Update for 0.13.0 release

Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>

.gitignore

@@ -2,11 +2,6 @@ config-devices.*
 config-all-devices.*
 config-host.*
 config-target.*
-trace.h
-trace.c
-trace-dtrace.h
-trace-dtrace.dtrace
-*-timestamp
 *-softmmu
 *-darwin-user
 *-linux-user
@@ -15,12 +10,6 @@ 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
@@ -38,10 +27,8 @@ qemu-options.texi
 qemu-img-cmds.texi
 qemu-img-cmds.h
 qemu-io
-qemu-ga
 qemu-monitor.texi
 QMP/qmp-commands.txt
-test-coroutine
 .gdbinit
 *.a
 *.aux
@@ -52,18 +39,12 @@ test-coroutine
 *.ky
 *.log
 *.pdf
-*.cps
-*.fns
-*.kys
 *.pg
-*.pyc
 *.toc
 *.tp
 *.vr
 *.d
 *.o
-*.swp
-*.orig
 .pc
 patches
 pc-bios/bios-pq/status
@@ -73,6 +54,3 @@ pc-bios/optionrom/multiboot.bin
 pc-bios/optionrom/multiboot.raw
 .stgit-*
 cscope.*
-tags
-TAGS
-*~

.gitmodules

@@ -4,18 +4,3 @@
 [submodule "roms/seabios"]
 	path = roms/seabios
 	url = git://git.qemu.org/seabios.git/
-[submodule "roms/SLOF"]
-	path = roms/SLOF
-	url = git://git.qemu.org/SLOF.git
-[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

CODING_STYLE

@@ -1,9 +1,6 @@
 Qemu Coding Style
 =================
 
-Please use the script checkpatch.pl in the scripts directory to check
-patches before submitting.
-
 1. Whitespace
 
 Of course, the most important aspect in any coding style is whitespace.
@@ -49,6 +46,9 @@ 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.
 
+Typedefs are used to eliminate the redundant 'struct' keyword.  It is the
+QEMU coding style.
+
 When wrapping standard library functions, use the prefix qemu_ to alert
 readers that they are seeing a wrapped version; otherwise avoid this prefix.
 
@@ -68,10 +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

@@ -1,8 +1,4 @@
-This file documents changes for QEMU releases 0.12 and earlier.
-For changelog information for later releases, see
-http://wiki.qemu.org/ChangeLog or look at the git history for
-more detailed information.
-
+See git history for Changelogs of recent releases.
 
 version 0.12.0:
 
@@ -531,7 +527,7 @@ version 0.1.5:
 
  - ppc64 support + personality() patch (Rusty Russell)
  - first Alpha CPU patches (Falk Hueffner)
- - removed bfd.h dependency
+ - removed bfd.h dependancy
  - fixed shrd, shld, idivl and divl on PowerPC.
  - fixed buggy glibc PowerPC rint() function (test-i386 passes now on PowerPC).
 

HACKING

@@ -1,122 +0,0 @@
-1. Preprocessor
-
-For variadic macros, stick with this C99-like syntax:
-
-#define DPRINTF(fmt, ...)                                       \
-    do { printf("IRQ: " fmt, ## __VA_ARGS__); } while (0)
-
-2. C types
-
-It should be common sense to use the right type, but we have collected
-a few useful guidelines here.
-
-2.1. Scalars
-
-If you're using "int" or "long", odds are good that there's a better type.
-If a variable is counting something, it should be declared with an
-unsigned type.
-
-If it's host memory-size related, size_t should be a good choice (use
-ssize_t only if required). Guest RAM memory offsets must use ram_addr_t,
-but only for RAM, it may not cover whole guest address space.
-
-If it's file-size related, use off_t.
-If it's file-offset related (i.e., signed), use off_t.
-If it's just counting small numbers use "unsigned int";
-(on all but oddball embedded systems, you can assume that that
-type is at least four bytes wide).
-
-In the event that you require a specific width, use a standard type
-like int32_t, uint32_t, uint64_t, etc.  The specific types are
-mandatory for VMState fields.
-
-Don't use Linux kernel internal types like u32, __u32 or __le32.
-
-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
-speaking, the size of guest memory can always fit into ram_addr_t but
-it would not be correct to store an actual guest physical address in a
-ram_addr_t.
-
-Use target_ulong (or abi_ulong) for CPU virtual addresses, however
-devices should not need to use target_ulong.
-
-Of course, take all of the above with a grain of salt.  If you're about
-to use some system interface that requires a type like size_t, pid_t or
-off_t, use matching types for any corresponding variables.
-
-Also, if you try to use e.g., "unsigned int" as a type, and that
-conflicts with the signedness of a related variable, sometimes
-it's best just to use the *wrong* type, if "pulling the thread"
-and fixing all related variables would be too invasive.
-
-Finally, while using descriptive types is important, be careful not to
-go overboard.  If whatever you're doing causes warnings, or requires
-casts, then reconsider or ask for help.
-
-2.2. Pointers
-
-Ensure that all of your pointers are "const-correct".
-Unless a pointer is used to modify the pointed-to storage,
-give it the "const" attribute.  That way, the reader knows
-up-front that this is a read-only pointer.  Perhaps more
-importantly, if we're diligent about this, when you see a non-const
-pointer, you're guaranteed that it is used to modify the storage
-it points to, or it is aliased to another pointer that is.
-
-2.3. Typedefs
-Typedefs are used to eliminate the redundant 'struct' keyword.
-
-2.4. Reserved namespaces in C and POSIX
-Underscore capital, double underscore, and underscore 't' suffixes should be
-avoided.
-
-3. Low level memory management
-
-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 replacement g_malloc/g_malloc0/g_realloc/g_free or
-qemu_vmalloc/qemu_memalign/qemu_vfree APIs.
-
-Please note that NULL check for the g_malloc result is redundant and
-that g_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
-emulators.
-
-4. String manipulation
-
-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)
-
-The same limitation exists with sprintf and vsprintf, so use snprintf and
-vsnprintf.
-
-QEMU provides other useful string functions:
-int strstart(const char *str, const char *val, const char **ptr)
-int stristart(const char *str, const char *val, const char **ptr)
-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
-instead of plain strdup/strndup.
-
-5. Printf-style functions
-
-Whenever you add a new printf-style function, i.e., one with a format
-string argument and following "..." in its prototype, be sure to use
-gcc's printf attribute directive in the prototype.
-
-This makes it so gcc's -Wformat and -Wformat-security options can do
-their jobs and cross-check format strings with the number and types
-of arguments.

MAINTAINERS

@@ -1,566 +1,88 @@
 QEMU Maintainers
 ================
 
-The intention of this file is not to establish who owns what portions of the
-code base, but to provide a set of names that developers can consult when they
-have a question about a particular subset and also to provide a set of names
-to be CC'd when submitting a patch to obtain appropriate review.
-
-In general, if you have a question about inclusion of a patch, you should
-consult qemu-devel and not any specific individual privately.
-
-Descriptions of section entries:
-
-	M: Mail patches to: FullName <address@domain>
-	L: Mailing list that is relevant to this area
-	W: Web-page with status/info
-	Q: Patchwork web based patch tracking system site
-	T: SCM tree type and location.  Type is one of: git, hg, quilt, stgit.
-	S: Status, one of the following:
-	   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..
-	   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
-			it has been replaced by a better system and you
-			should be using that.
-	F: Files and directories with wildcard patterns.
-	   A trailing slash includes all files and subdirectory files.
-	   F:	drivers/net/	all files in and below drivers/net
-	   F:	drivers/net/*	all files in drivers/net, but not below
-	   F:	*/net/*		all files in "any top level directory"/net
-	   One pattern per line.  Multiple F: lines acceptable.
-	X: Files and directories that are NOT maintained, same rules as F:
-	   Files exclusions are tested before file matches.
-	   Can be useful for excluding a specific subdirectory, for instance:
-	   F:	net/
-	   X:	net/ipv6/
-	   matches all files in and below net excluding net/ipv6/
-	K: Keyword perl extended regex pattern to match content in a
-	   patch or file.  For instance:
-	   K: of_get_profile
-	      matches patches or files that contain "of_get_profile"
-	   K: \b(printk|pr_(info|err))\b
-	      matches patches or files that contain one or more of the words
-	      printk, pr_info or pr_err
-	   One regex pattern per line.  Multiple K: lines acceptable.
-
-
-General Project Administration
-------------------------------
-M: Anthony Liguori <aliguori@us.ibm.com>
-M: Paul Brook <paul@codesourcery.com>
-
-Guest CPU cores (TCG):
-----------------------
-Alpha
-M: Richard Henderson <rth@twiddle.net>
-S: Maintained
-F: target-alpha/
-
-ARM
-M: Paul Brook <paul@codesourcery.com>
-M: Peter Maydell <peter.maydell@linaro.org>
-S: Maintained
-F: target-arm/
-
-CRIS
-M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
-S: Maintained
-F: target-cris/
-
-LM32
-M: Michael Walle <michael@walle.cc>
-S: Maintained
-F: target-lm32/
-
-M68K
-M: Paul Brook <paul@codesourcery.com>
-S: Maintained
-F: target-m68k/
-
-MicroBlaze
-M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
-S: Maintained
-F: target-microblaze/
-
-MIPS
-M: Aurelien Jarno <aurelien@aurel32.net>
-S: Maintained
-F: target-mips/
-
-PowerPC
-M: Alexander Graf <agraf@suse.de>
-S: Maintained
-F: target-ppc/
-
-S390
-M: Alexander Graf <agraf@suse.de>
-S: Maintained
-F: target-s390x/
-
-SH4
-M: Aurelien Jarno <aurelien@aurel32.net>
-S: Maintained
-F: target-sh4/
-
-SPARC
-M: Blue Swirl <blauwirbel@gmail.com>
-S: Maintained
-F: target-sparc/
-
-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):
-----------------------
-
-Overall
-M: Avi Kivity <avi@redhat.com>
-M: Marcelo Tosatti <mtosatti@redhat.com>
-L: kvm@vger.kernel.org
-S: Supported
-F: kvm-*
-F: */kvm.*
-
-PPC
-M: Alexander Graf <agraf@suse.de>
-S: Maintained
-F: target-ppc/kvm.c
-
-S390
-M: Alexander Graf <agraf@suse.de>
-S: Maintained
-F: target-s390x/kvm.c
-
-X86
-M: Avi Kivity <avi@redhat.com>
-M: Marcelo Tosatti <mtosatti@redhat.com>
-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*
-
-ARM Machines
-------------
-Gumstix
-M: qemu-devel@nongnu.org
-S: Orphan
-F: hw/gumstix.c
-
-Integrator CP
-M: Paul Brook <paul@codesourcery.com>
-M: Peter Maydell <peter.maydell@linaro.org>
-S: Maintained
-F: hw/integratorcp.c
-
-Mainstone
-M: qemu-devel@nongnu.org
-S: Orphan
-F: hw/mainstone.c
-
-Musicpal
-M: Jan Kiszka <jan.kiszka@web.de>
-S: Maintained
-F: hw/musicpal.c
-
-nSeries
-M: Andrzej Zaborowski <balrogg@gmail.com>
-S: Maintained
-F: hw/nseries.c
-
-Palm
-M: Andrzej Zaborowski <balrogg@gmail.com>
-S: Maintained
-F: hw/palm.c
-
-Real View
-M: Paul Brook <paul@codesourcery.com>
-M: Peter Maydell <peter.maydell@linaro.org>
-S: Maintained
-F: hw/realview*
-
-Spitz
-M: Andrzej Zaborowski <balrogg@gmail.com>
-S: Maintained
-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
-
-CRIS Machines
--------------
-Axis Dev88
-M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
-S: Maintained
-F: hw/axis_dev88.c
-
-etraxfs
-M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
-S: Maintained
-F: hw/etraxfs.c
-
-LM32 Machines
--------------
-EVR32 and uclinux BSP
-M: Michael Walle <michael@walle.cc>
-S: Maintained
-F: hw/lm32_boards.c
-
-milkymist
-M: Michael Walle <michael@walle.cc>
-S: Maintained
-F: hw/milkymist.c
-
-M68K Machines
--------------
-an5206
-M: Paul Brook <paul@codesourcery.com>
-S: Maintained
-F: hw/an5206.c
-
-dummy_m68k
-M: Paul Brook <paul@codesourcery.com>
-S: Maintained
-F: hw/dummy_m68k.c
-
-mcf5208
-M: Paul Brook <paul@codesourcery.com>
-S: Maintained
-F: hw/mcf5208.c
-
-MicroBlaze Machines
--------------------
-petalogix_s3adsp1800
-M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
-S: Maintained
-F: hw/petalogix_s3adsp1800.c
-
-MIPS Machines
--------------
-Jazz
-M: Hervé Poussineau <hpoussin@reactos.org>
-S: Maintained
-F: hw/mips_jazz.c
-
-Malta
-M: Aurelien Jarno <aurelien@aurel32.net>
-S: Maintained
-F: hw/mips_malta.c
-
-Mipssim
-M: qemu-devel@nongnu.org
-S: Orphan
-F: hw/mips_mipssim.c
-
-R4000
-M: Aurelien Jarno <aurelien@aurel32.net>
-S: Maintained
-F: hw/mips_r4k.c
-
-PowerPC Machines
+Project leaders:
 ----------------
-405
-M: Alexander Graf <agraf@suse.de>
-S: Maintained
-F: hw/ppc405_boards.c
 
-New World
-M: Alexander Graf <agraf@suse.de>
-S: Maintained
-F: hw/ppc_newworld.c
+Fabrice Bellard
+Paul Brook
 
-Old World
-M: Alexander Graf <agraf@suse.de>
-S: Maintained
-F: hw/ppc_oldworld.c
-
-PReP
-M: Andreas Färber <andreas.faerber@web.de>
-S: Odd Fixes
-F: hw/ppc_prep.c
-
-SH4 Machines
-------------
-R2D
-M: Magnus Damm <magnus.damm@gmail.com>
-S: Maintained
-F: hw/r2d.c
-
-Shix
-M: Magnus Damm <magnus.damm@gmail.com>
-S: Orphan
-F: hw/shix.c
-
-SPARC Machines
---------------
-Sun4m
-M: Blue Swirl <blauwirbel@gmail.com>
-S: Maintained
-F: hw/sun4m.c
-
-Sun4u
-M: Blue Swirl <blauwirbel@gmail.com>
-S: Maintained
-F: hw/sun4u.c
-
-S390 Machines
--------------
-S390 Virtio
-M: Alexander Graf <agraf@suse.de>
-S: Maintained
-F: hw/s390-*.c
-
-X86 Machines
-------------
-PC
-M: Anthony Liguori <aliguori@us.ibm.com>
-S: Supported
-F: hw/pc.[ch] 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
-
-Devices
--------
-IDE
-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*
-
-SCSI
-M: Paul Brook <paul@codesourcery.com>
-M: Kevin Wolf <kwolf@redhat.com>
-S: Odd Fixes
-F: hw/lsi53c895a.c
-F: hw/scsi*
-
-USB
-M: Gerd Hoffmann <kraxel@redhat.com>
-S: Maintained
-F: hw/usb*
-
-vhost
-M: Michael S. Tsirkin <mst@redhat.com>
-S: Supported
-F: hw/vhost*
-
-virtio
-M: Anthony Liguori <aliguori@us.ibm.com>
-S: Supported
-F: hw/virtio*
-
-virtio-9p
-M: Venkateswararao Jujjuri (JV) <jvrao@linux.vnet.ibm.com>
-S: Supported
-F: hw/virtio-9p*
-
-virtio-blk
-M: Kevin Wolf <kwolf@redhat.com>
-S: Supported
-F: hw/virtio-blk*
-
-virtio-serial
-M: Amit Shah <amit.shah@redhat.com>
-S: Supported
-F: hw/virtio-serial*
-F: hw/virtio-console*
-
-Subsystems
+CPU cores:
 ----------
-Audio
-M: Vassili Karpov (malc) <av1474@comtv.ru>
-S: Maintained
-F: audio/
 
-Block
-M: Kevin Wolf <kwolf@redhat.com>
-S: Supported
-F: block*
-F: block/
+x86                Fabrice Bellard
+ARM                Paul Brook
+SPARC              Blue Swirl
+MIPS               ?
+PowerPC            ?
+M68K               Paul Brook
+SH4                ?
+CRIS               Edgar E. Iglesias
+Alpha              ?
+MicroBlaze         Edgar E. Iglesias
+S390               ?
 
-Character Devices
-M: Anthony Liguori <aliguori@us.ibm.com>
-S: Maintained
-F: qemu-char.c
-
-GDB stub
-M: qemu-devel@nongnu.org
-S: Odd Fixes
-F: gdbstub*
-F: gdb-xml/
-
-SPICE
-M: Gerd Hoffmann <kraxel@redhat.com>
-S: Supported
-F: ui/qemu-spice.h
-F: ui/spice-*.c
-F: audio/spiceaudio.c
-F: hw/qxl*
-
-Graphics
-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
-F: vl.c
-
-Monitor (QMP/HMP)
-M: Luiz Capitulino <lcapitulino@redhat.com>
-M: Markus Armbruster <armbru@redhat.com>
-S: Supported
-F: monitor.c
-
-Network device layer
-M: Anthony Liguori <aliguori@us.ibm.com>
-M: Mark McLoughlin <markmc@redhat.com>
-S: Maintained
-F: net/
-
-SLIRP
-M: Jan Kiszka <jan.kiszka@siemens.com>
-S: Maintained
-F: slirp/
-T: git://git.kiszka.org/qemu.git queues/slirp
-
-Tracing
-M: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
-S: Maintained
-F: trace/
-T: git://repo.or.cz/qemu/stefanha.git tracing
-
-Checkpatch
-M: Blue Swirl <blauwirbel@gmail.com>
-S: Odd Fixes
-F: scripts/checkpatch.pl
-
-Usermode Emulation
-------------------
-BSD user
-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
-F: linux-user/
-
-Tiny Code Generator (TCG)
+Machines (sorted by CPU):
 -------------------------
-Common code
-M: qemu-devel@nongnu.org
-S: Maintained
-F: tcg/
 
-ARM target
-M: Andrzej Zaborowski <balrogg@gmail.com>
-S: Maintained
-F: tcg/arm/
+x86
+  pc.c                    Fabrice Bellard (new maintainer needed)
+ARM
+  integratorcp.c          Paul Brook
+  versatilepb.c           Paul Brook
+  Real View               Paul Brook
+  spitz.c                 Andrzej Zaborowski
+  palm.c                  Andrzej Zaborowski
+  nseries.c               Andrzej Zaborowski
+  stellaris.c             Paul Brook
+  gumstix.c               Thorsten Zitterell
+  mainstone.c             Armin Kuster
+  musicpal.c              Jan Kiszka
+SPARC
+  sun4u.c                 Blue Swirl
+  sun4m.c                 Blue Swirl
+MIPS
+  mips_r4k.c              Aurelien Jarno
+  mips_malta.c            Aurelien Jarno
+  mips_jazz.c             Hervé Poussineau
+  mips_mipssim.c          ?
+PowerPC
+  ppc_prep.c              ?
+  ppc_oldworld.c          Fabrice Bellard
+  ppc_chrp.c              Fabrice Bellard
+  ppc405_boards.c         ?
+M86K
+  mcf5208.c               Paul Brook
+  an5206.c                Paul Brook
+  dummy_m68k.c            Paul Brook
+SH4
+  shix.c                  ?
+  r2d.c                   Magnus Damm
+CRIS
+  etraxfs.c               Edgar E. Iglesias
+  axis_dev88.c            Edgar E. Iglesias
+Alpha
+MicroBlaze
+  petalogix_s3adsp1800.c  Edgar E. Iglesias
+S390
+  s390-*.c                Alexander Graf
 
-HPPA target
-M: Richard Henderson <rth@twiddle.net>
-S: Maintained
-F: tcg/hppa/
+Generic Subsystems:
+-------------------  
 
-i386 target
-M: qemu-devel@nongnu.org
-S: Maintained
-F: tcg/i386/
-
-IA64 target
-M: Aurelien Jarno <aurelien@aurel32.net>
-S: Maintained
-F: tcg/ia64/
-
-MIPS target
-M: Aurelien Jarno <aurelien@aurel32.net>
-S: Maintained
-F: tcg/mips/
-
-PPC
-M: Vassili Karpov (malc) <av1474@comtv.ru>
-S: Maintained
-F: tcg/ppc/
-
-PPC64 target
-M: Vassili Karpov (malc) <av1474@comtv.ru>
-S: Maintained
-F: tcg/ppc64/
-
-S390 target
-M: Alexander Graf <agraf@suse.de>
-M: Richard Henderson <rth@twiddle.net>
-S: Maintained
-F: tcg/s390/
-
-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
+Dynamic translator        Fabrice Bellard
+Main loop                 Fabrice Bellard (new maintainer needed)
+TCG                       Fabrice Bellard
+IDE device                ?
+SCSI device               Paul Brook
+PCI layer                 Michael S. Tsirkin
+USB layer                 ?
+Block layer               ?
+Graphic layer             ?
+Audio device layer        Vassili Karpov (malc)
+Character device layer    ?
+Network device layer      ?
+GDB stub                  ?
+Linux user                ?
+Darwin user               ?
+SLIRP                     ?

Makefile

@@ -1,14 +1,6 @@
 # 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
-GENERATED_HEADERS += qmp-commands.h qapi-types.h qapi-visit.h
-GENERATED_SOURCES += qmp-marshal.c qapi-types.c qapi-visit.c
+GENERATED_HEADERS = config-host.h
 
 ifneq ($(wildcard config-host.mak),)
 # Put the all: rule here so that config-host.mak can contain dependencies.
@@ -42,19 +34,16 @@ 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))
 
 config-all-devices.mak: $(SUBDIR_DEVICES_MAK)
 	$(call quiet-command,cat $(SUBDIR_DEVICES_MAK) | grep =y | sort -u > $@,"  GEN   $@")
 
--include $(SUBDIR_DEVICES_MAK_DEP)
-
 %/config-devices.mak: default-configs/%.mak
-	$(call quiet-command,$(SHELL) $(SRC_PATH)/scripts/make_device_config.sh $@ $<, "  GEN   $@")
+	$(call quiet-command,cat $< > $@.tmp, "  GEN   $@")
 	@if test -f $@; then \
-	  if cmp -s $@.old $@; then \
+	  if cmp -s $@.old $@ || cmp -s $@ $@.tmp; then \
 	    mv $@.tmp $@; \
 	    cp -p $@ $@.old; \
 	  else \
@@ -76,12 +65,10 @@ defconfig:
 
 -include config-all-devices.mak
 
-build-all: $(DOCS) $(TOOLS) $(CHECKS) recurse-all
+build-all: $(DOCS) $(TOOLS) recurse-all
 
 config-host.h: config-host.h-timestamp
 config-host.h-timestamp: config-host.mak
-qemu-options.def: $(SRC_PATH)/qemu-options.hx
-	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $@")
 
 SUBDIR_RULES=$(patsubst %,subdir-%, $(TARGET_DIRS))
 
@@ -93,11 +80,9 @@ include $(SRC_PATH)/Makefile.objs
 endif
 
 $(common-obj-y): $(GENERATED_HEADERS)
-subdir-libcacard: $(oslib-obj-y) $(trace-obj-y) qemu-timer-common.o
+$(filter %-softmmu,$(SUBDIR_RULES)): $(common-obj-y) subdir-libdis
 
-$(filter %-softmmu,$(SUBDIR_RULES)): $(trace-obj-y) $(common-obj-y) subdir-libdis
-
-$(filter %-user,$(SUBDIR_RULES)): $(GENERATED_HEADERS) $(trace-obj-y) subdir-libdis-user subdir-libuser
+$(filter %-user,$(SUBDIR_RULES)): $(GENERATED_HEADERS) subdir-libdis-user subdir-libuser
 
 ROMSUBDIR_RULES=$(patsubst %,romsubdir-%, $(ROMS))
 romsubdir-%:
@@ -111,8 +96,6 @@ audio/audio.o audio/fmodaudio.o: QEMU_CFLAGS += $(FMOD_CFLAGS)
 
 QEMU_CFLAGS+=$(CURL_CFLAGS)
 
-QEMU_CFLAGS+=$(GLIB_CFLAGS)
-
 ui/cocoa.o: ui/cocoa.m
 
 ui/sdl.o audio/sdlaudio.o ui/sdl_zoom.o baum.o: QEMU_CFLAGS += $(SDL_CFLAGS)
@@ -121,133 +104,48 @@ ui/vnc.o: QEMU_CFLAGS += $(VNC_TLS_CFLAGS)
 
 bt-host.o: QEMU_CFLAGS += $(BLUEZ_CFLAGS)
 
-version.o: $(SRC_PATH)/version.rc config-host.h
-	$(call quiet-command,$(WINDRES) -I. -o $@ $<,"  RC    $(TARGET_DIR)$@")
-
-version-obj-$(CONFIG_WIN32) += version.o
-######################################################################
-# Support building shared library libcacard
-
-.PHONY: libcacard.la install-libcacard
-ifeq ($(LIBTOOL),)
-libcacard.la:
-	@echo "libtool is missing, please install and rerun configure"; exit 1
-
-install-libcacard:
-	@echo "libtool is missing, please install and rerun configure"; exit 1
-else
-libcacard.la: $(GENERATED_HEADERS) $(oslib-obj-y) qemu-timer-common.o $(addsuffix .lo, $(basename $(trace-obj-y)))
-	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C libcacard V="$(V)" TARGET_DIR="$*/" libcacard.la,)
-
-install-libcacard: libcacard.la
-	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C libcacard V="$(V)" TARGET_DIR="$*/" install-libcacard,)
-endif
 ######################################################################
 
 qemu-img.o: qemu-img-cmds.h
-qemu-img.o qemu-tool.o qemu-nbd.o qemu-io.o cmd.o qemu-ga.o: $(GENERATED_HEADERS)
+qemu-img.o qemu-tool.o qemu-nbd.o qemu-io.o: $(GENERATED_HEADERS)
 
-tools-obj-y = qemu-tool.o $(oslib-obj-y) $(trace-obj-y) \
-	qemu-timer-common.o cutils.o
+qemu-img$(EXESUF): qemu-img.o qemu-tool.o qemu-error.o $(block-obj-y) $(qobject-obj-y)
 
-qemu-img$(EXESUF): qemu-img.o $(tools-obj-y) $(block-obj-y)
-qemu-nbd$(EXESUF): qemu-nbd.o $(tools-obj-y) $(block-obj-y)
-qemu-io$(EXESUF): qemu-io.o cmd.o $(tools-obj-y) $(block-obj-y)
+qemu-nbd$(EXESUF): qemu-nbd.o qemu-tool.o qemu-error.o $(block-obj-y) $(qobject-obj-y)
+
+qemu-io$(EXESUF): qemu-io.o cmd.o qemu-tool.o qemu-error.o $(block-obj-y) $(qobject-obj-y)
 
 qemu-img-cmds.h: $(SRC_PATH)/qemu-img-cmds.hx
-	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $@")
+	$(call quiet-command,sh $(SRC_PATH)/hxtool -h < $< > $@,"  GEN   $@")
 
-check-qint.o check-qstring.o check-qdict.o check-qlist.o check-qfloat.o check-qjson.o test-coroutine.o: $(GENERATED_HEADERS)
+check-qint.o check-qstring.o check-qdict.o check-qlist.o check-qfloat.o check-qjson.o: $(GENERATED_HEADERS)
 
-check-qint: check-qint.o qint.o $(tools-obj-y)
-check-qstring: check-qstring.o qstring.o $(tools-obj-y)
-check-qdict: check-qdict.o qdict.o qfloat.o qint.o qstring.o qbool.o qlist.o $(tools-obj-y)
-check-qlist: check-qlist.o qlist.o qint.o $(tools-obj-y)
-check-qfloat: check-qfloat.o qfloat.o $(tools-obj-y)
-check-qjson: check-qjson.o $(qobject-obj-y) $(tools-obj-y)
-test-coroutine: test-coroutine.o qemu-timer-common.o async.o $(coroutine-obj-y) $(tools-obj-y)
-
-$(qapi-obj-y): $(GENERATED_HEADERS)
-qapi-dir := $(BUILD_DIR)/qapi-generated
-test-visitor.o test-qmp-commands.o qemu-ga$(EXESUF): QEMU_CFLAGS += -I $(qapi-dir)
-qemu-ga$(EXESUF): LIBS = $(LIBS_QGA)
-
-$(qapi-dir)/test-qapi-types.c $(qapi-dir)/test-qapi-types.h :\
-$(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 $(qapi-dir)/test-qapi-visit.h :\
-$(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 $(qapi-dir)/test-qmp-marshal.c :\
-$(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-dir)/qga-qapi-types.c $(qapi-dir)/qga-qapi-types.h :\
-$(SRC_PATH)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-types.py
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py -o "$(qapi-dir)" -p "qga-" < $<, "  GEN   $@")
-$(qapi-dir)/qga-qapi-visit.c $(qapi-dir)/qga-qapi-visit.h :\
-$(SRC_PATH)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-visit.py
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py -o "$(qapi-dir)" -p "qga-" < $<, "  GEN   $@")
-$(qapi-dir)/qga-qmp-commands.h $(qapi-dir)/qga-qmp-marshal.c :\
-$(SRC_PATH)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-commands.py
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py -o "$(qapi-dir)" -p "qga-" < $<, "  GEN   $@")
-
-qapi-types.c qapi-types.h :\
-$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-types.py
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py -o "." < $<, "  GEN   $@")
-qapi-visit.c qapi-visit.h :\
-$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-visit.py
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py -o "."  < $<, "  GEN   $@")
-qmp-commands.h qmp-marshal.c :\
-$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py -m -o "." < $<, "  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 $(qobject-obj-y) $(qapi-obj-y) $(tools-obj-y) $(qapi-dir)/test-qapi-visit.o $(qapi-dir)/test-qapi-types.o
-
-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 $(qobject-obj-y) $(qapi-obj-y) $(tools-obj-y) $(qapi-dir)/test-qapi-visit.o $(qapi-dir)/test-qapi-types.o $(qapi-dir)/test-qmp-marshal.o module.o
-
-QGALIB_OBJ=$(addprefix $(qapi-dir)/, qga-qapi-types.o qga-qapi-visit.o qga-qmp-marshal.o)
-QGALIB_GEN=$(addprefix $(qapi-dir)/, qga-qapi-types.h qga-qapi-visit.h qga-qmp-commands.h)
-$(QGALIB_OBJ): $(QGALIB_GEN) $(GENERATED_HEADERS)
-$(qga-obj-y) qemu-ga.o: $(QGALIB_GEN) $(GENERATED_HEADERS)
-
-qemu-ga$(EXESUF): qemu-ga.o $(qga-obj-y) $(qapi-obj-y) $(tools-obj-y) $(qobject-obj-y) $(version-obj-y) $(QGALIB_OBJ)
-
-QEMULIBS=libhw32 libhw64 libuser libdis libdis-user
+check-qint: check-qint.o qint.o qemu-malloc.o
+check-qstring: check-qstring.o qstring.o qemu-malloc.o
+check-qdict: check-qdict.o qdict.o qfloat.o qint.o qstring.o qbool.o qemu-malloc.o qlist.o
+check-qlist: check-qlist.o qlist.o qint.o qemu-malloc.o
+check-qfloat: check-qfloat.o qfloat.o qemu-malloc.o
+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 qemu-malloc.o
 
 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
-	rm -f *.o *.d *.a *.lo $(TOOLS) $(CHECKS) 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 *.o *.d *.a $(TOOLS) TAGS cscope.* *.pod *~ */*~
+	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
 	rm -f qemu-img-cmds.h
-	rm -f trace/*.o trace/*.d
-	rm -f trace.c trace.h trace.c-timestamp trace.h-timestamp
-	rm -f trace-dtrace.dtrace trace-dtrace.dtrace-timestamp
-	rm -f trace-dtrace.h trace-dtrace.h-timestamp
-	rm -f $(GENERATED_SOURCES)
-	rm -rf $(qapi-dir)
 	$(MAKE) -C tests clean
-	for d in $(ALL_SUBDIRS) $(QEMULIBS) libcacard; do \
+	for d in $(ALL_SUBDIRS) libhw32 libhw64 libuser libdis libdis-user; do \
 	if test -d $$d; then $(MAKE) -C $$d $@ || exit 1; fi; \
-	rm -f $$d/qemu-options.def; \
         done
 
 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 qemu-options.def
 	rm -f config-all-devices.mak
 	rm -f roms/seabios/config.mak roms/vgabios/config.mak
-	rm -f qemu-doc.info qemu-doc.aux qemu-doc.cp qemu-doc.cps qemu-doc.dvi
-	rm -f qemu-doc.fn qemu-doc.fns qemu-doc.info qemu-doc.ky qemu-doc.kys
-	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 qemu-doc.info qemu-doc.aux qemu-doc.cp qemu-doc.dvi qemu-doc.fn qemu-doc.info qemu-doc.ky qemu-doc.log qemu-doc.pdf qemu-doc.pg qemu-doc.toc qemu-doc.tp qemu-doc.vr
 	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 \
+	for d in $(TARGET_DIRS) libhw32 libhw64 libuser libdis libdis-user; do \
 	rm -rf $$d || exit 1 ; \
         done
 
@@ -256,17 +154,16 @@ 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
 
 ifdef INSTALL_BLOBS
-BLOBS=bios.bin sgabios.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 \
-bamboo.dtb petalogix-s3adsp1800.dtb petalogix-ml605.dtb \
-mpc8544ds.dtb \
+BLOBS=bios.bin vgabios.bin vgabios-cirrus.bin ppc_rom.bin \
+video.x openbios-sparc32 openbios-sparc64 openbios-ppc \
+gpxe-eepro100-80861209.rom \
+gpxe-eepro100-80861229.rom \
+pxe-e1000.bin \
+pxe-ne2k_pci.bin pxe-pcnet.bin \
+pxe-rtl8139.bin pxe-virtio.bin \
+bamboo.dtb petalogix-s3adsp1800.dtb \
 multiboot.bin linuxboot.bin \
-s390-zipl.rom \
-spapr-rtas.bin slof.bin \
-palcode-clipper
+s390-zipl.rom
 else
 BLOBS=
 endif
@@ -308,19 +205,13 @@ endif
 test speed: all
 	$(MAKE) -C tests $@
 
-.PHONY: check
-check: $(patsubst %,run-check-%,$(CHECKS))
-
-run-check-%: %
-	./$<
-
 .PHONY: TAGS
 TAGS:
 	find "$(SRC_PATH)" -name '*.[hc]' -print0 | xargs -0 etags
 
 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
@@ -341,32 +232,32 @@ TEXIFLAG=$(if $(V),,--quiet)
 	$(call quiet-command,texi2pdf $(TEXIFLAG) -I . $<,"  GEN   $@")
 
 qemu-options.texi: $(SRC_PATH)/qemu-options.hx
-	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"  GEN   $@")
+	$(call quiet-command,sh $(SRC_PATH)/hxtool -t < $< > $@,"  GEN   $@")
 
-qemu-monitor.texi: $(SRC_PATH)/hmp-commands.hx
-	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"  GEN   $@")
+qemu-monitor.texi: $(SRC_PATH)/qemu-monitor.hx
+	$(call quiet-command,sh $(SRC_PATH)/hxtool -t < $< > $@,"  GEN   $@")
 
-QMP/qmp-commands.txt: $(SRC_PATH)/qmp-commands.hx
-	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -q < $< > $@,"  GEN   $@")
+QMP/qmp-commands.txt: $(SRC_PATH)/qemu-monitor.hx
+	$(call quiet-command,sh $(SRC_PATH)/hxtool -q < $< > $@,"  GEN   $@")
 
 qemu-img-cmds.texi: $(SRC_PATH)/qemu-img-cmds.hx
-	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"  GEN   $@")
+	$(call quiet-command,sh $(SRC_PATH)/hxtool -t < $< > $@,"  GEN   $@")
 
 qemu.1: qemu-doc.texi qemu-options.texi qemu-monitor.texi
 	$(call quiet-command, \
-	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< qemu.pod && \
+	  perl -Ww -- $(SRC_PATH)/texi2pod.pl $< 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 && \
+	  perl -Ww -- $(SRC_PATH)/texi2pod.pl $< qemu-img.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 && \
+	  perl -Ww -- $(SRC_PATH)/texi2pod.pl $< qemu-nbd.pod && \
 	  pod2man --section=8 --center=" " --release=" " qemu-nbd.pod > $@, \
 	  "  GEN   $@")
 
@@ -389,5 +280,41 @@ tar:
 	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)/video.x \
+	$(datadir)/openbios-sparc32 \
+	$(datadir)/openbios-sparc64 \
+	$(datadir)/openbios-ppc \
+	$(datadir)/pxe-ne2k_pci.bin \
+	$(datadir)/pxe-rtl8139.bin \
+	$(datadir)/pxe-pcnet.bin \
+	$(datadir)/pxe-e1000.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
--include $(wildcard *.d audio/*.d slirp/*.d block/*.d net/*.d ui/*.d qapi/*.d qga/*.d)
+-include $(wildcard *.d audio/*.d slirp/*.d block/*.d net/*.d ui/*.d)

Makefile.hw

@@ -9,8 +9,7 @@ include $(SRC_PATH)/rules.mak
 
 $(call set-vpath, $(SRC_PATH):$(SRC_PATH)/hw)
 
-QEMU_CFLAGS+=-I..
-QEMU_CFLAGS += $(GLIB_CFLAGS)
+QEMU_CFLAGS+=-I.. -I$(SRC_PATH)/fpu
 
 include $(SRC_PATH)/Makefile.objs
 

Makefile.objs

@@ -2,43 +2,22 @@
 # 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
-
-#######################################################################
-# oslib-obj-y is code depending on the OS (win32 vs posix)
-oslib-obj-y = osdep.o
-oslib-obj-$(CONFIG_WIN32) += oslib-win32.o qemu-thread-win32.o
-oslib-obj-$(CONFIG_POSIX) += oslib-posix.o qemu-thread-posix.o
-
-#######################################################################
-# coroutines
-coroutine-obj-y = qemu-coroutine.o qemu-coroutine-lock.o
-ifeq ($(CONFIG_UCONTEXT_COROUTINE),y)
-coroutine-obj-$(CONFIG_POSIX) += coroutine-ucontext.o
-else
-coroutine-obj-$(CONFIG_POSIX) += coroutine-gthread.o
-endif
-coroutine-obj-$(CONFIG_WIN32) += coroutine-win32.o
+qobject-obj-y += qerror.o
 
 #######################################################################
 # block-obj-y is code used by both qemu system emulation and qemu-img
 
-block-obj-y = cutils.o cache-utils.o qemu-option.o module.o async.o
-block-obj-y += nbd.o block.o aio.o aes.o qemu-config.o qemu-progress.o qemu-sockets.o
-block-obj-y += $(coroutine-obj-y) $(qobject-obj-y) $(version-obj-y)
+block-obj-y = cutils.o cache-utils.o qemu-malloc.o qemu-option.o module.o
+block-obj-y += nbd.o block.o aio.o aes.o osdep.o qemu-config.o
 block-obj-$(CONFIG_POSIX) += posix-aio-compat.o
 block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
 
 block-nested-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o
-block-nested-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
-block-nested-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
-block-nested-y += qed-check.o
-block-nested-y += parallels.o nbd.o blkdebug.o sheepdog.o blkverify.o
+block-nested-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o
+block-nested-y += parallels.o nbd.o blkdebug.o sheepdog.o
 block-nested-$(CONFIG_WIN32) += raw-win32.o
 block-nested-$(CONFIG_POSIX) += raw-posix.o
-block-nested-$(CONFIG_LIBISCSI) += iscsi.o
 block-nested-$(CONFIG_CURL) += curl.o
-block-nested-$(CONFIG_RBD) += rbd.o
 
 block-obj-y +=  $(addprefix block/, $(block-nested-y))
 
@@ -52,19 +31,11 @@ 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)$(CONFIG_PCI),yyy)
-# Lots of the fsdev/9pcode is pulled in by vl.c via qemu_fsdev_add.
-# only pull in the actual virtio-9p device if we also enabled virtio.
-CONFIG_REALLY_VIRTFS=y
-fsdev-nested-y = qemu-fsdev.o
-else
-fsdev-nested-y = qemu-fsdev-dummy.o
-endif
+fsdev-nested-$(CONFIG_VIRTFS) = qemu-fsdev.o
 fsdev-obj-$(CONFIG_VIRTFS) += $(addprefix fsdev/, $(fsdev-nested-y))
 
 ######################################################################
@@ -77,13 +48,12 @@ 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
-common-obj-y += $(oslib-obj-y)
+common-obj-y += readline.o console.o cursor.o async.o qemu-error.o
 common-obj-$(CONFIG_WIN32) += os-win32.o
 common-obj-$(CONFIG_POSIX) += os-posix.o
 
-common-obj-y += tcg-runtime.o host-utils.o main-loop.o
-common-obj-y += irq.o 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-$(CONFIG_WM8750) += wm8750.o
@@ -101,32 +71,25 @@ common-obj-y += i2c.o smbus.o smbus_eeprom.o
 common-obj-y += eeprom93xx.o
 common-obj-y += scsi-disk.o cdrom.o
 common-obj-y += scsi-generic.o scsi-bus.o
-common-obj-y += hid.o
 common-obj-y += usb.o usb-hub.o usb-$(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-y += usb-serial.o usb-net.o usb-bus.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 += buffered_file.o migration.o migration-tcp.o qemu-sockets.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 += block-migration.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) += ui/spice-core.o ui/spice-input.o ui/spice-display.o spice-qemu-char.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
@@ -141,35 +104,33 @@ common-obj-y += $(addprefix audio/, $(audio-obj-y))
 
 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-$(CONFIG_VNC_SASL) += vnc-auth-sasl.o
+ui-obj-y += vnc.o d3des.o
+ui-obj-y += vnc-enc-zlib.o vnc-enc-hextile.o
+ui-obj-y += vnc-enc-tight.o vnc-palette.o
+ui-obj-$(CONFIG_VNC_TLS) += vnc-tls.o vnc-auth-vencrypt.o
+ui-obj-$(CONFIG_VNC_SASL) += vnc-auth-sasl.o
+ui-obj-$(CONFIG_COCOA) += cocoa.o
 ifdef CONFIG_VNC_THREAD
-vnc-obj-y += vnc-jobs-async.o
+ui-obj-y += vnc-jobs-async.o
 else
-vnc-obj-y += vnc-jobs-sync.o
+ui-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-$(CONFIG_POSIX) += compatfd.o
+common-obj-$(CONFIG_THREAD) += qemu-thread.o
 common-obj-y += notify.o event_notifier.o
-common-obj-y += qemu-timer.o qemu-timer-common.o
+common-obj-y += qemu-timer.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 arp_table.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
+common-obj-$(CONFIG_XEN) += xen_backend.o xen_devconfig.o
+common-obj-$(CONFIG_XEN) += xen_console.o xenfb.o xen_disk.o xen_nic.o
 
 ######################################################################
 # libuser
@@ -178,21 +139,14 @@ user-obj-y =
 user-obj-y += envlist.o path.o
 user-obj-y += tcg-runtime.o host-utils.o
 user-obj-y += cutils.o cache-utils.o
-user-obj-y += $(trace-obj-y)
 
 ######################################################################
 # libhw
 
 hw-obj-y =
 hw-obj-y += vl.o loader.o
-hw-obj-$(CONFIG_VIRTIO) += virtio-console.o
-hw-obj-y += usb-libhw.o
-hw-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.o
-hw-obj-y += fw_cfg.o
-hw-obj-$(CONFIG_PCI) += pci.o pci_bridge.o
-hw-obj-$(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 += virtio.o virtio-console.o
+hw-obj-y += fw_cfg.o pci.o pci_host.o pcie_host.o
 hw-obj-y += watchdog.o
 hw-obj-$(CONFIG_ISA_MMIO) += isa_mmio.o
 hw-obj-$(CONFIG_ECC) += ecc.o
@@ -210,20 +164,13 @@ 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-$(CONFIG_FDC) += fdc.o
 hw-obj-$(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-$(CONFIG_USB_REDIR) += usb-redir.o
-hw-obj-$(CONFIG_I8259) += i8259.o
 
 # PPC devices
+hw-obj-$(CONFIG_OPENPIC) += openpic.o
 hw-obj-$(CONFIG_PREP_PCI) += prep_pci.o
 # Mac shared devices
 hw-obj-$(CONFIG_MACIO) += macio.o
@@ -242,28 +189,23 @@ hw-obj-$(CONFIG_PPCE500_PCI) += ppce500_pci.o
 
 # MIPS devices
 hw-obj-$(CONFIG_PIIX4) += piix4.o
-hw-obj-$(CONFIG_G364FB) += g364fb.o
 
 # PCI watchdog devices
-hw-obj-$(CONFIG_PCI) += wdt_i6300esb.o
+hw-obj-y += wdt_i6300esb.o
 
-hw-obj-$(CONFIG_PCI) += pcie.o pcie_aer.o pcie_port.o
+hw-obj-y += msix.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-y += ne2000.o
+hw-obj-y += eepro100.o
+hw-obj-y += pcnet.o
 
 hw-obj-$(CONFIG_SMC91C111) += smc91c111.o
 hw-obj-$(CONFIG_LAN9118) += lan9118.o
 hw-obj-$(CONFIG_NE2000_ISA) += ne2000-isa.o
-hw-obj-$(CONFIG_OPENCORES_ETH) += opencores_eth.o
 
 # IDE
-hw-obj-$(CONFIG_IDE_CORE) += ide/core.o ide/atapi.o
+hw-obj-$(CONFIG_IDE_CORE) += ide/core.o
 hw-obj-$(CONFIG_IDE_QDEV) += ide/qdev.o
 hw-obj-$(CONFIG_IDE_PCI) += ide/pci.o
 hw-obj-$(CONFIG_IDE_ISA) += ide/isa.o
@@ -271,11 +213,9 @@ hw-obj-$(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-$(CONFIG_LSI_SCSI_PCI) += lsi53c895a.o
+hw-obj-y += lsi53c895a.o
 hw-obj-$(CONFIG_ESP) += esp.o
 
 hw-obj-y += dma-helpers.o sysbus.o isa-bus.o
@@ -286,7 +226,6 @@ 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
@@ -301,21 +240,11 @@ sound-obj-$(CONFIG_AC97) += ac97.o
 sound-obj-$(CONFIG_ADLIB) += fmopl.o adlib.o
 sound-obj-$(CONFIG_GUS) += gus.o gusemu_hal.o gusemu_mixer.o
 sound-obj-$(CONFIG_CS4231A) += cs4231a.o
-sound-obj-$(CONFIG_HDA) += intel-hda.o hda-audio.o
 
 adlib.o fmopl.o: QEMU_CFLAGS += -DBUILD_Y8950=0
 hw-obj-$(CONFIG_SOUND) += $(sound-obj-y)
 
-9pfs-nested-$(CONFIG_VIRTFS)  = virtio-9p.o
-9pfs-nested-$(CONFIG_VIRTFS) += virtio-9p-local.o virtio-9p-xattr.o
-9pfs-nested-$(CONFIG_VIRTFS) += virtio-9p-xattr-user.o virtio-9p-posix-acl.o
-9pfs-nested-$(CONFIG_VIRTFS) += virtio-9p-coth.o cofs.o codir.o cofile.o
-9pfs-nested-$(CONFIG_VIRTFS) += coxattr.o virtio-9p-synth.o
-9pfs-nested-$(CONFIG_OPEN_BY_HANDLE) +=  virtio-9p-handle.o
-
-hw-obj-$(CONFIG_REALLY_VIRTFS) += $(addprefix 9pfs/, $(9pfs-nested-y))
-$(addprefix 9pfs/, $(9pfs-nested-y)): QEMU_CFLAGS+=$(GLIB_CFLAGS)
-
+hw-obj-$(CONFIG_VIRTFS) += virtio-9p-debug.o virtio-9p-local.o
 
 ######################################################################
 # libdis
@@ -336,94 +265,14 @@ libdis-$(CONFIG_S390_DIS) += s390-dis.o
 libdis-$(CONFIG_SH4_DIS) += sh4-dis.o
 libdis-$(CONFIG_SPARC_DIS) += sparc-dis.o
 
-######################################################################
-# trace
-
-ifeq ($(TRACE_BACKEND),dtrace)
-trace.h: trace.h-timestamp trace-dtrace.h
-else
-trace.h: trace.h-timestamp
-endif
-trace.h-timestamp: $(SRC_PATH)/trace-events $(BUILD_DIR)/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,sh $(SRC_PATH)/scripts/tracetool --$(TRACE_BACKEND) -c < $< > $@,"  GEN   trace.c")
-	@cmp -s $@ trace.c || cp $@ trace.c
-
-trace.o: trace.c $(GENERATED_HEADERS)
-
-trace-dtrace.h: trace-dtrace.dtrace
-	$(call quiet-command,dtrace -o $@ -h -s $<, "  GEN   trace-dtrace.h")
-
-# Normal practice is to name DTrace probe file with a '.d' extension
-# but that gets picked up by QEMU's Makefile as an external dependency
-# rule file. So we use '.dtrace' instead
-trace-dtrace.dtrace: trace-dtrace.dtrace-timestamp
-trace-dtrace.dtrace-timestamp: $(SRC_PATH)/trace-events $(BUILD_DIR)/config-host.mak
-	$(call quiet-command,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 $<, "  GEN trace-dtrace.o")
-
-ifeq ($(LIBTOOL),)
-trace-dtrace.lo: trace-dtrace.dtrace
-	@echo "missing libtool. please install and rerun configure."; exit 1
-else
-trace-dtrace.lo: trace-dtrace.dtrace
-	$(call quiet-command,$(LIBTOOL) --mode=compile --tag=CC dtrace -o $@ -G -s $<, "  lt GEN trace-dtrace.o")
-endif
-
-trace/simple.o: trace/simple.c $(GENERATED_HEADERS)
-
-trace-obj-$(CONFIG_TRACE_DTRACE) += trace-dtrace.o
-ifneq ($(TRACE_BACKEND),dtrace)
-trace-obj-y = trace.o
-endif
-
-trace-nested-$(CONFIG_TRACE_DEFAULT) += default.o
-
-trace-nested-$(CONFIG_TRACE_SIMPLE) += simple.o
-trace-obj-$(CONFIG_TRACE_SIMPLE) += qemu-timer-common.o
-
-trace-nested-$(CONFIG_TRACE_STDERR) += stderr.o
-
-trace-nested-y += control.o
-
-trace-obj-y += $(addprefix trace/, $(trace-nested-y))
-
-$(trace-obj-y): $(GENERATED_HEADERS)
-
-######################################################################
-# smartcard
-
-libcacard-y = cac.o event.o vcard.o vreader.o vcard_emul_nss.o vcard_emul_type.o card_7816.o
-
-######################################################################
-# qapi
-
-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))
-
-common-obj-y += qmp-marshal.o qapi-visit.o qapi-types.o $(qapi-obj-y)
-common-obj-y += qmp.o hmp.o
-
-######################################################################
-# guest agent
-
-qga-nested-y = guest-agent-commands.o guest-agent-command-state.o
-qga-obj-y = $(addprefix qga/, $(qga-nested-y))
-qga-obj-y += qemu-ga.o qemu-sockets.o module.o qemu-option.o
-qga-obj-$(CONFIG_WIN32) += oslib-win32.o
-qga-obj-$(CONFIG_POSIX) += oslib-posix.o
-
 vl.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
 
 vl.o: QEMU_CFLAGS+=$(SDL_CFLAGS)
 
-QEMU_CFLAGS+=$(GLIB_CFLAGS)
+vl.o: qemu-options.def
+os-posix.o: qemu-options.def
+os-win32.o: qemu-options.def
+
+qemu-options.def: $(SRC_PATH)/qemu-options.hx
+	$(call quiet-command,sh $(SRC_PATH)/hxtool -h < $< > $@,"  GEN   $(TARGET_DIR)$@")
 

Makefile.target

@@ -1,9 +1,7 @@
 # -*- 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
@@ -15,10 +13,7 @@ endif
 
 TARGET_PATH=$(SRC_PATH)/target-$(TARGET_BASE_ARCH)
 $(call set-vpath, $(SRC_PATH):$(TARGET_PATH):$(SRC_PATH)/hw)
-ifdef CONFIG_LINUX
-QEMU_CFLAGS += -I../linux-headers
-endif
-QEMU_CFLAGS += -I.. -I$(TARGET_PATH) -DNEED_CPU_H
+QEMU_CFLAGS+= -I.. -I$(TARGET_PATH) -DNEED_CPU_H
 
 include $(SRC_PATH)/Makefile.objs
 
@@ -27,40 +22,23 @@ ifdef CONFIG_USER_ONLY
 QEMU_PROG=qemu-$(TARGET_ARCH2)
 else
 # system emulator name
+ifeq ($(TARGET_ARCH), i386)
+QEMU_PROG=qemu$(EXESUF)
+else
 QEMU_PROG=qemu-system-$(TARGET_ARCH2)$(EXESUF)
 endif
+endif
 
 PROGS=$(QEMU_PROG)
-STPFILES=
 
-ifndef CONFIG_HAIKU
 LIBS+=-lm
-endif
+
+kvm.o kvm-all.o vhost.o vhost_net.o: QEMU_CFLAGS+=$(KVM_CFLAGS)
 
 config-target.h: config-target.h-timestamp
 config-target.h-timestamp: config-target.mak
 
-ifdef CONFIG_TRACE_SYSTEMTAP
-stap: $(QEMU_PROG).stp
-
-ifdef CONFIG_USER_ONLY
-TARGET_TYPE=user
-else
-TARGET_TYPE=system
-endif
-
-$(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
-
-all: $(PROGS) stap
+all: $(PROGS)
 
 # Dummy command so that make thinks it has done something
 	@true
@@ -68,27 +46,17 @@ all: $(PROGS) stap
 #########################################################
 # cpu emulator library
 libobj-y = exec.o translate-all.o cpu-exec.o translate.o
-libobj-y += tcg/tcg.o tcg/optimize.o
-libobj-$(CONFIG_TCG_INTERPRETER) += tci.o
-libobj-y += fpu/softfloat.o
+libobj-y += tcg/tcg.o
+libobj-$(CONFIG_SOFTFLOAT) += fpu/softfloat.o
+libobj-$(CONFIG_NOSOFTFLOAT) += fpu/softfloat-native.o
 libobj-y += op_helper.o helper.o
 ifeq ($(TARGET_BASE_ARCH), i386)
 libobj-y += cpuid.o
 endif
-libobj-$(TARGET_SPARC64) += vis_helper.o
 libobj-$(CONFIG_NEED_MMU) += mmu.o
 libobj-$(TARGET_ARM) += neon_helper.o iwmmxt_helper.o
-ifeq ($(TARGET_BASE_ARCH), sparc)
-libobj-y += fop_helper.o cc_helper.o win_helper.o mmu_helper.o ldst_helper.o
-libobj-y += cpu_init.o
-endif
-libobj-$(TARGET_SPARC) += int32_helper.o
-libobj-$(TARGET_SPARC64) += int64_helper.o
 
 libobj-y += disas.o
-libobj-$(CONFIG_TCI_DIS) += tci-dis.o
-
-tci-dis.o: QEMU_CFLAGS += -I$(SRC_PATH)/tcg -I$(SRC_PATH)/tcg/tci
 
 $(libobj-y): $(GENERATED_HEADERS)
 
@@ -102,10 +70,10 @@ tcg/tcg.o: cpu.h
 
 # HELPER_CFLAGS is used for all the code compiled with static register
 # variables
-op_helper.o ldst_helper.o user-exec.o: QEMU_CFLAGS += $(HELPER_CFLAGS)
+op_helper.o cpu-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.
+# cpu_signal_handler() in cpu-exec.c.
 signal.o: QEMU_CFLAGS += $(HELPER_CFLAGS)
 
 #########################################################
@@ -115,10 +83,10 @@ ifdef CONFIG_LINUX_USER
 
 $(call set-vpath, $(SRC_PATH)/linux-user:$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR))
 
-QEMU_CFLAGS+=-I$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR) -I$(SRC_PATH)/linux-user
+QEMU_CFLAGS+=-I$(SRC_PATH)/linux-user -I$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR)
 obj-y = main.o syscall.o strace.o mmap.o signal.o thunk.o \
       elfload.o linuxload.o uaccess.o gdbstub.o cpu-uname.o \
-      user-exec.o $(oslib-obj-y)
+      qemu-malloc.o
 
 obj-$(TARGET_HAS_BFLT) += flatload.o
 
@@ -156,7 +124,7 @@ 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
+        gdbstub.o
 
 obj-i386-y += ioport-user.o
 
@@ -178,7 +146,7 @@ $(call set-vpath, $(SRC_PATH)/bsd-user)
 QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ARCH)
 
 obj-y = main.o bsdload.o elfload.o mmap.o signal.o strace.o syscall.o \
-        gdbstub.o uaccess.o user-exec.o
+        gdbstub.o uaccess.o
 
 obj-i386-y += ioport-user.o
 
@@ -194,129 +162,86 @@ endif #CONFIG_BSD_USER
 # System emulator target
 ifdef CONFIG_SOFTMMU
 
-obj-y = arch_init.o cpus.o monitor.o machine.o gdbstub.o balloon.o ioport.o
+obj-y = arch_init.o cpus.o monitor.o machine.o gdbstub.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_VIRTIO) += virtio.o virtio-blk.o virtio-balloon.o virtio-net.o virtio-serial-bus.o
+obj-y += virtio-blk.o virtio-balloon.o virtio-net.o virtio-serial-bus.o
+obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.o
 obj-y += vhost_net.o
 obj-$(CONFIG_VHOST_NET) += vhost.o
-obj-$(CONFIG_REALLY_VIRTFS) += 9pfs/virtio-9p-device.o
+obj-$(CONFIG_VIRTFS) += virtio-9p.o
+obj-y += rwhandler.o
 obj-$(CONFIG_KVM) += kvm.o kvm-all.o
 obj-$(CONFIG_NO_KVM) += kvm-stub.o
-obj-y += memory.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-$(CONFIG_XEN) += xen-all.o xen_machine_pv.o xen_domainbuild.o xen-mapcache.o
-obj-$(CONFIG_NO_XEN) += xen-stub.o
+# xen backend driver support
+obj-$(CONFIG_XEN) += xen_machine_pv.o xen_domainbuild.o
 
-obj-i386-$(CONFIG_XEN) += xen_platform.o
+# USB layer
+obj-$(CONFIG_USB_OHCI) += usb-ohci.o
+
+# PCI network cards
+obj-y += rtl8139.o
+obj-y += e1000.o
 
 # Inter-VM PCI shared memory
-CONFIG_IVSHMEM =
-ifeq ($(CONFIG_KVM), y)
-  ifeq ($(CONFIG_PCI), y)
-    CONFIG_IVSHMEM = y
-  endif
-endif
-obj-$(CONFIG_IVSHMEM) += ivshmem.o
+obj-$(CONFIG_KVM) += ivshmem.o
 
 # Hardware support
 obj-i386-y += vga.o
-obj-i386-y += mc146818rtc.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 += mc146818rtc.o i8259.o pc.o
+obj-i386-y += cirrus_vga.o apic.o ioapic.o piix_pci.o
+obj-i386-y += vmmouse.o vmport.o hpet.o applesmc.o
 obj-i386-y += device-hotplug.o pci-hotplug.o smbios.o wdt_ib700.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
 
 # shared objects
-obj-ppc-y = ppc.o ppc_booke.o
+obj-ppc-y = ppc.o
 obj-ppc-y += vga.o
 # PREP target
-obj-ppc-y += mc146818rtc.o
+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)
-obj-ppc-$(CONFIG_PSERIES) += spapr.o spapr_hcall.o spapr_rtas.o spapr_vio.o
-obj-ppc-$(CONFIG_PSERIES) += xics.o spapr_vty.o spapr_llan.o spapr_vscsi.o
-obj-ppc-$(CONFIG_PSERIES) += spapr_pci.o device-hotplug.o pci-hotplug.o
 # PowerPC 4xx boards
 obj-ppc-y += ppc4xx_devs.o ppc4xx_pci.o ppc405_uc.o ppc405_boards.o
 obj-ppc-y += ppc440.o ppc440_bamboo.o
 # PowerPC E500 boards
-obj-ppc-y += ppce500_mpc8544ds.o mpc8544_guts.o ppce500_spin.o
-# PowerPC 440 Xilinx ML507 reference board.
-obj-ppc-y += virtex_ml507.o
+obj-ppc-y += ppce500_mpc8544ds.o
 obj-ppc-$(CONFIG_KVM) += kvm_ppc.o
 obj-ppc-$(CONFIG_FDT) += device_tree.o
-# PowerPC OpenPIC
-obj-ppc-y += openpic.o
-
-# Xilinx PPC peripherals
-obj-ppc-y += xilinx_intc.o
-obj-ppc-y += xilinx_timer.o
-obj-ppc-y += xilinx_uartlite.o
-obj-ppc-y += xilinx_ethlite.o
-
-# LM32 boards
-obj-lm32-y += lm32_boards.o
-obj-lm32-y += milkymist.o
-
-# LM32 peripherals
-obj-lm32-y += lm32_pic.o
-obj-lm32-y += lm32_juart.o
-obj-lm32-y += lm32_timer.o
-obj-lm32-y += lm32_uart.o
-obj-lm32-y += lm32_sys.o
-obj-lm32-y += milkymist-ac97.o
-obj-lm32-y += milkymist-hpdmc.o
-obj-lm32-y += milkymist-memcard.o
-obj-lm32-y += milkymist-minimac2.o
-obj-lm32-y += milkymist-pfpu.o
-obj-lm32-y += milkymist-softusb.o
-obj-lm32-y += milkymist-sysctl.o
-obj-lm32-$(CONFIG_OPENGL) += milkymist-tmu2.o
-obj-lm32-y += milkymist-uart.o
-obj-lm32-y += milkymist-vgafb.o
-obj-lm32-y += framebuffer.o
 
 obj-mips-y = mips_r4k.o mips_jazz.o mips_malta.o mips_mipssim.o
 obj-mips-y += mips_addr.o mips_timer.o mips_int.o
-obj-mips-y += vga.o
-obj-mips-y += jazz_led.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
@@ -334,10 +259,7 @@ obj-sparc-y += cirrus_vga.o
 else
 obj-sparc-y = sun4m.o lance.o tcx.o sun4m_iommu.o slavio_intctl.o
 obj-sparc-y += slavio_timer.o slavio_misc.o sparc32_dma.o
-obj-sparc-y += cs4231.o eccmemctl.o sbi.o sun4c_intctl.o leon3.o
-
-# GRLIB
-obj-sparc-y += grlib_gptimer.o grlib_irqmp.o grlib_apbuart.o
+obj-sparc-y += cs4231.o eccmemctl.o sbi.o sun4c_intctl.o
 endif
 
 obj-arm-y = integratorcp.o versatilepb.o arm_pic.o arm_timer.o
@@ -358,16 +280,11 @@ obj-arm-y += omap2.o omap_dss.o soc_dma.o omap_gptimer.o omap_synctimer.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 += z2.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-arm-y += pl041.o lm4549.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
@@ -378,20 +295,11 @@ obj-m68k-y += m68k-semi.o dummy_m68k.o
 
 obj-s390x-y = s390-virtio-bus.o s390-virtio.o
 
-obj-alpha-y = mc146818rtc.o
-obj-alpha-y += vga.o cirrus_vga.o
-obj-alpha-y += alpha_pci.o alpha_dp264.o alpha_typhoon.o
-
-obj-xtensa-y += xtensa_pic.o
-obj-xtensa-y += xtensa_sim.o
-obj-xtensa-y += xtensa_lx60.o
-obj-xtensa-y += xtensa-semi.o
-obj-xtensa-y += core-dc232b.o
-obj-xtensa-y += core-fsf.o
+obj-alpha-y = alpha_palcode.o
 
 main.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
 
-monitor.o: hmp-commands.h qmp-commands-old.h
+monitor.o: qemu-monitor.h
 
 $(obj-y) $(obj-$(TARGET_BASE_ARCH)-y): $(GENERATED_HEADERS)
 
@@ -399,51 +307,29 @@ obj-y += $(addprefix ../, $(common-obj-y))
 obj-y += $(addprefix ../libdis/, $(libdis-y))
 obj-y += $(libobj-y)
 obj-y += $(addprefix $(HWDIR)/, $(hw-obj-y))
-obj-y += $(addprefix ../, $(trace-obj-y))
 
 endif # CONFIG_SOFTMMU
 
-ifndef CONFIG_LINUX_USER
-ifndef CONFIG_BSD_USER
-# libcacard needs qemu-thread support, and besides is only needed by devices
-# so not requires with linux-user / bsd-user targets
-obj-$(CONFIG_SMARTCARD_NSS) += $(addprefix ../libcacard/, $(libcacard-y))
-endif # CONFIG_BSD_USER
-endif # CONFIG_LINUX_USER
-
 obj-$(CONFIG_GDBSTUB_XML) += gdbstub-xml.o
 
 $(QEMU_PROG): $(obj-y) $(obj-$(TARGET_BASE_ARCH)-y)
-	$(call LINK,$^)
+	$(call LINK,$(obj-y) $(obj-$(TARGET_BASE_ARCH)-y))
 
 
-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   $(TARGET_DIR)$@")
+gdbstub-xml.c: $(TARGET_XML_FILES) $(SRC_PATH)/feature_to_c.sh
+	$(call quiet-command,rm -f $@ && $(SHELL) $(SRC_PATH)/feature_to_c.sh $@ $(TARGET_XML_FILES),"  GEN   $(TARGET_DIR)$@")
 
-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
-	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $(TARGET_DIR)$@")
+qemu-monitor.h: $(SRC_PATH)/qemu-monitor.hx
+	$(call quiet-command,sh $(SRC_PATH)/hxtool -h < $< > $@,"  GEN   $(TARGET_DIR)$@")
 
 clean:
 	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-old.h gdbstub-xml.c
-ifdef CONFIG_TRACE_SYSTEMTAP
-	rm -f *.stp
-endif
+	rm -f *.d */*.d tcg/*.o ide/*.o
+	rm -f qemu-monitor.h gdbstub-xml.c
 
 install: all
 ifneq ($(PROGS),)
-	$(INSTALL) -m 755 $(PROGS) "$(DESTDIR)$(bindir)"
-ifneq ($(STRIP),)
-	$(STRIP) $(patsubst %,"$(DESTDIR)$(bindir)/%",$(PROGS))
-endif
-endif
-ifdef CONFIG_TRACE_SYSTEMTAP
-	$(INSTALL_DIR) "$(DESTDIR)$(datadir)/../systemtap/tapset"
-	$(INSTALL_DATA) $(QEMU_PROG).stp "$(DESTDIR)$(datadir)/../systemtap/tapset"
+	$(INSTALL) -m 755 $(STRIP_OPT) $(PROGS) "$(DESTDIR)$(bindir)"
 endif
 
 # Include automatically generated dependency files

Makefile.user

@@ -17,9 +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/README

@@ -19,7 +19,10 @@ o qmp-spec.txt      QEMU Monitor Protocol current specification
 o qmp-commands.txt  QMP supported commands (auto-generated at build-time)
 o qmp-events.txt    List of available asynchronous events
 
-There is also a simple Python script called 'qmp-shell' available.
+There are also two simple Python scripts available:
+
+o qmp-shell  A shell
+o vm-info    Show some information about the Virtual Machine
 
 IMPORTANT: It's strongly recommended to read the 'Stability Considerations'
 section in the qmp-commands.txt file before making any serious use of QMP.
@@ -79,7 +82,7 @@ doing any code change. This is so because:
   2. Review can improve your interface.  Letting that happen before
      you implement it can save you work.
 
-* The qmp-commands.txt file is generated from the qmp-commands.hx one, which
+* The qmp-commands.txt file is generated from the qemu-monitor.hx one, which
   is the file that should be edited.
 
 Homepage

QMP/qmp-events.txt

@@ -89,7 +89,7 @@ Data: None.
 
 Example:
 
-{ "event": "STOP",
+{ "event": "SHUTDOWN",
     "timestamp": { "seconds": 1267041730, "microseconds": 281295 } }
 
 VNC_CONNECTED
@@ -182,70 +182,6 @@ Example:
                     "host": "127.0.0.1", "sasl_username": "luiz" } },
         "timestamp": { "seconds": 1263475302, "microseconds": 150772 } }
 
-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}
-}}
-
-
 WATCHDOG
 --------
 

QMP/qmp-shell

@@ -1,8 +1,8 @@
 #!/usr/bin/python
 #
-# Low-level QEMU shell on top of QMP.
+# Simple QEMU shell on top of QMP
 #
-# Copyright (C) 2009, 2010 Red Hat Inc.
+# Copyright (C) 2009 Red Hat Inc.
 #
 # Authors:
 #  Luiz Capitulino <lcapitulino@redhat.com>
@@ -14,246 +14,60 @@
 #
 # Start QEMU with:
 #
-# # qemu [...] -qmp unix:./qmp-sock,server
+# $ qemu [...] -monitor control,unix:./qmp,server
 #
 # Run the shell:
 #
-# $ qmp-shell ./qmp-sock
+# $ qmp-shell ./qmp
 #
 # Commands have the following format:
 #
-#    < command-name > [ arg-name1=arg1 ] ... [ arg-nameN=argN ]
+# < command-name > [ arg-name1=arg1 ] ... [ arg-nameN=argN ]
 #
 # For example:
 #
-# (QEMU) device_add driver=e1000 id=net1
-# {u'return': {}}
-# (QEMU)
+# (QEMU) info item=network
 
 import qmp
 import readline
-import sys
+from sys import argv,exit
 
-class QMPCompleter(list):
-    def complete(self, text, state):
-        for cmd in self:
-            if cmd.startswith(text):
-                if not state:
-                    return cmd
-                else:
-                    state -= 1
-
-class QMPShellError(Exception):
-    pass
-
-class QMPShellBadPort(QMPShellError):
-    pass
-
-# 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):
-        qmp.QEMUMonitorProtocol.__init__(self, self.__get_address(address))
-        self._greeting = None
-        self._completer = None
-
-    def __get_address(self, arg):
-        """
-        Figure out if the argument is in the port:host form, if it's not it's
-        probably a file path.
-        """
-        addr = arg.split(':')
-        if len(addr) == 2:
-            try:
-                port = int(addr[1])
-            except ValueError:
-                raise QMPShellBadPort
-            return ( addr[0], port )
-        # socket path
-        return arg
-
-    def _fill_completion(self):
-        for cmd in self.cmd('query-commands')['return']:
-            self._completer.append(cmd['name'])
-
-    def __completer_setup(self):
-        self._completer = QMPCompleter()
-        self._fill_completion()
-        readline.set_completer(self._completer.complete)
-        readline.parse_and_bind("tab: complete")
-        # XXX: default delimiters conflict with some command names (eg. query-),
-        # clearing everything as it doesn't seem to matter
-        readline.set_completer_delims('')
-
-    def __build_cmd(self, cmdline):
-        """
-        Build a QMP input object from a user provided command-line in the
-        following format:
-    
-            < command-name > [ arg-name1=arg1 ] ... [ arg-nameN=argN ]
-        """
-        cmdargs = cmdline.split()
-        qmpcmd = { 'execute': cmdargs[0], 'arguments': {} }
-        for arg in cmdargs[1:]:
-            opt = arg.split('=')
-            try:
-                value = int(opt[1])
-            except ValueError:
-                value = opt[1]
-            qmpcmd['arguments'][opt[0]] = value
-        return qmpcmd
-
-    def _execute_cmd(self, cmdline):
-        try:
-            qmpcmd = self.__build_cmd(cmdline)
-        except:
-            print 'command format: <command-name> ',
-            print '[arg-name1=arg1] ... [arg-nameN=argN]'
-            return True
-        resp = self.cmd_obj(qmpcmd)
-        if resp is None:
-            print 'Disconnected'
-            return False
-        print resp
-        return True
-
-    def connect(self):
-        self._greeting = qmp.QEMUMonitorProtocol.connect(self)
-        self.__completer_setup()
-
-    def show_banner(self, msg='Welcome to the QMP low-level shell!'):
-        print msg
-        version = self._greeting['QMP']['version']['qemu']
-        print 'Connected to QEMU %d.%d.%d\n' % (version['major'],version['minor'],version['micro'])
-
-    def read_exec_command(self, prompt):
-        """
-        Read and execute a command.
-
-        @return True if execution was ok, return False if disconnected.
-        """
-        try:
-            cmdline = raw_input(prompt)
-        except EOFError:
-            print
-            return False
-        if cmdline == '':
-            for ev in self.get_events():
-                print ev
-            self.clear_events()
-            return True
-        else:
-            return self._execute_cmd(cmdline)
-
-class HMPShell(QMPShell):
-    def __init__(self, address):
-        QMPShell.__init__(self, address)
-        self.__cpu_index = 0
-
-    def __cmd_completion(self):
-        for cmd in self.__cmd_passthrough('help')['return'].split('\r\n'):
-            if cmd and cmd[0] != '[' and cmd[0] != '\t':
-                name = cmd.split()[0] # drop help text
-                if name == 'info':
-                    continue
-                if name.find('|') != -1:
-                    # Command in the form 'foobar|f' or 'f|foobar', take the
-                    # full name
-                    opt = name.split('|')
-                    if len(opt[0]) == 1:
-                        name = opt[1]
-                    else:
-                        name = opt[0]
-                self._completer.append(name)
-                self._completer.append('help ' + name) # help completion
-
-    def __info_completion(self):
-        for cmd in self.__cmd_passthrough('info')['return'].split('\r\n'):
-            if cmd:
-                self._completer.append('info ' + cmd.split()[1])
-
-    def __other_completion(self):
-        # special cases
-        self._completer.append('help info')
-
-    def _fill_completion(self):
-        self.__cmd_completion()
-        self.__info_completion()
-        self.__other_completion()
-
-    def __cmd_passthrough(self, cmdline, cpu_index = 0):
-        return self.cmd_obj({ 'execute': 'human-monitor-command', 'arguments':
-                              { 'command-line': cmdline,
-                                'cpu-index': cpu_index } })
-
-    def _execute_cmd(self, cmdline):
-        if cmdline.split()[0] == "cpu":
-            # trap the cpu command, it requires special setting
-            try:
-                idx = int(cmdline.split()[1])
-                if not 'return' in self.__cmd_passthrough('info version', idx):
-                    print 'bad CPU index'
-                    return True
-                self.__cpu_index = idx
-            except ValueError:
-                print 'cpu command takes an integer argument'
-                return True
-        resp = self.__cmd_passthrough(cmdline, self.__cpu_index)
-        if resp is None:
-            print 'Disconnected'
-            return False
-        assert 'return' in resp or 'error' in resp
-        if 'return' in resp:
-            # Success
-            if len(resp['return']) > 0:
-                print resp['return'],
-        else:
-            # Error
-            print '%s: %s' % (resp['error']['class'], resp['error']['desc'])
-        return True
-
-    def show_banner(self):
-        QMPShell.show_banner(self, msg='Welcome to the HMP shell!')
-
-def die(msg):
-    sys.stderr.write('ERROR: %s\n' % msg)
-    sys.exit(1)
-
-def fail_cmdline(option=None):
-    if option:
-        sys.stderr.write('ERROR: bad command-line option \'%s\'\n' % option)
-    sys.stderr.write('qemu-shell [ -H ] < UNIX socket path> | < TCP address:port >\n')
-    sys.exit(1)
+def shell_help():
+    print 'bye  exit from the shell'
 
 def main():
-    addr = ''
-    try:
-        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]
+    if len(argv) != 2:
+        print 'qemu-shell <unix-socket>'
+        exit(1)
+
+    qemu = qmp.QEMUMonitorProtocol(argv[1])
+    qemu.connect()
+    qemu.send("qmp_capabilities")
+
+    print 'Connected!'
+
+    while True:
+        try:
+            cmd = raw_input('(QEMU) ')
+        except EOFError:
+            print
+            break
+        if cmd == '':
+            continue
+        elif cmd == 'bye':
+            break
+        elif cmd == 'help':
+            shell_help()
         else:
-                fail_cmdline()
-    except QMPShellBadPort:
-        die('bad port number in command-line')
-
-    try:
-        qemu.connect()
-    except qmp.QMPConnectError:
-        die('Didn\'t get QMP greeting message')
-    except qmp.QMPCapabilitiesError:
-        die('Could not negotiate capabilities')
-    except qemu.error:
-        die('Could not connect to %s' % addr)
-
-    qemu.show_banner()
-    while qemu.read_exec_command('(QEMU) '):
-        pass
-    qemu.close()
+            try:
+                resp = qemu.send(cmd)
+                if resp == None:
+                    print 'Disconnected'
+                    break
+                print resp
+            except IndexError:
+                print '-> command format: <command-name> ',
+                print '[arg-name1=arg1] ... [arg-nameN=argN]'
 
 if __name__ == '__main__':
     main()

QMP/qmp.py

@@ -1,6 +1,6 @@
 # QEMU Monitor Protocol Python class
 # 
-# Copyright (C) 2009, 2010 Red Hat Inc.
+# Copyright (C) 2009 Red Hat Inc.
 #
 # Authors:
 #  Luiz Capitulino <lcapitulino@redhat.com>
@@ -8,9 +8,7 @@
 # This work is licensed under the terms of the GNU GPL, version 2.  See
 # the COPYING file in the top-level directory.
 
-import json
-import errno
-import socket
+import socket, json
 
 class QMPError(Exception):
     pass
@@ -18,140 +16,61 @@ class QMPError(Exception):
 class QMPConnectError(QMPError):
     pass
 
-class QMPCapabilitiesError(QMPError):
-    pass
-
 class QEMUMonitorProtocol:
-    def __init__(self, address, server=False):
-        """
-        Create a QEMUMonitorProtocol class.
-
-        @param address: QEMU address, can be either a unix socket path (string)
-                        or a tuple in the form ( address, port ) for a TCP
-                        connection
-        @param server: server mode listens on the socket (bool)
-        @raise socket.error on socket connection errors
-        @note No connection is established, this is done by the connect() or
-              accept() methods
-        """
-        self.__events = []
-        self.__address = address
-        self.__sock = self.__get_sock()
-        if server:
-            self.__sock.bind(self.__address)
-            self.__sock.listen(1)
-
-    def __get_sock(self):
-        if isinstance(self.__address, tuple):
-            family = socket.AF_INET
-        else:
-            family = socket.AF_UNIX
-        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
-        # Greeting seems ok, negotiate capabilities
-        resp = self.cmd('qmp_capabilities')
-        if "return" in resp:
-            return greeting
-        raise QMPCapabilitiesError
-
-    def __json_read(self, only_event=False):
-        while True:
-            data = self.__sockfile.readline()
-            if not data:
-                return
-            resp = json.loads(data)
-            if 'event' in resp:
-                self.__events.append(resp)
-                if not only_event:
-                    continue
-            return resp
-
-    error = socket.error
-
     def connect(self):
-        """
-        Connect to the QMP Monitor and perform capabilities negotiation.
-
-        @return QMP greeting dict
-        @raise socket.error on socket connection errors
-        @raise QMPConnectError if the greeting is not received
-        @raise QMPCapabilitiesError if fails to negotiate capabilities
-        """
-        self.__sock.connect(self.__address)
-        return self.__negotiate_capabilities()
-
-    def accept(self):
-        """
-        Await connection from QMP Monitor and perform capabilities negotiation.
-
-        @return QMP greeting dict
-        @raise socket.error on socket connection errors
-        @raise QMPConnectError if the greeting is not received
-        @raise QMPCapabilitiesError if fails to negotiate capabilities
-        """
-        self.__sock, _ = self.__sock.accept()
-        return self.__negotiate_capabilities()
-
-    def cmd_obj(self, qmp_cmd):
-        """
-        Send a QMP command to the QMP Monitor.
-
-        @param qmp_cmd: QMP command to be sent as a Python dict
-        @return QMP response as a Python dict or None if the connection has
-                been closed
-        """
-        try:
-            self.__sock.sendall(json.dumps(qmp_cmd))
-        except socket.error, err:
-            if err[0] == errno.EPIPE:
-                return
-            raise socket.error(err)
-        return self.__json_read()
-
-    def cmd(self, name, args=None, id=None):
-        """
-        Build a QMP command and send it to the QMP Monitor.
-
-        @param name: command name (string)
-        @param args: command arguments (dict)
-        @param id: command id (dict, list, string or int)
-        """
-        qmp_cmd = { 'execute': name }
-        if args:
-            qmp_cmd['arguments'] = args
-        if id:
-            qmp_cmd['id'] = id
-        return self.cmd_obj(qmp_cmd)
-
-    def get_events(self, wait=False):
-        """
-        Get a list of available QMP events.
-
-        @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)
-        return self.__events
-
-    def clear_events(self):
-        """
-        Clear current list of pending events.
-        """
-        self.__events = []
+        self.sock.connect(self.filename)
+        data = self.__json_read()
+        if data == None:
+            raise QMPConnectError
+        if not data.has_key('QMP'):
+            raise QMPConnectError
+        return data['QMP']['capabilities']
 
     def close(self):
-        self.__sock.close()
-        self.__sockfile.close()
+        self.sock.close()
+
+    def send_raw(self, line):
+        self.sock.send(str(line))
+        return self.__json_read()
+
+    def send(self, cmdline):
+        cmd = self.__build_cmd(cmdline)
+        self.__json_send(cmd)
+        resp = self.__json_read()
+        if resp == None:
+            return
+        elif resp.has_key('error'):
+            return resp['error']
+        else:
+            return resp['return']
+
+    def __build_cmd(self, cmdline):
+        cmdargs = cmdline.split()
+        qmpcmd = { 'execute': cmdargs[0], 'arguments': {} }
+        for arg in cmdargs[1:]:
+            opt = arg.split('=')
+            try:
+                value = int(opt[1])
+            except ValueError:
+                value = opt[1]
+            qmpcmd['arguments'][opt[0]] = value
+        return qmpcmd
+
+    def __json_send(self, cmd):
+        # XXX: We have to send any additional char, otherwise
+        # the Server won't read our input
+        self.sock.send(json.dumps(cmd) + ' ')
+
+    def __json_read(self):
+        try:
+            while True:
+                line = json.loads(self.sockfile.readline())
+                if not 'event' in line:
+                    return line
+        except ValueError:
+            return
+
+    def __init__(self, filename):
+        self.filename = filename
+        self.sock = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
+        self.sockfile = self.sock.makefile()

QMP/vm-info

@@ -0,0 +1,33 @@
+#!/usr/bin/python
+#
+# Print Virtual Machine information
+#
+# Usage:
+#
+# Start QEMU with:
+#
+# $ qemu [...] -monitor control,unix:./qmp,server
+#
+# Run vm-info:
+#
+# $ vm-info ./qmp
+#
+# Luiz Capitulino <lcapitulino@redhat.com>
+
+import qmp
+from sys import argv,exit
+
+def main():
+    if len(argv) != 2:
+        print 'vm-info <unix-socket>'
+        exit(1)
+
+    qemu = qmp.QEMUMonitorProtocol(argv[1])
+    qemu.connect()
+    qemu.send("qmp_capabilities")
+
+    for cmd in [ 'version', 'kvm', 'status', 'uuid', 'balloon' ]:
+        print cmd + ': ' + str(qemu.send('query-' + cmd))
+
+if __name__ == '__main__':
+    main()

VERSION

@@ -1 +1 @@
-1.0,1
+0.13.0

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

@@ -24,6 +24,7 @@
 
 
 #include "qemu-common.h"
+#include "sysemu.h"
 #include "acl.h"
 
 #ifdef CONFIG_FNMATCH
@@ -55,8 +56,8 @@ 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 +66,7 @@ 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 +96,13 @@ 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 +117,8 @@ 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 +143,8 @@ 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.c

@@ -75,13 +75,13 @@ int qemu_aio_set_fd_handler(int fd,
                  * releasing the walking_handlers lock.
                  */
                 QLIST_REMOVE(node, node);
-                g_free(node);
+                qemu_free(node);
             }
         }
     } else {
         if (node == NULL) {
             /* Alloc and insert if it's not already there */
-            node = g_malloc0(sizeof(AioHandler));
+            node = qemu_mallocz(sizeof(AioHandler));
             node->fd = fd;
             QLIST_INSERT_HEAD(&aio_handlers, node, node);
         }
@@ -220,7 +220,7 @@ void qemu_aio_wait(void)
 
                 if (tmp->deleted) {
                     QLIST_REMOVE(tmp, node);
-                    g_free(tmp);
+                    qemu_free(tmp);
                 }
             }
 

alpha-dis.c

@@ -22,9 +22,6 @@ along with this file; see the file COPYING.  If not, see
 #include <stdio.h>
 #include "dis-asm.h"
 
-/* MAX is redefined below, so remove any previous definition. */
-#undef MAX
-
 /* The opcode table is an array of struct alpha_opcode.  */
 
 struct alpha_opcode
@@ -238,6 +235,10 @@ extern const unsigned alpha_num_operands;
 #define AXP_REG_SP	30
 #define AXP_REG_ZERO	31
 
+#define bfd_mach_alpha_ev4  0x10
+#define bfd_mach_alpha_ev5  0x20
+#define bfd_mach_alpha_ev6  0x30
+
 enum bfd_reloc_code_real {
     BFD_RELOC_23_PCREL_S2,
     BFD_RELOC_ALPHA_HINT

arch_init.c

@@ -23,7 +23,6 @@
  */
 #include <stdint.h>
 #include <stdarg.h>
-#include <stdlib.h>
 #ifndef _WIN32
 #include <sys/types.h>
 #include <sys/mman.h>
@@ -64,8 +63,6 @@ const char arch_config_name[] = CONFIG_QEMU_CONFDIR "/target-" TARGET_ARCH ".con
 #define QEMU_ARCH QEMU_ARCH_I386
 #elif defined(TARGET_M68K)
 #define QEMU_ARCH QEMU_ARCH_M68K
-#elif defined(TARGET_LM32)
-#define QEMU_ARCH QEMU_ARCH_LM32
 #elif defined(TARGET_MICROBLAZE)
 #define QEMU_ARCH QEMU_ARCH_MICROBLAZE
 #elif defined(TARGET_MIPS)
@@ -78,8 +75,6 @@ const char arch_config_name[] = CONFIG_QEMU_CONFDIR "/target-" TARGET_ARCH ".con
 #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
 #endif
 
 const uint32_t arch_type = QEMU_ARCH;
@@ -87,12 +82,12 @@ const uint32_t arch_type = QEMU_ARCH;
 /***********************************************************/
 /* ram save/restore */
 
-#define RAM_SAVE_FLAG_FULL     0x01 /* Obsolete, not used anymore */
-#define RAM_SAVE_FLAG_COMPRESS 0x02
-#define RAM_SAVE_FLAG_MEM_SIZE 0x04
-#define RAM_SAVE_FLAG_PAGE     0x08
-#define RAM_SAVE_FLAG_EOS      0x10
-#define RAM_SAVE_FLAG_CONTINUE 0x20
+#define RAM_SAVE_FLAG_FULL	0x01 /* Obsolete, not used anymore */
+#define RAM_SAVE_FLAG_COMPRESS	0x02
+#define RAM_SAVE_FLAG_MEM_SIZE	0x04
+#define RAM_SAVE_FLAG_PAGE	0x08
+#define RAM_SAVE_FLAG_EOS	0x10
+#define RAM_SAVE_FLAG_CONTINUE	0x20
 
 static int is_dup_page(uint8_t *page, uint8_t ch)
 {
@@ -217,46 +212,12 @@ uint64_t ram_bytes_total(void)
     return total;
 }
 
-static int block_compar(const void *a, const void *b)
-{
-    RAMBlock * const *ablock = a;
-    RAMBlock * const *bblock = b;
-    if ((*ablock)->offset < (*bblock)->offset) {
-        return -1;
-    } else if ((*ablock)->offset > (*bblock)->offset) {
-        return 1;
-    }
-    return 0;
-}
-
-static void sort_ram_list(void)
-{
-    RAMBlock *block, *nblock, **blocks;
-    int n;
-    n = 0;
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
-        ++n;
-    }
-    blocks = g_malloc(n * sizeof *blocks);
-    n = 0;
-    QLIST_FOREACH_SAFE(block, &ram_list.blocks, next, nblock) {
-        blocks[n++] = block;
-        QLIST_REMOVE(block, next);
-    }
-    qsort(blocks, n, sizeof *blocks, block_compar);
-    while (--n >= 0) {
-        QLIST_INSERT_HEAD(&ram_list.blocks, blocks[n], next);
-    }
-    g_free(blocks);
-}
-
 int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
 {
     ram_addr_t addr;
     uint64_t bytes_transferred_last;
     double bwidth = 0;
     uint64_t expected_time = 0;
-    int ret;
 
     if (stage < 0) {
         cpu_physical_memory_set_dirty_tracking(0);
@@ -264,8 +225,8 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
     }
 
     if (cpu_physical_sync_dirty_bitmap(0, TARGET_PHYS_ADDR_MAX) != 0) {
-        qemu_file_set_error(f, -EINVAL);
-        return -EINVAL;
+        qemu_file_set_error(f);
+        return 0;
     }
 
     if (stage == 1) {
@@ -273,7 +234,6 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
         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) {
@@ -301,7 +261,7 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
     bytes_transferred_last = bytes_transferred;
     bwidth = qemu_get_clock_ns(rt_clock);
 
-    while ((ret = qemu_file_rate_limit(f)) == 0) {
+    while (!qemu_file_rate_limit(f)) {
         int bytes_sent;
 
         bytes_sent = ram_save_block(f);
@@ -311,10 +271,6 @@ int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
         }
     }
 
-    if (ret < 0) {
-        return ret;
-    }
-
     bwidth = qemu_get_clock_ns(rt_clock) - bwidth;
     bwidth = (bytes_transferred - bytes_transferred_last) / bwidth;
 
@@ -376,7 +332,6 @@ int ram_load(QEMUFile *f, void *opaque, int version_id)
 {
     ram_addr_t addr;
     int flags;
-    int error;
 
     if (version_id < 3 || version_id > 4) {
         return -EINVAL;
@@ -435,16 +390,13 @@ int ram_load(QEMUFile *f, void *opaque, int version_id)
                 host = qemu_get_ram_ptr(addr);
             else
                 host = host_from_stream_offset(f, addr, flags);
-            if (!host) {
-                return -EINVAL;
-            }
 
             ch = qemu_get_byte(f);
             memset(host, ch, TARGET_PAGE_SIZE);
 #ifndef _WIN32
             if (ch == 0 &&
                 (!kvm_enabled() || kvm_has_sync_mmu())) {
-                qemu_madvise(host, TARGET_PAGE_SIZE, QEMU_MADV_DONTNEED);
+                madvise(host, TARGET_PAGE_SIZE, MADV_DONTNEED);
             }
 #endif
         } else if (flags & RAM_SAVE_FLAG_PAGE) {
@@ -457,28 +409,21 @@ int ram_load(QEMUFile *f, void *opaque, int version_id)
 
             qemu_get_buffer(f, host, TARGET_PAGE_SIZE);
         }
-        error = qemu_file_get_error(f);
-        if (error) {
-            return error;
+        if (qemu_file_has_error(f)) {
+            return -EIO;
         }
     } while (!(flags & RAM_SAVE_FLAG_EOS));
 
     return 0;
 }
 
-#ifdef HAS_AUDIO
-struct soundhw {
-    const char *name;
-    const char *descr;
-    int enabled;
-    int isa;
-    union {
-        int (*init_isa) (qemu_irq *pic);
-        int (*init_pci) (PCIBus *bus);
-    } init;
-};
+void qemu_service_io(void)
+{
+    qemu_notify_event();
+}
 
-static struct soundhw soundhw[] = {
+#ifdef HAS_AUDIO
+struct soundhw soundhw[] = {
 #ifdef HAS_AUDIO_CHOICE
 #if defined(TARGET_I386) || defined(TARGET_MIPS)
     {
@@ -554,16 +499,6 @@ static struct soundhw soundhw[] = {
     },
 #endif
 
-#ifdef CONFIG_HDA
-    {
-        "hda",
-        "Intel HD Audio",
-        0,
-        0,
-        { .init_pci = intel_hda_and_codec_init }
-    },
-#endif
-
 #endif /* HAS_AUDIO_CHOICE */
 
     { NULL, NULL, 0, 0, { NULL } }
@@ -627,32 +562,10 @@ void select_soundhw(const char *optarg)
         }
     }
 }
-
-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_pic) {
-                    c->init.init_isa(isa_pic);
-                }
-            } else {
-                if (pci_bus) {
-                    c->init.init_pci(pci_bus);
-                }
-            }
-        }
-    }
-}
 #else
 void select_soundhw(const char *optarg)
 {
 }
-void audio_init(qemu_irq *isa_pic, PCIBus *pci_bus)
-{
-}
 #endif
 
 int qemu_uuid_parse(const char *str, uint8_t *uuid)
@@ -713,11 +626,6 @@ int audio_available(void)
 #endif
 }
 
-int tcg_available(void)
-{
-    return 1;
-}
-
 int kvm_available(void)
 {
 #ifdef CONFIG_KVM

arch_init.h

@@ -10,25 +10,23 @@ enum {
     QEMU_ARCH_CRIS = 4,
     QEMU_ARCH_I386 = 8,
     QEMU_ARCH_M68K = 16,
-    QEMU_ARCH_LM32 = 32,
-    QEMU_ARCH_MICROBLAZE = 64,
-    QEMU_ARCH_MIPS = 128,
-    QEMU_ARCH_PPC = 256,
-    QEMU_ARCH_S390X = 512,
-    QEMU_ARCH_SH4 = 1024,
-    QEMU_ARCH_SPARC = 2048,
-    QEMU_ARCH_XTENSA = 4096,
+    QEMU_ARCH_MICROBLAZE = 32,
+    QEMU_ARCH_MIPS = 64,
+    QEMU_ARCH_PPC = 128,
+    QEMU_ARCH_S390X = 256,
+    QEMU_ARCH_SH4 = 512,
+    QEMU_ARCH_SPARC = 1024,
 };
 
 extern const uint32_t arch_type;
 
 void select_soundhw(const char *optarg);
+int ram_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque);
+int ram_load(QEMUFile *f, void *opaque, int version_id);
 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(qemu_irq *isa_pic, PCIBus *pci_bus);
-int tcg_available(void);
 int kvm_available(void);
 int xen_available(void);
 

arm-dis.c

@@ -1587,7 +1587,7 @@ arm_decode_bitfield (const char *ptr, unsigned long insn,
 }
 
 static void
-arm_decode_shift (long given, fprintf_function func, void *stream,
+arm_decode_shift (long given, fprintf_ftype func, void *stream,
 		  int print_shift)
 {
   func (stream, "%s", arm_regnames[given & 0xf]);
@@ -1633,7 +1633,7 @@ print_insn_coprocessor (bfd_vma pc, struct disassemble_info *info, long given,
 {
   const struct opcode32 *insn;
   void *stream = info->stream;
-  fprintf_function func = info->fprintf_func;
+  fprintf_ftype func = info->fprintf_func;
   unsigned long mask;
   unsigned long value;
   int cond;
@@ -2127,7 +2127,7 @@ static void
 print_arm_address (bfd_vma pc, struct disassemble_info *info, long given)
 {
   void *stream = info->stream;
-  fprintf_function func = info->fprintf_func;
+  fprintf_ftype func = info->fprintf_func;
 
   if (((given & 0x000f0000) == 0x000f0000)
       && ((given & 0x02000000) == 0))
@@ -2222,7 +2222,7 @@ print_insn_neon (struct disassemble_info *info, long given, bfd_boolean thumb)
 {
   const struct opcode32 *insn;
   void *stream = info->stream;
-  fprintf_function func = info->fprintf_func;
+  fprintf_ftype func = info->fprintf_func;
 
   if (thumb)
     {
@@ -2676,7 +2676,7 @@ print_insn_arm_internal (bfd_vma pc, struct disassemble_info *info, long given)
 {
   const struct opcode32 *insn;
   void *stream = info->stream;
-  fprintf_function func = info->fprintf_func;
+  fprintf_ftype func = info->fprintf_func;
 
   if (print_insn_coprocessor (pc, info, given, false))
     return;
@@ -3036,7 +3036,7 @@ print_insn_thumb16 (bfd_vma pc, struct disassemble_info *info, long given)
 {
   const struct opcode16 *insn;
   void *stream = info->stream;
-  fprintf_function func = info->fprintf_func;
+  fprintf_ftype func = info->fprintf_func;
 
   for (insn = thumb_opcodes; insn->assembler; insn++)
     if ((given & insn->mask) == insn->value)
@@ -3312,7 +3312,7 @@ print_insn_thumb32 (bfd_vma pc, struct disassemble_info *info, long given)
 {
   const struct opcode32 *insn;
   void *stream = info->stream;
-  fprintf_function func = info->fprintf_func;
+  fprintf_ftype func = info->fprintf_func;
 
   if (print_insn_coprocessor (pc, info, given, true))
     return;
@@ -4101,30 +4101,6 @@ print_insn_arm (bfd_vma pc, struct disassemble_info *info)
        addresses, since the addend is not currently pc-relative.  */
     pc = 0;
 
-  /* We include the hexdump of the instruction. The format here
-     matches that used by objdump and the ARM ARM (in particular,
-     32 bit Thumb instructions are displayed as pairs of halfwords,
-     not as a single word.)  */
-  if (is_thumb)
-    {
-      if (size == 2)
-	{
-	  info->fprintf_func(info->stream, "%04lx       ",
-			     ((unsigned long)given) & 0xffff);
-	}
-      else
-	{
-	  info->fprintf_func(info->stream, "%04lx %04lx  ",
-			     (((unsigned long)given) >> 16) & 0xffff,
-			     ((unsigned long)given) & 0xffff);
-	}
-    }
-  else
-    {
-      info->fprintf_func(info->stream, "%08lx      ",
-			 ((unsigned long)given) & 0xffffffff);
-    }
-
   printer (pc, info, given);
 
   if (is_thumb)

arm-semi.c

@@ -33,8 +33,8 @@
 #define ARM_ANGEL_HEAP_SIZE (128 * 1024 * 1024)
 #else
 #include "qemu-common.h"
+#include "sysemu.h"
 #include "gdbstub.h"
-#include "hw/arm-misc.h"
 #endif
 
 #define SYS_OPEN        0x01
@@ -370,88 +370,49 @@ uint32_t do_arm_semihosting(CPUState *env)
         return syscall_err;
 #endif
     case SYS_GET_CMDLINE:
+#ifdef CONFIG_USER_ONLY
+        /* Build a commandline from the original argv.  */
         {
-            /* Build a command-line from the original argv.
-             *
-             * The inputs are:
-             *     * 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:
-             *     * ARG(0), pointer to null-terminated string of the
-             *               command line.
-             *     * ARG(1), length of the string pointed to by ARG(0).
-             */
+            char **arg = ts->info->host_argv;
+            int len = ARG(1);
+            /* lock the buffer on the ARM side */
+            char *cmdline_buffer = (char*)lock_user(VERIFY_WRITE, ARG(0), len, 0);
 
-            char *output_buffer;
-            size_t input_size = ARG(1);
-            size_t output_size;
-            int status = 0;
+            if (!cmdline_buffer)
+                /* FIXME - should this error code be -TARGET_EFAULT ? */
+                return (uint32_t)-1;
 
-            /* Compute the size of the output string.  */
-#if !defined(CONFIG_USER_ONLY)
-            output_size = strlen(ts->boot_info->kernel_filename)
-                        + 1  /* Separating space.  */
-                        + strlen(ts->boot_info->kernel_cmdline)
-                        + 1; /* Terminating null byte.  */
-#else
-            unsigned int i;
+            s = cmdline_buffer;
+            while (*arg && len > 2) {
+                int n = strlen(*arg);
 
-            output_size = ts->info->arg_end - ts->info->arg_start;
-            if (!output_size) {
-                /* We special-case the "empty command line" case (argc==0).
-                   Just provide the terminating 0. */
-                output_size = 1;
-            }
-#endif
-
-            if (output_size > input_size) {
-                 /* Not enough space to store command-line arguments.  */
-                return -1;
-            }
-
-            /* Adjust the command-line length.  */
-            SET_ARG(1, output_size - 1);
-
-            /* Lock the buffer on the ARM side.  */
-            output_buffer = lock_user(VERIFY_WRITE, ARG(0), output_size, 0);
-            if (!output_buffer) {
-                return -1;
-            }
-
-            /* Copy the command-line arguments.  */
-#if !defined(CONFIG_USER_ONLY)
-            pstrcpy(output_buffer, output_size, ts->boot_info->kernel_filename);
-            pstrcat(output_buffer, output_size, " ");
-            pstrcat(output_buffer, output_size, ts->boot_info->kernel_cmdline);
-#else
-            if (output_size == 1) {
-                /* Empty command-line.  */
-                output_buffer[0] = '\0';
-                goto out;
-            }
-
-            if (copy_from_user(output_buffer, ts->info->arg_start,
-                               output_size)) {
-                status = -1;
-                goto out;
-            }
-
-            /* Separate arguments by white spaces.  */
-            for (i = 0; i < output_size - 1; i++) {
-                if (output_buffer[i] == 0) {
-                    output_buffer[i] = ' ';
+                if (s != cmdline_buffer) {
+                    *(s++) = ' ';
+                    len--;
                 }
+                if (n >= len)
+                    n = len - 1;
+                memcpy(s, *arg, n);
+                s += n;
+                len -= n;
+                arg++;
             }
-        out:
-#endif
-            /* Unlock the buffer on the ARM side.  */
-            unlock_user(output_buffer, ARG(0), output_size);
+            /* Null terminate the string.  */
+            *s = 0;
+            len = s - cmdline_buffer;
 
-            return status;
+            /* Unlock the buffer on the ARM side.  */
+            unlock_user(cmdline_buffer, ARG(0), len);
+
+            /* Adjust the commandline length argument.  */
+            SET_ARG(1, len);
+
+            /* Return success if commandline fit into buffer.  */
+            return *arg ? -1 : 0;
         }
+#else
+      return -1;
+#endif
     case SYS_HEAPINFO:
         {
             uint32_t *ptr;
@@ -461,16 +422,15 @@ uint32_t do_arm_semihosting(CPUState *env)
             /* Some C libraries assume the heap immediately follows .bss, so
                allocate it using sbrk.  */
             if (!ts->heap_limit) {
-                abi_ulong ret;
+                long ret;
 
                 ts->heap_base = do_brk(0);
                 limit = ts->heap_base + ARM_ANGEL_HEAP_SIZE;
                 /* Try a big heap, and reduce the size if that fails.  */
                 for (;;) {
                     ret = do_brk(limit);
-                    if (ret >= limit) {
+                    if (ret != -1)
                         break;
-                    }
                     limit = (ts->heap_base >> 1) + (limit >> 1);
                 }
                 ts->heap_limit = limit;

arm.ld

@@ -71,23 +71,23 @@ SECTIONS
   .data1   : { *(.data1) }
   .preinit_array     :
   {
-    PROVIDE (__preinit_array_start = .);
+    PROVIDE_HIDDEN (__preinit_array_start = .);
     KEEP (*(.preinit_array))
-    PROVIDE (__preinit_array_end = .);
+    PROVIDE_HIDDEN (__preinit_array_end = .);
   }
   .init_array     :
   {
-     PROVIDE (__init_array_start = .);
+     PROVIDE_HIDDEN (__init_array_start = .);
      KEEP (*(SORT(.init_array.*)))
      KEEP (*(.init_array))
-     PROVIDE (__init_array_end = .);
+     PROVIDE_HIDDEN (__init_array_end = .);
   }
   .fini_array     :
   {
-    PROVIDE (__fini_array_start = .);
+    PROVIDE_HIDDEN (__fini_array_start = .);
     KEEP (*(.fini_array))
     KEEP (*(SORT(.fini_array.*)))
-    PROVIDE (__fini_array_end = .);
+    PROVIDE_HIDDEN (__fini_array_end = .);
   }
   .ctors         :
   {

async.c

@@ -24,10 +24,93 @@
 
 #include "qemu-common.h"
 #include "qemu-aio.h"
-#include "main-loop.h"
 
-/* Anchor of the list of Bottom Halves belonging to the context */
-static struct QEMUBH *first_bh;
+/*
+ * 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) */
@@ -44,25 +127,21 @@ struct QEMUBH {
 QEMUBH *qemu_bh_new(QEMUBHFunc *cb, void *opaque)
 {
     QEMUBH *bh;
-    bh = g_malloc0(sizeof(QEMUBH));
+    bh = qemu_mallocz(sizeof(QEMUBH));
     bh->cb = cb;
     bh->opaque = opaque;
-    bh->next = first_bh;
-    first_bh = bh;
+    bh->next = async_context->first_bh;
+    async_context->first_bh = bh;
     return bh;
 }
 
 int qemu_bh_poll(void)
 {
-    QEMUBH *bh, **bhp, *next;
+    QEMUBH *bh, **bhp;
     int ret;
-    static int nesting = 0;
-
-    nesting++;
 
     ret = 0;
-    for (bh = first_bh; bh; bh = next) {
-        next = bh->next;
+    for (bh = async_context->first_bh; bh; bh = bh->next) {
         if (!bh->deleted && bh->scheduled) {
             bh->scheduled = 0;
             if (!bh->idle)
@@ -72,20 +151,15 @@ int qemu_bh_poll(void)
         }
     }
 
-    nesting--;
-
     /* remove deleted bhs */
-    if (!nesting) {
-        bhp = &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;
@@ -124,7 +198,7 @@ void qemu_bh_update_timeout(int *timeout)
 {
     QEMUBH *bh;
 
-    for (bh = 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

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;
         }
     }
@@ -318,7 +318,7 @@ static int alsa_write (SWVoiceOut *sw, void *buf, int len)
     return audio_pcm_sw_write (sw, buf, len);
 }
 
-static snd_pcm_format_t aud_to_alsafmt (audfmt_e fmt, int endianness)
+static snd_pcm_format_t aud_to_alsafmt (audfmt_e fmt)
 {
     switch (fmt) {
     case AUD_FMT_S8:
@@ -328,36 +328,16 @@ static snd_pcm_format_t aud_to_alsafmt (audfmt_e fmt, int endianness)
         return SND_PCM_FORMAT_U8;
 
     case AUD_FMT_S16:
-        if (endianness) {
-            return SND_PCM_FORMAT_S16_BE;
-        }
-        else {
-            return SND_PCM_FORMAT_S16_LE;
-        }
+        return SND_PCM_FORMAT_S16_LE;
 
     case AUD_FMT_U16:
-        if (endianness) {
-            return SND_PCM_FORMAT_U16_BE;
-        }
-        else {
-            return SND_PCM_FORMAT_U16_LE;
-        }
+        return SND_PCM_FORMAT_U16_LE;
 
     case AUD_FMT_S32:
-        if (endianness) {
-            return SND_PCM_FORMAT_S32_BE;
-        }
-        else {
-            return SND_PCM_FORMAT_S32_LE;
-        }
+        return SND_PCM_FORMAT_S32_LE;
 
     case AUD_FMT_U32:
-        if (endianness) {
-            return SND_PCM_FORMAT_U32_BE;
-        }
-        else {
-            return SND_PCM_FORMAT_U32_LE;
-        }
+        return SND_PCM_FORMAT_U32_LE;
 
     default:
         dolog ("Internal logic error: Bad audio format %d\n", fmt);
@@ -816,7 +796,7 @@ 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;
     }
 }
@@ -829,7 +809,7 @@ static int alsa_init_out (HWVoiceOut *hw, struct audsettings *as)
     snd_pcm_t *handle;
     struct audsettings obt_as;
 
-    req.fmt = aud_to_alsafmt (as->fmt, as->endianness);
+    req.fmt = aud_to_alsafmt (as->fmt);
     req.freq = as->freq;
     req.nchannels = as->nchannels;
     req.period_size = conf.period_size_out;
@@ -863,15 +843,11 @@ static int alsa_init_out (HWVoiceOut *hw, struct audsettings *as)
     return 0;
 }
 
-#define VOICE_CTL_PAUSE 0
-#define VOICE_CTL_PREPARE 1
-#define VOICE_CTL_START 2
-
-static int alsa_voice_ctl (snd_pcm_t *handle, const char *typ, int ctl)
+static int alsa_voice_ctl (snd_pcm_t *handle, const char *typ, int pause)
 {
     int err;
 
-    if (ctl == VOICE_CTL_PAUSE) {
+    if (pause) {
         err = snd_pcm_drop (handle);
         if (err < 0) {
             alsa_logerr (err, "Could not stop %s\n", typ);
@@ -884,13 +860,6 @@ static int alsa_voice_ctl (snd_pcm_t *handle, const char *typ, int ctl)
             alsa_logerr (err, "Could not prepare handle for %s\n", typ);
             return -1;
         }
-        if (ctl == VOICE_CTL_START) {
-            err = snd_pcm_start(handle);
-            if (err < 0) {
-                alsa_logerr (err, "Could not start handle for %s\n", typ);
-                return -1;
-            }
-        }
     }
 
     return 0;
@@ -915,16 +884,12 @@ static int alsa_ctl_out (HWVoiceOut *hw, int cmd, ...)
                 poll_mode = 0;
             }
             hw->poll_mode = poll_mode;
-            return alsa_voice_ctl (alsa->handle, "playback", VOICE_CTL_PREPARE);
+            return alsa_voice_ctl (alsa->handle, "playback", 0);
         }
 
     case VOICE_DISABLE:
         ldebug ("disabling voice\n");
-        if (hw->poll_mode) {
-            hw->poll_mode = 0;
-            alsa_fini_poll (&alsa->pollhlp);
-        }
-        return alsa_voice_ctl (alsa->handle, "playback", VOICE_CTL_PAUSE);
+        return alsa_voice_ctl (alsa->handle, "playback", 1);
     }
 
     return -1;
@@ -938,7 +903,7 @@ static int alsa_init_in (HWVoiceIn *hw, struct audsettings *as)
     snd_pcm_t *handle;
     struct audsettings obt_as;
 
-    req.fmt = aud_to_alsafmt (as->fmt, as->endianness);
+    req.fmt = aud_to_alsafmt (as->fmt);
     req.freq = as->freq;
     req.nchannels = as->nchannels;
     req.period_size = conf.period_size_in;
@@ -979,7 +944,7 @@ 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;
     }
 }
@@ -1097,7 +1062,7 @@ static int alsa_run_in (HWVoiceIn *hw)
                 }
             }
 
-            hw->conv (dst, src, nread);
+            hw->conv (dst, src, nread, &nominal_volume);
 
             src = advance (src, nread << hwshift);
             dst += nread;
@@ -1137,7 +1102,7 @@ static int alsa_ctl_in (HWVoiceIn *hw, int cmd, ...)
             }
             hw->poll_mode = poll_mode;
 
-            return alsa_voice_ctl (alsa->handle, "capture", VOICE_CTL_START);
+            return alsa_voice_ctl (alsa->handle, "capture", 0);
         }
 
     case VOICE_DISABLE:
@@ -1146,7 +1111,7 @@ static int alsa_ctl_in (HWVoiceIn *hw, int cmd, ...)
             hw->poll_mode = 0;
             alsa_fini_poll (&alsa->pollhlp);
         }
-        return alsa_voice_ctl (alsa->handle, "capture", VOICE_CTL_PAUSE);
+        return alsa_voice_ctl (alsa->handle, "capture", 1);
     }
 
     return -1;

audio/audio.c

@@ -44,9 +44,6 @@
     that we generate the list.
 */
 static struct audio_driver *drvtab[] = {
-#ifdef CONFIG_SPICE
-    &spice_audio_driver,
-#endif
     CONFIG_AUDIO_DRIVERS
     &no_audio_driver,
     &wav_audio_driver
@@ -104,7 +101,7 @@ static struct {
 
 static AudioState glob_audio_state;
 
-const struct mixeng_volume nominal_volume = {
+struct mixeng_volume nominal_volume = {
     .mute = 0,
 #ifdef FLOAT_MIXENG
     .r = 1.0,
@@ -196,7 +193,7 @@ 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 +207,7 @@ 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 +422,7 @@ 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 +459,7 @@ 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 +504,7 @@ static void audio_process_options (const char *prefix,
             opt->overriddenp = &opt->overridden;
         }
         *opt->overriddenp = !def;
-        g_free (optname);
+        qemu_free (optname);
     }
 }
 
@@ -702,11 +699,13 @@ void audio_pcm_info_clear_buf (struct audio_pcm_info *info, void *buf, int len)
 /*
  * Capture
  */
-static void noop_conv (struct st_sample *dst, const void *src, int samples)
+static void noop_conv (struct st_sample *dst, const void *src,
+                       int samples, struct mixeng_volume *vol)
 {
     (void) src;
     (void) dst;
     (void) samples;
+    (void) vol;
 }
 
 static CaptureVoiceOut *audio_pcm_capture_find_specific (
@@ -778,7 +777,7 @@ 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
@@ -818,7 +817,7 @@ static int audio_attach_capture (HWVoiceOut *hw)
         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);
@@ -954,8 +953,6 @@ int audio_pcm_sw_read (SWVoiceIn *sw, void *buf, int size)
         total += isamp;
     }
 
-    mixeng_volume (sw->buf, ret, &sw->vol);
-
     sw->clip (buf, sw->buf, ret);
     sw->total_hw_samples_acquired += total;
     return ret << sw->info.shift;
@@ -1037,8 +1034,7 @@ int audio_pcm_sw_write (SWVoiceOut *sw, void *buf, int size)
     swlim = ((int64_t) dead << 32) / sw->ratio;
     swlim = audio_MIN (swlim, samples);
     if (swlim) {
-        sw->conv (sw->buf, buf, swlim);
-        mixeng_volume (sw->buf, swlim, &sw->vol);
+        sw->conv (sw->buf, buf, swlim, &sw->vol);
     }
 
     while (swlim) {
@@ -1097,6 +1093,15 @@ static void audio_pcm_print_info (const char *cap, struct audio_pcm_info *info)
 /*
  * Timer
  */
+static void audio_timer (void *opaque)
+{
+    AudioState *s = opaque;
+
+    audio_run ("timer");
+    qemu_mod_timer (s->ts, qemu_get_clock (vm_clock) + conf.period.ticks);
+}
+
+
 static int audio_is_timer_needed (void)
 {
     HWVoiceIn *hwi = NULL;
@@ -1111,22 +1116,18 @@ static int audio_is_timer_needed (void)
     return 0;
 }
 
-static void audio_reset_timer (AudioState *s)
+static void audio_reset_timer (void)
 {
+    AudioState *s = &glob_audio_state;
+
     if (audio_is_timer_needed ()) {
-        qemu_mod_timer (s->ts, qemu_get_clock_ns (vm_clock) + 1);
+        qemu_mod_timer (s->ts, qemu_get_clock (vm_clock) + 1);
     }
     else {
         qemu_del_timer (s->ts);
     }
 }
 
-static void audio_timer (void *opaque)
-{
-    audio_run ("timer");
-    audio_reset_timer (opaque);
-}
-
 /*
  * Public API
  */
@@ -1191,7 +1192,7 @@ void AUD_set_active_out (SWVoiceOut *sw, int on)
                 hw->enabled = 1;
                 if (s->vm_running) {
                     hw->pcm_ops->ctl_out (hw, VOICE_ENABLE, conf.try_poll_out);
-                    audio_reset_timer (s);
+                    audio_reset_timer ();
                 }
             }
         }
@@ -1236,7 +1237,6 @@ void AUD_set_active_in (SWVoiceIn *sw, int on)
                 hw->enabled = 1;
                 if (s->vm_running) {
                     hw->pcm_ops->ctl_in (hw, VOICE_ENABLE, conf.try_poll_in);
-                    audio_reset_timer (s);
                 }
             }
             sw->total_hw_samples_acquired = hw->total_samples_captured;
@@ -1743,7 +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;
@@ -1758,7 +1758,7 @@ static void audio_vm_change_state_handler (void *opaque, int running,
     while ((hwi = audio_pcm_hw_find_any_enabled_in (hwi))) {
         hwi->pcm_ops->ctl_in (hwi, op, conf.try_poll_in);
     }
-    audio_reset_timer (s);
+    audio_reset_timer ();
 }
 
 static void audio_atexit (void)
@@ -1820,7 +1820,7 @@ static void audio_init (void)
     QLIST_INIT (&s->cap_head);
     atexit (audio_atexit);
 
-    s->ts = qemu_new_timer_ns (vm_clock, audio_timer, s);
+    s->ts = qemu_new_timer (vm_clock, audio_timer, s);
     if (!s->ts) {
         hw_error("Could not create audio timer\n");
     }
@@ -1907,7 +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);
 }
@@ -1915,7 +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);
 }
 
 
@@ -2000,11 +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;
     }
@@ -2018,7 +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;
@@ -2036,11 +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;
         }

audio/audio.h

@@ -86,8 +86,12 @@ typedef struct QEMUAudioTimeStamp {
     uint64_t old_ts;
 } QEMUAudioTimeStamp;
 
-void AUD_vlog (const char *cap, const char *fmt, va_list ap) GCC_FMT_ATTR(2, 0);
-void AUD_log (const char *cap, const char *fmt, ...) GCC_FMT_ATTR(2, 3);
+void AUD_vlog (const char *cap, const char *fmt, va_list ap);
+void AUD_log (const char *cap, const char *fmt, ...)
+#ifdef __GNUC__
+    __attribute__ ((__format__ (__printf__, 2, 3)))
+#endif
+    ;
 
 void AUD_help (void);
 void AUD_register_card (const char *name, QEMUSoundCard *card);

audio/audio_int.h

@@ -209,9 +209,8 @@ extern struct audio_driver coreaudio_audio_driver;
 extern struct audio_driver dsound_audio_driver;
 extern struct audio_driver esd_audio_driver;
 extern struct audio_driver pa_audio_driver;
-extern struct audio_driver spice_audio_driver;
 extern struct audio_driver winwave_audio_driver;
-extern const struct mixeng_volume nominal_volume;
+extern struct mixeng_volume nominal_volume;
 
 void audio_pcm_init_info (struct audio_pcm_info *info, struct audsettings *as);
 void audio_pcm_info_clear_buf (struct audio_pcm_info *info, void *buf, int len);
@@ -237,6 +236,14 @@ static inline int audio_ring_dist (int dst, int src, int len)
     return (dst >= src) ? (dst - src) : (len - src + dst);
 }
 
+#if defined __GNUC__
+#define GCC_ATTR __attribute__ ((__unused__, __format__ (__printf__, 1, 2)))
+#define GCC_FMT_ATTR(n, m) __attribute__ ((__format__ (__printf__, n, m)))
+#else
+#define GCC_ATTR /**/
+#define GCC_FMT_ATTR(n, m)
+#endif
+
 static void GCC_ATTR dolog (const char *fmt, ...)
 {
     va_list ap;

audio/audio_pt_int.c

@@ -6,8 +6,7 @@
 #include "audio_int.h"
 #include "audio_pt_int.h"
 
-static void GCC_FMT_ATTR(3, 4) logerr (struct audio_pt *pt, int err,
-                                       const char *fmt, ...)
+static void logerr (struct audio_pt *pt, int err, const char *fmt, ...)
 {
     va_list ap;
 
@@ -24,16 +23,9 @@ int audio_pt_init (struct audio_pt *p, void *(*func) (void *),
 {
     int err, err2;
     const char *efunc;
-    sigset_t set, old_set;
 
     p->drv = drv;
 
-    err = sigfillset (&set);
-    if (err) {
-        logerr (p, errno, "%s(%s): sigfillset failed", cap, AUDIO_FUNC);
-        return -1;
-    }
-
     err = pthread_mutex_init (&p->mutex, NULL);
     if (err) {
         efunc = "pthread_mutex_init";
@@ -46,23 +38,7 @@ int audio_pt_init (struct audio_pt *p, void *(*func) (void *),
         goto err1;
     }
 
-    err = pthread_sigmask (SIG_BLOCK, &set, &old_set);
-    if (err) {
-        efunc = "pthread_sigmask";
-        goto err2;
-    }
-
     err = pthread_create (&p->thread, NULL, func, opaque);
-
-    err2 = pthread_sigmask (SIG_SETMASK, &old_set, NULL);
-    if (err2) {
-        logerr (p, err2, "%s(%s): pthread_sigmask (restore) failed",
-                cap, AUDIO_FUNC);
-        /* We have failed to restore original signal mask, all bets are off,
-           so terminate the process */
-        exit (EXIT_FAILURE);
-    }
-
     if (err) {
         efunc = "pthread_create";
         goto err2;

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) {
@@ -108,7 +108,11 @@ static int glue (audio_pcm_sw_alloc_resources_, TYPE) (SW *sw)
 {
     int samples;
 
+#ifdef DAC
+    samples = sw->hw->samples;
+#else
     samples = ((int64_t) sw->hw->samples << 32) / sw->ratio;
+#endif
 
     sw->buf = audio_calloc (AUDIO_FUNC, samples, sizeof (struct st_sample));
     if (!sw->buf) {
@@ -123,7 +127,7 @@ 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 +164,10 @@ 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 +177,7 @@ 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 +205,7 @@ 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;
     }
 }
@@ -300,7 +304,7 @@ 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;
 }
 
@@ -368,7 +372,7 @@ 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;
 }
@@ -378,7 +382,7 @@ 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)

audio/coreaudio.c

@@ -56,7 +56,7 @@ typedef struct coreaudioVoiceOut {
 
 static void coreaudio_logstatus (OSStatus status)
 {
-    const char *str = "BUG";
+    char *str = "BUG";
 
     switch(status) {
     case kAudioHardwareNoError:
@@ -104,7 +104,7 @@ static void coreaudio_logstatus (OSStatus status)
         break;
 
     default:
-        AUD_log (AUDIO_CAP, "Reason: status code %" PRId32 "\n", (int32_t)status);
+        AUD_log (AUDIO_CAP, "Reason: status code %ld\n", status);
         return;
     }
 
@@ -360,8 +360,8 @@ static int coreaudio_init_out (HWVoiceOut *hw, struct audsettings *as)
         &core->audioDevicePropertyBufferFrameSize);
     if (status != kAudioHardwareNoError) {
         coreaudio_logerr2 (status, typ,
-                           "Could not set device buffer frame size %" PRIu32 "\n",
-                           (uint32_t)core->audioDevicePropertyBufferFrameSize);
+                           "Could not set device buffer frame size %ld\n",
+                           core->audioDevicePropertyBufferFrameSize);
         return -1;
     }
 

audio/dsoundaudio.c

@@ -831,11 +831,11 @@ static int dsound_run_in (HWVoiceIn *hw)
     decr = len1 + len2;
 
     if (p1 && len1) {
-        hw->conv (hw->conv_buf + hw->wpos, p1, len1);
+        hw->conv (hw->conv_buf + hw->wpos, p1, len1, &nominal_volume);
     }
 
     if (p2 && len2) {
-        hw->conv (hw->conv_buf, p2, len2);
+        hw->conv (hw->conv_buf, p2, len2, &nominal_volume);
     }
 
     dsound_unlock_in (dscb, p1, p2, blen1, blen2);

audio/esdaudio.c

@@ -24,6 +24,7 @@
 #include <esd.h>
 #include "qemu-common.h"
 #include "audio.h"
+#include <signal.h>
 
 #define AUDIO_CAP "esd"
 #include "audio_int.h"
@@ -189,6 +190,10 @@ static int qesd_init_out (HWVoiceOut *hw, struct audsettings *as)
     ESDVoiceOut *esd = (ESDVoiceOut *) hw;
     struct audsettings obt_as = *as;
     int esdfmt = ESD_STREAM | ESD_PLAY;
+    int err;
+    sigset_t set, old_set;
+
+    sigfillset (&set);
 
     esdfmt |= (as->nchannels == 2) ? ESD_STEREO : ESD_MONO;
     switch (as->fmt) {
@@ -226,27 +231,45 @@ static int qesd_init_out (HWVoiceOut *hw, struct audsettings *as)
         return -1;
     }
 
-    esd->fd = esd_play_stream (esdfmt, as->freq, conf.dac_host, NULL);
-    if (esd->fd < 0) {
-        qesd_logerr (errno, "esd_play_stream failed\n");
+    esd->fd = -1;
+    err = pthread_sigmask (SIG_BLOCK, &set, &old_set);
+    if (err) {
+        qesd_logerr (err, "pthread_sigmask failed\n");
         goto fail1;
     }
 
-    if (audio_pt_init (&esd->pt, qesd_thread_out, esd, AUDIO_CAP, AUDIO_FUNC)) {
+    esd->fd = esd_play_stream (esdfmt, as->freq, conf.dac_host, NULL);
+    if (esd->fd < 0) {
+        qesd_logerr (errno, "esd_play_stream failed\n");
         goto fail2;
     }
 
+    if (audio_pt_init (&esd->pt, qesd_thread_out, esd, AUDIO_CAP, AUDIO_FUNC)) {
+        goto fail3;
+    }
+
+    err = pthread_sigmask (SIG_SETMASK, &old_set, NULL);
+    if (err) {
+        qesd_logerr (err, "pthread_sigmask(restore) failed\n");
+    }
+
     return 0;
 
- fail2:
+ fail3:
     if (close (esd->fd)) {
         qesd_logerr (errno, "%s: close on esd socket(%d) failed\n",
                      AUDIO_FUNC, esd->fd);
     }
     esd->fd = -1;
 
+ fail2:
+    err = pthread_sigmask (SIG_SETMASK, &old_set, NULL);
+    if (err) {
+        qesd_logerr (err, "pthread_sigmask(restore) failed\n");
+    }
+
  fail1:
-    g_free (esd->pcm_buf);
+    qemu_free (esd->pcm_buf);
     esd->pcm_buf = NULL;
     return -1;
 }
@@ -270,7 +293,7 @@ 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;
 }
 
@@ -346,7 +369,8 @@ static void *qesd_thread_in (void *arg)
                 break;
             }
 
-            hw->conv (hw->conv_buf + wpos, buf, nread >> hw->info.shift);
+            hw->conv (hw->conv_buf + wpos, buf, nread >> hw->info.shift,
+                      &nominal_volume);
             wpos = (wpos + chunk) % hw->samples;
             to_grab -= chunk;
         }
@@ -399,6 +423,10 @@ static int qesd_init_in (HWVoiceIn *hw, struct audsettings *as)
     ESDVoiceIn *esd = (ESDVoiceIn *) hw;
     struct audsettings obt_as = *as;
     int esdfmt = ESD_STREAM | ESD_RECORD;
+    int err;
+    sigset_t set, old_set;
+
+    sigfillset (&set);
 
     esdfmt |= (as->nchannels == 2) ? ESD_STEREO : ESD_MONO;
     switch (as->fmt) {
@@ -433,27 +461,46 @@ static int qesd_init_in (HWVoiceIn *hw, struct audsettings *as)
         return -1;
     }
 
-    esd->fd = esd_record_stream (esdfmt, as->freq, conf.adc_host, NULL);
-    if (esd->fd < 0) {
-        qesd_logerr (errno, "esd_record_stream failed\n");
+    esd->fd = -1;
+
+    err = pthread_sigmask (SIG_BLOCK, &set, &old_set);
+    if (err) {
+        qesd_logerr (err, "pthread_sigmask failed\n");
         goto fail1;
     }
 
-    if (audio_pt_init (&esd->pt, qesd_thread_in, esd, AUDIO_CAP, AUDIO_FUNC)) {
+    esd->fd = esd_record_stream (esdfmt, as->freq, conf.adc_host, NULL);
+    if (esd->fd < 0) {
+        qesd_logerr (errno, "esd_record_stream failed\n");
         goto fail2;
     }
 
+    if (audio_pt_init (&esd->pt, qesd_thread_in, esd, AUDIO_CAP, AUDIO_FUNC)) {
+        goto fail3;
+    }
+
+    err = pthread_sigmask (SIG_SETMASK, &old_set, NULL);
+    if (err) {
+        qesd_logerr (err, "pthread_sigmask(restore) failed\n");
+    }
+
     return 0;
 
- fail2:
+ fail3:
     if (close (esd->fd)) {
         qesd_logerr (errno, "%s: close on esd socket(%d) failed\n",
                      AUDIO_FUNC, esd->fd);
     }
     esd->fd = -1;
 
+ fail2:
+    err = pthread_sigmask (SIG_SETMASK, &old_set, NULL);
+    if (err) {
+        qesd_logerr (err, "pthread_sigmask(restore) failed\n");
+    }
+
  fail1:
-    g_free (esd->pcm_buf);
+    qemu_free (esd->pcm_buf);
     esd->pcm_buf = NULL;
     return -1;
 }
@@ -477,7 +524,7 @@ 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;
 }
@@ -486,10 +488,10 @@ static int fmod_run_in (HWVoiceIn *hw)
     decr = len1 + len2;
 
     if (p1 && blen1) {
-        hw->conv (hw->conv_buf + hw->wpos, p1, len1);
+        hw->conv (hw->conv_buf + hw->wpos, p1, len1, &nominal_volume);
     }
     if (p2 && len2) {
-        hw->conv (hw->conv_buf, p2, len2);
+        hw->conv (hw->conv_buf, p2, len2, &nominal_volume);
     }
 
     fmod_unlock_sample (fmd->fmod_sample, p1, p2, blen1, blen2);

audio/mixeng.c

@@ -326,35 +326,10 @@ 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)
 {
     memset (buf, 0, len * sizeof (struct st_sample));
 }
-
-void mixeng_volume (struct st_sample *buf, int len, struct mixeng_volume *vol)
-{
-#ifdef CONFIG_MIXEMU
-    if (vol->mute) {
-        mixeng_clear (buf, len);
-        return;
-    }
-
-    while (len--) {
-#ifdef FLOAT_MIXENG
-        buf->l = buf->l * vol->l;
-        buf->r = buf->r * vol->r;
-#else
-        buf->l = (buf->l * vol->l) >> 32;
-        buf->r = (buf->r * vol->r) >> 32;
-#endif
-        buf += 1;
-    }
-#else
-    (void) buf;
-    (void) len;
-    (void) vol;
-#endif
-}

audio/mixeng.h

@@ -33,7 +33,8 @@ struct mixeng_volume { int mute; int64_t r; int64_t l; };
 struct st_sample { int64_t l; int64_t r; };
 #endif
 
-typedef void (t_sample) (struct st_sample *dst, const void *src, int samples);
+typedef void (t_sample) (struct st_sample *dst, const void *src,
+                         int samples, struct mixeng_volume *vol);
 typedef void (f_sample) (void *dst, const struct st_sample *src, int samples);
 
 extern t_sample *mixeng_conv[2][2][2][3];
@@ -46,6 +47,5 @@ void st_rate_flow_mix (void *opaque, struct st_sample *ibuf, struct st_sample *o
                        int *isamp, int *osamp);
 void st_rate_stop (void *opaque);
 void mixeng_clear (struct st_sample *buf, int len);
-void mixeng_volume (struct st_sample *buf, int len, struct mixeng_volume *vol);
 
 #endif  /* mixeng.h */

audio/mixeng_template.h

@@ -31,6 +31,16 @@
 #define HALF (IN_MAX >> 1)
 #endif
 
+#ifdef CONFIG_MIXEMU
+#ifdef FLOAT_MIXENG
+#define VOL(a, b) ((a) * (b))
+#else
+#define VOL(a, b) ((a) * (b)) >> 32
+#endif
+#else
+#define VOL(a, b) a
+#endif
+
 #define ET glue (ENDIAN_CONVERSION, glue (_, IN_T))
 
 #ifdef FLOAT_MIXENG
@@ -46,7 +56,7 @@ static mixeng_real inline glue (conv_, ET) (IN_T v)
 #endif
 #else  /* !RECIPROCAL */
 #ifdef SIGNED
-    return nv / (mixeng_real) ((mixeng_real) IN_MAX - IN_MIN);
+    return nv / (mixeng_real) (IN_MAX - IN_MIN);
 #else
     return (nv - HALF) / (mixeng_real) IN_MAX;
 #endif
@@ -63,7 +73,7 @@ static IN_T inline glue (clip_, ET) (mixeng_real v)
     }
 
 #ifdef SIGNED
-    return ENDIAN_CONVERT ((IN_T) (v * ((mixeng_real) IN_MAX - IN_MIN)));
+    return ENDIAN_CONVERT ((IN_T) (v * (IN_MAX - IN_MIN)));
 #else
     return ENDIAN_CONVERT ((IN_T) ((v * IN_MAX) + HALF));
 #endif
@@ -99,26 +109,40 @@ static inline IN_T glue (clip_, ET) (int64_t v)
 #endif
 
 static void glue (glue (conv_, ET), _to_stereo)
-    (struct st_sample *dst, const void *src, int samples)
+    (struct st_sample *dst, const void *src, int samples, struct mixeng_volume *vol)
 {
     struct st_sample *out = dst;
     IN_T *in = (IN_T *) src;
-
+#ifdef CONFIG_MIXEMU
+    if (vol->mute) {
+        mixeng_clear (dst, samples);
+        return;
+    }
+#else
+    (void) vol;
+#endif
     while (samples--) {
-        out->l = glue (conv_, ET) (*in++);
-        out->r = glue (conv_, ET) (*in++);
+        out->l = VOL (glue (conv_, ET) (*in++), vol->l);
+        out->r = VOL (glue (conv_, ET) (*in++), vol->r);
         out += 1;
     }
 }
 
 static void glue (glue (conv_, ET), _to_mono)
-    (struct st_sample *dst, const void *src, int samples)
+    (struct st_sample *dst, const void *src, int samples, struct mixeng_volume *vol)
 {
     struct st_sample *out = dst;
     IN_T *in = (IN_T *) src;
-
+#ifdef CONFIG_MIXEMU
+    if (vol->mute) {
+        mixeng_clear (dst, samples);
+        return;
+    }
+#else
+    (void) vol;
+#endif
     while (samples--) {
-        out->l = glue (conv_, ET) (in[0]);
+        out->l = VOL (glue (conv_, ET) (in[0]), vol->l);
         out->r = out->l;
         out += 1;
         in += 1;
@@ -150,3 +174,4 @@ static void glue (glue (clip_, ET), _from_mono)
 
 #undef ET
 #undef HALF
+#undef VOL

audio/noaudio.c

@@ -46,7 +46,7 @@ static int no_run_out (HWVoiceOut *hw, int live)
     int64_t ticks;
     int64_t bytes;
 
-    now = qemu_get_clock_ns (vm_clock);
+    now = qemu_get_clock (vm_clock);
     ticks = now - no->old_ticks;
     bytes = muldiv64 (ticks, hw->info.bytes_per_second, get_ticks_per_sec ());
     bytes = audio_MIN (bytes, INT_MAX);
@@ -102,7 +102,7 @@ static int no_run_in (HWVoiceIn *hw)
     int samples = 0;
 
     if (dead) {
-        int64_t now = qemu_get_clock_ns (vm_clock);
+        int64_t now = qemu_get_clock (vm_clock);
         int64_t ticks = now - no->old_ticks;
         int64_t bytes =
             muldiv64 (ticks, hw->info.bytes_per_second, get_ticks_per_sec ());
@@ -117,14 +117,11 @@ static int no_run_in (HWVoiceIn *hw)
 
 static int no_read (SWVoiceIn *sw, void *buf, int size)
 {
-    /* use custom code here instead of audio_pcm_sw_read() to avoid
-     * useless resampling/mixing */
     int samples = size >> sw->info.shift;
     int total = sw->hw->total_samples_captured - sw->total_hw_samples_acquired;
     int to_clear = audio_MIN (samples, total);
-    sw->total_hw_samples_acquired += total;
     audio_pcm_info_clear_buf (&sw->info, buf, to_clear);
-    return to_clear << sw->info.shift;
+    return to_clear;
 }
 
 static int no_ctl_in (HWVoiceIn *hw, int cmd, ...)

audio/ossaudio.c

@@ -161,7 +161,7 @@ static int oss_write (SWVoiceOut *sw, void *buf, int len)
     return audio_pcm_sw_write (sw, buf, len);
 }
 
-static int aud_to_ossfmt (audfmt_e fmt, int endianness)
+static int aud_to_ossfmt (audfmt_e fmt)
 {
     switch (fmt) {
     case AUD_FMT_S8:
@@ -171,20 +171,10 @@ static int aud_to_ossfmt (audfmt_e fmt, int endianness)
         return AFMT_U8;
 
     case AUD_FMT_S16:
-        if (endianness) {
-            return AFMT_S16_BE;
-        }
-        else {
-            return AFMT_S16_LE;
-        }
+        return AFMT_S16_LE;
 
     case AUD_FMT_U16:
-        if (endianness) {
-            return AFMT_U16_BE;
-        }
-        else {
-            return AFMT_U16_LE;
-        }
+        return AFMT_U16_LE;
 
     default:
         dolog ("Internal logic error: Bad audio format %d\n", fmt);
@@ -508,7 +498,7 @@ static void oss_fini_out (HWVoiceOut *hw)
             }
         }
         else {
-            g_free (oss->pcm_buf);
+            qemu_free (oss->pcm_buf);
         }
         oss->pcm_buf = NULL;
     }
@@ -526,7 +516,7 @@ static int oss_init_out (HWVoiceOut *hw, struct audsettings *as)
 
     oss->fd = -1;
 
-    req.fmt = aud_to_ossfmt (as->fmt, as->endianness);
+    req.fmt = aud_to_ossfmt (as->fmt);
     req.freq = as->freq;
     req.nchannels = as->nchannels;
     req.fragsize = conf.fragsize;
@@ -692,7 +682,7 @@ static int oss_init_in (HWVoiceIn *hw, struct audsettings *as)
 
     oss->fd = -1;
 
-    req.fmt = aud_to_ossfmt (as->fmt, as->endianness);
+    req.fmt = aud_to_ossfmt (as->fmt);
     req.freq = as->freq;
     req.nchannels = as->nchannels;
     req.fragsize = conf.fragsize;
@@ -741,7 +731,7 @@ 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;
     }
 }
@@ -788,7 +778,8 @@ static int oss_run_in (HWVoiceIn *hw)
                            hw->info.align + 1);
                 }
                 read_samples += nread >> hwshift;
-                hw->conv (hw->conv_buf + bufs[i].add, p, nread >> hwshift);
+                hw->conv (hw->conv_buf + bufs[i].add, p, nread >> hwshift,
+                          &nominal_volume);
             }
 
             if (bufs[i].len - nread) {

audio/paaudio.c

@@ -33,11 +33,13 @@ typedef struct {
 
 static struct {
     int samples;
+    int divisor;
     char *server;
     char *sink;
     char *source;
 } conf = {
-    .samples = 4096,
+    .samples = 1024,
+    .divisor = 2,
 };
 
 static void GCC_FMT_ATTR (2, 3) qpa_logerr (int err, const char *fmt, ...)
@@ -55,6 +57,9 @@ static void *qpa_thread_out (void *arg)
 {
     PAVoiceOut *pa = arg;
     HWVoiceOut *hw = &pa->hw;
+    int threshold;
+
+    threshold = conf.divisor ? hw->samples / conf.divisor : 0;
 
     if (audio_pt_lock (&pa->pt, AUDIO_FUNC)) {
         return NULL;
@@ -68,7 +73,7 @@ static void *qpa_thread_out (void *arg)
                 goto exit;
             }
 
-            if (pa->live > 0) {
+            if (pa->live > threshold) {
                 break;
             }
 
@@ -77,8 +82,8 @@ static void *qpa_thread_out (void *arg)
             }
         }
 
-        decr = to_mix = audio_MIN (pa->live, conf.samples >> 2);
-        rpos = pa->rpos;
+        decr = to_mix = pa->live;
+        rpos = hw->rpos;
 
         if (audio_pt_unlock (&pa->pt, AUDIO_FUNC)) {
             return NULL;
@@ -147,6 +152,9 @@ static void *qpa_thread_in (void *arg)
 {
     PAVoiceIn *pa = arg;
     HWVoiceIn *hw = &pa->hw;
+    int threshold;
+
+    threshold = conf.divisor ? hw->samples / conf.divisor : 0;
 
     if (audio_pt_lock (&pa->pt, AUDIO_FUNC)) {
         return NULL;
@@ -160,7 +168,7 @@ static void *qpa_thread_in (void *arg)
                 goto exit;
             }
 
-            if (pa->dead > 0) {
+            if (pa->dead > threshold) {
                 break;
             }
 
@@ -169,8 +177,8 @@ static void *qpa_thread_in (void *arg)
             }
         }
 
-        incr = to_grab = audio_MIN (pa->dead, conf.samples >> 2);
-        wpos = pa->wpos;
+        incr = to_grab = pa->dead;
+        wpos = hw->wpos;
 
         if (audio_pt_unlock (&pa->pt, AUDIO_FUNC)) {
             return NULL;
@@ -187,7 +195,7 @@ static void *qpa_thread_in (void *arg)
                 return NULL;
             }
 
-            hw->conv (hw->conv_buf + wpos, buf, chunk);
+            hw->conv (hw->conv_buf + wpos, buf, chunk, &nominal_volume);
             wpos = (wpos + chunk) % hw->samples;
             to_grab -= chunk;
         }
@@ -287,7 +295,6 @@ static int qpa_init_out (HWVoiceOut *hw, struct audsettings *as)
 {
     int error;
     static pa_sample_spec ss;
-    static pa_buffer_attr ba;
     struct audsettings obt_as = *as;
     PAVoiceOut *pa = (PAVoiceOut *) hw;
 
@@ -295,15 +302,6 @@ static int qpa_init_out (HWVoiceOut *hw, struct audsettings *as)
     ss.channels = as->nchannels;
     ss.rate = as->freq;
 
-    /*
-     * qemu audio tick runs at 250 Hz (by default), so processing
-     * data chunks worth 4 ms of sound should be a good fit.
-     */
-    ba.tlength = pa_usec_to_bytes (4 * 1000, &ss);
-    ba.minreq = pa_usec_to_bytes (2 * 1000, &ss);
-    ba.maxlength = -1;
-    ba.prebuf = -1;
-
     obt_as.fmt = pa_to_audfmt (ss.format, &obt_as.endianness);
 
     pa->s = pa_simple_new (
@@ -314,7 +312,7 @@ static int qpa_init_out (HWVoiceOut *hw, struct audsettings *as)
         "pcm.playback",
         &ss,
         NULL,                   /* channel map */
-        &ba,                    /* buffering attributes */
+        NULL,                   /* buffering attributes */
         &error
         );
     if (!pa->s) {
@@ -325,7 +323,6 @@ static int qpa_init_out (HWVoiceOut *hw, struct audsettings *as)
     audio_pcm_init_info (&hw->info, &obt_as);
     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) {
         dolog ("Could not allocate buffer (%d bytes)\n",
                hw->samples << hw->info.shift);
@@ -339,7 +336,7 @@ 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:
     pa_simple_free (pa->s);
@@ -380,7 +377,6 @@ static int qpa_init_in (HWVoiceIn *hw, struct audsettings *as)
     audio_pcm_init_info (&hw->info, &obt_as);
     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) {
         dolog ("Could not allocate buffer (%d bytes)\n",
                hw->samples << hw->info.shift);
@@ -394,7 +390,7 @@ 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:
     pa_simple_free (pa->s);
@@ -419,7 +415,7 @@ static void qpa_fini_out (HWVoiceOut *hw)
     }
 
     audio_pt_fini (&pa->pt, AUDIO_FUNC);
-    g_free (pa->pcm_buf);
+    qemu_free (pa->pcm_buf);
     pa->pcm_buf = NULL;
 }
 
@@ -439,7 +435,7 @@ static void qpa_fini_in (HWVoiceIn *hw)
     }
 
     audio_pt_fini (&pa->pt, AUDIO_FUNC);
-    g_free (pa->pcm_buf);
+    qemu_free (pa->pcm_buf);
     pa->pcm_buf = NULL;
 }
 
@@ -475,6 +471,12 @@ struct audio_option qpa_options[] = {
         .valp  = &conf.samples,
         .descr = "buffer size in samples"
     },
+    {
+        .name  = "DIVISOR",
+        .tag   = AUD_OPT_INT,
+        .valp  = &conf.divisor,
+        .descr = "threshold divisor"
+    },
     {
         .name  = "SERVER",
         .tag   = AUD_OPT_STR,

audio/sdlaudio.c

@@ -32,6 +32,7 @@
 #elif defined(__OpenBSD__) || defined(__FreeBSD__) || defined(__DragonFly__)
 #include <pthread.h>
 #endif
+#include <signal.h>
 #endif
 
 #define AUDIO_CAP "sdl"
@@ -138,36 +139,36 @@ static int aud_to_sdlfmt (audfmt_e fmt)
     }
 }
 
-static int sdl_to_audfmt(int sdlfmt, audfmt_e *fmt, int *endianness)
+static int sdl_to_audfmt (int sdlfmt, audfmt_e *fmt, int *endianess)
 {
     switch (sdlfmt) {
     case AUDIO_S8:
-        *endianness = 0;
+        *endianess = 0;
         *fmt = AUD_FMT_S8;
         break;
 
     case AUDIO_U8:
-        *endianness = 0;
+        *endianess = 0;
         *fmt = AUD_FMT_U8;
         break;
 
     case AUDIO_S16LSB:
-        *endianness = 0;
+        *endianess = 0;
         *fmt = AUD_FMT_S16;
         break;
 
     case AUDIO_U16LSB:
-        *endianness = 0;
+        *endianess = 0;
         *fmt = AUD_FMT_U16;
         break;
 
     case AUDIO_S16MSB:
-        *endianness = 1;
+        *endianess = 1;
         *fmt = AUD_FMT_S16;
         break;
 
     case AUDIO_U16MSB:
-        *endianness = 1;
+        *endianess = 1;
         *fmt = AUD_FMT_U16;
         break;
 
@@ -183,20 +184,11 @@ static int sdl_open (SDL_AudioSpec *req, SDL_AudioSpec *obt)
 {
     int status;
 #ifndef _WIN32
-    int err;
     sigset_t new, old;
 
     /* Make sure potential threads created by SDL don't hog signals.  */
-    err = sigfillset (&new);
-    if (err) {
-        dolog ("sdl_open: sigfillset failed: %s\n", strerror (errno));
-        return -1;
-    }
-    err = pthread_sigmask (SIG_BLOCK, &new, &old);
-    if (err) {
-        dolog ("sdl_open: pthread_sigmask failed: %s\n", strerror (err));
-        return -1;
-    }
+    sigfillset (&new);
+    pthread_sigmask (SIG_BLOCK, &new, &old);
 #endif
 
     status = SDL_OpenAudio (req, obt);
@@ -205,14 +197,7 @@ static int sdl_open (SDL_AudioSpec *req, SDL_AudioSpec *obt)
     }
 
 #ifndef _WIN32
-    err = pthread_sigmask (SIG_SETMASK, &old, NULL);
-    if (err) {
-        dolog ("sdl_open: pthread_sigmask (restore) failed: %s\n",
-               strerror (errno));
-        /* We have failed to restore original signal mask, all bets are off,
-           so exit the process */
-        exit (EXIT_FAILURE);
-    }
+    pthread_sigmask (SIG_SETMASK, &old, NULL);
 #endif
     return status;
 }
@@ -337,7 +322,7 @@ static int sdl_init_out (HWVoiceOut *hw, struct audsettings *as)
     SDLVoiceOut *sdl = (SDLVoiceOut *) hw;
     SDLAudioState *s = &glob_sdl;
     SDL_AudioSpec req, obt;
-    int endianness;
+    int endianess;
     int err;
     audfmt_e effective_fmt;
     struct audsettings obt_as;
@@ -353,7 +338,7 @@ static int sdl_init_out (HWVoiceOut *hw, struct audsettings *as)
         return -1;
     }
 
-    err = sdl_to_audfmt(obt.format, &effective_fmt, &endianness);
+    err = sdl_to_audfmt (obt.format, &effective_fmt, &endianess);
     if (err) {
         sdl_close (s);
         return -1;
@@ -362,7 +347,7 @@ static int sdl_init_out (HWVoiceOut *hw, struct audsettings *as)
     obt_as.freq = obt.freq;
     obt_as.nchannels = obt.channels;
     obt_as.fmt = effective_fmt;
-    obt_as.endianness = endianness;
+    obt_as.endianness = endianess;
 
     audio_pcm_init_info (&hw->info, &obt_as);
     hw->samples = obt.samples;

audio/spiceaudio.c

@@ -1,345 +0,0 @@
-/*
- * Copyright (C) 2010 Red Hat, Inc.
- *
- * maintained by Gerd Hoffmann <kraxel@redhat.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 or
- * (at your option) version 3 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "hw/hw.h"
-#include "qemu-timer.h"
-#include "ui/qemu-spice.h"
-
-#define AUDIO_CAP "spice"
-#include "audio.h"
-#include "audio_int.h"
-
-#define LINE_IN_SAMPLES 1024
-#define LINE_OUT_SAMPLES 1024
-
-typedef struct SpiceRateCtl {
-    int64_t               start_ticks;
-    int64_t               bytes_sent;
-} SpiceRateCtl;
-
-typedef struct SpiceVoiceOut {
-    HWVoiceOut            hw;
-    SpicePlaybackInstance sin;
-    SpiceRateCtl          rate;
-    int                   active;
-    uint32_t              *frame;
-    uint32_t              *fpos;
-    uint32_t              fsize;
-} SpiceVoiceOut;
-
-typedef struct SpiceVoiceIn {
-    HWVoiceIn             hw;
-    SpiceRecordInstance   sin;
-    SpiceRateCtl          rate;
-    int                   active;
-    uint32_t              samples[LINE_IN_SAMPLES];
-} SpiceVoiceIn;
-
-static const SpicePlaybackInterface playback_sif = {
-    .base.type          = SPICE_INTERFACE_PLAYBACK,
-    .base.description   = "playback",
-    .base.major_version = SPICE_INTERFACE_PLAYBACK_MAJOR,
-    .base.minor_version = SPICE_INTERFACE_PLAYBACK_MINOR,
-};
-
-static const SpiceRecordInterface record_sif = {
-    .base.type          = SPICE_INTERFACE_RECORD,
-    .base.description   = "record",
-    .base.major_version = SPICE_INTERFACE_RECORD_MAJOR,
-    .base.minor_version = SPICE_INTERFACE_RECORD_MINOR,
-};
-
-static void *spice_audio_init (void)
-{
-    if (!using_spice) {
-        return NULL;
-    }
-    return &spice_audio_init;
-}
-
-static void spice_audio_fini (void *opaque)
-{
-    /* nothing */
-}
-
-static void rate_start (SpiceRateCtl *rate)
-{
-    memset (rate, 0, sizeof (*rate));
-    rate->start_ticks = qemu_get_clock_ns (vm_clock);
-}
-
-static int rate_get_samples (struct audio_pcm_info *info, SpiceRateCtl *rate)
-{
-    int64_t now;
-    int64_t ticks;
-    int64_t bytes;
-    int64_t samples;
-
-    now = qemu_get_clock_ns (vm_clock);
-    ticks = now - rate->start_ticks;
-    bytes = muldiv64 (ticks, info->bytes_per_second, get_ticks_per_sec ());
-    samples = (bytes - rate->bytes_sent) >> info->shift;
-    if (samples < 0 || samples > 65536) {
-        fprintf (stderr, "Resetting rate control (%" PRId64 " samples)\n", samples);
-        rate_start (rate);
-        samples = 0;
-    }
-    rate->bytes_sent += samples << info->shift;
-    return samples;
-}
-
-/* playback */
-
-static int line_out_init (HWVoiceOut *hw, struct audsettings *as)
-{
-    SpiceVoiceOut *out = container_of (hw, SpiceVoiceOut, hw);
-    struct audsettings settings;
-
-    settings.freq       = SPICE_INTERFACE_PLAYBACK_FREQ;
-    settings.nchannels  = SPICE_INTERFACE_PLAYBACK_CHAN;
-    settings.fmt        = AUD_FMT_S16;
-    settings.endianness = AUDIO_HOST_ENDIANNESS;
-
-    audio_pcm_init_info (&hw->info, &settings);
-    hw->samples = LINE_OUT_SAMPLES;
-    out->active = 0;
-
-    out->sin.base.sif = &playback_sif.base;
-    qemu_spice_add_interface (&out->sin.base);
-    return 0;
-}
-
-static void line_out_fini (HWVoiceOut *hw)
-{
-    SpiceVoiceOut *out = container_of (hw, SpiceVoiceOut, hw);
-
-    spice_server_remove_interface (&out->sin.base);
-}
-
-static int line_out_run (HWVoiceOut *hw, int live)
-{
-    SpiceVoiceOut *out = container_of (hw, SpiceVoiceOut, hw);
-    int rpos, decr;
-    int samples;
-
-    if (!live) {
-        return 0;
-    }
-
-    decr = rate_get_samples (&hw->info, &out->rate);
-    decr = audio_MIN (live, decr);
-
-    samples = decr;
-    rpos = hw->rpos;
-    while (samples) {
-        int left_till_end_samples = hw->samples - rpos;
-        int len = audio_MIN (samples, left_till_end_samples);
-
-        if (!out->frame) {
-            spice_server_playback_get_buffer (&out->sin, &out->frame, &out->fsize);
-            out->fpos = out->frame;
-        }
-        if (out->frame) {
-            len = audio_MIN (len, out->fsize);
-            hw->clip (out->fpos, hw->mix_buf + rpos, len);
-            out->fsize -= len;
-            out->fpos  += len;
-            if (out->fsize == 0) {
-                spice_server_playback_put_samples (&out->sin, out->frame);
-                out->frame = out->fpos = NULL;
-            }
-        }
-        rpos = (rpos + len) % hw->samples;
-        samples -= len;
-    }
-    hw->rpos = rpos;
-    return decr;
-}
-
-static int line_out_write (SWVoiceOut *sw, void *buf, int len)
-{
-    return audio_pcm_sw_write (sw, buf, len);
-}
-
-static int line_out_ctl (HWVoiceOut *hw, int cmd, ...)
-{
-    SpiceVoiceOut *out = container_of (hw, SpiceVoiceOut, hw);
-
-    switch (cmd) {
-    case VOICE_ENABLE:
-        if (out->active) {
-            break;
-        }
-        out->active = 1;
-        rate_start (&out->rate);
-        spice_server_playback_start (&out->sin);
-        break;
-    case VOICE_DISABLE:
-        if (!out->active) {
-            break;
-        }
-        out->active = 0;
-        if (out->frame) {
-            memset (out->fpos, 0, out->fsize << 2);
-            spice_server_playback_put_samples (&out->sin, out->frame);
-            out->frame = out->fpos = NULL;
-        }
-        spice_server_playback_stop (&out->sin);
-        break;
-    }
-    return 0;
-}
-
-/* record */
-
-static int line_in_init (HWVoiceIn *hw, struct audsettings *as)
-{
-    SpiceVoiceIn *in = container_of (hw, SpiceVoiceIn, hw);
-    struct audsettings settings;
-
-    settings.freq       = SPICE_INTERFACE_RECORD_FREQ;
-    settings.nchannels  = SPICE_INTERFACE_RECORD_CHAN;
-    settings.fmt        = AUD_FMT_S16;
-    settings.endianness = AUDIO_HOST_ENDIANNESS;
-
-    audio_pcm_init_info (&hw->info, &settings);
-    hw->samples = LINE_IN_SAMPLES;
-    in->active = 0;
-
-    in->sin.base.sif = &record_sif.base;
-    qemu_spice_add_interface (&in->sin.base);
-    return 0;
-}
-
-static void line_in_fini (HWVoiceIn *hw)
-{
-    SpiceVoiceIn *in = container_of (hw, SpiceVoiceIn, hw);
-
-    spice_server_remove_interface (&in->sin.base);
-}
-
-static int line_in_run (HWVoiceIn *hw)
-{
-    SpiceVoiceIn *in = container_of (hw, SpiceVoiceIn, hw);
-    int num_samples;
-    int ready;
-    int len[2];
-    uint64_t delta_samp;
-    const uint32_t *samples;
-
-    if (!(num_samples = hw->samples - audio_pcm_hw_get_live_in (hw))) {
-        return 0;
-    }
-
-    delta_samp = rate_get_samples (&hw->info, &in->rate);
-    num_samples = audio_MIN (num_samples, delta_samp);
-
-    ready = spice_server_record_get_samples (&in->sin, in->samples, num_samples);
-    samples = in->samples;
-    if (ready == 0) {
-        static const uint32_t silence[LINE_IN_SAMPLES];
-        samples = silence;
-        ready = LINE_IN_SAMPLES;
-    }
-
-    num_samples = audio_MIN (ready, num_samples);
-
-    if (hw->wpos + num_samples > hw->samples) {
-        len[0] = hw->samples - hw->wpos;
-        len[1] = num_samples - len[0];
-    } else {
-        len[0] = num_samples;
-        len[1] = 0;
-    }
-
-    hw->conv (hw->conv_buf + hw->wpos, samples, len[0]);
-
-    if (len[1]) {
-        hw->conv (hw->conv_buf, samples + len[0], len[1]);
-    }
-
-    hw->wpos = (hw->wpos + num_samples) % hw->samples;
-
-    return num_samples;
-}
-
-static int line_in_read (SWVoiceIn *sw, void *buf, int size)
-{
-    return audio_pcm_sw_read (sw, buf, size);
-}
-
-static int line_in_ctl (HWVoiceIn *hw, int cmd, ...)
-{
-    SpiceVoiceIn *in = container_of (hw, SpiceVoiceIn, hw);
-
-    switch (cmd) {
-    case VOICE_ENABLE:
-        if (in->active) {
-            break;
-        }
-        in->active = 1;
-        rate_start (&in->rate);
-        spice_server_record_start (&in->sin);
-        break;
-    case VOICE_DISABLE:
-        if (!in->active) {
-            break;
-        }
-        in->active = 0;
-        spice_server_record_stop (&in->sin);
-        break;
-    }
-    return 0;
-}
-
-static struct audio_option audio_options[] = {
-    { /* end of list */ },
-};
-
-static struct audio_pcm_ops audio_callbacks = {
-    .init_out = line_out_init,
-    .fini_out = line_out_fini,
-    .run_out  = line_out_run,
-    .write    = line_out_write,
-    .ctl_out  = line_out_ctl,
-
-    .init_in  = line_in_init,
-    .fini_in  = line_in_fini,
-    .run_in   = line_in_run,
-    .read     = line_in_read,
-    .ctl_in   = line_in_ctl,
-};
-
-struct audio_driver spice_audio_driver = {
-    .name           = "spice",
-    .descr          = "spice audio driver",
-    .options        = audio_options,
-    .init           = spice_audio_init,
-    .fini           = spice_audio_fini,
-    .pcm_ops        = &audio_callbacks,
-    .max_voices_out = 1,
-    .max_voices_in  = 1,
-    .voice_size_out = sizeof (SpiceVoiceOut),
-    .voice_size_in  = sizeof (SpiceVoiceIn),
-};
-
-void qemu_spice_audio_init (void)
-{
-    spice_audio_driver.can_be_default = 1;
-}

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

@@ -3,7 +3,7 @@
 #include "audio.h"
 
 typedef struct {
-    FILE *f;
+    QEMUFile *f;
     int bytes;
     char *path;
     int freq;
@@ -35,50 +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;
 }
 
@@ -94,9 +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 = {
@@ -121,13 +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;
     }
 
@@ -143,7 +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;
@@ -153,42 +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

@@ -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;
 }
 
@@ -511,9 +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:
@@ -550,10 +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;
 }
 
@@ -581,7 +581,8 @@ static int winwave_run_in (HWVoiceIn *hw)
         int conv = audio_MIN (left, decr);
         hw->conv (hw->conv_buf + hw->wpos,
                   advance (wave->pcm_buf, wave->rpos << hw->info.shift),
-                  conv);
+                  conv,
+                  &nominal_volume);
 
         wave->rpos = (wave->rpos + conv) % hw->samples;
         hw->wpos = (hw->wpos + conv) % hw->samples;

balloon.c

@@ -1,9 +1,7 @@
 /*
- * Generic Balloon handlers and management
+ * QEMU System Emulator
  *
  * Copyright (c) 2003-2008 Fabrice Bellard
- * Copyright (C) 2011 Red Hat, Inc.
- * Copyright (C) 2011 Amit Shah <amit.shah@redhat.com>
  *
  * Permission is hereby granted, free of charge, to any person obtaining a copy
  * of this software and associated documentation files (the "Software"), to deal
@@ -24,80 +22,104 @@
  * THE SOFTWARE.
  */
 
+#include "sysemu.h"
 #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"
 
-static QEMUBalloonEvent *balloon_event_fn;
-static QEMUBalloonStatus *balloon_stat_fn;
-static void *balloon_opaque;
 
-int qemu_add_balloon_handler(QEMUBalloonEvent *event_func,
-                             QEMUBalloonStatus *stat_func, void *opaque)
+static QEMUBalloonEvent *qemu_balloon_event;
+void *qemu_balloon_event_opaque;
+
+void qemu_add_balloon_handler(QEMUBalloonEvent *func, void *opaque)
 {
-    if (balloon_event_fn || balloon_stat_fn || balloon_opaque) {
-        /* We're already registered one balloon handler.  How many can
-         * a guest really have?
-         */
-        error_report("Another balloon device already registered");
-        return -1;
-    }
-    balloon_event_fn = event_func;
-    balloon_stat_fn = stat_func;
-    balloon_opaque = opaque;
-    return 0;
+    qemu_balloon_event = func;
+    qemu_balloon_event_opaque = opaque;
 }
 
-void qemu_remove_balloon_handler(void *opaque)
+int qemu_balloon(ram_addr_t target, MonitorCompletion cb, void *opaque)
 {
-    if (balloon_opaque != opaque) {
+    if (qemu_balloon_event) {
+        qemu_balloon_event(qemu_balloon_event_opaque, target, cb, opaque);
+        return 1;
+    } else {
+        return 0;
+    }
+}
+
+int qemu_balloon_status(MonitorCompletion cb, void *opaque)
+{
+    if (qemu_balloon_event) {
+        qemu_balloon_event(qemu_balloon_event_opaque, 0, cb, opaque);
+        return 1;
+    } else {
+        return 0;
+    }
+}
+
+static void print_balloon_stat(const char *key, QObject *obj, void *opaque)
+{
+    Monitor *mon = opaque;
+
+    if (strcmp(key, "actual"))
+        monitor_printf(mon, ",%s=%" PRId64, key,
+                       qint_get_int(qobject_to_qint(obj)));
+}
+
+void monitor_print_balloon(Monitor *mon, const QObject *data)
+{
+    QDict *qdict;
+
+    qdict = qobject_to_qdict(data);
+    if (!qdict_haskey(qdict, "actual"))
         return;
-    }
-    balloon_event_fn = NULL;
-    balloon_stat_fn = NULL;
-    balloon_opaque = NULL;
+
+    monitor_printf(mon, "balloon: actual=%" PRId64,
+                   qdict_get_int(qdict, "actual") >> 20);
+    qdict_iter(qdict, print_balloon_stat, mon);
+    monitor_printf(mon, "\n");
 }
 
-static int qemu_balloon(ram_addr_t target)
+/**
+ * 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)
 {
-    if (!balloon_event_fn) {
-        return 0;
-    }
-    trace_balloon_event(balloon_opaque, target);
-    balloon_event_fn(balloon_opaque, target);
-    return 1;
-}
-
-static int qemu_balloon_status(BalloonInfo *info)
-{
-    if (!balloon_stat_fn) {
-        return 0;
-    }
-    balloon_stat_fn(balloon_opaque, info);
-    return 1;
-}
-
-BalloonInfo *qmp_query_balloon(Error **errp)
-{
-    BalloonInfo *info;
+    int ret;
 
     if (kvm_enabled() && !kvm_has_sync_mmu()) {
-        error_set(errp, QERR_KVM_MISSING_CAP, "synchronous MMU", "balloon");
-        return NULL;
+        qerror_report(QERR_KVM_MISSING_CAP, "synchronous MMU", "balloon");
+        return -1;
     }
 
-    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;
+    ret = qemu_balloon_status(cb, opaque);
+    if (!ret) {
+        qerror_report(QERR_DEVICE_NOT_ACTIVE, "balloon");
+        return -1;
     }
 
-    return info;
+    return 0;
 }
 
 /**
@@ -106,7 +128,6 @@ BalloonInfo *qmp_query_balloon(Error **errp)
 int do_balloon(Monitor *mon, const QDict *params,
 	       MonitorCompletion cb, void *opaque)
 {
-    int64_t target;
     int ret;
 
     if (kvm_enabled() && !kvm_has_sync_mmu()) {
@@ -114,12 +135,7 @@ int do_balloon(Monitor *mon, const QDict *params,
         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);
+    ret = qemu_balloon(qdict_get_int(params, "value"), cb, opaque);
     if (ret == 0) {
         qerror_report(QERR_DEVICE_NOT_ACTIVE, "balloon");
         return -1;

balloon.h

@@ -15,15 +15,18 @@
 #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 (QEMUBalloonEvent)(void *opaque, ram_addr_t target,
+                                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_add_balloon_handler(QEMUBalloonEvent *func, void *opaque);
 
+int qemu_balloon(ram_addr_t target, MonitorCompletion cb, void *opaque);
+
+int qemu_balloon_status(MonitorCompletion cb, void *opaque);
+
+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);
 

bitmap.c

@@ -1,256 +0,0 @@
-/*
- * Bitmap Module
- *
- * Stolen from linux/src/lib/bitmap.c
- *
- * Copyright (C) 2010 Corentin Chary
- *
- * This source code is licensed under the GNU General Public License,
- * Version 2.
- */
-
-#include "bitops.h"
-#include "bitmap.h"
-
-/*
- * bitmaps provide an array of bits, implemented using an an
- * array of unsigned longs.  The number of valid bits in a
- * given bitmap does _not_ need to be an exact multiple of
- * BITS_PER_LONG.
- *
- * The possible unused bits in the last, partially used word
- * of a bitmap are 'don't care'.  The implementation makes
- * no particular effort to keep them zero.  It ensures that
- * their value will not affect the results of any operation.
- * The bitmap operations that return Boolean (bitmap_empty,
- * for example) or scalar (bitmap_weight, for example) results
- * carefully filter out these unused bits from impacting their
- * results.
- *
- * These operations actually hold to a slightly stronger rule:
- * if you don't input any bitmaps to these ops that have some
- * unused bits set, then they won't output any set unused bits
- * in output bitmaps.
- *
- * The byte ordering of bitmaps is more natural on little
- * endian architectures.
- */
-
-int slow_bitmap_empty(const unsigned long *bitmap, int bits)
-{
-    int k, lim = bits/BITS_PER_LONG;
-
-    for (k = 0; k < lim; ++k) {
-        if (bitmap[k]) {
-            return 0;
-        }
-    }
-    if (bits % BITS_PER_LONG) {
-        if (bitmap[k] & BITMAP_LAST_WORD_MASK(bits)) {
-            return 0;
-        }
-    }
-
-    return 1;
-}
-
-int slow_bitmap_full(const unsigned long *bitmap, int bits)
-{
-    int k, lim = bits/BITS_PER_LONG;
-
-    for (k = 0; k < lim; ++k) {
-        if (~bitmap[k]) {
-            return 0;
-        }
-    }
-
-    if (bits % BITS_PER_LONG) {
-        if (~bitmap[k] & BITMAP_LAST_WORD_MASK(bits)) {
-            return 0;
-        }
-    }
-
-    return 1;
-}
-
-int slow_bitmap_equal(const unsigned long *bitmap1,
-                      const unsigned long *bitmap2, int bits)
-{
-    int k, lim = bits/BITS_PER_LONG;
-
-    for (k = 0; k < lim; ++k) {
-        if (bitmap1[k] != bitmap2[k]) {
-            return 0;
-        }
-    }
-
-    if (bits % BITS_PER_LONG) {
-        if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) {
-            return 0;
-        }
-    }
-
-    return 1;
-}
-
-void slow_bitmap_complement(unsigned long *dst, const unsigned long *src,
-                            int bits)
-{
-    int k, lim = bits/BITS_PER_LONG;
-
-    for (k = 0; k < lim; ++k) {
-        dst[k] = ~src[k];
-    }
-
-    if (bits % BITS_PER_LONG) {
-        dst[k] = ~src[k] & BITMAP_LAST_WORD_MASK(bits);
-    }
-}
-
-int slow_bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
-                    const unsigned long *bitmap2, int bits)
-{
-    int k;
-    int nr = BITS_TO_LONGS(bits);
-    unsigned long result = 0;
-
-    for (k = 0; k < nr; k++) {
-        result |= (dst[k] = bitmap1[k] & bitmap2[k]);
-    }
-    return result != 0;
-}
-
-void slow_bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
-                    const unsigned long *bitmap2, int bits)
-{
-    int k;
-    int nr = BITS_TO_LONGS(bits);
-
-    for (k = 0; k < nr; k++) {
-        dst[k] = bitmap1[k] | bitmap2[k];
-    }
-}
-
-void slow_bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
-                     const unsigned long *bitmap2, int bits)
-{
-    int k;
-    int nr = BITS_TO_LONGS(bits);
-
-    for (k = 0; k < nr; k++) {
-        dst[k] = bitmap1[k] ^ bitmap2[k];
-    }
-}
-
-int slow_bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
-                       const unsigned long *bitmap2, int bits)
-{
-    int k;
-    int nr = BITS_TO_LONGS(bits);
-    unsigned long result = 0;
-
-    for (k = 0; k < nr; k++) {
-        result |= (dst[k] = bitmap1[k] & ~bitmap2[k]);
-    }
-    return result != 0;
-}
-
-#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) % BITS_PER_LONG))
-
-void bitmap_set(unsigned long *map, int start, int nr)
-{
-    unsigned long *p = map + BIT_WORD(start);
-    const int size = start + nr;
-    int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG);
-    unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start);
-
-    while (nr - bits_to_set >= 0) {
-        *p |= mask_to_set;
-        nr -= bits_to_set;
-        bits_to_set = BITS_PER_LONG;
-        mask_to_set = ~0UL;
-        p++;
-    }
-    if (nr) {
-        mask_to_set &= BITMAP_LAST_WORD_MASK(size);
-        *p |= mask_to_set;
-    }
-}
-
-void bitmap_clear(unsigned long *map, int start, int nr)
-{
-    unsigned long *p = map + BIT_WORD(start);
-    const int size = start + nr;
-    int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
-    unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
-
-    while (nr - bits_to_clear >= 0) {
-        *p &= ~mask_to_clear;
-        nr -= bits_to_clear;
-        bits_to_clear = BITS_PER_LONG;
-        mask_to_clear = ~0UL;
-        p++;
-    }
-    if (nr) {
-        mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
-        *p &= ~mask_to_clear;
-    }
-}
-
-#define ALIGN_MASK(x,mask)      (((x)+(mask))&~(mask))
-
-/**
- * bitmap_find_next_zero_area - find a contiguous aligned zero area
- * @map: The address to base the search on
- * @size: The bitmap size in bits
- * @start: The bitnumber to start searching at
- * @nr: The number of zeroed bits we're looking for
- * @align_mask: Alignment mask for zero area
- *
- * The @align_mask should be one less than a power of 2; the effect is that
- * the bit offset of all zero areas this function finds is multiples of that
- * power of 2. A @align_mask of 0 means no alignment is required.
- */
-unsigned long bitmap_find_next_zero_area(unsigned long *map,
-					 unsigned long size,
-					 unsigned long start,
-					 unsigned int nr,
-					 unsigned long align_mask)
-{
-    unsigned long index, end, i;
-again:
-    index = find_next_zero_bit(map, size, start);
-
-    /* Align allocation */
-    index = ALIGN_MASK(index, align_mask);
-
-    end = index + nr;
-    if (end > size) {
-        return end;
-    }
-    i = find_next_bit(map, end, index);
-    if (i < end) {
-        start = i + 1;
-        goto again;
-    }
-    return index;
-}
-
-int slow_bitmap_intersects(const unsigned long *bitmap1,
-                           const unsigned long *bitmap2, int bits)
-{
-    int k, lim = bits/BITS_PER_LONG;
-
-    for (k = 0; k < lim; ++k) {
-        if (bitmap1[k] & bitmap2[k]) {
-            return 1;
-        }
-    }
-
-    if (bits % BITS_PER_LONG) {
-        if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) {
-            return 1;
-        }
-    }
-    return 0;
-}

bitmap.h

@@ -1,222 +0,0 @@
-/*
- * Bitmap Module
- *
- * Copyright (C) 2010 Corentin Chary <corentin.chary@gmail.com>
- *
- * Mostly inspired by (stolen from) linux/bitmap.h and linux/bitops.h
- *
- * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
- * See the COPYING.LIB file in the top-level directory.
- */
-
-#ifndef BITMAP_H
-#define BITMAP_H
-
-#include "qemu-common.h"
-#include "bitops.h"
-
-/*
- * The available bitmap operations and their rough meaning in the
- * case that the bitmap is a single unsigned long are thus:
- *
- * Note that nbits should be always a compile time evaluable constant.
- * Otherwise many inlines will generate horrible code.
- *
- * bitmap_zero(dst, nbits)			*dst = 0UL
- * bitmap_fill(dst, nbits)			*dst = ~0UL
- * bitmap_copy(dst, src, nbits)			*dst = *src
- * bitmap_and(dst, src1, src2, nbits)		*dst = *src1 & *src2
- * bitmap_or(dst, src1, src2, nbits)		*dst = *src1 | *src2
- * bitmap_xor(dst, src1, src2, nbits)		*dst = *src1 ^ *src2
- * bitmap_andnot(dst, src1, src2, nbits)	*dst = *src1 & ~(*src2)
- * bitmap_complement(dst, src, nbits)		*dst = ~(*src)
- * bitmap_equal(src1, src2, nbits)		Are *src1 and *src2 equal?
- * bitmap_intersects(src1, src2, nbits) 	Do *src1 and *src2 overlap?
- * bitmap_empty(src, nbits)			Are all bits zero in *src?
- * bitmap_full(src, nbits)			Are all bits set in *src?
- * bitmap_set(dst, pos, nbits)			Set specified bit area
- * bitmap_clear(dst, pos, nbits)		Clear specified bit area
- * bitmap_find_next_zero_area(buf, len, pos, n, mask)	Find bit free area
- */
-
-/*
- * Also the following operations apply to bitmaps.
- *
- * set_bit(bit, addr)			*addr |= bit
- * clear_bit(bit, addr)			*addr &= ~bit
- * change_bit(bit, addr)		*addr ^= bit
- * test_bit(bit, addr)			Is bit set in *addr?
- * test_and_set_bit(bit, addr)		Set bit and return old value
- * test_and_clear_bit(bit, addr)	Clear bit and return old value
- * test_and_change_bit(bit, addr)	Change bit and return old value
- * find_first_zero_bit(addr, nbits)	Position first zero bit in *addr
- * find_first_bit(addr, nbits)		Position first set bit in *addr
- * find_next_zero_bit(addr, nbits, bit)	Position next zero bit in *addr >= bit
- * find_next_bit(addr, nbits, bit)	Position next set bit in *addr >= bit
- */
-
-#define BITMAP_LAST_WORD_MASK(nbits)                                    \
-    (                                                                   \
-        ((nbits) % BITS_PER_LONG) ?                                     \
-        (1UL<<((nbits) % BITS_PER_LONG))-1 : ~0UL                       \
-        )
-
-#define DECLARE_BITMAP(name,bits)                  \
-	unsigned long name[BITS_TO_LONGS(bits)]
-
-#define small_nbits(nbits)                      \
-	((nbits) <= BITS_PER_LONG)
-
-int slow_bitmap_empty(const unsigned long *bitmap, int bits);
-int slow_bitmap_full(const unsigned long *bitmap, int bits);
-int slow_bitmap_equal(const unsigned long *bitmap1,
-                   const unsigned long *bitmap2, int bits);
-void slow_bitmap_complement(unsigned long *dst, const unsigned long *src,
-                         int bits);
-void slow_bitmap_shift_right(unsigned long *dst,
-                          const unsigned long *src, int shift, int bits);
-void slow_bitmap_shift_left(unsigned long *dst,
-                         const unsigned long *src, int shift, int bits);
-int slow_bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
-                 const unsigned long *bitmap2, int bits);
-void slow_bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
-                 const unsigned long *bitmap2, int bits);
-void slow_bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
-                  const unsigned long *bitmap2, int bits);
-int slow_bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
-                    const unsigned long *bitmap2, int bits);
-int slow_bitmap_intersects(const unsigned long *bitmap1,
-			const unsigned long *bitmap2, int bits);
-
-static inline unsigned long *bitmap_new(int nbits)
-{
-    int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
-    return g_malloc0(len);
-}
-
-static inline void bitmap_zero(unsigned long *dst, int nbits)
-{
-    if (small_nbits(nbits)) {
-        *dst = 0UL;
-    } else {
-        int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
-        memset(dst, 0, len);
-    }
-}
-
-static inline void bitmap_fill(unsigned long *dst, int nbits)
-{
-    size_t nlongs = BITS_TO_LONGS(nbits);
-    if (!small_nbits(nbits)) {
-        int len = (nlongs - 1) * sizeof(unsigned long);
-        memset(dst, 0xff,  len);
-    }
-    dst[nlongs - 1] = BITMAP_LAST_WORD_MASK(nbits);
-}
-
-static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
-                               int nbits)
-{
-    if (small_nbits(nbits)) {
-        *dst = *src;
-    } else {
-        int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
-        memcpy(dst, src, len);
-    }
-}
-
-static inline int bitmap_and(unsigned long *dst, const unsigned long *src1,
-                             const unsigned long *src2, int nbits)
-{
-    if (small_nbits(nbits)) {
-        return (*dst = *src1 & *src2) != 0;
-    }
-    return slow_bitmap_and(dst, src1, src2, nbits);
-}
-
-static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, int nbits)
-{
-    if (small_nbits(nbits)) {
-        *dst = *src1 | *src2;
-    } else {
-        slow_bitmap_or(dst, src1, src2, nbits);
-    }
-}
-
-static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, int nbits)
-{
-    if (small_nbits(nbits)) {
-        *dst = *src1 ^ *src2;
-    } else {
-        slow_bitmap_xor(dst, src1, src2, nbits);
-    }
-}
-
-static inline int bitmap_andnot(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, int nbits)
-{
-    if (small_nbits(nbits)) {
-        return (*dst = *src1 & ~(*src2)) != 0;
-    }
-    return slow_bitmap_andnot(dst, src1, src2, nbits);
-}
-
-static inline void bitmap_complement(unsigned long *dst, const unsigned long *src,
-			int nbits)
-{
-    if (small_nbits(nbits)) {
-        *dst = ~(*src) & BITMAP_LAST_WORD_MASK(nbits);
-    } else {
-        slow_bitmap_complement(dst, src, nbits);
-    }
-}
-
-static inline int bitmap_equal(const unsigned long *src1,
-			const unsigned long *src2, int nbits)
-{
-    if (small_nbits(nbits)) {
-        return ! ((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
-    } else {
-        return slow_bitmap_equal(src1, src2, nbits);
-    }
-}
-
-static inline int bitmap_empty(const unsigned long *src, int nbits)
-{
-    if (small_nbits(nbits)) {
-        return ! (*src & BITMAP_LAST_WORD_MASK(nbits));
-    } else {
-        return slow_bitmap_empty(src, nbits);
-    }
-}
-
-static inline int bitmap_full(const unsigned long *src, int nbits)
-{
-    if (small_nbits(nbits)) {
-        return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits));
-    } else {
-        return slow_bitmap_full(src, nbits);
-    }
-}
-
-static inline int bitmap_intersects(const unsigned long *src1,
-			const unsigned long *src2, int nbits)
-{
-    if (small_nbits(nbits)) {
-        return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
-    } else {
-        return slow_bitmap_intersects(src1, src2, nbits);
-    }
-}
-
-void bitmap_set(unsigned long *map, int i, int len);
-void bitmap_clear(unsigned long *map, int start, int nr);
-unsigned long bitmap_find_next_zero_area(unsigned long *map,
-					 unsigned long size,
-					 unsigned long start,
-					 unsigned int nr,
-					 unsigned long align_mask);
-
-#endif /* BITMAP_H */

bitops.c

@@ -1,142 +0,0 @@
-/*
- * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- * Copyright (C) 2008 IBM Corporation
- * Written by Rusty Russell <rusty@rustcorp.com.au>
- * (Inspired by David Howell's find_next_bit implementation)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include "bitops.h"
-
-#define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
-
-/*
- * Find the next set bit in a memory region.
- */
-unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
-			    unsigned long offset)
-{
-    const unsigned long *p = addr + BITOP_WORD(offset);
-    unsigned long result = offset & ~(BITS_PER_LONG-1);
-    unsigned long tmp;
-
-    if (offset >= size) {
-        return size;
-    }
-    size -= result;
-    offset %= BITS_PER_LONG;
-    if (offset) {
-        tmp = *(p++);
-        tmp &= (~0UL << offset);
-        if (size < BITS_PER_LONG) {
-            goto found_first;
-        }
-        if (tmp) {
-            goto found_middle;
-        }
-        size -= BITS_PER_LONG;
-        result += BITS_PER_LONG;
-    }
-    while (size & ~(BITS_PER_LONG-1)) {
-        if ((tmp = *(p++))) {
-            goto found_middle;
-        }
-        result += BITS_PER_LONG;
-        size -= BITS_PER_LONG;
-    }
-    if (!size) {
-        return result;
-    }
-    tmp = *p;
-
-found_first:
-    tmp &= (~0UL >> (BITS_PER_LONG - size));
-    if (tmp == 0UL) {		/* Are any bits set? */
-        return result + size;	/* Nope. */
-    }
-found_middle:
-    return result + bitops_ffsl(tmp);
-}
-
-/*
- * This implementation of find_{first,next}_zero_bit was stolen from
- * Linus' asm-alpha/bitops.h.
- */
-unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
-				 unsigned long offset)
-{
-    const unsigned long *p = addr + BITOP_WORD(offset);
-    unsigned long result = offset & ~(BITS_PER_LONG-1);
-    unsigned long tmp;
-
-    if (offset >= size) {
-        return size;
-    }
-    size -= result;
-    offset %= BITS_PER_LONG;
-    if (offset) {
-        tmp = *(p++);
-        tmp |= ~0UL >> (BITS_PER_LONG - offset);
-        if (size < BITS_PER_LONG) {
-            goto found_first;
-        }
-        if (~tmp) {
-            goto found_middle;
-        }
-        size -= BITS_PER_LONG;
-        result += BITS_PER_LONG;
-    }
-    while (size & ~(BITS_PER_LONG-1)) {
-        if (~(tmp = *(p++))) {
-            goto found_middle;
-        }
-        result += BITS_PER_LONG;
-        size -= BITS_PER_LONG;
-    }
-    if (!size) {
-        return result;
-    }
-    tmp = *p;
-
-found_first:
-    tmp |= ~0UL << size;
-    if (tmp == ~0UL) {	/* Are any bits zero? */
-        return result + size;	/* Nope. */
-    }
-found_middle:
-    return result + ffz(tmp);
-}
-
-unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
-{
-    unsigned long words;
-    unsigned long tmp;
-
-    /* Start at final word. */
-    words = size / BITS_PER_LONG;
-
-    /* Partial final word? */
-    if (size & (BITS_PER_LONG-1)) {
-        tmp = (addr[words] & (~0UL >> (BITS_PER_LONG
-                                       - (size & (BITS_PER_LONG-1)))));
-        if (tmp) {
-            goto found;
-        }
-    }
-
-    while (words) {
-        tmp = addr[--words];
-        if (tmp) {
-        found:
-            return words * BITS_PER_LONG + bitops_flsl(tmp);
-        }
-    }
-
-    /* Not found */
-    return size;
-}

bitops.h

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

block-migration.c

@@ -19,7 +19,6 @@
 #include "monitor.h"
 #include "block-migration.h"
 #include "migration.h"
-#include "blockdev.h"
 #include <assert.h>
 
 #define BLOCK_SIZE (BDRV_SECTORS_PER_DIRTY_CHUNK << BDRV_SECTOR_BITS)
@@ -50,18 +49,17 @@ typedef struct BlkMigDevState {
     int64_t total_sectors;
     int64_t dirty;
     QSIMPLEQ_ENTRY(BlkMigDevState) entry;
-    unsigned long *aio_bitmap;
 } BlkMigDevState;
 
 typedef struct BlkMigBlock {
     uint8_t *buf;
     BlkMigDevState *bmds;
     int64_t sector;
-    int nr_sectors;
     struct iovec iov;
     QEMUIOVector qiov;
     BlockDriverAIOCB *aiocb;
     int ret;
+    int64_t time;
     QSIMPLEQ_ENTRY(BlkMigBlock) entry;
 } BlkMigBlock;
 
@@ -77,7 +75,6 @@ typedef struct BlkMigState {
     int prev_progress;
     int bulk_completed;
     long double total_time;
-    long double prev_time_offset;
     int reads;
 } BlkMigState;
 
@@ -131,71 +128,29 @@ uint64_t blk_mig_bytes_total(void)
     return sum << BDRV_SECTOR_BITS;
 }
 
+static inline void add_avg_read_time(int64_t time)
+{
+    block_mig_state.reads++;
+    block_mig_state.total_time += time;
+}
+
 static inline long double compute_read_bwidth(void)
 {
     assert(block_mig_state.total_time != 0);
-    return (block_mig_state.reads / block_mig_state.total_time) * BLOCK_SIZE;
-}
-
-static int bmds_aio_inflight(BlkMigDevState *bmds, int64_t sector)
-{
-    int64_t chunk = sector / (int64_t)BDRV_SECTORS_PER_DIRTY_CHUNK;
-
-    if ((sector << BDRV_SECTOR_BITS) < bdrv_getlength(bmds->bs)) {
-        return !!(bmds->aio_bitmap[chunk / (sizeof(unsigned long) * 8)] &
-            (1UL << (chunk % (sizeof(unsigned long) * 8))));
-    } else {
-        return 0;
-    }
-}
-
-static void bmds_set_aio_inflight(BlkMigDevState *bmds, int64_t sector_num,
-                             int nb_sectors, int set)
-{
-    int64_t start, end;
-    unsigned long val, idx, bit;
-
-    start = sector_num / BDRV_SECTORS_PER_DIRTY_CHUNK;
-    end = (sector_num + nb_sectors - 1) / BDRV_SECTORS_PER_DIRTY_CHUNK;
-
-    for (; start <= end; start++) {
-        idx = start / (sizeof(unsigned long) * 8);
-        bit = start % (sizeof(unsigned long) * 8);
-        val = bmds->aio_bitmap[idx];
-        if (set) {
-            val |= 1UL << bit;
-        } else {
-            val &= ~(1UL << bit);
-        }
-        bmds->aio_bitmap[idx] = val;
-    }
-}
-
-static void alloc_aio_bitmap(BlkMigDevState *bmds)
-{
-    BlockDriverState *bs = bmds->bs;
-    int64_t bitmap_size;
-
-    bitmap_size = (bdrv_getlength(bs) >> BDRV_SECTOR_BITS) +
-            BDRV_SECTORS_PER_DIRTY_CHUNK * 8 - 1;
-    bitmap_size /= BDRV_SECTORS_PER_DIRTY_CHUNK * 8;
-
-    bmds->aio_bitmap = g_malloc0(bitmap_size);
+    return  (block_mig_state.reads * BLOCK_SIZE)/ block_mig_state.total_time;
 }
 
 static void blk_mig_read_cb(void *opaque, int ret)
 {
-    long double curr_time = qemu_get_clock_ns(rt_clock);
     BlkMigBlock *blk = opaque;
 
     blk->ret = ret;
 
-    block_mig_state.reads++;
-    block_mig_state.total_time += (curr_time - block_mig_state.prev_time_offset);
-    block_mig_state.prev_time_offset = curr_time;
+    blk->time = qemu_get_clock_ns(rt_clock) - blk->time;
+
+    add_avg_read_time(blk->time);
 
     QSIMPLEQ_INSERT_TAIL(&block_mig_state.blk_list, blk, entry);
-    bmds_set_aio_inflight(blk->bmds, blk->sector, blk->nr_sectors, 0);
 
     block_mig_state.submitted--;
     block_mig_state.read_done++;
@@ -235,19 +190,16 @@ static int mig_save_device_bulk(Monitor *mon, QEMUFile *f,
         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;
 
     blk->iov.iov_base = blk->buf;
     blk->iov.iov_len = nr_sectors * BDRV_SECTOR_SIZE;
     qemu_iovec_init_external(&blk->qiov, &blk->iov, 1);
 
-    if (block_mig_state.submitted == 0) {
-        block_mig_state.prev_time_offset = qemu_get_clock_ns(rt_clock);
-    }
+    blk->time = qemu_get_clock_ns(rt_clock);
 
     blk->aiocb = bdrv_aio_readv(bs, cur_sector, &blk->qiov,
                                 nr_sectors, blk_mig_read_cb, blk);
@@ -263,9 +215,9 @@ static int mig_save_device_bulk(Monitor *mon, QEMUFile *f,
 
 error:
     monitor_printf(mon, "Error reading sector %" PRId64 "\n", cur_sector);
-    qemu_file_set_error(f, -EIO);
-    g_free(blk->buf);
-    g_free(blk);
+    qemu_file_set_error(f);
+    qemu_free(blk->buf);
+    qemu_free(blk);
     return 0;
 }
 
@@ -290,15 +242,12 @@ 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;
         bmds->completed_sectors = 0;
         bmds->shared_base = block_mig_state.shared_base;
-        alloc_aio_bitmap(bmds);
-        drive_get_ref(drive_get_by_blockdev(bs));
-        bdrv_set_in_use(bs, 1);
 
         block_mig_state.total_sector_sum += sectors;
 
@@ -350,12 +299,7 @@ static int blk_mig_save_bulked_block(Monitor *mon, QEMUFile *f)
         }
     }
 
-    if (block_mig_state.total_sector_sum != 0) {
-        progress = completed_sector_sum * 100 /
-                   block_mig_state.total_sector_sum;
-    } else {
-        progress = 100;
-    }
+    progress = completed_sector_sum * 100 / block_mig_state.total_sector_sum;
     if (progress != block_mig_state.prev_progress) {
         block_mig_state.prev_progress = progress;
         qemu_put_be64(f, (progress << BDRV_SECTOR_BITS)
@@ -383,12 +327,8 @@ static int mig_save_device_dirty(Monitor *mon, QEMUFile *f,
     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)) {
-            qemu_aio_flush();
-        }
         if (bdrv_get_dirty(bmds->bs, sector)) {
 
             if (total_sectors - sector < BDRV_SECTORS_PER_DIRTY_CHUNK) {
@@ -396,20 +336,17 @@ static int mig_save_device_dirty(Monitor *mon, QEMUFile *f,
             } 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;
 
             if (is_async) {
                 blk->iov.iov_base = blk->buf;
                 blk->iov.iov_len = nr_sectors * BDRV_SECTOR_SIZE;
                 qemu_iovec_init_external(&blk->qiov, &blk->iov, 1);
 
-                if (block_mig_state.submitted == 0) {
-                    block_mig_state.prev_time_offset = qemu_get_clock_ns(rt_clock);
-                }
+		blk->time = qemu_get_clock_ns(rt_clock);
 
                 blk->aiocb = bdrv_aio_readv(bmds->bs, sector, &blk->qiov,
                                             nr_sectors, blk_mig_read_cb, blk);
@@ -417,16 +354,15 @@ static int mig_save_device_dirty(Monitor *mon, QEMUFile *f,
                     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);
@@ -440,9 +376,9 @@ static int mig_save_device_dirty(Monitor *mon, QEMUFile *f,
 
 error:
     monitor_printf(mon, "Error reading sector %" PRId64 "\n", sector);
-    qemu_file_set_error(f, ret);
-    g_free(blk->buf);
-    g_free(blk);
+    qemu_file_set_error(f);
+    qemu_free(blk->buf);
+    qemu_free(blk);
     return 0;
 }
 
@@ -474,14 +410,14 @@ static void flush_blks(QEMUFile* f)
             break;
         }
         if (blk->ret < 0) {
-            qemu_file_set_error(f, 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++;
@@ -513,15 +449,15 @@ static int is_stage2_completed(void)
     if (block_mig_state.bulk_completed == 1) {
 
         remaining_dirty = get_remaining_dirty();
-        if (remaining_dirty == 0) {
-            return 1;
-        }
+	if (remaining_dirty == 0) {
+	    return 1;
+	}
 
-        bwidth = compute_read_bwidth();
+	bwidth = compute_read_bwidth();
 
-        if ((remaining_dirty / bwidth) <=
+	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;
@@ -536,29 +472,24 @@ static void blk_mig_cleanup(Monitor *mon)
     BlkMigDevState *bmds;
     BlkMigBlock *blk;
 
-    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);
     }
 
     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);
     }
 
+    set_dirty_tracking(0);
+
     monitor_printf(mon, "\n");
 }
 
 static int block_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
 {
-    int ret;
-
     DPRINTF("Enter save live stage %d submitted %d transferred %d\n",
             stage, block_mig_state.submitted, block_mig_state.transferred);
 
@@ -582,10 +513,9 @@ static int block_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
 
     flush_blks(f);
 
-    ret = qemu_file_get_error(f);
-    if (ret) {
+    if (qemu_file_has_error(f)) {
         blk_mig_cleanup(mon);
-        return ret;
+        return 0;
     }
 
     blk_mig_reset_dirty_cursor();
@@ -611,10 +541,9 @@ static int block_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
 
         flush_blks(f);
 
-        ret = qemu_file_get_error(f);
-        if (ret) {
+        if (qemu_file_has_error(f)) {
             blk_mig_cleanup(mon);
-            return ret;
+            return 0;
         }
     }
 
@@ -629,9 +558,8 @@ static int block_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
         /* report completion */
         qemu_put_be64(f, (100 << BDRV_SECTOR_BITS) | BLK_MIG_FLAG_PROGRESS);
 
-        ret = qemu_file_get_error(f);
-        if (ret) {
-            return ret;
+        if (qemu_file_has_error(f)) {
+            return 0;
         }
 
         monitor_printf(mon, "Block migration completed\n");
@@ -648,11 +576,8 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
     int len, flags;
     char device_name[256];
     int64_t addr;
-    BlockDriverState *bs, *bs_prev = NULL;
+    BlockDriverState *bs;
     uint8_t *buf;
-    int64_t total_sectors = 0;
-    int nr_sectors;
-    int ret;
 
     do {
         addr = qemu_get_be64(f);
@@ -661,6 +586,7 @@ 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);
@@ -673,28 +599,12 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
                 return -EINVAL;
             }
 
-            if (bs != bs_prev) {
-                bs_prev = bs;
-                total_sectors = bdrv_getlength(bs) >> BDRV_SECTOR_BITS;
-                if (total_sectors <= 0) {
-                    error_report("Error getting length of block device %s",
-                                 device_name);
-                    return -EINVAL;
-                }
-            }
-
-            if (total_sectors - addr < BDRV_SECTORS_PER_DIRTY_CHUNK) {
-                nr_sectors = total_sectors - addr;
-            } else {
-                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);
+            ret = bdrv_write(bs, addr, buf, BDRV_SECTORS_PER_DIRTY_CHUNK);
 
-            g_free(buf);
+            qemu_free(buf);
             if (ret < 0) {
                 return ret;
             }
@@ -710,9 +620,8 @@ 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));
 

block.h

@@ -4,7 +4,6 @@
 #include "qemu-aio.h"
 #include "qemu-common.h"
 #include "qemu-option.h"
-#include "qemu-coroutine.h"
 #include "qobject.h"
 
 /* block.c */
@@ -28,41 +27,6 @@ typedef struct QEMUSnapshotInfo {
     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 */
@@ -86,11 +50,6 @@ typedef enum {
     BDRV_ACTION_REPORT, BDRV_ACTION_IGNORE, BDRV_ACTION_STOP
 } BlockMonEventAction;
 
-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);
@@ -107,23 +66,14 @@ int bdrv_create(BlockDriver *drv, const char* filename,
     QEMUOptionParameter *options);
 int bdrv_create_file(const char* filename, QEMUOptionParameter *options);
 BlockDriverState *bdrv_new(const char *device_name);
-void bdrv_make_anon(BlockDriverState *bs);
 void bdrv_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(BlockDriverState *bs, const char *filename, int flags,
               BlockDriver *drv);
 void bdrv_close(BlockDriverState *bs);
-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_write(BlockDriverState *bs, int64_t sector_num,
@@ -134,13 +84,10 @@ 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_writev(BlockDriverState *bs, int64_t sector_num,
-    int nb_sectors, QEMUIOVector *qiov);
+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);
@@ -162,7 +109,7 @@ int bdrv_check(BlockDriverState *bs, BdrvCheckResult *res);
 typedef struct BlockDriverAIOCB BlockDriverAIOCB;
 typedef void BlockDriverCompletionFunc(void *opaque, int ret);
 typedef void BlockDriverDirtyHandler(BlockDriverState *bs, int64_t sector,
-                                     int sector_num);
+				     int sector_num);
 BlockDriverAIOCB *bdrv_aio_readv(BlockDriverState *bs, int64_t sector_num,
                                  QEMUIOVector *iov, int nb_sectors,
                                  BlockDriverCompletionFunc *cb, void *opaque);
@@ -170,10 +117,7 @@ BlockDriverAIOCB *bdrv_aio_writev(BlockDriverState *bs, int64_t sector_num,
                                   QEMUIOVector *iov, int nb_sectors,
                                   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);
+				 BlockDriverCompletionFunc *cb, void *opaque);
 void bdrv_aio_cancel(BlockDriverAIOCB *acb);
 
 typedef struct BlockRequest {
@@ -197,22 +141,18 @@ 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);
-
 /* Ensure contents are flushed to disk.  */
-int bdrv_flush(BlockDriverState *bs);
-int coroutine_fn bdrv_co_flush(BlockDriverState *bs);
+void bdrv_flush(BlockDriverState *bs);
 void bdrv_flush_all(void);
 void bdrv_close_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);
+	int *pnum);
 
+#define BDRV_TYPE_HD     0
+#define BDRV_TYPE_CDROM  1
+#define BDRV_TYPE_FLOPPY 2
 #define BIOS_ATA_TRANSLATION_AUTO   0
 #define BIOS_ATA_TRANSLATION_NONE   1
 #define BIOS_ATA_TRANSLATION_LBA    2
@@ -221,30 +161,27 @@ int bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
 
 void bdrv_set_geometry_hint(BlockDriverState *bs,
                             int cyls, int heads, int secs);
+void bdrv_set_type_hint(BlockDriverState *bs, int type);
 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_type_hint(BlockDriverState *bs);
 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);
 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, int eject_flag);
+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), void *opaque);
 void bdrv_get_format(BlockDriverState *bs, char *buf, int buf_size);
 BlockDriverState *bdrv_find(const char *name);
 BlockDriverState *bdrv_next(BlockDriverState *bs);
@@ -274,8 +211,6 @@ int bdrv_snapshot_goto(BlockDriverState *bs,
 int bdrv_snapshot_delete(BlockDriverState *bs, const char *snapshot_id);
 int bdrv_snapshot_list(BlockDriverState *bs,
                        QEMUSnapshotInfo **psn_info);
-int bdrv_snapshot_load_tmp(BlockDriverState *bs,
-                           const char *snapshot_name);
 char *bdrv_snapshot_dump(char *buf, int buf_size, QEMUSnapshotInfo *sn);
 
 char *get_human_readable_size(char *buf, int buf_size, int64_t size);
@@ -290,13 +225,6 @@ int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
 int bdrv_load_vmstate(BlockDriverState *bs, uint8_t *buf,
                       int64_t pos, int size);
 
-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);
@@ -305,25 +233,6 @@ void bdrv_reset_dirty(BlockDriverState *bs, int64_t cur_sector,
                       int nr_sectors);
 int64_t bdrv_get_dirty_count(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,
@@ -376,43 +285,4 @@ typedef enum {
 #define BLKDBG_EVENT(bs, evt) bdrv_debug_event(bs, evt)
 void bdrv_debug_event(BlockDriverState *bs, BlkDebugEvent event);
 
-
-/* Convenience for block device models */
-
-typedef struct BlockConf {
-    BlockDriverState *bs;
-    uint16_t physical_block_size;
-    uint16_t logical_block_size;
-    uint16_t min_io_size;
-    uint32_t opt_io_size;
-    int32_t bootindex;
-    uint32_t discard_granularity;
-} BlockConf;
-
-static inline unsigned int get_physical_block_exp(BlockConf *conf)
-{
-    unsigned int exp = 0, size;
-
-    for (size = conf->physical_block_size;
-        size > conf->logical_block_size;
-        size >>= 1) {
-        exp++;
-    }
-
-    return exp;
-}
-
-#define DEFINE_BLOCK_PROPERTIES(_state, _conf)                          \
-    DEFINE_PROP_DRIVE("drive", _state, _conf.bs),                       \
-    DEFINE_PROP_UINT16("logical_block_size", _state,                    \
-                       _conf.logical_block_size, 512),                  \
-    DEFINE_PROP_UINT16("physical_block_size", _state,                   \
-                       _conf.physical_block_size, 512),                 \
-    DEFINE_PROP_UINT16("min_io_size", _state, _conf.min_io_size, 0),  \
-    DEFINE_PROP_UINT32("opt_io_size", _state, _conf.opt_io_size, 0),    \
-    DEFINE_PROP_INT32("bootindex", _state, _conf.bootindex, -1),        \
-    DEFINE_PROP_UINT32("discard_granularity", _state, \
-                       _conf.discard_granularity, 0)
-
 #endif
-

block/blkdebug.c

@@ -214,7 +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,
@@ -392,11 +392,16 @@ 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 void blkdebug_flush(BlockDriverState *bs)
+{
+    bdrv_flush(bs->file);
+}
+
 static BlockDriverAIOCB *blkdebug_aio_flush(BlockDriverState *bs,
     BlockDriverCompletionFunc *cb, void *opaque)
 {
@@ -434,7 +439,9 @@ static void blkdebug_debug_event(BlockDriverState *bs, BlkDebugEvent event)
     struct BlkdebugRule *rule;
     BlkdebugVars old_vars = s->vars;
 
-    assert((int)event >= 0 && event < BLKDBG_EVENT_MAX);
+    if (event < 0 || event >= BLKDBG_EVENT_MAX) {
+        return;
+    }
 
     QLIST_FOREACH(rule, &s->rules[event], next) {
         process_rule(bs, rule, &old_vars);
@@ -449,6 +456,7 @@ static BlockDriver bdrv_blkdebug = {
 
     .bdrv_file_open     = blkdebug_open,
     .bdrv_close         = blkdebug_close,
+    .bdrv_flush         = blkdebug_flush,
 
     .bdrv_aio_readv     = blkdebug_aio_readv,
     .bdrv_aio_writev    = blkdebug_aio_writev,

block/blkverify.c

@@ -1,374 +0,0 @@
-/*
- * Block protocol for block driver correctness testing
- *
- * Copyright (C) 2010 IBM, Corp.
- *
- * 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 <stdarg.h>
-#include "qemu_socket.h" /* for EINPROGRESS on Windows */
-#include "block_int.h"
-
-typedef struct {
-    BlockDriverState *test_file;
-} BDRVBlkverifyState;
-
-typedef struct BlkverifyAIOCB BlkverifyAIOCB;
-struct BlkverifyAIOCB {
-    BlockDriverAIOCB common;
-    QEMUBH *bh;
-
-    /* Request metadata */
-    bool is_write;
-    int64_t sector_num;
-    int nb_sectors;
-
-    int ret;                    /* first completed request's result */
-    unsigned int done;          /* completion counter */
-    bool *finished;             /* completion signal for cancel */
-
-    QEMUIOVector *qiov;         /* user I/O vector */
-    QEMUIOVector raw_qiov;      /* cloned I/O vector for raw file */
-    void *buf;                  /* buffer for raw file I/O */
-
-    void (*verify)(BlkverifyAIOCB *acb);
-};
-
-static void blkverify_aio_cancel(BlockDriverAIOCB *blockacb)
-{
-    BlkverifyAIOCB *acb = (BlkverifyAIOCB *)blockacb;
-    bool finished = false;
-
-    /* Wait until request completes, invokes its callback, and frees itself */
-    acb->finished = &finished;
-    while (!finished) {
-        qemu_aio_wait();
-    }
-}
-
-static AIOPool blkverify_aio_pool = {
-    .aiocb_size         = sizeof(BlkverifyAIOCB),
-    .cancel             = blkverify_aio_cancel,
-};
-
-static void GCC_FMT_ATTR(2, 3) blkverify_err(BlkverifyAIOCB *acb,
-                                             const char *fmt, ...)
-{
-    va_list ap;
-
-    va_start(ap, fmt);
-    fprintf(stderr, "blkverify: %s sector_num=%" PRId64 " nb_sectors=%d ",
-            acb->is_write ? "write" : "read", acb->sector_num,
-            acb->nb_sectors);
-    vfprintf(stderr, fmt, ap);
-    fprintf(stderr, "\n");
-    va_end(ap);
-    exit(1);
-}
-
-/* Valid blkverify filenames look like blkverify:path/to/raw_image:path/to/image */
-static int blkverify_open(BlockDriverState *bs, const char *filename, int flags)
-{
-    BDRVBlkverifyState *s = bs->opaque;
-    int ret;
-    char *raw, *c;
-
-    /* Parse the blkverify: prefix */
-    if (strncmp(filename, "blkverify:", strlen("blkverify:"))) {
-        return -EINVAL;
-    }
-    filename += strlen("blkverify:");
-
-    /* Parse the raw image filename */
-    c = strchr(filename, ':');
-    if (c == NULL) {
-        return -EINVAL;
-    }
-
-    raw = strdup(filename);
-    raw[c - filename] = '\0';
-    ret = bdrv_file_open(&bs->file, raw, flags);
-    free(raw);
-    if (ret < 0) {
-        return ret;
-    }
-    filename = c + 1;
-
-    /* Open the test file */
-    s->test_file = bdrv_new("");
-    ret = bdrv_open(s->test_file, filename, flags, NULL);
-    if (ret < 0) {
-        bdrv_delete(s->test_file);
-        s->test_file = NULL;
-        return ret;
-    }
-
-    return 0;
-}
-
-static void blkverify_close(BlockDriverState *bs)
-{
-    BDRVBlkverifyState *s = bs->opaque;
-
-    bdrv_delete(s->test_file);
-    s->test_file = NULL;
-}
-
-static int64_t blkverify_getlength(BlockDriverState *bs)
-{
-    BDRVBlkverifyState *s = bs->opaque;
-
-    return bdrv_getlength(s->test_file);
-}
-
-/**
- * Check that I/O vector contents are identical
- *
- * @a:          I/O vector
- * @b:          I/O vector
- * @ret:        Offset to first mismatching byte or -1 if match
- */
-static ssize_t blkverify_iovec_compare(QEMUIOVector *a, QEMUIOVector *b)
-{
-    int i;
-    ssize_t offset = 0;
-
-    assert(a->niov == b->niov);
-    for (i = 0; i < a->niov; i++) {
-        size_t len = 0;
-        uint8_t *p = (uint8_t *)a->iov[i].iov_base;
-        uint8_t *q = (uint8_t *)b->iov[i].iov_base;
-
-        assert(a->iov[i].iov_len == b->iov[i].iov_len);
-        while (len < a->iov[i].iov_len && *p++ == *q++) {
-            len++;
-        }
-
-        offset += len;
-
-        if (len != a->iov[i].iov_len) {
-            return offset;
-        }
-    }
-    return -1;
-}
-
-typedef struct {
-    int src_index;
-    struct iovec *src_iov;
-    void *dest_base;
-} IOVectorSortElem;
-
-static int sortelem_cmp_src_base(const void *a, const void *b)
-{
-    const IOVectorSortElem *elem_a = a;
-    const IOVectorSortElem *elem_b = b;
-
-    /* Don't overflow */
-    if (elem_a->src_iov->iov_base < elem_b->src_iov->iov_base) {
-        return -1;
-    } else if (elem_a->src_iov->iov_base > elem_b->src_iov->iov_base) {
-        return 1;
-    } else {
-        return 0;
-    }
-}
-
-static int sortelem_cmp_src_index(const void *a, const void *b)
-{
-    const IOVectorSortElem *elem_a = a;
-    const IOVectorSortElem *elem_b = b;
-
-    return elem_a->src_index - elem_b->src_index;
-}
-
-/**
- * Copy contents of I/O vector
- *
- * The relative relationships of overlapping iovecs are preserved.  This is
- * necessary to ensure identical semantics in the cloned I/O vector.
- */
-static void blkverify_iovec_clone(QEMUIOVector *dest, const QEMUIOVector *src,
-                                  void *buf)
-{
-    IOVectorSortElem sortelems[src->niov];
-    void *last_end;
-    int i;
-
-    /* Sort by source iovecs by base address */
-    for (i = 0; i < src->niov; i++) {
-        sortelems[i].src_index = i;
-        sortelems[i].src_iov = &src->iov[i];
-    }
-    qsort(sortelems, src->niov, sizeof(sortelems[0]), sortelem_cmp_src_base);
-
-    /* Allocate buffer space taking into account overlapping iovecs */
-    last_end = NULL;
-    for (i = 0; i < src->niov; i++) {
-        struct iovec *cur = sortelems[i].src_iov;
-        ptrdiff_t rewind = 0;
-
-        /* Detect overlap */
-        if (last_end && last_end > cur->iov_base) {
-            rewind = last_end - cur->iov_base;
-        }
-
-        sortelems[i].dest_base = buf - rewind;
-        buf += cur->iov_len - MIN(rewind, cur->iov_len);
-        last_end = MAX(cur->iov_base + cur->iov_len, last_end);
-    }
-
-    /* Sort by source iovec index and build destination iovec */
-    qsort(sortelems, src->niov, sizeof(sortelems[0]), sortelem_cmp_src_index);
-    for (i = 0; i < src->niov; i++) {
-        qemu_iovec_add(dest, sortelems[i].dest_base, src->iov[i].iov_len);
-    }
-}
-
-static BlkverifyAIOCB *blkverify_aio_get(BlockDriverState *bs, bool is_write,
-                                         int64_t sector_num, QEMUIOVector *qiov,
-                                         int nb_sectors,
-                                         BlockDriverCompletionFunc *cb,
-                                         void *opaque)
-{
-    BlkverifyAIOCB *acb = qemu_aio_get(&blkverify_aio_pool, bs, cb, opaque);
-
-    acb->bh = NULL;
-    acb->is_write = is_write;
-    acb->sector_num = sector_num;
-    acb->nb_sectors = nb_sectors;
-    acb->ret = -EINPROGRESS;
-    acb->done = 0;
-    acb->qiov = qiov;
-    acb->buf = NULL;
-    acb->verify = NULL;
-    acb->finished = NULL;
-    return acb;
-}
-
-static void blkverify_aio_bh(void *opaque)
-{
-    BlkverifyAIOCB *acb = opaque;
-
-    qemu_bh_delete(acb->bh);
-    if (acb->buf) {
-        qemu_iovec_destroy(&acb->raw_qiov);
-        qemu_vfree(acb->buf);
-    }
-    acb->common.cb(acb->common.opaque, acb->ret);
-    if (acb->finished) {
-        *acb->finished = true;
-    }
-    qemu_aio_release(acb);
-}
-
-static void blkverify_aio_cb(void *opaque, int ret)
-{
-    BlkverifyAIOCB *acb = opaque;
-
-    switch (++acb->done) {
-    case 1:
-        acb->ret = ret;
-        break;
-
-    case 2:
-        if (acb->ret != ret) {
-            blkverify_err(acb, "return value mismatch %d != %d", acb->ret, ret);
-        }
-
-        if (acb->verify) {
-            acb->verify(acb);
-        }
-
-        acb->bh = qemu_bh_new(blkverify_aio_bh, acb);
-        qemu_bh_schedule(acb->bh);
-        break;
-    }
-}
-
-static void blkverify_verify_readv(BlkverifyAIOCB *acb)
-{
-    ssize_t offset = blkverify_iovec_compare(acb->qiov, &acb->raw_qiov);
-    if (offset != -1) {
-        blkverify_err(acb, "contents mismatch in sector %" PRId64,
-                      acb->sector_num + (int64_t)(offset / BDRV_SECTOR_SIZE));
-    }
-}
-
-static BlockDriverAIOCB *blkverify_aio_readv(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque)
-{
-    BDRVBlkverifyState *s = bs->opaque;
-    BlkverifyAIOCB *acb = blkverify_aio_get(bs, false, sector_num, qiov,
-                                            nb_sectors, cb, opaque);
-
-    acb->verify = blkverify_verify_readv;
-    acb->buf = qemu_blockalign(bs->file, qiov->size);
-    qemu_iovec_init(&acb->raw_qiov, acb->qiov->niov);
-    blkverify_iovec_clone(&acb->raw_qiov, qiov, acb->buf);
-
-    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;
-}
-
-static BlockDriverAIOCB *blkverify_aio_writev(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque)
-{
-    BDRVBlkverifyState *s = bs->opaque;
-    BlkverifyAIOCB *acb = blkverify_aio_get(bs, true, sector_num, qiov,
-                                            nb_sectors, cb, opaque);
-
-    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;
-}
-
-static BlockDriverAIOCB *blkverify_aio_flush(BlockDriverState *bs,
-                                             BlockDriverCompletionFunc *cb,
-                                             void *opaque)
-{
-    BDRVBlkverifyState *s = bs->opaque;
-
-    /* Only flush test file, the raw file is not important */
-    return bdrv_aio_flush(s->test_file, cb, opaque);
-}
-
-static BlockDriver bdrv_blkverify = {
-    .format_name        = "blkverify",
-    .protocol_name      = "blkverify",
-
-    .instance_size      = sizeof(BDRVBlkverifyState),
-
-    .bdrv_getlength     = blkverify_getlength,
-
-    .bdrv_file_open     = blkverify_open,
-    .bdrv_close         = blkverify_close,
-
-    .bdrv_aio_readv     = blkverify_aio_readv,
-    .bdrv_aio_writev    = blkverify_aio_writev,
-    .bdrv_aio_flush     = blkverify_aio_flush,
-};
-
-static void bdrv_blkverify_init(void)
-{
-    bdrv_register(&bdrv_blkverify);
-}
-
-block_init(bdrv_blkverify_init);

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/cow.c

@@ -42,7 +42,6 @@ struct cow_header_v2 {
 };
 
 typedef struct BDRVCowState {
-    CoMutex lock;
     int64_t cow_sectors_offset;
 } BDRVCowState;
 
@@ -85,7 +84,6 @@ 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 -1;
@@ -201,17 +199,6 @@ static int 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)
 {
@@ -226,17 +213,6 @@ static int cow_write(BlockDriverState *bs, int64_t sector_num,
     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)
 {
 }
@@ -306,9 +282,9 @@ exit:
     return ret;
 }
 
-static coroutine_fn int cow_co_flush(BlockDriverState *bs)
+static void cow_flush(BlockDriverState *bs)
 {
-    return bdrv_co_flush(bs->file);
+    bdrv_flush(bs->file);
 }
 
 static QEMUOptionParameter cow_create_options[] = {
@@ -326,18 +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_flush_to_disk  = cow_co_flush,
-    .bdrv_is_allocated      = cow_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)
@@ -89,16 +83,14 @@ 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,
-                                    NULL, 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,
-                                    NULL, 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, NULL, 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, NULL);
@@ -237,23 +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;
             }
@@ -302,8 +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
@@ -336,7 +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. */
@@ -416,25 +390,10 @@ 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...
@@ -445,86 +404,61 @@ static AIOPool curl_aio_pool = {
     .cancel             = curl_aio_cancel,
 };
 
-
-static void curl_readv_bh_cb(void *p)
+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;
 
-    CURLAIOCB *acb = p;
-    BDRVCURLState *s = acb->common.bs->opaque;
+    acb = qemu_aio_get(&curl_aio_pool, bs, cb, opaque);
+    if (!acb)
+        return NULL;
 
-    qemu_bh_delete(acb->bh);
-    acb->bh = NULL;
-
-    size_t start = acb->sector_num * SECTOR_SIZE;
-    size_t end;
+    acb->qiov = qiov;
 
     // 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)) {
+
+    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;
+            return &acb->common;
         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;
-    }
+    if (!state)
+        return NULL;
 
     acb->start = 0;
-    acb->end = (acb->nb_sectors * SECTOR_SIZE);
+    acb->end = (nb_sectors * SECTOR_SIZE);
 
     state->buf_off = 0;
     if (state->orig_buf)
-        g_free(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 = g_malloc(state->buf_len);
+    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",
-            (acb->nb_sectors * SECTOR_SIZE), start, state->range);
+            (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)
-{
-    CURLAIOCB *acb;
-
-    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);
-
-    if (!acb->bh) {
-        DPRINTF("CURL: qemu_bh_new failed\n");
-        return NULL;
-    }
-
-    qemu_bh_schedule(acb->bh);
     return &acb->common;
 }
 
@@ -542,7 +476,7 @@ 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;
         }
     }

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/iscsi.c

@@ -1,591 +0,0 @@
-/*
- * QEMU Block driver for iSCSI images
- *
- * Copyright (c) 2010-2011 Ronnie Sahlberg <ronniesahlberg@gmail.com>
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
- */
-
-#include "config-host.h"
-
-#include <poll.h>
-#include "qemu-common.h"
-#include "qemu-error.h"
-#include "block_int.h"
-#include "trace.h"
-
-#include <iscsi/iscsi.h>
-#include <iscsi/scsi-lowlevel.h>
-
-
-typedef struct IscsiLun {
-    struct iscsi_context *iscsi;
-    int lun;
-    int block_size;
-    unsigned long num_blocks;
-} IscsiLun;
-
-typedef struct IscsiAIOCB {
-    BlockDriverAIOCB common;
-    QEMUIOVector *qiov;
-    QEMUBH *bh;
-    IscsiLun *iscsilun;
-    struct scsi_task *task;
-    uint8_t *buf;
-    int status;
-    int canceled;
-    size_t read_size;
-    size_t read_offset;
-} IscsiAIOCB;
-
-struct IscsiTask {
-    IscsiLun *iscsilun;
-    BlockDriverState *bs;
-    int status;
-    int complete;
-};
-
-static void
-iscsi_abort_task_cb(struct iscsi_context *iscsi, int status, void *command_data,
-                    void *private_data)
-{
-}
-
-static void
-iscsi_aio_cancel(BlockDriverAIOCB *blockacb)
-{
-    IscsiAIOCB *acb = (IscsiAIOCB *)blockacb;
-    IscsiLun *iscsilun = acb->iscsilun;
-
-    acb->common.cb(acb->common.opaque, -ECANCELED);
-    acb->canceled = 1;
-
-    /* send a task mgmt call to the target to cancel the task on the target */
-    iscsi_task_mgmt_abort_task_async(iscsilun->iscsi, acb->task,
-                                     iscsi_abort_task_cb, NULL);
-
-    /* then also cancel the task locally in libiscsi */
-    iscsi_scsi_task_cancel(iscsilun->iscsi, acb->task);
-}
-
-static AIOPool iscsi_aio_pool = {
-    .aiocb_size         = sizeof(IscsiAIOCB),
-    .cancel             = iscsi_aio_cancel,
-};
-
-
-static void iscsi_process_read(void *arg);
-static void iscsi_process_write(void *arg);
-
-static int iscsi_process_flush(void *arg)
-{
-    IscsiLun *iscsilun = arg;
-
-    return iscsi_queue_length(iscsilun->iscsi) > 0;
-}
-
-static void
-iscsi_set_events(IscsiLun *iscsilun)
-{
-    struct iscsi_context *iscsi = iscsilun->iscsi;
-
-    qemu_aio_set_fd_handler(iscsi_get_fd(iscsi), iscsi_process_read,
-                           (iscsi_which_events(iscsi) & POLLOUT)
-                           ? iscsi_process_write : NULL,
-                           iscsi_process_flush, NULL, iscsilun);
-}
-
-static void
-iscsi_process_read(void *arg)
-{
-    IscsiLun *iscsilun = arg;
-    struct iscsi_context *iscsi = iscsilun->iscsi;
-
-    iscsi_service(iscsi, POLLIN);
-    iscsi_set_events(iscsilun);
-}
-
-static void
-iscsi_process_write(void *arg)
-{
-    IscsiLun *iscsilun = arg;
-    struct iscsi_context *iscsi = iscsilun->iscsi;
-
-    iscsi_service(iscsi, POLLOUT);
-    iscsi_set_events(iscsilun);
-}
-
-
-static int
-iscsi_schedule_bh(QEMUBHFunc *cb, IscsiAIOCB *acb)
-{
-    acb->bh = qemu_bh_new(cb, acb);
-    if (!acb->bh) {
-        error_report("oom: could not create iscsi bh");
-        return -EIO;
-    }
-
-    qemu_bh_schedule(acb->bh);
-    return 0;
-}
-
-static void
-iscsi_readv_writev_bh_cb(void *p)
-{
-    IscsiAIOCB *acb = p;
-
-    qemu_bh_delete(acb->bh);
-
-    if (acb->canceled == 0) {
-        acb->common.cb(acb->common.opaque, acb->status);
-    }
-
-    qemu_aio_release(acb);
-}
-
-
-static void
-iscsi_aio_write10_cb(struct iscsi_context *iscsi, int status,
-                     void *command_data, void *opaque)
-{
-    IscsiAIOCB *acb = opaque;
-
-    trace_iscsi_aio_write10_cb(iscsi, status, acb, acb->canceled);
-
-    g_free(acb->buf);
-
-    if (acb->canceled != 0) {
-        qemu_aio_release(acb);
-        scsi_free_scsi_task(acb->task);
-        acb->task = NULL;
-        return;
-    }
-
-    acb->status = 0;
-    if (status < 0) {
-        error_report("Failed to write10 data to iSCSI lun. %s",
-                     iscsi_get_error(iscsi));
-        acb->status = -EIO;
-    }
-
-    iscsi_schedule_bh(iscsi_readv_writev_bh_cb, acb);
-    scsi_free_scsi_task(acb->task);
-    acb->task = NULL;
-}
-
-static int64_t sector_qemu2lun(int64_t sector, IscsiLun *iscsilun)
-{
-    return sector * BDRV_SECTOR_SIZE / iscsilun->block_size;
-}
-
-static BlockDriverAIOCB *
-iscsi_aio_writev(BlockDriverState *bs, int64_t sector_num,
-                 QEMUIOVector *qiov, int nb_sectors,
-                 BlockDriverCompletionFunc *cb,
-                 void *opaque)
-{
-    IscsiLun *iscsilun = bs->opaque;
-    struct iscsi_context *iscsi = iscsilun->iscsi;
-    IscsiAIOCB *acb;
-    size_t size;
-    int fua = 0;
-
-    /* set FUA on writes when cache mode is write through */
-    if (!(bs->open_flags & BDRV_O_CACHE_WB)) {
-        fua = 1;
-    }
-
-    acb = qemu_aio_get(&iscsi_aio_pool, bs, cb, opaque);
-    trace_iscsi_aio_writev(iscsi, sector_num, nb_sectors, opaque, acb);
-
-    acb->iscsilun = iscsilun;
-    acb->qiov     = qiov;
-
-    acb->canceled   = 0;
-
-    /* XXX we should pass the iovec to write10 to avoid the extra copy */
-    /* this will allow us to get rid of 'buf' completely */
-    size = nb_sectors * BDRV_SECTOR_SIZE;
-    acb->buf = g_malloc(size);
-    qemu_iovec_to_buffer(acb->qiov, acb->buf);
-    acb->task = iscsi_write10_task(iscsi, iscsilun->lun, acb->buf, size,
-                              sector_qemu2lun(sector_num, iscsilun),
-                              fua, 0, iscsilun->block_size,
-                              iscsi_aio_write10_cb, acb);
-    if (acb->task == NULL) {
-        error_report("iSCSI: Failed to send write10 command. %s",
-                     iscsi_get_error(iscsi));
-        g_free(acb->buf);
-        qemu_aio_release(acb);
-        return NULL;
-    }
-
-    iscsi_set_events(iscsilun);
-
-    return &acb->common;
-}
-
-static void
-iscsi_aio_read10_cb(struct iscsi_context *iscsi, int status,
-                    void *command_data, void *opaque)
-{
-    IscsiAIOCB *acb = opaque;
-
-    trace_iscsi_aio_read10_cb(iscsi, status, acb, acb->canceled);
-
-    if (acb->canceled != 0) {
-        qemu_aio_release(acb);
-        scsi_free_scsi_task(acb->task);
-        acb->task = NULL;
-        return;
-    }
-
-    acb->status = 0;
-    if (status != 0) {
-        error_report("Failed to read10 data from iSCSI lun. %s",
-                     iscsi_get_error(iscsi));
-        acb->status = -EIO;
-    }
-
-    iscsi_schedule_bh(iscsi_readv_writev_bh_cb, acb);
-    scsi_free_scsi_task(acb->task);
-    acb->task = NULL;
-}
-
-static BlockDriverAIOCB *
-iscsi_aio_readv(BlockDriverState *bs, int64_t sector_num,
-                QEMUIOVector *qiov, int nb_sectors,
-                BlockDriverCompletionFunc *cb,
-                void *opaque)
-{
-    IscsiLun *iscsilun = bs->opaque;
-    struct iscsi_context *iscsi = iscsilun->iscsi;
-    IscsiAIOCB *acb;
-    size_t qemu_read_size, lun_read_size;
-    int i;
-
-    qemu_read_size = BDRV_SECTOR_SIZE * (size_t)nb_sectors;
-
-    acb = qemu_aio_get(&iscsi_aio_pool, bs, cb, opaque);
-    trace_iscsi_aio_readv(iscsi, sector_num, nb_sectors, opaque, acb);
-
-    acb->iscsilun = iscsilun;
-    acb->qiov     = qiov;
-
-    acb->canceled    = 0;
-    acb->read_size   = qemu_read_size;
-    acb->buf         = NULL;
-
-    /* If LUN blocksize is bigger than BDRV_BLOCK_SIZE a read from QEMU
-     * may be misaligned to the LUN, so we may need to read some extra
-     * data.
-     */
-    acb->read_offset = 0;
-    if (iscsilun->block_size > BDRV_SECTOR_SIZE) {
-        uint64_t bdrv_offset = BDRV_SECTOR_SIZE * sector_num;
-
-        acb->read_offset  = bdrv_offset % iscsilun->block_size;
-    }
-
-    lun_read_size  = (qemu_read_size + iscsilun->block_size
-                     + acb->read_offset - 1)
-                     / iscsilun->block_size * iscsilun->block_size;
-    acb->task = iscsi_read10_task(iscsi, iscsilun->lun,
-                             sector_qemu2lun(sector_num, iscsilun),
-                             lun_read_size, iscsilun->block_size,
-                             iscsi_aio_read10_cb, acb);
-    if (acb->task == NULL) {
-        error_report("iSCSI: Failed to send read10 command. %s",
-                     iscsi_get_error(iscsi));
-        qemu_aio_release(acb);
-        return NULL;
-    }
-
-    for (i = 0; i < acb->qiov->niov; i++) {
-        scsi_task_add_data_in_buffer(acb->task,
-                acb->qiov->iov[i].iov_len,
-                acb->qiov->iov[i].iov_base);
-    }
-
-    iscsi_set_events(iscsilun);
-
-    return &acb->common;
-}
-
-
-static void
-iscsi_synccache10_cb(struct iscsi_context *iscsi, int status,
-                     void *command_data, void *opaque)
-{
-    IscsiAIOCB *acb = opaque;
-
-    if (acb->canceled != 0) {
-        qemu_aio_release(acb);
-        scsi_free_scsi_task(acb->task);
-        acb->task = NULL;
-        return;
-    }
-
-    acb->status = 0;
-    if (status < 0) {
-        error_report("Failed to sync10 data on iSCSI lun. %s",
-                     iscsi_get_error(iscsi));
-        acb->status = -EIO;
-    }
-
-    iscsi_schedule_bh(iscsi_readv_writev_bh_cb, acb);
-    scsi_free_scsi_task(acb->task);
-    acb->task = NULL;
-}
-
-static BlockDriverAIOCB *
-iscsi_aio_flush(BlockDriverState *bs,
-                BlockDriverCompletionFunc *cb, void *opaque)
-{
-    IscsiLun *iscsilun = bs->opaque;
-    struct iscsi_context *iscsi = iscsilun->iscsi;
-    IscsiAIOCB *acb;
-
-    acb = qemu_aio_get(&iscsi_aio_pool, bs, cb, opaque);
-
-    acb->iscsilun = iscsilun;
-    acb->canceled   = 0;
-
-    acb->task = iscsi_synchronizecache10_task(iscsi, iscsilun->lun,
-                                         0, 0, 0, 0,
-                                         iscsi_synccache10_cb,
-                                         acb);
-    if (acb->task == NULL) {
-        error_report("iSCSI: Failed to send synchronizecache10 command. %s",
-                     iscsi_get_error(iscsi));
-        qemu_aio_release(acb);
-        return NULL;
-    }
-
-    iscsi_set_events(iscsilun);
-
-    return &acb->common;
-}
-
-static int64_t
-iscsi_getlength(BlockDriverState *bs)
-{
-    IscsiLun *iscsilun = bs->opaque;
-    int64_t len;
-
-    len  = iscsilun->num_blocks;
-    len *= iscsilun->block_size;
-
-    return len;
-}
-
-static void
-iscsi_readcapacity10_cb(struct iscsi_context *iscsi, int status,
-                        void *command_data, void *opaque)
-{
-    struct IscsiTask *itask = opaque;
-    struct scsi_readcapacity10 *rc10;
-    struct scsi_task *task = command_data;
-
-    if (status != 0) {
-        error_report("iSCSI: Failed to read capacity of iSCSI lun. %s",
-                     iscsi_get_error(iscsi));
-        itask->status   = 1;
-        itask->complete = 1;
-        scsi_free_scsi_task(task);
-        return;
-    }
-
-    rc10 = scsi_datain_unmarshall(task);
-    if (rc10 == NULL) {
-        error_report("iSCSI: Failed to unmarshall readcapacity10 data.");
-        itask->status   = 1;
-        itask->complete = 1;
-        scsi_free_scsi_task(task);
-        return;
-    }
-
-    itask->iscsilun->block_size = rc10->block_size;
-    itask->iscsilun->num_blocks = rc10->lba;
-    itask->bs->total_sectors = (uint64_t)rc10->lba *
-                               rc10->block_size / BDRV_SECTOR_SIZE ;
-
-    itask->status   = 0;
-    itask->complete = 1;
-    scsi_free_scsi_task(task);
-}
-
-
-static void
-iscsi_connect_cb(struct iscsi_context *iscsi, int status, void *command_data,
-                 void *opaque)
-{
-    struct IscsiTask *itask = opaque;
-    struct scsi_task *task;
-
-    if (status != 0) {
-        itask->status   = 1;
-        itask->complete = 1;
-        return;
-    }
-
-    task = iscsi_readcapacity10_task(iscsi, itask->iscsilun->lun, 0, 0,
-                                   iscsi_readcapacity10_cb, opaque);
-    if (task == NULL) {
-        error_report("iSCSI: failed to send readcapacity command.");
-        itask->status   = 1;
-        itask->complete = 1;
-        return;
-    }
-}
-
-/*
- * We support iscsi url's on the form
- * iscsi://[<username>%<password>@]<host>[:<port>]/<targetname>/<lun>
- */
-static int iscsi_open(BlockDriverState *bs, const char *filename, int flags)
-{
-    IscsiLun *iscsilun = bs->opaque;
-    struct iscsi_context *iscsi = NULL;
-    struct iscsi_url *iscsi_url = NULL;
-    struct IscsiTask task;
-    int ret;
-
-    if ((BDRV_SECTOR_SIZE % 512) != 0) {
-        error_report("iSCSI: Invalid BDRV_SECTOR_SIZE. "
-                     "BDRV_SECTOR_SIZE(%lld) is not a multiple "
-                     "of 512", BDRV_SECTOR_SIZE);
-        return -EINVAL;
-    }
-
-    memset(iscsilun, 0, sizeof(IscsiLun));
-
-    /* Should really append the KVM name after the ':' here */
-    iscsi = iscsi_create_context("iqn.2008-11.org.linux-kvm:");
-    if (iscsi == NULL) {
-        error_report("iSCSI: Failed to create iSCSI context.");
-        ret = -ENOMEM;
-        goto failed;
-    }
-
-    iscsi_url = iscsi_parse_full_url(iscsi, filename);
-    if (iscsi_url == NULL) {
-        error_report("Failed to parse URL : %s %s", filename,
-                     iscsi_get_error(iscsi));
-        ret = -EINVAL;
-        goto failed;
-    }
-
-    if (iscsi_set_targetname(iscsi, iscsi_url->target)) {
-        error_report("iSCSI: Failed to set target name.");
-        ret = -EINVAL;
-        goto failed;
-    }
-
-    if (iscsi_url->user != NULL) {
-        ret = iscsi_set_initiator_username_pwd(iscsi, iscsi_url->user,
-                                              iscsi_url->passwd);
-        if (ret != 0) {
-            error_report("Failed to set initiator username and password");
-            ret = -EINVAL;
-            goto failed;
-        }
-    }
-    if (iscsi_set_session_type(iscsi, ISCSI_SESSION_NORMAL) != 0) {
-        error_report("iSCSI: Failed to set session type to normal.");
-        ret = -EINVAL;
-        goto failed;
-    }
-
-    iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_NONE_CRC32C);
-
-    task.iscsilun = iscsilun;
-    task.status = 0;
-    task.complete = 0;
-    task.bs = bs;
-
-    iscsilun->iscsi = iscsi;
-    iscsilun->lun   = iscsi_url->lun;
-
-    if (iscsi_full_connect_async(iscsi, iscsi_url->portal, iscsi_url->lun,
-                                 iscsi_connect_cb, &task)
-        != 0) {
-        error_report("iSCSI: Failed to start async connect.");
-        ret = -EINVAL;
-        goto failed;
-    }
-
-    while (!task.complete) {
-        iscsi_set_events(iscsilun);
-        qemu_aio_wait();
-    }
-    if (task.status != 0) {
-        error_report("iSCSI: Failed to connect to LUN : %s",
-                     iscsi_get_error(iscsi));
-        ret = -EINVAL;
-        goto failed;
-    }
-
-    if (iscsi_url != NULL) {
-        iscsi_destroy_url(iscsi_url);
-    }
-    return 0;
-
-failed:
-    if (iscsi_url != NULL) {
-        iscsi_destroy_url(iscsi_url);
-    }
-    if (iscsi != NULL) {
-        iscsi_destroy_context(iscsi);
-    }
-    memset(iscsilun, 0, sizeof(IscsiLun));
-    return ret;
-}
-
-static void iscsi_close(BlockDriverState *bs)
-{
-    IscsiLun *iscsilun = bs->opaque;
-    struct iscsi_context *iscsi = iscsilun->iscsi;
-
-    qemu_aio_set_fd_handler(iscsi_get_fd(iscsi), NULL, NULL, NULL, NULL, NULL);
-    iscsi_destroy_context(iscsi);
-    memset(iscsilun, 0, sizeof(IscsiLun));
-}
-
-static BlockDriver bdrv_iscsi = {
-    .format_name     = "iscsi",
-    .protocol_name   = "iscsi",
-
-    .instance_size   = sizeof(IscsiLun),
-    .bdrv_file_open  = iscsi_open,
-    .bdrv_close      = iscsi_close,
-
-    .bdrv_getlength  = iscsi_getlength,
-
-    .bdrv_aio_readv  = iscsi_aio_readv,
-    .bdrv_aio_writev = iscsi_aio_writev,
-    .bdrv_aio_flush  = iscsi_aio_flush,
-};
-
-static void iscsi_block_init(void)
-{
-    bdrv_register(&bdrv_iscsi);
-}
-
-block_init(iscsi_block_init);

block/nbd.c

@@ -28,158 +28,71 @@
 
 #include "qemu-common.h"
 #include "nbd.h"
-#include "block_int.h"
 #include "module.h"
-#include "qemu_socket.h"
 
 #include <sys/types.h>
 #include <unistd.h>
 
-#define EN_OPTSTR ":exportname="
-
-/* #define DEBUG_NBD */
-
-#if defined(DEBUG_NBD)
-#define logout(fmt, ...) \
-                fprintf(stderr, "nbd\t%-24s" fmt, __func__, ##__VA_ARGS__)
-#else
-#define logout(fmt, ...) ((void)0)
-#endif
-
 typedef struct BDRVNBDState {
-    CoMutex lock;
     int sock;
-    uint32_t nbdflags;
     off_t size;
     size_t blocksize;
-    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_config(BDRVNBDState *s, const char *filename, int flags)
-{
-    char *file;
-    char *export_name;
-    const char *host_spec;
-    const char *unixpath;
-    int err = -EINVAL;
-
-    file = g_strdup(filename);
-
-    export_name = strstr(file, EN_OPTSTR);
-    if (export_name) {
-        if (export_name[strlen(EN_OPTSTR)] == 0) {
-            goto out;
-        }
-        export_name[0] = 0; /* truncate 'file' */
-        export_name += strlen(EN_OPTSTR);
-        s->export_name = g_strdup(export_name);
-    }
-
-    /* extract the host_spec - fail if it's not nbd:... */
-    if (!strstart(file, "nbd:", &host_spec)) {
-        goto out;
-    }
-
-    /* are we a UNIX or TCP socket? */
-    if (strstart(host_spec, "unix:", &unixpath)) {
-        if (unixpath[0] != '/') { /* We demand  an absolute path*/
-            goto out;
-        }
-        s->host_spec = g_strdup(unixpath);
-    } else {
-        s->host_spec = g_strdup(host_spec);
-    }
-
-    err = 0;
-
-out:
-    g_free(file);
-    if (err != 0) {
-        g_free(s->export_name);
-        g_free(s->host_spec);
-    }
-    return err;
-}
-
-static int nbd_establish_connection(BlockDriverState *bs)
+static int nbd_open(BlockDriverState *bs, const char* filename, int flags)
 {
     BDRVNBDState *s = bs->opaque;
+    const char *host;
+    const char *unixpath;
     int sock;
-    int ret;
     off_t size;
     size_t blocksize;
+    int ret;
+
+    if (!strstart(filename, "nbd:", &host))
+        return -EINVAL;
+
+    if (strstart(host, "unix:", &unixpath)) {
+
+        if (unixpath[0] != '/')
+            return -EINVAL;
+
+        sock = unix_socket_outgoing(unixpath);
 
-    if (s->host_spec[0] == '/') {
-        sock = unix_socket_outgoing(s->host_spec);
     } else {
-        sock = tcp_socket_outgoing_spec(s->host_spec);
+        uint16_t port;
+        char *p, *r;
+        char hostname[128];
+
+        pstrcpy(hostname, 128, host);
+
+        p = strchr(hostname, ':');
+        if (p == NULL)
+            return -EINVAL;
+
+        *p = '\0';
+        p++;
+
+        port = strtol(p, &r, 0);
+        if (r == p)
+            return -EINVAL;
+        sock = tcp_socket_outgoing(hostname, port);
     }
 
-    /* Failed to establish connection */
-    if (sock == -1) {
-        logout("Failed to establish connection to NBD server\n");
+    if (sock == -1)
         return -errno;
-    }
 
-    /* NBD handshake */
-    ret = nbd_receive_negotiate(sock, s->export_name, &s->nbdflags, &size,
-                                &blocksize);
-    if (ret == -1) {
-        logout("Failed to negotiate with the NBD server\n");
-        closesocket(sock);
+    ret = nbd_receive_negotiate(sock, &size, &blocksize);
+    if (ret == -1)
         return -errno;
-    }
-
-    /* Now that we're connected, set the socket to be non-blocking */
-    socket_set_nonblock(sock);
 
     s->sock = sock;
     s->size = size;
     s->blocksize = blocksize;
 
-    logout("Established connection with NBD server\n");
     return 0;
 }
 
-static void nbd_teardown_connection(BlockDriverState *bs)
-{
-    BDRVNBDState *s = bs->opaque;
-    struct nbd_request request;
-
-    request.type = NBD_CMD_DISC;
-    request.handle = (uint64_t)(intptr_t)bs;
-    request.from = 0;
-    request.len = 0;
-    nbd_send_request(s->sock, &request);
-
-    closesocket(s->sock);
-}
-
-static int nbd_open(BlockDriverState *bs, const char* filename, int flags)
-{
-    BDRVNBDState *s = bs->opaque;
-    int result;
-
-    /* Pop the config into our state object. Exit if invalid. */
-    result = nbd_config(s, filename, flags);
-    if (result != 0) {
-        return result;
-    }
-
-    /* establish TCP connection, return error if it fails
-     * TODO: Configurable retry-until-timeout behaviour.
-     */
-    result = nbd_establish_connection(bs);
-
-    qemu_co_mutex_init(&s->lock);
-    return result;
-}
-
 static int nbd_read(BlockDriverState *bs, int64_t sector_num,
                     uint8_t *buf, int nb_sectors)
 {
@@ -240,35 +153,18 @@ static int nbd_write(BlockDriverState *bs, int64_t sector_num,
     return 0;
 }
 
-static coroutine_fn int nbd_co_read(BlockDriverState *bs, int64_t sector_num,
-                                    uint8_t *buf, int nb_sectors)
-{
-    int ret;
-    BDRVNBDState *s = bs->opaque;
-    qemu_co_mutex_lock(&s->lock);
-    ret = nbd_read(bs, sector_num, buf, nb_sectors);
-    qemu_co_mutex_unlock(&s->lock);
-    return ret;
-}
-
-static coroutine_fn int nbd_co_write(BlockDriverState *bs, int64_t sector_num,
-                                     const uint8_t *buf, int nb_sectors)
-{
-    int ret;
-    BDRVNBDState *s = bs->opaque;
-    qemu_co_mutex_lock(&s->lock);
-    ret = nbd_write(bs, sector_num, buf, nb_sectors);
-    qemu_co_mutex_unlock(&s->lock);
-    return ret;
-}
-
 static void nbd_close(BlockDriverState *bs)
 {
     BDRVNBDState *s = bs->opaque;
-    g_free(s->export_name);
-    g_free(s->host_spec);
+    struct nbd_request request;
 
-    nbd_teardown_connection(bs);
+    request.type = NBD_CMD_DISC;
+    request.handle = (uint64_t)(intptr_t)bs;
+    request.from = 0;
+    request.len = 0;
+    nbd_send_request(s->sock, &request);
+
+    close(s->sock);
 }
 
 static int64_t nbd_getlength(BlockDriverState *bs)
@@ -282,8 +178,8 @@ static BlockDriver bdrv_nbd = {
     .format_name	= "nbd",
     .instance_size	= sizeof(BDRVNBDState),
     .bdrv_file_open	= nbd_open,
-    .bdrv_read          = nbd_co_read,
-    .bdrv_write         = nbd_co_write,
+    .bdrv_read		= nbd_read,
+    .bdrv_write		= nbd_write,
     .bdrv_close		= nbd_close,
     .bdrv_getlength	= nbd_getlength,
     .protocol_name	= "nbd",

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 */
@@ -55,6 +54,7 @@ typedef struct QCowHeader {
 #define L2_CACHE_SIZE 16
 
 typedef struct BDRVQcowState {
+    BlockDriverState *hd;
     int cluster_bits;
     int cluster_size;
     int cluster_sectors;
@@ -74,8 +74,6 @@ 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);
@@ -131,7 +129,7 @@ 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));
+    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)) !=
@@ -141,13 +139,13 @@ static int qcow_open(BlockDriverState *bs, int flags)
         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->l2_cache = qemu_malloc(s->l2_size * L2_CACHE_SIZE * sizeof(uint64_t));
     if (!s->l2_cache)
         goto fail;
-    s->cluster_cache = g_malloc(s->cluster_size);
+    s->cluster_cache = qemu_malloc(s->cluster_size);
     if (!s->cluster_cache)
         goto fail;
-    s->cluster_data = g_malloc(s->cluster_size);
+    s->cluster_data = qemu_malloc(s->cluster_size);
     if (!s->cluster_data)
         goto fail;
     s->cluster_cache_offset = -1;
@@ -161,21 +159,13 @@ static int qcow_open(BlockDriverState *bs, int flags)
             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);
+    qemu_free(s->l1_table);
+    qemu_free(s->l2_cache);
+    qemu_free(s->cluster_cache);
+    qemu_free(s->cluster_data);
     return -1;
 }
 
@@ -200,6 +190,24 @@ 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;
 }
 
@@ -433,193 +441,302 @@ static int decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
     return 0;
 }
 
-static 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;
+    QEMUIOVector hd_qiov;
+    BlockDriverAIOCB *hd_aiocb;
+} QCowAIOCB;
 
-    if (qiov->niov > 1) {
-        qemu_iovec_from_buffer(qiov, 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 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;
+    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)
+{
+    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)
+                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)
+            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)
+            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;
+
+    acb = qcow_aio_setup(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
+    if (!acb)
+        return NULL;
+
+    qcow_aio_read_cb(acb, 0);
+    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)
+        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;
 
     s->cluster_cache_offset = -1; /* disable compressed cache */
 
-    if (qiov->niov > 1) {
-        buf = orig_buf = qemu_blockalign(bs, qiov->size);
-        qemu_iovec_to_buffer(qiov, buf);
-    } 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;
 
-    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;
+    qcow_aio_write_cb(acb, 0);
+    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)
@@ -747,7 +864,9 @@ 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));
@@ -755,8 +874,8 @@ 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;
@@ -766,9 +885,9 @@ 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;
 
@@ -776,34 +895,30 @@ 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 coroutine_fn int qcow_co_flush(BlockDriverState *bs)
+static void qcow_flush(BlockDriverState *bs)
 {
-    return bdrv_co_flush(bs->file);
+    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)
@@ -840,16 +955,15 @@ static BlockDriver bdrv_qcow = {
     .bdrv_open		= qcow_open,
     .bdrv_close		= qcow_close,
     .bdrv_create	= qcow_create,
-
-    .bdrv_co_readv          = qcow_co_readv,
-    .bdrv_co_writev         = qcow_co_writev,
-    .bdrv_co_flush_to_disk  = qcow_co_flush,
-    .bdrv_is_allocated      = qcow_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

@@ -1,326 +0,0 @@
-/*
- * L2/refcount table cache for the QCOW2 format
- *
- * Copyright (c) 2010 Kevin Wolf <kwolf@redhat.com>
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
- */
-
-#include "block_int.h"
-#include "qemu-common.h"
-#include "qcow2.h"
-
-typedef struct Qcow2CachedTable {
-    void*   table;
-    int64_t offset;
-    bool    dirty;
-    int     cache_hits;
-    int     ref;
-} Qcow2CachedTable;
-
-struct Qcow2Cache {
-    Qcow2CachedTable*       entries;
-    struct Qcow2Cache*      depends;
-    int                     size;
-    bool                    depends_on_flush;
-    bool                    writethrough;
-};
-
-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->size = num_tables;
-    c->entries = g_malloc0(sizeof(*c->entries) * num_tables);
-    c->writethrough = writethrough;
-
-    for (i = 0; i < c->size; i++) {
-        c->entries[i].table = qemu_blockalign(bs, s->cluster_size);
-    }
-
-    return c;
-}
-
-int qcow2_cache_destroy(BlockDriverState* bs, Qcow2Cache *c)
-{
-    int i;
-
-    for (i = 0; i < c->size; i++) {
-        assert(c->entries[i].ref == 0);
-        qemu_vfree(c->entries[i].table);
-    }
-
-    g_free(c->entries);
-    g_free(c);
-
-    return 0;
-}
-
-static int qcow2_cache_flush_dependency(BlockDriverState *bs, Qcow2Cache *c)
-{
-    int ret;
-
-    ret = qcow2_cache_flush(bs, c->depends);
-    if (ret < 0) {
-        return ret;
-    }
-
-    c->depends = NULL;
-    c->depends_on_flush = false;
-
-    return 0;
-}
-
-static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)
-{
-    BDRVQcowState *s = bs->opaque;
-    int ret = 0;
-
-    if (!c->entries[i].dirty || !c->entries[i].offset) {
-        return 0;
-    }
-
-    if (c->depends) {
-        ret = qcow2_cache_flush_dependency(bs, c);
-    } else if (c->depends_on_flush) {
-        ret = bdrv_flush(bs->file);
-        if (ret >= 0) {
-            c->depends_on_flush = false;
-        }
-    }
-
-    if (ret < 0) {
-        return ret;
-    }
-
-    if (c == s->refcount_block_cache) {
-        BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_UPDATE_PART);
-    } else if (c == s->l2_table_cache) {
-        BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE);
-    }
-
-    ret = bdrv_pwrite(bs->file, c->entries[i].offset, c->entries[i].table,
-        s->cluster_size);
-    if (ret < 0) {
-        return ret;
-    }
-
-    c->entries[i].dirty = false;
-
-    return 0;
-}
-
-int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c)
-{
-    int result = 0;
-    int ret;
-    int i;
-
-    for (i = 0; i < c->size; i++) {
-        ret = qcow2_cache_entry_flush(bs, c, i);
-        if (ret < 0 && result != -ENOSPC) {
-            result = ret;
-        }
-    }
-
-    if (result == 0) {
-        ret = bdrv_flush(bs->file);
-        if (ret < 0) {
-            result = ret;
-        }
-    }
-
-    return result;
-}
-
-int qcow2_cache_set_dependency(BlockDriverState *bs, Qcow2Cache *c,
-    Qcow2Cache *dependency)
-{
-    int ret;
-
-    if (dependency->depends) {
-        ret = qcow2_cache_flush_dependency(bs, dependency);
-        if (ret < 0) {
-            return ret;
-        }
-    }
-
-    if (c->depends && (c->depends != dependency)) {
-        ret = qcow2_cache_flush_dependency(bs, c);
-        if (ret < 0) {
-            return ret;
-        }
-    }
-
-    c->depends = dependency;
-    return 0;
-}
-
-void qcow2_cache_depends_on_flush(Qcow2Cache *c)
-{
-    c->depends_on_flush = true;
-}
-
-static int qcow2_cache_find_entry_to_replace(Qcow2Cache *c)
-{
-    int i;
-    int min_count = INT_MAX;
-    int min_index = -1;
-
-
-    for (i = 0; i < c->size; i++) {
-        if (c->entries[i].ref) {
-            continue;
-        }
-
-        if (c->entries[i].cache_hits < min_count) {
-            min_index = i;
-            min_count = c->entries[i].cache_hits;
-        }
-
-        /* Give newer hits priority */
-        /* TODO Check how to optimize the replacement strategy */
-        c->entries[i].cache_hits /= 2;
-    }
-
-    if (min_index == -1) {
-        /* This can't happen in current synchronous code, but leave the check
-         * here as a reminder for whoever starts using AIO with the cache */
-        abort();
-    }
-    return min_index;
-}
-
-static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c,
-    uint64_t offset, void **table, bool read_from_disk)
-{
-    BDRVQcowState *s = bs->opaque;
-    int i;
-    int ret;
-
-    /* Check if the table is already cached */
-    for (i = 0; i < c->size; i++) {
-        if (c->entries[i].offset == offset) {
-            goto found;
-        }
-    }
-
-    /* If not, write a table back and replace it */
-    i = qcow2_cache_find_entry_to_replace(c);
-    if (i < 0) {
-        return i;
-    }
-
-    ret = qcow2_cache_entry_flush(bs, c, i);
-    if (ret < 0) {
-        return ret;
-    }
-
-    c->entries[i].offset = 0;
-    if (read_from_disk) {
-        if (c == s->l2_table_cache) {
-            BLKDBG_EVENT(bs->file, BLKDBG_L2_LOAD);
-        }
-
-        ret = bdrv_pread(bs->file, offset, c->entries[i].table, s->cluster_size);
-        if (ret < 0) {
-            return ret;
-        }
-    }
-
-    /* Give the table some hits for the start so that it won't be replaced
-     * immediately. The number 32 is completely arbitrary. */
-    c->entries[i].cache_hits = 32;
-    c->entries[i].offset = offset;
-
-    /* And return the right table */
-found:
-    c->entries[i].cache_hits++;
-    c->entries[i].ref++;
-    *table = c->entries[i].table;
-    return 0;
-}
-
-int qcow2_cache_get(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset,
-    void **table)
-{
-    return qcow2_cache_do_get(bs, c, offset, table, true);
-}
-
-int qcow2_cache_get_empty(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset,
-    void **table)
-{
-    return qcow2_cache_do_get(bs, c, offset, table, false);
-}
-
-int qcow2_cache_put(BlockDriverState *bs, Qcow2Cache *c, void **table)
-{
-    int i;
-
-    for (i = 0; i < c->size; i++) {
-        if (c->entries[i].table == *table) {
-            goto found;
-        }
-    }
-    return -ENOENT;
-
-found:
-    c->entries[i].ref--;
-    *table = NULL;
-
-    assert(c->entries[i].ref >= 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)
-{
-    int i;
-
-    for (i = 0; i < c->size; i++) {
-        if (c->entries[i].table == table) {
-            goto found;
-        }
-    }
-    abort();
-
-found:
-    c->entries[i].dirty = true;
-}
-
-bool qcow2_cache_set_writethrough(BlockDriverState *bs, Qcow2Cache *c,
-    bool enable)
-{
-    bool old = c->writethrough;
-
-    if (!old && enable) {
-        qcow2_cache_flush(bs, c);
-    }
-
-    c->writethrough = enable;
-    return old;
-}

block/qcow2-cluster.c

@@ -28,7 +28,7 @@
 #include "block_int.h"
 #include "block/qcow2.h"
 
-int qcow2_grow_l1_table(BlockDriverState *bs, int min_size, bool exact_size)
+int qcow2_grow_l1_table(BlockDriverState *bs, int min_size)
 {
     BDRVQcowState *s = bs->opaque;
     int new_l1_size, new_l1_size2, ret, i;
@@ -36,43 +36,31 @@ int qcow2_grow_l1_table(BlockDriverState *bs, int min_size, bool exact_size)
     int64_t new_l1_table_offset;
     uint8_t data[12];
 
-    if (min_size <= s->l1_size)
+    new_l1_size = s->l1_size;
+    if (min_size <= new_l1_size)
         return 0;
-
-    if (exact_size) {
-        new_l1_size = min_size;
-    } else {
-        /* Bump size up to reduce the number of times we have to grow */
-        new_l1_size = s->l1_size;
-        if (new_l1_size == 0) {
-            new_l1_size = 1;
-        }
-        while (min_size > new_l1_size) {
-            new_l1_size = (new_l1_size * 3 + 1) / 2;
-        }
+    if (new_l1_size == 0) {
+        new_l1_size = 1;
+    }
+    while (min_size > new_l1_size) {
+        new_l1_size = (new_l1_size * 3 + 1) / 2;
     }
-
 #ifdef DEBUG_ALLOC2
-    fprintf(stderr, "grow l1_table from %d to %d\n", s->l1_size, new_l1_size);
+    printf("grow l1_table from %d to %d\n", s->l1_size, new_l1_size);
 #endif
 
     new_l1_size2 = sizeof(uint64_t) * new_l1_size;
-    new_l1_table = g_malloc0(align_offset(new_l1_size2, 512));
+    new_l1_table = qemu_mallocz(align_offset(new_l1_size2, 512));
     memcpy(new_l1_table, s->l1_table, s->l1_size * sizeof(uint64_t));
 
     /* write new table (align to cluster) */
     BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_ALLOC_TABLE);
     new_l1_table_offset = qcow2_alloc_clusters(bs, new_l1_size2);
     if (new_l1_table_offset < 0) {
-        g_free(new_l1_table);
+        qemu_free(new_l1_table);
         return new_l1_table_offset;
     }
 
-    ret = qcow2_cache_flush(bs, s->refcount_block_cache);
-    if (ret < 0) {
-        goto fail;
-    }
-
     BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_WRITE_TABLE);
     for(i = 0; i < s->l1_size; i++)
         new_l1_table[i] = cpu_to_be64(new_l1_table[i]);
@@ -85,23 +73,80 @@ int qcow2_grow_l1_table(BlockDriverState *bs, int min_size, bool exact_size)
     /* set new table */
     BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_ACTIVATE_TABLE);
     cpu_to_be32w((uint32_t*)data, new_l1_size);
-    cpu_to_be64wu((uint64_t*)(data + 4), new_l1_table_offset);
+    cpu_to_be64w((uint64_t*)(data + 4), new_l1_table_offset);
     ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, l1_size), data,sizeof(data));
     if (ret < 0) {
         goto fail;
     }
-    g_free(s->l1_table);
+    qemu_free(s->l1_table);
     qcow2_free_clusters(bs, s->l1_table_offset, s->l1_size * sizeof(uint64_t));
     s->l1_table_offset = new_l1_table_offset;
     s->l1_table = new_l1_table;
     s->l1_size = new_l1_size;
     return 0;
  fail:
-    g_free(new_l1_table);
+    qemu_free(new_l1_table);
     qcow2_free_clusters(bs, new_l1_table_offset, new_l1_size2);
     return ret;
 }
 
+void qcow2_l2_cache_reset(BlockDriverState *bs)
+{
+    BDRVQcowState *s = bs->opaque;
+
+    memset(s->l2_cache, 0, s->l2_size * L2_CACHE_SIZE * sizeof(uint64_t));
+    memset(s->l2_cache_offsets, 0, L2_CACHE_SIZE * sizeof(uint64_t));
+    memset(s->l2_cache_counts, 0, L2_CACHE_SIZE * sizeof(uint32_t));
+}
+
+static inline int l2_cache_new_entry(BlockDriverState *bs)
+{
+    BDRVQcowState *s = bs->opaque;
+    uint32_t min_count;
+    int min_index, i;
+
+    /* find a new entry in the least used one */
+    min_index = 0;
+    min_count = 0xffffffff;
+    for(i = 0; i < L2_CACHE_SIZE; i++) {
+        if (s->l2_cache_counts[i] < min_count) {
+            min_count = s->l2_cache_counts[i];
+            min_index = i;
+        }
+    }
+    return min_index;
+}
+
+/*
+ * seek_l2_table
+ *
+ * seek l2_offset in the l2_cache table
+ * if not found, return NULL,
+ * if found,
+ *   increments the l2 cache hit count of the entry,
+ *   if counter overflow, divide by two all counters
+ *   return the pointer to the l2 cache entry
+ *
+ */
+
+static uint64_t *seek_l2_table(BDRVQcowState *s, uint64_t l2_offset)
+{
+    int i, j;
+
+    for(i = 0; i < L2_CACHE_SIZE; i++) {
+        if (l2_offset == s->l2_cache_offsets[i]) {
+            /* increment the hit count */
+            if (++s->l2_cache_counts[i] == 0xffffffff) {
+                for(j = 0; j < L2_CACHE_SIZE; j++) {
+                    s->l2_cache_counts[j] >>= 1;
+                }
+            }
+            return s->l2_cache + (i << s->l2_bits);
+        }
+    }
+    return NULL;
+}
+
 /*
  * l2_load
  *
@@ -116,11 +161,32 @@ static int l2_load(BlockDriverState *bs, uint64_t l2_offset,
     uint64_t **l2_table)
 {
     BDRVQcowState *s = bs->opaque;
+    int min_index;
     int ret;
 
-    ret = qcow2_cache_get(bs, s->l2_table_cache, l2_offset, (void**) l2_table);
+    /* seek if the table for the given offset is in the cache */
 
-    return ret;
+    *l2_table = seek_l2_table(s, l2_offset);
+    if (*l2_table != NULL) {
+        return 0;
+    }
+
+    /* not found: load a new entry in the least used one */
+
+    min_index = l2_cache_new_entry(bs);
+    *l2_table = s->l2_cache + (min_index << s->l2_bits);
+
+    BLKDBG_EVENT(bs->file, BLKDBG_L2_LOAD);
+    ret = bdrv_pread(bs->file, l2_offset, *l2_table,
+        s->l2_size * sizeof(uint64_t));
+    if (ret < 0) {
+        return ret;
+    }
+
+    s->l2_cache_offsets[min_index] = l2_offset;
+    s->l2_cache_counts[min_index] = 1;
+
+    return 0;
 }
 
 /*
@@ -163,6 +229,7 @@ static int write_l1_entry(BlockDriverState *bs, int l1_index)
 static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table)
 {
     BDRVQcowState *s = bs->opaque;
+    int min_index;
     uint64_t old_l2_offset;
     uint64_t *l2_table;
     int64_t l2_offset;
@@ -177,47 +244,27 @@ static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table)
         return l2_offset;
     }
 
-    ret = qcow2_cache_flush(bs, s->refcount_block_cache);
-    if (ret < 0) {
-        goto fail;
-    }
-
     /* allocate a new entry in the l2 cache */
 
-    ret = qcow2_cache_get_empty(bs, s->l2_table_cache, l2_offset, (void**) table);
-    if (ret < 0) {
-        return ret;
-    }
-
-    l2_table = *table;
+    min_index = l2_cache_new_entry(bs);
+    l2_table = s->l2_cache + (min_index << s->l2_bits);
 
     if (old_l2_offset == 0) {
         /* if there was no old l2 table, clear the new table */
         memset(l2_table, 0, s->l2_size * sizeof(uint64_t));
     } else {
-        uint64_t* old_table;
-
         /* if there was an old l2 table, read it from the disk */
         BLKDBG_EVENT(bs->file, BLKDBG_L2_ALLOC_COW_READ);
-        ret = qcow2_cache_get(bs, s->l2_table_cache, old_l2_offset,
-            (void**) &old_table);
-        if (ret < 0) {
-            goto fail;
-        }
-
-        memcpy(l2_table, old_table, s->cluster_size);
-
-        ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &old_table);
+        ret = bdrv_pread(bs->file, old_l2_offset, l2_table,
+            s->l2_size * sizeof(uint64_t));
         if (ret < 0) {
             goto fail;
         }
     }
-
     /* write the l2 table to the file */
     BLKDBG_EVENT(bs->file, BLKDBG_L2_ALLOC_WRITE);
-
-    qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
-    ret = qcow2_cache_flush(bs, s->l2_table_cache);
+    ret = bdrv_pwrite_sync(bs->file, l2_offset, l2_table,
+        s->l2_size * sizeof(uint64_t));
     if (ret < 0) {
         goto fail;
     }
@@ -229,12 +276,17 @@ static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table)
         goto fail;
     }
 
+    /* update the l2 cache entry */
+
+    s->l2_cache_offsets[min_index] = l2_offset;
+    s->l2_cache_counts[min_index] = 1;
+
     *table = l2_table;
     return 0;
 
 fail:
-    qcow2_cache_put(bs, s->l2_table_cache, (void**) table);
     s->l1_table[l1_index] = old_l2_offset;
+    qcow2_l2_cache_reset(bs);
     return ret;
 }
 
@@ -290,14 +342,12 @@ void qcow2_encrypt_sectors(BDRVQcowState *s, int64_t sector_num,
 }
 
 
-static int qcow2_read(BlockDriverState *bs, int64_t sector_num,
-                      uint8_t *buf, int nb_sectors)
+static int qcow_read(BlockDriverState *bs, int64_t sector_num,
+                     uint8_t *buf, int nb_sectors)
 {
     BDRVQcowState *s = bs->opaque;
     int ret, index_in_cluster, n, n1;
     uint64_t cluster_offset;
-    struct iovec iov;
-    QEMUIOVector qiov;
 
     while (nb_sectors > 0) {
         n = nb_sectors;
@@ -312,11 +362,7 @@ static int qcow2_read(BlockDriverState *bs, int64_t sector_num,
         if (!cluster_offset) {
             if (bs->backing_hd) {
                 /* read from the base image */
-                iov.iov_base = buf;
-                iov.iov_len = n * 512;
-                qemu_iovec_init_external(&qiov, &iov, 1);
-
-                n1 = qcow2_backing_read1(bs->backing_hd, &qiov, sector_num, n);
+                n1 = qcow2_backing_read1(bs->backing_hd, sector_num, buf, n);
                 if (n1 > 0) {
                     BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING);
                     ret = bdrv_read(bs->backing_hd, sector_num, buf, n1);
@@ -357,7 +403,7 @@ static int copy_sectors(BlockDriverState *bs, uint64_t start_sect,
     if (n <= 0)
         return 0;
     BLKDBG_EVENT(bs->file, BLKDBG_COW_READ);
-    ret = qcow2_read(bs, start_sect + n_start, s->cluster_data, n);
+    ret = qcow_read(bs, start_sect + n_start, s->cluster_data, n);
     if (ret < 0)
         return ret;
     if (s->crypt_method) {
@@ -367,7 +413,7 @@ static int copy_sectors(BlockDriverState *bs, uint64_t start_sect,
                         &s->aes_encrypt_key);
     }
     BLKDBG_EVENT(bs->file, BLKDBG_COW_WRITE);
-    ret = bdrv_write(bs->file, (cluster_offset >> 9) + n_start,
+    ret = bdrv_write_sync(bs->file, (cluster_offset >> 9) + n_start,
         s->cluster_data, n);
     if (ret < 0)
         return ret;
@@ -381,10 +427,10 @@ static int copy_sectors(BlockDriverState *bs, uint64_t start_sect,
  * For a given offset of the disk image, find the cluster offset in
  * qcow2 file. The offset is stored in *cluster_offset.
  *
- * on entry, *num is the number of contiguous sectors we'd like to
+ * on entry, *num is the number of contiguous clusters we'd like to
  * access following offset.
  *
- * on exit, *num is the number of contiguous sectors we can read.
+ * on exit, *num is the number of contiguous clusters we can read.
  *
  * Return 0, if the offset is found
  * Return -errno, otherwise.
@@ -459,8 +505,6 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
                 &l2_table[l2_index], 0, QCOW_OFLAG_COPIED);
     }
 
-    qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
-
    nb_available = (c * s->cluster_sectors);
 out:
     if (nb_available > nb_needed)
@@ -498,7 +542,7 @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset,
 
     l1_index = offset >> (s->l2_bits + s->cluster_bits);
     if (l1_index >= s->l1_size) {
-        ret = qcow2_grow_l1_table(bs, l1_index + 1, false);
+        ret = qcow2_grow_l1_table(bs, l1_index + 1);
         if (ret < 0) {
             return ret;
         }
@@ -515,16 +559,12 @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset,
             return ret;
         }
     } else {
-        /* First allocate a new L2 table (and do COW if needed) */
+        if (l2_offset)
+            qcow2_free_clusters(bs, l2_offset, s->l2_size * sizeof(uint64_t));
         ret = l2_allocate(bs, l1_index, &l2_table);
         if (ret < 0) {
             return ret;
         }
-
-        /* Then decrease the refcount of the old table */
-        if (l2_offset) {
-            qcow2_free_clusters(bs, l2_offset, s->l2_size * sizeof(uint64_t));
-        }
         l2_offset = s->l1_table[l1_index] & ~QCOW_OFLAG_COPIED;
     }
 
@@ -568,17 +608,14 @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
     }
 
     cluster_offset = be64_to_cpu(l2_table[l2_index]);
-    if (cluster_offset & QCOW_OFLAG_COPIED) {
-        qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
-        return 0;
-    }
+    if (cluster_offset & QCOW_OFLAG_COPIED)
+        return cluster_offset & ~QCOW_OFLAG_COPIED;
 
     if (cluster_offset)
         qcow2_free_any_clusters(bs, cluster_offset, 1);
 
     cluster_offset = qcow2_alloc_bytes(bs, compressed_size);
     if (cluster_offset < 0) {
-        qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
         return 0;
     }
 
@@ -593,33 +630,55 @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
     /* compressed clusters never have the copied flag */
 
     BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE_COMPRESSED);
-    qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
     l2_table[l2_index] = cpu_to_be64(cluster_offset);
-    ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
-    if (ret < 0) {
+    if (bdrv_pwrite_sync(bs->file,
+                    l2_offset + l2_index * sizeof(uint64_t),
+                    l2_table + l2_index,
+                    sizeof(uint64_t)) < 0)
         return 0;
-    }
 
     return cluster_offset;
 }
 
+/*
+ * Write L2 table updates to disk, writing whole sectors to avoid a
+ * read-modify-write in bdrv_pwrite
+ */
+#define L2_ENTRIES_PER_SECTOR (512 / 8)
+static int write_l2_entries(BlockDriverState *bs, uint64_t *l2_table,
+    uint64_t l2_offset, int l2_index, int num)
+{
+    int l2_start_index = l2_index & ~(L1_ENTRIES_PER_SECTOR - 1);
+    int start_offset = (8 * l2_index) & ~511;
+    int end_offset = (8 * (l2_index + num) + 511) & ~511;
+    size_t len = end_offset - start_offset;
+    int ret;
+
+    BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE);
+    ret = bdrv_pwrite(bs->file, l2_offset + start_offset,
+        &l2_table[l2_start_index], len);
+    if (ret < 0) {
+        return ret;
+    }
+
+    return 0;
+}
+
 int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
 {
     BDRVQcowState *s = bs->opaque;
     int i, j = 0, l2_index, ret;
     uint64_t *old_cluster, start_sect, l2_offset, *l2_table;
     uint64_t cluster_offset = m->cluster_offset;
-    bool cow = false;
 
     if (m->nb_clusters == 0)
         return 0;
 
-    old_cluster = g_malloc(m->nb_clusters * sizeof(uint64_t));
+    old_cluster = qemu_malloc(m->nb_clusters * sizeof(uint64_t));
 
     /* copy content of unmodified sectors */
     start_sect = (m->offset & ~(s->cluster_size - 1)) >> 9;
     if (m->n_start) {
-        cow = true;
         ret = copy_sectors(bs, start_sect, cluster_offset, 0, m->n_start);
         if (ret < 0)
             goto err;
@@ -627,30 +686,17 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
 
     if (m->nb_available & (s->cluster_sectors - 1)) {
         uint64_t end = m->nb_available & ~(uint64_t)(s->cluster_sectors - 1);
-        cow = true;
         ret = copy_sectors(bs, start_sect + end, cluster_offset + (end << 9),
                 m->nb_available - end, s->cluster_sectors);
         if (ret < 0)
             goto err;
     }
 
-    /*
-     * Update L2 table.
-     *
-     * Before we update the L2 table to actually point to the new cluster, we
-     * need to be sure that the refcounts have been increased and COW was
-     * handled.
-     */
-    if (cow) {
-        qcow2_cache_depends_on_flush(s->l2_table_cache);
-    }
-
-    qcow2_cache_set_dependency(bs, s->l2_table_cache, s->refcount_block_cache);
+    /* update L2 table */
     ret = get_cluster_table(bs, m->offset, &l2_table, &l2_offset, &l2_index);
     if (ret < 0) {
         goto err;
     }
-    qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
 
     for (i = 0; i < m->nb_clusters; i++) {
         /* if two concurrent writes happen to the same unallocated cluster
@@ -666,9 +712,9 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
                     (i << s->cluster_bits)) | QCOW_OFLAG_COPIED);
      }
 
-
-    ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+    ret = write_l2_entries(bs, l2_table, l2_offset, l2_index, m->nb_clusters);
     if (ret < 0) {
+        qcow2_l2_cache_reset(bs);
         goto err;
     }
 
@@ -677,6 +723,7 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
      * Also flush bs->file to get the right order for L2 and refcount update.
      */
     if (j != 0) {
+        bdrv_flush(bs->file);
         for (i = 0; i < j; i++) {
             qcow2_free_any_clusters(bs,
                 be64_to_cpu(old_cluster[i]) & ~QCOW_OFLAG_COPIED, 1);
@@ -685,7 +732,7 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
 
     ret = 0;
 err:
-    g_free(old_cluster);
+    qemu_free(old_cluster);
     return ret;
  }
 
@@ -696,15 +743,15 @@ err:
  * If the offset is not found, allocate a new cluster.
  *
  * If the cluster was already allocated, m->nb_clusters is set to 0,
- * other fields in m are meaningless.
+ * m->depends_on is set to NULL and the other fields in m are meaningless.
  *
  * If the cluster is newly allocated, m->nb_clusters is set to the number of
- * contiguous clusters that have been allocated. In this case, the other
- * fields of m are valid and contain information about the first allocated
- * cluster.
+ * contiguous clusters that have been allocated. This may be 0 if the request
+ * conflict with another write request in flight; in this case, m->depends_on
+ * is set and the remaining fields of m are meaningless.
  *
- * If the request conflicts with another write request in flight, the coroutine
- * is queued and will be reentered when the dependency has completed.
+ * If m->nb_clusters is non-zero, the other fields of m are valid and contain
+ * information about the first allocated cluster.
  *
  * Return 0 on success and -errno in error cases
  */
@@ -723,7 +770,6 @@ int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
         return ret;
     }
 
-again:
     nb_clusters = size_to_clusters(s, n_end << 9);
 
     nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
@@ -738,6 +784,7 @@ again:
 
         cluster_offset &= ~QCOW_OFLAG_COPIED;
         m->nb_clusters = 0;
+        m->depends_on = NULL;
 
         goto out;
     }
@@ -778,28 +825,27 @@ again:
      */
     QLIST_FOREACH(old_alloc, &s->cluster_allocs, next_in_flight) {
 
-        uint64_t start = offset >> s->cluster_bits;
-        uint64_t end = start + nb_clusters;
-        uint64_t old_start = old_alloc->offset >> s->cluster_bits;
-        uint64_t old_end = old_start + old_alloc->nb_clusters;
+        uint64_t end_offset = offset + nb_clusters * s->cluster_size;
+        uint64_t old_offset = old_alloc->offset;
+        uint64_t old_end_offset = old_alloc->offset +
+            old_alloc->nb_clusters * s->cluster_size;
 
-        if (end < old_start || start > old_end) {
+        if (end_offset < old_offset || offset > old_end_offset) {
             /* No intersection */
         } else {
-            if (start < old_start) {
+            if (offset < old_offset) {
                 /* Stop at the start of a running allocation */
-                nb_clusters = old_start - start;
+                nb_clusters = (old_offset - offset) >> s->cluster_bits;
             } else {
                 nb_clusters = 0;
             }
 
             if (nb_clusters == 0) {
-                /* Wait for the dependency to complete. We need to recheck
-                 * the free/allocated clusters when we continue. */
-                qemu_co_mutex_unlock(&s->lock);
-                qemu_co_queue_wait(&old_alloc->dependent_requests);
-                qemu_co_mutex_lock(&s->lock);
-                goto again;
+                /* Set dependency and wait for a callback */
+                m->depends_on = old_alloc;
+                m->nb_clusters = 0;
+                *num = 0;
+                return 0;
             }
         }
     }
@@ -808,39 +854,28 @@ again:
         abort();
     }
 
-    /* save info needed for meta data update */
-    m->offset = offset;
-    m->n_start = n_start;
-    m->nb_clusters = nb_clusters;
-
     QLIST_INSERT_HEAD(&s->cluster_allocs, m, next_in_flight);
 
     /* allocate a new cluster */
 
     cluster_offset = qcow2_alloc_clusters(bs, nb_clusters * s->cluster_size);
     if (cluster_offset < 0) {
-        ret = cluster_offset;
-        goto fail;
+        QLIST_REMOVE(m, next_in_flight);
+        return cluster_offset;
     }
 
+    /* save info needed for meta data update */
+    m->offset = offset;
+    m->n_start = n_start;
+    m->nb_clusters = nb_clusters;
+
 out:
-    ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
-    if (ret < 0) {
-        goto fail_put;
-    }
-
     m->nb_available = MIN(nb_clusters << (s->cluster_bits - 9), n_end);
     m->cluster_offset = cluster_offset;
 
     *num = m->nb_available - n_start;
 
     return 0;
-
-fail:
-    qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
-fail_put:
-    QLIST_REMOVE(m, next_in_flight);
-    return ret;
 }
 
 static int decompress_buffer(uint8_t *out_buf, int out_buf_size,
@@ -884,95 +919,13 @@ int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
         BLKDBG_EVENT(bs->file, BLKDBG_READ_COMPRESSED);
         ret = bdrv_read(bs->file, coffset >> 9, s->cluster_data, nb_csectors);
         if (ret < 0) {
-            return ret;
+            return -1;
         }
         if (decompress_buffer(s->cluster_cache, s->cluster_size,
                               s->cluster_data + sector_offset, csize) < 0) {
-            return -EIO;
+            return -1;
         }
         s->cluster_cache_offset = coffset;
     }
     return 0;
 }
-
-/*
- * This discards as many clusters of nb_clusters as possible at once (i.e.
- * all clusters in the same L2 table) and returns the number of discarded
- * clusters.
- */
-static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
-    unsigned int nb_clusters)
-{
-    BDRVQcowState *s = bs->opaque;
-    uint64_t l2_offset, *l2_table;
-    int l2_index;
-    int ret;
-    int i;
-
-    ret = get_cluster_table(bs, offset, &l2_table, &l2_offset, &l2_index);
-    if (ret < 0) {
-        return ret;
-    }
-
-    /* Limit nb_clusters to one L2 table */
-    nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
-
-    for (i = 0; i < nb_clusters; i++) {
-        uint64_t old_offset;
-
-        old_offset = be64_to_cpu(l2_table[l2_index + i]);
-        old_offset &= ~QCOW_OFLAG_COPIED;
-
-        if (old_offset == 0) {
-            continue;
-        }
-
-        /* First remove L2 entries */
-        qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
-        l2_table[l2_index + i] = cpu_to_be64(0);
-
-        /* Then decrease the refcount */
-        qcow2_free_any_clusters(bs, old_offset, 1);
-    }
-
-    ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
-    if (ret < 0) {
-        return ret;
-    }
-
-    return nb_clusters;
-}
-
-int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
-    int nb_sectors)
-{
-    BDRVQcowState *s = bs->opaque;
-    uint64_t end_offset;
-    unsigned int nb_clusters;
-    int ret;
-
-    end_offset = offset + (nb_sectors << BDRV_SECTOR_BITS);
-
-    /* Round start up and end down */
-    offset = align_offset(offset, s->cluster_size);
-    end_offset &= ~(s->cluster_size - 1);
-
-    if (offset > end_offset) {
-        return 0;
-    }
-
-    nb_clusters = size_to_clusters(s, end_offset - offset);
-
-    /* Each L2 table is handled by its own loop iteration */
-    while (nb_clusters > 0) {
-        ret = discard_single_l2(bs, offset, nb_clusters);
-        if (ret < 0) {
-            return ret;
-        }
-
-        nb_clusters -= ret;
-        offset += (ret * s->cluster_size);
-    }
-
-    return 0;
-}

block/qcow2-refcount.c

@@ -32,6 +32,27 @@ static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
                             int addend);
 
 
+static int cache_refcount_updates = 0;
+
+static int write_refcount_block(BlockDriverState *bs)
+{
+    BDRVQcowState *s = bs->opaque;
+    size_t size = s->cluster_size;
+
+    if (s->refcount_block_cache_offset == 0) {
+        return 0;
+    }
+
+    BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_UPDATE);
+    if (bdrv_pwrite_sync(bs->file, s->refcount_block_cache_offset,
+            s->refcount_block_cache, size) < 0)
+    {
+        return -EIO;
+    }
+
+    return 0;
+}
+
 /*********************************************************/
 /* refcount handling */
 
@@ -40,8 +61,9 @@ int qcow2_refcount_init(BlockDriverState *bs)
     BDRVQcowState *s = bs->opaque;
     int ret, refcount_table_size2, i;
 
+    s->refcount_block_cache = qemu_malloc(s->cluster_size);
     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,
@@ -59,22 +81,33 @@ 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_block_cache);
+    qemu_free(s->refcount_table);
 }
 
 
 static int load_refcount_block(BlockDriverState *bs,
-                               int64_t refcount_block_offset,
-                               void **refcount_block)
+                               int64_t refcount_block_offset)
 {
     BDRVQcowState *s = bs->opaque;
     int ret;
 
-    BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_LOAD);
-    ret = qcow2_cache_get(bs, s->refcount_block_cache, refcount_block_offset,
-        refcount_block);
+    if (cache_refcount_updates) {
+        ret = write_refcount_block(bs);
+        if (ret < 0) {
+            return ret;
+        }
+    }
 
-    return ret;
+    BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_LOAD);
+    ret = bdrv_pread(bs->file, refcount_block_offset, s->refcount_block_cache,
+                     s->cluster_size);
+    if (ret < 0) {
+        return ret;
+    }
+
+    s->refcount_block_cache_offset = refcount_block_offset;
+    return 0;
 }
 
 /*
@@ -88,8 +121,6 @@ static int get_refcount(BlockDriverState *bs, int64_t cluster_index)
     int refcount_table_index, block_index;
     int64_t refcount_block_offset;
     int ret;
-    uint16_t *refcount_block;
-    uint16_t refcount;
 
     refcount_table_index = cluster_index >> (s->cluster_bits - REFCOUNT_SHIFT);
     if (refcount_table_index >= s->refcount_table_size)
@@ -97,24 +128,16 @@ static int get_refcount(BlockDriverState *bs, int64_t cluster_index)
     refcount_block_offset = s->refcount_table[refcount_table_index];
     if (!refcount_block_offset)
         return 0;
-
-    ret = qcow2_cache_get(bs, s->refcount_block_cache, refcount_block_offset,
-        (void**) &refcount_block);
-    if (ret < 0) {
-        return ret;
+    if (refcount_block_offset != s->refcount_block_cache_offset) {
+        /* better than nothing: return allocated if read error */
+        ret = load_refcount_block(bs, refcount_block_offset);
+        if (ret < 0) {
+            return ret;
+        }
     }
-
     block_index = cluster_index &
         ((1 << (s->cluster_bits - REFCOUNT_SHIFT)) - 1);
-    refcount = be16_to_cpu(refcount_block[block_index]);
-
-    ret = qcow2_cache_put(bs, s->refcount_block_cache,
-        (void**) &refcount_block);
-    if (ret < 0) {
-        return ret;
-    }
-
-    return refcount;
+    return be16_to_cpu(s->refcount_block_cache[block_index]);
 }
 
 /*
@@ -150,10 +173,9 @@ static int in_same_refcount_block(BDRVQcowState *s, uint64_t offset_a,
  * Loads a refcount block. If it doesn't exist yet, it is allocated first
  * (including growing the refcount table if needed).
  *
- * Returns 0 on success or -errno in error case
+ * Returns the offset of the refcount block on success or -errno in error case
  */
-static int alloc_refcount_block(BlockDriverState *bs,
-    int64_t cluster_index, uint16_t **refcount_block)
+static int64_t alloc_refcount_block(BlockDriverState *bs, int64_t cluster_index)
 {
     BDRVQcowState *s = bs->opaque;
     unsigned int refcount_table_index;
@@ -171,8 +193,13 @@ static int alloc_refcount_block(BlockDriverState *bs,
 
         /* If it's already there, we're done */
         if (refcount_block_offset) {
-             return load_refcount_block(bs, refcount_block_offset,
-                 (void**) refcount_block);
+            if (refcount_block_offset != s->refcount_block_cache_offset) {
+                ret = load_refcount_block(bs, refcount_block_offset);
+                if (ret < 0) {
+                    return ret;
+                }
+            }
+            return refcount_block_offset;
         }
     }
 
@@ -198,10 +225,12 @@ static int alloc_refcount_block(BlockDriverState *bs,
      *   refcount block into the cache
      */
 
-    *refcount_block = NULL;
-
-    /* We write to the refcount table, so we might depend on L2 tables */
-    qcow2_cache_flush(bs, s->l2_table_cache);
+    if (cache_refcount_updates) {
+        ret = write_refcount_block(bs);
+        if (ret < 0) {
+            return ret;
+        }
+    }
 
     /* Allocate the refcount block itself and mark it as used */
     int64_t new_block = alloc_clusters_noref(bs, s->cluster_size);
@@ -217,18 +246,13 @@ static int alloc_refcount_block(BlockDriverState *bs,
 
     if (in_same_refcount_block(s, new_block, cluster_index << s->cluster_bits)) {
         /* Zero the new refcount block before updating it */
-        ret = qcow2_cache_get_empty(bs, s->refcount_block_cache, new_block,
-            (void**) refcount_block);
-        if (ret < 0) {
-            goto fail_block;
-        }
-
-        memset(*refcount_block, 0, s->cluster_size);
+        memset(s->refcount_block_cache, 0, s->cluster_size);
+        s->refcount_block_cache_offset = new_block;
 
         /* The block describes itself, need to update the cache */
         int block_index = (new_block >> s->cluster_bits) &
             ((1 << (s->cluster_bits - REFCOUNT_SHIFT)) - 1);
-        (*refcount_block)[block_index] = cpu_to_be16(1);
+        s->refcount_block_cache[block_index] = cpu_to_be16(1);
     } else {
         /* Described somewhere else. This can recurse at most twice before we
          * arrive at a block that describes itself. */
@@ -237,23 +261,16 @@ static int alloc_refcount_block(BlockDriverState *bs,
             goto fail_block;
         }
 
-        bdrv_flush(bs->file);
-
         /* Initialize the new refcount block only after updating its refcount,
          * update_refcount uses the refcount cache itself */
-        ret = qcow2_cache_get_empty(bs, s->refcount_block_cache, new_block,
-            (void**) refcount_block);
-        if (ret < 0) {
-            goto fail_block;
-        }
-
-        memset(*refcount_block, 0, s->cluster_size);
+        memset(s->refcount_block_cache, 0, s->cluster_size);
+        s->refcount_block_cache_offset = new_block;
     }
 
     /* Now the new refcount block needs to be written to disk */
     BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_WRITE);
-    qcow2_cache_entry_mark_dirty(s->refcount_block_cache, *refcount_block);
-    ret = qcow2_cache_flush(bs, s->refcount_block_cache);
+    ret = bdrv_pwrite_sync(bs->file, new_block, s->refcount_block_cache,
+        s->cluster_size);
     if (ret < 0) {
         goto fail_block;
     }
@@ -270,12 +287,7 @@ static int alloc_refcount_block(BlockDriverState *bs,
         }
 
         s->refcount_table[refcount_table_index] = new_block;
-        return 0;
-    }
-
-    ret = qcow2_cache_put(bs, s->refcount_block_cache, (void**) refcount_block);
-    if (ret < 0) {
-        goto fail_block;
+        return new_block;
     }
 
     /*
@@ -323,8 +335,8 @@ 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));
 
@@ -349,7 +361,7 @@ 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;
     }
@@ -385,7 +397,7 @@ 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;
@@ -395,34 +407,66 @@ static int alloc_refcount_block(BlockDriverState *bs,
     qcow2_free_clusters(bs, old_table_offset, old_table_size * sizeof(uint64_t));
     s->free_cluster_index = old_free_cluster_index;
 
-    ret = load_refcount_block(bs, new_block, (void**) refcount_block);
+    ret = load_refcount_block(bs, new_block);
     if (ret < 0) {
-        return ret;
+        goto fail_block;
     }
 
     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);
-    }
+    s->refcount_block_cache_offset = 0;
     return ret;
 }
 
+#define REFCOUNTS_PER_SECTOR (512 >> REFCOUNT_SHIFT)
+static int write_refcount_block_entries(BlockDriverState *bs,
+    int64_t refcount_block_offset, int first_index, int last_index)
+{
+    BDRVQcowState *s = bs->opaque;
+    size_t size;
+    int ret;
+
+    if (cache_refcount_updates) {
+        return 0;
+    }
+
+    if (first_index < 0) {
+        return 0;
+    }
+
+    first_index &= ~(REFCOUNTS_PER_SECTOR - 1);
+    last_index = (last_index + REFCOUNTS_PER_SECTOR)
+        & ~(REFCOUNTS_PER_SECTOR - 1);
+
+    size = (last_index - first_index) << REFCOUNT_SHIFT;
+
+    BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_UPDATE_PART);
+    ret = bdrv_pwrite_sync(bs->file,
+        refcount_block_offset + (first_index << REFCOUNT_SHIFT),
+        &s->refcount_block_cache[first_index], size);
+    if (ret < 0) {
+        return ret;
+    }
+
+    return 0;
+}
+
 /* XXX: cache several refcount block clusters ? */
 static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
     int64_t offset, int64_t length, int addend)
 {
     BDRVQcowState *s = bs->opaque;
     int64_t start, last, cluster_offset;
-    uint16_t *refcount_block = NULL;
-    int64_t old_table_index = -1;
+    int64_t refcount_block_offset = 0;
+    int64_t table_index = -1, old_table_index;
+    int first_index = -1, last_index = -1;
     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) {
@@ -431,11 +475,6 @@ static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
         return 0;
     }
 
-    if (addend < 0) {
-        qcow2_cache_set_dependency(bs, s->refcount_block_cache,
-            s->l2_table_cache);
-    }
-
     start = offset & ~(s->cluster_size - 1);
     last = (offset + length - 1) & ~(s->cluster_size - 1);
     for(cluster_offset = start; cluster_offset <= last;
@@ -443,33 +482,42 @@ static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
     {
         int block_index, refcount;
         int64_t cluster_index = cluster_offset >> s->cluster_bits;
-        int64_t table_index =
-            cluster_index >> (s->cluster_bits - REFCOUNT_SHIFT);
+        int64_t new_block;
+
+        /* Only write refcount block to disk when we are done with it */
+        old_table_index = table_index;
+        table_index = cluster_index >> (s->cluster_bits - REFCOUNT_SHIFT);
+        if ((old_table_index >= 0) && (table_index != old_table_index)) {
+
+            ret = write_refcount_block_entries(bs, refcount_block_offset,
+                first_index, last_index);
+            if (ret < 0) {
+                return ret;
+            }
+
+            first_index = -1;
+            last_index = -1;
+        }
 
         /* Load the refcount block and allocate it if needed */
-        if (table_index != old_table_index) {
-            if (refcount_block) {
-                ret = qcow2_cache_put(bs, s->refcount_block_cache,
-                    (void**) &refcount_block);
-                if (ret < 0) {
-                    goto fail;
-                }
-            }
-
-            ret = alloc_refcount_block(bs, cluster_index, &refcount_block);
-            if (ret < 0) {
-                goto fail;
-            }
+        new_block = alloc_refcount_block(bs, cluster_index);
+        if (new_block < 0) {
+            ret = new_block;
+            goto fail;
         }
-        old_table_index = table_index;
-
-        qcow2_cache_entry_mark_dirty(s->refcount_block_cache, refcount_block);
+        refcount_block_offset = new_block;
 
         /* we can update the count and save it */
         block_index = cluster_index &
             ((1 << (s->cluster_bits - REFCOUNT_SHIFT)) - 1);
+        if (first_index == -1 || block_index < first_index) {
+            first_index = block_index;
+        }
+        if (block_index > last_index) {
+            last_index = block_index;
+        }
 
-        refcount = be16_to_cpu(refcount_block[block_index]);
+        refcount = be16_to_cpu(s->refcount_block_cache[block_index]);
         refcount += addend;
         if (refcount < 0 || refcount > 0xffff) {
             ret = -EINVAL;
@@ -478,16 +526,17 @@ static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
         if (refcount == 0 && cluster_index < s->free_cluster_index) {
             s->free_cluster_index = cluster_index;
         }
-        refcount_block[block_index] = cpu_to_be16(refcount);
+        s->refcount_block_cache[block_index] = cpu_to_be16(refcount);
     }
 
     ret = 0;
 fail:
+
     /* Write last changed block to disk */
-    if (refcount_block) {
+    if (refcount_block_offset != 0) {
         int wret;
-        wret = qcow2_cache_put(bs, s->refcount_block_cache,
-            (void**) &refcount_block);
+        wret = write_refcount_block_entries(bs, refcount_block_offset,
+            first_index, last_index);
         if (wret < 0) {
             return ret < 0 ? ret : wret;
         }
@@ -500,7 +549,6 @@ fail:
     if (ret < 0) {
         int dummy;
         dummy = update_refcount(bs, offset, cluster_offset - offset, -addend);
-        (void)dummy;
     }
 
     return ret;
@@ -525,8 +573,6 @@ static int update_cluster_refcount(BlockDriverState *bs,
         return ret;
     }
 
-    bdrv_flush(bs->file);
-
     return get_refcount(bs, cluster_index);
 }
 
@@ -556,7 +602,7 @@ 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
@@ -578,7 +624,6 @@ int64_t qcow2_alloc_clusters(BlockDriverState *bs, int64_t size)
     if (ret < 0) {
         return ret;
     }
-
     return offset;
 }
 
@@ -626,8 +671,6 @@ int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size)
             goto redo;
         }
     }
-
-    bdrv_flush(bs->file);
     return offset;
 }
 
@@ -680,6 +723,24 @@ 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)
@@ -687,33 +748,24 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
     BDRVQcowState *s = bs->opaque;
     uint64_t *l1_table, *l2_table, l2_offset, offset, l1_size2, l1_allocated;
     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;
+    int l2_size, i, j, l1_modified, l2_modified, nb_csectors, refcount;
 
-    /* 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);
+    qcow2_l2_cache_reset(bs);
+    cache_refcount_updates = 1;
 
     l2_table = NULL;
     l1_table = NULL;
     l1_size2 = l1_size * sizeof(uint64_t);
     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;
         }
         l1_allocated = 1;
         if (bdrv_pread(bs->file, l1_table_offset,
                        l1_table, l1_size2) != l1_size2)
-        {
-            ret = -EIO;
             goto fail;
-        }
-
         for(i = 0;i < l1_size; i++)
             be64_to_cpus(&l1_table[i]);
     } else {
@@ -722,18 +774,17 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
         l1_allocated = 0;
     }
 
+    l2_size = s->l2_size * sizeof(uint64_t);
+    l2_table = qemu_malloc(l2_size);
+    l1_modified = 0;
     for(i = 0; i < l1_size; i++) {
         l2_offset = l1_table[i];
         if (l2_offset) {
             old_l2_offset = l2_offset;
             l2_offset &= ~QCOW_OFLAG_COPIED;
-
-            ret = qcow2_cache_get(bs, s->l2_table_cache, l2_offset,
-                (void**) &l2_table);
-            if (ret < 0) {
+            l2_modified = 0;
+            if (bdrv_pread(bs->file, l2_offset, l2_table, l2_size) != l2_size)
                 goto fail;
-            }
-
             for(j = 0; j < s->l2_size; j++) {
                 offset = be64_to_cpu(l2_table[j]);
                 if (offset != 0) {
@@ -750,10 +801,6 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
                             if (ret < 0) {
                                 goto fail;
                             }
-
-                            /* TODO Flushing once for the whole function should
-                             * be enough */
-                            bdrv_flush(bs->file);
                         }
                         /* compressed clusters are never modified */
                         refcount = 2;
@@ -765,7 +812,6 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
                         }
 
                         if (refcount < 0) {
-                            ret = -EIO;
                             goto fail;
                         }
                     }
@@ -774,29 +820,23 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
                         offset |= QCOW_OFLAG_COPIED;
                     }
                     if (offset != old_offset) {
-                        if (addend > 0) {
-                            qcow2_cache_set_dependency(bs, s->l2_table_cache,
-                                s->refcount_block_cache);
-                        }
                         l2_table[j] = cpu_to_be64(offset);
-                        qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
+                        l2_modified = 1;
                     }
                 }
             }
-
-            ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
-            if (ret < 0) {
-                goto fail;
+            if (l2_modified) {
+                if (bdrv_pwrite_sync(bs->file,
+                                l2_offset, l2_table, l2_size) < 0)
+                    goto fail;
             }
 
-
             if (addend != 0) {
                 refcount = update_cluster_refcount(bs, l2_offset >> s->cluster_bits, addend);
             } else {
                 refcount = get_refcount(bs, l2_offset >> s->cluster_bits);
             }
             if (refcount < 0) {
-                ret = -EIO;
                 goto fail;
             } else if (refcount == 1) {
                 l2_offset |= QCOW_OFLAG_COPIED;
@@ -807,18 +847,6 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
             }
         }
     }
-
-    ret = 0;
-fail:
-    if (l2_table) {
-        qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
-    }
-
-    /* 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]);
@@ -829,8 +857,18 @@ fail:
             be64_to_cpus(&l1_table[i]);
     }
     if (l1_allocated)
-        g_free(l1_table);
-    return ret;
+        qemu_free(l1_table);
+    qemu_free(l2_table);
+    cache_refcount_updates = 0;
+    write_refcount_block(bs);
+    return 0;
+ fail:
+    if (l1_allocated)
+        qemu_free(l1_table);
+    qemu_free(l2_table);
+    cache_refcount_updates = 0;
+    write_refcount_block(bs);
+    return -EIO;
 }
 
 
@@ -903,7 +941,7 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res,
 
     /* 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;
@@ -961,12 +999,12 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res,
         }
     }
 
-    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;
 }
 
@@ -999,7 +1037,7 @@ 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;
@@ -1047,13 +1085,13 @@ 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;
 }
 
@@ -1061,7 +1099,7 @@ fail:
  * Checks an image for refcount consistency.
  *
  * 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.
+ * detected as corrupted, and -errno when an internal error occured.
  */
 int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res)
 {
@@ -1074,7 +1112,7 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res)
 
     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,
@@ -1084,7 +1122,7 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res)
     ret = check_refcounts_l1(bs, res, refcount_table, nb_clusters,
                        s->l1_table_offset, s->l1_size, 1);
     if (ret < 0) {
-        goto fail;
+        return ret;
     }
 
     /* snapshots */
@@ -1093,7 +1131,7 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res)
         ret = check_refcounts_l1(bs, res, refcount_table, nb_clusters,
             sn->l1_table_offset, sn->l1_size, 0);
         if (ret < 0) {
-            goto fail;
+            return ret;
         }
     }
     inc_refcounts(bs, res, refcount_table, nb_clusters,
@@ -1157,11 +1195,8 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res)
         }
     }
 
-    ret = 0;
+    qemu_free(refcount_table);
 
-fail:
-    g_free(refcount_table);
-
-    return ret;
+    return 0;
 }
 

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;
 
@@ -52,10 +52,10 @@ void qcow2_free_snapshots(BlockDriverState *bs)
     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;
 }
@@ -76,7 +76,7 @@ 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++) {
         offset = align_offset(offset, 8);
         if (bdrv_pread(bs->file, offset, &h, sizeof(h)) != sizeof(h))
@@ -96,13 +96,13 @@ int qcow2_read_snapshots(BlockDriverState *bs)
 
         offset += extra_data_size;
 
-        sn->id_str = g_malloc(id_str_size + 1);
+        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';
 
-        sn->name = g_malloc(name_size + 1);
+        sn->name = qemu_malloc(name_size + 1);
         if (bdrv_pread(bs->file, offset, sn->name, name_size) != name_size)
             goto fail;
         offset += name_size;
@@ -116,7 +116,7 @@ int qcow2_read_snapshots(BlockDriverState *bs)
 }
 
 /* add at the end of the file a new list of snapshots */
-static int qcow2_write_snapshots(BlockDriverState *bs)
+static int qcow_write_snapshots(BlockDriverState *bs)
 {
     BDRVQcowState *s = bs->opaque;
     QCowSnapshot *sn;
@@ -138,7 +138,6 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
     snapshots_size = offset;
 
     snapshots_offset = qcow2_alloc_clusters(bs, snapshots_size);
-    bdrv_flush(bs->file);
     offset = snapshots_offset;
     if (offset < 0) {
         return offset;
@@ -252,10 +251,10 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
     if (find_snapshot_by_id(bs, sn_info->id_str) >= 0)
         return -ENOENT;
 
-    sn->id_str = g_strdup(sn_info->id_str);
+    sn->id_str = qemu_strdup(sn_info->id_str);
     if (!sn->id_str)
         goto fail;
-    sn->name = g_strdup(sn_info->name);
+    sn->name = qemu_strdup(sn_info->name);
     if (!sn->name)
         goto fail;
     sn->vm_state_size = sn_info->vm_state_size;
@@ -272,13 +271,12 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
     if (l1_table_offset < 0) {
         goto fail;
     }
-    bdrv_flush(bs->file);
 
     sn->l1_table_offset = l1_table_offset;
     sn->l1_size = s->l1_size;
 
     if (s->l1_size != 0) {
-        l1_table = g_malloc(s->l1_size * sizeof(uint64_t));
+        l1_table = qemu_malloc(s->l1_size * sizeof(uint64_t));
     } else {
         l1_table = NULL;
     }
@@ -289,29 +287,26 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
     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;
 
-    snapshots1 = g_malloc((s->nb_snapshots + 1) * sizeof(QCowSnapshot));
+    snapshots1 = qemu_malloc((s->nb_snapshots + 1) * sizeof(QCowSnapshot));
     if (s->snapshots) {
         memcpy(snapshots1, s->snapshots, s->nb_snapshots * sizeof(QCowSnapshot));
-        g_free(s->snapshots);
+        qemu_free(s->snapshots);
     }
     s->snapshots = snapshots1;
     s->snapshots[s->nb_snapshots++] = *sn;
 
-    if (qcow2_write_snapshots(bs) < 0)
+    if (qcow_write_snapshots(bs) < 0)
         goto fail;
 #ifdef DEBUG_ALLOC
-    {
-      BdrvCheckResult result = {0};
-      qcow2_check_refcounts(bs, &result);
-    }
+    qcow2_check_refcounts(bs);
 #endif
     return 0;
  fail:
-    g_free(sn->name);
-    g_free(l1_table);
+    qemu_free(sn->name);
+    qemu_free(l1_table);
     return -1;
 }
 
@@ -320,8 +315,7 @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
 {
     BDRVQcowState *s = bs->opaque;
     QCowSnapshot *sn;
-    int i, snapshot_index;
-    int cur_l1_bytes, sn_l1_bytes;
+    int i, snapshot_index, l1_size2;
 
     snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_id);
     if (snapshot_index < 0)
@@ -331,22 +325,17 @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
     if (qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, -1) < 0)
         goto fail;
 
-    if (qcow2_grow_l1_table(bs, sn->l1_size, true) < 0)
+    if (qcow2_grow_l1_table(bs, sn->l1_size) < 0)
         goto fail;
 
-    cur_l1_bytes = s->l1_size * sizeof(uint64_t);
-    sn_l1_bytes = sn->l1_size * sizeof(uint64_t);
-
-    if (cur_l1_bytes > sn_l1_bytes) {
-        memset(s->l1_table + sn->l1_size, 0, cur_l1_bytes - sn_l1_bytes);
-    }
-
+    s->l1_size = sn->l1_size;
+    l1_size2 = s->l1_size * sizeof(uint64_t);
     /* 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)
+                   s->l1_table, l1_size2) != l1_size2)
         goto fail;
     if (bdrv_pwrite_sync(bs->file, s->l1_table_offset,
-                    s->l1_table, cur_l1_bytes) < 0)
+                    s->l1_table, l1_size2) < 0)
         goto fail;
     for(i = 0;i < s->l1_size; i++) {
         be64_to_cpus(&s->l1_table[i]);
@@ -356,10 +345,7 @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
         goto fail;
 
 #ifdef DEBUG_ALLOC
-    {
-        BdrvCheckResult result = {0};
-        qcow2_check_refcounts(bs, &result);
-    }
+    qcow2_check_refcounts(bs);
 #endif
     return 0;
  fail:
@@ -386,20 +372,17 @@ int qcow2_snapshot_delete(BlockDriverState *bs, const char *snapshot_id)
         return ret;
     qcow2_free_clusters(bs, sn->l1_table_offset, sn->l1_size * sizeof(uint64_t));
 
-    g_free(sn->id_str);
-    g_free(sn->name);
+    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);
+    ret = qcow_write_snapshots(bs);
     if (ret < 0) {
         /* XXX: restore snapshot if error ? */
         return ret;
     }
 #ifdef DEBUG_ALLOC
-    {
-        BdrvCheckResult result = {0};
-        qcow2_check_refcounts(bs, &result);
-    }
+    qcow2_check_refcounts(bs);
 #endif
     return 0;
 }
@@ -416,7 +399,7 @@ 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;
@@ -433,34 +416,3 @@ int qcow2_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
     return s->nb_snapshots;
 }
 
-int qcow2_snapshot_load_tmp(BlockDriverState *bs, const char *snapshot_name)
-{
-    int i, snapshot_index, l1_size2;
-    BDRVQcowState *s = bs->opaque;
-    QCowSnapshot *sn;
-
-    snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_name);
-    if (snapshot_index < 0) {
-        return -ENOENT;
-    }
-
-    sn = &s->snapshots[snapshot_index];
-    s->l1_size = sn->l1_size;
-    l1_size2 = s->l1_size * sizeof(uint64_t);
-    if (s->l1_table != NULL) {
-        g_free(s->l1_table);
-    }
-
-    s->l1_table_offset = sn->l1_table_offset;
-    s->l1_table = g_malloc0(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

@@ -26,7 +26,6 @@
 #define BLOCK_QCOW2_H
 
 #include "aes.h"
-#include "qemu-coroutine.h"
 
 //#define DEBUG_ALLOC
 //#define DEBUG_ALLOC2
@@ -52,11 +51,6 @@
 
 #define L2_CACHE_SIZE 16
 
-/* Must be at least 4 to cover all cases of refcount table growth */
-#define REFCOUNT_CACHE_SIZE 4
-
-#define DEFAULT_CLUSTER_SIZE 65536
-
 typedef struct QCowHeader {
     uint32_t magic;
     uint32_t version;
@@ -84,10 +78,8 @@ typedef struct QCowSnapshot {
     uint64_t vm_clock_nsec;
 } QCowSnapshot;
 
-struct Qcow2Cache;
-typedef struct Qcow2Cache Qcow2Cache;
-
 typedef struct BDRVQcowState {
+    BlockDriverState *hd;
     int cluster_bits;
     int cluster_size;
     int cluster_sectors;
@@ -100,10 +92,9 @@ typedef struct BDRVQcowState {
     uint64_t cluster_offset_mask;
     uint64_t l1_table_offset;
     uint64_t *l1_table;
-
-    Qcow2Cache* l2_table_cache;
-    Qcow2Cache* refcount_block_cache;
-
+    uint64_t *l2_cache;
+    uint64_t l2_cache_offsets[L2_CACHE_SIZE];
+    uint32_t l2_cache_counts[L2_CACHE_SIZE];
     uint8_t *cluster_cache;
     uint8_t *cluster_data;
     uint64_t cluster_cache_offset;
@@ -112,11 +103,11 @@ typedef struct BDRVQcowState {
     uint64_t *refcount_table;
     uint64_t refcount_table_offset;
     uint32_t refcount_table_size;
+    uint64_t refcount_block_cache_offset;
+    uint16_t *refcount_block_cache;
     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;
@@ -125,8 +116,6 @@ typedef struct BDRVQcowState {
     int snapshots_size;
     int nb_snapshots;
     QCowSnapshot *snapshots;
-
-    int flags;
 } BDRVQcowState;
 
 /* XXX: use std qcow open function ? */
@@ -150,7 +139,8 @@ typedef struct QCowL2Meta
     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;
@@ -176,8 +166,8 @@ static inline int64_t align_offset(int64_t offset, int n)
 // 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_backing_read1(BlockDriverState *bs,
+                  int64_t sector_num, uint8_t *buf, int nb_sectors);
 
 /* qcow2-refcount.c functions */
 int qcow2_refcount_init(BlockDriverState *bs);
@@ -190,13 +180,15 @@ void qcow2_free_clusters(BlockDriverState *bs,
 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);
 
 /* qcow2-cluster.c functions */
-int qcow2_grow_l1_table(BlockDriverState *bs, int min_size, bool exact_size);
+int qcow2_grow_l1_table(BlockDriverState *bs, int min_size);
 void qcow2_l2_cache_reset(BlockDriverState *bs);
 int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset);
 void qcow2_encrypt_sectors(BDRVQcowState *s, int64_t sector_num,
@@ -213,36 +205,14 @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
                                          int compressed_size);
 
 int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m);
-int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
-    int nb_sectors);
 
 /* qcow2-snapshot.c functions */
 int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info);
 int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id);
 int qcow2_snapshot_delete(BlockDriverState *bs, const char *snapshot_id);
 int qcow2_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab);
-int qcow2_snapshot_load_tmp(BlockDriverState *bs, const char *snapshot_name);
 
 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,
-    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);
-int qcow2_cache_set_dependency(BlockDriverState *bs, Qcow2Cache *c,
-    Qcow2Cache *dependency);
-void qcow2_cache_depends_on_flush(Qcow2Cache *c);
-
-int qcow2_cache_get(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset,
-    void **table);
-int qcow2_cache_get_empty(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset,
-    void **table);
-int qcow2_cache_put(BlockDriverState *bs, Qcow2Cache *c, void **table);
-
 #endif

block/qed-check.c

@@ -1,211 +0,0 @@
-/*
- * QEMU Enhanced Disk Format Consistency Check
- *
- * Copyright IBM, Corp. 2010
- *
- * 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 "qed.h"
-
-typedef struct {
-    BDRVQEDState *s;
-    BdrvCheckResult *result;
-    bool fix;                           /* whether to fix invalid offsets */
-
-    uint64_t nclusters;
-    uint32_t *used_clusters;            /* referenced cluster bitmap */
-
-    QEDRequest request;
-} QEDCheck;
-
-static bool qed_test_bit(uint32_t *bitmap, uint64_t n) {
-    return !!(bitmap[n / 32] & (1 << (n % 32)));
-}
-
-static void qed_set_bit(uint32_t *bitmap, uint64_t n) {
-    bitmap[n / 32] |= 1 << (n % 32);
-}
-
-/**
- * Set bitmap bits for clusters
- *
- * @check:          Check structure
- * @offset:         Starting offset in bytes
- * @n:              Number of clusters
- */
-static bool qed_set_used_clusters(QEDCheck *check, uint64_t offset,
-                                  unsigned int n)
-{
-    uint64_t cluster = qed_bytes_to_clusters(check->s, offset);
-    unsigned int corruptions = 0;
-
-    while (n-- != 0) {
-        /* Clusters should only be referenced once */
-        if (qed_test_bit(check->used_clusters, cluster)) {
-            corruptions++;
-        }
-
-        qed_set_bit(check->used_clusters, cluster);
-        cluster++;
-    }
-
-    check->result->corruptions += corruptions;
-    return corruptions == 0;
-}
-
-/**
- * Check an L2 table
- *
- * @ret:            Number of invalid cluster offsets
- */
-static unsigned int qed_check_l2_table(QEDCheck *check, QEDTable *table)
-{
-    BDRVQEDState *s = check->s;
-    unsigned int i, num_invalid = 0;
-
-    for (i = 0; i < s->table_nelems; i++) {
-        uint64_t offset = table->offsets[i];
-
-        if (qed_offset_is_unalloc_cluster(offset) ||
-            qed_offset_is_zero_cluster(offset)) {
-            continue;
-        }
-
-        /* Detect invalid cluster offset */
-        if (!qed_check_cluster_offset(s, offset)) {
-            if (check->fix) {
-                table->offsets[i] = 0;
-            } else {
-                check->result->corruptions++;
-            }
-
-            num_invalid++;
-            continue;
-        }
-
-        qed_set_used_clusters(check, offset, 1);
-    }
-
-    return num_invalid;
-}
-
-/**
- * Descend tables and check each cluster is referenced once only
- */
-static int qed_check_l1_table(QEDCheck *check, QEDTable *table)
-{
-    BDRVQEDState *s = check->s;
-    unsigned int i, num_invalid_l1 = 0;
-    int ret, last_error = 0;
-
-    /* Mark L1 table clusters used */
-    qed_set_used_clusters(check, s->header.l1_table_offset,
-                          s->header.table_size);
-
-    for (i = 0; i < s->table_nelems; i++) {
-        unsigned int num_invalid_l2;
-        uint64_t offset = table->offsets[i];
-
-        if (qed_offset_is_unalloc_cluster(offset)) {
-            continue;
-        }
-
-        /* Detect invalid L2 offset */
-        if (!qed_check_table_offset(s, offset)) {
-            /* Clear invalid offset */
-            if (check->fix) {
-                table->offsets[i] = 0;
-            } else {
-                check->result->corruptions++;
-            }
-
-            num_invalid_l1++;
-            continue;
-        }
-
-        if (!qed_set_used_clusters(check, offset, s->header.table_size)) {
-            continue; /* skip an invalid table */
-        }
-
-        ret = qed_read_l2_table_sync(s, &check->request, offset);
-        if (ret) {
-            check->result->check_errors++;
-            last_error = ret;
-            continue;
-        }
-
-        num_invalid_l2 = qed_check_l2_table(check,
-                                            check->request.l2_table->table);
-
-        /* Write out fixed L2 table */
-        if (num_invalid_l2 > 0 && check->fix) {
-            ret = qed_write_l2_table_sync(s, &check->request, 0,
-                                          s->table_nelems, false);
-            if (ret) {
-                check->result->check_errors++;
-                last_error = ret;
-                continue;
-            }
-        }
-    }
-
-    /* Drop reference to final table */
-    qed_unref_l2_cache_entry(check->request.l2_table);
-    check->request.l2_table = NULL;
-
-    /* Write out fixed L1 table */
-    if (num_invalid_l1 > 0 && check->fix) {
-        ret = qed_write_l1_table_sync(s, 0, s->table_nelems);
-        if (ret) {
-            check->result->check_errors++;
-            last_error = ret;
-        }
-    }
-
-    return last_error;
-}
-
-/**
- * Check for unreferenced (leaked) clusters
- */
-static void qed_check_for_leaks(QEDCheck *check)
-{
-    BDRVQEDState *s = check->s;
-    uint64_t i;
-
-    for (i = s->header.header_size; i < check->nclusters; i++) {
-        if (!qed_test_bit(check->used_clusters, i)) {
-            check->result->leaks++;
-        }
-    }
-}
-
-int qed_check(BDRVQEDState *s, BdrvCheckResult *result, bool fix)
-{
-    QEDCheck check = {
-        .s = s,
-        .result = result,
-        .nclusters = qed_bytes_to_clusters(s, s->file_size),
-        .request = { .l2_table = NULL },
-        .fix = fix,
-    };
-    int ret;
-
-    check.used_clusters = g_malloc0(((check.nclusters + 31) / 32) *
-                                       sizeof(check.used_clusters[0]));
-
-    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);
-    }
-
-    g_free(check.used_clusters);
-    return ret;
-}

block/qed-cluster.c

@@ -1,165 +0,0 @@
-/*
- * QEMU Enhanced Disk Format Cluster functions
- *
- * Copyright IBM, Corp. 2010
- *
- * Authors:
- *  Stefan Hajnoczi   <stefanha@linux.vnet.ibm.com>
- *  Anthony Liguori   <aliguori@us.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 "qed.h"
-
-/**
- * Count the number of contiguous data clusters
- *
- * @s:              QED state
- * @table:          L2 table
- * @index:          First cluster index
- * @n:              Maximum number of clusters
- * @offset:         Set to first cluster offset
- *
- * This function scans tables for contiguous clusters.  A contiguous run of
- * clusters may be allocated, unallocated, or zero.
- */
-static unsigned int qed_count_contiguous_clusters(BDRVQEDState *s,
-                                                  QEDTable *table,
-                                                  unsigned int index,
-                                                  unsigned int n,
-                                                  uint64_t *offset)
-{
-    unsigned int end = MIN(index + n, s->table_nelems);
-    uint64_t last = table->offsets[index];
-    unsigned int i;
-
-    *offset = last;
-
-    for (i = index + 1; i < end; i++) {
-        if (qed_offset_is_unalloc_cluster(last)) {
-            /* Counting unallocated clusters */
-            if (!qed_offset_is_unalloc_cluster(table->offsets[i])) {
-                break;
-            }
-        } else if (qed_offset_is_zero_cluster(last)) {
-            /* Counting zero clusters */
-            if (!qed_offset_is_zero_cluster(table->offsets[i])) {
-                break;
-            }
-        } else {
-            /* Counting allocated clusters */
-            if (table->offsets[i] != last + s->header.cluster_size) {
-                break;
-            }
-            last = table->offsets[i];
-        }
-    }
-    return i - index;
-}
-
-typedef struct {
-    BDRVQEDState *s;
-    uint64_t pos;
-    size_t len;
-
-    QEDRequest *request;
-
-    /* User callback */
-    QEDFindClusterFunc *cb;
-    void *opaque;
-} QEDFindClusterCB;
-
-static void qed_find_cluster_cb(void *opaque, int ret)
-{
-    QEDFindClusterCB *find_cluster_cb = opaque;
-    BDRVQEDState *s = find_cluster_cb->s;
-    QEDRequest *request = find_cluster_cb->request;
-    uint64_t offset = 0;
-    size_t len = 0;
-    unsigned int index;
-    unsigned int n;
-
-    if (ret) {
-        goto out;
-    }
-
-    index = qed_l2_index(s, find_cluster_cb->pos);
-    n = qed_bytes_to_clusters(s,
-                              qed_offset_into_cluster(s, find_cluster_cb->pos) +
-                              find_cluster_cb->len);
-    n = qed_count_contiguous_clusters(s, request->l2_table->table,
-                                      index, n, &offset);
-
-    if (qed_offset_is_unalloc_cluster(offset)) {
-        ret = QED_CLUSTER_L2;
-    } else if (qed_offset_is_zero_cluster(offset)) {
-        ret = QED_CLUSTER_ZERO;
-    } else if (qed_check_cluster_offset(s, offset)) {
-        ret = QED_CLUSTER_FOUND;
-    } else {
-        ret = -EINVAL;
-    }
-
-    len = MIN(find_cluster_cb->len, n * s->header.cluster_size -
-              qed_offset_into_cluster(s, find_cluster_cb->pos));
-
-out:
-    find_cluster_cb->cb(find_cluster_cb->opaque, ret, offset, len);
-    g_free(find_cluster_cb);
-}
-
-/**
- * Find the offset of a data cluster
- *
- * @s:          QED state
- * @request:    L2 cache entry
- * @pos:        Byte position in device
- * @len:        Number of bytes
- * @cb:         Completion function
- * @opaque:     User data for completion function
- *
- * This function translates a position in the block device to an offset in the
- * image file.  It invokes the cb completion callback to report back the
- * translated offset or unallocated range in the image file.
- *
- * If the L2 table exists, request->l2_table points to the L2 table cache entry
- * and the caller must free the reference when they are finished.  The cache
- * entry is exposed in this way to avoid callers having to read the L2 table
- * again later during request processing.  If request->l2_table is non-NULL it
- * will be unreferenced before taking on the new cache entry.
- */
-void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos,
-                      size_t len, QEDFindClusterFunc *cb, void *opaque)
-{
-    QEDFindClusterCB *find_cluster_cb;
-    uint64_t l2_offset;
-
-    /* Limit length to L2 boundary.  Requests are broken up at the L2 boundary
-     * so that a request acts on one L2 table at a time.
-     */
-    len = MIN(len, (((pos >> s->l1_shift) + 1) << s->l1_shift) - pos);
-
-    l2_offset = s->l1_table->offsets[qed_l1_index(s, pos)];
-    if (qed_offset_is_unalloc_cluster(l2_offset)) {
-        cb(opaque, QED_CLUSTER_L1, 0, len);
-        return;
-    }
-    if (!qed_check_table_offset(s, l2_offset)) {
-        cb(opaque, -EINVAL, 0, 0);
-        return;
-    }
-
-    find_cluster_cb = g_malloc(sizeof(*find_cluster_cb));
-    find_cluster_cb->s = s;
-    find_cluster_cb->pos = pos;
-    find_cluster_cb->len = len;
-    find_cluster_cb->cb = cb;
-    find_cluster_cb->opaque = opaque;
-    find_cluster_cb->request = request;
-
-    qed_read_l2_table(s, request, l2_offset,
-                      qed_find_cluster_cb, find_cluster_cb);
-}

block/qed-gencb.c

@@ -1,32 +0,0 @@
-/*
- * QEMU Enhanced Disk Format
- *
- * Copyright IBM, Corp. 2010
- *
- * 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 "qed.h"
-
-void *gencb_alloc(size_t len, BlockDriverCompletionFunc *cb, void *opaque)
-{
-    GenericCB *gencb = g_malloc(len);
-    gencb->cb = cb;
-    gencb->opaque = opaque;
-    return gencb;
-}
-
-void gencb_complete(void *opaque, int ret)
-{
-    GenericCB *gencb = opaque;
-    BlockDriverCompletionFunc *cb = gencb->cb;
-    void *user_opaque = gencb->opaque;
-
-    g_free(gencb);
-    cb(user_opaque, ret);
-}

block/qed-l2-cache.c

@@ -1,173 +0,0 @@
-/*
- * QEMU Enhanced Disk Format L2 Cache
- *
- * Copyright IBM, Corp. 2010
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.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.
- *
- */
-
-/*
- * L2 table cache usage is as follows:
- *
- * An open image has one L2 table cache that is used to avoid accessing the
- * image file for recently referenced L2 tables.
- *
- * Cluster offset lookup translates the logical offset within the block device
- * to a cluster offset within the image file.  This is done by indexing into
- * the L1 and L2 tables which store cluster offsets.  It is here where the L2
- * table cache serves up recently referenced L2 tables.
- *
- * If there is a cache miss, that L2 table is read from the image file and
- * committed to the cache.  Subsequent accesses to that L2 table will be served
- * from the cache until the table is evicted from the cache.
- *
- * L2 tables are also committed to the cache when new L2 tables are allocated
- * in the image file.  Since the L2 table cache is write-through, the new L2
- * table is first written out to the image file and then committed to the
- * cache.
- *
- * Multiple I/O requests may be using an L2 table cache entry at any given
- * time.  That means an entry may be in use across several requests and
- * reference counting is needed to free the entry at the correct time.  In
- * particular, an entry evicted from the cache will only be freed once all
- * references are dropped.
- *
- * An in-flight I/O request will hold a reference to a L2 table cache entry for
- * the period during which it needs to access the L2 table.  This includes
- * cluster offset lookup, L2 table allocation, and L2 table update when a new
- * data cluster has been allocated.
- *
- * An interesting case occurs when two requests need to access an L2 table that
- * is not in the cache.  Since the operation to read the table from the image
- * file takes some time to complete, both requests may see a cache miss and
- * start reading the L2 table from the image file.  The first to finish will
- * commit its L2 table into the cache.  When the second tries to commit its
- * table will be deleted in favor of the existing cache entry.
- */
-
-#include "trace.h"
-#include "qed.h"
-
-/* Each L2 holds 2GB so this let's us fully cache a 100GB disk */
-#define MAX_L2_CACHE_SIZE 50
-
-/**
- * Initialize the L2 cache
- */
-void qed_init_l2_cache(L2TableCache *l2_cache)
-{
-    QTAILQ_INIT(&l2_cache->entries);
-    l2_cache->n_entries = 0;
-}
-
-/**
- * Free the L2 cache
- */
-void qed_free_l2_cache(L2TableCache *l2_cache)
-{
-    CachedL2Table *entry, *next_entry;
-
-    QTAILQ_FOREACH_SAFE(entry, &l2_cache->entries, node, next_entry) {
-        qemu_vfree(entry->table);
-        g_free(entry);
-    }
-}
-
-/**
- * Allocate an uninitialized entry from the cache
- *
- * The returned entry has a reference count of 1 and is owned by the caller.
- * The caller must allocate the actual table field for this entry and it must
- * be freeable using qemu_vfree().
- */
-CachedL2Table *qed_alloc_l2_cache_entry(L2TableCache *l2_cache)
-{
-    CachedL2Table *entry;
-
-    entry = g_malloc0(sizeof(*entry));
-    entry->ref++;
-
-    trace_qed_alloc_l2_cache_entry(l2_cache, entry);
-
-    return entry;
-}
-
-/**
- * Decrease an entry's reference count and free if necessary when the reference
- * count drops to zero.
- */
-void qed_unref_l2_cache_entry(CachedL2Table *entry)
-{
-    if (!entry) {
-        return;
-    }
-
-    entry->ref--;
-    trace_qed_unref_l2_cache_entry(entry, entry->ref);
-    if (entry->ref == 0) {
-        qemu_vfree(entry->table);
-        g_free(entry);
-    }
-}
-
-/**
- * Find an entry in the L2 cache.  This may return NULL and it's up to the
- * caller to satisfy the cache miss.
- *
- * For a cached entry, this function increases the reference count and returns
- * the entry.
- */
-CachedL2Table *qed_find_l2_cache_entry(L2TableCache *l2_cache, uint64_t offset)
-{
-    CachedL2Table *entry;
-
-    QTAILQ_FOREACH(entry, &l2_cache->entries, node) {
-        if (entry->offset == offset) {
-            trace_qed_find_l2_cache_entry(l2_cache, entry, offset, entry->ref);
-            entry->ref++;
-            return entry;
-        }
-    }
-    return NULL;
-}
-
-/**
- * Commit an L2 cache entry into the cache.  This is meant to be used as part of
- * the process to satisfy a cache miss.  A caller would allocate an entry which
- * is not actually in the L2 cache and then once the entry was valid and
- * present on disk, the entry can be committed into the cache.
- *
- * Since the cache is write-through, it's important that this function is not
- * called until the entry is present on disk and the L1 has been updated to
- * point to the entry.
- *
- * N.B. This function steals a reference to the l2_table from the caller so the
- * caller must obtain a new reference by issuing a call to
- * qed_find_l2_cache_entry().
- */
-void qed_commit_l2_cache_entry(L2TableCache *l2_cache, CachedL2Table *l2_table)
-{
-    CachedL2Table *entry;
-
-    entry = qed_find_l2_cache_entry(l2_cache, l2_table->offset);
-    if (entry) {
-        qed_unref_l2_cache_entry(entry);
-        qed_unref_l2_cache_entry(l2_table);
-        return;
-    }
-
-    if (l2_cache->n_entries >= MAX_L2_CACHE_SIZE) {
-        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++;
-    QTAILQ_INSERT_TAIL(&l2_cache->entries, l2_table, node);
-}

block/qed-table.c

@@ -1,305 +0,0 @@
-/*
- * QEMU Enhanced Disk Format Table I/O
- *
- * Copyright IBM, Corp. 2010
- *
- * Authors:
- *  Stefan Hajnoczi   <stefanha@linux.vnet.ibm.com>
- *  Anthony Liguori   <aliguori@us.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 "qemu_socket.h" /* for EINPROGRESS on Windows */
-#include "qed.h"
-
-typedef struct {
-    GenericCB gencb;
-    BDRVQEDState *s;
-    QEDTable *table;
-
-    struct iovec iov;
-    QEMUIOVector qiov;
-} QEDReadTableCB;
-
-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->iov.iov_len / sizeof(uint64_t);
-    int i;
-
-    /* Handle I/O error */
-    if (ret) {
-        goto out;
-    }
-
-    /* Byteswap offsets */
-    for (i = 0; i < noffsets; i++) {
-        table->offsets[i] = le64_to_cpu(table->offsets[i]);
-    }
-
-out:
-    /* Completion */
-    trace_qed_read_table_cb(read_table_cb->s, read_table_cb->table, ret);
-    gencb_complete(&read_table_cb->gencb, ret);
-}
-
-static void qed_read_table(BDRVQEDState *s, uint64_t offset, QEDTable *table,
-                           BlockDriverCompletionFunc *cb, void *opaque)
-{
-    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);
-
-    read_table_cb->s = s;
-    read_table_cb->table = table;
-    read_table_cb->iov.iov_base = table->offsets,
-    read_table_cb->iov.iov_len = s->header.cluster_size * s->header.table_size,
-
-    qemu_iovec_init_external(qiov, &read_table_cb->iov, 1);
-    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 {
-    GenericCB gencb;
-    BDRVQEDState *s;
-    QEDTable *orig_table;
-    QEDTable *table;
-    bool flush;             /* flush after write? */
-
-    struct iovec iov;
-    QEMUIOVector qiov;
-} QEDWriteTableCB;
-
-static void qed_write_table_cb(void *opaque, int ret)
-{
-    QEDWriteTableCB *write_table_cb = opaque;
-
-    trace_qed_write_table_cb(write_table_cb->s,
-                             write_table_cb->orig_table,
-                             write_table_cb->flush,
-                             ret);
-
-    if (ret) {
-        goto out;
-    }
-
-    if (write_table_cb->flush) {
-        /* We still need to flush first */
-        write_table_cb->flush = false;
-        bdrv_aio_flush(write_table_cb->s->bs, qed_write_table_cb,
-                       write_table_cb);
-        return;
-    }
-
-out:
-    qemu_vfree(write_table_cb->table);
-    gencb_complete(&write_table_cb->gencb, ret);
-    return;
-}
-
-/**
- * Write out an updated part or all of a table
- *
- * @s:          QED state
- * @offset:     Offset of table in image file, in bytes
- * @table:      Table
- * @index:      Index of first element
- * @n:          Number of elements
- * @flush:      Whether or not to sync to disk
- * @cb:         Completion function
- * @opaque:     Argument for completion function
- */
-static void qed_write_table(BDRVQEDState *s, uint64_t offset, QEDTable *table,
-                            unsigned int index, unsigned int n, bool flush,
-                            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;
-
-    trace_qed_write_table(s, offset, table, index, n);
-
-    /* Calculate indices of the first and one after last elements */
-    start = index & ~sector_mask;
-    end = (index + n + sector_mask) & ~sector_mask;
-
-    len_bytes = (end - start) * sizeof(uint64_t);
-
-    write_table_cb = gencb_alloc(sizeof(*write_table_cb), cb, opaque);
-    write_table_cb->s = s;
-    write_table_cb->orig_table = table;
-    write_table_cb->flush = flush;
-    write_table_cb->table = qemu_blockalign(s->bs, len_bytes);
-    write_table_cb->iov.iov_base = write_table_cb->table->offsets;
-    write_table_cb->iov.iov_len = len_bytes;
-    qemu_iovec_init_external(&write_table_cb->qiov, &write_table_cb->iov, 1);
-
-    /* Byteswap table */
-    for (i = start; i < end; i++) {
-        uint64_t le_offset = cpu_to_le64(table->offsets[i]);
-        write_table_cb->table->offsets[i - start] = le_offset;
-    }
-
-    /* Adjust for offset into table */
-    offset += start * sizeof(uint64_t);
-
-    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);
-    }
-}
-
-/**
- * Propagate return value from async callback
- */
-static void qed_sync_cb(void *opaque, int ret)
-{
-    *(int *)opaque = ret;
-}
-
-int qed_read_l1_table_sync(BDRVQEDState *s)
-{
-    int ret = -EINPROGRESS;
-
-    qed_read_table(s, s->header.l1_table_offset,
-                   s->l1_table, qed_sync_cb, &ret);
-    while (ret == -EINPROGRESS) {
-        qemu_aio_wait();
-    }
-
-    return ret;
-}
-
-void qed_write_l1_table(BDRVQEDState *s, unsigned int index, unsigned int n,
-                        BlockDriverCompletionFunc *cb, void *opaque)
-{
-    BLKDBG_EVENT(s->bs->file, BLKDBG_L1_UPDATE);
-    qed_write_table(s, s->header.l1_table_offset,
-                    s->l1_table, index, n, false, cb, opaque);
-}
-
-int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index,
-                            unsigned int n)
-{
-    int ret = -EINPROGRESS;
-
-    qed_write_l1_table(s, index, n, qed_sync_cb, &ret);
-    while (ret == -EINPROGRESS) {
-        qemu_aio_wait();
-    }
-
-    return ret;
-}
-
-typedef struct {
-    GenericCB gencb;
-    BDRVQEDState *s;
-    uint64_t l2_offset;
-    QEDRequest *request;
-} QEDReadL2TableCB;
-
-static void qed_read_l2_table_cb(void *opaque, int ret)
-{
-    QEDReadL2TableCB *read_l2_table_cb = opaque;
-    QEDRequest *request = read_l2_table_cb->request;
-    BDRVQEDState *s = read_l2_table_cb->s;
-    CachedL2Table *l2_table = request->l2_table;
-    uint64_t l2_offset = read_l2_table_cb->l2_offset;
-
-    if (ret) {
-        /* can't trust loaded L2 table anymore */
-        qed_unref_l2_cache_entry(l2_table);
-        request->l2_table = NULL;
-    } else {
-        l2_table->offset = l2_offset;
-
-        qed_commit_l2_cache_entry(&s->l2_cache, l2_table);
-
-        /* This is guaranteed to succeed because we just committed the entry
-         * to the cache.
-         */
-        request->l2_table = qed_find_l2_cache_entry(&s->l2_cache, l2_offset);
-        assert(request->l2_table != NULL);
-    }
-
-    gencb_complete(&read_l2_table_cb->gencb, ret);
-}
-
-void qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset,
-                       BlockDriverCompletionFunc *cb, void *opaque)
-{
-    QEDReadL2TableCB *read_l2_table_cb;
-
-    qed_unref_l2_cache_entry(request->l2_table);
-
-    /* Check for cached L2 entry */
-    request->l2_table = qed_find_l2_cache_entry(&s->l2_cache, offset);
-    if (request->l2_table) {
-        cb(opaque, 0);
-        return;
-    }
-
-    request->l2_table = qed_alloc_l2_cache_entry(&s->l2_cache);
-    request->l2_table->table = qed_alloc_table(s);
-
-    read_l2_table_cb = gencb_alloc(sizeof(*read_l2_table_cb), cb, opaque);
-    read_l2_table_cb->s = s;
-    read_l2_table_cb->l2_offset = offset;
-    read_l2_table_cb->request = request;
-
-    BLKDBG_EVENT(s->bs->file, BLKDBG_L2_LOAD);
-    qed_read_table(s, offset, request->l2_table->table,
-                   qed_read_l2_table_cb, read_l2_table_cb);
-}
-
-int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request, uint64_t offset)
-{
-    int ret = -EINPROGRESS;
-
-    qed_read_l2_table(s, request, offset, qed_sync_cb, &ret);
-    while (ret == -EINPROGRESS) {
-        qemu_aio_wait();
-    }
-
-    return ret;
-}
-
-void qed_write_l2_table(BDRVQEDState *s, QEDRequest *request,
-                        unsigned int index, unsigned int n, bool flush,
-                        BlockDriverCompletionFunc *cb, void *opaque)
-{
-    BLKDBG_EVENT(s->bs->file, BLKDBG_L2_UPDATE);
-    qed_write_table(s, request->l2_table->offset,
-                    request->l2_table->table, index, n, flush, cb, opaque);
-}
-
-int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request,
-                            unsigned int index, unsigned int n, bool flush)
-{
-    int ret = -EINPROGRESS;
-
-    qed_write_l2_table(s, request, index, n, flush, qed_sync_cb, &ret);
-    while (ret == -EINPROGRESS) {
-        qemu_aio_wait();
-    }
-
-    return ret;
-}

block/qed.h

@@ -1,336 +0,0 @@
-/*
- * QEMU Enhanced Disk Format
- *
- * Copyright IBM, Corp. 2010
- *
- * Authors:
- *  Stefan Hajnoczi   <stefanha@linux.vnet.ibm.com>
- *  Anthony Liguori   <aliguori@us.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.
- *
- */
-
-#ifndef BLOCK_QED_H
-#define BLOCK_QED_H
-
-#include "block_int.h"
-
-/* The layout of a QED file is as follows:
- *
- * +--------+----------+----------+----------+-----+
- * | header | L1 table | cluster0 | cluster1 | ... |
- * +--------+----------+----------+----------+-----+
- *
- * There is a 2-level pagetable for cluster allocation:
- *
- *                     +----------+
- *                     | L1 table |
- *                     +----------+
- *                ,------'  |  '------.
- *           +----------+   |    +----------+
- *           | L2 table |  ...   | L2 table |
- *           +----------+        +----------+
- *       ,------'  |  '------.
- *  +----------+   |    +----------+
- *  |   Data   |  ...   |   Data   |
- *  +----------+        +----------+
- *
- * The L1 table is fixed size and always present.  L2 tables are allocated on
- * demand.  The L1 table size determines the maximum possible image size; it
- * can be influenced using the cluster_size and table_size values.
- *
- * All fields are little-endian on disk.
- */
-
-enum {
-    QED_MAGIC = 'Q' | 'E' << 8 | 'D' << 16 | '\0' << 24,
-
-    /* The image supports a backing file */
-    QED_F_BACKING_FILE = 0x01,
-
-    /* The image needs a consistency check before use */
-    QED_F_NEED_CHECK = 0x02,
-
-    /* The backing file format must not be probed, treat as raw image */
-    QED_F_BACKING_FORMAT_NO_PROBE = 0x04,
-
-    /* Feature bits must be used when the on-disk format changes */
-    QED_FEATURE_MASK = QED_F_BACKING_FILE | /* supported feature bits */
-                       QED_F_NEED_CHECK |
-                       QED_F_BACKING_FORMAT_NO_PROBE,
-    QED_COMPAT_FEATURE_MASK = 0,            /* supported compat feature bits */
-    QED_AUTOCLEAR_FEATURE_MASK = 0,         /* supported autoclear feature bits */
-
-    /* Data is stored in groups of sectors called clusters.  Cluster size must
-     * be large to avoid keeping too much metadata.  I/O requests that have
-     * sub-cluster size will require read-modify-write.
-     */
-    QED_MIN_CLUSTER_SIZE = 4 * 1024, /* in bytes */
-    QED_MAX_CLUSTER_SIZE = 64 * 1024 * 1024,
-    QED_DEFAULT_CLUSTER_SIZE = 64 * 1024,
-
-    /* Allocated clusters are tracked using a 2-level pagetable.  Table size is
-     * a multiple of clusters so large maximum image sizes can be supported
-     * without jacking up the cluster size too much.
-     */
-    QED_MIN_TABLE_SIZE = 1,        /* in clusters */
-    QED_MAX_TABLE_SIZE = 16,
-    QED_DEFAULT_TABLE_SIZE = 4,
-
-    /* Delay to flush and clean image after last allocating write completes */
-    QED_NEED_CHECK_TIMEOUT = 5,    /* in seconds */
-};
-
-typedef struct {
-    uint32_t magic;                 /* QED\0 */
-
-    uint32_t cluster_size;          /* in bytes */
-    uint32_t table_size;            /* for L1 and L2 tables, in clusters */
-    uint32_t header_size;           /* in clusters */
-
-    uint64_t features;              /* format feature bits */
-    uint64_t compat_features;       /* compatible feature bits */
-    uint64_t autoclear_features;    /* self-resetting feature bits */
-
-    uint64_t l1_table_offset;       /* in bytes */
-    uint64_t image_size;            /* total logical image size, in bytes */
-
-    /* if (features & QED_F_BACKING_FILE) */
-    uint32_t backing_filename_offset; /* in bytes from start of header */
-    uint32_t backing_filename_size;   /* in bytes */
-} QEDHeader;
-
-typedef struct {
-    uint64_t offsets[0];            /* in bytes */
-} QEDTable;
-
-/* The L2 cache is a simple write-through cache for L2 structures */
-typedef struct CachedL2Table {
-    QEDTable *table;
-    uint64_t offset;    /* offset=0 indicates an invalidate entry */
-    QTAILQ_ENTRY(CachedL2Table) node;
-    int ref;
-} CachedL2Table;
-
-typedef struct {
-    QTAILQ_HEAD(, CachedL2Table) entries;
-    unsigned int n_entries;
-} L2TableCache;
-
-typedef struct QEDRequest {
-    CachedL2Table *l2_table;
-} QEDRequest;
-
-typedef struct QEDAIOCB {
-    BlockDriverAIOCB common;
-    QEMUBH *bh;
-    int bh_ret;                     /* final return status for completion bh */
-    QSIMPLEQ_ENTRY(QEDAIOCB) next;  /* next request */
-    bool is_write;                  /* false - read, true - write */
-    bool *finished;                 /* signal for cancel completion */
-    uint64_t end_pos;               /* request end on block device, in bytes */
-
-    /* User scatter-gather list */
-    QEMUIOVector *qiov;
-    size_t qiov_offset;             /* byte count already processed */
-
-    /* Current cluster scatter-gather list */
-    QEMUIOVector cur_qiov;
-    uint64_t cur_pos;               /* position on block device, in bytes */
-    uint64_t cur_cluster;           /* cluster offset in image file */
-    unsigned int cur_nclusters;     /* number of clusters being accessed */
-    int find_cluster_ret;           /* used for L1/L2 update */
-
-    QEDRequest request;
-} QEDAIOCB;
-
-typedef struct {
-    BlockDriverState *bs;           /* device */
-    uint64_t file_size;             /* length of image file, in bytes */
-
-    QEDHeader header;               /* always cpu-endian */
-    QEDTable *l1_table;
-    L2TableCache l2_cache;          /* l2 table cache */
-    uint32_t table_nelems;
-    uint32_t l1_shift;
-    uint32_t l2_shift;
-    uint32_t l2_mask;
-
-    /* Allocating write request queue */
-    QSIMPLEQ_HEAD(, QEDAIOCB) allocating_write_reqs;
-    bool allocating_write_reqs_plugged;
-
-    /* Periodic flush and clear need check flag */
-    QEMUTimer *need_check_timer;
-
-    Error *migration_blocker;
-} BDRVQEDState;
-
-enum {
-    QED_CLUSTER_FOUND,         /* cluster found */
-    QED_CLUSTER_ZERO,          /* zero cluster found */
-    QED_CLUSTER_L2,            /* cluster missing in L2 */
-    QED_CLUSTER_L1,            /* cluster missing in L1 */
-};
-
-/**
- * qed_find_cluster() completion callback
- *
- * @opaque:     User data for completion callback
- * @ret:        QED_CLUSTER_FOUND   Success
- *              QED_CLUSTER_L2      Data cluster unallocated in L2
- *              QED_CLUSTER_L1      L2 unallocated in L1
- *              -errno              POSIX error occurred
- * @offset:     Data cluster offset
- * @len:        Contiguous bytes starting from cluster offset
- *
- * This function is invoked when qed_find_cluster() completes.
- *
- * On success ret is QED_CLUSTER_FOUND and offset/len are a contiguous range
- * in the image file.
- *
- * On failure ret is QED_CLUSTER_L2 or QED_CLUSTER_L1 for missing L2 or L1
- * table offset, respectively.  len is number of contiguous unallocated bytes.
- */
-typedef void QEDFindClusterFunc(void *opaque, int ret, uint64_t offset, size_t len);
-
-/**
- * Generic callback for chaining async callbacks
- */
-typedef struct {
-    BlockDriverCompletionFunc *cb;
-    void *opaque;
-} GenericCB;
-
-void *gencb_alloc(size_t len, BlockDriverCompletionFunc *cb, void *opaque);
-void gencb_complete(void *opaque, int ret);
-
-/**
- * L2 cache functions
- */
-void qed_init_l2_cache(L2TableCache *l2_cache);
-void qed_free_l2_cache(L2TableCache *l2_cache);
-CachedL2Table *qed_alloc_l2_cache_entry(L2TableCache *l2_cache);
-void qed_unref_l2_cache_entry(CachedL2Table *entry);
-CachedL2Table *qed_find_l2_cache_entry(L2TableCache *l2_cache, uint64_t offset);
-void qed_commit_l2_cache_entry(L2TableCache *l2_cache, CachedL2Table *l2_table);
-
-/**
- * Table I/O functions
- */
-int qed_read_l1_table_sync(BDRVQEDState *s);
-void qed_write_l1_table(BDRVQEDState *s, unsigned int index, unsigned int n,
-                        BlockDriverCompletionFunc *cb, void *opaque);
-int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index,
-                            unsigned int n);
-int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request,
-                           uint64_t offset);
-void qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset,
-                       BlockDriverCompletionFunc *cb, void *opaque);
-void qed_write_l2_table(BDRVQEDState *s, QEDRequest *request,
-                        unsigned int index, unsigned int n, bool flush,
-                        BlockDriverCompletionFunc *cb, void *opaque);
-int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request,
-                            unsigned int index, unsigned int n, bool flush);
-
-/**
- * Cluster functions
- */
-void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos,
-                      size_t len, QEDFindClusterFunc *cb, void *opaque);
-
-/**
- * Consistency check
- */
-int qed_check(BDRVQEDState *s, BdrvCheckResult *result, bool fix);
-
-QEDTable *qed_alloc_table(BDRVQEDState *s);
-
-/**
- * Round down to the start of a cluster
- */
-static inline uint64_t qed_start_of_cluster(BDRVQEDState *s, uint64_t offset)
-{
-    return offset & ~(uint64_t)(s->header.cluster_size - 1);
-}
-
-static inline uint64_t qed_offset_into_cluster(BDRVQEDState *s, uint64_t offset)
-{
-    return offset & (s->header.cluster_size - 1);
-}
-
-static inline uint64_t qed_bytes_to_clusters(BDRVQEDState *s, uint64_t bytes)
-{
-    return qed_start_of_cluster(s, bytes + (s->header.cluster_size - 1)) /
-           (s->header.cluster_size - 1);
-}
-
-static inline unsigned int qed_l1_index(BDRVQEDState *s, uint64_t pos)
-{
-    return pos >> s->l1_shift;
-}
-
-static inline unsigned int qed_l2_index(BDRVQEDState *s, uint64_t pos)
-{
-    return (pos >> s->l2_shift) & s->l2_mask;
-}
-
-/**
- * Test if a cluster offset is valid
- */
-static inline bool qed_check_cluster_offset(BDRVQEDState *s, uint64_t offset)
-{
-    uint64_t header_size = (uint64_t)s->header.header_size *
-                           s->header.cluster_size;
-
-    if (offset & (s->header.cluster_size - 1)) {
-        return false;
-    }
-    return offset >= header_size && offset < s->file_size;
-}
-
-/**
- * Test if a table offset is valid
- */
-static inline bool qed_check_table_offset(BDRVQEDState *s, uint64_t offset)
-{
-    uint64_t end_offset = offset + (s->header.table_size - 1) *
-                          s->header.cluster_size;
-
-    /* Overflow check */
-    if (end_offset <= offset) {
-        return false;
-    }
-
-    return qed_check_cluster_offset(s, offset) &&
-           qed_check_cluster_offset(s, end_offset);
-}
-
-static inline bool qed_offset_is_cluster_aligned(BDRVQEDState *s,
-                                                 uint64_t offset)
-{
-    if (qed_offset_into_cluster(s, offset)) {
-        return false;
-    }
-    return true;
-}
-
-static inline bool qed_offset_is_unalloc_cluster(uint64_t offset)
-{
-    if (offset == 0) {
-        return true;
-    }
-    return false;
-}
-
-static inline bool qed_offset_is_zero_cluster(uint64_t offset)
-{
-    if (offset == 1) {
-        return true;
-    }
-    return false;
-}
-
-#endif /* BLOCK_QED_H */

block/raw-posix.c

@@ -43,17 +43,16 @@
 
 #ifdef __sun__
 #define _POSIX_PTHREAD_SEMANTICS 1
+#include <signal.h>
 #include <sys/dkio.h>
 #endif
 #ifdef __linux__
-#include <sys/types.h>
-#include <sys/stat.h>
 #include <sys/ioctl.h>
-#include <sys/param.h>
 #include <linux/cdrom.h>
 #include <linux/fd.h>
 #endif
 #if defined (__FreeBSD__) || defined(__FreeBSD_kernel__)
+#include <signal.h>
 #include <sys/disk.h>
 #include <sys/cdio.h>
 #endif
@@ -64,22 +63,11 @@
 #include <sys/dkio.h>
 #endif
 
-#ifdef __NetBSD__
-#include <sys/ioctl.h>
-#include <sys/disklabel.h>
-#include <sys/dkio.h>
-#include <sys/disk.h>
-#endif
-
 #ifdef __DragonFly__
 #include <sys/ioctl.h>
 #include <sys/diskslice.h>
 #endif
 
-#ifdef CONFIG_XFS
-#include <xfs/xfs.h>
-#endif
-
 //#define DEBUG_FLOPPY
 
 //#define DEBUG_BLOCK
@@ -108,11 +96,11 @@
 #define FTYPE_CD     1
 #define FTYPE_FD     2
 
-/* if the FD is not accessed during that time (in ns), we try to
-   reopen it to see if the disk has been changed */
-#define FD_OPEN_TIMEOUT (1000000000)
+#define ALIGNED_BUFFER_SIZE (32 * 512)
 
-#define MAX_BLOCKSIZE	4096
+/* if the FD is not accessed during that time (in ms), we try to
+   reopen it to see if the disk has been changed */
+#define FD_OPEN_TIMEOUT 1000
 
 typedef struct BDRVRawState {
     int fd;
@@ -129,11 +117,7 @@ typedef struct BDRVRawState {
     int use_aio;
     void *aio_ctx;
 #endif
-    uint8_t *aligned_buf;
-    unsigned aligned_buf_size;
-#ifdef CONFIG_XFS
-    bool is_xfs : 1;
-#endif
+    uint8_t* aligned_buf;
 } BDRVRawState;
 
 static int fd_open(BlockDriverState *bs);
@@ -143,55 +127,12 @@ static int64_t raw_getlength(BlockDriverState *bs);
 static int cdrom_reopen(BlockDriverState *bs);
 #endif
 
-#if defined(__NetBSD__)
-static int raw_normalize_devicepath(const char **filename)
-{
-    static char namebuf[PATH_MAX];
-    const char *dp, *fname;
-    struct stat sb;
-
-    fname = *filename;
-    dp = strrchr(fname, '/');
-    if (lstat(fname, &sb) < 0) {
-        fprintf(stderr, "%s: stat failed: %s\n",
-            fname, strerror(errno));
-        return -errno;
-    }
-
-    if (!S_ISBLK(sb.st_mode)) {
-        return 0;
-    }
-
-    if (dp == NULL) {
-        snprintf(namebuf, PATH_MAX, "r%s", fname);
-    } else {
-        snprintf(namebuf, PATH_MAX, "%.*s/r%s",
-            (int)(dp - fname), fname, dp + 1);
-    }
-    fprintf(stderr, "%s is a block device", fname);
-    *filename = namebuf;
-    fprintf(stderr, ", using %s\n", *filename);
-
-    return 0;
-}
-#else
-static int raw_normalize_devicepath(const char **filename)
-{
-    return 0;
-}
-#endif
-
 static int raw_open_common(BlockDriverState *bs, const char *filename,
                            int bdrv_flags, int open_flags)
 {
     BDRVRawState *s = bs->opaque;
     int fd, ret;
 
-    ret = raw_normalize_devicepath(&filename);
-    if (ret != 0) {
-        return ret;
-    }
-
     s->open_flags = open_flags | O_BINARY;
     s->open_flags &= ~O_ACCMODE;
     if (bdrv_flags & BDRV_O_RDWR) {
@@ -204,7 +145,7 @@ static int raw_open_common(BlockDriverState *bs, const char *filename,
      * and O_DIRECT for no caching. */
     if ((bdrv_flags & BDRV_O_NOCACHE))
         s->open_flags |= O_DIRECT;
-    if (!(bdrv_flags & BDRV_O_CACHE_WB))
+    else if (!(bdrv_flags & BDRV_O_CACHE_WB))
         s->open_flags |= O_DSYNC;
 
     s->fd = -1;
@@ -219,30 +160,19 @@ static int raw_open_common(BlockDriverState *bs, const char *filename,
     s->aligned_buf = NULL;
 
     if ((bdrv_flags & BDRV_O_NOCACHE)) {
-        /*
-         * Allocate a buffer for read/modify/write cycles.  Chose the size
-         * pessimistically as we don't know the block size yet.
-         */
-        s->aligned_buf_size = 32 * MAX_BLOCKSIZE;
-        s->aligned_buf = qemu_memalign(MAX_BLOCKSIZE, s->aligned_buf_size);
+        s->aligned_buf = qemu_blockalign(bs, ALIGNED_BUFFER_SIZE);
         if (s->aligned_buf == NULL) {
             goto out_close;
         }
     }
 
-    /* We're falling back to POSIX AIO in some cases so init always */
-    if (paio_init() < 0) {
-        goto out_free_buf;
-    }
-
 #ifdef CONFIG_LINUX_AIO
-    /*
-     * Currently Linux do AIO only for files opened with O_DIRECT
-     * specified so check NOCACHE flag too
-     */
     if ((bdrv_flags & (BDRV_O_NOCACHE|BDRV_O_NATIVE_AIO)) ==
                       (BDRV_O_NOCACHE|BDRV_O_NATIVE_AIO)) {
 
+        /* We're falling back to POSIX AIO in some cases */
+        paio_init();
+
         s->aio_ctx = laio_init();
         if (!s->aio_ctx) {
             goto out_free_buf;
@@ -251,17 +181,14 @@ static int raw_open_common(BlockDriverState *bs, const char *filename,
     } else
 #endif
     {
+        if (paio_init() < 0) {
+            goto out_free_buf;
+        }
 #ifdef CONFIG_LINUX_AIO
         s->use_aio = 0;
 #endif
     }
 
-#ifdef CONFIG_XFS
-    if (platform_test_xfs_fd(s->fd)) {
-        s->is_xfs = 1;
-    }
-#endif
-
     return 0;
 
 out_free_buf:
@@ -296,15 +223,275 @@ static int raw_open(BlockDriverState *bs, const char *filename, int flags)
 #endif
 */
 
+/*
+ * offset and count are in bytes, but must be multiples of 512 for files
+ * opened with O_DIRECT. buf must be aligned to 512 bytes then.
+ *
+ * This function may be called without alignment if the caller ensures
+ * that O_DIRECT is not in effect.
+ */
+static int raw_pread_aligned(BlockDriverState *bs, int64_t offset,
+                     uint8_t *buf, int count)
+{
+    BDRVRawState *s = bs->opaque;
+    int ret;
+
+    ret = fd_open(bs);
+    if (ret < 0)
+        return ret;
+
+    ret = pread(s->fd, buf, count, offset);
+    if (ret == count)
+        return ret;
+
+    /* Allow reads beyond the end (needed for pwrite) */
+    if ((ret == 0) && bs->growable) {
+        int64_t size = raw_getlength(bs);
+        if (offset >= size) {
+            memset(buf, 0, count);
+            return count;
+        }
+    }
+
+    DEBUG_BLOCK_PRINT("raw_pread(%d:%s, %" PRId64 ", %p, %d) [%" PRId64
+                      "] read failed %d : %d = %s\n",
+                      s->fd, bs->filename, offset, buf, count,
+                      bs->total_sectors, ret, errno, strerror(errno));
+
+    /* Try harder for CDrom. */
+    if (s->type != FTYPE_FILE) {
+        ret = pread(s->fd, buf, count, offset);
+        if (ret == count)
+            return ret;
+        ret = pread(s->fd, buf, count, offset);
+        if (ret == count)
+            return ret;
+
+        DEBUG_BLOCK_PRINT("raw_pread(%d:%s, %" PRId64 ", %p, %d) [%" PRId64
+                          "] retry read failed %d : %d = %s\n",
+                          s->fd, bs->filename, offset, buf, count,
+                          bs->total_sectors, ret, errno, strerror(errno));
+    }
+
+    return  (ret < 0) ? -errno : ret;
+}
+
+/*
+ * offset and count are in bytes, but must be multiples of 512 for files
+ * opened with O_DIRECT. buf must be aligned to 512 bytes then.
+ *
+ * This function may be called without alignment if the caller ensures
+ * that O_DIRECT is not in effect.
+ */
+static int raw_pwrite_aligned(BlockDriverState *bs, int64_t offset,
+                      const uint8_t *buf, int count)
+{
+    BDRVRawState *s = bs->opaque;
+    int ret;
+
+    ret = fd_open(bs);
+    if (ret < 0)
+        return -errno;
+
+    ret = pwrite(s->fd, buf, count, offset);
+    if (ret == count)
+        return ret;
+
+    DEBUG_BLOCK_PRINT("raw_pwrite(%d:%s, %" PRId64 ", %p, %d) [%" PRId64
+                      "] write failed %d : %d = %s\n",
+                      s->fd, bs->filename, offset, buf, count,
+                      bs->total_sectors, ret, errno, strerror(errno));
+
+    return  (ret < 0) ? -errno : ret;
+}
+
+
+/*
+ * offset and count are in bytes and possibly not aligned. For files opened
+ * with O_DIRECT, necessary alignments are ensured before calling
+ * raw_pread_aligned to do the actual read.
+ */
+static int raw_pread(BlockDriverState *bs, int64_t offset,
+                     uint8_t *buf, int count)
+{
+    BDRVRawState *s = bs->opaque;
+    int size, ret, shift, sum;
+
+    sum = 0;
+
+    if (s->aligned_buf != NULL)  {
+
+        if (offset & 0x1ff) {
+            /* align offset on a 512 bytes boundary */
+
+            shift = offset & 0x1ff;
+            size = (shift + count + 0x1ff) & ~0x1ff;
+            if (size > ALIGNED_BUFFER_SIZE)
+                size = ALIGNED_BUFFER_SIZE;
+            ret = raw_pread_aligned(bs, offset - shift, s->aligned_buf, size);
+            if (ret < 0)
+                return ret;
+
+            size = 512 - shift;
+            if (size > count)
+                size = count;
+            memcpy(buf, s->aligned_buf + shift, size);
+
+            buf += size;
+            offset += size;
+            count -= size;
+            sum += size;
+
+            if (count == 0)
+                return sum;
+        }
+        if (count & 0x1ff || (uintptr_t) buf & 0x1ff) {
+
+            /* read on aligned buffer */
+
+            while (count) {
+
+                size = (count + 0x1ff) & ~0x1ff;
+                if (size > ALIGNED_BUFFER_SIZE)
+                    size = ALIGNED_BUFFER_SIZE;
+
+                ret = raw_pread_aligned(bs, offset, s->aligned_buf, size);
+                if (ret < 0) {
+                    return ret;
+                } else if (ret == 0) {
+                    fprintf(stderr, "raw_pread: read beyond end of file\n");
+                    abort();
+                }
+
+                size = ret;
+                if (size > count)
+                    size = count;
+
+                memcpy(buf, s->aligned_buf, size);
+
+                buf += size;
+                offset += size;
+                count -= size;
+                sum += size;
+            }
+
+            return sum;
+        }
+    }
+
+    return raw_pread_aligned(bs, offset, buf, count) + sum;
+}
+
+static int raw_read(BlockDriverState *bs, int64_t sector_num,
+                    uint8_t *buf, int nb_sectors)
+{
+    int ret;
+
+    ret = raw_pread(bs, sector_num * BDRV_SECTOR_SIZE, buf,
+                    nb_sectors * BDRV_SECTOR_SIZE);
+    if (ret == (nb_sectors * BDRV_SECTOR_SIZE))
+        ret = 0;
+    return ret;
+}
+
+/*
+ * offset and count are in bytes and possibly not aligned. For files opened
+ * with O_DIRECT, necessary alignments are ensured before calling
+ * raw_pwrite_aligned to do the actual write.
+ */
+static int raw_pwrite(BlockDriverState *bs, int64_t offset,
+                      const uint8_t *buf, int count)
+{
+    BDRVRawState *s = bs->opaque;
+    int size, ret, shift, sum;
+
+    sum = 0;
+
+    if (s->aligned_buf != NULL) {
+
+        if (offset & 0x1ff) {
+            /* align offset on a 512 bytes boundary */
+            shift = offset & 0x1ff;
+            ret = raw_pread_aligned(bs, offset - shift, s->aligned_buf, 512);
+            if (ret < 0)
+                return ret;
+
+            size = 512 - shift;
+            if (size > count)
+                size = count;
+            memcpy(s->aligned_buf + shift, buf, size);
+
+            ret = raw_pwrite_aligned(bs, offset - shift, s->aligned_buf, 512);
+            if (ret < 0)
+                return ret;
+
+            buf += size;
+            offset += size;
+            count -= size;
+            sum += size;
+
+            if (count == 0)
+                return sum;
+        }
+        if (count & 0x1ff || (uintptr_t) buf & 0x1ff) {
+
+            while ((size = (count & ~0x1ff)) != 0) {
+
+                if (size > ALIGNED_BUFFER_SIZE)
+                    size = ALIGNED_BUFFER_SIZE;
+
+                memcpy(s->aligned_buf, buf, size);
+
+                ret = raw_pwrite_aligned(bs, offset, s->aligned_buf, size);
+                if (ret < 0)
+                    return ret;
+
+                buf += ret;
+                offset += ret;
+                count -= ret;
+                sum += ret;
+            }
+            /* here, count < 512 because (count & ~0x1ff) == 0 */
+            if (count) {
+                ret = raw_pread_aligned(bs, offset, s->aligned_buf, 512);
+                if (ret < 0)
+                    return ret;
+                 memcpy(s->aligned_buf, buf, count);
+
+                 ret = raw_pwrite_aligned(bs, offset, s->aligned_buf, 512);
+                 if (ret < 0)
+                     return ret;
+                 if (count < ret)
+                     ret = count;
+
+                 sum += ret;
+            }
+            return sum;
+        }
+    }
+    return raw_pwrite_aligned(bs, offset, buf, count) + sum;
+}
+
+static int raw_write(BlockDriverState *bs, int64_t sector_num,
+                     const uint8_t *buf, int nb_sectors)
+{
+    int ret;
+    ret = raw_pwrite(bs, sector_num * BDRV_SECTOR_SIZE, buf,
+                     nb_sectors * BDRV_SECTOR_SIZE);
+    if (ret == (nb_sectors * BDRV_SECTOR_SIZE))
+        ret = 0;
+    return ret;
+}
+
 /*
  * Check if all memory in this vector is sector aligned.
  */
-static int qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov)
+static int qiov_is_aligned(QEMUIOVector *qiov)
 {
     int i;
 
     for (i = 0; i < qiov->niov; i++) {
-        if ((uintptr_t) qiov->iov[i].iov_base % bs->buffer_alignment) {
+        if ((uintptr_t) qiov->iov[i].iov_base % BDRV_SECTOR_SIZE) {
             return 0;
         }
     }
@@ -323,11 +510,11 @@ static BlockDriverAIOCB *raw_aio_submit(BlockDriverState *bs,
 
     /*
      * If O_DIRECT is used the buffer needs to be aligned on a sector
-     * boundary.  Check if this is the case or tell the low-level
+     * boundary.  Check if this is the case or telll the low-level
      * driver that it needs to copy the buffer.
      */
     if (s->aligned_buf) {
-        if (!qiov_is_aligned(bs, qiov)) {
+        if (!qiov_is_aligned(qiov)) {
             type |= QEMU_AIO_MISALIGNED;
 #ifdef CONFIG_LINUX_AIO
         } else if (s->use_aio) {
@@ -382,24 +569,10 @@ static void raw_close(BlockDriverState *bs)
 static int raw_truncate(BlockDriverState *bs, int64_t offset)
 {
     BDRVRawState *s = bs->opaque;
-    struct stat st;
-
-    if (fstat(s->fd, &st)) {
-        return -errno;
-    }
-
-    if (S_ISREG(st.st_mode)) {
-        if (ftruncate(s->fd, offset) < 0) {
-            return -errno;
-        }
-    } else if (S_ISCHR(st.st_mode) || S_ISBLK(st.st_mode)) {
-       if (offset > raw_getlength(bs)) {
-           return -EINVAL;
-       }
-    } else {
+    if (s->type != FTYPE_FILE)
         return -ENOTSUP;
-    }
-
+    if (ftruncate(s->fd, offset) < 0)
+        return -errno;
     return 0;
 }
 
@@ -422,31 +595,6 @@ static int64_t raw_getlength(BlockDriverState *bs)
     } else
         return st.st_size;
 }
-#elif defined(__NetBSD__)
-static int64_t raw_getlength(BlockDriverState *bs)
-{
-    BDRVRawState *s = bs->opaque;
-    int fd = s->fd;
-    struct stat st;
-
-    if (fstat(fd, &st))
-        return -1;
-    if (S_ISCHR(st.st_mode) || S_ISBLK(st.st_mode)) {
-        struct dkwedge_info dkw;
-
-        if (ioctl(fd, DIOCGWEDGEINFO, &dkw) != -1) {
-            return dkw.dkw_size * 512;
-        } else {
-            struct disklabel dl;
-
-            if (ioctl(fd, DIOCGDINFO, &dl))
-                return -1;
-            return (uint64_t)dl.d_secsize *
-                dl.d_partitions[DISKPART(st.st_rdev)].p_size;
-        }
-    } else
-        return st.st_size;
-}
 #elif defined(__sun__)
 static int64_t raw_getlength(BlockDriverState *bs)
 {
@@ -543,17 +691,6 @@ static int64_t raw_getlength(BlockDriverState *bs)
 }
 #endif
 
-static int64_t raw_get_allocated_file_size(BlockDriverState *bs)
-{
-    struct stat st;
-    BDRVRawState *s = bs->opaque;
-
-    if (fstat(s->fd, &st) < 0) {
-        return -errno;
-    }
-    return (int64_t)st.st_blocks * 512;
-}
-
 static int raw_create(const char *filename, QEMUOptionParameter *options)
 {
     int fd;
@@ -583,39 +720,13 @@ static int raw_create(const char *filename, QEMUOptionParameter *options)
     return result;
 }
 
-#ifdef CONFIG_XFS
-static int xfs_discard(BDRVRawState *s, int64_t sector_num, int nb_sectors)
+static void raw_flush(BlockDriverState *bs)
 {
-    struct xfs_flock64 fl;
-
-    memset(&fl, 0, sizeof(fl));
-    fl.l_whence = SEEK_SET;
-    fl.l_start = sector_num << 9;
-    fl.l_len = (int64_t)nb_sectors << 9;
-
-    if (xfsctl(NULL, s->fd, XFS_IOC_UNRESVSP64, &fl) < 0) {
-        DEBUG_BLOCK_PRINT("cannot punch hole (%s)\n", strerror(errno));
-        return -errno;
-    }
-
-    return 0;
-}
-#endif
-
-static coroutine_fn int raw_co_discard(BlockDriverState *bs,
-    int64_t sector_num, int nb_sectors)
-{
-#ifdef CONFIG_XFS
     BDRVRawState *s = bs->opaque;
-
-    if (s->is_xfs) {
-        return xfs_discard(s, sector_num, nb_sectors);
-    }
-#endif
-
-    return 0;
+    qemu_fdatasync(s->fd);
 }
 
+
 static QEMUOptionParameter raw_create_options[] = {
     {
         .name = BLOCK_OPT_SIZE,
@@ -631,9 +742,11 @@ static BlockDriver bdrv_file = {
     .instance_size = sizeof(BDRVRawState),
     .bdrv_probe = NULL, /* no probe for protocols */
     .bdrv_file_open = raw_open,
+    .bdrv_read = raw_read,
+    .bdrv_write = raw_write,
     .bdrv_close = raw_close,
     .bdrv_create = raw_create,
-    .bdrv_co_discard = raw_co_discard,
+    .bdrv_flush = raw_flush,
 
     .bdrv_aio_readv = raw_aio_readv,
     .bdrv_aio_writev = raw_aio_writev,
@@ -641,8 +754,6 @@ static BlockDriver bdrv_file = {
 
     .bdrv_truncate = raw_truncate,
     .bdrv_getlength = raw_getlength,
-    .bdrv_get_allocated_file_size
-                        = raw_get_allocated_file_size,
 
     .create_options = raw_create_options,
 };
@@ -757,13 +868,8 @@ static int hdev_open(BlockDriverState *bs, const char *filename, int flags)
 
     s->type = FTYPE_FILE;
 #if defined(__linux__)
-    {
-        char resolved_path[ MAXPATHLEN ], *temp;
-
-        temp = realpath(filename, resolved_path);
-        if (temp && strstart(temp, "/dev/sg", NULL)) {
-            bs->sg = 1;
-        }
+    if (strstart(filename, "/dev/sg", NULL)) {
+        bs->sg = 1;
     }
 #endif
 
@@ -783,7 +889,7 @@ static int fd_open(BlockDriverState *bs)
         return 0;
     last_media_present = (s->fd >= 0);
     if (s->fd >= 0 &&
-        (get_clock() - s->fd_open_time) >= FD_OPEN_TIMEOUT) {
+        (qemu_get_clock(rt_clock) - s->fd_open_time) >= FD_OPEN_TIMEOUT) {
         close(s->fd);
         s->fd = -1;
 #ifdef DEBUG_FLOPPY
@@ -792,7 +898,7 @@ static int fd_open(BlockDriverState *bs)
     }
     if (s->fd < 0) {
         if (s->fd_got_error &&
-            (get_clock() - s->fd_error_time) < FD_OPEN_TIMEOUT) {
+            (qemu_get_clock(rt_clock) - s->fd_error_time) < FD_OPEN_TIMEOUT) {
 #ifdef DEBUG_FLOPPY
             printf("No floppy (open delayed)\n");
 #endif
@@ -800,7 +906,7 @@ static int fd_open(BlockDriverState *bs)
         }
         s->fd = open(bs->filename, s->open_flags & ~O_NONBLOCK);
         if (s->fd < 0) {
-            s->fd_error_time = get_clock();
+            s->fd_error_time = qemu_get_clock(rt_clock);
             s->fd_got_error = 1;
             if (last_media_present)
                 s->fd_media_changed = 1;
@@ -815,7 +921,7 @@ static int fd_open(BlockDriverState *bs)
     }
     if (!last_media_present)
         s->fd_media_changed = 1;
-    s->fd_open_time = get_clock();
+    s->fd_open_time = qemu_get_clock(rt_clock);
     s->fd_got_error = 0;
     return 0;
 }
@@ -902,15 +1008,15 @@ static BlockDriver bdrv_host_device = {
     .bdrv_create        = hdev_create,
     .create_options     = raw_create_options,
     .bdrv_has_zero_init = hdev_has_zero_init,
+    .bdrv_flush         = raw_flush,
 
     .bdrv_aio_readv	= raw_aio_readv,
     .bdrv_aio_writev	= raw_aio_writev,
     .bdrv_aio_flush	= raw_aio_flush,
 
-    .bdrv_truncate      = raw_truncate,
+    .bdrv_read          = raw_read,
+    .bdrv_write         = raw_write,
     .bdrv_getlength	= raw_getlength,
-    .bdrv_get_allocated_file_size
-                        = raw_get_allocated_file_size,
 
     /* generic scsi device */
 #ifdef __linux__
@@ -945,7 +1051,6 @@ static int floppy_probe_device(const char *filename)
     int fd, ret;
     int prio = 0;
     struct floppy_struct fdparam;
-    struct stat st;
 
     if (strstart(filename, "/dev/fd", NULL))
         prio = 50;
@@ -954,17 +1059,12 @@ static int floppy_probe_device(const char *filename)
     if (fd < 0) {
         goto out;
     }
-    ret = fstat(fd, &st);
-    if (ret == -1 || !S_ISBLK(st.st_mode)) {
-        goto outc;
-    }
 
     /* Attempt to detect via a floppy specific ioctl */
     ret = ioctl(fd, FDGETPRM, &fdparam);
     if (ret >= 0)
         prio = 100;
 
-outc:
     close(fd);
 out:
     return prio;
@@ -994,7 +1094,7 @@ static int floppy_media_changed(BlockDriverState *bs)
     return ret;
 }
 
-static void floppy_eject(BlockDriverState *bs, int eject_flag)
+static int floppy_eject(BlockDriverState *bs, int eject_flag)
 {
     BDRVRawState *s = bs->opaque;
     int fd;
@@ -1009,6 +1109,8 @@ static void floppy_eject(BlockDriverState *bs, int eject_flag)
             perror("FDEJECT");
         close(fd);
     }
+
+    return 0;
 }
 
 static BlockDriver bdrv_host_floppy = {
@@ -1021,15 +1123,15 @@ static BlockDriver bdrv_host_floppy = {
     .bdrv_create        = hdev_create,
     .create_options     = raw_create_options,
     .bdrv_has_zero_init = hdev_has_zero_init,
+    .bdrv_flush         = raw_flush,
 
     .bdrv_aio_readv     = raw_aio_readv,
     .bdrv_aio_writev    = raw_aio_writev,
     .bdrv_aio_flush	= raw_aio_flush,
 
-    .bdrv_truncate      = raw_truncate,
+    .bdrv_read          = raw_read,
+    .bdrv_write         = raw_write,
     .bdrv_getlength	= raw_getlength,
-    .bdrv_get_allocated_file_size
-                        = raw_get_allocated_file_size,
 
     /* removable device support */
     .bdrv_is_inserted   = floppy_is_inserted,
@@ -1051,23 +1153,17 @@ static int cdrom_probe_device(const char *filename)
 {
     int fd, ret;
     int prio = 0;
-    struct stat st;
 
     fd = open(filename, O_RDONLY | O_NONBLOCK);
     if (fd < 0) {
         goto out;
     }
-    ret = fstat(fd, &st);
-    if (ret == -1 || !S_ISBLK(st.st_mode)) {
-        goto outc;
-    }
 
     /* Attempt to detect via a CDROM specific ioctl */
     ret = ioctl(fd, CDROM_DRIVE_STATUS, CDSL_CURRENT);
     if (ret >= 0)
         prio = 100;
 
-outc:
     close(fd);
 out:
     return prio;
@@ -1084,7 +1180,7 @@ static int cdrom_is_inserted(BlockDriverState *bs)
     return 0;
 }
 
-static void cdrom_eject(BlockDriverState *bs, int eject_flag)
+static int cdrom_eject(BlockDriverState *bs, int eject_flag)
 {
     BDRVRawState *s = bs->opaque;
 
@@ -1095,9 +1191,11 @@ static void cdrom_eject(BlockDriverState *bs, int eject_flag)
         if (ioctl(s->fd, CDROMCLOSETRAY, NULL) < 0)
             perror("CDROMEJECT");
     }
+
+    return 0;
 }
 
-static void cdrom_lock_medium(BlockDriverState *bs, bool locked)
+static int cdrom_set_locked(BlockDriverState *bs, int locked)
 {
     BDRVRawState *s = bs->opaque;
 
@@ -1108,6 +1206,8 @@ static void cdrom_lock_medium(BlockDriverState *bs, bool locked)
          */
         /* perror("CDROM_LOCKDOOR"); */
     }
+
+    return 0;
 }
 
 static BlockDriver bdrv_host_cdrom = {
@@ -1120,20 +1220,20 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_create        = hdev_create,
     .create_options     = raw_create_options,
     .bdrv_has_zero_init = hdev_has_zero_init,
+    .bdrv_flush         = raw_flush,
 
     .bdrv_aio_readv     = raw_aio_readv,
     .bdrv_aio_writev    = raw_aio_writev,
     .bdrv_aio_flush	= raw_aio_flush,
 
-    .bdrv_truncate      = raw_truncate,
+    .bdrv_read          = raw_read,
+    .bdrv_write         = raw_write,
     .bdrv_getlength     = raw_getlength,
-    .bdrv_get_allocated_file_size
-                        = raw_get_allocated_file_size,
 
     /* removable device support */
     .bdrv_is_inserted   = cdrom_is_inserted,
     .bdrv_eject         = cdrom_eject,
-    .bdrv_lock_medium   = cdrom_lock_medium,
+    .bdrv_set_locked    = cdrom_set_locked,
 
     /* generic scsi device */
     .bdrv_ioctl         = hdev_ioctl,
@@ -1194,12 +1294,12 @@ static int cdrom_is_inserted(BlockDriverState *bs)
     return raw_getlength(bs) > 0;
 }
 
-static void cdrom_eject(BlockDriverState *bs, int eject_flag)
+static int cdrom_eject(BlockDriverState *bs, int eject_flag)
 {
     BDRVRawState *s = bs->opaque;
 
     if (s->fd < 0)
-        return;
+        return -ENOTSUP;
 
     (void) ioctl(s->fd, CDIOCALLOW);
 
@@ -1211,15 +1311,17 @@ static void cdrom_eject(BlockDriverState *bs, int eject_flag)
             perror("CDIOCCLOSE");
     }
 
-    cdrom_reopen(bs);
+    if (cdrom_reopen(bs) < 0)
+        return -ENOTSUP;
+    return 0;
 }
 
-static void cdrom_lock_medium(BlockDriverState *bs, bool locked)
+static int cdrom_set_locked(BlockDriverState *bs, int locked)
 {
     BDRVRawState *s = bs->opaque;
 
     if (s->fd < 0)
-        return;
+        return -ENOTSUP;
     if (ioctl(s->fd, (locked ? CDIOCPREVENT : CDIOCALLOW)) < 0) {
         /*
          * Note: an error can happen if the distribution automatically
@@ -1227,6 +1329,8 @@ static void cdrom_lock_medium(BlockDriverState *bs, bool locked)
          */
         /* perror("CDROM_LOCKDOOR"); */
     }
+
+    return 0;
 }
 
 static BlockDriver bdrv_host_cdrom = {
@@ -1239,20 +1343,20 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_create        = hdev_create,
     .create_options     = raw_create_options,
     .bdrv_has_zero_init = hdev_has_zero_init,
+    .bdrv_flush         = raw_flush,
 
     .bdrv_aio_readv     = raw_aio_readv,
     .bdrv_aio_writev    = raw_aio_writev,
     .bdrv_aio_flush	= raw_aio_flush,
 
-    .bdrv_truncate      = raw_truncate,
+    .bdrv_read          = raw_read,
+    .bdrv_write         = raw_write,
     .bdrv_getlength     = raw_getlength,
-    .bdrv_get_allocated_file_size
-                        = raw_get_allocated_file_size,
 
     /* removable device support */
     .bdrv_is_inserted   = cdrom_is_inserted,
     .bdrv_eject         = cdrom_eject,
-    .bdrv_lock_medium   = cdrom_lock_medium,
+    .bdrv_set_locked    = cdrom_set_locked,
 };
 #endif /* __FreeBSD__ */
 

block/raw-win32.c

@@ -41,7 +41,6 @@ typedef struct BDRVRawState {
 int qemu_ftruncate64(int fd, int64_t length)
 {
     LARGE_INTEGER li;
-    DWORD dw;
     LONG high;
     HANDLE h;
     BOOL res;
@@ -54,15 +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 */
@@ -92,9 +88,9 @@ static int raw_open(BlockDriverState *bs, const char *filename, int flags)
     }
 
     overlapped = FILE_ATTRIBUTE_NORMAL;
-    if (flags & BDRV_O_NOCACHE)
-        overlapped |= FILE_FLAG_NO_BUFFERING;
-    if (!(flags & BDRV_O_CACHE_WB))
+    if ((flags & BDRV_O_NOCACHE))
+        overlapped |= FILE_FLAG_NO_BUFFERING | FILE_FLAG_WRITE_THROUGH;
+    else if (!(flags & BDRV_O_CACHE_WB))
         overlapped |= FILE_FLAG_WRITE_THROUGH;
     s->hfile = CreateFile(filename, access_flags,
                           FILE_SHARE_READ, NULL,
@@ -151,17 +147,10 @@ static int raw_write(BlockDriverState *bs, int64_t sector_num,
     return ret_count;
 }
 
-static int raw_flush(BlockDriverState *bs)
+static void raw_flush(BlockDriverState *bs)
 {
     BDRVRawState *s = bs->opaque;
-    int ret;
-
-    ret = FlushFileBuffers(s->hfile);
-    if (ret == 0) {
-        return -EIO;
-    }
-
-    return 0;
+    FlushFileBuffers(s->hfile);
 }
 
 static void raw_close(BlockDriverState *bs)
@@ -217,31 +206,6 @@ static int64_t raw_getlength(BlockDriverState *bs)
     return l.QuadPart;
 }
 
-static int64_t raw_get_allocated_file_size(BlockDriverState *bs)
-{
-    typedef DWORD (WINAPI * get_compressed_t)(const char *filename,
-                                              DWORD * high);
-    get_compressed_t get_compressed;
-    struct _stati64 st;
-    const char *filename = bs->filename;
-    /* WinNT support GetCompressedFileSize to determine allocate size */
-    get_compressed =
-        (get_compressed_t) GetProcAddress(GetModuleHandle("kernel32"),
-                                            "GetCompressedFileSizeA");
-    if (get_compressed) {
-        DWORD high, low;
-        low = get_compressed(filename, &high);
-        if (low != 0xFFFFFFFFlu || GetLastError() == NO_ERROR) {
-            return (((int64_t) high) << 32) + low;
-        }
-    }
-
-    if (_stati64(filename, &st) < 0) {
-        return -1;
-    }
-    return st.st_size;
-}
-
 static int raw_create(const char *filename, QEMUOptionParameter *options)
 {
     int fd;
@@ -281,15 +245,11 @@ static BlockDriver bdrv_file = {
     .bdrv_file_open	= raw_open,
     .bdrv_close		= raw_close,
     .bdrv_create	= raw_create,
-
-    .bdrv_read              = raw_read,
-    .bdrv_write             = raw_write,
-    .bdrv_co_flush_to_disk  = raw_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
-                        = raw_get_allocated_file_size,
 
     .create_options = raw_create_options,
 };
@@ -382,9 +342,9 @@ static int hdev_open(BlockDriverState *bs, const char *filename, int flags)
     create_flags = OPEN_EXISTING;
 
     overlapped = FILE_ATTRIBUTE_NORMAL;
-    if (flags & BDRV_O_NOCACHE)
-        overlapped |= FILE_FLAG_NO_BUFFERING;
-    if (!(flags & BDRV_O_CACHE_WB))
+    if ((flags & BDRV_O_NOCACHE))
+        overlapped |= FILE_FLAG_NO_BUFFERING | FILE_FLAG_WRITE_THROUGH;
+    else if (!(flags & BDRV_O_CACHE_WB))
         overlapped |= FILE_FLAG_WRITE_THROUGH;
     s->hfile = CreateFile(filename, access_flags,
                           FILE_SHARE_READ, NULL,
@@ -399,6 +359,41 @@ 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;
@@ -411,15 +406,12 @@ 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_read              = raw_read,
-    .bdrv_write             = raw_write,
-    .bdrv_co_flush_to_disk  = raw_flush,
-
+    .bdrv_read		= raw_read,
+    .bdrv_write	        = raw_write,
     .bdrv_getlength	= raw_getlength,
-    .bdrv_get_allocated_file_size
-                        = raw_get_allocated_file_size,
 };
 
 static void bdrv_file_init(void)

block/raw.c

@@ -9,25 +9,45 @@ static int raw_open(BlockDriverState *bs, int flags)
     return 0;
 }
 
-static int coroutine_fn raw_co_readv(BlockDriverState *bs, int64_t sector_num,
-                                     int nb_sectors, QEMUIOVector *qiov)
+static int raw_read(BlockDriverState *bs, int64_t sector_num,
+                    uint8_t *buf, int nb_sectors)
 {
-    return bdrv_co_readv(bs->file, sector_num, nb_sectors, qiov);
+    return bdrv_read(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 int raw_write(BlockDriverState *bs, int64_t sector_num,
+                     const uint8_t *buf, int nb_sectors)
 {
-    return bdrv_co_writev(bs->file, sector_num, nb_sectors, qiov);
+    return bdrv_write(bs->file, sector_num, buf, nb_sectors);
+}
+
+static BlockDriverAIOCB *raw_aio_readv(BlockDriverState *bs,
+    int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+    BlockDriverCompletionFunc *cb, void *opaque)
+{
+    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_flush(BlockDriverState *bs)
+static void raw_flush(BlockDriverState *bs)
 {
-    return bdrv_co_flush(bs->file);
+    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)
@@ -45,30 +65,20 @@ static int raw_probe(const uint8_t *buf, int buf_size, const char *filename)
    return 1; /* everything can be opened as raw image */
 }
 
-static int coroutine_fn raw_co_discard(BlockDriverState *bs,
-                                       int64_t sector_num, int nb_sectors)
-{
-    return bdrv_co_discard(bs->file, sector_num, nb_sectors);
-}
-
 static int raw_is_inserted(BlockDriverState *bs)
 {
     return bdrv_is_inserted(bs->file);
 }
 
-static int raw_media_changed(BlockDriverState *bs)
+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, int 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)
@@ -105,26 +115,25 @@ 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_co_readv          = raw_co_readv,
-    .bdrv_co_writev         = raw_co_writev,
-    .bdrv_co_flush_to_disk  = raw_co_flush,
-    .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_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

@@ -1,874 +0,0 @@
-/*
- * QEMU Block driver for RADOS (Ceph)
- *
- * 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.
- *
- */
-
-#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.
- *
- * devicename is the name of the rbd image.
- *
- * Each option given is used to configure rados, and may be any valid
- * Ceph option, "id", or "conf".
- *
- * 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').
- *
- * 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.
- *
- * Configuration values containing :, @, or = can be escaped with a
- * leading "\".
- */
-
-#define OBJ_MAX_SIZE (1UL << OBJ_DEFAULT_OBJ_ORDER)
-
-#define RBD_MAX_CONF_NAME_SIZE 128
-#define RBD_MAX_CONF_VAL_SIZE 512
-#define RBD_MAX_CONF_SIZE 1024
-#define RBD_MAX_POOL_NAME_SIZE 128
-#define RBD_MAX_SNAP_NAME_SIZE 128
-#define RBD_MAX_SNAPS 100
-
-typedef struct RBDAIOCB {
-    BlockDriverAIOCB common;
-    QEMUBH *bh;
-    int ret;
-    QEMUIOVector *qiov;
-    char *bounce;
-    int write;
-    int64_t sector_num;
-    int error;
-    struct BDRVRBDState *s;
-    int cancelled;
-} RBDAIOCB;
-
-typedef struct RADOSCB {
-    int rcbid;
-    RBDAIOCB *acb;
-    struct BDRVRBDState *s;
-    int done;
-    int64_t size;
-    char *buf;
-    int ret;
-} RADOSCB;
-
-#define RBD_FD_READ 0
-#define RBD_FD_WRITE 1
-
-typedef struct BDRVRBDState {
-    int fds[2];
-    rados_t cluster;
-    rados_ioctx_t io_ctx;
-    rbd_image_t image;
-    char name[RBD_MAX_IMAGE_NAME_SIZE];
-    int qemu_aio_count;
-    char *snap;
-    int event_reader_pos;
-    RADOSCB *event_rcb;
-} BDRVRBDState;
-
-static void rbd_aio_bh_cb(void *opaque);
-
-static int qemu_rbd_next_tok(char *dst, int dst_len,
-                             char *src, char delim,
-                             const char *name,
-                             char **p)
-{
-    int l;
-    char *end;
-
-    *p = NULL;
-
-    if (delim != '\0') {
-        for (end = src; *end; ++end) {
-            if (*end == delim) {
-                break;
-            }
-            if (*end == '\\' && end[1] != '\0') {
-                end++;
-            }
-        }
-        if (*end == delim) {
-            *p = end + 1;
-            *end = '\0';
-        }
-    }
-    l = strlen(src);
-    if (l >= dst_len) {
-        error_report("%s too long", name);
-        return -EINVAL;
-    } else if (l == 0) {
-        error_report("%s too short", name);
-        return -EINVAL;
-    }
-
-    pstrcpy(dst, dst_len, src);
-
-    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,
-                              char *name, int name_len,
-                              char *conf, int conf_len)
-{
-    const char *start;
-    char *p, *buf;
-    int ret;
-
-    if (!strstart(filename, "rbd:", &start)) {
-        return -EINVAL;
-    }
-
-    buf = g_strdup(start);
-    p = buf;
-    *snap = '\0';
-    *conf = '\0';
-
-    ret = qemu_rbd_next_tok(pool, pool_len, p, '/', "pool name", &p);
-    if (ret < 0 || !p) {
-        ret = -EINVAL;
-        goto done;
-    }
-    qemu_rbd_unescape(pool);
-
-    if (strchr(p, '@')) {
-        ret = qemu_rbd_next_tok(name, name_len, p, '@', "object name", &p);
-        if (ret < 0) {
-            goto done;
-        }
-        ret = qemu_rbd_next_tok(snap, snap_len, p, ':', "snap name", &p);
-        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;
-    }
-
-    ret = qemu_rbd_next_tok(conf, conf_len, p, '\0', "configuration", &p);
-
-done:
-    g_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;
-    char name[RBD_MAX_CONF_NAME_SIZE];
-    char value[RBD_MAX_CONF_VAL_SIZE];
-    int ret = 0;
-
-    buf = g_strdup(conf);
-    p = buf;
-
-    while (p) {
-        ret = qemu_rbd_next_tok(name, sizeof(name), p,
-                                '=', "conf option name", &p);
-        if (ret < 0) {
-            break;
-        }
-        qemu_rbd_unescape(name);
-
-        if (!p) {
-            error_report("conf option %s has no value", name);
-            ret = -EINVAL;
-            break;
-        }
-
-        ret = qemu_rbd_next_tok(value, sizeof(value), p,
-                                ':', "conf option value", &p);
-        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 {
-            ret = rados_conf_set(cluster, name, value);
-            if (ret < 0) {
-                error_report("invalid conf option %s", name);
-                ret = -EINVAL;
-                break;
-            }
-        }
-    }
-
-    g_free(buf);
-    return ret;
-}
-
-static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options)
-{
-    int64_t bytes = 0;
-    int64_t objsize;
-    int obj_order = 0;
-    char pool[RBD_MAX_POOL_NAME_SIZE];
-    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;
-
-    if (qemu_rbd_parsename(filename, pool, sizeof(pool),
-                           snap_buf, sizeof(snap_buf),
-                           name, sizeof(name),
-                           conf, sizeof(conf)) < 0) {
-        return -EINVAL;
-    }
-
-    /* Read out options */
-    while (options && options->name) {
-        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
-            bytes = options->value.n;
-        } else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) {
-            if (options->value.n) {
-                objsize = options->value.n;
-                if ((objsize - 1) & objsize) {    /* not a power of 2? */
-                    error_report("obj size needs to be power of 2");
-                    return -EINVAL;
-                }
-                if (objsize < 4096) {
-                    error_report("obj size too small");
-                    return -EINVAL;
-                }
-                obj_order = ffs(objsize) - 1;
-            }
-        }
-        options++;
-    }
-
-    clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
-    if (rados_create(&cluster, clientname) < 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 (conf[0] != '\0' &&
-        qemu_rbd_set_conf(cluster, conf) < 0) {
-        error_report("error setting config options");
-        rados_shutdown(cluster);
-        return -EIO;
-    }
-
-    if (rados_connect(cluster) < 0) {
-        error_report("error connecting");
-        rados_shutdown(cluster);
-        return -EIO;
-    }
-
-    if (rados_ioctx_create(cluster, pool, &io_ctx) < 0) {
-        error_report("error opening pool %s", pool);
-        rados_shutdown(cluster);
-        return -EIO;
-    }
-
-    ret = rbd_create(io_ctx, name, bytes, &obj_order);
-    rados_ioctx_destroy(io_ctx);
-    rados_shutdown(cluster);
-
-    return ret;
-}
-
-/*
- * This aio completion is being called from qemu_rbd_aio_event_reader()
- * and runs in qemu context. It schedules a bh, but just in case the aio
- * was not cancelled before.
- */
-static void qemu_rbd_complete_aio(RADOSCB *rcb)
-{
-    RBDAIOCB *acb = rcb->acb;
-    int64_t r;
-
-    if (acb->cancelled) {
-        qemu_vfree(acb->bounce);
-        qemu_aio_release(acb);
-        goto done;
-    }
-
-    r = rcb->ret;
-
-    if (acb->write) {
-        if (r < 0) {
-            acb->ret = r;
-            acb->error = 1;
-        } else if (!acb->error) {
-            acb->ret = rcb->size;
-        }
-    } else {
-        if (r < 0) {
-            memset(rcb->buf, 0, rcb->size);
-            acb->ret = r;
-            acb->error = 1;
-        } else if (r < rcb->size) {
-            memset(rcb->buf + r, 0, rcb->size - r);
-            if (!acb->error) {
-                acb->ret = rcb->size;
-            }
-        } else if (!acb->error) {
-            acb->ret = r;
-        }
-    }
-    /* Note that acb->bh can be NULL in case where the aio was cancelled */
-    acb->bh = qemu_bh_new(rbd_aio_bh_cb, acb);
-    qemu_bh_schedule(acb->bh);
-done:
-    g_free(rcb);
-}
-
-/*
- * aio fd read handler. It runs in the qemu context and calls the
- * completion handling of completed rados aio operations.
- */
-static void qemu_rbd_aio_event_reader(void *opaque)
-{
-    BDRVRBDState *s = opaque;
-
-    ssize_t ret;
-
-    do {
-        char *p = (char *)&s->event_rcb;
-
-        /* now read the rcb pointer that was sent from a non qemu thread */
-        ret = read(s->fds[RBD_FD_READ], p + s->event_reader_pos,
-                   sizeof(s->event_rcb) - s->event_reader_pos);
-        if (ret > 0) {
-            s->event_reader_pos += ret;
-            if (s->event_reader_pos == sizeof(s->event_rcb)) {
-                s->event_reader_pos = 0;
-                qemu_rbd_complete_aio(s->event_rcb);
-                s->qemu_aio_count--;
-            }
-        }
-    } while (ret < 0 && errno == EINTR);
-}
-
-static int qemu_rbd_aio_flush_cb(void *opaque)
-{
-    BDRVRBDState *s = opaque;
-
-    return (s->qemu_aio_count > 0);
-}
-
-static int qemu_rbd_open(BlockDriverState *bs, const char *filename, int flags)
-{
-    BDRVRBDState *s = bs->opaque;
-    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),
-                           snap_buf, sizeof(snap_buf),
-                           s->name, sizeof(s->name),
-                           conf, sizeof(conf)) < 0) {
-        return -EINVAL;
-    }
-
-    clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
-    r = rados_create(&s->cluster, clientname);
-    if (r < 0) {
-        error_report("error initializing");
-        return r;
-    }
-
-    s->snap = NULL;
-    if (snap_buf[0] != '\0') {
-        s->snap = g_strdup(snap_buf);
-    }
-
-    if (strstr(conf, "conf=") == NULL) {
-        /* try default location, but ignore failure */
-        rados_conf_read_file(s->cluster, NULL);
-    }
-
-    if (conf[0] != '\0') {
-        r = qemu_rbd_set_conf(s->cluster, conf);
-        if (r < 0) {
-            error_report("error setting config options");
-            goto failed_shutdown;
-        }
-    }
-
-    r = rados_connect(s->cluster);
-    if (r < 0) {
-        error_report("error connecting");
-        goto failed_shutdown;
-    }
-
-    r = rados_ioctx_create(s->cluster, pool, &s->io_ctx);
-    if (r < 0) {
-        error_report("error opening pool %s", pool);
-        goto failed_shutdown;
-    }
-
-    r = rbd_open(s->io_ctx, s->name, &s->image, s->snap);
-    if (r < 0) {
-        error_report("error reading header from %s", s->name);
-        goto failed_open;
-    }
-
-    bs->read_only = (s->snap != NULL);
-
-    s->event_reader_pos = 0;
-    r = qemu_pipe(s->fds);
-    if (r < 0) {
-        error_report("error opening eventfd");
-        goto failed;
-    }
-    fcntl(s->fds[0], F_SETFL, O_NONBLOCK);
-    fcntl(s->fds[1], F_SETFL, O_NONBLOCK);
-    qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], qemu_rbd_aio_event_reader,
-                            NULL, qemu_rbd_aio_flush_cb, 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;
-}
-
-static void qemu_rbd_close(BlockDriverState *bs)
-{
-    BDRVRBDState *s = bs->opaque;
-
-    close(s->fds[0]);
-    close(s->fds[1]);
-    qemu_aio_set_fd_handler(s->fds[RBD_FD_READ], NULL , NULL, NULL, NULL,
-        NULL);
-
-    rbd_close(s->image);
-    rados_ioctx_destroy(s->io_ctx);
-    g_free(s->snap);
-    rados_shutdown(s->cluster);
-}
-
-/*
- * Cancel aio. Since we don't reference acb in a non qemu threads,
- * it is safe to access it here.
- */
-static void qemu_rbd_aio_cancel(BlockDriverAIOCB *blockacb)
-{
-    RBDAIOCB *acb = (RBDAIOCB *) blockacb;
-    acb->cancelled = 1;
-}
-
-static AIOPool rbd_aio_pool = {
-    .aiocb_size = sizeof(RBDAIOCB),
-    .cancel = qemu_rbd_aio_cancel,
-};
-
-static int qemu_rbd_send_pipe(BDRVRBDState *s, RADOSCB *rcb)
-{
-    int ret = 0;
-    while (1) {
-        fd_set wfd;
-        int fd = s->fds[RBD_FD_WRITE];
-
-        /* send the op pointer to the qemu thread that is responsible
-           for the aio/op completion. Must do it in a qemu thread context */
-        ret = write(fd, (void *)&rcb, sizeof(rcb));
-        if (ret >= 0) {
-            break;
-        }
-        if (errno == EINTR) {
-            continue;
-        }
-        if (errno != EAGAIN) {
-            break;
-        }
-
-        FD_ZERO(&wfd);
-        FD_SET(fd, &wfd);
-        do {
-            ret = select(fd + 1, NULL, &wfd, NULL, NULL);
-        } while (ret < 0 && errno == EINTR);
-    }
-
-    return ret;
-}
-
-/*
- * This is the callback function for rbd_aio_read and _write
- *
- * Note: this function is being called from a non qemu thread so
- * we need to be careful about what we do here. Generally we only
- * write to the block notification pipe, and do the rest of the
- * io completion handling from qemu_rbd_aio_event_reader() which
- * runs in a qemu context.
- */
-static void rbd_finish_aiocb(rbd_completion_t c, RADOSCB *rcb)
-{
-    int ret;
-    rcb->ret = rbd_aio_get_return_value(c);
-    rbd_aio_release(c);
-    ret = qemu_rbd_send_pipe(rcb->s, rcb);
-    if (ret < 0) {
-        error_report("failed writing to acb->s->fds");
-        g_free(rcb);
-    }
-}
-
-/* Callback when all queued rbd_aio requests are complete */
-
-static void rbd_aio_bh_cb(void *opaque)
-{
-    RBDAIOCB *acb = opaque;
-
-    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));
-    qemu_bh_delete(acb->bh);
-    acb->bh = NULL;
-
-    qemu_aio_release(acb);
-}
-
-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;
-    rbd_completion_t c;
-    int64_t off, size;
-    char *buf;
-    int r;
-
-    BDRVRBDState *s = bs->opaque;
-
-    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 (write) {
-        qemu_iovec_to_buffer(acb->qiov, acb->bounce);
-    }
-
-    buf = acb->bounce;
-
-    off = sector_num * BDRV_SECTOR_SIZE;
-    size = nb_sectors * BDRV_SECTOR_SIZE;
-
-    s->qemu_aio_count++; /* All the RADOSCB */
-
-    rcb = g_malloc(sizeof(RADOSCB));
-    rcb->done = 0;
-    rcb->acb = acb;
-    rcb->buf = buf;
-    rcb->s = acb->s;
-    rcb->size = size;
-    r = rbd_aio_create_completion(rcb, (rbd_callback_t) rbd_finish_aiocb, &c);
-    if (r < 0) {
-        goto failed;
-    }
-
-    if (write) {
-        r = rbd_aio_write(s->image, off, size, buf, c);
-    } else {
-        r = rbd_aio_read(s->image, off, size, buf, c);
-    }
-
-    if (r < 0) {
-        goto failed;
-    }
-
-    return &acb->common;
-
-failed:
-    g_free(rcb);
-    s->qemu_aio_count--;
-    qemu_aio_release(acb);
-    return NULL;
-}
-
-static BlockDriverAIOCB *qemu_rbd_aio_readv(BlockDriverState *bs,
-                                            int64_t sector_num,
-                                            QEMUIOVector *qiov,
-                                            int nb_sectors,
-                                            BlockDriverCompletionFunc *cb,
-                                            void *opaque)
-{
-    return rbd_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
-}
-
-static BlockDriverAIOCB *qemu_rbd_aio_writev(BlockDriverState *bs,
-                                             int64_t sector_num,
-                                             QEMUIOVector *qiov,
-                                             int nb_sectors,
-                                             BlockDriverCompletionFunc *cb,
-                                             void *opaque)
-{
-    return rbd_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque, 1);
-}
-
-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
-}
-
-static int qemu_rbd_getinfo(BlockDriverState *bs, BlockDriverInfo *bdi)
-{
-    BDRVRBDState *s = bs->opaque;
-    rbd_image_info_t info;
-    int r;
-
-    r = rbd_stat(s->image, &info, sizeof(info));
-    if (r < 0) {
-        return r;
-    }
-
-    bdi->cluster_size = info.obj_size;
-    return 0;
-}
-
-static int64_t qemu_rbd_getlength(BlockDriverState *bs)
-{
-    BDRVRBDState *s = bs->opaque;
-    rbd_image_info_t info;
-    int r;
-
-    r = rbd_stat(s->image, &info, sizeof(info));
-    if (r < 0) {
-        return r;
-    }
-
-    return info.size;
-}
-
-static int qemu_rbd_truncate(BlockDriverState *bs, int64_t offset)
-{
-    BDRVRBDState *s = bs->opaque;
-    int r;
-
-    r = rbd_resize(s->image, offset);
-    if (r < 0) {
-        return r;
-    }
-
-    return 0;
-}
-
-static int qemu_rbd_snap_create(BlockDriverState *bs,
-                                QEMUSnapshotInfo *sn_info)
-{
-    BDRVRBDState *s = bs->opaque;
-    int r;
-
-    if (sn_info->name[0] == '\0') {
-        return -EINVAL; /* we need a name for rbd snapshots */
-    }
-
-    /*
-     * rbd snapshots are using the name as the user controlled unique identifier
-     * we can't use the rbd snapid for that purpose, as it can't be set
-     */
-    if (sn_info->id_str[0] != '\0' &&
-        strcmp(sn_info->id_str, sn_info->name) != 0) {
-        return -EINVAL;
-    }
-
-    if (strlen(sn_info->name) >= sizeof(sn_info->id_str)) {
-        return -ERANGE;
-    }
-
-    r = rbd_snap_create(s->image, sn_info->name);
-    if (r < 0) {
-        error_report("failed to create snap: %s", strerror(-r));
-        return r;
-    }
-
-    return 0;
-}
-
-static int qemu_rbd_snap_list(BlockDriverState *bs,
-                              QEMUSnapshotInfo **psn_tab)
-{
-    BDRVRBDState *s = bs->opaque;
-    QEMUSnapshotInfo *sn_info, *sn_tab = NULL;
-    int i, snap_count;
-    rbd_snap_info_t *snaps;
-    int max_snaps = RBD_MAX_SNAPS;
-
-    do {
-        snaps = g_malloc(sizeof(*snaps) * max_snaps);
-        snap_count = rbd_snap_list(s->image, snaps, &max_snaps);
-        if (snap_count < 0) {
-            g_free(snaps);
-        }
-    } while (snap_count == -ERANGE);
-
-    if (snap_count <= 0) {
-        goto done;
-    }
-
-    sn_tab = g_malloc0(snap_count * sizeof(QEMUSnapshotInfo));
-
-    for (i = 0; i < snap_count; i++) {
-        const char *snap_name = snaps[i].name;
-
-        sn_info = sn_tab + i;
-        pstrcpy(sn_info->id_str, sizeof(sn_info->id_str), snap_name);
-        pstrcpy(sn_info->name, sizeof(sn_info->name), snap_name);
-
-        sn_info->vm_state_size = snaps[i].size;
-        sn_info->date_sec = 0;
-        sn_info->date_nsec = 0;
-        sn_info->vm_clock_nsec = 0;
-    }
-    rbd_snap_list_end(snaps);
-
- done:
-    *psn_tab = sn_tab;
-    return snap_count;
-}
-
-static QEMUOptionParameter qemu_rbd_create_options[] = {
-    {
-     .name = BLOCK_OPT_SIZE,
-     .type = OPT_SIZE,
-     .help = "Virtual disk size"
-    },
-    {
-     .name = BLOCK_OPT_CLUSTER_SIZE,
-     .type = OPT_SIZE,
-     .help = "RBD object size"
-    },
-    {NULL}
-};
-
-static BlockDriver bdrv_rbd = {
-    .format_name        = "rbd",
-    .instance_size      = sizeof(BDRVRBDState),
-    .bdrv_file_open     = qemu_rbd_open,
-    .bdrv_close         = qemu_rbd_close,
-    .bdrv_create        = qemu_rbd_create,
-    .bdrv_get_info      = qemu_rbd_getinfo,
-    .create_options     = qemu_rbd_create_options,
-    .bdrv_getlength     = qemu_rbd_getlength,
-    .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_snapshot_create   = qemu_rbd_snap_create,
-    .bdrv_snapshot_list     = qemu_rbd_snap_list,
-};
-
-static void bdrv_rbd_init(void)
-{
-    bdrv_register(&bdrv_rbd);
-}
-
-block_init(bdrv_rbd_init);

block/sheepdog.c

@@ -8,12 +8,21 @@
  * You should have received a copy of the GNU General Public License
  * along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
+#ifdef _WIN32
+#include <windows.h>
+#include <winsock2.h>
+#include <ws2tcpip.h>
+#else
+#include <netdb.h>
+#include <netinet/tcp.h>
+
+#define closesocket(s) close(s)
+#endif
 
 #include "qemu-common.h"
 #include "qemu-error.h"
 #include "qemu_socket.h"
 #include "block_int.h"
-#include "bitops.h"
 
 #define SD_PROTO_VER 0x01
 
@@ -66,7 +75,7 @@
  * 20 - 31 (12 bits): reserved data object space
  * 32 - 55 (24 bits): vdi object space
  * 56 - 59 ( 4 bits): reserved vdi object space
- * 60 - 63 ( 4 bits): object type identifier space
+ * 60 - 63 ( 4 bits): object type indentifier space
  */
 
 #define VDI_SPACE_SHIFT   32
@@ -196,7 +205,7 @@ static inline uint64_t fnv_64a_buf(void *buf, size_t len, uint64_t hval)
     return hval;
 }
 
-static inline int is_data_obj_writable(SheepdogInode *inode, unsigned int idx)
+static inline int is_data_obj_writeable(SheepdogInode *inode, unsigned int idx)
 {
     return inode->vdi_id == inode->data_vdi_id[idx];
 }
@@ -274,7 +283,7 @@ struct SheepdogAIOCB {
     int ret;
     enum AIOCBState aiocb_type;
 
-    Coroutine *coroutine;
+    QEMUBH *bh;
     void (*aio_done_func)(SheepdogAIOCB *);
 
     int canceled;
@@ -295,10 +304,6 @@ typedef struct BDRVSheepdogState {
     char *port;
     int fd;
 
-    CoMutex lock;
-    Coroutine *co_send;
-    Coroutine *co_recv;
-
     uint32_t aioreq_seq_num;
     QLIST_HEAD(outstanding_aio_head, AIOReq) outstanding_aio_head;
 } BDRVSheepdogState;
@@ -350,16 +355,19 @@ static const char * sd_strerror(int err)
 /*
  * Sheepdog I/O handling:
  *
- * 1. In sd_co_rw_vector, we send the I/O requests to the server and
- *    link the requests to the outstanding_list in the
- *    BDRVSheepdogState.  The function exits without waiting for
- *    receiving the response.
+ * 1. In the sd_aio_readv/writev, read/write requests are added to the
+ *    QEMU Bottom Halves.
  *
- * 2. We receive the response in aio_read_response, the fd handler to
+ * 2. In sd_readv_writev_bh_cb, the callbacks of BHs, we send the I/O
+ *    requests to the server and link the requests to the
+ *    outstanding_list in the BDRVSheepdogState.  we exits the
+ *    function without waiting for receiving the response.
+ *
+ * 3. We receive the response in aio_read_response, the fd handler to
  *    the sheepdog connection.  If metadata update is needed, we send
  *    the write request to the vdi object in sd_write_done, the write
- *    completion function.  We switch back to sd_co_readv/writev after
- *    all the requests belonging to the AIOCB are finished.
+ *    completion function.  The AIOCB callback is not called until all
+ *    the requests belonging to the AIOCB are finished.
  */
 
 static inline AIOReq *alloc_aio_req(BDRVSheepdogState *s, SheepdogAIOCB *acb,
@@ -369,7 +377,7 @@ static inline AIOReq *alloc_aio_req(BDRVSheepdogState *s, SheepdogAIOCB *acb,
 {
     AIOReq *aio_req;
 
-    aio_req = g_malloc(sizeof(*aio_req));
+    aio_req = qemu_malloc(sizeof(*aio_req));
     aio_req->aiocb = acb;
     aio_req->iov_offset = iov_offset;
     aio_req->oid = oid;
@@ -391,15 +399,15 @@ static inline int free_aio_req(BDRVSheepdogState *s, AIOReq *aio_req)
     SheepdogAIOCB *acb = aio_req->aiocb;
     QLIST_REMOVE(aio_req, outstanding_aio_siblings);
     QLIST_REMOVE(aio_req, aioreq_siblings);
-    g_free(aio_req);
+    qemu_free(aio_req);
 
     return !QLIST_EMPTY(&acb->aioreq_head);
 }
 
-static void coroutine_fn sd_finish_aiocb(SheepdogAIOCB *acb)
+static void sd_finish_aiocb(SheepdogAIOCB *acb)
 {
     if (!acb->canceled) {
-        qemu_coroutine_enter(acb->coroutine, NULL);
+        acb->common.cb(acb->common.opaque, acb->ret);
     }
     qemu_aio_release(acb);
 }
@@ -412,8 +420,7 @@ static void sd_aio_cancel(BlockDriverAIOCB *blockacb)
      * Sheepdog cannot cancel the requests which are already sent to
      * the servers, so we just complete the request with -EIO here.
      */
-    acb->ret = -EIO;
-    qemu_coroutine_enter(acb->coroutine, NULL);
+    acb->common.cb(acb->common.opaque, -EIO);
     acb->canceled = 1;
 }
 
@@ -437,12 +444,30 @@ static SheepdogAIOCB *sd_aio_setup(BlockDriverState *bs, QEMUIOVector *qiov,
 
     acb->aio_done_func = NULL;
     acb->canceled = 0;
-    acb->coroutine = qemu_coroutine_self();
+    acb->bh = NULL;
     acb->ret = 0;
     QLIST_INIT(&acb->aioreq_head);
     return acb;
 }
 
+static int sd_schedule_bh(QEMUBHFunc *cb, SheepdogAIOCB *acb)
+{
+    if (acb->bh) {
+        error_report("bug: %d %d\n", acb->aiocb_type, acb->aiocb_type);
+        return -EIO;
+    }
+
+    acb->bh = qemu_bh_new(cb, acb);
+    if (!acb->bh) {
+        error_report("oom: %d %d\n", acb->aiocb_type, acb->aiocb_type);
+        return -EIO;
+    }
+
+    qemu_bh_schedule(acb->bh);
+
+    return 0;
+}
+
 #ifdef _WIN32
 
 struct msghdr {
@@ -460,7 +485,7 @@ static ssize_t sendmsg(int s, const struct msghdr *msg, int flags)
     for (i = 0; i < msg->msg_iovlen; i++) {
         size += msg->msg_iov[i].iov_len;
     }
-    buf = g_malloc(size);
+    buf = qemu_malloc(size);
 
     p = buf;
     for (i = 0; i < msg->msg_iovlen; i++) {
@@ -470,7 +495,7 @@ static ssize_t sendmsg(int s, const struct msghdr *msg, int flags)
 
     ret = send(s, buf, size, flags);
 
-    g_free(buf);
+    qemu_free(buf);
     return ret;
 }
 
@@ -484,9 +509,9 @@ static ssize_t recvmsg(int s, struct msghdr *msg, int flags)
     for (i = 0; i < msg->msg_iovlen; i++) {
         size += msg->msg_iov[i].iov_len;
     }
-    buf = g_malloc(size);
+    buf = qemu_malloc(size);
 
-    ret = qemu_recv(s, buf, size, flags);
+    ret = recv(s, buf, size, flags);
     if (ret < 0) {
         goto out;
     }
@@ -497,7 +522,7 @@ static ssize_t recvmsg(int s, struct msghdr *msg, int flags)
         p += msg->msg_iov[i].iov_len;
     }
 out:
-    g_free(buf);
+    qemu_free(buf);
     return ret;
 }
 
@@ -582,7 +607,7 @@ static int connect_to_sdog(const char *addr, const char *port)
 
     ret = getaddrinfo(addr, port, &hints, &res0);
     if (ret) {
-        error_report("unable to get address info %s, %s",
+        error_report("unable to get address info %s, %s\n",
                      addr, strerror(errno));
         return -1;
     }
@@ -612,7 +637,7 @@ static int connect_to_sdog(const char *addr, const char *port)
         goto success;
     }
     fd = -1;
-    error_report("failed connect to %s:%s", addr, port);
+    error_report("failed connect to %s:%s\n", addr, port);
 success:
     freeaddrinfo(res0);
     return fd;
@@ -625,16 +650,10 @@ static int do_readv_writev(int sockfd, struct iovec *iov, int len,
 again:
     ret = do_send_recv(sockfd, iov, len, iov_offset, write);
     if (ret < 0) {
-        if (errno == EINTR) {
+        if (errno == EINTR || errno == EAGAIN) {
             goto again;
         }
-        if (errno == EAGAIN) {
-            if (qemu_in_coroutine()) {
-                qemu_coroutine_yield();
-            }
-            goto again;
-        }
-        error_report("failed to recv a rsp, %s", strerror(errno));
+        error_report("failed to recv a rsp, %s\n", strerror(errno));
         return 1;
     }
 
@@ -693,7 +712,7 @@ static int send_req(int sockfd, SheepdogReq *hdr, void *data,
 
     ret = do_writev(sockfd, iov, sizeof(*hdr) + *wlen, 0);
     if (ret) {
-        error_report("failed to send a req, %s", strerror(errno));
+        error_report("failed to send a req, %s\n", strerror(errno));
         ret = -1;
     }
 
@@ -713,7 +732,7 @@ static int do_req(int sockfd, SheepdogReq *hdr, void *data,
 
     ret = do_read(sockfd, hdr, sizeof(*hdr));
     if (ret) {
-        error_report("failed to get a rsp, %s", strerror(errno));
+        error_report("failed to get a rsp, %s\n", strerror(errno));
         ret = -1;
         goto out;
     }
@@ -725,7 +744,7 @@ static int do_req(int sockfd, SheepdogReq *hdr, void *data,
     if (*rlen) {
         ret = do_read(sockfd, data, *rlen);
         if (ret) {
-            error_report("failed to get the data, %s", strerror(errno));
+            error_report("failed to get the data, %s\n", strerror(errno));
             ret = -1;
             goto out;
         }
@@ -735,7 +754,7 @@ out:
     return ret;
 }
 
-static int coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
+static int add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
                            struct iovec *iov, int niov, int create,
                            enum AIOCBState aiocb_type);
 
@@ -743,7 +762,7 @@ static int coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
  * This function searchs pending requests to the object `oid', and
  * sends them.
  */
-static void coroutine_fn send_pending_req(BDRVSheepdogState *s, uint64_t oid, uint32_t id)
+static void send_pending_req(BDRVSheepdogState *s, uint64_t oid, uint32_t id)
 {
     AIOReq *aio_req, *next;
     SheepdogAIOCB *acb;
@@ -762,7 +781,7 @@ static void coroutine_fn send_pending_req(BDRVSheepdogState *s, uint64_t oid, ui
         ret = add_aio_request(s, aio_req, acb->qiov->iov,
                               acb->qiov->niov, 0, acb->aiocb_type);
         if (ret < 0) {
-            error_report("add_aio_request is failed");
+            error_report("add_aio_request is failed\n");
             free_aio_req(s, aio_req);
             if (QLIST_EMPTY(&acb->aioreq_head)) {
                 sd_finish_aiocb(acb);
@@ -777,7 +796,7 @@ static void coroutine_fn send_pending_req(BDRVSheepdogState *s, uint64_t oid, ui
  * This function is registered as a fd handler, and called from the
  * main loop when s->fd is ready for reading responses.
  */
-static void coroutine_fn aio_read_response(void *opaque)
+static void aio_read_response(void *opaque)
 {
     SheepdogObjRsp rsp;
     BDRVSheepdogState *s = opaque;
@@ -789,14 +808,14 @@ static void coroutine_fn aio_read_response(void *opaque)
     unsigned long idx;
 
     if (QLIST_EMPTY(&s->outstanding_aio_head)) {
-        goto out;
+        return;
     }
 
     /* read a header */
     ret = do_read(fd, &rsp, sizeof(rsp));
     if (ret) {
-        error_report("failed to get the header, %s", strerror(errno));
-        goto out;
+        error_report("failed to get the header, %s\n", strerror(errno));
+        return;
     }
 
     /* find the right aio_req from the outstanding_aio list */
@@ -806,8 +825,8 @@ static void coroutine_fn aio_read_response(void *opaque)
         }
     }
     if (!aio_req) {
-        error_report("cannot find aio_req %x", rsp.id);
-        goto out;
+        error_report("cannot find aio_req %x\n", rsp.id);
+        return;
     }
 
     acb = aio_req->aiocb;
@@ -842,45 +861,25 @@ static void coroutine_fn aio_read_response(void *opaque)
         ret = do_readv(fd, acb->qiov->iov, rsp.data_length,
                        aio_req->iov_offset);
         if (ret) {
-            error_report("failed to get the data, %s", strerror(errno));
-            goto out;
+            error_report("failed to get the data, %s\n", strerror(errno));
+            return;
         }
         break;
     }
 
     if (rsp.result != SD_RES_SUCCESS) {
         acb->ret = -EIO;
-        error_report("%s", sd_strerror(rsp.result));
+        error_report("%s\n", sd_strerror(rsp.result));
     }
 
     rest = free_aio_req(s, aio_req);
     if (!rest) {
         /*
          * We've finished all requests which belong to the AIOCB, so
-         * we can switch back to sd_co_readv/writev now.
+         * we can call the callback now.
          */
         acb->aio_done_func(acb);
     }
-out:
-    s->co_recv = NULL;
-}
-
-static void co_read_response(void *opaque)
-{
-    BDRVSheepdogState *s = opaque;
-
-    if (!s->co_recv) {
-        s->co_recv = qemu_coroutine_create(aio_read_response);
-    }
-
-    qemu_coroutine_enter(s->co_recv, opaque);
-}
-
-static void co_write_request(void *opaque)
-{
-    BDRVSheepdogState *s = opaque;
-
-    qemu_coroutine_enter(s->co_send, NULL);
 }
 
 static int aio_flush_request(void *opaque)
@@ -927,7 +926,7 @@ static int get_sheep_fd(BDRVSheepdogState *s)
 
     fd = connect_to_sdog(s->addr, s->port);
     if (fd < 0) {
-        error_report("%s", strerror(errno));
+        error_report("%s\n", strerror(errno));
         return -1;
     }
 
@@ -935,12 +934,12 @@ static int get_sheep_fd(BDRVSheepdogState *s)
 
     ret = set_nodelay(fd);
     if (ret) {
-        error_report("%s", strerror(errno));
+        error_report("%s\n", strerror(errno));
         closesocket(fd);
         return -1;
     }
 
-    qemu_aio_set_fd_handler(fd, co_read_response, NULL, aio_flush_request,
+    qemu_aio_set_fd_handler(fd, aio_read_response, NULL, aio_flush_request,
                             NULL, s);
     return fd;
 }
@@ -968,7 +967,7 @@ static int parse_vdiname(BDRVSheepdogState *s, const char *filename,
     char *p, *q;
     int nr_sep;
 
-    p = q = g_strdup(filename);
+    p = q = qemu_strdup(filename);
 
     /* count the number of separators */
     nr_sep = 0;
@@ -1008,7 +1007,7 @@ static int parse_vdiname(BDRVSheepdogState *s, const char *filename,
     }
 
     if (s->addr == NULL) {
-        g_free(q);
+        qemu_free(q);
     }
 
     return 0;
@@ -1051,7 +1050,7 @@ static int find_vdi_name(BDRVSheepdogState *s, char *filename, uint32_t snapid,
     }
 
     if (rsp->result != SD_RES_SUCCESS) {
-        error_report("cannot get vdi info, %s, %s %d %s",
+        error_report("cannot get vdi info, %s, %s %d %s\n",
                      sd_strerror(rsp->result), filename, snapid, tag);
         ret = -1;
         goto out;
@@ -1064,7 +1063,7 @@ out:
     return ret;
 }
 
-static int coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
+static int add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
                            struct iovec *iov, int niov, int create,
                            enum AIOCBState aiocb_type)
 {
@@ -1079,7 +1078,7 @@ static int coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
     uint64_t old_oid = aio_req->base_oid;
 
     if (!nr_copies) {
-        error_report("bug");
+        error_report("bug\n");
     }
 
     memset(&hdr, 0, sizeof(hdr));
@@ -1107,33 +1106,24 @@ static int coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
 
     hdr.id = aio_req->id;
 
-    qemu_co_mutex_lock(&s->lock);
-    s->co_send = qemu_coroutine_self();
-    qemu_aio_set_fd_handler(s->fd, co_read_response, co_write_request,
-                            aio_flush_request, NULL, s);
     set_cork(s->fd, 1);
 
     /* send a header */
     ret = do_write(s->fd, &hdr, sizeof(hdr));
     if (ret) {
-        qemu_co_mutex_unlock(&s->lock);
-        error_report("failed to send a req, %s", strerror(errno));
+        error_report("failed to send a req, %s\n", strerror(errno));
         return -EIO;
     }
 
     if (wlen) {
         ret = do_writev(s->fd, iov, wlen, aio_req->iov_offset);
         if (ret) {
-            qemu_co_mutex_unlock(&s->lock);
-            error_report("failed to send a data, %s", strerror(errno));
+            error_report("failed to send a data, %s\n", strerror(errno));
             return -EIO;
         }
     }
 
     set_cork(s->fd, 0);
-    qemu_aio_set_fd_handler(s->fd, co_read_response, NULL,
-                            aio_flush_request, NULL, s);
-    qemu_co_mutex_unlock(&s->lock);
 
     return 0;
 }
@@ -1170,7 +1160,7 @@ static int read_write_object(int fd, char *buf, uint64_t oid, int copies,
 
     ret = do_req(fd, (SheepdogReq *)&hdr, buf, &wlen, &rlen);
     if (ret) {
-        error_report("failed to send a request to the sheep");
+        error_report("failed to send a request to the sheep\n");
         return -1;
     }
 
@@ -1178,7 +1168,7 @@ static int read_write_object(int fd, char *buf, uint64_t oid, int copies,
     case SD_RES_SUCCESS:
         return 0;
     default:
-        error_report("%s", sd_strerror(rsp->result));
+        error_report("%s\n", sd_strerror(rsp->result));
         return -1;
     }
 }
@@ -1231,11 +1221,11 @@ static int sd_open(BlockDriverState *bs, const char *filename, int flags)
 
     fd = connect_to_sdog(s->addr, s->port);
     if (fd < 0) {
-        error_report("failed to connect");
+        error_report("failed to connect\n");
         goto out;
     }
 
-    buf = g_malloc(SD_INODE_SIZE);
+    buf = qemu_malloc(SD_INODE_SIZE);
     ret = read_object(fd, buf, vid_to_vdi_oid(vid), 0, SD_INODE_SIZE, 0);
 
     closesocket(fd);
@@ -1250,15 +1240,14 @@ static int sd_open(BlockDriverState *bs, const char *filename, int flags)
 
     bs->total_sectors = s->inode.vdi_size / SECTOR_SIZE;
     strncpy(s->name, vdi, sizeof(s->name));
-    qemu_co_mutex_init(&s->lock);
-    g_free(buf);
+    qemu_free(buf);
     return 0;
 out:
     qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL, NULL, NULL);
     if (s->fd >= 0) {
         closesocket(s->fd);
     }
-    g_free(buf);
+    qemu_free(buf);
     return -1;
 }
 
@@ -1301,7 +1290,7 @@ static int do_sd_create(char *filename, int64_t vdi_size,
     }
 
     if (rsp->result != SD_RES_SUCCESS) {
-        error_report("%s, %s", sd_strerror(rsp->result), filename);
+        error_report("%s, %s\n", sd_strerror(rsp->result), filename);
         return -EIO;
     }
 
@@ -1312,92 +1301,26 @@ static int do_sd_create(char *filename, int64_t vdi_size,
     return 0;
 }
 
-static int sd_prealloc(const char *filename)
-{
-    BlockDriverState *bs = NULL;
-    uint32_t idx, max_idx;
-    int64_t vdi_size;
-    void *buf = g_malloc0(SD_DATA_OBJ_SIZE);
-    int ret;
-
-    ret = bdrv_file_open(&bs, filename, BDRV_O_RDWR);
-    if (ret < 0) {
-        goto out;
-    }
-
-    vdi_size = bdrv_getlength(bs);
-    if (vdi_size < 0) {
-        ret = vdi_size;
-        goto out;
-    }
-    max_idx = DIV_ROUND_UP(vdi_size, SD_DATA_OBJ_SIZE);
-
-    for (idx = 0; idx < max_idx; idx++) {
-        /*
-         * The created image can be a cloned image, so we need to read
-         * a data from the source image.
-         */
-        ret = bdrv_pread(bs, idx * SD_DATA_OBJ_SIZE, buf, SD_DATA_OBJ_SIZE);
-        if (ret < 0) {
-            goto out;
-        }
-        ret = bdrv_pwrite(bs, idx * SD_DATA_OBJ_SIZE, buf, SD_DATA_OBJ_SIZE);
-        if (ret < 0) {
-            goto out;
-        }
-    }
-out:
-    if (bs) {
-        bdrv_delete(bs);
-    }
-    g_free(buf);
-
-    return ret;
-}
-
 static int sd_create(const char *filename, QEMUOptionParameter *options)
 {
     int ret;
-    uint32_t vid = 0, base_vid = 0;
+    uint32_t vid = 0;
     int64_t vdi_size = 0;
     char *backing_file = NULL;
-    BDRVSheepdogState s;
-    char vdi[SD_MAX_VDI_LEN], tag[SD_MAX_VDI_TAG_LEN];
-    uint32_t snapid;
-    int prealloc = 0;
-    const char *vdiname;
 
-    strstart(filename, "sheepdog:", &vdiname);
-
-    memset(&s, 0, sizeof(s));
-    memset(vdi, 0, sizeof(vdi));
-    memset(tag, 0, sizeof(tag));
-    if (parse_vdiname(&s, vdiname, vdi, &snapid, tag) < 0) {
-        error_report("invalid filename");
-        return -EINVAL;
-    }
+    strstart(filename, "sheepdog:", (const char **)&filename);
 
     while (options && options->name) {
         if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
             vdi_size = options->value.n;
         } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
             backing_file = options->value.s;
-        } else if (!strcmp(options->name, BLOCK_OPT_PREALLOC)) {
-            if (!options->value.s || !strcmp(options->value.s, "off")) {
-                prealloc = 0;
-            } else if (!strcmp(options->value.s, "full")) {
-                prealloc = 1;
-            } else {
-                error_report("Invalid preallocation mode: '%s'",
-                             options->value.s);
-                return -EINVAL;
-            }
         }
         options++;
     }
 
     if (vdi_size > SD_MAX_VDI_SIZE) {
-        error_report("too big image size");
+        error_report("too big image size\n");
         return -EINVAL;
     }
 
@@ -1409,7 +1332,7 @@ static int sd_create(const char *filename, QEMUOptionParameter *options)
         /* Currently, only Sheepdog backing image is supported. */
         drv = bdrv_find_protocol(backing_file);
         if (!drv || strcmp(drv->protocol_name, "sheepdog") != 0) {
-            error_report("backing_file must be a sheepdog image");
+            error_report("backing_file must be a sheepdog image\n");
             return -EINVAL;
         }
 
@@ -1420,21 +1343,16 @@ static int sd_create(const char *filename, QEMUOptionParameter *options)
         s = bs->opaque;
 
         if (!is_snapshot(&s->inode)) {
-            error_report("cannot clone from a non snapshot vdi");
+            error_report("cannot clone from a non snapshot vdi\n");
             bdrv_delete(bs);
             return -EINVAL;
         }
 
-        base_vid = s->inode.vdi_id;
+        vid = s->inode.vdi_id;
         bdrv_delete(bs);
     }
 
-    ret = do_sd_create(vdi, vdi_size, base_vid, &vid, 0, s.addr, s.port);
-    if (!prealloc || ret) {
-        return ret;
-    }
-
-    return sd_prealloc(filename);
+    return do_sd_create((char *)filename, vdi_size, vid, NULL, 0, NULL, NULL);
 }
 
 static void sd_close(BlockDriverState *bs)
@@ -1465,12 +1383,12 @@ static void sd_close(BlockDriverState *bs)
 
     if (!ret && rsp->result != SD_RES_SUCCESS &&
         rsp->result != SD_RES_VDI_NOT_LOCKED) {
-        error_report("%s, %s", sd_strerror(rsp->result), s->name);
+        error_report("%s, %s\n", sd_strerror(rsp->result), s->name);
     }
 
     qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL, NULL, NULL);
     closesocket(s->fd);
-    g_free(s->addr);
+    qemu_free(s->addr);
 }
 
 static int64_t sd_getlength(BlockDriverState *bs)
@@ -1487,10 +1405,10 @@ static int sd_truncate(BlockDriverState *bs, int64_t offset)
     unsigned int datalen;
 
     if (offset < s->inode.vdi_size) {
-        error_report("shrinking is not supported");
+        error_report("shrinking is not supported\n");
         return -EINVAL;
     } else if (offset > SD_MAX_VDI_SIZE) {
-        error_report("too big image size");
+        error_report("too big image size\n");
         return -EINVAL;
     }
 
@@ -1507,7 +1425,7 @@ static int sd_truncate(BlockDriverState *bs, int64_t offset)
     close(fd);
 
     if (ret < 0) {
-        error_report("failed to update an inode.");
+        error_report("failed to update an inode.\n");
         return -EIO;
     }
 
@@ -1517,9 +1435,9 @@ static int sd_truncate(BlockDriverState *bs, int64_t offset)
 /*
  * This function is called after writing data objects.  If we need to
  * update metadata, this sends a write request to the vdi object.
- * Otherwise, this switches back to sd_co_readv/writev.
+ * Otherwise, this calls the AIOCB callback.
  */
-static void coroutine_fn sd_write_done(SheepdogAIOCB *acb)
+static void sd_write_done(SheepdogAIOCB *acb)
 {
     int ret;
     BDRVSheepdogState *s = acb->common.bs->opaque;
@@ -1568,7 +1486,7 @@ static int sd_create_branch(BDRVSheepdogState *s)
 
     dprintf("%" PRIx32 " is snapshot.\n", s->inode.vdi_id);
 
-    buf = g_malloc(SD_INODE_SIZE);
+    buf = qemu_malloc(SD_INODE_SIZE);
 
     ret = do_sd_create(s->name, s->inode.vdi_size, s->inode.vdi_id, &vid, 1,
                        s->addr, s->port);
@@ -1580,7 +1498,7 @@ static int sd_create_branch(BDRVSheepdogState *s)
 
     fd = connect_to_sdog(s->addr, s->port);
     if (fd < 0) {
-        error_report("failed to connect");
+        error_report("failed to connect\n");
         goto out;
     }
 
@@ -1600,7 +1518,7 @@ static int sd_create_branch(BDRVSheepdogState *s)
     dprintf("%" PRIx32 " was newly created.\n", s->inode.vdi_id);
 
 out:
-    g_free(buf);
+    qemu_free(buf);
 
     return ret;
 }
@@ -1613,11 +1531,8 @@ out:
  * waiting the response.  The responses are received in the
  * `aio_read_response' function which is called from the main loop as
  * a fd handler.
- *
- * Returns 1 when we need to wait a response, 0 when there is no sent
- * request and -errno in error cases.
  */
-static int coroutine_fn sd_co_rw_vector(void *p)
+static void sd_readv_writev_bh_cb(void *p)
 {
     SheepdogAIOCB *acb = p;
     int ret = 0;
@@ -1629,6 +1544,9 @@ static int coroutine_fn sd_co_rw_vector(void *p)
     SheepdogInode *inode = &s->inode;
     AIOReq *aio_req;
 
+    qemu_bh_delete(acb->bh);
+    acb->bh = NULL;
+
     if (acb->aiocb_type == AIOCB_WRITE_UDATA && s->is_snapshot) {
         /*
          * In the case we open the snapshot VDI, Sheepdog creates the
@@ -1657,7 +1575,7 @@ static int coroutine_fn sd_co_rw_vector(void *p)
 
             create = 1;
         } else if (acb->aiocb_type == AIOCB_WRITE_UDATA
-                   && !is_data_obj_writable(inode, idx)) {
+                   && !is_data_obj_writeable(inode, idx)) {
             /* Copy-On-Write */
             create = 1;
             old_oid = oid;
@@ -1698,7 +1616,7 @@ static int coroutine_fn sd_co_rw_vector(void *p)
         ret = add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov,
                               create, acb->aiocb_type);
         if (ret < 0) {
-            error_report("add_aio_request is failed");
+            error_report("add_aio_request is failed\n");
             free_aio_req(s, aio_req);
             acb->ret = -EIO;
             goto out;
@@ -1710,47 +1628,42 @@ static int coroutine_fn sd_co_rw_vector(void *p)
     }
 out:
     if (QLIST_EMPTY(&acb->aioreq_head)) {
-        return acb->ret;
+        sd_finish_aiocb(acb);
     }
-    return 1;
 }
 
-static int sd_co_writev(BlockDriverState *bs, int64_t sector_num,
-                        int nb_sectors, QEMUIOVector *qiov)
+static BlockDriverAIOCB *sd_aio_writev(BlockDriverState *bs, int64_t sector_num,
+                                       QEMUIOVector *qiov, int nb_sectors,
+                                       BlockDriverCompletionFunc *cb,
+                                       void *opaque)
 {
     SheepdogAIOCB *acb;
-    int ret;
 
     if (bs->growable && sector_num + nb_sectors > bs->total_sectors) {
         /* TODO: shouldn't block here */
         if (sd_truncate(bs, (sector_num + nb_sectors) * SECTOR_SIZE) < 0) {
-            return -EIO;
+            return NULL;
         }
         bs->total_sectors = sector_num + nb_sectors;
     }
 
-    acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors, NULL, NULL);
+    acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors, cb, opaque);
     acb->aio_done_func = sd_write_done;
     acb->aiocb_type = AIOCB_WRITE_UDATA;
 
-    ret = sd_co_rw_vector(acb);
-    if (ret <= 0) {
-        qemu_aio_release(acb);
-        return ret;
-    }
-
-    qemu_coroutine_yield();
-
-    return acb->ret;
+    sd_schedule_bh(sd_readv_writev_bh_cb, acb);
+    return &acb->common;
 }
 
-static int sd_co_readv(BlockDriverState *bs, int64_t sector_num,
-                       int nb_sectors, QEMUIOVector *qiov)
+static BlockDriverAIOCB *sd_aio_readv(BlockDriverState *bs, int64_t sector_num,
+                                      QEMUIOVector *qiov, int nb_sectors,
+                                      BlockDriverCompletionFunc *cb,
+                                      void *opaque)
 {
     SheepdogAIOCB *acb;
-    int i, ret;
+    int i;
 
-    acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors, NULL, NULL);
+    acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors, cb, opaque);
     acb->aiocb_type = AIOCB_READ_UDATA;
     acb->aio_done_func = sd_finish_aiocb;
 
@@ -1762,15 +1675,8 @@ static int sd_co_readv(BlockDriverState *bs, int64_t sector_num,
         memset(qiov->iov[i].iov_base, 0, qiov->iov[i].iov_len);
     }
 
-    ret = sd_co_rw_vector(acb);
-    if (ret <= 0) {
-        qemu_aio_release(acb);
-        return ret;
-    }
-
-    qemu_coroutine_yield();
-
-    return acb->ret;
+    sd_schedule_bh(sd_readv_writev_bh_cb, acb);
+    return &acb->common;
 }
 
 static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
@@ -1787,7 +1693,7 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
 
     if (s->is_snapshot) {
         error_report("You can't create a snapshot of a snapshot VDI, "
-                     "%s (%" PRIu32 ").", s->name, s->inode.vdi_id);
+                     "%s (%" PRIu32 ").\n", s->name, s->inode.vdi_id);
 
         return -EINVAL;
     }
@@ -1810,7 +1716,7 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
     ret = write_object(fd, (char *)&s->inode, vid_to_vdi_oid(s->inode.vdi_id),
                        s->inode.nr_copies, datalen, 0, 0);
     if (ret < 0) {
-        error_report("failed to write snapshot's inode.");
+        error_report("failed to write snapshot's inode.\n");
         ret = -EIO;
         goto cleanup;
     }
@@ -1818,19 +1724,19 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
     ret = do_sd_create(s->name, s->inode.vdi_size, s->inode.vdi_id, &new_vid, 1,
                        s->addr, s->port);
     if (ret < 0) {
-        error_report("failed to create inode for snapshot. %s",
+        error_report("failed to create inode for snapshot. %s\n",
                      strerror(errno));
         ret = -EIO;
         goto cleanup;
     }
 
-    inode = (SheepdogInode *)g_malloc(datalen);
+    inode = (SheepdogInode *)qemu_malloc(datalen);
 
     ret = read_object(fd, (char *)inode, vid_to_vdi_oid(new_vid),
                       s->inode.nr_copies, datalen, 0);
 
     if (ret < 0) {
-        error_report("failed to read new inode info. %s", strerror(errno));
+        error_report("failed to read new inode info. %s\n", strerror(errno));
         ret = -EIO;
         goto cleanup;
     }
@@ -1854,7 +1760,7 @@ static int sd_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
     uint32_t snapid = 0;
     int ret = -ENOENT, fd;
 
-    old_s = g_malloc(sizeof(BDRVSheepdogState));
+    old_s = qemu_malloc(sizeof(BDRVSheepdogState));
 
     memcpy(old_s, s, sizeof(BDRVSheepdogState));
 
@@ -1869,18 +1775,18 @@ static int sd_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
 
     ret = find_vdi_name(s, vdi, snapid, tag, &vid, 1);
     if (ret) {
-        error_report("Failed to find_vdi_name");
+        error_report("Failed to find_vdi_name\n");
         ret = -ENOENT;
         goto out;
     }
 
     fd = connect_to_sdog(s->addr, s->port);
     if (fd < 0) {
-        error_report("failed to connect");
+        error_report("failed to connect\n");
         goto out;
     }
 
-    buf = g_malloc(SD_INODE_SIZE);
+    buf = qemu_malloc(SD_INODE_SIZE);
     ret = read_object(fd, buf, vid_to_vdi_oid(vid), s->inode.nr_copies,
                       SD_INODE_SIZE, 0);
 
@@ -1894,24 +1800,24 @@ static int sd_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
     memcpy(&s->inode, buf, sizeof(s->inode));
 
     if (!s->inode.vm_state_size) {
-        error_report("Invalid snapshot");
+        error_report("Invalid snapshot\n");
         ret = -ENOENT;
         goto out;
     }
 
     s->is_snapshot = 1;
 
-    g_free(buf);
-    g_free(old_s);
+    qemu_free(buf);
+    qemu_free(old_s);
 
     return 0;
 out:
     /* recover bdrv_sd_state */
     memcpy(s, old_s, sizeof(BDRVSheepdogState));
-    g_free(buf);
-    g_free(old_s);
+    qemu_free(buf);
+    qemu_free(old_s);
 
-    error_report("failed to open. recover old bdrv_sd_state.");
+    error_report("failed to open. recover old bdrv_sd_state.\n");
 
     return ret;
 }
@@ -1922,6 +1828,20 @@ static int sd_snapshot_delete(BlockDriverState *bs, const char *snapshot_id)
     return 0;
 }
 
+#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
+#define BITS_PER_BYTE        8
+#define BITS_TO_LONGS(nr)    DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
+#define DECLARE_BITMAP(name,bits)               \
+    unsigned long name[BITS_TO_LONGS(bits)]
+
+#define BITS_PER_LONG (BITS_PER_BYTE * sizeof(long))
+
+static inline int test_bit(unsigned int nr, const unsigned long *addr)
+{
+    return ((1UL << (nr % BITS_PER_LONG)) &
+            (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
+}
+
 static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
 {
     BDRVSheepdogState *s = bs->opaque;
@@ -1936,7 +1856,7 @@ static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
     uint64_t hval;
     uint32_t vid;
 
-    vdi_inuse = g_malloc(max);
+    vdi_inuse = qemu_malloc(max);
 
     fd = connect_to_sdog(s->addr, s->port);
     if (fd < 0) {
@@ -1958,7 +1878,7 @@ static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
         goto out;
     }
 
-    sn_tab = g_malloc0(nr * sizeof(*sn_tab));
+    sn_tab = qemu_mallocz(nr * sizeof(*sn_tab));
 
     /* calculate a vdi id with hash function */
     hval = fnv_64a_buf(s->name, strlen(s->name), FNV1A_64_INIT);
@@ -1966,7 +1886,7 @@ static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
 
     fd = connect_to_sdog(s->addr, s->port);
     if (fd < 0) {
-        error_report("failed to connect");
+        error_report("failed to connect\n");
         goto out;
     }
 
@@ -2001,7 +1921,7 @@ static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
 out:
     *psn_tab = sn_tab;
 
-    g_free(vdi_inuse);
+    qemu_free(vdi_inuse);
 
     return found;
 }
@@ -2040,7 +1960,7 @@ static int do_load_save_vmstate(BDRVSheepdogState *s, uint8_t *data,
         }
 
         if (ret < 0) {
-            error_report("failed to save vmstate %s", strerror(errno));
+            error_report("failed to save vmstate %s\n", strerror(errno));
             ret = -EIO;
             goto cleanup;
         }
@@ -2082,11 +2002,6 @@ static QEMUOptionParameter sd_create_options[] = {
         .type = OPT_STRING,
         .help = "File name of a base image"
     },
-    {
-        .name = BLOCK_OPT_PREALLOC,
-        .type = OPT_STRING,
-        .help = "Preallocation mode (allowed values: off, full)"
-    },
     { NULL }
 };
 
@@ -2100,8 +2015,8 @@ BlockDriver bdrv_sheepdog = {
     .bdrv_getlength = sd_getlength,
     .bdrv_truncate  = sd_truncate,
 
-    .bdrv_co_readv  = sd_co_readv,
-    .bdrv_co_writev = sd_co_writev,
+    .bdrv_aio_readv     = sd_aio_readv,
+    .bdrv_aio_writev    = sd_aio_writev,
 
     .bdrv_snapshot_create   = sd_snapshot_create,
     .bdrv_snapshot_goto     = sd_snapshot_goto,

block/vdi.c

@@ -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>
@@ -88,7 +87,6 @@ void uuid_unparse(const uuid_t uu, char *out);
 #define MiB     (KiB * KiB)
 
 #define SECTOR_SIZE 512
-#define DEFAULT_CLUSTER_SIZE (1 * MiB)
 
 #if defined(CONFIG_VDI_DEBUG)
 #define logout(fmt, ...) \
@@ -115,24 +113,19 @@ void uuid_unparse(const uuid_t uu, char *out);
  */
 #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 endianess). */
+#define VDI_UNALLOCATED UINT32_MAX
 
 #if !defined(CONFIG_UUID)
 void uuid_generate(uuid_t out)
 {
-    memset(out, 0, sizeof(uuid_t));
+    memset(out, 0, sizeof(out));
 }
 
 int uuid_is_null(const uuid_t uu)
 {
     uuid_t null_uuid = { 0 };
-    return memcmp(uu, null_uuid, sizeof(uuid_t)) == 0;
+    return memcmp(uu, null_uuid, sizeof(uu)) == 0;
 }
 
 void uuid_unparse(const uuid_t uu, char *out)
@@ -158,7 +151,6 @@ typedef struct {
     /* Buffer for new allocated block. */
     void *block_buffer;
     void *orig_buf;
-    bool is_write;
     int header_modified;
     BlockDriverAIOCB *hd_aiocb;
     struct iovec hd_iov;
@@ -194,6 +186,7 @@ typedef struct {
 } VdiHeader;
 
 typedef struct {
+    BlockDriverState *hd;
     /* The block map entries are little endian (even in memory). */
     uint32_t *bmap;
     /* Size of block (bytes). */
@@ -202,10 +195,8 @@ typedef struct {
     uint32_t block_sectors;
     /* First sector of block map. */
     uint32_t bmap_sector;
-    /* VDI header (converted to host endianness). */
+    /* VDI header (converted to host endianess). */
     VdiHeader header;
-
-    Error *migration_blocker;
 } BDRVVdiState;
 
 /* Change UUID from little endian (IPRT = VirtualBox format) to big endian
@@ -309,16 +300,16 @@ static int vdi_check(BlockDriverState *bs, BdrvCheckResult *res)
     uint32_t *bmap;
     logout("\n");
 
-    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
@@ -339,7 +330,7 @@ static int vdi_check(BlockDriverState *bs, BdrvCheckResult *res)
         res->corruptions++;
     }
 
-    g_free(bmap);
+    qemu_free(bmap);
 
     return 0;
 }
@@ -451,22 +442,16 @@ 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;
@@ -486,7 +471,7 @@ static int vdi_is_allocated(BlockDriverState *bs, int64_t sector_num,
         n_sectors = nb_sectors;
     }
     *pnum = n_sectors;
-    return VDI_IS_ALLOCATED(bmap_entry);
+    return bmap_entry != VDI_UNALLOCATED;
 }
 
 static void vdi_aio_cancel(BlockDriverAIOCB *blockacb)
@@ -519,8 +504,6 @@ static VdiAIOCB *vdi_aio_setup(BlockDriverState *bs, int64_t sector_num,
         acb->hd_aiocb = NULL;
         acb->sector_num = sector_num;
         acb->qiov = qiov;
-        acb->is_write = is_write;
-
         if (qiov->niov > 1) {
             acb->buf = qemu_blockalign(bs, qiov->size);
             acb->orig_buf = acb->buf;
@@ -559,20 +542,14 @@ static int vdi_schedule_bh(QEMUBHFunc *cb, VdiAIOCB *acb)
 }
 
 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)
+static void vdi_aio_read_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);
-    }
+    vdi_aio_read_cb(opaque, 0);
 }
 
 static void vdi_aio_read_cb(void *opaque, int ret)
@@ -617,10 +594,10 @@ static void vdi_aio_read_cb(void *opaque, int ret)
     /* prepare next AIO request */
     acb->n_sectors = n_sectors;
     bmap_entry = le32_to_cpu(s->bmap[block_index]);
-    if (!VDI_IS_ALLOCATED(bmap_entry)) {
+    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);
+        ret = vdi_schedule_bh(vdi_aio_read_bh, acb);
         if (ret < 0) {
             goto done;
         }
@@ -634,7 +611,6 @@ static void vdi_aio_read_cb(void *opaque, int ret)
         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;
         }
     }
@@ -653,23 +629,12 @@ static BlockDriverAIOCB *vdi_aio_readv(BlockDriverState *bs,
         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;
     }
-
-    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;
-    }
-
+    vdi_aio_read_cb(acb, 0);
     return &acb->common;
 }
 
@@ -699,7 +664,7 @@ static void vdi_aio_write_cb(void *opaque, int ret)
         if (acb->header_modified) {
             VdiHeader *header = acb->block_buffer;
             logout("now writing modified header\n");
-            assert(VDI_IS_ALLOCATED(acb->bmap_first));
+            assert(acb->bmap_first != VDI_UNALLOCATED);
             *header = s->header;
             vdi_header_to_le(header);
             acb->header_modified = 0;
@@ -709,16 +674,15 @@ static void vdi_aio_write_cb(void *opaque, int ret)
             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 (VDI_IS_ALLOCATED(acb->bmap_first)) {
+        } 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;
-            g_free(acb->block_buffer);
+            qemu_free(acb->block_buffer);
             acb->block_buffer = NULL;
             bmap_first = acb->bmap_first;
             bmap_last = acb->bmap_last;
@@ -739,7 +703,6 @@ static void vdi_aio_write_cb(void *opaque, int ret)
             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;
@@ -763,7 +726,7 @@ static void vdi_aio_write_cb(void *opaque, int ret)
     /* prepare next AIO request */
     acb->n_sectors = n_sectors;
     bmap_entry = le32_to_cpu(s->bmap[block_index]);
-    if (!VDI_IS_ALLOCATED(bmap_entry)) {
+    if (bmap_entry == VDI_UNALLOCATED) {
         /* Allocate new block and write to it. */
         uint64_t offset;
         uint8_t *block;
@@ -774,7 +737,7 @@ static void vdi_aio_write_cb(void *opaque, int ret)
                  (uint64_t)bmap_entry * s->block_sectors;
         block = acb->block_buffer;
         if (block == NULL) {
-            block = g_malloc0(s->block_size);
+            block = qemu_mallocz(s->block_size);
             acb->block_buffer = block;
             acb->bmap_first = block_index;
             assert(!acb->header_modified);
@@ -790,7 +753,6 @@ static void vdi_aio_write_cb(void *opaque, int ret)
                                         &acb->hd_qiov, s->block_sectors,
                                         vdi_aio_write_cb, acb);
         if (acb->hd_aiocb == NULL) {
-            ret = -EIO;
             goto done;
         }
     } else {
@@ -803,7 +765,6 @@ static void vdi_aio_write_cb(void *opaque, int ret)
         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;
         }
     }
@@ -823,23 +784,12 @@ static BlockDriverAIOCB *vdi_aio_writev(BlockDriverState *bs,
         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;
-    }
-
+    vdi_aio_write_cb(acb, 0);
     return &acb->common;
 }
 
@@ -849,7 +799,7 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options)
     int result = 0;
     uint64_t bytes = 0;
     uint32_t blocks;
-    size_t block_size = DEFAULT_CLUSTER_SIZE;
+    size_t block_size = 1 * MiB;
     uint32_t image_type = VDI_TYPE_DYNAMIC;
     VdiHeader header;
     size_t i;
@@ -920,7 +870,7 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options)
 
     bmap = NULL;
     if (bmap_size > 0) {
-        bmap = (uint32_t *)g_malloc0(bmap_size);
+        bmap = (uint32_t *)qemu_mallocz(bmap_size);
     }
     for (i = 0; i < blocks; i++) {
         if (image_type == VDI_TYPE_STATIC) {
@@ -932,7 +882,7 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options)
     if (write(fd, bmap, bmap_size) < 0) {
         result = -errno;
     }
-    g_free(bmap);
+    qemu_free(bmap);
     if (image_type == VDI_TYPE_STATIC) {
         if (ftruncate(fd, sizeof(header) + bmap_size + blocks * block_size)) {
             result = -errno;
@@ -948,18 +898,12 @@ 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 coroutine_fn int vdi_co_flush(BlockDriverState *bs)
+static void vdi_flush(BlockDriverState *bs)
 {
     logout("\n");
-    return bdrv_co_flush(bs->file);
+    bdrv_flush(bs->file);
 }
 
 
@@ -973,8 +917,7 @@ static QEMUOptionParameter vdi_create_options[] = {
     {
         .name = BLOCK_OPT_CLUSTER_SIZE,
         .type = OPT_SIZE,
-        .help = "VDI cluster (block) size",
-        .value = { .n = DEFAULT_CLUSTER_SIZE },
+        .help = "VDI cluster (block) size"
     },
 #endif
 #if defined(CONFIG_VDI_STATIC_IMAGE)
@@ -995,7 +938,7 @@ static BlockDriver bdrv_vdi = {
     .bdrv_open = vdi_open,
     .bdrv_close = vdi_close,
     .bdrv_create = vdi_create,
-    .bdrv_co_flush_to_disk = vdi_co_flush,
+    .bdrv_flush = vdi_flush,
     .bdrv_is_allocated = vdi_is_allocated,
     .bdrv_make_empty = vdi_make_empty,
 

block/vpc.c

@@ -25,7 +25,6 @@
 #include "qemu-common.h"
 #include "block_int.h"
 #include "module.h"
-#include "migration.h"
 
 /**************************************************************/
 
@@ -111,7 +110,8 @@ struct vhd_dyndisk_header {
 };
 
 typedef struct BDRVVPCState {
-    CoMutex lock;
+    BlockDriverState *hd;
+
     uint8_t footer_buf[HEADER_SIZE];
     uint64_t free_data_block_offset;
     int max_table_entries;
@@ -129,8 +129,6 @@ typedef struct BDRVVPCState {
 
     uint64_t last_bitmap;
 #endif
-
-    Error *migration_blocker;
 } BDRVVPCState;
 
 static uint32_t vpc_checksum(uint8_t* buf, size_t size)
@@ -160,7 +158,6 @@ static int vpc_open(BlockDriverState *bs, int flags)
     struct vhd_dyndisk_header* dyndisk_header;
     uint8_t buf[HEADER_SIZE];
     uint32_t checksum;
-    int err = -1;
 
     if (bdrv_pread(bs->file, 0, s->footer_buf, HEADER_SIZE) != HEADER_SIZE)
         goto fail;
@@ -181,11 +178,6 @@ static int vpc_open(BlockDriverState *bs, int flags)
     bs->total_sectors = (int64_t)
         be16_to_cpu(footer->cyls) * footer->heads * footer->secs_per_cyl;
 
-    if (bs->total_sectors >= 65535 * 16 * 255) {
-        err = -EFBIG;
-        goto fail;
-    }
-
     if (bdrv_pread(bs->file, be64_to_cpu(footer->data_offset), buf, HEADER_SIZE)
             != HEADER_SIZE)
         goto fail;
@@ -200,7 +192,7 @@ static int vpc_open(BlockDriverState *bs, int flags)
     s->bitmap_size = ((s->block_size / (8 * 512)) + 511) & ~511;
 
     s->max_table_entries = be32_to_cpu(dyndisk_header->max_table_entries);
-    s->pagetable = g_malloc(s->max_table_entries * 4);
+    s->pagetable = qemu_malloc(s->max_table_entries * 4);
 
     s->bat_offset = be64_to_cpu(dyndisk_header->table_offset);
     if (bdrv_pread(bs->file, s->bat_offset, s->pagetable,
@@ -224,23 +216,15 @@ static int vpc_open(BlockDriverState *bs, int flags)
     s->last_bitmap_offset = (int64_t) -1;
 
 #ifdef CACHE
-    s->pageentry_u8 = g_malloc(512);
+    s->pageentry_u8 = qemu_malloc(512);
     s->pageentry_u32 = s->pageentry_u8;
     s->pageentry_u16 = s->pageentry_u8;
     s->last_pagetable = -1;
 #endif
 
-    qemu_co_mutex_init(&s->lock);
-
-    /* Disable migration when VHD images are used */
-    error_set(&s->migration_blocker,
-              QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
-              "vpc", bs->device_name, "live migration");
-    migrate_add_blocker(s->migration_blocker);
-
     return 0;
  fail:
-    return err;
+    return -1;
 }
 
 /*
@@ -362,11 +346,8 @@ static int64_t alloc_block(BlockDriverState* bs, int64_t sector_num)
 
     // Initialize the block's bitmap
     memset(bitmap, 0xff, s->bitmap_size);
-    ret = bdrv_pwrite_sync(bs->file, s->free_data_block_offset, bitmap,
+    bdrv_pwrite_sync(bs->file, s->free_data_block_offset, bitmap,
         s->bitmap_size);
-    if (ret < 0) {
-        return ret;
-    }
 
     // Write new footer (the old one will be overwritten)
     s->free_data_block_offset += s->block_size + s->bitmap_size;
@@ -422,17 +403,6 @@ static int vpc_read(BlockDriverState *bs, int64_t sector_num,
     return 0;
 }
 
-static coroutine_fn int vpc_co_read(BlockDriverState *bs, int64_t sector_num,
-                                    uint8_t *buf, int nb_sectors)
-{
-    int ret;
-    BDRVVPCState *s = bs->opaque;
-    qemu_co_mutex_lock(&s->lock);
-    ret = vpc_read(bs, sector_num, buf, nb_sectors);
-    qemu_co_mutex_unlock(&s->lock);
-    return ret;
-}
-
 static int vpc_write(BlockDriverState *bs, int64_t sector_num,
     const uint8_t *buf, int nb_sectors)
 {
@@ -469,21 +439,6 @@ static int vpc_write(BlockDriverState *bs, int64_t sector_num,
     return 0;
 }
 
-static coroutine_fn int vpc_co_write(BlockDriverState *bs, int64_t sector_num,
-                                     const uint8_t *buf, int nb_sectors)
-{
-    int ret;
-    BDRVVPCState *s = bs->opaque;
-    qemu_co_mutex_lock(&s->lock);
-    ret = vpc_write(bs, sector_num, buf, nb_sectors);
-    qemu_co_mutex_unlock(&s->lock);
-    return ret;
-}
-
-static coroutine_fn int vpc_co_flush(BlockDriverState *bs)
-{
-    return bdrv_co_flush(bs->file);
-}
 
 /*
  * Calculates the number of cylinders, heads and sectors per cylinder
@@ -545,11 +500,14 @@ static int vpc_create(const char *filename, QEMUOptionParameter *options)
     uint8_t secs_per_cyl = 0;
     size_t block_size, num_bat_entries;
     int64_t total_sectors = 0;
-    int ret = -EIO;
 
     // Read out options
-    total_sectors = get_option_parameter(options, BLOCK_OPT_SIZE)->value.n /
-                    BDRV_SECTOR_SIZE;
+    while (options && options->name) {
+        if (!strcmp(options->name, "size")) {
+            total_sectors = options->value.n / 512;
+        }
+        options++;
+    }
 
     // Create the file
     fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, 0644);
@@ -561,8 +519,7 @@ static int vpc_create(const char *filename, QEMUOptionParameter *options)
     for (i = 0; total_sectors > (int64_t)cyls * heads * secs_per_cyl; i++) {
         if (calculate_geometry(total_sectors + i,
                                &cyls, &heads, &secs_per_cyl)) {
-            ret = -EFBIG;
-            goto fail;
+            return -EFBIG;
         }
     }
     total_sectors = (int64_t) cyls * heads * secs_per_cyl;
@@ -601,28 +558,22 @@ static int vpc_create(const char *filename, QEMUOptionParameter *options)
     block_size = 0x200000;
     num_bat_entries = (total_sectors + block_size / 512) / (block_size / 512);
 
-    if (write(fd, buf, HEADER_SIZE) != HEADER_SIZE) {
-        goto fail;
-    }
+    if (write(fd, buf, HEADER_SIZE) != HEADER_SIZE)
+        return -EIO;
 
-    if (lseek(fd, 1536 + ((num_bat_entries * 4 + 511) & ~511), SEEK_SET) < 0) {
-        goto fail;
-    }
-    if (write(fd, buf, HEADER_SIZE) != HEADER_SIZE) {
-        goto fail;
-    }
+    if (lseek(fd, 1536 + ((num_bat_entries * 4 + 511) & ~511), SEEK_SET) < 0)
+        return -EIO;
+    if (write(fd, buf, HEADER_SIZE) != HEADER_SIZE)
+        return -EIO;
 
     // Write the initial BAT
-    if (lseek(fd, 3 * 512, SEEK_SET) < 0) {
-        goto fail;
-    }
+    if (lseek(fd, 3 * 512, SEEK_SET) < 0)
+        return -EIO;
 
     memset(buf, 0xFF, 512);
-    for (i = 0; i < (num_bat_entries * 4 + 511) / 512; i++) {
-        if (write(fd, buf, 512) != 512) {
-            goto fail;
-        }
-    }
+    for (i = 0; i < (num_bat_entries * 4 + 511) / 512; i++)
+        if (write(fd, buf, 512) != 512)
+            return -EIO;
 
 
     // Prepare the Dynamic Disk Header
@@ -630,11 +581,7 @@ static int vpc_create(const char *filename, QEMUOptionParameter *options)
 
     memcpy(dyndisk_header->magic, "cxsparse", 8);
 
-    /*
-     * Note: The spec is actually wrong here for data_offset, it says
-     * 0xFFFFFFFF, but MS tools expect all 64 bits to be set.
-     */
-    dyndisk_header->data_offset = be64_to_cpu(0xFFFFFFFFFFFFFFFFULL);
+    dyndisk_header->data_offset = be64_to_cpu(0xFFFFFFFF);
     dyndisk_header->table_offset = be64_to_cpu(3 * 512);
     dyndisk_header->version = be32_to_cpu(0x00010000);
     dyndisk_header->block_size = be32_to_cpu(block_size);
@@ -643,30 +590,22 @@ static int vpc_create(const char *filename, QEMUOptionParameter *options)
     dyndisk_header->checksum = be32_to_cpu(vpc_checksum(buf, 1024));
 
     // Write the header
-    if (lseek(fd, 512, SEEK_SET) < 0) {
-        goto fail;
-    }
+    if (lseek(fd, 512, SEEK_SET) < 0)
+        return -EIO;
+    if (write(fd, buf, 1024) != 1024)
+        return -EIO;
 
-    if (write(fd, buf, 1024) != 1024) {
-        goto fail;
-    }
-    ret = 0;
-
- fail:
     close(fd);
-    return ret;
+    return 0;
 }
 
 static void vpc_close(BlockDriverState *bs)
 {
     BDRVVPCState *s = bs->opaque;
-    g_free(s->pagetable);
+    qemu_free(s->pagetable);
 #ifdef CACHE
-    g_free(s->pageentry_u8);
+    qemu_free(s->pageentry_u8);
 #endif
-
-    migrate_del_blocker(s->migration_blocker);
-    error_free(s->migration_blocker);
 }
 
 static QEMUOptionParameter vpc_create_options[] = {
@@ -679,17 +618,14 @@ static QEMUOptionParameter vpc_create_options[] = {
 };
 
 static BlockDriver bdrv_vpc = {
-    .format_name    = "vpc",
-    .instance_size  = sizeof(BDRVVPCState),
-
-    .bdrv_probe     = vpc_probe,
-    .bdrv_open      = vpc_open,
-    .bdrv_close     = vpc_close,
-    .bdrv_create    = vpc_create,
-
-    .bdrv_read              = vpc_co_read,
-    .bdrv_write             = vpc_co_write,
-    .bdrv_co_flush_to_disk  = vpc_co_flush,
+    .format_name	= "vpc",
+    .instance_size	= sizeof(BDRVVPCState),
+    .bdrv_probe		= vpc_probe,
+    .bdrv_open		= vpc_open,
+    .bdrv_read		= vpc_read,
+    .bdrv_write		= vpc_write,
+    .bdrv_close		= vpc_close,
+    .bdrv_create	= vpc_create,
 
     .create_options = vpc_create_options,
 };

block/vvfat.c

@@ -27,7 +27,6 @@
 #include "qemu-common.h"
 #include "block_int.h"
 #include "module.h"
-#include "migration.h"
 
 #ifndef S_IWGRP
 #define S_IWGRP 0
@@ -87,7 +86,8 @@ static inline void array_init(array_t* array,unsigned int item_size)
 
 static inline void array_free(array_t* array)
 {
-    g_free(array->pointer);
+    if(array->pointer)
+        free(array->pointer);
     array->size=array->next=0;
 }
 
@@ -101,7 +101,7 @@ static inline int array_ensure_allocated(array_t* array, int index)
 {
     if((index + 1) * array->item_size > array->size) {
 	int new_size = (index + 32) * array->item_size;
-	array->pointer = g_realloc(array->pointer, new_size);
+	array->pointer = qemu_realloc(array->pointer, new_size);
 	if (!array->pointer)
 	    return -1;
 	array->size = new_size;
@@ -127,7 +127,7 @@ static inline void* array_get_next(array_t* array) {
 static inline void* array_insert(array_t* array,unsigned int index,unsigned int count) {
     if((array->next+count)*array->item_size>array->size) {
 	int increment=count*array->item_size;
-	array->pointer=g_realloc(array->pointer,array->size+increment);
+	array->pointer=qemu_realloc(array->pointer,array->size+increment);
 	if(!array->pointer)
             return NULL;
 	array->size+=increment;
@@ -159,7 +159,7 @@ static inline int array_roll(array_t* array,int index_to,int index_from,int coun
     is=array->item_size;
     from=array->pointer+index_from*is;
     to=array->pointer+index_to*is;
-    buf=g_malloc(is*count);
+    buf=qemu_malloc(is*count);
     memcpy(buf,from,is*count);
 
     if(index_to<index_from)
@@ -169,7 +169,7 @@ static inline int array_roll(array_t* array,int index_to,int index_from,int coun
 
     memcpy(to,buf,is*count);
 
-    g_free(buf);
+    free(buf);
 
     return 0;
 }
@@ -200,7 +200,7 @@ static int array_index(array_t* array, void* pointer)
 }
 
 /* These structures are used to fake a disk and the VFAT filesystem.
- * For this reason we need to use QEMU_PACKED. */
+ * For this reason we need to use __attribute__((packed)). */
 
 typedef struct bootsector_t {
     uint8_t jump[3];
@@ -224,7 +224,7 @@ typedef struct bootsector_t {
 	    uint8_t signature;
 	    uint32_t id;
 	    uint8_t volume_label[11];
-	} QEMU_PACKED fat16;
+	} __attribute__((packed)) fat16;
 	struct {
 	    uint32_t sectors_per_fat;
 	    uint16_t flags;
@@ -233,12 +233,12 @@ typedef struct bootsector_t {
 	    uint16_t info_sector;
 	    uint16_t backup_boot_sector;
 	    uint16_t ignored;
-	} QEMU_PACKED fat32;
+	} __attribute__((packed)) fat32;
     } u;
     uint8_t fat_type[8];
     uint8_t ignored[0x1c0];
     uint8_t magic[2];
-} QEMU_PACKED bootsector_t;
+} __attribute__((packed)) bootsector_t;
 
 typedef struct {
     uint8_t head;
@@ -253,7 +253,7 @@ typedef struct partition_t {
     mbr_chs_t end_CHS;
     uint32_t start_sector_long;
     uint32_t length_sector_long;
-} QEMU_PACKED partition_t;
+} __attribute__((packed)) partition_t;
 
 typedef struct mbr_t {
     uint8_t ignored[0x1b8];
@@ -261,7 +261,7 @@ typedef struct mbr_t {
     uint8_t ignored2[2];
     partition_t partition[4];
     uint8_t magic[2];
-} QEMU_PACKED mbr_t;
+} __attribute__((packed)) mbr_t;
 
 typedef struct direntry_t {
     uint8_t name[8];
@@ -276,7 +276,7 @@ typedef struct direntry_t {
     uint16_t mdate;
     uint16_t begin;
     uint32_t size;
-} QEMU_PACKED direntry_t;
+} __attribute__((packed)) direntry_t;
 
 /* this structure are used to transparently access the files */
 
@@ -318,7 +318,6 @@ static void print_mapping(const struct mapping_t* mapping);
 /* here begins the real VVFAT driver */
 
 typedef struct BDRVVVFATState {
-    CoMutex lock;
     BlockDriverState* bs; /* pointer to parent */
     unsigned int first_sectors_number; /* 1 for a single partition, 0x40 for a disk with partition table */
     unsigned char first_sectors[0x40*0x200];
@@ -351,8 +350,6 @@ typedef struct BDRVVVFATState {
     array_t commits;
     const char* path;
     int downcase_short_names;
-
-    Error *migration_blocker;
 } BDRVVVFATState;
 
 /* take the sector position spos and convert it to Cylinder/Head/Sector position
@@ -731,11 +728,11 @@ static int read_directory(BDRVVVFATState* s, int mapping_index)
 	if(first_cluster == 0 && (is_dotdot || is_dot))
 	    continue;
 
-	buffer=(char*)g_malloc(length);
+	buffer=(char*)qemu_malloc(length);
 	snprintf(buffer,length,"%s/%s",dirname,entry->d_name);
 
 	if(stat(buffer,&st)<0) {
-            g_free(buffer);
+	    free(buffer);
             continue;
 	}
 
@@ -758,8 +755,7 @@ static int read_directory(BDRVVVFATState* s, int mapping_index)
 	    direntry->begin=0; /* do that later */
         if (st.st_size > 0x7fffffff) {
 	    fprintf(stderr, "File %s is larger than 2GB\n", buffer);
-            g_free(buffer);
-            closedir(dir);
+	    free(buffer);
 	    return -2;
         }
 	direntry->size=cpu_to_le32(S_ISDIR(st.st_mode)?0:st.st_size);
@@ -802,7 +798,6 @@ static int read_directory(BDRVVVFATState* s, int mapping_index)
 	/* root directory */
 	int cur = s->directory.next;
 	array_ensure_allocated(&(s->directory), ROOT_ENTRIES - 1);
-	s->directory.next = ROOT_ENTRIES;
 	memset(array_get(&(s->directory), cur), 0,
 		(ROOT_ENTRIES - cur) * sizeof(direntry_t));
     }
@@ -829,6 +824,20 @@ static inline off_t cluster2sector(BDRVVVFATState* s, uint32_t cluster_num)
     return s->faked_sectors + s->sectors_per_cluster * cluster_num;
 }
 
+static inline uint32_t sector_offset_in_cluster(BDRVVVFATState* s,off_t sector_num)
+{
+    return (sector_num-s->first_sectors_number-2*s->sectors_per_fat)%s->sectors_per_cluster;
+}
+
+#ifdef DBG
+static direntry_t* get_direntry_for_mapping(BDRVVVFATState* s,mapping_t* mapping)
+{
+    if(mapping->mode==MODE_UNDEFINED)
+	return 0;
+    return (direntry_t*)(s->directory.pointer+sizeof(direntry_t)*mapping->dir_index);
+}
+#endif
+
 static int init_directories(BDRVVVFATState* s,
 	const char* dirname)
 {
@@ -840,7 +849,7 @@ static int init_directories(BDRVVVFATState* s,
     memset(&(s->first_sectors[0]),0,0x40*0x200);
 
     s->cluster_size=s->sectors_per_cluster*0x200;
-    s->cluster_buffer=g_malloc(s->cluster_size);
+    s->cluster_buffer=qemu_malloc(s->cluster_size);
 
     /*
      * The formula: sc = spf+1+spf*spc*(512*8/fat_type),
@@ -874,7 +883,7 @@ static int init_directories(BDRVVVFATState* s,
     mapping->dir_index = 0;
     mapping->info.dir.parent_mapping_index = -1;
     mapping->first_mapping_index = -1;
-    mapping->path = g_strdup(dirname);
+    mapping->path = qemu_strdup(dirname);
     i = strlen(mapping->path);
     if (i > 0 && mapping->path[i - 1] == '/')
 	mapping->path[i - 1] = '\0';
@@ -919,8 +928,11 @@ static int init_directories(BDRVVVFATState* s,
 	cluster = mapping->end;
 
 	if(cluster > s->cluster_count) {
-	    fprintf(stderr,"Directory does not fit in FAT%d (capacity %.2f MB)\n",
-		    s->fat_type, s->sector_count / 2000.0);
+	    fprintf(stderr,"Directory does not fit in FAT%d (capacity %s)\n",
+		    s->fat_type,
+		    s->fat_type == 12 ? s->sector_count == 2880 ? "1.44 MB"
+								: "2.88 MB"
+				      : "504MB");
 	    return -EINVAL;
 	}
 
@@ -954,7 +966,7 @@ static int init_directories(BDRVVVFATState* s,
     bootsector->number_of_fats=0x2; /* number of FATs */
     bootsector->root_entries=cpu_to_le16(s->sectors_of_root_directory*0x10);
     bootsector->total_sectors16=s->sector_count>0xffff?0:cpu_to_le16(s->sector_count);
-    bootsector->media_type=(s->first_sectors_number>1?0xf8:0xf0); /* media descriptor (f8=hd, f0=3.5 fd)*/
+    bootsector->media_type=(s->fat_type!=12?0xf8:s->sector_count==5760?0xf9:0xf8); /* media descriptor */
     s->fat.pointer[0] = bootsector->media_type;
     bootsector->sectors_per_fat=cpu_to_le16(s->sectors_per_fat);
     bootsector->sectors_per_track=cpu_to_le16(s->bs->secs);
@@ -963,7 +975,7 @@ static int init_directories(BDRVVVFATState* s,
     bootsector->total_sectors=cpu_to_le32(s->sector_count>0xffff?s->sector_count:0);
 
     /* LATER TODO: if FAT32, this is wrong */
-    bootsector->u.fat16.drive_number=s->first_sectors_number==1?0:0x80; /* fda=0, hda=0x80 */
+    bootsector->u.fat16.drive_number=s->fat_type==12?0:0x80; /* assume this is hda (TODO) */
     bootsector->u.fat16.current_head=0;
     bootsector->u.fat16.signature=0x29;
     bootsector->u.fat16.id=cpu_to_le32(0xfabe1afd);
@@ -985,6 +997,7 @@ static int is_consistent(BDRVVVFATState *s);
 static int vvfat_open(BlockDriverState *bs, const char* dirname, int flags)
 {
     BDRVVVFATState *s = bs->opaque;
+    int floppy = 0;
     int i;
 
 #ifdef DEBUG
@@ -998,8 +1011,11 @@ DLOG(if (stderr == NULL) {
 
     s->bs = bs;
 
+    s->fat_type=16;
     /* LATER TODO: if FAT32, adjust */
     s->sectors_per_cluster=0x10;
+    /* 504MB disk*/
+    bs->cyls=1024; bs->heads=16; bs->secs=63;
 
     s->current_cluster=0xffffffff;
 
@@ -1014,6 +1030,16 @@ DLOG(if (stderr == NULL) {
     if (!strstart(dirname, "fat:", NULL))
 	return -1;
 
+    if (strstr(dirname, ":floppy:")) {
+	floppy = 1;
+	s->fat_type = 12;
+	s->first_sectors_number = 1;
+	s->sectors_per_cluster=2;
+	bs->cyls = 80; bs->heads = 2; bs->secs = 36;
+    }
+
+    s->sector_count=bs->cyls*bs->heads*bs->secs;
+
     if (strstr(dirname, ":32:")) {
 	fprintf(stderr, "Big fat greek warning: FAT32 has not been tested. You are welcome to do so!\n");
 	s->fat_type = 32;
@@ -1021,31 +1047,9 @@ DLOG(if (stderr == NULL) {
 	s->fat_type = 16;
     } else if (strstr(dirname, ":12:")) {
 	s->fat_type = 12;
+	s->sector_count=2880;
     }
 
-    if (strstr(dirname, ":floppy:")) {
-	/* 1.44MB or 2.88MB floppy.  2.88MB can be FAT12 (default) or FAT16. */
-	if (!s->fat_type) {
-	    s->fat_type = 12;
-	    bs->secs = 36;
-	    s->sectors_per_cluster=2;
-	} else {
-	    bs->secs=(s->fat_type == 12 ? 18 : 36);
-	    s->sectors_per_cluster=1;
-	}
-	s->first_sectors_number = 1;
-	bs->cyls=80; bs->heads=2;
-    } else {
-	/* 32MB or 504MB disk*/
-	if (!s->fat_type) {
-	    s->fat_type = 16;
-	}
-	bs->cyls=(s->fat_type == 12 ? 64 : 1024);
-	bs->heads=16; bs->secs=63;
-    }
-
-    s->sector_count=bs->cyls*bs->heads*bs->secs-(s->first_sectors_number-1);
-
     if (strstr(dirname, ":rw:")) {
 	if (enable_write_target(s))
 	    return -1;
@@ -1069,22 +1073,12 @@ DLOG(if (stderr == NULL) {
 
     if(s->first_sectors_number==0x40)
 	init_mbr(s);
-    else {
-        /* MS-DOS does not like to know about CHS (?). */
+
+    /* for some reason or other, MS-DOS does not like to know about CHS... */
+    if (floppy)
 	bs->heads = bs->cyls = bs->secs = 0;
-    }
 
     //    assert(is_consistent(s));
-    qemu_co_mutex_init(&s->lock);
-
-    /* Disable migration when vvfat is used rw */
-    if (s->qcow) {
-        error_set(&s->migration_blocker,
-                  QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
-                  "vvfat (rw)", bs->device_name, "live migration");
-        migrate_add_blocker(s->migration_blocker);
-    }
-
     return 0;
 }
 
@@ -1143,6 +1137,25 @@ static inline mapping_t* find_mapping_for_cluster(BDRVVVFATState* s,int cluster_
     return mapping;
 }
 
+/*
+ * This function simply compares path == mapping->path. Since the mappings
+ * are sorted by cluster, this is expensive: O(n).
+ */
+static inline mapping_t* find_mapping_for_path(BDRVVVFATState* s,
+	const char* path)
+{
+    int i;
+
+    for (i = 0; i < s->mapping.next; i++) {
+	mapping_t* mapping = array_get(&(s->mapping), i);
+	if (mapping->first_mapping_index < 0 &&
+		!strcmp(path, mapping->path))
+	    return mapping;
+    }
+
+    return NULL;
+}
+
 static int open_file(BDRVVVFATState* s,mapping_t* mapping)
 {
     if(!mapping)
@@ -1209,6 +1222,23 @@ read_cluster_directory:
 }
 
 #ifdef DEBUG
+static void hexdump(const void* address, uint32_t len)
+{
+    const unsigned char* p = address;
+    int i, j;
+
+    for (i = 0; i < len; i += 16) {
+	for (j = 0; j < 16 && i + j < len; j++)
+	    fprintf(stderr, "%02x ", p[i + j]);
+	for (; j < 16; j++)
+	    fprintf(stderr, "   ");
+	fprintf(stderr, " ");
+	for (j = 0; j < 16 && i + j < len; j++)
+	    fprintf(stderr, "%c", (p[i + j] < ' ' || p[i + j] > 0x7f) ? '.' : p[i + j]);
+	fprintf(stderr, "\n");
+    }
+}
+
 static void print_direntry(const direntry_t* direntry)
 {
     int j = 0;
@@ -1262,19 +1292,19 @@ static int vvfat_read(BlockDriverState *bs, int64_t sector_num,
     int i;
 
     for(i=0;i<nb_sectors;i++,sector_num++) {
-	if (sector_num >= bs->total_sectors)
+	if (sector_num >= s->sector_count)
 	   return -1;
 	if (s->qcow) {
 	    int n;
-            if (bdrv_is_allocated(s->qcow, sector_num, nb_sectors-i, &n)) {
+	    if (s->qcow->drv->bdrv_is_allocated(s->qcow,
+			sector_num, nb_sectors-i, &n)) {
 DLOG(fprintf(stderr, "sectors %d+%d allocated\n", (int)sector_num, n));
-                if (bdrv_read(s->qcow, sector_num, buf + i*0x200, n)) {
-                    return -1;
-                }
-                i += n - 1;
-                sector_num += n - 1;
-                continue;
-            }
+		if (s->qcow->drv->bdrv_read(s->qcow, sector_num, buf+i*0x200, n))
+		    return -1;
+		i += n - 1;
+		sector_num += n - 1;
+		continue;
+	    }
 DLOG(fprintf(stderr, "sector %d not allocated\n", (int)sector_num));
 	}
 	if(sector_num<s->faked_sectors) {
@@ -1288,7 +1318,7 @@ DLOG(fprintf(stderr, "sector %d not allocated\n", (int)sector_num));
 	    uint32_t sector=sector_num-s->faked_sectors,
 	    sector_offset_in_cluster=(sector%s->sectors_per_cluster),
 	    cluster_num=sector/s->sectors_per_cluster;
-	    if(cluster_num > s->cluster_count || read_cluster(s, cluster_num) != 0) {
+	    if(read_cluster(s, cluster_num) != 0) {
 		/* LATER TODO: strict: return -1; */
 		memset(buf+i*0x200,0,0x200);
 		continue;
@@ -1299,17 +1329,6 @@ DLOG(fprintf(stderr, "sector %d not allocated\n", (int)sector_num));
     return 0;
 }
 
-static coroutine_fn int vvfat_co_read(BlockDriverState *bs, int64_t sector_num,
-                                      uint8_t *buf, int nb_sectors)
-{
-    int ret;
-    BDRVVVFATState *s = bs->opaque;
-    qemu_co_mutex_lock(&s->lock);
-    ret = vvfat_read(bs, sector_num, buf, nb_sectors);
-    qemu_co_mutex_unlock(&s->lock);
-    return ret;
-}
-
 /* LATER TODO: statify all functions */
 
 /*
@@ -1355,7 +1374,7 @@ DLOG(fprintf(stderr, "clear_commits (%d commits)\n", s->commits.next));
 	assert(commit->path || commit->action == ACTION_WRITEOUT);
 	if (commit->action != ACTION_WRITEOUT) {
 	    assert(commit->path);
-            g_free(commit->path);
+	    free(commit->path);
 	} else
 	    assert(commit->path == NULL);
     }
@@ -1528,7 +1547,7 @@ static inline int cluster_was_modified(BDRVVVFATState* s, uint32_t cluster_num)
 	return 0;
 
     for (i = 0; !was_modified && i < s->sectors_per_cluster; i++)
-	was_modified = bdrv_is_allocated(s->qcow,
+	was_modified = s->qcow->drv->bdrv_is_allocated(s->qcow,
 		cluster2sector(s, cluster_num) + i, 1, &dummy);
 
     return was_modified;
@@ -1618,10 +1637,10 @@ static uint32_t get_cluster_count_for_direntry(BDRVVVFATState* s,
 
 	    /* rename */
 	    if (strcmp(basename, basename2))
-		schedule_rename(s, cluster_num, g_strdup(path));
+		schedule_rename(s, cluster_num, qemu_strdup(path));
 	} else if (is_file(direntry))
 	    /* new file */
-	    schedule_new_file(s, g_strdup(path), cluster_num);
+	    schedule_new_file(s, qemu_strdup(path), cluster_num);
 	else {
             abort();
 	    return 0;
@@ -1677,16 +1696,16 @@ static uint32_t get_cluster_count_for_direntry(BDRVVVFATState* s,
 		int64_t offset = cluster2sector(s, cluster_num);
 
 		vvfat_close_current_file(s);
-                for (i = 0; i < s->sectors_per_cluster; i++) {
-                    if (!bdrv_is_allocated(s->qcow, offset + i, 1, &dummy)) {
-                        if (vvfat_read(s->bs, offset, s->cluster_buffer, 1)) {
-                            return -1;
-                        }
-                        if (bdrv_write(s->qcow, offset, s->cluster_buffer, 1)) {
-                            return -2;
-                        }
-                    }
-                }
+		for (i = 0; i < s->sectors_per_cluster; i++)
+		    if (!s->qcow->drv->bdrv_is_allocated(s->qcow,
+				offset + i, 1, &dummy)) {
+			if (vvfat_read(s->bs,
+				    offset, s->cluster_buffer, 1))
+			    return -1;
+			if (s->qcow->drv->bdrv_write(s->qcow,
+				    offset, s->cluster_buffer, 1))
+			    return -2;
+		    }
 	    }
 	}
 
@@ -1715,13 +1734,13 @@ static int check_directory_consistency(BDRVVVFATState *s,
 	int cluster_num, const char* path)
 {
     int ret = 0;
-    unsigned char* cluster = g_malloc(s->cluster_size);
+    unsigned char* cluster = qemu_malloc(s->cluster_size);
     direntry_t* direntries = (direntry_t*)cluster;
     mapping_t* mapping = find_mapping_for_cluster(s, cluster_num);
 
     long_file_name lfn;
     int path_len = strlen(path);
-    char path2[PATH_MAX + 1];
+    char path2[PATH_MAX];
 
     assert(path_len < PATH_MAX); /* len was tested before! */
     pstrcpy(path2, sizeof(path2), path);
@@ -1738,10 +1757,10 @@ static int check_directory_consistency(BDRVVVFATState *s,
 	mapping->mode &= ~MODE_DELETED;
 
 	if (strcmp(basename, basename2))
-	    schedule_rename(s, cluster_num, g_strdup(path));
+	    schedule_rename(s, cluster_num, qemu_strdup(path));
     } else
 	/* new directory */
-	schedule_mkdir(s, cluster_num, g_strdup(path));
+	schedule_mkdir(s, cluster_num, qemu_strdup(path));
 
     lfn_init(&lfn);
     do {
@@ -1762,14 +1781,14 @@ DLOG(fprintf(stderr, "read cluster %d (sector %d)\n", (int)cluster_num, (int)clu
 	if (subret) {
 	    fprintf(stderr, "Error fetching direntries\n");
 	fail:
-            g_free(cluster);
+	    free(cluster);
 	    return 0;
 	}
 
 	for (i = 0; i < 0x10 * s->sectors_per_cluster; i++) {
 	    int cluster_count = 0;
 
-DLOG(fprintf(stderr, "check direntry %d:\n", i); print_direntry(direntries + i));
+DLOG(fprintf(stderr, "check direntry %d: \n", i); print_direntry(direntries + i));
 	    if (is_volume_label(direntries + i) || is_dot(direntries + i) ||
 		    is_free(direntries + i))
 		continue;
@@ -1830,7 +1849,7 @@ DLOG(fprintf(stderr, "check direntry %d:\n", i); print_direntry(direntries + i))
 	cluster_num = modified_fat_get(s, cluster_num);
     } while(!fat_eof(s, cluster_num));
 
-    g_free(cluster);
+    free(cluster);
     return ret;
 }
 
@@ -1856,7 +1875,7 @@ DLOG(checkpoint());
      */
     if (s->fat2 == NULL) {
 	int size = 0x200 * s->sectors_per_fat;
-	s->fat2 = g_malloc(size);
+	s->fat2 = qemu_malloc(size);
 	memcpy(s->fat2, s->fat.pointer, size);
     }
     check = vvfat_read(s->bs,
@@ -1975,9 +1994,8 @@ static int remove_mapping(BDRVVVFATState* s, int mapping_index)
     mapping_t* first_mapping = array_get(&(s->mapping), 0);
 
     /* free mapping */
-    if (mapping->first_mapping_index < 0) {
-        g_free(mapping->path);
-    }
+    if (mapping->first_mapping_index < 0)
+	free(mapping->path);
 
     /* remove from s->mapping */
     array_remove(&(s->mapping), mapping_index);
@@ -2199,7 +2217,7 @@ static int commit_one_file(BDRVVVFATState* s,
     uint32_t first_cluster = c;
     mapping_t* mapping = find_mapping_for_cluster(s, c);
     uint32_t size = filesize_of_direntry(direntry);
-    char* cluster = g_malloc(s->cluster_size);
+    char* cluster = qemu_malloc(s->cluster_size);
     uint32_t i;
     int fd = 0;
 
@@ -2213,15 +2231,11 @@ static int commit_one_file(BDRVVVFATState* s,
     if (fd < 0) {
 	fprintf(stderr, "Could not open %s... (%s, %d)\n", mapping->path,
 		strerror(errno), errno);
-        g_free(cluster);
 	return fd;
     }
-    if (offset > 0) {
-        if (lseek(fd, offset, SEEK_SET) != offset) {
-            g_free(cluster);
-            return -3;
-        }
-    }
+    if (offset > 0)
+	if (lseek(fd, offset, SEEK_SET) != offset)
+	    return -3;
 
     while (offset < size) {
 	uint32_t c1;
@@ -2237,15 +2251,11 @@ static int commit_one_file(BDRVVVFATState* s,
 	ret = vvfat_read(s->bs, cluster2sector(s, c),
 	    (uint8_t*)cluster, (rest_size + 0x1ff) / 0x200);
 
-        if (ret < 0) {
-            g_free(cluster);
-            return ret;
-        }
+	if (ret < 0)
+	    return ret;
 
-        if (write(fd, cluster, rest_size) < 0) {
-            g_free(cluster);
-            return -2;
-        }
+	if (write(fd, cluster, rest_size) < 0)
+	    return -2;
 
 	offset += rest_size;
 	c = c1;
@@ -2254,11 +2264,9 @@ static int commit_one_file(BDRVVVFATState* s,
     if (ftruncate(fd, size)) {
         perror("ftruncate()");
         close(fd);
-        g_free(cluster);
         return -4;
     }
     close(fd);
-    g_free(cluster);
 
     return commit_mappings(s, first_cluster, dir_index);
 }
@@ -2274,6 +2282,7 @@ static void check1(BDRVVVFATState* s)
 	    fprintf(stderr, "deleted\n");
 	    continue;
 	}
+	assert(mapping->dir_index >= 0);
 	assert(mapping->dir_index < s->directory.next);
 	direntry_t* direntry = array_get(&(s->directory), mapping->dir_index);
 	assert(mapping->begin == begin_of_direntry(direntry) || mapping->first_mapping_index >= 0);
@@ -2374,7 +2383,7 @@ static int handle_renames_and_mkdirs(BDRVVVFATState* s)
 			    mapping_t* m = find_mapping_for_cluster(s,
 				    begin_of_direntry(d));
 			    int l = strlen(m->path);
-			    char* new_path = g_malloc(l + diff + 1);
+			    char* new_path = qemu_malloc(l + diff + 1);
 
 			    assert(!strncmp(m->path, mapping->path, l2));
 
@@ -2390,7 +2399,7 @@ static int handle_renames_and_mkdirs(BDRVVVFATState* s)
 		}
 	    }
 
-            g_free(old_path);
+	    free(old_path);
 	    array_remove(&(s->commits), i);
 	    continue;
 	} else if (commit->action == ACTION_MKDIR) {
@@ -2631,9 +2640,7 @@ static int do_commit(BDRVVVFATState* s)
 	return ret;
     }
 
-    if (s->qcow->drv->bdrv_make_empty) {
-        s->qcow->drv->bdrv_make_empty(s->qcow);
-    }
+    s->qcow->drv->bdrv_make_empty(s->qcow);
 
     memset(s->used_clusters, 0, sector2cluster(s, s->sector_count));
 
@@ -2728,7 +2735,7 @@ DLOG(checkpoint());
      * Use qcow backend. Commit later.
      */
 DLOG(fprintf(stderr, "Write to qcow backend: %d + %d\n", (int)sector_num, nb_sectors));
-    ret = bdrv_write(s->qcow, sector_num, buf, nb_sectors);
+    ret = s->qcow->drv->bdrv_write(s->qcow, sector_num, buf, nb_sectors);
     if (ret < 0) {
 	fprintf(stderr, "Error writing to qcow backend\n");
 	return ret;
@@ -2747,17 +2754,6 @@ DLOG(checkpoint());
     return 0;
 }
 
-static coroutine_fn int vvfat_co_write(BlockDriverState *bs, int64_t sector_num,
-                                       const uint8_t *buf, int nb_sectors)
-{
-    int ret;
-    BDRVVVFATState *s = bs->opaque;
-    qemu_co_mutex_lock(&s->lock);
-    ret = vvfat_write(bs, sector_num, buf, nb_sectors);
-    qemu_co_mutex_unlock(&s->lock);
-    return ret;
-}
-
 static int vvfat_is_allocated(BlockDriverState *bs,
 	int64_t sector_num, int nb_sectors, int* n)
 {
@@ -2779,7 +2775,7 @@ static int write_target_commit(BlockDriverState *bs, int64_t sector_num,
 static void write_target_close(BlockDriverState *bs) {
     BDRVVVFATState* s = *((BDRVVVFATState**) bs->opaque);
     bdrv_delete(s->qcow);
-    g_free(s->qcow_filename);
+    free(s->qcow_filename);
 }
 
 static BlockDriver vvfat_write_target = {
@@ -2798,7 +2794,7 @@ static int enable_write_target(BDRVVVFATState *s)
 
     array_init(&(s->commits), sizeof(commit_t));
 
-    s->qcow_filename = g_malloc(1024);
+    s->qcow_filename = qemu_malloc(1024);
     get_tmp_filename(s->qcow_filename, 1024);
 
     bdrv_qcow = bdrv_find_format("qcow");
@@ -2826,7 +2822,7 @@ static int enable_write_target(BDRVVVFATState *s)
 
     s->bs->backing_hd = calloc(sizeof(BlockDriverState), 1);
     s->bs->backing_hd->drv = &vvfat_write_target;
-    s->bs->backing_hd->opaque = g_malloc(sizeof(void*));
+    s->bs->backing_hd->opaque = qemu_malloc(sizeof(void*));
     *(void**)s->bs->backing_hd->opaque = s;
 
     return 0;
@@ -2840,20 +2836,16 @@ static void vvfat_close(BlockDriverState *bs)
     array_free(&(s->fat));
     array_free(&(s->directory));
     array_free(&(s->mapping));
-    g_free(s->cluster_buffer);
-
-    if (s->qcow) {
-        migrate_del_blocker(s->migration_blocker);
-        error_free(s->migration_blocker);
-    }
+    if(s->cluster_buffer)
+        free(s->cluster_buffer);
 }
 
 static BlockDriver bdrv_vvfat = {
     .format_name	= "vvfat",
     .instance_size	= sizeof(BDRVVVFATState),
     .bdrv_file_open	= vvfat_open,
-    .bdrv_read          = vvfat_co_read,
-    .bdrv_write         = vvfat_co_write,
+    .bdrv_read		= vvfat_read,
+    .bdrv_write		= vvfat_write,
     .bdrv_close		= vvfat_close,
     .bdrv_is_allocated	= vvfat_is_allocated,
     .protocol_name	= "fat",
@@ -2886,5 +2878,11 @@ static void checkpoint(void) {
     direntry = array_get(&(vvv->directory), mapping->dir_index);
     assert(!memcmp(direntry->name, "USB     H  ", 11) || direntry->name[0]==0);
 #endif
+    return;
+    /* avoid compiler warnings: */
+    hexdump(NULL, 100);
+    remove_mapping(vvv, 0);
+    print_mapping(NULL);
+    print_direntry(NULL);
 }
 #endif

block_int.h

@@ -27,11 +27,9 @@
 #include "block.h"
 #include "qemu-option.h"
 #include "qemu-queue.h"
-#include "qemu-coroutine.h"
-#include "qemu-timer.h"
-#include "qapi-types.h"
 
 #define BLOCK_FLAG_ENCRYPT	1
+#define BLOCK_FLAG_COMPRESS	2
 #define BLOCK_FLAG_COMPAT6	4
 
 #define BLOCK_OPT_SIZE          "size"
@@ -40,9 +38,7 @@
 #define BLOCK_OPT_BACKING_FILE  "backing_file"
 #define BLOCK_OPT_BACKING_FMT   "backing_fmt"
 #define BLOCK_OPT_CLUSTER_SIZE  "cluster_size"
-#define BLOCK_OPT_TABLE_SIZE    "table_size"
 #define BLOCK_OPT_PREALLOC      "preallocation"
-#define BLOCK_OPT_SUBFMT        "subformat"
 
 typedef struct AIOPool {
     void (*cancel)(BlockDriverAIOCB *acb);
@@ -63,6 +59,7 @@ struct BlockDriver {
                       const uint8_t *buf, int nb_sectors);
     void (*bdrv_close)(BlockDriverState *bs);
     int (*bdrv_create)(const char *filename, QEMUOptionParameter *options);
+    void (*bdrv_flush)(BlockDriverState *bs);
     int (*bdrv_is_allocated)(BlockDriverState *bs, int64_t sector_num,
                              int nb_sectors, int *pnum);
     int (*bdrv_set_key)(BlockDriverState *bs, const char *key);
@@ -76,34 +73,6 @@ struct BlockDriver {
         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);
-
-    int coroutine_fn (*bdrv_co_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);
-    int coroutine_fn (*bdrv_co_discard)(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors);
-
-    /*
-     * Invalidate any cached meta-data.
-     */
-    void (*bdrv_invalidate_cache)(BlockDriverState *bs);
-
-    /*
-     * Flushes all data that was already written to the OS all the way down to
-     * the disk (for example raw-posix calls fsync()).
-     */
-    int coroutine_fn (*bdrv_co_flush_to_disk)(BlockDriverState *bs);
-
-    /*
-     * Flushes all internal caches to the OS. The data may still sit in a
-     * writeback cache of the host OS, but it will survive a crash of the qemu
-     * process.
-     */
-    int coroutine_fn (*bdrv_co_flush_to_os)(BlockDriverState *bs);
 
     int (*bdrv_aio_multiwrite)(BlockDriverState *bs, BlockRequest *reqs,
         int num_reqs);
@@ -114,7 +83,6 @@ struct BlockDriver {
     const char *protocol_name;
     int (*bdrv_truncate)(BlockDriverState *bs, int64_t offset);
     int64_t (*bdrv_getlength)(BlockDriverState *bs);
-    int64_t (*bdrv_get_allocated_file_size)(BlockDriverState *bs);
     int (*bdrv_write_compressed)(BlockDriverState *bs, int64_t sector_num,
                                  const uint8_t *buf, int nb_sectors);
 
@@ -125,8 +93,6 @@ struct BlockDriver {
     int (*bdrv_snapshot_delete)(BlockDriverState *bs, const char *snapshot_id);
     int (*bdrv_snapshot_list)(BlockDriverState *bs,
                               QEMUSnapshotInfo **psn_info);
-    int (*bdrv_snapshot_load_tmp)(BlockDriverState *bs,
-                                  const char *snapshot_name);
     int (*bdrv_get_info)(BlockDriverState *bs, BlockDriverInfo *bdi);
 
     int (*bdrv_save_vmstate)(BlockDriverState *bs, const uint8_t *buf,
@@ -140,8 +106,8 @@ struct BlockDriver {
     /* removable device specific */
     int (*bdrv_is_inserted)(BlockDriverState *bs);
     int (*bdrv_media_changed)(BlockDriverState *bs);
-    void (*bdrv_eject)(BlockDriverState *bs, int eject_flag);
-    void (*bdrv_lock_medium)(BlockDriverState *bs, bool locked);
+    int (*bdrv_eject)(BlockDriverState *bs, int eject_flag);
+    int (*bdrv_set_locked)(BlockDriverState *bs, int locked);
 
     /* to control generic scsi devices */
     int (*bdrv_ioctl)(BlockDriverState *bs, unsigned long int req, void *buf);
@@ -176,23 +142,27 @@ struct BlockDriverState {
     int read_only; /* if true, the media is read only */
     int keep_read_only; /* if true, the media was requested to stay read only */
     int open_flags; /* flags used to open the file, re-used for re-open */
+    int removable; /* if true, the media can be removed */
+    int locked;    /* if true, the media cannot temporarily be ejected */
+    int tray_open; /* if true, the virtual tray is open */
     int encrypted; /* if true, the media is encrypted */
     int valid_key; /* if true, a valid encryption key has been set */
     int sg;        /* if true, the device is a /dev/sg* */
+    /* event callback when inserting/removing */
+    void (*change_cb)(void *opaque);
+    void *change_opaque;
 
     BlockDriver *drv; /* NULL means no media */
     void *opaque;
 
-    void *dev;                  /* attached device model, if any */
-    /* TODO change to DeviceState when all users are qdevified */
-    const BlockDevOps *dev_ops;
-    void *dev_opaque;
+    DeviceState *peer;
 
     char filename[1024];
     char backing_file[1024]; /* if non zero, the image is a diff of
                                 this file image */
     char backing_format[16]; /* if non-zero and backing_file exists */
     int is_temporary;
+    int media_changed;
 
     BlockDriverState *backing_hd;
     BlockDriverState *file;
@@ -202,9 +172,10 @@ struct BlockDriverState {
     void *sync_aiocb;
 
     /* I/O stats (display with "info blockstats"). */
-    uint64_t nr_bytes[BDRV_MAX_IOTYPE];
-    uint64_t nr_ops[BDRV_MAX_IOTYPE];
-    uint64_t total_time_ns[BDRV_MAX_IOTYPE];
+    uint64_t rd_bytes;
+    uint64_t wr_bytes;
+    uint64_t rd_ops;
+    uint64_t wr_ops;
     uint64_t wr_highest_sector;
 
     /* Whether the disk can expand beyond total_sectors */
@@ -219,13 +190,11 @@ struct BlockDriverState {
     /* NOTE: the following infos are only hints for real hardware
        drivers. They are not used by the block driver */
     int cyls, heads, secs, translation;
+    int type;
     BlockErrorAction on_read_error, on_write_error;
-    bool iostatus_enabled;
-    BlockDeviceIoStatus iostatus;
     char device_name[32];
     unsigned long *dirty_bitmap;
     int64_t dirty_count;
-    int in_use; /* users other than guest access, eg. block migration */
     QTAILQ_ENTRY(BlockDriverState) list;
     void *private;
 };
@@ -244,8 +213,40 @@ void *qemu_aio_get(AIOPool *pool, BlockDriverState *bs,
                    BlockDriverCompletionFunc *cb, void *opaque);
 void qemu_aio_release(void *p);
 
+void *qemu_blockalign(BlockDriverState *bs, size_t size);
+
 #ifdef _WIN32
 int is_windows_drive(const char *filename);
 #endif
 
+typedef struct BlockConf {
+    BlockDriverState *bs;
+    uint16_t physical_block_size;
+    uint16_t logical_block_size;
+    uint16_t min_io_size;
+    uint32_t opt_io_size;
+} BlockConf;
+
+static inline unsigned int get_physical_block_exp(BlockConf *conf)
+{
+    unsigned int exp = 0, size;
+
+    for (size = conf->physical_block_size;
+        size > conf->logical_block_size;
+        size >>= 1) {
+        exp++;
+    }
+
+    return exp;
+}
+
+#define DEFINE_BLOCK_PROPERTIES(_state, _conf)                          \
+    DEFINE_PROP_DRIVE("drive", _state, _conf.bs),                       \
+    DEFINE_PROP_UINT16("logical_block_size", _state,                    \
+                       _conf.logical_block_size, 512),                  \
+    DEFINE_PROP_UINT16("physical_block_size", _state,                   \
+                       _conf.physical_block_size, 512),                 \
+    DEFINE_PROP_UINT16("min_io_size", _state, _conf.min_io_size, 0),  \
+    DEFINE_PROP_UINT32("opt_io_size", _state, _conf.opt_io_size, 0)
+
 #endif /* BLOCK_INT_H */

blockdev.c

@@ -14,41 +14,9 @@
 #include "qemu-option.h"
 #include "qemu-config.h"
 #include "sysemu.h"
-#include "block_int.h"
 
 static QTAILQ_HEAD(drivelist, DriveInfo) drives = QTAILQ_HEAD_INITIALIZER(drives);
 
-static const char *const if_name[IF_COUNT] = {
-    [IF_NONE] = "none",
-    [IF_IDE] = "ide",
-    [IF_SCSI] = "scsi",
-    [IF_FLOPPY] = "floppy",
-    [IF_PFLASH] = "pflash",
-    [IF_MTD] = "mtd",
-    [IF_SD] = "sd",
-    [IF_VIRTIO] = "virtio",
-    [IF_XEN] = "xen",
-};
-
-static const int if_max_devs[IF_COUNT] = {
-    /*
-     * Do not change these numbers!  They govern how drive option
-     * index maps to unit and bus.  That mapping is ABI.
-     *
-     * All controllers used to imlement if=T drives need to support
-     * if_max_devs[T] units, for any T with if_max_devs[T] != 0.
-     * Otherwise, some index values map to "impossible" bus, unit
-     * values.
-     *
-     * For instance, if you change [IF_SCSI] to 255, -drive
-     * if=scsi,index=12 no longer means bus=1,unit=5, but
-     * bus=0,unit=12.  With an lsi53c895a controller (7 units max),
-     * the drive can't be set up.  Regression.
-     */
-    [IF_IDE] = 2,
-    [IF_SCSI] = 7,
-};
-
 /*
  * We automatically delete the drive when a device using it gets
  * unplugged.  Questionable feature, but we can't just drop it.
@@ -60,54 +28,32 @@ void blockdev_mark_auto_del(BlockDriverState *bs)
 {
     DriveInfo *dinfo = drive_get_by_blockdev(bs);
 
-    if (dinfo) {
-        dinfo->auto_del = 1;
-    }
+    dinfo->auto_del = 1;
 }
 
 void blockdev_auto_del(BlockDriverState *bs)
 {
     DriveInfo *dinfo = drive_get_by_blockdev(bs);
 
-    if (dinfo && dinfo->auto_del) {
-        drive_put_ref(dinfo);
+    if (dinfo->auto_del) {
+        drive_uninit(dinfo);
     }
 }
 
-static int drive_index_to_bus_id(BlockInterfaceType type, int index)
-{
-    int max_devs = if_max_devs[type];
-    return max_devs ? index / max_devs : 0;
-}
-
-static int drive_index_to_unit_id(BlockInterfaceType type, int index)
-{
-    int max_devs = if_max_devs[type];
-    return max_devs ? index % max_devs : index;
-}
-
-QemuOpts *drive_def(const char *optstr)
-{
-    return qemu_opts_parse(qemu_find_opts("drive"), optstr, 0);
-}
-
-QemuOpts *drive_add(BlockInterfaceType type, int index, const char *file,
-                    const char *optstr)
+QemuOpts *drive_add(const char *file, const char *fmt, ...)
 {
+    va_list ap;
+    char optstr[1024];
     QemuOpts *opts;
-    char buf[32];
 
-    opts = drive_def(optstr);
+    va_start(ap, fmt);
+    vsnprintf(optstr, sizeof(optstr), fmt, ap);
+    va_end(ap);
+
+    opts = qemu_opts_parse(&qemu_drive_opts, optstr, 0);
     if (!opts) {
         return NULL;
     }
-    if (type != IF_DEFAULT) {
-        qemu_opt_set(opts, "if", if_name[type]);
-    }
-    if (index >= 0) {
-        snprintf(buf, sizeof(buf), "%d", index);
-        qemu_opt_set(opts, "index", buf);
-    }
     if (file)
         qemu_opt_set(opts, "file", file);
     return opts;
@@ -129,13 +75,6 @@ DriveInfo *drive_get(BlockInterfaceType type, int bus, int unit)
     return NULL;
 }
 
-DriveInfo *drive_get_by_index(BlockInterfaceType type, int index)
-{
-    return drive_get(type,
-                     drive_index_to_bus_id(type, index),
-                     drive_index_to_unit_id(type, index));
-}
-
 int drive_get_max_bus(BlockInterfaceType type)
 {
     int max_bus;
@@ -150,16 +89,6 @@ int drive_get_max_bus(BlockInterfaceType type)
     return max_bus;
 }
 
-/* Get a block device.  This should only be used for single-drive devices
-   (e.g. SD/Floppy/MTD).  Multi-disk devices (scsi/ide) should use the
-   appropriate bus.  */
-DriveInfo *drive_get_next(BlockInterfaceType type)
-{
-    static int next_block_unit[IF_COUNT];
-
-    return drive_get(type, 0, next_block_unit[type]++);
-}
-
 DriveInfo *drive_get_by_blockdev(BlockDriverState *bs)
 {
     DriveInfo *dinfo;
@@ -174,29 +103,15 @@ DriveInfo *drive_get_by_blockdev(BlockDriverState *bs)
 
 static void bdrv_format_print(void *opaque, const char *name)
 {
-    error_printf(" %s", name);
+    fprintf(stderr, " %s", name);
 }
 
-static void drive_uninit(DriveInfo *dinfo)
+void drive_uninit(DriveInfo *dinfo)
 {
     qemu_opts_del(dinfo->opts);
     bdrv_delete(dinfo->bdrv);
-    g_free(dinfo->id);
     QTAILQ_REMOVE(&drives, dinfo, next);
-    g_free(dinfo);
-}
-
-void drive_put_ref(DriveInfo *dinfo)
-{
-    assert(dinfo->refcount);
-    if (--dinfo->refcount == 0) {
-        drive_uninit(dinfo);
-    }
-}
-
-void drive_get_ref(DriveInfo *dinfo)
-{
-    dinfo->refcount++;
+    qemu_free(dinfo);
 }
 
 static int parse_block_error_action(const char *buf, int is_read)
@@ -210,13 +125,13 @@ static int parse_block_error_action(const char *buf, int is_read)
     } else if (!strcmp(buf, "report")) {
         return BLOCK_ERR_REPORT;
     } else {
-        error_report("'%s' invalid %s error action",
-                     buf, is_read ? "read" : "write");
+        fprintf(stderr, "qemu: '%s' invalid %s error action\n",
+            buf, is_read ? "read" : "write");
         return -1;
     }
 }
 
-DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
+DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi, int *fatal_error)
 {
     const char *buf;
     const char *file = NULL;
@@ -238,7 +153,19 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
     int snapshot = 0;
     int ret;
 
+    *fatal_error = 1;
+
     translation = BIOS_ATA_TRANSLATION_AUTO;
+
+    if (default_to_scsi) {
+        type = IF_SCSI;
+        max_devs = MAX_SCSI_DEVS;
+        pstrcpy(devname, sizeof(devname), "scsi");
+    } else {
+        type = IF_IDE;
+        max_devs = MAX_IDE_DEVS;
+        pstrcpy(devname, sizeof(devname), "ide");
+    }
     media = MEDIA_DISK;
 
     /* extract parameters */
@@ -258,38 +185,59 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
 
     if ((buf = qemu_opt_get(opts, "if")) != NULL) {
         pstrcpy(devname, sizeof(devname), buf);
-        for (type = 0; type < IF_COUNT && strcmp(buf, if_name[type]); type++)
-            ;
-        if (type == IF_COUNT) {
-            error_report("unsupported bus type '%s'", buf);
+        if (!strcmp(buf, "ide")) {
+	    type = IF_IDE;
+            max_devs = MAX_IDE_DEVS;
+        } else if (!strcmp(buf, "scsi")) {
+	    type = IF_SCSI;
+            max_devs = MAX_SCSI_DEVS;
+        } else if (!strcmp(buf, "floppy")) {
+	    type = IF_FLOPPY;
+            max_devs = 0;
+        } else if (!strcmp(buf, "pflash")) {
+	    type = IF_PFLASH;
+            max_devs = 0;
+	} else if (!strcmp(buf, "mtd")) {
+	    type = IF_MTD;
+            max_devs = 0;
+	} else if (!strcmp(buf, "sd")) {
+	    type = IF_SD;
+            max_devs = 0;
+        } else if (!strcmp(buf, "virtio")) {
+            type = IF_VIRTIO;
+            max_devs = 0;
+	} else if (!strcmp(buf, "xen")) {
+	    type = IF_XEN;
+            max_devs = 0;
+	} else if (!strcmp(buf, "none")) {
+	    type = IF_NONE;
+            max_devs = 0;
+	} else {
+            fprintf(stderr, "qemu: unsupported bus type '%s'\n", buf);
             return NULL;
 	}
-    } else {
-        type = default_to_scsi ? IF_SCSI : IF_IDE;
-        pstrcpy(devname, sizeof(devname), if_name[type]);
     }
 
-    max_devs = if_max_devs[type];
-
     if (cyls || heads || secs) {
         if (cyls < 1 || (type == IF_IDE && cyls > 16383)) {
-            error_report("invalid physical cyls number");
+            fprintf(stderr, "qemu: '%s' invalid physical cyls number\n", buf);
 	    return NULL;
 	}
         if (heads < 1 || (type == IF_IDE && heads > 16)) {
-            error_report("invalid physical heads number");
+            fprintf(stderr, "qemu: '%s' invalid physical heads number\n", buf);
 	    return NULL;
 	}
         if (secs < 1 || (type == IF_IDE && secs > 63)) {
-            error_report("invalid physical secs number");
+            fprintf(stderr, "qemu: '%s' invalid physical secs number\n", buf);
 	    return NULL;
 	}
     }
 
     if ((buf = qemu_opt_get(opts, "trans")) != NULL) {
         if (!cyls) {
-            error_report("'%s' trans must be used with cyls, heads and secs",
-                         buf);
+            fprintf(stderr,
+                    "qemu: '%s' trans must be used with cyls,heads and secs\n",
+                    buf);
             return NULL;
         }
         if (!strcmp(buf, "none"))
@@ -299,7 +247,7 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
         else if (!strcmp(buf, "auto"))
             translation = BIOS_ATA_TRANSLATION_AUTO;
 	else {
-            error_report("'%s' invalid translation type", buf);
+            fprintf(stderr, "qemu: '%s' invalid translation type\n", buf);
 	    return NULL;
 	}
     }
@@ -309,20 +257,30 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
 	    media = MEDIA_DISK;
 	} else if (!strcmp(buf, "cdrom")) {
             if (cyls || secs || heads) {
-                error_report("CHS can't be set with media=%s", buf);
+                fprintf(stderr,
+                        "qemu: '%s' invalid physical CHS format\n", buf);
 	        return NULL;
             }
 	    media = MEDIA_CDROM;
 	} else {
-	    error_report("'%s' invalid media", buf);
+	    fprintf(stderr, "qemu: '%s' invalid media\n", buf);
 	    return NULL;
 	}
     }
 
     if ((buf = qemu_opt_get(opts, "cache")) != NULL) {
-        if (bdrv_parse_cache_flags(buf, &bdrv_flags) != 0) {
-            error_report("invalid cache option");
-            return NULL;
+        if (!strcmp(buf, "off") || !strcmp(buf, "none")) {
+            bdrv_flags |= BDRV_O_NOCACHE;
+        } else if (!strcmp(buf, "writeback")) {
+            bdrv_flags |= BDRV_O_CACHE_WB;
+        } else if (!strcmp(buf, "unsafe")) {
+            bdrv_flags |= BDRV_O_CACHE_WB;
+            bdrv_flags |= BDRV_O_NO_FLUSH;
+        } else if (!strcmp(buf, "writethrough")) {
+            /* this is the default */
+        } else {
+           fprintf(stderr, "qemu: invalid cache option\n");
+           return NULL;
         }
     }
 
@@ -333,7 +291,7 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
         } else if (!strcmp(buf, "threads")) {
             /* this is the default */
         } else {
-           error_report("invalid aio option");
+           fprintf(stderr, "qemu: invalid aio option\n");
            return NULL;
         }
     }
@@ -341,14 +299,14 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
 
     if ((buf = qemu_opt_get(opts, "format")) != NULL) {
        if (strcmp(buf, "?") == 0) {
-           error_printf("Supported formats:");
-           bdrv_iterate_format(bdrv_format_print, NULL);
-           error_printf("\n");
-           return NULL;
+            fprintf(stderr, "qemu: Supported formats:");
+            bdrv_iterate_format(bdrv_format_print, NULL);
+            fprintf(stderr, "\n");
+	    return NULL;
         }
         drv = bdrv_find_whitelisted_format(buf);
         if (!drv) {
-            error_report("'%s' invalid format", buf);
+            fprintf(stderr, "qemu: '%s' invalid format\n", buf);
             return NULL;
         }
     }
@@ -356,7 +314,7 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
     on_write_error = BLOCK_ERR_STOP_ENOSPC;
     if ((buf = qemu_opt_get(opts, "werror")) != NULL) {
         if (type != IF_IDE && type != IF_SCSI && type != IF_VIRTIO && type != IF_NONE) {
-            error_report("werror is not supported by this bus type");
+            fprintf(stderr, "werror is no supported by this format\n");
             return NULL;
         }
 
@@ -368,8 +326,8 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
 
     on_read_error = BLOCK_ERR_REPORT;
     if ((buf = qemu_opt_get(opts, "rerror")) != NULL) {
-        if (type != IF_IDE && type != IF_VIRTIO && type != IF_SCSI && type != IF_NONE) {
-            error_report("rerror is not supported by this bus type");
+        if (type != IF_IDE && type != IF_VIRTIO && type != IF_NONE) {
+            fprintf(stderr, "rerror is no supported by this format\n");
             return NULL;
         }
 
@@ -381,7 +339,7 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
 
     if ((devaddr = qemu_opt_get(opts, "addr")) != NULL) {
         if (type != IF_VIRTIO) {
-            error_report("addr is not supported by this bus type");
+            fprintf(stderr, "addr is not supported\n");
             return NULL;
         }
     }
@@ -390,11 +348,18 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
 
     if (index != -1) {
         if (bus_id != 0 || unit_id != -1) {
-            error_report("index cannot be used with bus and unit");
+            fprintf(stderr,
+                    "qemu: index cannot be used with bus and unit\n");
             return NULL;
         }
-        bus_id = drive_index_to_bus_id(type, index);
-        unit_id = drive_index_to_unit_id(type, index);
+        if (max_devs == 0)
+        {
+            unit_id = index;
+            bus_id = 0;
+        } else {
+            unit_id = index % max_devs;
+            bus_id = index / max_devs;
+        }
     }
 
     /* if user doesn't specify a unit_id,
@@ -415,29 +380,28 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
     /* check unit id */
 
     if (max_devs && unit_id >= max_devs) {
-        error_report("unit %d too big (max is %d)",
-                     unit_id, max_devs - 1);
+        fprintf(stderr, "qemu: unit %d too big (max is %d)\n",
+                unit_id, max_devs - 1);
         return NULL;
     }
 
     /*
-     * catch multiple definitions
+     * ignore multiple definitions
      */
 
     if (drive_get(type, bus_id, unit_id) != NULL) {
-        error_report("drive with bus=%d, unit=%d (index=%d) exists",
-                     bus_id, unit_id, index);
+        *fatal_error = 0;
         return NULL;
     }
 
     /* init */
 
-    dinfo = g_malloc0(sizeof(*dinfo));
+    dinfo = qemu_mallocz(sizeof(*dinfo));
     if ((buf = qemu_opts_id(opts)) != NULL) {
-        dinfo->id = g_strdup(buf);
+        dinfo->id = qemu_strdup(buf);
     } else {
         /* no id supplied -> create one */
-        dinfo->id = g_malloc0(32);
+        dinfo->id = qemu_mallocz(32);
         if (type == IF_IDE || type == IF_SCSI)
             mediastr = (media == MEDIA_CDROM) ? "-cd" : "-hd";
         if (max_devs)
@@ -453,7 +417,6 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
     dinfo->bus = bus_id;
     dinfo->unit = unit_id;
     dinfo->opts = opts;
-    dinfo->refcount = 1;
     if (serial)
         strncpy(dinfo->serial, serial, sizeof(dinfo->serial) - 1);
     QTAILQ_INSERT_TAIL(&drives, dinfo, next);
@@ -473,28 +436,33 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
             }
 	    break;
 	case MEDIA_CDROM:
-            dinfo->media_cd = 1;
+            bdrv_set_type_hint(dinfo->bdrv, BDRV_TYPE_CDROM);
 	    break;
 	}
         break;
     case IF_SD:
+        /* FIXME: This isn't really a floppy, but it's a reasonable
+           approximation.  */
     case IF_FLOPPY:
+        bdrv_set_type_hint(dinfo->bdrv, BDRV_TYPE_FLOPPY);
+        break;
     case IF_PFLASH:
     case IF_MTD:
         break;
     case IF_VIRTIO:
         /* add virtio block device */
-        opts = qemu_opts_create(qemu_find_opts("device"), NULL, 0);
-        qemu_opt_set(opts, "driver", "virtio-blk");
+        opts = qemu_opts_create(&qemu_device_opts, NULL, 0);
+        qemu_opt_set(opts, "driver", "virtio-blk-pci");
         qemu_opt_set(opts, "drive", dinfo->id);
         if (devaddr)
             qemu_opt_set(opts, "addr", devaddr);
         break;
-    default:
+    case IF_COUNT:
         abort();
     }
     if (!file || !*file) {
-        return dinfo;
+        *fatal_error = 0;
+        return NULL;
     }
     if (snapshot) {
         /* always use cache=unsafe with snapshot */
@@ -507,8 +475,8 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
         ro = 1;
     } else if (ro == 1) {
         if (type != IF_SCSI && type != IF_VIRTIO && type != IF_FLOPPY && type != IF_NONE) {
-            error_report("readonly not supported by this bus type");
-            goto err;
+            fprintf(stderr, "qemu: readonly flag not supported for drive with this interface\n");
+            return NULL;
         }
     }
 
@@ -516,21 +484,15 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
 
     ret = bdrv_open(dinfo->bdrv, file, bdrv_flags, drv);
     if (ret < 0) {
-        error_report("could not open disk image %s: %s",
-                     file, strerror(-ret));
-        goto err;
+        fprintf(stderr, "qemu: could not open disk image %s: %s\n",
+                        file, strerror(-ret));
+        return NULL;
     }
 
     if (bdrv_key_required(dinfo->bdrv))
         autostart = 0;
+    *fatal_error = 0;
     return dinfo;
-
-err:
-    bdrv_delete(dinfo->bdrv);
-    g_free(dinfo->id);
-    QTAILQ_REMOVE(&drives, dinfo, next);
-    g_free(dinfo);
-    return NULL;
 }
 
 void do_commit(Monitor *mon, const QDict *qdict)
@@ -550,94 +512,15 @@ void do_commit(Monitor *mon, const QDict *qdict)
     }
 }
 
-int do_snapshot_blkdev(Monitor *mon, const QDict *qdict, QObject **ret_data)
-{
-    const char *device = qdict_get_str(qdict, "device");
-    const char *filename = qdict_get_try_str(qdict, "snapshot-file");
-    const char *format = qdict_get_try_str(qdict, "format");
-    BlockDriverState *bs;
-    BlockDriver *drv, *old_drv, *proto_drv;
-    int ret = 0;
-    int flags;
-    char old_filename[1024];
-
-    if (!filename) {
-        qerror_report(QERR_MISSING_PARAMETER, "snapshot-file");
-        ret = -1;
-        goto out;
-    }
-
-    bs = bdrv_find(device);
-    if (!bs) {
-        qerror_report(QERR_DEVICE_NOT_FOUND, device);
-        ret = -1;
-        goto out;
-    }
-
-    pstrcpy(old_filename, sizeof(old_filename), bs->filename);
-
-    old_drv = bs->drv;
-    flags = bs->open_flags;
-
-    if (!format) {
-        format = "qcow2";
-    }
-
-    drv = bdrv_find_format(format);
-    if (!drv) {
-        qerror_report(QERR_INVALID_BLOCK_FORMAT, format);
-        ret = -1;
-        goto out;
-    }
-
-    proto_drv = bdrv_find_protocol(filename);
-    if (!proto_drv) {
-        qerror_report(QERR_INVALID_BLOCK_FORMAT, format);
-        ret = -1;
-        goto out;
-    }
-
-    ret = bdrv_img_create(filename, format, bs->filename,
-                          bs->drv->format_name, NULL, -1, flags);
-    if (ret) {
-        goto out;
-    }
-
-    qemu_aio_flush();
-    bdrv_flush(bs);
-
-    bdrv_close(bs);
-    ret = bdrv_open(bs, filename, flags, drv);
-    /*
-     * If reopening the image file we just created fails, fall back
-     * and try to re-open the original image. If that fails too, we
-     * are in serious trouble.
-     */
-    if (ret != 0) {
-        ret = bdrv_open(bs, old_filename, flags, old_drv);
-        if (ret != 0) {
-            qerror_report(QERR_OPEN_FILE_FAILED, old_filename);
-        } else {
-            qerror_report(QERR_OPEN_FILE_FAILED, filename);
-        }
-    }
-out:
-    if (ret) {
-        ret = -1;
-    }
-
-    return ret;
-}
-
 static int eject_device(Monitor *mon, BlockDriverState *bs, int force)
 {
-    if (!bdrv_dev_has_removable_media(bs)) {
-        qerror_report(QERR_DEVICE_NOT_REMOVABLE, bdrv_get_device_name(bs));
-        return -1;
-    }
-    if (bdrv_dev_is_medium_locked(bs) && !bdrv_dev_is_tray_open(bs)) {
-        bdrv_dev_eject_request(bs, force);
-        if (!force) {
+    if (!force) {
+        if (!bdrv_is_removable(bs)) {
+            qerror_report(QERR_DEVICE_NOT_REMOVABLE,
+                           bdrv_get_device_name(bs));
+            return -1;
+        }
+        if (bdrv_is_locked(bs)) {
             qerror_report(QERR_DEVICE_LOCKED, bdrv_get_device_name(bs));
             return -1;
         }
@@ -714,67 +597,3 @@ int do_change_block(Monitor *mon, const char *device,
     }
     return monitor_read_bdrv_key_start(mon, bs, NULL, NULL);
 }
-
-int do_drive_del(Monitor *mon, const QDict *qdict, QObject **ret_data)
-{
-    const char *id = qdict_get_str(qdict, "id");
-    BlockDriverState *bs;
-
-    bs = bdrv_find(id);
-    if (!bs) {
-        qerror_report(QERR_DEVICE_NOT_FOUND, id);
-        return -1;
-    }
-    if (bdrv_in_use(bs)) {
-        qerror_report(QERR_DEVICE_IN_USE, id);
-        return -1;
-    }
-
-    /* quiesce block driver; prevent further io */
-    qemu_aio_flush();
-    bdrv_flush(bs);
-    bdrv_close(bs);
-
-    /* if we have a device attached to this BlockDriverState
-     * then we need to make the drive anonymous until the device
-     * can be removed.  If this is a drive with no device backing
-     * then we can just get rid of the block driver state right here.
-     */
-    if (bdrv_get_attached_dev(bs)) {
-        bdrv_make_anon(bs);
-    } else {
-        drive_uninit(drive_get_by_blockdev(bs));
-    }
-
-    return 0;
-}
-
-/*
- * XXX: replace the QERR_UNDEFINED_ERROR errors with real values once the
- * existing QERR_ macro mess is cleaned up.  A good example for better
- * error reports can be found in the qemu-img resize code.
- */
-int do_block_resize(Monitor *mon, const QDict *qdict, QObject **ret_data)
-{
-    const char *device = qdict_get_str(qdict, "device");
-    int64_t size = qdict_get_int(qdict, "size");
-    BlockDriverState *bs;
-
-    bs = bdrv_find(device);
-    if (!bs) {
-        qerror_report(QERR_DEVICE_NOT_FOUND, device);
-        return -1;
-    }
-
-    if (size < 0) {
-        qerror_report(QERR_UNDEFINED_ERROR);
-        return -1;
-    }
-
-    if (bdrv_truncate(bs, size)) {
-        qerror_report(QERR_UNDEFINED_ERROR);
-        return -1;
-    }
-
-    return 0;
-}

blockdev.h

@@ -16,16 +16,15 @@
 void blockdev_mark_auto_del(BlockDriverState *bs);
 void blockdev_auto_del(BlockDriverState *bs);
 
-#define BLOCK_SERIAL_STRLEN 20
-
 typedef enum {
-    IF_DEFAULT = -1,            /* for use with drive_add() only */
     IF_NONE,
     IF_IDE, IF_SCSI, IF_FLOPPY, IF_PFLASH, IF_MTD, IF_SD, IF_VIRTIO, IF_XEN,
     IF_COUNT
 } BlockInterfaceType;
 
-struct DriveInfo {
+#define BLOCK_SERIAL_STRLEN 20
+
+typedef struct DriveInfo {
     BlockDriverState *bdrv;
     char *id;
     const char *devaddr;
@@ -33,25 +32,22 @@ struct DriveInfo {
     int bus;
     int unit;
     int auto_del;               /* see blockdev_mark_auto_del() */
-    int media_cd;
     QemuOpts *opts;
     char serial[BLOCK_SERIAL_STRLEN + 1];
     QTAILQ_ENTRY(DriveInfo) next;
-    int refcount;
-};
+} DriveInfo;
 
-DriveInfo *drive_get(BlockInterfaceType type, int bus, int unit);
-DriveInfo *drive_get_by_index(BlockInterfaceType type, int index);
-int drive_get_max_bus(BlockInterfaceType type);
-DriveInfo *drive_get_next(BlockInterfaceType type);
-void drive_get_ref(DriveInfo *dinfo);
-void drive_put_ref(DriveInfo *dinfo);
-DriveInfo *drive_get_by_blockdev(BlockDriverState *bs);
+#define MAX_IDE_DEVS	2
+#define MAX_SCSI_DEVS	7
 
-QemuOpts *drive_def(const char *optstr);
-QemuOpts *drive_add(BlockInterfaceType type, int index, const char *file,
-                    const char *optstr);
-DriveInfo *drive_init(QemuOpts *arg, int default_to_scsi);
+extern DriveInfo *drive_get(BlockInterfaceType type, int bus, int unit);
+extern int drive_get_max_bus(BlockInterfaceType type);
+extern void drive_uninit(DriveInfo *dinfo);
+extern DriveInfo *drive_get_by_blockdev(BlockDriverState *bs);
+
+extern QemuOpts *drive_add(const char *file, const char *fmt, ...);
+extern DriveInfo *drive_init(QemuOpts *arg, int default_to_scsi,
+                             int *fatal_error);
 
 /* device-hotplug */
 
@@ -62,8 +58,5 @@ int do_eject(Monitor *mon, const QDict *qdict, QObject **ret_data);
 int do_block_set_passwd(Monitor *mon, const QDict *qdict, QObject **ret_data);
 int do_change_block(Monitor *mon, const char *device,
                     const char *filename, const char *fmt);
-int do_drive_del(Monitor *mon, const QDict *qdict, QObject **ret_data);
-int do_snapshot_blkdev(Monitor *mon, const QDict *qdict, QObject **ret_data);
-int do_block_resize(Monitor *mon, const QDict *qdict, QObject **ret_data);
 
 #endif

bsd-user/bsdload.c

@@ -176,6 +176,8 @@ int loader_exec(const char * filename, char ** argv, char ** envp,
 
     retval = prepare_binprm(&bprm);
 
+    infop->host_argv = argv;
+
     if(retval>=0) {
         if (bprm.buf[0] == 0x7f
                 && bprm.buf[1] == 'E'

bsd-user/elfload.c

@@ -1044,7 +1044,7 @@ static void load_symbols(struct elfhdr *hdr, int fd)
     struct elf_shdr sechdr, symtab, strtab;
     char *strings;
     struct syminfo *s;
-    struct elf_sym *syms, *new_syms;
+    struct elf_sym *syms;
 
     lseek(fd, hdr->e_shoff, SEEK_SET);
     for (i = 0; i < hdr->e_shnum; i++) {
@@ -1072,24 +1072,15 @@ static void load_symbols(struct elfhdr *hdr, int fd)
     /* Now know where the strtab and symtab are.  Snarf them. */
     s = malloc(sizeof(*s));
     syms = malloc(symtab.sh_size);
-    if (!syms) {
-        free(s);
+    if (!syms)
         return;
-    }
     s->disas_strtab = strings = malloc(strtab.sh_size);
-    if (!s->disas_strtab) {
-        free(s);
-        free(syms);
+    if (!s->disas_strtab)
         return;
-    }
 
     lseek(fd, symtab.sh_offset, SEEK_SET);
-    if (read(fd, syms, symtab.sh_size) != symtab.sh_size) {
-        free(s);
-        free(syms);
-        free(strings);
+    if (read(fd, syms, symtab.sh_size) != symtab.sh_size)
         return;
-    }
 
     nsyms = symtab.sh_size / sizeof(struct elf_sym);
 
@@ -1114,29 +1105,13 @@ static void load_symbols(struct elfhdr *hdr, int fd)
 #endif
         i++;
     }
-
-     /* Attempt to free the storage associated with the local symbols
-        that we threw away.  Whether or not this has any effect on the
-        memory allocation depends on the malloc implementation and how
-        many symbols we managed to discard. */
-    new_syms = realloc(syms, nsyms * sizeof(*syms));
-    if (new_syms == NULL) {
-        free(s);
-        free(syms);
-        free(strings);
-        return;
-    }
-    syms = new_syms;
+    syms = realloc(syms, nsyms * sizeof(*syms));
 
     qsort(syms, nsyms, sizeof(*syms), symcmp);
 
     lseek(fd, strtab.sh_offset, SEEK_SET);
-    if (read(fd, strings, strtab.sh_size) != strtab.sh_size) {
-        free(s);
-        free(syms);
-        free(strings);
+    if (read(fd, strings, strtab.sh_size) != strtab.sh_size)
         return;
-    }
     s->disas_num_syms = nsyms;
 #if ELF_CLASS == ELFCLASS32
     s->disas_symtab.elf32 = syms;

bsd-user/main.c

@@ -29,7 +29,7 @@
 #include "qemu.h"
 #include "qemu-common.h"
 /* For tb_lock */
-#include "cpu.h"
+#include "exec-all.h"
 #include "tcg.h"
 #include "qemu-timer.h"
 #include "envlist.h"
@@ -237,7 +237,7 @@ void cpu_loop(CPUX86State *env)
             break;
 #ifndef TARGET_ABI32
         case EXCP_SYSCALL:
-            /* syscall from syscall instruction */
+            /* syscall from syscall intruction */
             if (bsd_type == target_freebsd)
                 env->regs[R_EAX] = do_freebsd_syscall(env,
                                                       env->regs[R_EAX],
@@ -690,8 +690,7 @@ static void usage(void)
            "-bsd type         select emulated BSD type FreeBSD/NetBSD/OpenBSD (default)\n"
            "\n"
            "Debug options:\n"
-           "-d options   activate log (default logfile=%s)\n"
-           "-D logfile   override default logfile location\n"
+           "-d options   activate log (logfile=%s)\n"
            "-p pagesize  set the host page size to 'pagesize'\n"
            "-singlestep  always run in singlestep mode\n"
            "-strace      log system calls\n"
@@ -732,8 +731,6 @@ int main(int argc, char **argv)
 {
     const char *filename;
     const char *cpu_model;
-    const char *log_file = DEBUG_LOGFILE;
-    const char *log_mask = NULL;
     struct target_pt_regs regs1, *regs = &regs1;
     struct image_info info1, *info = &info1;
     TaskState ts1, *ts = &ts1;
@@ -748,6 +745,9 @@ int main(int argc, char **argv)
     if (argc <= 1)
         usage();
 
+    /* init debug */
+    cpu_set_log_filename(DEBUG_LOGFILE);
+
     if ((envlist = envlist_create()) == NULL) {
         (void) fprintf(stderr, "Unable to allocate envlist\n");
         exit(1);
@@ -775,25 +775,26 @@ int main(int argc, char **argv)
         if (!strcmp(r, "-")) {
             break;
         } else if (!strcmp(r, "d")) {
-            if (optind >= argc) {
+            int mask;
+            const CPULogItem *item;
+
+            if (optind >= argc)
                 break;
+
+            r = argv[optind++];
+            mask = cpu_str_to_log_mask(r);
+            if (!mask) {
+                printf("Log items (comma separated):\n");
+                for(item = cpu_log_items; item->mask != 0; item++) {
+                    printf("%-10s %s\n", item->name, item->help);
+                }
+                exit(1);
             }
-            log_mask = argv[optind++];
-        } else if (!strcmp(r, "D")) {
-            if (optind >= argc) {
-                break;
-            }
-            log_file = argv[optind++];
+            cpu_set_log(mask);
         } else if (!strcmp(r, "E")) {
             r = argv[optind++];
             if (envlist_setenv(envlist, r) != 0)
                 usage();
-        } else if (!strcmp(r, "ignore-environment")) {
-            envlist_free(envlist);
-            if ((envlist = envlist_create()) == NULL) {
-                (void) fprintf(stderr, "Unable to allocate envlist\n");
-                exit(1);
-            }
         } else if (!strcmp(r, "U")) {
             r = argv[optind++];
             if (envlist_unsetenv(envlist, r) != 0)
@@ -856,27 +857,8 @@ int main(int argc, char **argv)
             usage();
         }
     }
-
-    /* init debug */
-    cpu_set_log_filename(log_file);
-    if (log_mask) {
-        int mask;
-        const CPULogItem *item;
-
-        mask = cpu_str_to_log_mask(log_mask);
-        if (!mask) {
-            printf("Log items (comma separated):\n");
-            for (item = cpu_log_items; item->mask != 0; item++) {
-                printf("%-10s %s\n", item->name, item->help);
-            }
-            exit(1);
-        }
-        cpu_set_log(mask);
-    }
-
-    if (optind >= argc) {
+    if (optind >= argc)
         usage();
-    }
     filename = argv[optind];
 
     /* Zero out regs */
@@ -905,8 +887,7 @@ int main(int argc, char **argv)
         cpu_model = "any";
 #endif
     }
-    tcg_exec_init(0);
-    cpu_exec_init_all();
+    cpu_exec_init_all(0);
     /* NOTE: we need to init the CPU at this stage to get
        qemu_host_page_size */
     env = cpu_init(cpu_model);

bsd-user/mmap.c

@@ -94,7 +94,7 @@ void *qemu_vmalloc(size_t size)
     return p;
 }
 
-void *g_malloc(size_t size)
+void *qemu_malloc(size_t size)
 {
     char * p;
     size += 16;
@@ -104,12 +104,12 @@ void *g_malloc(size_t size)
 }
 
 /* We use map, which is always zero initialized.  */
-void * g_malloc0(size_t size)
+void * qemu_mallocz(size_t size)
 {
-    return g_malloc(size);
+    return qemu_malloc(size);
 }
 
-void g_free(void *ptr)
+void qemu_free(void *ptr)
 {
     /* FIXME: We should unmark the reserved pages here.  However this gets
        complicated when one target page spans multiple host pages, so we
@@ -119,18 +119,18 @@ void g_free(void *ptr)
     munmap(p, *p);
 }
 
-void *g_realloc(void *ptr, size_t size)
+void *qemu_realloc(void *ptr, size_t size)
 {
     size_t old_size, copy;
     void *new_ptr;
 
     if (!ptr)
-        return g_malloc(size);
+        return qemu_malloc(size);
     old_size = *(size_t *)((char *)ptr - 16);
     copy = old_size < size ? old_size : size;
-    new_ptr = g_malloc(size);
+    new_ptr = qemu_malloc(size);
     memcpy(new_ptr, ptr, copy);
-    g_free(ptr);
+    qemu_free(ptr);
     return new_ptr;
 }
 

bsd-user/qemu.h

@@ -50,6 +50,7 @@ struct image_info {
     abi_ulong entry;
     abi_ulong code_offset;
     abi_ulong data_offset;
+    char      **host_argv;
     int       personality;
 };
 
@@ -138,7 +139,7 @@ abi_long do_netbsd_syscall(void *cpu_env, int num, abi_long arg1,
 abi_long do_openbsd_syscall(void *cpu_env, int num, abi_long arg1,
                             abi_long arg2, abi_long arg3, abi_long arg4,
                             abi_long arg5, abi_long arg6);
-void gemu_log(const char *fmt, ...) GCC_FMT_ATTR(1, 2);
+void gemu_log(const char *fmt, ...) __attribute__((format(printf,1,2)));
 extern THREAD CPUState *thread_env;
 void cpu_loop(CPUState *env);
 char *target_strerror(int err);
@@ -323,7 +324,7 @@ abi_long copy_from_user(void *hptr, abi_ulong gaddr, size_t len);
 abi_long copy_to_user(abi_ulong gaddr, void *hptr, size_t len);
 
 /* Functions for accessing guest memory.  The tget and tput functions
-   read/write single values, byteswapping as necessary.  The lock_user
+   read/write single values, byteswapping as neccessary.  The lock_user
    gets a pointer to a contiguous area of guest memory, but does not perform
    and byteswapping.  lock_user may return either a pointer to the guest
    memory, or a temporary buffer.  */

bsd-user/syscall.c

@@ -31,6 +31,7 @@
 #include <sys/syscall.h>
 #include <sys/param.h>
 #include <sys/sysctl.h>
+#include <signal.h>
 #include <utime.h>
 
 #include "qemu.h"
@@ -231,7 +232,7 @@ static abi_long do_freebsd_sysctl(abi_ulong namep, int32_t namelen, abi_ulong ol
     void *hnamep, *holdp, *hnewp = NULL;
     size_t holdlen;
     abi_ulong oldlen = 0;
-    int32_t *snamep = g_malloc(sizeof(int32_t) * namelen), *p, *q, i;
+    int32_t *snamep = qemu_malloc(sizeof(int32_t) * namelen), *p, *q, i;
     uint32_t kind = 0;
 
     if (oldlenp)
@@ -255,7 +256,7 @@ static abi_long do_freebsd_sysctl(abi_ulong namep, int32_t namelen, abi_ulong ol
     unlock_user(holdp, oldp, holdlen);
     if (hnewp)
         unlock_user(hnewp, newp, 0);
-    g_free(snamep);
+    qemu_free(snamep);
     return ret;
 }
 #endif

bswap.h

@@ -4,7 +4,6 @@
 #include "config-host.h"
 
 #include <inttypes.h>
-#include "softfloat.h"
 
 #ifdef CONFIG_MACHINE_BSWAP_H
 #include <sys/endian.h>
@@ -145,7 +144,6 @@ CPU_CONVERT(le, 64, uint64_t)
 
 #define cpu_to_be16wu(p, v) cpu_to_be16w(p, v)
 #define cpu_to_be32wu(p, v) cpu_to_be32w(p, v)
-#define cpu_to_be64wu(p, v) cpu_to_be64w(p, v)
 
 #else
 
@@ -203,20 +201,6 @@ static inline void cpu_to_be32wu(uint32_t *p, uint32_t v)
     p1[3] = v & 0xff;
 }
 
-static inline void cpu_to_be64wu(uint64_t *p, uint64_t v)
-{
-    uint8_t *p1 = (uint8_t *)p;
-
-    p1[0] = v >> 56;
-    p1[1] = v >> 48;
-    p1[2] = v >> 40;
-    p1[3] = v >> 32;
-    p1[4] = v >> 24;
-    p1[5] = v >> 16;
-    p1[6] = v >> 8;
-    p1[7] = v & 0xff;
-}
-
 #endif
 
 #ifdef HOST_WORDS_BIGENDIAN
@@ -238,476 +222,4 @@ static inline uint32_t qemu_bswap_len(uint32_t value, int len)
     return bswap32(value) >> (32 - 8 * len);
 }
 
-typedef union {
-    float32 f;
-    uint32_t l;
-} CPU_FloatU;
-
-typedef union {
-    float64 d;
-#if defined(HOST_WORDS_BIGENDIAN)
-    struct {
-        uint32_t upper;
-        uint32_t lower;
-    } l;
-#else
-    struct {
-        uint32_t lower;
-        uint32_t upper;
-    } l;
-#endif
-    uint64_t ll;
-} CPU_DoubleU;
-
-typedef union {
-     floatx80 d;
-     struct {
-         uint64_t lower;
-         uint16_t upper;
-     } l;
-} CPU_LDoubleU;
-
-typedef union {
-    float128 q;
-#if defined(HOST_WORDS_BIGENDIAN)
-    struct {
-        uint32_t upmost;
-        uint32_t upper;
-        uint32_t lower;
-        uint32_t lowest;
-    } l;
-    struct {
-        uint64_t upper;
-        uint64_t lower;
-    } ll;
-#else
-    struct {
-        uint32_t lowest;
-        uint32_t lower;
-        uint32_t upper;
-        uint32_t upmost;
-    } l;
-    struct {
-        uint64_t lower;
-        uint64_t upper;
-    } ll;
-#endif
-} CPU_QuadU;
-
-/* unaligned/endian-independent pointer access */
-
-/*
- * the generic syntax is:
- *
- * load: ld{type}{sign}{size}{endian}_p(ptr)
- *
- * store: st{type}{size}{endian}_p(ptr, val)
- *
- * Note there are small differences with the softmmu access API!
- *
- * type is:
- * (empty): integer access
- *   f    : float access
- *
- * sign is:
- * (empty): for floats or 32 bit size
- *   u    : unsigned
- *   s    : signed
- *
- * size is:
- *   b: 8 bits
- *   w: 16 bits
- *   l: 32 bits
- *   q: 64 bits
- *
- * endian is:
- * (empty): 8 bit access
- *   be   : big endian
- *   le   : little endian
- */
-static inline int ldub_p(const void *ptr)
-{
-    return *(uint8_t *)ptr;
-}
-
-static inline int ldsb_p(const void *ptr)
-{
-    return *(int8_t *)ptr;
-}
-
-static inline void stb_p(void *ptr, int v)
-{
-    *(uint8_t *)ptr = v;
-}
-
-/* NOTE: on arm, putting 2 in /proc/sys/debug/alignment so that the
-   kernel handles unaligned load/stores may give better results, but
-   it is a system wide setting : bad */
-#if defined(HOST_WORDS_BIGENDIAN) || defined(WORDS_ALIGNED)
-
-/* conservative code for little endian unaligned accesses */
-static inline int lduw_le_p(const void *ptr)
-{
-#ifdef _ARCH_PPC
-    int val;
-    __asm__ __volatile__ ("lhbrx %0,0,%1" : "=r" (val) : "r" (ptr));
-    return val;
-#else
-    const uint8_t *p = ptr;
-    return p[0] | (p[1] << 8);
-#endif
-}
-
-static inline int ldsw_le_p(const void *ptr)
-{
-#ifdef _ARCH_PPC
-    int val;
-    __asm__ __volatile__ ("lhbrx %0,0,%1" : "=r" (val) : "r" (ptr));
-    return (int16_t)val;
-#else
-    const uint8_t *p = ptr;
-    return (int16_t)(p[0] | (p[1] << 8));
-#endif
-}
-
-static inline int ldl_le_p(const void *ptr)
-{
-#ifdef _ARCH_PPC
-    int val;
-    __asm__ __volatile__ ("lwbrx %0,0,%1" : "=r" (val) : "r" (ptr));
-    return val;
-#else
-    const uint8_t *p = ptr;
-    return p[0] | (p[1] << 8) | (p[2] << 16) | (p[3] << 24);
-#endif
-}
-
-static inline uint64_t ldq_le_p(const void *ptr)
-{
-    const uint8_t *p = ptr;
-    uint32_t v1, v2;
-    v1 = ldl_le_p(p);
-    v2 = ldl_le_p(p + 4);
-    return v1 | ((uint64_t)v2 << 32);
-}
-
-static inline void stw_le_p(void *ptr, int v)
-{
-#ifdef _ARCH_PPC
-    __asm__ __volatile__ ("sthbrx %1,0,%2" : "=m" (*(uint16_t *)ptr) : "r" (v), "r" (ptr));
-#else
-    uint8_t *p = ptr;
-    p[0] = v;
-    p[1] = v >> 8;
-#endif
-}
-
-static inline void stl_le_p(void *ptr, int v)
-{
-#ifdef _ARCH_PPC
-    __asm__ __volatile__ ("stwbrx %1,0,%2" : "=m" (*(uint32_t *)ptr) : "r" (v), "r" (ptr));
-#else
-    uint8_t *p = ptr;
-    p[0] = v;
-    p[1] = v >> 8;
-    p[2] = v >> 16;
-    p[3] = v >> 24;
-#endif
-}
-
-static inline void stq_le_p(void *ptr, uint64_t v)
-{
-    uint8_t *p = ptr;
-    stl_le_p(p, (uint32_t)v);
-    stl_le_p(p + 4, v >> 32);
-}
-
-/* float access */
-
-static inline float32 ldfl_le_p(const void *ptr)
-{
-    union {
-        float32 f;
-        uint32_t i;
-    } u;
-    u.i = ldl_le_p(ptr);
-    return u.f;
-}
-
-static inline void stfl_le_p(void *ptr, float32 v)
-{
-    union {
-        float32 f;
-        uint32_t i;
-    } u;
-    u.f = v;
-    stl_le_p(ptr, u.i);
-}
-
-static inline float64 ldfq_le_p(const void *ptr)
-{
-    CPU_DoubleU u;
-    u.l.lower = ldl_le_p(ptr);
-    u.l.upper = ldl_le_p(ptr + 4);
-    return u.d;
-}
-
-static inline void stfq_le_p(void *ptr, float64 v)
-{
-    CPU_DoubleU u;
-    u.d = v;
-    stl_le_p(ptr, u.l.lower);
-    stl_le_p(ptr + 4, u.l.upper);
-}
-
-#else
-
-static inline int lduw_le_p(const void *ptr)
-{
-    return *(uint16_t *)ptr;
-}
-
-static inline int ldsw_le_p(const void *ptr)
-{
-    return *(int16_t *)ptr;
-}
-
-static inline int ldl_le_p(const void *ptr)
-{
-    return *(uint32_t *)ptr;
-}
-
-static inline uint64_t ldq_le_p(const void *ptr)
-{
-    return *(uint64_t *)ptr;
-}
-
-static inline void stw_le_p(void *ptr, int v)
-{
-    *(uint16_t *)ptr = v;
-}
-
-static inline void stl_le_p(void *ptr, int v)
-{
-    *(uint32_t *)ptr = v;
-}
-
-static inline void stq_le_p(void *ptr, uint64_t v)
-{
-    *(uint64_t *)ptr = v;
-}
-
-/* float access */
-
-static inline float32 ldfl_le_p(const void *ptr)
-{
-    return *(float32 *)ptr;
-}
-
-static inline float64 ldfq_le_p(const void *ptr)
-{
-    return *(float64 *)ptr;
-}
-
-static inline void stfl_le_p(void *ptr, float32 v)
-{
-    *(float32 *)ptr = v;
-}
-
-static inline void stfq_le_p(void *ptr, float64 v)
-{
-    *(float64 *)ptr = v;
-}
-#endif
-
-#if !defined(HOST_WORDS_BIGENDIAN) || defined(WORDS_ALIGNED)
-
-static inline int lduw_be_p(const void *ptr)
-{
-#if defined(__i386__)
-    int val;
-    asm volatile ("movzwl %1, %0\n"
-                  "xchgb %b0, %h0\n"
-                  : "=q" (val)
-                  : "m" (*(uint16_t *)ptr));
-    return val;
-#else
-    const uint8_t *b = ptr;
-    return ((b[0] << 8) | b[1]);
-#endif
-}
-
-static inline int ldsw_be_p(const void *ptr)
-{
-#if defined(__i386__)
-    int val;
-    asm volatile ("movzwl %1, %0\n"
-                  "xchgb %b0, %h0\n"
-                  : "=q" (val)
-                  : "m" (*(uint16_t *)ptr));
-    return (int16_t)val;
-#else
-    const uint8_t *b = ptr;
-    return (int16_t)((b[0] << 8) | b[1]);
-#endif
-}
-
-static inline int ldl_be_p(const void *ptr)
-{
-#if defined(__i386__) || defined(__x86_64__)
-    int val;
-    asm volatile ("movl %1, %0\n"
-                  "bswap %0\n"
-                  : "=r" (val)
-                  : "m" (*(uint32_t *)ptr));
-    return val;
-#else
-    const uint8_t *b = ptr;
-    return (b[0] << 24) | (b[1] << 16) | (b[2] << 8) | b[3];
-#endif
-}
-
-static inline uint64_t ldq_be_p(const void *ptr)
-{
-    uint32_t a,b;
-    a = ldl_be_p(ptr);
-    b = ldl_be_p((uint8_t *)ptr + 4);
-    return (((uint64_t)a<<32)|b);
-}
-
-static inline void stw_be_p(void *ptr, int v)
-{
-#if defined(__i386__)
-    asm volatile ("xchgb %b0, %h0\n"
-                  "movw %w0, %1\n"
-                  : "=q" (v)
-                  : "m" (*(uint16_t *)ptr), "0" (v));
-#else
-    uint8_t *d = (uint8_t *) ptr;
-    d[0] = v >> 8;
-    d[1] = v;
-#endif
-}
-
-static inline void stl_be_p(void *ptr, int v)
-{
-#if defined(__i386__) || defined(__x86_64__)
-    asm volatile ("bswap %0\n"
-                  "movl %0, %1\n"
-                  : "=r" (v)
-                  : "m" (*(uint32_t *)ptr), "0" (v));
-#else
-    uint8_t *d = (uint8_t *) ptr;
-    d[0] = v >> 24;
-    d[1] = v >> 16;
-    d[2] = v >> 8;
-    d[3] = v;
-#endif
-}
-
-static inline void stq_be_p(void *ptr, uint64_t v)
-{
-    stl_be_p(ptr, v >> 32);
-    stl_be_p((uint8_t *)ptr + 4, v);
-}
-
-/* float access */
-
-static inline float32 ldfl_be_p(const void *ptr)
-{
-    union {
-        float32 f;
-        uint32_t i;
-    } u;
-    u.i = ldl_be_p(ptr);
-    return u.f;
-}
-
-static inline void stfl_be_p(void *ptr, float32 v)
-{
-    union {
-        float32 f;
-        uint32_t i;
-    } u;
-    u.f = v;
-    stl_be_p(ptr, u.i);
-}
-
-static inline float64 ldfq_be_p(const void *ptr)
-{
-    CPU_DoubleU u;
-    u.l.upper = ldl_be_p(ptr);
-    u.l.lower = ldl_be_p((uint8_t *)ptr + 4);
-    return u.d;
-}
-
-static inline void stfq_be_p(void *ptr, float64 v)
-{
-    CPU_DoubleU u;
-    u.d = v;
-    stl_be_p(ptr, u.l.upper);
-    stl_be_p((uint8_t *)ptr + 4, u.l.lower);
-}
-
-#else
-
-static inline int lduw_be_p(const void *ptr)
-{
-    return *(uint16_t *)ptr;
-}
-
-static inline int ldsw_be_p(const void *ptr)
-{
-    return *(int16_t *)ptr;
-}
-
-static inline int ldl_be_p(const void *ptr)
-{
-    return *(uint32_t *)ptr;
-}
-
-static inline uint64_t ldq_be_p(const void *ptr)
-{
-    return *(uint64_t *)ptr;
-}
-
-static inline void stw_be_p(void *ptr, int v)
-{
-    *(uint16_t *)ptr = v;
-}
-
-static inline void stl_be_p(void *ptr, int v)
-{
-    *(uint32_t *)ptr = v;
-}
-
-static inline void stq_be_p(void *ptr, uint64_t v)
-{
-    *(uint64_t *)ptr = v;
-}
-
-/* float access */
-
-static inline float32 ldfl_be_p(const void *ptr)
-{
-    return *(float32 *)ptr;
-}
-
-static inline float64 ldfq_be_p(const void *ptr)
-{
-    return *(float64 *)ptr;
-}
-
-static inline void stfl_be_p(void *ptr, float32 v)
-{
-    *(float32 *)ptr = v;
-}
-
-static inline void stfq_be_p(void *ptr, float64 v)
-{
-    *(float64 *)ptr = v;
-}
-
-#endif
-
 #endif /* BSWAP_H */