_store (rlen, rifflen, 4);
         le_store (dlen, datalen, 4);
 
-        if (fseek (wav->f, 4, SEEK_SET)) {
-            monitor_printf (mon, "wav_destroy: rlen fseek failed\nReason: %s\n",
-                            strerror (errno));
-            goto doclose;
-        }
-        if (fwrite (rlen, 4, 1, wav->f) != 1) {
-            monitor_printf (mon, "wav_destroy: rlen fwrite failed\nReason %s\n",
-                            strerror (errno));
-            goto doclose;
-        }
-        if (fseek (wav->f, 32, SEEK_CUR)) {
-            monitor_printf (mon, "wav_destroy: dlen fseek failed\nReason %s\n",
-                            strerror (errno));
-            goto doclose;
-        }
-        if (fwrite (dlen, 1, 4, wav->f) != 4) {
-            monitor_printf (mon, "wav_destroy: dlen fwrite failed\nReason %s\n",
-                            strerror (errno));
-            goto doclose;
-        }
-    doclose:
-        if (fclose (wav->f)) {
-            fprintf (stderr, "wav_destroy: fclose failed: %s",
-                     strerror (errno));
-        }
+        qemu_fseek (wav->f, 4, SEEK_SET);
+        qemu_put_buffer (wav->f, rlen, 4);
+
+        qemu_fseek (wav->f, 32, SEEK_CUR);
+        qemu_put_buffer (wav->f, dlen, 4);
+        qemu_fclose (wav->f);
     }
 
-    g_free (wav->path);
+    qemu_free (wav->path);
 }
 
 static void wav_capture (void *opaque, void *buf, int size)
 {
     WAVState *wav = opaque;
 
-    if (fwrite (buf, size, 1, wav->f) != 1) {
-        monitor_printf (cur_mon, "wav_capture: fwrite error\nReason: %s",
-                        strerror (errno));
-    }
+    qemu_put_buffer (wav->f, buf, size);
     wav->bytes += size;
 }
 
@@ -95,9 +71,9 @@ static void wav_capture_info (void *opaque)
     WAVState *wav = opaque;
     char *path = wav->path;
 
-    monitor_printf (cur_mon, "Capturing audio(%d,%d,%d) to %s: %d bytes\n",
-                    wav->freq, wav->bits, wav->nchannels,
-                    path ? path : "<not available>", wav->bytes);
+    monitor_printf(cur_mon, "Capturing audio(%d,%d,%d) to %s: %d bytes\n",
+                   wav->freq, wav->bits, wav->nchannels,
+                   path ? path : "<not available>", wav->bytes);
 }
 
 static struct capture_ops wav_capture_ops = {
@@ -122,13 +98,13 @@ int wav_start_capture (CaptureState *s, const char *path, int freq,
     CaptureVoiceOut *cap;
 
     if (bits != 8 && bits != 16) {
-        monitor_printf (mon, "incorrect bit count %d, must be 8 or 16\n", bits);
+        monitor_printf(mon, "incorrect bit count %d, must be 8 or 16\n", bits);
         return -1;
     }
 
     if (nchannels != 1 && nchannels != 2) {
-        monitor_printf (mon, "incorrect channel count %d, must be 1 or 2\n",
-                        nchannels);
+        monitor_printf(mon, "incorrect channel count %d, must be 1 or 2\n",
+                       nchannels);
         return -1;
     }
 
@@ -144,7 +120,7 @@ int wav_start_capture (CaptureState *s, const char *path, int freq,
     ops.capture = wav_capture;
     ops.destroy = wav_destroy;
 
-    wav = g_malloc0 (sizeof (*wav));
+    wav = qemu_mallocz (sizeof (*wav));
 
     shift = bits16 + stereo;
     hdr[34] = bits16 ? 0x10 : 0x08;
@@ -154,42 +130,32 @@ int wav_start_capture (CaptureState *s, const char *path, int freq,
     le_store (hdr + 28, freq << shift, 4);
     le_store (hdr + 32, 1 << shift, 2);
 
-    wav->f = fopen (path, "wb");
+    wav->f = qemu_fopen (path, "wb");
     if (!wav->f) {
-        monitor_printf (mon, "Failed to open wave file `%s'\nReason: %s\n",
-                        path, strerror (errno));
-        g_free (wav);
+        monitor_printf(mon, "Failed to open wave file `%s'\nReason: %s\n",
+                       path, strerror (errno));
+        qemu_free (wav);
         return -1;
     }
 
-    wav->path = g_strdup (path);
+    wav->path = qemu_strdup (path);
     wav->bits = bits;
     wav->nchannels = nchannels;
     wav->freq = freq;
 
-    if (fwrite (hdr, sizeof (hdr), 1, wav->f) != 1) {
-        monitor_printf (mon, "Failed to write header\nReason: %s\n",
-                        strerror (errno));
-        goto error_free;
-    }
+    qemu_put_buffer (wav->f, hdr, sizeof (hdr));
 
     cap = AUD_add_capture (&as, &ops, wav);
     if (!cap) {
-        monitor_printf (mon, "Failed to add audio capture\n");
-        goto error_free;
+        monitor_printf(mon, "Failed to add audio capture\n");
+        qemu_free (wav->path);
+        qemu_fclose (wav->f);
+        qemu_free (wav);
+        return -1;
     }
 
     wav->cap = cap;
     s->opaque = wav;
     s->ops = wav_capture_ops;
     return 0;
-
-error_free:
-    g_free (wav->path);
-    if (fclose (wav->f)) {
-        monitor_printf (mon, "Failed to close wave file\nReason: %s\n",
-                        strerror (errno));
-    }
-    g_free (wav);
-    return -1;
 }

audio/winwaveaudio.c

@@ -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:
@@ -222,9 +222,9 @@ static int winwave_init_out (HWVoiceOut *hw, struct audsettings *as)
     return 0;
 
  err4:
-    g_free (wave->pcm_buf);
+    qemu_free (wave->pcm_buf);
  err3:
-    g_free (wave->hdrs);
+    qemu_free (wave->hdrs);
  err2:
     winwave_anal_close_out (wave);
  err1:
@@ -310,10 +310,10 @@ static void winwave_fini_out (HWVoiceOut *hw)
         wave->event = NULL;
     }
 
-    g_free (wave->pcm_buf);
+    qemu_free (wave->pcm_buf);
     wave->pcm_buf = NULL;
 
-    g_free (wave->hdrs);
+    qemu_free (wave->hdrs);
     wave->hdrs = NULL;
 }
 
@@ -349,15 +349,21 @@ static int winwave_ctl_out (HWVoiceOut *hw, int cmd, ...)
             else {
                 hw->poll_mode = 0;
             }
-            wave->paused = 0;
+            if (wave->paused) {
+                mr = waveOutRestart (wave->hwo);
+                if (mr != MMSYSERR_NOERROR) {
+                    winwave_logerr (mr, "waveOutRestart");
+                }
+                wave->paused = 0;
+            }
         }
         return 0;
 
     case VOICE_DISABLE:
         if (!wave->paused) {
-            mr = waveOutReset (wave->hwo);
+            mr = waveOutPause (wave->hwo);
             if (mr != MMSYSERR_NOERROR) {
-                winwave_logerr (mr, "waveOutReset");
+                winwave_logerr (mr, "waveOutPause");
             }
             else {
                 wave->paused = 1;
@@ -505,9 +511,9 @@ static int winwave_init_in (HWVoiceIn *hw, struct audsettings *as)
     return 0;
 
  err4:
-    g_free (wave->pcm_buf);
+    qemu_free (wave->pcm_buf);
  err3:
-    g_free (wave->hdrs);
+    qemu_free (wave->hdrs);
  err2:
     winwave_anal_close_in (wave);
  err1:
@@ -544,10 +550,10 @@ static void winwave_fini_in (HWVoiceIn *hw)
         wave->event = NULL;
     }
 
-    g_free (wave->pcm_buf);
+    qemu_free (wave->pcm_buf);
     wave->pcm_buf = NULL;
 
-    g_free (wave->hdrs);
+    qemu_free (wave->hdrs);
     wave->hdrs = NULL;
 }
 

backends/Makefile.objs

@@ -1,2 +0,0 @@
-common-obj-y += rng.o rng-egd.o
-common-obj-$(CONFIG_POSIX) += rng-random.o

backends/rng-egd.c

@@ -1,224 +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 "qemu/rng.h"
-#include "qemu-char.h"
-#include "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;
-    }
-
-    /* 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);
-    }
-
-    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 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

@@ -1,161 +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 "qemu/rng-random.h"
-#include "qemu/rng.h"
-#include "qerror.h"
-#include "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);
-    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 = open(s->filename, O_RDONLY | O_NONBLOCK);
-
-        if (s->fd == -1) {
-            error_set(errp, QERR_OPEN_FILE_FAILED, 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) {
-        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 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 "qemu/rng.h"
-#include "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 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);

balloon.c

@@ -25,12 +25,12 @@
  */
 
 #include "monitor.h"
+#include "qjson.h"
+#include "qint.h"
 #include "cpu-common.h"
 #include "kvm.h"
 #include "balloon.h"
 #include "trace.h"
-#include "qmp-commands.h"
-#include "qjson.h"
 
 static QEMUBalloonEvent *balloon_event_fn;
 static QEMUBalloonStatus *balloon_stat_fn;
@@ -52,16 +52,6 @@ int qemu_add_balloon_handler(QEMUBalloonEvent *event_func,
     return 0;
 }
 
-void qemu_remove_balloon_handler(void *opaque)
-{
-    if (balloon_opaque != opaque) {
-        return;
-    }
-    balloon_event_fn = NULL;
-    balloon_stat_fn = NULL;
-    balloon_opaque = NULL;
-}
-
 static int qemu_balloon(ram_addr_t target)
 {
     if (!balloon_event_fn) {
@@ -72,61 +62,103 @@ static int qemu_balloon(ram_addr_t target)
     return 1;
 }
 
-static int qemu_balloon_status(BalloonInfo *info)
+static int qemu_balloon_status(MonitorCompletion cb, void *opaque)
 {
     if (!balloon_stat_fn) {
         return 0;
     }
-    balloon_stat_fn(balloon_opaque, info);
+    balloon_stat_fn(balloon_opaque, cb, opaque);
     return 1;
 }
 
-void qemu_balloon_changed(int64_t actual)
+static void print_balloon_stat(const char *key, QObject *obj, void *opaque)
 {
-    QObject *data;
+    Monitor *mon = opaque;
 
-    data = qobject_from_jsonf("{ 'actual': %" PRId64 " }",
-                              actual);
-
-    monitor_protocol_event(QEVENT_BALLOON_CHANGE, data);
-
-    qobject_decref(data);
+    if (strcmp(key, "actual")) {
+        monitor_printf(mon, ",%s=%" PRId64, key,
+                       qint_get_int(qobject_to_qint(obj)));
+    }
 }
 
-
-BalloonInfo *qmp_query_balloon(Error **errp)
+void monitor_print_balloon(Monitor *mon, const QObject *data)
 {
-    BalloonInfo *info;
+    QDict *qdict;
 
-    if (kvm_enabled() && !kvm_has_sync_mmu()) {
-        error_set(errp, QERR_KVM_MISSING_CAP, "synchronous MMU", "balloon");
-        return NULL;
-    }
-
-    info = g_malloc0(sizeof(*info));
-
-    if (qemu_balloon_status(info) == 0) {
-        error_set(errp, QERR_DEVICE_NOT_ACTIVE, "balloon");
-        qapi_free_BalloonInfo(info);
-        return NULL;
-    }
-
-    return info;
-}
-
-void qmp_balloon(int64_t value, Error **errp)
-{
-    if (kvm_enabled() && !kvm_has_sync_mmu()) {
-        error_set(errp, QERR_KVM_MISSING_CAP, "synchronous MMU", "balloon");
+    qdict = qobject_to_qdict(data);
+    if (!qdict_haskey(qdict, "actual")) {
         return;
     }
-
-    if (value <= 0) {
-        error_set(errp, QERR_INVALID_PARAMETER_VALUE, "target", "a size");
-        return;
-    }
-    
-    if (qemu_balloon(value) == 0) {
-        error_set(errp, QERR_DEVICE_NOT_ACTIVE, "balloon");
-    }
+    monitor_printf(mon, "balloon: actual=%" PRId64,
+                   qdict_get_int(qdict, "actual") >> 20);
+    qdict_iter(qdict, print_balloon_stat, mon);
+    monitor_printf(mon, "\n");
+}
+
+/**
+ * do_info_balloon(): Balloon information
+ *
+ * Make an asynchronous request for balloon info.  When the request completes
+ * a QDict will be returned according to the following specification:
+ *
+ * - "actual": current balloon value in bytes
+ * The following fields may or may not be present:
+ * - "mem_swapped_in": Amount of memory swapped in (bytes)
+ * - "mem_swapped_out": Amount of memory swapped out (bytes)
+ * - "major_page_faults": Number of major faults
+ * - "minor_page_faults": Number of minor faults
+ * - "free_mem": Total amount of free and unused memory (bytes)
+ * - "total_mem": Total amount of available memory (bytes)
+ *
+ * Example:
+ *
+ * { "actual": 1073741824, "mem_swapped_in": 0, "mem_swapped_out": 0,
+ *   "major_page_faults": 142, "minor_page_faults": 239245,
+ *   "free_mem": 1014185984, "total_mem": 1044668416 }
+ */
+int do_info_balloon(Monitor *mon, MonitorCompletion cb, void *opaque)
+{
+    int ret;
+
+    if (kvm_enabled() && !kvm_has_sync_mmu()) {
+        qerror_report(QERR_KVM_MISSING_CAP, "synchronous MMU", "balloon");
+        return -1;
+    }
+
+    ret = qemu_balloon_status(cb, opaque);
+    if (!ret) {
+        qerror_report(QERR_DEVICE_NOT_ACTIVE, "balloon");
+        return -1;
+    }
+
+    return 0;
+}
+
+/**
+ * do_balloon(): Request VM to change its memory allocation
+ */
+int do_balloon(Monitor *mon, const QDict *params,
+	       MonitorCompletion cb, void *opaque)
+{
+    int64_t target;
+    int ret;
+
+    if (kvm_enabled() && !kvm_has_sync_mmu()) {
+        qerror_report(QERR_KVM_MISSING_CAP, "synchronous MMU", "balloon");
+        return -1;
+    }
+
+    target = qdict_get_int(params, "value");
+    if (target <= 0) {
+        qerror_report(QERR_INVALID_PARAMETER_VALUE, "target", "a size");
+        return -1;
+    }
+    ret = qemu_balloon(target);
+    if (ret == 0) {
+        qerror_report(QERR_DEVICE_NOT_ACTIVE, "balloon");
+        return -1;
+    }
+
+    cb(opaque, NULL);
+    return 0;
 }

balloon.h

@@ -15,15 +15,17 @@
 #define _QEMU_BALLOON_H
 
 #include "monitor.h"
-#include "qapi-types.h"
 
 typedef void (QEMUBalloonEvent)(void *opaque, ram_addr_t target);
-typedef void (QEMUBalloonStatus)(void *opaque, BalloonInfo *info);
+typedef void (QEMUBalloonStatus)(void *opaque, MonitorCompletion cb,
+                                 void *cb_data);
 
 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);
+void monitor_print_balloon(Monitor *mon, const QObject *data);
+int do_info_balloon(Monitor *mon, MonitorCompletion cb, void *opaque);
+int do_balloon(Monitor *mon, const QDict *params,
+               MonitorCompletion cb, void *opaque);
 
 #endif

bitmap.h

@@ -91,7 +91,7 @@ int slow_bitmap_intersects(const unsigned long *bitmap1,
 static inline unsigned long *bitmap_new(int nbits)
 {
     int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
-    return g_malloc0(len);
+    return qemu_mallocz(len);
 }
 
 static inline void bitmap_zero(unsigned long *dst, int nbits)

bitops.h

@@ -114,10 +114,10 @@ static inline unsigned long ffz(unsigned long word)
  * @nr: the bit to set
  * @addr: the address to start counting from
  */
-static inline void set_bit(int nr, unsigned long *addr)
+static inline void set_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = addr + BIT_WORD(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
 
 	*p  |= mask;
 }
@@ -127,10 +127,10 @@ static inline void set_bit(int nr, unsigned long *addr)
  * @nr: Bit to clear
  * @addr: Address to start counting from
  */
-static inline void clear_bit(int nr, unsigned long *addr)
+static inline void clear_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = addr + BIT_WORD(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
 
 	*p &= ~mask;
 }
@@ -140,10 +140,10 @@ static inline void clear_bit(int nr, unsigned long *addr)
  * @nr: Bit to change
  * @addr: Address to start counting from
  */
-static inline void change_bit(int nr, unsigned long *addr)
+static inline void change_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = addr + BIT_WORD(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
 
 	*p ^= mask;
 }
@@ -153,10 +153,10 @@ static inline void change_bit(int nr, unsigned long *addr)
  * @nr: Bit to set
  * @addr: Address to count from
  */
-static inline int test_and_set_bit(int nr, unsigned long *addr)
+static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = addr + BIT_WORD(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
 	unsigned long old = *p;
 
 	*p = old | mask;
@@ -168,10 +168,10 @@ static inline int test_and_set_bit(int nr, unsigned long *addr)
  * @nr: Bit to clear
  * @addr: Address to count from
  */
-static inline int test_and_clear_bit(int nr, unsigned long *addr)
+static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = addr + BIT_WORD(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
 	unsigned long old = *p;
 
 	*p = old & ~mask;
@@ -183,10 +183,10 @@ static inline int test_and_clear_bit(int nr, unsigned long *addr)
  * @nr: Bit to change
  * @addr: Address to count from
  */
-static inline int test_and_change_bit(int nr, unsigned long *addr)
+static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
 {
 	unsigned long mask = BIT_MASK(nr);
-        unsigned long *p = addr + BIT_WORD(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
 	unsigned long old = *p;
 
 	*p = old ^ mask;
@@ -198,7 +198,7 @@ static inline int test_and_change_bit(int nr, unsigned long *addr)
  * @nr: bit number to test
  * @addr: Address to start counting from
  */
-static inline int test_bit(int nr, const unsigned long *addr)
+static inline int test_bit(int nr, const volatile unsigned long *addr)
 {
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
@@ -269,94 +269,4 @@ static inline unsigned long hweight_long(unsigned long w)
     return count;
 }
 
-/**
- * extract32:
- * @value: the value to extract the bit field from
- * @start: the lowest bit in the bit field (numbered from 0)
- * @length: the length of the bit field
- *
- * Extract from the 32 bit input @value the bit field specified by the
- * @start and @length parameters, and return it. The bit field must
- * lie entirely within the 32 bit word. It is valid to request that
- * all 32 bits are returned (ie @length 32 and @start 0).
- *
- * Returns: the value of the bit field extracted from the input value.
- */
-static inline uint32_t extract32(uint32_t value, int start, int length)
-{
-    assert(start >= 0 && length > 0 && length <= 32 - start);
-    return (value >> start) & (~0U >> (32 - length));
-}
-
-/**
- * extract64:
- * @value: the value to extract the bit field from
- * @start: the lowest bit in the bit field (numbered from 0)
- * @length: the length of the bit field
- *
- * Extract from the 64 bit input @value the bit field specified by the
- * @start and @length parameters, and return it. The bit field must
- * lie entirely within the 64 bit word. It is valid to request that
- * all 64 bits are returned (ie @length 64 and @start 0).
- *
- * Returns: the value of the bit field extracted from the input value.
- */
-static inline uint64_t extract64(uint64_t value, int start, int length)
-{
-    assert(start >= 0 && length > 0 && length <= 64 - start);
-    return (value >> start) & (~0ULL >> (64 - length));
-}
-
-/**
- * deposit32:
- * @value: initial value to insert bit field into
- * @start: the lowest bit in the bit field (numbered from 0)
- * @length: the length of the bit field
- * @fieldval: the value to insert into the bit field
- *
- * Deposit @fieldval into the 32 bit @value at the bit field specified
- * by the @start and @length parameters, and return the modified
- * @value. Bits of @value outside the bit field are not modified.
- * Bits of @fieldval above the least significant @length bits are
- * ignored. The bit field must lie entirely within the 32 bit word.
- * It is valid to request that all 32 bits are modified (ie @length
- * 32 and @start 0).
- *
- * Returns: the modified @value.
- */
-static inline uint32_t deposit32(uint32_t value, int start, int length,
-                                 uint32_t fieldval)
-{
-    uint32_t mask;
-    assert(start >= 0 && length > 0 && length <= 32 - start);
-    mask = (~0U >> (32 - length)) << start;
-    return (value & ~mask) | ((fieldval << start) & mask);
-}
-
-/**
- * deposit64:
- * @value: initial value to insert bit field into
- * @start: the lowest bit in the bit field (numbered from 0)
- * @length: the length of the bit field
- * @fieldval: the value to insert into the bit field
- *
- * Deposit @fieldval into the 64 bit @value at the bit field specified
- * by the @start and @length parameters, and return the modified
- * @value. Bits of @value outside the bit field are not modified.
- * Bits of @fieldval above the least significant @length bits are
- * ignored. The bit field must lie entirely within the 64 bit word.
- * It is valid to request that all 64 bits are modified (ie @length
- * 64 and @start 0).
- *
- * Returns: the modified @value.
- */
-static inline uint64_t deposit64(uint64_t value, int start, int length,
-                                 uint64_t fieldval)
-{
-    uint64_t mask;
-    assert(start >= 0 && length > 0 && length <= 64 - start);
-    mask = (~0ULL >> (64 - length)) << start;
-    return (value & ~mask) | ((fieldval << start) & mask);
-}
-
 #endif

block-migration.c

@@ -9,8 +9,6 @@
  * 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"
@@ -18,6 +16,7 @@
 #include "hw/hw.h"
 #include "qemu-queue.h"
 #include "qemu-timer.h"
+#include "monitor.h"
 #include "block-migration.h"
 #include "migration.h"
 #include "blockdev.h"
@@ -181,7 +180,7 @@ static void alloc_aio_bitmap(BlkMigDevState *bmds)
             BDRV_SECTORS_PER_DIRTY_CHUNK * 8 - 1;
     bitmap_size /= BDRV_SECTORS_PER_DIRTY_CHUNK * 8;
 
-    bmds->aio_bitmap = g_malloc0(bitmap_size);
+    bmds->aio_bitmap = qemu_mallocz(bitmap_size);
 }
 
 static void blk_mig_read_cb(void *opaque, int ret)
@@ -203,7 +202,8 @@ static void blk_mig_read_cb(void *opaque, int ret)
     assert(block_mig_state.submitted >= 0);
 }
 
-static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds)
+static int mig_save_device_bulk(Monitor *mon, QEMUFile *f,
+                                BlkMigDevState *bmds)
 {
     int64_t total_sectors = bmds->total_sectors;
     int64_t cur_sector = bmds->cur_sector;
@@ -235,8 +235,8 @@ static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds)
         nr_sectors = total_sectors - cur_sector;
     }
 
-    blk = g_malloc(sizeof(BlkMigBlock));
-    blk->buf = g_malloc(BLOCK_SIZE);
+    blk = qemu_malloc(sizeof(BlkMigBlock));
+    blk->buf = qemu_malloc(BLOCK_SIZE);
     blk->bmds = bmds;
     blk->sector = cur_sector;
     blk->nr_sectors = nr_sectors;
@@ -251,12 +251,22 @@ static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds)
 
     blk->aiocb = bdrv_aio_readv(bs, cur_sector, &blk->qiov,
                                 nr_sectors, blk_mig_read_cb, blk);
+    if (!blk->aiocb) {
+        goto error;
+    }
     block_mig_state.submitted++;
 
     bdrv_reset_dirty(bs, cur_sector, nr_sectors);
     bmds->cur_sector = cur_sector + nr_sectors;
 
     return (bmds->cur_sector >= total_sectors);
+
+error:
+    monitor_printf(mon, "Error reading sector %" PRId64 "\n", cur_sector);
+    qemu_file_set_error(f);
+    qemu_free(blk->buf);
+    qemu_free(blk);
+    return 0;
 }
 
 static void set_dirty_tracking(int enable)
@@ -270,6 +280,7 @@ static void set_dirty_tracking(int enable)
 
 static void init_blk_migration_it(void *opaque, BlockDriverState *bs)
 {
+    Monitor *mon = opaque;
     BlkMigDevState *bmds;
     int64_t sectors;
 
@@ -279,7 +290,7 @@ static void init_blk_migration_it(void *opaque, BlockDriverState *bs)
             return;
         }
 
-        bmds = g_malloc0(sizeof(BlkMigDevState));
+        bmds = qemu_mallocz(sizeof(BlkMigDevState));
         bmds->bs = bs;
         bmds->bulk_completed = 0;
         bmds->total_sectors = sectors;
@@ -292,17 +303,19 @@ static void init_blk_migration_it(void *opaque, BlockDriverState *bs)
         block_mig_state.total_sector_sum += sectors;
 
         if (bmds->shared_base) {
-            DPRINTF("Start migration for %s with shared base image\n",
-                    bs->device_name);
+            monitor_printf(mon, "Start migration for %s with shared base "
+                                "image\n",
+                           bs->device_name);
         } else {
-            DPRINTF("Start full migration for %s\n", bs->device_name);
+            monitor_printf(mon, "Start full migration for %s\n",
+                           bs->device_name);
         }
 
         QSIMPLEQ_INSERT_TAIL(&block_mig_state.bmds_list, bmds, entry);
     }
 }
 
-static void init_blk_migration(QEMUFile *f)
+static void init_blk_migration(Monitor *mon, QEMUFile *f)
 {
     block_mig_state.submitted = 0;
     block_mig_state.read_done = 0;
@@ -313,10 +326,10 @@ static void init_blk_migration(QEMUFile *f)
     block_mig_state.total_time = 0;
     block_mig_state.reads = 0;
 
-    bdrv_iterate(init_blk_migration_it, NULL);
+    bdrv_iterate(init_blk_migration_it, mon);
 }
 
-static int blk_mig_save_bulked_block(QEMUFile *f)
+static int blk_mig_save_bulked_block(Monitor *mon, QEMUFile *f)
 {
     int64_t completed_sector_sum = 0;
     BlkMigDevState *bmds;
@@ -325,7 +338,7 @@ static int blk_mig_save_bulked_block(QEMUFile *f)
 
     QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
         if (bmds->bulk_completed == 0) {
-            if (mig_save_device_bulk(f, bmds) == 1) {
+            if (mig_save_device_bulk(mon, f, bmds) == 1) {
                 /* completed bulk section for this device */
                 bmds->bulk_completed = 1;
             }
@@ -347,7 +360,8 @@ static int blk_mig_save_bulked_block(QEMUFile *f)
         block_mig_state.prev_progress = progress;
         qemu_put_be64(f, (progress << BDRV_SECTOR_BITS)
                          | BLK_MIG_FLAG_PROGRESS);
-        DPRINTF("Completed %d %%\r", progress);
+        monitor_printf(mon, "Completed %d %%\r", progress);
+        monitor_flush(mon);
     }
 
     return ret;
@@ -362,18 +376,17 @@ static void blk_mig_reset_dirty_cursor(void)
     }
 }
 
-static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
-                                 int is_async)
+static int mig_save_device_dirty(Monitor *mon, QEMUFile *f,
+                                 BlkMigDevState *bmds, int is_async)
 {
     BlkMigBlock *blk;
     int64_t total_sectors = bmds->total_sectors;
     int64_t sector;
     int nr_sectors;
-    int ret = -EIO;
 
     for (sector = bmds->cur_dirty; sector < bmds->total_sectors;) {
         if (bmds_aio_inflight(bmds, sector)) {
-            bdrv_drain_all();
+            qemu_aio_flush();
         }
         if (bdrv_get_dirty(bmds->bs, sector)) {
 
@@ -382,8 +395,8 @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
             } else {
                 nr_sectors = BDRV_SECTORS_PER_DIRTY_CHUNK;
             }
-            blk = g_malloc(sizeof(BlkMigBlock));
-            blk->buf = g_malloc(BLOCK_SIZE);
+            blk = qemu_malloc(sizeof(BlkMigBlock));
+            blk->buf = qemu_malloc(BLOCK_SIZE);
             blk->bmds = bmds;
             blk->sector = sector;
             blk->nr_sectors = nr_sectors;
@@ -399,17 +412,20 @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
 
                 blk->aiocb = bdrv_aio_readv(bmds->bs, sector, &blk->qiov,
                                             nr_sectors, blk_mig_read_cb, blk);
+                if (!blk->aiocb) {
+                    goto error;
+                }
                 block_mig_state.submitted++;
                 bmds_set_aio_inflight(bmds, sector, nr_sectors, 1);
             } else {
-                ret = bdrv_read(bmds->bs, sector, blk->buf, nr_sectors);
-                if (ret < 0) {
+                if (bdrv_read(bmds->bs, sector, blk->buf,
+                              nr_sectors) < 0) {
                     goto error;
                 }
                 blk_send(f, blk);
 
-                g_free(blk->buf);
-                g_free(blk);
+                qemu_free(blk->buf);
+                qemu_free(blk);
             }
 
             bdrv_reset_dirty(bmds->bs, sector, nr_sectors);
@@ -422,24 +438,21 @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
     return (bmds->cur_dirty >= bmds->total_sectors);
 
 error:
-    DPRINTF("Error reading sector %" PRId64 "\n", sector);
-    g_free(blk->buf);
-    g_free(blk);
-    return ret;
+    monitor_printf(mon, "Error reading sector %" PRId64 "\n", sector);
+    qemu_file_set_error(f);
+    qemu_free(blk->buf);
+    qemu_free(blk);
+    return 0;
 }
 
-/* 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)
+static int blk_mig_save_dirty_block(Monitor *mon, 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(mon, f, bmds, is_async) == 0) {
+            ret = 1;
             break;
         }
     }
@@ -447,10 +460,9 @@ static int blk_mig_save_dirty_block(QEMUFile *f, int is_async)
     return ret;
 }
 
-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,
@@ -461,14 +473,14 @@ static int flush_blks(QEMUFile *f)
             break;
         }
         if (blk->ret < 0) {
-            ret = blk->ret;
+            qemu_file_set_error(f);
             break;
         }
         blk_send(f, blk);
 
         QSIMPLEQ_REMOVE_HEAD(&block_mig_state.blk_list, entry);
-        g_free(blk->buf);
-        g_free(blk);
+        qemu_free(blk->buf);
+        qemu_free(blk);
 
         block_mig_state.read_done--;
         block_mig_state.transferred++;
@@ -478,7 +490,6 @@ static int flush_blks(QEMUFile *f)
     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;
 }
 
 static int64_t get_remaining_dirty(void)
@@ -509,7 +520,7 @@ static int is_stage2_completed(void)
 
         if ((remaining_dirty / bwidth) <=
             migrate_max_downtime()) {
-            /* finish stage2 because we think that we can finish remaining work
+            /* finish stage2 because we think that we can finish remaing work
                below max_downtime */
 
             return 1;
@@ -519,144 +530,110 @@ static int is_stage2_completed(void)
     return 0;
 }
 
-static void blk_mig_cleanup(void)
+static void blk_mig_cleanup(Monitor *mon)
 {
     BlkMigDevState *bmds;
     BlkMigBlock *blk;
 
-    bdrv_drain_all();
-
     set_dirty_tracking(0);
 
     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);
         drive_put_ref(drive_get_by_blockdev(bmds->bs));
-        g_free(bmds->aio_bitmap);
-        g_free(bmds);
+        qemu_free(bmds->aio_bitmap);
+        qemu_free(bmds);
     }
 
     while ((blk = QSIMPLEQ_FIRST(&block_mig_state.blk_list)) != NULL) {
         QSIMPLEQ_REMOVE_HEAD(&block_mig_state.blk_list, entry);
-        g_free(blk->buf);
-        g_free(blk);
+        qemu_free(blk->buf);
+        qemu_free(blk);
     }
+
+    monitor_printf(mon, "\n");
 }
 
-static void block_migration_cancel(void *opaque)
+static int block_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
 {
-    blk_mig_cleanup();
-}
+    DPRINTF("Enter save live stage %d submitted %d transferred %d\n",
+            stage, block_mig_state.submitted, block_mig_state.transferred);
 
-static int block_save_setup(QEMUFile *f, void *opaque)
-{
-    int ret;
+    if (stage < 0) {
+        blk_mig_cleanup(mon);
+        return 0;
+    }
 
-    DPRINTF("Enter save live setup submitted %d transferred %d\n",
-            block_mig_state.submitted, block_mig_state.transferred);
+    if (block_mig_state.blk_enable != 1) {
+        /* no need to migrate storage */
+        qemu_put_be64(f, BLK_MIG_FLAG_EOS);
+        return 1;
+    }
 
-    init_blk_migration(f);
+    if (stage == 1) {
+        init_blk_migration(mon, f);
 
-    /* start track dirty blocks */
-    set_dirty_tracking(1);
+        /* start track dirty blocks */
+        set_dirty_tracking(1);
+    }
 
-    ret = flush_blks(f);
-    if (ret) {
-        blk_mig_cleanup();
-        return ret;
+    flush_blks(f);
+
+    if (qemu_file_has_error(f)) {
+        blk_mig_cleanup(mon);
+        return 0;
     }
 
     blk_mig_reset_dirty_cursor();
 
-    qemu_put_be64(f, BLK_MIG_FLAG_EOS);
-
-    return 0;
-}
-
-static int block_save_iterate(QEMUFile *f, void *opaque)
-{
-    int ret;
-
-    DPRINTF("Enter save live iterate submitted %d transferred %d\n",
-            block_mig_state.submitted, block_mig_state.transferred);
-
-    ret = flush_blks(f);
-    if (ret) {
-        blk_mig_cleanup();
-        return ret;
-    }
-
-    blk_mig_reset_dirty_cursor();
-
-    /* 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 {
-            ret = blk_mig_save_dirty_block(f, 1);
-            if (ret != 0) {
-                /* no more dirty blocks */
-                break;
+    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(mon, f) == 0) {
+                    /* finished saving bulk on all devices */
+                    block_mig_state.bulk_completed = 1;
+                }
+            } else {
+                if (blk_mig_save_dirty_block(mon, f, 1) == 0) {
+                    /* no more dirty blocks */
+                    break;
+                }
             }
         }
-    }
-    if (ret) {
-        blk_mig_cleanup();
-        return ret;
+
+        flush_blks(f);
+
+        if (qemu_file_has_error(f)) {
+            blk_mig_cleanup(mon);
+            return 0;
+        }
     }
 
-    ret = flush_blks(f);
-    if (ret) {
-        blk_mig_cleanup();
-        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(mon, f, 0) != 0);
+        blk_mig_cleanup(mon);
+
+        /* report completion */
+        qemu_put_be64(f, (100 << BDRV_SECTOR_BITS) | BLK_MIG_FLAG_PROGRESS);
+
+        if (qemu_file_has_error(f)) {
+            return 0;
+        }
+
+        monitor_printf(mon, "Block migration completed\n");
     }
 
     qemu_put_be64(f, BLK_MIG_FLAG_EOS);
 
-    return is_stage2_completed();
-}
-
-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) {
-        blk_mig_cleanup();
-        return ret;
-    }
-
-    blk_mig_reset_dirty_cursor();
-
-    /* we know for sure that save bulk is completed and
-       all async read completed */
-    assert(block_mig_state.submitted == 0);
-
-    do {
-        ret = blk_mig_save_dirty_block(f, 0);
-    } while (ret == 0);
-
-    blk_mig_cleanup();
-    if (ret) {
-        return ret;
-    }
-    /* 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);
-
-    return 0;
+    return ((stage == 2) && is_stage2_completed());
 }
 
 static int block_load(QEMUFile *f, void *opaque, int version_id)
@@ -669,7 +646,6 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
     uint8_t *buf;
     int64_t total_sectors = 0;
     int nr_sectors;
-    int ret;
 
     do {
         addr = qemu_get_be64(f);
@@ -678,6 +654,7 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
         addr >>= BDRV_SECTOR_BITS;
 
         if (flags & BLK_MIG_FLAG_DEVICE_BLOCK) {
+            int ret;
             /* get device name */
             len = qemu_get_byte(f);
             qemu_get_buffer(f, (uint8_t *)device_name, len);
@@ -706,12 +683,12 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
                 nr_sectors = BDRV_SECTORS_PER_DIRTY_CHUNK;
             }
 
-            buf = g_malloc(BLOCK_SIZE);
+            buf = qemu_malloc(BLOCK_SIZE);
 
             qemu_get_buffer(f, buf, BLOCK_SIZE);
             ret = bdrv_write(bs, addr, buf, nr_sectors);
 
-            g_free(buf);
+            qemu_free(buf);
             if (ret < 0) {
                 return ret;
             }
@@ -727,44 +704,28 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
             fprintf(stderr, "Unknown flags\n");
             return -EINVAL;
         }
-        ret = qemu_file_get_error(f);
-        if (ret != 0) {
-            return ret;
+        if (qemu_file_has_error(f)) {
+            return -EIO;
         }
     } while (!(flags & BLK_MIG_FLAG_EOS));
 
     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,
-    .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);
 
-    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

@@ -4,74 +4,29 @@
 #include "qemu-aio.h"
 #include "qemu-common.h"
 #include "qemu-option.h"
-#include "qemu-coroutine.h"
 #include "qobject.h"
-#include "qapi-types.h"
 
 /* block.c */
 typedef struct BlockDriver BlockDriver;
-typedef struct BlockJob BlockJob;
 
 typedef struct BlockDriverInfo {
     /* in bytes, 0 if irrelevant */
     int cluster_size;
     /* offset at which the VM state can be saved (0 if not possible) */
     int64_t vm_state_offset;
-    bool is_dirty;
 } BlockDriverInfo;
 
-typedef struct BlockFragInfo {
-    uint64_t allocated_clusters;
-    uint64_t total_clusters;
-    uint64_t fragmented_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 */
+    char name[256]; /* user choosen name */
+    uint32_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 {
-    /*
-     * Runs when virtual media changed (monitor commands eject, change)
-     * Argument load is true on load and false on eject.
-     * Beware: doesn't run when a host device's physical media
-     * changes.  Sure would be useful if it did.
-     * Device models with removable media must implement this callback.
-     */
-    void (*change_media_cb)(void *opaque, bool load);
-    /*
-     * Runs when an eject request is issued from the monitor, the tray
-     * is closed, and the medium is locked.
-     * Device models that do not implement is_medium_locked will not need
-     * this callback.  Device models that can lock the medium or tray might
-     * want to implement the callback and unlock the tray when "force" is
-     * true, even if they do not support eject requests.
-     */
-    void (*eject_request_cb)(void *opaque, bool force);
-    /*
-     * Is the virtual tray open?
-     * Device models implement this only when the device has a tray.
-     */
-    bool (*is_tray_open)(void *opaque);
-    /*
-     * Is the virtual medium locked into the device?
-     * Device models implement this only when device has such a lock.
-     */
-    bool (*is_medium_locked)(void *opaque);
-    /*
-     * Runs when the size changed (e.g. monitor command block_resize)
-     */
-    void (*resize_cb)(void *opaque);
-} BlockDevOps;
-
 #define BDRV_O_RDWR        0x0002
 #define BDRV_O_SNAPSHOT    0x0008 /* open the file read only and save writes in a snapshot */
 #define BDRV_O_NOCACHE     0x0020 /* do not use the host page cache */
@@ -79,10 +34,6 @@ typedef struct BlockDevOps {
 #define BDRV_O_NATIVE_AIO  0x0080 /* use native AIO instead of the thread pool */
 #define BDRV_O_NO_BACKING  0x0100 /* don't open the backing file */
 #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_CACHE_MASK  (BDRV_O_NOCACHE | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH)
 
@@ -91,33 +42,21 @@ 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 enum {
+    BDRV_ACTION_REPORT, BDRV_ACTION_IGNORE, BDRV_ACTION_STOP
+} BlockMonEventAction;
 
-typedef struct BDRVReopenState {
-    BlockDriverState *bs;
-    int flags;
-    void *opaque;
-} BDRVReopenState;
-
-
-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_mon_event(const BlockDriverState *bdrv,
+                    BlockMonEventAction 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);
 void bdrv_info_stats(Monitor *mon, QObject **ret_data);
 
-/* disk I/O throttling */
-void bdrv_io_limits_enable(BlockDriverState *bs);
-void bdrv_io_limits_disable(BlockDriverState *bs);
-bool bdrv_io_limits_enabled(BlockDriverState *bs);
-
 void bdrv_init(void);
 void bdrv_init_with_whitelist(void);
 BlockDriver *bdrv_find_protocol(const char *filename);
@@ -128,38 +67,16 @@ int bdrv_create(BlockDriver *drv, const char* filename,
 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_file_open(BlockDriverState **pbs, const char *filename, int flags);
-int bdrv_open_backing_file(BlockDriverState *bs);
 int bdrv_open(BlockDriverState *bs, const char *filename, 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);
 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);
-void *bdrv_get_attached_dev(BlockDriverState *bs);
-void bdrv_set_dev_ops(BlockDriverState *bs, const BlockDevOps *ops,
-                      void *opaque);
-void bdrv_dev_eject_request(BlockDriverState *bs, bool force);
-bool bdrv_dev_has_removable_media(BlockDriverState *bs);
-bool bdrv_dev_is_tray_open(BlockDriverState *bs);
-bool bdrv_dev_is_medium_locked(BlockDriverState *bs);
+int bdrv_attach(BlockDriverState *bs, DeviceState *qdev);
+void bdrv_detach(BlockDriverState *bs, DeviceState *qdev);
+DeviceState *bdrv_get_attached(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_pread(BlockDriverState *bs, int64_t offset,
@@ -168,62 +85,31 @@ int bdrv_pwrite(BlockDriverState *bs, int64_t offset,
                 const void *buf, int count);
 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,
-    int nb_sectors, QEMUIOVector *qiov);
-int coroutine_fn bdrv_co_copy_on_readv(BlockDriverState *bs,
-    int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
-int coroutine_fn bdrv_co_writev(BlockDriverState *bs, int64_t sector_num,
-    int nb_sectors, QEMUIOVector *qiov);
-/*
- * Efficiently zero a region of the disk image.  Note that this is a regular
- * I/O request like read or write and should have a reasonable size.  This
- * function is not suitable for zeroing the entire image in a single request
- * because it may allocate memory for the entire region.
- */
-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_write_sync(BlockDriverState *bs, int64_t sector_num,
+    const uint8_t *buf, int nb_sectors);
 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);
+void 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;
-    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 struct BlockDriverAIOCB BlockDriverAIOCB;
+typedef void BlockDriverCompletionFunc(void *opaque, int ret);
 typedef void BlockDriverDirtyHandler(BlockDriverState *bs, int64_t sector,
                                      int sector_num);
 BlockDriverAIOCB *bdrv_aio_readv(BlockDriverState *bs, int64_t sector_num,
@@ -234,9 +120,6 @@ BlockDriverAIOCB *bdrv_aio_writev(BlockDriverState *bs, int64_t sector_num,
                                   BlockDriverCompletionFunc *cb, void *opaque);
 BlockDriverAIOCB *bdrv_aio_flush(BlockDriverState *bs,
                                  BlockDriverCompletionFunc *cb, void *opaque);
-BlockDriverAIOCB *bdrv_aio_discard(BlockDriverState *bs,
-                                   int64_t sector_num, int nb_sectors,
-                                   BlockDriverCompletionFunc *cb, void *opaque);
 void bdrv_aio_cancel(BlockDriverAIOCB *acb);
 
 typedef struct BlockRequest {
@@ -260,40 +143,55 @@ BlockDriverAIOCB *bdrv_aio_ioctl(BlockDriverState *bs,
         unsigned long int req, void *buf,
         BlockDriverCompletionFunc *cb, void *opaque);
 
-/* Invalidate any cached metadata used by image formats */
-void bdrv_invalidate_cache(BlockDriverState *bs);
-void bdrv_invalidate_cache_all(void);
-
-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);
 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(BlockDriverState *bs);
 int bdrv_is_allocated(BlockDriverState *bs, 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;
+
+void bdrv_get_floppy_geometry_hint(BlockDriverState *bs, int *nb_heads,
+                                   int *max_track, int *last_sect,
+                                   FDriveType drive_in, FDriveType *drive);
+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);
+void bdrv_set_removable(BlockDriverState *bs, int removable);
+int bdrv_is_removable(BlockDriverState *bs);
 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);
+int bdrv_is_locked(BlockDriverState *bs);
+void bdrv_set_locked(BlockDriverState *bs, int locked);
+int bdrv_eject(BlockDriverState *bs, int eject_flag);
+void bdrv_set_change_cb(BlockDriverState *bs,
+                        void (*change_cb)(void *opaque, int reason),
+                        void *opaque);
+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),
@@ -305,7 +203,6 @@ 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);
@@ -313,10 +210,6 @@ int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi);
 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);
-BlockInfo *bdrv_query_info(BlockDriverState *s);
-BlockStats *bdrv_query_stats(const BlockDriverState *bs);
 int bdrv_can_snapshot(BlockDriverState *bs);
 int bdrv_is_snapshot(BlockDriverState *bs);
 BlockDriverState *bdrv_snapshots(void);
@@ -347,41 +240,17 @@ 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);
-
 #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);
-int64_t bdrv_get_next_dirty(BlockDriverState *bs, int64_t sector);
+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);
-void bdrv_disable_copy_on_read(BlockDriverState *bs);
-
 void bdrv_set_in_use(BlockDriverState *bs, int in_use);
 int bdrv_in_use(BlockDriverState *bs);
 
-enum BlockAcctType {
-    BDRV_ACCT_READ,
-    BDRV_ACCT_WRITE,
-    BDRV_ACCT_FLUSH,
-    BDRV_MAX_IOTYPE,
-};
-
-typedef struct BlockAcctCookie {
-    int64_t bytes;
-    int64_t start_time_ns;
-    enum BlockAcctType type;
-} BlockAcctCookie;
-
-void bdrv_acct_start(BlockDriverState *bs, BlockAcctCookie *cookie,
-        int64_t bytes, enum BlockAcctType type);
-void bdrv_acct_done(BlockDriverState *bs, BlockAcctCookie *cookie);
-
 typedef enum {
     BLKDBG_L1_UPDATE,
 
@@ -395,7 +264,9 @@ 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,
 

block/Makefile.objs

@@ -1,20 +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 += parallels.o blkdebug.o blkverify.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
-endif
-
-common-obj-y += stream.o
-common-obj-y += commit.o
-common-obj-y += mirror.o

block/blkdebug.c

@@ -26,11 +26,24 @@
 #include "block_int.h"
 #include "module.h"
 
-typedef struct BDRVBlkdebugState {
+typedef struct BlkdebugVars {
     int state;
-    int new_state;
-    QLIST_HEAD(, BlkdebugRule) rules[BLKDBG_EVENT_MAX];
-    QSIMPLEQ_HEAD(, BlkdebugRule) active_rules;
+
+    /* 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 {
+    BlkdebugVars vars;
+    QLIST_HEAD(list, BlkdebugRule) rules[BLKDBG_EVENT_MAX];
 } BDRVBlkdebugState;
 
 typedef struct BlkdebugAIOCB {
@@ -41,7 +54,7 @@ typedef struct BlkdebugAIOCB {
 
 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,
 };
@@ -60,14 +73,12 @@ typedef struct BlkdebugRule {
             int error;
             int immediately;
             int once;
-            int64_t sector;
         } inject;
         struct {
             int new_state;
         } set_state;
     } options;
     QLIST_ENTRY(BlkdebugRule) next;
-    QSIMPLEQ_ENTRY(BlkdebugRule) active_next;
 } BlkdebugRule;
 
 static QemuOptsList inject_error_opts = {
@@ -86,10 +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,
@@ -140,7 +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",
 
@@ -205,7 +214,7 @@ static int add_rule(QemuOpts *opts, void *opaque)
     }
 
     /* Set attributes common for all actions */
-    rule = g_malloc0(sizeof(*rule));
+    rule = qemu_mallocz(sizeof(*rule));
     *rule = (struct BlkdebugRule) {
         .event  = event,
         .action = d->action,
@@ -219,7 +228,6 @@ 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:
@@ -284,17 +292,17 @@ static int blkdebug_open(BlockDriverState *bs, const char *filename, int flags)
         return -EINVAL;
     }
 
-    config = g_strdup(filename);
+    config = strdup(filename);
     config[c - filename] = '\0';
     ret = read_config(s, config);
-    g_free(config);
+    free(config);
     if (ret < 0) {
         return ret;
     }
     filename = c + 1;
 
     /* Set initial state */
-    s->state = 1;
+    s->vars.state = 1;
 
     /* Open the backing file */
     ret = bdrv_file_open(&bs->file, filename, flags);
@@ -320,22 +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);
@@ -350,21 +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,
@@ -372,21 +373,14 @@ 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)
@@ -398,57 +392,58 @@ static void blkdebug_close(BlockDriverState *bs)
     for (i = 0; i < BLKDBG_EVENT_MAX; i++) {
         QLIST_FOREACH_SAFE(rule, &s->rules[i], next, next) {
             QLIST_REMOVE(rule, next);
-            g_free(rule);
+            qemu_free(rule);
         }
     }
 }
 
-static bool process_rule(BlockDriverState *bs, struct BlkdebugRule *rule,
-    bool injected)
+static int blkdebug_flush(BlockDriverState *bs)
+{
+    return bdrv_flush(bs->file);
+}
+
+static BlockDriverAIOCB *blkdebug_aio_flush(BlockDriverState *bs,
+    BlockDriverCompletionFunc *cb, void *opaque)
+{
+    return bdrv_aio_flush(bs->file, cb, opaque);
+}
+
+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;
+        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;
-    bool injected;
+    BlkdebugVars old_vars = s->vars;
 
     assert((int)event >= 0 && event < BLKDBG_EVENT_MAX);
 
-    injected = false;
-    s->new_state = s->state;
     QLIST_FOREACH(rule, &s->rules[event], next) {
-        injected = process_rule(bs, rule, injected);
+        process_rule(bs, rule, &old_vars);
     }
-    s->state = s->new_state;
-}
-
-static int64_t blkdebug_getlength(BlockDriverState *bs)
-{
-    return bdrv_getlength(bs->file);
 }
 
 static BlockDriver bdrv_blkdebug = {
@@ -459,10 +454,11 @@ static BlockDriver bdrv_blkdebug = {
 
     .bdrv_file_open     = blkdebug_open,
     .bdrv_close         = blkdebug_close,
-    .bdrv_getlength     = blkdebug_getlength,
+    .bdrv_flush         = blkdebug_flush,
 
     .bdrv_aio_readv     = blkdebug_aio_readv,
     .bdrv_aio_writev    = blkdebug_aio_writev,
+    .bdrv_aio_flush     = blkdebug_aio_flush,
 
     .bdrv_debug_event   = blkdebug_debug_event,
 };

block/blkverify.c

@@ -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,
 };
@@ -87,10 +87,10 @@ static int blkverify_open(BlockDriverState *bs, const char *filename, int flags)
         return -EINVAL;
     }
 
-    raw = g_strdup(filename);
+    raw = strdup(filename);
     raw[c - filename] = '\0';
     ret = bdrv_file_open(&bs->file, raw, flags);
-    g_free(raw);
+    free(raw);
     if (ret < 0) {
         return ret;
     }
@@ -116,6 +116,14 @@ static void blkverify_close(BlockDriverState *bs)
     s->test_file = NULL;
 }
 
+static int blkverify_flush(BlockDriverState *bs)
+{
+    BDRVBlkverifyState *s = bs->opaque;
+
+    /* Only flush test file, the raw file is not important */
+    return bdrv_flush(s->test_file);
+}
+
 static int64_t blkverify_getlength(BlockDriverState *bs)
 {
     BDRVBlkverifyState *s = bs->opaque;
@@ -233,7 +241,7 @@ 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;
@@ -310,10 +318,14 @@ static BlockDriverAIOCB *blkverify_aio_readv(BlockDriverState *bs,
     qemu_iovec_init(&acb->raw_qiov, acb->qiov->niov);
     blkverify_iovec_clone(&acb->raw_qiov, qiov, acb->buf);
 
-    bdrv_aio_readv(s->test_file, sector_num, qiov, nb_sectors,
-                   blkverify_aio_cb, acb);
-    bdrv_aio_readv(bs->file, sector_num, &acb->raw_qiov, nb_sectors,
-                   blkverify_aio_cb, acb);
+    if (!bdrv_aio_readv(s->test_file, sector_num, qiov, nb_sectors,
+                        blkverify_aio_cb, acb)) {
+        blkverify_aio_cb(acb, -EIO);
+    }
+    if (!bdrv_aio_readv(bs->file, sector_num, &acb->raw_qiov, nb_sectors,
+                        blkverify_aio_cb, acb)) {
+        blkverify_aio_cb(acb, -EIO);
+    }
     return &acb->common;
 }
 
@@ -325,10 +337,14 @@ static BlockDriverAIOCB *blkverify_aio_writev(BlockDriverState *bs,
     BlkverifyAIOCB *acb = blkverify_aio_get(bs, true, sector_num, qiov,
                                             nb_sectors, cb, opaque);
 
-    bdrv_aio_writev(s->test_file, sector_num, qiov, nb_sectors,
-                    blkverify_aio_cb, acb);
-    bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors,
-                    blkverify_aio_cb, acb);
+    if (!bdrv_aio_writev(s->test_file, sector_num, qiov, nb_sectors,
+                         blkverify_aio_cb, acb)) {
+        blkverify_aio_cb(acb, -EIO);
+    }
+    if (!bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors,
+                         blkverify_aio_cb, acb)) {
+        blkverify_aio_cb(acb, -EIO);
+    }
     return &acb->common;
 }
 
@@ -352,6 +368,7 @@ static BlockDriver bdrv_blkverify = {
 
     .bdrv_file_open     = blkverify_open,
     .bdrv_close         = blkverify_close,
+    .bdrv_flush         = blkverify_flush,
 
     .bdrv_aio_readv     = blkverify_aio_readv,
     .bdrv_aio_writev    = blkverify_aio_writev,

block/bochs.c

@@ -80,7 +80,6 @@ struct bochs_header {
 };
 
 typedef struct BDRVBochsState {
-    CoMutex lock;
     uint32_t *catalog_bitmap;
     int catalog_size;
 
@@ -137,7 +136,7 @@ static int bochs_open(BlockDriverState *bs, int flags)
     }
 
     s->catalog_size = le32_to_cpu(bochs.extra.redolog.catalog);
-    s->catalog_bitmap = g_malloc(s->catalog_size * 4);
+    s->catalog_bitmap = qemu_malloc(s->catalog_size * 4);
     if (bdrv_pread(bs->file, le32_to_cpu(bochs.header), s->catalog_bitmap,
                    s->catalog_size * 4) != s->catalog_size * 4)
 	goto fail;
@@ -151,7 +150,6 @@ static int bochs_open(BlockDriverState *bs, int flags)
 
     s->extent_size = le32_to_cpu(bochs.extra.redolog.extent);
 
-    qemu_co_mutex_init(&s->lock);
     return 0;
  fail:
     return -1;
@@ -209,21 +207,10 @@ static int bochs_read(BlockDriverState *bs, int64_t sector_num,
     return 0;
 }
 
-static coroutine_fn int bochs_co_read(BlockDriverState *bs, int64_t sector_num,
-                                      uint8_t *buf, int nb_sectors)
-{
-    int ret;
-    BDRVBochsState *s = bs->opaque;
-    qemu_co_mutex_lock(&s->lock);
-    ret = bochs_read(bs, sector_num, buf, nb_sectors);
-    qemu_co_mutex_unlock(&s->lock);
-    return ret;
-}
-
 static void bochs_close(BlockDriverState *bs)
 {
     BDRVBochsState *s = bs->opaque;
-    g_free(s->catalog_bitmap);
+    qemu_free(s->catalog_bitmap);
 }
 
 static BlockDriver bdrv_bochs = {
@@ -231,7 +218,7 @@ static BlockDriver bdrv_bochs = {
     .instance_size	= sizeof(BDRVBochsState),
     .bdrv_probe		= bochs_probe,
     .bdrv_open		= bochs_open,
-    .bdrv_read          = bochs_co_read,
+    .bdrv_read		= bochs_read,
     .bdrv_close		= bochs_close,
 };
 

block/cloop.c

@@ -27,10 +27,9 @@
 #include <zlib.h>
 
 typedef struct BDRVCloopState {
-    CoMutex lock;
     uint32_t block_size;
     uint32_t n_blocks;
-    uint64_t *offsets;
+    uint64_t* offsets;
     uint32_t sectors_per_block;
     uint32_t current_block;
     uint8_t *compressed_block;
@@ -40,23 +39,21 @@ typedef struct BDRVCloopState {
 
 static int cloop_probe(const uint8_t *buf, int buf_size, const char *filename)
 {
-    const char *magic_version_2_0 = "#!/bin/sh\n"
-        "#V2.0 Format\n"
-        "modprobe cloop file=$0 && mount -r -t iso9660 /dev/cloop $1\n";
-    int length = strlen(magic_version_2_0);
-    if (length > buf_size) {
-        length = buf_size;
-    }
-    if (!memcmp(magic_version_2_0, buf, length)) {
-        return 2;
-    }
+    const char* magic_version_2_0="#!/bin/sh\n"
+	"#V2.0 Format\n"
+	"modprobe cloop file=$0 && mount -r -t iso9660 /dev/cloop $1\n";
+    int length=strlen(magic_version_2_0);
+    if(length>buf_size)
+	length=buf_size;
+    if(!memcmp(magic_version_2_0,buf,length))
+	return 2;
     return 0;
 }
 
 static int cloop_open(BlockDriverState *bs, int flags)
 {
     BDRVCloopState *s = bs->opaque;
-    uint32_t offsets_size, max_compressed_block_size = 1, i;
+    uint32_t offsets_size,max_compressed_block_size=1,i;
 
     bs->read_only = 1;
 
@@ -73,32 +70,29 @@ static int cloop_open(BlockDriverState *bs, int flags)
 
     /* read offsets */
     offsets_size = s->n_blocks * sizeof(uint64_t);
-    s->offsets = g_malloc(offsets_size);
+    s->offsets = qemu_malloc(offsets_size);
     if (bdrv_pread(bs->file, 128 + 4 + 4, s->offsets, offsets_size) <
             offsets_size) {
-        goto cloop_close;
+	goto cloop_close;
     }
     for(i=0;i<s->n_blocks;i++) {
-        s->offsets[i] = be64_to_cpu(s->offsets[i]);
-        if (i > 0) {
-            uint32_t size = s->offsets[i] - s->offsets[i - 1];
-            if (size > max_compressed_block_size) {
-                max_compressed_block_size = size;
-            }
-        }
+	s->offsets[i]=be64_to_cpu(s->offsets[i]);
+	if(i>0) {
+	    uint32_t size=s->offsets[i]-s->offsets[i-1];
+	    if(size>max_compressed_block_size)
+		max_compressed_block_size=size;
+	}
     }
 
     /* initialize zlib engine */
-    s->compressed_block = g_malloc(max_compressed_block_size + 1);
-    s->uncompressed_block = g_malloc(s->block_size);
-    if (inflateInit(&s->zstream) != Z_OK) {
-        goto cloop_close;
-    }
-    s->current_block = s->n_blocks;
+    s->compressed_block = qemu_malloc(max_compressed_block_size+1);
+    s->uncompressed_block = qemu_malloc(s->block_size);
+    if(inflateInit(&s->zstream) != Z_OK)
+	goto cloop_close;
+    s->current_block=s->n_blocks;
 
     s->sectors_per_block = s->block_size/512;
-    bs->total_sectors = s->n_blocks * s->sectors_per_block;
-    qemu_co_mutex_init(&s->lock);
+    bs->total_sectors = s->n_blocks*s->sectors_per_block;
     return 0;
 
 cloop_close:
@@ -109,30 +103,27 @@ static inline int cloop_read_block(BlockDriverState *bs, int block_num)
 {
     BDRVCloopState *s = bs->opaque;
 
-    if (s->current_block != block_num) {
-        int ret;
-        uint32_t bytes = s->offsets[block_num + 1] - s->offsets[block_num];
+    if(s->current_block != block_num) {
+	int ret;
+        uint32_t bytes = s->offsets[block_num+1]-s->offsets[block_num];
 
         ret = bdrv_pread(bs->file, s->offsets[block_num], s->compressed_block,
                          bytes);
-        if (ret != bytes) {
+        if (ret != bytes)
             return -1;
-        }
 
-        s->zstream.next_in = s->compressed_block;
-        s->zstream.avail_in = bytes;
-        s->zstream.next_out = s->uncompressed_block;
-        s->zstream.avail_out = s->block_size;
-        ret = inflateReset(&s->zstream);
-        if (ret != Z_OK) {
-            return -1;
-        }
-        ret = inflate(&s->zstream, Z_FINISH);
-        if (ret != Z_STREAM_END || s->zstream.total_out != s->block_size) {
-            return -1;
-        }
+	s->zstream.next_in = s->compressed_block;
+	s->zstream.avail_in = bytes;
+	s->zstream.next_out = s->uncompressed_block;
+	s->zstream.avail_out = s->block_size;
+	ret = inflateReset(&s->zstream);
+	if(ret != Z_OK)
+	    return -1;
+	ret = inflate(&s->zstream, Z_FINISH);
+	if(ret != Z_STREAM_END || s->zstream.total_out != s->block_size)
+	    return -1;
 
-        s->current_block = block_num;
+	s->current_block = block_num;
     }
     return 0;
 }
@@ -143,48 +134,33 @@ static int cloop_read(BlockDriverState *bs, int64_t sector_num,
     BDRVCloopState *s = bs->opaque;
     int i;
 
-    for (i = 0; i < nb_sectors; i++) {
-        uint32_t sector_offset_in_block =
-            ((sector_num + i) % s->sectors_per_block),
-            block_num = (sector_num + i) / s->sectors_per_block;
-        if (cloop_read_block(bs, block_num) != 0) {
-            return -1;
-        }
-        memcpy(buf + i * 512,
-            s->uncompressed_block + sector_offset_in_block * 512, 512);
+    for(i=0;i<nb_sectors;i++) {
+	uint32_t sector_offset_in_block=((sector_num+i)%s->sectors_per_block),
+	    block_num=(sector_num+i)/s->sectors_per_block;
+	if(cloop_read_block(bs, block_num) != 0)
+	    return -1;
+	memcpy(buf+i*512,s->uncompressed_block+sector_offset_in_block*512,512);
     }
     return 0;
 }
 
-static coroutine_fn int cloop_co_read(BlockDriverState *bs, int64_t sector_num,
-                                      uint8_t *buf, int nb_sectors)
-{
-    int ret;
-    BDRVCloopState *s = bs->opaque;
-    qemu_co_mutex_lock(&s->lock);
-    ret = cloop_read(bs, sector_num, buf, nb_sectors);
-    qemu_co_mutex_unlock(&s->lock);
-    return ret;
-}
-
 static void cloop_close(BlockDriverState *bs)
 {
     BDRVCloopState *s = bs->opaque;
-    if (s->n_blocks > 0) {
-        g_free(s->offsets);
-    }
-    g_free(s->compressed_block);
-    g_free(s->uncompressed_block);
+    if(s->n_blocks>0)
+	free(s->offsets);
+    free(s->compressed_block);
+    free(s->uncompressed_block);
     inflateEnd(&s->zstream);
 }
 
 static BlockDriver bdrv_cloop = {
-    .format_name    = "cloop",
-    .instance_size  = sizeof(BDRVCloopState),
-    .bdrv_probe     = cloop_probe,
-    .bdrv_open      = cloop_open,
-    .bdrv_read      = cloop_co_read,
-    .bdrv_close     = cloop_close,
+    .format_name	= "cloop",
+    .instance_size	= sizeof(BDRVCloopState),
+    .bdrv_probe		= cloop_probe,
+    .bdrv_open		= cloop_open,
+    .bdrv_read		= cloop_read,
+    .bdrv_close		= cloop_close,
 };
 
 static void bdrv_cloop_init(void)

block/commit.c

@@ -1,259 +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_int.h"
-#include "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 = NULL;
-    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;
-        }
-    }
-
-    overlay_bs = bdrv_find_overlay(active, top);
-
-    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 qemu_aio_flush() 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);
-    }
-    if (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 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

@@ -42,7 +42,6 @@ struct cow_header_v2 {
 };
 
 typedef struct BDRVCowState {
-    CoMutex lock;
     int64_t cow_sectors_offset;
 } BDRVCowState;
 
@@ -64,26 +63,15 @@ static int cow_open(BlockDriverState *bs, int flags)
     struct cow_header_v2 cow_header;
     int bitmap_size;
     int64_t size;
-    int ret;
 
     /* see if it is a cow image */
-    ret = bdrv_pread(bs->file, 0, &cow_header, sizeof(cow_header));
-    if (ret < 0) {
+    if (bdrv_pread(bs->file, 0, &cow_header, sizeof(cow_header)) !=
+            sizeof(cow_header)) {
         goto fail;
     }
 
-    if (be32_to_cpu(cow_header.magic) != COW_MAGIC) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    if (be32_to_cpu(cow_header.version) != COW_VERSION) {
-        char version[64];
-        snprintf(version, sizeof(version),
-               "COW version %d", cow_header.version);
-        qerror_report(QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
-            bs->device_name, "cow", version);
-        ret = -ENOTSUP;
+    if (be32_to_cpu(cow_header.magic) != COW_MAGIC ||
+        be32_to_cpu(cow_header.version) != COW_VERSION) {
         goto fail;
     }
 
@@ -96,14 +84,13 @@ static int cow_open(BlockDriverState *bs, int flags)
 
     bitmap_size = ((bs->total_sectors + 7) >> 3) + sizeof(cow_header);
     s->cow_sectors_offset = (bitmap_size + 511) & ~511;
-    qemu_co_mutex_init(&s->lock);
     return 0;
  fail:
-    return ret;
+    return -1;
 }
 
 /*
- * XXX(hch): right now these functions are extremely inefficient.
+ * XXX(hch): right now these functions are extremly ineffcient.
  * We should just read the whole bitmap we'll need in one go instead.
  */
 static inline int cow_set_bit(BlockDriverState *bs, int64_t bitnum)
@@ -143,8 +130,8 @@ static inline int is_bit_set(BlockDriverState *bs, int64_t bitnum)
 /* Return true if first block has been changed (ie. current version is
  * in COW file).  Set the number of continuous blocks for which that
  * is true. */
-static int coroutine_fn cow_co_is_allocated(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *num_same)
+static int cow_is_allocated(BlockDriverState *bs, int64_t sector_num,
+        int nb_sectors, int *num_same)
 {
     int changed;
 
@@ -182,30 +169,28 @@ static int cow_update_bitmap(BlockDriverState *bs, int64_t sector_num,
     return error;
 }
 
-static int coroutine_fn cow_read(BlockDriverState *bs, int64_t sector_num,
-                                 uint8_t *buf, int nb_sectors)
+static int cow_read(BlockDriverState *bs, int64_t sector_num,
+                    uint8_t *buf, int nb_sectors)
 {
     BDRVCowState *s = bs->opaque;
     int ret, n;
 
     while (nb_sectors > 0) {
-        if (bdrv_co_is_allocated(bs, sector_num, nb_sectors, &n)) {
+        if (cow_is_allocated(bs, sector_num, nb_sectors, &n)) {
             ret = bdrv_pread(bs->file,
                         s->cow_sectors_offset + sector_num * 512,
                         buf, n * 512);
-            if (ret < 0) {
-                return ret;
-            }
+            if (ret != n * 512)
+                return -1;
         } else {
             if (bs->backing_hd) {
                 /* read from the base image */
                 ret = bdrv_read(bs->backing_hd, sector_num, buf, n);
-                if (ret < 0) {
-                    return ret;
-                }
+                if (ret < 0)
+                    return -1;
             } else {
-                memset(buf, 0, n * 512);
-            }
+            memset(buf, 0, n * 512);
+        }
         }
         nb_sectors -= n;
         sector_num += n;
@@ -214,17 +199,6 @@ static int coroutine_fn cow_read(BlockDriverState *bs, int64_t sector_num,
     return 0;
 }
 
-static coroutine_fn int cow_co_read(BlockDriverState *bs, int64_t sector_num,
-                                    uint8_t *buf, int nb_sectors)
-{
-    int ret;
-    BDRVCowState *s = bs->opaque;
-    qemu_co_mutex_lock(&s->lock);
-    ret = cow_read(bs, sector_num, buf, nb_sectors);
-    qemu_co_mutex_unlock(&s->lock);
-    return ret;
-}
-
 static int cow_write(BlockDriverState *bs, int64_t sector_num,
                      const uint8_t *buf, int nb_sectors)
 {
@@ -233,36 +207,24 @@ static int cow_write(BlockDriverState *bs, int64_t sector_num,
 
     ret = bdrv_pwrite(bs->file, s->cow_sectors_offset + sector_num * 512,
                       buf, nb_sectors * 512);
-    if (ret < 0) {
-        return ret;
-    }
+    if (ret != nb_sectors * 512)
+        return -1;
 
     return cow_update_bitmap(bs, sector_num, nb_sectors);
 }
 
-static coroutine_fn int cow_co_write(BlockDriverState *bs, int64_t sector_num,
-                                     const uint8_t *buf, int nb_sectors)
-{
-    int ret;
-    BDRVCowState *s = bs->opaque;
-    qemu_co_mutex_lock(&s->lock);
-    ret = cow_write(bs, sector_num, buf, nb_sectors);
-    qemu_co_mutex_unlock(&s->lock);
-    return ret;
-}
-
 static void cow_close(BlockDriverState *bs)
 {
 }
 
 static int cow_create(const char *filename, QEMUOptionParameter *options)
 {
+    int fd, cow_fd;
     struct cow_header_v2 cow_header;
     struct stat st;
     int64_t image_sectors = 0;
     const char *image_filename = NULL;
     int ret;
-    BlockDriverState *cow_bs;
 
     /* Read out options */
     while (options && options->name) {
@@ -274,16 +236,10 @@ static int cow_create(const char *filename, QEMUOptionParameter *options)
         options++;
     }
 
-    ret = bdrv_create_file(filename, options);
-    if (ret < 0) {
-        return ret;
-    }
-
-    ret = bdrv_file_open(&cow_bs, filename, BDRV_O_RDWR);
-    if (ret < 0) {
-        return ret;
-    }
-
+    cow_fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
+              0644);
+    if (cow_fd < 0)
+        return -errno;
     memset(&cow_header, 0, sizeof(cow_header));
     cow_header.magic = cpu_to_be32(COW_MAGIC);
     cow_header.version = cpu_to_be32(COW_VERSION);
@@ -291,9 +247,16 @@ static int cow_create(const char *filename, QEMUOptionParameter *options)
         /* Note: if no file, we put a dummy mtime */
         cow_header.mtime = cpu_to_be32(0);
 
-        if (stat(image_filename, &st) != 0) {
+        fd = open(image_filename, O_RDONLY | O_BINARY);
+        if (fd < 0) {
+            close(cow_fd);
             goto mtime_fail;
         }
+        if (fstat(fd, &st) != 0) {
+            close(fd);
+            goto mtime_fail;
+        }
+        close(fd);
         cow_header.mtime = cpu_to_be32(st.st_mtime);
     mtime_fail:
         pstrcpy(cow_header.backing_file, sizeof(cow_header.backing_file),
@@ -301,23 +264,29 @@ static int cow_create(const char *filename, QEMUOptionParameter *options)
     }
     cow_header.sectorsize = cpu_to_be32(512);
     cow_header.size = cpu_to_be64(image_sectors * 512);
-    ret = bdrv_pwrite(cow_bs, 0, &cow_header, sizeof(cow_header));
-    if (ret < 0) {
+    ret = qemu_write_full(cow_fd, &cow_header, sizeof(cow_header));
+    if (ret != sizeof(cow_header)) {
+        ret = -errno;
         goto exit;
     }
 
     /* resize to include at least all the bitmap */
-    ret = bdrv_truncate(cow_bs,
-        sizeof(cow_header) + ((image_sectors + 7) >> 3));
-    if (ret < 0) {
+    ret = ftruncate(cow_fd, sizeof(cow_header) + ((image_sectors + 7) >> 3));
+    if (ret) {
+        ret = -errno;
         goto exit;
     }
 
 exit:
-    bdrv_delete(cow_bs);
+    close(cow_fd);
     return ret;
 }
 
+static int cow_flush(BlockDriverState *bs)
+{
+    return bdrv_flush(bs->file);
+}
+
 static QEMUOptionParameter cow_create_options[] = {
     {
         .name = BLOCK_OPT_SIZE,
@@ -333,17 +302,16 @@ static QEMUOptionParameter cow_create_options[] = {
 };
 
 static BlockDriver bdrv_cow = {
-    .format_name    = "cow",
-    .instance_size  = sizeof(BDRVCowState),
-
-    .bdrv_probe     = cow_probe,
-    .bdrv_open      = cow_open,
-    .bdrv_close     = cow_close,
-    .bdrv_create    = cow_create,
-
-    .bdrv_read              = cow_co_read,
-    .bdrv_write             = cow_co_write,
-    .bdrv_co_is_allocated   = cow_co_is_allocated,
+    .format_name	= "cow",
+    .instance_size	= sizeof(BDRVCowState),
+    .bdrv_probe		= cow_probe,
+    .bdrv_open		= cow_open,
+    .bdrv_read		= cow_read,
+    .bdrv_write		= cow_write,
+    .bdrv_close		= cow_close,
+    .bdrv_create	= cow_create,
+    .bdrv_flush		= cow_flush,
+    .bdrv_is_allocated	= cow_is_allocated,
 
     .create_options = cow_create_options,
 };

block/curl.c

@@ -47,12 +47,7 @@ struct BDRVCURLState;
 
 typedef struct CURLAIOCB {
     BlockDriverAIOCB common;
-    QEMUBH *bh;
     QEMUIOVector *qiov;
-
-    int64_t sector_num;
-    int nb_sectors;
-
     size_t start;
     size_t end;
 } CURLAIOCB;
@@ -81,7 +76,6 @@ typedef struct BDRVCURLState {
 
 static void curl_clean_state(CURLState *s);
 static void curl_multi_do(void *arg);
-static int curl_aio_flush(void *opaque);
 
 static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
                         void *s, void *sp)
@@ -89,17 +83,17 @@ static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
     DPRINTF("CURL (AIO): Sock action %d on fd %d\n", action, fd);
     switch (action) {
         case CURL_POLL_IN:
-            qemu_aio_set_fd_handler(fd, curl_multi_do, NULL, curl_aio_flush, s);
+            qemu_aio_set_fd_handler(fd, curl_multi_do, NULL, NULL, NULL, s);
             break;
         case CURL_POLL_OUT:
-            qemu_aio_set_fd_handler(fd, NULL, curl_multi_do, curl_aio_flush, s);
+            qemu_aio_set_fd_handler(fd, NULL, curl_multi_do, NULL, NULL, s);
             break;
         case CURL_POLL_INOUT:
-            qemu_aio_set_fd_handler(fd, curl_multi_do, curl_multi_do,
-                                    curl_aio_flush, s);
+            qemu_aio_set_fd_handler(fd, curl_multi_do,
+                                    curl_multi_do, NULL, NULL, s);
             break;
         case CURL_POLL_REMOVE:
-            qemu_aio_set_fd_handler(fd, NULL, NULL, NULL, NULL);
+            qemu_aio_set_fd_handler(fd, NULL, NULL, NULL, NULL, NULL);
             break;
     }
 
@@ -140,8 +134,8 @@ 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;
@@ -176,7 +170,7 @@ 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;
@@ -235,23 +229,6 @@ static void curl_multi_do(void *arg)
             {
                 CURLState *state = NULL;
                 curl_easy_getinfo(msg->easy_handle, CURLINFO_PRIVATE, (char**)&state);
-
-                /* ACBs for successful messages get completed in curl_read_cb */
-                if (msg->data.result != CURLE_OK) {
-                    int i;
-                    for (i = 0; i < CURL_NUM_ACB; i++) {
-                        CURLAIOCB *acb = state->acb[i];
-
-                        if (acb == NULL) {
-                            continue;
-                        }
-
-                        acb->common.cb(acb->common.opaque, -EIO);
-                        qemu_aio_release(acb);
-                        state->acb[i] = NULL;
-                    }
-                }
-
                 curl_clean_state(state);
                 break;
             }
@@ -280,7 +257,7 @@ static CURLState *curl_init_state(BDRVCURLState *s)
             break;
         }
         if (!state) {
-            g_usleep(100);
+            usleep(100);
             curl_multi_do(s);
         }
     } while(!state);
@@ -300,8 +277,7 @@ static CURLState *curl_init_state(BDRVCURLState *s)
     curl_easy_setopt(state->curl, CURLOPT_FOLLOWLOCATION, 1);
     curl_easy_setopt(state->curl, CURLOPT_NOSIGNAL, 1);
     curl_easy_setopt(state->curl, CURLOPT_ERRORBUFFER, state->errmsg);
-    curl_easy_setopt(state->curl, CURLOPT_FAILONERROR, 1);
-
+    
 #ifdef DEBUG_VERBOSE
     curl_easy_setopt(state->curl, CURLOPT_VERBOSE, 1);
 #endif
@@ -334,7 +310,7 @@ static int curl_open(BlockDriverState *bs, const char *filename, int flags)
 
     static int inited = 0;
 
-    file = g_strdup(filename);
+    file = qemu_strdup(filename);
     s->readahead_size = READ_AHEAD_SIZE;
 
     /* Parse a trailing ":readahead=#:" param, if present. */
@@ -414,111 +390,75 @@ out:
     curl_easy_cleanup(state->curl);
     state->curl = NULL;
 out_noclean:
-    g_free(file);
+    qemu_free(file);
     return -EINVAL;
 }
 
-static int curl_aio_flush(void *opaque)
-{
-    BDRVCURLState *s = opaque;
-    int i, j;
-
-    for (i=0; i < CURL_NUM_STATES; i++) {
-        for(j=0; j < CURL_NUM_ACB; j++) {
-            if (s->states[i].acb[j]) {
-                return 1;
-            }
-        }
-    }
-    return 0;
-}
-
 static void curl_aio_cancel(BlockDriverAIOCB *blockacb)
 {
     // Do we have to implement canceling? Seems to work without...
 }
 
-static const AIOCBInfo curl_aiocb_info = {
+static AIOPool curl_aio_pool = {
     .aiocb_size         = sizeof(CURLAIOCB),
     .cancel             = curl_aio_cancel,
 };
 
-
-static void curl_readv_bh_cb(void *p)
-{
-    CURLState *state;
-
-    CURLAIOCB *acb = p;
-    BDRVCURLState *s = acb->common.bs->opaque;
-
-    qemu_bh_delete(acb->bh);
-    acb->bh = NULL;
-
-    size_t start = acb->sector_num * SECTOR_SIZE;
-    size_t end;
-
-    // In case we have the requested data already (e.g. read-ahead),
-    // we can just call the callback and be done.
-    switch (curl_find_buf(s, start, acb->nb_sectors * SECTOR_SIZE, acb)) {
-        case FIND_RET_OK:
-            qemu_aio_release(acb);
-            // fall through
-        case FIND_RET_WAIT:
-            return;
-        default:
-            break;
-    }
-
-    // No cache found, so let's start a new request
-    state = curl_init_state(s);
-    if (!state) {
-        acb->common.cb(acb->common.opaque, -EIO);
-        qemu_aio_release(acb);
-        return;
-    }
-
-    acb->start = 0;
-    acb->end = (acb->nb_sectors * SECTOR_SIZE);
-
-    state->buf_off = 0;
-    if (state->orig_buf)
-        g_free(state->orig_buf);
-    state->buf_start = start;
-    state->buf_len = acb->end + s->readahead_size;
-    end = MIN(start + state->buf_len, s->len) - 1;
-    state->orig_buf = g_malloc(state->buf_len);
-    state->acb[0] = acb;
-
-    snprintf(state->range, 127, "%zd-%zd", start, end);
-    DPRINTF("CURL (AIO): Reading %d at %zd (%s)\n",
-            (acb->nb_sectors * SECTOR_SIZE), start, state->range);
-    curl_easy_setopt(state->curl, CURLOPT_RANGE, state->range);
-
-    curl_multi_add_handle(s->multi, state->curl);
-    curl_multi_do(s);
-
-}
-
 static BlockDriverAIOCB *curl_aio_readv(BlockDriverState *bs,
         int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
         BlockDriverCompletionFunc *cb, void *opaque)
 {
+    BDRVCURLState *s = bs->opaque;
     CURLAIOCB *acb;
+    size_t start = sector_num * SECTOR_SIZE;
+    size_t end;
+    CURLState *state;
 
-    acb = qemu_aio_get(&curl_aiocb_info, bs, cb, opaque);
+    acb = qemu_aio_get(&curl_aio_pool, bs, cb, opaque);
+    if (!acb)
+        return NULL;
 
     acb->qiov = qiov;
-    acb->sector_num = sector_num;
-    acb->nb_sectors = nb_sectors;
 
-    acb->bh = qemu_bh_new(curl_readv_bh_cb, acb);
+    // In case we have the requested data already (e.g. read-ahead),
+    // we can just call the callback and be done.
 
-    if (!acb->bh) {
-        DPRINTF("CURL: qemu_bh_new failed\n");
-        return NULL;
+    switch (curl_find_buf(s, start, nb_sectors * SECTOR_SIZE, acb)) {
+        case FIND_RET_OK:
+            qemu_aio_release(acb);
+            // fall through
+        case FIND_RET_WAIT:
+            return &acb->common;
+        default:
+            break;
     }
 
-    qemu_bh_schedule(acb->bh);
+    // No cache found, so let's start a new request
+
+    state = curl_init_state(s);
+    if (!state)
+        return NULL;
+
+    acb->start = 0;
+    acb->end = (nb_sectors * SECTOR_SIZE);
+
+    state->buf_off = 0;
+    if (state->orig_buf)
+        qemu_free(state->orig_buf);
+    state->buf_start = start;
+    state->buf_len = acb->end + s->readahead_size;
+    end = MIN(start + state->buf_len, s->len) - 1;
+    state->orig_buf = qemu_malloc(state->buf_len);
+    state->acb[0] = acb;
+
+    snprintf(state->range, 127, "%zd-%zd", start, end);
+    DPRINTF("CURL (AIO): Reading %d at %zd (%s)\n",
+            (nb_sectors * SECTOR_SIZE), start, state->range);
+    curl_easy_setopt(state->curl, CURLOPT_RANGE, state->range);
+
+    curl_multi_add_handle(s->multi, state->curl);
+    curl_multi_do(s);
+
     return &acb->common;
 }
 
@@ -536,13 +476,14 @@ static void curl_close(BlockDriverState *bs)
             s->states[i].curl = NULL;
         }
         if (s->states[i].orig_buf) {
-            g_free(s->states[i].orig_buf);
+            qemu_free(s->states[i].orig_buf);
             s->states[i].orig_buf = NULL;
         }
     }
     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)

block/dmg.c

@@ -28,7 +28,6 @@
 #include <zlib.h>
 
 typedef struct BDRVDMGState {
-    CoMutex lock;
     /* each chunk contains a certain number of sectors,
      * offsets[i] is the offset in the .dmg file,
      * lengths[i] is the length of the compressed chunk,
@@ -128,11 +127,11 @@ static int dmg_open(BlockDriverState *bs, int flags)
 
 	    chunk_count = (count-204)/40;
 	    new_size = sizeof(uint64_t) * (s->n_chunks + chunk_count);
-	    s->types = g_realloc(s->types, new_size/2);
-	    s->offsets = g_realloc(s->offsets, new_size);
-	    s->lengths = g_realloc(s->lengths, new_size);
-	    s->sectors = g_realloc(s->sectors, new_size);
-	    s->sectorcounts = g_realloc(s->sectorcounts, new_size);
+	    s->types = qemu_realloc(s->types, new_size/2);
+	    s->offsets = qemu_realloc(s->offsets, new_size);
+	    s->lengths = qemu_realloc(s->lengths, new_size);
+	    s->sectors = qemu_realloc(s->sectors, new_size);
+	    s->sectorcounts = qemu_realloc(s->sectorcounts, new_size);
 
 	    for(i=s->n_chunks;i<s->n_chunks+chunk_count;i++) {
 		s->types[i] = read_uint32(bs, offset);
@@ -171,14 +170,13 @@ static int dmg_open(BlockDriverState *bs, int flags)
     }
 
     /* initialize zlib engine */
-    s->compressed_chunk = g_malloc(max_compressed_size+1);
-    s->uncompressed_chunk = g_malloc(512*max_sectors_per_chunk);
+    s->compressed_chunk = qemu_malloc(max_compressed_size+1);
+    s->uncompressed_chunk = qemu_malloc(512*max_sectors_per_chunk);
     if(inflateInit(&s->zstream) != Z_OK)
 	goto fail;
 
     s->current_chunk = s->n_chunks;
 
-    qemu_co_mutex_init(&s->lock);
     return 0;
 fail:
     return -1;
@@ -282,17 +280,6 @@ static int dmg_read(BlockDriverState *bs, int64_t sector_num,
     return 0;
 }
 
-static coroutine_fn int dmg_co_read(BlockDriverState *bs, int64_t sector_num,
-                                    uint8_t *buf, int nb_sectors)
-{
-    int ret;
-    BDRVDMGState *s = bs->opaque;
-    qemu_co_mutex_lock(&s->lock);
-    ret = dmg_read(bs, sector_num, buf, nb_sectors);
-    qemu_co_mutex_unlock(&s->lock);
-    return ret;
-}
-
 static void dmg_close(BlockDriverState *bs)
 {
     BDRVDMGState *s = bs->opaque;
@@ -313,7 +300,7 @@ static BlockDriver bdrv_dmg = {
     .instance_size	= sizeof(BDRVDMGState),
     .bdrv_probe		= dmg_probe,
     .bdrv_open		= dmg_open,
-    .bdrv_read          = dmg_co_read,
+    .bdrv_read		= dmg_read,
     .bdrv_close		= dmg_close,
 };
 

block/gluster.c

@@ -1,624 +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_int.h"
-#include "qemu_socket.h"
-#include "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\n", 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);
-}
-
-static int qemu_gluster_open(BlockDriverState *bs, const char *filename,
-    int bdrv_flags)
-{
-    BDRVGlusterState *s = bs->opaque;
-    int open_flags = O_BINARY;
-    int ret = 0;
-    GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
-
-    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_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 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;
-}
-
-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 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_aio_readv               = qemu_gluster_aio_readv,
-    .bdrv_aio_writev              = qemu_gluster_aio_writev,
-    .bdrv_aio_flush               = qemu_gluster_aio_flush,
-    .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_aio_readv               = qemu_gluster_aio_readv,
-    .bdrv_aio_writev              = qemu_gluster_aio_writev,
-    .bdrv_aio_flush               = qemu_gluster_aio_flush,
-    .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_aio_readv               = qemu_gluster_aio_readv,
-    .bdrv_aio_writev              = qemu_gluster_aio_writev,
-    .bdrv_aio_flush               = qemu_gluster_aio_flush,
-    .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_aio_readv               = qemu_gluster_aio_readv,
-    .bdrv_aio_writev              = qemu_gluster_aio_writev,
-    .bdrv_aio_flush               = qemu_gluster_aio_flush,
-    .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

@@ -1,322 +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 "blockjob.h"
-#include "block_int.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.
-     */
-    BLOCK_SIZE = 512 * BDRV_SECTORS_PER_DIRTY_CHUNK, /* in bytes */
-};
-
-#define SLICE_TIME 100000000ULL /* ns */
-
-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;
-    uint8_t *buf;
-} MirrorBlockJob;
-
-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 int coroutine_fn mirror_iteration(MirrorBlockJob *s,
-                                         BlockErrorAction *p_action)
-{
-    BlockDriverState *source = s->common.bs;
-    BlockDriverState *target = s->target;
-    QEMUIOVector qiov;
-    int ret, nb_sectors;
-    int64_t end;
-    struct iovec iov;
-
-    end = s->common.len >> BDRV_SECTOR_BITS;
-    s->sector_num = bdrv_get_next_dirty(source, s->sector_num);
-    nb_sectors = MIN(BDRV_SECTORS_PER_DIRTY_CHUNK, end - s->sector_num);
-    bdrv_reset_dirty(source, s->sector_num, nb_sectors);
-
-    /* Copy the dirty cluster.  */
-    iov.iov_base = s->buf;
-    iov.iov_len  = nb_sectors * 512;
-    qemu_iovec_init_external(&qiov, &iov, 1);
-
-    trace_mirror_one_iteration(s, s->sector_num, nb_sectors);
-    ret = bdrv_co_readv(source, s->sector_num, nb_sectors, &qiov);
-    if (ret < 0) {
-        *p_action = mirror_error_action(s, true, -ret);
-        goto fail;
-    }
-    ret = bdrv_co_writev(target, s->sector_num, nb_sectors, &qiov);
-    if (ret < 0) {
-        *p_action = mirror_error_action(s, false, -ret);
-        s->synced = false;
-        goto fail;
-    }
-    return 0;
-
-fail:
-    /* Try again later.  */
-    bdrv_set_dirty(source, s->sector_num, nb_sectors);
-    return ret;
-}
-
-static void coroutine_fn mirror_run(void *opaque)
-{
-    MirrorBlockJob *s = opaque;
-    BlockDriverState *bs = s->common.bs;
-    int64_t sector_num, end;
-    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;
-    }
-
-    end = s->common.len >> BDRV_SECTOR_BITS;
-    s->buf = qemu_blockalign(bs, BLOCK_SIZE);
-
-    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 | (BDRV_SECTORS_PER_DIRTY_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;
-            }
-        }
-    }
-
-    s->sector_num = -1;
-    for (;;) {
-        uint64_t delay_ns;
-        int64_t cnt;
-        bool should_complete;
-
-        cnt = bdrv_get_dirty_count(bs);
-        if (cnt != 0) {
-            BlockErrorAction action = BDRV_ACTION_REPORT;
-            ret = mirror_iteration(s, &action);
-            if (ret < 0 && action == BDRV_ACTION_REPORT) {
-                goto immediate_exit;
-            }
-            cnt = bdrv_get_dirty_count(bs);
-        }
-
-        should_complete = false;
-        if (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 * BDRV_SECTOR_SIZE - cnt * BLOCK_SIZE;
-
-            if (s->common.speed) {
-                delay_ns = ratelimit_calculate_delay(&s->limit, BDRV_SECTORS_PER_DIRTY_CHUNK);
-            } else {
-                delay_ns = 0;
-            }
-
-            /* Note that even when no rate limit is applied we need to yield
-             * 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;
-            }
-        } else if (!should_complete) {
-            delay_ns = (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;
-        }
-    }
-
-immediate_exit:
-    g_free(s->buf);
-    bdrv_set_dirty_tracking(bs, false);
-    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);
-    if (ret < 0) {
-        char backing_filename[PATH_MAX];
-        bdrv_get_full_backing_filename(s->target, backing_filename,
-                                       sizeof(backing_filename));
-        error_set(errp, QERR_OPEN_FILE_FAILED, 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 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, MirrorSyncMode mode,
-                  BlockdevOnError on_source_error,
-                  BlockdevOnError on_target_error,
-                  BlockDriverCompletionFunc *cb,
-                  void *opaque, Error **errp)
-{
-    MirrorBlockJob *s;
-
-    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;
-    bdrv_set_dirty_tracking(bs, true);
-    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

@@ -28,8 +28,6 @@
 
 #include "qemu-common.h"
 #include "nbd.h"
-#include "uri.h"
-#include "block_int.h"
 #include "module.h"
 #include "qemu_socket.h"
 
@@ -47,93 +45,19 @@
 #define logout(fmt, ...) ((void)0)
 #endif
 
-#define MAX_NBD_REQUESTS	16
-#define HANDLE_TO_INDEX(bs, handle) ((handle) ^ ((uint64_t)(intptr_t)bs))
-#define INDEX_TO_HANDLE(bs, index)  ((index)  ^ ((uint64_t)(intptr_t)bs))
-
 typedef struct BDRVNBDState {
     int sock;
-    uint32_t nbdflags;
     off_t size;
     size_t blocksize;
-
-    CoMutex send_mutex;
-    CoMutex free_sema;
-    Coroutine *send_coroutine;
-    int in_flight;
-
-    Coroutine *recv_coroutine[MAX_NBD_REQUESTS];
-    struct nbd_reply reply;
-
-    int is_unix;
-    char *host_spec;
     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(BDRVNBDState *s, const char *filename)
-{
-    URI *uri;
-    const char *p;
-    QueryParams *qp = NULL;
-    int ret = 0;
-
-    uri = uri_parse(filename);
-    if (!uri) {
-        return -EINVAL;
-    }
-
-    /* transport */
-    if (!strcmp(uri->scheme, "nbd")) {
-        s->is_unix = false;
-    } else if (!strcmp(uri->scheme, "nbd+tcp")) {
-        s->is_unix = false;
-    } else if (!strcmp(uri->scheme, "nbd+unix")) {
-        s->is_unix = true;
-    } else {
-        ret = -EINVAL;
-        goto out;
-    }
-
-    p = uri->path ? uri->path : "/";
-    p += strspn(p, "/");
-    if (p[0]) {
-        s->export_name = g_strdup(p);
-    }
-
-    qp = query_params_parse(uri->query);
-    if (qp->n > 1 || (s->is_unix && !qp->n) || (!s->is_unix && qp->n)) {
-        ret = -EINVAL;
-        goto out;
-    }
-
-    if (s->is_unix) {
-        /* nbd+unix:///export?socket=path */
-        if (uri->server || uri->port || strcmp(qp->p[0].name, "socket")) {
-            ret = -EINVAL;
-            goto out;
-        }
-        s->host_spec = g_strdup(qp->p[0].value);
-    } else {
-        /* nbd[+tcp]://host:port/export */
-        if (!uri->server) {
-            ret = -EINVAL;
-            goto out;
-        }
-        if (!uri->port) {
-            uri->port = NBD_DEFAULT_PORT;
-        }
-        s->host_spec = g_strdup_printf("%s:%d", uri->server, uri->port);
-    }
-
-out:
-    if (qp) {
-        query_params_free(qp);
-    }
-    uri_free(uri);
-    return ret;
-}
-
-static int nbd_config(BDRVNBDState *s, const char *filename)
+static int nbd_config(BDRVNBDState *s, const char *filename, int flags)
 {
     char *file;
     char *export_name;
@@ -141,11 +65,7 @@ static int nbd_config(BDRVNBDState *s, const char *filename)
     const char *unixpath;
     int err = -EINVAL;
 
-    if (strstr(filename, "://")) {
-        return nbd_parse_uri(s, filename);
-    }
-
-    file = g_strdup(filename);
+    file = qemu_strdup(filename);
 
     export_name = strstr(file, EN_OPTSTR);
     if (export_name) {
@@ -154,7 +74,7 @@ static int nbd_config(BDRVNBDState *s, const char *filename)
         }
         export_name[0] = 0; /* truncate 'file' */
         export_name += strlen(EN_OPTSTR);
-        s->export_name = g_strdup(export_name);
+        s->export_name = qemu_strdup(export_name);
     }
 
     /* extract the host_spec - fail if it's not nbd:... */
@@ -164,161 +84,25 @@ static int nbd_config(BDRVNBDState *s, const char *filename)
 
     /* are we a UNIX or TCP socket? */
     if (strstart(host_spec, "unix:", &unixpath)) {
-        s->is_unix = true;
-        s->host_spec = g_strdup(unixpath);
+        if (unixpath[0] != '/') { /* We demand  an absolute path*/
+            goto out;
+        }
+        s->host_spec = qemu_strdup(unixpath);
     } else {
-        s->is_unix = false;
-        s->host_spec = g_strdup(host_spec);
+        s->host_spec = qemu_strdup(host_spec);
     }
 
     err = 0;
 
 out:
-    g_free(file);
+    qemu_free(file);
     if (err != 0) {
-        g_free(s->export_name);
-        g_free(s->host_spec);
+        qemu_free(s->export_name);
+        qemu_free(s->host_spec);
     }
     return err;
 }
 
-static void nbd_coroutine_start(BDRVNBDState *s, struct nbd_request *request)
-{
-    int i;
-
-    /* Poor man semaphore.  The free_sema is locked when no other request
-     * can be accepted, and unlocked after receiving one reply.  */
-    if (s->in_flight >= MAX_NBD_REQUESTS - 1) {
-        qemu_co_mutex_lock(&s->free_sema);
-        assert(s->in_flight < MAX_NBD_REQUESTS);
-    }
-    s->in_flight++;
-
-    for (i = 0; i < MAX_NBD_REQUESTS; i++) {
-        if (s->recv_coroutine[i] == NULL) {
-            s->recv_coroutine[i] = qemu_coroutine_self();
-            break;
-        }
-    }
-
-    assert(i < MAX_NBD_REQUESTS);
-    request->handle = INDEX_TO_HANDLE(s, i);
-}
-
-static int nbd_have_request(void *opaque)
-{
-    BDRVNBDState *s = opaque;
-
-    return s->in_flight > 0;
-}
-
-static void nbd_reply_ready(void *opaque)
-{
-    BDRVNBDState *s = opaque;
-    uint64_t i;
-    int ret;
-
-    if (s->reply.handle == 0) {
-        /* No reply already in flight.  Fetch a header.  It is possible
-         * that another thread has done the same thing in parallel, so
-         * the socket is not readable anymore.
-         */
-        ret = nbd_receive_reply(s->sock, &s->reply);
-        if (ret == -EAGAIN) {
-            return;
-        }
-        if (ret < 0) {
-            s->reply.handle = 0;
-            goto fail;
-        }
-    }
-
-    /* There's no need for a mutex on the receive side, because the
-     * handler acts as a synchronization point and ensures that only
-     * one coroutine is called until the reply finishes.  */
-    i = HANDLE_TO_INDEX(s, s->reply.handle);
-    if (i >= MAX_NBD_REQUESTS) {
-        goto fail;
-    }
-
-    if (s->recv_coroutine[i]) {
-        qemu_coroutine_enter(s->recv_coroutine[i], NULL);
-        return;
-    }
-
-fail:
-    for (i = 0; i < MAX_NBD_REQUESTS; i++) {
-        if (s->recv_coroutine[i]) {
-            qemu_coroutine_enter(s->recv_coroutine[i], NULL);
-        }
-    }
-}
-
-static void nbd_restart_write(void *opaque)
-{
-    BDRVNBDState *s = opaque;
-    qemu_coroutine_enter(s->send_coroutine, NULL);
-}
-
-static int nbd_co_send_request(BDRVNBDState *s, struct nbd_request *request,
-                               QEMUIOVector *qiov, int offset)
-{
-    int rc, ret;
-
-    qemu_co_mutex_lock(&s->send_mutex);
-    s->send_coroutine = qemu_coroutine_self();
-    qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, nbd_restart_write,
-                            nbd_have_request, s);
-    rc = nbd_send_request(s->sock, request);
-    if (rc >= 0 && qiov) {
-        ret = qemu_co_sendv(s->sock, qiov->iov, qiov->niov,
-                            offset, request->len);
-        if (ret != request->len) {
-            return -EIO;
-        }
-    }
-    qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, NULL,
-                            nbd_have_request, s);
-    s->send_coroutine = NULL;
-    qemu_co_mutex_unlock(&s->send_mutex);
-    return rc;
-}
-
-static void nbd_co_receive_reply(BDRVNBDState *s, struct nbd_request *request,
-                                 struct nbd_reply *reply,
-                                 QEMUIOVector *qiov, int offset)
-{
-    int ret;
-
-    /* Wait until we're woken up by the read handler.  TODO: perhaps
-     * peek at the next reply and avoid yielding if it's ours?  */
-    qemu_coroutine_yield();
-    *reply = s->reply;
-    if (reply->handle != request->handle) {
-        reply->error = EIO;
-    } else {
-        if (qiov && reply->error == 0) {
-            ret = qemu_co_recvv(s->sock, qiov->iov, qiov->niov,
-                                offset, request->len);
-            if (ret != request->len) {
-                reply->error = EIO;
-            }
-        }
-
-        /* Tell the read handler to read another header.  */
-        s->reply.handle = 0;
-    }
-}
-
-static void nbd_coroutine_end(BDRVNBDState *s, struct nbd_request *request)
-{
-    int i = HANDLE_TO_INDEX(s, request->handle);
-    s->recv_coroutine[i] = NULL;
-    if (s->in_flight-- == MAX_NBD_REQUESTS) {
-        qemu_co_mutex_unlock(&s->free_sema);
-    }
-}
-
 static int nbd_establish_connection(BlockDriverState *bs)
 {
     BDRVNBDState *s = bs->opaque;
@@ -326,33 +110,31 @@ static int nbd_establish_connection(BlockDriverState *bs)
     int ret;
     off_t size;
     size_t blocksize;
+    uint32_t nbdflags;
 
-    if (s->is_unix) {
+    if (s->host_spec[0] == '/') {
         sock = unix_socket_outgoing(s->host_spec);
     } else {
         sock = tcp_socket_outgoing_spec(s->host_spec);
     }
 
     /* Failed to establish connection */
-    if (sock < 0) {
+    if (sock == -1) {
         logout("Failed to establish connection to NBD server\n");
         return -errno;
     }
 
     /* NBD handshake */
-    ret = nbd_receive_negotiate(sock, s->export_name, &s->nbdflags, &size,
+    ret = nbd_receive_negotiate(sock, s->export_name, &nbdflags, &size,
                                 &blocksize);
-    if (ret < 0) {
+    if (ret == -1) {
         logout("Failed to negotiate with the NBD server\n");
         closesocket(sock);
-        return ret;
+        return -errno;
     }
 
-    /* Now that we're connected, set the socket to be non-blocking and
-     * kick the reply mechanism.  */
+    /* Now that we're connected, set the socket to be non-blocking */
     socket_set_nonblock(sock);
-    qemu_aio_set_fd_handler(sock, nbd_reply_ready, NULL,
-                            nbd_have_request, s);
 
     s->sock = sock;
     s->size = size;
@@ -368,11 +150,11 @@ static void nbd_teardown_connection(BlockDriverState *bs)
     struct nbd_request request;
 
     request.type = NBD_CMD_DISC;
+    request.handle = (uint64_t)(intptr_t)bs;
     request.from = 0;
     request.len = 0;
     nbd_send_request(s->sock, &request);
 
-    qemu_aio_set_fd_handler(s->sock, NULL, NULL, NULL, NULL);
     closesocket(s->sock);
 }
 
@@ -381,11 +163,8 @@ static int nbd_open(BlockDriverState *bs, const char* filename, int flags)
     BDRVNBDState *s = bs->opaque;
     int result;
 
-    qemu_co_mutex_init(&s->send_mutex);
-    qemu_co_mutex_init(&s->free_sema);
-
     /* Pop the config into our state object. Exit if invalid. */
-    result = nbd_config(s, filename);
+    result = nbd_config(s, filename, flags);
     if (result != 0) {
         return result;
     }
@@ -398,158 +177,71 @@ static int nbd_open(BlockDriverState *bs, const char* filename, int flags)
     return result;
 }
 
-static int nbd_co_readv_1(BlockDriverState *bs, int64_t sector_num,
-                          int nb_sectors, QEMUIOVector *qiov,
-                          int offset)
+static int nbd_read(BlockDriverState *bs, int64_t sector_num,
+                    uint8_t *buf, int nb_sectors)
 {
     BDRVNBDState *s = bs->opaque;
     struct nbd_request request;
     struct nbd_reply reply;
-    ssize_t ret;
 
     request.type = NBD_CMD_READ;
-    request.from = sector_num * 512;
-    request.len = nb_sectors * 512;
-
-    nbd_coroutine_start(s, &request);
-    ret = nbd_co_send_request(s, &request, NULL, 0);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(s, &request, &reply, qiov, offset);
-    }
-    nbd_coroutine_end(s, &request);
-    return -reply.error;
-
-}
-
-static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num,
-                           int nb_sectors, QEMUIOVector *qiov,
-                           int offset)
-{
-    BDRVNBDState *s = bs->opaque;
-    struct nbd_request request;
-    struct nbd_reply reply;
-    ssize_t ret;
-
-    request.type = NBD_CMD_WRITE;
-    if (!bdrv_enable_write_cache(bs) && (s->nbdflags & NBD_FLAG_SEND_FUA)) {
-        request.type |= NBD_CMD_FLAG_FUA;
-    }
-
-    request.from = sector_num * 512;
-    request.len = nb_sectors * 512;
-
-    nbd_coroutine_start(s, &request);
-    ret = nbd_co_send_request(s, &request, qiov, offset);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(s, &request, &reply, NULL, 0);
-    }
-    nbd_coroutine_end(s, &request);
-    return -reply.error;
-}
-
-/* qemu-nbd has a limit of slightly less than 1M per request.  Try to
- * remain aligned to 4K. */
-#define NBD_MAX_SECTORS 2040
-
-static int nbd_co_readv(BlockDriverState *bs, int64_t sector_num,
-                        int nb_sectors, QEMUIOVector *qiov)
-{
-    int offset = 0;
-    int ret;
-    while (nb_sectors > NBD_MAX_SECTORS) {
-        ret = nbd_co_readv_1(bs, sector_num, NBD_MAX_SECTORS, qiov, offset);
-        if (ret < 0) {
-            return ret;
-        }
-        offset += NBD_MAX_SECTORS * 512;
-        sector_num += NBD_MAX_SECTORS;
-        nb_sectors -= NBD_MAX_SECTORS;
-    }
-    return nbd_co_readv_1(bs, sector_num, nb_sectors, qiov, offset);
-}
-
-static int nbd_co_writev(BlockDriverState *bs, int64_t sector_num,
-                         int nb_sectors, QEMUIOVector *qiov)
-{
-    int offset = 0;
-    int ret;
-    while (nb_sectors > NBD_MAX_SECTORS) {
-        ret = nbd_co_writev_1(bs, sector_num, NBD_MAX_SECTORS, qiov, offset);
-        if (ret < 0) {
-            return ret;
-        }
-        offset += NBD_MAX_SECTORS * 512;
-        sector_num += NBD_MAX_SECTORS;
-        nb_sectors -= NBD_MAX_SECTORS;
-    }
-    return nbd_co_writev_1(bs, sector_num, nb_sectors, qiov, offset);
-}
-
-static int nbd_co_flush(BlockDriverState *bs)
-{
-    BDRVNBDState *s = bs->opaque;
-    struct nbd_request request;
-    struct nbd_reply reply;
-    ssize_t ret;
-
-    if (!(s->nbdflags & NBD_FLAG_SEND_FLUSH)) {
-        return 0;
-    }
-
-    request.type = NBD_CMD_FLUSH;
-    if (s->nbdflags & NBD_FLAG_SEND_FUA) {
-        request.type |= NBD_CMD_FLAG_FUA;
-    }
-
-    request.from = 0;
-    request.len = 0;
-
-    nbd_coroutine_start(s, &request);
-    ret = nbd_co_send_request(s, &request, NULL, 0);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(s, &request, &reply, NULL, 0);
-    }
-    nbd_coroutine_end(s, &request);
-    return -reply.error;
-}
-
-static int nbd_co_discard(BlockDriverState *bs, int64_t sector_num,
-                          int nb_sectors)
-{
-    BDRVNBDState *s = bs->opaque;
-    struct nbd_request request;
-    struct nbd_reply reply;
-    ssize_t ret;
-
-    if (!(s->nbdflags & NBD_FLAG_SEND_TRIM)) {
-        return 0;
-    }
-    request.type = NBD_CMD_TRIM;
+    request.handle = (uint64_t)(intptr_t)bs;
     request.from = sector_num * 512;;
     request.len = nb_sectors * 512;
 
-    nbd_coroutine_start(s, &request);
-    ret = nbd_co_send_request(s, &request, NULL, 0);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(s, &request, &reply, NULL, 0);
-    }
-    nbd_coroutine_end(s, &request);
-    return -reply.error;
+    if (nbd_send_request(s->sock, &request) == -1)
+        return -errno;
+
+    if (nbd_receive_reply(s->sock, &reply) == -1)
+        return -errno;
+
+    if (reply.error !=0)
+        return -reply.error;
+
+    if (reply.handle != request.handle)
+        return -EIO;
+
+    if (nbd_wr_sync(s->sock, buf, request.len, 1) != request.len)
+        return -EIO;
+
+    return 0;
+}
+
+static int nbd_write(BlockDriverState *bs, int64_t sector_num,
+                     const uint8_t *buf, int nb_sectors)
+{
+    BDRVNBDState *s = bs->opaque;
+    struct nbd_request request;
+    struct nbd_reply reply;
+
+    request.type = NBD_CMD_WRITE;
+    request.handle = (uint64_t)(intptr_t)bs;
+    request.from = sector_num * 512;;
+    request.len = nb_sectors * 512;
+
+    if (nbd_send_request(s->sock, &request) == -1)
+        return -errno;
+
+    if (nbd_wr_sync(s->sock, (uint8_t*)buf, request.len, 0) != request.len)
+        return -EIO;
+
+    if (nbd_receive_reply(s->sock, &reply) == -1)
+        return -errno;
+
+    if (reply.error !=0)
+        return -reply.error;
+
+    if (reply.handle != request.handle)
+        return -EIO;
+
+    return 0;
 }
 
 static void nbd_close(BlockDriverState *bs)
 {
     BDRVNBDState *s = bs->opaque;
-    g_free(s->export_name);
-    g_free(s->host_spec);
+    qemu_free(s->export_name);
+    qemu_free(s->host_spec);
 
     nbd_teardown_connection(bs);
 }
@@ -562,49 +254,19 @@ static int64_t nbd_getlength(BlockDriverState *bs)
 }
 
 static BlockDriver bdrv_nbd = {
-    .format_name         = "nbd",
-    .protocol_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,
-};
-
-static BlockDriver bdrv_nbd_tcp = {
-    .format_name         = "nbd",
-    .protocol_name       = "nbd+tcp",
-    .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,
-};
-
-static BlockDriver bdrv_nbd_unix = {
-    .format_name         = "nbd",
-    .protocol_name       = "nbd+unix",
-    .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,
+    .format_name	= "nbd",
+    .instance_size	= sizeof(BDRVNBDState),
+    .bdrv_file_open	= nbd_open,
+    .bdrv_read		= nbd_read,
+    .bdrv_write		= nbd_write,
+    .bdrv_close		= nbd_close,
+    .bdrv_getlength	= nbd_getlength,
+    .protocol_name	= "nbd",
 };
 
 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

@@ -43,10 +43,9 @@ struct parallels_header {
     uint32_t catalog_entries;
     uint32_t nb_sectors;
     char padding[24];
-} QEMU_PACKED;
+} __attribute__((packed));
 
 typedef struct BDRVParallelsState {
-    CoMutex lock;
 
     uint32_t *catalog_bitmap;
     int catalog_size;
@@ -89,18 +88,17 @@ static int parallels_open(BlockDriverState *bs, int flags)
     s->tracks = le32_to_cpu(ph.tracks);
 
     s->catalog_size = le32_to_cpu(ph.catalog_entries);
-    s->catalog_bitmap = g_malloc(s->catalog_size * 4);
+    s->catalog_bitmap = qemu_malloc(s->catalog_size * 4);
     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:
     if (s->catalog_bitmap)
-	g_free(s->catalog_bitmap);
+	qemu_free(s->catalog_bitmap);
     return -1;
 }
 
@@ -136,21 +134,10 @@ static int parallels_read(BlockDriverState *bs, int64_t sector_num,
     return 0;
 }
 
-static coroutine_fn int parallels_co_read(BlockDriverState *bs, int64_t sector_num,
-                                          uint8_t *buf, int nb_sectors)
-{
-    int ret;
-    BDRVParallelsState *s = bs->opaque;
-    qemu_co_mutex_lock(&s->lock);
-    ret = parallels_read(bs, sector_num, buf, nb_sectors);
-    qemu_co_mutex_unlock(&s->lock);
-    return ret;
-}
-
 static void parallels_close(BlockDriverState *bs)
 {
     BDRVParallelsState *s = bs->opaque;
-    g_free(s->catalog_bitmap);
+    qemu_free(s->catalog_bitmap);
 }
 
 static BlockDriver bdrv_parallels = {
@@ -158,7 +145,7 @@ static BlockDriver bdrv_parallels = {
     .instance_size	= sizeof(BDRVParallelsState),
     .bdrv_probe		= parallels_probe,
     .bdrv_open		= parallels_open,
-    .bdrv_read          = parallels_co_read,
+    .bdrv_read		= parallels_read,
     .bdrv_close		= parallels_close,
 };
 

block/qcow.c

@@ -26,7 +26,6 @@
 #include "module.h"
 #include <zlib.h>
 #include "aes.h"
-#include "migration.h"
 
 /**************************************************************/
 /* QEMU COW block driver with compression and encryption support */
@@ -74,8 +73,6 @@ typedef struct BDRVQcowState {
     uint32_t crypt_method_header;
     AES_KEY aes_encrypt_key;
     AES_KEY aes_decrypt_key;
-    CoMutex lock;
-    Error *migration_blocker;
 } BDRVQcowState;
 
 static int decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset);
@@ -95,13 +92,11 @@ static int qcow_probe(const uint8_t *buf, int buf_size, const char *filename)
 static int qcow_open(BlockDriverState *bs, int flags)
 {
     BDRVQcowState *s = bs->opaque;
-    int len, i, shift, ret;
+    int len, i, shift;
     QCowHeader header;
 
-    ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
-    if (ret < 0) {
+    if (bdrv_pread(bs->file, 0, &header, sizeof(header)) != sizeof(header))
         goto fail;
-    }
     be32_to_cpus(&header.magic);
     be32_to_cpus(&header.version);
     be64_to_cpus(&header.backing_file_offset);
@@ -111,31 +106,15 @@ static int qcow_open(BlockDriverState *bs, int flags)
     be32_to_cpus(&header.crypt_method);
     be64_to_cpus(&header.l1_table_offset);
 
-    if (header.magic != QCOW_MAGIC) {
-        ret = -EINVAL;
+    if (header.magic != QCOW_MAGIC || header.version != QCOW_VERSION)
         goto fail;
-    }
-    if (header.version != QCOW_VERSION) {
-        char version[64];
-        snprintf(version, sizeof(version), "QCOW version %d", header.version);
-        qerror_report(QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
-            bs->device_name, "qcow", version);
-        ret = -ENOTSUP;
+    if (header.size <= 1 || header.cluster_bits < 9)
         goto fail;
-    }
-
-    if (header.size <= 1 || header.cluster_bits < 9) {
-        ret = -EINVAL;
+    if (header.crypt_method > QCOW_CRYPT_AES)
         goto fail;
-    }
-    if (header.crypt_method > QCOW_CRYPT_AES) {
-        ret = -EINVAL;
-        goto fail;
-    }
     s->crypt_method_header = header.crypt_method;
-    if (s->crypt_method_header) {
+    if (s->crypt_method_header)
         bs->encrypted = 1;
-    }
     s->cluster_bits = header.cluster_bits;
     s->cluster_size = 1 << s->cluster_bits;
     s->cluster_sectors = 1 << (s->cluster_bits - 9);
@@ -149,61 +128,44 @@ static int qcow_open(BlockDriverState *bs, int flags)
     s->l1_size = (header.size + (1LL << shift) - 1) >> shift;
 
     s->l1_table_offset = header.l1_table_offset;
-    s->l1_table = g_malloc(s->l1_size * sizeof(uint64_t));
-
-    ret = bdrv_pread(bs->file, s->l1_table_offset, s->l1_table,
-               s->l1_size * sizeof(uint64_t));
-    if (ret < 0) {
+    s->l1_table = qemu_malloc(s->l1_size * sizeof(uint64_t));
+    if (!s->l1_table)
+        goto fail;
+    if (bdrv_pread(bs->file, s->l1_table_offset, s->l1_table, s->l1_size * sizeof(uint64_t)) !=
+        s->l1_size * sizeof(uint64_t))
         goto fail;
-    }
-
     for(i = 0;i < s->l1_size; i++) {
         be64_to_cpus(&s->l1_table[i]);
     }
     /* alloc L2 cache */
-    s->l2_cache = g_malloc(s->l2_size * L2_CACHE_SIZE * sizeof(uint64_t));
-    s->cluster_cache = g_malloc(s->cluster_size);
-    s->cluster_data = g_malloc(s->cluster_size);
+    s->l2_cache = qemu_malloc(s->l2_size * L2_CACHE_SIZE * sizeof(uint64_t));
+    if (!s->l2_cache)
+        goto fail;
+    s->cluster_cache = qemu_malloc(s->cluster_size);
+    if (!s->cluster_cache)
+        goto fail;
+    s->cluster_data = qemu_malloc(s->cluster_size);
+    if (!s->cluster_data)
+        goto fail;
     s->cluster_cache_offset = -1;
 
     /* read the backing file name */
     if (header.backing_file_offset != 0) {
         len = header.backing_file_size;
-        if (len > 1023) {
+        if (len > 1023)
             len = 1023;
-        }
-        ret = bdrv_pread(bs->file, header.backing_file_offset,
-                   bs->backing_file, len);
-        if (ret < 0) {
+        if (bdrv_pread(bs->file, header.backing_file_offset, bs->backing_file, len) != len)
             goto fail;
-        }
         bs->backing_file[len] = '\0';
     }
-
-    /* Disable migration when qcow images are used */
-    error_set(&s->migration_blocker,
-              QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
-              "qcow", bs->device_name, "live migration");
-    migrate_add_blocker(s->migration_blocker);
-
-    qemu_co_mutex_init(&s->lock);
     return 0;
 
  fail:
-    g_free(s->l1_table);
-    g_free(s->l2_cache);
-    g_free(s->cluster_cache);
-    g_free(s->cluster_data);
-    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;
+    qemu_free(s->l1_table);
+    qemu_free(s->l2_cache);
+    qemu_free(s->cluster_cache);
+    qemu_free(s->cluster_data);
+    return -1;
 }
 
 static int qcow_set_key(BlockDriverState *bs, const char *key)
@@ -227,6 +189,24 @@ static int qcow_set_key(BlockDriverState *bs, const char *key)
         return -1;
     if (AES_set_decrypt_key(keybuf, 128, &s->aes_decrypt_key) != 0)
         return -1;
+#if 0
+    /* test */
+    {
+        uint8_t in[16];
+        uint8_t out[16];
+        uint8_t tmp[16];
+        for(i=0;i<16;i++)
+            in[i] = i;
+        AES_encrypt(in, tmp, &s->aes_encrypt_key);
+        AES_decrypt(tmp, out, &s->aes_decrypt_key);
+        for(i = 0; i < 16; i++)
+            printf(" %02x", tmp[i]);
+        printf("\n");
+        for(i = 0; i < 16; i++)
+            printf(" %02x", out[i]);
+        printf("\n");
+    }
+#endif
     return 0;
 }
 
@@ -395,16 +375,14 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
     return cluster_offset;
 }
 
-static int coroutine_fn qcow_co_is_allocated(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *pnum)
+static int qcow_is_allocated(BlockDriverState *bs, int64_t sector_num,
+                             int nb_sectors, int *pnum)
 {
     BDRVQcowState *s = bs->opaque;
     int index_in_cluster, n;
     uint64_t cluster_offset;
 
-    qemu_co_mutex_lock(&s->lock);
     cluster_offset = get_cluster_offset(bs, sector_num << 9, 0, 0, 0, 0);
-    qemu_co_mutex_unlock(&s->lock);
     index_in_cluster = sector_num & (s->cluster_sectors - 1);
     n = s->cluster_sectors - index_in_cluster;
     if (n > nb_sectors)
@@ -462,205 +440,375 @@ static int decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
     return 0;
 }
 
-static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num,
-                         int nb_sectors, QEMUIOVector *qiov)
+#if 0
+
+static int qcow_read(BlockDriverState *bs, int64_t sector_num,
+                     uint8_t *buf, int nb_sectors)
 {
     BDRVQcowState *s = bs->opaque;
-    int index_in_cluster;
-    int ret = 0, n;
+    int ret, index_in_cluster, n;
     uint64_t cluster_offset;
-    struct iovec hd_iov;
-    QEMUIOVector hd_qiov;
-    uint8_t *buf;
-    void *orig_buf;
 
-    if (qiov->niov > 1) {
-        buf = orig_buf = qemu_blockalign(bs, qiov->size);
-    } else {
-        orig_buf = NULL;
-        buf = (uint8_t *)qiov->iov->iov_base;
-    }
-
-    qemu_co_mutex_lock(&s->lock);
-
-    while (nb_sectors != 0) {
-        /* prepare next request */
-        cluster_offset = get_cluster_offset(bs, sector_num << 9,
-                                                 0, 0, 0, 0);
+    while (nb_sectors > 0) {
+        cluster_offset = get_cluster_offset(bs, sector_num << 9, 0, 0, 0, 0);
         index_in_cluster = sector_num & (s->cluster_sectors - 1);
         n = s->cluster_sectors - index_in_cluster;
-        if (n > nb_sectors) {
+        if (n > nb_sectors)
             n = nb_sectors;
-        }
-
         if (!cluster_offset) {
             if (bs->backing_hd) {
                 /* read from the base image */
-                hd_iov.iov_base = (void *)buf;
-                hd_iov.iov_len = n * 512;
-                qemu_iovec_init_external(&hd_qiov, &hd_iov, 1);
-                qemu_co_mutex_unlock(&s->lock);
-                ret = bdrv_co_readv(bs->backing_hd, sector_num,
-                                    n, &hd_qiov);
-                qemu_co_mutex_lock(&s->lock);
-                if (ret < 0) {
-                    goto fail;
-                }
+                ret = bdrv_read(bs->backing_hd, sector_num, buf, n);
+                if (ret < 0)
+                    return -1;
             } else {
-                /* Note: in this case, no need to wait */
                 memset(buf, 0, 512 * n);
             }
         } else if (cluster_offset & QCOW_OFLAG_COMPRESSED) {
-            /* add AIO support for compressed blocks ? */
-            if (decompress_cluster(bs, cluster_offset) < 0) {
-                goto fail;
-            }
-            memcpy(buf,
-                   s->cluster_cache + index_in_cluster * 512, 512 * n);
+            if (decompress_cluster(bs, cluster_offset) < 0)
+                return -1;
+            memcpy(buf, s->cluster_cache + index_in_cluster * 512, 512 * n);
         } else {
-            if ((cluster_offset & 511) != 0) {
-                goto fail;
-            }
-            hd_iov.iov_base = (void *)buf;
-            hd_iov.iov_len = n * 512;
-            qemu_iovec_init_external(&hd_qiov, &hd_iov, 1);
-            qemu_co_mutex_unlock(&s->lock);
-            ret = bdrv_co_readv(bs->file,
-                                (cluster_offset >> 9) + index_in_cluster,
-                                n, &hd_qiov);
-            qemu_co_mutex_lock(&s->lock);
-            if (ret < 0) {
-                break;
-            }
+            ret = bdrv_pread(bs->file, cluster_offset + index_in_cluster * 512, buf, n * 512);
+            if (ret != n * 512)
+                return -1;
             if (s->crypt_method) {
-                encrypt_sectors(s, sector_num, buf, buf,
-                                n, 0,
+                encrypt_sectors(s, sector_num, buf, buf, n, 0,
                                 &s->aes_decrypt_key);
             }
         }
-        ret = 0;
-
         nb_sectors -= n;
         sector_num += n;
         buf += n * 512;
     }
+    return 0;
+}
+#endif
 
-done:
-    qemu_co_mutex_unlock(&s->lock);
+typedef struct QCowAIOCB {
+    BlockDriverAIOCB common;
+    int64_t sector_num;
+    QEMUIOVector *qiov;
+    uint8_t *buf;
+    void *orig_buf;
+    int nb_sectors;
+    int n;
+    uint64_t cluster_offset;
+    uint8_t *cluster_data;
+    struct iovec hd_iov;
+    bool is_write;
+    QEMUBH *bh;
+    QEMUIOVector hd_qiov;
+    BlockDriverAIOCB *hd_aiocb;
+} QCowAIOCB;
 
-    if (qiov->niov > 1) {
-        qemu_iovec_from_buf(qiov, 0, orig_buf, qiov->size);
-        qemu_vfree(orig_buf);
-    }
-
-    return ret;
-
-fail:
-    ret = -EIO;
-    goto done;
+static void qcow_aio_cancel(BlockDriverAIOCB *blockacb)
+{
+    QCowAIOCB *acb = container_of(blockacb, QCowAIOCB, common);
+    if (acb->hd_aiocb)
+        bdrv_aio_cancel(acb->hd_aiocb);
+    qemu_aio_release(acb);
 }
 
-static coroutine_fn int qcow_co_writev(BlockDriverState *bs, int64_t sector_num,
-                          int nb_sectors, QEMUIOVector *qiov)
+static AIOPool qcow_aio_pool = {
+    .aiocb_size         = sizeof(QCowAIOCB),
+    .cancel             = qcow_aio_cancel,
+};
+
+static QCowAIOCB *qcow_aio_setup(BlockDriverState *bs,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockDriverCompletionFunc *cb, void *opaque, int is_write)
 {
+    QCowAIOCB *acb;
+
+    acb = qemu_aio_get(&qcow_aio_pool, bs, cb, opaque);
+    if (!acb)
+        return NULL;
+    acb->hd_aiocb = NULL;
+    acb->sector_num = sector_num;
+    acb->qiov = qiov;
+    acb->is_write = is_write;
+
+    if (qiov->niov > 1) {
+        acb->buf = acb->orig_buf = qemu_blockalign(bs, qiov->size);
+        if (is_write)
+            qemu_iovec_to_buffer(qiov, acb->buf);
+    } else {
+        acb->buf = (uint8_t *)qiov->iov->iov_base;
+    }
+    acb->nb_sectors = nb_sectors;
+    acb->n = 0;
+    acb->cluster_offset = 0;
+    return acb;
+}
+
+static void qcow_aio_read_cb(void *opaque, int ret);
+static void qcow_aio_write_cb(void *opaque, int ret);
+
+static void qcow_aio_rw_bh(void *opaque)
+{
+    QCowAIOCB *acb = opaque;
+    qemu_bh_delete(acb->bh);
+    acb->bh = NULL;
+
+    if (acb->is_write) {
+        qcow_aio_write_cb(opaque, 0);
+    } else {
+        qcow_aio_read_cb(opaque, 0);
+    }
+}
+
+static int qcow_schedule_bh(QEMUBHFunc *cb, QCowAIOCB *acb)
+{
+    if (acb->bh) {
+        return -EIO;
+    }
+
+    acb->bh = qemu_bh_new(cb, acb);
+    if (!acb->bh) {
+        return -EIO;
+    }
+
+    qemu_bh_schedule(acb->bh);
+
+    return 0;
+}
+
+static void qcow_aio_read_cb(void *opaque, int ret)
+{
+    QCowAIOCB *acb = opaque;
+    BlockDriverState *bs = acb->common.bs;
+    BDRVQcowState *s = bs->opaque;
+    int index_in_cluster;
+
+    acb->hd_aiocb = NULL;
+    if (ret < 0)
+        goto done;
+
+ redo:
+    /* post process the read buffer */
+    if (!acb->cluster_offset) {
+        /* nothing to do */
+    } else if (acb->cluster_offset & QCOW_OFLAG_COMPRESSED) {
+        /* nothing to do */
+    } else {
+        if (s->crypt_method) {
+            encrypt_sectors(s, acb->sector_num, acb->buf, acb->buf,
+                            acb->n, 0,
+                            &s->aes_decrypt_key);
+        }
+    }
+
+    acb->nb_sectors -= acb->n;
+    acb->sector_num += acb->n;
+    acb->buf += acb->n * 512;
+
+    if (acb->nb_sectors == 0) {
+        /* request completed */
+        ret = 0;
+        goto done;
+    }
+
+    /* prepare next AIO request */
+    acb->cluster_offset = get_cluster_offset(bs, acb->sector_num << 9,
+                                             0, 0, 0, 0);
+    index_in_cluster = acb->sector_num & (s->cluster_sectors - 1);
+    acb->n = s->cluster_sectors - index_in_cluster;
+    if (acb->n > acb->nb_sectors)
+        acb->n = acb->nb_sectors;
+
+    if (!acb->cluster_offset) {
+        if (bs->backing_hd) {
+            /* read from the base image */
+            acb->hd_iov.iov_base = (void *)acb->buf;
+            acb->hd_iov.iov_len = acb->n * 512;
+            qemu_iovec_init_external(&acb->hd_qiov, &acb->hd_iov, 1);
+            acb->hd_aiocb = bdrv_aio_readv(bs->backing_hd, acb->sector_num,
+                &acb->hd_qiov, acb->n, qcow_aio_read_cb, acb);
+            if (acb->hd_aiocb == NULL) {
+                ret = -EIO;
+                goto done;
+            }
+        } else {
+            /* Note: in this case, no need to wait */
+            memset(acb->buf, 0, 512 * acb->n);
+            goto redo;
+        }
+    } else if (acb->cluster_offset & QCOW_OFLAG_COMPRESSED) {
+        /* add AIO support for compressed blocks ? */
+        if (decompress_cluster(bs, acb->cluster_offset) < 0) {
+            ret = -EIO;
+            goto done;
+        }
+        memcpy(acb->buf,
+               s->cluster_cache + index_in_cluster * 512, 512 * acb->n);
+        goto redo;
+    } else {
+        if ((acb->cluster_offset & 511) != 0) {
+            ret = -EIO;
+            goto done;
+        }
+        acb->hd_iov.iov_base = (void *)acb->buf;
+        acb->hd_iov.iov_len = acb->n * 512;
+        qemu_iovec_init_external(&acb->hd_qiov, &acb->hd_iov, 1);
+        acb->hd_aiocb = bdrv_aio_readv(bs->file,
+                            (acb->cluster_offset >> 9) + index_in_cluster,
+                            &acb->hd_qiov, acb->n, qcow_aio_read_cb, acb);
+        if (acb->hd_aiocb == NULL) {
+            ret = -EIO;
+            goto done;
+        }
+    }
+
+    return;
+
+done:
+    if (acb->qiov->niov > 1) {
+        qemu_iovec_from_buffer(acb->qiov, acb->orig_buf, acb->qiov->size);
+        qemu_vfree(acb->orig_buf);
+    }
+    acb->common.cb(acb->common.opaque, ret);
+    qemu_aio_release(acb);
+}
+
+static BlockDriverAIOCB *qcow_aio_readv(BlockDriverState *bs,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockDriverCompletionFunc *cb, void *opaque)
+{
+    QCowAIOCB *acb;
+    int ret;
+
+    acb = qcow_aio_setup(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
+    if (!acb)
+        return NULL;
+
+    ret = qcow_schedule_bh(qcow_aio_rw_bh, acb);
+    if (ret < 0) {
+        if (acb->qiov->niov > 1) {
+            qemu_vfree(acb->orig_buf);
+        }
+        qemu_aio_release(acb);
+        return NULL;
+    }
+
+    return &acb->common;
+}
+
+static void qcow_aio_write_cb(void *opaque, int ret)
+{
+    QCowAIOCB *acb = opaque;
+    BlockDriverState *bs = acb->common.bs;
     BDRVQcowState *s = bs->opaque;
     int index_in_cluster;
     uint64_t cluster_offset;
     const uint8_t *src_buf;
-    int ret = 0, n;
-    uint8_t *cluster_data = NULL;
-    struct iovec hd_iov;
-    QEMUIOVector hd_qiov;
-    uint8_t *buf;
-    void *orig_buf;
+
+    acb->hd_aiocb = NULL;
+
+    if (ret < 0)
+        goto done;
+
+    acb->nb_sectors -= acb->n;
+    acb->sector_num += acb->n;
+    acb->buf += acb->n * 512;
+
+    if (acb->nb_sectors == 0) {
+        /* request completed */
+        ret = 0;
+        goto done;
+    }
+
+    index_in_cluster = acb->sector_num & (s->cluster_sectors - 1);
+    acb->n = s->cluster_sectors - index_in_cluster;
+    if (acb->n > acb->nb_sectors)
+        acb->n = acb->nb_sectors;
+    cluster_offset = get_cluster_offset(bs, acb->sector_num << 9, 1, 0,
+                                        index_in_cluster,
+                                        index_in_cluster + acb->n);
+    if (!cluster_offset || (cluster_offset & 511) != 0) {
+        ret = -EIO;
+        goto done;
+    }
+    if (s->crypt_method) {
+        if (!acb->cluster_data) {
+            acb->cluster_data = qemu_mallocz(s->cluster_size);
+            if (!acb->cluster_data) {
+                ret = -ENOMEM;
+                goto done;
+            }
+        }
+        encrypt_sectors(s, acb->sector_num, acb->cluster_data, acb->buf,
+                        acb->n, 1, &s->aes_encrypt_key);
+        src_buf = acb->cluster_data;
+    } else {
+        src_buf = acb->buf;
+    }
+
+    acb->hd_iov.iov_base = (void *)src_buf;
+    acb->hd_iov.iov_len = acb->n * 512;
+    qemu_iovec_init_external(&acb->hd_qiov, &acb->hd_iov, 1);
+    acb->hd_aiocb = bdrv_aio_writev(bs->file,
+                                    (cluster_offset >> 9) + index_in_cluster,
+                                    &acb->hd_qiov, acb->n,
+                                    qcow_aio_write_cb, acb);
+    if (acb->hd_aiocb == NULL) {
+        ret = -EIO;
+        goto done;
+    }
+    return;
+
+done:
+    if (acb->qiov->niov > 1)
+        qemu_vfree(acb->orig_buf);
+    acb->common.cb(acb->common.opaque, ret);
+    qemu_aio_release(acb);
+}
+
+static BlockDriverAIOCB *qcow_aio_writev(BlockDriverState *bs,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockDriverCompletionFunc *cb, void *opaque)
+{
+    BDRVQcowState *s = bs->opaque;
+    QCowAIOCB *acb;
+    int ret;
 
     s->cluster_cache_offset = -1; /* disable compressed cache */
 
-    if (qiov->niov > 1) {
-        buf = orig_buf = qemu_blockalign(bs, qiov->size);
-        qemu_iovec_to_buf(qiov, 0, buf, qiov->size);
-    } else {
-        orig_buf = NULL;
-        buf = (uint8_t *)qiov->iov->iov_base;
+    acb = qcow_aio_setup(bs, sector_num, qiov, nb_sectors, cb, opaque, 1);
+    if (!acb)
+        return NULL;
+
+
+    ret = qcow_schedule_bh(qcow_aio_rw_bh, acb);
+    if (ret < 0) {
+        if (acb->qiov->niov > 1) {
+            qemu_vfree(acb->orig_buf);
+        }
+        qemu_aio_release(acb);
+        return NULL;
     }
 
-    qemu_co_mutex_lock(&s->lock);
-
-    while (nb_sectors != 0) {
-
-        index_in_cluster = sector_num & (s->cluster_sectors - 1);
-        n = s->cluster_sectors - index_in_cluster;
-        if (n > nb_sectors) {
-            n = nb_sectors;
-        }
-        cluster_offset = get_cluster_offset(bs, sector_num << 9, 1, 0,
-                                            index_in_cluster,
-                                            index_in_cluster + n);
-        if (!cluster_offset || (cluster_offset & 511) != 0) {
-            ret = -EIO;
-            break;
-        }
-        if (s->crypt_method) {
-            if (!cluster_data) {
-                cluster_data = g_malloc0(s->cluster_size);
-            }
-            encrypt_sectors(s, sector_num, cluster_data, buf,
-                            n, 1, &s->aes_encrypt_key);
-            src_buf = cluster_data;
-        } else {
-            src_buf = buf;
-        }
-
-        hd_iov.iov_base = (void *)src_buf;
-        hd_iov.iov_len = n * 512;
-        qemu_iovec_init_external(&hd_qiov, &hd_iov, 1);
-        qemu_co_mutex_unlock(&s->lock);
-        ret = bdrv_co_writev(bs->file,
-                             (cluster_offset >> 9) + index_in_cluster,
-                             n, &hd_qiov);
-        qemu_co_mutex_lock(&s->lock);
-        if (ret < 0) {
-            break;
-        }
-        ret = 0;
-
-        nb_sectors -= n;
-        sector_num += n;
-        buf += n * 512;
-    }
-    qemu_co_mutex_unlock(&s->lock);
-
-    if (qiov->niov > 1) {
-        qemu_vfree(orig_buf);
-    }
-    g_free(cluster_data);
-
-    return ret;
+    return &acb->common;
 }
 
 static void qcow_close(BlockDriverState *bs)
 {
     BDRVQcowState *s = bs->opaque;
-
-    g_free(s->l1_table);
-    g_free(s->l2_cache);
-    g_free(s->cluster_cache);
-    g_free(s->cluster_data);
-
-    migrate_del_blocker(s->migration_blocker);
-    error_free(s->migration_blocker);
+    qemu_free(s->l1_table);
+    qemu_free(s->l2_cache);
+    qemu_free(s->cluster_cache);
+    qemu_free(s->cluster_data);
 }
 
 static int qcow_create(const char *filename, QEMUOptionParameter *options)
 {
-    int header_size, backing_filename_len, l1_size, shift, i;
+    int fd, header_size, backing_filename_len, l1_size, i, shift;
     QCowHeader header;
-    uint8_t *tmp;
+    uint64_t tmp;
     int64_t total_size = 0;
     const char *backing_file = NULL;
     int flags = 0;
     int ret;
-    BlockDriverState *qcow_bs;
 
     /* Read out options */
     while (options && options->name) {
@@ -674,21 +822,9 @@ static int qcow_create(const char *filename, QEMUOptionParameter *options)
         options++;
     }
 
-    ret = bdrv_create_file(filename, options);
-    if (ret < 0) {
-        return ret;
-    }
-
-    ret = bdrv_file_open(&qcow_bs, filename, BDRV_O_RDWR);
-    if (ret < 0) {
-        return ret;
-    }
-
-    ret = bdrv_truncate(qcow_bs, 0);
-    if (ret < 0) {
-        goto exit;
-    }
-
+    fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, 0644);
+    if (fd < 0)
+        return -errno;
     memset(&header, 0, sizeof(header));
     header.magic = cpu_to_be32(QCOW_MAGIC);
     header.version = cpu_to_be32(QCOW_VERSION);
@@ -724,34 +860,33 @@ static int qcow_create(const char *filename, QEMUOptionParameter *options)
     }
 
     /* write all the data */
-    ret = bdrv_pwrite(qcow_bs, 0, &header, sizeof(header));
+    ret = qemu_write_full(fd, &header, sizeof(header));
     if (ret != sizeof(header)) {
+        ret = -errno;
         goto exit;
     }
 
     if (backing_file) {
-        ret = bdrv_pwrite(qcow_bs, sizeof(header),
-            backing_file, backing_filename_len);
+        ret = qemu_write_full(fd, backing_file, backing_filename_len);
         if (ret != backing_filename_len) {
+            ret = -errno;
+            goto exit;
+        }
+
+    }
+    lseek(fd, header_size, SEEK_SET);
+    tmp = 0;
+    for(i = 0;i < l1_size; i++) {
+        ret = qemu_write_full(fd, &tmp, sizeof(tmp));
+        if (ret != sizeof(tmp)) {
+            ret = -errno;
             goto exit;
         }
     }
 
-    tmp = g_malloc0(BDRV_SECTOR_SIZE);
-    for (i = 0; i < ((sizeof(uint64_t)*l1_size + BDRV_SECTOR_SIZE - 1)/
-        BDRV_SECTOR_SIZE); i++) {
-        ret = bdrv_pwrite(qcow_bs, header_size +
-            BDRV_SECTOR_SIZE*i, tmp, BDRV_SECTOR_SIZE);
-        if (ret != BDRV_SECTOR_SIZE) {
-            g_free(tmp);
-            goto exit;
-        }
-    }
-
-    g_free(tmp);
     ret = 0;
 exit:
-    bdrv_delete(qcow_bs);
+    close(fd);
     return ret;
 }
 
@@ -790,7 +925,9 @@ static int qcow_write_compressed(BlockDriverState *bs, int64_t sector_num,
     if (nb_sectors != s->cluster_sectors)
         return -EINVAL;
 
-    out_buf = g_malloc(s->cluster_size + (s->cluster_size / 1000) + 128);
+    out_buf = qemu_malloc(s->cluster_size + (s->cluster_size / 1000) + 128);
+    if (!out_buf)
+        return -1;
 
     /* best compression, small window, no zlib header */
     memset(&strm, 0, sizeof(strm));
@@ -798,8 +935,8 @@ static int qcow_write_compressed(BlockDriverState *bs, int64_t sector_num,
                        Z_DEFLATED, -12,
                        9, Z_DEFAULT_STRATEGY);
     if (ret != 0) {
-        ret = -EINVAL;
-        goto fail;
+        qemu_free(out_buf);
+        return -1;
     }
 
     strm.avail_in = s->cluster_size;
@@ -809,9 +946,9 @@ static int qcow_write_compressed(BlockDriverState *bs, int64_t sector_num,
 
     ret = deflate(&strm, Z_FINISH);
     if (ret != Z_STREAM_END && ret != Z_OK) {
+        qemu_free(out_buf);
         deflateEnd(&strm);
-        ret = -EINVAL;
-        goto fail;
+        return -1;
     }
     out_len = strm.next_out - out_buf;
 
@@ -819,29 +956,30 @@ static int qcow_write_compressed(BlockDriverState *bs, int64_t sector_num,
 
     if (ret != Z_STREAM_END || out_len >= s->cluster_size) {
         /* could not compress: write normal cluster */
-        ret = bdrv_write(bs, sector_num, buf, s->cluster_sectors);
-        if (ret < 0) {
-            goto fail;
-        }
+        bdrv_write(bs, sector_num, buf, s->cluster_sectors);
     } else {
         cluster_offset = get_cluster_offset(bs, sector_num << 9, 2,
                                             out_len, 0, 0);
-        if (cluster_offset == 0) {
-            ret = -EIO;
-            goto fail;
-        }
-
         cluster_offset &= s->cluster_offset_mask;
-        ret = bdrv_pwrite(bs->file, cluster_offset, out_buf, out_len);
-        if (ret < 0) {
-            goto fail;
+        if (bdrv_pwrite(bs->file, cluster_offset, out_buf, out_len) != out_len) {
+            qemu_free(out_buf);
+            return -1;
         }
     }
 
-    ret = 0;
-fail:
-    g_free(out_buf);
-    return ret;
+    qemu_free(out_buf);
+    return 0;
+}
+
+static int qcow_flush(BlockDriverState *bs)
+{
+    return bdrv_flush(bs->file);
+}
+
+static BlockDriverAIOCB *qcow_aio_flush(BlockDriverState *bs,
+        BlockDriverCompletionFunc *cb, void *opaque)
+{
+    return bdrv_aio_flush(bs->file, cb, opaque);
 }
 
 static int qcow_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
@@ -877,17 +1015,16 @@ 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_co_readv          = qcow_co_readv,
-    .bdrv_co_writev         = qcow_co_writev,
-    .bdrv_co_is_allocated   = qcow_co_is_allocated,
-
-    .bdrv_set_key           = qcow_set_key,
-    .bdrv_make_empty        = qcow_make_empty,
-    .bdrv_write_compressed  = qcow_write_compressed,
-    .bdrv_get_info          = qcow_get_info,
+    .bdrv_flush		= qcow_flush,
+    .bdrv_is_allocated	= qcow_is_allocated,
+    .bdrv_set_key	= qcow_set_key,
+    .bdrv_make_empty	= qcow_make_empty,
+    .bdrv_aio_readv	= qcow_aio_readv,
+    .bdrv_aio_writev	= qcow_aio_writev,
+    .bdrv_aio_flush	= qcow_aio_flush,
+    .bdrv_write_compressed = qcow_write_compressed,
+    .bdrv_get_info	= qcow_get_info,
 
     .create_options = qcow_create_options,
 };

block/qcow2-cache.c

@@ -25,7 +25,6 @@
 #include "block_int.h"
 #include "qemu-common.h"
 #include "qcow2.h"
-#include "trace.h"
 
 typedef struct Qcow2CachedTable {
     void*   table;
@@ -40,17 +39,20 @@ 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;
     int i;
 
-    c = g_malloc0(sizeof(*c));
+    c = qemu_mallocz(sizeof(*c));
     c->size = num_tables;
-    c->entries = g_malloc0(sizeof(*c->entries) * num_tables);
+    c->entries = qemu_mallocz(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);
@@ -68,8 +70,8 @@ int qcow2_cache_destroy(BlockDriverState* bs, Qcow2Cache *c)
         qemu_vfree(c->entries[i].table);
     }
 
-    g_free(c->entries);
-    g_free(c);
+    qemu_free(c->entries);
+    qemu_free(c);
 
     return 0;
 }
@@ -98,9 +100,6 @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)
         return 0;
     }
 
-    trace_qcow2_cache_entry_flush(qemu_coroutine_self(),
-                                  c == s->l2_table_cache, i);
-
     if (c->depends) {
         ret = qcow2_cache_flush_dependency(bs, c);
     } else if (c->depends_on_flush) {
@@ -133,13 +132,10 @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)
 
 int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c)
 {
-    BDRVQcowState *s = bs->opaque;
     int result = 0;
     int ret;
     int i;
 
-    trace_qcow2_cache_flush(qemu_coroutine_self(), c == s->l2_table_cache);
-
     for (i = 0; i < c->size; i++) {
         ret = qcow2_cache_entry_flush(bs, c, i);
         if (ret < 0 && result != -ENOSPC) {
@@ -222,9 +218,6 @@ static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c,
     int i;
     int ret;
 
-    trace_qcow2_cache_get(qemu_coroutine_self(), c == s->l2_table_cache,
-                          offset, read_from_disk);
-
     /* Check if the table is already cached */
     for (i = 0; i < c->size; i++) {
         if (c->entries[i].offset == offset) {
@@ -234,8 +227,6 @@ static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c,
 
     /* If not, write a table back and replace it */
     i = qcow2_cache_find_entry_to_replace(c);
-    trace_qcow2_cache_get_replace_entry(qemu_coroutine_self(),
-                                        c == s->l2_table_cache, i);
     if (i < 0) {
         return i;
     }
@@ -245,8 +236,6 @@ static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c,
         return ret;
     }
 
-    trace_qcow2_cache_get_read(qemu_coroutine_self(),
-                               c == s->l2_table_cache, i);
     c->entries[i].offset = 0;
     if (read_from_disk) {
         if (c == s->l2_table_cache) {
@@ -269,10 +258,6 @@ found:
     c->entries[i].cache_hits++;
     c->entries[i].ref++;
     *table = c->entries[i].table;
-
-    trace_qcow2_cache_get_done(qemu_coroutine_self(),
-                               c == s->l2_table_cache, i);
-
     return 0;
 }
 
@@ -304,7 +289,12 @@ 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 +311,16 @@ 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-refcount.c

@@ -41,7 +41,7 @@ int qcow2_refcount_init(BlockDriverState *bs)
     int ret, refcount_table_size2, i;
 
     refcount_table_size2 = s->refcount_table_size * sizeof(uint64_t);
-    s->refcount_table = g_malloc(refcount_table_size2);
+    s->refcount_table = qemu_malloc(refcount_table_size2);
     if (s->refcount_table_size > 0) {
         BLKDBG_EVENT(bs->file, BLKDBG_REFTABLE_LOAD);
         ret = bdrv_pread(bs->file, s->refcount_table_offset,
@@ -59,7 +59,7 @@ int qcow2_refcount_init(BlockDriverState *bs)
 void qcow2_refcount_close(BlockDriverState *bs)
 {
     BDRVQcowState *s = bs->opaque;
-    g_free(s->refcount_table);
+    qemu_free(s->refcount_table);
 }
 
 
@@ -167,7 +167,7 @@ static int alloc_refcount_block(BlockDriverState *bs,
     if (refcount_table_index < s->refcount_table_size) {
 
         uint64_t refcount_block_offset =
-            s->refcount_table[refcount_table_index] & REFT_OFFSET_MASK;
+            s->refcount_table[refcount_table_index];
 
         /* If it's already there, we're done */
         if (refcount_block_offset) {
@@ -301,8 +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);
@@ -324,8 +323,8 @@ static int alloc_refcount_block(BlockDriverState *bs,
     uint64_t meta_offset = (blocks_used * refcount_block_clusters) *
         s->cluster_size;
     uint64_t table_offset = meta_offset + blocks_clusters * s->cluster_size;
-    uint16_t *new_blocks = g_malloc0(blocks_clusters * s->cluster_size);
-    uint64_t *new_table = g_malloc0(table_size * sizeof(uint64_t));
+    uint16_t *new_blocks = qemu_mallocz(blocks_clusters * s->cluster_size);
+    uint64_t *new_table = qemu_mallocz(table_size * sizeof(uint64_t));
 
     assert(meta_offset >= (s->free_cluster_index * s->cluster_size));
 
@@ -350,7 +349,7 @@ static int alloc_refcount_block(BlockDriverState *bs,
     BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_WRITE_BLOCKS);
     ret = bdrv_pwrite_sync(bs->file, meta_offset, new_blocks,
         blocks_clusters * s->cluster_size);
-    g_free(new_blocks);
+    qemu_free(new_blocks);
     if (ret < 0) {
         goto fail_table;
     }
@@ -368,7 +367,7 @@ static int alloc_refcount_block(BlockDriverState *bs,
     }
 
     for(i = 0; i < table_size; i++) {
-        be64_to_cpus(&new_table[i]);
+        cpu_to_be64s(&new_table[i]);
     }
 
     /* Hook up the new refcount table in the qcow2 header */
@@ -386,7 +385,7 @@ static int alloc_refcount_block(BlockDriverState *bs,
     uint64_t old_table_offset = s->refcount_table_offset;
     uint64_t old_table_size = s->refcount_table_size;
 
-    g_free(s->refcount_table);
+    qemu_free(s->refcount_table);
     s->refcount_table = new_table;
     s->refcount_table_size = table_size;
     s->refcount_table_offset = table_offset;
@@ -401,10 +400,10 @@ static int alloc_refcount_block(BlockDriverState *bs,
         return ret;
     }
 
-    return 0;
+    return new_block;
 
 fail_table:
-    g_free(new_table);
+    qemu_free(new_table);
 fail_block:
     if (*refcount_block != NULL) {
         qcow2_cache_put(bs, s->refcount_block_cache, (void**) refcount_block);
@@ -423,7 +422,7 @@ static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
     int ret;
 
 #ifdef DEBUG_ALLOC2
-    fprintf(stderr, "update_refcount: offset=%" PRId64 " size=%" PRId64 " addend=%d\n",
+    printf("update_refcount: offset=%" PRId64 " size=%" PRId64 " addend=%d\n",
            offset, length, addend);
 #endif
     if (length < 0) {
@@ -557,7 +556,7 @@ retry:
         }
     }
 #ifdef DEBUG_ALLOC2
-    fprintf(stderr, "alloc_clusters: size=%" PRId64 " -> %" PRId64 "\n",
+    printf("alloc_clusters: size=%" PRId64 " -> %" PRId64 "\n",
             size,
             (s->free_cluster_index - nb_clusters) << s->cluster_bits);
 #endif
@@ -583,40 +582,6 @@ int64_t qcow2_alloc_clusters(BlockDriverState *bs, int64_t size)
     return offset;
 }
 
-int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
-    int nb_clusters)
-{
-    BDRVQcowState *s = bs->opaque;
-    uint64_t cluster_index;
-    uint64_t old_free_cluster_index;
-    int i, refcount, ret;
-
-    /* Check how many clusters there are free */
-    cluster_index = offset >> s->cluster_bits;
-    for(i = 0; i < nb_clusters; i++) {
-        refcount = get_refcount(bs, cluster_index++);
-
-        if (refcount < 0) {
-            return refcount;
-        } else if (refcount != 0) {
-            break;
-        }
-    }
-
-    /* And then allocate them */
-    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);
-    if (ret < 0) {
-        return ret;
-    }
-
-    s->free_cluster_index = old_free_cluster_index;
-
-    return i;
-}
-
 /* only used to allocate compressed sectors. We try to allocate
    contiguous sectors. size must be <= cluster_size */
 int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size)
@@ -628,11 +593,10 @@ 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 -
@@ -681,35 +645,32 @@ 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.)
+ * free_any_clusters
+ *
+ * free clusters according to its type: compressed or not
+ *
  */
+
 void qcow2_free_any_clusters(BlockDriverState *bs,
-    uint64_t l2_entry, int nb_clusters)
+    uint64_t cluster_offset, int nb_clusters)
 {
     BDRVQcowState *s = bs->opaque;
 
-    switch (qcow2_get_cluster_type(l2_entry)) {
-    case QCOW2_CLUSTER_COMPRESSED:
-        {
-            int nb_csectors;
-            nb_csectors = ((l2_entry >> s->csize_shift) &
-                           s->csize_mask) + 1;
-            qcow2_free_clusters(bs,
-                (l2_entry & s->cluster_offset_mask) & ~511,
-                nb_csectors * 512);
-        }
-        break;
-    case QCOW2_CLUSTER_NORMAL:
-        qcow2_free_clusters(bs, l2_entry & L2E_OFFSET_MASK,
-                            nb_clusters << s->cluster_bits);
-        break;
-    case QCOW2_CLUSTER_UNALLOCATED:
-    case QCOW2_CLUSTER_ZERO:
-        break;
-    default:
-        abort();
+    /* free the cluster */
+
+    if (cluster_offset & QCOW_OFLAG_COMPRESSED) {
+        int nb_csectors;
+        nb_csectors = ((cluster_offset >> s->csize_shift) &
+                       s->csize_mask) + 1;
+        qcow2_free_clusters(bs,
+            (cluster_offset & s->cluster_offset_mask) & ~511,
+            nb_csectors * 512);
+        return;
     }
+
+    qcow2_free_clusters(bs, cluster_offset, nb_clusters << s->cluster_bits);
+
+    return;
 }
 
 
@@ -719,6 +680,24 @@ void qcow2_free_any_clusters(BlockDriverState *bs,
 
 
 
+void qcow2_create_refcount_update(QCowCreateState *s, int64_t offset,
+    int64_t size)
+{
+    int refcount;
+    int64_t start, last, cluster_offset;
+    uint16_t *p;
+
+    start = offset & ~(s->cluster_size - 1);
+    last = (offset + size - 1)  & ~(s->cluster_size - 1);
+    for(cluster_offset = start; cluster_offset <= last;
+        cluster_offset += s->cluster_size) {
+        p = &s->refcount_block[cluster_offset >> s->cluster_bits];
+        refcount = be16_to_cpu(*p);
+        refcount++;
+        *p = cpu_to_be16(refcount);
+    }
+}
+
 /* update the refcounts of snapshots and the copied flag */
 int qcow2_update_snapshot_refcount(BlockDriverState *bs,
     int64_t l1_table_offset, int l1_size, int addend)
@@ -728,17 +707,20 @@ 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);
-
-    /* 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) {
         if (l1_size2 != 0) {
-            l1_table = g_malloc0(align_offset(l1_size2, 512));
+            l1_table = qemu_mallocz(align_offset(l1_size2, 512));
         } else {
             l1_table = NULL;
         }
@@ -762,7 +744,7 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
         l2_offset = l1_table[i];
         if (l2_offset) {
             old_l2_offset = l2_offset;
-            l2_offset &= L1E_OFFSET_MASK;
+            l2_offset &= ~QCOW_OFLAG_COPIED;
 
             ret = qcow2_cache_get(bs, s->l2_table_cache, l2_offset,
                 (void**) &l2_table);
@@ -794,11 +776,10 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
                         /* 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);
+                            refcount = update_cluster_refcount(bs, offset >> s->cluster_bits, addend);
                         } else {
-                            refcount = get_refcount(bs, cluster_index);
+                            refcount = get_refcount(bs, offset >> s->cluster_bits);
                         }
 
                         if (refcount < 0) {
@@ -851,8 +832,12 @@ fail:
         qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
     }
 
-    /* Update L1 only if it isn't deleted anyway (addend = -1) */
-    if (addend >= 0 && l1_modified) {
+    /* 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);
+
+    if (l1_modified) {
         for(i = 0; i < l1_size; i++)
             cpu_to_be64s(&l1_table[i]);
         if (bdrv_pwrite_sync(bs->file, l1_table_offset, l1_table,
@@ -862,7 +847,7 @@ fail:
             be64_to_cpus(&l1_table[i]);
     }
     if (l1_allocated)
-        g_free(l1_table);
+        qemu_free(l1_table);
     return ret;
 }
 
@@ -931,91 +916,75 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res,
     int check_copied)
 {
     BDRVQcowState *s = bs->opaque;
-    uint64_t *l2_table, l2_entry;
+    uint64_t *l2_table, offset;
     int i, l2_size, nb_csectors, refcount;
 
     /* Read L2 table from disk */
     l2_size = s->l2_size * sizeof(uint64_t);
-    l2_table = g_malloc(l2_size);
+    l2_table = qemu_malloc(l2_size);
 
     if (bdrv_pread(bs->file, l2_offset, l2_table, l2_size) != l2_size)
         goto fail;
 
     /* Do the actual checks */
     for(i = 0; i < s->l2_size; i++) {
-        l2_entry = be64_to_cpu(l2_table[i]);
-
-        switch (qcow2_get_cluster_type(l2_entry)) {
-        case QCOW2_CLUSTER_COMPRESSED:
-            /* Compressed clusters don't have QCOW_OFLAG_COPIED */
-            if (l2_entry & QCOW_OFLAG_COPIED) {
-                fprintf(stderr, "ERROR: cluster %" PRId64 ": "
-                    "copied flag must never be set for compressed "
-                    "clusters\n", l2_entry >> s->cluster_bits);
-                l2_entry &= ~QCOW_OFLAG_COPIED;
-                res->corruptions++;
-            }
-
-            /* Mark cluster as used */
-            nb_csectors = ((l2_entry >> s->csize_shift) &
-                           s->csize_mask) + 1;
-            l2_entry &= s->cluster_offset_mask;
-            inc_refcounts(bs, res, refcount_table, refcount_table_size,
-                l2_entry & ~511, nb_csectors * 512);
-            break;
-
-        case QCOW2_CLUSTER_ZERO:
-            if ((l2_entry & L2E_OFFSET_MASK) == 0) {
-                break;
-            }
-            /* fall through */
-
-        case QCOW2_CLUSTER_NORMAL:
-        {
-            /* QCOW_OFLAG_COPIED must be set iff refcount == 1 */
-            uint64_t offset = l2_entry & L2E_OFFSET_MASK;
-
-            if (check_copied) {
-                refcount = get_refcount(bs, offset >> s->cluster_bits);
-                if (refcount < 0) {
-                    fprintf(stderr, "Can't get refcount for offset %"
-                        PRIx64 ": %s\n", l2_entry, strerror(-refcount));
-                    goto fail;
+        offset = be64_to_cpu(l2_table[i]);
+        if (offset != 0) {
+            if (offset & QCOW_OFLAG_COMPRESSED) {
+                /* Compressed clusters don't have QCOW_OFLAG_COPIED */
+                if (offset & QCOW_OFLAG_COPIED) {
+                    fprintf(stderr, "ERROR: cluster %" PRId64 ": "
+                        "copied flag must never be set for compressed "
+                        "clusters\n", offset >> s->cluster_bits);
+                    offset &= ~QCOW_OFLAG_COPIED;
+                    res->corruptions++;
                 }
-                if ((refcount == 1) != ((l2_entry & QCOW_OFLAG_COPIED) != 0)) {
-                    fprintf(stderr, "ERROR OFLAG_COPIED: offset=%"
-                        PRIx64 " refcount=%d\n", l2_entry, refcount);
+
+                /* Mark cluster as used */
+                nb_csectors = ((offset >> s->csize_shift) &
+                               s->csize_mask) + 1;
+                offset &= s->cluster_offset_mask;
+                inc_refcounts(bs, res, refcount_table, refcount_table_size,
+                    offset & ~511, nb_csectors * 512);
+            } else {
+                /* QCOW_OFLAG_COPIED must be set iff refcount == 1 */
+                if (check_copied) {
+                    uint64_t entry = offset;
+                    offset &= ~QCOW_OFLAG_COPIED;
+                    refcount = get_refcount(bs, offset >> s->cluster_bits);
+                    if (refcount < 0) {
+                        fprintf(stderr, "Can't get refcount for offset %"
+                            PRIx64 ": %s\n", entry, strerror(-refcount));
+                        goto fail;
+                    }
+                    if ((refcount == 1) != ((entry & QCOW_OFLAG_COPIED) != 0)) {
+                        fprintf(stderr, "ERROR OFLAG_COPIED: offset=%"
+                            PRIx64 " refcount=%d\n", entry, refcount);
+                        res->corruptions++;
+                    }
+                }
+
+                /* Mark cluster as used */
+                offset &= ~QCOW_OFLAG_COPIED;
+                inc_refcounts(bs, res, refcount_table,refcount_table_size,
+                    offset, s->cluster_size);
+
+                /* Correct offsets are cluster aligned */
+                if (offset & (s->cluster_size - 1)) {
+                    fprintf(stderr, "ERROR offset=%" PRIx64 ": Cluster is not "
+                        "properly aligned; L2 entry corrupted.\n", offset);
                     res->corruptions++;
                 }
             }
-
-            /* Mark cluster as used */
-            inc_refcounts(bs, res, refcount_table,refcount_table_size,
-                offset, s->cluster_size);
-
-            /* Correct offsets are cluster aligned */
-            if (offset & (s->cluster_size - 1)) {
-                fprintf(stderr, "ERROR offset=%" PRIx64 ": Cluster is not "
-                    "properly aligned; L2 entry corrupted.\n", offset);
-                res->corruptions++;
-            }
-            break;
-        }
-
-        case QCOW2_CLUSTER_UNALLOCATED:
-            break;
-
-        default:
-            abort();
         }
     }
 
-    g_free(l2_table);
+    qemu_free(l2_table);
     return 0;
 
 fail:
     fprintf(stderr, "ERROR: I/O error in check_refcounts_l2\n");
-    g_free(l2_table);
+    qemu_free(l2_table);
     return -EIO;
 }
 
@@ -1048,7 +1017,7 @@ static int check_refcounts_l1(BlockDriverState *bs,
     if (l1_size2 == 0) {
         l1_table = NULL;
     } else {
-        l1_table = g_malloc(l1_size2);
+        l1_table = qemu_malloc(l1_size2);
         if (bdrv_pread(bs->file, l1_table_offset,
                        l1_table, l1_size2) != l1_size2)
             goto fail;
@@ -1077,7 +1046,7 @@ static int check_refcounts_l1(BlockDriverState *bs,
             }
 
             /* Mark L2 table as used */
-            l2_offset &= L1E_OFFSET_MASK;
+            l2_offset &= ~QCOW_OFLAG_COPIED;
             inc_refcounts(bs, res, refcount_table, refcount_table_size,
                 l2_offset, s->cluster_size);
 
@@ -1096,13 +1065,13 @@ static int check_refcounts_l1(BlockDriverState *bs,
             }
         }
     }
-    g_free(l1_table);
+    qemu_free(l1_table);
     return 0;
 
 fail:
     fprintf(stderr, "ERROR: I/O error in check_refcounts_l1\n");
     res->check_errors++;
-    g_free(l1_table);
+    qemu_free(l1_table);
     return -EIO;
 }
 
@@ -1112,19 +1081,18 @@ 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;
-    int nb_clusters, refcount1, refcount2;
+    int64_t size;
+    int nb_clusters, refcount1, refcount2, i;
     QCowSnapshot *sn;
     uint16_t *refcount_table;
     int ret;
 
     size = bdrv_getlength(bs->file);
     nb_clusters = size_to_clusters(s, size);
-    refcount_table = g_malloc0(nb_clusters * sizeof(uint16_t));
+    refcount_table = qemu_mallocz(nb_clusters * sizeof(uint16_t));
 
     /* header */
     inc_refcounts(bs, res, refcount_table, nb_clusters,
@@ -1161,15 +1129,14 @@ 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;
         }
@@ -1178,8 +1145,7 @@ 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++;
             }
@@ -1190,7 +1156,7 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
     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;
@@ -1198,31 +1164,9 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
 
         refcount2 = refcount_table[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);
-                if (ret >= 0) {
-                    (*num_fixed)++;
-                    continue;
-                }
-            }
-
-            /* And if we couldn't, print an error */
             if (refcount1 < refcount2) {
                 res->corruptions++;
             } else {
@@ -1234,7 +1178,7 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
     ret = 0;
 
 fail:
-    g_free(refcount_table);
+    qemu_free(refcount_table);
 
     return ret;
 }

block/qcow2-snapshot.c

@@ -26,7 +26,7 @@
 #include "block_int.h"
 #include "block/qcow2.h"
 
-typedef struct QEMU_PACKED QCowSnapshotHeader {
+typedef struct __attribute__((packed)) QCowSnapshotHeader {
     /* header is 8 byte aligned */
     uint64_t l1_table_offset;
 
@@ -46,21 +46,16 @@ typedef struct QEMU_PACKED QCowSnapshotHeader {
     /* name follows  */
 } QCowSnapshotHeader;
 
-typedef struct QEMU_PACKED QCowSnapshotExtraData {
-    uint64_t vm_state_size_large;
-    uint64_t disk_size;
-} QCowSnapshotExtraData;
-
 void qcow2_free_snapshots(BlockDriverState *bs)
 {
     BDRVQcowState *s = bs->opaque;
     int i;
 
     for(i = 0; i < s->nb_snapshots; i++) {
-        g_free(s->snapshots[i].name);
-        g_free(s->snapshots[i].id_str);
+        qemu_free(s->snapshots[i].name);
+        qemu_free(s->snapshots[i].id_str);
     }
-    g_free(s->snapshots);
+    qemu_free(s->snapshots);
     s->snapshots = NULL;
     s->nb_snapshots = 0;
 }
@@ -69,12 +64,10 @@ int qcow2_read_snapshots(BlockDriverState *bs)
 {
     BDRVQcowState *s = bs->opaque;
     QCowSnapshotHeader h;
-    QCowSnapshotExtraData extra;
     QCowSnapshot *sn;
     int i, id_str_size, name_size;
     int64_t offset;
     uint32_t extra_data_size;
-    int ret;
 
     if (!s->nb_snapshots) {
         s->snapshots = NULL;
@@ -83,16 +76,11 @@ int qcow2_read_snapshots(BlockDriverState *bs)
     }
 
     offset = s->snapshots_offset;
-    s->snapshots = g_malloc0(s->nb_snapshots * sizeof(QCowSnapshot));
-
+    s->snapshots = qemu_mallocz(s->nb_snapshots * sizeof(QCowSnapshot));
     for(i = 0; i < s->nb_snapshots; i++) {
-        /* Read statically sized part of the snapshot header */
         offset = align_offset(offset, 8);
-        ret = bdrv_pread(bs->file, offset, &h, sizeof(h));
-        if (ret < 0) {
+        if (bdrv_pread(bs->file, offset, &h, sizeof(h)) != sizeof(h))
             goto fail;
-        }
-
         offset += sizeof(h);
         sn = s->snapshots + i;
         sn->l1_table_offset = be64_to_cpu(h.l1_table_offset);
@@ -106,49 +94,25 @@ int qcow2_read_snapshots(BlockDriverState *bs)
         id_str_size = be16_to_cpu(h.id_str_size);
         name_size = be16_to_cpu(h.name_size);
 
-        /* Read extra data */
-        ret = bdrv_pread(bs->file, offset, &extra,
-                         MIN(sizeof(extra), extra_data_size));
-        if (ret < 0) {
-            goto fail;
-        }
         offset += extra_data_size;
 
-        if (extra_data_size >= 8) {
-            sn->vm_state_size = be64_to_cpu(extra.vm_state_size_large);
-        }
-
-        if (extra_data_size >= 16) {
-            sn->disk_size = be64_to_cpu(extra.disk_size);
-        } else {
-            sn->disk_size = bs->total_sectors * BDRV_SECTOR_SIZE;
-        }
-
-        /* Read snapshot ID */
-        sn->id_str = g_malloc(id_str_size + 1);
-        ret = bdrv_pread(bs->file, offset, sn->id_str, id_str_size);
-        if (ret < 0) {
+        sn->id_str = qemu_malloc(id_str_size + 1);
+        if (bdrv_pread(bs->file, offset, sn->id_str, id_str_size) != id_str_size)
             goto fail;
-        }
         offset += id_str_size;
         sn->id_str[id_str_size] = '\0';
 
-        /* Read snapshot name */
-        sn->name = g_malloc(name_size + 1);
-        ret = bdrv_pread(bs->file, offset, sn->name, name_size);
-        if (ret < 0) {
+        sn->name = qemu_malloc(name_size + 1);
+        if (bdrv_pread(bs->file, offset, sn->name, name_size) != name_size)
             goto fail;
-        }
         offset += name_size;
         sn->name[name_size] = '\0';
     }
-
     s->snapshots_size = offset - s->snapshots_offset;
     return 0;
-
-fail:
+ fail:
     qcow2_free_snapshots(bs);
-    return ret;
+    return -1;
 }
 
 /* add at the end of the file a new list of snapshots */
@@ -157,14 +121,10 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
     BDRVQcowState *s = bs->opaque;
     QCowSnapshot *sn;
     QCowSnapshotHeader h;
-    QCowSnapshotExtraData extra;
     int i, name_size, id_str_size, snapshots_size;
-    struct {
-        uint32_t nb_snapshots;
-        uint64_t snapshots_offset;
-    } QEMU_PACKED header_data;
+    uint64_t data64;
+    uint32_t data32;
     int64_t offset, snapshots_offset;
-    int ret;
 
     /* compute the size of the snapshots */
     offset = 0;
@@ -172,13 +132,11 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
         sn = s->snapshots + i;
         offset = align_offset(offset, 8);
         offset += sizeof(h);
-        offset += sizeof(extra);
         offset += strlen(sn->id_str);
         offset += strlen(sn->name);
     }
     snapshots_size = offset;
 
-    /* Allocate space for the new snapshot list */
     snapshots_offset = qcow2_alloc_clusters(bs, snapshots_size);
     bdrv_flush(bs->file);
     offset = snapshots_offset;
@@ -186,86 +144,49 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
         return offset;
     }
 
-    /* Write all snapshots to the new list */
     for(i = 0; i < s->nb_snapshots; i++) {
         sn = s->snapshots + i;
         memset(&h, 0, sizeof(h));
         h.l1_table_offset = cpu_to_be64(sn->l1_table_offset);
         h.l1_size = cpu_to_be32(sn->l1_size);
-        /* If it doesn't fit in 32 bit, older implementations should treat it
-         * as a disk-only snapshot rather than truncate the VM state */
-        if (sn->vm_state_size <= 0xffffffff) {
-            h.vm_state_size = cpu_to_be32(sn->vm_state_size);
-        }
+        h.vm_state_size = cpu_to_be32(sn->vm_state_size);
         h.date_sec = cpu_to_be32(sn->date_sec);
         h.date_nsec = cpu_to_be32(sn->date_nsec);
         h.vm_clock_nsec = cpu_to_be64(sn->vm_clock_nsec);
-        h.extra_data_size = cpu_to_be32(sizeof(extra));
-
-        memset(&extra, 0, sizeof(extra));
-        extra.vm_state_size_large = cpu_to_be64(sn->vm_state_size);
-        extra.disk_size = cpu_to_be64(sn->disk_size);
 
         id_str_size = strlen(sn->id_str);
         name_size = strlen(sn->name);
         h.id_str_size = cpu_to_be16(id_str_size);
         h.name_size = cpu_to_be16(name_size);
         offset = align_offset(offset, 8);
-
-        ret = bdrv_pwrite(bs->file, offset, &h, sizeof(h));
-        if (ret < 0) {
+        if (bdrv_pwrite_sync(bs->file, offset, &h, sizeof(h)) < 0)
             goto fail;
-        }
         offset += sizeof(h);
-
-        ret = bdrv_pwrite(bs->file, offset, &extra, sizeof(extra));
-        if (ret < 0) {
+        if (bdrv_pwrite_sync(bs->file, offset, sn->id_str, id_str_size) < 0)
             goto fail;
-        }
-        offset += sizeof(extra);
-
-        ret = bdrv_pwrite(bs->file, offset, sn->id_str, id_str_size);
-        if (ret < 0) {
-            goto fail;
-        }
         offset += id_str_size;
-
-        ret = bdrv_pwrite(bs->file, offset, sn->name, name_size);
-        if (ret < 0) {
+        if (bdrv_pwrite_sync(bs->file, offset, sn->name, name_size) < 0)
             goto fail;
-        }
         offset += name_size;
     }
 
-    /*
-     * Update the header to point to the new snapshot table. This requires the
-     * new table and its refcounts to be stable on disk.
-     */
-    ret = bdrv_flush(bs);
-    if (ret < 0) {
+    /* update the various header fields */
+    data64 = cpu_to_be64(snapshots_offset);
+    if (bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, snapshots_offset),
+                    &data64, sizeof(data64)) < 0)
         goto fail;
-    }
-
-    QEMU_BUILD_BUG_ON(offsetof(QCowHeader, snapshots_offset) !=
-        offsetof(QCowHeader, nb_snapshots) + sizeof(header_data.nb_snapshots));
-
-    header_data.nb_snapshots        = cpu_to_be32(s->nb_snapshots);
-    header_data.snapshots_offset    = cpu_to_be64(snapshots_offset);
-
-    ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, nb_snapshots),
-                           &header_data, sizeof(header_data));
-    if (ret < 0) {
+    data32 = cpu_to_be32(s->nb_snapshots);
+    if (bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, nb_snapshots),
+                    &data32, sizeof(data32)) < 0)
         goto fail;
-    }
 
     /* free the old snapshot table */
     qcow2_free_clusters(bs, s->snapshots_offset, s->snapshots_size);
     s->snapshots_offset = snapshots_offset;
     s->snapshots_size = snapshots_size;
     return 0;
-
-fail:
-    return ret;
+ fail:
+    return -1;
 }
 
 static void find_new_snapshot_id(BlockDriverState *bs,
@@ -315,107 +236,80 @@ static int find_snapshot_by_id_or_name(BlockDriverState *bs, const char *name)
 int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
 {
     BDRVQcowState *s = bs->opaque;
-    QCowSnapshot *new_snapshot_list = NULL;
-    QCowSnapshot *old_snapshot_list = NULL;
-    QCowSnapshot sn1, *sn = &sn1;
+    QCowSnapshot *snapshots1, sn1, *sn = &sn1;
     int i, ret;
     uint64_t *l1_table = NULL;
     int64_t l1_table_offset;
 
     memset(sn, 0, sizeof(*sn));
 
-    /* Generate an ID if it wasn't passed */
     if (sn_info->id_str[0] == '\0') {
+        /* compute a new id */
         find_new_snapshot_id(bs, sn_info->id_str, sizeof(sn_info->id_str));
     }
 
-    /* Check that the ID is unique */
-    if (find_snapshot_by_id(bs, sn_info->id_str) >= 0) {
-        return -EEXIST;
-    }
+    /* check that the ID is unique */
+    if (find_snapshot_by_id(bs, sn_info->id_str) >= 0)
+        return -ENOENT;
 
-    /* Populate sn with passed data */
-    sn->id_str = g_strdup(sn_info->id_str);
-    sn->name = g_strdup(sn_info->name);
-
-    sn->disk_size = bs->total_sectors * BDRV_SECTOR_SIZE;
+    sn->id_str = qemu_strdup(sn_info->id_str);
+    if (!sn->id_str)
+        goto fail;
+    sn->name = qemu_strdup(sn_info->name);
+    if (!sn->name)
+        goto fail;
     sn->vm_state_size = sn_info->vm_state_size;
     sn->date_sec = sn_info->date_sec;
     sn->date_nsec = sn_info->date_nsec;
     sn->vm_clock_nsec = sn_info->vm_clock_nsec;
 
-    /* Allocate the L1 table of the snapshot and copy the current one there. */
+    ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 1);
+    if (ret < 0)
+        goto fail;
+
+    /* create the L1 table of the snapshot */
     l1_table_offset = qcow2_alloc_clusters(bs, s->l1_size * sizeof(uint64_t));
     if (l1_table_offset < 0) {
-        ret = l1_table_offset;
         goto fail;
     }
+    bdrv_flush(bs->file);
 
     sn->l1_table_offset = l1_table_offset;
     sn->l1_size = s->l1_size;
 
-    l1_table = g_malloc(s->l1_size * sizeof(uint64_t));
+    if (s->l1_size != 0) {
+        l1_table = qemu_malloc(s->l1_size * sizeof(uint64_t));
+    } else {
+        l1_table = NULL;
+    }
+
     for(i = 0; i < s->l1_size; i++) {
         l1_table[i] = cpu_to_be64(s->l1_table[i]);
     }
-
-    ret = bdrv_pwrite(bs->file, sn->l1_table_offset, l1_table,
-                      s->l1_size * sizeof(uint64_t));
-    if (ret < 0) {
+    if (bdrv_pwrite_sync(bs->file, sn->l1_table_offset,
+                    l1_table, s->l1_size * sizeof(uint64_t)) < 0)
         goto fail;
-    }
-
-    g_free(l1_table);
+    qemu_free(l1_table);
     l1_table = NULL;
 
-    /*
-     * Increase the refcounts of all clusters and make sure everything is
-     * stable on disk before updating the snapshot table to contain a pointer
-     * to the new L1 table.
-     */
-    ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 1);
-    if (ret < 0) {
-        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));
+    snapshots1 = qemu_malloc((s->nb_snapshots + 1) * sizeof(QCowSnapshot));
     if (s->snapshots) {
-        memcpy(new_snapshot_list, s->snapshots,
-               s->nb_snapshots * sizeof(QCowSnapshot));
-        old_snapshot_list = s->snapshots;
+        memcpy(snapshots1, s->snapshots, s->nb_snapshots * sizeof(QCowSnapshot));
+        qemu_free(s->snapshots);
     }
-    s->snapshots = new_snapshot_list;
+    s->snapshots = snapshots1;
     s->snapshots[s->nb_snapshots++] = *sn;
 
-    ret = qcow2_write_snapshots(bs);
-    if (ret < 0) {
-        g_free(s->snapshots);
-        s->snapshots = old_snapshot_list;
+    if (qcow2_write_snapshots(bs) < 0)
         goto fail;
-    }
-
-    g_free(old_snapshot_list);
-
 #ifdef DEBUG_ALLOC
-    {
-      BdrvCheckResult result = {0};
-      qcow2_check_refcounts(bs, &result, 0);
-    }
+    qcow2_check_refcounts(bs);
 #endif
     return 0;
-
-fail:
-    g_free(sn->id_str);
-    g_free(sn->name);
-    g_free(l1_table);
-
-    return ret;
+ fail:
+    qemu_free(sn->name);
+    qemu_free(l1_table);
+    return -1;
 }
 
 /* copy the snapshot 'snapshot_name' into the current disk image */
@@ -425,165 +319,78 @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
     QCowSnapshot *sn;
     int i, snapshot_index;
     int cur_l1_bytes, sn_l1_bytes;
-    int ret;
-    uint64_t *sn_l1_table = NULL;
 
-    /* Search the snapshot */
     snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_id);
-    if (snapshot_index < 0) {
+    if (snapshot_index < 0)
         return -ENOENT;
-    }
     sn = &s->snapshots[snapshot_index];
 
-    if (sn->disk_size != bs->total_sectors * BDRV_SECTOR_SIZE) {
-        error_report("qcow2: Loading snapshots with different disk "
-            "size is not implemented");
-        ret = -ENOTSUP;
+    if (qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, -1) < 0)
         goto fail;
-    }
 
-    /*
-     * Make sure that the current L1 table is big enough to contain the whole
-     * L1 table of the snapshot. If the snapshot L1 table is smaller, the
-     * current one must be padded with zeros.
-     */
-    ret = qcow2_grow_l1_table(bs, sn->l1_size, true);
-    if (ret < 0) {
+    if (qcow2_grow_l1_table(bs, sn->l1_size, true) < 0)
         goto fail;
-    }
 
     cur_l1_bytes = s->l1_size * sizeof(uint64_t);
     sn_l1_bytes = sn->l1_size * sizeof(uint64_t);
 
-    /*
-     * Copy the snapshot L1 table to the current L1 table.
-     *
-     * Before overwriting the old current L1 table on disk, make sure to
-     * increase all refcounts for the clusters referenced by the new one.
-     * Decrease the refcount referenced by the old one only when the L1
-     * table is overwritten.
-     */
-    sn_l1_table = g_malloc0(cur_l1_bytes);
-
-    ret = bdrv_pread(bs->file, sn->l1_table_offset, sn_l1_table, sn_l1_bytes);
-    if (ret < 0) {
-        goto fail;
+    if (cur_l1_bytes > sn_l1_bytes) {
+        memset(s->l1_table + sn->l1_size, 0, cur_l1_bytes - sn_l1_bytes);
     }
 
-    ret = qcow2_update_snapshot_refcount(bs, sn->l1_table_offset,
-                                         sn->l1_size, 1);
-    if (ret < 0) {
+    /* copy the snapshot l1 table to the current l1 table */
+    if (bdrv_pread(bs->file, sn->l1_table_offset,
+                   s->l1_table, sn_l1_bytes) < 0)
         goto fail;
-    }
-
-    ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset, sn_l1_table,
-                           cur_l1_bytes);
-    if (ret < 0) {
+    if (bdrv_pwrite_sync(bs->file, s->l1_table_offset,
+                    s->l1_table, cur_l1_bytes) < 0)
         goto fail;
-    }
-
-    /*
-     * Decrease refcount of clusters of current L1 table.
-     *
-     * At this point, the in-memory s->l1_table points to the old L1 table,
-     * whereas on disk we already have the new one.
-     *
-     * qcow2_update_snapshot_refcount special cases the current L1 table to use
-     * the in-memory data instead of really using the offset to load a new one,
-     * which is why this works.
-     */
-    ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset,
-                                         s->l1_size, -1);
-
-    /*
-     * Now update the in-memory L1 table to be in sync with the on-disk one. We
-     * need to do this even if updating refcounts failed.
-     */
     for(i = 0;i < s->l1_size; i++) {
-        s->l1_table[i] = be64_to_cpu(sn_l1_table[i]);
+        be64_to_cpus(&s->l1_table[i]);
     }
 
-    if (ret < 0) {
+    if (qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 1) < 0)
         goto fail;
-    }
-
-    g_free(sn_l1_table);
-    sn_l1_table = NULL;
-
-    /*
-     * Update QCOW_OFLAG_COPIED in the active L1 table (it may have changed
-     * when we decreased the refcount of the old snapshot.
-     */
-    ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 0);
-    if (ret < 0) {
-        goto fail;
-    }
 
 #ifdef DEBUG_ALLOC
-    {
-        BdrvCheckResult result = {0};
-        qcow2_check_refcounts(bs, &result, 0);
-    }
+    qcow2_check_refcounts(bs);
 #endif
     return 0;
-
-fail:
-    g_free(sn_l1_table);
-    return ret;
+ fail:
+    return -EIO;
 }
 
 int qcow2_snapshot_delete(BlockDriverState *bs, const char *snapshot_id)
 {
     BDRVQcowState *s = bs->opaque;
-    QCowSnapshot sn;
+    QCowSnapshot *sn;
     int snapshot_index, ret;
 
-    /* Search the snapshot */
     snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_id);
-    if (snapshot_index < 0) {
+    if (snapshot_index < 0)
         return -ENOENT;
-    }
-    sn = s->snapshots[snapshot_index];
+    sn = &s->snapshots[snapshot_index];
 
-    /* Remove it from the snapshot list */
-    memmove(s->snapshots + snapshot_index,
-            s->snapshots + snapshot_index + 1,
-            (s->nb_snapshots - snapshot_index - 1) * sizeof(sn));
+    ret = qcow2_update_snapshot_refcount(bs, sn->l1_table_offset, sn->l1_size, -1);
+    if (ret < 0)
+        return ret;
+    /* must update the copied flag on the current cluster offsets */
+    ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 0);
+    if (ret < 0)
+        return ret;
+    qcow2_free_clusters(bs, sn->l1_table_offset, sn->l1_size * sizeof(uint64_t));
+
+    qemu_free(sn->id_str);
+    qemu_free(sn->name);
+    memmove(sn, sn + 1, (s->nb_snapshots - snapshot_index - 1) * sizeof(*sn));
     s->nb_snapshots--;
     ret = qcow2_write_snapshots(bs);
     if (ret < 0) {
+        /* XXX: restore snapshot if error ? */
         return ret;
     }
-
-    /*
-     * The snapshot is now unused, clean up. If we fail after this point, we
-     * won't recover but just leak clusters.
-     */
-    g_free(sn.id_str);
-    g_free(sn.name);
-
-    /*
-     * Now decrease the refcounts of clusters referenced by the snapshot and
-     * free the L1 table.
-     */
-    ret = qcow2_update_snapshot_refcount(bs, sn.l1_table_offset,
-                                         sn.l1_size, -1);
-    if (ret < 0) {
-        return ret;
-    }
-    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);
-    if (ret < 0) {
-        return ret;
-    }
-
 #ifdef DEBUG_ALLOC
-    {
-        BdrvCheckResult result = {0};
-        qcow2_check_refcounts(bs, &result, 0);
-    }
+    qcow2_check_refcounts(bs);
 #endif
     return 0;
 }
@@ -600,7 +407,7 @@ int qcow2_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
         return s->nb_snapshots;
     }
 
-    sn_tab = g_malloc0(s->nb_snapshots * sizeof(QEMUSnapshotInfo));
+    sn_tab = qemu_mallocz(s->nb_snapshots * sizeof(QEMUSnapshotInfo));
     for(i = 0; i < s->nb_snapshots; i++) {
         sn_info = sn_tab + i;
         sn = s->snapshots + i;
@@ -619,42 +426,32 @@ int qcow2_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
 
 int qcow2_snapshot_load_tmp(BlockDriverState *bs, const char *snapshot_name)
 {
-    int i, snapshot_index;
+    int i, snapshot_index, l1_size2;
     BDRVQcowState *s = bs->opaque;
     QCowSnapshot *sn;
-    uint64_t *new_l1_table;
-    int new_l1_bytes;
-    int ret;
 
-    assert(bs->read_only);
-
-    /* Search the snapshot */
     snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_name);
     if (snapshot_index < 0) {
         return -ENOENT;
     }
+
     sn = &s->snapshots[snapshot_index];
-
-    /* Allocate and read in the snapshot's L1 table */
-    new_l1_bytes = s->l1_size * sizeof(uint64_t);
-    new_l1_table = g_malloc0(align_offset(new_l1_bytes, 512));
-
-    ret = bdrv_pread(bs->file, sn->l1_table_offset, new_l1_table, new_l1_bytes);
-    if (ret < 0) {
-        g_free(new_l1_table);
-        return ret;
+    s->l1_size = sn->l1_size;
+    l1_size2 = s->l1_size * sizeof(uint64_t);
+    if (s->l1_table != NULL) {
+        qemu_free(s->l1_table);
     }
 
-    /* Switch the L1 table */
-    g_free(s->l1_table);
-
-    s->l1_size = sn->l1_size;
     s->l1_table_offset = sn->l1_table_offset;
-    s->l1_table = new_l1_table;
+    s->l1_table = qemu_mallocz(align_offset(l1_size2, 512));
+
+    if (bdrv_pread(bs->file, sn->l1_table_offset,
+                   s->l1_table, l1_size2) != l1_size2) {
+        return -1;
+    }
 
     for(i = 0;i < s->l1_size; i++) {
         be64_to_cpus(&s->l1_table[i]);
     }
-
     return 0;
 }

block/qcow2.h

@@ -26,13 +26,13 @@
 #define BLOCK_QCOW2_H
 
 #include "aes.h"
-#include "qemu-coroutine.h"
 
 //#define DEBUG_ALLOC
 //#define DEBUG_ALLOC2
 //#define DEBUG_EXT
 
 #define QCOW_MAGIC (('Q' << 24) | ('F' << 16) | ('I' << 8) | 0xfb)
+#define QCOW_VERSION 2
 
 #define QCOW_CRYPT_NONE 0
 #define QCOW_CRYPT_AES  1
@@ -43,8 +43,6 @@
 #define QCOW_OFLAG_COPIED     (1LL << 63)
 /* indicate that the cluster is compressed (they never have the copied flag) */
 #define QCOW_OFLAG_COMPRESSED (1LL << 62)
-/* The cluster reads as all zeros */
-#define QCOW_OFLAG_ZERO (1LL << 0)
 
 #define REFCOUNT_SHIFT 1 /* refcount size is 2 bytes */
 
@@ -72,14 +70,6 @@ typedef struct QCowHeader {
     uint32_t refcount_table_clusters;
     uint32_t nb_snapshots;
     uint64_t snapshots_offset;
-
-    /* The following fields are only valid for version >= 3 */
-    uint64_t incompatible_features;
-    uint64_t compatible_features;
-    uint64_t autoclear_features;
-
-    uint32_t refcount_order;
-    uint32_t header_length;
 } QCowHeader;
 
 typedef struct QCowSnapshot {
@@ -87,8 +77,7 @@ typedef struct QCowSnapshot {
     uint32_t l1_size;
     char *id_str;
     char *name;
-    uint64_t disk_size;
-    uint64_t vm_state_size;
+    uint32_t vm_state_size;
     uint32_t date_sec;
     uint32_t date_nsec;
     uint64_t vm_clock_nsec;
@@ -97,41 +86,6 @@ typedef struct QCowSnapshot {
 struct Qcow2Cache;
 typedef struct Qcow2Cache Qcow2Cache;
 
-typedef struct Qcow2UnknownHeaderExtension {
-    uint32_t magic;
-    uint32_t len;
-    QLIST_ENTRY(Qcow2UnknownHeaderExtension) next;
-    uint8_t data[];
-} Qcow2UnknownHeaderExtension;
-
-enum {
-    QCOW2_FEAT_TYPE_INCOMPATIBLE    = 0,
-    QCOW2_FEAT_TYPE_COMPATIBLE      = 1,
-    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,
-};
-
-typedef struct Qcow2Feature {
-    uint8_t type;
-    uint8_t bit;
-    char    name[46];
-} QEMU_PACKED Qcow2Feature;
-
 typedef struct BDRVQcowState {
     int cluster_bits;
     int cluster_size;
@@ -160,8 +114,6 @@ typedef struct BDRVQcowState {
     int64_t free_cluster_index;
     int64_t free_byte_offset;
 
-    CoMutex lock;
-
     uint32_t crypt_method; /* current crypt method, 0 if no key yet */
     uint32_t crypt_method_header;
     AES_KEY aes_encrypt_key;
@@ -170,17 +122,6 @@ typedef struct BDRVQcowState {
     int snapshots_size;
     int nb_snapshots;
     QCowSnapshot *snapshots;
-
-    int flags;
-    int qcow_version;
-
-    uint64_t incompatible_features;
-    uint64_t compatible_features;
-    uint64_t autoclear_features;
-
-    size_t unknown_header_fields_size;
-    void* unknown_header_fields;
-    QLIST_HEAD(, Qcow2UnknownHeaderExtension) unknown_header_ext;
 } BDRVQcowState;
 
 /* XXX: use std qcow open function ? */
@@ -201,28 +142,15 @@ typedef struct QCowL2Meta
 {
     uint64_t offset;
     uint64_t cluster_offset;
-    uint64_t alloc_offset;
     int n_start;
     int nb_available;
     int nb_clusters;
-    CoQueue dependent_requests;
+    struct QCowL2Meta *depends_on;
+    QLIST_HEAD(QCowAioDependencies, QCowAIOCB) dependent_requests;
 
     QLIST_ENTRY(QCowL2Meta) next_in_flight;
 } QCowL2Meta;
 
-enum {
-    QCOW2_CLUSTER_UNALLOCATED,
-    QCOW2_CLUSTER_NORMAL,
-    QCOW2_CLUSTER_COMPRESSED,
-    QCOW2_CLUSTER_ZERO
-};
-
-#define L1E_OFFSET_MASK 0x00ffffffffffff00ULL
-#define L2E_OFFSET_MASK 0x00ffffffffffff00ULL
-#define L2E_COMPRESSED_OFFSET_SIZE_MASK 0x3fffffffffffffffULL
-
-#define REFT_OFFSET_MASK 0xffffffffffffff00ULL
-
 static inline int size_to_clusters(BDRVQcowState *s, int64_t size)
 {
     return (size + (s->cluster_size - 1)) >> s->cluster_bits;
@@ -240,50 +168,30 @@ static inline int64_t align_offset(int64_t offset, int n)
     return offset;
 }
 
-static inline int qcow2_get_cluster_type(uint64_t l2_entry)
-{
-    if (l2_entry & QCOW_OFLAG_COMPRESSED) {
-        return QCOW2_CLUSTER_COMPRESSED;
-    } else if (l2_entry & QCOW_OFLAG_ZERO) {
-        return QCOW2_CLUSTER_ZERO;
-    } else if (!(l2_entry & L2E_OFFSET_MASK)) {
-        return QCOW2_CLUSTER_UNALLOCATED;
-    } else {
-        return QCOW2_CLUSTER_NORMAL;
-    }
-}
-
-/* Check whether refcounts are eager or lazy */
-static inline bool qcow2_need_accurate_refcounts(BDRVQcowState *s)
-{
-    return !(s->incompatible_features & QCOW2_INCOMPAT_DIRTY);
-}
 
 // 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_update_header(BlockDriverState *bs);
 
 /* qcow2-refcount.c functions */
 int qcow2_refcount_init(BlockDriverState *bs);
 void qcow2_refcount_close(BlockDriverState *bs);
 
 int64_t qcow2_alloc_clusters(BlockDriverState *bs, int64_t size);
-int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
-    int nb_clusters);
 int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size);
 void qcow2_free_clusters(BlockDriverState *bs,
     int64_t offset, int64_t size);
 void qcow2_free_any_clusters(BlockDriverState *bs,
     uint64_t cluster_offset, int nb_clusters);
 
+void qcow2_create_refcount_update(QCowCreateState *s, int64_t offset,
+    int64_t size);
 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);
+int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res);
 
 /* qcow2-cluster.c functions */
 int qcow2_grow_l1_table(BlockDriverState *bs, int min_size, bool exact_size);
@@ -305,7 +213,6 @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
 int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m);
 int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
     int nb_sectors);
-int qcow2_zero_clusters(BlockDriverState *bs, uint64_t offset, int nb_sectors);
 
 /* qcow2-snapshot.c functions */
 int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info);
@@ -318,8 +225,11 @@ 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

@@ -68,7 +68,6 @@ static unsigned int qed_check_l2_table(QEDCheck *check, QEDTable *table)
 {
     BDRVQEDState *s = check->s;
     unsigned int i, num_invalid = 0;
-    uint64_t last_offset = 0;
 
     for (i = 0; i < s->table_nelems; i++) {
         uint64_t offset = table->offsets[i];
@@ -77,17 +76,11 @@ static unsigned int qed_check_l2_table(QEDCheck *check, QEDTable *table)
             qed_offset_is_zero_cluster(offset)) {
             continue;
         }
-        check->result->bfi.allocated_clusters++;
-        if (last_offset && (last_offset + s->header.cluster_size != offset)) {
-            check->result->bfi.fragmented_clusters++;
-        }
-        last_offset = offset;
 
         /* Detect invalid cluster offset */
         if (!qed_check_cluster_offset(s, offset)) {
             if (check->fix) {
                 table->offsets[i] = 0;
-                check->result->corruptions_fixed++;
             } else {
                 check->result->corruptions++;
             }
@@ -128,7 +121,6 @@ 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 +186,6 @@ 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 = {
@@ -227,22 +197,15 @@ int qed_check(BDRVQEDState *s, BdrvCheckResult *result, bool fix)
     };
     int ret;
 
-    check.used_clusters = g_malloc0(((check.nclusters + 31) / 32) *
+    check.used_clusters = qemu_mallocz(((check.nclusters + 31) / 32) *
                                        sizeof(check.used_clusters[0]));
 
-    check.result->bfi.total_clusters =
-        (s->header.image_size + s->header.cluster_size - 1) /
-            s->header.cluster_size;
     ret = qed_check_l1_table(&check, s->l1_table);
     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);
+    qemu_free(check.used_clusters);
     return ret;
 }

block/qed-cluster.c

@@ -108,7 +108,7 @@ static void qed_find_cluster_cb(void *opaque, int ret)
 
 out:
     find_cluster_cb->cb(find_cluster_cb->opaque, ret, offset, len);
-    g_free(find_cluster_cb);
+    qemu_free(find_cluster_cb);
 }
 
 /**
@@ -152,7 +152,7 @@ void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos,
         return;
     }
 
-    find_cluster_cb = g_malloc(sizeof(*find_cluster_cb));
+    find_cluster_cb = qemu_malloc(sizeof(*find_cluster_cb));
     find_cluster_cb->s = s;
     find_cluster_cb->pos = pos;
     find_cluster_cb->len = len;

block/qed-gencb.c

@@ -15,7 +15,7 @@
 
 void *gencb_alloc(size_t len, BlockDriverCompletionFunc *cb, void *opaque)
 {
-    GenericCB *gencb = g_malloc(len);
+    GenericCB *gencb = qemu_malloc(len);
     gencb->cb = cb;
     gencb->opaque = opaque;
     return gencb;
@@ -27,6 +27,6 @@ void gencb_complete(void *opaque, int ret)
     BlockDriverCompletionFunc *cb = gencb->cb;
     void *user_opaque = gencb->opaque;
 
-    g_free(gencb);
+    qemu_free(gencb);
     cb(user_opaque, ret);
 }

block/qed-l2-cache.c

@@ -74,7 +74,7 @@ void qed_free_l2_cache(L2TableCache *l2_cache)
 
     QTAILQ_FOREACH_SAFE(entry, &l2_cache->entries, node, next_entry) {
         qemu_vfree(entry->table);
-        g_free(entry);
+        qemu_free(entry);
     }
 }
 
@@ -89,7 +89,7 @@ CachedL2Table *qed_alloc_l2_cache_entry(L2TableCache *l2_cache)
 {
     CachedL2Table *entry;
 
-    entry = g_malloc0(sizeof(*entry));
+    entry = qemu_mallocz(sizeof(*entry));
     entry->ref++;
 
     trace_qed_alloc_l2_cache_entry(l2_cache, entry);
@@ -111,7 +111,7 @@ void qed_unref_l2_cache_entry(CachedL2Table *entry)
     trace_qed_unref_l2_cache_entry(entry, entry->ref);
     if (entry->ref == 0) {
         qemu_vfree(entry->table);
-        g_free(entry);
+        qemu_free(entry);
     }
 }
 
@@ -161,25 +161,11 @@ void qed_commit_l2_cache_entry(L2TableCache *l2_cache, CachedL2Table *l2_table)
         return;
     }
 
-    /* Evict an unused cache entry so we have space.  If all entries are in use
-     * we can grow the cache temporarily and we try to shrink back down later.
-     */
     if (l2_cache->n_entries >= MAX_L2_CACHE_SIZE) {
-        CachedL2Table *next;
-        QTAILQ_FOREACH_SAFE(entry, &l2_cache->entries, node, next) {
-            if (entry->ref > 1) {
-                continue;
-            }
-
-            QTAILQ_REMOVE(&l2_cache->entries, entry, node);
-            l2_cache->n_entries--;
-            qed_unref_l2_cache_entry(entry);
-
-            /* Stop evicting when we've shrunk back to max size */
-            if (l2_cache->n_entries < MAX_L2_CACHE_SIZE) {
-                break;
-            }
-        }
+        entry = QTAILQ_FIRST(&l2_cache->entries);
+        QTAILQ_REMOVE(&l2_cache->entries, entry, node);
+        l2_cache->n_entries--;
+        qed_unref_l2_cache_entry(entry);
     }
 
     l2_cache->n_entries++;

block/qed-table.c

@@ -29,7 +29,7 @@ static void qed_read_table_cb(void *opaque, int ret)
 {
     QEDReadTableCB *read_table_cb = opaque;
     QEDTable *table = read_table_cb->table;
-    int noffsets = read_table_cb->qiov.size / sizeof(uint64_t);
+    int noffsets = read_table_cb->iov.iov_len / sizeof(uint64_t);
     int i;
 
     /* Handle I/O error */
@@ -54,6 +54,7 @@ static void qed_read_table(BDRVQEDState *s, uint64_t offset, QEDTable *table,
     QEDReadTableCB *read_table_cb = gencb_alloc(sizeof(*read_table_cb),
                                                 cb, opaque);
     QEMUIOVector *qiov = &read_table_cb->qiov;
+    BlockDriverAIOCB *aiocb;
 
     trace_qed_read_table(s, offset, table);
 
@@ -63,9 +64,12 @@ static void qed_read_table(BDRVQEDState *s, uint64_t offset, QEDTable *table,
     read_table_cb->iov.iov_len = s->header.cluster_size * s->header.table_size,
 
     qemu_iovec_init_external(qiov, &read_table_cb->iov, 1);
-    bdrv_aio_readv(s->bs->file, offset / BDRV_SECTOR_SIZE, qiov,
-                   qiov->size / BDRV_SECTOR_SIZE,
-                   qed_read_table_cb, read_table_cb);
+    aiocb = bdrv_aio_readv(s->bs->file, offset / BDRV_SECTOR_SIZE, qiov,
+                           read_table_cb->iov.iov_len / BDRV_SECTOR_SIZE,
+                           qed_read_table_cb, read_table_cb);
+    if (!aiocb) {
+        qed_read_table_cb(read_table_cb, -EIO);
+    }
 }
 
 typedef struct {
@@ -103,6 +107,7 @@ 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;
 }
 
 /**
@@ -122,6 +127,7 @@ static void qed_write_table(BDRVQEDState *s, uint64_t offset, QEDTable *table,
                             BlockDriverCompletionFunc *cb, void *opaque)
 {
     QEDWriteTableCB *write_table_cb;
+    BlockDriverAIOCB *aiocb;
     unsigned int sector_mask = BDRV_SECTOR_SIZE / sizeof(uint64_t) - 1;
     unsigned int start, end, i;
     size_t len_bytes;
@@ -152,10 +158,13 @@ static void qed_write_table(BDRVQEDState *s, uint64_t offset, QEDTable *table,
     /* Adjust for offset into table */
     offset += start * sizeof(uint64_t);
 
-    bdrv_aio_writev(s->bs->file, offset / BDRV_SECTOR_SIZE,
-                    &write_table_cb->qiov,
-                    write_table_cb->qiov.size / BDRV_SECTOR_SIZE,
-                    qed_write_table_cb, write_table_cb);
+    aiocb = bdrv_aio_writev(s->bs->file, offset / BDRV_SECTOR_SIZE,
+                            &write_table_cb->qiov,
+                            write_table_cb->iov.iov_len / BDRV_SECTOR_SIZE,
+                            qed_write_table_cb, write_table_cb);
+    if (!aiocb) {
+        qed_write_table_cb(write_table_cb, -EIO);
+    }
 }
 
 /**
@@ -170,12 +179,16 @@ int qed_read_l1_table_sync(BDRVQEDState *s)
 {
     int ret = -EINPROGRESS;
 
+    async_context_push();
+
     qed_read_table(s, s->header.l1_table_offset,
                    s->l1_table, qed_sync_cb, &ret);
     while (ret == -EINPROGRESS) {
         qemu_aio_wait();
     }
 
+    async_context_pop();
+
     return ret;
 }
 
@@ -192,11 +205,15 @@ int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index,
 {
     int ret = -EINPROGRESS;
 
+    async_context_push();
+
     qed_write_l1_table(s, index, n, qed_sync_cb, &ret);
     while (ret == -EINPROGRESS) {
         qemu_aio_wait();
     }
 
+    async_context_pop();
+
     return ret;
 }
 
@@ -265,11 +282,14 @@ int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request, uint64_t offset
 {
     int ret = -EINPROGRESS;
 
+    async_context_push();
+
     qed_read_l2_table(s, request, offset, qed_sync_cb, &ret);
     while (ret == -EINPROGRESS) {
         qemu_aio_wait();
     }
 
+    async_context_pop();
     return ret;
 }
 
@@ -287,10 +307,13 @@ int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request,
 {
     int ret = -EINPROGRESS;
 
+    async_context_push();
+
     qed_write_l2_table(s, request, index, n, flush, qed_sync_cb, &ret);
     while (ret == -EINPROGRESS) {
         qemu_aio_wait();
     }
 
+    async_context_pop();
     return ret;
 }

block/qed.c

@@ -16,7 +16,6 @@
 #include "trace.h"
 #include "qed.h"
 #include "qerror.h"
-#include "migration.h"
 
 static void qed_aio_cancel(BlockDriverAIOCB *blockacb)
 {
@@ -30,7 +29,7 @@ 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 +88,7 @@ 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;
@@ -123,6 +122,7 @@ static void qed_write_header_read_cb(void *opaque, int ret)
 {
     QEDWriteHeaderCB *write_header_cb = opaque;
     BDRVQEDState *s = write_header_cb->s;
+    BlockDriverAIOCB *acb;
 
     if (ret) {
         qed_write_header_cb(write_header_cb, ret);
@@ -132,9 +132,12 @@ static void qed_write_header_read_cb(void *opaque, int ret)
     /* Update header */
     qed_header_cpu_to_le(&s->header, (QEDHeader *)write_header_cb->buf);
 
-    bdrv_aio_writev(s->bs->file, 0, &write_header_cb->qiov,
-                    write_header_cb->nsectors, qed_write_header_cb,
-                    write_header_cb);
+    acb = bdrv_aio_writev(s->bs->file, 0, &write_header_cb->qiov,
+                          write_header_cb->nsectors, qed_write_header_cb,
+                          write_header_cb);
+    if (!acb) {
+        qed_write_header_cb(write_header_cb, -EIO);
+    }
 }
 
 /**
@@ -152,6 +155,7 @@ static void qed_write_header(BDRVQEDState *s, BlockDriverCompletionFunc cb,
      * them, and write back.
      */
 
+    BlockDriverAIOCB *acb;
     int nsectors = (sizeof(QEDHeader) + BDRV_SECTOR_SIZE - 1) /
                    BDRV_SECTOR_SIZE;
     size_t len = nsectors * BDRV_SECTOR_SIZE;
@@ -165,8 +169,11 @@ static void qed_write_header(BDRVQEDState *s, BlockDriverCompletionFunc cb,
     write_header_cb->iov.iov_len = len;
     qemu_iovec_init_external(&write_header_cb->qiov, &write_header_cb->iov, 1);
 
-    bdrv_aio_readv(s->bs->file, 0, &write_header_cb->qiov, nsectors,
-                   qed_write_header_read_cb, write_header_cb);
+    acb = bdrv_aio_readv(s->bs->file, 0, &write_header_cb->qiov, nsectors,
+                         qed_write_header_read_cb, write_header_cb);
+    if (!acb) {
+        qed_write_header_cb(write_header_cb, -EIO);
+    }
 }
 
 static uint64_t qed_max_image_size(uint32_t cluster_size, uint32_t table_size)
@@ -367,12 +374,6 @@ static void qed_cancel_need_check_timer(BDRVQEDState *s)
     qemu_del_timer(s->need_check_timer);
 }
 
-static void bdrv_qed_rebind(BlockDriverState *bs)
-{
-    BDRVQEDState *s = bs->opaque;
-    s->bs = bs;
-}
-
 static int bdrv_qed_open(BlockDriverState *bs, int flags)
 {
     BDRVQEDState *s = bs->opaque;
@@ -387,6 +388,7 @@ static int bdrv_qed_open(BlockDriverState *bs, int flags)
     if (ret < 0) {
         return ret;
     }
+    ret = 0; /* ret should always be 0 or -errno */
     qed_header_le_to_cpu(&le_header, &s->header);
 
     if (s->header.magic != QED_MAGIC) {
@@ -456,7 +458,7 @@ static int bdrv_qed_open(BlockDriverState *bs, int flags)
      * feature is no longer valid.
      */
     if ((s->header.autoclear_features & ~QED_AUTOCLEAR_FEATURE_MASK) != 0 &&
-        !bdrv_is_read_only(bs->file) && !(flags & BDRV_O_INCOMING)) {
+        !bdrv_is_read_only(bs->file)) {
         s->header.autoclear_features &= QED_AUTOCLEAR_FEATURE_MASK;
 
         ret = qed_write_header_sync(s);
@@ -477,20 +479,26 @@ static int bdrv_qed_open(BlockDriverState *bs, 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
          * aid data recovery from an otherwise inconsistent image.
          */
-        if (!bdrv_is_read_only(bs->file) &&
-            !(flags & BDRV_O_INCOMING)) {
+        if (!bdrv_is_read_only(bs->file)) {
             BdrvCheckResult result = {0};
 
             ret = qed_check(s, &result, true);
             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 +513,6 @@ 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;
@@ -533,6 +533,11 @@ static void bdrv_qed_close(BlockDriverState *bs)
     qemu_vfree(s->l1_table);
 }
 
+static int bdrv_qed_flush(BlockDriverState *bs)
+{
+    return bdrv_flush(bs->file);
+}
+
 static int qed_create(const char *filename, uint32_t cluster_size,
                       uint64_t image_size, uint32_t table_size,
                       const char *backing_file, const char *backing_fmt)
@@ -590,7 +595,7 @@ static int qed_create(const char *filename, uint32_t cluster_size,
         goto out;
     }
 
-    l1_table = g_malloc0(l1_size);
+    l1_table = qemu_mallocz(l1_size);
     ret = bdrv_pwrite(bs, header.l1_table_offset, l1_table, l1_size);
     if (ret < 0) {
         goto out;
@@ -598,7 +603,7 @@ static int qed_create(const char *filename, uint32_t cluster_size,
 
     ret = 0; /* success */
 out:
-    g_free(l1_table);
+    qemu_free(l1_table);
     bdrv_delete(bs);
     return ret;
 }
@@ -652,7 +657,6 @@ static int bdrv_qed_create(const char *filename, QEMUOptionParameter *options)
 }
 
 typedef struct {
-    Coroutine *co;
     int is_allocated;
     int *pnum;
 } QEDIsAllocatedCB;
@@ -662,14 +666,10 @@ static void qed_is_allocated_cb(void *opaque, int ret, uint64_t offset, size_t l
     QEDIsAllocatedCB *cb = opaque;
     *cb->pnum = len / BDRV_SECTOR_SIZE;
     cb->is_allocated = (ret == QED_CLUSTER_FOUND || ret == QED_CLUSTER_ZERO);
-    if (cb->co) {
-        qemu_coroutine_enter(cb->co, NULL);
-    }
 }
 
-static int coroutine_fn bdrv_qed_co_is_allocated(BlockDriverState *bs,
-                                                 int64_t sector_num,
-                                                 int nb_sectors, int *pnum)
+static int bdrv_qed_is_allocated(BlockDriverState *bs, int64_t sector_num,
+                                  int nb_sectors, int *pnum)
 {
     BDRVQEDState *s = bs->opaque;
     uint64_t pos = (uint64_t)sector_num * BDRV_SECTOR_SIZE;
@@ -680,14 +680,16 @@ static int coroutine_fn bdrv_qed_co_is_allocated(BlockDriverState *bs,
     };
     QEDRequest request = { .l2_table = NULL };
 
+    async_context_push();
+
     qed_find_cluster(s, &request, pos, len, qed_is_allocated_cb, &cb);
 
-    /* Now sleep if the callback wasn't invoked immediately */
     while (cb.is_allocated == -1) {
-        cb.co = qemu_coroutine_self();
-        qemu_coroutine_yield();
+        qemu_aio_wait();
     }
 
+    async_context_pop();
+
     qed_unref_l2_cache_entry(request.l2_table);
 
     return cb.is_allocated;
@@ -719,6 +721,7 @@ static void qed_read_backing_file(BDRVQEDState *s, uint64_t pos,
                                   QEMUIOVector *qiov,
                                   BlockDriverCompletionFunc *cb, void *opaque)
 {
+    BlockDriverAIOCB *aiocb;
     uint64_t backing_length = 0;
     size_t size;
 
@@ -737,7 +740,7 @@ 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 */
@@ -749,9 +752,12 @@ 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);
-    bdrv_aio_readv(s->bs->backing_hd, pos / BDRV_SECTOR_SIZE,
-                   qiov, size / BDRV_SECTOR_SIZE, cb, opaque);
+    BLKDBG_EVENT(s->bs->file, BLKDBG_READ_BACKING);
+    aiocb = bdrv_aio_readv(s->bs->backing_hd, pos / BDRV_SECTOR_SIZE,
+                           qiov, size / BDRV_SECTOR_SIZE, cb, opaque);
+    if (!aiocb) {
+        cb(opaque, -EIO);
+    }
 }
 
 typedef struct {
@@ -773,6 +779,7 @@ static void qed_copy_from_backing_file_write(void *opaque, int ret)
 {
     CopyFromBackingFileCB *copy_cb = opaque;
     BDRVQEDState *s = copy_cb->s;
+    BlockDriverAIOCB *aiocb;
 
     if (ret) {
         qed_copy_from_backing_file_cb(copy_cb, ret);
@@ -780,9 +787,13 @@ static void qed_copy_from_backing_file_write(void *opaque, int ret)
     }
 
     BLKDBG_EVENT(s->bs->file, BLKDBG_COW_WRITE);
-    bdrv_aio_writev(s->bs->file, copy_cb->offset / BDRV_SECTOR_SIZE,
-                    &copy_cb->qiov, copy_cb->qiov.size / BDRV_SECTOR_SIZE,
-                    qed_copy_from_backing_file_cb, copy_cb);
+    aiocb = bdrv_aio_writev(s->bs->file, copy_cb->offset / BDRV_SECTOR_SIZE,
+                            &copy_cb->qiov,
+                            copy_cb->qiov.size / BDRV_SECTOR_SIZE,
+                            qed_copy_from_backing_file_cb, copy_cb);
+    if (!aiocb) {
+        qed_copy_from_backing_file_cb(copy_cb, -EIO);
+    }
 }
 
 /**
@@ -874,12 +885,6 @@ static void qed_aio_complete(QEDAIOCB *acb, int ret)
     qemu_iovec_destroy(&acb->cur_qiov);
     qed_unref_l2_cache_entry(acb->request.l2_table);
 
-    /* Free the buffer we may have allocated for zero writes */
-    if (acb->flags & QED_AIOCB_ZERO) {
-        qemu_vfree(acb->qiov->iov[0].iov_base);
-        acb->qiov->iov[0].iov_base = NULL;
-    }
-
     /* Arrange for a bh to invoke the completion function */
     acb->bh_ret = ret;
     acb->bh = qemu_bh_new(qed_aio_complete_bh, acb);
@@ -946,8 +951,9 @@ static void qed_aio_write_l1_update(void *opaque, int ret)
 /**
  * Update L2 table with new cluster offsets and write them out
  */
-static void qed_aio_write_l2_update(QEDAIOCB *acb, int ret, uint64_t offset)
+static void qed_aio_write_l2_update(void *opaque, int ret)
 {
+    QEDAIOCB *acb = opaque;
     BDRVQEDState *s = acb_to_s(acb);
     bool need_alloc = acb->find_cluster_ret == QED_CLUSTER_L1;
     int index;
@@ -963,7 +969,7 @@ static void qed_aio_write_l2_update(QEDAIOCB *acb, int ret, uint64_t offset)
 
     index = qed_l2_index(s, acb->cur_pos);
     qed_update_l2_table(s, acb->request.l2_table->table, index, acb->cur_nclusters,
-                         offset);
+                         acb->cur_cluster);
 
     if (need_alloc) {
         /* Write out the whole new L2 table */
@@ -980,12 +986,6 @@ err:
     qed_aio_complete(acb, ret);
 }
 
-static void qed_aio_write_l2_update_cb(void *opaque, int ret)
-{
-    QEDAIOCB *acb = opaque;
-    qed_aio_write_l2_update(acb, ret, acb->cur_cluster);
-}
-
 /**
  * Flush new data clusters before updating the L2 table
  *
@@ -1000,7 +1000,7 @@ static void qed_aio_write_flush_before_l2_update(void *opaque, int ret)
     QEDAIOCB *acb = opaque;
     BDRVQEDState *s = acb_to_s(acb);
 
-    if (!bdrv_aio_flush(s->bs->file, qed_aio_write_l2_update_cb, opaque)) {
+    if (!bdrv_aio_flush(s->bs->file, qed_aio_write_l2_update, opaque)) {
         qed_aio_complete(acb, -EIO);
     }
 }
@@ -1015,6 +1015,7 @@ static void qed_aio_write_main(void *opaque, int ret)
     uint64_t offset = acb->cur_cluster +
                       qed_offset_into_cluster(s, acb->cur_pos);
     BlockDriverCompletionFunc *next_fn;
+    BlockDriverAIOCB *file_acb;
 
     trace_qed_aio_write_main(s, acb, ret, offset, acb->cur_qiov.size);
 
@@ -1029,14 +1030,18 @@ static void qed_aio_write_main(void *opaque, int ret)
         if (s->bs->backing_hd) {
             next_fn = qed_aio_write_flush_before_l2_update;
         } else {
-            next_fn = qed_aio_write_l2_update_cb;
+            next_fn = qed_aio_write_l2_update;
         }
     }
 
     BLKDBG_EVENT(s->bs->file, BLKDBG_WRITE_AIO);
-    bdrv_aio_writev(s->bs->file, offset / BDRV_SECTOR_SIZE,
-                    &acb->cur_qiov, acb->cur_qiov.size / BDRV_SECTOR_SIZE,
-                    next_fn, acb);
+    file_acb = bdrv_aio_writev(s->bs->file, offset / BDRV_SECTOR_SIZE,
+                               &acb->cur_qiov,
+                               acb->cur_qiov.size / BDRV_SECTOR_SIZE,
+                               next_fn, acb);
+    if (!file_acb) {
+        qed_aio_complete(acb, -EIO);
+    }
 }
 
 /**
@@ -1091,18 +1096,6 @@ static bool qed_should_set_need_check(BDRVQEDState *s)
     return !(s->header.features & QED_F_NEED_CHECK);
 }
 
-static void qed_aio_write_zero_cluster(void *opaque, int ret)
-{
-    QEDAIOCB *acb = opaque;
-
-    if (ret) {
-        qed_aio_complete(acb, ret);
-        return;
-    }
-
-    qed_aio_write_l2_update(acb, 0, 1);
-}
-
 /**
  * Write new data cluster
  *
@@ -1114,7 +1107,6 @@ static void qed_aio_write_zero_cluster(void *opaque, int ret)
 static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len)
 {
     BDRVQEDState *s = acb_to_s(acb);
-    BlockDriverCompletionFunc *cb;
 
     /* Cancel timer when the first allocating request comes in */
     if (QSIMPLEQ_EMPTY(&s->allocating_write_reqs)) {
@@ -1132,26 +1124,14 @@ 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);
-
-    if (acb->flags & QED_AIOCB_ZERO) {
-        /* Skip ahead if the clusters are already zero */
-        if (acb->find_cluster_ret == QED_CLUSTER_ZERO) {
-            qed_aio_next_io(acb, 0);
-            return;
-        }
-
-        cb = qed_aio_write_zero_cluster;
-    } else {
-        cb = qed_aio_write_prefill;
-        acb->cur_cluster = qed_alloc_clusters(s, acb->cur_nclusters);
-    }
+    acb->cur_cluster = qed_alloc_clusters(s, acb->cur_nclusters);
+    qemu_iovec_copy(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
 
     if (qed_should_set_need_check(s)) {
         s->header.features |= QED_F_NEED_CHECK;
-        qed_write_header(s, cb, acb);
+        qed_write_header(s, qed_aio_write_prefill, acb);
     } else {
-        cb(acb, 0);
+        qed_aio_write_prefill(acb, 0);
     }
 }
 
@@ -1166,19 +1146,9 @@ static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len)
  */
 static void qed_aio_write_inplace(QEDAIOCB *acb, uint64_t offset, size_t len)
 {
-    /* Allocate buffer for zero writes */
-    if (acb->flags & QED_AIOCB_ZERO) {
-        struct iovec *iov = acb->qiov->iov;
-
-        if (!iov->iov_base) {
-            iov->iov_base = qemu_blockalign(acb->common.bs, iov->iov_len);
-            memset(iov->iov_base, 0, iov->iov_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);
@@ -1238,6 +1208,7 @@ static void qed_aio_read_data(void *opaque, int ret,
     QEDAIOCB *acb = opaque;
     BDRVQEDState *s = acb_to_s(acb);
     BlockDriverState *bs = acb->common.bs;
+    BlockDriverAIOCB *file_acb;
 
     /* Adjust offset into cluster */
     offset += qed_offset_into_cluster(s, acb->cur_pos);
@@ -1248,11 +1219,11 @@ 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) {
@@ -1262,9 +1233,14 @@ static void qed_aio_read_data(void *opaque, int ret,
     }
 
     BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
-    bdrv_aio_readv(bs->file, offset / BDRV_SECTOR_SIZE,
-                   &acb->cur_qiov, acb->cur_qiov.size / BDRV_SECTOR_SIZE,
-                   qed_aio_next_io, acb);
+    file_acb = bdrv_aio_readv(bs->file, offset / BDRV_SECTOR_SIZE,
+                              &acb->cur_qiov,
+                              acb->cur_qiov.size / BDRV_SECTOR_SIZE,
+                              qed_aio_next_io, acb);
+    if (!file_acb) {
+        ret = -EIO;
+        goto err;
+    }
     return;
 
 err:
@@ -1278,8 +1254,8 @@ static void qed_aio_next_io(void *opaque, int ret)
 {
     QEDAIOCB *acb = opaque;
     BDRVQEDState *s = acb_to_s(acb);
-    QEDFindClusterFunc *io_fn = (acb->flags & QED_AIOCB_WRITE) ?
-                                qed_aio_write_data : qed_aio_read_data;
+    QEDFindClusterFunc *io_fn =
+        acb->is_write ? qed_aio_write_data : qed_aio_read_data;
 
     trace_qed_aio_next_io(s, acb, ret, acb->cur_pos + acb->cur_qiov.size);
 
@@ -1309,14 +1285,14 @@ static BlockDriverAIOCB *qed_aio_setup(BlockDriverState *bs,
                                        int64_t sector_num,
                                        QEMUIOVector *qiov, int nb_sectors,
                                        BlockDriverCompletionFunc *cb,
-                                       void *opaque, int flags)
+                                       void *opaque, bool is_write)
 {
-    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);
+                         opaque, is_write);
 
-    acb->flags = flags;
+    acb->is_write = is_write;
     acb->finished = NULL;
     acb->qiov = qiov;
     acb->qiov_offset = 0;
@@ -1336,7 +1312,7 @@ static BlockDriverAIOCB *bdrv_qed_aio_readv(BlockDriverState *bs,
                                             BlockDriverCompletionFunc *cb,
                                             void *opaque)
 {
-    return qed_aio_setup(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
+    return qed_aio_setup(bs, sector_num, qiov, nb_sectors, cb, opaque, false);
 }
 
 static BlockDriverAIOCB *bdrv_qed_aio_writev(BlockDriverState *bs,
@@ -1345,66 +1321,14 @@ static BlockDriverAIOCB *bdrv_qed_aio_writev(BlockDriverState *bs,
                                              BlockDriverCompletionFunc *cb,
                                              void *opaque)
 {
-    return qed_aio_setup(bs, sector_num, qiov, nb_sectors, cb,
-                         opaque, QED_AIOCB_WRITE);
+    return qed_aio_setup(bs, sector_num, qiov, nb_sectors, cb, opaque, true);
 }
 
-typedef struct {
-    Coroutine *co;
-    int ret;
-    bool done;
-} QEDWriteZeroesCB;
-
-static void coroutine_fn qed_co_write_zeroes_cb(void *opaque, int ret)
+static BlockDriverAIOCB *bdrv_qed_aio_flush(BlockDriverState *bs,
+                                            BlockDriverCompletionFunc *cb,
+                                            void *opaque)
 {
-    QEDWriteZeroesCB *cb = opaque;
-
-    cb->done = true;
-    cb->ret = ret;
-    if (cb->co) {
-        qemu_coroutine_enter(cb->co, NULL);
-    }
-}
-
-static int coroutine_fn bdrv_qed_co_write_zeroes(BlockDriverState *bs,
-                                                 int64_t sector_num,
-                                                 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.
-     */
-    iov.iov_base = NULL,
-    iov.iov_len  = nb_sectors * BDRV_SECTOR_SIZE,
-
-    qemu_iovec_init_external(&qiov, &iov, 1);
-    blockacb = qed_aio_setup(bs, sector_num, &qiov, nb_sectors,
-                             qed_co_write_zeroes_cb, &cb,
-                             QED_AIOCB_WRITE | QED_AIOCB_ZERO);
-    if (!blockacb) {
-        return -EIO;
-    }
-    if (!cb.done) {
-        cb.co = qemu_coroutine_self();
-        qemu_coroutine_yield();
-    }
-    assert(cb.done);
-    return cb.ret;
+    return bdrv_aio_flush(bs->file, cb, opaque);
 }
 
 static int bdrv_qed_truncate(BlockDriverState *bs, int64_t offset)
@@ -1444,7 +1368,6 @@ static int bdrv_qed_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
 
     memset(bdi, 0, sizeof(*bdi));
     bdi->cluster_size = s->header.cluster_size;
-    bdi->is_dirty = s->header.features & QED_F_NEED_CHECK;
     return 0;
 }
 
@@ -1500,41 +1423,29 @@ static int bdrv_qed_change_backing_file(BlockDriverState *bs,
     }
 
     /* Prepare new header */
-    buffer = g_malloc(buffer_len);
+    buffer = qemu_malloc(buffer_len);
 
     qed_header_cpu_to_le(&new_header, &le_header);
     memcpy(buffer, &le_header, sizeof(le_header));
     buffer_len = sizeof(le_header);
 
-    if (backing_file) {
-        memcpy(buffer + buffer_len, backing_file, backing_file_len);
-        buffer_len += backing_file_len;
-    }
+    memcpy(buffer + buffer_len, backing_file, backing_file_len);
+    buffer_len += backing_file_len;
 
     /* Write new header */
     ret = bdrv_pwrite_sync(bs->file, 0, buffer, buffer_len);
-    g_free(buffer);
+    qemu_free(buffer);
     if (ret == 0) {
         memcpy(&s->header, &new_header, sizeof(new_header));
     }
     return ret;
 }
 
-static void bdrv_qed_invalidate_cache(BlockDriverState *bs)
+static int bdrv_qed_check(BlockDriverState *bs, BdrvCheckResult *result)
 {
     BDRVQEDState *s = bs->opaque;
 
-    bdrv_qed_close(bs);
-    memset(s, 0, sizeof(BDRVQEDState));
-    bdrv_qed_open(bs, bs->open_flags);
-}
-
-static int bdrv_qed_check(BlockDriverState *bs, BdrvCheckResult *result,
-                          BdrvCheckMode fix)
-{
-    BDRVQEDState *s = bs->opaque;
-
-    return qed_check(s, result, !!fix);
+    return qed_check(s, result, false);
 }
 
 static QEMUOptionParameter qed_create_options[] = {
@@ -1569,21 +1480,19 @@ static BlockDriver bdrv_qed = {
     .create_options           = qed_create_options,
 
     .bdrv_probe               = bdrv_qed_probe,
-    .bdrv_rebind              = bdrv_qed_rebind,
     .bdrv_open                = bdrv_qed_open,
     .bdrv_close               = bdrv_qed_close,
-    .bdrv_reopen_prepare      = bdrv_qed_reopen_prepare,
     .bdrv_create              = bdrv_qed_create,
-    .bdrv_co_is_allocated     = bdrv_qed_co_is_allocated,
+    .bdrv_flush               = bdrv_qed_flush,
+    .bdrv_is_allocated        = bdrv_qed_is_allocated,
     .bdrv_make_empty          = bdrv_qed_make_empty,
     .bdrv_aio_readv           = bdrv_qed_aio_readv,
     .bdrv_aio_writev          = bdrv_qed_aio_writev,
-    .bdrv_co_write_zeroes     = bdrv_qed_co_write_zeroes,
+    .bdrv_aio_flush           = bdrv_qed_aio_flush,
     .bdrv_truncate            = bdrv_qed_truncate,
     .bdrv_getlength           = bdrv_qed_getlength,
     .bdrv_get_info            = bdrv_qed_get_info,
     .bdrv_change_backing_file = bdrv_qed_change_backing_file,
-    .bdrv_invalidate_cache    = bdrv_qed_invalidate_cache,
     .bdrv_check               = bdrv_qed_check,
 };
 

block/qed.h

@@ -123,17 +123,12 @@ typedef struct QEDRequest {
     CachedL2Table *l2_table;
 } QEDRequest;
 
-enum {
-    QED_AIOCB_WRITE = 0x0001,       /* read or write? */
-    QED_AIOCB_ZERO  = 0x0002,       /* zero write, used with QED_AIOCB_WRITE */
-};
-
 typedef struct QEDAIOCB {
     BlockDriverAIOCB common;
     QEMUBH *bh;
     int bh_ret;                     /* final return status for completion bh */
     QSIMPLEQ_ENTRY(QEDAIOCB) next;  /* next request */
-    int flags;                      /* QED_AIOCB_* bits ORed together */
+    bool is_write;                  /* false - read, true - write */
     bool *finished;                 /* signal for cancel completion */
     uint64_t end_pos;               /* request end on block device, in bytes */
 
@@ -210,11 +205,6 @@ 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
  *
@@ -9,11 +9,9 @@
  * 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.
  */
-#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
@@ -27,22 +25,19 @@
 #define QEMU_AIO_MISALIGNED   0x1000
 
 
+/* 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

@@ -25,10 +25,6 @@
 #include "qemu-timer.h"
 #include "block_int.h"
 #include "module.h"
-#include "raw-aio.h"
-#include "trace.h"
-#include "thread-pool.h"
-#include "iov.h"
 #include <windows.h>
 #include <winioctl.h>
 
@@ -36,134 +32,15 @@
 #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);
-
-    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);
-    return thread_pool_submit_aio(aio_worker, acb, cb, opaque);
-}
-
 int qemu_ftruncate64(int fd, int64_t length)
 {
     LARGE_INTEGER li;
-    DWORD dw;
     LONG high;
     HANDLE h;
     BOOL res;
@@ -176,15 +53,12 @@ int qemu_ftruncate64(int fd, int64_t length)
     /* get current position, ftruncate do not change position */
     li.HighPart = 0;
     li.LowPart = SetFilePointer (h, 0, &li.HighPart, FILE_CURRENT);
-    if (li.LowPart == INVALID_SET_FILE_POINTER && GetLastError() != NO_ERROR) {
+    if (li.LowPart == 0xffffffffUL && GetLastError() != NO_ERROR)
 	return -1;
-    }
 
     high = length >> 32;
-    dw = SetFilePointer(h, (DWORD) length, &high, FILE_BEGIN);
-    if (dw == INVALID_SET_FILE_POINTER && GetLastError() != NO_ERROR) {
+    if (!SetFilePointer(h, (DWORD) length, &high, FILE_BEGIN))
 	return -1;
-    }
     res = SetEndOfFile(h);
 
     /* back to old position */
@@ -199,26 +73,6 @@ 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 int raw_open(BlockDriverState *bs, const char *filename, int flags)
 {
     BDRVRawState *s = bs->opaque;
@@ -227,15 +81,17 @@ static int raw_open(BlockDriverState *bs, const char *filename, int flags)
 
     s->type = FTYPE_FILE;
 
-    raw_parse_flags(flags, &access_flags, &overlapped);
-    
-    if ((flags & BDRV_O_NATIVE_AIO) && aio == NULL) {
-        aio = win32_aio_init();
-        if (aio == NULL) {
-            return -EINVAL;
-        }
+    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);
@@ -244,53 +100,64 @@ static int raw_open(BlockDriverState *bs, const char *filename, int flags)
 
         if (err == ERROR_ACCESS_DENIED)
             return -EACCES;
-        return -EINVAL;
-    }
-
-    if (flags & BDRV_O_NATIVE_AIO) {
-        int ret = win32_aio_attach(aio, s->hfile);
-        if (ret < 0) {
-            CloseHandle(s->hfile);
-            return ret;
-        }
-        s->aio = aio;
+        return -1;
     }
     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)
@@ -384,13 +251,13 @@ 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;
 }
 
@@ -410,11 +277,9 @@ static BlockDriver bdrv_file = {
     .bdrv_file_open	= raw_open,
     .bdrv_close		= raw_close,
     .bdrv_create	= raw_create,
-
-    .bdrv_aio_readv     = raw_aio_readv,
-    .bdrv_aio_writev    = raw_aio_writev,
-    .bdrv_aio_flush     = raw_aio_flush,
-
+    .bdrv_flush		= raw_flush,
+    .bdrv_read		= raw_read,
+    .bdrv_write		= raw_write,
     .bdrv_truncate	= raw_truncate,
     .bdrv_getlength	= raw_getlength,
     .bdrv_get_allocated_file_size
@@ -503,10 +368,18 @@ static int hdev_open(BlockDriverState *bs, const char *filename, 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);
@@ -520,6 +393,41 @@ static int hdev_open(BlockDriverState *bs, const char *filename, int flags)
     return 0;
 }
 
+#if 0
+/***********************************************/
+/* removable device additional commands */
+
+static int raw_is_inserted(BlockDriverState *bs)
+{
+    return 1;
+}
+
+static int raw_media_changed(BlockDriverState *bs)
+{
+    return -ENOTSUP;
+}
+
+static int raw_eject(BlockDriverState *bs, int eject_flag)
+{
+    DWORD ret_count;
+
+    if (s->type == FTYPE_FILE)
+        return -ENOTSUP;
+    if (eject_flag) {
+        DeviceIoControl(s->hfile, IOCTL_STORAGE_EJECT_MEDIA,
+                        NULL, 0, NULL, 0, &lpBytesReturned, NULL);
+    } else {
+        DeviceIoControl(s->hfile, IOCTL_STORAGE_LOAD_MEDIA,
+                        NULL, 0, NULL, 0, &lpBytesReturned, NULL);
+    }
+}
+
+static int raw_set_locked(BlockDriverState *bs, int locked)
+{
+    return -ENOTSUP;
+}
+#endif
+
 static int hdev_has_zero_init(BlockDriverState *bs)
 {
     return 0;
@@ -532,12 +440,11 @@ static BlockDriver bdrv_host_device = {
     .bdrv_probe_device	= hdev_probe_device,
     .bdrv_file_open	= hdev_open,
     .bdrv_close		= raw_close,
+    .bdrv_flush		= raw_flush,
     .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_getlength	= raw_getlength,
     .bdrv_get_allocated_file_size
                         = raw_get_allocated_file_size,

block/raw.c

@@ -9,37 +9,45 @@ static int raw_open(BlockDriverState *bs, int flags)
     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)
+static int raw_read(BlockDriverState *bs, int64_t sector_num,
+                    uint8_t *buf, int nb_sectors)
 {
-    return 0;
+    return bdrv_read(bs->file, sector_num, buf, nb_sectors);
 }
 
-static int coroutine_fn raw_co_readv(BlockDriverState *bs, int64_t sector_num,
-                                     int nb_sectors, QEMUIOVector *qiov)
+static int raw_write(BlockDriverState *bs, int64_t sector_num,
+                     const uint8_t *buf, int nb_sectors)
 {
-    BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
-    return bdrv_co_readv(bs->file, sector_num, nb_sectors, qiov);
+    return bdrv_write(bs->file, sector_num, buf, nb_sectors);
 }
 
-static int coroutine_fn raw_co_writev(BlockDriverState *bs, int64_t sector_num,
-                                      int nb_sectors, QEMUIOVector *qiov)
+static BlockDriverAIOCB *raw_aio_readv(BlockDriverState *bs,
+    int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+    BlockDriverCompletionFunc *cb, void *opaque)
 {
-    BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
-    return bdrv_co_writev(bs->file, sector_num, nb_sectors, qiov);
+    return bdrv_aio_readv(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
+}
+
+static BlockDriverAIOCB *raw_aio_writev(BlockDriverState *bs,
+    int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+    BlockDriverCompletionFunc *cb, void *opaque)
+{
+    return bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
 }
 
 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)
+static int raw_flush(BlockDriverState *bs)
 {
-    return bdrv_co_is_allocated(bs->file, sector_num, nb_sectors, pnum);
+    return bdrv_flush(bs->file);
+}
+
+static BlockDriverAIOCB *raw_aio_flush(BlockDriverState *bs,
+    BlockDriverCompletionFunc *cb, void *opaque)
+{
+    return bdrv_aio_flush(bs->file, cb, opaque);
 }
 
 static int64_t raw_getlength(BlockDriverState *bs)
@@ -57,10 +65,9 @@ static int raw_probe(const uint8_t *buf, int buf_size, const char *filename)
    return 1; /* everything can be opened as raw image */
 }
 
-static int coroutine_fn raw_co_discard(BlockDriverState *bs,
-                                       int64_t sector_num, int nb_sectors)
+static int raw_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors)
 {
-    return bdrv_co_discard(bs->file, sector_num, nb_sectors);
+    return bdrv_discard(bs->file, sector_num, nb_sectors);
 }
 
 static int raw_is_inserted(BlockDriverState *bs)
@@ -68,19 +75,15 @@ static int raw_is_inserted(BlockDriverState *bs)
     return bdrv_is_inserted(bs->file);
 }
 
-static int raw_media_changed(BlockDriverState *bs)
+static int raw_eject(BlockDriverState *bs, int eject_flag)
 {
-    return bdrv_media_changed(bs->file);
+    return bdrv_eject(bs->file, eject_flag);
 }
 
-static void raw_eject(BlockDriverState *bs, bool eject_flag)
+static int raw_set_locked(BlockDriverState *bs, int locked)
 {
-    bdrv_eject(bs->file, eject_flag);
-}
-
-static void raw_lock_medium(BlockDriverState *bs, bool locked)
-{
-    bdrv_lock_medium(bs->file, locked);
+    bdrv_set_locked(bs->file, locked);
+    return 0;
 }
 
 static int raw_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
@@ -117,28 +120,26 @@ static int raw_has_zero_init(BlockDriverState *bs)
 static BlockDriver bdrv_raw = {
     .format_name        = "raw",
 
-    /* It's really 0, but we need to make g_malloc() happy */
+    /* It's really 0, but we need to make qemu_malloc() happy */
     .instance_size      = 1,
 
     .bdrv_open          = raw_open,
     .bdrv_close         = raw_close,
-
-    .bdrv_reopen_prepare  = raw_reopen_prepare,
-
-    .bdrv_co_readv          = raw_co_readv,
-    .bdrv_co_writev         = raw_co_writev,
-    .bdrv_co_is_allocated   = raw_co_is_allocated,
-    .bdrv_co_discard        = raw_co_discard,
-
+    .bdrv_read          = raw_read,
+    .bdrv_write         = raw_write,
+    .bdrv_flush         = raw_flush,
     .bdrv_probe         = raw_probe,
     .bdrv_getlength     = raw_getlength,
     .bdrv_truncate      = raw_truncate,
 
-    .bdrv_is_inserted   = raw_is_inserted,
-    .bdrv_media_changed = raw_media_changed,
-    .bdrv_eject         = raw_eject,
-    .bdrv_lock_medium   = raw_lock_medium,
+    .bdrv_aio_readv     = raw_aio_readv,
+    .bdrv_aio_writev    = raw_aio_writev,
+    .bdrv_aio_flush     = raw_aio_flush,
+    .bdrv_discard       = raw_discard,
 
+    .bdrv_is_inserted   = raw_is_inserted,
+    .bdrv_eject         = raw_eject,
+    .bdrv_set_locked    = raw_set_locked,
     .bdrv_ioctl         = raw_ioctl,
     .bdrv_aio_ioctl     = raw_aio_ioctl,
 

block/rbd.c

@@ -7,50 +7,43 @@
  * 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 <inttypes.h>
 
 #include "qemu-common.h"
 #include "qemu-error.h"
+
 #include "block_int.h"
 
 #include <rbd/librbd.h>
 
+
+
 /*
  * When specifying the image filename use:
  *
  * rbd:poolname/devicename[@snapshotname][:option1=value1[:option2=value2...]]
  *
- * poolname must be the name of an existing rados pool.
+ * poolname must be the name of an existing rados pool
  *
- * devicename is the name of the rbd image.
+ * devicename is the basename for all objects used to
+ * emulate the raw device.
  *
- * Each option given is used to configure rados, and may be any valid
- * Ceph option, "id", or "conf".
+ * Each option given is used to configure rados, and may be
+ * any Ceph option, or "conf". The "conf" option specifies
+ * a Ceph configuration file to read.
  *
- * The "id" option indicates what user we should authenticate as to
- * the Ceph cluster.  If it is excluded we will use the Ceph default
- * (normally 'admin').
+ * Metadata information (image size, ...) is stored in an
+ * object with the name "devicename.rbd".
  *
- * The "conf" option specifies a Ceph configuration file to read.  If
- * it is not specified, we will read from the default Ceph locations
- * (e.g., /etc/ceph/ceph.conf).  To avoid reading _any_ configuration
- * file, specify conf=/dev/null.
+ * The raw device is split into 4MB sized objects by default.
+ * The sequencenumber is encoded in a 12 byte long hex-string,
+ * and is attached to the devicename, separated by a dot.
+ * e.g. "devicename.1234567890ab"
  *
- * Configuration values containing :, @, or = can be escaped with a
- * leading "\".
  */
 
-/* rbd_aio_discard added in 0.1.2 */
-#if LIBRBD_VERSION_CODE >= LIBRBD_VERSION(0, 1, 2)
-#define LIBRBD_SUPPORTS_DISCARD
-#else
-#undef LIBRBD_SUPPORTS_DISCARD
-#endif
-
 #define OBJ_MAX_SIZE (1UL << OBJ_DEFAULT_OBJ_ORDER)
 
 #define RBD_MAX_CONF_NAME_SIZE 128
@@ -60,19 +53,13 @@
 #define RBD_MAX_SNAP_NAME_SIZE 128
 #define RBD_MAX_SNAPS 100
 
-typedef enum {
-    RBD_AIO_READ,
-    RBD_AIO_WRITE,
-    RBD_AIO_DISCARD
-} RBDAIOCmd;
-
 typedef struct RBDAIOCB {
     BlockDriverAIOCB common;
     QEMUBH *bh;
-    int64_t ret;
+    int ret;
     QEMUIOVector *qiov;
     char *bounce;
-    RBDAIOCmd cmd;
+    int write;
     int64_t sector_num;
     int error;
     struct BDRVRBDState *s;
@@ -86,7 +73,7 @@ typedef struct RADOSCB {
     int done;
     int64_t size;
     char *buf;
-    int64_t ret;
+    int ret;
 } RADOSCB;
 
 #define RBD_FD_READ 0
@@ -117,15 +104,8 @@ static int qemu_rbd_next_tok(char *dst, int dst_len,
     *p = NULL;
 
     if (delim != '\0') {
-        for (end = src; *end; ++end) {
-            if (*end == delim) {
-                break;
-            }
-            if (*end == '\\' && end[1] != '\0') {
-                end++;
-            }
-        }
-        if (*end == delim) {
+        end = strchr(src, delim);
+        if (end) {
             *p = end + 1;
             *end = '\0';
         }
@@ -144,19 +124,6 @@ static int qemu_rbd_next_tok(char *dst, int dst_len,
     return 0;
 }
 
-static void qemu_rbd_unescape(char *src)
-{
-    char *p;
-
-    for (p = src; *src; ++src, ++p) {
-        if (*src == '\\' && src[1] != '\0') {
-            src++;
-        }
-        *p = *src;
-    }
-    *p = '\0';
-}
-
 static int qemu_rbd_parsename(const char *filename,
                               char *pool, int pool_len,
                               char *snap, int snap_len,
@@ -171,7 +138,7 @@ static int qemu_rbd_parsename(const char *filename,
         return -EINVAL;
     }
 
-    buf = g_strdup(start);
+    buf = qemu_strdup(start);
     p = buf;
     *snap = '\0';
     *conf = '\0';
@@ -181,7 +148,6 @@ static int qemu_rbd_parsename(const char *filename,
         ret = -EINVAL;
         goto done;
     }
-    qemu_rbd_unescape(pool);
 
     if (strchr(p, '@')) {
         ret = qemu_rbd_next_tok(name, name_len, p, '@', "object name", &p);
@@ -189,11 +155,9 @@ static int qemu_rbd_parsename(const char *filename,
             goto done;
         }
         ret = qemu_rbd_next_tok(snap, snap_len, p, ':', "snap name", &p);
-        qemu_rbd_unescape(snap);
     } else {
         ret = qemu_rbd_next_tok(name, name_len, p, ':', "object name", &p);
     }
-    qemu_rbd_unescape(name);
     if (ret < 0 || !p) {
         goto done;
     }
@@ -201,38 +165,10 @@ static int qemu_rbd_parsename(const char *filename,
     ret = qemu_rbd_next_tok(conf, conf_len, p, '\0', "configuration", &p);
 
 done:
-    g_free(buf);
+    qemu_free(buf);
     return ret;
 }
 
-static char *qemu_rbd_parse_clientname(const char *conf, char *clientname)
-{
-    const char *p = conf;
-
-    while (*p) {
-        int len;
-        const char *end = strchr(p, ':');
-
-        if (end) {
-            len = end - p;
-        } else {
-            len = strlen(p);
-        }
-
-        if (strncmp(p, "id=", 3) == 0) {
-            len -= 3;
-            strncpy(clientname, p + 3, len);
-            clientname[len] = '\0';
-            return clientname;
-        }
-        if (end == NULL) {
-            break;
-        }
-        p = end + 1;
-    }
-    return NULL;
-}
-
 static int qemu_rbd_set_conf(rados_t cluster, const char *conf)
 {
     char *p, *buf;
@@ -240,7 +176,7 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf)
     char value[RBD_MAX_CONF_VAL_SIZE];
     int ret = 0;
 
-    buf = g_strdup(conf);
+    buf = qemu_strdup(conf);
     p = buf;
 
     while (p) {
@@ -249,7 +185,6 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf)
         if (ret < 0) {
             break;
         }
-        qemu_rbd_unescape(name);
 
         if (!p) {
             error_report("conf option %s has no value", name);
@@ -262,27 +197,24 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf)
         if (ret < 0) {
             break;
         }
-        qemu_rbd_unescape(value);
 
-        if (strcmp(name, "conf") == 0) {
-            ret = rados_conf_read_file(cluster, value);
-            if (ret < 0) {
-                error_report("error reading conf file %s", value);
-                break;
-            }
-        } else if (strcmp(name, "id") == 0) {
-            /* ignore, this is parsed by qemu_rbd_parse_clientname() */
-        } else {
+        if (strcmp(name, "conf")) {
             ret = rados_conf_set(cluster, name, value);
             if (ret < 0) {
                 error_report("invalid conf option %s", name);
                 ret = -EINVAL;
                 break;
             }
+        } else {
+            ret = rados_conf_read_file(cluster, value);
+            if (ret < 0) {
+                error_report("error reading conf file %s", value);
+                break;
+            }
         }
     }
 
-    g_free(buf);
+    qemu_free(buf);
     return ret;
 }
 
@@ -295,8 +227,6 @@ static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options)
     char name[RBD_MAX_IMAGE_NAME_SIZE];
     char snap_buf[RBD_MAX_SNAP_NAME_SIZE];
     char conf[RBD_MAX_CONF_SIZE];
-    char clientname_buf[RBD_MAX_CONF_SIZE];
-    char *clientname;
     rados_t cluster;
     rados_ioctx_t io_ctx;
     int ret;
@@ -329,15 +259,17 @@ static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options)
         options++;
     }
 
-    clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
-    if (rados_create(&cluster, clientname) < 0) {
+    if (rados_create(&cluster, NULL) < 0) {
         error_report("error initializing");
         return -EIO;
     }
 
     if (strstr(conf, "conf=") == NULL) {
-        /* try default location, but ignore failure */
-        rados_conf_read_file(cluster, NULL);
+        if (rados_conf_read_file(cluster, NULL) < 0) {
+            error_report("error reading config file");
+            rados_shutdown(cluster);
+            return -EIO;
+        }
     }
 
     if (conf[0] != '\0' &&
@@ -384,8 +316,7 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
 
     r = rcb->ret;
 
-    if (acb->cmd == RBD_AIO_WRITE ||
-        acb->cmd == RBD_AIO_DISCARD) {
+    if (acb->write) {
         if (r < 0) {
             acb->ret = r;
             acb->error = 1;
@@ -410,7 +341,7 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
     acb->bh = qemu_bh_new(rbd_aio_bh_cb, acb);
     qemu_bh_schedule(acb->bh);
 done:
-    g_free(rcb);
+    qemu_free(rcb);
 }
 
 /*
@@ -427,14 +358,15 @@ static void qemu_rbd_aio_event_reader(void *opaque)
         char *p = (char *)&s->event_rcb;
 
         /* now read the rcb pointer that was sent from a non qemu thread */
-        ret = read(s->fds[RBD_FD_READ], p + s->event_reader_pos,
-                   sizeof(s->event_rcb) - s->event_reader_pos);
-        if (ret > 0) {
-            s->event_reader_pos += ret;
-            if (s->event_reader_pos == sizeof(s->event_rcb)) {
-                s->event_reader_pos = 0;
-                qemu_rbd_complete_aio(s->event_rcb);
-                s->qemu_aio_count--;
+        if ((ret = read(s->fds[RBD_FD_READ], p + s->event_reader_pos,
+                        sizeof(s->event_rcb) - s->event_reader_pos)) > 0) {
+            if (ret > 0) {
+                s->event_reader_pos += ret;
+                if (s->event_reader_pos == sizeof(s->event_rcb)) {
+                    s->event_reader_pos = 0;
+                    qemu_rbd_complete_aio(s->event_rcb);
+                    s->qemu_aio_count--;
+                }
             }
         }
     } while (ret < 0 && errno == EINTR);
@@ -453,8 +385,6 @@ static int qemu_rbd_open(BlockDriverState *bs, const char *filename, int flags)
     char pool[RBD_MAX_POOL_NAME_SIZE];
     char snap_buf[RBD_MAX_SNAP_NAME_SIZE];
     char conf[RBD_MAX_CONF_SIZE];
-    char clientname_buf[RBD_MAX_CONF_SIZE];
-    char *clientname;
     int r;
 
     if (qemu_rbd_parsename(filename, pool, sizeof(pool),
@@ -463,61 +393,55 @@ static int qemu_rbd_open(BlockDriverState *bs, const char *filename, int flags)
                            conf, sizeof(conf)) < 0) {
         return -EINVAL;
     }
+    s->snap = NULL;
+    if (snap_buf[0] != '\0') {
+        s->snap = qemu_strdup(snap_buf);
+    }
 
-    clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
-    r = rados_create(&s->cluster, clientname);
+    r = rados_create(&s->cluster, NULL);
     if (r < 0) {
         error_report("error initializing");
         return r;
     }
 
-    s->snap = NULL;
-    if (snap_buf[0] != '\0') {
-        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);
+        r = rados_conf_read_file(s->cluster, NULL);
+        if (r < 0) {
+            error_report("error reading config file");
+            rados_shutdown(s->cluster);
+            return r;
+        }
     }
 
     if (conf[0] != '\0') {
         r = qemu_rbd_set_conf(s->cluster, conf);
         if (r < 0) {
             error_report("error setting config options");
-            goto failed_shutdown;
+            rados_shutdown(s->cluster);
+            return r;
         }
     }
 
     r = rados_connect(s->cluster);
     if (r < 0) {
         error_report("error connecting");
-        goto failed_shutdown;
+        rados_shutdown(s->cluster);
+        return r;
     }
 
     r = rados_ioctx_create(s->cluster, pool, &s->io_ctx);
     if (r < 0) {
         error_report("error opening pool %s", pool);
-        goto failed_shutdown;
+        rados_shutdown(s->cluster);
+        return r;
     }
 
     r = rbd_open(s->io_ctx, s->name, &s->image, s->snap);
     if (r < 0) {
         error_report("error reading header from %s", s->name);
-        goto failed_open;
+        rados_ioctx_destroy(s->io_ctx);
+        rados_shutdown(s->cluster);
+        return r;
     }
 
     bs->read_only = (s->snap != NULL);
@@ -531,18 +455,15 @@ static int qemu_rbd_open(BlockDriverState *bs, const char *filename, int flags)
     fcntl(s->fds[0], F_SETFL, O_NONBLOCK);
     fcntl(s->fds[1], F_SETFL, O_NONBLOCK);
     qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], qemu_rbd_aio_event_reader,
-                            NULL, qemu_rbd_aio_flush_cb, s);
+                            NULL, qemu_rbd_aio_flush_cb, NULL, s);
 
 
     return 0;
 
 failed:
     rbd_close(s->image);
-failed_open:
     rados_ioctx_destroy(s->io_ctx);
-failed_shutdown:
     rados_shutdown(s->cluster);
-    g_free(s->snap);
     return r;
 }
 
@@ -552,11 +473,12 @@ static void qemu_rbd_close(BlockDriverState *bs)
 
     close(s->fds[0]);
     close(s->fds[1]);
-    qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], NULL, NULL, NULL, NULL);
+    qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], NULL , NULL, NULL, NULL,
+        NULL);
 
     rbd_close(s->image);
     rados_ioctx_destroy(s->io_ctx);
-    g_free(s->snap);
+    qemu_free(s->snap);
     rados_shutdown(s->cluster);
 }
 
@@ -570,7 +492,7 @@ static void qemu_rbd_aio_cancel(BlockDriverAIOCB *blockacb)
     acb->cancelled = 1;
 }
 
-static const AIOCBInfo rbd_aiocb_info = {
+static AIOPool rbd_aio_pool = {
     .aiocb_size = sizeof(RBDAIOCB),
     .cancel = qemu_rbd_aio_cancel,
 };
@@ -622,7 +544,7 @@ static void rbd_finish_aiocb(rbd_completion_t c, RADOSCB *rcb)
     ret = qemu_rbd_send_pipe(rcb->s, rcb);
     if (ret < 0) {
         error_report("failed writing to acb->s->fds");
-        g_free(rcb);
+        qemu_free(rcb);
     }
 }
 
@@ -632,8 +554,8 @@ 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);
+    if (!acb->write) {
+        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));
@@ -643,25 +565,12 @@ static void rbd_aio_bh_cb(void *opaque)
     qemu_aio_release(acb);
 }
 
-static int rbd_aio_discard_wrapper(rbd_image_t image,
-                                   uint64_t off,
-                                   uint64_t len,
-                                   rbd_completion_t comp)
-{
-#ifdef LIBRBD_SUPPORTS_DISCARD
-    return rbd_aio_discard(image, off, len, comp);
-#else
-    return -ENOTSUP;
-#endif
-}
-
-static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
-                                       int64_t sector_num,
-                                       QEMUIOVector *qiov,
-                                       int nb_sectors,
-                                       BlockDriverCompletionFunc *cb,
-                                       void *opaque,
-                                       RBDAIOCmd cmd)
+static BlockDriverAIOCB *rbd_aio_rw_vector(BlockDriverState *bs,
+                                           int64_t sector_num,
+                                           QEMUIOVector *qiov,
+                                           int nb_sectors,
+                                           BlockDriverCompletionFunc *cb,
+                                           void *opaque, int write)
 {
     RBDAIOCB *acb;
     RADOSCB *rcb;
@@ -672,22 +581,21 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
 
     BDRVRBDState *s = bs->opaque;
 
-    acb = qemu_aio_get(&rbd_aiocb_info, bs, cb, opaque);
-    acb->cmd = cmd;
-    acb->qiov = qiov;
-    if (cmd == RBD_AIO_DISCARD) {
-        acb->bounce = NULL;
-    } else {
-        acb->bounce = qemu_blockalign(bs, qiov->size);
+    acb = qemu_aio_get(&rbd_aio_pool, bs, cb, opaque);
+    if (!acb) {
+        return NULL;
     }
+    acb->write = write;
+    acb->qiov = qiov;
+    acb->bounce = qemu_blockalign(bs, qiov->size);
     acb->ret = 0;
     acb->error = 0;
     acb->s = s;
     acb->cancelled = 0;
     acb->bh = NULL;
 
-    if (cmd == RBD_AIO_WRITE) {
-        qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
+    if (write) {
+        qemu_iovec_to_buffer(acb->qiov, acb->bounce);
     }
 
     buf = acb->bounce;
@@ -697,7 +605,7 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
 
     s->qemu_aio_count++; /* All the RADOSCB */
 
-    rcb = g_malloc(sizeof(RADOSCB));
+    rcb = qemu_malloc(sizeof(RADOSCB));
     rcb->done = 0;
     rcb->acb = acb;
     rcb->buf = buf;
@@ -708,18 +616,10 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
         goto failed;
     }
 
-    switch (cmd) {
-    case RBD_AIO_WRITE:
+    if (write) {
         r = rbd_aio_write(s->image, off, size, buf, c);
-        break;
-    case RBD_AIO_READ:
+    } else {
         r = rbd_aio_read(s->image, off, size, buf, c);
-        break;
-    case RBD_AIO_DISCARD:
-        r = rbd_aio_discard_wrapper(s->image, off, size, c);
-        break;
-    default:
-        r = -EINVAL;
     }
 
     if (r < 0) {
@@ -729,7 +629,7 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
     return &acb->common;
 
 failed:
-    g_free(rcb);
+    qemu_free(rcb);
     s->qemu_aio_count--;
     qemu_aio_release(acb);
     return NULL;
@@ -742,8 +642,7 @@ static BlockDriverAIOCB *qemu_rbd_aio_readv(BlockDriverState *bs,
                                             BlockDriverCompletionFunc *cb,
                                             void *opaque)
 {
-    return rbd_start_aio(bs, sector_num, qiov, nb_sectors, cb, opaque,
-                         RBD_AIO_READ);
+    return rbd_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
 }
 
 static BlockDriverAIOCB *qemu_rbd_aio_writev(BlockDriverState *bs,
@@ -753,19 +652,7 @@ static BlockDriverAIOCB *qemu_rbd_aio_writev(BlockDriverState *bs,
                                              BlockDriverCompletionFunc *cb,
                                              void *opaque)
 {
-    return rbd_start_aio(bs, sector_num, qiov, nb_sectors, cb, opaque,
-                         RBD_AIO_WRITE);
-}
-
-static int qemu_rbd_co_flush(BlockDriverState *bs)
-{
-#if LIBRBD_VERSION_CODE >= LIBRBD_VERSION(0, 1, 1)
-    /* rbd_flush added in 0.1.1 */
-    BDRVRBDState *s = bs->opaque;
-    return rbd_flush(s->image);
-#else
-    return 0;
-#endif
+    return rbd_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque, 1);
 }
 
 static int qemu_rbd_getinfo(BlockDriverState *bs, BlockDriverInfo *bdi)
@@ -842,26 +729,6 @@ static int qemu_rbd_snap_create(BlockDriverState *bs,
     return 0;
 }
 
-static int qemu_rbd_snap_remove(BlockDriverState *bs,
-                                const char *snapshot_name)
-{
-    BDRVRBDState *s = bs->opaque;
-    int r;
-
-    r = rbd_snap_remove(s->image, snapshot_name);
-    return r;
-}
-
-static int qemu_rbd_snap_rollback(BlockDriverState *bs,
-                                  const char *snapshot_name)
-{
-    BDRVRBDState *s = bs->opaque;
-    int r;
-
-    r = rbd_snap_rollback(s->image, snapshot_name);
-    return r;
-}
-
 static int qemu_rbd_snap_list(BlockDriverState *bs,
                               QEMUSnapshotInfo **psn_tab)
 {
@@ -872,18 +739,18 @@ static int qemu_rbd_snap_list(BlockDriverState *bs,
     int max_snaps = RBD_MAX_SNAPS;
 
     do {
-        snaps = g_malloc(sizeof(*snaps) * max_snaps);
+        snaps = qemu_malloc(sizeof(*snaps) * max_snaps);
         snap_count = rbd_snap_list(s->image, snaps, &max_snaps);
         if (snap_count < 0) {
-            g_free(snaps);
+            qemu_free(snaps);
         }
     } while (snap_count == -ERANGE);
 
     if (snap_count <= 0) {
-        goto done;
+        return snap_count;
     }
 
-    sn_tab = g_malloc0(snap_count * sizeof(QEMUSnapshotInfo));
+    sn_tab = qemu_mallocz(snap_count * sizeof(QEMUSnapshotInfo));
 
     for (i = 0; i < snap_count; i++) {
         const char *snap_name = snaps[i].name;
@@ -899,23 +766,10 @@ static int qemu_rbd_snap_list(BlockDriverState *bs,
     }
     rbd_snap_list_end(snaps);
 
- done:
     *psn_tab = sn_tab;
     return snap_count;
 }
 
-#ifdef LIBRBD_SUPPORTS_DISCARD
-static BlockDriverAIOCB* qemu_rbd_aio_discard(BlockDriverState *bs,
-                                              int64_t sector_num,
-                                              int nb_sectors,
-                                              BlockDriverCompletionFunc *cb,
-                                              void *opaque)
-{
-    return rbd_start_aio(bs, sector_num, NULL, nb_sectors, cb, opaque,
-                         RBD_AIO_DISCARD);
-}
-#endif
-
 static QEMUOptionParameter qemu_rbd_create_options[] = {
     {
      .name = BLOCK_OPT_SIZE,
@@ -942,18 +796,11 @@ static BlockDriver bdrv_rbd = {
     .bdrv_truncate      = qemu_rbd_truncate,
     .protocol_name      = "rbd",
 
-    .bdrv_aio_readv         = qemu_rbd_aio_readv,
-    .bdrv_aio_writev        = qemu_rbd_aio_writev,
-    .bdrv_co_flush_to_disk  = qemu_rbd_co_flush,
+    .bdrv_aio_readv     = qemu_rbd_aio_readv,
+    .bdrv_aio_writev    = qemu_rbd_aio_writev,
 
-#ifdef LIBRBD_SUPPORTS_DISCARD
-    .bdrv_aio_discard       = qemu_rbd_aio_discard,
-#endif
-
-    .bdrv_snapshot_create   = qemu_rbd_snap_create,
-    .bdrv_snapshot_delete   = qemu_rbd_snap_remove,
-    .bdrv_snapshot_list     = qemu_rbd_snap_list,
-    .bdrv_snapshot_goto     = qemu_rbd_snap_rollback,
+    .bdrv_snapshot_create = qemu_rbd_snap_create,
+    .bdrv_snapshot_list = qemu_rbd_snap_list,
 };
 
 static void bdrv_rbd_init(void)

block/stream.c

@@ -1,236 +0,0 @@
-/*
- * Image streaming
- *
- * Copyright IBM, Corp. 2011
- *
- * Authors:
- *  Stefan Hajnoczi   <stefanha@linux.vnet.ibm.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_int.h"
-#include "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.
-     */
-    STREAM_BUFFER_SIZE = 512 * 1024, /* in bytes */
-};
-
-#define SLICE_TIME 100000000ULL /* ns */
-
-typedef struct StreamBlockJob {
-    BlockJob common;
-    RateLimit limit;
-    BlockDriverState *base;
-    BlockdevOnError on_error;
-    char backing_file_id[1024];
-} StreamBlockJob;
-
-static int coroutine_fn stream_populate(BlockDriverState *bs,
-                                        int64_t sector_num, int nb_sectors,
-                                        void *buf)
-{
-    struct iovec iov = {
-        .iov_base = buf,
-        .iov_len  = nb_sectors * BDRV_SECTOR_SIZE,
-    };
-    QEMUIOVector qiov;
-
-    qemu_iovec_init_external(&qiov, &iov, 1);
-
-    /* Copy-on-read the unallocated clusters */
-    return bdrv_co_copy_on_readv(bs, sector_num, nb_sectors, &qiov);
-}
-
-static void close_unused_images(BlockDriverState *top, BlockDriverState *base,
-                                const char *base_id)
-{
-    BlockDriverState *intermediate;
-    intermediate = top->backing_hd;
-
-    while (intermediate) {
-        BlockDriverState *unused;
-
-        /* reached base */
-        if (intermediate == base) {
-            break;
-        }
-
-        unused = intermediate;
-        intermediate = intermediate->backing_hd;
-        unused->backing_hd = NULL;
-        bdrv_delete(unused);
-    }
-    top->backing_hd = base;
-}
-
-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);
-        return;
-    }
-
-    end = s->common.len >> BDRV_SECTOR_BITS;
-    buf = qemu_blockalign(bs, STREAM_BUFFER_SIZE);
-
-    /* Turn on copy-on-read for the whole block device so that guest read
-     * requests help us make progress.  Only do this when copying the entire
-     * backing chain since the copy-on-read operation does not take base into
-     * account.
-     */
-    if (!base) {
-        bdrv_enable_copy_on_read(bs);
-    }
-
-    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 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);
-        }
-        trace_stream_one_iteration(s, sector_num, n, ret);
-        if (ret >= 0 && copy) {
-            if (s->common.speed) {
-                delay_ns = ratelimit_calculate_delay(&s->limit, n);
-                if (delay_ns > 0) {
-                    goto 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;
-            }
-        }
-        ret = 0;
-
-        /* Publish progress */
-        s->common.offset += n * BDRV_SECTOR_SIZE;
-    }
-
-    if (!base) {
-        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) {
-            base_id = s->backing_file_id;
-            if (base->drv) {
-                base_fmt = base->drv->format_name;
-            }
-        }
-        ret = bdrv_change_backing_file(bs, base_id, base_fmt);
-        close_unused_images(bs, base, base_id);
-    }
-
-    qemu_vfree(buf);
-    block_job_completed(&s->common, ret);
-}
-
-static void stream_set_speed(BlockJob *job, int64_t speed, Error **errp)
-{
-    StreamBlockJob *s = container_of(job, StreamBlockJob, common);
-
-    if (speed < 0) {
-        error_set(errp, QERR_INVALID_PARAMETER, "speed");
-        return;
-    }
-    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
-}
-
-static BlockJobType stream_job_type = {
-    .instance_size = sizeof(StreamBlockJob),
-    .job_type      = "stream",
-    .set_speed     = stream_set_speed,
-};
-
-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;
-    }
-
-    s->base = base;
-    if (base_id) {
-        pstrcpy(s->backing_file_id, sizeof(s->backing_file_id), base_id);
-    }
-
-    s->on_error = on_error;
-    s->common.co = qemu_coroutine_create(stream_run);
-    trace_stream_start(bs, base, s, s->common.co, opaque);
-    qemu_coroutine_enter(s->common.co, s);
-}

block/vdi.c

@@ -1,7 +1,7 @@
 /*
  * Block driver for the Virtual Disk Image (VDI) format
  *
- * Copyright (c) 2009, 2012 Stefan Weil
+ * Copyright (c) 2009 Stefan Weil
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -52,7 +52,6 @@
 #include "qemu-common.h"
 #include "block_int.h"
 #include "module.h"
-#include "migration.h"
 
 #if defined(CONFIG_UUID)
 #include <uuid/uuid.h>
@@ -60,6 +59,9 @@
 /* TODO: move uuid emulation to some central place in QEMU. */
 #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. */
@@ -112,27 +114,22 @@ typedef unsigned char uuid_t[16];
  */
 #define VDI_TEXT "<<< QEMU VM Virtual Disk Image >>>\n"
 
-/* A never-allocated block; semantically arbitrary content. */
-#define VDI_UNALLOCATED 0xffffffffU
-
-/* A discarded (no longer allocated) block; semantically zero-filled. */
-#define VDI_DISCARDED   0xfffffffeU
-
-#define VDI_IS_ALLOCATED(X) ((X) < VDI_DISCARDED)
+/* Unallocated blocks use this index (no need to convert endianness). */
+#define VDI_UNALLOCATED UINT32_MAX
 
 #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],
@@ -140,6 +137,29 @@ static inline void uuid_unparse(const uuid_t uu, char *out)
 }
 #endif
 
+typedef struct {
+    BlockDriverAIOCB common;
+    int64_t sector_num;
+    QEMUIOVector *qiov;
+    uint8_t *buf;
+    /* Total number of sectors. */
+    int nb_sectors;
+    /* Number of sectors for current AIO. */
+    int n_sectors;
+    /* New allocated block map entry. */
+    uint32_t bmap_first;
+    uint32_t bmap_last;
+    /* Buffer for new allocated block. */
+    void *block_buffer;
+    void *orig_buf;
+    bool is_write;
+    int header_modified;
+    BlockDriverAIOCB *hd_aiocb;
+    struct iovec hd_iov;
+    QEMUIOVector hd_qiov;
+    QEMUBH *bh;
+} VdiAIOCB;
+
 typedef struct {
     char text[0x40];
     uint32_t signature;
@@ -178,8 +198,6 @@ typedef struct {
     uint32_t bmap_sector;
     /* VDI header (converted to host endianness). */
     VdiHeader header;
-
-    Error *migration_blocker;
 } BDRVVdiState;
 
 /* Change UUID from little endian (IPRT = VirtualBox format) to big endian
@@ -274,8 +292,7 @@ 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;
@@ -284,20 +301,16 @@ 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));
+    bmap = qemu_malloc(s->header.blocks_in_image * sizeof(uint32_t));
     memset(bmap, 0xff, s->header.blocks_in_image * sizeof(uint32_t));
 
     /* Check block map and value of blocks_allocated. */
     for (block = 0; block < s->header.blocks_in_image; block++) {
         uint32_t bmap_entry = le32_to_cpu(s->bmap[block]);
-        if (VDI_IS_ALLOCATED(bmap_entry)) {
+        if (bmap_entry != VDI_UNALLOCATED) {
             if (bmap_entry < s->header.blocks_in_image) {
                 blocks_allocated++;
-                if (!VDI_IS_ALLOCATED(bmap[bmap_entry])) {
+                if (bmap[bmap_entry] == VDI_UNALLOCATED) {
                     bmap[bmap_entry] = bmap_entry;
                 } else {
                     fprintf(stderr, "ERROR: block index %" PRIu32
@@ -318,7 +331,7 @@ static int vdi_check(BlockDriverState *bs, BdrvCheckResult *res,
         res->corruptions++;
     }
 
-    g_free(bmap);
+    qemu_free(bmap);
 
     return 0;
 }
@@ -430,35 +443,23 @@ static int vdi_open(BlockDriverState *bs, int flags)
     bmap_size = header.blocks_in_image * sizeof(uint32_t);
     bmap_size = (bmap_size + SECTOR_SIZE - 1) / SECTOR_SIZE;
     if (bmap_size > 0) {
-        s->bmap = g_malloc(bmap_size * SECTOR_SIZE);
+        s->bmap = qemu_malloc(bmap_size * SECTOR_SIZE);
     }
     if (bdrv_read(bs->file, s->bmap_sector, (uint8_t *)s->bmap, bmap_size) < 0) {
         goto fail_free_bmap;
     }
 
-    /* Disable migration when vdi images are used */
-    error_set(&s->migration_blocker,
-              QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
-              "vdi", bs->device_name, "live migration");
-    migrate_add_blocker(s->migration_blocker);
-
     return 0;
 
  fail_free_bmap:
-    g_free(s->bmap);
+    qemu_free(s->bmap);
 
  fail:
     return -1;
 }
 
-static int vdi_reopen_prepare(BDRVReopenState *state,
-                              BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
-}
-
-static int coroutine_fn vdi_co_is_allocated(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *pnum)
+static int vdi_is_allocated(BlockDriverState *bs, int64_t sector_num,
+                             int nb_sectors, int *pnum)
 {
     /* TODO: Check for too large sector_num (in bdrv_is_allocated or here). */
     BDRVVdiState *s = (BDRVVdiState *)bs->opaque;
@@ -471,153 +472,361 @@ static int coroutine_fn vdi_co_is_allocated(BlockDriverState *bs,
         n_sectors = nb_sectors;
     }
     *pnum = n_sectors;
-    return VDI_IS_ALLOCATED(bmap_entry);
+    return bmap_entry != VDI_UNALLOCATED;
 }
 
-static int vdi_co_read(BlockDriverState *bs,
-        int64_t sector_num, uint8_t *buf, int nb_sectors)
+static void vdi_aio_cancel(BlockDriverAIOCB *blockacb)
 {
-    BDRVVdiState *s = bs->opaque;
-    uint32_t bmap_entry;
-    uint32_t block_index;
-    uint32_t sector_in_block;
-    uint32_t n_sectors;
-    int ret = 0;
-
+    /* TODO: This code is untested. How can I get it executed? */
+    VdiAIOCB *acb = container_of(blockacb, VdiAIOCB, common);
     logout("\n");
-
-    while (ret >= 0 && nb_sectors > 0) {
-        block_index = sector_num / s->block_sectors;
-        sector_in_block = sector_num % s->block_sectors;
-        n_sectors = s->block_sectors - sector_in_block;
-        if (n_sectors > nb_sectors) {
-            n_sectors = nb_sectors;
-        }
-
-        logout("will read %u sectors starting at sector %" PRIu64 "\n",
-               n_sectors, sector_num);
-
-        /* prepare next AIO request */
-        bmap_entry = le32_to_cpu(s->bmap[block_index]);
-        if (!VDI_IS_ALLOCATED(bmap_entry)) {
-            /* Block not allocated, return zeros, no need to wait. */
-            memset(buf, 0, n_sectors * SECTOR_SIZE);
-            ret = 0;
-        } else {
-            uint64_t offset = s->header.offset_data / SECTOR_SIZE +
-                              (uint64_t)bmap_entry * s->block_sectors +
-                              sector_in_block;
-            ret = bdrv_read(bs->file, offset, buf, n_sectors);
-        }
-        logout("%u sectors read\n", n_sectors);
-
-        nb_sectors -= n_sectors;
-        sector_num += n_sectors;
-        buf += n_sectors * SECTOR_SIZE;
+    if (acb->hd_aiocb) {
+        bdrv_aio_cancel(acb->hd_aiocb);
     }
-
-    return ret;
+    qemu_aio_release(acb);
 }
 
-static int vdi_co_write(BlockDriverState *bs,
-        int64_t sector_num, const uint8_t *buf, int nb_sectors)
+static AIOPool vdi_aio_pool = {
+    .aiocb_size = sizeof(VdiAIOCB),
+    .cancel = vdi_aio_cancel,
+};
+
+static VdiAIOCB *vdi_aio_setup(BlockDriverState *bs, int64_t sector_num,
+        QEMUIOVector *qiov, int nb_sectors,
+        BlockDriverCompletionFunc *cb, void *opaque, int is_write)
 {
-    BDRVVdiState *s = bs->opaque;
-    uint32_t bmap_entry;
-    uint32_t block_index;
-    uint32_t sector_in_block;
-    uint32_t n_sectors;
-    uint32_t bmap_first = VDI_UNALLOCATED;
-    uint32_t bmap_last = VDI_UNALLOCATED;
-    uint8_t *block = NULL;
-    int ret = 0;
+    VdiAIOCB *acb;
 
-    logout("\n");
+    logout("%p, %" PRId64 ", %p, %d, %p, %p, %d\n",
+           bs, sector_num, qiov, nb_sectors, cb, opaque, is_write);
 
-    while (ret >= 0 && nb_sectors > 0) {
-        block_index = sector_num / s->block_sectors;
-        sector_in_block = sector_num % s->block_sectors;
-        n_sectors = s->block_sectors - sector_in_block;
-        if (n_sectors > nb_sectors) {
-            n_sectors = nb_sectors;
-        }
+    acb = qemu_aio_get(&vdi_aio_pool, bs, cb, opaque);
+    if (acb) {
+        acb->hd_aiocb = NULL;
+        acb->sector_num = sector_num;
+        acb->qiov = qiov;
+        acb->is_write = is_write;
 
-        logout("will write %u sectors starting at sector %" PRIu64 "\n",
-               n_sectors, sector_num);
-
-        /* prepare next AIO request */
-        bmap_entry = le32_to_cpu(s->bmap[block_index]);
-        if (!VDI_IS_ALLOCATED(bmap_entry)) {
-            /* Allocate new block and write to it. */
-            uint64_t offset;
-            bmap_entry = s->header.blocks_allocated;
-            s->bmap[block_index] = cpu_to_le32(bmap_entry);
-            s->header.blocks_allocated++;
-            offset = s->header.offset_data / SECTOR_SIZE +
-                     (uint64_t)bmap_entry * s->block_sectors;
-            if (block == NULL) {
-                block = g_malloc(s->block_size);
-                bmap_first = block_index;
+        if (qiov->niov > 1) {
+            acb->buf = qemu_blockalign(bs, qiov->size);
+            acb->orig_buf = acb->buf;
+            if (is_write) {
+                qemu_iovec_to_buffer(qiov, acb->buf);
             }
-            bmap_last = block_index;
-            /* Copy data to be written to new block and zero unused parts. */
-            memset(block, 0, sector_in_block * SECTOR_SIZE);
-            memcpy(block + sector_in_block * SECTOR_SIZE,
-                   buf, n_sectors * SECTOR_SIZE);
-            memset(block + (sector_in_block + n_sectors) * SECTOR_SIZE, 0,
-                   (s->block_sectors - n_sectors - sector_in_block) * SECTOR_SIZE);
-            ret = bdrv_write(bs->file, offset, block, s->block_sectors);
         } else {
-            uint64_t offset = s->header.offset_data / SECTOR_SIZE +
-                              (uint64_t)bmap_entry * s->block_sectors +
-                              sector_in_block;
-            ret = bdrv_write(bs->file, offset, buf, n_sectors);
+            acb->buf = (uint8_t *)qiov->iov->iov_base;
         }
+        acb->nb_sectors = nb_sectors;
+        acb->n_sectors = 0;
+        acb->bmap_first = VDI_UNALLOCATED;
+        acb->bmap_last = VDI_UNALLOCATED;
+        acb->block_buffer = NULL;
+        acb->header_modified = 0;
+    }
+    return acb;
+}
 
-        nb_sectors -= n_sectors;
-        sector_num += n_sectors;
-        buf += n_sectors * SECTOR_SIZE;
+static int vdi_schedule_bh(QEMUBHFunc *cb, VdiAIOCB *acb)
+{
+    logout("\n");
 
-        logout("%u sectors written\n", n_sectors);
+    if (acb->bh) {
+        return -EIO;
     }
 
-    logout("finished data write\n");
+    acb->bh = qemu_bh_new(cb, acb);
+    if (!acb->bh) {
+        return -EIO;
+    }
+
+    qemu_bh_schedule(acb->bh);
+
+    return 0;
+}
+
+static void vdi_aio_read_cb(void *opaque, int ret);
+static void vdi_aio_write_cb(void *opaque, int ret);
+
+static void vdi_aio_rw_bh(void *opaque)
+{
+    VdiAIOCB *acb = opaque;
+    logout("\n");
+    qemu_bh_delete(acb->bh);
+    acb->bh = NULL;
+
+    if (acb->is_write) {
+        vdi_aio_write_cb(opaque, 0);
+    } else {
+        vdi_aio_read_cb(opaque, 0);
+    }
+}
+
+static void vdi_aio_read_cb(void *opaque, int ret)
+{
+    VdiAIOCB *acb = opaque;
+    BlockDriverState *bs = acb->common.bs;
+    BDRVVdiState *s = bs->opaque;
+    uint32_t bmap_entry;
+    uint32_t block_index;
+    uint32_t sector_in_block;
+    uint32_t n_sectors;
+
+    logout("%u sectors read\n", acb->n_sectors);
+
+    acb->hd_aiocb = NULL;
+
     if (ret < 0) {
-        return ret;
+        goto done;
     }
 
-    if (block) {
-        /* One or more new blocks were allocated. */
-        VdiHeader *header = (VdiHeader *) block;
-        uint8_t *base;
-        uint64_t offset;
+    acb->nb_sectors -= acb->n_sectors;
 
-        logout("now writing modified header\n");
-        assert(VDI_IS_ALLOCATED(bmap_first));
-        *header = s->header;
-        vdi_header_to_le(header);
-        ret = bdrv_write(bs->file, 0, block, 1);
-        g_free(block);
-        block = NULL;
+    if (acb->nb_sectors == 0) {
+        /* request completed */
+        ret = 0;
+        goto done;
+    }
 
+    acb->sector_num += acb->n_sectors;
+    acb->buf += acb->n_sectors * SECTOR_SIZE;
+
+    block_index = acb->sector_num / s->block_sectors;
+    sector_in_block = acb->sector_num % s->block_sectors;
+    n_sectors = s->block_sectors - sector_in_block;
+    if (n_sectors > acb->nb_sectors) {
+        n_sectors = acb->nb_sectors;
+    }
+
+    logout("will read %u sectors starting at sector %" PRIu64 "\n",
+           n_sectors, acb->sector_num);
+
+    /* prepare next AIO request */
+    acb->n_sectors = n_sectors;
+    bmap_entry = le32_to_cpu(s->bmap[block_index]);
+    if (bmap_entry == VDI_UNALLOCATED) {
+        /* Block not allocated, return zeros, no need to wait. */
+        memset(acb->buf, 0, n_sectors * SECTOR_SIZE);
+        ret = vdi_schedule_bh(vdi_aio_rw_bh, acb);
         if (ret < 0) {
-            return ret;
+            goto done;
         }
+    } else {
+        uint64_t offset = s->header.offset_data / SECTOR_SIZE +
+                          (uint64_t)bmap_entry * s->block_sectors +
+                          sector_in_block;
+        acb->hd_iov.iov_base = (void *)acb->buf;
+        acb->hd_iov.iov_len = n_sectors * SECTOR_SIZE;
+        qemu_iovec_init_external(&acb->hd_qiov, &acb->hd_iov, 1);
+        acb->hd_aiocb = bdrv_aio_readv(bs->file, offset, &acb->hd_qiov,
+                                       n_sectors, vdi_aio_read_cb, acb);
+        if (acb->hd_aiocb == NULL) {
+            ret = -EIO;
+            goto done;
+        }
+    }
+    return;
+done:
+    if (acb->qiov->niov > 1) {
+        qemu_iovec_from_buffer(acb->qiov, acb->orig_buf, acb->qiov->size);
+        qemu_vfree(acb->orig_buf);
+    }
+    acb->common.cb(acb->common.opaque, ret);
+    qemu_aio_release(acb);
+}
 
-        logout("now writing modified block map entry %u...%u\n",
-               bmap_first, bmap_last);
-        /* Write modified sectors from block map. */
-        bmap_first /= (SECTOR_SIZE / sizeof(uint32_t));
-        bmap_last /= (SECTOR_SIZE / sizeof(uint32_t));
-        n_sectors = bmap_last - bmap_first + 1;
-        offset = s->bmap_sector + bmap_first;
-        base = ((uint8_t *)&s->bmap[0]) + bmap_first * SECTOR_SIZE;
-        logout("will write %u block map sectors starting from entry %u\n",
-               n_sectors, bmap_first);
-        ret = bdrv_write(bs->file, offset, base, n_sectors);
+static BlockDriverAIOCB *vdi_aio_readv(BlockDriverState *bs,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockDriverCompletionFunc *cb, void *opaque)
+{
+    VdiAIOCB *acb;
+    int ret;
+
+    logout("\n");
+    acb = vdi_aio_setup(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
+    if (!acb) {
+        return NULL;
     }
 
-    return ret;
+    ret = vdi_schedule_bh(vdi_aio_rw_bh, acb);
+    if (ret < 0) {
+        if (acb->qiov->niov > 1) {
+            qemu_vfree(acb->orig_buf);
+        }
+        qemu_aio_release(acb);
+        return NULL;
+    }
+
+    return &acb->common;
+}
+
+static void vdi_aio_write_cb(void *opaque, int ret)
+{
+    VdiAIOCB *acb = opaque;
+    BlockDriverState *bs = acb->common.bs;
+    BDRVVdiState *s = bs->opaque;
+    uint32_t bmap_entry;
+    uint32_t block_index;
+    uint32_t sector_in_block;
+    uint32_t n_sectors;
+
+    acb->hd_aiocb = NULL;
+
+    if (ret < 0) {
+        goto done;
+    }
+
+    acb->nb_sectors -= acb->n_sectors;
+    acb->sector_num += acb->n_sectors;
+    acb->buf += acb->n_sectors * SECTOR_SIZE;
+
+    if (acb->nb_sectors == 0) {
+        logout("finished data write\n");
+        acb->n_sectors = 0;
+        if (acb->header_modified) {
+            VdiHeader *header = acb->block_buffer;
+            logout("now writing modified header\n");
+            assert(acb->bmap_first != VDI_UNALLOCATED);
+            *header = s->header;
+            vdi_header_to_le(header);
+            acb->header_modified = 0;
+            acb->hd_iov.iov_base = acb->block_buffer;
+            acb->hd_iov.iov_len = SECTOR_SIZE;
+            qemu_iovec_init_external(&acb->hd_qiov, &acb->hd_iov, 1);
+            acb->hd_aiocb = bdrv_aio_writev(bs->file, 0, &acb->hd_qiov, 1,
+                                            vdi_aio_write_cb, acb);
+            if (acb->hd_aiocb == NULL) {
+                ret = -EIO;
+                goto done;
+            }
+            return;
+        } else if (acb->bmap_first != VDI_UNALLOCATED) {
+            /* One or more new blocks were allocated. */
+            uint64_t offset;
+            uint32_t bmap_first;
+            uint32_t bmap_last;
+            qemu_free(acb->block_buffer);
+            acb->block_buffer = NULL;
+            bmap_first = acb->bmap_first;
+            bmap_last = acb->bmap_last;
+            logout("now writing modified block map entry %u...%u\n",
+                   bmap_first, bmap_last);
+            /* Write modified sectors from block map. */
+            bmap_first /= (SECTOR_SIZE / sizeof(uint32_t));
+            bmap_last /= (SECTOR_SIZE / sizeof(uint32_t));
+            n_sectors = bmap_last - bmap_first + 1;
+            offset = s->bmap_sector + bmap_first;
+            acb->bmap_first = VDI_UNALLOCATED;
+            acb->hd_iov.iov_base = (void *)((uint8_t *)&s->bmap[0] +
+                                            bmap_first * SECTOR_SIZE);
+            acb->hd_iov.iov_len = n_sectors * SECTOR_SIZE;
+            qemu_iovec_init_external(&acb->hd_qiov, &acb->hd_iov, 1);
+            logout("will write %u block map sectors starting from entry %u\n",
+                   n_sectors, bmap_first);
+            acb->hd_aiocb = bdrv_aio_writev(bs->file, offset, &acb->hd_qiov,
+                                            n_sectors, vdi_aio_write_cb, acb);
+            if (acb->hd_aiocb == NULL) {
+                ret = -EIO;
+                goto done;
+            }
+            return;
+        }
+        ret = 0;
+        goto done;
+    }
+
+    logout("%u sectors written\n", acb->n_sectors);
+
+    block_index = acb->sector_num / s->block_sectors;
+    sector_in_block = acb->sector_num % s->block_sectors;
+    n_sectors = s->block_sectors - sector_in_block;
+    if (n_sectors > acb->nb_sectors) {
+        n_sectors = acb->nb_sectors;
+    }
+
+    logout("will write %u sectors starting at sector %" PRIu64 "\n",
+           n_sectors, acb->sector_num);
+
+    /* prepare next AIO request */
+    acb->n_sectors = n_sectors;
+    bmap_entry = le32_to_cpu(s->bmap[block_index]);
+    if (bmap_entry == VDI_UNALLOCATED) {
+        /* Allocate new block and write to it. */
+        uint64_t offset;
+        uint8_t *block;
+        bmap_entry = s->header.blocks_allocated;
+        s->bmap[block_index] = cpu_to_le32(bmap_entry);
+        s->header.blocks_allocated++;
+        offset = s->header.offset_data / SECTOR_SIZE +
+                 (uint64_t)bmap_entry * s->block_sectors;
+        block = acb->block_buffer;
+        if (block == NULL) {
+            block = qemu_mallocz(s->block_size);
+            acb->block_buffer = block;
+            acb->bmap_first = block_index;
+            assert(!acb->header_modified);
+            acb->header_modified = 1;
+        }
+        acb->bmap_last = block_index;
+        memcpy(block + sector_in_block * SECTOR_SIZE,
+               acb->buf, n_sectors * SECTOR_SIZE);
+        acb->hd_iov.iov_base = (void *)block;
+        acb->hd_iov.iov_len = s->block_size;
+        qemu_iovec_init_external(&acb->hd_qiov, &acb->hd_iov, 1);
+        acb->hd_aiocb = bdrv_aio_writev(bs->file, offset,
+                                        &acb->hd_qiov, s->block_sectors,
+                                        vdi_aio_write_cb, acb);
+        if (acb->hd_aiocb == NULL) {
+            ret = -EIO;
+            goto done;
+        }
+    } else {
+        uint64_t offset = s->header.offset_data / SECTOR_SIZE +
+                          (uint64_t)bmap_entry * s->block_sectors +
+                          sector_in_block;
+        acb->hd_iov.iov_base = (void *)acb->buf;
+        acb->hd_iov.iov_len = n_sectors * SECTOR_SIZE;
+        qemu_iovec_init_external(&acb->hd_qiov, &acb->hd_iov, 1);
+        acb->hd_aiocb = bdrv_aio_writev(bs->file, offset, &acb->hd_qiov,
+                                        n_sectors, vdi_aio_write_cb, acb);
+        if (acb->hd_aiocb == NULL) {
+            ret = -EIO;
+            goto done;
+        }
+    }
+
+    return;
+
+done:
+    if (acb->qiov->niov > 1) {
+        qemu_vfree(acb->orig_buf);
+    }
+    acb->common.cb(acb->common.opaque, ret);
+    qemu_aio_release(acb);
+}
+
+static BlockDriverAIOCB *vdi_aio_writev(BlockDriverState *bs,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockDriverCompletionFunc *cb, void *opaque)
+{
+    VdiAIOCB *acb;
+    int ret;
+
+    logout("\n");
+    acb = vdi_aio_setup(bs, sector_num, qiov, nb_sectors, cb, opaque, 1);
+    if (!acb) {
+        return NULL;
+    }
+
+    ret = vdi_schedule_bh(vdi_aio_rw_bh, acb);
+    if (ret < 0) {
+        if (acb->qiov->niov > 1) {
+            qemu_vfree(acb->orig_buf);
+        }
+        qemu_aio_release(acb);
+        return NULL;
+    }
+
+    return &acb->common;
 }
 
 static int vdi_create(const char *filename, QEMUOptionParameter *options)
@@ -631,6 +840,7 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options)
     VdiHeader header;
     size_t i;
     size_t bmap_size;
+    uint32_t *bmap;
 
     logout("\n");
 
@@ -655,9 +865,8 @@ 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;
     }
@@ -695,21 +904,21 @@ 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 *)qemu_mallocz(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;
+    }
+    qemu_free(bmap);
     if (image_type == VDI_TYPE_STATIC) {
         if (ftruncate(fd, sizeof(header) + bmap_size + blocks * block_size)) {
             result = -errno;
@@ -725,14 +934,15 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options)
 
 static void vdi_close(BlockDriverState *bs)
 {
-    BDRVVdiState *s = bs->opaque;
-
-    g_free(s->bmap);
-
-    migrate_del_blocker(s->migration_blocker);
-    error_free(s->migration_blocker);
 }
 
+static int vdi_flush(BlockDriverState *bs)
+{
+    logout("\n");
+    return bdrv_flush(bs->file);
+}
+
+
 static QEMUOptionParameter vdi_create_options[] = {
     {
         .name = BLOCK_OPT_SIZE,
@@ -764,14 +974,14 @@ 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_co_is_allocated = vdi_co_is_allocated,
+    .bdrv_flush = vdi_flush,
+    .bdrv_is_allocated = vdi_is_allocated,
     .bdrv_make_empty = vdi_make_empty,
 
-    .bdrv_read = vdi_co_read,
+    .bdrv_aio_readv = vdi_aio_readv,
 #if defined(CONFIG_VDI_WRITE)
-    .bdrv_write = vdi_co_write,
+    .bdrv_aio_writev = vdi_aio_writev,
 #endif
 
     .bdrv_get_info = vdi_get_info,