Version 1.0.1

Signed-off-by: Justin M. Forbes <jforbes@redhat.com>

.exrc

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

.gitignore

@@ -1,67 +1,53 @@
-/config-devices.*
-/config-all-devices.*
-/config-all-disas.*
-/config-host.*
-/config-target.*
-/config.status
-/config-temp
-/trace/generated-tracers.h
-/trace/generated-tracers.c
-/trace/generated-tracers-dtrace.h
-/trace/generated-tracers.dtrace
-/trace/generated-events.h
-/trace/generated-events.c
-/trace/generated-ust-provider.h
-/trace/generated-ust.c
-/libcacard/trace/generated-tracers.c
+config-devices.*
+config-all-devices.*
+config-host.*
+config-target.*
+trace.h
+trace.c
+trace-dtrace.h
+trace-dtrace.dtrace
 *-timestamp
-/*-softmmu
-/*-darwin-user
-/*-linux-user
-/*-bsd-user
-/libdis*
-/libuser
-/linux-headers/asm
-/qga/qapi-generated
-/qapi-generated
-/qapi-types.[ch]
-/qapi-visit.[ch]
-/qapi-event.[ch]
-/qmp-commands.h
-/qmp-marshal.c
-/qemu-doc.html
-/qemu-tech.html
-/qemu-doc.info
-/qemu-tech.info
-/qemu.1
-/qemu.pod
-/qemu-img.1
-/qemu-img.pod
-/qemu-img
-/qemu-nbd
-/qemu-nbd.8
-/qemu-nbd.pod
-/qemu-options.def
-/qemu-options.texi
-/qemu-img-cmds.texi
-/qemu-img-cmds.h
-/qemu-io
-/qemu-ga
-/qemu-bridge-helper
-/qemu-monitor.texi
-/qmp-commands.txt
-/vscclient
-/fsdev/virtfs-proxy-helper
-/fsdev/virtfs-proxy-helper.1
-/fsdev/virtfs-proxy-helper.pod
+*-softmmu
+*-darwin-user
+*-linux-user
+*-bsd-user
+libdis*
+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
+qemu-tech.info
+qemu.1
+qemu.pod
+qemu-img.1
+qemu-img.pod
+qemu-img
+qemu-nbd
+qemu-nbd.8
+qemu-nbd.pod
+qemu-options.def
+qemu-options.texi
+qemu-img-cmds.texi
+qemu-img-cmds.h
+qemu-io
+qemu-ga
+qemu-monitor.texi
+QMP/qmp-commands.txt
+test-coroutine
+.gdbinit
 *.a
 *.aux
 *.cp
 *.dvi
 *.exe
-*.dll
-*.so
-*.mo
 *.fn
 *.ky
 *.log
@@ -75,31 +61,16 @@
 *.tp
 *.vr
 *.d
-!/scripts/qemu-guest-agent/fsfreeze-hook.d
 *.o
-*.lo
-*.la
-*.pc
-.libs
-.sdk
-*.gcda
-*.gcno
-/pc-bios/bios-pq/status
-/pc-bios/vgabios-pq/status
-/pc-bios/optionrom/linuxboot.asm
-/pc-bios/optionrom/linuxboot.bin
-/pc-bios/optionrom/linuxboot.raw
-/pc-bios/optionrom/linuxboot.img
-/pc-bios/optionrom/multiboot.asm
-/pc-bios/optionrom/multiboot.bin
-/pc-bios/optionrom/multiboot.raw
-/pc-bios/optionrom/multiboot.img
-/pc-bios/optionrom/kvmvapic.asm
-/pc-bios/optionrom/kvmvapic.bin
-/pc-bios/optionrom/kvmvapic.raw
-/pc-bios/optionrom/kvmvapic.img
-/pc-bios/s390-ccw/s390-ccw.elf
-/pc-bios/s390-ccw/s390-ccw.img
+*.swp
+*.orig
+.pc
+patches
+pc-bios/bios-pq/status
+pc-bios/vgabios-pq/status
+pc-bios/optionrom/linuxboot.bin
+pc-bios/optionrom/multiboot.bin
+pc-bios/optionrom/multiboot.raw
 .stgit-*
 cscope.*
 tags

.gitmodules

@@ -1,33 +1,21 @@
 [submodule "roms/vgabios"]
 	path = roms/vgabios
-	url = git://git.qemu-project.org/vgabios.git/
+	url = git://git.qemu.org/vgabios.git/
 [submodule "roms/seabios"]
 	path = roms/seabios
-	url = git://git.qemu-project.org/seabios.git/
+	url = git://git.qemu.org/seabios.git/
 [submodule "roms/SLOF"]
 	path = roms/SLOF
-	url = git://git.qemu-project.org/SLOF.git
+	url = git://git.qemu.org/SLOF.git
 [submodule "roms/ipxe"]
 	path = roms/ipxe
-	url = git://git.qemu-project.org/ipxe.git
+	url = git://git.qemu.org/ipxe.git
 [submodule "roms/openbios"]
 	path = roms/openbios
-	url = git://git.qemu-project.org/openbios.git
-[submodule "roms/openhackware"]
-	path = roms/openhackware
-	url = git://git.qemu-project.org/openhackware.git
+	url = git://git.qemu.org/openbios.git
 [submodule "roms/qemu-palcode"]
 	path = roms/qemu-palcode
-	url = git://github.com/rth7680/qemu-palcode.git
+	url = git://repo.or.cz/qemu-palcode.git
 [submodule "roms/sgabios"]
 	path = roms/sgabios
-	url = git://git.qemu-project.org/sgabios.git
-[submodule "pixman"]
-	path = pixman
-	url = git://anongit.freedesktop.org/pixman
-[submodule "dtc"]
-	path = dtc
-	url = git://git.qemu-project.org/dtc.git
-[submodule "roms/u-boot"]
-	path = roms/u-boot
-	url = git://git.qemu-project.org/u-boot.git
+	url = git://git.qemu.org/sgabios.git

.mailmap

@@ -1,17 +0,0 @@
-# This mailmap just translates the weird addresses from the original import into git
-# into proper addresses so that they are counted properly in git shortlog output.
-#
-Andrzej Zaborowski <balrogg@gmail.com> balrog <balrog@c046a42c-6fe2-441c-8c8c-71466251a162>
-Anthony Liguori <anthony@codemonkey.ws> aliguori <aliguori@c046a42c-6fe2-441c-8c8c-71466251a162>
-Anthony Liguori <anthony@codemonkey.ws> Anthony Liguori <aliguori@us.ibm.com>
-Aurelien Jarno <aurelien@aurel32.net> aurel32 <aurel32@c046a42c-6fe2-441c-8c8c-71466251a162>
-Blue Swirl <blauwirbel@gmail.com> blueswir1 <blueswir1@c046a42c-6fe2-441c-8c8c-71466251a162>
-Edgar E. Iglesias <edgar.iglesias@gmail.com> edgar_igl <edgar_igl@c046a42c-6fe2-441c-8c8c-71466251a162>
-Fabrice Bellard <fabrice@bellard.org> bellard <bellard@c046a42c-6fe2-441c-8c8c-71466251a162>
-Jocelyn Mayer <l_indien@magic.fr> j_mayer <j_mayer@c046a42c-6fe2-441c-8c8c-71466251a162>
-Paul Brook <paul@codesourcery.com> pbrook <pbrook@c046a42c-6fe2-441c-8c8c-71466251a162>
-Thiemo Seufer <ths@networkno.de> ths <ths@c046a42c-6fe2-441c-8c8c-71466251a162>
-malc <av1474@comtv.ru> malc <malc@c046a42c-6fe2-441c-8c8c-71466251a162>
-# There is also a:
-#    (no author) <(no author)@c046a42c-6fe2-441c-8c8c-71466251a162>
-# for the cvs2svn initialization commit e63c3dc74bf.

.travis.yml

@@ -1,81 +0,0 @@
-language: c
-python:
-  - "2.4"
-compiler:
-  - gcc
-  - clang
-notifications:
-  irc:
-    channels:
-      - "irc.oftc.net#qemu"
-    on_success: change
-    on_failure: always
-env:
-  global:
-    - TEST_CMD="make check"
-    - EXTRA_CONFIG=""
-    # Development packages, EXTRA_PKGS saved for additional builds
-    - CORE_PKGS="libusb-1.0-0-dev libiscsi-dev librados-dev libncurses5-dev"
-    - NET_PKGS="libseccomp-dev libgnutls-dev libssh2-1-dev  libspice-server-dev libspice-protocol-dev libnss3-dev"
-    - GUI_PKGS="libgtk-3-dev libvte-2.90-dev libsdl1.2-dev libpng12-dev libpixman-1-dev"
-    - EXTRA_PKGS=""
-  matrix:
-    - TARGETS=alpha-softmmu,alpha-linux-user
-    - TARGETS=arm-softmmu,arm-linux-user
-    - TARGETS=aarch64-softmmu,aarch64-linux-user
-    - TARGETS=cris-softmmu
-    - TARGETS=i386-softmmu,x86_64-softmmu
-    - TARGETS=lm32-softmmu
-    - TARGETS=m68k-softmmu
-    - TARGETS=microblaze-softmmu,microblazeel-softmmu
-    - TARGETS=mips-softmmu,mips64-softmmu,mips64el-softmmu,mipsel-softmmu
-    - TARGETS=moxie-softmmu
-    - TARGETS=or32-softmmu,
-    - TARGETS=ppc-softmmu,ppc64-softmmu,ppcemb-softmmu
-    - TARGETS=s390x-softmmu
-    - TARGETS=sh4-softmmu,sh4eb-softmmu
-    - TARGETS=sparc-softmmu,sparc64-softmmu
-    - TARGETS=unicore32-softmmu
-    - TARGETS=xtensa-softmmu,xtensaeb-softmmu
-before_install:
-  - git submodule update --init --recursive
-  - sudo apt-get update -qq
-  - sudo apt-get install -qq ${CORE_PKGS} ${NET_PKGS} ${GUI_PKGS} ${EXTRA_PKGS}
-script: "./configure --target-list=${TARGETS} ${EXTRA_CONFIG} && make && ${TEST_CMD}"
-matrix:
-  # We manually include a number of additional build for non-standard bits
-  include:
-    # Debug related options
-    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-debug"
-      compiler: gcc
-    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-debug --enable-tcg-interpreter"
-      compiler: gcc
-    # All the extra -dev packages
-    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_PKGS="libaio-dev libcap-ng-dev libattr1-dev libbrlapi-dev uuid-dev libusb-1.0.0-dev"
-      compiler: gcc
-    # Currently configure doesn't force --disable-pie
-    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-gprof --enable-gcov --disable-pie"
-      compiler: gcc
-    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_PKGS="sparse"
-           EXTRA_CONFIG="--enable-sparse"
-      compiler: gcc
-    # All the trace backends (apart from dtrace)
-    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-trace-backends=stderr"
-      compiler: gcc
-    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-trace-backends=simple"
-      compiler: gcc
-    - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-trace-backends=ftrace"
-           TEST_CMD=""
-      compiler: gcc
-    - env: TARGETS=i386-softmmu,x86_64-softmmu
-          EXTRA_PKGS="liblttng-ust-dev liburcu-dev"
-          EXTRA_CONFIG="--enable-trace-backends=ust"
-      compiler: gcc

CODING_STYLE

@@ -1,4 +1,4 @@
-QEMU Coding Style
+Qemu Coding Style
 =================
 
 Please use the script checkpatch.pl in the scripts directory to check
@@ -44,8 +44,7 @@ Rationale:
 3. Naming
 
 Variables are lower_case_with_underscores; easy to type and read.  Structured
-type names are in CamelCase; harder to type but standing out.  Enum type
-names and function type names should also be in CamelCase.  Scalar type
+type names are in CamelCase; harder to type but standing out.  Scalar type
 names are lower_case_with_underscores_ending_with_a_t, like the POSIX
 uint64_t and family.  Note that this last convention contradicts POSIX
 and is therefore likely to be changed.
@@ -84,10 +83,3 @@ and clarity it comes on a line by itself:
 Rationale: a consistent (except for functions...) bracing style reduces
 ambiguity and avoids needless churn when lines are added or removed.
 Furthermore, it is the QEMU coding style.
-
-5. Declarations
-
-Mixed declarations (interleaving statements and declarations within blocks)
-are not allowed; declarations should be at the beginning of blocks.  In other
-words, the code should not generate warnings if using GCC's
--Wdeclaration-after-statement option.

Changelog

@@ -1,6 +1,6 @@
 This file documents changes for QEMU releases 0.12 and earlier.
 For changelog information for later releases, see
-http://wiki.qemu-project.org/ChangeLog or look at the git history for
+http://wiki.qemu.org/ChangeLog or look at the git history for
 more detailed information.
 
 
@@ -78,7 +78,7 @@ version 0.10.2:
 
   - fix savevm/loadvm (Anthony Liguori)
   - live migration: fix dirty tracking windows (Glauber Costa)
-  - live migration: improve error propagation (Glauber Costa)
+  - live migration: improve error propogation (Glauber Costa)
   - qcow2: fix image creation for > ~2TB images (Chris Wright)
   - hotplug: fix error handling for if= parameter (Eduardo Habkost)
   - qcow2: fix data corruption (Nolan Leake)
@@ -386,7 +386,7 @@ version 0.5.3:
   - support of CD-ROM change
   - multiple network interface support
   - initial x86-64 host support (Gwenole Beauchesne)
-  - lret to outer privilege fix (OS/2 install fix)
+  - lret to outer priviledge fix (OS/2 install fix)
   - task switch fixes (SkyOS boot)
   - VM save/restore commands
   - new timer API
@@ -447,7 +447,7 @@ version 0.5.0:
   - multi-target build
   - fixed: no error code in hardware interrupts
   - fixed: pop ss, mov ss, x and sti disable hardware irqs for the next insn
-  - correct single stepping through string operations
+  - correct single stepping thru string operations
   - preliminary SPARC target support (Thomas M. Ogrisegg)
   - tun-fd option (Rusty Russell)
   - automatic IDE geometry detection

HACKING

@@ -32,7 +32,7 @@ mandatory for VMState fields.
 
 Don't use Linux kernel internal types like u32, __u32 or __le32.
 
-Use hwaddr for guest physical addresses except pcibus_t
+Use target_phys_addr_t for guest physical addresses except pcibus_t
 for PCI addresses.  In addition, ram_addr_t is a QEMU internal address
 space that maps guest RAM physical addresses into an intermediate
 address space that can map to host virtual address spaces.  Generally
@@ -40,23 +40,8 @@ speaking, the size of guest memory can always fit into ram_addr_t but
 it would not be correct to store an actual guest physical address in a
 ram_addr_t.
 
-For CPU virtual addresses there are several possible types.
-vaddr is the best type to use to hold a CPU virtual address in
-target-independent code. It is guaranteed to be large enough to hold a
-virtual address for any target, and it does not change size from target
-to target. It is always unsigned.
-target_ulong is a type the size of a virtual address on the CPU; this means
-it may be 32 or 64 bits depending on which target is being built. It should
-therefore be used only in target-specific code, and in some
-performance-critical built-per-target core code such as the TLB code.
-There is also a signed version, target_long.
-abi_ulong is for the *-user targets, and represents a type the size of
-'void *' in that target's ABI. (This may not be the same as the size of a
-full CPU virtual address in the case of target ABIs which use 32 bit pointers
-on 64 bit CPUs, like sparc32plus.) Definitions of structures that must match
-the target's ABI must use this type for anything that on the target is defined
-to be an 'unsigned long' or a pointer type.
-There is also a signed version, abi_long.
+Use target_ulong (or abi_ulong) for CPU virtual addresses, however
+devices should not need to use target_ulong.
 
 Of course, take all of the above with a grain of salt.  If you're about
 to use some system interface that requires a type like size_t, pid_t or
@@ -92,24 +77,22 @@ avoided.
 
 Use of the malloc/free/realloc/calloc/valloc/memalign/posix_memalign
 APIs is not allowed in the QEMU codebase. Instead of these routines,
-use the GLib memory allocation routines g_malloc/g_malloc0/g_new/
-g_new0/g_realloc/g_free or QEMU's qemu_memalign/qemu_blockalign/qemu_vfree
-APIs.
+use the replacement g_malloc/g_malloc0/g_realloc/g_free or
+qemu_vmalloc/qemu_memalign/qemu_vfree APIs.
 
-Please note that g_malloc will exit on allocation failure, so there
-is no need to test for failure (as you would have to with malloc).
-Calling g_malloc with a zero size is valid and will return NULL.
+Please note that NULL check for the g_malloc result is redundant and
+that g_malloc() call with zero size is not allowed.
 
-Memory allocated by qemu_memalign or qemu_blockalign must be freed with
-qemu_vfree, since breaking this will cause problems on Win32.
+Memory allocated by qemu_vmalloc or qemu_memalign must be freed with
+qemu_vfree, since breaking this will cause problems on Win32 and user
+emulators.
 
 4. String manipulation
 
-Do not use the strncpy function.  As mentioned in the man page, it does *not*
-guarantee a NULL-terminated buffer, which makes it extremely dangerous to use.
-It also zeros trailing destination bytes out to the specified length.  Instead,
-use this similar function when possible, but note its different signature:
-void pstrcpy(char *dest, int dest_buf_size, const char *src)
+Do not use the strncpy function.  According to the man page, it does
+*not* guarantee a NULL-terminated buffer, which makes it extremely dangerous
+to use.  Instead, use functionally equivalent function:
+void pstrcpy(char *buf, int buf_size, const char *str)
 
 Don't use strcat because it can't check for buffer overflows, but:
 char *pstrcat(char *buf, int buf_size, const char *s)
@@ -137,23 +120,3 @@ gcc's printf attribute directive in the prototype.
 This makes it so gcc's -Wformat and -Wformat-security options can do
 their jobs and cross-check format strings with the number and types
 of arguments.
-
-6. C standard, implementation defined and undefined behaviors
-
-C code in QEMU should be written to the C99 language specification. A copy
-of the final version of the C99 standard with corrigenda TC1, TC2, and TC3
-included, formatted as a draft, can be downloaded from:
- http://www.open-std.org/jtc1/sc22/WG14/www/docs/n1256.pdf
-
-The C language specification defines regions of undefined behavior and
-implementation defined behavior (to give compiler authors enough leeway to
-produce better code).  In general, code in QEMU should follow the language
-specification and avoid both undefined and implementation defined
-constructs. ("It works fine on the gcc I tested it with" is not a valid
-argument...) However there are a few areas where we allow ourselves to
-assume certain behaviors because in practice all the platforms we care about
-behave in the same way and writing strictly conformant code would be
-painful. These are:
- * you may assume that integers are 2s complement representation
- * you may assume that right shift of a signed integer duplicates
-   the sign bit (ie it is an arithmetic shift, not a logical shift)

LICENSE

@@ -1,21 +1,18 @@
 The following points clarify the QEMU license:
 
-1) QEMU as a whole is released under the GNU General Public License,
-version 2.
+1) QEMU as a whole is released under the GNU General Public License
 
 2) Parts of QEMU have specific licenses which are compatible with the
-GNU General Public License, version 2. Hence each source file contains
-its own licensing information.  Source files with no licensing information
-are released under the GNU General Public License, version 2 or (at your
-option) any later version.
+GNU General Public License. Hence each source file contains its own
+licensing information.
 
-As of July 2013, contributions under version 2 of the GNU General Public
-License (and no later version) are only accepted for the following files
-or directories: bsd-user/, linux-user/, hw/misc/vfio.c, hw/xen/xen_pt*.
+In particular, the QEMU virtual CPU core library (libqemu.a) is
+released under the GNU Lesser General Public License. Many hardware
+device emulation sources are released under the BSD license.
 
 3) The Tiny Code Generator (TCG) is released under the BSD license
    (see license headers in files).
 
 4) QEMU is a trademark of Fabrice Bellard.
 
-Fabrice Bellard and the QEMU team
+Fabrice Bellard.

Makefile

@@ -3,64 +3,26 @@
 # Always point to the root of the build tree (needs GNU make).
 BUILD_DIR=$(CURDIR)
 
-# All following code might depend on configuration variables
+GENERATED_HEADERS = config-host.h trace.h qemu-options.def
+ifeq ($(TRACE_BACKEND),dtrace)
+GENERATED_HEADERS += trace-dtrace.h
+endif
+GENERATED_HEADERS += qmp-commands.h qapi-types.h qapi-visit.h
+GENERATED_SOURCES += qmp-marshal.c qapi-types.c qapi-visit.c
+
 ifneq ($(wildcard config-host.mak),)
 # Put the all: rule here so that config-host.mak can contain dependencies.
-all:
+all: build-all
 include config-host.mak
-
-# Check that we're not trying to do an out-of-tree build from
-# a tree that's been used for an in-tree build.
-ifneq ($(realpath $(SRC_PATH)),$(realpath .))
-ifneq ($(wildcard $(SRC_PATH)/config-host.mak),)
-$(error This is an out of tree build but your source tree ($(SRC_PATH)) \
-seems to have been used for an in-tree build. You can fix this by running \
-"make distclean && rm -rf *-linux-user *-softmmu" in your source tree)
-endif
-endif
-
-CONFIG_SOFTMMU := $(if $(filter %-softmmu,$(TARGET_DIRS)),y)
-CONFIG_USER_ONLY := $(if $(filter %-user,$(TARGET_DIRS)),y)
-CONFIG_ALL=y
--include config-all-devices.mak
--include config-all-disas.mak
-
 include $(SRC_PATH)/rules.mak
 config-host.mak: $(SRC_PATH)/configure
 	@echo $@ is out-of-date, running configure
-	@# TODO: The next lines include code which supports a smooth
-	@# transition from old configurations without config.status.
-	@# This code can be removed after QEMU 1.7.
-	@if test -x config.status; then \
-	    ./config.status; \
-        else \
-	    sed -n "/.*Configured with/s/[^:]*: //p" $@ | sh; \
-	fi
+	@sed -n "/.*Configured with/s/[^:]*: //p" $@ | sh
 else
 config-host.mak:
-ifneq ($(filter-out %clean,$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
 	@echo "Please call configure before running make!"
 	@exit 1
 endif
-endif
-
-GENERATED_HEADERS = config-host.h qemu-options.def
-GENERATED_HEADERS += qmp-commands.h qapi-types.h qapi-visit.h qapi-event.h
-GENERATED_SOURCES += qmp-marshal.c qapi-types.c qapi-visit.c qapi-event.c
-
-GENERATED_HEADERS += trace/generated-events.h
-GENERATED_SOURCES += trace/generated-events.c
-
-GENERATED_HEADERS += trace/generated-tracers.h
-ifeq ($(findstring dtrace,$(TRACE_BACKENDS)),dtrace)
-GENERATED_HEADERS += trace/generated-tracers-dtrace.h
-endif
-GENERATED_SOURCES += trace/generated-tracers.c
-
-ifeq ($(findstring ust,$(TRACE_BACKENDS)),ust)
-GENERATED_HEADERS += trace/generated-ust-provider.h
-GENERATED_SOURCES += trace/generated-ust.c
-endif
 
 # Don't try to regenerate Makefile or configure
 # We don't generate any of them
@@ -68,37 +30,24 @@ Makefile: ;
 configure: ;
 
 .PHONY: all clean cscope distclean dvi html info install install-doc \
-	pdf recurse-all speed test dist
+	pdf recurse-all speed tar tarbin test build-all
 
-$(call set-vpath, $(SRC_PATH))
+$(call set-vpath, $(SRC_PATH):$(SRC_PATH)/hw)
 
 LIBS+=-lz $(LIBS_TOOLS)
 
-HELPERS-$(CONFIG_LINUX) = qemu-bridge-helper$(EXESUF)
-
 ifdef BUILD_DOCS
-DOCS=qemu-doc.html qemu-tech.html qemu.1 qemu-img.1 qemu-nbd.8 qmp-commands.txt
-ifdef CONFIG_VIRTFS
-DOCS+=fsdev/virtfs-proxy-helper.1
-endif
+DOCS=qemu-doc.html qemu-tech.html qemu.1 qemu-img.1 qemu-nbd.8 QMP/qmp-commands.txt
 else
 DOCS=
 endif
 
 SUBDIR_MAKEFLAGS=$(if $(V),,--no-print-directory) BUILD_DIR=$(BUILD_DIR)
 SUBDIR_DEVICES_MAK=$(patsubst %, %/config-devices.mak, $(TARGET_DIRS))
-SUBDIR_DEVICES_MAK_DEP=$(patsubst %, %-config-devices.mak.d, $(TARGET_DIRS))
+SUBDIR_DEVICES_MAK_DEP=$(patsubst %, %/config-devices.mak.d, $(TARGET_DIRS))
 
-ifeq ($(SUBDIR_DEVICES_MAK),)
-config-all-devices.mak:
-	$(call quiet-command,echo '# no devices' > $@,"  GEN   $@")
-else
 config-all-devices.mak: $(SUBDIR_DEVICES_MAK)
-	$(call quiet-command, sed -n \
-             's|^\([^=]*\)=\(.*\)$$|\1:=$$(findstring y,$$(\1)\2)|p' \
-             $(SUBDIR_DEVICES_MAK) | sort -u > $@, \
-             "  GEN   $@")
-endif
+	$(call quiet-command,cat $(SUBDIR_DEVICES_MAK) | grep =y | sort -u > $@,"  GEN   $@")
 
 -include $(SUBDIR_DEVICES_MAK_DEP)
 
@@ -125,28 +74,9 @@ endif
 defconfig:
 	rm -f config-all-devices.mak $(SUBDIR_DEVICES_MAK)
 
-ifneq ($(wildcard config-host.mak),)
-include $(SRC_PATH)/Makefile.objs
-endif
+-include config-all-devices.mak
 
-dummy := $(call unnest-vars,, \
-                stub-obj-y \
-                util-obj-y \
-                qga-obj-y \
-                qga-vss-dll-obj-y \
-                block-obj-y \
-                block-obj-m \
-                common-obj-y \
-                common-obj-m)
-
-ifneq ($(wildcard config-host.mak),)
-include $(SRC_PATH)/tests/Makefile
-endif
-ifeq ($(CONFIG_SMARTCARD_NSS),y)
-include $(SRC_PATH)/libcacard/Makefile
-endif
-
-all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all modules
+build-all: $(DOCS) $(TOOLS) $(CHECKS) recurse-all
 
 config-host.h: config-host.h-timestamp
 config-host.h-timestamp: config-host.mak
@@ -154,34 +84,20 @@ qemu-options.def: $(SRC_PATH)/qemu-options.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $@")
 
 SUBDIR_RULES=$(patsubst %,subdir-%, $(TARGET_DIRS))
-SOFTMMU_SUBDIR_RULES=$(filter %-softmmu,$(SUBDIR_RULES))
 
-$(SOFTMMU_SUBDIR_RULES): $(block-obj-y)
-$(SOFTMMU_SUBDIR_RULES): config-all-devices.mak
-
-subdir-%:
+subdir-%: $(GENERATED_HEADERS)
 	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C $* V="$(V)" TARGET_DIR="$*/" all,)
 
-subdir-pixman: pixman/Makefile
-	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C pixman V="$(V)" all,)
+ifneq ($(wildcard config-host.mak),)
+include $(SRC_PATH)/Makefile.objs
+endif
 
-pixman/Makefile: $(SRC_PATH)/pixman/configure
-	(cd pixman; CFLAGS="$(CFLAGS) -fPIC $(extra_cflags) $(extra_ldflags)" $(SRC_PATH)/pixman/configure $(AUTOCONF_HOST) --disable-gtk --disable-shared --enable-static)
+$(common-obj-y): $(GENERATED_HEADERS)
+subdir-libcacard: $(oslib-obj-y) $(trace-obj-y) qemu-timer-common.o
 
-$(SRC_PATH)/pixman/configure:
-	(cd $(SRC_PATH)/pixman; autoreconf -v --install)
+$(filter %-softmmu,$(SUBDIR_RULES)): $(trace-obj-y) $(common-obj-y) subdir-libdis
 
-DTC_MAKE_ARGS=-I$(SRC_PATH)/dtc VPATH=$(SRC_PATH)/dtc -C dtc V="$(V)" LIBFDT_srcdir=$(SRC_PATH)/dtc/libfdt
-DTC_CFLAGS=$(CFLAGS) $(QEMU_CFLAGS)
-DTC_CPPFLAGS=-I$(BUILD_DIR)/dtc -I$(SRC_PATH)/dtc -I$(SRC_PATH)/dtc/libfdt
-
-subdir-dtc:dtc/libfdt dtc/tests
-	$(call quiet-command,$(MAKE) $(DTC_MAKE_ARGS) CPPFLAGS="$(DTC_CPPFLAGS)" CFLAGS="$(DTC_CFLAGS)" LDFLAGS="$(LDFLAGS)" ARFLAGS="$(ARFLAGS)" CC="$(CC)" AR="$(AR)" LD="$(LD)" $(SUBDIR_MAKEFLAGS) libfdt/libfdt.a,)
-
-dtc/%:
-	mkdir -p $@
-
-$(SUBDIR_RULES): libqemuutil.a libqemustub.a $(common-obj-y)
+$(filter %-user,$(SUBDIR_RULES)): $(GENERATED_HEADERS) $(trace-obj-y) subdir-libdis-user subdir-libuser
 
 ROMSUBDIR_RULES=$(patsubst %,romsubdir-%, $(ROMS))
 romsubdir-%:
@@ -191,239 +107,216 @@ ALL_SUBDIRS=$(TARGET_DIRS) $(patsubst %,pc-bios/%, $(ROMS))
 
 recurse-all: $(SUBDIR_RULES) $(ROMSUBDIR_RULES)
 
-$(BUILD_DIR)/version.o: $(SRC_PATH)/version.rc $(BUILD_DIR)/config-host.h | $(BUILD_DIR)/version.lo
-	$(call quiet-command,$(WINDRES) -I$(BUILD_DIR) -o $@ $<,"  RC    version.o")
-$(BUILD_DIR)/version.lo: $(SRC_PATH)/version.rc $(BUILD_DIR)/config-host.h
-	$(call quiet-command,$(WINDRES) -I$(BUILD_DIR) -o $@ $<,"  RC    version.lo")
+audio/audio.o audio/fmodaudio.o: QEMU_CFLAGS += $(FMOD_CFLAGS)
 
-Makefile: $(version-obj-y) $(version-lobj-y)
+QEMU_CFLAGS+=$(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)
+
+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
 ######################################################################
-# Build libraries
+# Support building shared library libcacard
 
-libqemustub.a: $(stub-obj-y)
-libqemuutil.a: $(util-obj-y) qapi-types.o qapi-visit.o qapi-event.o
+.PHONY: libcacard.la install-libcacard
+ifeq ($(LIBTOOL),)
+libcacard.la:
+	@echo "libtool is missing, please install and rerun configure"; exit 1
 
-block-modules = $(foreach o,$(block-obj-m),"$(basename $(subst /,-,$o))",) NULL
-util/module.o-cflags = -D'CONFIG_BLOCK_MODULES=$(block-modules)'
+install-libcacard:
+	@echo "libtool is missing, please install and rerun configure"; exit 1
+else
+libcacard.la: $(GENERATED_HEADERS) $(oslib-obj-y) qemu-timer-common.o $(addsuffix .lo, $(basename $(trace-obj-y)))
+	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C libcacard V="$(V)" TARGET_DIR="$*/" libcacard.la,)
 
+install-libcacard: libcacard.la
+	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C libcacard V="$(V)" TARGET_DIR="$*/" install-libcacard,)
+endif
 ######################################################################
 
 qemu-img.o: qemu-img-cmds.h
+qemu-img.o qemu-tool.o qemu-nbd.o qemu-io.o cmd.o qemu-ga.o: $(GENERATED_HEADERS)
 
-qemu-img$(EXESUF): qemu-img.o $(block-obj-y) libqemuutil.a libqemustub.a
-qemu-nbd$(EXESUF): qemu-nbd.o $(block-obj-y) libqemuutil.a libqemustub.a
-qemu-io$(EXESUF): qemu-io.o $(block-obj-y) libqemuutil.a libqemustub.a
+tools-obj-y = qemu-tool.o $(oslib-obj-y) $(trace-obj-y) \
+	qemu-timer-common.o cutils.o
 
-qemu-bridge-helper$(EXESUF): qemu-bridge-helper.o
-
-fsdev/virtfs-proxy-helper$(EXESUF): fsdev/virtfs-proxy-helper.o fsdev/virtio-9p-marshal.o libqemuutil.a libqemustub.a
-fsdev/virtfs-proxy-helper$(EXESUF): LIBS += -lcap
+qemu-img$(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-img-cmds.h: $(SRC_PATH)/qemu-img-cmds.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/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: 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 = $(LIBS_QGA)
-qemu-ga$(EXESUF): QEMU_CFLAGS += -I qga/qapi-generated
 
-gen-out-type = $(subst .,-,$(suffix $@))
+$(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-py = $(SRC_PATH)/scripts/qapi.py $(SRC_PATH)/scripts/ordereddict.py
-
-qga/qapi-generated/qga-qapi-types.c qga/qapi-generated/qga-qapi-types.h :\
-$(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py \
-		$(gen-out-type) -o qga/qapi-generated -p "qga-" -i $<, \
-		"  GEN   $@")
-qga/qapi-generated/qga-qapi-visit.c qga/qapi-generated/qga-qapi-visit.h :\
-$(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-visit.py $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py \
-		$(gen-out-type) -o qga/qapi-generated -p "qga-" -i $<, \
-		"  GEN   $@")
-qga/qapi-generated/qga-qmp-commands.h qga/qapi-generated/qga-qmp-marshal.c :\
-$(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py \
-		$(gen-out-type) -o qga/qapi-generated -p "qga-" -i $<, \
-		"  GEN   $@")
-
-qapi-modules = $(SRC_PATH)/qapi-schema.json $(SRC_PATH)/qapi/common.json \
-               $(SRC_PATH)/qapi/block.json $(SRC_PATH)/qapi/block-core.json \
-               $(SRC_PATH)/qapi/event.json
+$(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 :\
-$(qapi-modules) $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py \
-		$(gen-out-type) -o "." -b -i $<, \
-		"  GEN   $@")
+$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-types.py
+	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py -o "." < $<, "  GEN   $@")
 qapi-visit.c qapi-visit.h :\
-$(qapi-modules) $(SRC_PATH)/scripts/qapi-visit.py $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py \
-		$(gen-out-type) -o "." -b -i $<, \
-		"  GEN   $@")
-qapi-event.c qapi-event.h :\
-$(qapi-modules) $(SRC_PATH)/scripts/qapi-event.py $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-event.py \
-		$(gen-out-type) -o "." -b -i $<, \
-		"  GEN   $@")
+$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-visit.py
+	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py -o "."  < $<, "  GEN   $@")
 qmp-commands.h qmp-marshal.c :\
-$(qapi-modules) $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py \
-		$(gen-out-type) -o "." -m -i $<, \
-		"  GEN   $@")
+$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py
+	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py -m -o "." < $<, "  GEN   $@")
 
-QGALIB_GEN=$(addprefix qga/qapi-generated/, qga-qapi-types.h qga-qapi-visit.h qga-qmp-commands.h)
-$(qga-obj-y) qemu-ga.o: $(QGALIB_GEN)
+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
 
-qemu-ga$(EXESUF): $(qga-obj-y) libqemuutil.a libqemustub.a
-	$(call LINK, $^)
+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
 
 clean:
 # avoid old build problems by removing potentially incorrect old files
 	rm -f config.mak op-i386.h opc-i386.h gen-op-i386.h op-arm.h opc-arm.h gen-op-arm.h
 	rm -f qemu-options.def
-	find . \( -name '*.l[oa]' -o -name '*.so' -o -name '*.dll' -o -name '*.mo' -o -name '*.[oda]' \) -type f -exec rm {} +
-	rm -f $(filter-out %.tlb,$(TOOLS)) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
-	rm -f fsdev/*.pod
-	rm -rf .libs */.libs
+	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 qemu-img-cmds.h
-	@# May not be present in GENERATED_HEADERS
-	rm -f trace/generated-tracers-dtrace.dtrace*
-	rm -f trace/generated-tracers-dtrace.h*
-	rm -f $(foreach f,$(GENERATED_HEADERS),$(f) $(f)-timestamp)
-	rm -f $(foreach f,$(GENERATED_SOURCES),$(f) $(f)-timestamp)
-	rm -rf qapi-generated
-	rm -rf qga/qapi-generated
-	for d in $(ALL_SUBDIRS); do \
+	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 \
 	if test -d $$d; then $(MAKE) -C $$d $@ || exit 1; fi; \
 	rm -f $$d/qemu-options.def; \
         done
 
-VERSION ?= $(shell cat VERSION)
-
-dist: qemu-$(VERSION).tar.bz2
-
-qemu-%.tar.bz2:
-	$(SRC_PATH)/scripts/make-release "$(SRC_PATH)" "$(patsubst qemu-%.tar.bz2,%,$@)"
-
 distclean: clean
 	rm -f config-host.mak config-host.h* config-host.ld $(DOCS) qemu-options.texi qemu-img-cmds.texi qemu-monitor.texi
-	rm -f config-all-devices.mak config-all-disas.mak
-	rm -f po/*.mo
+	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 linux-headers/asm
 	rm -f qemu-tech.info qemu-tech.aux qemu-tech.cp qemu-tech.dvi qemu-tech.fn qemu-tech.info qemu-tech.ky qemu-tech.log qemu-tech.pdf qemu-tech.pg qemu-tech.toc qemu-tech.tp qemu-tech.vr
-	for d in $(TARGET_DIRS); do \
+	for d in $(TARGET_DIRS) $(QEMULIBS); do \
 	rm -rf $$d || exit 1 ; \
         done
-	rm -Rf .sdk
-	if test -f pixman/config.log; then make -C pixman distclean; fi
-	if test -f dtc/version_gen.h; then make $(DTC_MAKE_ARGS) clean; fi
 
 KEYMAPS=da     en-gb  et  fr     fr-ch  is  lt  modifiers  no  pt-br  sv \
 ar      de     en-us  fi  fr-be  hr     it  lv  nl         pl  ru     th \
-common  de-ch  es     fo  fr-ca  hu     ja  mk  nl-be      pt  sl     tr \
-bepo    cz
+common  de-ch  es     fo  fr-ca  hu     ja  mk  nl-be      pt  sl     tr
 
 ifdef INSTALL_BLOBS
-BLOBS=bios.bin bios-256k.bin sgabios.bin vgabios.bin vgabios-cirrus.bin \
+BLOBS=bios.bin sgabios.bin vgabios.bin vgabios-cirrus.bin \
 vgabios-stdvga.bin vgabios-vmware.bin vgabios-qxl.bin \
-acpi-dsdt.aml q35-acpi-dsdt.aml \
-ppc_rom.bin openbios-sparc32 openbios-sparc64 openbios-ppc QEMU,tcx.bin QEMU,cgthree.bin \
+ppc_rom.bin openbios-sparc32 openbios-sparc64 openbios-ppc \
 pxe-e1000.rom pxe-eepro100.rom pxe-ne2k_pci.rom \
 pxe-pcnet.rom pxe-rtl8139.rom pxe-virtio.rom \
-efi-e1000.rom efi-eepro100.rom efi-ne2k_pci.rom \
-efi-pcnet.rom efi-rtl8139.rom efi-virtio.rom \
-qemu-icon.bmp qemu_logo_no_text.svg \
 bamboo.dtb petalogix-s3adsp1800.dtb petalogix-ml605.dtb \
-multiboot.bin linuxboot.bin kvmvapic.bin \
+mpc8544ds.dtb \
+multiboot.bin linuxboot.bin \
 s390-zipl.rom \
-s390-ccw.img \
 spapr-rtas.bin slof.bin \
-palcode-clipper \
-u-boot.e500
+palcode-clipper
 else
 BLOBS=
 endif
 
 install-doc: $(DOCS)
-	$(INSTALL_DIR) "$(DESTDIR)$(qemu_docdir)"
-	$(INSTALL_DATA) qemu-doc.html  qemu-tech.html "$(DESTDIR)$(qemu_docdir)"
-	$(INSTALL_DATA) qmp-commands.txt "$(DESTDIR)$(qemu_docdir)"
+	$(INSTALL_DIR) "$(DESTDIR)$(docdir)"
+	$(INSTALL_DATA) qemu-doc.html  qemu-tech.html "$(DESTDIR)$(docdir)"
 ifdef CONFIG_POSIX
 	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man1"
-	$(INSTALL_DATA) qemu.1 "$(DESTDIR)$(mandir)/man1"
-ifneq ($(TOOLS),)
-	$(INSTALL_DATA) qemu-img.1 "$(DESTDIR)$(mandir)/man1"
+	$(INSTALL_DATA) qemu.1 qemu-img.1 "$(DESTDIR)$(mandir)/man1"
 	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man8"
 	$(INSTALL_DATA) qemu-nbd.8 "$(DESTDIR)$(mandir)/man8"
 endif
-endif
-ifdef CONFIG_VIRTFS
-	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man1"
-	$(INSTALL_DATA) fsdev/virtfs-proxy-helper.1 "$(DESTDIR)$(mandir)/man1"
-endif
 
-install-datadir:
-	$(INSTALL_DIR) "$(DESTDIR)$(qemu_datadir)"
+install-sysconfig:
+	$(INSTALL_DIR) "$(DESTDIR)$(sysconfdir)/qemu"
+	$(INSTALL_DATA) $(SRC_PATH)/sysconfigs/target/target-x86_64.conf "$(DESTDIR)$(sysconfdir)/qemu"
 
-install-localstatedir:
-ifdef CONFIG_POSIX
-ifneq (,$(findstring qemu-ga,$(TOOLS)))
-	$(INSTALL_DIR) "$(DESTDIR)$(qemu_localstatedir)"/run
-endif
-endif
-
-install-confdir:
-	$(INSTALL_DIR) "$(DESTDIR)$(qemu_confdir)"
-
-install-sysconfig: install-datadir install-confdir
-	$(INSTALL_DATA) $(SRC_PATH)/sysconfigs/target/target-x86_64.conf "$(DESTDIR)$(qemu_confdir)"
-
-install: all $(if $(BUILD_DOCS),install-doc) install-sysconfig \
-install-datadir install-localstatedir
+install: all $(if $(BUILD_DOCS),install-doc) install-sysconfig
+	$(INSTALL_DIR) "$(DESTDIR)$(bindir)"
 ifneq ($(TOOLS),)
-	$(call install-prog,$(TOOLS),$(DESTDIR)$(bindir))
-endif
-ifneq ($(CONFIG_MODULES),)
-	$(INSTALL_DIR) "$(DESTDIR)$(qemu_moddir)"
-	for s in $(modules-m:.mo=$(DSOSUF)); do \
-		t="$(DESTDIR)$(qemu_moddir)/$$(echo $$s | tr / -)"; \
-		$(INSTALL_LIB) $$s "$$t"; \
-		test -z "$(STRIP)" || $(STRIP) "$$t"; \
-	done
-endif
-ifneq ($(HELPERS-y),)
-	$(call install-prog,$(HELPERS-y),$(DESTDIR)$(libexecdir))
+	$(INSTALL_PROG) $(STRIP_OPT) $(TOOLS) "$(DESTDIR)$(bindir)"
 endif
 ifneq ($(BLOBS),)
+	$(INSTALL_DIR) "$(DESTDIR)$(datadir)"
 	set -e; for x in $(BLOBS); do \
-		$(INSTALL_DATA) $(SRC_PATH)/pc-bios/$$x "$(DESTDIR)$(qemu_datadir)"; \
+		$(INSTALL_DATA) $(SRC_PATH)/pc-bios/$$x "$(DESTDIR)$(datadir)"; \
 	done
 endif
-ifeq ($(CONFIG_GTK),y)
-	$(MAKE) -C po $@
-endif
-	$(INSTALL_DIR) "$(DESTDIR)$(qemu_datadir)/keymaps"
+	$(INSTALL_DIR) "$(DESTDIR)$(datadir)/keymaps"
 	set -e; for x in $(KEYMAPS); do \
-		$(INSTALL_DATA) $(SRC_PATH)/pc-bios/keymaps/$$x "$(DESTDIR)$(qemu_datadir)/keymaps"; \
+		$(INSTALL_DATA) $(SRC_PATH)/pc-bios/keymaps/$$x "$(DESTDIR)$(datadir)/keymaps"; \
 	done
 	for d in $(TARGET_DIRS); do \
-	$(MAKE) $(SUBDIR_MAKEFLAGS) TARGET_DIR=$$d/ -C $$d $@ || exit 1 ; \
+	$(MAKE) -C $$d $@ || exit 1 ; \
         done
 
 # various test targets
 test speed: all
-	$(MAKE) -C tests/tcg $@
+	$(MAKE) -C tests $@
+
+.PHONY: check
+check: $(patsubst %,run-check-%,$(CHECKS))
+
+run-check-%: %
+	./$<
 
 .PHONY: TAGS
 TAGS:
-	rm -f $@
-	find "$(SRC_PATH)" -name '*.[hc]' -exec etags --append {} +
+	find "$(SRC_PATH)" -name '*.[hc]' -print0 | xargs -0 etags
 
 cscope:
 	rm -f ./cscope.*
@@ -438,7 +331,7 @@ TEXIFLAG=$(if $(V),,--quiet)
 	$(call quiet-command,texi2dvi $(TEXIFLAG) -I . $<,"  GEN   $@")
 
 %.html: %.texi
-	$(call quiet-command,LC_ALL=C $(MAKEINFO) $(MAKEINFOFLAGS) --html $< -o $@, \
+	$(call quiet-command,$(MAKEINFO) $(MAKEINFOFLAGS) --html $< -o $@, \
 	"  GEN   $@")
 
 %.info: %.texi
@@ -453,7 +346,7 @@ qemu-options.texi: $(SRC_PATH)/qemu-options.hx
 qemu-monitor.texi: $(SRC_PATH)/hmp-commands.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"  GEN   $@")
 
-qmp-commands.txt: $(SRC_PATH)/qmp-commands.hx
+QMP/qmp-commands.txt: $(SRC_PATH)/qmp-commands.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -q < $< > $@,"  GEN   $@")
 
 qemu-img-cmds.texi: $(SRC_PATH)/qemu-img-cmds.hx
@@ -462,25 +355,19 @@ qemu-img-cmds.texi: $(SRC_PATH)/qemu-img-cmds.hx
 qemu.1: qemu-doc.texi qemu-options.texi qemu-monitor.texi
 	$(call quiet-command, \
 	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< qemu.pod && \
-	  $(POD2MAN) --section=1 --center=" " --release=" " qemu.pod > $@, \
+	  pod2man --section=1 --center=" " --release=" " qemu.pod > $@, \
 	  "  GEN   $@")
 
 qemu-img.1: qemu-img.texi qemu-img-cmds.texi
 	$(call quiet-command, \
 	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< qemu-img.pod && \
-	  $(POD2MAN) --section=1 --center=" " --release=" " qemu-img.pod > $@, \
-	  "  GEN   $@")
-
-fsdev/virtfs-proxy-helper.1: fsdev/virtfs-proxy-helper.texi
-	$(call quiet-command, \
-	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< fsdev/virtfs-proxy-helper.pod && \
-	  $(POD2MAN) --section=1 --center=" " --release=" " fsdev/virtfs-proxy-helper.pod > $@, \
+	  pod2man --section=1 --center=" " --release=" " qemu-img.pod > $@, \
 	  "  GEN   $@")
 
 qemu-nbd.8: qemu-nbd.texi
 	$(call quiet-command, \
 	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< qemu-nbd.pod && \
-	  $(POD2MAN) --section=8 --center=" " --release=" " qemu-nbd.pod > $@, \
+	  pod2man --section=8 --center=" " --release=" " qemu-nbd.pod > $@, \
 	  "  GEN   $@")
 
 dvi: qemu-doc.dvi qemu-tech.dvi
@@ -492,67 +379,15 @@ qemu-doc.dvi qemu-doc.html qemu-doc.info qemu-doc.pdf: \
 	qemu-img.texi qemu-nbd.texi qemu-options.texi \
 	qemu-monitor.texi qemu-img-cmds.texi
 
-ifdef CONFIG_WIN32
+VERSION ?= $(shell cat VERSION)
+FILE = qemu-$(VERSION)
 
-INSTALLER = qemu-setup-$(VERSION)$(EXESUF)
-
-nsisflags = -V2 -NOCD
-
-ifneq ($(wildcard $(SRC_PATH)/dll),)
-ifeq ($(ARCH),x86_64)
-# 64 bit executables
-DLL_PATH = $(SRC_PATH)/dll/w64
-nsisflags += -DW64
-else
-# 32 bit executables
-DLL_PATH = $(SRC_PATH)/dll/w32
-endif
-endif
-
-.PHONY: installer
-installer: $(INSTALLER)
-
-INSTDIR=/tmp/qemu-nsis
-
-$(INSTALLER): $(SRC_PATH)/qemu.nsi
-	make install prefix=${INSTDIR}
-ifdef SIGNCODE
-	(cd ${INSTDIR}; \
-         for i in *.exe; do \
-           $(SIGNCODE) $${i}; \
-         done \
-        )
-endif # SIGNCODE
-	(cd ${INSTDIR}; \
-         for i in qemu-system-*.exe; do \
-           arch=$${i%.exe}; \
-           arch=$${arch#qemu-system-}; \
-           echo Section \"$$arch\" Section_$$arch; \
-           echo SetOutPath \"\$$INSTDIR\"; \
-           echo File \"\$${BINDIR}\\$$i\"; \
-           echo SectionEnd; \
-         done \
-        ) >${INSTDIR}/system-emulations.nsh
-	makensis $(nsisflags) \
-                $(if $(BUILD_DOCS),-DCONFIG_DOCUMENTATION="y") \
-                $(if $(CONFIG_GTK),-DCONFIG_GTK="y") \
-                -DBINDIR="${INSTDIR}" \
-                $(if $(DLL_PATH),-DDLLDIR="$(DLL_PATH)") \
-                -DSRCDIR="$(SRC_PATH)" \
-                -DOUTFILE="$(INSTALLER)" \
-                $(SRC_PATH)/qemu.nsi
-	rm -r ${INSTDIR}
-ifdef SIGNCODE
-	$(SIGNCODE) $(INSTALLER)
-endif # SIGNCODE
-endif # CONFIG_WIN
-
-# Add a dependency on the generated files, so that they are always
-# rebuilt before other object files
-ifneq ($(filter-out %clean,$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
-Makefile: $(GENERATED_HEADERS)
-endif
+# tar release (use 'make -k tar' on a checkouted tree)
+tar:
+	rm -rf /tmp/$(FILE)
+	cp -r . /tmp/$(FILE)
+	cd /tmp && tar zcvf ~/$(FILE).tar.gz $(FILE) --exclude CVS --exclude .git --exclude .svn
+	rm -rf /tmp/$(FILE)
 
 # Include automatically generated dependency files
-# Dependencies in Makefile.objs files come from our recursive subdir rules
--include $(wildcard *.d tests/*.d)
+-include $(wildcard *.d audio/*.d slirp/*.d block/*.d net/*.d ui/*.d qapi/*.d qga/*.d)

Makefile.dis

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

Makefile.hw

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

Makefile.objs

@@ -1,115 +1,429 @@
 #######################################################################
-# Common libraries for tools and emulators
-stub-obj-y = stubs/
-util-obj-y = util/ qobject/ qapi/ trace/
+# 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
 
 #######################################################################
 # block-obj-y is code used by both qemu system emulation and qemu-img
 
-block-obj-y = async.o thread-pool.o
-block-obj-y += nbd.o block.o blockjob.o
-block-obj-y += main-loop.o iohandler.o qemu-timer.o
-block-obj-$(CONFIG_POSIX) += aio-posix.o
-block-obj-$(CONFIG_WIN32) += aio-win32.o
-block-obj-y += block/
-block-obj-y += qapi-types.o qapi-visit.o qapi-event.o
-block-obj-y += qemu-io-cmds.o
+block-obj-y = cutils.o cache-utils.o qemu-option.o module.o async.o
+block-obj-y += nbd.o block.o aio.o aes.o qemu-config.o qemu-progress.o qemu-sockets.o
+block-obj-y += $(coroutine-obj-y) $(qobject-obj-y) $(version-obj-y)
+block-obj-$(CONFIG_POSIX) += posix-aio-compat.o
+block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
 
-block-obj-y += qemu-coroutine.o qemu-coroutine-lock.o qemu-coroutine-io.o
-block-obj-y += qemu-coroutine-sleep.o
-block-obj-y += coroutine-$(CONFIG_COROUTINE_BACKEND).o
+block-nested-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o
+block-nested-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
+block-nested-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
+block-nested-y += qed-check.o
+block-nested-y += parallels.o nbd.o blkdebug.o sheepdog.o blkverify.o
+block-nested-$(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-m = block/
+block-obj-y +=  $(addprefix block/, $(block-nested-y))
 
+net-obj-y = net.o
+net-nested-y = queue.o checksum.o util.o
+net-nested-y += socket.o
+net-nested-y += dump.o
+net-nested-$(CONFIG_POSIX) += tap.o
+net-nested-$(CONFIG_LINUX) += tap-linux.o
+net-nested-$(CONFIG_WIN32) += tap-win32.o
+net-nested-$(CONFIG_BSD) += tap-bsd.o
+net-nested-$(CONFIG_SOLARIS) += tap-solaris.o
+net-nested-$(CONFIG_AIX) += tap-aix.o
+net-nested-$(CONFIG_HAIKU) += tap-haiku.o
+net-nested-$(CONFIG_SLIRP) += slirp.o
+net-nested-$(CONFIG_VDE) += vde.o
+net-obj-y += $(addprefix net/, $(net-nested-y))
+
+ifeq ($(CONFIG_VIRTIO)$(CONFIG_VIRTFS)$(CONFIG_PCI),yyy)
+# Lots of the fsdev/9pcode is pulled in by vl.c via qemu_fsdev_add.
+# only pull in the actual virtio-9p device if we also enabled virtio.
+CONFIG_REALLY_VIRTFS=y
+fsdev-nested-y = qemu-fsdev.o
+else
+fsdev-nested-y = qemu-fsdev-dummy.o
+endif
+fsdev-obj-$(CONFIG_VIRTFS) += $(addprefix fsdev/, $(fsdev-nested-y))
+
+######################################################################
+# libqemu_common.a: Target independent part of system emulation. The
+# long term path is to suppress *all* target specific code in case of
+# system emulation, i.e. a single QEMU executable should support all
+# CPUs and machines.
+
+common-obj-y = $(block-obj-y) blockdev.o
+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 += $(oslib-obj-y)
+common-obj-$(CONFIG_WIN32) += os-win32.o
+common-obj-$(CONFIG_POSIX) += os-posix.o
+
+common-obj-y += tcg-runtime.o host-utils.o main-loop.o
+common-obj-y += irq.o input.o
+common-obj-$(CONFIG_PTIMER) += ptimer.o
+common-obj-$(CONFIG_MAX7310) += max7310.o
+common-obj-$(CONFIG_WM8750) += wm8750.o
+common-obj-$(CONFIG_TWL92230) += twl92230.o
+common-obj-$(CONFIG_TSC2005) += tsc2005.o
+common-obj-$(CONFIG_LM832X) += lm832x.o
+common-obj-$(CONFIG_TMP105) += tmp105.o
+common-obj-$(CONFIG_STELLARIS_INPUT) += stellaris_input.o
+common-obj-$(CONFIG_SSD0303) += ssd0303.o
+common-obj-$(CONFIG_SSD0323) += ssd0323.o
+common-obj-$(CONFIG_ADS7846) += ads7846.o
+common-obj-$(CONFIG_MAX111X) += max111x.o
+common-obj-$(CONFIG_DS1338) += ds1338.o
+common-obj-y += i2c.o smbus.o smbus_eeprom.o
+common-obj-y += eeprom93xx.o
+common-obj-y += scsi-disk.o cdrom.o
+common-obj-y += scsi-generic.o scsi-bus.o
+common-obj-y += hid.o
+common-obj-y += usb.o usb-hub.o usb-$(HOST_USB).o usb-hid.o usb-msd.o usb-wacom.o
+common-obj-y += usb-serial.o usb-net.o usb-bus.o usb-desc.o
+common-obj-$(CONFIG_SSI) += ssi.o
+common-obj-$(CONFIG_SSI_SD) += ssi-sd.o
+common-obj-$(CONFIG_SD) += sd.o
+common-obj-y += bt.o bt-host.o bt-vhci.o bt-l2cap.o bt-sdp.o bt-hci.o bt-hid.o usb-bt.o
+common-obj-y += bt-hci-csr.o
+common-obj-y += buffered_file.o migration.o migration-tcp.o
+common-obj-y += qemu-char.o 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-$(CONFIG_BRLAPI) += baum.o
+common-obj-$(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
+audio-obj-$(CONFIG_FMOD) += fmodaudio.o
+audio-obj-$(CONFIG_ESD) += esdaudio.o
+audio-obj-$(CONFIG_PA) += paaudio.o
+audio-obj-$(CONFIG_WINWAVE) += winwaveaudio.o
+audio-obj-$(CONFIG_AUDIO_PT_INT) += audio_pt_int.o
+audio-obj-$(CONFIG_AUDIO_WIN_INT) += audio_win_int.o
+audio-obj-y += wavcapture.o
+common-obj-y += $(addprefix audio/, $(audio-obj-y))
+
+ui-obj-y += keymaps.o
+ui-obj-$(CONFIG_SDL) += sdl.o sdl_zoom.o x_keymap.o
+ui-obj-$(CONFIG_COCOA) += cocoa.o
+ui-obj-$(CONFIG_CURSES) += curses.o
+vnc-obj-y += vnc.o d3des.o
+vnc-obj-y += vnc-enc-zlib.o vnc-enc-hextile.o
+vnc-obj-y += vnc-enc-tight.o vnc-palette.o
+vnc-obj-y += vnc-enc-zrle.o
+vnc-obj-$(CONFIG_VNC_TLS) += vnc-tls.o vnc-auth-vencrypt.o
+vnc-obj-$(CONFIG_VNC_SASL) += vnc-auth-sasl.o
+ifdef CONFIG_VNC_THREAD
+vnc-obj-y += vnc-jobs-async.o
+else
+vnc-obj-y += vnc-jobs-sync.o
+endif
+common-obj-y += $(addprefix ui/, $(ui-obj-y))
+common-obj-$(CONFIG_VNC) += $(addprefix ui/, $(vnc-obj-y))
+
+common-obj-y += iov.o acl.o
+common-obj-$(CONFIG_POSIX) += compatfd.o
+common-obj-y += notify.o event_notifier.o
+common-obj-y += qemu-timer.o qemu-timer-common.o
+
+slirp-obj-y = cksum.o if.o ip_icmp.o ip_input.o ip_output.o
+slirp-obj-y += slirp.o mbuf.o misc.o sbuf.o socket.o tcp_input.o tcp_output.o
+slirp-obj-y += tcp_subr.o tcp_timer.o udp.o bootp.o tftp.o arp_table.o
+common-obj-$(CONFIG_SLIRP) += $(addprefix slirp/, $(slirp-obj-y))
+
+# xen backend driver support
+common-obj-$(CONFIG_XEN_BACKEND) += xen_backend.o xen_devconfig.o
+common-obj-$(CONFIG_XEN_BACKEND) += xen_console.o xenfb.o xen_disk.o xen_nic.o
+
+######################################################################
+# libuser
+
+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-$(CONFIG_PCI) += ioh3420.o xio3130_upstream.o xio3130_downstream.o
+hw-obj-y += watchdog.o
+hw-obj-$(CONFIG_ISA_MMIO) += isa_mmio.o
+hw-obj-$(CONFIG_ECC) += ecc.o
+hw-obj-$(CONFIG_NAND) += nand.o
+hw-obj-$(CONFIG_PFLASH_CFI01) += pflash_cfi01.o
+hw-obj-$(CONFIG_PFLASH_CFI02) += pflash_cfi02.o
+
+hw-obj-$(CONFIG_M48T59) += m48t59.o
+hw-obj-$(CONFIG_ESCC) += escc.o
+hw-obj-$(CONFIG_EMPTY_SLOT) += empty_slot.o
+
+hw-obj-$(CONFIG_SERIAL) += serial.o
+hw-obj-$(CONFIG_PARALLEL) += parallel.o
+hw-obj-$(CONFIG_I8254) += i8254.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_PREP_PCI) += prep_pci.o
+# Mac shared devices
+hw-obj-$(CONFIG_MACIO) += macio.o
+hw-obj-$(CONFIG_CUDA) += cuda.o
+hw-obj-$(CONFIG_ADB) += adb.o
+hw-obj-$(CONFIG_MAC_NVRAM) += mac_nvram.o
+hw-obj-$(CONFIG_MAC_DBDMA) += mac_dbdma.o
+# OldWorld PowerMac
+hw-obj-$(CONFIG_HEATHROW_PIC) += heathrow_pic.o
+hw-obj-$(CONFIG_GRACKLE_PCI) += grackle_pci.o
+# NewWorld PowerMac
+hw-obj-$(CONFIG_UNIN_PCI) += unin_pci.o
+hw-obj-$(CONFIG_DEC_PCI) += dec_pci.o
+# PowerPC E500 boards
+hw-obj-$(CONFIG_PPCE500_PCI) += ppce500_pci.o
+
+# MIPS devices
+hw-obj-$(CONFIG_PIIX4) += piix4.o
+hw-obj-$(CONFIG_G364FB) += g364fb.o
+
+# PCI watchdog devices
+hw-obj-$(CONFIG_PCI) += wdt_i6300esb.o
+
+hw-obj-$(CONFIG_PCI) += pcie.o pcie_aer.o pcie_port.o
+
+# PCI network cards
+hw-obj-$(CONFIG_NE2000_PCI) += ne2000.o
+hw-obj-$(CONFIG_EEPRO100_PCI) += eepro100.o
+hw-obj-$(CONFIG_PCNET_PCI) += pcnet-pci.o
+hw-obj-$(CONFIG_PCNET_COMMON) += pcnet.o
+hw-obj-$(CONFIG_E1000_PCI) += e1000.o
+hw-obj-$(CONFIG_RTL8139_PCI) += rtl8139.o
+
+hw-obj-$(CONFIG_SMC91C111) += smc91c111.o
+hw-obj-$(CONFIG_LAN9118) += lan9118.o
+hw-obj-$(CONFIG_NE2000_ISA) += ne2000-isa.o
+hw-obj-$(CONFIG_OPENCORES_ETH) += opencores_eth.o
+
+# IDE
+hw-obj-$(CONFIG_IDE_CORE) += ide/core.o ide/atapi.o
+hw-obj-$(CONFIG_IDE_QDEV) += ide/qdev.o
+hw-obj-$(CONFIG_IDE_PCI) += ide/pci.o
+hw-obj-$(CONFIG_IDE_ISA) += ide/isa.o
+hw-obj-$(CONFIG_IDE_PIIX) += ide/piix.o
+hw-obj-$(CONFIG_IDE_CMD646) += ide/cmd646.o
+hw-obj-$(CONFIG_IDE_MACIO) += ide/macio.o
+hw-obj-$(CONFIG_IDE_VIA) += ide/via.o
+hw-obj-$(CONFIG_AHCI) += ide/ahci.o
+hw-obj-$(CONFIG_AHCI) += ide/ich.o
+
+# SCSI layer
+hw-obj-$(CONFIG_LSI_SCSI_PCI) += lsi53c895a.o
+hw-obj-$(CONFIG_ESP) += esp.o
+
+hw-obj-y += dma-helpers.o sysbus.o isa-bus.o
+hw-obj-y += qdev-addr.o
+
+# VGA
+hw-obj-$(CONFIG_VGA_PCI) += vga-pci.o
+hw-obj-$(CONFIG_VGA_ISA) += vga-isa.o
+hw-obj-$(CONFIG_VGA_ISA_MM) += vga-isa-mm.o
+hw-obj-$(CONFIG_VMWARE_VGA) += vmware_vga.o
+hw-obj-$(CONFIG_VMMOUSE) += vmmouse.o
+
+hw-obj-$(CONFIG_RC4030) += rc4030.o
+hw-obj-$(CONFIG_DP8393X) += dp8393x.o
+hw-obj-$(CONFIG_DS1225Y) += ds1225y.o
+hw-obj-$(CONFIG_MIPSNET) += mipsnet.o
+
+# Sound
+sound-obj-y =
+sound-obj-$(CONFIG_SB16) += sb16.o
+sound-obj-$(CONFIG_ES1370) += es1370.o
+sound-obj-$(CONFIG_AC97) += ac97.o
+sound-obj-$(CONFIG_ADLIB) += fmopl.o adlib.o
+sound-obj-$(CONFIG_GUS) += gus.o gusemu_hal.o gusemu_mixer.o
+sound-obj-$(CONFIG_CS4231A) += cs4231a.o
+sound-obj-$(CONFIG_HDA) += intel-hda.o hda-audio.o
+
+adlib.o fmopl.o: QEMU_CFLAGS += -DBUILD_Y8950=0
+hw-obj-$(CONFIG_SOUND) += $(sound-obj-y)
+
+9pfs-nested-$(CONFIG_VIRTFS)  = virtio-9p.o
+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)
+
+
+######################################################################
+# libdis
+# NOTE: the disassembler code is only needed for debugging
+
+libdis-y =
+libdis-$(CONFIG_ALPHA_DIS) += alpha-dis.o
+libdis-$(CONFIG_ARM_DIS) += arm-dis.o
+libdis-$(CONFIG_CRIS_DIS) += cris-dis.o
+libdis-$(CONFIG_HPPA_DIS) += hppa-dis.o
+libdis-$(CONFIG_I386_DIS) += i386-dis.o
+libdis-$(CONFIG_IA64_DIS) += ia64-dis.o
+libdis-$(CONFIG_M68K_DIS) += m68k-dis.o
+libdis-$(CONFIG_MICROBLAZE_DIS) += microblaze-dis.o
+libdis-$(CONFIG_MIPS_DIS) += mips-dis.o
+libdis-$(CONFIG_PPC_DIS) += ppc-dis.o
+libdis-$(CONFIG_S390_DIS) += s390-dis.o
+libdis-$(CONFIG_SH4_DIS) += sh4-dis.o
+libdis-$(CONFIG_SPARC_DIS) += sparc-dis.o
+
+######################################################################
+# trace
+
+ifeq ($(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 += libcacard/cac.o libcacard/event.o
-libcacard-y += libcacard/vcard.o libcacard/vreader.o
-libcacard-y += libcacard/vcard_emul_nss.o
-libcacard-y += libcacard/vcard_emul_type.o
-libcacard-y += libcacard/card_7816.o
-libcacard-y += libcacard/vcardt.o
-libcacard/vcard_emul_nss.o-cflags := $(NSS_CFLAGS)
-libcacard/vcard_emul_nss.o-libs := $(NSS_LIBS)
-
-######################################################################
-# Target independent part of system emulation. The long term path is to
-# suppress *all* target specific code in case of system emulation, i.e. a
-# single QEMU executable should support all CPUs and machines.
-
-ifeq ($(CONFIG_SOFTMMU),y)
-common-obj-y = blockdev.o blockdev-nbd.o block/
-common-obj-y += iothread.o
-common-obj-y += net/
-common-obj-y += qdev-monitor.o device-hotplug.o
-common-obj-$(CONFIG_WIN32) += os-win32.o
-common-obj-$(CONFIG_POSIX) += os-posix.o
-
-common-obj-$(CONFIG_LINUX) += fsdev/
-
-common-obj-y += migration.o migration-tcp.o
-common-obj-y += vmstate.o
-common-obj-y += qemu-file.o
-common-obj-$(CONFIG_RDMA) += migration-rdma.o
-common-obj-y += qemu-char.o #aio.o
-common-obj-y += block-migration.o
-common-obj-y += page_cache.o xbzrle.o
-
-common-obj-$(CONFIG_POSIX) += migration-exec.o migration-unix.o migration-fd.o
-
-common-obj-$(CONFIG_SPICE) += spice-qemu-char.o
-
-common-obj-y += audio/
-common-obj-y += hw/
-
-common-obj-y += ui/
-common-obj-y += bt-host.o bt-vhci.o
-bt-host.o-cflags := $(BLUEZ_CFLAGS)
-
-common-obj-y += dma-helpers.o
-common-obj-y += vl.o
-vl.o-cflags := $(GPROF_CFLAGS) $(SDL_CFLAGS)
-common-obj-y += tpm.o
-
-common-obj-$(CONFIG_SLIRP) += slirp/
-
-common-obj-y += backends/
-
-common-obj-$(CONFIG_SECCOMP) += qemu-seccomp.o
-
-common-obj-$(CONFIG_SMARTCARD_NSS) += $(libcacard-y)
+libcacard-y = cac.o event.o vcard.o vreader.o vcard_emul_nss.o vcard_emul_type.o card_7816.o
 
 ######################################################################
 # qapi
 
-common-obj-y += qmp-marshal.o
+qapi-nested-y = qapi-visit-core.o qmp-input-visitor.o qmp-output-visitor.o qapi-dealloc-visitor.o
+qapi-nested-y += qmp-registry.o qmp-dispatch.o
+qapi-obj-y = $(addprefix qapi/, $(qapi-nested-y))
+
+common-obj-y += qmp-marshal.o qapi-visit.o qapi-types.o $(qapi-obj-y)
 common-obj-y += qmp.o hmp.o
-endif
-
-######################################################################
-# some qapi visitors are used by both system and user emulation:
-
-common-obj-y += qapi-visit.o qapi-types.o
-
-#######################################################################
-# Target-independent parts used in system and user emulation
-common-obj-y += qemu-log.o
-common-obj-y += tcg-runtime.o
-common-obj-y += hw/
-common-obj-y += qom/
-common-obj-y += disas/
-
-######################################################################
-# Resource file for Windows executables
-version-obj-$(CONFIG_WIN32) += $(BUILD_DIR)/version.o
-version-lobj-$(CONFIG_WIN32) += $(BUILD_DIR)/version.lo
 
 ######################################################################
 # guest agent
 
-# FIXME: a few definitions from qapi-types.o/qapi-visit.o are needed
-# by libqemuutil.a.  These should be moved to a separate .json schema.
-qga-obj-y = qga/ qapi-types.o qapi-visit.o
-qga-vss-dll-obj-y = qga/
+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)
+

Makefile.target

@@ -1,44 +1,47 @@
 # -*- Mode: makefile -*-
 
-include ../config-host.mak
-include config-target.mak
-include config-devices.mak
-include $(SRC_PATH)/rules.mak
+GENERATED_HEADERS = config-target.h
+CONFIG_NO_PCI = $(if $(subst n,,$(CONFIG_PCI)),n,y)
+CONFIG_NO_KVM = $(if $(subst n,,$(CONFIG_KVM)),n,y)
+CONFIG_NO_XEN = $(if $(subst n,,$(CONFIG_XEN)),n,y)
 
-$(call set-vpath, $(SRC_PATH))
+include ../config-host.mak
+include config-devices.mak
+include config-target.mak
+include $(SRC_PATH)/rules.mak
+ifneq ($(HWDIR),)
+include $(HWDIR)/config.mak
+endif
+
+TARGET_PATH=$(SRC_PATH)/target-$(TARGET_BASE_ARCH)
+$(call set-vpath, $(SRC_PATH):$(TARGET_PATH):$(SRC_PATH)/hw)
 ifdef CONFIG_LINUX
 QEMU_CFLAGS += -I../linux-headers
 endif
-QEMU_CFLAGS += -I.. -I$(SRC_PATH)/target-$(TARGET_BASE_ARCH) -DNEED_CPU_H
+QEMU_CFLAGS += -I.. -I$(TARGET_PATH) -DNEED_CPU_H
 
-QEMU_CFLAGS+=-I$(SRC_PATH)/include
+include $(SRC_PATH)/Makefile.objs
 
 ifdef CONFIG_USER_ONLY
 # user emulator name
-QEMU_PROG=qemu-$(TARGET_NAME)
-QEMU_PROG_BUILD = $(QEMU_PROG)
+QEMU_PROG=qemu-$(TARGET_ARCH2)
 else
 # system emulator name
-QEMU_PROG=qemu-system-$(TARGET_NAME)$(EXESUF)
-ifneq (,$(findstring -mwindows,$(libs_softmmu)))
-# Terminate program name with a 'w' because the linker builds a windows executable.
-QEMU_PROGW=qemu-system-$(TARGET_NAME)w$(EXESUF)
-$(QEMU_PROG): $(QEMU_PROGW)
-	$(call quiet-command,$(OBJCOPY) --subsystem console $(QEMU_PROGW) $(QEMU_PROG),"  GEN   $(TARGET_DIR)$(QEMU_PROG)")
-QEMU_PROG_BUILD = $(QEMU_PROGW)
-else
-QEMU_PROG_BUILD = $(QEMU_PROG)
-endif
+QEMU_PROG=qemu-system-$(TARGET_ARCH2)$(EXESUF)
 endif
 
-PROGS=$(QEMU_PROG) $(QEMU_PROGW)
+PROGS=$(QEMU_PROG)
 STPFILES=
 
+ifndef CONFIG_HAIKU
+LIBS+=-lm
+endif
+
 config-target.h: config-target.h-timestamp
 config-target.h-timestamp: config-target.mak
 
 ifdef CONFIG_TRACE_SYSTEMTAP
-stap: $(QEMU_PROG).stp-installed $(QEMU_PROG).stp
+stap: $(QEMU_PROG).stp
 
 ifdef CONFIG_USER_ONLY
 TARGET_TYPE=user
@@ -46,24 +49,13 @@ else
 TARGET_TYPE=system
 endif
 
-$(QEMU_PROG).stp-installed: $(SRC_PATH)/trace-events
-	$(call quiet-command,$(TRACETOOL) \
-		--format=stap \
-		--backends=$(TRACE_BACKENDS) \
-		--binary=$(bindir)/$(QEMU_PROG) \
-		--target-name=$(TARGET_NAME) \
-		--target-type=$(TARGET_TYPE) \
-		< $< > $@,"  GEN   $(TARGET_DIR)$(QEMU_PROG).stp-installed")
-
-$(QEMU_PROG).stp: $(SRC_PATH)/trace-events
-	$(call quiet-command,$(TRACETOOL) \
-		--format=stap \
-		--backends=$(TRACE_BACKENDS) \
-		--binary=$(realpath .)/$(QEMU_PROG) \
-		--target-name=$(TARGET_NAME) \
-		--target-type=$(TARGET_TYPE) \
-		< $< > $@,"  GEN   $(TARGET_DIR)$(QEMU_PROG).stp")
-
+$(QEMU_PROG).stp:
+	$(call quiet-command,sh $(SRC_PATH)/scripts/tracetool \
+		--$(TRACE_BACKEND) \
+		--binary $(bindir)/$(QEMU_PROG) \
+		--target-arch $(TARGET_ARCH) \
+		--target-type $(TARGET_TYPE) \
+		--stap < $(SRC_PATH)/trace-events > $(QEMU_PROG).stp,"  GEN   $(QEMU_PROG).stp")
 else
 stap:
 endif
@@ -75,98 +67,356 @@ all: $(PROGS) stap
 
 #########################################################
 # cpu emulator library
-obj-y = exec.o translate-all.o cpu-exec.o
-obj-y += tcg/tcg.o tcg/optimize.o
-obj-$(CONFIG_TCG_INTERPRETER) += tci.o
-obj-$(CONFIG_TCG_INTERPRETER) += disas/tci.o
-obj-y += fpu/softfloat.o
-obj-y += target-$(TARGET_BASE_ARCH)/
-obj-y += disas.o
-obj-$(call notempty,$(TARGET_XML_FILES)) += gdbstub-xml.o
-obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o
+libobj-y = exec.o translate-all.o cpu-exec.o translate.o
+libobj-y += tcg/tcg.o tcg/optimize.o
+libobj-$(CONFIG_TCG_INTERPRETER) += tci.o
+libobj-y += fpu/softfloat.o
+libobj-y += 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
 
-obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/decContext.o
-obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/decNumber.o
-obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/dpd/decimal32.o
-obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/dpd/decimal64.o
-obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/dpd/decimal128.o
+libobj-y += disas.o
+libobj-$(CONFIG_TCI_DIS) += tci-dis.o
+
+tci-dis.o: QEMU_CFLAGS += -I$(SRC_PATH)/tcg -I$(SRC_PATH)/tcg/tci
+
+$(libobj-y): $(GENERATED_HEADERS)
+
+# libqemu
+
+translate.o: translate.c cpu.h
+
+translate-all.o: translate-all.c cpu.h
+
+tcg/tcg.o: cpu.h
+
+# HELPER_CFLAGS is used for all the code compiled with static register
+# variables
+op_helper.o ldst_helper.o user-exec.o: QEMU_CFLAGS += $(HELPER_CFLAGS)
+
+# Note: this is a workaround. The real fix is to avoid compiling
+# cpu_signal_handler() in user-exec.c.
+signal.o: QEMU_CFLAGS += $(HELPER_CFLAGS)
 
 #########################################################
 # Linux user emulator target
 
 ifdef CONFIG_LINUX_USER
 
-QEMU_CFLAGS+=-I$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR) -I$(SRC_PATH)/linux-user
+$(call set-vpath, $(SRC_PATH)/linux-user:$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR))
 
-obj-y += linux-user/
-obj-y += gdbstub.o thunk.o user-exec.o
+QEMU_CFLAGS+=-I$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR) -I$(SRC_PATH)/linux-user
+obj-y = main.o syscall.o strace.o mmap.o signal.o thunk.o \
+      elfload.o linuxload.o uaccess.o gdbstub.o cpu-uname.o \
+      user-exec.o $(oslib-obj-y)
+
+obj-$(TARGET_HAS_BFLT) += flatload.o
+
+obj-$(TARGET_I386) += vm86.o
+
+obj-i386-y += ioport-user.o
+
+nwfpe-obj-y = fpa11.o fpa11_cpdo.o fpa11_cpdt.o fpa11_cprt.o fpopcode.o
+nwfpe-obj-y += single_cpdo.o double_cpdo.o extended_cpdo.o
+obj-arm-y +=  $(addprefix nwfpe/, $(nwfpe-obj-y))
+obj-arm-y += arm-semi.o
+
+obj-m68k-y += m68k-sim.o m68k-semi.o
+
+$(obj-y) $(obj-$(TARGET_BASE_ARCH)-y): $(GENERATED_HEADERS)
+
+obj-y += $(addprefix ../libuser/, $(user-obj-y))
+obj-y += $(addprefix ../libdis-user/, $(libdis-y))
+obj-y += $(libobj-y)
 
 endif #CONFIG_LINUX_USER
 
+#########################################################
+# Darwin user emulator target
+
+ifdef CONFIG_DARWIN_USER
+
+$(call set-vpath, $(SRC_PATH)/darwin-user)
+
+QEMU_CFLAGS+=-I$(SRC_PATH)/darwin-user -I$(SRC_PATH)/darwin-user/$(TARGET_ARCH)
+
+# Leave some space for the regular program loading zone
+LDFLAGS+=-Wl,-segaddr,__STD_PROG_ZONE,0x1000 -image_base 0x0e000000
+
+LIBS+=-lmx
+
+obj-y = main.o commpage.o machload.o mmap.o signal.o syscall.o thunk.o \
+        gdbstub.o user-exec.o
+
+obj-i386-y += ioport-user.o
+
+$(obj-y) $(obj-$(TARGET_BASE_ARCH)-y): $(GENERATED_HEADERS)
+
+obj-y += $(addprefix ../libuser/, $(user-obj-y))
+obj-y += $(addprefix ../libdis-user/, $(libdis-y))
+obj-y += $(libobj-y)
+
+endif #CONFIG_DARWIN_USER
+
 #########################################################
 # BSD user emulator target
 
 ifdef CONFIG_BSD_USER
 
-QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ABI_DIR) \
-			 -I$(SRC_PATH)/bsd-user/$(HOST_VARIANT_DIR)
+$(call set-vpath, $(SRC_PATH)/bsd-user)
 
-obj-y += bsd-user/
-obj-y += gdbstub.o user-exec.o
+QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ARCH)
+
+obj-y = main.o bsdload.o elfload.o mmap.o signal.o strace.o syscall.o \
+        gdbstub.o uaccess.o user-exec.o
+
+obj-i386-y += ioport-user.o
+
+$(obj-y) $(obj-$(TARGET_BASE_ARCH)-y): $(GENERATED_HEADERS)
+
+obj-y += $(addprefix ../libuser/, $(user-obj-y))
+obj-y += $(addprefix ../libdis-user/, $(libdis-y))
+obj-y += $(libobj-y)
 
 endif #CONFIG_BSD_USER
 
 #########################################################
 # System emulator target
 ifdef CONFIG_SOFTMMU
-obj-y += arch_init.o cpus.o monitor.o gdbstub.o balloon.o ioport.o numa.o
-obj-y += qtest.o
-obj-y += hw/
-obj-$(CONFIG_FDT) += device_tree.o
-obj-$(CONFIG_KVM) += kvm-all.o
-obj-y += memory.o savevm.o cputlb.o
-obj-y += memory_mapping.o
-obj-y += dump.o
-LIBS+=$(libs_softmmu)
+
+obj-y = arch_init.o cpus.o monitor.o machine.o gdbstub.o balloon.o ioport.o
+# virtio has to be here due to weird dependency between PCI and virtio-net.
+# need to fix this properly
+obj-$(CONFIG_NO_PCI) += pci-stub.o
+obj-$(CONFIG_VIRTIO) += virtio.o virtio-blk.o virtio-balloon.o virtio-net.o virtio-serial-bus.o
+obj-y += vhost_net.o
+obj-$(CONFIG_VHOST_NET) += vhost.o
+obj-$(CONFIG_REALLY_VIRTFS) += 9pfs/virtio-9p-device.o
+obj-$(CONFIG_KVM) += kvm.o kvm-all.o
+obj-$(CONFIG_NO_KVM) += kvm-stub.o
+obj-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-$(CONFIG_XEN) += xen-common.o
-obj-$(CONFIG_XEN_I386) += xen-hvm.o xen-mapcache.o
-obj-$(call lnot,$(CONFIG_XEN)) += xen-common-stub.o
-obj-$(call lnot,$(CONFIG_XEN_I386)) += xen-hvm-stub.o
+obj-$(CONFIG_XEN) += xen-all.o xen_machine_pv.o xen_domainbuild.o xen-mapcache.o
+obj-$(CONFIG_NO_XEN) += xen-stub.o
+
+obj-i386-$(CONFIG_XEN) += xen_platform.o
+
+# Inter-VM PCI shared memory
+CONFIG_IVSHMEM =
+ifeq ($(CONFIG_KVM), y)
+  ifeq ($(CONFIG_PCI), y)
+    CONFIG_IVSHMEM = y
+  endif
+endif
+obj-$(CONFIG_IVSHMEM) += ivshmem.o
 
 # Hardware support
-ifeq ($(TARGET_NAME), sparc64)
-obj-y += hw/sparc64/
+obj-i386-y += vga.o
+obj-i386-y += mc146818rtc.o pc.o
+obj-i386-y += cirrus_vga.o sga.o apic.o ioapic.o piix_pci.o
+obj-i386-y += vmport.o
+obj-i386-y += device-hotplug.o pci-hotplug.o smbios.o wdt_ib700.o
+obj-i386-y += debugcon.o multiboot.o
+obj-i386-y += pc_piix.o
+obj-i386-$(CONFIG_KVM) += kvmclock.o
+obj-i386-$(CONFIG_SPICE) += qxl.o qxl-logger.o qxl-render.o
+
+# shared objects
+obj-ppc-y = ppc.o ppc_booke.o
+obj-ppc-y += vga.o
+# PREP target
+obj-ppc-y += mc146818rtc.o
+obj-ppc-y += ppc_prep.o
+# OldWorld PowerMac
+obj-ppc-y += ppc_oldworld.o
+# NewWorld PowerMac
+obj-ppc-y += ppc_newworld.o
+# IBM pSeries (sPAPR)
+obj-ppc-$(CONFIG_PSERIES) += spapr.o spapr_hcall.o spapr_rtas.o spapr_vio.o
+obj-ppc-$(CONFIG_PSERIES) += xics.o spapr_vty.o spapr_llan.o spapr_vscsi.o
+obj-ppc-$(CONFIG_PSERIES) += spapr_pci.o device-hotplug.o pci-hotplug.o
+# PowerPC 4xx boards
+obj-ppc-y += ppc4xx_devs.o ppc4xx_pci.o ppc405_uc.o ppc405_boards.o
+obj-ppc-y += ppc440.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-$(CONFIG_KVM) += kvm_ppc.o
+obj-ppc-$(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-$(CONFIG_OPENGL) += milkymist-tmu2.o
+obj-lm32-y += milkymist-uart.o
+obj-lm32-y += milkymist-vgafb.o
+obj-lm32-y += framebuffer.o
+
+obj-mips-y = mips_r4k.o mips_jazz.o mips_malta.o mips_mipssim.o
+obj-mips-y += mips_addr.o mips_timer.o mips_int.o
+obj-mips-y += vga.o
+obj-mips-y += jazz_led.o
+obj-mips-y += gt64xxx.o mc146818rtc.o
+obj-mips-y += cirrus_vga.o
+obj-mips-$(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-$(CONFIG_FDT) += device_tree.o
+
+# Boards
+obj-cris-y = cris_pic_cpu.o
+obj-cris-y += cris-boot.o
+obj-cris-y += axis_dev88.o
+
+# IO blocks
+obj-cris-y += etraxfs_dma.o
+obj-cris-y += etraxfs_pic.o
+obj-cris-y += etraxfs_eth.o
+obj-cris-y += etraxfs_timer.o
+obj-cris-y += etraxfs_ser.o
+
+ifeq ($(TARGET_ARCH), sparc64)
+obj-sparc-y = sun4u.o apb_pci.o
+obj-sparc-y += vga.o
+obj-sparc-y += mc146818rtc.o
+obj-sparc-y += cirrus_vga.o
 else
-obj-y += hw/$(TARGET_BASE_ARCH)/
+obj-sparc-y = sun4m.o lance.o tcx.o sun4m_iommu.o slavio_intctl.o
+obj-sparc-y += slavio_timer.o slavio_misc.o sparc32_dma.o
+obj-sparc-y += cs4231.o eccmemctl.o sbi.o sun4c_intctl.o leon3.o
+
+# GRLIB
+obj-sparc-y += grlib_gptimer.o grlib_irqmp.o grlib_apbuart.o
 endif
 
-GENERATED_HEADERS += hmp-commands.h qmp-commands-old.h
+obj-arm-y = integratorcp.o versatilepb.o arm_pic.o arm_timer.o
+obj-arm-y += arm_boot.o pl011.o pl031.o pl050.o pl080.o pl110.o pl181.o pl190.o
+obj-arm-y += versatile_pci.o
+obj-arm-y += realview_gic.o realview.o arm_sysctl.o arm11mpcore.o a9mpcore.o
+obj-arm-y += armv7m.o armv7m_nvic.o stellaris.o pl022.o stellaris_enet.o
+obj-arm-y += pl061.o
+obj-arm-y += arm-semi.o
+obj-arm-y += pxa2xx.o pxa2xx_pic.o pxa2xx_gpio.o pxa2xx_timer.o pxa2xx_dma.o
+obj-arm-y += pxa2xx_lcd.o pxa2xx_mmci.o pxa2xx_pcmcia.o pxa2xx_keypad.o
+obj-arm-y += gumstix.o
+obj-arm-y += zaurus.o ide/microdrive.o spitz.o tosa.o tc6393xb.o
+obj-arm-y += omap1.o omap_lcdc.o omap_dma.o omap_clk.o omap_mmc.o omap_i2c.o \
+		omap_gpio.o omap_intc.o omap_uart.o
+obj-arm-y += omap2.o omap_dss.o soc_dma.o omap_gptimer.o omap_synctimer.o \
+		omap_gpmc.o omap_sdrc.o omap_spi.o omap_tap.o omap_l4.o
+obj-arm-y += omap_sx1.o palm.o tsc210x.o
+obj-arm-y += nseries.o blizzard.o onenand.o vga.o cbus.o tusb6010.o usb-musb.o
+obj-arm-y += mst_fpga.o mainstone.o
+obj-arm-y += 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
+obj-sh4-y += ide/mmio.o
+
+obj-m68k-y = an5206.o mcf5206.o mcf_uart.o mcf_intc.o mcf5208.o mcf_fec.o
+obj-m68k-y += m68k-semi.o dummy_m68k.o
+
+obj-s390x-y = s390-virtio-bus.o s390-virtio.o
+
+obj-alpha-y = mc146818rtc.o
+obj-alpha-y += 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
+
+main.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
+
+monitor.o: hmp-commands.h qmp-commands-old.h
+
+$(obj-y) $(obj-$(TARGET_BASE_ARCH)-y): $(GENERATED_HEADERS)
+
+obj-y += $(addprefix ../, $(common-obj-y))
+obj-y += $(addprefix ../libdis/, $(libdis-y))
+obj-y += $(libobj-y)
+obj-y += $(addprefix $(HWDIR)/, $(hw-obj-y))
+obj-y += $(addprefix ../, $(trace-obj-y))
 
 endif # CONFIG_SOFTMMU
 
-# Workaround for http://gcc.gnu.org/PR55489, see configure.
-%/translate.o: QEMU_CFLAGS += $(TRANSLATE_OPT_CFLAGS)
+ifndef CONFIG_LINUX_USER
+ifndef CONFIG_BSD_USER
+# libcacard needs qemu-thread support, and besides is only needed by devices
+# so not requires with linux-user / bsd-user targets
+obj-$(CONFIG_SMARTCARD_NSS) += $(addprefix ../libcacard/, $(libcacard-y))
+endif # CONFIG_BSD_USER
+endif # CONFIG_LINUX_USER
 
-dummy := $(call unnest-vars,,obj-y)
-all-obj-y := $(obj-y)
+obj-$(CONFIG_GDBSTUB_XML) += gdbstub-xml.o
 
-block-obj-y :=
-common-obj-y :=
-include $(SRC_PATH)/Makefile.objs
-dummy := $(call unnest-vars,.., \
-               block-obj-y \
-               block-obj-m \
-               common-obj-y \
-               common-obj-m)
-all-obj-y += $(common-obj-y)
-all-obj-$(CONFIG_SOFTMMU) += $(block-obj-y)
-
-# build either PROG or PROGW
-$(QEMU_PROG_BUILD): $(all-obj-y) ../libqemuutil.a ../libqemustub.a
+$(QEMU_PROG): $(obj-y) $(obj-$(TARGET_BASE_ARCH)-y)
 	$(call LINK,$^)
 
+
 gdbstub-xml.c: $(TARGET_XML_FILES) $(SRC_PATH)/scripts/feature_to_c.sh
 	$(call quiet-command,rm -f $@ && $(SHELL) $(SRC_PATH)/scripts/feature_to_c.sh $@ $(TARGET_XML_FILES),"  GEN   $(TARGET_DIR)$@")
 
@@ -177,8 +427,8 @@ qmp-commands-old.h: $(SRC_PATH)/qmp-commands.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $(TARGET_DIR)$@")
 
 clean:
-	rm -f *.a *~ $(PROGS)
-	rm -f $(shell find . -name '*.[od]')
+	rm -f *.o *.a *~ $(PROGS) nwfpe/*.o fpu/*.o
+	rm -f *.d */*.d tcg/*.o ide/*.o 9pfs/*.o
 	rm -f hmp-commands.h qmp-commands-old.h gdbstub-xml.c
 ifdef CONFIG_TRACE_SYSTEMTAP
 	rm -f *.stp
@@ -186,12 +436,15 @@ endif
 
 install: all
 ifneq ($(PROGS),)
-	$(call install-prog,$(PROGS),$(DESTDIR)$(bindir))
+	$(INSTALL) -m 755 $(PROGS) "$(DESTDIR)$(bindir)"
+ifneq ($(STRIP),)
+	$(STRIP) $(patsubst %,"$(DESTDIR)$(bindir)/%",$(PROGS))
+endif
 endif
 ifdef CONFIG_TRACE_SYSTEMTAP
-	$(INSTALL_DIR) "$(DESTDIR)$(qemu_datadir)/../systemtap/tapset"
-	$(INSTALL_DATA) $(QEMU_PROG).stp-installed "$(DESTDIR)$(qemu_datadir)/../systemtap/tapset/$(QEMU_PROG).stp"
+	$(INSTALL_DIR) "$(DESTDIR)$(datadir)/../systemtap/tapset"
+	$(INSTALL_DATA) $(QEMU_PROG).stp "$(DESTDIR)$(datadir)/../systemtap/tapset"
 endif
 
-GENERATED_HEADERS += config-target.h
-Makefile: $(GENERATED_HEADERS)
+# Include automatically generated dependency files
+-include $(wildcard *.d */*.d)

Makefile.user

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

QMP/README

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

QMP/qmp-events.txt

@@ -0,0 +1,266 @@
+                   QEMU Monitor Protocol Events
+                   ============================
+
+BLOCK_IO_ERROR
+--------------
+
+Emitted when a disk I/O error occurs.
+
+Data:
+
+- "device": device name (json-string)
+- "operation": I/O operation (json-string, "read" or "write")
+- "action": action that has been taken, it's one of the following (json-string):
+    "ignore": error has been ignored
+    "report": error has been reported to the device
+    "stop": error caused VM to be stopped
+
+Example:
+
+{ "event": "BLOCK_IO_ERROR",
+    "data": { "device": "ide0-hd1",
+              "operation": "write",
+              "action": "stop" },
+    "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
+
+Note: If action is "stop", a STOP event will eventually follow the
+BLOCK_IO_ERROR event.
+
+RESET
+-----
+
+Emitted when the Virtual Machine is reseted.
+
+Data: None.
+
+Example:
+
+{ "event": "RESET",
+    "timestamp": { "seconds": 1267041653, "microseconds": 9518 } }
+
+RESUME
+------
+
+Emitted when the Virtual Machine resumes execution.
+
+Data: None.
+
+Example:
+
+{ "event": "RESUME",
+    "timestamp": { "seconds": 1271770767, "microseconds": 582542 } }
+
+RTC_CHANGE
+----------
+
+Emitted when the guest changes the RTC time.
+
+Data:
+
+- "offset": delta against the host UTC in seconds (json-number)
+
+Example:
+
+{ "event": "RTC_CHANGE",
+    "data": { "offset": 78 },
+    "timestamp": { "seconds": 1267020223, "microseconds": 435656 } }
+
+SHUTDOWN
+--------
+
+Emitted when the Virtual Machine is powered down.
+
+Data: None.
+
+Example:
+
+{ "event": "SHUTDOWN",
+    "timestamp": { "seconds": 1267040730, "microseconds": 682951 } }
+
+Note: If the command-line option "-no-shutdown" has been specified, a STOP
+event will eventually follow the SHUTDOWN event.
+
+STOP
+----
+
+Emitted when the Virtual Machine is stopped.
+
+Data: None.
+
+Example:
+
+{ "event": "STOP",
+    "timestamp": { "seconds": 1267041730, "microseconds": 281295 } }
+
+VNC_CONNECTED
+-------------
+
+Emitted when a VNC client establishes a connection.
+
+Data:
+
+- "server": Server information (json-object)
+  - "host": IP address (json-string)
+  - "service": 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)
+  - "service": port number (json-string)
+  - "family": address family (json-string, "ipv4" or "ipv6")
+
+Example:
+
+{ "event": "VNC_CONNECTED",
+    "data": {
+        "server": { "auth": "sasl", "family": "ipv4",
+                    "service": "5901", "host": "0.0.0.0" },
+        "client": { "family": "ipv4", "service": "58425",
+                    "host": "127.0.0.1" } },
+    "timestamp": { "seconds": 1262976601, "microseconds": 975795 } }
+
+
+Note: This event is emitted before any authentication takes place, thus
+the authentication ID is not provided.
+
+VNC_DISCONNECTED
+----------------
+
+Emitted when the conection is closed.
+
+Data:
+
+- "server": Server information (json-object)
+  - "host": IP address (json-string)
+  - "service": 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)
+  - "service": port number (json-string)
+  - "family": address family (json-string, "ipv4" or "ipv6")
+  - "x509_dname": TLS dname (json-string, optional)
+  - "sasl_username": SASL username (json-string, optional)
+
+Example:
+
+{ "event": "VNC_DISCONNECTED",
+    "data": {
+        "server": { "auth": "sasl", "family": "ipv4",
+                    "service": "5901", "host": "0.0.0.0" },
+        "client": { "family": "ipv4", "service": "58425",
+                    "host": "127.0.0.1", "sasl_username": "luiz" } },
+    "timestamp": { "seconds": 1262976601, "microseconds": 975795 } }
+
+VNC_INITIALIZED
+---------------
+
+Emitted after authentication takes place (if any) and the VNC session is
+made active.
+
+Data:
+
+- "server": Server information (json-object)
+  - "host": IP address (json-string)
+  - "service": 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)
+  - "service": port number (json-string)
+  - "family": address family (json-string, "ipv4" or "ipv6")
+  - "x509_dname": TLS dname (json-string, optional)
+  - "sasl_username": SASL username (json-string, optional)
+
+Example:
+
+{ "event": "VNC_INITIALIZED",
+    "data": {
+        "server": { "auth": "sasl", "family": "ipv4",
+                    "service": "5901", "host": "0.0.0.0"},
+        "client": { "family": "ipv4", "service": "46089",
+                    "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
+--------
+
+Emitted when the watchdog device's timer is expired.
+
+Data:
+
+- "action": Action that has been taken, it's one of the following (json-string):
+            "reset", "shutdown", "poweroff", "pause", "debug", or "none"
+
+Example:
+
+{ "event": "WATCHDOG",
+     "data": { "action": "reset" },
+     "timestamp": { "seconds": 1267061043, "microseconds": 959568 } }
+
+Note: If action is "reset", "shutdown", or "pause" the WATCHDOG event is
+followed respectively by the RESET, SHUTDOWN, or STOP events.

QMP/qmp-shell

@@ -31,10 +31,8 @@
 # (QEMU)
 
 import qmp
-import json
 import readline
 import sys
-import pprint
 
 class QMPCompleter(list):
     def complete(self, text, state):
@@ -54,11 +52,10 @@ class QMPShellBadPort(QMPShellError):
 # TODO: QMPShell's interface is a bit ugly (eg. _fill_completion() and
 #       _execute_cmd()). Let's design a better one.
 class QMPShell(qmp.QEMUMonitorProtocol):
-    def __init__(self, address, pp=None):
+    def __init__(self, address):
         qmp.QEMUMonitorProtocol.__init__(self, self.__get_address(address))
         self._greeting = None
         self._completer = None
-        self._pp = pp
 
     def __get_address(self, arg):
         """
@@ -92,7 +89,7 @@ class QMPShell(qmp.QEMUMonitorProtocol):
         """
         Build a QMP input object from a user provided command-line in the
         following format:
-
+    
             < command-name > [ arg-name1=arg1 ] ... [ arg-nameN=argN ]
         """
         cmdargs = cmdline.split()
@@ -100,41 +97,16 @@ class QMPShell(qmp.QEMUMonitorProtocol):
         for arg in cmdargs[1:]:
             opt = arg.split('=')
             try:
-                if(len(opt) > 2):
-                    opt[1] = '='.join(opt[1:])
                 value = int(opt[1])
             except ValueError:
-                if opt[1] == 'true':
-                    value = True
-                elif opt[1] == 'false':
-                    value = False
-                elif opt[1].startswith('{'):
-                    value = json.loads(opt[1])
-                else:
-                    value = opt[1]
-            optpath = opt[0].split('.')
-            parent = qmpcmd['arguments']
-            curpath = []
-            for p in optpath[:-1]:
-                curpath.append(p)
-                d = parent.get(p, {})
-                if type(d) is not dict:
-                    raise QMPShellError('Cannot use "%s" as both leaf and non-leaf key' % '.'.join(curpath))
-                parent[p] = d
-                parent = d
-            if optpath[-1] in parent:
-                if type(parent[optpath[-1]]) is dict:
-                    raise QMPShellError('Cannot use "%s" as both leaf and non-leaf key' % '.'.join(curpath))
-                else:
-                    raise QMPShellError('Cannot set "%s" multiple times' % opt[0])
-            parent[optpath[-1]] = value
+                value = opt[1]
+            qmpcmd['arguments'][opt[0]] = value
         return qmpcmd
 
     def _execute_cmd(self, cmdline):
         try:
             qmpcmd = self.__build_cmd(cmdline)
-        except Exception, e:
-            print 'Error while parsing command line: %s' % e
+        except:
             print 'command format: <command-name> ',
             print '[arg-name1=arg1] ... [arg-nameN=argN]'
             return True
@@ -142,11 +114,7 @@ class QMPShell(qmp.QEMUMonitorProtocol):
         if resp is None:
             print 'Disconnected'
             return False
-
-        if self._pp is not None:
-            self._pp.pprint(resp)
-        else:
-            print resp
+        print resp
         return True
 
     def connect(self):
@@ -254,36 +222,22 @@ def die(msg):
 def fail_cmdline(option=None):
     if option:
         sys.stderr.write('ERROR: bad command-line option \'%s\'\n' % option)
-    sys.stderr.write('qemu-shell [ -p ] [ -H ] < UNIX socket path> | < TCP address:port >\n')
+    sys.stderr.write('qemu-shell [ -H ] < UNIX socket path> | < TCP address:port >\n')
     sys.exit(1)
 
 def main():
     addr = ''
-    qemu = None
-    hmp = False
-    pp = None
-
     try:
-        for arg in sys.argv[1:]:
-            if arg == "-H":
-                if qemu is not None:
-                    fail_cmdline(arg)
-                hmp = True
-            elif arg == "-p":
-                if pp is not None:
-                    fail_cmdline(arg)
-                pp = pprint.PrettyPrinter(indent=4)
-            else:
-                if qemu is not None:
-                    fail_cmdline(arg)
-                if hmp:
-                    qemu = HMPShell(arg)
-                else:
-                    qemu = QMPShell(arg, pp)
-                addr = arg
-
-        if qemu is None:
-            fail_cmdline()
+        if len(sys.argv) == 2:
+            qemu = QMPShell(sys.argv[1])
+            addr = sys.argv[1]
+        elif len(sys.argv) == 3:
+            if sys.argv[1] != '-H':
+                fail_cmdline(sys.argv[1])
+            qemu = HMPShell(sys.argv[2])
+            addr = sys.argv[2]
+        else:
+                fail_cmdline()
     except QMPShellBadPort:
         die('bad port number in command-line')
 

QMP/qmp-spec.txt

@@ -1,17 +1,21 @@
-                      QEMU Machine Protocol Specification
+           QEMU Monitor Protocol Specification - Version 0.1
 
 1. Introduction
 ===============
 
-This document specifies the QEMU Machine Protocol (QMP), a JSON-based protocol
-which is available for applications to operate QEMU at the machine-level.
+This document specifies the QEMU Monitor Protocol (QMP), a JSON-based protocol
+which is available for applications to control QEMU at the machine-level.
+
+To enable QMP support, QEMU has to be run in "control mode". This is done by
+starting QEMU with the appropriate command-line options. Please, refer to the
+QEMU manual page for more information.
 
 2. Protocol Specification
 =========================
 
 This section details the protocol format. For the purpose of this document
-"Client" is any application which is using QMP to communicate with QEMU and
-"Server" is QEMU itself.
+"Client" is any application which is communicating with QEMU in control mode,
+and "Server" is QEMU itself.
 
 JSON data structures, when mentioned in this document, are always in the
 following format:
@@ -43,14 +47,14 @@ that the connection has been successfully established and that the Server is
 ready for capabilities negotiation (for more information refer to section
 '4. Capabilities Negotiation').
 
-The greeting message format is:
+The format is:
 
 { "QMP": { "version": json-object, "capabilities": json-array } }
 
  Where,
 
 - The "version" member contains the Server's version information (the format
-  is the same of the query-version command)
+  is the same of the 'query-version' command)
 - The "capabilities" member specify the availability of features beyond the
   baseline specification
 
@@ -79,7 +83,10 @@ of a command execution: success or error.
 2.4.1 success
 -------------
 
-The format of a success response is:
+The success response is issued when the command execution has finished
+without errors.
+
+The format is:
 
 { "return": json-object, "id": json-value }
 
@@ -89,22 +96,28 @@ The format of a success response is:
   in a per-command basis or an empty json-object if the command does not
   return data
 - The "id" member contains the transaction identification associated
-  with the command execution if issued by the Client
+  with the command execution (if issued by the Client)
 
 2.4.2 error
 -----------
 
-The format of an error response is:
+The error response is issued when the command execution could not be
+completed because of an error condition.
 
-{ "error": { "class": json-string, "desc": json-string }, "id": json-value }
+The format is:
+
+{ "error": { "class": json-string, "data": json-object, "desc": json-string },
+  "id": json-value }
 
  Where,
 
-- The "class" member contains the error class name (eg. "GenericError")
+- The "class" member contains the error class name (eg. "ServiceUnavailable")
+- The "data" member contains specific error data and is defined in a
+  per-command basis, it will be an empty json-object if the error has no data
 - The "desc" member is a human-readable error message. Clients should
   not attempt to parse this message.
 - The "id" member contains the transaction identification associated with
-  the command execution if issued by the Client
+  the command execution (if issued by the Client)
 
 NOTE: Some errors can occur before the Server is able to read the "id" member,
 in these cases the "id" member will not be part of the error response, even
@@ -114,9 +127,9 @@ if provided by the client.
 -----------------------
 
 As a result of state changes, the Server may send messages unilaterally
-to the Client at any time. They are called "asynchronous events".
+to the Client at any time. They are called 'asynchronous events'.
 
-The format of asynchronous events is:
+The format is:
 
 { "event": json-string, "data": json-object,
   "timestamp": { "seconds": json-number, "microseconds": json-number } }
@@ -137,37 +150,37 @@ qmp-events.txt file.
 ===============
 
 This section provides some examples of real QMP usage, in all of them
-"C" stands for "Client" and "S" stands for "Server".
+'C' stands for 'Client' and 'S' stands for 'Server'.
 
 3.1 Server greeting
 -------------------
 
-S: { "QMP": { "version": { "qemu": { "micro": 50, "minor": 6, "major": 1 },
-     "package": ""}, "capabilities": []}}
+S: {"QMP": {"version": {"qemu": "0.12.50", "package": ""}, "capabilities": []}}
 
 3.2 Simple 'stop' execution
 ---------------------------
 
 C: { "execute": "stop" }
-S: { "return": {} }
+S: {"return": {}}
 
 3.3 KVM information
 -------------------
 
 C: { "execute": "query-kvm", "id": "example" }
-S: { "return": { "enabled": true, "present": true }, "id": "example"}
+S: {"return": {"enabled": true, "present": true}, "id": "example"}
 
 3.4 Parsing error
 ------------------
 
 C: { "execute": }
-S: { "error": { "class": "GenericError", "desc": "Invalid JSON syntax" } }
+S: {"error": {"class": "JSONParsing", "desc": "Invalid JSON syntax", "data":
+{}}}
 
 3.5 Powerdown event
 -------------------
 
-S: { "timestamp": { "seconds": 1258551470, "microseconds": 802384 },
-    "event": "POWERDOWN" }
+S: {"timestamp": {"seconds": 1258551470, "microseconds": 802384}, "event":
+"POWERDOWN"}
 
 4. Capabilities Negotiation
 ----------------------------
@@ -175,17 +188,17 @@ S: { "timestamp": { "seconds": 1258551470, "microseconds": 802384 },
 When a Client successfully establishes a connection, the Server is in
 Capabilities Negotiation mode.
 
-In this mode only the qmp_capabilities command is allowed to run, all
-other commands will return the CommandNotFound error. Asynchronous
-messages are not delivered either.
+In this mode only the 'qmp_capabilities' command is allowed to run, all
+other commands will return the CommandNotFound error. Asynchronous messages
+are not delivered either.
 
-Clients should use the qmp_capabilities command to enable capabilities
+Clients should use the 'qmp_capabilities' command to enable capabilities
 advertised in the Server's greeting (section '2.2 Server Greeting') they
 support.
 
-When the qmp_capabilities command is issued, and if it does not return an
+When the 'qmp_capabilities' command is issued, and if it does not return an
 error, the Server enters in Command mode where capabilities changes take
-effect, all commands (except qmp_capabilities) are allowed and asynchronous
+effect, all commands (except 'qmp_capabilities') are allowed and asynchronous
 messages are delivered.
 
 5 Compatibility Considerations
@@ -196,27 +209,13 @@ incompatible way are disabled by default and will be advertised by the
 capabilities array (section '2.2 Server Greeting'). Thus, Clients can check
 that array and enable the capabilities they support.
 
-The QMP Server performs a type check on the arguments to a command.  It
-generates an error if a value does not have the expected type for its
-key, or if it does not understand a key that the Client included.  The
-strictness of the Server catches wrong assumptions of Clients about
-the Server's schema.  Clients can assume that, when such validation
-errors occur, they will be reported before the command generated any
-side effect.
+Additionally, Clients must not assume any particular:
 
-However, Clients must not assume any particular:
-
-- Length of json-arrays
-- Size of json-objects; in particular, future versions of QEMU may add
-  new keys and Clients should be able to ignore them.
+- Size of json-objects or length of json-arrays
 - Order of json-object members or json-array elements
 - Amount of errors generated by a command, that is, new errors can be added
   to any existing command in newer versions of the Server
 
-Of course, the Server does guarantee to send valid JSON.  But apart from
-this, a Client should be "conservative in what they send, and liberal in
-what they accept".
-
 6. Downstream extension of QMP
 ------------------------------
 
@@ -236,7 +235,7 @@ arguments, errors, asynchronous events, and so forth.
 
 Any new names downstream wishes to add must begin with '__'.  To
 ensure compatibility with other downstreams, it is strongly
-recommended that you prefix your downstream names with '__RFQDN_' where
+recommended that you prefix your downstram names with '__RFQDN_' where
 RFQDN is a valid, reverse fully qualified domain name which you
 control.  For example, a qemu-kvm specific monitor command would be:
 

QMP/qmp.py

@@ -1,5 +1,5 @@
 # QEMU Monitor Protocol Python class
-#
+# 
 # Copyright (C) 2009, 2010 Red Hat Inc.
 #
 # Authors:
@@ -49,6 +49,7 @@ class QEMUMonitorProtocol:
         return socket.socket(family, socket.SOCK_STREAM)
 
     def __negotiate_capabilities(self):
+        self.__sockfile = self.__sock.makefile()
         greeting = self.__json_read()
         if greeting is None or not greeting.has_key('QMP'):
             raise QMPConnectError
@@ -72,7 +73,7 @@ class QEMUMonitorProtocol:
 
     error = socket.error
 
-    def connect(self, negotiate=True):
+    def connect(self):
         """
         Connect to the QMP Monitor and perform capabilities negotiation.
 
@@ -82,9 +83,7 @@ class QEMUMonitorProtocol:
         @raise QMPCapabilitiesError if fails to negotiate capabilities
         """
         self.__sock.connect(self.__address)
-        self.__sockfile = self.__sock.makefile()
-        if negotiate:
-            return self.__negotiate_capabilities()
+        return self.__negotiate_capabilities()
 
     def accept(self):
         """
@@ -96,7 +95,6 @@ class QEMUMonitorProtocol:
         @raise QMPCapabilitiesError if fails to negotiate capabilities
         """
         self.__sock, _ = self.__sock.accept()
-        self.__sockfile = self.__sock.makefile()
         return self.__negotiate_capabilities()
 
     def cmd_obj(self, qmp_cmd):
@@ -130,32 +128,6 @@ class QEMUMonitorProtocol:
             qmp_cmd['id'] = id
         return self.cmd_obj(qmp_cmd)
 
-    def command(self, cmd, **kwds):
-        ret = self.cmd(cmd, kwds)
-        if ret.has_key('error'):
-            raise Exception(ret['error']['desc'])
-        return ret['return']
-
-    def pull_event(self, wait=False):
-        """
-        Get and delete the first available QMP event.
-
-        @param wait: block until an event is available (bool)
-        """
-        self.__sock.setblocking(0)
-        try:
-            self.__json_read()
-        except socket.error, err:
-            if err[0] == errno.EAGAIN:
-                # No data available
-                pass
-        self.__sock.setblocking(1)
-        if not self.__events and wait:
-            self.__json_read(only_event=True)
-        event = self.__events[0]
-        del self.__events[0]
-        return event
-
     def get_events(self, wait=False):
         """
         Get a list of available QMP events.
@@ -171,12 +143,7 @@ class QEMUMonitorProtocol:
                 pass
         self.__sock.setblocking(1)
         if not self.__events and wait:
-            ret = self.__json_read(only_event=True)
-            if ret == None:
-                # We are in blocking mode, if don't get anything, something
-                # went wrong
-                raise QMPConnectError("Error while reading from socket")
-
+            self.__json_read(only_event=True)
         return self.__events
 
     def clear_events(self):
@@ -188,14 +155,3 @@ class QEMUMonitorProtocol:
     def close(self):
         self.__sock.close()
         self.__sockfile.close()
-
-    timeout = socket.timeout
-
-    def settimeout(self, timeout):
-        self.__sock.settimeout(timeout)
-
-    def get_sock_fd(self):
-        return self.__sock.fileno()
-
-    def is_scm_available(self):
-        return self.__sock.family == socket.AF_UNIX

README

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

TODO

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

VERSION

@@ -1 +1 @@
-2.1.2
+1.0,1

a.out.h

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

acl.c

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

acl.h

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

aes.h

@@ -0,0 +1,26 @@
+#ifndef QEMU_AES_H
+#define QEMU_AES_H
+
+#define AES_MAXNR 14
+#define AES_BLOCK_SIZE 16
+
+struct aes_key_st {
+    uint32_t rd_key[4 *(AES_MAXNR + 1)];
+    int rounds;
+};
+typedef struct aes_key_st AES_KEY;
+
+int AES_set_encrypt_key(const unsigned char *userKey, const int bits,
+	AES_KEY *key);
+int AES_set_decrypt_key(const unsigned char *userKey, const int bits,
+	AES_KEY *key);
+
+void AES_encrypt(const unsigned char *in, unsigned char *out,
+	const AES_KEY *key);
+void AES_decrypt(const unsigned char *in, unsigned char *out,
+	const AES_KEY *key);
+void AES_cbc_encrypt(const unsigned char *in, unsigned char *out,
+		     const unsigned long length, const AES_KEY *key,
+		     unsigned char *ivec, const int enc);
+
+#endif

aio-posix.c

@@ -1,274 +0,0 @@
-/*
- * QEMU aio implementation
- *
- * Copyright IBM, Corp. 2008
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
- * Contributions after 2012-01-13 are licensed under the terms of the
- * GNU GPL, version 2 or (at your option) any later version.
- */
-
-#include "qemu-common.h"
-#include "block/block.h"
-#include "qemu/queue.h"
-#include "qemu/sockets.h"
-
-struct AioHandler
-{
-    GPollFD pfd;
-    IOHandler *io_read;
-    IOHandler *io_write;
-    int deleted;
-    int pollfds_idx;
-    void *opaque;
-    QLIST_ENTRY(AioHandler) node;
-};
-
-static AioHandler *find_aio_handler(AioContext *ctx, int fd)
-{
-    AioHandler *node;
-
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        if (node->pfd.fd == fd)
-            if (!node->deleted)
-                return node;
-    }
-
-    return NULL;
-}
-
-void aio_set_fd_handler(AioContext *ctx,
-                        int fd,
-                        IOHandler *io_read,
-                        IOHandler *io_write,
-                        void *opaque)
-{
-    AioHandler *node;
-
-    node = find_aio_handler(ctx, fd);
-
-    /* Are we deleting the fd handler? */
-    if (!io_read && !io_write) {
-        if (node) {
-            g_source_remove_poll(&ctx->source, &node->pfd);
-
-            /* If the lock is held, just mark the node as deleted */
-            if (ctx->walking_handlers) {
-                node->deleted = 1;
-                node->pfd.revents = 0;
-            } else {
-                /* Otherwise, delete it for real.  We can't just mark it as
-                 * deleted because deleted nodes are only cleaned up after
-                 * releasing the walking_handlers lock.
-                 */
-                QLIST_REMOVE(node, node);
-                g_free(node);
-            }
-        }
-    } else {
-        if (node == NULL) {
-            /* Alloc and insert if it's not already there */
-            node = g_malloc0(sizeof(AioHandler));
-            node->pfd.fd = fd;
-            QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
-
-            g_source_add_poll(&ctx->source, &node->pfd);
-        }
-        /* Update handler with latest information */
-        node->io_read = io_read;
-        node->io_write = io_write;
-        node->opaque = opaque;
-        node->pollfds_idx = -1;
-
-        node->pfd.events = (io_read ? G_IO_IN | G_IO_HUP | G_IO_ERR : 0);
-        node->pfd.events |= (io_write ? G_IO_OUT | G_IO_ERR : 0);
-    }
-
-    aio_notify(ctx);
-}
-
-void aio_set_event_notifier(AioContext *ctx,
-                            EventNotifier *notifier,
-                            EventNotifierHandler *io_read)
-{
-    aio_set_fd_handler(ctx, event_notifier_get_fd(notifier),
-                       (IOHandler *)io_read, NULL, notifier);
-}
-
-bool aio_pending(AioContext *ctx)
-{
-    AioHandler *node;
-
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        int revents;
-
-        revents = node->pfd.revents & node->pfd.events;
-        if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR) && node->io_read) {
-            return true;
-        }
-        if (revents & (G_IO_OUT | G_IO_ERR) && node->io_write) {
-            return true;
-        }
-    }
-
-    return false;
-}
-
-static bool aio_dispatch(AioContext *ctx)
-{
-    AioHandler *node;
-    bool progress = false;
-
-    /*
-     * We have to walk very carefully in case aio_set_fd_handler is
-     * called while we're walking.
-     */
-    node = QLIST_FIRST(&ctx->aio_handlers);
-    while (node) {
-        AioHandler *tmp;
-        int revents;
-
-        ctx->walking_handlers++;
-
-        revents = node->pfd.revents & node->pfd.events;
-        node->pfd.revents = 0;
-
-        if (!node->deleted &&
-            (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) &&
-            node->io_read) {
-            node->io_read(node->opaque);
-
-            /* aio_notify() does not count as progress */
-            if (node->opaque != &ctx->notifier) {
-                progress = true;
-            }
-        }
-        if (!node->deleted &&
-            (revents & (G_IO_OUT | G_IO_ERR)) &&
-            node->io_write) {
-            node->io_write(node->opaque);
-            progress = true;
-        }
-
-        tmp = node;
-        node = QLIST_NEXT(node, node);
-
-        ctx->walking_handlers--;
-
-        if (!ctx->walking_handlers && tmp->deleted) {
-            QLIST_REMOVE(tmp, node);
-            g_free(tmp);
-        }
-    }
-
-    /* Run our timers */
-    progress |= timerlistgroup_run_timers(&ctx->tlg);
-
-    return progress;
-}
-
-bool aio_poll(AioContext *ctx, bool blocking)
-{
-    AioHandler *node;
-    bool was_dispatching;
-    int ret;
-    bool progress;
-
-    was_dispatching = ctx->dispatching;
-    progress = false;
-
-    /* aio_notify can avoid the expensive event_notifier_set if
-     * everything (file descriptors, bottom halves, timers) will
-     * be re-evaluated before the next blocking poll().  This happens
-     * in two cases:
-     *
-     * 1) when aio_poll is called with blocking == false
-     *
-     * 2) when we are called after poll().  If we are called before
-     *    poll(), bottom halves will not be re-evaluated and we need
-     *    aio_notify() if blocking == true.
-     *
-     * The first aio_dispatch() only does something when AioContext is
-     * running as a GSource, and in that case aio_poll is used only
-     * with blocking == false, so this optimization is already quite
-     * effective.  However, the code is ugly and should be restructured
-     * to have a single aio_dispatch() call.  To do this, we need to
-     * reorganize aio_poll into a prepare/poll/dispatch model like
-     * glib's.
-     *
-     * If we're in a nested event loop, ctx->dispatching might be true.
-     * In that case we can restore it just before returning, but we
-     * have to clear it now.
-     */
-    aio_set_dispatching(ctx, !blocking);
-
-    /*
-     * If there are callbacks left that have been queued, we need to call them.
-     * Do not call select in this case, because it is possible that the caller
-     * does not need a complete flush (as is the case for aio_poll loops).
-     */
-    if (aio_bh_poll(ctx)) {
-        blocking = false;
-        progress = true;
-    }
-
-    /* Re-evaluate condition (1) above.  */
-    aio_set_dispatching(ctx, !blocking);
-    if (aio_dispatch(ctx)) {
-        progress = true;
-    }
-
-    if (progress && !blocking) {
-        goto out;
-    }
-
-    ctx->walking_handlers++;
-
-    g_array_set_size(ctx->pollfds, 0);
-
-    /* fill pollfds */
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        node->pollfds_idx = -1;
-        if (!node->deleted && node->pfd.events) {
-            GPollFD pfd = {
-                .fd = node->pfd.fd,
-                .events = node->pfd.events,
-            };
-            node->pollfds_idx = ctx->pollfds->len;
-            g_array_append_val(ctx->pollfds, pfd);
-        }
-    }
-
-    ctx->walking_handlers--;
-
-    /* wait until next event */
-    ret = qemu_poll_ns((GPollFD *)ctx->pollfds->data,
-                         ctx->pollfds->len,
-                         blocking ? timerlistgroup_deadline_ns(&ctx->tlg) : 0);
-
-    /* if we have any readable fds, dispatch event */
-    if (ret > 0) {
-        QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-            if (node->pollfds_idx != -1) {
-                GPollFD *pfd = &g_array_index(ctx->pollfds, GPollFD,
-                                              node->pollfds_idx);
-                node->pfd.revents = pfd->revents;
-            }
-        }
-    }
-
-    /* Run dispatch even if there were no readable fds to run timers */
-    aio_set_dispatching(ctx, true);
-    if (aio_dispatch(ctx)) {
-        progress = true;
-    }
-
-out:
-    aio_set_dispatching(ctx, was_dispatching);
-    return progress;
-}

aio-win32.c

@@ -1,223 +0,0 @@
-/*
- * QEMU aio implementation
- *
- * Copyright IBM Corp., 2008
- * Copyright Red Hat Inc., 2012
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.ibm.com>
- *  Paolo Bonzini     <pbonzini@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
- * Contributions after 2012-01-13 are licensed under the terms of the
- * GNU GPL, version 2 or (at your option) any later version.
- */
-
-#include "qemu-common.h"
-#include "block/block.h"
-#include "qemu/queue.h"
-#include "qemu/sockets.h"
-
-struct AioHandler {
-    EventNotifier *e;
-    EventNotifierHandler *io_notify;
-    GPollFD pfd;
-    int deleted;
-    QLIST_ENTRY(AioHandler) node;
-};
-
-void aio_set_event_notifier(AioContext *ctx,
-                            EventNotifier *e,
-                            EventNotifierHandler *io_notify)
-{
-    AioHandler *node;
-
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        if (node->e == e && !node->deleted) {
-            break;
-        }
-    }
-
-    /* Are we deleting the fd handler? */
-    if (!io_notify) {
-        if (node) {
-            g_source_remove_poll(&ctx->source, &node->pfd);
-
-            /* If the lock is held, just mark the node as deleted */
-            if (ctx->walking_handlers) {
-                node->deleted = 1;
-                node->pfd.revents = 0;
-            } else {
-                /* Otherwise, delete it for real.  We can't just mark it as
-                 * deleted because deleted nodes are only cleaned up after
-                 * releasing the walking_handlers lock.
-                 */
-                QLIST_REMOVE(node, node);
-                g_free(node);
-            }
-        }
-    } else {
-        if (node == NULL) {
-            /* Alloc and insert if it's not already there */
-            node = g_malloc0(sizeof(AioHandler));
-            node->e = e;
-            node->pfd.fd = (uintptr_t)event_notifier_get_handle(e);
-            node->pfd.events = G_IO_IN;
-            QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
-
-            g_source_add_poll(&ctx->source, &node->pfd);
-        }
-        /* Update handler with latest information */
-        node->io_notify = io_notify;
-    }
-
-    aio_notify(ctx);
-}
-
-bool aio_pending(AioContext *ctx)
-{
-    AioHandler *node;
-
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        if (node->pfd.revents && node->io_notify) {
-            return true;
-        }
-    }
-
-    return false;
-}
-
-bool aio_poll(AioContext *ctx, bool blocking)
-{
-    AioHandler *node;
-    HANDLE events[MAXIMUM_WAIT_OBJECTS + 1];
-    bool progress;
-    int count;
-    int timeout;
-
-    progress = false;
-
-    /*
-     * If there are callbacks left that have been queued, we need to call then.
-     * Do not call select in this case, because it is possible that the caller
-     * does not need a complete flush (as is the case for aio_poll loops).
-     */
-    if (aio_bh_poll(ctx)) {
-        blocking = false;
-        progress = true;
-    }
-
-    /* Run timers */
-    progress |= timerlistgroup_run_timers(&ctx->tlg);
-
-    /*
-     * Then dispatch any pending callbacks from the GSource.
-     *
-     * We have to walk very carefully in case aio_set_fd_handler is
-     * called while we're walking.
-     */
-    node = QLIST_FIRST(&ctx->aio_handlers);
-    while (node) {
-        AioHandler *tmp;
-
-        ctx->walking_handlers++;
-
-        if (node->pfd.revents && node->io_notify) {
-            node->pfd.revents = 0;
-            node->io_notify(node->e);
-
-            /* aio_notify() does not count as progress */
-            if (node->e != &ctx->notifier) {
-                progress = true;
-            }
-        }
-
-        tmp = node;
-        node = QLIST_NEXT(node, node);
-
-        ctx->walking_handlers--;
-
-        if (!ctx->walking_handlers && tmp->deleted) {
-            QLIST_REMOVE(tmp, node);
-            g_free(tmp);
-        }
-    }
-
-    if (progress && !blocking) {
-        return true;
-    }
-
-    ctx->walking_handlers++;
-
-    /* fill fd sets */
-    count = 0;
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        if (!node->deleted && node->io_notify) {
-            events[count++] = event_notifier_get_handle(node->e);
-        }
-    }
-
-    ctx->walking_handlers--;
-
-    /* wait until next event */
-    while (count > 0) {
-        int ret;
-
-        timeout = blocking ?
-            qemu_timeout_ns_to_ms(timerlistgroup_deadline_ns(&ctx->tlg)) : 0;
-        ret = WaitForMultipleObjects(count, events, FALSE, timeout);
-
-        /* if we have any signaled events, dispatch event */
-        if ((DWORD) (ret - WAIT_OBJECT_0) >= count) {
-            break;
-        }
-
-        blocking = false;
-
-        /* we have to walk very carefully in case
-         * aio_set_fd_handler is called while we're walking */
-        node = QLIST_FIRST(&ctx->aio_handlers);
-        while (node) {
-            AioHandler *tmp;
-
-            ctx->walking_handlers++;
-
-            if (!node->deleted &&
-                event_notifier_get_handle(node->e) == events[ret - WAIT_OBJECT_0] &&
-                node->io_notify) {
-                node->io_notify(node->e);
-
-                /* aio_notify() does not count as progress */
-                if (node->e != &ctx->notifier) {
-                    progress = true;
-                }
-            }
-
-            tmp = node;
-            node = QLIST_NEXT(node, node);
-
-            ctx->walking_handlers--;
-
-            if (!ctx->walking_handlers && tmp->deleted) {
-                QLIST_REMOVE(tmp, node);
-                g_free(tmp);
-            }
-        }
-
-        /* Try again, but only call each handler once.  */
-        events[ret - WAIT_OBJECT_0] = events[--count];
-    }
-
-    if (blocking) {
-        /* Run the timers a second time. We do this because otherwise aio_wait
-         * will not note progress - and will stop a drain early - if we have
-         * a timer that was not ready to run entering g_poll but is ready
-         * after g_poll. This will only do anything if a timer has expired.
-         */
-        progress |= timerlistgroup_run_timers(&ctx->tlg);
-    }
-
-    return progress;
-}

aio.c

@@ -0,0 +1,230 @@
+/*
+ * QEMU aio implementation
+ *
+ * Copyright IBM, Corp. 2008
+ *
+ * Authors:
+ *  Anthony Liguori   <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu-common.h"
+#include "block.h"
+#include "qemu-queue.h"
+#include "qemu_socket.h"
+
+typedef struct AioHandler AioHandler;
+
+/* The list of registered AIO handlers */
+static QLIST_HEAD(, AioHandler) aio_handlers;
+
+/* This is a simple lock used to protect the aio_handlers list.  Specifically,
+ * it's used to ensure that no callbacks are removed while we're walking and
+ * dispatching callbacks.
+ */
+static int walking_handlers;
+
+struct AioHandler
+{
+    int fd;
+    IOHandler *io_read;
+    IOHandler *io_write;
+    AioFlushHandler *io_flush;
+    AioProcessQueue *io_process_queue;
+    int deleted;
+    void *opaque;
+    QLIST_ENTRY(AioHandler) node;
+};
+
+static AioHandler *find_aio_handler(int fd)
+{
+    AioHandler *node;
+
+    QLIST_FOREACH(node, &aio_handlers, node) {
+        if (node->fd == fd)
+            if (!node->deleted)
+                return node;
+    }
+
+    return NULL;
+}
+
+int qemu_aio_set_fd_handler(int fd,
+                            IOHandler *io_read,
+                            IOHandler *io_write,
+                            AioFlushHandler *io_flush,
+                            AioProcessQueue *io_process_queue,
+                            void *opaque)
+{
+    AioHandler *node;
+
+    node = find_aio_handler(fd);
+
+    /* Are we deleting the fd handler? */
+    if (!io_read && !io_write) {
+        if (node) {
+            /* If the lock is held, just mark the node as deleted */
+            if (walking_handlers)
+                node->deleted = 1;
+            else {
+                /* Otherwise, delete it for real.  We can't just mark it as
+                 * deleted because deleted nodes are only cleaned up after
+                 * releasing the walking_handlers lock.
+                 */
+                QLIST_REMOVE(node, node);
+                g_free(node);
+            }
+        }
+    } else {
+        if (node == NULL) {
+            /* Alloc and insert if it's not already there */
+            node = g_malloc0(sizeof(AioHandler));
+            node->fd = fd;
+            QLIST_INSERT_HEAD(&aio_handlers, node, node);
+        }
+        /* Update handler with latest information */
+        node->io_read = io_read;
+        node->io_write = io_write;
+        node->io_flush = io_flush;
+        node->io_process_queue = io_process_queue;
+        node->opaque = opaque;
+    }
+
+    qemu_set_fd_handler2(fd, NULL, io_read, io_write, opaque);
+
+    return 0;
+}
+
+void qemu_aio_flush(void)
+{
+    AioHandler *node;
+    int ret;
+
+    do {
+        ret = 0;
+
+	/*
+	 * If there are pending emulated aio start them now so flush
+	 * will be able to return 1.
+	 */
+        qemu_aio_wait();
+
+        QLIST_FOREACH(node, &aio_handlers, node) {
+            if (node->io_flush) {
+                ret |= node->io_flush(node->opaque);
+            }
+        }
+    } while (qemu_bh_poll() || ret > 0);
+}
+
+int qemu_aio_process_queue(void)
+{
+    AioHandler *node;
+    int ret = 0;
+
+    walking_handlers = 1;
+
+    QLIST_FOREACH(node, &aio_handlers, node) {
+        if (node->io_process_queue) {
+            if (node->io_process_queue(node->opaque)) {
+                ret = 1;
+            }
+        }
+    }
+
+    walking_handlers = 0;
+
+    return ret;
+}
+
+void qemu_aio_wait(void)
+{
+    int ret;
+
+    if (qemu_bh_poll())
+        return;
+
+    /*
+     * If there are callbacks left that have been queued, we need to call then.
+     * Return afterwards to avoid waiting needlessly in select().
+     */
+    if (qemu_aio_process_queue())
+        return;
+
+    do {
+        AioHandler *node;
+        fd_set rdfds, wrfds;
+        int max_fd = -1;
+
+        walking_handlers = 1;
+
+        FD_ZERO(&rdfds);
+        FD_ZERO(&wrfds);
+
+        /* fill fd sets */
+        QLIST_FOREACH(node, &aio_handlers, node) {
+            /* If there aren't pending AIO operations, don't invoke callbacks.
+             * Otherwise, if there are no AIO requests, qemu_aio_wait() would
+             * wait indefinitely.
+             */
+            if (node->io_flush && node->io_flush(node->opaque) == 0)
+                continue;
+
+            if (!node->deleted && node->io_read) {
+                FD_SET(node->fd, &rdfds);
+                max_fd = MAX(max_fd, node->fd + 1);
+            }
+            if (!node->deleted && node->io_write) {
+                FD_SET(node->fd, &wrfds);
+                max_fd = MAX(max_fd, node->fd + 1);
+            }
+        }
+
+        walking_handlers = 0;
+
+        /* No AIO operations?  Get us out of here */
+        if (max_fd == -1)
+            break;
+
+        /* wait until next event */
+        ret = select(max_fd, &rdfds, &wrfds, NULL, NULL);
+        if (ret == -1 && errno == EINTR)
+            continue;
+
+        /* if we have any readable fds, dispatch event */
+        if (ret > 0) {
+            walking_handlers = 1;
+
+            /* we have to walk very carefully in case
+             * qemu_aio_set_fd_handler is called while we're walking */
+            node = QLIST_FIRST(&aio_handlers);
+            while (node) {
+                AioHandler *tmp;
+
+                if (!node->deleted &&
+                    FD_ISSET(node->fd, &rdfds) &&
+                    node->io_read) {
+                    node->io_read(node->opaque);
+                }
+                if (!node->deleted &&
+                    FD_ISSET(node->fd, &wrfds) &&
+                    node->io_write) {
+                    node->io_write(node->opaque);
+                }
+
+                tmp = node;
+                node = QLIST_NEXT(node, node);
+
+                if (tmp->deleted) {
+                    QLIST_REMOVE(tmp, node);
+                    g_free(tmp);
+                }
+            }
+
+            walking_handlers = 0;
+        }
+    } while (ret == 0);
+}

alpha.ld

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

arch_init.h

@@ -0,0 +1,35 @@
+#ifndef QEMU_ARCH_INIT_H
+#define QEMU_ARCH_INIT_H
+
+extern const char arch_config_name[];
+
+enum {
+    QEMU_ARCH_ALL = -1,
+    QEMU_ARCH_ALPHA = 1,
+    QEMU_ARCH_ARM = 2,
+    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,
+};
+
+extern const uint32_t arch_type;
+
+void select_soundhw(const char *optarg);
+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);
+
+#endif

arm-semi.c

@@ -0,0 +1,509 @@
+/*
+ *  Arm "Angel" semihosting syscalls
+ *
+ *  Copyright (c) 2005, 2007 CodeSourcery.
+ *  Written by Paul Brook.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <time.h>
+
+#include "cpu.h"
+#ifdef CONFIG_USER_ONLY
+#include "qemu.h"
+
+#define ARM_ANGEL_HEAP_SIZE (128 * 1024 * 1024)
+#else
+#include "qemu-common.h"
+#include "gdbstub.h"
+#include "hw/arm-misc.h"
+#endif
+
+#define SYS_OPEN        0x01
+#define SYS_CLOSE       0x02
+#define SYS_WRITEC      0x03
+#define SYS_WRITE0      0x04
+#define SYS_WRITE       0x05
+#define SYS_READ        0x06
+#define SYS_READC       0x07
+#define SYS_ISTTY       0x09
+#define SYS_SEEK        0x0a
+#define SYS_FLEN        0x0c
+#define SYS_TMPNAM      0x0d
+#define SYS_REMOVE      0x0e
+#define SYS_RENAME      0x0f
+#define SYS_CLOCK       0x10
+#define SYS_TIME        0x11
+#define SYS_SYSTEM      0x12
+#define SYS_ERRNO       0x13
+#define SYS_GET_CMDLINE 0x15
+#define SYS_HEAPINFO    0x16
+#define SYS_EXIT        0x18
+
+#ifndef O_BINARY
+#define O_BINARY 0
+#endif
+
+#define GDB_O_RDONLY  0x000
+#define GDB_O_WRONLY  0x001
+#define GDB_O_RDWR    0x002
+#define GDB_O_APPEND  0x008
+#define GDB_O_CREAT   0x200
+#define GDB_O_TRUNC   0x400
+#define GDB_O_BINARY  0
+
+static int gdb_open_modeflags[12] = {
+    GDB_O_RDONLY,
+    GDB_O_RDONLY | GDB_O_BINARY,
+    GDB_O_RDWR,
+    GDB_O_RDWR | GDB_O_BINARY,
+    GDB_O_WRONLY | GDB_O_CREAT | GDB_O_TRUNC,
+    GDB_O_WRONLY | GDB_O_CREAT | GDB_O_TRUNC | GDB_O_BINARY,
+    GDB_O_RDWR | GDB_O_CREAT | GDB_O_TRUNC,
+    GDB_O_RDWR | GDB_O_CREAT | GDB_O_TRUNC | GDB_O_BINARY,
+    GDB_O_WRONLY | GDB_O_CREAT | GDB_O_APPEND,
+    GDB_O_WRONLY | GDB_O_CREAT | GDB_O_APPEND | GDB_O_BINARY,
+    GDB_O_RDWR | GDB_O_CREAT | GDB_O_APPEND,
+    GDB_O_RDWR | GDB_O_CREAT | GDB_O_APPEND | GDB_O_BINARY
+};
+
+static int open_modeflags[12] = {
+    O_RDONLY,
+    O_RDONLY | O_BINARY,
+    O_RDWR,
+    O_RDWR | O_BINARY,
+    O_WRONLY | O_CREAT | O_TRUNC,
+    O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
+    O_RDWR | O_CREAT | O_TRUNC,
+    O_RDWR | O_CREAT | O_TRUNC | O_BINARY,
+    O_WRONLY | O_CREAT | O_APPEND,
+    O_WRONLY | O_CREAT | O_APPEND | O_BINARY,
+    O_RDWR | O_CREAT | O_APPEND,
+    O_RDWR | O_CREAT | O_APPEND | O_BINARY
+};
+
+#ifdef CONFIG_USER_ONLY
+static inline uint32_t set_swi_errno(TaskState *ts, uint32_t code)
+{
+    if (code == (uint32_t)-1)
+        ts->swi_errno = errno;
+    return code;
+}
+#else
+static inline uint32_t set_swi_errno(CPUState *env, uint32_t code)
+{
+    return code;
+}
+
+#include "softmmu-semi.h"
+#endif
+
+static target_ulong arm_semi_syscall_len;
+
+#if !defined(CONFIG_USER_ONLY)
+static target_ulong syscall_err;
+#endif
+
+static void arm_semi_cb(CPUState *env, target_ulong ret, target_ulong err)
+{
+#ifdef CONFIG_USER_ONLY
+    TaskState *ts = env->opaque;
+#endif
+
+    if (ret == (target_ulong)-1) {
+#ifdef CONFIG_USER_ONLY
+        ts->swi_errno = err;
+#else
+	syscall_err = err;
+#endif
+        env->regs[0] = ret;
+    } else {
+        /* Fixup syscalls that use nonstardard return conventions.  */
+        switch (env->regs[0]) {
+        case SYS_WRITE:
+        case SYS_READ:
+            env->regs[0] = arm_semi_syscall_len - ret;
+            break;
+        case SYS_SEEK:
+            env->regs[0] = 0;
+            break;
+        default:
+            env->regs[0] = ret;
+            break;
+        }
+    }
+}
+
+static void arm_semi_flen_cb(CPUState *env, target_ulong ret, target_ulong err)
+{
+    /* The size is always stored in big-endian order, extract
+       the value. We assume the size always fit in 32 bits.  */
+    uint32_t size;
+    cpu_memory_rw_debug(env, env->regs[13]-64+32, (uint8_t *)&size, 4, 0);
+    env->regs[0] = be32_to_cpu(size);
+#ifdef CONFIG_USER_ONLY
+    ((TaskState *)env->opaque)->swi_errno = err;
+#else
+    syscall_err = err;
+#endif
+}
+
+#define ARG(n)					\
+({						\
+    target_ulong __arg;				\
+    /* FIXME - handle get_user() failure */	\
+    get_user_ual(__arg, args + (n) * 4);	\
+    __arg;					\
+})
+#define SET_ARG(n, val) put_user_ual(val, args + (n) * 4)
+uint32_t do_arm_semihosting(CPUState *env)
+{
+    target_ulong args;
+    char * s;
+    int nr;
+    uint32_t ret;
+    uint32_t len;
+#ifdef CONFIG_USER_ONLY
+    TaskState *ts = env->opaque;
+#else
+    CPUState *ts = env;
+#endif
+
+    nr = env->regs[0];
+    args = env->regs[1];
+    switch (nr) {
+    case SYS_OPEN:
+        if (!(s = lock_user_string(ARG(0))))
+            /* FIXME - should this error code be -TARGET_EFAULT ? */
+            return (uint32_t)-1;
+        if (ARG(1) >= 12)
+            return (uint32_t)-1;
+        if (strcmp(s, ":tt") == 0) {
+            if (ARG(1) < 4)
+                return STDIN_FILENO;
+            else
+                return STDOUT_FILENO;
+        }
+        if (use_gdb_syscalls()) {
+            gdb_do_syscall(arm_semi_cb, "open,%s,%x,1a4", ARG(0),
+			   (int)ARG(2)+1, gdb_open_modeflags[ARG(1)]);
+            return env->regs[0];
+        } else {
+            ret = set_swi_errno(ts, open(s, open_modeflags[ARG(1)], 0644));
+        }
+        unlock_user(s, ARG(0), 0);
+        return ret;
+    case SYS_CLOSE:
+        if (use_gdb_syscalls()) {
+            gdb_do_syscall(arm_semi_cb, "close,%x", ARG(0));
+            return env->regs[0];
+        } else {
+            return set_swi_errno(ts, close(ARG(0)));
+        }
+    case SYS_WRITEC:
+        {
+          char c;
+
+          if (get_user_u8(c, args))
+              /* FIXME - should this error code be -TARGET_EFAULT ? */
+              return (uint32_t)-1;
+          /* Write to debug console.  stderr is near enough.  */
+          if (use_gdb_syscalls()) {
+                gdb_do_syscall(arm_semi_cb, "write,2,%x,1", args);
+                return env->regs[0];
+          } else {
+                return write(STDERR_FILENO, &c, 1);
+          }
+        }
+    case SYS_WRITE0:
+        if (!(s = lock_user_string(args)))
+            /* FIXME - should this error code be -TARGET_EFAULT ? */
+            return (uint32_t)-1;
+        len = strlen(s);
+        if (use_gdb_syscalls()) {
+            gdb_do_syscall(arm_semi_cb, "write,2,%x,%x\n", args, len);
+            ret = env->regs[0];
+        } else {
+            ret = write(STDERR_FILENO, s, len);
+        }
+        unlock_user(s, args, 0);
+        return ret;
+    case SYS_WRITE:
+        len = ARG(2);
+        if (use_gdb_syscalls()) {
+            arm_semi_syscall_len = len;
+            gdb_do_syscall(arm_semi_cb, "write,%x,%x,%x", ARG(0), ARG(1), len);
+            return env->regs[0];
+        } else {
+            if (!(s = lock_user(VERIFY_READ, ARG(1), len, 1)))
+                /* FIXME - should this error code be -TARGET_EFAULT ? */
+                return (uint32_t)-1;
+            ret = set_swi_errno(ts, write(ARG(0), s, len));
+            unlock_user(s, ARG(1), 0);
+            if (ret == (uint32_t)-1)
+                return -1;
+            return len - ret;
+        }
+    case SYS_READ:
+        len = ARG(2);
+        if (use_gdb_syscalls()) {
+            arm_semi_syscall_len = len;
+            gdb_do_syscall(arm_semi_cb, "read,%x,%x,%x", ARG(0), ARG(1), len);
+            return env->regs[0];
+        } else {
+            if (!(s = lock_user(VERIFY_WRITE, ARG(1), len, 0)))
+                /* FIXME - should this error code be -TARGET_EFAULT ? */
+                return (uint32_t)-1;
+            do
+              ret = set_swi_errno(ts, read(ARG(0), s, len));
+            while (ret == -1 && errno == EINTR);
+            unlock_user(s, ARG(1), len);
+            if (ret == (uint32_t)-1)
+                return -1;
+            return len - ret;
+        }
+    case SYS_READC:
+       /* XXX: Read from debug cosole. Not implemented.  */
+        return 0;
+    case SYS_ISTTY:
+        if (use_gdb_syscalls()) {
+            gdb_do_syscall(arm_semi_cb, "isatty,%x", ARG(0));
+            return env->regs[0];
+        } else {
+            return isatty(ARG(0));
+        }
+    case SYS_SEEK:
+        if (use_gdb_syscalls()) {
+            gdb_do_syscall(arm_semi_cb, "lseek,%x,%x,0", ARG(0), ARG(1));
+            return env->regs[0];
+        } else {
+            ret = set_swi_errno(ts, lseek(ARG(0), ARG(1), SEEK_SET));
+            if (ret == (uint32_t)-1)
+              return -1;
+            return 0;
+        }
+    case SYS_FLEN:
+        if (use_gdb_syscalls()) {
+            gdb_do_syscall(arm_semi_flen_cb, "fstat,%x,%x",
+			   ARG(0), env->regs[13]-64);
+            return env->regs[0];
+        } else {
+            struct stat buf;
+            ret = set_swi_errno(ts, fstat(ARG(0), &buf));
+            if (ret == (uint32_t)-1)
+                return -1;
+            return buf.st_size;
+        }
+    case SYS_TMPNAM:
+        /* XXX: Not implemented.  */
+        return -1;
+    case SYS_REMOVE:
+        if (use_gdb_syscalls()) {
+            gdb_do_syscall(arm_semi_cb, "unlink,%s", ARG(0), (int)ARG(1)+1);
+            ret = env->regs[0];
+        } else {
+            if (!(s = lock_user_string(ARG(0))))
+                /* FIXME - should this error code be -TARGET_EFAULT ? */
+                return (uint32_t)-1;
+            ret =  set_swi_errno(ts, remove(s));
+            unlock_user(s, ARG(0), 0);
+        }
+        return ret;
+    case SYS_RENAME:
+        if (use_gdb_syscalls()) {
+            gdb_do_syscall(arm_semi_cb, "rename,%s,%s",
+                           ARG(0), (int)ARG(1)+1, ARG(2), (int)ARG(3)+1);
+            return env->regs[0];
+        } else {
+            char *s2;
+            s = lock_user_string(ARG(0));
+            s2 = lock_user_string(ARG(2));
+            if (!s || !s2)
+                /* FIXME - should this error code be -TARGET_EFAULT ? */
+                ret = (uint32_t)-1;
+            else
+                ret = set_swi_errno(ts, rename(s, s2));
+            if (s2)
+                unlock_user(s2, ARG(2), 0);
+            if (s)
+                unlock_user(s, ARG(0), 0);
+            return ret;
+        }
+    case SYS_CLOCK:
+        return clock() / (CLOCKS_PER_SEC / 100);
+    case SYS_TIME:
+        return set_swi_errno(ts, time(NULL));
+    case SYS_SYSTEM:
+        if (use_gdb_syscalls()) {
+            gdb_do_syscall(arm_semi_cb, "system,%s", ARG(0), (int)ARG(1)+1);
+            return env->regs[0];
+        } else {
+            if (!(s = lock_user_string(ARG(0))))
+                /* FIXME - should this error code be -TARGET_EFAULT ? */
+                return (uint32_t)-1;
+            ret = set_swi_errno(ts, system(s));
+            unlock_user(s, ARG(0), 0);
+            return ret;
+        }
+    case SYS_ERRNO:
+#ifdef CONFIG_USER_ONLY
+        return ts->swi_errno;
+#else
+        return syscall_err;
+#endif
+    case SYS_GET_CMDLINE:
+        {
+            /* 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 *output_buffer;
+            size_t input_size = ARG(1);
+            size_t output_size;
+            int status = 0;
+
+            /* 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;
+
+            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] = ' ';
+                }
+            }
+        out:
+#endif
+            /* Unlock the buffer on the ARM side.  */
+            unlock_user(output_buffer, ARG(0), output_size);
+
+            return status;
+        }
+    case SYS_HEAPINFO:
+        {
+            uint32_t *ptr;
+            uint32_t limit;
+
+#ifdef CONFIG_USER_ONLY
+            /* Some C libraries assume the heap immediately follows .bss, so
+               allocate it using sbrk.  */
+            if (!ts->heap_limit) {
+                abi_ulong 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) {
+                        break;
+                    }
+                    limit = (ts->heap_base >> 1) + (limit >> 1);
+                }
+                ts->heap_limit = limit;
+            }
+
+            if (!(ptr = lock_user(VERIFY_WRITE, ARG(0), 16, 0)))
+                /* FIXME - should this error code be -TARGET_EFAULT ? */
+                return (uint32_t)-1;
+            ptr[0] = tswap32(ts->heap_base);
+            ptr[1] = tswap32(ts->heap_limit);
+            ptr[2] = tswap32(ts->stack_base);
+            ptr[3] = tswap32(0); /* Stack limit.  */
+            unlock_user(ptr, ARG(0), 16);
+#else
+            limit = ram_size;
+            if (!(ptr = lock_user(VERIFY_WRITE, ARG(0), 16, 0)))
+                /* FIXME - should this error code be -TARGET_EFAULT ? */
+                return (uint32_t)-1;
+            /* TODO: Make this use the limit of the loaded application.  */
+            ptr[0] = tswap32(limit / 2);
+            ptr[1] = tswap32(limit);
+            ptr[2] = tswap32(limit); /* Stack base */
+            ptr[3] = tswap32(0); /* Stack limit.  */
+            unlock_user(ptr, ARG(0), 16);
+#endif
+            return 0;
+        }
+    case SYS_EXIT:
+        gdb_exit(env, 0);
+        exit(0);
+    default:
+        fprintf(stderr, "qemu: Unsupported SemiHosting SWI 0x%02x\n", nr);
+        cpu_dump_state(env, stderr, fprintf, 0);
+        abort();
+    }
+}

arm.ld

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

async.c

@@ -23,59 +23,48 @@
  */
 
 #include "qemu-common.h"
-#include "block/aio.h"
-#include "block/thread-pool.h"
-#include "qemu/main-loop.h"
-#include "qemu/atomic.h"
+#include "qemu-aio.h"
+#include "main-loop.h"
+
+/* Anchor of the list of Bottom Halves belonging to the context */
+static struct QEMUBH *first_bh;
 
 /***********************************************************/
 /* bottom halves (can be seen as timers which expire ASAP) */
 
 struct QEMUBH {
-    AioContext *ctx;
     QEMUBHFunc *cb;
     void *opaque;
+    int scheduled;
+    int idle;
+    int deleted;
     QEMUBH *next;
-    bool scheduled;
-    bool idle;
-    bool deleted;
 };
 
-QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
+QEMUBH *qemu_bh_new(QEMUBHFunc *cb, void *opaque)
 {
     QEMUBH *bh;
     bh = g_malloc0(sizeof(QEMUBH));
-    bh->ctx = ctx;
     bh->cb = cb;
     bh->opaque = opaque;
-    qemu_mutex_lock(&ctx->bh_lock);
-    bh->next = ctx->first_bh;
-    /* Make sure that the members are ready before putting bh into list */
-    smp_wmb();
-    ctx->first_bh = bh;
-    qemu_mutex_unlock(&ctx->bh_lock);
+    bh->next = first_bh;
+    first_bh = bh;
     return bh;
 }
 
-/* Multiple occurrences of aio_bh_poll cannot be called concurrently */
-int aio_bh_poll(AioContext *ctx)
+int qemu_bh_poll(void)
 {
     QEMUBH *bh, **bhp, *next;
     int ret;
+    static int nesting = 0;
 
-    ctx->walking_bh++;
+    nesting++;
 
     ret = 0;
-    for (bh = ctx->first_bh; bh; bh = next) {
-        /* Make sure that fetching bh happens before accessing its members */
-        smp_read_barrier_depends();
+    for (bh = first_bh; bh; bh = next) {
         next = bh->next;
         if (!bh->deleted && bh->scheduled) {
             bh->scheduled = 0;
-            /* Paired with write barrier in bh schedule to ensure reading for
-             * idle & callbacks coming after bh's scheduling.
-             */
-            smp_rmb();
             if (!bh->idle)
                 ret = 1;
             bh->idle = 0;
@@ -83,12 +72,11 @@ int aio_bh_poll(AioContext *ctx)
         }
     }
 
-    ctx->walking_bh--;
+    nesting--;
 
     /* remove deleted bhs */
-    if (!ctx->walking_bh) {
-        qemu_mutex_lock(&ctx->bh_lock);
-        bhp = &ctx->first_bh;
+    if (!nesting) {
+        bhp = &first_bh;
         while (*bhp) {
             bh = *bhp;
             if (bh->deleted) {
@@ -98,7 +86,6 @@ int aio_bh_poll(AioContext *ctx)
                 bhp = &bh->next;
             }
         }
-        qemu_mutex_unlock(&ctx->bh_lock);
     }
 
     return ret;
@@ -108,211 +95,48 @@ void qemu_bh_schedule_idle(QEMUBH *bh)
 {
     if (bh->scheduled)
         return;
-    bh->idle = 1;
-    /* Make sure that idle & any writes needed by the callback are done
-     * before the locations are read in the aio_bh_poll.
-     */
-    smp_wmb();
     bh->scheduled = 1;
+    bh->idle = 1;
 }
 
 void qemu_bh_schedule(QEMUBH *bh)
 {
-    AioContext *ctx;
-
     if (bh->scheduled)
         return;
-    ctx = bh->ctx;
-    bh->idle = 0;
-    /* Make sure that:
-     * 1. idle & any writes needed by the callback are done before the
-     *    locations are read in the aio_bh_poll.
-     * 2. ctx is loaded before scheduled is set and the callback has a chance
-     *    to execute.
-     */
-    smp_mb();
     bh->scheduled = 1;
-    aio_notify(ctx);
+    bh->idle = 0;
+    /* stop the currently executing CPU to execute the BH ASAP */
+    qemu_notify_event();
 }
 
-
-/* This func is async.
- */
 void qemu_bh_cancel(QEMUBH *bh)
 {
     bh->scheduled = 0;
 }
 
-/* This func is async.The bottom half will do the delete action at the finial
- * end.
- */
 void qemu_bh_delete(QEMUBH *bh)
 {
     bh->scheduled = 0;
     bh->deleted = 1;
 }
 
-static gboolean
-aio_ctx_prepare(GSource *source, gint    *timeout)
+void qemu_bh_update_timeout(int *timeout)
 {
-    AioContext *ctx = (AioContext *) source;
     QEMUBH *bh;
-    int deadline;
 
-    /* We assume there is no timeout already supplied */
-    *timeout = -1;
-    for (bh = ctx->first_bh; bh; bh = bh->next) {
+    for (bh = first_bh; bh; bh = bh->next) {
         if (!bh->deleted && bh->scheduled) {
             if (bh->idle) {
                 /* idle bottom halves will be polled at least
                  * every 10ms */
-                *timeout = 10;
+                *timeout = MIN(10, *timeout);
             } else {
                 /* non-idle bottom halves will be executed
                  * immediately */
                 *timeout = 0;
-                return true;
+                break;
             }
         }
     }
-
-    deadline = qemu_timeout_ns_to_ms(timerlistgroup_deadline_ns(&ctx->tlg));
-    if (deadline == 0) {
-        *timeout = 0;
-        return true;
-    } else {
-        *timeout = qemu_soonest_timeout(*timeout, deadline);
-    }
-
-    return false;
 }
 
-static gboolean
-aio_ctx_check(GSource *source)
-{
-    AioContext *ctx = (AioContext *) source;
-    QEMUBH *bh;
-
-    for (bh = ctx->first_bh; bh; bh = bh->next) {
-        if (!bh->deleted && bh->scheduled) {
-            return true;
-	}
-    }
-    return aio_pending(ctx) || (timerlistgroup_deadline_ns(&ctx->tlg) == 0);
-}
-
-static gboolean
-aio_ctx_dispatch(GSource     *source,
-                 GSourceFunc  callback,
-                 gpointer     user_data)
-{
-    AioContext *ctx = (AioContext *) source;
-
-    assert(callback == NULL);
-    aio_poll(ctx, false);
-    return true;
-}
-
-static void
-aio_ctx_finalize(GSource     *source)
-{
-    AioContext *ctx = (AioContext *) source;
-
-    thread_pool_free(ctx->thread_pool);
-    aio_set_event_notifier(ctx, &ctx->notifier, NULL);
-    event_notifier_cleanup(&ctx->notifier);
-    rfifolock_destroy(&ctx->lock);
-    qemu_mutex_destroy(&ctx->bh_lock);
-    g_array_free(ctx->pollfds, TRUE);
-    timerlistgroup_deinit(&ctx->tlg);
-}
-
-static GSourceFuncs aio_source_funcs = {
-    aio_ctx_prepare,
-    aio_ctx_check,
-    aio_ctx_dispatch,
-    aio_ctx_finalize
-};
-
-GSource *aio_get_g_source(AioContext *ctx)
-{
-    g_source_ref(&ctx->source);
-    return &ctx->source;
-}
-
-ThreadPool *aio_get_thread_pool(AioContext *ctx)
-{
-    if (!ctx->thread_pool) {
-        ctx->thread_pool = thread_pool_new(ctx);
-    }
-    return ctx->thread_pool;
-}
-
-void aio_set_dispatching(AioContext *ctx, bool dispatching)
-{
-    ctx->dispatching = dispatching;
-    if (!dispatching) {
-        /* Write ctx->dispatching before reading e.g. bh->scheduled.
-         * Optimization: this is only needed when we're entering the "unsafe"
-         * phase where other threads must call event_notifier_set.
-         */
-        smp_mb();
-    }
-}
-
-void aio_notify(AioContext *ctx)
-{
-    /* Write e.g. bh->scheduled before reading ctx->dispatching.  */
-    smp_mb();
-    if (!ctx->dispatching) {
-        event_notifier_set(&ctx->notifier);
-    }
-}
-
-static void aio_timerlist_notify(void *opaque)
-{
-    aio_notify(opaque);
-}
-
-static void aio_rfifolock_cb(void *opaque)
-{
-    /* Kick owner thread in case they are blocked in aio_poll() */
-    aio_notify(opaque);
-}
-
-AioContext *aio_context_new(void)
-{
-    AioContext *ctx;
-    ctx = (AioContext *) g_source_new(&aio_source_funcs, sizeof(AioContext));
-    ctx->pollfds = g_array_new(FALSE, FALSE, sizeof(GPollFD));
-    ctx->thread_pool = NULL;
-    qemu_mutex_init(&ctx->bh_lock);
-    rfifolock_init(&ctx->lock, aio_rfifolock_cb, ctx);
-    event_notifier_init(&ctx->notifier, false);
-    aio_set_event_notifier(ctx, &ctx->notifier, 
-                           (EventNotifierHandler *)
-                           event_notifier_test_and_clear);
-    timerlistgroup_init(&ctx->tlg, aio_timerlist_notify, ctx);
-
-    return ctx;
-}
-
-void aio_context_ref(AioContext *ctx)
-{
-    g_source_ref(&ctx->source);
-}
-
-void aio_context_unref(AioContext *ctx)
-{
-    g_source_unref(&ctx->source);
-}
-
-void aio_context_acquire(AioContext *ctx)
-{
-    rfifolock_lock(&ctx->lock);
-}
-
-void aio_context_release(AioContext *ctx)
-{
-    rfifolock_unlock(&ctx->lock);
-}

audio/Makefile.objs

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

audio/alsaaudio.c

@@ -23,7 +23,7 @@
  */
 #include <alsa/asoundlib.h>
 #include "qemu-common.h"
-#include "qemu/main-loop.h"
+#include "qemu-char.h"
 #include "audio.h"
 
 #if QEMU_GNUC_PREREQ(4, 3)
@@ -815,8 +815,10 @@ static void alsa_fini_out (HWVoiceOut *hw)
     ldebug ("alsa_fini\n");
     alsa_anal_close (&alsa->handle, &alsa->pollhlp);
 
-    g_free(alsa->pcm_buf);
-    alsa->pcm_buf = NULL;
+    if (alsa->pcm_buf) {
+        g_free (alsa->pcm_buf);
+        alsa->pcm_buf = NULL;
+    }
 }
 
 static int alsa_init_out (HWVoiceOut *hw, struct audsettings *as)
@@ -976,8 +978,10 @@ static void alsa_fini_in (HWVoiceIn *hw)
 
     alsa_anal_close (&alsa->handle, &alsa->pollhlp);
 
-    g_free(alsa->pcm_buf);
-    alsa->pcm_buf = NULL;
+    if (alsa->pcm_buf) {
+        g_free (alsa->pcm_buf);
+        alsa->pcm_buf = NULL;
+    }
 }
 
 static int alsa_run_in (HWVoiceIn *hw)

audio/audio.c

@@ -23,9 +23,9 @@
  */
 #include "hw/hw.h"
 #include "audio.h"
-#include "monitor/monitor.h"
-#include "qemu/timer.h"
-#include "sysemu/sysemu.h"
+#include "monitor.h"
+#include "qemu-timer.h"
+#include "sysemu.h"
 
 #define AUDIO_CAP "audio"
 #include "audio_int.h"
@@ -95,7 +95,7 @@ static struct {
         }
     },
 
-    .period = { .hertz = 100 },
+    .period = { .hertz = 250 },
     .plive = 0,
     .log_to_monitor = 0,
     .try_poll_in = 1,
@@ -585,20 +585,17 @@ static int audio_pcm_info_eq (struct audio_pcm_info *info, struct audsettings *a
     switch (as->fmt) {
     case AUD_FMT_S8:
         sign = 1;
-        /* fall through */
     case AUD_FMT_U8:
         break;
 
     case AUD_FMT_S16:
         sign = 1;
-        /* fall through */
     case AUD_FMT_U16:
         bits = 16;
         break;
 
     case AUD_FMT_S32:
         sign = 1;
-        /* fall through */
     case AUD_FMT_U32:
         bits = 32;
         break;
@@ -818,7 +815,6 @@ static int audio_attach_capture (HWVoiceOut *hw)
         sw->active = hw->enabled;
         sw->conv = noop_conv;
         sw->ratio = ((int64_t) hw_cap->info.freq << 32) / sw->info.freq;
-        sw->vol = nominal_volume;
         sw->rate = st_rate_start (sw->info.freq, hw_cap->info.freq);
         if (!sw->rate) {
             dolog ("Could not start rate conversion for `%s'\n", SW_NAME (sw));
@@ -828,9 +824,8 @@ static int audio_attach_capture (HWVoiceOut *hw)
         QLIST_INSERT_HEAD (&hw_cap->sw_head, sw, entries);
         QLIST_INSERT_HEAD (&hw->cap_head, sc, entries);
 #ifdef DEBUG_CAPTURE
-        sw->name = g_strdup_printf ("for %p %d,%d,%d",
-                                    hw, sw->info.freq, sw->info.bits,
-                                    sw->info.nchannels);
+        asprintf (&sw->name, "for %p %d,%d,%d",
+                  hw, sw->info.freq, sw->info.bits, sw->info.nchannels);
         dolog ("Added %s active = %d\n", sw->name, sw->active);
 #endif
         if (sw->active) {
@@ -959,9 +954,7 @@ int audio_pcm_sw_read (SWVoiceIn *sw, void *buf, int size)
         total += isamp;
     }
 
-    if (!(hw->ctl_caps & VOICE_VOLUME_CAP)) {
-        mixeng_volume (sw->buf, ret, &sw->vol);
-    }
+    mixeng_volume (sw->buf, ret, &sw->vol);
 
     sw->clip (buf, sw->buf, ret);
     sw->total_hw_samples_acquired += total;
@@ -1045,10 +1038,7 @@ int audio_pcm_sw_write (SWVoiceOut *sw, void *buf, int size)
     swlim = audio_MIN (swlim, samples);
     if (swlim) {
         sw->conv (sw->buf, buf, swlim);
-
-        if (!(sw->hw->ctl_caps & VOICE_VOLUME_CAP)) {
-            mixeng_volume (sw->buf, swlim, &sw->vol);
-        }
+        mixeng_volume (sw->buf, swlim, &sw->vol);
     }
 
     while (swlim) {
@@ -1124,11 +1114,10 @@ static int audio_is_timer_needed (void)
 static void audio_reset_timer (AudioState *s)
 {
     if (audio_is_timer_needed ()) {
-        timer_mod (s->ts,
-            qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + conf.period.ticks);
+        qemu_mod_timer (s->ts, qemu_get_clock_ns (vm_clock) + 1);
     }
     else {
-        timer_del (s->ts);
+        qemu_del_timer (s->ts);
     }
 }
 
@@ -1676,7 +1665,7 @@ static void audio_pp_nb_voices (const char *typ, int nb)
         printf ("Theoretically supports many %s voices\n", typ);
         break;
     default:
-        printf ("Theoretically supports up to %d %s voices\n", nb, typ);
+        printf ("Theoretically supports upto %d %s voices\n", nb, typ);
         break;
     }
 
@@ -1778,12 +1767,10 @@ static void audio_atexit (void)
     HWVoiceOut *hwo = NULL;
     HWVoiceIn *hwi = NULL;
 
-    while ((hwo = audio_pcm_hw_find_any_out (hwo))) {
+    while ((hwo = audio_pcm_hw_find_any_enabled_out (hwo))) {
         SWVoiceCap *sc;
 
-        if (hwo->enabled) {
-            hwo->pcm_ops->ctl_out (hwo, VOICE_DISABLE);
-        }
+        hwo->pcm_ops->ctl_out (hwo, VOICE_DISABLE);
         hwo->pcm_ops->fini_out (hwo);
 
         for (sc = hwo->cap_head.lh_first; sc; sc = sc->entries.le_next) {
@@ -1796,10 +1783,8 @@ static void audio_atexit (void)
         }
     }
 
-    while ((hwi = audio_pcm_hw_find_any_in (hwi))) {
-        if (hwi->enabled) {
-            hwi->pcm_ops->ctl_in (hwi, VOICE_DISABLE);
-        }
+    while ((hwi = audio_pcm_hw_find_any_enabled_in (hwi))) {
+        hwi->pcm_ops->ctl_in (hwi, VOICE_DISABLE);
         hwi->pcm_ops->fini_in (hwi);
     }
 
@@ -1812,7 +1797,8 @@ static const VMStateDescription vmstate_audio = {
     .name = "audio",
     .version_id = 1,
     .minimum_version_id = 1,
-    .fields = (VMStateField[]) {
+    .minimum_version_id_old = 1,
+    .fields      = (VMStateField []) {
         VMSTATE_END_OF_LIST()
     }
 };
@@ -1834,7 +1820,7 @@ static void audio_init (void)
     QLIST_INIT (&s->cap_head);
     atexit (audio_atexit);
 
-    s->ts = timer_new_ns(QEMU_CLOCK_VIRTUAL, audio_timer, s);
+    s->ts = qemu_new_timer_ns (vm_clock, audio_timer, s);
     if (!s->ts) {
         hw_error("Could not create audio timer\n");
     }
@@ -2064,29 +2050,17 @@ void AUD_del_capture (CaptureVoiceOut *cap, void *cb_opaque)
 void AUD_set_volume_out (SWVoiceOut *sw, int mute, uint8_t lvol, uint8_t rvol)
 {
     if (sw) {
-        HWVoiceOut *hw = sw->hw;
-
         sw->vol.mute = mute;
         sw->vol.l = nominal_volume.l * lvol / 255;
         sw->vol.r = nominal_volume.r * rvol / 255;
-
-        if (hw->pcm_ops->ctl_out) {
-            hw->pcm_ops->ctl_out (hw, VOICE_VOLUME, sw);
-        }
     }
 }
 
 void AUD_set_volume_in (SWVoiceIn *sw, int mute, uint8_t lvol, uint8_t rvol)
 {
     if (sw) {
-        HWVoiceIn *hw = sw->hw;
-
         sw->vol.mute = mute;
         sw->vol.l = nominal_volume.l * lvol / 255;
         sw->vol.r = nominal_volume.r * rvol / 255;
-
-        if (hw->pcm_ops->ctl_in) {
-            hw->pcm_ops->ctl_in (hw, VOICE_VOLUME, sw);
-        }
     }
 }

audio/audio.h

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

audio/audio_int.h

@@ -82,7 +82,6 @@ typedef struct HWVoiceOut {
     int samples;
     QLIST_HEAD (sw_out_listhead, SWVoiceOut) sw_head;
     QLIST_HEAD (sw_cap_listhead, SWVoiceCap) cap_head;
-    int ctl_caps;
     struct audio_pcm_ops *pcm_ops;
     QLIST_ENTRY (HWVoiceOut) entries;
 } HWVoiceOut;
@@ -102,7 +101,6 @@ typedef struct HWVoiceIn {
 
     int samples;
     QLIST_HEAD (sw_in_listhead, SWVoiceIn) sw_head;
-    int ctl_caps;
     struct audio_pcm_ops *pcm_ops;
     QLIST_ENTRY (HWVoiceIn) entries;
 } HWVoiceIn;
@@ -152,7 +150,6 @@ struct audio_driver {
     int max_voices_in;
     int voice_size_out;
     int voice_size_in;
-    int ctl_caps;
 };
 
 struct audio_pcm_ops {
@@ -234,22 +231,44 @@ void audio_run (const char *msg);
 
 #define VOICE_ENABLE 1
 #define VOICE_DISABLE 2
-#define VOICE_VOLUME 3
-
-#define VOICE_VOLUME_CAP (1 << VOICE_VOLUME)
 
 static inline int audio_ring_dist (int dst, int src, int len)
 {
     return (dst >= src) ? (dst - src) : (len - src + dst);
 }
 
-#define dolog(fmt, ...) AUD_log(AUDIO_CAP, fmt, ## __VA_ARGS__)
+static void GCC_ATTR dolog (const char *fmt, ...)
+{
+    va_list ap;
+
+    va_start (ap, fmt);
+    AUD_vlog (AUDIO_CAP, fmt, ap);
+    va_end (ap);
+}
 
 #ifdef DEBUG
-#define ldebug(fmt, ...) AUD_log(AUDIO_CAP, fmt, ## __VA_ARGS__)
+static void GCC_ATTR ldebug (const char *fmt, ...)
+{
+    va_list ap;
+
+    va_start (ap, fmt);
+    AUD_vlog (AUDIO_CAP, fmt, ap);
+    va_end (ap);
+}
 #else
-#define ldebug(fmt, ...) (void)0
+#if defined NDEBUG && defined __GNUC__
+#define ldebug(...)
+#elif defined NDEBUG && defined _MSC_VER
+#define ldebug __noop
+#else
+static void GCC_ATTR ldebug (const char *fmt, ...)
+{
+    (void) fmt;
+}
 #endif
+#endif
+
+#undef GCC_ATTR
 
 #define AUDIO_STRINGIFY_(n) #n
 #define AUDIO_STRINGIFY(n) AUDIO_STRINGIFY_(n)

audio/audio_template.h

@@ -71,7 +71,10 @@ static void glue (audio_init_nb_voices_, TYPE) (struct audio_driver *drv)
 
 static void glue (audio_pcm_hw_free_resources_, TYPE) (HW *hw)
 {
-    g_free (HWBUF);
+    if (HWBUF) {
+        g_free (HWBUF);
+    }
+
     HWBUF = NULL;
 }
 
@@ -89,7 +92,9 @@ static int glue (audio_pcm_hw_alloc_resources_, TYPE) (HW *hw)
 
 static void glue (audio_pcm_sw_free_resources_, TYPE) (SW *sw)
 {
-    g_free (sw->buf);
+    if (sw->buf) {
+        g_free (sw->buf);
+    }
 
     if (sw->rate) {
         st_rate_stop (sw->rate);
@@ -167,8 +172,10 @@ static int glue (audio_pcm_sw_init_, TYPE) (
 static void glue (audio_pcm_sw_fini_, TYPE) (SW *sw)
 {
     glue (audio_pcm_sw_free_resources_, TYPE) (sw);
-    g_free (sw->name);
-    sw->name = NULL;
+    if (sw->name) {
+        g_free (sw->name);
+        sw->name = NULL;
+    }
 }
 
 static void glue (audio_pcm_hw_add_sw_, TYPE) (HW *hw, SW *sw)
@@ -256,8 +263,6 @@ static HW *glue (audio_pcm_hw_add_new_, TYPE) (struct audsettings *as)
     }
 
     hw->pcm_ops = drv->pcm_ops;
-    hw->ctl_caps = drv->ctl_caps;
-
     QLIST_INIT (&hw->sw_head);
 #ifdef DAC
     QLIST_INIT (&hw->cap_head);
@@ -403,15 +408,15 @@ SW *glue (AUD_open_, TYPE) (
     SW *old_sw = NULL;
 #endif
 
+    ldebug ("open %s, freq %d, nchannels %d, fmt %d\n",
+            name, as->freq, as->nchannels, as->fmt);
+
     if (audio_bug (AUDIO_FUNC, !card || !name || !callback_fn || !as)) {
         dolog ("card=%p name=%p callback_fn=%p as=%p\n",
                card, name, callback_fn, as);
         goto fail;
     }
 
-    ldebug ("open %s, freq %d, nchannels %d, fmt %d\n",
-            name, as->freq, as->nchannels, as->fmt);
-
     if (audio_bug (AUDIO_FUNC, audio_validate_settings (as))) {
         audio_print_settings (as);
         goto fail;

audio/audio_win_int.c

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

audio/esdaudio.c

@@ -201,7 +201,7 @@ static int qesd_init_out (HWVoiceOut *hw, struct audsettings *as)
     case AUD_FMT_S32:
     case AUD_FMT_U32:
         dolog ("Will use 16 instead of 32 bit samples\n");
-        /* fall through */
+
     case AUD_FMT_S16:
     case AUD_FMT_U16:
     deffmt:

audio/mixeng.c

@@ -33,8 +33,7 @@
 #define ENDIAN_CONVERT(v) (v)
 
 /* Signed 8 bit */
-#define BSIZE 8
-#define ITYPE int
+#define IN_T int8_t
 #define IN_MIN SCHAR_MIN
 #define IN_MAX SCHAR_MAX
 #define SIGNED
@@ -43,29 +42,25 @@
 #undef SIGNED
 #undef IN_MAX
 #undef IN_MIN
-#undef BSIZE
-#undef ITYPE
+#undef IN_T
 #undef SHIFT
 
 /* Unsigned 8 bit */
-#define BSIZE 8
-#define ITYPE uint
+#define IN_T uint8_t
 #define IN_MIN 0
 #define IN_MAX UCHAR_MAX
 #define SHIFT 8
 #include "mixeng_template.h"
 #undef IN_MAX
 #undef IN_MIN
-#undef BSIZE
-#undef ITYPE
+#undef IN_T
 #undef SHIFT
 
 #undef ENDIAN_CONVERT
 #undef ENDIAN_CONVERSION
 
 /* Signed 16 bit */
-#define BSIZE 16
-#define ITYPE int
+#define IN_T int16_t
 #define IN_MIN SHRT_MIN
 #define IN_MAX SHRT_MAX
 #define SIGNED
@@ -83,13 +78,11 @@
 #undef SIGNED
 #undef IN_MAX
 #undef IN_MIN
-#undef BSIZE
-#undef ITYPE
+#undef IN_T
 #undef SHIFT
 
 /* Unsigned 16 bit */
-#define BSIZE 16
-#define ITYPE uint
+#define IN_T uint16_t
 #define IN_MIN 0
 #define IN_MAX USHRT_MAX
 #define SHIFT 16
@@ -105,13 +98,11 @@
 #undef ENDIAN_CONVERSION
 #undef IN_MAX
 #undef IN_MIN
-#undef BSIZE
-#undef ITYPE
+#undef IN_T
 #undef SHIFT
 
 /* Signed 32 bit */
-#define BSIZE 32
-#define ITYPE int
+#define IN_T int32_t
 #define IN_MIN INT32_MIN
 #define IN_MAX INT32_MAX
 #define SIGNED
@@ -129,13 +120,11 @@
 #undef SIGNED
 #undef IN_MAX
 #undef IN_MIN
-#undef BSIZE
-#undef ITYPE
+#undef IN_T
 #undef SHIFT
 
 /* Unsigned 32 bit */
-#define BSIZE 32
-#define ITYPE uint
+#define IN_T uint32_t
 #define IN_MIN 0
 #define IN_MAX UINT32_MAX
 #define SHIFT 32
@@ -151,8 +140,7 @@
 #undef ENDIAN_CONVERSION
 #undef IN_MAX
 #undef IN_MIN
-#undef BSIZE
-#undef ITYPE
+#undef IN_T
 #undef SHIFT
 
 t_sample *mixeng_conv[2][2][2][3] = {
@@ -348,6 +336,7 @@ void mixeng_clear (struct st_sample *buf, int len)
 
 void mixeng_volume (struct st_sample *buf, int len, struct mixeng_volume *vol)
 {
+#ifdef CONFIG_MIXEMU
     if (vol->mute) {
         mixeng_clear (buf, len);
         return;
@@ -363,4 +352,9 @@ void mixeng_volume (struct st_sample *buf, int len, struct mixeng_volume *vol)
 #endif
         buf += 1;
     }
+#else
+    (void) buf;
+    (void) len;
+    (void) vol;
+#endif
 }

audio/mixeng_template.h

@@ -31,11 +31,10 @@
 #define HALF (IN_MAX >> 1)
 #endif
 
-#define ET glue (ENDIAN_CONVERSION, glue (glue (glue (_, ITYPE), BSIZE), _t))
-#define IN_T glue (glue (ITYPE, BSIZE), _t)
+#define ET glue (ENDIAN_CONVERSION, glue (_, IN_T))
 
 #ifdef FLOAT_MIXENG
-static inline mixeng_real glue (conv_, ET) (IN_T v)
+static mixeng_real inline glue (conv_, ET) (IN_T v)
 {
     IN_T nv = ENDIAN_CONVERT (v);
 
@@ -54,7 +53,7 @@ static inline mixeng_real glue (conv_, ET) (IN_T v)
 #endif
 }
 
-static inline IN_T glue (clip_, ET) (mixeng_real v)
+static IN_T inline glue (clip_, ET) (mixeng_real v)
 {
     if (v >= 0.5) {
         return IN_MAX;
@@ -151,4 +150,3 @@ static void glue (glue (clip_, ET), _from_mono)
 
 #undef ET
 #undef HALF
-#undef IN_T

audio/noaudio.c

@@ -23,7 +23,7 @@
  */
 #include "qemu-common.h"
 #include "audio.h"
-#include "qemu/timer.h"
+#include "qemu-timer.h"
 
 #define AUDIO_CAP "noaudio"
 #include "audio_int.h"
@@ -46,7 +46,7 @@ static int no_run_out (HWVoiceOut *hw, int live)
     int64_t ticks;
     int64_t bytes;
 
-    now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+    now = qemu_get_clock_ns (vm_clock);
     ticks = now - no->old_ticks;
     bytes = muldiv64 (ticks, hw->info.bytes_per_second, get_ticks_per_sec ());
     bytes = audio_MIN (bytes, INT_MAX);
@@ -102,7 +102,7 @@ static int no_run_in (HWVoiceIn *hw)
     int samples = 0;
 
     if (dead) {
-        int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+        int64_t now = qemu_get_clock_ns (vm_clock);
         int64_t ticks = now - no->old_ticks;
         int64_t bytes =
             muldiv64 (ticks, hw->info.bytes_per_second, get_ticks_per_sec ());

audio/ossaudio.c

@@ -25,10 +25,14 @@
 #include <sys/mman.h>
 #include <sys/types.h>
 #include <sys/ioctl.h>
+#ifdef __OpenBSD__
+#include <soundcard.h>
+#else
 #include <sys/soundcard.h>
+#endif
 #include "qemu-common.h"
-#include "qemu/main-loop.h"
-#include "qemu/host-utils.h"
+#include "host-utils.h"
+#include "qemu-char.h"
 #include "audio.h"
 
 #define AUDIO_CAP "oss"
@@ -736,8 +740,10 @@ static void oss_fini_in (HWVoiceIn *hw)
 
     oss_anal_close (&oss->fd);
 
-    g_free(oss->pcm_buf);
-    oss->pcm_buf = NULL;
+    if (oss->pcm_buf) {
+        g_free (oss->pcm_buf);
+        oss->pcm_buf = NULL;
+    }
 }
 
 static int oss_run_in (HWVoiceIn *hw)
@@ -847,10 +853,6 @@ static int oss_ctl_in (HWVoiceIn *hw, int cmd, ...)
 
 static void *oss_audio_init (void)
 {
-    if (access(conf.devpath_in, R_OK | W_OK) < 0 ||
-        access(conf.devpath_out, R_OK | W_OK) < 0) {
-        return NULL;
-    }
     return &conf;
 }
 

audio/paaudio.c

@@ -2,7 +2,8 @@
 #include "qemu-common.h"
 #include "audio.h"
 
-#include <pulse/pulseaudio.h>
+#include <pulse/simple.h>
+#include <pulse/error.h>
 
 #define AUDIO_CAP "pulseaudio"
 #include "audio_int.h"
@@ -14,7 +15,7 @@ typedef struct {
     int live;
     int decr;
     int rpos;
-    pa_stream *stream;
+    pa_simple *s;
     void *pcm_buf;
     struct audio_pt pt;
 } PAVoiceOut;
@@ -25,23 +26,17 @@ typedef struct {
     int dead;
     int incr;
     int wpos;
-    pa_stream *stream;
+    pa_simple *s;
     void *pcm_buf;
     struct audio_pt pt;
-    const void *read_data;
-    size_t read_index, read_length;
 } PAVoiceIn;
 
-typedef struct {
+static struct {
     int samples;
     char *server;
     char *sink;
     char *source;
-    pa_threaded_mainloop *mainloop;
-    pa_context *context;
-} paaudio;
-
-static paaudio glob_paaudio = {
+} conf = {
     .samples = 4096,
 };
 
@@ -56,146 +51,6 @@ static void GCC_FMT_ATTR (2, 3) qpa_logerr (int err, const char *fmt, ...)
     AUD_log (AUDIO_CAP, "Reason: %s\n", pa_strerror (err));
 }
 
-#ifndef PA_CONTEXT_IS_GOOD
-static inline int PA_CONTEXT_IS_GOOD(pa_context_state_t x)
-{
-    return
-        x == PA_CONTEXT_CONNECTING ||
-        x == PA_CONTEXT_AUTHORIZING ||
-        x == PA_CONTEXT_SETTING_NAME ||
-        x == PA_CONTEXT_READY;
-}
-#endif
-
-#ifndef PA_STREAM_IS_GOOD
-static inline int PA_STREAM_IS_GOOD(pa_stream_state_t x)
-{
-    return
-        x == PA_STREAM_CREATING ||
-        x == PA_STREAM_READY;
-}
-#endif
-
-#define CHECK_SUCCESS_GOTO(c, rerror, expression, label)        \
-    do {                                                        \
-        if (!(expression)) {                                    \
-            if (rerror) {                                       \
-                *(rerror) = pa_context_errno ((c)->context);    \
-            }                                                   \
-            goto label;                                         \
-        }                                                       \
-    } while (0);
-
-#define CHECK_DEAD_GOTO(c, stream, rerror, label)                       \
-    do {                                                                \
-        if (!(c)->context || !PA_CONTEXT_IS_GOOD (pa_context_get_state((c)->context)) || \
-            !(stream) || !PA_STREAM_IS_GOOD (pa_stream_get_state ((stream)))) { \
-            if (((c)->context && pa_context_get_state ((c)->context) == PA_CONTEXT_FAILED) || \
-                ((stream) && pa_stream_get_state ((stream)) == PA_STREAM_FAILED)) { \
-                if (rerror) {                                           \
-                    *(rerror) = pa_context_errno ((c)->context);        \
-                }                                                       \
-            } else {                                                    \
-                if (rerror) {                                           \
-                    *(rerror) = PA_ERR_BADSTATE;                        \
-                }                                                       \
-            }                                                           \
-            goto label;                                                 \
-        }                                                               \
-    } while (0);
-
-static int qpa_simple_read (PAVoiceIn *p, void *data, size_t length, int *rerror)
-{
-    paaudio *g = &glob_paaudio;
-
-    pa_threaded_mainloop_lock (g->mainloop);
-
-    CHECK_DEAD_GOTO (g, p->stream, rerror, unlock_and_fail);
-
-    while (length > 0) {
-        size_t l;
-
-        while (!p->read_data) {
-            int r;
-
-            r = pa_stream_peek (p->stream, &p->read_data, &p->read_length);
-            CHECK_SUCCESS_GOTO (g, rerror, r == 0, unlock_and_fail);
-
-            if (!p->read_data) {
-                pa_threaded_mainloop_wait (g->mainloop);
-                CHECK_DEAD_GOTO (g, p->stream, rerror, unlock_and_fail);
-            } else {
-                p->read_index = 0;
-            }
-        }
-
-        l = p->read_length < length ? p->read_length : length;
-        memcpy (data, (const uint8_t *) p->read_data+p->read_index, l);
-
-        data = (uint8_t *) data + l;
-        length -= l;
-
-        p->read_index += l;
-        p->read_length -= l;
-
-        if (!p->read_length) {
-            int r;
-
-            r = pa_stream_drop (p->stream);
-            p->read_data = NULL;
-            p->read_length = 0;
-            p->read_index = 0;
-
-            CHECK_SUCCESS_GOTO (g, rerror, r == 0, unlock_and_fail);
-        }
-    }
-
-    pa_threaded_mainloop_unlock (g->mainloop);
-    return 0;
-
-unlock_and_fail:
-    pa_threaded_mainloop_unlock (g->mainloop);
-    return -1;
-}
-
-static int qpa_simple_write (PAVoiceOut *p, const void *data, size_t length, int *rerror)
-{
-    paaudio *g = &glob_paaudio;
-
-    pa_threaded_mainloop_lock (g->mainloop);
-
-    CHECK_DEAD_GOTO (g, p->stream, rerror, unlock_and_fail);
-
-    while (length > 0) {
-        size_t l;
-        int r;
-
-        while (!(l = pa_stream_writable_size (p->stream))) {
-            pa_threaded_mainloop_wait (g->mainloop);
-            CHECK_DEAD_GOTO (g, p->stream, rerror, unlock_and_fail);
-        }
-
-        CHECK_SUCCESS_GOTO (g, rerror, l != (size_t) -1, unlock_and_fail);
-
-        if (l > length) {
-            l = length;
-        }
-
-        r = pa_stream_write (p->stream, data, l, NULL, 0LL, PA_SEEK_RELATIVE);
-        CHECK_SUCCESS_GOTO (g, rerror, r >= 0, unlock_and_fail);
-
-        data = (const uint8_t *) data + l;
-        length -= l;
-    }
-
-    pa_threaded_mainloop_unlock (g->mainloop);
-    return 0;
-
-unlock_and_fail:
-    pa_threaded_mainloop_unlock (g->mainloop);
-    return -1;
-}
-
 static void *qpa_thread_out (void *arg)
 {
     PAVoiceOut *pa = arg;
@@ -222,7 +77,7 @@ static void *qpa_thread_out (void *arg)
             }
         }
 
-        decr = to_mix = audio_MIN (pa->live, glob_paaudio.samples >> 2);
+        decr = to_mix = audio_MIN (pa->live, conf.samples >> 2);
         rpos = pa->rpos;
 
         if (audio_pt_unlock (&pa->pt, AUDIO_FUNC)) {
@@ -236,8 +91,8 @@ static void *qpa_thread_out (void *arg)
 
             hw->clip (pa->pcm_buf, src, chunk);
 
-            if (qpa_simple_write (pa, pa->pcm_buf,
-                                  chunk << hw->info.shift, &error) < 0) {
+            if (pa_simple_write (pa->s, pa->pcm_buf,
+                                 chunk << hw->info.shift, &error) < 0) {
                 qpa_logerr (error, "pa_simple_write failed\n");
                 return NULL;
             }
@@ -314,7 +169,7 @@ static void *qpa_thread_in (void *arg)
             }
         }
 
-        incr = to_grab = audio_MIN (pa->dead, glob_paaudio.samples >> 2);
+        incr = to_grab = audio_MIN (pa->dead, conf.samples >> 2);
         wpos = pa->wpos;
 
         if (audio_pt_unlock (&pa->pt, AUDIO_FUNC)) {
@@ -326,8 +181,8 @@ static void *qpa_thread_in (void *arg)
             int chunk = audio_MIN (to_grab, hw->samples - wpos);
             void *buf = advance (pa->pcm_buf, wpos);
 
-            if (qpa_simple_read (pa, buf,
-                                 chunk << hw->info.shift, &error) < 0) {
+            if (pa_simple_read (pa->s, buf,
+                                chunk << hw->info.shift, &error) < 0) {
                 qpa_logerr (error, "pa_simple_read failed\n");
                 return NULL;
             }
@@ -428,112 +283,6 @@ static audfmt_e pa_to_audfmt (pa_sample_format_t fmt, int *endianness)
     }
 }
 
-static void context_state_cb (pa_context *c, void *userdata)
-{
-    paaudio *g = &glob_paaudio;
-
-    switch (pa_context_get_state(c)) {
-    case PA_CONTEXT_READY:
-    case PA_CONTEXT_TERMINATED:
-    case PA_CONTEXT_FAILED:
-        pa_threaded_mainloop_signal (g->mainloop, 0);
-        break;
-
-    case PA_CONTEXT_UNCONNECTED:
-    case PA_CONTEXT_CONNECTING:
-    case PA_CONTEXT_AUTHORIZING:
-    case PA_CONTEXT_SETTING_NAME:
-        break;
-    }
-}
-
-static void stream_state_cb (pa_stream *s, void * userdata)
-{
-    paaudio *g = &glob_paaudio;
-
-    switch (pa_stream_get_state (s)) {
-
-    case PA_STREAM_READY:
-    case PA_STREAM_FAILED:
-    case PA_STREAM_TERMINATED:
-        pa_threaded_mainloop_signal (g->mainloop, 0);
-        break;
-
-    case PA_STREAM_UNCONNECTED:
-    case PA_STREAM_CREATING:
-        break;
-    }
-}
-
-static void stream_request_cb (pa_stream *s, size_t length, void *userdata)
-{
-    paaudio *g = &glob_paaudio;
-
-    pa_threaded_mainloop_signal (g->mainloop, 0);
-}
-
-static pa_stream *qpa_simple_new (
-        const char *server,
-        const char *name,
-        pa_stream_direction_t dir,
-        const char *dev,
-        const char *stream_name,
-        const pa_sample_spec *ss,
-        const pa_channel_map *map,
-        const pa_buffer_attr *attr,
-        int *rerror)
-{
-    paaudio *g = &glob_paaudio;
-    int r;
-    pa_stream *stream;
-
-    pa_threaded_mainloop_lock (g->mainloop);
-
-    stream = pa_stream_new (g->context, name, ss, map);
-    if (!stream) {
-        goto fail;
-    }
-
-    pa_stream_set_state_callback (stream, stream_state_cb, g);
-    pa_stream_set_read_callback (stream, stream_request_cb, g);
-    pa_stream_set_write_callback (stream, stream_request_cb, g);
-
-    if (dir == PA_STREAM_PLAYBACK) {
-        r = pa_stream_connect_playback (stream, dev, attr,
-                                        PA_STREAM_INTERPOLATE_TIMING
-#ifdef PA_STREAM_ADJUST_LATENCY
-                                        |PA_STREAM_ADJUST_LATENCY
-#endif
-                                        |PA_STREAM_AUTO_TIMING_UPDATE, NULL, NULL);
-    } else {
-        r = pa_stream_connect_record (stream, dev, attr,
-                                      PA_STREAM_INTERPOLATE_TIMING
-#ifdef PA_STREAM_ADJUST_LATENCY
-                                      |PA_STREAM_ADJUST_LATENCY
-#endif
-                                      |PA_STREAM_AUTO_TIMING_UPDATE);
-    }
-
-    if (r < 0) {
-      goto fail;
-    }
-
-    pa_threaded_mainloop_unlock (g->mainloop);
-
-    return stream;
-
-fail:
-    pa_threaded_mainloop_unlock (g->mainloop);
-
-    if (stream) {
-        pa_stream_unref (stream);
-    }
-
-    *rerror = pa_context_errno (g->context);
-
-    return NULL;
-}
-
 static int qpa_init_out (HWVoiceOut *hw, struct audsettings *as)
 {
     int error;
@@ -547,34 +296,34 @@ static int qpa_init_out (HWVoiceOut *hw, struct audsettings *as)
     ss.rate = as->freq;
 
     /*
-     * qemu audio tick runs at 100 Hz (by default), so processing
-     * data chunks worth 10 ms of sound should be a good fit.
+     * qemu audio tick runs at 250 Hz (by default), so processing
+     * data chunks worth 4 ms of sound should be a good fit.
      */
-    ba.tlength = pa_usec_to_bytes (10 * 1000, &ss);
-    ba.minreq = pa_usec_to_bytes (5 * 1000, &ss);
+    ba.tlength = pa_usec_to_bytes (4 * 1000, &ss);
+    ba.minreq = pa_usec_to_bytes (2 * 1000, &ss);
     ba.maxlength = -1;
     ba.prebuf = -1;
 
     obt_as.fmt = pa_to_audfmt (ss.format, &obt_as.endianness);
 
-    pa->stream = qpa_simple_new (
-        glob_paaudio.server,
+    pa->s = pa_simple_new (
+        conf.server,
         "qemu",
         PA_STREAM_PLAYBACK,
-        glob_paaudio.sink,
+        conf.sink,
         "pcm.playback",
         &ss,
         NULL,                   /* channel map */
         &ba,                    /* buffering attributes */
         &error
         );
-    if (!pa->stream) {
+    if (!pa->s) {
         qpa_logerr (error, "pa_simple_new for playback failed\n");
         goto fail1;
     }
 
     audio_pcm_init_info (&hw->info, &obt_as);
-    hw->samples = glob_paaudio.samples;
+    hw->samples = conf.samples;
     pa->pcm_buf = audio_calloc (AUDIO_FUNC, hw->samples, 1 << hw->info.shift);
     pa->rpos = hw->rpos;
     if (!pa->pcm_buf) {
@@ -593,10 +342,8 @@ static int qpa_init_out (HWVoiceOut *hw, struct audsettings *as)
     g_free (pa->pcm_buf);
     pa->pcm_buf = NULL;
  fail2:
-    if (pa->stream) {
-        pa_stream_unref (pa->stream);
-        pa->stream = NULL;
-    }
+    pa_simple_free (pa->s);
+    pa->s = NULL;
  fail1:
     return -1;
 }
@@ -614,24 +361,24 @@ static int qpa_init_in (HWVoiceIn *hw, struct audsettings *as)
 
     obt_as.fmt = pa_to_audfmt (ss.format, &obt_as.endianness);
 
-    pa->stream = qpa_simple_new (
-        glob_paaudio.server,
+    pa->s = pa_simple_new (
+        conf.server,
         "qemu",
         PA_STREAM_RECORD,
-        glob_paaudio.source,
+        conf.source,
         "pcm.capture",
         &ss,
         NULL,                   /* channel map */
         NULL,                   /* buffering attributes */
         &error
         );
-    if (!pa->stream) {
+    if (!pa->s) {
         qpa_logerr (error, "pa_simple_new for capture failed\n");
         goto fail1;
     }
 
     audio_pcm_init_info (&hw->info, &obt_as);
-    hw->samples = glob_paaudio.samples;
+    hw->samples = conf.samples;
     pa->pcm_buf = audio_calloc (AUDIO_FUNC, hw->samples, 1 << hw->info.shift);
     pa->wpos = hw->wpos;
     if (!pa->pcm_buf) {
@@ -650,10 +397,8 @@ static int qpa_init_in (HWVoiceIn *hw, struct audsettings *as)
     g_free (pa->pcm_buf);
     pa->pcm_buf = NULL;
  fail2:
-    if (pa->stream) {
-        pa_stream_unref (pa->stream);
-        pa->stream = NULL;
-    }
+    pa_simple_free (pa->s);
+    pa->s = NULL;
  fail1:
     return -1;
 }
@@ -668,9 +413,9 @@ static void qpa_fini_out (HWVoiceOut *hw)
     audio_pt_unlock_and_signal (&pa->pt, AUDIO_FUNC);
     audio_pt_join (&pa->pt, &ret, AUDIO_FUNC);
 
-    if (pa->stream) {
-        pa_stream_unref (pa->stream);
-        pa->stream = NULL;
+    if (pa->s) {
+        pa_simple_free (pa->s);
+        pa->s = NULL;
     }
 
     audio_pt_fini (&pa->pt, AUDIO_FUNC);
@@ -688,9 +433,9 @@ static void qpa_fini_in (HWVoiceIn *hw)
     audio_pt_unlock_and_signal (&pa->pt, AUDIO_FUNC);
     audio_pt_join (&pa->pt, &ret, AUDIO_FUNC);
 
-    if (pa->stream) {
-        pa_stream_unref (pa->stream);
-        pa->stream = NULL;
+    if (pa->s) {
+        pa_simple_free (pa->s);
+        pa->s = NULL;
     }
 
     audio_pt_fini (&pa->pt, AUDIO_FUNC);
@@ -700,213 +445,52 @@ static void qpa_fini_in (HWVoiceIn *hw)
 
 static int qpa_ctl_out (HWVoiceOut *hw, int cmd, ...)
 {
-    PAVoiceOut *pa = (PAVoiceOut *) hw;
-    pa_operation *op;
-    pa_cvolume v;
-    paaudio *g = &glob_paaudio;
-
-#ifdef PA_CHECK_VERSION    /* macro is present in 0.9.16+ */
-    pa_cvolume_init (&v);  /* function is present in 0.9.13+ */
-#endif
-
-    switch (cmd) {
-    case VOICE_VOLUME:
-        {
-            SWVoiceOut *sw;
-            va_list ap;
-
-            va_start (ap, cmd);
-            sw = va_arg (ap, SWVoiceOut *);
-            va_end (ap);
-
-            v.channels = 2;
-            v.values[0] = ((PA_VOLUME_NORM - PA_VOLUME_MUTED) * sw->vol.l) / UINT32_MAX;
-            v.values[1] = ((PA_VOLUME_NORM - PA_VOLUME_MUTED) * sw->vol.r) / UINT32_MAX;
-
-            pa_threaded_mainloop_lock (g->mainloop);
-
-            op = pa_context_set_sink_input_volume (g->context,
-                pa_stream_get_index (pa->stream),
-                &v, NULL, NULL);
-            if (!op)
-                qpa_logerr (pa_context_errno (g->context),
-                            "set_sink_input_volume() failed\n");
-            else
-                pa_operation_unref (op);
-
-            op = pa_context_set_sink_input_mute (g->context,
-                pa_stream_get_index (pa->stream),
-               sw->vol.mute, NULL, NULL);
-            if (!op) {
-                qpa_logerr (pa_context_errno (g->context),
-                            "set_sink_input_mute() failed\n");
-            } else {
-                pa_operation_unref (op);
-            }
-
-            pa_threaded_mainloop_unlock (g->mainloop);
-        }
-    }
+    (void) hw;
+    (void) cmd;
     return 0;
 }
 
 static int qpa_ctl_in (HWVoiceIn *hw, int cmd, ...)
 {
-    PAVoiceIn *pa = (PAVoiceIn *) hw;
-    pa_operation *op;
-    pa_cvolume v;
-    paaudio *g = &glob_paaudio;
-
-#ifdef PA_CHECK_VERSION
-    pa_cvolume_init (&v);
-#endif
-
-    switch (cmd) {
-    case VOICE_VOLUME:
-        {
-            SWVoiceIn *sw;
-            va_list ap;
-
-            va_start (ap, cmd);
-            sw = va_arg (ap, SWVoiceIn *);
-            va_end (ap);
-
-            v.channels = 2;
-            v.values[0] = ((PA_VOLUME_NORM - PA_VOLUME_MUTED) * sw->vol.l) / UINT32_MAX;
-            v.values[1] = ((PA_VOLUME_NORM - PA_VOLUME_MUTED) * sw->vol.r) / UINT32_MAX;
-
-            pa_threaded_mainloop_lock (g->mainloop);
-
-            /* FIXME: use the upcoming "set_source_output_{volume,mute}" */
-            op = pa_context_set_source_volume_by_index (g->context,
-                pa_stream_get_device_index (pa->stream),
-                &v, NULL, NULL);
-            if (!op) {
-                qpa_logerr (pa_context_errno (g->context),
-                            "set_source_volume() failed\n");
-            } else {
-                pa_operation_unref(op);
-            }
-
-            op = pa_context_set_source_mute_by_index (g->context,
-                pa_stream_get_index (pa->stream),
-                sw->vol.mute, NULL, NULL);
-            if (!op) {
-                qpa_logerr (pa_context_errno (g->context),
-                            "set_source_mute() failed\n");
-            } else {
-                pa_operation_unref (op);
-            }
-
-            pa_threaded_mainloop_unlock (g->mainloop);
-        }
-    }
+    (void) hw;
+    (void) cmd;
     return 0;
 }
 
 /* common */
 static void *qpa_audio_init (void)
 {
-    paaudio *g = &glob_paaudio;
-
-    g->mainloop = pa_threaded_mainloop_new ();
-    if (!g->mainloop) {
-        goto fail;
-    }
-
-    g->context = pa_context_new (pa_threaded_mainloop_get_api (g->mainloop), glob_paaudio.server);
-    if (!g->context) {
-        goto fail;
-    }
-
-    pa_context_set_state_callback (g->context, context_state_cb, g);
-
-    if (pa_context_connect (g->context, glob_paaudio.server, 0, NULL) < 0) {
-        qpa_logerr (pa_context_errno (g->context),
-                    "pa_context_connect() failed\n");
-        goto fail;
-    }
-
-    pa_threaded_mainloop_lock (g->mainloop);
-
-    if (pa_threaded_mainloop_start (g->mainloop) < 0) {
-        goto unlock_and_fail;
-    }
-
-    for (;;) {
-        pa_context_state_t state;
-
-        state = pa_context_get_state (g->context);
-
-        if (state == PA_CONTEXT_READY) {
-            break;
-        }
-
-        if (!PA_CONTEXT_IS_GOOD (state)) {
-            qpa_logerr (pa_context_errno (g->context),
-                        "Wrong context state\n");
-            goto unlock_and_fail;
-        }
-
-        /* Wait until the context is ready */
-        pa_threaded_mainloop_wait (g->mainloop);
-    }
-
-    pa_threaded_mainloop_unlock (g->mainloop);
-
-    return &glob_paaudio;
-
-unlock_and_fail:
-    pa_threaded_mainloop_unlock (g->mainloop);
-fail:
-    AUD_log (AUDIO_CAP, "Failed to initialize PA context");
-    return NULL;
+    return &conf;
 }
 
 static void qpa_audio_fini (void *opaque)
 {
-    paaudio *g = opaque;
-
-    if (g->mainloop) {
-        pa_threaded_mainloop_stop (g->mainloop);
-    }
-
-    if (g->context) {
-        pa_context_disconnect (g->context);
-        pa_context_unref (g->context);
-        g->context = NULL;
-    }
-
-    if (g->mainloop) {
-        pa_threaded_mainloop_free (g->mainloop);
-    }
-
-    g->mainloop = NULL;
+    (void) opaque;
 }
 
 struct audio_option qpa_options[] = {
     {
         .name  = "SAMPLES",
         .tag   = AUD_OPT_INT,
-        .valp  = &glob_paaudio.samples,
+        .valp  = &conf.samples,
         .descr = "buffer size in samples"
     },
     {
         .name  = "SERVER",
         .tag   = AUD_OPT_STR,
-        .valp  = &glob_paaudio.server,
+        .valp  = &conf.server,
         .descr = "server address"
     },
     {
         .name  = "SINK",
         .tag   = AUD_OPT_STR,
-        .valp  = &glob_paaudio.sink,
+        .valp  = &conf.sink,
         .descr = "sink device name"
     },
     {
         .name  = "SOURCE",
         .tag   = AUD_OPT_STR,
-        .valp  = &glob_paaudio.source,
+        .valp  = &conf.source,
         .descr = "source device name"
     },
     { /* End of list */ }
@@ -937,6 +521,5 @@ struct audio_driver pa_audio_driver = {
     .max_voices_out = INT_MAX,
     .max_voices_in  = INT_MAX,
     .voice_size_out = sizeof (PAVoiceOut),
-    .voice_size_in  = sizeof (PAVoiceIn),
-    .ctl_caps       = VOICE_VOLUME_CAP
+    .voice_size_in  = sizeof (PAVoiceIn)
 };

audio/spiceaudio.c

@@ -18,24 +18,15 @@
  */
 
 #include "hw/hw.h"
-#include "qemu/timer.h"
+#include "qemu-timer.h"
 #include "ui/qemu-spice.h"
 
 #define AUDIO_CAP "spice"
 #include "audio.h"
 #include "audio_int.h"
 
-#if SPICE_INTERFACE_PLAYBACK_MAJOR > 1 || SPICE_INTERFACE_PLAYBACK_MINOR >= 3
-#define LINE_OUT_SAMPLES (480 * 4)
-#else
-#define LINE_OUT_SAMPLES (256 * 4)
-#endif
-
-#if SPICE_INTERFACE_RECORD_MAJOR > 2 || SPICE_INTERFACE_RECORD_MINOR >= 3
-#define LINE_IN_SAMPLES (480 * 4)
-#else
-#define LINE_IN_SAMPLES (256 * 4)
-#endif
+#define LINE_IN_SAMPLES 1024
+#define LINE_OUT_SAMPLES 1024
 
 typedef struct SpiceRateCtl {
     int64_t               start_ticks;
@@ -90,7 +81,7 @@ static void spice_audio_fini (void *opaque)
 static void rate_start (SpiceRateCtl *rate)
 {
     memset (rate, 0, sizeof (*rate));
-    rate->start_ticks = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+    rate->start_ticks = qemu_get_clock_ns (vm_clock);
 }
 
 static int rate_get_samples (struct audio_pcm_info *info, SpiceRateCtl *rate)
@@ -100,12 +91,12 @@ static int rate_get_samples (struct audio_pcm_info *info, SpiceRateCtl *rate)
     int64_t bytes;
     int64_t samples;
 
-    now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+    now = qemu_get_clock_ns (vm_clock);
     ticks = now - rate->start_ticks;
     bytes = muldiv64 (ticks, info->bytes_per_second, get_ticks_per_sec ());
     samples = (bytes - rate->bytes_sent) >> info->shift;
     if (samples < 0 || samples > 65536) {
-        error_report("Resetting rate control (%" PRId64 " samples)", samples);
+        fprintf (stderr, "Resetting rate control (%" PRId64 " samples)\n", samples);
         rate_start (rate);
         samples = 0;
     }
@@ -120,11 +111,7 @@ static int line_out_init (HWVoiceOut *hw, struct audsettings *as)
     SpiceVoiceOut *out = container_of (hw, SpiceVoiceOut, hw);
     struct audsettings settings;
 
-#if SPICE_INTERFACE_PLAYBACK_MAJOR > 1 || SPICE_INTERFACE_PLAYBACK_MINOR >= 3
-    settings.freq       = spice_server_get_best_playback_rate(NULL);
-#else
     settings.freq       = SPICE_INTERFACE_PLAYBACK_FREQ;
-#endif
     settings.nchannels  = SPICE_INTERFACE_PLAYBACK_CHAN;
     settings.fmt        = AUD_FMT_S16;
     settings.endianness = AUDIO_HOST_ENDIANNESS;
@@ -135,9 +122,6 @@ static int line_out_init (HWVoiceOut *hw, struct audsettings *as)
 
     out->sin.base.sif = &playback_sif.base;
     qemu_spice_add_interface (&out->sin.base);
-#if SPICE_INTERFACE_PLAYBACK_MAJOR > 1 || SPICE_INTERFACE_PLAYBACK_MINOR >= 3
-    spice_server_set_playback_rate(&out->sin, settings.freq);
-#endif
     return 0;
 }
 
@@ -218,26 +202,7 @@ static int line_out_ctl (HWVoiceOut *hw, int cmd, ...)
         }
         spice_server_playback_stop (&out->sin);
         break;
-    case VOICE_VOLUME:
-        {
-#if ((SPICE_INTERFACE_PLAYBACK_MAJOR >= 1) && (SPICE_INTERFACE_PLAYBACK_MINOR >= 2))
-            SWVoiceOut *sw;
-            va_list ap;
-            uint16_t vol[2];
-
-            va_start (ap, cmd);
-            sw = va_arg (ap, SWVoiceOut *);
-            va_end (ap);
-
-            vol[0] = sw->vol.l / ((1ULL << 16) + 1);
-            vol[1] = sw->vol.r / ((1ULL << 16) + 1);
-            spice_server_playback_set_volume (&out->sin, 2, vol);
-            spice_server_playback_set_mute (&out->sin, sw->vol.mute);
-#endif
-            break;
-        }
     }
-
     return 0;
 }
 
@@ -248,11 +213,7 @@ static int line_in_init (HWVoiceIn *hw, struct audsettings *as)
     SpiceVoiceIn *in = container_of (hw, SpiceVoiceIn, hw);
     struct audsettings settings;
 
-#if SPICE_INTERFACE_RECORD_MAJOR > 2 || SPICE_INTERFACE_RECORD_MINOR >= 3
-    settings.freq       = spice_server_get_best_record_rate(NULL);
-#else
     settings.freq       = SPICE_INTERFACE_RECORD_FREQ;
-#endif
     settings.nchannels  = SPICE_INTERFACE_RECORD_CHAN;
     settings.fmt        = AUD_FMT_S16;
     settings.endianness = AUDIO_HOST_ENDIANNESS;
@@ -263,9 +224,6 @@ static int line_in_init (HWVoiceIn *hw, struct audsettings *as)
 
     in->sin.base.sif = &record_sif.base;
     qemu_spice_add_interface (&in->sin.base);
-#if SPICE_INTERFACE_RECORD_MAJOR > 2 || SPICE_INTERFACE_RECORD_MINOR >= 3
-    spice_server_set_record_rate(&in->sin, settings.freq);
-#endif
     return 0;
 }
 
@@ -346,26 +304,7 @@ static int line_in_ctl (HWVoiceIn *hw, int cmd, ...)
         in->active = 0;
         spice_server_record_stop (&in->sin);
         break;
-    case VOICE_VOLUME:
-        {
-#if ((SPICE_INTERFACE_RECORD_MAJOR >= 2) && (SPICE_INTERFACE_RECORD_MINOR >= 2))
-            SWVoiceIn *sw;
-            va_list ap;
-            uint16_t vol[2];
-
-            va_start (ap, cmd);
-            sw = va_arg (ap, SWVoiceIn *);
-            va_end (ap);
-
-            vol[0] = sw->vol.l / ((1ULL << 16) + 1);
-            vol[1] = sw->vol.r / ((1ULL << 16) + 1);
-            spice_server_record_set_volume (&in->sin, 2, vol);
-            spice_server_record_set_mute (&in->sin, sw->vol.mute);
-#endif
-            break;
-        }
     }
-
     return 0;
 }
 
@@ -398,9 +337,6 @@ struct audio_driver spice_audio_driver = {
     .max_voices_in  = 1,
     .voice_size_out = sizeof (SpiceVoiceOut),
     .voice_size_in  = sizeof (SpiceVoiceIn),
-#if ((SPICE_INTERFACE_PLAYBACK_MAJOR >= 1) && (SPICE_INTERFACE_PLAYBACK_MINOR >= 2))
-    .ctl_caps       = VOICE_VOLUME_CAP
-#endif
 };
 
 void qemu_spice_audio_init (void)

audio/wavaudio.c

@@ -22,7 +22,7 @@
  * THE SOFTWARE.
  */
 #include "hw/hw.h"
-#include "qemu/timer.h"
+#include "qemu-timer.h"
 #include "audio.h"
 
 #define AUDIO_CAP "wav"
@@ -52,7 +52,7 @@ static int wav_run_out (HWVoiceOut *hw, int live)
     int rpos, decr, samples;
     uint8_t *dst;
     struct st_sample *src;
-    int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+    int64_t now = qemu_get_clock_ns (vm_clock);
     int64_t ticks = now - wav->old_ticks;
     int64_t bytes =
         muldiv64 (ticks, hw->info.bytes_per_second, get_ticks_per_sec ());

audio/wavcapture.c

@@ -1,5 +1,5 @@
 #include "hw/hw.h"
-#include "monitor/monitor.h"
+#include "monitor.h"
 #include "audio.h"
 
 typedef struct {
@@ -63,7 +63,8 @@ static void wav_destroy (void *opaque)
         }
     doclose:
         if (fclose (wav->f)) {
-            error_report("wav_destroy: fclose failed: %s", strerror(errno));
+            fprintf (stderr, "wav_destroy: fclose failed: %s",
+                     strerror (errno));
         }
     }
 

audio/winwaveaudio.c

@@ -1,7 +1,7 @@
 /* public domain */
 
 #include "qemu-common.h"
-#include "sysemu/sysemu.h"
+#include "sysemu.h"
 #include "audio.h"
 
 #define AUDIO_CAP "winwave"
@@ -72,7 +72,7 @@ static void winwave_log_mmresult (MMRESULT mr)
         break;
 
     case MMSYSERR_NOMEM:
-        str = "Unable to allocate or lock memory";
+        str = "Unable to allocate or locl memory";
         break;
 
     case WAVERR_SYNC:
@@ -349,15 +349,21 @@ static int winwave_ctl_out (HWVoiceOut *hw, int cmd, ...)
             else {
                 hw->poll_mode = 0;
             }
-            wave->paused = 0;
+            if (wave->paused) {
+                mr = waveOutRestart (wave->hwo);
+                if (mr != MMSYSERR_NOERROR) {
+                    winwave_logerr (mr, "waveOutRestart");
+                }
+                wave->paused = 0;
+            }
         }
         return 0;
 
     case VOICE_DISABLE:
         if (!wave->paused) {
-            mr = waveOutReset (wave->hwo);
+            mr = waveOutPause (wave->hwo);
             if (mr != MMSYSERR_NOERROR) {
-                winwave_logerr (mr, "waveOutReset");
+                winwave_logerr (mr, "waveOutPause");
             }
             else {
                 wave->paused = 1;

backends/Makefile.objs

@@ -1,11 +0,0 @@
-common-obj-y += rng.o rng-egd.o
-common-obj-$(CONFIG_POSIX) += rng-random.o
-
-common-obj-y += msmouse.o
-common-obj-$(CONFIG_BRLAPI) += baum.o
-baum.o-cflags := $(SDL_CFLAGS)
-
-common-obj-$(CONFIG_TPM) += tpm.o
-
-common-obj-y += hostmem.o hostmem-ram.o
-common-obj-$(CONFIG_LINUX) += hostmem-file.o

backends/hostmem-file.c

@@ -1,134 +0,0 @@
-/*
- * QEMU Host Memory Backend for hugetlbfs
- *
- * Copyright (C) 2013-2014 Red Hat Inc
- *
- * Authors:
- *   Paolo Bonzini <pbonzini@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-#include "qemu-common.h"
-#include "sysemu/hostmem.h"
-#include "sysemu/sysemu.h"
-#include "qom/object_interfaces.h"
-
-/* hostmem-file.c */
-/**
- * @TYPE_MEMORY_BACKEND_FILE:
- * name of backend that uses mmap on a file descriptor
- */
-#define TYPE_MEMORY_BACKEND_FILE "memory-backend-file"
-
-#define MEMORY_BACKEND_FILE(obj) \
-    OBJECT_CHECK(HostMemoryBackendFile, (obj), TYPE_MEMORY_BACKEND_FILE)
-
-typedef struct HostMemoryBackendFile HostMemoryBackendFile;
-
-struct HostMemoryBackendFile {
-    HostMemoryBackend parent_obj;
-
-    bool share;
-    char *mem_path;
-};
-
-static void
-file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
-{
-    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(backend);
-
-    if (!backend->size) {
-        error_setg(errp, "can't create backend with size 0");
-        return;
-    }
-    if (!fb->mem_path) {
-        error_setg(errp, "mem_path property not set");
-        return;
-    }
-#ifndef CONFIG_LINUX
-    error_setg(errp, "-mem-path not supported on this host");
-#else
-    if (!memory_region_size(&backend->mr)) {
-        backend->force_prealloc = mem_prealloc;
-        memory_region_init_ram_from_file(&backend->mr, OBJECT(backend),
-                                 object_get_canonical_path(OBJECT(backend)),
-                                 backend->size, fb->share,
-                                 fb->mem_path, errp);
-    }
-#endif
-}
-
-static void
-file_backend_class_init(ObjectClass *oc, void *data)
-{
-    HostMemoryBackendClass *bc = MEMORY_BACKEND_CLASS(oc);
-
-    bc->alloc = file_backend_memory_alloc;
-}
-
-static char *get_mem_path(Object *o, Error **errp)
-{
-    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
-
-    return g_strdup(fb->mem_path);
-}
-
-static void set_mem_path(Object *o, const char *str, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(o);
-    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
-
-    if (memory_region_size(&backend->mr)) {
-        error_setg(errp, "cannot change property value");
-        return;
-    }
-    if (fb->mem_path) {
-        g_free(fb->mem_path);
-    }
-    fb->mem_path = g_strdup(str);
-}
-
-static bool file_memory_backend_get_share(Object *o, Error **errp)
-{
-    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
-
-    return fb->share;
-}
-
-static void file_memory_backend_set_share(Object *o, bool value, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(o);
-    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
-
-    if (memory_region_size(&backend->mr)) {
-        error_setg(errp, "cannot change property value");
-        return;
-    }
-    fb->share = value;
-}
-
-static void
-file_backend_instance_init(Object *o)
-{
-    object_property_add_bool(o, "share",
-                        file_memory_backend_get_share,
-                        file_memory_backend_set_share, NULL);
-    object_property_add_str(o, "mem-path", get_mem_path,
-                            set_mem_path, NULL);
-}
-
-static const TypeInfo file_backend_info = {
-    .name = TYPE_MEMORY_BACKEND_FILE,
-    .parent = TYPE_MEMORY_BACKEND,
-    .class_init = file_backend_class_init,
-    .instance_init = file_backend_instance_init,
-    .instance_size = sizeof(HostMemoryBackendFile),
-};
-
-static void register_types(void)
-{
-    type_register_static(&file_backend_info);
-}
-
-type_init(register_types);

backends/hostmem-ram.c

@@ -1,53 +0,0 @@
-/*
- * QEMU Host Memory Backend
- *
- * Copyright (C) 2013-2014 Red Hat Inc
- *
- * Authors:
- *   Igor Mammedov <imammedo@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-#include "sysemu/hostmem.h"
-#include "qom/object_interfaces.h"
-
-#define TYPE_MEMORY_BACKEND_RAM "memory-backend-ram"
-
-
-static void
-ram_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
-{
-    char *path;
-
-    if (!backend->size) {
-        error_setg(errp, "can't create backend with size 0");
-        return;
-    }
-
-    path = object_get_canonical_path_component(OBJECT(backend));
-    memory_region_init_ram(&backend->mr, OBJECT(backend), path,
-                           backend->size);
-    g_free(path);
-}
-
-static void
-ram_backend_class_init(ObjectClass *oc, void *data)
-{
-    HostMemoryBackendClass *bc = MEMORY_BACKEND_CLASS(oc);
-
-    bc->alloc = ram_backend_memory_alloc;
-}
-
-static const TypeInfo ram_backend_info = {
-    .name = TYPE_MEMORY_BACKEND_RAM,
-    .parent = TYPE_MEMORY_BACKEND,
-    .class_init = ram_backend_class_init,
-};
-
-static void register_types(void)
-{
-    type_register_static(&ram_backend_info);
-}
-
-type_init(register_types);

backends/hostmem.c

@@ -1,375 +0,0 @@
-/*
- * QEMU Host Memory Backend
- *
- * Copyright (C) 2013-2014 Red Hat Inc
- *
- * Authors:
- *   Igor Mammedov <imammedo@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-#include "sysemu/hostmem.h"
-#include "qapi/visitor.h"
-#include "qapi-types.h"
-#include "qapi-visit.h"
-#include "qapi/qmp/qerror.h"
-#include "qemu/config-file.h"
-#include "qom/object_interfaces.h"
-
-#ifdef CONFIG_NUMA
-#include <numaif.h>
-QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_DEFAULT != MPOL_DEFAULT);
-QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_PREFERRED != MPOL_PREFERRED);
-QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_BIND != MPOL_BIND);
-QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_INTERLEAVE != MPOL_INTERLEAVE);
-#endif
-
-static void
-host_memory_backend_get_size(Object *obj, Visitor *v, void *opaque,
-                             const char *name, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-    uint64_t value = backend->size;
-
-    visit_type_size(v, &value, name, errp);
-}
-
-static void
-host_memory_backend_set_size(Object *obj, Visitor *v, void *opaque,
-                             const char *name, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-    Error *local_err = NULL;
-    uint64_t value;
-
-    if (memory_region_size(&backend->mr)) {
-        error_setg(&local_err, "cannot change property value");
-        goto out;
-    }
-
-    visit_type_size(v, &value, name, &local_err);
-    if (local_err) {
-        goto out;
-    }
-    if (!value) {
-        error_setg(&local_err, "Property '%s.%s' doesn't take value '%"
-                   PRIu64 "'", object_get_typename(obj), name, value);
-        goto out;
-    }
-    backend->size = value;
-out:
-    error_propagate(errp, local_err);
-}
-
-static void
-host_memory_backend_get_host_nodes(Object *obj, Visitor *v, void *opaque,
-                                   const char *name, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-    uint16List *host_nodes = NULL;
-    uint16List **node = &host_nodes;
-    unsigned long value;
-
-    value = find_first_bit(backend->host_nodes, MAX_NODES);
-    if (value == MAX_NODES) {
-        return;
-    }
-
-    *node = g_malloc0(sizeof(**node));
-    (*node)->value = value;
-    node = &(*node)->next;
-
-    do {
-        value = find_next_bit(backend->host_nodes, MAX_NODES, value + 1);
-        if (value == MAX_NODES) {
-            break;
-        }
-
-        *node = g_malloc0(sizeof(**node));
-        (*node)->value = value;
-        node = &(*node)->next;
-    } while (true);
-
-    visit_type_uint16List(v, &host_nodes, name, errp);
-}
-
-static void
-host_memory_backend_set_host_nodes(Object *obj, Visitor *v, void *opaque,
-                                   const char *name, Error **errp)
-{
-#ifdef CONFIG_NUMA
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-    uint16List *l = NULL;
-
-    visit_type_uint16List(v, &l, name, errp);
-
-    while (l) {
-        bitmap_set(backend->host_nodes, l->value, 1);
-        l = l->next;
-    }
-#else
-    error_setg(errp, "NUMA node binding are not supported by this QEMU");
-#endif
-}
-
-static void
-host_memory_backend_get_policy(Object *obj, Visitor *v, void *opaque,
-                               const char *name, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-    int policy = backend->policy;
-
-    visit_type_enum(v, &policy, HostMemPolicy_lookup, NULL, name, errp);
-}
-
-static void
-host_memory_backend_set_policy(Object *obj, Visitor *v, void *opaque,
-                               const char *name, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-    int policy;
-
-    visit_type_enum(v, &policy, HostMemPolicy_lookup, NULL, name, errp);
-    backend->policy = policy;
-
-#ifndef CONFIG_NUMA
-    if (policy != HOST_MEM_POLICY_DEFAULT) {
-        error_setg(errp, "NUMA policies are not supported by this QEMU");
-    }
-#endif
-}
-
-static bool host_memory_backend_get_merge(Object *obj, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-
-    return backend->merge;
-}
-
-static void host_memory_backend_set_merge(Object *obj, bool value, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-
-    if (!memory_region_size(&backend->mr)) {
-        backend->merge = value;
-        return;
-    }
-
-    if (value != backend->merge) {
-        void *ptr = memory_region_get_ram_ptr(&backend->mr);
-        uint64_t sz = memory_region_size(&backend->mr);
-
-        qemu_madvise(ptr, sz,
-                     value ? QEMU_MADV_MERGEABLE : QEMU_MADV_UNMERGEABLE);
-        backend->merge = value;
-    }
-}
-
-static bool host_memory_backend_get_dump(Object *obj, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-
-    return backend->dump;
-}
-
-static void host_memory_backend_set_dump(Object *obj, bool value, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-
-    if (!memory_region_size(&backend->mr)) {
-        backend->dump = value;
-        return;
-    }
-
-    if (value != backend->dump) {
-        void *ptr = memory_region_get_ram_ptr(&backend->mr);
-        uint64_t sz = memory_region_size(&backend->mr);
-
-        qemu_madvise(ptr, sz,
-                     value ? QEMU_MADV_DODUMP : QEMU_MADV_DONTDUMP);
-        backend->dump = value;
-    }
-}
-
-static bool host_memory_backend_get_prealloc(Object *obj, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-
-    return backend->prealloc || backend->force_prealloc;
-}
-
-static void host_memory_backend_set_prealloc(Object *obj, bool value,
-                                             Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-
-    if (backend->force_prealloc) {
-        if (value) {
-            error_setg(errp,
-                       "remove -mem-prealloc to use the prealloc property");
-            return;
-        }
-    }
-
-    if (!memory_region_size(&backend->mr)) {
-        backend->prealloc = value;
-        return;
-    }
-
-    if (value && !backend->prealloc) {
-        int fd = memory_region_get_fd(&backend->mr);
-        void *ptr = memory_region_get_ram_ptr(&backend->mr);
-        uint64_t sz = memory_region_size(&backend->mr);
-
-        os_mem_prealloc(fd, ptr, sz);
-        backend->prealloc = true;
-    }
-}
-
-static void host_memory_backend_init(Object *obj)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-
-    backend->merge = qemu_opt_get_bool(qemu_get_machine_opts(),
-                                       "mem-merge", true);
-    backend->dump = qemu_opt_get_bool(qemu_get_machine_opts(),
-                                      "dump-guest-core", true);
-    backend->prealloc = mem_prealloc;
-
-    object_property_add_bool(obj, "merge",
-                        host_memory_backend_get_merge,
-                        host_memory_backend_set_merge, NULL);
-    object_property_add_bool(obj, "dump",
-                        host_memory_backend_get_dump,
-                        host_memory_backend_set_dump, NULL);
-    object_property_add_bool(obj, "prealloc",
-                        host_memory_backend_get_prealloc,
-                        host_memory_backend_set_prealloc, NULL);
-    object_property_add(obj, "size", "int",
-                        host_memory_backend_get_size,
-                        host_memory_backend_set_size, NULL, NULL, NULL);
-    object_property_add(obj, "host-nodes", "int",
-                        host_memory_backend_get_host_nodes,
-                        host_memory_backend_set_host_nodes, NULL, NULL, NULL);
-    object_property_add(obj, "policy", "str",
-                        host_memory_backend_get_policy,
-                        host_memory_backend_set_policy, NULL, NULL, NULL);
-}
-
-static void host_memory_backend_finalize(Object *obj)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
-
-    if (memory_region_size(&backend->mr)) {
-        memory_region_destroy(&backend->mr);
-    }
-}
-
-MemoryRegion *
-host_memory_backend_get_memory(HostMemoryBackend *backend, Error **errp)
-{
-    return memory_region_size(&backend->mr) ? &backend->mr : NULL;
-}
-
-static void
-host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(uc);
-    HostMemoryBackendClass *bc = MEMORY_BACKEND_GET_CLASS(uc);
-    Error *local_err = NULL;
-    void *ptr;
-    uint64_t sz;
-
-    if (bc->alloc) {
-        bc->alloc(backend, &local_err);
-        if (local_err) {
-            error_propagate(errp, local_err);
-            return;
-        }
-
-        ptr = memory_region_get_ram_ptr(&backend->mr);
-        sz = memory_region_size(&backend->mr);
-
-        if (backend->merge) {
-            qemu_madvise(ptr, sz, QEMU_MADV_MERGEABLE);
-        }
-        if (!backend->dump) {
-            qemu_madvise(ptr, sz, QEMU_MADV_DONTDUMP);
-        }
-#ifdef CONFIG_NUMA
-        unsigned long lastbit = find_last_bit(backend->host_nodes, MAX_NODES);
-        /* lastbit == MAX_NODES means maxnode = 0 */
-        unsigned long maxnode = (lastbit + 1) % (MAX_NODES + 1);
-        /* ensure policy won't be ignored in case memory is preallocated
-         * before mbind(). note: MPOL_MF_STRICT is ignored on hugepages so
-         * this doesn't catch hugepage case. */
-        unsigned flags = MPOL_MF_STRICT | MPOL_MF_MOVE;
-
-        /* check for invalid host-nodes and policies and give more verbose
-         * error messages than mbind(). */
-        if (maxnode && backend->policy == MPOL_DEFAULT) {
-            error_setg(errp, "host-nodes must be empty for policy default,"
-                       " or you should explicitly specify a policy other"
-                       " than default");
-            return;
-        } else if (maxnode == 0 && backend->policy != MPOL_DEFAULT) {
-            error_setg(errp, "host-nodes must be set for policy %s",
-                       HostMemPolicy_lookup[backend->policy]);
-            return;
-        }
-
-        /* We can have up to MAX_NODES nodes, but we need to pass maxnode+1
-         * as argument to mbind() due to an old Linux bug (feature?) which
-         * cuts off the last specified node. This means backend->host_nodes
-         * must have MAX_NODES+1 bits available.
-         */
-        assert(sizeof(backend->host_nodes) >=
-               BITS_TO_LONGS(MAX_NODES + 1) * sizeof(unsigned long));
-        assert(maxnode <= MAX_NODES);
-        if (mbind(ptr, sz, backend->policy,
-                  maxnode ? backend->host_nodes : NULL, maxnode + 1, flags)) {
-            error_setg_errno(errp, errno,
-                             "cannot bind memory to host NUMA nodes");
-            return;
-        }
-#endif
-        /* Preallocate memory after the NUMA policy has been instantiated.
-         * This is necessary to guarantee memory is allocated with
-         * specified NUMA policy in place.
-         */
-        if (backend->prealloc) {
-            os_mem_prealloc(memory_region_get_fd(&backend->mr), ptr, sz);
-        }
-    }
-}
-
-static void
-host_memory_backend_class_init(ObjectClass *oc, void *data)
-{
-    UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
-
-    ucc->complete = host_memory_backend_memory_complete;
-}
-
-static const TypeInfo host_memory_backend_info = {
-    .name = TYPE_MEMORY_BACKEND,
-    .parent = TYPE_OBJECT,
-    .abstract = true,
-    .class_size = sizeof(HostMemoryBackendClass),
-    .class_init = host_memory_backend_class_init,
-    .instance_size = sizeof(HostMemoryBackend),
-    .instance_init = host_memory_backend_init,
-    .instance_finalize = host_memory_backend_finalize,
-    .interfaces = (InterfaceInfo[]) {
-        { TYPE_USER_CREATABLE },
-        { }
-    }
-};
-
-static void register_types(void)
-{
-    type_register_static(&host_memory_backend_info);
-}
-
-type_init(register_types);

backends/rng-egd.c

@@ -1,232 +0,0 @@
-/*
- * QEMU Random Number Generator Backend
- *
- * Copyright IBM, Corp. 2012
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-
-#include "sysemu/rng.h"
-#include "sysemu/char.h"
-#include "qapi/qmp/qerror.h"
-#include "hw/qdev.h" /* just for DEFINE_PROP_CHR */
-
-#define TYPE_RNG_EGD "rng-egd"
-#define RNG_EGD(obj) OBJECT_CHECK(RngEgd, (obj), TYPE_RNG_EGD)
-
-typedef struct RngEgd
-{
-    RngBackend parent;
-
-    CharDriverState *chr;
-    char *chr_name;
-
-    GSList *requests;
-} RngEgd;
-
-typedef struct RngRequest
-{
-    EntropyReceiveFunc *receive_entropy;
-    uint8_t *data;
-    void *opaque;
-    size_t offset;
-    size_t size;
-} RngRequest;
-
-static void rng_egd_request_entropy(RngBackend *b, size_t size,
-                                    EntropyReceiveFunc *receive_entropy,
-                                    void *opaque)
-{
-    RngEgd *s = RNG_EGD(b);
-    RngRequest *req;
-
-    req = g_malloc(sizeof(*req));
-
-    req->offset = 0;
-    req->size = size;
-    req->receive_entropy = receive_entropy;
-    req->opaque = opaque;
-    req->data = g_malloc(req->size);
-
-    while (size > 0) {
-        uint8_t header[2];
-        uint8_t len = MIN(size, 255);
-
-        /* synchronous entropy request */
-        header[0] = 0x02;
-        header[1] = len;
-
-        qemu_chr_fe_write(s->chr, header, sizeof(header));
-
-        size -= len;
-    }
-
-    s->requests = g_slist_append(s->requests, req);
-}
-
-static void rng_egd_free_request(RngRequest *req)
-{
-    g_free(req->data);
-    g_free(req);
-}
-
-static int rng_egd_chr_can_read(void *opaque)
-{
-    RngEgd *s = RNG_EGD(opaque);
-    GSList *i;
-    int size = 0;
-
-    for (i = s->requests; i; i = i->next) {
-        RngRequest *req = i->data;
-        size += req->size - req->offset;
-    }
-
-    return size;
-}
-
-static void rng_egd_chr_read(void *opaque, const uint8_t *buf, int size)
-{
-    RngEgd *s = RNG_EGD(opaque);
-    size_t buf_offset = 0;
-
-    while (size > 0 && s->requests) {
-        RngRequest *req = s->requests->data;
-        int len = MIN(size, req->size - req->offset);
-
-        memcpy(req->data + req->offset, buf + buf_offset, len);
-        buf_offset += len;
-        req->offset += len;
-        size -= len;
-
-        if (req->offset == req->size) {
-            s->requests = g_slist_remove_link(s->requests, s->requests);
-
-            req->receive_entropy(req->opaque, req->data, req->size);
-
-            rng_egd_free_request(req);
-        }
-    }
-}
-
-static void rng_egd_free_requests(RngEgd *s)
-{
-    GSList *i;
-
-    for (i = s->requests; i; i = i->next) {
-        rng_egd_free_request(i->data);
-    }
-
-    g_slist_free(s->requests);
-    s->requests = NULL;
-}
-
-static void rng_egd_cancel_requests(RngBackend *b)
-{
-    RngEgd *s = RNG_EGD(b);
-
-    /* We simply delete the list of pending requests.  If there is data in the 
-     * queue waiting to be read, this is okay, because there will always be
-     * more data than we requested originally
-     */
-    rng_egd_free_requests(s);
-}
-
-static void rng_egd_opened(RngBackend *b, Error **errp)
-{
-    RngEgd *s = RNG_EGD(b);
-
-    if (s->chr_name == NULL) {
-        error_set(errp, QERR_INVALID_PARAMETER_VALUE,
-                  "chardev", "a valid character device");
-        return;
-    }
-
-    s->chr = qemu_chr_find(s->chr_name);
-    if (s->chr == NULL) {
-        error_set(errp, QERR_DEVICE_NOT_FOUND, s->chr_name);
-        return;
-    }
-
-    if (qemu_chr_fe_claim(s->chr) != 0) {
-        error_set(errp, QERR_DEVICE_IN_USE, s->chr_name);
-        return;
-    }
-
-    /* FIXME we should resubmit pending requests when the CDS reconnects. */
-    qemu_chr_add_handlers(s->chr, rng_egd_chr_can_read, rng_egd_chr_read,
-                          NULL, s);
-}
-
-static void rng_egd_set_chardev(Object *obj, const char *value, Error **errp)
-{
-    RngBackend *b = RNG_BACKEND(obj);
-    RngEgd *s = RNG_EGD(b);
-
-    if (b->opened) {
-        error_set(errp, QERR_PERMISSION_DENIED);
-    } else {
-        g_free(s->chr_name);
-        s->chr_name = g_strdup(value);
-    }
-}
-
-static char *rng_egd_get_chardev(Object *obj, Error **errp)
-{
-    RngEgd *s = RNG_EGD(obj);
-
-    if (s->chr && s->chr->label) {
-        return g_strdup(s->chr->label);
-    }
-
-    return NULL;
-}
-
-static void rng_egd_init(Object *obj)
-{
-    object_property_add_str(obj, "chardev",
-                            rng_egd_get_chardev, rng_egd_set_chardev,
-                            NULL);
-}
-
-static void rng_egd_finalize(Object *obj)
-{
-    RngEgd *s = RNG_EGD(obj);
-
-    if (s->chr) {
-        qemu_chr_add_handlers(s->chr, NULL, NULL, NULL, NULL);
-        qemu_chr_fe_release(s->chr);
-    }
-
-    g_free(s->chr_name);
-
-    rng_egd_free_requests(s);
-}
-
-static void rng_egd_class_init(ObjectClass *klass, void *data)
-{
-    RngBackendClass *rbc = RNG_BACKEND_CLASS(klass);
-
-    rbc->request_entropy = rng_egd_request_entropy;
-    rbc->cancel_requests = rng_egd_cancel_requests;
-    rbc->opened = rng_egd_opened;
-}
-
-static const TypeInfo rng_egd_info = {
-    .name = TYPE_RNG_EGD,
-    .parent = TYPE_RNG_BACKEND,
-    .instance_size = sizeof(RngEgd),
-    .class_init = rng_egd_class_init,
-    .instance_init = rng_egd_init,
-    .instance_finalize = rng_egd_finalize,
-};
-
-static void register_types(void)
-{
-    type_register_static(&rng_egd_info);
-}
-
-type_init(register_types);

backends/rng-random.c

@@ -1,160 +0,0 @@
-/*
- * QEMU Random Number Generator Backend
- *
- * Copyright IBM, Corp. 2012
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-
-#include "sysemu/rng-random.h"
-#include "sysemu/rng.h"
-#include "qapi/qmp/qerror.h"
-#include "qemu/main-loop.h"
-
-struct RndRandom
-{
-    RngBackend parent;
-
-    int fd;
-    char *filename;
-
-    EntropyReceiveFunc *receive_func;
-    void *opaque;
-    size_t size;
-};
-
-/**
- * A simple and incomplete backend to request entropy from /dev/random.
- *
- * This backend exposes an additional "filename" property that can be used to
- * set the filename to use to open the backend.
- */
-
-static void entropy_available(void *opaque)
-{
-    RndRandom *s = RNG_RANDOM(opaque);
-    uint8_t buffer[s->size];
-    ssize_t len;
-
-    len = read(s->fd, buffer, s->size);
-    if (len < 0 && errno == EAGAIN) {
-        return;
-    }
-    g_assert(len != -1);
-
-    s->receive_func(s->opaque, buffer, len);
-    s->receive_func = NULL;
-
-    qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
-}
-
-static void rng_random_request_entropy(RngBackend *b, size_t size,
-                                        EntropyReceiveFunc *receive_entropy,
-                                        void *opaque)
-{
-    RndRandom *s = RNG_RANDOM(b);
-
-    if (s->receive_func) {
-        s->receive_func(s->opaque, NULL, 0);
-    }
-
-    s->receive_func = receive_entropy;
-    s->opaque = opaque;
-    s->size = size;
-
-    qemu_set_fd_handler(s->fd, entropy_available, NULL, s);
-}
-
-static void rng_random_opened(RngBackend *b, Error **errp)
-{
-    RndRandom *s = RNG_RANDOM(b);
-
-    if (s->filename == NULL) {
-        error_set(errp, QERR_INVALID_PARAMETER_VALUE,
-                  "filename", "a valid filename");
-    } else {
-        s->fd = qemu_open(s->filename, O_RDONLY | O_NONBLOCK);
-        if (s->fd == -1) {
-            error_setg_file_open(errp, errno, s->filename);
-        }
-    }
-}
-
-static char *rng_random_get_filename(Object *obj, Error **errp)
-{
-    RndRandom *s = RNG_RANDOM(obj);
-
-    if (s->filename) {
-        return g_strdup(s->filename);
-    }
-
-    return NULL;
-}
-
-static void rng_random_set_filename(Object *obj, const char *filename,
-                                 Error **errp)
-{
-    RngBackend *b = RNG_BACKEND(obj);
-    RndRandom *s = RNG_RANDOM(obj);
-
-    if (b->opened) {
-        error_set(errp, QERR_PERMISSION_DENIED);
-        return;
-    }
-
-    g_free(s->filename);
-    s->filename = g_strdup(filename);
-}
-
-static void rng_random_init(Object *obj)
-{
-    RndRandom *s = RNG_RANDOM(obj);
-
-    object_property_add_str(obj, "filename",
-                            rng_random_get_filename,
-                            rng_random_set_filename,
-                            NULL);
-
-    s->filename = g_strdup("/dev/random");
-    s->fd = -1;
-}
-
-static void rng_random_finalize(Object *obj)
-{
-    RndRandom *s = RNG_RANDOM(obj);
-
-    if (s->fd != -1) {
-        qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
-        qemu_close(s->fd);
-    }
-
-    g_free(s->filename);
-}
-
-static void rng_random_class_init(ObjectClass *klass, void *data)
-{
-    RngBackendClass *rbc = RNG_BACKEND_CLASS(klass);
-
-    rbc->request_entropy = rng_random_request_entropy;
-    rbc->opened = rng_random_opened;
-}
-
-static const TypeInfo rng_random_info = {
-    .name = TYPE_RNG_RANDOM,
-    .parent = TYPE_RNG_BACKEND,
-    .instance_size = sizeof(RndRandom),
-    .class_init = rng_random_class_init,
-    .instance_init = rng_random_init,
-    .instance_finalize = rng_random_finalize,
-};
-
-static void register_types(void)
-{
-    type_register_static(&rng_random_info);
-}
-
-type_init(register_types);

backends/rng.c

@@ -1,109 +0,0 @@
-/*
- * QEMU Random Number Generator Backend
- *
- * Copyright IBM, Corp. 2012
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-
-#include "sysemu/rng.h"
-#include "qapi/qmp/qerror.h"
-#include "qom/object_interfaces.h"
-
-void rng_backend_request_entropy(RngBackend *s, size_t size,
-                                 EntropyReceiveFunc *receive_entropy,
-                                 void *opaque)
-{
-    RngBackendClass *k = RNG_BACKEND_GET_CLASS(s);
-
-    if (k->request_entropy) {
-        k->request_entropy(s, size, receive_entropy, opaque);
-    }
-}
-
-void rng_backend_cancel_requests(RngBackend *s)
-{
-    RngBackendClass *k = RNG_BACKEND_GET_CLASS(s);
-
-    if (k->cancel_requests) {
-        k->cancel_requests(s);
-    }
-}
-
-static bool rng_backend_prop_get_opened(Object *obj, Error **errp)
-{
-    RngBackend *s = RNG_BACKEND(obj);
-
-    return s->opened;
-}
-
-static void rng_backend_complete(UserCreatable *uc, Error **errp)
-{
-    object_property_set_bool(OBJECT(uc), true, "opened", errp);
-}
-
-static void rng_backend_prop_set_opened(Object *obj, bool value, Error **errp)
-{
-    RngBackend *s = RNG_BACKEND(obj);
-    RngBackendClass *k = RNG_BACKEND_GET_CLASS(s);
-    Error *local_err = NULL;
-
-    if (value == s->opened) {
-        return;
-    }
-
-    if (!value && s->opened) {
-        error_set(errp, QERR_PERMISSION_DENIED);
-        return;
-    }
-
-    if (k->opened) {
-        k->opened(s, &local_err);
-        if (local_err) {
-            error_propagate(errp, local_err);
-            return;
-        }
-    }
-
-    s->opened = true;
-}
-
-static void rng_backend_init(Object *obj)
-{
-    object_property_add_bool(obj, "opened",
-                             rng_backend_prop_get_opened,
-                             rng_backend_prop_set_opened,
-                             NULL);
-}
-
-static void rng_backend_class_init(ObjectClass *oc, void *data)
-{
-    UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
-
-    ucc->complete = rng_backend_complete;
-}
-
-static const TypeInfo rng_backend_info = {
-    .name = TYPE_RNG_BACKEND,
-    .parent = TYPE_OBJECT,
-    .instance_size = sizeof(RngBackend),
-    .instance_init = rng_backend_init,
-    .class_size = sizeof(RngBackendClass),
-    .class_init = rng_backend_class_init,
-    .abstract = true,
-    .interfaces = (InterfaceInfo[]) {
-        { TYPE_USER_CREATABLE },
-        { }
-    }
-};
-
-static void register_types(void)
-{
-    type_register_static(&rng_backend_info);
-}
-
-type_init(register_types);

backends/tpm.c

@@ -1,193 +0,0 @@
-/*
- * QEMU TPM Backend
- *
- * Copyright IBM, Corp. 2013
- *
- * Authors:
- *  Stefan Berger   <stefanb@us.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- *
- * Based on backends/rng.c by Anthony Liguori
- */
-
-#include "sysemu/tpm_backend.h"
-#include "qapi/qmp/qerror.h"
-#include "sysemu/tpm.h"
-#include "qemu/thread.h"
-#include "sysemu/tpm_backend_int.h"
-
-enum TpmType tpm_backend_get_type(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->type;
-}
-
-const char *tpm_backend_get_desc(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->desc();
-}
-
-void tpm_backend_destroy(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->destroy(s);
-}
-
-int tpm_backend_init(TPMBackend *s, TPMState *state,
-                     TPMRecvDataCB *datacb)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->init(s, state, datacb);
-}
-
-int tpm_backend_startup_tpm(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->startup_tpm(s);
-}
-
-bool tpm_backend_had_startup_error(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->had_startup_error(s);
-}
-
-size_t tpm_backend_realloc_buffer(TPMBackend *s, TPMSizedBuffer *sb)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->realloc_buffer(sb);
-}
-
-void tpm_backend_deliver_request(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    k->ops->deliver_request(s);
-}
-
-void tpm_backend_reset(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    k->ops->reset(s);
-}
-
-void tpm_backend_cancel_cmd(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    k->ops->cancel_cmd(s);
-}
-
-bool tpm_backend_get_tpm_established_flag(TPMBackend *s)
-{
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-
-    return k->ops->get_tpm_established_flag(s);
-}
-
-static bool tpm_backend_prop_get_opened(Object *obj, Error **errp)
-{
-    TPMBackend *s = TPM_BACKEND(obj);
-
-    return s->opened;
-}
-
-void tpm_backend_open(TPMBackend *s, Error **errp)
-{
-    object_property_set_bool(OBJECT(s), true, "opened", errp);
-}
-
-static void tpm_backend_prop_set_opened(Object *obj, bool value, Error **errp)
-{
-    TPMBackend *s = TPM_BACKEND(obj);
-    TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
-    Error *local_err = NULL;
-
-    if (value == s->opened) {
-        return;
-    }
-
-    if (!value && s->opened) {
-        error_set(errp, QERR_PERMISSION_DENIED);
-        return;
-    }
-
-    if (k->opened) {
-        k->opened(s, &local_err);
-        if (local_err) {
-            error_propagate(errp, local_err);
-            return;
-        }
-    }
-
-    s->opened = true;
-}
-
-static void tpm_backend_instance_init(Object *obj)
-{
-    object_property_add_bool(obj, "opened",
-                             tpm_backend_prop_get_opened,
-                             tpm_backend_prop_set_opened,
-                             NULL);
-}
-
-void tpm_backend_thread_deliver_request(TPMBackendThread *tbt)
-{
-   g_thread_pool_push(tbt->pool, (gpointer)TPM_BACKEND_CMD_PROCESS_CMD, NULL);
-}
-
-void tpm_backend_thread_create(TPMBackendThread *tbt,
-                               GFunc func, gpointer user_data)
-{
-    if (!tbt->pool) {
-        tbt->pool = g_thread_pool_new(func, user_data, 1, TRUE, NULL);
-        g_thread_pool_push(tbt->pool, (gpointer)TPM_BACKEND_CMD_INIT, NULL);
-    }
-}
-
-void tpm_backend_thread_end(TPMBackendThread *tbt)
-{
-    if (tbt->pool) {
-        g_thread_pool_push(tbt->pool, (gpointer)TPM_BACKEND_CMD_END, NULL);
-        g_thread_pool_free(tbt->pool, FALSE, TRUE);
-        tbt->pool = NULL;
-    }
-}
-
-void tpm_backend_thread_tpm_reset(TPMBackendThread *tbt,
-                                  GFunc func, gpointer user_data)
-{
-    if (!tbt->pool) {
-        tpm_backend_thread_create(tbt, func, user_data);
-    } else {
-        g_thread_pool_push(tbt->pool, (gpointer)TPM_BACKEND_CMD_TPM_RESET,
-                           NULL);
-    }
-}
-
-static const TypeInfo tpm_backend_info = {
-    .name = TYPE_TPM_BACKEND,
-    .parent = TYPE_OBJECT,
-    .instance_size = sizeof(TPMBackend),
-    .instance_init = tpm_backend_instance_init,
-    .class_size = sizeof(TPMBackendClass),
-    .abstract = true,
-};
-
-static void register_types(void)
-{
-    type_register_static(&tpm_backend_info);
-}
-
-type_init(register_types);

balloon.c

@@ -24,13 +24,12 @@
  * THE SOFTWARE.
  */
 
-#include "monitor/monitor.h"
-#include "exec/cpu-common.h"
-#include "sysemu/kvm.h"
-#include "sysemu/balloon.h"
+#include "monitor.h"
+#include "cpu-common.h"
+#include "kvm.h"
+#include "balloon.h"
 #include "trace.h"
 #include "qmp-commands.h"
-#include "qapi/qmp/qjson.h"
 
 static QEMUBalloonEvent *balloon_event_fn;
 static QEMUBalloonStatus *balloon_stat_fn;
@@ -101,19 +100,31 @@ BalloonInfo *qmp_query_balloon(Error **errp)
     return info;
 }
 
-void qmp_balloon(int64_t value, Error **errp)
+/**
+ * do_balloon(): Request VM to change its memory allocation
+ */
+int do_balloon(Monitor *mon, const QDict *params,
+	       MonitorCompletion cb, void *opaque)
 {
+    int64_t target;
+    int ret;
+
     if (kvm_enabled() && !kvm_has_sync_mmu()) {
-        error_set(errp, QERR_KVM_MISSING_CAP, "synchronous MMU", "balloon");
-        return;
+        qerror_report(QERR_KVM_MISSING_CAP, "synchronous MMU", "balloon");
+        return -1;
     }
 
-    if (value <= 0) {
-        error_set(errp, QERR_INVALID_PARAMETER_VALUE, "target", "a size");
-        return;
+    target = qdict_get_int(params, "value");
+    if (target <= 0) {
+        qerror_report(QERR_INVALID_PARAMETER_VALUE, "target", "a size");
+        return -1;
     }
-    
-    if (qemu_balloon(value) == 0) {
-        error_set(errp, QERR_DEVICE_NOT_ACTIVE, "balloon");
+    ret = qemu_balloon(target);
+    if (ret == 0) {
+        qerror_report(QERR_DEVICE_NOT_ACTIVE, "balloon");
+        return -1;
     }
+
+    cb(opaque, NULL);
+    return 0;
 }

balloon.h

@@ -14,7 +14,7 @@
 #ifndef _QEMU_BALLOON_H
 #define _QEMU_BALLOON_H
 
-#include "monitor/monitor.h"
+#include "monitor.h"
 #include "qapi-types.h"
 
 typedef void (QEMUBalloonEvent)(void *opaque, ram_addr_t target);
@@ -24,4 +24,7 @@ int qemu_add_balloon_handler(QEMUBalloonEvent *event_func,
 			     QEMUBalloonStatus *stat_func, void *opaque);
 void qemu_remove_balloon_handler(void *opaque);
 
+int do_balloon(Monitor *mon, const QDict *params,
+               MonitorCompletion cb, void *opaque);
+
 #endif

bitmap.c

@@ -9,8 +9,8 @@
  * Version 2.
  */
 
-#include "qemu/bitops.h"
-#include "qemu/bitmap.h"
+#include "bitops.h"
+#include "bitmap.h"
 
 /*
  * bitmaps provide an array of bits, implemented using an an
@@ -36,9 +36,9 @@
  * endian architectures.
  */
 
-int slow_bitmap_empty(const unsigned long *bitmap, long bits)
+int slow_bitmap_empty(const unsigned long *bitmap, int bits)
 {
-    long k, lim = bits/BITS_PER_LONG;
+    int k, lim = bits/BITS_PER_LONG;
 
     for (k = 0; k < lim; ++k) {
         if (bitmap[k]) {
@@ -54,9 +54,9 @@ int slow_bitmap_empty(const unsigned long *bitmap, long bits)
     return 1;
 }
 
-int slow_bitmap_full(const unsigned long *bitmap, long bits)
+int slow_bitmap_full(const unsigned long *bitmap, int bits)
 {
-    long k, lim = bits/BITS_PER_LONG;
+    int k, lim = bits/BITS_PER_LONG;
 
     for (k = 0; k < lim; ++k) {
         if (~bitmap[k]) {
@@ -74,9 +74,9 @@ int slow_bitmap_full(const unsigned long *bitmap, long bits)
 }
 
 int slow_bitmap_equal(const unsigned long *bitmap1,
-                      const unsigned long *bitmap2, long bits)
+                      const unsigned long *bitmap2, int bits)
 {
-    long k, lim = bits/BITS_PER_LONG;
+    int k, lim = bits/BITS_PER_LONG;
 
     for (k = 0; k < lim; ++k) {
         if (bitmap1[k] != bitmap2[k]) {
@@ -94,9 +94,9 @@ int slow_bitmap_equal(const unsigned long *bitmap1,
 }
 
 void slow_bitmap_complement(unsigned long *dst, const unsigned long *src,
-                            long bits)
+                            int bits)
 {
-    long k, lim = bits/BITS_PER_LONG;
+    int k, lim = bits/BITS_PER_LONG;
 
     for (k = 0; k < lim; ++k) {
         dst[k] = ~src[k];
@@ -108,10 +108,10 @@ void slow_bitmap_complement(unsigned long *dst, const unsigned long *src,
 }
 
 int slow_bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
-                    const unsigned long *bitmap2, long bits)
+                    const unsigned long *bitmap2, int bits)
 {
-    long k;
-    long nr = BITS_TO_LONGS(bits);
+    int k;
+    int nr = BITS_TO_LONGS(bits);
     unsigned long result = 0;
 
     for (k = 0; k < nr; k++) {
@@ -121,10 +121,10 @@ int slow_bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
 }
 
 void slow_bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
-                    const unsigned long *bitmap2, long bits)
+                    const unsigned long *bitmap2, int bits)
 {
-    long k;
-    long nr = BITS_TO_LONGS(bits);
+    int k;
+    int nr = BITS_TO_LONGS(bits);
 
     for (k = 0; k < nr; k++) {
         dst[k] = bitmap1[k] | bitmap2[k];
@@ -132,10 +132,10 @@ void slow_bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
 }
 
 void slow_bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
-                     const unsigned long *bitmap2, long bits)
+                     const unsigned long *bitmap2, int bits)
 {
-    long k;
-    long nr = BITS_TO_LONGS(bits);
+    int k;
+    int nr = BITS_TO_LONGS(bits);
 
     for (k = 0; k < nr; k++) {
         dst[k] = bitmap1[k] ^ bitmap2[k];
@@ -143,10 +143,10 @@ void slow_bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
 }
 
 int slow_bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
-                       const unsigned long *bitmap2, long bits)
+                       const unsigned long *bitmap2, int bits)
 {
-    long k;
-    long nr = BITS_TO_LONGS(bits);
+    int k;
+    int nr = BITS_TO_LONGS(bits);
     unsigned long result = 0;
 
     for (k = 0; k < nr; k++) {
@@ -157,10 +157,10 @@ int slow_bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
 
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) % BITS_PER_LONG))
 
-void bitmap_set(unsigned long *map, long start, long nr)
+void bitmap_set(unsigned long *map, int start, int nr)
 {
     unsigned long *p = map + BIT_WORD(start);
-    const long size = start + nr;
+    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);
 
@@ -177,10 +177,10 @@ void bitmap_set(unsigned long *map, long start, long nr)
     }
 }
 
-void bitmap_clear(unsigned long *map, long start, long nr)
+void bitmap_clear(unsigned long *map, int start, int nr)
 {
     unsigned long *p = map + BIT_WORD(start);
-    const long size = start + nr;
+    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);
 
@@ -212,10 +212,10 @@ void bitmap_clear(unsigned long *map, long start, long nr)
  * 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 long nr,
-                                         unsigned long align_mask)
+					 unsigned long size,
+					 unsigned long start,
+					 unsigned int nr,
+					 unsigned long align_mask)
 {
     unsigned long index, end, i;
 again:
@@ -237,9 +237,9 @@ again:
 }
 
 int slow_bitmap_intersects(const unsigned long *bitmap1,
-                           const unsigned long *bitmap2, long bits)
+                           const unsigned long *bitmap2, int bits)
 {
-    long k, lim = bits/BITS_PER_LONG;
+    int k, lim = bits/BITS_PER_LONG;
 
     for (k = 0; k < lim; ++k) {
         if (bitmap1[k] & bitmap2[k]) {

bitmap.h

@@ -0,0 +1,222 @@
+/*
+ * 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

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

bitops.h

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

block-migration.c

@@ -9,27 +9,24 @@
  * This work is licensed under the terms of the GNU GPL, version 2.  See
  * the COPYING file in the top-level directory.
  *
- * Contributions after 2012-01-13 are licensed under the terms of the
- * GNU GPL, version 2 or (at your option) any later version.
  */
 
 #include "qemu-common.h"
-#include "block/block_int.h"
+#include "block_int.h"
 #include "hw/hw.h"
-#include "qemu/queue.h"
-#include "qemu/timer.h"
-#include "migration/block.h"
-#include "migration/migration.h"
-#include "sysemu/blockdev.h"
+#include "qemu-queue.h"
+#include "qemu-timer.h"
+#include "monitor.h"
+#include "block-migration.h"
+#include "migration.h"
+#include "blockdev.h"
 #include <assert.h>
 
-#define BLOCK_SIZE                       (1 << 20)
-#define BDRV_SECTORS_PER_DIRTY_CHUNK     (BLOCK_SIZE >> BDRV_SECTOR_BITS)
+#define BLOCK_SIZE (BDRV_SECTORS_PER_DIRTY_CHUNK << BDRV_SECTOR_BITS)
 
 #define BLK_MIG_FLAG_DEVICE_BLOCK       0x01
 #define BLK_MIG_FLAG_EOS                0x02
 #define BLK_MIG_FLAG_PROGRESS           0x04
-#define BLK_MIG_FLAG_ZERO_BLOCK         0x08
 
 #define MAX_IS_ALLOCATED_SEARCH 65536
 
@@ -44,26 +41,19 @@
 #endif
 
 typedef struct BlkMigDevState {
-    /* Written during setup phase.  Can be read without a lock.  */
     BlockDriverState *bs;
-    int shared_base;
-    int64_t total_sectors;
-    QSIMPLEQ_ENTRY(BlkMigDevState) entry;
-
-    /* Only used by migration thread.  Does not need a lock.  */
     int bulk_completed;
+    int shared_base;
     int64_t cur_sector;
     int64_t cur_dirty;
-
-    /* Protected by block migration lock.  */
-    unsigned long *aio_bitmap;
     int64_t completed_sectors;
-    BdrvDirtyBitmap *dirty_bitmap;
-    Error *blocker;
+    int64_t total_sectors;
+    int64_t dirty;
+    QSIMPLEQ_ENTRY(BlkMigDevState) entry;
+    unsigned long *aio_bitmap;
 } BlkMigDevState;
 
 typedef struct BlkMigBlock {
-    /* Only used by migration thread.  */
     uint8_t *buf;
     BlkMigDevState *bmds;
     int64_t sector;
@@ -71,77 +61,41 @@ typedef struct BlkMigBlock {
     struct iovec iov;
     QEMUIOVector qiov;
     BlockDriverAIOCB *aiocb;
-
-    /* Protected by block migration lock.  */
     int ret;
     QSIMPLEQ_ENTRY(BlkMigBlock) entry;
 } BlkMigBlock;
 
 typedef struct BlkMigState {
-    /* Written during setup phase.  Can be read without a lock.  */
     int blk_enable;
     int shared_base;
     QSIMPLEQ_HEAD(bmds_list, BlkMigDevState) bmds_list;
-    int64_t total_sector_sum;
-    bool zero_blocks;
-
-    /* Protected by lock.  */
     QSIMPLEQ_HEAD(blk_list, BlkMigBlock) blk_list;
     int submitted;
     int read_done;
-
-    /* Only used by migration thread.  Does not need a lock.  */
     int transferred;
+    int64_t total_sector_sum;
     int prev_progress;
     int bulk_completed;
-
-    /* Lock must be taken _inside_ the iothread lock.  */
-    QemuMutex lock;
+    long double total_time;
+    long double prev_time_offset;
+    int reads;
 } BlkMigState;
 
 static BlkMigState block_mig_state;
 
-static void blk_mig_lock(void)
-{
-    qemu_mutex_lock(&block_mig_state.lock);
-}
-
-static void blk_mig_unlock(void)
-{
-    qemu_mutex_unlock(&block_mig_state.lock);
-}
-
-/* Must run outside of the iothread lock during the bulk phase,
- * or the VM will stall.
- */
-
 static void blk_send(QEMUFile *f, BlkMigBlock * blk)
 {
     int len;
-    uint64_t flags = BLK_MIG_FLAG_DEVICE_BLOCK;
-
-    if (block_mig_state.zero_blocks &&
-        buffer_is_zero(blk->buf, BLOCK_SIZE)) {
-        flags |= BLK_MIG_FLAG_ZERO_BLOCK;
-    }
 
     /* sector number and flags */
     qemu_put_be64(f, (blk->sector << BDRV_SECTOR_BITS)
-                     | flags);
+                     | BLK_MIG_FLAG_DEVICE_BLOCK);
 
     /* device name */
     len = strlen(blk->bmds->bs->device_name);
     qemu_put_byte(f, len);
     qemu_put_buffer(f, (uint8_t *)blk->bmds->bs->device_name, len);
 
-    /* if a block is zero we need to flush here since the network
-     * bandwidth is now a lot higher than the storage device bandwidth.
-     * thus if we queue zero blocks we slow down the migration */
-    if (flags & BLK_MIG_FLAG_ZERO_BLOCK) {
-        qemu_fflush(f);
-        return;
-    }
-
     qemu_put_buffer(f, blk->buf, BLOCK_SIZE);
 }
 
@@ -155,11 +109,9 @@ uint64_t blk_mig_bytes_transferred(void)
     BlkMigDevState *bmds;
     uint64_t sum = 0;
 
-    blk_mig_lock();
     QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
         sum += bmds->completed_sectors;
     }
-    blk_mig_unlock();
     return sum << BDRV_SECTOR_BITS;
 }
 
@@ -179,8 +131,11 @@ uint64_t blk_mig_bytes_total(void)
     return sum << BDRV_SECTOR_BITS;
 }
 
-
-/* Called with migration lock held.  */
+static inline long double compute_read_bwidth(void)
+{
+    assert(block_mig_state.total_time != 0);
+    return (block_mig_state.reads / block_mig_state.total_time) * BLOCK_SIZE;
+}
 
 static int bmds_aio_inflight(BlkMigDevState *bmds, int64_t sector)
 {
@@ -194,8 +149,6 @@ static int bmds_aio_inflight(BlkMigDevState *bmds, int64_t sector)
     }
 }
 
-/* Called with migration lock held.  */
-
 static void bmds_set_aio_inflight(BlkMigDevState *bmds, int64_t sector_num,
                              int nb_sectors, int set)
 {
@@ -230,27 +183,27 @@ static void alloc_aio_bitmap(BlkMigDevState *bmds)
     bmds->aio_bitmap = g_malloc0(bitmap_size);
 }
 
-/* Never hold migration lock when yielding to the main loop!  */
-
 static void blk_mig_read_cb(void *opaque, int ret)
 {
+    long double curr_time = qemu_get_clock_ns(rt_clock);
     BlkMigBlock *blk = opaque;
 
-    blk_mig_lock();
     blk->ret = ret;
 
+    block_mig_state.reads++;
+    block_mig_state.total_time += (curr_time - block_mig_state.prev_time_offset);
+    block_mig_state.prev_time_offset = curr_time;
+
     QSIMPLEQ_INSERT_TAIL(&block_mig_state.blk_list, blk, entry);
     bmds_set_aio_inflight(blk->bmds, blk->sector, blk->nr_sectors, 0);
 
     block_mig_state.submitted--;
     block_mig_state.read_done++;
     assert(block_mig_state.submitted >= 0);
-    blk_mig_unlock();
 }
 
-/* Called with no lock taken.  */
-
-static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds)
+static int mig_save_device_bulk(Monitor *mon, QEMUFile *f,
+                                BlkMigDevState *bmds)
 {
     int64_t total_sectors = bmds->total_sectors;
     int64_t cur_sector = bmds->cur_sector;
@@ -259,13 +212,11 @@ static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds)
     int nr_sectors;
 
     if (bmds->shared_base) {
-        qemu_mutex_lock_iothread();
         while (cur_sector < total_sectors &&
                !bdrv_is_allocated(bs, cur_sector, MAX_IS_ALLOCATED_SEARCH,
                                   &nr_sectors)) {
             cur_sector += nr_sectors;
         }
-        qemu_mutex_unlock_iothread();
     }
 
     if (cur_sector >= total_sectors) {
@@ -294,58 +245,42 @@ static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds)
     blk->iov.iov_len = nr_sectors * BDRV_SECTOR_SIZE;
     qemu_iovec_init_external(&blk->qiov, &blk->iov, 1);
 
-    blk_mig_lock();
-    block_mig_state.submitted++;
-    blk_mig_unlock();
+    if (block_mig_state.submitted == 0) {
+        block_mig_state.prev_time_offset = qemu_get_clock_ns(rt_clock);
+    }
 
-    qemu_mutex_lock_iothread();
     blk->aiocb = bdrv_aio_readv(bs, cur_sector, &blk->qiov,
                                 nr_sectors, blk_mig_read_cb, blk);
+    if (!blk->aiocb) {
+        goto error;
+    }
+    block_mig_state.submitted++;
 
     bdrv_reset_dirty(bs, cur_sector, nr_sectors);
-    qemu_mutex_unlock_iothread();
-
     bmds->cur_sector = cur_sector + nr_sectors;
+
     return (bmds->cur_sector >= total_sectors);
-}
 
-/* Called with iothread lock taken.  */
-
-static int set_dirty_tracking(void)
-{
-    BlkMigDevState *bmds;
-    int ret;
-
-    QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
-        bmds->dirty_bitmap = bdrv_create_dirty_bitmap(bmds->bs, BLOCK_SIZE,
-                                                      NULL);
-        if (!bmds->dirty_bitmap) {
-            ret = -errno;
-            goto fail;
-        }
-    }
+error:
+    monitor_printf(mon, "Error reading sector %" PRId64 "\n", cur_sector);
+    qemu_file_set_error(f, -EIO);
+    g_free(blk->buf);
+    g_free(blk);
     return 0;
-
-fail:
-    QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
-        if (bmds->dirty_bitmap) {
-            bdrv_release_dirty_bitmap(bmds->bs, bmds->dirty_bitmap);
-        }
-    }
-    return ret;
 }
 
-static void unset_dirty_tracking(void)
+static void set_dirty_tracking(int enable)
 {
     BlkMigDevState *bmds;
 
     QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
-        bdrv_release_dirty_bitmap(bmds->bs, bmds->dirty_bitmap);
+        bdrv_set_dirty_tracking(bmds->bs, enable);
     }
 }
 
 static void init_blk_migration_it(void *opaque, BlockDriverState *bs)
 {
+    Monitor *mon = opaque;
     BlkMigDevState *bmds;
     int64_t sectors;
 
@@ -362,24 +297,25 @@ static void init_blk_migration_it(void *opaque, BlockDriverState *bs)
         bmds->completed_sectors = 0;
         bmds->shared_base = block_mig_state.shared_base;
         alloc_aio_bitmap(bmds);
-        error_setg(&bmds->blocker, "block device is in use by migration");
-        bdrv_op_block_all(bs, bmds->blocker);
-        bdrv_ref(bs);
+        drive_get_ref(drive_get_by_blockdev(bs));
+        bdrv_set_in_use(bs, 1);
 
         block_mig_state.total_sector_sum += sectors;
 
         if (bmds->shared_base) {
-            DPRINTF("Start migration for %s with shared base image\n",
-                    bs->device_name);
+            monitor_printf(mon, "Start migration for %s with shared base "
+                                "image\n",
+                           bs->device_name);
         } else {
-            DPRINTF("Start full migration for %s\n", bs->device_name);
+            monitor_printf(mon, "Start full migration for %s\n",
+                           bs->device_name);
         }
 
         QSIMPLEQ_INSERT_TAIL(&block_mig_state.bmds_list, bmds, entry);
     }
 }
 
-static void init_blk_migration(QEMUFile *f)
+static void init_blk_migration(Monitor *mon, QEMUFile *f)
 {
     block_mig_state.submitted = 0;
     block_mig_state.read_done = 0;
@@ -387,14 +323,13 @@ static void init_blk_migration(QEMUFile *f)
     block_mig_state.total_sector_sum = 0;
     block_mig_state.prev_progress = -1;
     block_mig_state.bulk_completed = 0;
-    block_mig_state.zero_blocks = migrate_zero_blocks();
+    block_mig_state.total_time = 0;
+    block_mig_state.reads = 0;
 
-    bdrv_iterate(init_blk_migration_it, NULL);
+    bdrv_iterate(init_blk_migration_it, mon);
 }
 
-/* Called with no lock taken.  */
-
-static int blk_mig_save_bulked_block(QEMUFile *f)
+static int blk_mig_save_bulked_block(Monitor *mon, QEMUFile *f)
 {
     int64_t completed_sector_sum = 0;
     BlkMigDevState *bmds;
@@ -403,7 +338,7 @@ static int blk_mig_save_bulked_block(QEMUFile *f)
 
     QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
         if (bmds->bulk_completed == 0) {
-            if (mig_save_device_bulk(f, bmds) == 1) {
+            if (mig_save_device_bulk(mon, f, bmds) == 1) {
                 /* completed bulk section for this device */
                 bmds->bulk_completed = 1;
             }
@@ -425,7 +360,8 @@ static int blk_mig_save_bulked_block(QEMUFile *f)
         block_mig_state.prev_progress = progress;
         qemu_put_be64(f, (progress << BDRV_SECTOR_BITS)
                          | BLK_MIG_FLAG_PROGRESS);
-        DPRINTF("Completed %d %%\r", progress);
+        monitor_printf(mon, "Completed %d %%\r", progress);
+        monitor_flush(mon);
     }
 
     return ret;
@@ -440,10 +376,8 @@ static void blk_mig_reset_dirty_cursor(void)
     }
 }
 
-/* Called with iothread lock taken.  */
-
-static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
-                                 int is_async)
+static int mig_save_device_dirty(Monitor *mon, QEMUFile *f,
+                                 BlkMigDevState *bmds, int is_async)
 {
     BlkMigBlock *blk;
     int64_t total_sectors = bmds->total_sectors;
@@ -452,14 +386,10 @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
     int ret = -EIO;
 
     for (sector = bmds->cur_dirty; sector < bmds->total_sectors;) {
-        blk_mig_lock();
         if (bmds_aio_inflight(bmds, sector)) {
-            blk_mig_unlock();
-            bdrv_drain_all();
-        } else {
-            blk_mig_unlock();
+            qemu_aio_flush();
         }
-        if (bdrv_get_dirty(bmds->bs, bmds->dirty_bitmap, sector)) {
+        if (bdrv_get_dirty(bmds->bs, sector)) {
 
             if (total_sectors - sector < BDRV_SECTORS_PER_DIRTY_CHUNK) {
                 nr_sectors = total_sectors - sector;
@@ -477,13 +407,17 @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
                 blk->iov.iov_len = nr_sectors * BDRV_SECTOR_SIZE;
                 qemu_iovec_init_external(&blk->qiov, &blk->iov, 1);
 
+                if (block_mig_state.submitted == 0) {
+                    block_mig_state.prev_time_offset = qemu_get_clock_ns(rt_clock);
+                }
+
                 blk->aiocb = bdrv_aio_readv(bmds->bs, sector, &blk->qiov,
                                             nr_sectors, blk_mig_read_cb, blk);
-
-                blk_mig_lock();
+                if (!blk->aiocb) {
+                    goto error;
+                }
                 block_mig_state.submitted++;
                 bmds_set_aio_inflight(bmds, sector, nr_sectors, 1);
-                blk_mig_unlock();
             } else {
                 ret = bdrv_read(bmds->bs, sector, blk->buf, nr_sectors);
                 if (ret < 0) {
@@ -505,26 +439,21 @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
     return (bmds->cur_dirty >= bmds->total_sectors);
 
 error:
-    DPRINTF("Error reading sector %" PRId64 "\n", sector);
+    monitor_printf(mon, "Error reading sector %" PRId64 "\n", sector);
+    qemu_file_set_error(f, ret);
     g_free(blk->buf);
     g_free(blk);
-    return ret;
+    return 0;
 }
 
-/* Called with iothread lock taken.
- *
- * return value:
- * 0: too much data for max_downtime
- * 1: few enough data for max_downtime
-*/
-static int blk_mig_save_dirty_block(QEMUFile *f, int is_async)
+static int blk_mig_save_dirty_block(Monitor *mon, QEMUFile *f, int is_async)
 {
     BlkMigDevState *bmds;
-    int ret = 1;
+    int ret = 0;
 
     QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
-        ret = mig_save_device_dirty(f, bmds, is_async);
-        if (ret <= 0) {
+        if (mig_save_device_dirty(mon, f, bmds, is_async) == 0) {
+            ret = 1;
             break;
         }
     }
@@ -532,32 +461,25 @@ static int blk_mig_save_dirty_block(QEMUFile *f, int is_async)
     return ret;
 }
 
-/* Called with no locks taken.  */
-
-static int flush_blks(QEMUFile *f)
+static void flush_blks(QEMUFile* f)
 {
     BlkMigBlock *blk;
-    int ret = 0;
 
     DPRINTF("%s Enter submitted %d read_done %d transferred %d\n",
             __FUNCTION__, block_mig_state.submitted, block_mig_state.read_done,
             block_mig_state.transferred);
 
-    blk_mig_lock();
     while ((blk = QSIMPLEQ_FIRST(&block_mig_state.blk_list)) != NULL) {
         if (qemu_file_rate_limit(f)) {
             break;
         }
         if (blk->ret < 0) {
-            ret = blk->ret;
+            qemu_file_set_error(f, blk->ret);
             break;
         }
+        blk_send(f, blk);
 
         QSIMPLEQ_REMOVE_HEAD(&block_mig_state.blk_list, entry);
-        blk_mig_unlock();
-        blk_send(f, blk);
-        blk_mig_lock();
-
         g_free(blk->buf);
         g_free(blk);
 
@@ -565,45 +487,61 @@ static int flush_blks(QEMUFile *f)
         block_mig_state.transferred++;
         assert(block_mig_state.read_done >= 0);
     }
-    blk_mig_unlock();
 
     DPRINTF("%s Exit submitted %d read_done %d transferred %d\n", __FUNCTION__,
             block_mig_state.submitted, block_mig_state.read_done,
             block_mig_state.transferred);
-    return ret;
 }
 
-/* Called with iothread lock taken.  */
-
 static int64_t get_remaining_dirty(void)
 {
     BlkMigDevState *bmds;
     int64_t dirty = 0;
 
     QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
-        dirty += bdrv_get_dirty_count(bmds->bs, bmds->dirty_bitmap);
+        dirty += bdrv_get_dirty_count(bmds->bs);
     }
 
-    return dirty << BDRV_SECTOR_BITS;
+    return dirty * BLOCK_SIZE;
 }
 
-/* Called with iothread lock taken.  */
+static int is_stage2_completed(void)
+{
+    int64_t remaining_dirty;
+    long double bwidth;
 
-static void blk_mig_cleanup(void)
+    if (block_mig_state.bulk_completed == 1) {
+
+        remaining_dirty = get_remaining_dirty();
+        if (remaining_dirty == 0) {
+            return 1;
+        }
+
+        bwidth = compute_read_bwidth();
+
+        if ((remaining_dirty / bwidth) <=
+            migrate_max_downtime()) {
+            /* finish stage2 because we think that we can finish remaining work
+               below max_downtime */
+
+            return 1;
+        }
+    }
+
+    return 0;
+}
+
+static void blk_mig_cleanup(Monitor *mon)
 {
     BlkMigDevState *bmds;
     BlkMigBlock *blk;
 
-    bdrv_drain_all();
+    set_dirty_tracking(0);
 
-    unset_dirty_tracking();
-
-    blk_mig_lock();
     while ((bmds = QSIMPLEQ_FIRST(&block_mig_state.bmds_list)) != NULL) {
         QSIMPLEQ_REMOVE_HEAD(&block_mig_state.bmds_list, entry);
-        bdrv_op_unblock_all(bmds->bs, bmds->blocker);
-        error_free(bmds->blocker);
-        bdrv_unref(bmds->bs);
+        bdrv_set_in_use(bmds->bs, 0);
+        drive_put_ref(drive_get_by_blockdev(bmds->bs));
         g_free(bmds->aio_bitmap);
         g_free(bmds);
     }
@@ -613,157 +551,95 @@ static void blk_mig_cleanup(void)
         g_free(blk->buf);
         g_free(blk);
     }
-    blk_mig_unlock();
+
+    monitor_printf(mon, "\n");
 }
 
-static void block_migration_cancel(void *opaque)
-{
-    blk_mig_cleanup();
-}
-
-static int block_save_setup(QEMUFile *f, void *opaque)
+static int block_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
 {
     int ret;
 
-    DPRINTF("Enter save live setup submitted %d transferred %d\n",
-            block_mig_state.submitted, block_mig_state.transferred);
+    DPRINTF("Enter save live stage %d submitted %d transferred %d\n",
+            stage, block_mig_state.submitted, block_mig_state.transferred);
 
-    qemu_mutex_lock_iothread();
-    init_blk_migration(f);
-
-    /* start track dirty blocks */
-    ret = set_dirty_tracking();
-
-    if (ret) {
-        qemu_mutex_unlock_iothread();
-        return ret;
+    if (stage < 0) {
+        blk_mig_cleanup(mon);
+        return 0;
     }
 
-    qemu_mutex_unlock_iothread();
+    if (block_mig_state.blk_enable != 1) {
+        /* no need to migrate storage */
+        qemu_put_be64(f, BLK_MIG_FLAG_EOS);
+        return 1;
+    }
 
-    ret = flush_blks(f);
-    blk_mig_reset_dirty_cursor();
-    qemu_put_be64(f, BLK_MIG_FLAG_EOS);
+    if (stage == 1) {
+        init_blk_migration(mon, f);
 
-    return ret;
-}
+        /* start track dirty blocks */
+        set_dirty_tracking(1);
+    }
 
-static int block_save_iterate(QEMUFile *f, void *opaque)
-{
-    int ret;
-    int64_t last_ftell = qemu_ftell(f);
+    flush_blks(f);
 
-    DPRINTF("Enter save live iterate submitted %d transferred %d\n",
-            block_mig_state.submitted, block_mig_state.transferred);
-
-    ret = flush_blks(f);
+    ret = qemu_file_get_error(f);
     if (ret) {
+        blk_mig_cleanup(mon);
         return ret;
     }
 
     blk_mig_reset_dirty_cursor();
 
-    /* control the rate of transfer */
-    blk_mig_lock();
-    while ((block_mig_state.submitted +
-            block_mig_state.read_done) * BLOCK_SIZE <
-           qemu_file_get_rate_limit(f)) {
-        blk_mig_unlock();
-        if (block_mig_state.bulk_completed == 0) {
-            /* first finish the bulk phase */
-            if (blk_mig_save_bulked_block(f) == 0) {
-                /* finished saving bulk on all devices */
-                block_mig_state.bulk_completed = 1;
+    if (stage == 2) {
+        /* control the rate of transfer */
+        while ((block_mig_state.submitted +
+                block_mig_state.read_done) * BLOCK_SIZE <
+               qemu_file_get_rate_limit(f)) {
+            if (block_mig_state.bulk_completed == 0) {
+                /* first finish the bulk phase */
+                if (blk_mig_save_bulked_block(mon, f) == 0) {
+                    /* finished saving bulk on all devices */
+                    block_mig_state.bulk_completed = 1;
+                }
+            } else {
+                if (blk_mig_save_dirty_block(mon, f, 1) == 0) {
+                    /* no more dirty blocks */
+                    break;
+                }
             }
-            ret = 0;
-        } else {
-            /* Always called with iothread lock taken for
-             * simplicity, block_save_complete also calls it.
-             */
-            qemu_mutex_lock_iothread();
-            ret = blk_mig_save_dirty_block(f, 1);
-            qemu_mutex_unlock_iothread();
         }
-        if (ret < 0) {
+
+        flush_blks(f);
+
+        ret = qemu_file_get_error(f);
+        if (ret) {
+            blk_mig_cleanup(mon);
             return ret;
         }
-        blk_mig_lock();
-        if (ret != 0) {
-            /* no more dirty blocks */
-            break;
-        }
     }
-    blk_mig_unlock();
 
-    ret = flush_blks(f);
-    if (ret) {
-        return ret;
+    if (stage == 3) {
+        /* we know for sure that save bulk is completed and
+           all async read completed */
+        assert(block_mig_state.submitted == 0);
+
+        while (blk_mig_save_dirty_block(mon, f, 0) != 0);
+        blk_mig_cleanup(mon);
+
+        /* report completion */
+        qemu_put_be64(f, (100 << BDRV_SECTOR_BITS) | BLK_MIG_FLAG_PROGRESS);
+
+        ret = qemu_file_get_error(f);
+        if (ret) {
+            return ret;
+        }
+
+        monitor_printf(mon, "Block migration completed\n");
     }
 
     qemu_put_be64(f, BLK_MIG_FLAG_EOS);
-    return qemu_ftell(f) - last_ftell;
-}
 
-/* Called with iothread lock taken.  */
-
-static int block_save_complete(QEMUFile *f, void *opaque)
-{
-    int ret;
-
-    DPRINTF("Enter save live complete submitted %d transferred %d\n",
-            block_mig_state.submitted, block_mig_state.transferred);
-
-    ret = flush_blks(f);
-    if (ret) {
-        return ret;
-    }
-
-    blk_mig_reset_dirty_cursor();
-
-    /* we know for sure that save bulk is completed and
-       all async read completed */
-    blk_mig_lock();
-    assert(block_mig_state.submitted == 0);
-    blk_mig_unlock();
-
-    do {
-        ret = blk_mig_save_dirty_block(f, 0);
-        if (ret < 0) {
-            return ret;
-        }
-    } while (ret == 0);
-
-    /* report completion */
-    qemu_put_be64(f, (100 << BDRV_SECTOR_BITS) | BLK_MIG_FLAG_PROGRESS);
-
-    DPRINTF("Block migration completed\n");
-
-    qemu_put_be64(f, BLK_MIG_FLAG_EOS);
-
-    blk_mig_cleanup();
-    return 0;
-}
-
-static uint64_t block_save_pending(QEMUFile *f, void *opaque, uint64_t max_size)
-{
-    /* Estimate pending number of bytes to send */
-    uint64_t pending;
-
-    qemu_mutex_lock_iothread();
-    blk_mig_lock();
-    pending = get_remaining_dirty() +
-                       block_mig_state.submitted * BLOCK_SIZE +
-                       block_mig_state.read_done * BLOCK_SIZE;
-
-    /* Report at least one block pending during bulk phase */
-    if (pending == 0 && !block_mig_state.bulk_completed) {
-        pending = BLOCK_SIZE;
-    }
-    blk_mig_unlock();
-    qemu_mutex_unlock_iothread();
-
-    DPRINTF("Enter save live pending  %" PRIu64 "\n", pending);
-    return pending;
+    return ((stage == 2) && is_stage2_completed());
 }
 
 static int block_load(QEMUFile *f, void *opaque, int version_id)
@@ -813,16 +689,12 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
                 nr_sectors = BDRV_SECTORS_PER_DIRTY_CHUNK;
             }
 
-            if (flags & BLK_MIG_FLAG_ZERO_BLOCK) {
-                ret = bdrv_write_zeroes(bs, addr, nr_sectors,
-                                        BDRV_REQ_MAY_UNMAP);
-            } else {
-                buf = g_malloc(BLOCK_SIZE);
-                qemu_get_buffer(f, buf, BLOCK_SIZE);
-                ret = bdrv_write(bs, addr, buf, nr_sectors);
-                g_free(buf);
-            }
+            buf = g_malloc(BLOCK_SIZE);
 
+            qemu_get_buffer(f, buf, BLOCK_SIZE);
+            ret = bdrv_write(bs, addr, buf, nr_sectors);
+
+            g_free(buf);
             if (ret < 0) {
                 return ret;
             }
@@ -835,7 +707,7 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
                    (addr == 100) ? '\n' : '\r');
             fflush(stdout);
         } else if (!(flags & BLK_MIG_FLAG_EOS)) {
-            fprintf(stderr, "Unknown block migration flags: %#x\n", flags);
+            fprintf(stderr, "Unknown flags\n");
             return -EINVAL;
         }
         ret = qemu_file_get_error(f);
@@ -847,37 +719,20 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
     return 0;
 }
 
-static void block_set_params(const MigrationParams *params, void *opaque)
+static void block_set_params(int blk_enable, int shared_base, void *opaque)
 {
-    block_mig_state.blk_enable = params->blk;
-    block_mig_state.shared_base = params->shared;
+    block_mig_state.blk_enable = blk_enable;
+    block_mig_state.shared_base = shared_base;
 
     /* shared base means that blk_enable = 1 */
-    block_mig_state.blk_enable |= params->shared;
+    block_mig_state.blk_enable |= shared_base;
 }
 
-static bool block_is_active(void *opaque)
-{
-    return block_mig_state.blk_enable == 1;
-}
-
-static SaveVMHandlers savevm_block_handlers = {
-    .set_params = block_set_params,
-    .save_live_setup = block_save_setup,
-    .save_live_iterate = block_save_iterate,
-    .save_live_complete = block_save_complete,
-    .save_live_pending = block_save_pending,
-    .load_state = block_load,
-    .cancel = block_migration_cancel,
-    .is_active = block_is_active,
-};
-
 void blk_mig_init(void)
 {
     QSIMPLEQ_INIT(&block_mig_state.bmds_list);
     QSIMPLEQ_INIT(&block_mig_state.blk_list);
-    qemu_mutex_init(&block_mig_state.lock);
 
-    register_savevm_live(NULL, "block", 0, 1, &savevm_block_handlers,
-                         &block_mig_state);
+    register_savevm_live(NULL, "block", 0, 1, block_set_params,
+                         block_save_live, NULL, block_load, &block_mig_state);
 }

block.h

@@ -0,0 +1,418 @@
+#ifndef BLOCK_H
+#define BLOCK_H
+
+#include "qemu-aio.h"
+#include "qemu-common.h"
+#include "qemu-option.h"
+#include "qemu-coroutine.h"
+#include "qobject.h"
+
+/* block.c */
+typedef struct BlockDriver BlockDriver;
+
+typedef struct BlockDriverInfo {
+    /* in bytes, 0 if irrelevant */
+    int cluster_size;
+    /* offset at which the VM state can be saved (0 if not possible) */
+    int64_t vm_state_offset;
+} BlockDriverInfo;
+
+typedef struct QEMUSnapshotInfo {
+    char id_str[128]; /* unique snapshot id */
+    /* the following fields are informative. They are not needed for
+       the consistency of the snapshot */
+    char name[256]; /* user choosen name */
+    uint32_t vm_state_size; /* VM state info size */
+    uint32_t date_sec; /* UTC date of the snapshot */
+    uint32_t date_nsec;
+    uint64_t vm_clock_nsec; /* VM clock relative to boot */
+} QEMUSnapshotInfo;
+
+/* Callbacks for block device models */
+typedef struct BlockDevOps {
+    /*
+     * Runs when virtual media changed (monitor commands eject, change)
+     * Argument load is true on load and false on eject.
+     * Beware: doesn't run when a host device's physical media
+     * changes.  Sure would be useful if it did.
+     * Device models with removable media must implement this callback.
+     */
+    void (*change_media_cb)(void *opaque, bool load);
+    /*
+     * Runs when an eject request is issued from the monitor, the tray
+     * is closed, and the medium is locked.
+     * Device models that do not implement is_medium_locked will not need
+     * this callback.  Device models that can lock the medium or tray might
+     * want to implement the callback and unlock the tray when "force" is
+     * true, even if they do not support eject requests.
+     */
+    void (*eject_request_cb)(void *opaque, bool force);
+    /*
+     * Is the virtual tray open?
+     * Device models implement this only when the device has a tray.
+     */
+    bool (*is_tray_open)(void *opaque);
+    /*
+     * Is the virtual medium locked into the device?
+     * Device models implement this only when device has such a lock.
+     */
+    bool (*is_medium_locked)(void *opaque);
+    /*
+     * Runs when the size changed (e.g. monitor command block_resize)
+     */
+    void (*resize_cb)(void *opaque);
+} BlockDevOps;
+
+#define BDRV_O_RDWR        0x0002
+#define BDRV_O_SNAPSHOT    0x0008 /* open the file read only and save writes in a snapshot */
+#define BDRV_O_NOCACHE     0x0020 /* do not use the host page cache */
+#define BDRV_O_CACHE_WB    0x0040 /* use write-back caching */
+#define BDRV_O_NATIVE_AIO  0x0080 /* use native AIO instead of the thread pool */
+#define BDRV_O_NO_BACKING  0x0100 /* don't open the backing file */
+#define BDRV_O_NO_FLUSH    0x0200 /* disable flushing on this disk */
+
+#define BDRV_O_CACHE_MASK  (BDRV_O_NOCACHE | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH)
+
+#define BDRV_SECTOR_BITS   9
+#define BDRV_SECTOR_SIZE   (1ULL << BDRV_SECTOR_BITS)
+#define BDRV_SECTOR_MASK   ~(BDRV_SECTOR_SIZE - 1)
+
+typedef enum {
+    BLOCK_ERR_REPORT, BLOCK_ERR_IGNORE, BLOCK_ERR_STOP_ENOSPC,
+    BLOCK_ERR_STOP_ANY
+} BlockErrorAction;
+
+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);
+void bdrv_info(Monitor *mon, QObject **ret_data);
+void bdrv_stats_print(Monitor *mon, const QObject *data);
+void bdrv_info_stats(Monitor *mon, QObject **ret_data);
+
+void bdrv_init(void);
+void bdrv_init_with_whitelist(void);
+BlockDriver *bdrv_find_protocol(const char *filename);
+BlockDriver *bdrv_find_format(const char *format_name);
+BlockDriver *bdrv_find_whitelisted_format(const char *format_name);
+int bdrv_create(BlockDriver *drv, const char* filename,
+    QEMUOptionParameter *options);
+int bdrv_create_file(const char* filename, QEMUOptionParameter *options);
+BlockDriverState *bdrv_new(const char *device_name);
+void bdrv_make_anon(BlockDriverState *bs);
+void bdrv_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_read(BlockDriverState *bs, int64_t sector_num,
+              uint8_t *buf, int nb_sectors);
+int bdrv_write(BlockDriverState *bs, int64_t sector_num,
+               const uint8_t *buf, int nb_sectors);
+int bdrv_pread(BlockDriverState *bs, int64_t offset,
+               void *buf, int count);
+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_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);
+void bdrv_commit_all(void);
+int bdrv_change_backing_file(BlockDriverState *bs,
+    const char *backing_file, const char *backing_fmt);
+void bdrv_register(BlockDriver *bdrv);
+
+
+typedef struct BdrvCheckResult {
+    int corruptions;
+    int leaks;
+    int check_errors;
+} BdrvCheckResult;
+
+int bdrv_check(BlockDriverState *bs, BdrvCheckResult *res);
+
+/* async block I/O */
+typedef struct BlockDriverAIOCB BlockDriverAIOCB;
+typedef void BlockDriverCompletionFunc(void *opaque, int ret);
+typedef void BlockDriverDirtyHandler(BlockDriverState *bs, int64_t sector,
+                                     int sector_num);
+BlockDriverAIOCB *bdrv_aio_readv(BlockDriverState *bs, int64_t sector_num,
+                                 QEMUIOVector *iov, int nb_sectors,
+                                 BlockDriverCompletionFunc *cb, void *opaque);
+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);
+void bdrv_aio_cancel(BlockDriverAIOCB *acb);
+
+typedef struct BlockRequest {
+    /* Fields to be filled by multiwrite caller */
+    int64_t sector;
+    int nb_sectors;
+    QEMUIOVector *qiov;
+    BlockDriverCompletionFunc *cb;
+    void *opaque;
+
+    /* Filled by multiwrite implementation */
+    int error;
+} BlockRequest;
+
+int bdrv_aio_multiwrite(BlockDriverState *bs, BlockRequest *reqs,
+    int num_reqs);
+
+/* sg packet commands */
+int bdrv_ioctl(BlockDriverState *bs, unsigned long int req, void *buf);
+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_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);
+
+#define BIOS_ATA_TRANSLATION_AUTO   0
+#define BIOS_ATA_TRANSLATION_NONE   1
+#define BIOS_ATA_TRANSLATION_LBA    2
+#define BIOS_ATA_TRANSLATION_LARGE  3
+#define BIOS_ATA_TRANSLATION_RECHS  4
+
+void bdrv_set_geometry_hint(BlockDriverState *bs,
+                            int cyls, int heads, int secs);
+void bdrv_set_translation_hint(BlockDriverState *bs, int translation);
+void bdrv_get_geometry_hint(BlockDriverState *bs,
+                            int *pcyls, int *pheads, int *psecs);
+typedef enum FDriveType {
+    FDRIVE_DRV_144  = 0x00,   /* 1.44 MB 3"5 drive      */
+    FDRIVE_DRV_288  = 0x01,   /* 2.88 MB 3"5 drive      */
+    FDRIVE_DRV_120  = 0x02,   /* 1.2  MB 5"25 drive     */
+    FDRIVE_DRV_NONE = 0x03,   /* No drive connected     */
+} FDriveType;
+
+void bdrv_get_floppy_geometry_hint(BlockDriverState *bs, int *nb_heads,
+                                   int *max_track, int *last_sect,
+                                   FDriveType drive_in, FDriveType *drive);
+int bdrv_get_translation_hint(BlockDriverState *bs);
+void bdrv_set_on_error(BlockDriverState *bs, BlockErrorAction on_read_error,
+                       BlockErrorAction on_write_error);
+BlockErrorAction bdrv_get_on_error(BlockDriverState *bs, int is_read);
+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);
+void bdrv_get_format(BlockDriverState *bs, char *buf, int buf_size);
+BlockDriverState *bdrv_find(const char *name);
+BlockDriverState *bdrv_next(BlockDriverState *bs);
+void bdrv_iterate(void (*it)(void *opaque, BlockDriverState *bs),
+                  void *opaque);
+int bdrv_is_encrypted(BlockDriverState *bs);
+int bdrv_key_required(BlockDriverState *bs);
+int bdrv_set_key(BlockDriverState *bs, const char *key);
+int bdrv_query_missing_keys(void);
+void bdrv_iterate_format(void (*it)(void *opaque, const char *name),
+                         void *opaque);
+const char *bdrv_get_device_name(BlockDriverState *bs);
+int bdrv_write_compressed(BlockDriverState *bs, int64_t sector_num,
+                          const uint8_t *buf, int nb_sectors);
+int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi);
+
+const char *bdrv_get_encrypted_filename(BlockDriverState *bs);
+void bdrv_get_backing_filename(BlockDriverState *bs,
+                               char *filename, int filename_size);
+int bdrv_can_snapshot(BlockDriverState *bs);
+int bdrv_is_snapshot(BlockDriverState *bs);
+BlockDriverState *bdrv_snapshots(void);
+int bdrv_snapshot_create(BlockDriverState *bs,
+                         QEMUSnapshotInfo *sn_info);
+int bdrv_snapshot_goto(BlockDriverState *bs,
+                       const char *snapshot_id);
+int bdrv_snapshot_delete(BlockDriverState *bs, const char *snapshot_id);
+int bdrv_snapshot_list(BlockDriverState *bs,
+                       QEMUSnapshotInfo **psn_info);
+int bdrv_snapshot_load_tmp(BlockDriverState *bs,
+                           const char *snapshot_name);
+char *bdrv_snapshot_dump(char *buf, int buf_size, QEMUSnapshotInfo *sn);
+
+char *get_human_readable_size(char *buf, int buf_size, int64_t size);
+int path_is_absolute(const char *path);
+void path_combine(char *dest, int dest_size,
+                  const char *base_path,
+                  const char *filename);
+
+int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
+                      int64_t pos, int size);
+
+int bdrv_load_vmstate(BlockDriverState *bs, uint8_t *buf,
+                      int64_t pos, int size);
+
+int bdrv_img_create(const char *filename, const char *fmt,
+                    const char *base_filename, const char *base_fmt,
+                    char *options, uint64_t img_size, int flags);
+
+void bdrv_set_buffer_alignment(BlockDriverState *bs, int align);
+void *qemu_blockalign(BlockDriverState *bs, size_t size);
+
+#define BDRV_SECTORS_PER_DIRTY_CHUNK 2048
+
+void bdrv_set_dirty_tracking(BlockDriverState *bs, int enable);
+int bdrv_get_dirty(BlockDriverState *bs, int64_t sector);
+void bdrv_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,
+
+    BLKDBG_L1_GROW_ALLOC_TABLE,
+    BLKDBG_L1_GROW_WRITE_TABLE,
+    BLKDBG_L1_GROW_ACTIVATE_TABLE,
+
+    BLKDBG_L2_LOAD,
+    BLKDBG_L2_UPDATE,
+    BLKDBG_L2_UPDATE_COMPRESSED,
+    BLKDBG_L2_ALLOC_COW_READ,
+    BLKDBG_L2_ALLOC_WRITE,
+
+    BLKDBG_READ,
+    BLKDBG_READ_AIO,
+    BLKDBG_READ_BACKING,
+    BLKDBG_READ_BACKING_AIO,
+    BLKDBG_READ_COMPRESSED,
+
+    BLKDBG_WRITE_AIO,
+    BLKDBG_WRITE_COMPRESSED,
+
+    BLKDBG_VMSTATE_LOAD,
+    BLKDBG_VMSTATE_SAVE,
+
+    BLKDBG_COW_READ,
+    BLKDBG_COW_WRITE,
+
+    BLKDBG_REFTABLE_LOAD,
+    BLKDBG_REFTABLE_GROW,
+
+    BLKDBG_REFBLOCK_LOAD,
+    BLKDBG_REFBLOCK_UPDATE,
+    BLKDBG_REFBLOCK_UPDATE_PART,
+    BLKDBG_REFBLOCK_ALLOC,
+    BLKDBG_REFBLOCK_ALLOC_HOOKUP,
+    BLKDBG_REFBLOCK_ALLOC_WRITE,
+    BLKDBG_REFBLOCK_ALLOC_WRITE_BLOCKS,
+    BLKDBG_REFBLOCK_ALLOC_WRITE_TABLE,
+    BLKDBG_REFBLOCK_ALLOC_SWITCH_TABLE,
+
+    BLKDBG_CLUSTER_ALLOC,
+    BLKDBG_CLUSTER_ALLOC_BYTES,
+    BLKDBG_CLUSTER_FREE,
+
+    BLKDBG_EVENT_MAX,
+} BlkDebugEvent;
+
+#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/Makefile.objs

@@ -1,39 +0,0 @@
-block-obj-y += raw_bsd.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o
-block-obj-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
-block-obj-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
-block-obj-y += qed-check.o
-block-obj-$(CONFIG_VHDX) += vhdx.o vhdx-endian.o vhdx-log.o
-block-obj-$(CONFIG_QUORUM) += quorum.o
-block-obj-y += parallels.o blkdebug.o blkverify.o
-block-obj-y += snapshot.o qapi.o
-block-obj-$(CONFIG_WIN32) += raw-win32.o win32-aio.o
-block-obj-$(CONFIG_POSIX) += raw-posix.o
-block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
-
-ifeq ($(CONFIG_POSIX),y)
-block-obj-y += nbd.o nbd-client.o sheepdog.o
-block-obj-$(CONFIG_LIBISCSI) += iscsi.o
-block-obj-$(CONFIG_LIBNFS) += nfs.o
-block-obj-$(CONFIG_CURL) += curl.o
-block-obj-$(CONFIG_RBD) += rbd.o
-block-obj-$(CONFIG_GLUSTERFS) += gluster.o
-block-obj-$(CONFIG_LIBSSH2) += ssh.o
-endif
-
-common-obj-y += stream.o
-common-obj-y += commit.o
-common-obj-y += mirror.o
-common-obj-y += backup.o
-
-iscsi.o-cflags     := $(LIBISCSI_CFLAGS)
-iscsi.o-libs       := $(LIBISCSI_LIBS)
-curl.o-cflags      := $(CURL_CFLAGS)
-curl.o-libs        := $(CURL_LIBS)
-rbd.o-cflags       := $(RBD_CFLAGS)
-rbd.o-libs         := $(RBD_LIBS)
-gluster.o-cflags   := $(GLUSTERFS_CFLAGS)
-gluster.o-libs     := $(GLUSTERFS_LIBS)
-ssh.o-cflags       := $(LIBSSH2_CFLAGS)
-ssh.o-libs         := $(LIBSSH2_LIBS)
-qcow.o-libs        := -lz
-linux-aio.o-libs   := -laio

block/backup.c

@@ -1,392 +0,0 @@
-/*
- * QEMU backup
- *
- * Copyright (C) 2013 Proxmox Server Solutions
- *
- * Authors:
- *  Dietmar Maurer (dietmar@proxmox.com)
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- *
- */
-
-#include <stdio.h>
-#include <errno.h>
-#include <unistd.h>
-
-#include "trace.h"
-#include "block/block.h"
-#include "block/block_int.h"
-#include "block/blockjob.h"
-#include "qemu/ratelimit.h"
-
-#define BACKUP_CLUSTER_BITS 16
-#define BACKUP_CLUSTER_SIZE (1 << BACKUP_CLUSTER_BITS)
-#define BACKUP_SECTORS_PER_CLUSTER (BACKUP_CLUSTER_SIZE / BDRV_SECTOR_SIZE)
-
-#define SLICE_TIME 100000000ULL /* ns */
-
-typedef struct CowRequest {
-    int64_t start;
-    int64_t end;
-    QLIST_ENTRY(CowRequest) list;
-    CoQueue wait_queue; /* coroutines blocked on this request */
-} CowRequest;
-
-typedef struct BackupBlockJob {
-    BlockJob common;
-    BlockDriverState *target;
-    MirrorSyncMode sync_mode;
-    RateLimit limit;
-    BlockdevOnError on_source_error;
-    BlockdevOnError on_target_error;
-    CoRwlock flush_rwlock;
-    uint64_t sectors_read;
-    HBitmap *bitmap;
-    QLIST_HEAD(, CowRequest) inflight_reqs;
-} BackupBlockJob;
-
-/* See if in-flight requests overlap and wait for them to complete */
-static void coroutine_fn wait_for_overlapping_requests(BackupBlockJob *job,
-                                                       int64_t start,
-                                                       int64_t end)
-{
-    CowRequest *req;
-    bool retry;
-
-    do {
-        retry = false;
-        QLIST_FOREACH(req, &job->inflight_reqs, list) {
-            if (end > req->start && start < req->end) {
-                qemu_co_queue_wait(&req->wait_queue);
-                retry = true;
-                break;
-            }
-        }
-    } while (retry);
-}
-
-/* Keep track of an in-flight request */
-static void cow_request_begin(CowRequest *req, BackupBlockJob *job,
-                                     int64_t start, int64_t end)
-{
-    req->start = start;
-    req->end = end;
-    qemu_co_queue_init(&req->wait_queue);
-    QLIST_INSERT_HEAD(&job->inflight_reqs, req, list);
-}
-
-/* Forget about a completed request */
-static void cow_request_end(CowRequest *req)
-{
-    QLIST_REMOVE(req, list);
-    qemu_co_queue_restart_all(&req->wait_queue);
-}
-
-static int coroutine_fn backup_do_cow(BlockDriverState *bs,
-                                      int64_t sector_num, int nb_sectors,
-                                      bool *error_is_read)
-{
-    BackupBlockJob *job = (BackupBlockJob *)bs->job;
-    CowRequest cow_request;
-    struct iovec iov;
-    QEMUIOVector bounce_qiov;
-    void *bounce_buffer = NULL;
-    int ret = 0;
-    int64_t start, end;
-    int n;
-
-    qemu_co_rwlock_rdlock(&job->flush_rwlock);
-
-    start = sector_num / BACKUP_SECTORS_PER_CLUSTER;
-    end = DIV_ROUND_UP(sector_num + nb_sectors, BACKUP_SECTORS_PER_CLUSTER);
-
-    trace_backup_do_cow_enter(job, start, sector_num, nb_sectors);
-
-    wait_for_overlapping_requests(job, start, end);
-    cow_request_begin(&cow_request, job, start, end);
-
-    for (; start < end; start++) {
-        if (hbitmap_get(job->bitmap, start)) {
-            trace_backup_do_cow_skip(job, start);
-            continue; /* already copied */
-        }
-
-        trace_backup_do_cow_process(job, start);
-
-        n = MIN(BACKUP_SECTORS_PER_CLUSTER,
-                job->common.len / BDRV_SECTOR_SIZE -
-                start * BACKUP_SECTORS_PER_CLUSTER);
-
-        if (!bounce_buffer) {
-            bounce_buffer = qemu_blockalign(bs, BACKUP_CLUSTER_SIZE);
-        }
-        iov.iov_base = bounce_buffer;
-        iov.iov_len = n * BDRV_SECTOR_SIZE;
-        qemu_iovec_init_external(&bounce_qiov, &iov, 1);
-
-        ret = bdrv_co_readv(bs, start * BACKUP_SECTORS_PER_CLUSTER, n,
-                            &bounce_qiov);
-        if (ret < 0) {
-            trace_backup_do_cow_read_fail(job, start, ret);
-            if (error_is_read) {
-                *error_is_read = true;
-            }
-            goto out;
-        }
-
-        if (buffer_is_zero(iov.iov_base, iov.iov_len)) {
-            ret = bdrv_co_write_zeroes(job->target,
-                                       start * BACKUP_SECTORS_PER_CLUSTER,
-                                       n, BDRV_REQ_MAY_UNMAP);
-        } else {
-            ret = bdrv_co_writev(job->target,
-                                 start * BACKUP_SECTORS_PER_CLUSTER, n,
-                                 &bounce_qiov);
-        }
-        if (ret < 0) {
-            trace_backup_do_cow_write_fail(job, start, ret);
-            if (error_is_read) {
-                *error_is_read = false;
-            }
-            goto out;
-        }
-
-        hbitmap_set(job->bitmap, start, 1);
-
-        /* Publish progress, guest I/O counts as progress too.  Note that the
-         * offset field is an opaque progress value, it is not a disk offset.
-         */
-        job->sectors_read += n;
-        job->common.offset += n * BDRV_SECTOR_SIZE;
-    }
-
-out:
-    if (bounce_buffer) {
-        qemu_vfree(bounce_buffer);
-    }
-
-    cow_request_end(&cow_request);
-
-    trace_backup_do_cow_return(job, sector_num, nb_sectors, ret);
-
-    qemu_co_rwlock_unlock(&job->flush_rwlock);
-
-    return ret;
-}
-
-static int coroutine_fn backup_before_write_notify(
-        NotifierWithReturn *notifier,
-        void *opaque)
-{
-    BdrvTrackedRequest *req = opaque;
-    int64_t sector_num = req->offset >> BDRV_SECTOR_BITS;
-    int nb_sectors = req->bytes >> BDRV_SECTOR_BITS;
-
-    assert((req->offset & (BDRV_SECTOR_SIZE - 1)) == 0);
-    assert((req->bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
-
-    return backup_do_cow(req->bs, sector_num, nb_sectors, NULL);
-}
-
-static void backup_set_speed(BlockJob *job, int64_t speed, Error **errp)
-{
-    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
-
-    if (speed < 0) {
-        error_set(errp, QERR_INVALID_PARAMETER, "speed");
-        return;
-    }
-    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
-}
-
-static void backup_iostatus_reset(BlockJob *job)
-{
-    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
-
-    bdrv_iostatus_reset(s->target);
-}
-
-static const BlockJobDriver backup_job_driver = {
-    .instance_size  = sizeof(BackupBlockJob),
-    .job_type       = BLOCK_JOB_TYPE_BACKUP,
-    .set_speed      = backup_set_speed,
-    .iostatus_reset = backup_iostatus_reset,
-};
-
-static BlockErrorAction backup_error_action(BackupBlockJob *job,
-                                            bool read, int error)
-{
-    if (read) {
-        return block_job_error_action(&job->common, job->common.bs,
-                                      job->on_source_error, true, error);
-    } else {
-        return block_job_error_action(&job->common, job->target,
-                                      job->on_target_error, false, error);
-    }
-}
-
-static void coroutine_fn backup_run(void *opaque)
-{
-    BackupBlockJob *job = opaque;
-    BlockDriverState *bs = job->common.bs;
-    BlockDriverState *target = job->target;
-    BlockdevOnError on_target_error = job->on_target_error;
-    NotifierWithReturn before_write = {
-        .notify = backup_before_write_notify,
-    };
-    int64_t start, end;
-    int ret = 0;
-
-    QLIST_INIT(&job->inflight_reqs);
-    qemu_co_rwlock_init(&job->flush_rwlock);
-
-    start = 0;
-    end = DIV_ROUND_UP(job->common.len / BDRV_SECTOR_SIZE,
-                       BACKUP_SECTORS_PER_CLUSTER);
-
-    job->bitmap = hbitmap_alloc(end, 0);
-
-    bdrv_set_enable_write_cache(target, true);
-    bdrv_set_on_error(target, on_target_error, on_target_error);
-    bdrv_iostatus_enable(target);
-
-    bdrv_add_before_write_notifier(bs, &before_write);
-
-    if (job->sync_mode == MIRROR_SYNC_MODE_NONE) {
-        while (!block_job_is_cancelled(&job->common)) {
-            /* Yield until the job is cancelled.  We just let our before_write
-             * notify callback service CoW requests. */
-            job->common.busy = false;
-            qemu_coroutine_yield();
-            job->common.busy = true;
-        }
-    } else {
-        /* Both FULL and TOP SYNC_MODE's require copying.. */
-        for (; start < end; start++) {
-            bool error_is_read;
-
-            if (block_job_is_cancelled(&job->common)) {
-                break;
-            }
-
-            /* we need to yield so that qemu_aio_flush() returns.
-             * (without, VM does not reboot)
-             */
-            if (job->common.speed) {
-                uint64_t delay_ns = ratelimit_calculate_delay(
-                        &job->limit, job->sectors_read);
-                job->sectors_read = 0;
-                block_job_sleep_ns(&job->common, QEMU_CLOCK_REALTIME, delay_ns);
-            } else {
-                block_job_sleep_ns(&job->common, QEMU_CLOCK_REALTIME, 0);
-            }
-
-            if (block_job_is_cancelled(&job->common)) {
-                break;
-            }
-
-            if (job->sync_mode == MIRROR_SYNC_MODE_TOP) {
-                int i, n;
-                int alloced = 0;
-
-                /* Check to see if these blocks are already in the
-                 * backing file. */
-
-                for (i = 0; i < BACKUP_SECTORS_PER_CLUSTER;) {
-                    /* bdrv_is_allocated() only returns true/false based
-                     * on the first set of sectors it comes across that
-                     * are are all in the same state.
-                     * For that reason we must verify each sector in the
-                     * backup cluster length.  We end up copying more than
-                     * needed but at some point that is always the case. */
-                    alloced =
-                        bdrv_is_allocated(bs,
-                                start * BACKUP_SECTORS_PER_CLUSTER + i,
-                                BACKUP_SECTORS_PER_CLUSTER - i, &n);
-                    i += n;
-
-                    if (alloced == 1 || n == 0) {
-                        break;
-                    }
-                }
-
-                /* If the above loop never found any sectors that are in
-                 * the topmost image, skip this backup. */
-                if (alloced == 0) {
-                    continue;
-                }
-            }
-            /* FULL sync mode we copy the whole drive. */
-            ret = backup_do_cow(bs, start * BACKUP_SECTORS_PER_CLUSTER,
-                    BACKUP_SECTORS_PER_CLUSTER, &error_is_read);
-            if (ret < 0) {
-                /* Depending on error action, fail now or retry cluster */
-                BlockErrorAction action =
-                    backup_error_action(job, error_is_read, -ret);
-                if (action == BLOCK_ERROR_ACTION_REPORT) {
-                    break;
-                } else {
-                    start--;
-                    continue;
-                }
-            }
-        }
-    }
-
-    notifier_with_return_remove(&before_write);
-
-    /* wait until pending backup_do_cow() calls have completed */
-    qemu_co_rwlock_wrlock(&job->flush_rwlock);
-    qemu_co_rwlock_unlock(&job->flush_rwlock);
-
-    hbitmap_free(job->bitmap);
-
-    bdrv_iostatus_disable(target);
-    bdrv_unref(target);
-
-    block_job_completed(&job->common, ret);
-}
-
-void backup_start(BlockDriverState *bs, BlockDriverState *target,
-                  int64_t speed, MirrorSyncMode sync_mode,
-                  BlockdevOnError on_source_error,
-                  BlockdevOnError on_target_error,
-                  BlockDriverCompletionFunc *cb, void *opaque,
-                  Error **errp)
-{
-    int64_t len;
-
-    assert(bs);
-    assert(target);
-    assert(cb);
-
-    if ((on_source_error == BLOCKDEV_ON_ERROR_STOP ||
-         on_source_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        !bdrv_iostatus_is_enabled(bs)) {
-        error_set(errp, QERR_INVALID_PARAMETER, "on-source-error");
-        return;
-    }
-
-    len = bdrv_getlength(bs);
-    if (len < 0) {
-        error_setg_errno(errp, -len, "unable to get length for '%s'",
-                         bdrv_get_device_name(bs));
-        return;
-    }
-
-    BackupBlockJob *job = block_job_create(&backup_job_driver, bs, speed,
-                                           cb, opaque, errp);
-    if (!job) {
-        return;
-    }
-
-    job->on_source_error = on_source_error;
-    job->on_target_error = on_target_error;
-    job->target = target;
-    job->sync_mode = sync_mode;
-    job->common.len = len;
-    job->common.co = qemu_coroutine_create(backup_run);
-    qemu_coroutine_enter(job->common.co, job);
-}

block/blkdebug.c

@@ -23,17 +23,27 @@
  */
 
 #include "qemu-common.h"
-#include "qemu/config-file.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
+
+typedef struct BlkdebugVars {
+    int state;
+
+    /* If inject_errno != 0, an error is injected for requests */
+    int inject_errno;
+
+    /* Decides if all future requests fail (false) or only the next one and
+     * after the next request inject_errno is reset to 0 (true) */
+    bool inject_once;
+
+    /* Decides if aio_readv/writev fails right away (true) or returns an error
+     * return value only in the callback (false) */
+    bool inject_immediately;
+} BlkdebugVars;
 
 typedef struct BDRVBlkdebugState {
-    int state;
-    int new_state;
-
-    QLIST_HEAD(, BlkdebugRule) rules[BLKDBG_EVENT_MAX];
-    QSIMPLEQ_HEAD(, BlkdebugRule) active_rules;
-    QLIST_HEAD(, BlkdebugSuspendedReq) suspended_reqs;
+    BlkdebugVars vars;
+    QLIST_HEAD(list, BlkdebugRule) rules[BLKDBG_EVENT_MAX];
 } BDRVBlkdebugState;
 
 typedef struct BlkdebugAIOCB {
@@ -42,15 +52,9 @@ typedef struct BlkdebugAIOCB {
     int ret;
 } BlkdebugAIOCB;
 
-typedef struct BlkdebugSuspendedReq {
-    Coroutine *co;
-    char *tag;
-    QLIST_ENTRY(BlkdebugSuspendedReq) next;
-} BlkdebugSuspendedReq;
-
 static void blkdebug_aio_cancel(BlockDriverAIOCB *blockacb);
 
-static const AIOCBInfo blkdebug_aiocb_info = {
+static AIOPool blkdebug_aio_pool = {
     .aiocb_size = sizeof(BlkdebugAIOCB),
     .cancel     = blkdebug_aio_cancel,
 };
@@ -58,7 +62,6 @@ static const AIOCBInfo blkdebug_aiocb_info = {
 enum {
     ACTION_INJECT_ERROR,
     ACTION_SET_STATE,
-    ACTION_SUSPEND,
 };
 
 typedef struct BlkdebugRule {
@@ -70,17 +73,12 @@ typedef struct BlkdebugRule {
             int error;
             int immediately;
             int once;
-            int64_t sector;
         } inject;
         struct {
             int new_state;
         } set_state;
-        struct {
-            char *tag;
-        } suspend;
     } options;
     QLIST_ENTRY(BlkdebugRule) next;
-    QSIMPLEQ_ENTRY(BlkdebugRule) active_next;
 } BlkdebugRule;
 
 static QemuOptsList inject_error_opts = {
@@ -99,10 +97,6 @@ static QemuOptsList inject_error_opts = {
             .name = "errno",
             .type = QEMU_OPT_NUMBER,
         },
-        {
-            .name = "sector",
-            .type = QEMU_OPT_NUMBER,
-        },
         {
             .name = "once",
             .type = QEMU_OPT_BOOL,
@@ -153,7 +147,9 @@ static const char *event_names[BLKDBG_EVENT_MAX] = {
     [BLKDBG_L2_ALLOC_COW_READ]              = "l2_alloc.cow_read",
     [BLKDBG_L2_ALLOC_WRITE]                 = "l2_alloc.write",
 
+    [BLKDBG_READ]                           = "read",
     [BLKDBG_READ_AIO]                       = "read_aio",
+    [BLKDBG_READ_BACKING]                   = "read_backing",
     [BLKDBG_READ_BACKING_AIO]               = "read_backing_aio",
     [BLKDBG_READ_COMPRESSED]                = "read_compressed",
 
@@ -168,7 +164,6 @@ static const char *event_names[BLKDBG_EVENT_MAX] = {
 
     [BLKDBG_REFTABLE_LOAD]                  = "reftable_load",
     [BLKDBG_REFTABLE_GROW]                  = "reftable_grow",
-    [BLKDBG_REFTABLE_UPDATE]                = "reftable_update",
 
     [BLKDBG_REFBLOCK_LOAD]                  = "refblock_load",
     [BLKDBG_REFBLOCK_UPDATE]                = "refblock_update",
@@ -183,17 +178,6 @@ static const char *event_names[BLKDBG_EVENT_MAX] = {
     [BLKDBG_CLUSTER_ALLOC]                  = "cluster_alloc",
     [BLKDBG_CLUSTER_ALLOC_BYTES]            = "cluster_alloc_bytes",
     [BLKDBG_CLUSTER_FREE]                   = "cluster_free",
-
-    [BLKDBG_FLUSH_TO_OS]                    = "flush_to_os",
-    [BLKDBG_FLUSH_TO_DISK]                  = "flush_to_disk",
-
-    [BLKDBG_PWRITEV_RMW_HEAD]               = "pwritev_rmw.head",
-    [BLKDBG_PWRITEV_RMW_AFTER_HEAD]         = "pwritev_rmw.after_head",
-    [BLKDBG_PWRITEV_RMW_TAIL]               = "pwritev_rmw.tail",
-    [BLKDBG_PWRITEV_RMW_AFTER_TAIL]         = "pwritev_rmw.after_tail",
-    [BLKDBG_PWRITEV]                        = "pwritev",
-    [BLKDBG_PWRITEV_ZERO]                   = "pwritev_zero",
-    [BLKDBG_PWRITEV_DONE]                   = "pwritev_done",
 };
 
 static int get_event_by_name(const char *name, BlkDebugEvent *event)
@@ -244,18 +228,12 @@ static int add_rule(QemuOpts *opts, void *opaque)
         rule->options.inject.once  = qemu_opt_get_bool(opts, "once", 0);
         rule->options.inject.immediately =
             qemu_opt_get_bool(opts, "immediately", 0);
-        rule->options.inject.sector = qemu_opt_get_number(opts, "sector", -1);
         break;
 
     case ACTION_SET_STATE:
         rule->options.set_state.new_state =
             qemu_opt_get_number(opts, "new_state", 0);
         break;
-
-    case ACTION_SUSPEND:
-        rule->options.suspend.tag =
-            g_strdup(qemu_opt_get(opts, "tag"));
-        break;
     };
 
     /* Add the rule */
@@ -264,48 +242,19 @@ static int add_rule(QemuOpts *opts, void *opaque)
     return 0;
 }
 
-static void remove_rule(BlkdebugRule *rule)
+static int read_config(BDRVBlkdebugState *s, const char *filename)
 {
-    switch (rule->action) {
-    case ACTION_INJECT_ERROR:
-    case ACTION_SET_STATE:
-        break;
-    case ACTION_SUSPEND:
-        g_free(rule->options.suspend.tag);
-        break;
-    }
-
-    QLIST_REMOVE(rule, next);
-    g_free(rule);
-}
-
-static int read_config(BDRVBlkdebugState *s, const char *filename,
-                       QDict *options, Error **errp)
-{
-    FILE *f = NULL;
+    FILE *f;
     int ret;
     struct add_rule_data d;
-    Error *local_err = NULL;
 
-    if (filename) {
-        f = fopen(filename, "r");
-        if (f == NULL) {
-            error_setg_errno(errp, errno, "Could not read blkdebug config file");
-            return -errno;
-        }
-
-        ret = qemu_config_parse(f, config_groups, filename);
-        if (ret < 0) {
-            error_setg(errp, "Could not parse blkdebug config file");
-            ret = -EINVAL;
-            goto fail;
-        }
+    f = fopen(filename, "r");
+    if (f == NULL) {
+        return -errno;
     }
 
-    qemu_config_parse_qdict(options, config_groups, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        ret = -EINVAL;
+    ret = qemu_config_parse(f, config_groups, filename);
+    if (ret < 0) {
         goto fail;
     }
 
@@ -320,122 +269,48 @@ static int read_config(BDRVBlkdebugState *s, const char *filename,
 fail:
     qemu_opts_reset(&inject_error_opts);
     qemu_opts_reset(&set_state_opts);
-    if (f) {
-        fclose(f);
-    }
+    fclose(f);
     return ret;
 }
 
 /* Valid blkdebug filenames look like blkdebug:path/to/config:path/to/image */
-static void blkdebug_parse_filename(const char *filename, QDict *options,
-                                    Error **errp)
-{
-    const char *c;
-
-    /* Parse the blkdebug: prefix */
-    if (!strstart(filename, "blkdebug:", &filename)) {
-        /* There was no prefix; therefore, all options have to be already
-           present in the QDict (except for the filename) */
-        qdict_put(options, "x-image", qstring_from_str(filename));
-        return;
-    }
-
-    /* Parse config file path */
-    c = strchr(filename, ':');
-    if (c == NULL) {
-        error_setg(errp, "blkdebug requires both config file and image path");
-        return;
-    }
-
-    if (c != filename) {
-        QString *config_path;
-        config_path = qstring_from_substr(filename, 0, c - filename - 1);
-        qdict_put(options, "config", config_path);
-    }
-
-    /* TODO Allow multi-level nesting and set file.filename here */
-    filename = c + 1;
-    qdict_put(options, "x-image", qstring_from_str(filename));
-}
-
-static QemuOptsList runtime_opts = {
-    .name = "blkdebug",
-    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
-    .desc = {
-        {
-            .name = "config",
-            .type = QEMU_OPT_STRING,
-            .help = "Path to the configuration file",
-        },
-        {
-            .name = "x-image",
-            .type = QEMU_OPT_STRING,
-            .help = "[internal use only, will be removed]",
-        },
-        {
-            .name = "align",
-            .type = QEMU_OPT_SIZE,
-            .help = "Required alignment in bytes",
-        },
-        { /* end of list */ }
-    },
-};
-
-static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
-                         Error **errp)
+static int blkdebug_open(BlockDriverState *bs, const char *filename, int flags)
 {
     BDRVBlkdebugState *s = bs->opaque;
-    QemuOpts *opts;
-    Error *local_err = NULL;
-    const char *config;
-    uint64_t align;
     int ret;
+    char *config, *c;
 
-    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        ret = -EINVAL;
-        goto out;
+    /* Parse the blkdebug: prefix */
+    if (strncmp(filename, "blkdebug:", strlen("blkdebug:"))) {
+        return -EINVAL;
+    }
+    filename += strlen("blkdebug:");
+
+    /* Read rules from config file */
+    c = strchr(filename, ':');
+    if (c == NULL) {
+        return -EINVAL;
     }
 
-    /* Read rules from config file or command line options */
-    config = qemu_opt_get(opts, "config");
-    ret = read_config(s, config, options, errp);
-    if (ret) {
-        goto out;
+    config = strdup(filename);
+    config[c - filename] = '\0';
+    ret = read_config(s, config);
+    free(config);
+    if (ret < 0) {
+        return ret;
     }
+    filename = c + 1;
 
     /* Set initial state */
-    s->state = 1;
+    s->vars.state = 1;
 
     /* Open the backing file */
-    assert(bs->file == NULL);
-    ret = bdrv_open_image(&bs->file, qemu_opt_get(opts, "x-image"), options, "image",
-                          flags | BDRV_O_PROTOCOL, false, &local_err);
+    ret = bdrv_file_open(&bs->file, filename, flags);
     if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto out;
+        return ret;
     }
 
-    /* Set request alignment */
-    align = qemu_opt_get_size(opts, "align", bs->request_alignment);
-    if (align > 0 && align < INT_MAX && !(align & (align - 1))) {
-        bs->request_alignment = align;
-    } else {
-        error_setg(errp, "Invalid alignment");
-        ret = -EINVAL;
-        goto fail_unref;
-    }
-
-    ret = 0;
-    goto out;
-
-fail_unref:
-    bdrv_unref(bs->file);
-out:
-    qemu_opts_del(opts);
-    return ret;
+    return 0;
 }
 
 static void error_callback_bh(void *opaque)
@@ -449,33 +324,29 @@ static void error_callback_bh(void *opaque)
 static void blkdebug_aio_cancel(BlockDriverAIOCB *blockacb)
 {
     BlkdebugAIOCB *acb = container_of(blockacb, BlkdebugAIOCB, common);
-    if (acb->bh) {
-        qemu_bh_delete(acb->bh);
-        acb->bh = NULL;
-    }
     qemu_aio_release(acb);
 }
 
 static BlockDriverAIOCB *inject_error(BlockDriverState *bs,
-    BlockDriverCompletionFunc *cb, void *opaque, BlkdebugRule *rule)
+    BlockDriverCompletionFunc *cb, void *opaque)
 {
     BDRVBlkdebugState *s = bs->opaque;
-    int error = rule->options.inject.error;
+    int error = s->vars.inject_errno;
     struct BlkdebugAIOCB *acb;
     QEMUBH *bh;
 
-    if (rule->options.inject.once) {
-        QSIMPLEQ_INIT(&s->active_rules);
+    if (s->vars.inject_once) {
+        s->vars.inject_errno = 0;
     }
 
-    if (rule->options.inject.immediately) {
+    if (s->vars.inject_immediately) {
         return NULL;
     }
 
-    acb = qemu_aio_get(&blkdebug_aiocb_info, bs, cb, opaque);
+    acb = qemu_aio_get(&blkdebug_aio_pool, bs, cb, opaque);
     acb->ret = -error;
 
-    bh = aio_bh_new(bdrv_get_aio_context(bs), error_callback_bh, acb);
+    bh = qemu_bh_new(error_callback_bh, acb);
     acb->bh = bh;
     qemu_bh_schedule(bh);
 
@@ -487,21 +358,14 @@ static BlockDriverAIOCB *blkdebug_aio_readv(BlockDriverState *bs,
     BlockDriverCompletionFunc *cb, void *opaque)
 {
     BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugRule *rule = NULL;
 
-    QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
-        if (rule->options.inject.sector == -1 ||
-            (rule->options.inject.sector >= sector_num &&
-             rule->options.inject.sector < sector_num + nb_sectors)) {
-            break;
-        }
+    if (s->vars.inject_errno) {
+        return inject_error(bs, cb, opaque);
     }
 
-    if (rule && rule->options.inject.error) {
-        return inject_error(bs, cb, opaque, rule);
-    }
-
-    return bdrv_aio_readv(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
+    BlockDriverAIOCB *acb =
+        bdrv_aio_readv(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
+    return acb;
 }
 
 static BlockDriverAIOCB *blkdebug_aio_writev(BlockDriverState *bs,
@@ -509,24 +373,16 @@ static BlockDriverAIOCB *blkdebug_aio_writev(BlockDriverState *bs,
     BlockDriverCompletionFunc *cb, void *opaque)
 {
     BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugRule *rule = NULL;
 
-    QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
-        if (rule->options.inject.sector == -1 ||
-            (rule->options.inject.sector >= sector_num &&
-             rule->options.inject.sector < sector_num + nb_sectors)) {
-            break;
-        }
+    if (s->vars.inject_errno) {
+        return inject_error(bs, cb, opaque);
     }
 
-    if (rule && rule->options.inject.error) {
-        return inject_error(bs, cb, opaque, rule);
-    }
-
-    return bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
+    BlockDriverAIOCB *acb =
+        bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
+    return acb;
 }
 
-
 static void blkdebug_close(BlockDriverState *bs)
 {
     BDRVBlkdebugState *s = bs->opaque;
@@ -535,181 +391,70 @@ static void blkdebug_close(BlockDriverState *bs)
 
     for (i = 0; i < BLKDBG_EVENT_MAX; i++) {
         QLIST_FOREACH_SAFE(rule, &s->rules[i], next, next) {
-            remove_rule(rule);
+            QLIST_REMOVE(rule, next);
+            g_free(rule);
         }
     }
 }
 
-static void suspend_request(BlockDriverState *bs, BlkdebugRule *rule)
+static BlockDriverAIOCB *blkdebug_aio_flush(BlockDriverState *bs,
+    BlockDriverCompletionFunc *cb, void *opaque)
 {
-    BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugSuspendedReq r;
-
-    r = (BlkdebugSuspendedReq) {
-        .co         = qemu_coroutine_self(),
-        .tag        = g_strdup(rule->options.suspend.tag),
-    };
-
-    remove_rule(rule);
-    QLIST_INSERT_HEAD(&s->suspended_reqs, &r, next);
-
-    printf("blkdebug: Suspended request '%s'\n", r.tag);
-    qemu_coroutine_yield();
-    printf("blkdebug: Resuming request '%s'\n", r.tag);
-
-    QLIST_REMOVE(&r, next);
-    g_free(r.tag);
+    return bdrv_aio_flush(bs->file, cb, opaque);
 }
 
-static bool process_rule(BlockDriverState *bs, struct BlkdebugRule *rule,
-    bool injected)
+static void process_rule(BlockDriverState *bs, struct BlkdebugRule *rule,
+    BlkdebugVars *old_vars)
 {
     BDRVBlkdebugState *s = bs->opaque;
+    BlkdebugVars *vars = &s->vars;
 
     /* Only process rules for the current state */
-    if (rule->state && rule->state != s->state) {
-        return injected;
+    if (rule->state && rule->state != old_vars->state) {
+        return;
     }
 
     /* Take the action */
     switch (rule->action) {
     case ACTION_INJECT_ERROR:
-        if (!injected) {
-            QSIMPLEQ_INIT(&s->active_rules);
-            injected = true;
-        }
-        QSIMPLEQ_INSERT_HEAD(&s->active_rules, rule, active_next);
+        vars->inject_errno       = rule->options.inject.error;
+        vars->inject_once        = rule->options.inject.once;
+        vars->inject_immediately = rule->options.inject.immediately;
         break;
 
     case ACTION_SET_STATE:
-        s->new_state = rule->options.set_state.new_state;
-        break;
-
-    case ACTION_SUSPEND:
-        suspend_request(bs, rule);
+        vars->state              = rule->options.set_state.new_state;
         break;
     }
-    return injected;
 }
 
 static void blkdebug_debug_event(BlockDriverState *bs, BlkDebugEvent event)
 {
     BDRVBlkdebugState *s = bs->opaque;
-    struct BlkdebugRule *rule, *next;
-    bool injected;
+    struct BlkdebugRule *rule;
+    BlkdebugVars old_vars = s->vars;
 
     assert((int)event >= 0 && event < BLKDBG_EVENT_MAX);
 
-    injected = false;
-    s->new_state = s->state;
-    QLIST_FOREACH_SAFE(rule, &s->rules[event], next, next) {
-        injected = process_rule(bs, rule, injected);
+    QLIST_FOREACH(rule, &s->rules[event], next) {
+        process_rule(bs, rule, &old_vars);
     }
-    s->state = s->new_state;
-}
-
-static int blkdebug_debug_breakpoint(BlockDriverState *bs, const char *event,
-                                     const char *tag)
-{
-    BDRVBlkdebugState *s = bs->opaque;
-    struct BlkdebugRule *rule;
-    BlkDebugEvent blkdebug_event;
-
-    if (get_event_by_name(event, &blkdebug_event) < 0) {
-        return -ENOENT;
-    }
-
-
-    rule = g_malloc(sizeof(*rule));
-    *rule = (struct BlkdebugRule) {
-        .event  = blkdebug_event,
-        .action = ACTION_SUSPEND,
-        .state  = 0,
-        .options.suspend.tag = g_strdup(tag),
-    };
-
-    QLIST_INSERT_HEAD(&s->rules[blkdebug_event], rule, next);
-
-    return 0;
-}
-
-static int blkdebug_debug_resume(BlockDriverState *bs, const char *tag)
-{
-    BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugSuspendedReq *r, *next;
-
-    QLIST_FOREACH_SAFE(r, &s->suspended_reqs, next, next) {
-        if (!strcmp(r->tag, tag)) {
-            qemu_coroutine_enter(r->co, NULL);
-            return 0;
-        }
-    }
-    return -ENOENT;
-}
-
-static int blkdebug_debug_remove_breakpoint(BlockDriverState *bs,
-                                            const char *tag)
-{
-    BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugSuspendedReq *r, *r_next;
-    BlkdebugRule *rule, *next;
-    int i, ret = -ENOENT;
-
-    for (i = 0; i < BLKDBG_EVENT_MAX; i++) {
-        QLIST_FOREACH_SAFE(rule, &s->rules[i], next, next) {
-            if (rule->action == ACTION_SUSPEND &&
-                !strcmp(rule->options.suspend.tag, tag)) {
-                remove_rule(rule);
-                ret = 0;
-            }
-        }
-    }
-    QLIST_FOREACH_SAFE(r, &s->suspended_reqs, next, r_next) {
-        if (!strcmp(r->tag, tag)) {
-            qemu_coroutine_enter(r->co, NULL);
-            ret = 0;
-        }
-    }
-    return ret;
-}
-
-static bool blkdebug_debug_is_suspended(BlockDriverState *bs, const char *tag)
-{
-    BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugSuspendedReq *r;
-
-    QLIST_FOREACH(r, &s->suspended_reqs, next) {
-        if (!strcmp(r->tag, tag)) {
-            return true;
-        }
-    }
-    return false;
-}
-
-static int64_t blkdebug_getlength(BlockDriverState *bs)
-{
-    return bdrv_getlength(bs->file);
 }
 
 static BlockDriver bdrv_blkdebug = {
-    .format_name            = "blkdebug",
-    .protocol_name          = "blkdebug",
-    .instance_size          = sizeof(BDRVBlkdebugState),
+    .format_name        = "blkdebug",
+    .protocol_name      = "blkdebug",
 
-    .bdrv_parse_filename    = blkdebug_parse_filename,
-    .bdrv_file_open         = blkdebug_open,
-    .bdrv_close             = blkdebug_close,
-    .bdrv_getlength         = blkdebug_getlength,
+    .instance_size      = sizeof(BDRVBlkdebugState),
 
-    .bdrv_aio_readv         = blkdebug_aio_readv,
-    .bdrv_aio_writev        = blkdebug_aio_writev,
+    .bdrv_file_open     = blkdebug_open,
+    .bdrv_close         = blkdebug_close,
 
-    .bdrv_debug_event           = blkdebug_debug_event,
-    .bdrv_debug_breakpoint      = blkdebug_debug_breakpoint,
-    .bdrv_debug_remove_breakpoint
-                                = blkdebug_debug_remove_breakpoint,
-    .bdrv_debug_resume          = blkdebug_debug_resume,
-    .bdrv_debug_is_suspended    = blkdebug_debug_is_suspended,
+    .bdrv_aio_readv     = blkdebug_aio_readv,
+    .bdrv_aio_writev    = blkdebug_aio_writev,
+    .bdrv_aio_flush     = blkdebug_aio_flush,
+
+    .bdrv_debug_event   = blkdebug_debug_event,
 };
 
 static void bdrv_blkdebug_init(void)

block/blkverify.c

@@ -8,8 +8,8 @@
  */
 
 #include <stdarg.h>
-#include "qemu/sockets.h" /* for EINPROGRESS on Windows */
-#include "block/block_int.h"
+#include "qemu_socket.h" /* for EINPROGRESS on Windows */
+#include "block_int.h"
 
 typedef struct {
     BlockDriverState *test_file;
@@ -39,17 +39,16 @@ struct BlkverifyAIOCB {
 static void blkverify_aio_cancel(BlockDriverAIOCB *blockacb)
 {
     BlkverifyAIOCB *acb = (BlkverifyAIOCB *)blockacb;
-    AioContext *aio_context = bdrv_get_aio_context(blockacb->bs);
     bool finished = false;
 
     /* Wait until request completes, invokes its callback, and frees itself */
     acb->finished = &finished;
     while (!finished) {
-        aio_poll(aio_context, true);
+        qemu_aio_wait();
     }
 }
 
-static const AIOCBInfo blkverify_aiocb_info = {
+static AIOPool blkverify_aio_pool = {
     .aiocb_size         = sizeof(BlkverifyAIOCB),
     .cancel             = blkverify_aio_cancel,
 };
@@ -70,100 +69,50 @@ static void GCC_FMT_ATTR(2, 3) blkverify_err(BlkverifyAIOCB *acb,
 }
 
 /* Valid blkverify filenames look like blkverify:path/to/raw_image:path/to/image */
-static void blkverify_parse_filename(const char *filename, QDict *options,
-                                     Error **errp)
+static int blkverify_open(BlockDriverState *bs, const char *filename, int flags)
 {
-    const char *c;
-    QString *raw_path;
-
+    BDRVBlkverifyState *s = bs->opaque;
+    int ret;
+    char *raw, *c;
 
     /* Parse the blkverify: prefix */
-    if (!strstart(filename, "blkverify:", &filename)) {
-        /* There was no prefix; therefore, all options have to be already
-           present in the QDict (except for the filename) */
-        qdict_put(options, "x-image", qstring_from_str(filename));
-        return;
+    if (strncmp(filename, "blkverify:", strlen("blkverify:"))) {
+        return -EINVAL;
     }
+    filename += strlen("blkverify:");
 
     /* Parse the raw image filename */
     c = strchr(filename, ':');
     if (c == NULL) {
-        error_setg(errp, "blkverify requires raw copy and original image path");
-        return;
+        return -EINVAL;
     }
 
-    /* TODO Implement option pass-through and set raw.filename here */
-    raw_path = qstring_from_substr(filename, 0, c - filename - 1);
-    qdict_put(options, "x-raw", raw_path);
-
-    /* TODO Allow multi-level nesting and set file.filename here */
-    filename = c + 1;
-    qdict_put(options, "x-image", qstring_from_str(filename));
-}
-
-static QemuOptsList runtime_opts = {
-    .name = "blkverify",
-    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
-    .desc = {
-        {
-            .name = "x-raw",
-            .type = QEMU_OPT_STRING,
-            .help = "[internal use only, will be removed]",
-        },
-        {
-            .name = "x-image",
-            .type = QEMU_OPT_STRING,
-            .help = "[internal use only, will be removed]",
-        },
-        { /* end of list */ }
-    },
-};
-
-static int blkverify_open(BlockDriverState *bs, QDict *options, int flags,
-                          Error **errp)
-{
-    BDRVBlkverifyState *s = bs->opaque;
-    QemuOpts *opts;
-    Error *local_err = NULL;
-    int ret;
-
-    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    /* Open the raw file */
-    assert(bs->file == NULL);
-    ret = bdrv_open_image(&bs->file, qemu_opt_get(opts, "x-raw"), options,
-                          "raw", flags | BDRV_O_PROTOCOL, false, &local_err);
+    raw = strdup(filename);
+    raw[c - filename] = '\0';
+    ret = bdrv_file_open(&bs->file, raw, flags);
+    free(raw);
     if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto fail;
+        return ret;
     }
+    filename = c + 1;
 
     /* Open the test file */
-    assert(s->test_file == NULL);
-    ret = bdrv_open_image(&s->test_file, qemu_opt_get(opts, "x-image"), options,
-                          "test", flags, false, &local_err);
+    s->test_file = bdrv_new("");
+    ret = bdrv_open(s->test_file, filename, flags, NULL);
     if (ret < 0) {
-        error_propagate(errp, local_err);
+        bdrv_delete(s->test_file);
         s->test_file = NULL;
-        goto fail;
+        return ret;
     }
 
-    ret = 0;
-fail:
-    return ret;
+    return 0;
 }
 
 static void blkverify_close(BlockDriverState *bs)
 {
     BDRVBlkverifyState *s = bs->opaque;
 
-    bdrv_unref(s->test_file);
+    bdrv_delete(s->test_file);
     s->test_file = NULL;
 }
 
@@ -174,13 +123,117 @@ static int64_t blkverify_getlength(BlockDriverState *bs)
     return bdrv_getlength(s->test_file);
 }
 
+/**
+ * Check that I/O vector contents are identical
+ *
+ * @a:          I/O vector
+ * @b:          I/O vector
+ * @ret:        Offset to first mismatching byte or -1 if match
+ */
+static ssize_t blkverify_iovec_compare(QEMUIOVector *a, QEMUIOVector *b)
+{
+    int i;
+    ssize_t offset = 0;
+
+    assert(a->niov == b->niov);
+    for (i = 0; i < a->niov; i++) {
+        size_t len = 0;
+        uint8_t *p = (uint8_t *)a->iov[i].iov_base;
+        uint8_t *q = (uint8_t *)b->iov[i].iov_base;
+
+        assert(a->iov[i].iov_len == b->iov[i].iov_len);
+        while (len < a->iov[i].iov_len && *p++ == *q++) {
+            len++;
+        }
+
+        offset += len;
+
+        if (len != a->iov[i].iov_len) {
+            return offset;
+        }
+    }
+    return -1;
+}
+
+typedef struct {
+    int src_index;
+    struct iovec *src_iov;
+    void *dest_base;
+} IOVectorSortElem;
+
+static int sortelem_cmp_src_base(const void *a, const void *b)
+{
+    const IOVectorSortElem *elem_a = a;
+    const IOVectorSortElem *elem_b = b;
+
+    /* Don't overflow */
+    if (elem_a->src_iov->iov_base < elem_b->src_iov->iov_base) {
+        return -1;
+    } else if (elem_a->src_iov->iov_base > elem_b->src_iov->iov_base) {
+        return 1;
+    } else {
+        return 0;
+    }
+}
+
+static int sortelem_cmp_src_index(const void *a, const void *b)
+{
+    const IOVectorSortElem *elem_a = a;
+    const IOVectorSortElem *elem_b = b;
+
+    return elem_a->src_index - elem_b->src_index;
+}
+
+/**
+ * Copy contents of I/O vector
+ *
+ * The relative relationships of overlapping iovecs are preserved.  This is
+ * necessary to ensure identical semantics in the cloned I/O vector.
+ */
+static void blkverify_iovec_clone(QEMUIOVector *dest, const QEMUIOVector *src,
+                                  void *buf)
+{
+    IOVectorSortElem sortelems[src->niov];
+    void *last_end;
+    int i;
+
+    /* Sort by source iovecs by base address */
+    for (i = 0; i < src->niov; i++) {
+        sortelems[i].src_index = i;
+        sortelems[i].src_iov = &src->iov[i];
+    }
+    qsort(sortelems, src->niov, sizeof(sortelems[0]), sortelem_cmp_src_base);
+
+    /* Allocate buffer space taking into account overlapping iovecs */
+    last_end = NULL;
+    for (i = 0; i < src->niov; i++) {
+        struct iovec *cur = sortelems[i].src_iov;
+        ptrdiff_t rewind = 0;
+
+        /* Detect overlap */
+        if (last_end && last_end > cur->iov_base) {
+            rewind = last_end - cur->iov_base;
+        }
+
+        sortelems[i].dest_base = buf - rewind;
+        buf += cur->iov_len - MIN(rewind, cur->iov_len);
+        last_end = MAX(cur->iov_base + cur->iov_len, last_end);
+    }
+
+    /* Sort by source iovec index and build destination iovec */
+    qsort(sortelems, src->niov, sizeof(sortelems[0]), sortelem_cmp_src_index);
+    for (i = 0; i < src->niov; i++) {
+        qemu_iovec_add(dest, sortelems[i].dest_base, src->iov[i].iov_len);
+    }
+}
+
 static BlkverifyAIOCB *blkverify_aio_get(BlockDriverState *bs, bool is_write,
                                          int64_t sector_num, QEMUIOVector *qiov,
                                          int nb_sectors,
                                          BlockDriverCompletionFunc *cb,
                                          void *opaque)
 {
-    BlkverifyAIOCB *acb = qemu_aio_get(&blkverify_aiocb_info, bs, cb, opaque);
+    BlkverifyAIOCB *acb = qemu_aio_get(&blkverify_aio_pool, bs, cb, opaque);
 
     acb->bh = NULL;
     acb->is_write = is_write;
@@ -229,8 +282,7 @@ static void blkverify_aio_cb(void *opaque, int ret)
             acb->verify(acb);
         }
 
-        acb->bh = aio_bh_new(bdrv_get_aio_context(acb->common.bs),
-                             blkverify_aio_bh, acb);
+        acb->bh = qemu_bh_new(blkverify_aio_bh, acb);
         qemu_bh_schedule(acb->bh);
         break;
     }
@@ -238,7 +290,7 @@ static void blkverify_aio_cb(void *opaque, int ret)
 
 static void blkverify_verify_readv(BlkverifyAIOCB *acb)
 {
-    ssize_t offset = qemu_iovec_compare(acb->qiov, &acb->raw_qiov);
+    ssize_t offset = blkverify_iovec_compare(acb->qiov, &acb->raw_qiov);
     if (offset != -1) {
         blkverify_err(acb, "contents mismatch in sector %" PRId64,
                       acb->sector_num + (int64_t)(offset / BDRV_SECTOR_SIZE));
@@ -256,12 +308,16 @@ static BlockDriverAIOCB *blkverify_aio_readv(BlockDriverState *bs,
     acb->verify = blkverify_verify_readv;
     acb->buf = qemu_blockalign(bs->file, qiov->size);
     qemu_iovec_init(&acb->raw_qiov, acb->qiov->niov);
-    qemu_iovec_clone(&acb->raw_qiov, qiov, acb->buf);
+    blkverify_iovec_clone(&acb->raw_qiov, qiov, acb->buf);
 
-    bdrv_aio_readv(s->test_file, sector_num, qiov, nb_sectors,
-                   blkverify_aio_cb, acb);
-    bdrv_aio_readv(bs->file, sector_num, &acb->raw_qiov, nb_sectors,
-                   blkverify_aio_cb, acb);
+    if (!bdrv_aio_readv(s->test_file, sector_num, qiov, nb_sectors,
+                        blkverify_aio_cb, acb)) {
+        blkverify_aio_cb(acb, -EIO);
+    }
+    if (!bdrv_aio_readv(bs->file, sector_num, &acb->raw_qiov, nb_sectors,
+                        blkverify_aio_cb, acb)) {
+        blkverify_aio_cb(acb, -EIO);
+    }
     return &acb->common;
 }
 
@@ -273,10 +329,14 @@ static BlockDriverAIOCB *blkverify_aio_writev(BlockDriverState *bs,
     BlkverifyAIOCB *acb = blkverify_aio_get(bs, true, sector_num, qiov,
                                             nb_sectors, cb, opaque);
 
-    bdrv_aio_writev(s->test_file, sector_num, qiov, nb_sectors,
-                    blkverify_aio_cb, acb);
-    bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors,
-                    blkverify_aio_cb, acb);
+    if (!bdrv_aio_writev(s->test_file, sector_num, qiov, nb_sectors,
+                         blkverify_aio_cb, acb)) {
+        blkverify_aio_cb(acb, -EIO);
+    }
+    if (!bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors,
+                         blkverify_aio_cb, acb)) {
+        blkverify_aio_cb(acb, -EIO);
+    }
     return &acb->common;
 }
 
@@ -290,55 +350,20 @@ static BlockDriverAIOCB *blkverify_aio_flush(BlockDriverState *bs,
     return bdrv_aio_flush(s->test_file, cb, opaque);
 }
 
-static bool blkverify_recurse_is_first_non_filter(BlockDriverState *bs,
-                                                  BlockDriverState *candidate)
-{
-    BDRVBlkverifyState *s = bs->opaque;
-
-    bool perm = bdrv_recurse_is_first_non_filter(bs->file, candidate);
-
-    if (perm) {
-        return true;
-    }
-
-    return bdrv_recurse_is_first_non_filter(s->test_file, candidate);
-}
-
-/* Propagate AioContext changes to ->test_file */
-static void blkverify_detach_aio_context(BlockDriverState *bs)
-{
-    BDRVBlkverifyState *s = bs->opaque;
-
-    bdrv_detach_aio_context(s->test_file);
-}
-
-static void blkverify_attach_aio_context(BlockDriverState *bs,
-                                         AioContext *new_context)
-{
-    BDRVBlkverifyState *s = bs->opaque;
-
-    bdrv_attach_aio_context(s->test_file, new_context);
-}
-
 static BlockDriver bdrv_blkverify = {
-    .format_name                      = "blkverify",
-    .protocol_name                    = "blkverify",
-    .instance_size                    = sizeof(BDRVBlkverifyState),
+    .format_name        = "blkverify",
+    .protocol_name      = "blkverify",
 
-    .bdrv_parse_filename              = blkverify_parse_filename,
-    .bdrv_file_open                   = blkverify_open,
-    .bdrv_close                       = blkverify_close,
-    .bdrv_getlength                   = blkverify_getlength,
+    .instance_size      = sizeof(BDRVBlkverifyState),
 
-    .bdrv_aio_readv                   = blkverify_aio_readv,
-    .bdrv_aio_writev                  = blkverify_aio_writev,
-    .bdrv_aio_flush                   = blkverify_aio_flush,
+    .bdrv_getlength     = blkverify_getlength,
 
-    .bdrv_attach_aio_context          = blkverify_attach_aio_context,
-    .bdrv_detach_aio_context          = blkverify_detach_aio_context,
+    .bdrv_file_open     = blkverify_open,
+    .bdrv_close         = blkverify_close,
 
-    .is_filter                        = true,
-    .bdrv_recurse_is_first_non_filter = blkverify_recurse_is_first_non_filter,
+    .bdrv_aio_readv     = blkverify_aio_readv,
+    .bdrv_aio_writev    = blkverify_aio_writev,
+    .bdrv_aio_flush     = blkverify_aio_flush,
 };
 
 static void bdrv_blkverify_init(void)

block/bochs.c

@@ -23,8 +23,8 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
 
 /**************************************************************/
 
@@ -39,41 +39,56 @@
 // not allocated: 0xffffffff
 
 // always little-endian
-struct bochs_header {
-    char magic[32];     /* "Bochs Virtual HD Image" */
-    char type[16];      /* "Redolog" */
-    char subtype[16];   /* "Undoable" / "Volatile" / "Growing" */
+struct bochs_header_v1 {
+    char magic[32]; // "Bochs Virtual HD Image"
+    char type[16]; // "Redolog"
+    char subtype[16]; // "Undoable" / "Volatile" / "Growing"
     uint32_t version;
-    uint32_t header;    /* size of header */
-
-    uint32_t catalog;   /* num of entries */
-    uint32_t bitmap;    /* bitmap size */
-    uint32_t extent;    /* extent size */
+    uint32_t header; // size of header
 
     union {
-        struct {
-            uint32_t reserved;  /* for ??? */
-            uint64_t disk;      /* disk size */
-            char padding[HEADER_SIZE - 64 - 20 - 12];
-        } QEMU_PACKED redolog;
-        struct {
-            uint64_t disk;      /* disk size */
-            char padding[HEADER_SIZE - 64 - 20 - 8];
-        } QEMU_PACKED redolog_v1;
-        char padding[HEADER_SIZE - 64 - 20];
+	struct {
+	    uint32_t catalog; // num of entries
+	    uint32_t bitmap; // bitmap size
+	    uint32_t extent; // extent size
+	    uint64_t disk; // disk size
+	    char padding[HEADER_SIZE - 64 - 8 - 20];
+	} redolog;
+	char padding[HEADER_SIZE - 64 - 8];
     } extra;
-} QEMU_PACKED;
+};
+
+// always little-endian
+struct bochs_header {
+    char magic[32]; // "Bochs Virtual HD Image"
+    char type[16]; // "Redolog"
+    char subtype[16]; // "Undoable" / "Volatile" / "Growing"
+    uint32_t version;
+    uint32_t header; // size of header
+
+    union {
+	struct {
+	    uint32_t catalog; // num of entries
+	    uint32_t bitmap; // bitmap size
+	    uint32_t extent; // extent size
+	    uint32_t reserved; // for ???
+	    uint64_t disk; // disk size
+	    char padding[HEADER_SIZE - 64 - 8 - 24];
+	} redolog;
+	char padding[HEADER_SIZE - 64 - 8];
+    } extra;
+};
 
 typedef struct BDRVBochsState {
     CoMutex lock;
     uint32_t *catalog_bitmap;
-    uint32_t catalog_size;
+    int catalog_size;
 
-    uint32_t data_offset;
+    int data_offset;
 
-    uint32_t bitmap_blocks;
-    uint32_t extent_blocks;
-    uint32_t extent_size;
+    int bitmap_blocks;
+    int extent_blocks;
+    int extent_size;
 } BDRVBochsState;
 
 static int bochs_probe(const uint8_t *buf, int buf_size, const char *filename)
@@ -93,19 +108,17 @@ static int bochs_probe(const uint8_t *buf, int buf_size, const char *filename)
     return 0;
 }
 
-static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
-                      Error **errp)
+static int bochs_open(BlockDriverState *bs, int flags)
 {
     BDRVBochsState *s = bs->opaque;
-    uint32_t i;
+    int i;
     struct bochs_header bochs;
-    int ret;
+    struct bochs_header_v1 header_v1;
 
     bs->read_only = 1; // no write support yet
 
-    ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs));
-    if (ret < 0) {
-        return ret;
+    if (bdrv_pread(bs->file, 0, &bochs, sizeof(bochs)) != sizeof(bochs)) {
+        goto fail;
     }
 
     if (strcmp(bochs.magic, HEADER_MAGIC) ||
@@ -113,103 +126,63 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
         strcmp(bochs.subtype, GROWING_TYPE) ||
 	((le32_to_cpu(bochs.version) != HEADER_VERSION) &&
 	(le32_to_cpu(bochs.version) != HEADER_V1))) {
-        error_setg(errp, "Image not in Bochs format");
-        return -EINVAL;
-    }
-
-    if (le32_to_cpu(bochs.version) == HEADER_V1) {
-        bs->total_sectors = le64_to_cpu(bochs.extra.redolog_v1.disk) / 512;
-    } else {
-        bs->total_sectors = le64_to_cpu(bochs.extra.redolog.disk) / 512;
-    }
-
-    /* Limit to 1M entries to avoid unbounded allocation. This is what is
-     * needed for the largest image that bximage can create (~8 TB). */
-    s->catalog_size = le32_to_cpu(bochs.catalog);
-    if (s->catalog_size > 0x100000) {
-        error_setg(errp, "Catalog size is too large");
-        return -EFBIG;
-    }
-
-    s->catalog_bitmap = g_malloc(s->catalog_size * 4);
-
-    ret = bdrv_pread(bs->file, le32_to_cpu(bochs.header), s->catalog_bitmap,
-                     s->catalog_size * 4);
-    if (ret < 0) {
         goto fail;
     }
 
+    if (le32_to_cpu(bochs.version) == HEADER_V1) {
+      memcpy(&header_v1, &bochs, sizeof(bochs));
+      bs->total_sectors = le64_to_cpu(header_v1.extra.redolog.disk) / 512;
+    } else {
+      bs->total_sectors = le64_to_cpu(bochs.extra.redolog.disk) / 512;
+    }
+
+    s->catalog_size = le32_to_cpu(bochs.extra.redolog.catalog);
+    s->catalog_bitmap = g_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;
     for (i = 0; i < s->catalog_size; i++)
 	le32_to_cpus(&s->catalog_bitmap[i]);
 
     s->data_offset = le32_to_cpu(bochs.header) + (s->catalog_size * 4);
 
-    s->bitmap_blocks = 1 + (le32_to_cpu(bochs.bitmap) - 1) / 512;
-    s->extent_blocks = 1 + (le32_to_cpu(bochs.extent) - 1) / 512;
+    s->bitmap_blocks = 1 + (le32_to_cpu(bochs.extra.redolog.bitmap) - 1) / 512;
+    s->extent_blocks = 1 + (le32_to_cpu(bochs.extra.redolog.extent) - 1) / 512;
 
-    s->extent_size = le32_to_cpu(bochs.extent);
-    if (s->extent_size < BDRV_SECTOR_SIZE) {
-        /* bximage actually never creates extents smaller than 4k */
-        error_setg(errp, "Extent size must be at least 512");
-        ret = -EINVAL;
-        goto fail;
-    } else if (!is_power_of_2(s->extent_size)) {
-        error_setg(errp, "Extent size %" PRIu32 " is not a power of two",
-                   s->extent_size);
-        ret = -EINVAL;
-        goto fail;
-    } else if (s->extent_size > 0x800000) {
-        error_setg(errp, "Extent size %" PRIu32 " is too large",
-                   s->extent_size);
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    if (s->catalog_size < DIV_ROUND_UP(bs->total_sectors,
-                                       s->extent_size / BDRV_SECTOR_SIZE))
-    {
-        error_setg(errp, "Catalog size is too small for this disk size");
-        ret = -EINVAL;
-        goto fail;
-    }
+    s->extent_size = le32_to_cpu(bochs.extra.redolog.extent);
 
     qemu_co_mutex_init(&s->lock);
     return 0;
-
-fail:
-    g_free(s->catalog_bitmap);
-    return ret;
+ fail:
+    return -1;
 }
 
 static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)
 {
     BDRVBochsState *s = bs->opaque;
-    uint64_t offset = sector_num * 512;
-    uint64_t extent_index, extent_offset, bitmap_offset;
+    int64_t offset = sector_num * 512;
+    int64_t extent_index, extent_offset, bitmap_offset;
     char bitmap_entry;
-    int ret;
 
     // seek to sector
     extent_index = offset / s->extent_size;
     extent_offset = (offset % s->extent_size) / 512;
 
     if (s->catalog_bitmap[extent_index] == 0xffffffff) {
-	return 0; /* not allocated */
+	return -1; /* not allocated */
     }
 
-    bitmap_offset = s->data_offset +
-        (512 * (uint64_t) s->catalog_bitmap[extent_index] *
-        (s->extent_blocks + s->bitmap_blocks));
+    bitmap_offset = s->data_offset + (512 * s->catalog_bitmap[extent_index] *
+	(s->extent_blocks + s->bitmap_blocks));
 
     /* read in bitmap for current extent */
-    ret = bdrv_pread(bs->file, bitmap_offset + (extent_offset / 8),
-                     &bitmap_entry, 1);
-    if (ret < 0) {
-        return ret;
+    if (bdrv_pread(bs->file, bitmap_offset + (extent_offset / 8),
+                   &bitmap_entry, 1) != 1) {
+        return -1;
     }
 
     if (!((bitmap_entry >> (extent_offset % 8)) & 1)) {
-	return 0; /* not allocated */
+	return -1; /* not allocated */
     }
 
     return bitmap_offset + (512 * (s->bitmap_blocks + extent_offset));
@@ -222,16 +195,13 @@ static int bochs_read(BlockDriverState *bs, int64_t sector_num,
 
     while (nb_sectors > 0) {
         int64_t block_offset = seek_to_sector(bs, sector_num);
-        if (block_offset < 0) {
-            return block_offset;
-        } else if (block_offset > 0) {
+        if (block_offset >= 0) {
             ret = bdrv_pread(bs->file, block_offset, buf, 512);
-            if (ret < 0) {
-                return ret;
+            if (ret != 512) {
+                return -1;
             }
-        } else {
+        } else
             memset(buf, 0, 512);
-        }
         nb_sectors--;
         sector_num++;
         buf += 512;

block/cloop.c

@@ -22,13 +22,10 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
 #include <zlib.h>
 
-/* Maximum compressed block size */
-#define MAX_BLOCK_SIZE (64 * 1024 * 1024)
-
 typedef struct BDRVCloopState {
     CoMutex lock;
     uint32_t block_size;
@@ -56,104 +53,38 @@ static int cloop_probe(const uint8_t *buf, int buf_size, const char *filename)
     return 0;
 }
 
-static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
-                      Error **errp)
+static int cloop_open(BlockDriverState *bs, int flags)
 {
     BDRVCloopState *s = bs->opaque;
     uint32_t offsets_size, max_compressed_block_size = 1, i;
-    int ret;
 
     bs->read_only = 1;
 
     /* read header */
-    ret = bdrv_pread(bs->file, 128, &s->block_size, 4);
-    if (ret < 0) {
-        return ret;
+    if (bdrv_pread(bs->file, 128, &s->block_size, 4) < 4) {
+        goto cloop_close;
     }
     s->block_size = be32_to_cpu(s->block_size);
-    if (s->block_size % 512) {
-        error_setg(errp, "block_size %" PRIu32 " must be a multiple of 512",
-                   s->block_size);
-        return -EINVAL;
-    }
-    if (s->block_size == 0) {
-        error_setg(errp, "block_size cannot be zero");
-        return -EINVAL;
-    }
 
-    /* cloop's create_compressed_fs.c warns about block sizes beyond 256 KB but
-     * we can accept more.  Prevent ridiculous values like 4 GB - 1 since we
-     * need a buffer this big.
-     */
-    if (s->block_size > MAX_BLOCK_SIZE) {
-        error_setg(errp, "block_size %" PRIu32 " must be %u MB or less",
-                   s->block_size,
-                   MAX_BLOCK_SIZE / (1024 * 1024));
-        return -EINVAL;
-    }
-
-    ret = bdrv_pread(bs->file, 128 + 4, &s->n_blocks, 4);
-    if (ret < 0) {
-        return ret;
+    if (bdrv_pread(bs->file, 128 + 4, &s->n_blocks, 4) < 4) {
+        goto cloop_close;
     }
     s->n_blocks = be32_to_cpu(s->n_blocks);
 
     /* read offsets */
-    if (s->n_blocks > (UINT32_MAX - 1) / sizeof(uint64_t)) {
-        /* Prevent integer overflow */
-        error_setg(errp, "n_blocks %" PRIu32 " must be %zu or less",
-                   s->n_blocks,
-                   (UINT32_MAX - 1) / sizeof(uint64_t));
-        return -EINVAL;
-    }
-    offsets_size = (s->n_blocks + 1) * sizeof(uint64_t);
-    if (offsets_size > 512 * 1024 * 1024) {
-        /* Prevent ridiculous offsets_size which causes memory allocation to
-         * fail or overflows bdrv_pread() size.  In practice the 512 MB
-         * offsets[] limit supports 16 TB images at 256 KB block size.
-         */
-        error_setg(errp, "image requires too many offsets, "
-                   "try increasing block size");
-        return -EINVAL;
-    }
+    offsets_size = s->n_blocks * sizeof(uint64_t);
     s->offsets = g_malloc(offsets_size);
-
-    ret = bdrv_pread(bs->file, 128 + 4 + 4, s->offsets, offsets_size);
-    if (ret < 0) {
-        goto fail;
+    if (bdrv_pread(bs->file, 128 + 4 + 4, s->offsets, offsets_size) <
+            offsets_size) {
+        goto cloop_close;
     }
-
-    for (i = 0; i < s->n_blocks + 1; i++) {
-        uint64_t size;
-
+    for(i=0;i<s->n_blocks;i++) {
         s->offsets[i] = be64_to_cpu(s->offsets[i]);
-        if (i == 0) {
-            continue;
-        }
-
-        if (s->offsets[i] < s->offsets[i - 1]) {
-            error_setg(errp, "offsets not monotonically increasing at "
-                       "index %" PRIu32 ", image file is corrupt", i);
-            ret = -EINVAL;
-            goto fail;
-        }
-
-        size = s->offsets[i] - s->offsets[i - 1];
-
-        /* Compressed blocks should be smaller than the uncompressed block size
-         * but maybe compression performed poorly so the compressed block is
-         * actually bigger.  Clamp down on unrealistic values to prevent
-         * ridiculous s->compressed_block allocation.
-         */
-        if (size > 2 * MAX_BLOCK_SIZE) {
-            error_setg(errp, "invalid compressed block size at index %" PRIu32
-                       ", image file is corrupt", i);
-            ret = -EINVAL;
-            goto fail;
-        }
-
-        if (size > max_compressed_block_size) {
-            max_compressed_block_size = size;
+        if (i > 0) {
+            uint32_t size = s->offsets[i] - s->offsets[i - 1];
+            if (size > max_compressed_block_size) {
+                max_compressed_block_size = size;
+            }
         }
     }
 
@@ -161,8 +92,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
     s->compressed_block = g_malloc(max_compressed_block_size + 1);
     s->uncompressed_block = g_malloc(s->block_size);
     if (inflateInit(&s->zstream) != Z_OK) {
-        ret = -EINVAL;
-        goto fail;
+        goto cloop_close;
     }
     s->current_block = s->n_blocks;
 
@@ -171,11 +101,8 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
     qemu_co_mutex_init(&s->lock);
     return 0;
 
-fail:
-    g_free(s->offsets);
-    g_free(s->compressed_block);
-    g_free(s->uncompressed_block);
-    return ret;
+cloop_close:
+    return -1;
 }
 
 static inline int cloop_read_block(BlockDriverState *bs, int block_num)
@@ -243,7 +170,9 @@ static coroutine_fn int cloop_co_read(BlockDriverState *bs, int64_t sector_num,
 static void cloop_close(BlockDriverState *bs)
 {
     BDRVCloopState *s = bs->opaque;
-    g_free(s->offsets);
+    if (s->n_blocks > 0) {
+        g_free(s->offsets);
+    }
     g_free(s->compressed_block);
     g_free(s->uncompressed_block);
     inflateEnd(&s->zstream);

block/commit.c

@@ -1,255 +0,0 @@
-/*
- * Live block commit
- *
- * Copyright Red Hat, Inc. 2012
- *
- * Authors:
- *  Jeff Cody   <jcody@redhat.com>
- *  Based on stream.c by Stefan Hajnoczi
- *
- * This work is licensed under the terms of the GNU LGPL, version 2 or later.
- * See the COPYING.LIB file in the top-level directory.
- *
- */
-
-#include "trace.h"
-#include "block/block_int.h"
-#include "block/blockjob.h"
-#include "qemu/ratelimit.h"
-
-enum {
-    /*
-     * Size of data buffer for populating the image file.  This should be large
-     * enough to process multiple clusters in a single call, so that populating
-     * contiguous regions of the image is efficient.
-     */
-    COMMIT_BUFFER_SIZE = 512 * 1024, /* in bytes */
-};
-
-#define SLICE_TIME 100000000ULL /* ns */
-
-typedef struct CommitBlockJob {
-    BlockJob common;
-    RateLimit limit;
-    BlockDriverState *active;
-    BlockDriverState *top;
-    BlockDriverState *base;
-    BlockdevOnError on_error;
-    int base_flags;
-    int orig_overlay_flags;
-    char *backing_file_str;
-} CommitBlockJob;
-
-static int coroutine_fn commit_populate(BlockDriverState *bs,
-                                        BlockDriverState *base,
-                                        int64_t sector_num, int nb_sectors,
-                                        void *buf)
-{
-    int ret = 0;
-
-    ret = bdrv_read(bs, sector_num, buf, nb_sectors);
-    if (ret) {
-        return ret;
-    }
-
-    ret = bdrv_write(base, sector_num, buf, nb_sectors);
-    if (ret) {
-        return ret;
-    }
-
-    return 0;
-}
-
-static void coroutine_fn commit_run(void *opaque)
-{
-    CommitBlockJob *s = opaque;
-    BlockDriverState *active = s->active;
-    BlockDriverState *top = s->top;
-    BlockDriverState *base = s->base;
-    BlockDriverState *overlay_bs;
-    int64_t sector_num, end;
-    int ret = 0;
-    int n = 0;
-    void *buf;
-    int bytes_written = 0;
-    int64_t base_len;
-
-    ret = s->common.len = bdrv_getlength(top);
-
-
-    if (s->common.len < 0) {
-        goto exit_restore_reopen;
-    }
-
-    ret = base_len = bdrv_getlength(base);
-    if (base_len < 0) {
-        goto exit_restore_reopen;
-    }
-
-    if (base_len < s->common.len) {
-        ret = bdrv_truncate(base, s->common.len);
-        if (ret) {
-            goto exit_restore_reopen;
-        }
-    }
-
-    end = s->common.len >> BDRV_SECTOR_BITS;
-    buf = qemu_blockalign(top, COMMIT_BUFFER_SIZE);
-
-    for (sector_num = 0; sector_num < end; sector_num += n) {
-        uint64_t delay_ns = 0;
-        bool copy;
-
-wait:
-        /* Note that even when no rate limit is applied we need to yield
-         * with no pending I/O here so that bdrv_drain_all() returns.
-         */
-        block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, delay_ns);
-        if (block_job_is_cancelled(&s->common)) {
-            break;
-        }
-        /* Copy if allocated above the base */
-        ret = bdrv_is_allocated_above(top, base, sector_num,
-                                      COMMIT_BUFFER_SIZE / BDRV_SECTOR_SIZE,
-                                      &n);
-        copy = (ret == 1);
-        trace_commit_one_iteration(s, sector_num, n, ret);
-        if (copy) {
-            if (s->common.speed) {
-                delay_ns = ratelimit_calculate_delay(&s->limit, n);
-                if (delay_ns > 0) {
-                    goto wait;
-                }
-            }
-            ret = commit_populate(top, base, sector_num, n, buf);
-            bytes_written += n * BDRV_SECTOR_SIZE;
-        }
-        if (ret < 0) {
-            if (s->on_error == BLOCKDEV_ON_ERROR_STOP ||
-                s->on_error == BLOCKDEV_ON_ERROR_REPORT||
-                (s->on_error == BLOCKDEV_ON_ERROR_ENOSPC && ret == -ENOSPC)) {
-                goto exit_free_buf;
-            } else {
-                n = 0;
-                continue;
-            }
-        }
-        /* Publish progress */
-        s->common.offset += n * BDRV_SECTOR_SIZE;
-    }
-
-    ret = 0;
-
-    if (!block_job_is_cancelled(&s->common) && sector_num == end) {
-        /* success */
-        ret = bdrv_drop_intermediate(active, top, base, s->backing_file_str);
-    }
-
-exit_free_buf:
-    qemu_vfree(buf);
-
-exit_restore_reopen:
-    /* restore base open flags here if appropriate (e.g., change the base back
-     * to r/o). These reopens do not need to be atomic, since we won't abort
-     * even on failure here */
-    if (s->base_flags != bdrv_get_flags(base)) {
-        bdrv_reopen(base, s->base_flags, NULL);
-    }
-    overlay_bs = bdrv_find_overlay(active, top);
-    if (overlay_bs && s->orig_overlay_flags != bdrv_get_flags(overlay_bs)) {
-        bdrv_reopen(overlay_bs, s->orig_overlay_flags, NULL);
-    }
-    g_free(s->backing_file_str);
-    block_job_completed(&s->common, ret);
-}
-
-static void commit_set_speed(BlockJob *job, int64_t speed, Error **errp)
-{
-    CommitBlockJob *s = container_of(job, CommitBlockJob, common);
-
-    if (speed < 0) {
-        error_set(errp, QERR_INVALID_PARAMETER, "speed");
-        return;
-    }
-    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
-}
-
-static const BlockJobDriver commit_job_driver = {
-    .instance_size = sizeof(CommitBlockJob),
-    .job_type      = BLOCK_JOB_TYPE_COMMIT,
-    .set_speed     = commit_set_speed,
-};
-
-void commit_start(BlockDriverState *bs, BlockDriverState *base,
-                  BlockDriverState *top, int64_t speed,
-                  BlockdevOnError on_error, BlockDriverCompletionFunc *cb,
-                  void *opaque, const char *backing_file_str, Error **errp)
-{
-    CommitBlockJob *s;
-    BlockReopenQueue *reopen_queue = NULL;
-    int orig_overlay_flags;
-    int orig_base_flags;
-    BlockDriverState *overlay_bs;
-    Error *local_err = NULL;
-
-    if ((on_error == BLOCKDEV_ON_ERROR_STOP ||
-         on_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        !bdrv_iostatus_is_enabled(bs)) {
-        error_setg(errp, "Invalid parameter combination");
-        return;
-    }
-
-    assert(top != bs);
-    if (top == base) {
-        error_setg(errp, "Invalid files for merge: top and base are the same");
-        return;
-    }
-
-    overlay_bs = bdrv_find_overlay(bs, top);
-
-    if (overlay_bs == NULL) {
-        error_setg(errp, "Could not find overlay image for %s:", top->filename);
-        return;
-    }
-
-    orig_base_flags    = bdrv_get_flags(base);
-    orig_overlay_flags = bdrv_get_flags(overlay_bs);
-
-    /* convert base & overlay_bs to r/w, if necessary */
-    if (!(orig_base_flags & BDRV_O_RDWR)) {
-        reopen_queue = bdrv_reopen_queue(reopen_queue, base,
-                                         orig_base_flags | BDRV_O_RDWR);
-    }
-    if (!(orig_overlay_flags & BDRV_O_RDWR)) {
-        reopen_queue = bdrv_reopen_queue(reopen_queue, overlay_bs,
-                                         orig_overlay_flags | BDRV_O_RDWR);
-    }
-    if (reopen_queue) {
-        bdrv_reopen_multiple(reopen_queue, &local_err);
-        if (local_err != NULL) {
-            error_propagate(errp, local_err);
-            return;
-        }
-    }
-
-
-    s = block_job_create(&commit_job_driver, bs, speed, cb, opaque, errp);
-    if (!s) {
-        return;
-    }
-
-    s->base   = base;
-    s->top    = top;
-    s->active = bs;
-
-    s->base_flags          = orig_base_flags;
-    s->orig_overlay_flags  = orig_overlay_flags;
-
-    s->backing_file_str = g_strdup(backing_file_str);
-
-    s->on_error = on_error;
-    s->common.co = qemu_coroutine_create(commit_run);
-
-    trace_commit_start(bs, base, top, s, s->common.co, opaque);
-    qemu_coroutine_enter(s->common.co, s);
-}

block/cow.c

@@ -22,8 +22,8 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
 
 /**************************************************************/
 /* COW block driver using file system holes */
@@ -58,34 +58,21 @@ static int cow_probe(const uint8_t *buf, int buf_size, const char *filename)
         return 0;
 }
 
-static int cow_open(BlockDriverState *bs, QDict *options, int flags,
-                    Error **errp)
+static int cow_open(BlockDriverState *bs, int flags)
 {
     BDRVCowState *s = bs->opaque;
     struct cow_header_v2 cow_header;
     int bitmap_size;
     int64_t size;
-    int ret;
 
     /* see if it is a cow image */
-    ret = bdrv_pread(bs->file, 0, &cow_header, sizeof(cow_header));
-    if (ret < 0) {
+    if (bdrv_pread(bs->file, 0, &cow_header, sizeof(cow_header)) !=
+            sizeof(cow_header)) {
         goto fail;
     }
 
-    if (be32_to_cpu(cow_header.magic) != COW_MAGIC) {
-        error_setg(errp, "Image not in COW format");
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    if (be32_to_cpu(cow_header.version) != COW_VERSION) {
-        char version[64];
-        snprintf(version, sizeof(version),
-               "COW version %" PRIu32, cow_header.version);
-        error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
-            bs->device_name, "cow", version);
-        ret = -ENOTSUP;
+    if (be32_to_cpu(cow_header.magic) != COW_MAGIC ||
+        be32_to_cpu(cow_header.version) != COW_VERSION) {
         goto fail;
     }
 
@@ -101,180 +88,111 @@ static int cow_open(BlockDriverState *bs, QDict *options, int flags,
     qemu_co_mutex_init(&s->lock);
     return 0;
  fail:
-    return ret;
+    return -1;
 }
 
-static inline void cow_set_bits(uint8_t *bitmap, int start, int64_t nb_sectors)
+/*
+ * XXX(hch): right now these functions are extremly ineffcient.
+ * We should just read the whole bitmap we'll need in one go instead.
+ */
+static inline int cow_set_bit(BlockDriverState *bs, int64_t bitnum)
 {
-    int64_t bitnum = start, last = start + nb_sectors;
-    while (bitnum < last) {
-        if ((bitnum & 7) == 0 && bitnum + 8 <= last) {
-            bitmap[bitnum / 8] = 0xFF;
-            bitnum += 8;
-            continue;
-        }
-        bitmap[bitnum/8] |= (1 << (bitnum % 8));
-        bitnum++;
+    uint64_t offset = sizeof(struct cow_header_v2) + bitnum / 8;
+    uint8_t bitmap;
+    int ret;
+
+    ret = bdrv_pread(bs->file, offset, &bitmap, sizeof(bitmap));
+    if (ret < 0) {
+       return ret;
     }
-}
 
-#define BITS_PER_BITMAP_SECTOR (512 * 8)
+    bitmap |= (1 << (bitnum % 8));
 
-/* Cannot use bitmap.c on big-endian machines.  */
-static int cow_test_bit(int64_t bitnum, const uint8_t *bitmap)
-{
-    return (bitmap[bitnum / 8] & (1 << (bitnum & 7))) != 0;
-}
-
-static int cow_find_streak(const uint8_t *bitmap, int value, int start, int nb_sectors)
-{
-    int streak_value = value ? 0xFF : 0;
-    int last = MIN(start + nb_sectors, BITS_PER_BITMAP_SECTOR);
-    int bitnum = start;
-    while (bitnum < last) {
-        if ((bitnum & 7) == 0 && bitmap[bitnum / 8] == streak_value) {
-            bitnum += 8;
-            continue;
-        }
-        if (cow_test_bit(bitnum, bitmap) == value) {
-            bitnum++;
-            continue;
-        }
-        break;
+    ret = bdrv_pwrite_sync(bs->file, offset, &bitmap, sizeof(bitmap));
+    if (ret < 0) {
+       return ret;
     }
-    return MIN(bitnum, last) - start;
+    return 0;
+}
+
+static inline int is_bit_set(BlockDriverState *bs, int64_t bitnum)
+{
+    uint64_t offset = sizeof(struct cow_header_v2) + bitnum / 8;
+    uint8_t bitmap;
+    int ret;
+
+    ret = bdrv_pread(bs->file, offset, &bitmap, sizeof(bitmap));
+    if (ret < 0) {
+       return ret;
+    }
+
+    return !!(bitmap & (1 << (bitnum % 8)));
 }
 
 /* Return true if first block has been changed (ie. current version is
  * in COW file).  Set the number of continuous blocks for which that
  * is true. */
-static int coroutine_fn cow_co_is_allocated(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *num_same)
+static int cow_is_allocated(BlockDriverState *bs, int64_t sector_num,
+        int nb_sectors, int *num_same)
 {
-    int64_t bitnum = sector_num + sizeof(struct cow_header_v2) * 8;
-    uint64_t offset = (bitnum / 8) & -BDRV_SECTOR_SIZE;
-    bool first = true;
-    int changed = 0, same = 0;
+    int changed;
 
-    do {
-        int ret;
-        uint8_t bitmap[BDRV_SECTOR_SIZE];
-
-        bitnum &= BITS_PER_BITMAP_SECTOR - 1;
-        int sector_bits = MIN(nb_sectors, BITS_PER_BITMAP_SECTOR - bitnum);
-
-        ret = bdrv_pread(bs->file, offset, &bitmap, sizeof(bitmap));
-        if (ret < 0) {
-            return ret;
-        }
-
-        if (first) {
-            changed = cow_test_bit(bitnum, bitmap);
-            first = false;
-        }
-
-        same += cow_find_streak(bitmap, changed, bitnum, nb_sectors);
-
-        bitnum += sector_bits;
-        nb_sectors -= sector_bits;
-        offset += BDRV_SECTOR_SIZE;
-    } while (nb_sectors);
-
-    *num_same = same;
-    return changed;
-}
-
-static int64_t coroutine_fn cow_co_get_block_status(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *num_same)
-{
-    BDRVCowState *s = bs->opaque;
-    int ret = cow_co_is_allocated(bs, sector_num, nb_sectors, num_same);
-    int64_t offset = s->cow_sectors_offset + (sector_num << BDRV_SECTOR_BITS);
-    if (ret < 0) {
-        return ret;
+    if (nb_sectors == 0) {
+	*num_same = nb_sectors;
+	return 0;
     }
-    return (ret ? BDRV_BLOCK_DATA : 0) | offset | BDRV_BLOCK_OFFSET_VALID;
+
+    changed = is_bit_set(bs, sector_num);
+    if (changed < 0) {
+        return 0; /* XXX: how to return I/O errors? */
+    }
+
+    for (*num_same = 1; *num_same < nb_sectors; (*num_same)++) {
+	if (is_bit_set(bs, sector_num + *num_same) != changed)
+	    break;
+    }
+
+    return changed;
 }
 
 static int cow_update_bitmap(BlockDriverState *bs, int64_t sector_num,
         int nb_sectors)
 {
-    int64_t bitnum = sector_num + sizeof(struct cow_header_v2) * 8;
-    uint64_t offset = (bitnum / 8) & -BDRV_SECTOR_SIZE;
-    bool first = true;
-    int sector_bits;
+    int error = 0;
+    int i;
 
-    for ( ; nb_sectors;
-            bitnum += sector_bits,
-            nb_sectors -= sector_bits,
-            offset += BDRV_SECTOR_SIZE) {
-        int ret, set;
-        uint8_t bitmap[BDRV_SECTOR_SIZE];
-
-        bitnum &= BITS_PER_BITMAP_SECTOR - 1;
-        sector_bits = MIN(nb_sectors, BITS_PER_BITMAP_SECTOR - bitnum);
-
-        ret = bdrv_pread(bs->file, offset, &bitmap, sizeof(bitmap));
-        if (ret < 0) {
-            return ret;
-        }
-
-        /* Skip over any already set bits */
-        set = cow_find_streak(bitmap, 1, bitnum, sector_bits);
-        bitnum += set;
-        sector_bits -= set;
-        nb_sectors -= set;
-        if (!sector_bits) {
-            continue;
-        }
-
-        if (first) {
-            ret = bdrv_flush(bs->file);
-            if (ret < 0) {
-                return ret;
-            }
-            first = false;
-        }
-
-        cow_set_bits(bitmap, bitnum, sector_bits);
-
-        ret = bdrv_pwrite(bs->file, offset, &bitmap, sizeof(bitmap));
-        if (ret < 0) {
-            return ret;
+    for (i = 0; i < nb_sectors; i++) {
+        error = cow_set_bit(bs, sector_num + i);
+        if (error) {
+            break;
         }
     }
 
-    return 0;
+    return error;
 }
 
-static int coroutine_fn cow_read(BlockDriverState *bs, int64_t sector_num,
-                                 uint8_t *buf, int nb_sectors)
+static int cow_read(BlockDriverState *bs, int64_t sector_num,
+                    uint8_t *buf, int nb_sectors)
 {
     BDRVCowState *s = bs->opaque;
     int ret, n;
 
     while (nb_sectors > 0) {
-        ret = cow_co_is_allocated(bs, sector_num, nb_sectors, &n);
-        if (ret < 0) {
-            return ret;
-        }
-        if (ret) {
+        if (cow_is_allocated(bs, sector_num, nb_sectors, &n)) {
             ret = bdrv_pread(bs->file,
                         s->cow_sectors_offset + sector_num * 512,
                         buf, n * 512);
-            if (ret < 0) {
-                return ret;
-            }
+            if (ret != n * 512)
+                return -1;
         } else {
             if (bs->backing_hd) {
                 /* read from the base image */
                 ret = bdrv_read(bs->backing_hd, sector_num, buf, n);
-                if (ret < 0) {
-                    return ret;
-                }
+                if (ret < 0)
+                    return -1;
             } else {
-                memset(buf, 0, n * 512);
-            }
+            memset(buf, 0, n * 512);
+        }
         }
         nb_sectors -= n;
         sector_num += n;
@@ -302,9 +220,8 @@ static int cow_write(BlockDriverState *bs, int64_t sector_num,
 
     ret = bdrv_pwrite(bs->file, s->cow_sectors_offset + sector_num * 512,
                       buf, nb_sectors * 512);
-    if (ret < 0) {
-        return ret;
-    }
+    if (ret != nb_sectors * 512)
+        return -1;
 
     return cow_update_bitmap(bs, sector_num, nb_sectors);
 }
@@ -324,33 +241,29 @@ static void cow_close(BlockDriverState *bs)
 {
 }
 
-static int cow_create(const char *filename, QemuOpts *opts, Error **errp)
+static int cow_create(const char *filename, QEMUOptionParameter *options)
 {
+    int fd, cow_fd;
     struct cow_header_v2 cow_header;
     struct stat st;
     int64_t image_sectors = 0;
-    char *image_filename = NULL;
-    Error *local_err = NULL;
+    const char *image_filename = NULL;
     int ret;
-    BlockDriverState *cow_bs = NULL;
 
     /* Read out options */
-    image_sectors = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
-    image_filename = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
-
-    ret = bdrv_create_file(filename, opts, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto exit;
-    }
-
-    ret = bdrv_open(&cow_bs, filename, NULL, NULL,
-                    BDRV_O_RDWR | BDRV_O_PROTOCOL, NULL, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto exit;
+    while (options && options->name) {
+        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+            image_sectors = options->value.n / 512;
+        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
+            image_filename = options->value.s;
+        }
+        options++;
     }
 
+    cow_fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
+              0644);
+    if (cow_fd < 0)
+        return -errno;
     memset(&cow_header, 0, sizeof(cow_header));
     cow_header.magic = cpu_to_be32(COW_MAGIC);
     cow_header.version = cpu_to_be32(COW_VERSION);
@@ -358,9 +271,16 @@ static int cow_create(const char *filename, QemuOpts *opts, Error **errp)
         /* Note: if no file, we put a dummy mtime */
         cow_header.mtime = cpu_to_be32(0);
 
-        if (stat(image_filename, &st) != 0) {
+        fd = open(image_filename, O_RDONLY | O_BINARY);
+        if (fd < 0) {
+            close(cow_fd);
             goto mtime_fail;
         }
+        if (fstat(fd, &st) != 0) {
+            close(fd);
+            goto mtime_fail;
+        }
+        close(fd);
         cow_header.mtime = cpu_to_be32(st.st_mtime);
     mtime_fail:
         pstrcpy(cow_header.backing_file, sizeof(cow_header.backing_file),
@@ -368,42 +288,41 @@ static int cow_create(const char *filename, QemuOpts *opts, Error **errp)
     }
     cow_header.sectorsize = cpu_to_be32(512);
     cow_header.size = cpu_to_be64(image_sectors * 512);
-    ret = bdrv_pwrite(cow_bs, 0, &cow_header, sizeof(cow_header));
-    if (ret < 0) {
+    ret = qemu_write_full(cow_fd, &cow_header, sizeof(cow_header));
+    if (ret != sizeof(cow_header)) {
+        ret = -errno;
         goto exit;
     }
 
     /* resize to include at least all the bitmap */
-    ret = bdrv_truncate(cow_bs,
-        sizeof(cow_header) + ((image_sectors + 7) >> 3));
-    if (ret < 0) {
+    ret = ftruncate(cow_fd, sizeof(cow_header) + ((image_sectors + 7) >> 3));
+    if (ret) {
+        ret = -errno;
         goto exit;
     }
 
 exit:
-    g_free(image_filename);
-    if (cow_bs) {
-        bdrv_unref(cow_bs);
-    }
+    close(cow_fd);
     return ret;
 }
 
-static QemuOptsList cow_create_opts = {
-    .name = "cow-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(cow_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        {
-            .name = BLOCK_OPT_BACKING_FILE,
-            .type = QEMU_OPT_STRING,
-            .help = "File name of a base image"
-        },
-        { /* end of list */ }
-    }
+static coroutine_fn int cow_co_flush(BlockDriverState *bs)
+{
+    return bdrv_co_flush(bs->file);
+}
+
+static QEMUOptionParameter cow_create_options[] = {
+    {
+        .name = BLOCK_OPT_SIZE,
+        .type = OPT_SIZE,
+        .help = "Virtual disk size"
+    },
+    {
+        .name = BLOCK_OPT_BACKING_FILE,
+        .type = OPT_STRING,
+        .help = "File name of a base image"
+    },
+    { NULL }
 };
 
 static BlockDriver bdrv_cow = {
@@ -414,14 +333,13 @@ static BlockDriver bdrv_cow = {
     .bdrv_open      = cow_open,
     .bdrv_close     = cow_close,
     .bdrv_create    = cow_create,
-    .bdrv_has_zero_init     = bdrv_has_zero_init_1,
-    .supports_backing       = true,
 
     .bdrv_read              = cow_co_read,
     .bdrv_write             = cow_co_write,
-    .bdrv_co_get_block_status   = cow_co_get_block_status,
+    .bdrv_co_flush_to_disk  = cow_co_flush,
+    .bdrv_is_allocated      = cow_is_allocated,
 
-    .create_opts    = &cow_create_opts,
+    .create_options = cow_create_options,
 };
 
 static void bdrv_cow_init(void)

block/curl.c

@@ -22,8 +22,7 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qapi/qmp/qbool.h"
+#include "block_int.h"
 #include <curl/curl.h>
 
 // #define DEBUG
@@ -35,43 +34,15 @@
 #define DPRINTF(fmt, ...) do { } while (0)
 #endif
 
-#if LIBCURL_VERSION_NUM >= 0x071000
-/* The multi interface timer callback was introduced in 7.16.0 */
-#define NEED_CURL_TIMER_CALLBACK
-#define HAVE_SOCKET_ACTION
-#endif
-
-#ifndef HAVE_SOCKET_ACTION
-/* If curl_multi_socket_action isn't available, define it statically here in
- * terms of curl_multi_socket. Note that ev_bitmask will be ignored, which is
- * less efficient but still safe. */
-static CURLMcode __curl_multi_socket_action(CURLM *multi_handle,
-                                            curl_socket_t sockfd,
-                                            int ev_bitmask,
-                                            int *running_handles)
-{
-    return curl_multi_socket(multi_handle, sockfd, running_handles);
-}
-#define curl_multi_socket_action __curl_multi_socket_action
-#endif
-
-#define PROTOCOLS (CURLPROTO_HTTP | CURLPROTO_HTTPS | \
-                   CURLPROTO_FTP | CURLPROTO_FTPS | \
-                   CURLPROTO_TFTP)
-
 #define CURL_NUM_STATES 8
 #define CURL_NUM_ACB    8
 #define SECTOR_SIZE     512
-#define READ_AHEAD_DEFAULT (256 * 1024)
+#define READ_AHEAD_SIZE (256 * 1024)
 
 #define FIND_RET_NONE   0
 #define FIND_RET_OK     1
 #define FIND_RET_WAIT   2
 
-#define CURL_BLOCK_OPT_URL       "url"
-#define CURL_BLOCK_OPT_READAHEAD "readahead"
-#define CURL_BLOCK_OPT_SSLVERIFY "sslverify"
-
 struct BDRVCURLState;
 
 typedef struct CURLAIOCB {
@@ -91,7 +62,6 @@ typedef struct CURLState
     struct BDRVCURLState *s;
     CURLAIOCB *acb[CURL_NUM_ACB];
     CURL *curl;
-    curl_socket_t sock_fd;
     char *orig_buf;
     size_t buf_start;
     size_t buf_off;
@@ -103,76 +73,49 @@ typedef struct CURLState
 
 typedef struct BDRVCURLState {
     CURLM *multi;
-    QEMUTimer timer;
     size_t len;
     CURLState states[CURL_NUM_STATES];
     char *url;
     size_t readahead_size;
-    bool sslverify;
-    bool accept_range;
-    AioContext *aio_context;
 } BDRVCURLState;
 
 static void curl_clean_state(CURLState *s);
 static void curl_multi_do(void *arg);
-static void curl_multi_read(void *arg);
-
-#ifdef NEED_CURL_TIMER_CALLBACK
-static int curl_timer_cb(CURLM *multi, long timeout_ms, void *opaque)
-{
-    BDRVCURLState *s = opaque;
-
-    DPRINTF("CURL: timer callback timeout_ms %ld\n", timeout_ms);
-    if (timeout_ms == -1) {
-        timer_del(&s->timer);
-    } else {
-        int64_t timeout_ns = (int64_t)timeout_ms * 1000 * 1000;
-        timer_mod(&s->timer,
-                  qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + timeout_ns);
-    }
-    return 0;
-}
-#endif
+static int curl_aio_flush(void *opaque);
 
 static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
-                        void *userp, void *sp)
+                        void *s, void *sp)
 {
-    BDRVCURLState *s;
-    CURLState *state = NULL;
-    curl_easy_getinfo(curl, CURLINFO_PRIVATE, (char **)&state);
-    state->sock_fd = fd;
-    s = state->s;
-
     DPRINTF("CURL (AIO): Sock action %d on fd %d\n", action, fd);
     switch (action) {
         case CURL_POLL_IN:
-            aio_set_fd_handler(s->aio_context, fd, curl_multi_read,
-                               NULL, state);
+            qemu_aio_set_fd_handler(fd, curl_multi_do, NULL, curl_aio_flush,
+                                    NULL, s);
             break;
         case CURL_POLL_OUT:
-            aio_set_fd_handler(s->aio_context, fd, NULL, curl_multi_do, state);
+            qemu_aio_set_fd_handler(fd, NULL, curl_multi_do, curl_aio_flush,
+                                    NULL, s);
             break;
         case CURL_POLL_INOUT:
-            aio_set_fd_handler(s->aio_context, fd, curl_multi_read,
-                               curl_multi_do, state);
+            qemu_aio_set_fd_handler(fd, curl_multi_do, curl_multi_do,
+                                    curl_aio_flush, NULL, s);
             break;
         case CURL_POLL_REMOVE:
-            aio_set_fd_handler(s->aio_context, fd, NULL, NULL, NULL);
+            qemu_aio_set_fd_handler(fd, NULL, NULL, NULL, NULL, NULL);
             break;
     }
 
     return 0;
 }
 
-static size_t curl_header_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
+static size_t curl_size_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
 {
-    BDRVCURLState *s = opaque;
+    CURLState *s = ((CURLState*)opaque);
     size_t realsize = size * nmemb;
-    const char *accept_line = "Accept-Ranges: bytes";
+    size_t fsize;
 
-    if (realsize >= strlen(accept_line)
-        && strncmp((char *)ptr, accept_line, strlen(accept_line)) == 0) {
-        s->accept_range = true;
+    if(sscanf(ptr, "Content-Length: %zd", &fsize) == 1) {
+        s->s->len = fsize;
     }
 
     return realsize;
@@ -187,13 +130,8 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
     DPRINTF("CURL: Just reading %zd bytes\n", realsize);
 
     if (!s || !s->orig_buf)
-        return 0;
+        goto read_end;
 
-    if (s->buf_off >= s->buf_len) {
-        /* buffer full, read nothing */
-        return 0;
-    }
-    realsize = MIN(realsize, s->buf_len - s->buf_off);
     memcpy(s->orig_buf + s->buf_off, ptr, realsize);
     s->buf_off += realsize;
 
@@ -204,14 +142,15 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
             continue;
 
         if ((s->buf_off >= acb->end)) {
-            qemu_iovec_from_buf(acb->qiov, 0, s->orig_buf + acb->start,
-                                acb->end - acb->start);
+            qemu_iovec_from_buffer(acb->qiov, s->orig_buf + acb->start,
+                                   acb->end - acb->start);
             acb->common.cb(acb->common.opaque, 0);
             qemu_aio_release(acb);
             s->acb[i] = NULL;
         }
     }
 
+read_end:
     return realsize;
 }
 
@@ -239,15 +178,14 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
         {
             char *buf = state->orig_buf + (start - state->buf_start);
 
-            qemu_iovec_from_buf(acb->qiov, 0, buf, len);
+            qemu_iovec_from_buffer(acb->qiov, buf, len);
             acb->common.cb(acb->common.opaque, 0);
 
             return FIND_RET_OK;
         }
 
         // Wait for unfinished chunks
-        if (state->in_use &&
-            (start >= state->buf_start) &&
+        if ((start >= state->buf_start) &&
             (start <= buf_fend) &&
             (end >= state->buf_start) &&
             (end <= buf_fend))
@@ -269,87 +207,61 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
     return FIND_RET_NONE;
 }
 
-static void curl_multi_check_completion(BDRVCURLState *s)
+static void curl_multi_do(void *arg)
 {
+    BDRVCURLState *s = (BDRVCURLState *)arg;
+    int running;
+    int r;
     int msgs_in_queue;
 
+    if (!s->multi)
+        return;
+
+    do {
+        r = curl_multi_socket_all(s->multi, &running);
+    } while(r == CURLM_CALL_MULTI_PERFORM);
+
     /* Try to find done transfers, so we can free the easy
      * handle again. */
-    for (;;) {
+    do {
         CURLMsg *msg;
         msg = curl_multi_info_read(s->multi, &msgs_in_queue);
 
-        /* Quit when there are no more completions */
         if (!msg)
             break;
-
-        if (msg->msg == CURLMSG_DONE) {
-            CURLState *state = NULL;
-            curl_easy_getinfo(msg->easy_handle, CURLINFO_PRIVATE,
-                              (char **)&state);
-
-            /* ACBs for successful messages get completed in curl_read_cb */
-            if (msg->data.result != CURLE_OK) {
-                int i;
-                for (i = 0; i < CURL_NUM_ACB; i++) {
-                    CURLAIOCB *acb = state->acb[i];
-
-                    if (acb == NULL) {
-                        continue;
-                    }
-
-                    acb->common.cb(acb->common.opaque, -EIO);
-                    qemu_aio_release(acb);
-                    state->acb[i] = NULL;
-                }
-            }
-
-            curl_clean_state(state);
+        if (msg->msg == CURLMSG_NONE)
             break;
+
+        switch (msg->msg) {
+            case CURLMSG_DONE:
+            {
+                CURLState *state = NULL;
+                curl_easy_getinfo(msg->easy_handle, CURLINFO_PRIVATE, (char**)&state);
+
+                /* ACBs for successful messages get completed in curl_read_cb */
+                if (msg->data.result != CURLE_OK) {
+                    int i;
+                    for (i = 0; i < CURL_NUM_ACB; i++) {
+                        CURLAIOCB *acb = state->acb[i];
+
+                        if (acb == NULL) {
+                            continue;
+                        }
+
+                        acb->common.cb(acb->common.opaque, -EIO);
+                        qemu_aio_release(acb);
+                        state->acb[i] = NULL;
+                    }
+                }
+
+                curl_clean_state(state);
+                break;
+            }
+            default:
+                msgs_in_queue = 0;
+                break;
         }
-    }
-}
-
-static void curl_multi_do(void *arg)
-{
-    CURLState *s = (CURLState *)arg;
-    int running;
-    int r;
-
-    if (!s->s->multi) {
-        return;
-    }
-
-    do {
-        r = curl_multi_socket_action(s->s->multi, s->sock_fd, 0, &running);
-    } while(r == CURLM_CALL_MULTI_PERFORM);
-
-}
-
-static void curl_multi_read(void *arg)
-{
-    CURLState *s = (CURLState *)arg;
-
-    curl_multi_do(arg);
-    curl_multi_check_completion(s->s);
-}
-
-static void curl_multi_timeout_do(void *arg)
-{
-#ifdef NEED_CURL_TIMER_CALLBACK
-    BDRVCURLState *s = (BDRVCURLState *)arg;
-    int running;
-
-    if (!s->multi) {
-        return;
-    }
-
-    curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
-
-    curl_multi_check_completion(s);
-#else
-    abort();
-#endif
+    } while(msgs_in_queue);
 }
 
 static CURLState *curl_init_state(BDRVCURLState *s)
@@ -370,44 +282,33 @@ static CURLState *curl_init_state(BDRVCURLState *s)
             break;
         }
         if (!state) {
-            aio_poll(state->s->aio_context, true);
+            usleep(100);
+            curl_multi_do(s);
         }
     } while(!state);
 
-    if (!state->curl) {
-        state->curl = curl_easy_init();
-        if (!state->curl) {
-            return NULL;
-        }
-        curl_easy_setopt(state->curl, CURLOPT_URL, s->url);
-        curl_easy_setopt(state->curl, CURLOPT_SSL_VERIFYPEER,
-                         (long) s->sslverify);
-        curl_easy_setopt(state->curl, CURLOPT_TIMEOUT, 5);
-        curl_easy_setopt(state->curl, CURLOPT_WRITEFUNCTION,
-                         (void *)curl_read_cb);
-        curl_easy_setopt(state->curl, CURLOPT_WRITEDATA, (void *)state);
-        curl_easy_setopt(state->curl, CURLOPT_PRIVATE, (void *)state);
-        curl_easy_setopt(state->curl, CURLOPT_AUTOREFERER, 1);
-        curl_easy_setopt(state->curl, CURLOPT_FOLLOWLOCATION, 1);
-        curl_easy_setopt(state->curl, CURLOPT_NOSIGNAL, 1);
-        curl_easy_setopt(state->curl, CURLOPT_ERRORBUFFER, state->errmsg);
-        curl_easy_setopt(state->curl, CURLOPT_FAILONERROR, 1);
+    if (state->curl)
+        goto has_curl;
 
-        /* Restrict supported protocols to avoid security issues in the more
-         * obscure protocols.  For example, do not allow POP3/SMTP/IMAP see
-         * CVE-2013-0249.
-         *
-         * Restricting protocols is only supported from 7.19.4 upwards.
-         */
-#if LIBCURL_VERSION_NUM >= 0x071304
-        curl_easy_setopt(state->curl, CURLOPT_PROTOCOLS, PROTOCOLS);
-        curl_easy_setopt(state->curl, CURLOPT_REDIR_PROTOCOLS, PROTOCOLS);
-#endif
+    state->curl = curl_easy_init();
+    if (!state->curl)
+        return NULL;
+    curl_easy_setopt(state->curl, CURLOPT_URL, s->url);
+    curl_easy_setopt(state->curl, CURLOPT_TIMEOUT, 5);
+    curl_easy_setopt(state->curl, CURLOPT_WRITEFUNCTION, (void *)curl_read_cb);
+    curl_easy_setopt(state->curl, CURLOPT_WRITEDATA, (void *)state);
+    curl_easy_setopt(state->curl, CURLOPT_PRIVATE, (void *)state);
+    curl_easy_setopt(state->curl, CURLOPT_AUTOREFERER, 1);
+    curl_easy_setopt(state->curl, CURLOPT_FOLLOWLOCATION, 1);
+    curl_easy_setopt(state->curl, CURLOPT_NOSIGNAL, 1);
+    curl_easy_setopt(state->curl, CURLOPT_ERRORBUFFER, state->errmsg);
+    curl_easy_setopt(state->curl, CURLOPT_FAILONERROR, 1);
 
 #ifdef DEBUG_VERBOSE
-        curl_easy_setopt(state->curl, CURLOPT_VERBOSE, 1);
+    curl_easy_setopt(state->curl, CURLOPT_VERBOSE, 1);
 #endif
-    }
+
+has_curl:
 
     state->s = s;
 
@@ -421,115 +322,52 @@ static void curl_clean_state(CURLState *s)
     s->in_use = 0;
 }
 
-static void curl_parse_filename(const char *filename, QDict *options,
-                                Error **errp)
-{
-    qdict_put(options, CURL_BLOCK_OPT_URL, qstring_from_str(filename));
-}
-
-static void curl_detach_aio_context(BlockDriverState *bs)
-{
-    BDRVCURLState *s = bs->opaque;
-    int i;
-
-    for (i = 0; i < CURL_NUM_STATES; i++) {
-        if (s->states[i].in_use) {
-            curl_clean_state(&s->states[i]);
-        }
-        if (s->states[i].curl) {
-            curl_easy_cleanup(s->states[i].curl);
-            s->states[i].curl = NULL;
-        }
-        g_free(s->states[i].orig_buf);
-        s->states[i].orig_buf = NULL;
-    }
-    if (s->multi) {
-        curl_multi_cleanup(s->multi);
-        s->multi = NULL;
-    }
-
-    timer_del(&s->timer);
-}
-
-static void curl_attach_aio_context(BlockDriverState *bs,
-                                    AioContext *new_context)
-{
-    BDRVCURLState *s = bs->opaque;
-
-    aio_timer_init(new_context, &s->timer,
-                   QEMU_CLOCK_REALTIME, SCALE_NS,
-                   curl_multi_timeout_do, s);
-
-    assert(!s->multi);
-    s->multi = curl_multi_init();
-    s->aio_context = new_context;
-    curl_multi_setopt(s->multi, CURLMOPT_SOCKETFUNCTION, curl_sock_cb);
-#ifdef NEED_CURL_TIMER_CALLBACK
-    curl_multi_setopt(s->multi, CURLMOPT_TIMERDATA, s);
-    curl_multi_setopt(s->multi, CURLMOPT_TIMERFUNCTION, curl_timer_cb);
-#endif
-}
-
-static QemuOptsList runtime_opts = {
-    .name = "curl",
-    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
-    .desc = {
-        {
-            .name = CURL_BLOCK_OPT_URL,
-            .type = QEMU_OPT_STRING,
-            .help = "URL to open",
-        },
-        {
-            .name = CURL_BLOCK_OPT_READAHEAD,
-            .type = QEMU_OPT_SIZE,
-            .help = "Readahead size",
-        },
-        {
-            .name = CURL_BLOCK_OPT_SSLVERIFY,
-            .type = QEMU_OPT_BOOL,
-            .help = "Verify SSL certificate"
-        },
-        { /* end of list */ }
-    },
-};
-
-static int curl_open(BlockDriverState *bs, QDict *options, int flags,
-                     Error **errp)
+static int curl_open(BlockDriverState *bs, const char *filename, int flags)
 {
     BDRVCURLState *s = bs->opaque;
     CURLState *state = NULL;
-    QemuOpts *opts;
-    Error *local_err = NULL;
-    const char *file;
     double d;
 
+    #define RA_OPTSTR ":readahead="
+    char *file;
+    char *ra;
+    const char *ra_val;
+    int parse_state = 0;
+
     static int inited = 0;
 
-    if (flags & BDRV_O_RDWR) {
-        error_setg(errp, "curl block device does not support writes");
-        return -EROFS;
+    file = g_strdup(filename);
+    s->readahead_size = READ_AHEAD_SIZE;
+
+    /* Parse a trailing ":readahead=#:" param, if present. */
+    ra = file + strlen(file) - 1;
+    while (ra >= file) {
+        if (parse_state == 0) {
+            if (*ra == ':')
+                parse_state++;
+            else
+                break;
+        } else if (parse_state == 1) {
+            if (*ra > '9' || *ra < '0') {
+                char *opt_start = ra - strlen(RA_OPTSTR) + 1;
+                if (opt_start > file &&
+                    strncmp(opt_start, RA_OPTSTR, strlen(RA_OPTSTR)) == 0) {
+                    ra_val = ra + 1;
+                    ra -= strlen(RA_OPTSTR) - 1;
+                    *ra = '\0';
+                    s->readahead_size = atoi(ra_val);
+                    break;
+                } else {
+                    break;
+                }
+            }
+        }
+        ra--;
     }
 
-    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        goto out_noclean;
-    }
-
-    s->readahead_size = qemu_opt_get_size(opts, CURL_BLOCK_OPT_READAHEAD,
-                                          READ_AHEAD_DEFAULT);
     if ((s->readahead_size & 0x1ff) != 0) {
-        error_setg(errp, "HTTP_READAHEAD_SIZE %zd is not a multiple of 512",
-                   s->readahead_size);
-        goto out_noclean;
-    }
-
-    s->sslverify = qemu_opt_get_bool(opts, CURL_BLOCK_OPT_SSLVERIFY, true);
-
-    file = qemu_opt_get(opts, CURL_BLOCK_OPT_URL);
-    if (file == NULL) {
-        error_setg(errp, "curl block driver requires an 'url' option");
+        fprintf(stderr, "HTTP_READAHEAD_SIZE %zd is not a multiple of 512\n",
+                s->readahead_size);
         goto out_noclean;
     }
 
@@ -539,60 +377,70 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     DPRINTF("CURL: Opening %s\n", file);
-    s->aio_context = bdrv_get_aio_context(bs);
-    s->url = g_strdup(file);
+    s->url = file;
     state = curl_init_state(s);
     if (!state)
         goto out_noclean;
 
     // Get file size
 
-    s->accept_range = false;
     curl_easy_setopt(state->curl, CURLOPT_NOBODY, 1);
-    curl_easy_setopt(state->curl, CURLOPT_HEADERFUNCTION,
-                     curl_header_cb);
-    curl_easy_setopt(state->curl, CURLOPT_HEADERDATA, s);
+    curl_easy_setopt(state->curl, CURLOPT_WRITEFUNCTION, (void *)curl_size_cb);
     if (curl_easy_perform(state->curl))
         goto out;
     curl_easy_getinfo(state->curl, CURLINFO_CONTENT_LENGTH_DOWNLOAD, &d);
+    curl_easy_setopt(state->curl, CURLOPT_WRITEFUNCTION, (void *)curl_read_cb);
+    curl_easy_setopt(state->curl, CURLOPT_NOBODY, 0);
     if (d)
         s->len = (size_t)d;
     else if(!s->len)
         goto out;
-    if ((!strncasecmp(s->url, "http://", strlen("http://"))
-        || !strncasecmp(s->url, "https://", strlen("https://")))
-        && !s->accept_range) {
-        pstrcpy(state->errmsg, CURL_ERROR_SIZE,
-                "Server does not support 'range' (byte ranges).");
-        goto out;
-    }
     DPRINTF("CURL: Size = %zd\n", s->len);
 
     curl_clean_state(state);
     curl_easy_cleanup(state->curl);
     state->curl = NULL;
 
-    curl_attach_aio_context(bs, bdrv_get_aio_context(bs));
+    // Now we know the file exists and its size, so let's
+    // initialize the multi interface!
+
+    s->multi = curl_multi_init();
+    curl_multi_setopt( s->multi, CURLMOPT_SOCKETDATA, s); 
+    curl_multi_setopt( s->multi, CURLMOPT_SOCKETFUNCTION, curl_sock_cb ); 
+    curl_multi_do(s);
 
-    qemu_opts_del(opts);
     return 0;
 
 out:
-    error_setg(errp, "CURL: Error opening file: %s", state->errmsg);
+    fprintf(stderr, "CURL: Error opening file: %s\n", state->errmsg);
     curl_easy_cleanup(state->curl);
     state->curl = NULL;
 out_noclean:
-    g_free(s->url);
-    qemu_opts_del(opts);
+    g_free(file);
     return -EINVAL;
 }
 
+static int curl_aio_flush(void *opaque)
+{
+    BDRVCURLState *s = opaque;
+    int i, j;
+
+    for (i=0; i < CURL_NUM_STATES; i++) {
+        for(j=0; j < CURL_NUM_ACB; j++) {
+            if (s->states[i].acb[j]) {
+                return 1;
+            }
+        }
+    }
+    return 0;
+}
+
 static void curl_aio_cancel(BlockDriverAIOCB *blockacb)
 {
     // Do we have to implement canceling? Seems to work without...
 }
 
-static const AIOCBInfo curl_aiocb_info = {
+static AIOPool curl_aio_pool = {
     .aiocb_size         = sizeof(CURLAIOCB),
     .cancel             = curl_aio_cancel,
 };
@@ -601,7 +449,6 @@ static const AIOCBInfo curl_aiocb_info = {
 static void curl_readv_bh_cb(void *p)
 {
     CURLState *state;
-    int running;
 
     CURLAIOCB *acb = p;
     BDRVCURLState *s = acb->common.bs->opaque;
@@ -636,7 +483,8 @@ static void curl_readv_bh_cb(void *p)
     acb->end = (acb->nb_sectors * SECTOR_SIZE);
 
     state->buf_off = 0;
-    g_free(state->orig_buf);
+    if (state->orig_buf)
+        g_free(state->orig_buf);
     state->buf_start = start;
     state->buf_len = acb->end + s->readahead_size;
     end = MIN(start + state->buf_len, s->len) - 1;
@@ -649,9 +497,8 @@ static void curl_readv_bh_cb(void *p)
     curl_easy_setopt(state->curl, CURLOPT_RANGE, state->range);
 
     curl_multi_add_handle(s->multi, state->curl);
+    curl_multi_do(s);
 
-    /* Tell curl it needs to kick things off */
-    curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
 }
 
 static BlockDriverAIOCB *curl_aio_readv(BlockDriverState *bs,
@@ -660,13 +507,23 @@ static BlockDriverAIOCB *curl_aio_readv(BlockDriverState *bs,
 {
     CURLAIOCB *acb;
 
-    acb = qemu_aio_get(&curl_aiocb_info, bs, cb, opaque);
+    acb = qemu_aio_get(&curl_aio_pool, bs, cb, opaque);
+
+    if (!acb) {
+        return NULL;
+    }
 
     acb->qiov = qiov;
     acb->sector_num = sector_num;
     acb->nb_sectors = nb_sectors;
 
-    acb->bh = aio_bh_new(bdrv_get_aio_context(bs), curl_readv_bh_cb, acb);
+    acb->bh = qemu_bh_new(curl_readv_bh_cb, acb);
+
+    if (!acb->bh) {
+        DPRINTF("CURL: qemu_bh_new failed\n");
+        return NULL;
+    }
+
     qemu_bh_schedule(acb->bh);
     return &acb->common;
 }
@@ -674,11 +531,25 @@ static BlockDriverAIOCB *curl_aio_readv(BlockDriverState *bs,
 static void curl_close(BlockDriverState *bs)
 {
     BDRVCURLState *s = bs->opaque;
+    int i;
 
     DPRINTF("CURL: Close\n");
-    curl_detach_aio_context(bs);
-
-    g_free(s->url);
+    for (i=0; i<CURL_NUM_STATES; i++) {
+        if (s->states[i].in_use)
+            curl_clean_state(&s->states[i]);
+        if (s->states[i].curl) {
+            curl_easy_cleanup(s->states[i].curl);
+            s->states[i].curl = NULL;
+        }
+        if (s->states[i].orig_buf) {
+            g_free(s->states[i].orig_buf);
+            s->states[i].orig_buf = NULL;
+        }
+    }
+    if (s->multi)
+        curl_multi_cleanup(s->multi);
+    if (s->url)
+        free(s->url);
 }
 
 static int64_t curl_getlength(BlockDriverState *bs)
@@ -688,83 +559,63 @@ static int64_t curl_getlength(BlockDriverState *bs)
 }
 
 static BlockDriver bdrv_http = {
-    .format_name                = "http",
-    .protocol_name              = "http",
+    .format_name     = "http",
+    .protocol_name   = "http",
 
-    .instance_size              = sizeof(BDRVCURLState),
-    .bdrv_parse_filename        = curl_parse_filename,
-    .bdrv_file_open             = curl_open,
-    .bdrv_close                 = curl_close,
-    .bdrv_getlength             = curl_getlength,
+    .instance_size   = sizeof(BDRVCURLState),
+    .bdrv_file_open  = curl_open,
+    .bdrv_close      = curl_close,
+    .bdrv_getlength  = curl_getlength,
 
-    .bdrv_aio_readv             = curl_aio_readv,
-
-    .bdrv_detach_aio_context    = curl_detach_aio_context,
-    .bdrv_attach_aio_context    = curl_attach_aio_context,
+    .bdrv_aio_readv  = curl_aio_readv,
 };
 
 static BlockDriver bdrv_https = {
-    .format_name                = "https",
-    .protocol_name              = "https",
+    .format_name     = "https",
+    .protocol_name   = "https",
 
-    .instance_size              = sizeof(BDRVCURLState),
-    .bdrv_parse_filename        = curl_parse_filename,
-    .bdrv_file_open             = curl_open,
-    .bdrv_close                 = curl_close,
-    .bdrv_getlength             = curl_getlength,
+    .instance_size   = sizeof(BDRVCURLState),
+    .bdrv_file_open  = curl_open,
+    .bdrv_close      = curl_close,
+    .bdrv_getlength  = curl_getlength,
 
-    .bdrv_aio_readv             = curl_aio_readv,
-
-    .bdrv_detach_aio_context    = curl_detach_aio_context,
-    .bdrv_attach_aio_context    = curl_attach_aio_context,
+    .bdrv_aio_readv  = curl_aio_readv,
 };
 
 static BlockDriver bdrv_ftp = {
-    .format_name                = "ftp",
-    .protocol_name              = "ftp",
+    .format_name     = "ftp",
+    .protocol_name   = "ftp",
 
-    .instance_size              = sizeof(BDRVCURLState),
-    .bdrv_parse_filename        = curl_parse_filename,
-    .bdrv_file_open             = curl_open,
-    .bdrv_close                 = curl_close,
-    .bdrv_getlength             = curl_getlength,
+    .instance_size   = sizeof(BDRVCURLState),
+    .bdrv_file_open  = curl_open,
+    .bdrv_close      = curl_close,
+    .bdrv_getlength  = curl_getlength,
 
-    .bdrv_aio_readv             = curl_aio_readv,
-
-    .bdrv_detach_aio_context    = curl_detach_aio_context,
-    .bdrv_attach_aio_context    = curl_attach_aio_context,
+    .bdrv_aio_readv  = curl_aio_readv,
 };
 
 static BlockDriver bdrv_ftps = {
-    .format_name                = "ftps",
-    .protocol_name              = "ftps",
+    .format_name     = "ftps",
+    .protocol_name   = "ftps",
 
-    .instance_size              = sizeof(BDRVCURLState),
-    .bdrv_parse_filename        = curl_parse_filename,
-    .bdrv_file_open             = curl_open,
-    .bdrv_close                 = curl_close,
-    .bdrv_getlength             = curl_getlength,
+    .instance_size   = sizeof(BDRVCURLState),
+    .bdrv_file_open  = curl_open,
+    .bdrv_close      = curl_close,
+    .bdrv_getlength  = curl_getlength,
 
-    .bdrv_aio_readv             = curl_aio_readv,
-
-    .bdrv_detach_aio_context    = curl_detach_aio_context,
-    .bdrv_attach_aio_context    = curl_attach_aio_context,
+    .bdrv_aio_readv  = curl_aio_readv,
 };
 
 static BlockDriver bdrv_tftp = {
-    .format_name                = "tftp",
-    .protocol_name              = "tftp",
+    .format_name     = "tftp",
+    .protocol_name   = "tftp",
 
-    .instance_size              = sizeof(BDRVCURLState),
-    .bdrv_parse_filename        = curl_parse_filename,
-    .bdrv_file_open             = curl_open,
-    .bdrv_close                 = curl_close,
-    .bdrv_getlength             = curl_getlength,
+    .instance_size   = sizeof(BDRVCURLState),
+    .bdrv_file_open  = curl_open,
+    .bdrv_close      = curl_close,
+    .bdrv_getlength  = curl_getlength,
 
-    .bdrv_aio_readv             = curl_aio_readv,
-
-    .bdrv_detach_aio_context    = curl_detach_aio_context,
-    .bdrv_attach_aio_context    = curl_attach_aio_context,
+    .bdrv_aio_readv  = curl_aio_readv,
 };
 
 static void curl_block_init(void)

block/dmg.c

@@ -22,19 +22,11 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/bswap.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "bswap.h"
+#include "module.h"
 #include <zlib.h>
 
-enum {
-    /* Limit chunk sizes to prevent unreasonable amounts of memory being used
-     * or truncating when converting to 32-bit types
-     */
-    DMG_LENGTHS_MAX = 64 * 1024 * 1024, /* 64 MB */
-    DMG_SECTORCOUNTS_MAX = DMG_LENGTHS_MAX / 512,
-};
-
 typedef struct BDRVDMGState {
     CoMutex lock;
     /* each chunk contains a certain number of sectors,
@@ -59,87 +51,35 @@ typedef struct BDRVDMGState {
 
 static int dmg_probe(const uint8_t *buf, int buf_size, const char *filename)
 {
-    int len;
-
-    if (!filename) {
-        return 0;
-    }
-
-    len = strlen(filename);
-    if (len > 4 && !strcmp(filename + len - 4, ".dmg")) {
-        return 2;
-    }
+    int len=strlen(filename);
+    if(len>4 && !strcmp(filename+len-4,".dmg"))
+	return 2;
     return 0;
 }
 
-static int read_uint64(BlockDriverState *bs, int64_t offset, uint64_t *result)
+static off_t read_off(BlockDriverState *bs, int64_t offset)
 {
-    uint64_t buffer;
-    int ret;
-
-    ret = bdrv_pread(bs->file, offset, &buffer, 8);
-    if (ret < 0) {
-        return ret;
-    }
-
-    *result = be64_to_cpu(buffer);
-    return 0;
+	uint64_t buffer;
+	if (bdrv_pread(bs->file, offset, &buffer, 8) < 8)
+		return 0;
+	return be64_to_cpu(buffer);
 }
 
-static int read_uint32(BlockDriverState *bs, int64_t offset, uint32_t *result)
+static off_t read_uint32(BlockDriverState *bs, int64_t offset)
 {
-    uint32_t buffer;
-    int ret;
-
-    ret = bdrv_pread(bs->file, offset, &buffer, 4);
-    if (ret < 0) {
-        return ret;
-    }
-
-    *result = be32_to_cpu(buffer);
-    return 0;
+	uint32_t buffer;
+	if (bdrv_pread(bs->file, offset, &buffer, 4) < 4)
+		return 0;
+	return be32_to_cpu(buffer);
 }
 
-/* Increase max chunk sizes, if necessary.  This function is used to calculate
- * the buffer sizes needed for compressed/uncompressed chunk I/O.
- */
-static void update_max_chunk_size(BDRVDMGState *s, uint32_t chunk,
-                                  uint32_t *max_compressed_size,
-                                  uint32_t *max_sectors_per_chunk)
-{
-    uint32_t compressed_size = 0;
-    uint32_t uncompressed_sectors = 0;
-
-    switch (s->types[chunk]) {
-    case 0x80000005: /* zlib compressed */
-        compressed_size = s->lengths[chunk];
-        uncompressed_sectors = s->sectorcounts[chunk];
-        break;
-    case 1: /* copy */
-        uncompressed_sectors = (s->lengths[chunk] + 511) / 512;
-        break;
-    case 2: /* zero */
-        uncompressed_sectors = s->sectorcounts[chunk];
-        break;
-    }
-
-    if (compressed_size > *max_compressed_size) {
-        *max_compressed_size = compressed_size;
-    }
-    if (uncompressed_sectors > *max_sectors_per_chunk) {
-        *max_sectors_per_chunk = uncompressed_sectors;
-    }
-}
-
-static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
-                    Error **errp)
+static int dmg_open(BlockDriverState *bs, int flags)
 {
     BDRVDMGState *s = bs->opaque;
-    uint64_t info_begin, info_end, last_in_offset, last_out_offset;
-    uint32_t count, tmp;
-    uint32_t max_compressed_size = 1, max_sectors_per_chunk = 1, i;
+    off_t info_begin,info_end,last_in_offset,last_out_offset;
+    uint32_t count;
+    uint32_t max_compressed_size=1,max_sectors_per_chunk=1,i;
     int64_t offset;
-    int ret;
 
     bs->read_only = 1;
     s->n_chunks = 0;
@@ -148,32 +88,21 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
     /* read offset of info blocks */
     offset = bdrv_getlength(bs->file);
     if (offset < 0) {
-        ret = offset;
         goto fail;
     }
     offset -= 0x1d8;
 
-    ret = read_uint64(bs, offset, &info_begin);
-    if (ret < 0) {
-        goto fail;
-    } else if (info_begin == 0) {
-        ret = -EINVAL;
+    info_begin = read_off(bs, offset);
+    if (info_begin == 0) {
+	goto fail;
+    }
+
+    if (read_uint32(bs, info_begin) != 0x100) {
         goto fail;
     }
 
-    ret = read_uint32(bs, info_begin, &tmp);
-    if (ret < 0) {
-        goto fail;
-    } else if (tmp != 0x100) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    ret = read_uint32(bs, info_begin + 4, &count);
-    if (ret < 0) {
-        goto fail;
-    } else if (count == 0) {
-        ret = -EINVAL;
+    count = read_uint32(bs, info_begin + 4);
+    if (count == 0) {
         goto fail;
     }
     info_end = info_begin + count;
@@ -185,205 +114,154 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
     while (offset < info_end) {
         uint32_t type;
 
-        ret = read_uint32(bs, offset, &count);
-        if (ret < 0) {
-            goto fail;
-        } else if (count == 0) {
-            ret = -EINVAL;
-            goto fail;
-        }
+	count = read_uint32(bs, offset);
+	if(count==0)
+	    goto fail;
         offset += 4;
 
-        ret = read_uint32(bs, offset, &type);
-        if (ret < 0) {
-            goto fail;
-        }
-
-        if (type == 0x6d697368 && count >= 244) {
-            size_t new_size;
-            uint32_t chunk_count;
+	type = read_uint32(bs, offset);
+	if (type == 0x6d697368 && count >= 244) {
+	    int new_size, chunk_count;
 
             offset += 4;
             offset += 200;
 
-            chunk_count = (count - 204) / 40;
-            new_size = sizeof(uint64_t) * (s->n_chunks + chunk_count);
-            s->types = g_realloc(s->types, new_size / 2);
-            s->offsets = g_realloc(s->offsets, new_size);
-            s->lengths = g_realloc(s->lengths, new_size);
-            s->sectors = g_realloc(s->sectors, new_size);
-            s->sectorcounts = g_realloc(s->sectorcounts, new_size);
+	    chunk_count = (count-204)/40;
+	    new_size = sizeof(uint64_t) * (s->n_chunks + chunk_count);
+	    s->types = g_realloc(s->types, new_size/2);
+	    s->offsets = g_realloc(s->offsets, new_size);
+	    s->lengths = g_realloc(s->lengths, new_size);
+	    s->sectors = g_realloc(s->sectors, new_size);
+	    s->sectorcounts = g_realloc(s->sectorcounts, new_size);
 
-            for (i = s->n_chunks; i < s->n_chunks + chunk_count; i++) {
-                ret = read_uint32(bs, offset, &s->types[i]);
-                if (ret < 0) {
-                    goto fail;
-                }
-                offset += 4;
-                if (s->types[i] != 0x80000005 && s->types[i] != 1 &&
-                    s->types[i] != 2) {
-                    if (s->types[i] == 0xffffffff && i > 0) {
-                        last_in_offset = s->offsets[i - 1] + s->lengths[i - 1];
-                        last_out_offset = s->sectors[i - 1] +
-                                          s->sectorcounts[i - 1];
-                    }
-                    chunk_count--;
-                    i--;
-                    offset += 36;
-                    continue;
-                }
-                offset += 4;
+	    for(i=s->n_chunks;i<s->n_chunks+chunk_count;i++) {
+		s->types[i] = read_uint32(bs, offset);
+		offset += 4;
+		if(s->types[i]!=0x80000005 && s->types[i]!=1 && s->types[i]!=2) {
+		    if(s->types[i]==0xffffffff) {
+			last_in_offset = s->offsets[i-1]+s->lengths[i-1];
+			last_out_offset = s->sectors[i-1]+s->sectorcounts[i-1];
+		    }
+		    chunk_count--;
+		    i--;
+		    offset += 36;
+		    continue;
+		}
+		offset += 4;
 
-                ret = read_uint64(bs, offset, &s->sectors[i]);
-                if (ret < 0) {
-                    goto fail;
-                }
-                s->sectors[i] += last_out_offset;
-                offset += 8;
+		s->sectors[i] = last_out_offset+read_off(bs, offset);
+		offset += 8;
 
-                ret = read_uint64(bs, offset, &s->sectorcounts[i]);
-                if (ret < 0) {
-                    goto fail;
-                }
-                offset += 8;
+		s->sectorcounts[i] = read_off(bs, offset);
+		offset += 8;
 
-                if (s->sectorcounts[i] > DMG_SECTORCOUNTS_MAX) {
-                    error_report("sector count %" PRIu64 " for chunk %" PRIu32
-                                 " is larger than max (%u)",
-                                 s->sectorcounts[i], i, DMG_SECTORCOUNTS_MAX);
-                    ret = -EINVAL;
-                    goto fail;
-                }
+		s->offsets[i] = last_in_offset+read_off(bs, offset);
+		offset += 8;
 
-                ret = read_uint64(bs, offset, &s->offsets[i]);
-                if (ret < 0) {
-                    goto fail;
-                }
-                s->offsets[i] += last_in_offset;
-                offset += 8;
+		s->lengths[i] = read_off(bs, offset);
+		offset += 8;
 
-                ret = read_uint64(bs, offset, &s->lengths[i]);
-                if (ret < 0) {
-                    goto fail;
-                }
-                offset += 8;
-
-                if (s->lengths[i] > DMG_LENGTHS_MAX) {
-                    error_report("length %" PRIu64 " for chunk %" PRIu32
-                                 " is larger than max (%u)",
-                                 s->lengths[i], i, DMG_LENGTHS_MAX);
-                    ret = -EINVAL;
-                    goto fail;
-                }
-
-                update_max_chunk_size(s, i, &max_compressed_size,
-                                      &max_sectors_per_chunk);
-            }
-            s->n_chunks += chunk_count;
-        }
+		if(s->lengths[i]>max_compressed_size)
+		    max_compressed_size = s->lengths[i];
+		if(s->sectorcounts[i]>max_sectors_per_chunk)
+		    max_sectors_per_chunk = s->sectorcounts[i];
+	    }
+	    s->n_chunks+=chunk_count;
+	}
     }
 
     /* initialize zlib engine */
-    s->compressed_chunk = g_malloc(max_compressed_size + 1);
-    s->uncompressed_chunk = g_malloc(512 * max_sectors_per_chunk);
-    if (inflateInit(&s->zstream) != Z_OK) {
-        ret = -EINVAL;
-        goto fail;
-    }
+    s->compressed_chunk = g_malloc(max_compressed_size+1);
+    s->uncompressed_chunk = g_malloc(512*max_sectors_per_chunk);
+    if(inflateInit(&s->zstream) != Z_OK)
+	goto fail;
 
     s->current_chunk = s->n_chunks;
 
     qemu_co_mutex_init(&s->lock);
     return 0;
-
 fail:
-    g_free(s->types);
-    g_free(s->offsets);
-    g_free(s->lengths);
-    g_free(s->sectors);
-    g_free(s->sectorcounts);
-    g_free(s->compressed_chunk);
-    g_free(s->uncompressed_chunk);
-    return ret;
+    return -1;
 }
 
 static inline int is_sector_in_chunk(BDRVDMGState* s,
-                uint32_t chunk_num, uint64_t sector_num)
+		uint32_t chunk_num,int sector_num)
 {
-    if (chunk_num >= s->n_chunks || s->sectors[chunk_num] > sector_num ||
-            s->sectors[chunk_num] + s->sectorcounts[chunk_num] <= sector_num) {
-        return 0;
-    } else {
-        return -1;
-    }
+    if(chunk_num>=s->n_chunks || s->sectors[chunk_num]>sector_num ||
+	    s->sectors[chunk_num]+s->sectorcounts[chunk_num]<=sector_num)
+	return 0;
+    else
+	return -1;
 }
 
-static inline uint32_t search_chunk(BDRVDMGState *s, uint64_t sector_num)
+static inline uint32_t search_chunk(BDRVDMGState* s,int sector_num)
 {
     /* binary search */
-    uint32_t chunk1 = 0, chunk2 = s->n_chunks, chunk3;
-    while (chunk1 != chunk2) {
-        chunk3 = (chunk1 + chunk2) / 2;
-        if (s->sectors[chunk3] > sector_num) {
-            chunk2 = chunk3;
-        } else if (s->sectors[chunk3] + s->sectorcounts[chunk3] > sector_num) {
-            return chunk3;
-        } else {
-            chunk1 = chunk3;
-        }
+    uint32_t chunk1=0,chunk2=s->n_chunks,chunk3;
+    while(chunk1!=chunk2) {
+	chunk3 = (chunk1+chunk2)/2;
+	if(s->sectors[chunk3]>sector_num)
+	    chunk2 = chunk3;
+	else if(s->sectors[chunk3]+s->sectorcounts[chunk3]>sector_num)
+	    return chunk3;
+	else
+	    chunk1 = chunk3;
     }
     return s->n_chunks; /* error */
 }
 
-static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num)
+static inline int dmg_read_chunk(BlockDriverState *bs, int sector_num)
 {
     BDRVDMGState *s = bs->opaque;
 
-    if (!is_sector_in_chunk(s, s->current_chunk, sector_num)) {
-        int ret;
-        uint32_t chunk = search_chunk(s, sector_num);
+    if(!is_sector_in_chunk(s,s->current_chunk,sector_num)) {
+	int ret;
+	uint32_t chunk = search_chunk(s,sector_num);
 
-        if (chunk >= s->n_chunks) {
-            return -1;
-        }
+	if(chunk>=s->n_chunks)
+	    return -1;
 
-        s->current_chunk = s->n_chunks;
-        switch (s->types[chunk]) {
-        case 0x80000005: { /* zlib compressed */
-            /* we need to buffer, because only the chunk as whole can be
-             * inflated. */
-            ret = bdrv_pread(bs->file, s->offsets[chunk],
-                             s->compressed_chunk, s->lengths[chunk]);
-            if (ret != s->lengths[chunk]) {
-                return -1;
-            }
+	s->current_chunk = s->n_chunks;
+	switch(s->types[chunk]) {
+	case 0x80000005: { /* zlib compressed */
+	    int i;
 
-            s->zstream.next_in = s->compressed_chunk;
-            s->zstream.avail_in = s->lengths[chunk];
-            s->zstream.next_out = s->uncompressed_chunk;
-            s->zstream.avail_out = 512 * s->sectorcounts[chunk];
-            ret = inflateReset(&s->zstream);
-            if (ret != Z_OK) {
-                return -1;
-            }
-            ret = inflate(&s->zstream, Z_FINISH);
-            if (ret != Z_STREAM_END ||
-                s->zstream.total_out != 512 * s->sectorcounts[chunk]) {
-                return -1;
-            }
-            break; }
-        case 1: /* copy */
-            ret = bdrv_pread(bs->file, s->offsets[chunk],
+	    /* we need to buffer, because only the chunk as whole can be
+	     * inflated. */
+	    i=0;
+	    do {
+                ret = bdrv_pread(bs->file, s->offsets[chunk] + i,
+                                 s->compressed_chunk+i, s->lengths[chunk]-i);
+		if(ret<0 && errno==EINTR)
+		    ret=0;
+		i+=ret;
+	    } while(ret>=0 && ret+i<s->lengths[chunk]);
+
+	    if (ret != s->lengths[chunk])
+		return -1;
+
+	    s->zstream.next_in = s->compressed_chunk;
+	    s->zstream.avail_in = s->lengths[chunk];
+	    s->zstream.next_out = s->uncompressed_chunk;
+	    s->zstream.avail_out = 512*s->sectorcounts[chunk];
+	    ret = inflateReset(&s->zstream);
+	    if(ret != Z_OK)
+		return -1;
+	    ret = inflate(&s->zstream, Z_FINISH);
+	    if(ret != Z_STREAM_END || s->zstream.total_out != 512*s->sectorcounts[chunk])
+		return -1;
+	    break; }
+	case 1: /* copy */
+	    ret = bdrv_pread(bs->file, s->offsets[chunk],
                              s->uncompressed_chunk, s->lengths[chunk]);
-            if (ret != s->lengths[chunk]) {
-                return -1;
-            }
-            break;
-        case 2: /* zero */
-            memset(s->uncompressed_chunk, 0, 512 * s->sectorcounts[chunk]);
-            break;
-        }
-        s->current_chunk = chunk;
+	    if (ret != s->lengths[chunk])
+		return -1;
+	    break;
+	case 2: /* zero */
+	    memset(s->uncompressed_chunk, 0, 512*s->sectorcounts[chunk]);
+	    break;
+	}
+	s->current_chunk = chunk;
     }
     return 0;
 }
@@ -394,14 +272,12 @@ static int dmg_read(BlockDriverState *bs, int64_t sector_num,
     BDRVDMGState *s = bs->opaque;
     int i;
 
-    for (i = 0; i < nb_sectors; i++) {
-        uint32_t sector_offset_in_chunk;
-        if (dmg_read_chunk(bs, sector_num + i) != 0) {
-            return -1;
-        }
-        sector_offset_in_chunk = sector_num + i - s->sectors[s->current_chunk];
-        memcpy(buf + i * 512,
-               s->uncompressed_chunk + sector_offset_in_chunk * 512, 512);
+    for(i=0;i<nb_sectors;i++) {
+	uint32_t sector_offset_in_chunk;
+	if(dmg_read_chunk(bs, sector_num+i) != 0)
+	    return -1;
+	sector_offset_in_chunk = sector_num+i-s->sectors[s->current_chunk];
+	memcpy(buf+i*512,s->uncompressed_chunk+sector_offset_in_chunk*512,512);
     }
     return 0;
 }
@@ -420,25 +296,25 @@ static coroutine_fn int dmg_co_read(BlockDriverState *bs, int64_t sector_num,
 static void dmg_close(BlockDriverState *bs)
 {
     BDRVDMGState *s = bs->opaque;
-
-    g_free(s->types);
-    g_free(s->offsets);
-    g_free(s->lengths);
-    g_free(s->sectors);
-    g_free(s->sectorcounts);
-    g_free(s->compressed_chunk);
-    g_free(s->uncompressed_chunk);
-
+    if(s->n_chunks>0) {
+	free(s->types);
+	free(s->offsets);
+	free(s->lengths);
+	free(s->sectors);
+	free(s->sectorcounts);
+    }
+    free(s->compressed_chunk);
+    free(s->uncompressed_chunk);
     inflateEnd(&s->zstream);
 }
 
 static BlockDriver bdrv_dmg = {
-    .format_name    = "dmg",
-    .instance_size  = sizeof(BDRVDMGState),
-    .bdrv_probe     = dmg_probe,
-    .bdrv_open      = dmg_open,
-    .bdrv_read      = dmg_co_read,
-    .bdrv_close     = dmg_close,
+    .format_name	= "dmg",
+    .instance_size	= sizeof(BDRVDMGState),
+    .bdrv_probe		= dmg_probe,
+    .bdrv_open		= dmg_open,
+    .bdrv_read          = dmg_co_read,
+    .bdrv_close		= dmg_close,
 };
 
 static void bdrv_dmg_init(void)

block/gluster.c

@@ -1,834 +0,0 @@
-/*
- * GlusterFS backend for QEMU
- *
- * Copyright (C) 2012 Bharata B Rao <bharata@linux.vnet.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- *
- */
-#include <glusterfs/api/glfs.h>
-#include "block/block_int.h"
-#include "qemu/uri.h"
-
-typedef struct GlusterAIOCB {
-    int64_t size;
-    int ret;
-    QEMUBH *bh;
-    Coroutine *coroutine;
-    AioContext *aio_context;
-} GlusterAIOCB;
-
-typedef struct BDRVGlusterState {
-    struct glfs *glfs;
-    struct glfs_fd *fd;
-} BDRVGlusterState;
-
-typedef struct GlusterConf {
-    char *server;
-    int port;
-    char *volname;
-    char *image;
-    char *transport;
-} GlusterConf;
-
-static void qemu_gluster_gconf_free(GlusterConf *gconf)
-{
-    if (gconf) {
-        g_free(gconf->server);
-        g_free(gconf->volname);
-        g_free(gconf->image);
-        g_free(gconf->transport);
-        g_free(gconf);
-    }
-}
-
-static int parse_volume_options(GlusterConf *gconf, char *path)
-{
-    char *p, *q;
-
-    if (!path) {
-        return -EINVAL;
-    }
-
-    /* volume */
-    p = q = path + strspn(path, "/");
-    p += strcspn(p, "/");
-    if (*p == '\0') {
-        return -EINVAL;
-    }
-    gconf->volname = g_strndup(q, p - q);
-
-    /* image */
-    p += strspn(p, "/");
-    if (*p == '\0') {
-        return -EINVAL;
-    }
-    gconf->image = g_strdup(p);
-    return 0;
-}
-
-/*
- * file=gluster[+transport]://[server[:port]]/volname/image[?socket=...]
- *
- * 'gluster' is the protocol.
- *
- * 'transport' specifies the transport type used to connect to gluster
- * management daemon (glusterd). Valid transport types are
- * tcp, unix and rdma. If a transport type isn't specified, then tcp
- * type is assumed.
- *
- * 'server' specifies the server where the volume file specification for
- * the given volume resides. This can be either hostname, ipv4 address
- * or ipv6 address. ipv6 address needs to be within square brackets [ ].
- * If transport type is 'unix', then 'server' field should not be specified.
- * The 'socket' field needs to be populated with the path to unix domain
- * socket.
- *
- * 'port' is the port number on which glusterd is listening. This is optional
- * and if not specified, QEMU will send 0 which will make gluster to use the
- * default port. If the transport type is unix, then 'port' should not be
- * specified.
- *
- * 'volname' is the name of the gluster volume which contains the VM image.
- *
- * 'image' is the path to the actual VM image that resides on gluster volume.
- *
- * Examples:
- *
- * file=gluster://1.2.3.4/testvol/a.img
- * file=gluster+tcp://1.2.3.4/testvol/a.img
- * file=gluster+tcp://1.2.3.4:24007/testvol/dir/a.img
- * file=gluster+tcp://[1:2:3:4:5:6:7:8]/testvol/dir/a.img
- * file=gluster+tcp://[1:2:3:4:5:6:7:8]:24007/testvol/dir/a.img
- * file=gluster+tcp://server.domain.com:24007/testvol/dir/a.img
- * file=gluster+unix:///testvol/dir/a.img?socket=/tmp/glusterd.socket
- * file=gluster+rdma://1.2.3.4:24007/testvol/a.img
- */
-static int qemu_gluster_parseuri(GlusterConf *gconf, const char *filename)
-{
-    URI *uri;
-    QueryParams *qp = NULL;
-    bool is_unix = false;
-    int ret = 0;
-
-    uri = uri_parse(filename);
-    if (!uri) {
-        return -EINVAL;
-    }
-
-    /* transport */
-    if (!uri->scheme || !strcmp(uri->scheme, "gluster")) {
-        gconf->transport = g_strdup("tcp");
-    } else if (!strcmp(uri->scheme, "gluster+tcp")) {
-        gconf->transport = g_strdup("tcp");
-    } else if (!strcmp(uri->scheme, "gluster+unix")) {
-        gconf->transport = g_strdup("unix");
-        is_unix = true;
-    } else if (!strcmp(uri->scheme, "gluster+rdma")) {
-        gconf->transport = g_strdup("rdma");
-    } else {
-        ret = -EINVAL;
-        goto out;
-    }
-
-    ret = parse_volume_options(gconf, uri->path);
-    if (ret < 0) {
-        goto out;
-    }
-
-    qp = query_params_parse(uri->query);
-    if (qp->n > 1 || (is_unix && !qp->n) || (!is_unix && qp->n)) {
-        ret = -EINVAL;
-        goto out;
-    }
-
-    if (is_unix) {
-        if (uri->server || uri->port) {
-            ret = -EINVAL;
-            goto out;
-        }
-        if (strcmp(qp->p[0].name, "socket")) {
-            ret = -EINVAL;
-            goto out;
-        }
-        gconf->server = g_strdup(qp->p[0].value);
-    } else {
-        gconf->server = g_strdup(uri->server ? uri->server : "localhost");
-        gconf->port = uri->port;
-    }
-
-out:
-    if (qp) {
-        query_params_free(qp);
-    }
-    uri_free(uri);
-    return ret;
-}
-
-static struct glfs *qemu_gluster_init(GlusterConf *gconf, const char *filename,
-                                      Error **errp)
-{
-    struct glfs *glfs = NULL;
-    int ret;
-    int old_errno;
-
-    ret = qemu_gluster_parseuri(gconf, filename);
-    if (ret < 0) {
-        error_setg(errp, "Usage: file=gluster[+transport]://[server[:port]]/"
-                   "volname/image[?socket=...]");
-        errno = -ret;
-        goto out;
-    }
-
-    glfs = glfs_new(gconf->volname);
-    if (!glfs) {
-        goto out;
-    }
-
-    ret = glfs_set_volfile_server(glfs, gconf->transport, gconf->server,
-            gconf->port);
-    if (ret < 0) {
-        goto out;
-    }
-
-    /*
-     * TODO: Use GF_LOG_ERROR instead of hard code value of 4 here when
-     * GlusterFS makes GF_LOG_* macros available to libgfapi users.
-     */
-    ret = glfs_set_logging(glfs, "-", 4);
-    if (ret < 0) {
-        goto out;
-    }
-
-    ret = glfs_init(glfs);
-    if (ret) {
-        error_setg_errno(errp, errno,
-                         "Gluster connection failed for server=%s port=%d "
-                         "volume=%s image=%s transport=%s", gconf->server,
-                         gconf->port, gconf->volname, gconf->image,
-                         gconf->transport);
-
-        /* glfs_init sometimes doesn't set errno although docs suggest that */
-        if (errno == 0)
-            errno = EINVAL;
-
-        goto out;
-    }
-    return glfs;
-
-out:
-    if (glfs) {
-        old_errno = errno;
-        glfs_fini(glfs);
-        errno = old_errno;
-    }
-    return NULL;
-}
-
-static void qemu_gluster_complete_aio(void *opaque)
-{
-    GlusterAIOCB *acb = (GlusterAIOCB *)opaque;
-
-    qemu_bh_delete(acb->bh);
-    acb->bh = NULL;
-    qemu_coroutine_enter(acb->coroutine, NULL);
-}
-
-/*
- * AIO callback routine called from GlusterFS thread.
- */
-static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg)
-{
-    GlusterAIOCB *acb = (GlusterAIOCB *)arg;
-
-    if (!ret || ret == acb->size) {
-        acb->ret = 0; /* Success */
-    } else if (ret < 0) {
-        acb->ret = ret; /* Read/Write failed */
-    } else {
-        acb->ret = -EIO; /* Partial read/write - fail it */
-    }
-
-    acb->bh = aio_bh_new(acb->aio_context, qemu_gluster_complete_aio, acb);
-    qemu_bh_schedule(acb->bh);
-}
-
-/* TODO Convert to fine grained options */
-static QemuOptsList runtime_opts = {
-    .name = "gluster",
-    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
-    .desc = {
-        {
-            .name = "filename",
-            .type = QEMU_OPT_STRING,
-            .help = "URL to the gluster image",
-        },
-        { /* end of list */ }
-    },
-};
-
-static void qemu_gluster_parse_flags(int bdrv_flags, int *open_flags)
-{
-    assert(open_flags != NULL);
-
-    *open_flags |= O_BINARY;
-
-    if (bdrv_flags & BDRV_O_RDWR) {
-        *open_flags |= O_RDWR;
-    } else {
-        *open_flags |= O_RDONLY;
-    }
-
-    if ((bdrv_flags & BDRV_O_NOCACHE)) {
-        *open_flags |= O_DIRECT;
-    }
-}
-
-static int qemu_gluster_open(BlockDriverState *bs,  QDict *options,
-                             int bdrv_flags, Error **errp)
-{
-    BDRVGlusterState *s = bs->opaque;
-    int open_flags = 0;
-    int ret = 0;
-    GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
-    QemuOpts *opts;
-    Error *local_err = NULL;
-    const char *filename;
-
-    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        ret = -EINVAL;
-        goto out;
-    }
-
-    filename = qemu_opt_get(opts, "filename");
-
-    s->glfs = qemu_gluster_init(gconf, filename, errp);
-    if (!s->glfs) {
-        ret = -errno;
-        goto out;
-    }
-
-    qemu_gluster_parse_flags(bdrv_flags, &open_flags);
-
-    s->fd = glfs_open(s->glfs, gconf->image, open_flags);
-    if (!s->fd) {
-        ret = -errno;
-    }
-
-out:
-    qemu_opts_del(opts);
-    qemu_gluster_gconf_free(gconf);
-    if (!ret) {
-        return ret;
-    }
-    if (s->fd) {
-        glfs_close(s->fd);
-    }
-    if (s->glfs) {
-        glfs_fini(s->glfs);
-    }
-    return ret;
-}
-
-typedef struct BDRVGlusterReopenState {
-    struct glfs *glfs;
-    struct glfs_fd *fd;
-} BDRVGlusterReopenState;
-
-
-static int qemu_gluster_reopen_prepare(BDRVReopenState *state,
-                                       BlockReopenQueue *queue, Error **errp)
-{
-    int ret = 0;
-    BDRVGlusterReopenState *reop_s;
-    GlusterConf *gconf = NULL;
-    int open_flags = 0;
-
-    assert(state != NULL);
-    assert(state->bs != NULL);
-
-    state->opaque = g_malloc0(sizeof(BDRVGlusterReopenState));
-    reop_s = state->opaque;
-
-    qemu_gluster_parse_flags(state->flags, &open_flags);
-
-    gconf = g_malloc0(sizeof(GlusterConf));
-
-    reop_s->glfs = qemu_gluster_init(gconf, state->bs->filename, errp);
-    if (reop_s->glfs == NULL) {
-        ret = -errno;
-        goto exit;
-    }
-
-    reop_s->fd = glfs_open(reop_s->glfs, gconf->image, open_flags);
-    if (reop_s->fd == NULL) {
-        /* reops->glfs will be cleaned up in _abort */
-        ret = -errno;
-        goto exit;
-    }
-
-exit:
-    /* state->opaque will be freed in either the _abort or _commit */
-    qemu_gluster_gconf_free(gconf);
-    return ret;
-}
-
-static void qemu_gluster_reopen_commit(BDRVReopenState *state)
-{
-    BDRVGlusterReopenState *reop_s = state->opaque;
-    BDRVGlusterState *s = state->bs->opaque;
-
-
-    /* close the old */
-    if (s->fd) {
-        glfs_close(s->fd);
-    }
-    if (s->glfs) {
-        glfs_fini(s->glfs);
-    }
-
-    /* use the newly opened image / connection */
-    s->fd         = reop_s->fd;
-    s->glfs       = reop_s->glfs;
-
-    g_free(state->opaque);
-    state->opaque = NULL;
-
-    return;
-}
-
-
-static void qemu_gluster_reopen_abort(BDRVReopenState *state)
-{
-    BDRVGlusterReopenState *reop_s = state->opaque;
-
-    if (reop_s == NULL) {
-        return;
-    }
-
-    if (reop_s->fd) {
-        glfs_close(reop_s->fd);
-    }
-
-    if (reop_s->glfs) {
-        glfs_fini(reop_s->glfs);
-    }
-
-    g_free(state->opaque);
-    state->opaque = NULL;
-
-    return;
-}
-
-#ifdef CONFIG_GLUSTERFS_ZEROFILL
-static coroutine_fn int qemu_gluster_co_write_zeroes(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, BdrvRequestFlags flags)
-{
-    int ret;
-    GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
-    BDRVGlusterState *s = bs->opaque;
-    off_t size = nb_sectors * BDRV_SECTOR_SIZE;
-    off_t offset = sector_num * BDRV_SECTOR_SIZE;
-
-    acb->size = size;
-    acb->ret = 0;
-    acb->coroutine = qemu_coroutine_self();
-    acb->aio_context = bdrv_get_aio_context(bs);
-
-    ret = glfs_zerofill_async(s->fd, offset, size, &gluster_finish_aiocb, acb);
-    if (ret < 0) {
-        ret = -errno;
-        goto out;
-    }
-
-    qemu_coroutine_yield();
-    ret = acb->ret;
-
-out:
-    g_slice_free(GlusterAIOCB, acb);
-    return ret;
-}
-
-static inline bool gluster_supports_zerofill(void)
-{
-    return 1;
-}
-
-static inline int qemu_gluster_zerofill(struct glfs_fd *fd, int64_t offset,
-        int64_t size)
-{
-    return glfs_zerofill(fd, offset, size);
-}
-
-#else
-static inline bool gluster_supports_zerofill(void)
-{
-    return 0;
-}
-
-static inline int qemu_gluster_zerofill(struct glfs_fd *fd, int64_t offset,
-        int64_t size)
-{
-    return 0;
-}
-#endif
-
-static int qemu_gluster_create(const char *filename,
-                               QemuOpts *opts, Error **errp)
-{
-    struct glfs *glfs;
-    struct glfs_fd *fd;
-    int ret = 0;
-    int prealloc = 0;
-    int64_t total_size = 0;
-    char *tmp = NULL;
-    GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
-
-    glfs = qemu_gluster_init(gconf, filename, errp);
-    if (!glfs) {
-        ret = -errno;
-        goto out;
-    }
-
-    total_size =
-        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / BDRV_SECTOR_SIZE;
-
-    tmp = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
-    if (!tmp || !strcmp(tmp, "off")) {
-        prealloc = 0;
-    } else if (!strcmp(tmp, "full") &&
-               gluster_supports_zerofill()) {
-        prealloc = 1;
-    } else {
-        error_setg(errp, "Invalid preallocation mode: '%s'"
-            " or GlusterFS doesn't support zerofill API",
-            tmp);
-        ret = -EINVAL;
-        goto out;
-    }
-
-    fd = glfs_creat(glfs, gconf->image,
-        O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, S_IRUSR | S_IWUSR);
-    if (!fd) {
-        ret = -errno;
-    } else {
-        if (!glfs_ftruncate(fd, total_size * BDRV_SECTOR_SIZE)) {
-            if (prealloc && qemu_gluster_zerofill(fd, 0,
-                    total_size * BDRV_SECTOR_SIZE)) {
-                ret = -errno;
-            }
-        } else {
-            ret = -errno;
-        }
-
-        if (glfs_close(fd) != 0) {
-            ret = -errno;
-        }
-    }
-out:
-    g_free(tmp);
-    qemu_gluster_gconf_free(gconf);
-    if (glfs) {
-        glfs_fini(glfs);
-    }
-    return ret;
-}
-
-static coroutine_fn int qemu_gluster_co_rw(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov, int write)
-{
-    int ret;
-    GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
-    BDRVGlusterState *s = bs->opaque;
-    size_t size = nb_sectors * BDRV_SECTOR_SIZE;
-    off_t offset = sector_num * BDRV_SECTOR_SIZE;
-
-    acb->size = size;
-    acb->ret = 0;
-    acb->coroutine = qemu_coroutine_self();
-    acb->aio_context = bdrv_get_aio_context(bs);
-
-    if (write) {
-        ret = glfs_pwritev_async(s->fd, qiov->iov, qiov->niov, offset, 0,
-            &gluster_finish_aiocb, acb);
-    } else {
-        ret = glfs_preadv_async(s->fd, qiov->iov, qiov->niov, offset, 0,
-            &gluster_finish_aiocb, acb);
-    }
-
-    if (ret < 0) {
-        ret = -errno;
-        goto out;
-    }
-
-    qemu_coroutine_yield();
-    ret = acb->ret;
-
-out:
-    g_slice_free(GlusterAIOCB, acb);
-    return ret;
-}
-
-static int qemu_gluster_truncate(BlockDriverState *bs, int64_t offset)
-{
-    int ret;
-    BDRVGlusterState *s = bs->opaque;
-
-    ret = glfs_ftruncate(s->fd, offset);
-    if (ret < 0) {
-        return -errno;
-    }
-
-    return 0;
-}
-
-static coroutine_fn int qemu_gluster_co_readv(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
-{
-    return qemu_gluster_co_rw(bs, sector_num, nb_sectors, qiov, 0);
-}
-
-static coroutine_fn int qemu_gluster_co_writev(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
-{
-    return qemu_gluster_co_rw(bs, sector_num, nb_sectors, qiov, 1);
-}
-
-static coroutine_fn int qemu_gluster_co_flush_to_disk(BlockDriverState *bs)
-{
-    int ret;
-    GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
-    BDRVGlusterState *s = bs->opaque;
-
-    acb->size = 0;
-    acb->ret = 0;
-    acb->coroutine = qemu_coroutine_self();
-    acb->aio_context = bdrv_get_aio_context(bs);
-
-    ret = glfs_fsync_async(s->fd, &gluster_finish_aiocb, acb);
-    if (ret < 0) {
-        ret = -errno;
-        goto out;
-    }
-
-    qemu_coroutine_yield();
-    ret = acb->ret;
-
-out:
-    g_slice_free(GlusterAIOCB, acb);
-    return ret;
-}
-
-#ifdef CONFIG_GLUSTERFS_DISCARD
-static coroutine_fn int qemu_gluster_co_discard(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors)
-{
-    int ret;
-    GlusterAIOCB *acb = g_slice_new(GlusterAIOCB);
-    BDRVGlusterState *s = bs->opaque;
-    size_t size = nb_sectors * BDRV_SECTOR_SIZE;
-    off_t offset = sector_num * BDRV_SECTOR_SIZE;
-
-    acb->size = 0;
-    acb->ret = 0;
-    acb->coroutine = qemu_coroutine_self();
-    acb->aio_context = bdrv_get_aio_context(bs);
-
-    ret = glfs_discard_async(s->fd, offset, size, &gluster_finish_aiocb, acb);
-    if (ret < 0) {
-        ret = -errno;
-        goto out;
-    }
-
-    qemu_coroutine_yield();
-    ret = acb->ret;
-
-out:
-    g_slice_free(GlusterAIOCB, acb);
-    return ret;
-}
-#endif
-
-static int64_t qemu_gluster_getlength(BlockDriverState *bs)
-{
-    BDRVGlusterState *s = bs->opaque;
-    int64_t ret;
-
-    ret = glfs_lseek(s->fd, 0, SEEK_END);
-    if (ret < 0) {
-        return -errno;
-    } else {
-        return ret;
-    }
-}
-
-static int64_t qemu_gluster_allocated_file_size(BlockDriverState *bs)
-{
-    BDRVGlusterState *s = bs->opaque;
-    struct stat st;
-    int ret;
-
-    ret = glfs_fstat(s->fd, &st);
-    if (ret < 0) {
-        return -errno;
-    } else {
-        return st.st_blocks * 512;
-    }
-}
-
-static void qemu_gluster_close(BlockDriverState *bs)
-{
-    BDRVGlusterState *s = bs->opaque;
-
-    if (s->fd) {
-        glfs_close(s->fd);
-        s->fd = NULL;
-    }
-    glfs_fini(s->glfs);
-}
-
-static int qemu_gluster_has_zero_init(BlockDriverState *bs)
-{
-    /* GlusterFS volume could be backed by a block device */
-    return 0;
-}
-
-static QemuOptsList qemu_gluster_create_opts = {
-    .name = "qemu-gluster-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(qemu_gluster_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        {
-            .name = BLOCK_OPT_PREALLOC,
-            .type = QEMU_OPT_STRING,
-            .help = "Preallocation mode (allowed values: off, full)"
-        },
-        { /* end of list */ }
-    }
-};
-
-static BlockDriver bdrv_gluster = {
-    .format_name                  = "gluster",
-    .protocol_name                = "gluster",
-    .instance_size                = sizeof(BDRVGlusterState),
-    .bdrv_needs_filename          = true,
-    .bdrv_file_open               = qemu_gluster_open,
-    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
-    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
-    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
-    .bdrv_close                   = qemu_gluster_close,
-    .bdrv_create                  = qemu_gluster_create,
-    .bdrv_getlength               = qemu_gluster_getlength,
-    .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
-    .bdrv_truncate                = qemu_gluster_truncate,
-    .bdrv_co_readv                = qemu_gluster_co_readv,
-    .bdrv_co_writev               = qemu_gluster_co_writev,
-    .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
-    .bdrv_has_zero_init           = qemu_gluster_has_zero_init,
-#ifdef CONFIG_GLUSTERFS_DISCARD
-    .bdrv_co_discard              = qemu_gluster_co_discard,
-#endif
-#ifdef CONFIG_GLUSTERFS_ZEROFILL
-    .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
-#endif
-    .create_opts                  = &qemu_gluster_create_opts,
-};
-
-static BlockDriver bdrv_gluster_tcp = {
-    .format_name                  = "gluster",
-    .protocol_name                = "gluster+tcp",
-    .instance_size                = sizeof(BDRVGlusterState),
-    .bdrv_needs_filename          = true,
-    .bdrv_file_open               = qemu_gluster_open,
-    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
-    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
-    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
-    .bdrv_close                   = qemu_gluster_close,
-    .bdrv_create                  = qemu_gluster_create,
-    .bdrv_getlength               = qemu_gluster_getlength,
-    .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
-    .bdrv_truncate                = qemu_gluster_truncate,
-    .bdrv_co_readv                = qemu_gluster_co_readv,
-    .bdrv_co_writev               = qemu_gluster_co_writev,
-    .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
-    .bdrv_has_zero_init           = qemu_gluster_has_zero_init,
-#ifdef CONFIG_GLUSTERFS_DISCARD
-    .bdrv_co_discard              = qemu_gluster_co_discard,
-#endif
-#ifdef CONFIG_GLUSTERFS_ZEROFILL
-    .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
-#endif
-    .create_opts                  = &qemu_gluster_create_opts,
-};
-
-static BlockDriver bdrv_gluster_unix = {
-    .format_name                  = "gluster",
-    .protocol_name                = "gluster+unix",
-    .instance_size                = sizeof(BDRVGlusterState),
-    .bdrv_needs_filename          = true,
-    .bdrv_file_open               = qemu_gluster_open,
-    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
-    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
-    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
-    .bdrv_close                   = qemu_gluster_close,
-    .bdrv_create                  = qemu_gluster_create,
-    .bdrv_getlength               = qemu_gluster_getlength,
-    .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
-    .bdrv_truncate                = qemu_gluster_truncate,
-    .bdrv_co_readv                = qemu_gluster_co_readv,
-    .bdrv_co_writev               = qemu_gluster_co_writev,
-    .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
-    .bdrv_has_zero_init           = qemu_gluster_has_zero_init,
-#ifdef CONFIG_GLUSTERFS_DISCARD
-    .bdrv_co_discard              = qemu_gluster_co_discard,
-#endif
-#ifdef CONFIG_GLUSTERFS_ZEROFILL
-    .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
-#endif
-    .create_opts                  = &qemu_gluster_create_opts,
-};
-
-static BlockDriver bdrv_gluster_rdma = {
-    .format_name                  = "gluster",
-    .protocol_name                = "gluster+rdma",
-    .instance_size                = sizeof(BDRVGlusterState),
-    .bdrv_needs_filename          = true,
-    .bdrv_file_open               = qemu_gluster_open,
-    .bdrv_reopen_prepare          = qemu_gluster_reopen_prepare,
-    .bdrv_reopen_commit           = qemu_gluster_reopen_commit,
-    .bdrv_reopen_abort            = qemu_gluster_reopen_abort,
-    .bdrv_close                   = qemu_gluster_close,
-    .bdrv_create                  = qemu_gluster_create,
-    .bdrv_getlength               = qemu_gluster_getlength,
-    .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
-    .bdrv_truncate                = qemu_gluster_truncate,
-    .bdrv_co_readv                = qemu_gluster_co_readv,
-    .bdrv_co_writev               = qemu_gluster_co_writev,
-    .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
-    .bdrv_has_zero_init           = qemu_gluster_has_zero_init,
-#ifdef CONFIG_GLUSTERFS_DISCARD
-    .bdrv_co_discard              = qemu_gluster_co_discard,
-#endif
-#ifdef CONFIG_GLUSTERFS_ZEROFILL
-    .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
-#endif
-    .create_opts                  = &qemu_gluster_create_opts,
-};
-
-static void bdrv_gluster_init(void)
-{
-    bdrv_register(&bdrv_gluster_rdma);
-    bdrv_register(&bdrv_gluster_unix);
-    bdrv_register(&bdrv_gluster_tcp);
-    bdrv_register(&bdrv_gluster);
-}
-
-block_init(bdrv_gluster_init);

block/linux-aio.c

@@ -1,319 +0,0 @@
-/*
- * Linux native AIO support.
- *
- * Copyright (C) 2009 IBM, Corp.
- * Copyright (C) 2009 Red Hat, Inc.
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-#include "qemu-common.h"
-#include "block/aio.h"
-#include "qemu/queue.h"
-#include "block/raw-aio.h"
-#include "qemu/event_notifier.h"
-
-#include <libaio.h>
-
-/*
- * Queue size (per-device).
- *
- * XXX: eventually we need to communicate this to the guest and/or make it
- *      tunable by the guest.  If we get more outstanding requests at a time
- *      than this we will get EAGAIN from io_submit which is communicated to
- *      the guest as an I/O error.
- */
-#define MAX_EVENTS 128
-
-#define MAX_QUEUED_IO  128
-
-struct qemu_laiocb {
-    BlockDriverAIOCB common;
-    struct qemu_laio_state *ctx;
-    struct iocb iocb;
-    ssize_t ret;
-    size_t nbytes;
-    QEMUIOVector *qiov;
-    bool is_read;
-    QLIST_ENTRY(qemu_laiocb) node;
-};
-
-typedef struct {
-    struct iocb *iocbs[MAX_QUEUED_IO];
-    int plugged;
-    unsigned int size;
-    unsigned int idx;
-} LaioQueue;
-
-struct qemu_laio_state {
-    io_context_t ctx;
-    EventNotifier e;
-
-    /* io queue for submit at batch */
-    LaioQueue io_q;
-};
-
-static inline ssize_t io_event_ret(struct io_event *ev)
-{
-    return (ssize_t)(((uint64_t)ev->res2 << 32) | ev->res);
-}
-
-/*
- * Completes an AIO request (calls the callback and frees the ACB).
- */
-static void qemu_laio_process_completion(struct qemu_laio_state *s,
-    struct qemu_laiocb *laiocb)
-{
-    int ret;
-
-    ret = laiocb->ret;
-    if (ret != -ECANCELED) {
-        if (ret == laiocb->nbytes) {
-            ret = 0;
-        } else if (ret >= 0) {
-            /* Short reads mean EOF, pad with zeros. */
-            if (laiocb->is_read) {
-                qemu_iovec_memset(laiocb->qiov, ret, 0,
-                    laiocb->qiov->size - ret);
-            } else {
-                ret = -EINVAL;
-            }
-        }
-
-        laiocb->common.cb(laiocb->common.opaque, ret);
-    }
-
-    qemu_aio_release(laiocb);
-}
-
-static void qemu_laio_completion_cb(EventNotifier *e)
-{
-    struct qemu_laio_state *s = container_of(e, struct qemu_laio_state, e);
-
-    while (event_notifier_test_and_clear(&s->e)) {
-        struct io_event events[MAX_EVENTS];
-        struct timespec ts = { 0 };
-        int nevents, i;
-
-        do {
-            nevents = io_getevents(s->ctx, MAX_EVENTS, MAX_EVENTS, events, &ts);
-        } while (nevents == -EINTR);
-
-        for (i = 0; i < nevents; i++) {
-            struct iocb *iocb = events[i].obj;
-            struct qemu_laiocb *laiocb =
-                    container_of(iocb, struct qemu_laiocb, iocb);
-
-            laiocb->ret = io_event_ret(&events[i]);
-            qemu_laio_process_completion(s, laiocb);
-        }
-    }
-}
-
-static void laio_cancel(BlockDriverAIOCB *blockacb)
-{
-    struct qemu_laiocb *laiocb = (struct qemu_laiocb *)blockacb;
-    struct io_event event;
-    int ret;
-
-    if (laiocb->ret != -EINPROGRESS)
-        return;
-
-    /*
-     * Note that as of Linux 2.6.31 neither the block device code nor any
-     * filesystem implements cancellation of AIO request.
-     * Thus the polling loop below is the normal code path.
-     */
-    ret = io_cancel(laiocb->ctx->ctx, &laiocb->iocb, &event);
-    if (ret == 0) {
-        laiocb->ret = -ECANCELED;
-        return;
-    }
-
-    /*
-     * We have to wait for the iocb to finish.
-     *
-     * The only way to get the iocb status update is by polling the io context.
-     * We might be able to do this slightly more optimal by removing the
-     * O_NONBLOCK flag.
-     */
-    while (laiocb->ret == -EINPROGRESS) {
-        qemu_laio_completion_cb(&laiocb->ctx->e);
-    }
-}
-
-static const AIOCBInfo laio_aiocb_info = {
-    .aiocb_size         = sizeof(struct qemu_laiocb),
-    .cancel             = laio_cancel,
-};
-
-static void ioq_init(LaioQueue *io_q)
-{
-    io_q->size = MAX_QUEUED_IO;
-    io_q->idx = 0;
-    io_q->plugged = 0;
-}
-
-static int ioq_submit(struct qemu_laio_state *s)
-{
-    int ret, i = 0;
-    int len = s->io_q.idx;
-
-    do {
-        ret = io_submit(s->ctx, len, s->io_q.iocbs);
-    } while (i++ < 3 && ret == -EAGAIN);
-
-    /* empty io queue */
-    s->io_q.idx = 0;
-
-    if (ret < 0) {
-        i = 0;
-    } else {
-        i = ret;
-    }
-
-    for (; i < len; i++) {
-        struct qemu_laiocb *laiocb =
-            container_of(s->io_q.iocbs[i], struct qemu_laiocb, iocb);
-
-        laiocb->ret = (ret < 0) ? ret : -EIO;
-        qemu_laio_process_completion(s, laiocb);
-    }
-    return ret;
-}
-
-static void ioq_enqueue(struct qemu_laio_state *s, struct iocb *iocb)
-{
-    unsigned int idx = s->io_q.idx;
-
-    s->io_q.iocbs[idx++] = iocb;
-    s->io_q.idx = idx;
-
-    /* submit immediately if queue is full */
-    if (idx == s->io_q.size) {
-        ioq_submit(s);
-    }
-}
-
-void laio_io_plug(BlockDriverState *bs, void *aio_ctx)
-{
-    struct qemu_laio_state *s = aio_ctx;
-
-    s->io_q.plugged++;
-}
-
-int laio_io_unplug(BlockDriverState *bs, void *aio_ctx, bool unplug)
-{
-    struct qemu_laio_state *s = aio_ctx;
-    int ret = 0;
-
-    assert(s->io_q.plugged > 0 || !unplug);
-
-    if (unplug && --s->io_q.plugged > 0) {
-        return 0;
-    }
-
-    if (s->io_q.idx > 0) {
-        ret = ioq_submit(s);
-    }
-
-    return ret;
-}
-
-BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque, int type)
-{
-    struct qemu_laio_state *s = aio_ctx;
-    struct qemu_laiocb *laiocb;
-    struct iocb *iocbs;
-    off_t offset = sector_num * 512;
-
-    laiocb = qemu_aio_get(&laio_aiocb_info, bs, cb, opaque);
-    laiocb->nbytes = nb_sectors * 512;
-    laiocb->ctx = s;
-    laiocb->ret = -EINPROGRESS;
-    laiocb->is_read = (type == QEMU_AIO_READ);
-    laiocb->qiov = qiov;
-
-    iocbs = &laiocb->iocb;
-
-    switch (type) {
-    case QEMU_AIO_WRITE:
-        io_prep_pwritev(iocbs, fd, qiov->iov, qiov->niov, offset);
-	break;
-    case QEMU_AIO_READ:
-        io_prep_preadv(iocbs, fd, qiov->iov, qiov->niov, offset);
-	break;
-    /* Currently Linux kernel does not support other operations */
-    default:
-        fprintf(stderr, "%s: invalid AIO request type 0x%x.\n",
-                        __func__, type);
-        goto out_free_aiocb;
-    }
-    io_set_eventfd(&laiocb->iocb, event_notifier_get_fd(&s->e));
-
-    if (!s->io_q.plugged) {
-        if (io_submit(s->ctx, 1, &iocbs) < 0) {
-            goto out_free_aiocb;
-        }
-    } else {
-        ioq_enqueue(s, iocbs);
-    }
-    return &laiocb->common;
-
-out_free_aiocb:
-    qemu_aio_release(laiocb);
-    return NULL;
-}
-
-void laio_detach_aio_context(void *s_, AioContext *old_context)
-{
-    struct qemu_laio_state *s = s_;
-
-    aio_set_event_notifier(old_context, &s->e, NULL);
-}
-
-void laio_attach_aio_context(void *s_, AioContext *new_context)
-{
-    struct qemu_laio_state *s = s_;
-
-    aio_set_event_notifier(new_context, &s->e, qemu_laio_completion_cb);
-}
-
-void *laio_init(void)
-{
-    struct qemu_laio_state *s;
-
-    s = g_malloc0(sizeof(*s));
-    if (event_notifier_init(&s->e, false) < 0) {
-        goto out_free_state;
-    }
-
-    if (io_setup(MAX_EVENTS, &s->ctx) != 0) {
-        goto out_close_efd;
-    }
-
-    ioq_init(&s->io_q);
-
-    return s;
-
-out_close_efd:
-    event_notifier_cleanup(&s->e);
-out_free_state:
-    g_free(s);
-    return NULL;
-}
-
-void laio_cleanup(void *s_)
-{
-    struct qemu_laio_state *s = s_;
-
-    event_notifier_cleanup(&s->e);
-
-    if (io_destroy(s->ctx) != 0) {
-        fprintf(stderr, "%s: destroy AIO context %p failed\n",
-                        __func__, &s->ctx);
-    }
-    g_free(s);
-}

block/mirror.c

@@ -1,744 +0,0 @@
-/*
- * Image mirroring
- *
- * Copyright Red Hat, Inc. 2012
- *
- * Authors:
- *  Paolo Bonzini  <pbonzini@redhat.com>
- *
- * This work is licensed under the terms of the GNU LGPL, version 2 or later.
- * See the COPYING.LIB file in the top-level directory.
- *
- */
-
-#include "trace.h"
-#include "block/blockjob.h"
-#include "block/block_int.h"
-#include "qemu/ratelimit.h"
-#include "qemu/bitmap.h"
-
-#define SLICE_TIME    100000000ULL /* ns */
-#define MAX_IN_FLIGHT 16
-
-/* The mirroring buffer is a list of granularity-sized chunks.
- * Free chunks are organized in a list.
- */
-typedef struct MirrorBuffer {
-    QSIMPLEQ_ENTRY(MirrorBuffer) next;
-} MirrorBuffer;
-
-typedef struct MirrorBlockJob {
-    BlockJob common;
-    RateLimit limit;
-    BlockDriverState *target;
-    BlockDriverState *base;
-    /* The name of the graph node to replace */
-    char *replaces;
-    /* The BDS to replace */
-    BlockDriverState *to_replace;
-    /* Used to block operations on the drive-mirror-replace target */
-    Error *replace_blocker;
-    bool is_none_mode;
-    BlockdevOnError on_source_error, on_target_error;
-    bool synced;
-    bool should_complete;
-    int64_t sector_num;
-    int64_t granularity;
-    size_t buf_size;
-    unsigned long *cow_bitmap;
-    BdrvDirtyBitmap *dirty_bitmap;
-    HBitmapIter hbi;
-    uint8_t *buf;
-    QSIMPLEQ_HEAD(, MirrorBuffer) buf_free;
-    int buf_free_count;
-
-    unsigned long *in_flight_bitmap;
-    int in_flight;
-    int ret;
-} MirrorBlockJob;
-
-typedef struct MirrorOp {
-    MirrorBlockJob *s;
-    QEMUIOVector qiov;
-    int64_t sector_num;
-    int nb_sectors;
-} MirrorOp;
-
-static BlockErrorAction mirror_error_action(MirrorBlockJob *s, bool read,
-                                            int error)
-{
-    s->synced = false;
-    if (read) {
-        return block_job_error_action(&s->common, s->common.bs,
-                                      s->on_source_error, true, error);
-    } else {
-        return block_job_error_action(&s->common, s->target,
-                                      s->on_target_error, false, error);
-    }
-}
-
-static void mirror_iteration_done(MirrorOp *op, int ret)
-{
-    MirrorBlockJob *s = op->s;
-    struct iovec *iov;
-    int64_t chunk_num;
-    int i, nb_chunks, sectors_per_chunk;
-
-    trace_mirror_iteration_done(s, op->sector_num, op->nb_sectors, ret);
-
-    s->in_flight--;
-    iov = op->qiov.iov;
-    for (i = 0; i < op->qiov.niov; i++) {
-        MirrorBuffer *buf = (MirrorBuffer *) iov[i].iov_base;
-        QSIMPLEQ_INSERT_TAIL(&s->buf_free, buf, next);
-        s->buf_free_count++;
-    }
-
-    sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
-    chunk_num = op->sector_num / sectors_per_chunk;
-    nb_chunks = op->nb_sectors / sectors_per_chunk;
-    bitmap_clear(s->in_flight_bitmap, chunk_num, nb_chunks);
-    if (s->cow_bitmap && ret >= 0) {
-        bitmap_set(s->cow_bitmap, chunk_num, nb_chunks);
-    }
-
-    qemu_iovec_destroy(&op->qiov);
-    g_slice_free(MirrorOp, op);
-
-    /* Enter coroutine when it is not sleeping.  The coroutine sleeps to
-     * rate-limit itself.  The coroutine will eventually resume since there is
-     * a sleep timeout so don't wake it early.
-     */
-    if (s->common.busy) {
-        qemu_coroutine_enter(s->common.co, NULL);
-    }
-}
-
-static void mirror_write_complete(void *opaque, int ret)
-{
-    MirrorOp *op = opaque;
-    MirrorBlockJob *s = op->s;
-    if (ret < 0) {
-        BlockDriverState *source = s->common.bs;
-        BlockErrorAction action;
-
-        bdrv_set_dirty(source, op->sector_num, op->nb_sectors);
-        action = mirror_error_action(s, false, -ret);
-        if (action == BLOCK_ERROR_ACTION_REPORT && s->ret >= 0) {
-            s->ret = ret;
-        }
-    }
-    mirror_iteration_done(op, ret);
-}
-
-static void mirror_read_complete(void *opaque, int ret)
-{
-    MirrorOp *op = opaque;
-    MirrorBlockJob *s = op->s;
-    if (ret < 0) {
-        BlockDriverState *source = s->common.bs;
-        BlockErrorAction action;
-
-        bdrv_set_dirty(source, op->sector_num, op->nb_sectors);
-        action = mirror_error_action(s, true, -ret);
-        if (action == BLOCK_ERROR_ACTION_REPORT && s->ret >= 0) {
-            s->ret = ret;
-        }
-
-        mirror_iteration_done(op, ret);
-        return;
-    }
-    bdrv_aio_writev(s->target, op->sector_num, &op->qiov, op->nb_sectors,
-                    mirror_write_complete, op);
-}
-
-static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
-{
-    BlockDriverState *source = s->common.bs;
-    int nb_sectors, sectors_per_chunk, nb_chunks;
-    int64_t end, sector_num, next_chunk, next_sector, hbitmap_next_sector;
-    uint64_t delay_ns;
-    MirrorOp *op;
-
-    s->sector_num = hbitmap_iter_next(&s->hbi);
-    if (s->sector_num < 0) {
-        bdrv_dirty_iter_init(source, s->dirty_bitmap, &s->hbi);
-        s->sector_num = hbitmap_iter_next(&s->hbi);
-        trace_mirror_restart_iter(s,
-                                  bdrv_get_dirty_count(source, s->dirty_bitmap));
-        assert(s->sector_num >= 0);
-    }
-
-    hbitmap_next_sector = s->sector_num;
-    sector_num = s->sector_num;
-    sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
-    end = s->common.len >> BDRV_SECTOR_BITS;
-
-    /* Extend the QEMUIOVector to include all adjacent blocks that will
-     * be copied in this operation.
-     *
-     * We have to do this if we have no backing file yet in the destination,
-     * and the cluster size is very large.  Then we need to do COW ourselves.
-     * The first time a cluster is copied, copy it entirely.  Note that,
-     * because both the granularity and the cluster size are powers of two,
-     * the number of sectors to copy cannot exceed one cluster.
-     *
-     * We also want to extend the QEMUIOVector to include more adjacent
-     * dirty blocks if possible, to limit the number of I/O operations and
-     * run efficiently even with a small granularity.
-     */
-    nb_chunks = 0;
-    nb_sectors = 0;
-    next_sector = sector_num;
-    next_chunk = sector_num / sectors_per_chunk;
-
-    /* Wait for I/O to this cluster (from a previous iteration) to be done.  */
-    while (test_bit(next_chunk, s->in_flight_bitmap)) {
-        trace_mirror_yield_in_flight(s, sector_num, s->in_flight);
-        qemu_coroutine_yield();
-    }
-
-    do {
-        int added_sectors, added_chunks;
-
-        if (!bdrv_get_dirty(source, s->dirty_bitmap, next_sector) ||
-            test_bit(next_chunk, s->in_flight_bitmap)) {
-            assert(nb_sectors > 0);
-            break;
-        }
-
-        added_sectors = sectors_per_chunk;
-        if (s->cow_bitmap && !test_bit(next_chunk, s->cow_bitmap)) {
-            bdrv_round_to_clusters(s->target,
-                                   next_sector, added_sectors,
-                                   &next_sector, &added_sectors);
-
-            /* On the first iteration, the rounding may make us copy
-             * sectors before the first dirty one.
-             */
-            if (next_sector < sector_num) {
-                assert(nb_sectors == 0);
-                sector_num = next_sector;
-                next_chunk = next_sector / sectors_per_chunk;
-            }
-        }
-
-        added_sectors = MIN(added_sectors, end - (sector_num + nb_sectors));
-        added_chunks = (added_sectors + sectors_per_chunk - 1) / sectors_per_chunk;
-
-        /* When doing COW, it may happen that there is not enough space for
-         * a full cluster.  Wait if that is the case.
-         */
-        while (nb_chunks == 0 && s->buf_free_count < added_chunks) {
-            trace_mirror_yield_buf_busy(s, nb_chunks, s->in_flight);
-            qemu_coroutine_yield();
-        }
-        if (s->buf_free_count < nb_chunks + added_chunks) {
-            trace_mirror_break_buf_busy(s, nb_chunks, s->in_flight);
-            break;
-        }
-
-        /* We have enough free space to copy these sectors.  */
-        bitmap_set(s->in_flight_bitmap, next_chunk, added_chunks);
-
-        nb_sectors += added_sectors;
-        nb_chunks += added_chunks;
-        next_sector += added_sectors;
-        next_chunk += added_chunks;
-        if (!s->synced && s->common.speed) {
-            delay_ns = ratelimit_calculate_delay(&s->limit, added_sectors);
-        } else {
-            delay_ns = 0;
-        }
-    } while (delay_ns == 0 && next_sector < end);
-
-    /* Allocate a MirrorOp that is used as an AIO callback.  */
-    op = g_slice_new(MirrorOp);
-    op->s = s;
-    op->sector_num = sector_num;
-    op->nb_sectors = nb_sectors;
-
-    /* Now make a QEMUIOVector taking enough granularity-sized chunks
-     * from s->buf_free.
-     */
-    qemu_iovec_init(&op->qiov, nb_chunks);
-    next_sector = sector_num;
-    while (nb_chunks-- > 0) {
-        MirrorBuffer *buf = QSIMPLEQ_FIRST(&s->buf_free);
-        size_t remaining = (nb_sectors * BDRV_SECTOR_SIZE) - op->qiov.size;
-
-        QSIMPLEQ_REMOVE_HEAD(&s->buf_free, next);
-        s->buf_free_count--;
-        qemu_iovec_add(&op->qiov, buf, MIN(s->granularity, remaining));
-
-        /* Advance the HBitmapIter in parallel, so that we do not examine
-         * the same sector twice.
-         */
-        if (next_sector > hbitmap_next_sector
-            && bdrv_get_dirty(source, s->dirty_bitmap, next_sector)) {
-            hbitmap_next_sector = hbitmap_iter_next(&s->hbi);
-        }
-
-        next_sector += sectors_per_chunk;
-    }
-
-    bdrv_reset_dirty(source, sector_num, nb_sectors);
-
-    /* Copy the dirty cluster.  */
-    s->in_flight++;
-    trace_mirror_one_iteration(s, sector_num, nb_sectors);
-    bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors,
-                   mirror_read_complete, op);
-    return delay_ns;
-}
-
-static void mirror_free_init(MirrorBlockJob *s)
-{
-    int granularity = s->granularity;
-    size_t buf_size = s->buf_size;
-    uint8_t *buf = s->buf;
-
-    assert(s->buf_free_count == 0);
-    QSIMPLEQ_INIT(&s->buf_free);
-    while (buf_size != 0) {
-        MirrorBuffer *cur = (MirrorBuffer *)buf;
-        QSIMPLEQ_INSERT_TAIL(&s->buf_free, cur, next);
-        s->buf_free_count++;
-        buf_size -= granularity;
-        buf += granularity;
-    }
-}
-
-static void mirror_drain(MirrorBlockJob *s)
-{
-    while (s->in_flight > 0) {
-        qemu_coroutine_yield();
-    }
-}
-
-static void coroutine_fn mirror_run(void *opaque)
-{
-    MirrorBlockJob *s = opaque;
-    BlockDriverState *bs = s->common.bs;
-    int64_t sector_num, end, sectors_per_chunk, length;
-    uint64_t last_pause_ns;
-    BlockDriverInfo bdi;
-    char backing_filename[1024];
-    int ret = 0;
-    int n;
-
-    if (block_job_is_cancelled(&s->common)) {
-        goto immediate_exit;
-    }
-
-    s->common.len = bdrv_getlength(bs);
-    if (s->common.len < 0) {
-        ret = s->common.len;
-        goto immediate_exit;
-    } else if (s->common.len == 0) {
-        /* Report BLOCK_JOB_READY and wait for complete. */
-        block_job_event_ready(&s->common);
-        s->synced = true;
-        while (!block_job_is_cancelled(&s->common) && !s->should_complete) {
-            block_job_yield(&s->common);
-        }
-        s->common.cancelled = false;
-        goto immediate_exit;
-    }
-
-    length = DIV_ROUND_UP(s->common.len, s->granularity);
-    s->in_flight_bitmap = bitmap_new(length);
-
-    /* If we have no backing file yet in the destination, we cannot let
-     * the destination do COW.  Instead, we copy sectors around the
-     * dirty data if needed.  We need a bitmap to do that.
-     */
-    bdrv_get_backing_filename(s->target, backing_filename,
-                              sizeof(backing_filename));
-    if (backing_filename[0] && !s->target->backing_hd) {
-        ret = bdrv_get_info(s->target, &bdi);
-        if (ret < 0) {
-            goto immediate_exit;
-        }
-        if (s->granularity < bdi.cluster_size) {
-            s->buf_size = MAX(s->buf_size, bdi.cluster_size);
-            s->cow_bitmap = bitmap_new(length);
-        }
-    }
-
-    end = s->common.len >> BDRV_SECTOR_BITS;
-    s->buf = qemu_blockalign(bs, s->buf_size);
-    sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
-    mirror_free_init(s);
-
-    if (!s->is_none_mode) {
-        /* First part, loop on the sectors and initialize the dirty bitmap.  */
-        BlockDriverState *base = s->base;
-        for (sector_num = 0; sector_num < end; ) {
-            int64_t next = (sector_num | (sectors_per_chunk - 1)) + 1;
-            ret = bdrv_is_allocated_above(bs, base,
-                                          sector_num, next - sector_num, &n);
-
-            if (ret < 0) {
-                goto immediate_exit;
-            }
-
-            assert(n > 0);
-            if (ret == 1) {
-                bdrv_set_dirty(bs, sector_num, n);
-                sector_num = next;
-            } else {
-                sector_num += n;
-            }
-        }
-    }
-
-    bdrv_dirty_iter_init(bs, s->dirty_bitmap, &s->hbi);
-    last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
-    for (;;) {
-        uint64_t delay_ns = 0;
-        int64_t cnt;
-        bool should_complete;
-
-        if (s->ret < 0) {
-            ret = s->ret;
-            goto immediate_exit;
-        }
-
-        cnt = bdrv_get_dirty_count(bs, s->dirty_bitmap);
-
-        /* Note that even when no rate limit is applied we need to yield
-         * periodically with no pending I/O so that qemu_aio_flush() returns.
-         * We do so every SLICE_TIME nanoseconds, or when there is an error,
-         * or when the source is clean, whichever comes first.
-         */
-        if (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - last_pause_ns < SLICE_TIME &&
-            s->common.iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
-            if (s->in_flight == MAX_IN_FLIGHT || s->buf_free_count == 0 ||
-                (cnt == 0 && s->in_flight > 0)) {
-                trace_mirror_yield(s, s->in_flight, s->buf_free_count, cnt);
-                qemu_coroutine_yield();
-                continue;
-            } else if (cnt != 0) {
-                delay_ns = mirror_iteration(s);
-                if (delay_ns == 0) {
-                    continue;
-                }
-            }
-        }
-
-        should_complete = false;
-        if (s->in_flight == 0 && cnt == 0) {
-            trace_mirror_before_flush(s);
-            ret = bdrv_flush(s->target);
-            if (ret < 0) {
-                if (mirror_error_action(s, false, -ret) ==
-                    BLOCK_ERROR_ACTION_REPORT) {
-                    goto immediate_exit;
-                }
-            } else {
-                /* We're out of the streaming phase.  From now on, if the job
-                 * is cancelled we will actually complete all pending I/O and
-                 * report completion.  This way, block-job-cancel will leave
-                 * the target in a consistent state.
-                 */
-                s->common.offset = end * BDRV_SECTOR_SIZE;
-                if (!s->synced) {
-                    block_job_event_ready(&s->common);
-                    s->synced = true;
-                }
-
-                should_complete = s->should_complete ||
-                    block_job_is_cancelled(&s->common);
-                cnt = bdrv_get_dirty_count(bs, s->dirty_bitmap);
-            }
-        }
-
-        if (cnt == 0 && should_complete) {
-            /* The dirty bitmap is not updated while operations are pending.
-             * If we're about to exit, wait for pending operations before
-             * calling bdrv_get_dirty_count(bs), or we may exit while the
-             * source has dirty data to copy!
-             *
-             * Note that I/O can be submitted by the guest while
-             * mirror_populate runs.
-             */
-            trace_mirror_before_drain(s, cnt);
-            bdrv_drain_all();
-            cnt = bdrv_get_dirty_count(bs, s->dirty_bitmap);
-        }
-
-        ret = 0;
-        trace_mirror_before_sleep(s, cnt, s->synced, delay_ns);
-        if (!s->synced) {
-            /* Publish progress */
-            s->common.offset = (end - cnt) * BDRV_SECTOR_SIZE;
-            block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, delay_ns);
-            if (block_job_is_cancelled(&s->common)) {
-                break;
-            }
-        } else if (!should_complete) {
-            delay_ns = (s->in_flight == 0 && cnt == 0 ? SLICE_TIME : 0);
-            block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, delay_ns);
-        } else if (cnt == 0) {
-            /* The two disks are in sync.  Exit and report successful
-             * completion.
-             */
-            assert(QLIST_EMPTY(&bs->tracked_requests));
-            s->common.cancelled = false;
-            break;
-        }
-        last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
-    }
-
-immediate_exit:
-    if (s->in_flight > 0) {
-        /* We get here only if something went wrong.  Either the job failed,
-         * or it was cancelled prematurely so that we do not guarantee that
-         * the target is a copy of the source.
-         */
-        assert(ret < 0 || (!s->synced && block_job_is_cancelled(&s->common)));
-        mirror_drain(s);
-    }
-
-    assert(s->in_flight == 0);
-    qemu_vfree(s->buf);
-    g_free(s->cow_bitmap);
-    g_free(s->in_flight_bitmap);
-    bdrv_release_dirty_bitmap(bs, s->dirty_bitmap);
-    bdrv_iostatus_disable(s->target);
-    if (s->should_complete && ret == 0) {
-        BlockDriverState *to_replace = s->common.bs;
-        if (s->to_replace) {
-            to_replace = s->to_replace;
-        }
-        if (bdrv_get_flags(s->target) != bdrv_get_flags(to_replace)) {
-            bdrv_reopen(s->target, bdrv_get_flags(to_replace), NULL);
-        }
-        bdrv_swap(s->target, to_replace);
-        if (s->common.driver->job_type == BLOCK_JOB_TYPE_COMMIT) {
-            /* drop the bs loop chain formed by the swap: break the loop then
-             * trigger the unref from the top one */
-            BlockDriverState *p = s->base->backing_hd;
-            bdrv_set_backing_hd(s->base, NULL);
-            bdrv_unref(p);
-        }
-    }
-    if (s->to_replace) {
-        bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
-        error_free(s->replace_blocker);
-        bdrv_unref(s->to_replace);
-    }
-    g_free(s->replaces);
-    bdrv_unref(s->target);
-    block_job_completed(&s->common, ret);
-}
-
-static void mirror_set_speed(BlockJob *job, int64_t speed, Error **errp)
-{
-    MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
-
-    if (speed < 0) {
-        error_set(errp, QERR_INVALID_PARAMETER, "speed");
-        return;
-    }
-    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
-}
-
-static void mirror_iostatus_reset(BlockJob *job)
-{
-    MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
-
-    bdrv_iostatus_reset(s->target);
-}
-
-static void mirror_complete(BlockJob *job, Error **errp)
-{
-    MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
-    Error *local_err = NULL;
-    int ret;
-
-    ret = bdrv_open_backing_file(s->target, NULL, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        return;
-    }
-    if (!s->synced) {
-        error_set(errp, QERR_BLOCK_JOB_NOT_READY, job->bs->device_name);
-        return;
-    }
-
-    /* check the target bs is not blocked and block all operations on it */
-    if (s->replaces) {
-        s->to_replace = check_to_replace_node(s->replaces, &local_err);
-        if (!s->to_replace) {
-            error_propagate(errp, local_err);
-            return;
-        }
-
-        error_setg(&s->replace_blocker,
-                   "block device is in use by block-job-complete");
-        bdrv_op_block_all(s->to_replace, s->replace_blocker);
-        bdrv_ref(s->to_replace);
-    }
-
-    s->should_complete = true;
-    block_job_resume(job);
-}
-
-static const BlockJobDriver mirror_job_driver = {
-    .instance_size = sizeof(MirrorBlockJob),
-    .job_type      = BLOCK_JOB_TYPE_MIRROR,
-    .set_speed     = mirror_set_speed,
-    .iostatus_reset= mirror_iostatus_reset,
-    .complete      = mirror_complete,
-};
-
-static const BlockJobDriver commit_active_job_driver = {
-    .instance_size = sizeof(MirrorBlockJob),
-    .job_type      = BLOCK_JOB_TYPE_COMMIT,
-    .set_speed     = mirror_set_speed,
-    .iostatus_reset
-                   = mirror_iostatus_reset,
-    .complete      = mirror_complete,
-};
-
-static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
-                             const char *replaces,
-                             int64_t speed, int64_t granularity,
-                             int64_t buf_size,
-                             BlockdevOnError on_source_error,
-                             BlockdevOnError on_target_error,
-                             BlockDriverCompletionFunc *cb,
-                             void *opaque, Error **errp,
-                             const BlockJobDriver *driver,
-                             bool is_none_mode, BlockDriverState *base)
-{
-    MirrorBlockJob *s;
-
-    if (granularity == 0) {
-        /* Choose the default granularity based on the target file's cluster
-         * size, clamped between 4k and 64k.  */
-        BlockDriverInfo bdi;
-        if (bdrv_get_info(target, &bdi) >= 0 && bdi.cluster_size != 0) {
-            granularity = MAX(4096, bdi.cluster_size);
-            granularity = MIN(65536, granularity);
-        } else {
-            granularity = 65536;
-        }
-    }
-
-    assert ((granularity & (granularity - 1)) == 0);
-
-    if ((on_source_error == BLOCKDEV_ON_ERROR_STOP ||
-         on_source_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        !bdrv_iostatus_is_enabled(bs)) {
-        error_set(errp, QERR_INVALID_PARAMETER, "on-source-error");
-        return;
-    }
-
-
-    s = block_job_create(driver, bs, speed, cb, opaque, errp);
-    if (!s) {
-        return;
-    }
-
-    s->replaces = g_strdup(replaces);
-    s->on_source_error = on_source_error;
-    s->on_target_error = on_target_error;
-    s->target = target;
-    s->is_none_mode = is_none_mode;
-    s->base = base;
-    s->granularity = granularity;
-    s->buf_size = MAX(buf_size, granularity);
-
-    s->dirty_bitmap = bdrv_create_dirty_bitmap(bs, granularity, errp);
-    if (!s->dirty_bitmap) {
-        return;
-    }
-    bdrv_set_enable_write_cache(s->target, true);
-    bdrv_set_on_error(s->target, on_target_error, on_target_error);
-    bdrv_iostatus_enable(s->target);
-    s->common.co = qemu_coroutine_create(mirror_run);
-    trace_mirror_start(bs, s, s->common.co, opaque);
-    qemu_coroutine_enter(s->common.co, s);
-}
-
-void mirror_start(BlockDriverState *bs, BlockDriverState *target,
-                  const char *replaces,
-                  int64_t speed, int64_t granularity, int64_t buf_size,
-                  MirrorSyncMode mode, BlockdevOnError on_source_error,
-                  BlockdevOnError on_target_error,
-                  BlockDriverCompletionFunc *cb,
-                  void *opaque, Error **errp)
-{
-    bool is_none_mode;
-    BlockDriverState *base;
-
-    is_none_mode = mode == MIRROR_SYNC_MODE_NONE;
-    base = mode == MIRROR_SYNC_MODE_TOP ? bs->backing_hd : NULL;
-    mirror_start_job(bs, target, replaces,
-                     speed, granularity, buf_size,
-                     on_source_error, on_target_error, cb, opaque, errp,
-                     &mirror_job_driver, is_none_mode, base);
-}
-
-void commit_active_start(BlockDriverState *bs, BlockDriverState *base,
-                         int64_t speed,
-                         BlockdevOnError on_error,
-                         BlockDriverCompletionFunc *cb,
-                         void *opaque, Error **errp)
-{
-    int64_t length, base_length;
-    int orig_base_flags;
-    int ret;
-    Error *local_err = NULL;
-
-    orig_base_flags = bdrv_get_flags(base);
-
-    if (bdrv_reopen(base, bs->open_flags, errp)) {
-        return;
-    }
-
-    length = bdrv_getlength(bs);
-    if (length < 0) {
-        error_setg_errno(errp, -length,
-                         "Unable to determine length of %s", bs->filename);
-        goto error_restore_flags;
-    }
-
-    base_length = bdrv_getlength(base);
-    if (base_length < 0) {
-        error_setg_errno(errp, -base_length,
-                         "Unable to determine length of %s", base->filename);
-        goto error_restore_flags;
-    }
-
-    if (length > base_length) {
-        ret = bdrv_truncate(base, length);
-        if (ret < 0) {
-            error_setg_errno(errp, -ret,
-                            "Top image %s is larger than base image %s, and "
-                             "resize of base image failed",
-                             bs->filename, base->filename);
-            goto error_restore_flags;
-        }
-    }
-
-    bdrv_ref(base);
-    mirror_start_job(bs, base, NULL, speed, 0, 0,
-                     on_error, on_error, cb, opaque, &local_err,
-                     &commit_active_job_driver, false, base);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        goto error_restore_flags;
-    }
-
-    return;
-
-error_restore_flags:
-    /* ignore error and errp for bdrv_reopen, because we want to propagate
-     * the original error */
-    bdrv_reopen(base, orig_base_flags, NULL);
-    return;
-}

block/nbd-client.c

@@ -1,404 +0,0 @@
-/*
- * QEMU Block driver for  NBD
- *
- * Copyright (C) 2008 Bull S.A.S.
- *     Author: Laurent Vivier <Laurent.Vivier@bull.net>
- *
- * Some parts:
- *    Copyright (C) 2007 Anthony Liguori <anthony@codemonkey.ws>
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
- */
-
-#include "nbd-client.h"
-#include "qemu/sockets.h"
-
-#define HANDLE_TO_INDEX(bs, handle) ((handle) ^ ((uint64_t)(intptr_t)bs))
-#define INDEX_TO_HANDLE(bs, index)  ((index)  ^ ((uint64_t)(intptr_t)bs))
-
-static void nbd_recv_coroutines_enter_all(NbdClientSession *s)
-{
-    int i;
-
-    for (i = 0; i < MAX_NBD_REQUESTS; i++) {
-        if (s->recv_coroutine[i]) {
-            qemu_coroutine_enter(s->recv_coroutine[i], NULL);
-        }
-    }
-}
-
-static void nbd_teardown_connection(NbdClientSession *client)
-{
-    /* finish any pending coroutines */
-    shutdown(client->sock, 2);
-    nbd_recv_coroutines_enter_all(client);
-
-    nbd_client_session_detach_aio_context(client);
-    closesocket(client->sock);
-    client->sock = -1;
-}
-
-static void nbd_reply_ready(void *opaque)
-{
-    NbdClientSession *s = opaque;
-    uint64_t i;
-    int ret;
-
-    if (s->reply.handle == 0) {
-        /* No reply already in flight.  Fetch a header.  It is possible
-         * that another thread has done the same thing in parallel, so
-         * the socket is not readable anymore.
-         */
-        ret = nbd_receive_reply(s->sock, &s->reply);
-        if (ret == -EAGAIN) {
-            return;
-        }
-        if (ret < 0) {
-            s->reply.handle = 0;
-            goto fail;
-        }
-    }
-
-    /* There's no need for a mutex on the receive side, because the
-     * handler acts as a synchronization point and ensures that only
-     * one coroutine is called until the reply finishes.  */
-    i = HANDLE_TO_INDEX(s, s->reply.handle);
-    if (i >= MAX_NBD_REQUESTS) {
-        goto fail;
-    }
-
-    if (s->recv_coroutine[i]) {
-        qemu_coroutine_enter(s->recv_coroutine[i], NULL);
-        return;
-    }
-
-fail:
-    nbd_teardown_connection(s);
-}
-
-static void nbd_restart_write(void *opaque)
-{
-    NbdClientSession *s = opaque;
-
-    qemu_coroutine_enter(s->send_coroutine, NULL);
-}
-
-static int nbd_co_send_request(NbdClientSession *s,
-    struct nbd_request *request,
-    QEMUIOVector *qiov, int offset)
-{
-    AioContext *aio_context;
-    int rc, ret;
-
-    qemu_co_mutex_lock(&s->send_mutex);
-    s->send_coroutine = qemu_coroutine_self();
-    aio_context = bdrv_get_aio_context(s->bs);
-    aio_set_fd_handler(aio_context, s->sock,
-                       nbd_reply_ready, nbd_restart_write, s);
-    if (qiov) {
-        if (!s->is_unix) {
-            socket_set_cork(s->sock, 1);
-        }
-        rc = nbd_send_request(s->sock, request);
-        if (rc >= 0) {
-            ret = qemu_co_sendv(s->sock, qiov->iov, qiov->niov,
-                                offset, request->len);
-            if (ret != request->len) {
-                rc = -EIO;
-            }
-        }
-        if (!s->is_unix) {
-            socket_set_cork(s->sock, 0);
-        }
-    } else {
-        rc = nbd_send_request(s->sock, request);
-    }
-    aio_set_fd_handler(aio_context, s->sock, nbd_reply_ready, NULL, s);
-    s->send_coroutine = NULL;
-    qemu_co_mutex_unlock(&s->send_mutex);
-    return rc;
-}
-
-static void nbd_co_receive_reply(NbdClientSession *s,
-    struct nbd_request *request, struct nbd_reply *reply,
-    QEMUIOVector *qiov, int offset)
-{
-    int ret;
-
-    /* Wait until we're woken up by the read handler.  TODO: perhaps
-     * peek at the next reply and avoid yielding if it's ours?  */
-    qemu_coroutine_yield();
-    *reply = s->reply;
-    if (reply->handle != request->handle) {
-        reply->error = EIO;
-    } else {
-        if (qiov && reply->error == 0) {
-            ret = qemu_co_recvv(s->sock, qiov->iov, qiov->niov,
-                                offset, request->len);
-            if (ret != request->len) {
-                reply->error = EIO;
-            }
-        }
-
-        /* Tell the read handler to read another header.  */
-        s->reply.handle = 0;
-    }
-}
-
-static void nbd_coroutine_start(NbdClientSession *s,
-   struct nbd_request *request)
-{
-    int i;
-
-    /* Poor man semaphore.  The free_sema is locked when no other request
-     * can be accepted, and unlocked after receiving one reply.  */
-    if (s->in_flight >= MAX_NBD_REQUESTS - 1) {
-        qemu_co_mutex_lock(&s->free_sema);
-        assert(s->in_flight < MAX_NBD_REQUESTS);
-    }
-    s->in_flight++;
-
-    for (i = 0; i < MAX_NBD_REQUESTS; i++) {
-        if (s->recv_coroutine[i] == NULL) {
-            s->recv_coroutine[i] = qemu_coroutine_self();
-            break;
-        }
-    }
-
-    assert(i < MAX_NBD_REQUESTS);
-    request->handle = INDEX_TO_HANDLE(s, i);
-}
-
-static void nbd_coroutine_end(NbdClientSession *s,
-    struct nbd_request *request)
-{
-    int i = HANDLE_TO_INDEX(s, request->handle);
-    s->recv_coroutine[i] = NULL;
-    if (s->in_flight-- == MAX_NBD_REQUESTS) {
-        qemu_co_mutex_unlock(&s->free_sema);
-    }
-}
-
-static int nbd_co_readv_1(NbdClientSession *client, int64_t sector_num,
-                          int nb_sectors, QEMUIOVector *qiov,
-                          int offset)
-{
-    struct nbd_request request = { .type = NBD_CMD_READ };
-    struct nbd_reply reply;
-    ssize_t ret;
-
-    request.from = sector_num * 512;
-    request.len = nb_sectors * 512;
-
-    nbd_coroutine_start(client, &request);
-    ret = nbd_co_send_request(client, &request, NULL, 0);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(client, &request, &reply, qiov, offset);
-    }
-    nbd_coroutine_end(client, &request);
-    return -reply.error;
-
-}
-
-static int nbd_co_writev_1(NbdClientSession *client, int64_t sector_num,
-                           int nb_sectors, QEMUIOVector *qiov,
-                           int offset)
-{
-    struct nbd_request request = { .type = NBD_CMD_WRITE };
-    struct nbd_reply reply;
-    ssize_t ret;
-
-    if (!bdrv_enable_write_cache(client->bs) &&
-        (client->nbdflags & NBD_FLAG_SEND_FUA)) {
-        request.type |= NBD_CMD_FLAG_FUA;
-    }
-
-    request.from = sector_num * 512;
-    request.len = nb_sectors * 512;
-
-    nbd_coroutine_start(client, &request);
-    ret = nbd_co_send_request(client, &request, qiov, offset);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(client, &request, &reply, NULL, 0);
-    }
-    nbd_coroutine_end(client, &request);
-    return -reply.error;
-}
-
-/* qemu-nbd has a limit of slightly less than 1M per request.  Try to
- * remain aligned to 4K. */
-#define NBD_MAX_SECTORS 2040
-
-int nbd_client_session_co_readv(NbdClientSession *client, int64_t sector_num,
-    int nb_sectors, QEMUIOVector *qiov)
-{
-    int offset = 0;
-    int ret;
-    while (nb_sectors > NBD_MAX_SECTORS) {
-        ret = nbd_co_readv_1(client, sector_num,
-                             NBD_MAX_SECTORS, qiov, offset);
-        if (ret < 0) {
-            return ret;
-        }
-        offset += NBD_MAX_SECTORS * 512;
-        sector_num += NBD_MAX_SECTORS;
-        nb_sectors -= NBD_MAX_SECTORS;
-    }
-    return nbd_co_readv_1(client, sector_num, nb_sectors, qiov, offset);
-}
-
-int nbd_client_session_co_writev(NbdClientSession *client, int64_t sector_num,
-                                 int nb_sectors, QEMUIOVector *qiov)
-{
-    int offset = 0;
-    int ret;
-    while (nb_sectors > NBD_MAX_SECTORS) {
-        ret = nbd_co_writev_1(client, sector_num,
-                              NBD_MAX_SECTORS, qiov, offset);
-        if (ret < 0) {
-            return ret;
-        }
-        offset += NBD_MAX_SECTORS * 512;
-        sector_num += NBD_MAX_SECTORS;
-        nb_sectors -= NBD_MAX_SECTORS;
-    }
-    return nbd_co_writev_1(client, sector_num, nb_sectors, qiov, offset);
-}
-
-int nbd_client_session_co_flush(NbdClientSession *client)
-{
-    struct nbd_request request = { .type = NBD_CMD_FLUSH };
-    struct nbd_reply reply;
-    ssize_t ret;
-
-    if (!(client->nbdflags & NBD_FLAG_SEND_FLUSH)) {
-        return 0;
-    }
-
-    if (client->nbdflags & NBD_FLAG_SEND_FUA) {
-        request.type |= NBD_CMD_FLAG_FUA;
-    }
-
-    request.from = 0;
-    request.len = 0;
-
-    nbd_coroutine_start(client, &request);
-    ret = nbd_co_send_request(client, &request, NULL, 0);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(client, &request, &reply, NULL, 0);
-    }
-    nbd_coroutine_end(client, &request);
-    return -reply.error;
-}
-
-int nbd_client_session_co_discard(NbdClientSession *client, int64_t sector_num,
-    int nb_sectors)
-{
-    struct nbd_request request = { .type = NBD_CMD_TRIM };
-    struct nbd_reply reply;
-    ssize_t ret;
-
-    if (!(client->nbdflags & NBD_FLAG_SEND_TRIM)) {
-        return 0;
-    }
-    request.from = sector_num * 512;
-    request.len = nb_sectors * 512;
-
-    nbd_coroutine_start(client, &request);
-    ret = nbd_co_send_request(client, &request, NULL, 0);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(client, &request, &reply, NULL, 0);
-    }
-    nbd_coroutine_end(client, &request);
-    return -reply.error;
-
-}
-
-void nbd_client_session_detach_aio_context(NbdClientSession *client)
-{
-    aio_set_fd_handler(bdrv_get_aio_context(client->bs), client->sock,
-                       NULL, NULL, NULL);
-}
-
-void nbd_client_session_attach_aio_context(NbdClientSession *client,
-                                           AioContext *new_context)
-{
-    aio_set_fd_handler(new_context, client->sock,
-                       nbd_reply_ready, NULL, client);
-}
-
-void nbd_client_session_close(NbdClientSession *client)
-{
-    struct nbd_request request = {
-        .type = NBD_CMD_DISC,
-        .from = 0,
-        .len = 0
-    };
-
-    if (!client->bs) {
-        return;
-    }
-    if (client->sock == -1) {
-        return;
-    }
-
-    nbd_send_request(client->sock, &request);
-
-    nbd_teardown_connection(client);
-    client->bs = NULL;
-}
-
-int nbd_client_session_init(NbdClientSession *client, BlockDriverState *bs,
-    int sock, const char *export)
-{
-    int ret;
-
-    /* NBD handshake */
-    logout("session init %s\n", export);
-    qemu_set_block(sock);
-    ret = nbd_receive_negotiate(sock, export,
-                                &client->nbdflags, &client->size,
-                                &client->blocksize);
-    if (ret < 0) {
-        logout("Failed to negotiate with the NBD server\n");
-        closesocket(sock);
-        return ret;
-    }
-
-    qemu_co_mutex_init(&client->send_mutex);
-    qemu_co_mutex_init(&client->free_sema);
-    client->bs = bs;
-    client->sock = sock;
-
-    /* Now that we're connected, set the socket to be non-blocking and
-     * kick the reply mechanism.  */
-    qemu_set_nonblock(sock);
-    nbd_client_session_attach_aio_context(client, bdrv_get_aio_context(bs));
-
-    logout("Established connection with NBD server\n");
-    return 0;
-}

block/nbd-client.h

@@ -1,54 +0,0 @@
-#ifndef NBD_CLIENT_H
-#define NBD_CLIENT_H
-
-#include "qemu-common.h"
-#include "block/nbd.h"
-#include "block/block_int.h"
-
-/* #define DEBUG_NBD */
-
-#if defined(DEBUG_NBD)
-#define logout(fmt, ...) \
-    fprintf(stderr, "nbd\t%-24s" fmt, __func__, ##__VA_ARGS__)
-#else
-#define logout(fmt, ...) ((void)0)
-#endif
-
-#define MAX_NBD_REQUESTS    16
-
-typedef struct NbdClientSession {
-    int sock;
-    uint32_t nbdflags;
-    off_t size;
-    size_t blocksize;
-
-    CoMutex send_mutex;
-    CoMutex free_sema;
-    Coroutine *send_coroutine;
-    int in_flight;
-
-    Coroutine *recv_coroutine[MAX_NBD_REQUESTS];
-    struct nbd_reply reply;
-
-    bool is_unix;
-
-    BlockDriverState *bs;
-} NbdClientSession;
-
-int nbd_client_session_init(NbdClientSession *client, BlockDriverState *bs,
-                            int sock, const char *export_name);
-void nbd_client_session_close(NbdClientSession *client);
-
-int nbd_client_session_co_discard(NbdClientSession *client, int64_t sector_num,
-                                  int nb_sectors);
-int nbd_client_session_co_flush(NbdClientSession *client);
-int nbd_client_session_co_writev(NbdClientSession *client, int64_t sector_num,
-                                 int nb_sectors, QEMUIOVector *qiov);
-int nbd_client_session_co_readv(NbdClientSession *client, int64_t sector_num,
-                                int nb_sectors, QEMUIOVector *qiov);
-
-void nbd_client_session_detach_aio_context(NbdClientSession *client);
-void nbd_client_session_attach_aio_context(NbdClientSession *client,
-                                           AioContext *new_context);
-
-#endif /* NBD_CLIENT_H */

block/nbd.c

@@ -26,124 +26,47 @@
  * THE SOFTWARE.
  */
 
-#include "block/nbd-client.h"
-#include "qemu/uri.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
-#include "qemu/sockets.h"
-#include "qapi/qmp/qjson.h"
-#include "qapi/qmp/qint.h"
+#include "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 {
-    NbdClientSession client;
-    QemuOpts *socket_opts;
+    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_parse_uri(const char *filename, QDict *options)
-{
-    URI *uri;
-    const char *p;
-    QueryParams *qp = NULL;
-    int ret = 0;
-    bool is_unix;
-
-    uri = uri_parse(filename);
-    if (!uri) {
-        return -EINVAL;
-    }
-
-    /* transport */
-    if (!strcmp(uri->scheme, "nbd")) {
-        is_unix = false;
-    } else if (!strcmp(uri->scheme, "nbd+tcp")) {
-        is_unix = false;
-    } else if (!strcmp(uri->scheme, "nbd+unix")) {
-        is_unix = true;
-    } else {
-        ret = -EINVAL;
-        goto out;
-    }
-
-    p = uri->path ? uri->path : "/";
-    p += strspn(p, "/");
-    if (p[0]) {
-        qdict_put(options, "export", qstring_from_str(p));
-    }
-
-    qp = query_params_parse(uri->query);
-    if (qp->n > 1 || (is_unix && !qp->n) || (!is_unix && qp->n)) {
-        ret = -EINVAL;
-        goto out;
-    }
-
-    if (is_unix) {
-        /* nbd+unix:///export?socket=path */
-        if (uri->server || uri->port || strcmp(qp->p[0].name, "socket")) {
-            ret = -EINVAL;
-            goto out;
-        }
-        qdict_put(options, "path", qstring_from_str(qp->p[0].value));
-    } else {
-        QString *host;
-        /* nbd[+tcp]://host[:port]/export */
-        if (!uri->server) {
-            ret = -EINVAL;
-            goto out;
-        }
-
-        /* strip braces from literal IPv6 address */
-        if (uri->server[0] == '[') {
-            host = qstring_from_substr(uri->server, 1,
-                                       strlen(uri->server) - 2);
-        } else {
-            host = qstring_from_str(uri->server);
-        }
-
-        qdict_put(options, "host", host);
-        if (uri->port) {
-            char* port_str = g_strdup_printf("%d", uri->port);
-            qdict_put(options, "port", qstring_from_str(port_str));
-            g_free(port_str);
-        }
-    }
-
-out:
-    if (qp) {
-        query_params_free(qp);
-    }
-    uri_free(uri);
-    return ret;
-}
-
-static void nbd_parse_filename(const char *filename, QDict *options,
-                               Error **errp)
+static int nbd_config(BDRVNBDState *s, const char *filename, int flags)
 {
     char *file;
     char *export_name;
     const char *host_spec;
     const char *unixpath;
-
-    if (qdict_haskey(options, "host")
-        || qdict_haskey(options, "port")
-        || qdict_haskey(options, "path"))
-    {
-        error_setg(errp, "host/port/path and a file name may not be specified "
-                         "at the same time");
-        return;
-    }
-
-    if (strstr(filename, "://")) {
-        int ret = nbd_parse_uri(filename, options);
-        if (ret < 0) {
-            error_setg(errp, "No valid URL specified");
-        }
-        return;
-    }
+    int err = -EINVAL;
 
     file = g_strdup(filename);
 
@@ -154,243 +77,221 @@ static void nbd_parse_filename(const char *filename, QDict *options,
         }
         export_name[0] = 0; /* truncate 'file' */
         export_name += strlen(EN_OPTSTR);
-
-        qdict_put(options, "export", qstring_from_str(export_name));
+        s->export_name = g_strdup(export_name);
     }
 
     /* extract the host_spec - fail if it's not nbd:... */
     if (!strstart(file, "nbd:", &host_spec)) {
-        error_setg(errp, "File name string for NBD must start with 'nbd:'");
-        goto out;
-    }
-
-    if (!*host_spec) {
         goto out;
     }
 
     /* are we a UNIX or TCP socket? */
     if (strstart(host_spec, "unix:", &unixpath)) {
-        qdict_put(options, "path", qstring_from_str(unixpath));
-    } else {
-        InetSocketAddress *addr = NULL;
-
-        addr = inet_parse(host_spec, errp);
-        if (!addr) {
+        if (unixpath[0] != '/') { /* We demand  an absolute path*/
             goto out;
         }
-
-        qdict_put(options, "host", qstring_from_str(addr->host));
-        qdict_put(options, "port", qstring_from_str(addr->port));
-        qapi_free_InetSocketAddress(addr);
+        s->host_spec = g_strdup(unixpath);
+    } else {
+        s->host_spec = g_strdup(host_spec);
     }
 
+    err = 0;
+
 out:
     g_free(file);
+    if (err != 0) {
+        g_free(s->export_name);
+        g_free(s->host_spec);
+    }
+    return err;
 }
 
-static void nbd_config(BDRVNBDState *s, QDict *options, char **export,
-                       Error **errp)
-{
-    Error *local_err = NULL;
-
-    if (qdict_haskey(options, "path") == qdict_haskey(options, "host")) {
-        if (qdict_haskey(options, "path")) {
-            error_setg(errp, "path and host may not be used at the same time.");
-        } else {
-            error_setg(errp, "one of path and host must be specified.");
-        }
-        return;
-    }
-
-    s->client.is_unix = qdict_haskey(options, "path");
-    s->socket_opts = qemu_opts_create(&socket_optslist, NULL, 0,
-                                      &error_abort);
-
-    qemu_opts_absorb_qdict(s->socket_opts, options, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        return;
-    }
-
-    if (!qemu_opt_get(s->socket_opts, "port")) {
-        qemu_opt_set_number(s->socket_opts, "port", NBD_DEFAULT_PORT);
-    }
-
-    *export = g_strdup(qdict_get_try_str(options, "export"));
-    if (*export) {
-        qdict_del(options, "export");
-    }
-}
-
-static int nbd_establish_connection(BlockDriverState *bs, Error **errp)
+static int nbd_establish_connection(BlockDriverState *bs)
 {
     BDRVNBDState *s = bs->opaque;
     int sock;
+    int ret;
+    off_t size;
+    size_t blocksize;
 
-    if (s->client.is_unix) {
-        sock = unix_connect_opts(s->socket_opts, errp, NULL, NULL);
+    if (s->host_spec[0] == '/') {
+        sock = unix_socket_outgoing(s->host_spec);
     } else {
-        sock = inet_connect_opts(s->socket_opts, errp, NULL, NULL);
-        if (sock >= 0) {
-            socket_set_nodelay(sock);
-        }
+        sock = tcp_socket_outgoing_spec(s->host_spec);
     }
 
     /* Failed to establish connection */
-    if (sock < 0) {
+    if (sock == -1) {
         logout("Failed to establish connection to NBD server\n");
         return -errno;
     }
 
-    return sock;
+    /* 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);
+        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 int nbd_open(BlockDriverState *bs, QDict *options, int flags,
-                    Error **errp)
+static void nbd_teardown_connection(BlockDriverState *bs)
 {
     BDRVNBDState *s = bs->opaque;
-    char *export = NULL;
-    int result, sock;
-    Error *local_err = NULL;
+    struct nbd_request request;
+
+    request.type = NBD_CMD_DISC;
+    request.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. */
-    nbd_config(s, options, &export, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        return -EINVAL;
+    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.
      */
-    sock = nbd_establish_connection(bs, errp);
-    if (sock < 0) {
-        return sock;
-    }
+    result = nbd_establish_connection(bs);
 
-    /* NBD handshake */
-    result = nbd_client_session_init(&s->client, bs, sock, export);
-    g_free(export);
+    qemu_co_mutex_init(&s->lock);
     return result;
 }
 
-static int nbd_co_readv(BlockDriverState *bs, int64_t sector_num,
-                        int nb_sectors, QEMUIOVector *qiov)
+static int nbd_read(BlockDriverState *bs, int64_t sector_num,
+                    uint8_t *buf, int nb_sectors)
 {
     BDRVNBDState *s = bs->opaque;
+    struct nbd_request request;
+    struct nbd_reply reply;
 
-    return nbd_client_session_co_readv(&s->client, sector_num,
-                                       nb_sectors, qiov);
+    request.type = NBD_CMD_READ;
+    request.handle = (uint64_t)(intptr_t)bs;
+    request.from = sector_num * 512;;
+    request.len = nb_sectors * 512;
+
+    if (nbd_send_request(s->sock, &request) == -1)
+        return -errno;
+
+    if (nbd_receive_reply(s->sock, &reply) == -1)
+        return -errno;
+
+    if (reply.error !=0)
+        return -reply.error;
+
+    if (reply.handle != request.handle)
+        return -EIO;
+
+    if (nbd_wr_sync(s->sock, buf, request.len, 1) != request.len)
+        return -EIO;
+
+    return 0;
 }
 
-static int nbd_co_writev(BlockDriverState *bs, int64_t sector_num,
-                         int nb_sectors, QEMUIOVector *qiov)
+static int nbd_write(BlockDriverState *bs, int64_t sector_num,
+                     const uint8_t *buf, int nb_sectors)
 {
     BDRVNBDState *s = bs->opaque;
+    struct nbd_request request;
+    struct nbd_reply reply;
 
-    return nbd_client_session_co_writev(&s->client, sector_num,
-                                        nb_sectors, qiov);
+    request.type = NBD_CMD_WRITE;
+    request.handle = (uint64_t)(intptr_t)bs;
+    request.from = sector_num * 512;;
+    request.len = nb_sectors * 512;
+
+    if (nbd_send_request(s->sock, &request) == -1)
+        return -errno;
+
+    if (nbd_wr_sync(s->sock, (uint8_t*)buf, request.len, 0) != request.len)
+        return -EIO;
+
+    if (nbd_receive_reply(s->sock, &reply) == -1)
+        return -errno;
+
+    if (reply.error !=0)
+        return -reply.error;
+
+    if (reply.handle != request.handle)
+        return -EIO;
+
+    return 0;
 }
 
-static int nbd_co_flush(BlockDriverState *bs)
+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;
-
-    return nbd_client_session_co_flush(&s->client);
+    qemu_co_mutex_lock(&s->lock);
+    ret = nbd_read(bs, sector_num, buf, nb_sectors);
+    qemu_co_mutex_unlock(&s->lock);
+    return ret;
 }
 
-static int nbd_co_discard(BlockDriverState *bs, int64_t sector_num,
-                          int nb_sectors)
+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;
-
-    return nbd_client_session_co_discard(&s->client, sector_num,
-                                         nb_sectors);
+    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);
 
-    qemu_opts_del(s->socket_opts);
-    nbd_client_session_close(&s->client);
+    nbd_teardown_connection(bs);
 }
 
 static int64_t nbd_getlength(BlockDriverState *bs)
 {
     BDRVNBDState *s = bs->opaque;
 
-    return s->client.size;
-}
-
-static void nbd_detach_aio_context(BlockDriverState *bs)
-{
-    BDRVNBDState *s = bs->opaque;
-
-    nbd_client_session_detach_aio_context(&s->client);
-}
-
-static void nbd_attach_aio_context(BlockDriverState *bs,
-                                   AioContext *new_context)
-{
-    BDRVNBDState *s = bs->opaque;
-
-    nbd_client_session_attach_aio_context(&s->client, new_context);
+    return s->size;
 }
 
 static BlockDriver bdrv_nbd = {
-    .format_name                = "nbd",
-    .protocol_name              = "nbd",
-    .instance_size              = sizeof(BDRVNBDState),
-    .bdrv_parse_filename        = nbd_parse_filename,
-    .bdrv_file_open             = nbd_open,
-    .bdrv_co_readv              = nbd_co_readv,
-    .bdrv_co_writev             = nbd_co_writev,
-    .bdrv_close                 = nbd_close,
-    .bdrv_co_flush_to_os        = nbd_co_flush,
-    .bdrv_co_discard            = nbd_co_discard,
-    .bdrv_getlength             = nbd_getlength,
-    .bdrv_detach_aio_context    = nbd_detach_aio_context,
-    .bdrv_attach_aio_context    = nbd_attach_aio_context,
-};
-
-static BlockDriver bdrv_nbd_tcp = {
-    .format_name                = "nbd",
-    .protocol_name              = "nbd+tcp",
-    .instance_size              = sizeof(BDRVNBDState),
-    .bdrv_parse_filename        = nbd_parse_filename,
-    .bdrv_file_open             = nbd_open,
-    .bdrv_co_readv              = nbd_co_readv,
-    .bdrv_co_writev             = nbd_co_writev,
-    .bdrv_close                 = nbd_close,
-    .bdrv_co_flush_to_os        = nbd_co_flush,
-    .bdrv_co_discard            = nbd_co_discard,
-    .bdrv_getlength             = nbd_getlength,
-    .bdrv_detach_aio_context    = nbd_detach_aio_context,
-    .bdrv_attach_aio_context    = nbd_attach_aio_context,
-};
-
-static BlockDriver bdrv_nbd_unix = {
-    .format_name                = "nbd",
-    .protocol_name              = "nbd+unix",
-    .instance_size              = sizeof(BDRVNBDState),
-    .bdrv_parse_filename        = nbd_parse_filename,
-    .bdrv_file_open             = nbd_open,
-    .bdrv_co_readv              = nbd_co_readv,
-    .bdrv_co_writev             = nbd_co_writev,
-    .bdrv_close                 = nbd_close,
-    .bdrv_co_flush_to_os        = nbd_co_flush,
-    .bdrv_co_discard            = nbd_co_discard,
-    .bdrv_getlength             = nbd_getlength,
-    .bdrv_detach_aio_context    = nbd_detach_aio_context,
-    .bdrv_attach_aio_context    = nbd_attach_aio_context,
+    .format_name	= "nbd",
+    .instance_size	= sizeof(BDRVNBDState),
+    .bdrv_file_open	= nbd_open,
+    .bdrv_read          = nbd_co_read,
+    .bdrv_write         = nbd_co_write,
+    .bdrv_close		= nbd_close,
+    .bdrv_getlength	= nbd_getlength,
+    .protocol_name	= "nbd",
 };
 
 static void bdrv_nbd_init(void)
 {
     bdrv_register(&bdrv_nbd);
-    bdrv_register(&bdrv_nbd_tcp);
-    bdrv_register(&bdrv_nbd_unix);
 }
 
 block_init(bdrv_nbd_init);

block/nfs.c

@@ -1,485 +0,0 @@
-/*
- * QEMU Block driver for native access to files on NFS shares
- *
- * Copyright (c) 2014 Peter Lieven <pl@kamp.de>
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
- */
-
-#include "config-host.h"
-
-#include <poll.h>
-#include "qemu-common.h"
-#include "qemu/config-file.h"
-#include "qemu/error-report.h"
-#include "block/block_int.h"
-#include "trace.h"
-#include "qemu/iov.h"
-#include "qemu/uri.h"
-#include "sysemu/sysemu.h"
-#include <nfsc/libnfs.h>
-
-typedef struct NFSClient {
-    struct nfs_context *context;
-    struct nfsfh *fh;
-    int events;
-    bool has_zero_init;
-    AioContext *aio_context;
-} NFSClient;
-
-typedef struct NFSRPC {
-    int ret;
-    int complete;
-    QEMUIOVector *iov;
-    struct stat *st;
-    Coroutine *co;
-    QEMUBH *bh;
-    NFSClient *client;
-} NFSRPC;
-
-static void nfs_process_read(void *arg);
-static void nfs_process_write(void *arg);
-
-static void nfs_set_events(NFSClient *client)
-{
-    int ev = nfs_which_events(client->context);
-    if (ev != client->events) {
-        aio_set_fd_handler(client->aio_context,
-                           nfs_get_fd(client->context),
-                           (ev & POLLIN) ? nfs_process_read : NULL,
-                           (ev & POLLOUT) ? nfs_process_write : NULL,
-                           client);
-
-    }
-    client->events = ev;
-}
-
-static void nfs_process_read(void *arg)
-{
-    NFSClient *client = arg;
-    nfs_service(client->context, POLLIN);
-    nfs_set_events(client);
-}
-
-static void nfs_process_write(void *arg)
-{
-    NFSClient *client = arg;
-    nfs_service(client->context, POLLOUT);
-    nfs_set_events(client);
-}
-
-static void nfs_co_init_task(NFSClient *client, NFSRPC *task)
-{
-    *task = (NFSRPC) {
-        .co             = qemu_coroutine_self(),
-        .client         = client,
-    };
-}
-
-static void nfs_co_generic_bh_cb(void *opaque)
-{
-    NFSRPC *task = opaque;
-    task->complete = 1;
-    qemu_bh_delete(task->bh);
-    qemu_coroutine_enter(task->co, NULL);
-}
-
-static void
-nfs_co_generic_cb(int ret, struct nfs_context *nfs, void *data,
-                  void *private_data)
-{
-    NFSRPC *task = private_data;
-    task->ret = ret;
-    if (task->ret > 0 && task->iov) {
-        if (task->ret <= task->iov->size) {
-            qemu_iovec_from_buf(task->iov, 0, data, task->ret);
-        } else {
-            task->ret = -EIO;
-        }
-    }
-    if (task->ret == 0 && task->st) {
-        memcpy(task->st, data, sizeof(struct stat));
-    }
-    if (task->ret < 0) {
-        error_report("NFS Error: %s", nfs_get_error(nfs));
-    }
-    if (task->co) {
-        task->bh = aio_bh_new(task->client->aio_context,
-                              nfs_co_generic_bh_cb, task);
-        qemu_bh_schedule(task->bh);
-    } else {
-        task->complete = 1;
-    }
-}
-
-static int coroutine_fn nfs_co_readv(BlockDriverState *bs,
-                                     int64_t sector_num, int nb_sectors,
-                                     QEMUIOVector *iov)
-{
-    NFSClient *client = bs->opaque;
-    NFSRPC task;
-
-    nfs_co_init_task(client, &task);
-    task.iov = iov;
-
-    if (nfs_pread_async(client->context, client->fh,
-                        sector_num * BDRV_SECTOR_SIZE,
-                        nb_sectors * BDRV_SECTOR_SIZE,
-                        nfs_co_generic_cb, &task) != 0) {
-        return -ENOMEM;
-    }
-
-    while (!task.complete) {
-        nfs_set_events(client);
-        qemu_coroutine_yield();
-    }
-
-    if (task.ret < 0) {
-        return task.ret;
-    }
-
-    /* zero pad short reads */
-    if (task.ret < iov->size) {
-        qemu_iovec_memset(iov, task.ret, 0, iov->size - task.ret);
-    }
-
-    return 0;
-}
-
-static int coroutine_fn nfs_co_writev(BlockDriverState *bs,
-                                        int64_t sector_num, int nb_sectors,
-                                        QEMUIOVector *iov)
-{
-    NFSClient *client = bs->opaque;
-    NFSRPC task;
-    char *buf = NULL;
-
-    nfs_co_init_task(client, &task);
-
-    buf = g_malloc(nb_sectors * BDRV_SECTOR_SIZE);
-    qemu_iovec_to_buf(iov, 0, buf, nb_sectors * BDRV_SECTOR_SIZE);
-
-    if (nfs_pwrite_async(client->context, client->fh,
-                         sector_num * BDRV_SECTOR_SIZE,
-                         nb_sectors * BDRV_SECTOR_SIZE,
-                         buf, nfs_co_generic_cb, &task) != 0) {
-        g_free(buf);
-        return -ENOMEM;
-    }
-
-    while (!task.complete) {
-        nfs_set_events(client);
-        qemu_coroutine_yield();
-    }
-
-    g_free(buf);
-
-    if (task.ret != nb_sectors * BDRV_SECTOR_SIZE) {
-        return task.ret < 0 ? task.ret : -EIO;
-    }
-
-    return 0;
-}
-
-static int coroutine_fn nfs_co_flush(BlockDriverState *bs)
-{
-    NFSClient *client = bs->opaque;
-    NFSRPC task;
-
-    nfs_co_init_task(client, &task);
-
-    if (nfs_fsync_async(client->context, client->fh, nfs_co_generic_cb,
-                        &task) != 0) {
-        return -ENOMEM;
-    }
-
-    while (!task.complete) {
-        nfs_set_events(client);
-        qemu_coroutine_yield();
-    }
-
-    return task.ret;
-}
-
-/* TODO Convert to fine grained options */
-static QemuOptsList runtime_opts = {
-    .name = "nfs",
-    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
-    .desc = {
-        {
-            .name = "filename",
-            .type = QEMU_OPT_STRING,
-            .help = "URL to the NFS file",
-        },
-        { /* end of list */ }
-    },
-};
-
-static void nfs_detach_aio_context(BlockDriverState *bs)
-{
-    NFSClient *client = bs->opaque;
-
-    aio_set_fd_handler(client->aio_context,
-                       nfs_get_fd(client->context),
-                       NULL, NULL, NULL);
-    client->events = 0;
-}
-
-static void nfs_attach_aio_context(BlockDriverState *bs,
-                                   AioContext *new_context)
-{
-    NFSClient *client = bs->opaque;
-
-    client->aio_context = new_context;
-    nfs_set_events(client);
-}
-
-static void nfs_client_close(NFSClient *client)
-{
-    if (client->context) {
-        if (client->fh) {
-            nfs_close(client->context, client->fh);
-        }
-        aio_set_fd_handler(client->aio_context,
-                           nfs_get_fd(client->context),
-                           NULL, NULL, NULL);
-        nfs_destroy_context(client->context);
-    }
-    memset(client, 0, sizeof(NFSClient));
-}
-
-static void nfs_file_close(BlockDriverState *bs)
-{
-    NFSClient *client = bs->opaque;
-    nfs_client_close(client);
-}
-
-static int64_t nfs_client_open(NFSClient *client, const char *filename,
-                               int flags, Error **errp)
-{
-    int ret = -EINVAL, i;
-    struct stat st;
-    URI *uri;
-    QueryParams *qp = NULL;
-    char *file = NULL, *strp = NULL;
-
-    uri = uri_parse(filename);
-    if (!uri) {
-        error_setg(errp, "Invalid URL specified");
-        goto fail;
-    }
-    if (!uri->server) {
-        error_setg(errp, "Invalid URL specified");
-        goto fail;
-    }
-    strp = strrchr(uri->path, '/');
-    if (strp == NULL) {
-        error_setg(errp, "Invalid URL specified");
-        goto fail;
-    }
-    file = g_strdup(strp);
-    *strp = 0;
-
-    client->context = nfs_init_context();
-    if (client->context == NULL) {
-        error_setg(errp, "Failed to init NFS context");
-        goto fail;
-    }
-
-    qp = query_params_parse(uri->query);
-    for (i = 0; i < qp->n; i++) {
-        unsigned long long val;
-        if (!qp->p[i].value) {
-            error_setg(errp, "Value for NFS parameter expected: %s",
-                       qp->p[i].name);
-            goto fail;
-        }
-        if (parse_uint_full(qp->p[i].value, &val, 0)) {
-            error_setg(errp, "Illegal value for NFS parameter: %s",
-                       qp->p[i].name);
-            goto fail;
-        }
-        if (!strcmp(qp->p[i].name, "uid")) {
-            nfs_set_uid(client->context, val);
-        } else if (!strcmp(qp->p[i].name, "gid")) {
-            nfs_set_gid(client->context, val);
-        } else if (!strcmp(qp->p[i].name, "tcp-syncnt")) {
-            nfs_set_tcp_syncnt(client->context, val);
-#ifdef LIBNFS_FEATURE_READAHEAD
-        } else if (!strcmp(qp->p[i].name, "readahead")) {
-            nfs_set_readahead(client->context, val);
-#endif
-        } else {
-            error_setg(errp, "Unknown NFS parameter name: %s",
-                       qp->p[i].name);
-            goto fail;
-        }
-    }
-
-    ret = nfs_mount(client->context, uri->server, uri->path);
-    if (ret < 0) {
-        error_setg(errp, "Failed to mount nfs share: %s",
-                   nfs_get_error(client->context));
-        goto fail;
-    }
-
-    if (flags & O_CREAT) {
-        ret = nfs_creat(client->context, file, 0600, &client->fh);
-        if (ret < 0) {
-            error_setg(errp, "Failed to create file: %s",
-                       nfs_get_error(client->context));
-            goto fail;
-        }
-    } else {
-        ret = nfs_open(client->context, file, flags, &client->fh);
-        if (ret < 0) {
-            error_setg(errp, "Failed to open file : %s",
-                       nfs_get_error(client->context));
-            goto fail;
-        }
-    }
-
-    ret = nfs_fstat(client->context, client->fh, &st);
-    if (ret < 0) {
-        error_setg(errp, "Failed to fstat file: %s",
-                   nfs_get_error(client->context));
-        goto fail;
-    }
-
-    ret = DIV_ROUND_UP(st.st_size, BDRV_SECTOR_SIZE);
-    client->has_zero_init = S_ISREG(st.st_mode);
-    goto out;
-fail:
-    nfs_client_close(client);
-out:
-    if (qp) {
-        query_params_free(qp);
-    }
-    uri_free(uri);
-    g_free(file);
-    return ret;
-}
-
-static int nfs_file_open(BlockDriverState *bs, QDict *options, int flags,
-                         Error **errp) {
-    NFSClient *client = bs->opaque;
-    int64_t ret;
-    QemuOpts *opts;
-    Error *local_err = NULL;
-
-    client->aio_context = bdrv_get_aio_context(bs);
-
-    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        return -EINVAL;
-    }
-    ret = nfs_client_open(client, qemu_opt_get(opts, "filename"),
-                          (flags & BDRV_O_RDWR) ? O_RDWR : O_RDONLY,
-                          errp);
-    if (ret < 0) {
-        return ret;
-    }
-    bs->total_sectors = ret;
-    return 0;
-}
-
-static int nfs_file_create(const char *url, QemuOpts *opts, Error **errp)
-{
-    int ret = 0;
-    int64_t total_size = 0;
-    NFSClient *client = g_malloc0(sizeof(NFSClient));
-
-    client->aio_context = qemu_get_aio_context();
-
-    /* Read out options */
-    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
-
-    ret = nfs_client_open(client, url, O_CREAT, errp);
-    if (ret < 0) {
-        goto out;
-    }
-    ret = nfs_ftruncate(client->context, client->fh, total_size);
-    nfs_client_close(client);
-out:
-    g_free(client);
-    return ret;
-}
-
-static int nfs_has_zero_init(BlockDriverState *bs)
-{
-    NFSClient *client = bs->opaque;
-    return client->has_zero_init;
-}
-
-static int64_t nfs_get_allocated_file_size(BlockDriverState *bs)
-{
-    NFSClient *client = bs->opaque;
-    NFSRPC task = {0};
-    struct stat st;
-
-    task.st = &st;
-    if (nfs_fstat_async(client->context, client->fh, nfs_co_generic_cb,
-                        &task) != 0) {
-        return -ENOMEM;
-    }
-
-    while (!task.complete) {
-        nfs_set_events(client);
-        aio_poll(client->aio_context, true);
-    }
-
-    return (task.ret < 0 ? task.ret : st.st_blocks * st.st_blksize);
-}
-
-static int nfs_file_truncate(BlockDriverState *bs, int64_t offset)
-{
-    NFSClient *client = bs->opaque;
-    return nfs_ftruncate(client->context, client->fh, offset);
-}
-
-static BlockDriver bdrv_nfs = {
-    .format_name                    = "nfs",
-    .protocol_name                  = "nfs",
-
-    .instance_size                  = sizeof(NFSClient),
-    .bdrv_needs_filename            = true,
-    .bdrv_has_zero_init             = nfs_has_zero_init,
-    .bdrv_get_allocated_file_size   = nfs_get_allocated_file_size,
-    .bdrv_truncate                  = nfs_file_truncate,
-
-    .bdrv_file_open                 = nfs_file_open,
-    .bdrv_close                     = nfs_file_close,
-    .bdrv_create                    = nfs_file_create,
-
-    .bdrv_co_readv                  = nfs_co_readv,
-    .bdrv_co_writev                 = nfs_co_writev,
-    .bdrv_co_flush_to_disk          = nfs_co_flush,
-
-    .bdrv_detach_aio_context        = nfs_detach_aio_context,
-    .bdrv_attach_aio_context        = nfs_attach_aio_context,
-};
-
-static void nfs_block_init(void)
-{
-    bdrv_register(&bdrv_nfs);
-}
-
-block_init(nfs_block_init);

block/parallels.c

@@ -24,8 +24,8 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
 
 /**************************************************************/
 
@@ -49,9 +49,9 @@ typedef struct BDRVParallelsState {
     CoMutex lock;
 
     uint32_t *catalog_bitmap;
-    unsigned int catalog_size;
+    int catalog_size;
 
-    unsigned int tracks;
+    int tracks;
 } BDRVParallelsState;
 
 static int parallels_probe(const uint8_t *buf, int buf_size, const char *filename)
@@ -68,59 +68,40 @@ static int parallels_probe(const uint8_t *buf, int buf_size, const char *filenam
     return 0;
 }
 
-static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
-                          Error **errp)
+static int parallels_open(BlockDriverState *bs, int flags)
 {
     BDRVParallelsState *s = bs->opaque;
     int i;
     struct parallels_header ph;
-    int ret;
 
     bs->read_only = 1; // no write support yet
 
-    ret = bdrv_pread(bs->file, 0, &ph, sizeof(ph));
-    if (ret < 0) {
+    if (bdrv_pread(bs->file, 0, &ph, sizeof(ph)) != sizeof(ph))
         goto fail;
-    }
 
     if (memcmp(ph.magic, HEADER_MAGIC, 16) ||
-        (le32_to_cpu(ph.version) != HEADER_VERSION)) {
-        error_setg(errp, "Image not in Parallels format");
-        ret = -EINVAL;
+	(le32_to_cpu(ph.version) != HEADER_VERSION)) {
         goto fail;
     }
 
     bs->total_sectors = le32_to_cpu(ph.nb_sectors);
 
     s->tracks = le32_to_cpu(ph.tracks);
-    if (s->tracks == 0) {
-        error_setg(errp, "Invalid image: Zero sectors per track");
-        ret = -EINVAL;
-        goto fail;
-    }
 
     s->catalog_size = le32_to_cpu(ph.catalog_entries);
-    if (s->catalog_size > INT_MAX / 4) {
-        error_setg(errp, "Catalog too large");
-        ret = -EFBIG;
-        goto fail;
-    }
     s->catalog_bitmap = g_malloc(s->catalog_size * 4);
-
-    ret = bdrv_pread(bs->file, 64, s->catalog_bitmap, s->catalog_size * 4);
-    if (ret < 0) {
-        goto fail;
-    }
-
+    if (bdrv_pread(bs->file, 64, s->catalog_bitmap, s->catalog_size * 4) !=
+	s->catalog_size * 4)
+	goto fail;
     for (i = 0; i < s->catalog_size; i++)
 	le32_to_cpus(&s->catalog_bitmap[i]);
 
     qemu_co_mutex_init(&s->lock);
     return 0;
-
 fail:
-    g_free(s->catalog_bitmap);
-    return ret;
+    if (s->catalog_bitmap)
+	g_free(s->catalog_bitmap);
+    return -1;
 }
 
 static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)

block/qapi.c

@@ -1,628 +0,0 @@
-/*
- * Block layer qmp and info dump related functions
- *
- * Copyright (c) 2003-2008 Fabrice Bellard
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
- */
-
-#include "block/qapi.h"
-#include "block/block_int.h"
-#include "qmp-commands.h"
-#include "qapi-visit.h"
-#include "qapi/qmp-output-visitor.h"
-#include "qapi/qmp/types.h"
-
-BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs)
-{
-    BlockDeviceInfo *info = g_malloc0(sizeof(*info));
-
-    info->file                   = g_strdup(bs->filename);
-    info->ro                     = bs->read_only;
-    info->drv                    = g_strdup(bs->drv->format_name);
-    info->encrypted              = bs->encrypted;
-    info->encryption_key_missing = bdrv_key_required(bs);
-
-    if (bs->node_name[0]) {
-        info->has_node_name = true;
-        info->node_name = g_strdup(bs->node_name);
-    }
-
-    if (bs->backing_file[0]) {
-        info->has_backing_file = true;
-        info->backing_file = g_strdup(bs->backing_file);
-    }
-
-    info->backing_file_depth = bdrv_get_backing_file_depth(bs);
-    info->detect_zeroes = bs->detect_zeroes;
-
-    if (bs->io_limits_enabled) {
-        ThrottleConfig cfg;
-        throttle_get_config(&bs->throttle_state, &cfg);
-        info->bps     = cfg.buckets[THROTTLE_BPS_TOTAL].avg;
-        info->bps_rd  = cfg.buckets[THROTTLE_BPS_READ].avg;
-        info->bps_wr  = cfg.buckets[THROTTLE_BPS_WRITE].avg;
-
-        info->iops    = cfg.buckets[THROTTLE_OPS_TOTAL].avg;
-        info->iops_rd = cfg.buckets[THROTTLE_OPS_READ].avg;
-        info->iops_wr = cfg.buckets[THROTTLE_OPS_WRITE].avg;
-
-        info->has_bps_max     = cfg.buckets[THROTTLE_BPS_TOTAL].max;
-        info->bps_max         = cfg.buckets[THROTTLE_BPS_TOTAL].max;
-        info->has_bps_rd_max  = cfg.buckets[THROTTLE_BPS_READ].max;
-        info->bps_rd_max      = cfg.buckets[THROTTLE_BPS_READ].max;
-        info->has_bps_wr_max  = cfg.buckets[THROTTLE_BPS_WRITE].max;
-        info->bps_wr_max      = cfg.buckets[THROTTLE_BPS_WRITE].max;
-
-        info->has_iops_max    = cfg.buckets[THROTTLE_OPS_TOTAL].max;
-        info->iops_max        = cfg.buckets[THROTTLE_OPS_TOTAL].max;
-        info->has_iops_rd_max = cfg.buckets[THROTTLE_OPS_READ].max;
-        info->iops_rd_max     = cfg.buckets[THROTTLE_OPS_READ].max;
-        info->has_iops_wr_max = cfg.buckets[THROTTLE_OPS_WRITE].max;
-        info->iops_wr_max     = cfg.buckets[THROTTLE_OPS_WRITE].max;
-
-        info->has_iops_size = cfg.op_size;
-        info->iops_size = cfg.op_size;
-    }
-
-    return info;
-}
-
-/*
- * Returns 0 on success, with *p_list either set to describe snapshot
- * information, or NULL because there are no snapshots.  Returns -errno on
- * error, with *p_list untouched.
- */
-int bdrv_query_snapshot_info_list(BlockDriverState *bs,
-                                  SnapshotInfoList **p_list,
-                                  Error **errp)
-{
-    int i, sn_count;
-    QEMUSnapshotInfo *sn_tab = NULL;
-    SnapshotInfoList *info_list, *cur_item = NULL, *head = NULL;
-    SnapshotInfo *info;
-
-    sn_count = bdrv_snapshot_list(bs, &sn_tab);
-    if (sn_count < 0) {
-        const char *dev = bdrv_get_device_name(bs);
-        switch (sn_count) {
-        case -ENOMEDIUM:
-            error_setg(errp, "Device '%s' is not inserted", dev);
-            break;
-        case -ENOTSUP:
-            error_setg(errp,
-                       "Device '%s' does not support internal snapshots",
-                       dev);
-            break;
-        default:
-            error_setg_errno(errp, -sn_count,
-                             "Can't list snapshots of device '%s'", dev);
-            break;
-        }
-        return sn_count;
-    }
-
-    for (i = 0; i < sn_count; i++) {
-        info = g_new0(SnapshotInfo, 1);
-        info->id            = g_strdup(sn_tab[i].id_str);
-        info->name          = g_strdup(sn_tab[i].name);
-        info->vm_state_size = sn_tab[i].vm_state_size;
-        info->date_sec      = sn_tab[i].date_sec;
-        info->date_nsec     = sn_tab[i].date_nsec;
-        info->vm_clock_sec  = sn_tab[i].vm_clock_nsec / 1000000000;
-        info->vm_clock_nsec = sn_tab[i].vm_clock_nsec % 1000000000;
-
-        info_list = g_new0(SnapshotInfoList, 1);
-        info_list->value = info;
-
-        /* XXX: waiting for the qapi to support qemu-queue.h types */
-        if (!cur_item) {
-            head = cur_item = info_list;
-        } else {
-            cur_item->next = info_list;
-            cur_item = info_list;
-        }
-
-    }
-
-    g_free(sn_tab);
-    *p_list = head;
-    return 0;
-}
-
-/**
- * bdrv_query_image_info:
- * @bs: block device to examine
- * @p_info: location to store image information
- * @errp: location to store error information
- *
- * Store "flat" image information in @p_info.
- *
- * "Flat" means it does *not* query backing image information,
- * i.e. (*pinfo)->has_backing_image will be set to false and
- * (*pinfo)->backing_image to NULL even when the image does in fact have
- * a backing image.
- *
- * @p_info will be set only on success. On error, store error in @errp.
- */
-void bdrv_query_image_info(BlockDriverState *bs,
-                           ImageInfo **p_info,
-                           Error **errp)
-{
-    uint64_t total_sectors;
-    const char *backing_filename;
-    char backing_filename2[1024];
-    BlockDriverInfo bdi;
-    int ret;
-    Error *err = NULL;
-    ImageInfo *info = g_new0(ImageInfo, 1);
-
-    bdrv_get_geometry(bs, &total_sectors);
-
-    info->filename        = g_strdup(bs->filename);
-    info->format          = g_strdup(bdrv_get_format_name(bs));
-    info->virtual_size    = total_sectors * 512;
-    info->actual_size     = bdrv_get_allocated_file_size(bs);
-    info->has_actual_size = info->actual_size >= 0;
-    if (bdrv_is_encrypted(bs)) {
-        info->encrypted = true;
-        info->has_encrypted = true;
-    }
-    if (bdrv_get_info(bs, &bdi) >= 0) {
-        if (bdi.cluster_size != 0) {
-            info->cluster_size = bdi.cluster_size;
-            info->has_cluster_size = true;
-        }
-        info->dirty_flag = bdi.is_dirty;
-        info->has_dirty_flag = true;
-    }
-    info->format_specific     = bdrv_get_specific_info(bs);
-    info->has_format_specific = info->format_specific != NULL;
-
-    backing_filename = bs->backing_file;
-    if (backing_filename[0] != '\0') {
-        info->backing_filename = g_strdup(backing_filename);
-        info->has_backing_filename = true;
-        bdrv_get_full_backing_filename(bs, backing_filename2,
-                                       sizeof(backing_filename2));
-
-        if (strcmp(backing_filename, backing_filename2) != 0) {
-            info->full_backing_filename =
-                        g_strdup(backing_filename2);
-            info->has_full_backing_filename = true;
-        }
-
-        if (bs->backing_format[0]) {
-            info->backing_filename_format = g_strdup(bs->backing_format);
-            info->has_backing_filename_format = true;
-        }
-    }
-
-    ret = bdrv_query_snapshot_info_list(bs, &info->snapshots, &err);
-    switch (ret) {
-    case 0:
-        if (info->snapshots) {
-            info->has_snapshots = true;
-        }
-        break;
-    /* recoverable error */
-    case -ENOMEDIUM:
-    case -ENOTSUP:
-        error_free(err);
-        break;
-    default:
-        error_propagate(errp, err);
-        qapi_free_ImageInfo(info);
-        return;
-    }
-
-    *p_info = info;
-}
-
-/* @p_info will be set only on success. */
-void bdrv_query_info(BlockDriverState *bs,
-                     BlockInfo **p_info,
-                     Error **errp)
-{
-    BlockInfo *info = g_malloc0(sizeof(*info));
-    BlockDriverState *bs0;
-    ImageInfo **p_image_info;
-    Error *local_err = NULL;
-    info->device = g_strdup(bs->device_name);
-    info->type = g_strdup("unknown");
-    info->locked = bdrv_dev_is_medium_locked(bs);
-    info->removable = bdrv_dev_has_removable_media(bs);
-
-    if (bdrv_dev_has_removable_media(bs)) {
-        info->has_tray_open = true;
-        info->tray_open = bdrv_dev_is_tray_open(bs);
-    }
-
-    if (bdrv_iostatus_is_enabled(bs)) {
-        info->has_io_status = true;
-        info->io_status = bs->iostatus;
-    }
-
-    if (!QLIST_EMPTY(&bs->dirty_bitmaps)) {
-        info->has_dirty_bitmaps = true;
-        info->dirty_bitmaps = bdrv_query_dirty_bitmaps(bs);
-    }
-
-    if (bs->drv) {
-        info->has_inserted = true;
-        info->inserted = bdrv_block_device_info(bs);
-
-        bs0 = bs;
-        p_image_info = &info->inserted->image;
-        while (1) {
-            bdrv_query_image_info(bs0, p_image_info, &local_err);
-            if (local_err) {
-                error_propagate(errp, local_err);
-                goto err;
-            }
-            if (bs0->drv && bs0->backing_hd) {
-                bs0 = bs0->backing_hd;
-                (*p_image_info)->has_backing_image = true;
-                p_image_info = &((*p_image_info)->backing_image);
-            } else {
-                break;
-            }
-        }
-    }
-
-    *p_info = info;
-    return;
-
- err:
-    qapi_free_BlockInfo(info);
-}
-
-static BlockStats *bdrv_query_stats(const BlockDriverState *bs)
-{
-    BlockStats *s;
-
-    s = g_malloc0(sizeof(*s));
-
-    if (bs->device_name[0]) {
-        s->has_device = true;
-        s->device = g_strdup(bs->device_name);
-    }
-
-    s->stats = g_malloc0(sizeof(*s->stats));
-    s->stats->rd_bytes = bs->nr_bytes[BDRV_ACCT_READ];
-    s->stats->wr_bytes = bs->nr_bytes[BDRV_ACCT_WRITE];
-    s->stats->rd_operations = bs->nr_ops[BDRV_ACCT_READ];
-    s->stats->wr_operations = bs->nr_ops[BDRV_ACCT_WRITE];
-    s->stats->wr_highest_offset = bs->wr_highest_sector * BDRV_SECTOR_SIZE;
-    s->stats->flush_operations = bs->nr_ops[BDRV_ACCT_FLUSH];
-    s->stats->wr_total_time_ns = bs->total_time_ns[BDRV_ACCT_WRITE];
-    s->stats->rd_total_time_ns = bs->total_time_ns[BDRV_ACCT_READ];
-    s->stats->flush_total_time_ns = bs->total_time_ns[BDRV_ACCT_FLUSH];
-
-    if (bs->file) {
-        s->has_parent = true;
-        s->parent = bdrv_query_stats(bs->file);
-    }
-
-    if (bs->backing_hd) {
-        s->has_backing = true;
-        s->backing = bdrv_query_stats(bs->backing_hd);
-    }
-
-    return s;
-}
-
-BlockInfoList *qmp_query_block(Error **errp)
-{
-    BlockInfoList *head = NULL, **p_next = &head;
-    BlockDriverState *bs = NULL;
-    Error *local_err = NULL;
-
-     while ((bs = bdrv_next(bs))) {
-        BlockInfoList *info = g_malloc0(sizeof(*info));
-        bdrv_query_info(bs, &info->value, &local_err);
-        if (local_err) {
-            error_propagate(errp, local_err);
-            goto err;
-        }
-
-        *p_next = info;
-        p_next = &info->next;
-    }
-
-    return head;
-
- err:
-    qapi_free_BlockInfoList(head);
-    return NULL;
-}
-
-BlockStatsList *qmp_query_blockstats(Error **errp)
-{
-    BlockStatsList *head = NULL, **p_next = &head;
-    BlockDriverState *bs = NULL;
-
-     while ((bs = bdrv_next(bs))) {
-        BlockStatsList *info = g_malloc0(sizeof(*info));
-        AioContext *ctx = bdrv_get_aio_context(bs);
-
-        aio_context_acquire(ctx);
-        info->value = bdrv_query_stats(bs);
-        aio_context_release(ctx);
-
-        *p_next = info;
-        p_next = &info->next;
-    }
-
-    return head;
-}
-
-#define NB_SUFFIXES 4
-
-static char *get_human_readable_size(char *buf, int buf_size, int64_t size)
-{
-    static const char suffixes[NB_SUFFIXES] = "KMGT";
-    int64_t base;
-    int i;
-
-    if (size <= 999) {
-        snprintf(buf, buf_size, "%" PRId64, size);
-    } else {
-        base = 1024;
-        for (i = 0; i < NB_SUFFIXES; i++) {
-            if (size < (10 * base)) {
-                snprintf(buf, buf_size, "%0.1f%c",
-                         (double)size / base,
-                         suffixes[i]);
-                break;
-            } else if (size < (1000 * base) || i == (NB_SUFFIXES - 1)) {
-                snprintf(buf, buf_size, "%" PRId64 "%c",
-                         ((size + (base >> 1)) / base),
-                         suffixes[i]);
-                break;
-            }
-            base = base * 1024;
-        }
-    }
-    return buf;
-}
-
-void bdrv_snapshot_dump(fprintf_function func_fprintf, void *f,
-                        QEMUSnapshotInfo *sn)
-{
-    char buf1[128], date_buf[128], clock_buf[128];
-    struct tm tm;
-    time_t ti;
-    int64_t secs;
-
-    if (!sn) {
-        func_fprintf(f,
-                     "%-10s%-20s%7s%20s%15s",
-                     "ID", "TAG", "VM SIZE", "DATE", "VM CLOCK");
-    } else {
-        ti = sn->date_sec;
-        localtime_r(&ti, &tm);
-        strftime(date_buf, sizeof(date_buf),
-                 "%Y-%m-%d %H:%M:%S", &tm);
-        secs = sn->vm_clock_nsec / 1000000000;
-        snprintf(clock_buf, sizeof(clock_buf),
-                 "%02d:%02d:%02d.%03d",
-                 (int)(secs / 3600),
-                 (int)((secs / 60) % 60),
-                 (int)(secs % 60),
-                 (int)((sn->vm_clock_nsec / 1000000) % 1000));
-        func_fprintf(f,
-                     "%-10s%-20s%7s%20s%15s",
-                     sn->id_str, sn->name,
-                     get_human_readable_size(buf1, sizeof(buf1),
-                                             sn->vm_state_size),
-                     date_buf,
-                     clock_buf);
-    }
-}
-
-static void dump_qdict(fprintf_function func_fprintf, void *f, int indentation,
-                       QDict *dict);
-static void dump_qlist(fprintf_function func_fprintf, void *f, int indentation,
-                       QList *list);
-
-static void dump_qobject(fprintf_function func_fprintf, void *f,
-                         int comp_indent, QObject *obj)
-{
-    switch (qobject_type(obj)) {
-        case QTYPE_QINT: {
-            QInt *value = qobject_to_qint(obj);
-            func_fprintf(f, "%" PRId64, qint_get_int(value));
-            break;
-        }
-        case QTYPE_QSTRING: {
-            QString *value = qobject_to_qstring(obj);
-            func_fprintf(f, "%s", qstring_get_str(value));
-            break;
-        }
-        case QTYPE_QDICT: {
-            QDict *value = qobject_to_qdict(obj);
-            dump_qdict(func_fprintf, f, comp_indent, value);
-            break;
-        }
-        case QTYPE_QLIST: {
-            QList *value = qobject_to_qlist(obj);
-            dump_qlist(func_fprintf, f, comp_indent, value);
-            break;
-        }
-        case QTYPE_QFLOAT: {
-            QFloat *value = qobject_to_qfloat(obj);
-            func_fprintf(f, "%g", qfloat_get_double(value));
-            break;
-        }
-        case QTYPE_QBOOL: {
-            QBool *value = qobject_to_qbool(obj);
-            func_fprintf(f, "%s", qbool_get_int(value) ? "true" : "false");
-            break;
-        }
-        case QTYPE_QERROR: {
-            QString *value = qerror_human((QError *)obj);
-            func_fprintf(f, "%s", qstring_get_str(value));
-            QDECREF(value);
-            break;
-        }
-        case QTYPE_NONE:
-            break;
-        case QTYPE_MAX:
-        default:
-            abort();
-    }
-}
-
-static void dump_qlist(fprintf_function func_fprintf, void *f, int indentation,
-                       QList *list)
-{
-    const QListEntry *entry;
-    int i = 0;
-
-    for (entry = qlist_first(list); entry; entry = qlist_next(entry), i++) {
-        qtype_code type = qobject_type(entry->value);
-        bool composite = (type == QTYPE_QDICT || type == QTYPE_QLIST);
-        const char *format = composite ? "%*s[%i]:\n" : "%*s[%i]: ";
-
-        func_fprintf(f, format, indentation * 4, "", i);
-        dump_qobject(func_fprintf, f, indentation + 1, entry->value);
-        if (!composite) {
-            func_fprintf(f, "\n");
-        }
-    }
-}
-
-static void dump_qdict(fprintf_function func_fprintf, void *f, int indentation,
-                       QDict *dict)
-{
-    const QDictEntry *entry;
-
-    for (entry = qdict_first(dict); entry; entry = qdict_next(dict, entry)) {
-        qtype_code type = qobject_type(entry->value);
-        bool composite = (type == QTYPE_QDICT || type == QTYPE_QLIST);
-        const char *format = composite ? "%*s%s:\n" : "%*s%s: ";
-        char key[strlen(entry->key) + 1];
-        int i;
-
-        /* replace dashes with spaces in key (variable) names */
-        for (i = 0; entry->key[i]; i++) {
-            key[i] = entry->key[i] == '-' ? ' ' : entry->key[i];
-        }
-        key[i] = 0;
-
-        func_fprintf(f, format, indentation * 4, "", key);
-        dump_qobject(func_fprintf, f, indentation + 1, entry->value);
-        if (!composite) {
-            func_fprintf(f, "\n");
-        }
-    }
-}
-
-void bdrv_image_info_specific_dump(fprintf_function func_fprintf, void *f,
-                                   ImageInfoSpecific *info_spec)
-{
-    QmpOutputVisitor *ov = qmp_output_visitor_new();
-    QObject *obj, *data;
-
-    visit_type_ImageInfoSpecific(qmp_output_get_visitor(ov), &info_spec, NULL,
-                                 &error_abort);
-    obj = qmp_output_get_qobject(ov);
-    assert(qobject_type(obj) == QTYPE_QDICT);
-    data = qdict_get(qobject_to_qdict(obj), "data");
-    dump_qobject(func_fprintf, f, 1, data);
-    qmp_output_visitor_cleanup(ov);
-}
-
-void bdrv_image_info_dump(fprintf_function func_fprintf, void *f,
-                          ImageInfo *info)
-{
-    char size_buf[128], dsize_buf[128];
-    if (!info->has_actual_size) {
-        snprintf(dsize_buf, sizeof(dsize_buf), "unavailable");
-    } else {
-        get_human_readable_size(dsize_buf, sizeof(dsize_buf),
-                                info->actual_size);
-    }
-    get_human_readable_size(size_buf, sizeof(size_buf), info->virtual_size);
-    func_fprintf(f,
-                 "image: %s\n"
-                 "file format: %s\n"
-                 "virtual size: %s (%" PRId64 " bytes)\n"
-                 "disk size: %s\n",
-                 info->filename, info->format, size_buf,
-                 info->virtual_size,
-                 dsize_buf);
-
-    if (info->has_encrypted && info->encrypted) {
-        func_fprintf(f, "encrypted: yes\n");
-    }
-
-    if (info->has_cluster_size) {
-        func_fprintf(f, "cluster_size: %" PRId64 "\n",
-                       info->cluster_size);
-    }
-
-    if (info->has_dirty_flag && info->dirty_flag) {
-        func_fprintf(f, "cleanly shut down: no\n");
-    }
-
-    if (info->has_backing_filename) {
-        func_fprintf(f, "backing file: %s", info->backing_filename);
-        if (info->has_full_backing_filename) {
-            func_fprintf(f, " (actual path: %s)", info->full_backing_filename);
-        }
-        func_fprintf(f, "\n");
-        if (info->has_backing_filename_format) {
-            func_fprintf(f, "backing file format: %s\n",
-                         info->backing_filename_format);
-        }
-    }
-
-    if (info->has_snapshots) {
-        SnapshotInfoList *elem;
-
-        func_fprintf(f, "Snapshot list:\n");
-        bdrv_snapshot_dump(func_fprintf, f, NULL);
-        func_fprintf(f, "\n");
-
-        /* Ideally bdrv_snapshot_dump() would operate on SnapshotInfoList but
-         * we convert to the block layer's native QEMUSnapshotInfo for now.
-         */
-        for (elem = info->snapshots; elem; elem = elem->next) {
-            QEMUSnapshotInfo sn = {
-                .vm_state_size = elem->value->vm_state_size,
-                .date_sec = elem->value->date_sec,
-                .date_nsec = elem->value->date_nsec,
-                .vm_clock_nsec = elem->value->vm_clock_sec * 1000000000ULL +
-                                 elem->value->vm_clock_nsec,
-            };
-
-            pstrcpy(sn.id_str, sizeof(sn.id_str), elem->value->id);
-            pstrcpy(sn.name, sizeof(sn.name), elem->value->name);
-            bdrv_snapshot_dump(func_fprintf, f, &sn);
-            func_fprintf(f, "\n");
-        }
-    }
-
-    if (info->has_format_specific) {
-        func_fprintf(f, "Format specific information:\n");
-        bdrv_image_info_specific_dump(func_fprintf, f, info->format_specific);
-    }
-}

block/qcow.c

@@ -22,11 +22,11 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
 #include <zlib.h>
-#include "qemu/aes.h"
-#include "migration/migration.h"
+#include "aes.h"
+#include "migration.h"
 
 /**************************************************************/
 /* QEMU COW block driver with compression and encryption support */
@@ -48,10 +48,9 @@ typedef struct QCowHeader {
     uint64_t size; /* in bytes */
     uint8_t cluster_bits;
     uint8_t l2_bits;
-    uint16_t padding;
     uint32_t crypt_method;
     uint64_t l1_table_offset;
-} QEMU_PACKED QCowHeader;
+} QCowHeader;
 
 #define L2_CACHE_SIZE 16
 
@@ -61,7 +60,7 @@ typedef struct BDRVQcowState {
     int cluster_sectors;
     int l2_bits;
     int l2_size;
-    unsigned int l1_size;
+    int l1_size;
     uint64_t cluster_offset_mask;
     uint64_t l1_table_offset;
     uint64_t *l1_table;
@@ -93,18 +92,14 @@ static int qcow_probe(const uint8_t *buf, int buf_size, const char *filename)
         return 0;
 }
 
-static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
-                     Error **errp)
+static int qcow_open(BlockDriverState *bs, int flags)
 {
     BDRVQcowState *s = bs->opaque;
-    unsigned int len, i, shift;
-    int ret;
+    int len, i, shift;
     QCowHeader header;
 
-    ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
-    if (ret < 0) {
+    if (bdrv_pread(bs->file, 0, &header, sizeof(header)) != sizeof(header))
         goto fail;
-    }
     be32_to_cpus(&header.magic);
     be32_to_cpus(&header.version);
     be64_to_cpus(&header.backing_file_offset);
@@ -114,49 +109,15 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
     be32_to_cpus(&header.crypt_method);
     be64_to_cpus(&header.l1_table_offset);
 
-    if (header.magic != QCOW_MAGIC) {
-        error_setg(errp, "Image not in qcow format");
-        ret = -EINVAL;
+    if (header.magic != QCOW_MAGIC || header.version != QCOW_VERSION)
         goto fail;
-    }
-    if (header.version != QCOW_VERSION) {
-        char version[64];
-        snprintf(version, sizeof(version), "QCOW version %" PRIu32,
-                 header.version);
-        error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
-                  bs->device_name, "qcow", version);
-        ret = -ENOTSUP;
+    if (header.size <= 1 || header.cluster_bits < 9)
         goto fail;
-    }
-
-    if (header.size <= 1) {
-        error_setg(errp, "Image size is too small (must be at least 2 bytes)");
-        ret = -EINVAL;
+    if (header.crypt_method > QCOW_CRYPT_AES)
         goto fail;
-    }
-    if (header.cluster_bits < 9 || header.cluster_bits > 16) {
-        error_setg(errp, "Cluster size must be between 512 and 64k");
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    /* l2_bits specifies number of entries; storing a uint64_t in each entry,
-     * so bytes = num_entries << 3. */
-    if (header.l2_bits < 9 - 3 || header.l2_bits > 16 - 3) {
-        error_setg(errp, "L2 table size must be between 512 and 64k");
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    if (header.crypt_method > QCOW_CRYPT_AES) {
-        error_setg(errp, "invalid encryption method in qcow header");
-        ret = -EINVAL;
-        goto fail;
-    }
     s->crypt_method_header = header.crypt_method;
-    if (s->crypt_method_header) {
+    if (s->crypt_method_header)
         bs->encrypted = 1;
-    }
     s->cluster_bits = header.cluster_bits;
     s->cluster_size = 1 << s->cluster_bits;
     s->cluster_sectors = 1 << (s->cluster_bits - 9);
@@ -167,51 +128,37 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
 
     /* read the level 1 table */
     shift = s->cluster_bits + s->l2_bits;
-    if (header.size > UINT64_MAX - (1LL << shift)) {
-        error_setg(errp, "Image too large");
-        ret = -EINVAL;
-        goto fail;
-    } else {
-        uint64_t l1_size = (header.size + (1LL << shift) - 1) >> shift;
-        if (l1_size > INT_MAX / sizeof(uint64_t)) {
-            error_setg(errp, "Image too large");
-            ret = -EINVAL;
-            goto fail;
-        }
-        s->l1_size = l1_size;
-    }
+    s->l1_size = (header.size + (1LL << shift) - 1) >> shift;
 
     s->l1_table_offset = header.l1_table_offset;
     s->l1_table = g_malloc(s->l1_size * sizeof(uint64_t));
-
-    ret = bdrv_pread(bs->file, s->l1_table_offset, s->l1_table,
-               s->l1_size * sizeof(uint64_t));
-    if (ret < 0) {
+    if (!s->l1_table)
+        goto fail;
+    if (bdrv_pread(bs->file, s->l1_table_offset, s->l1_table, s->l1_size * sizeof(uint64_t)) !=
+        s->l1_size * sizeof(uint64_t))
         goto fail;
-    }
-
     for(i = 0;i < s->l1_size; i++) {
         be64_to_cpus(&s->l1_table[i]);
     }
     /* alloc L2 cache */
     s->l2_cache = g_malloc(s->l2_size * L2_CACHE_SIZE * sizeof(uint64_t));
+    if (!s->l2_cache)
+        goto fail;
     s->cluster_cache = g_malloc(s->cluster_size);
+    if (!s->cluster_cache)
+        goto fail;
     s->cluster_data = g_malloc(s->cluster_size);
+    if (!s->cluster_data)
+        goto fail;
     s->cluster_cache_offset = -1;
 
     /* read the backing file name */
     if (header.backing_file_offset != 0) {
         len = header.backing_file_size;
-        if (len > 1023) {
-            error_setg(errp, "Backing file name too long");
-            ret = -EINVAL;
+        if (len > 1023)
+            len = 1023;
+        if (bdrv_pread(bs->file, header.backing_file_offset, bs->backing_file, len) != len)
             goto fail;
-        }
-        ret = bdrv_pread(bs->file, header.backing_file_offset,
-                   bs->backing_file, len);
-        if (ret < 0) {
-            goto fail;
-        }
         bs->backing_file[len] = '\0';
     }
 
@@ -229,16 +176,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
     g_free(s->l2_cache);
     g_free(s->cluster_cache);
     g_free(s->cluster_data);
-    return ret;
-}
-
-
-/* We have nothing to do for QCOW reopen, stubs just return
- * success */
-static int qcow_reopen_prepare(BDRVReopenState *state,
-                               BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
+    return -1;
 }
 
 static int qcow_set_key(BlockDriverState *bs, const char *key)
@@ -430,29 +368,20 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
     return cluster_offset;
 }
 
-static int64_t coroutine_fn qcow_co_get_block_status(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *pnum)
+static int qcow_is_allocated(BlockDriverState *bs, int64_t sector_num,
+                             int nb_sectors, int *pnum)
 {
     BDRVQcowState *s = bs->opaque;
     int index_in_cluster, n;
     uint64_t cluster_offset;
 
-    qemu_co_mutex_lock(&s->lock);
     cluster_offset = get_cluster_offset(bs, sector_num << 9, 0, 0, 0, 0);
-    qemu_co_mutex_unlock(&s->lock);
     index_in_cluster = sector_num & (s->cluster_sectors - 1);
     n = s->cluster_sectors - index_in_cluster;
     if (n > nb_sectors)
         n = nb_sectors;
     *pnum = n;
-    if (!cluster_offset) {
-        return 0;
-    }
-    if ((cluster_offset & QCOW_OFLAG_COMPRESSED) || s->crypt_method) {
-        return BDRV_BLOCK_DATA;
-    }
-    cluster_offset |= (index_in_cluster << BDRV_SECTOR_BITS);
-    return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | cluster_offset;
+    return (cluster_offset != 0);
 }
 
 static int decompress_buffer(uint8_t *out_buf, int out_buf_size,
@@ -504,7 +433,7 @@ static int decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
     return 0;
 }
 
-static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num,
+static int qcow_co_readv(BlockDriverState *bs, int64_t sector_num,
                          int nb_sectors, QEMUIOVector *qiov)
 {
     BDRVQcowState *s = bs->opaque;
@@ -591,7 +520,7 @@ done:
     qemu_co_mutex_unlock(&s->lock);
 
     if (qiov->niov > 1) {
-        qemu_iovec_from_buf(qiov, 0, orig_buf, qiov->size);
+        qemu_iovec_from_buffer(qiov, orig_buf, qiov->size);
         qemu_vfree(orig_buf);
     }
 
@@ -602,7 +531,7 @@ fail:
     goto done;
 }
 
-static coroutine_fn int qcow_co_writev(BlockDriverState *bs, int64_t sector_num,
+static int qcow_co_writev(BlockDriverState *bs, int64_t sector_num,
                           int nb_sectors, QEMUIOVector *qiov)
 {
     BDRVQcowState *s = bs->opaque;
@@ -620,7 +549,7 @@ static coroutine_fn int qcow_co_writev(BlockDriverState *bs, int64_t sector_num,
 
     if (qiov->niov > 1) {
         buf = orig_buf = qemu_blockalign(bs, qiov->size);
-        qemu_iovec_to_buf(qiov, 0, buf, qiov->size);
+        qemu_iovec_to_buffer(qiov, buf);
     } else {
         orig_buf = NULL;
         buf = (uint8_t *)qiov->iov->iov_base;
@@ -693,44 +622,31 @@ static void qcow_close(BlockDriverState *bs)
     error_free(s->migration_blocker);
 }
 
-static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
+static int qcow_create(const char *filename, QEMUOptionParameter *options)
 {
-    int header_size, backing_filename_len, l1_size, shift, i;
+    int fd, header_size, backing_filename_len, l1_size, i, shift;
     QCowHeader header;
-    uint8_t *tmp;
+    uint64_t tmp;
     int64_t total_size = 0;
-    char *backing_file = NULL;
+    const char *backing_file = NULL;
     int flags = 0;
-    Error *local_err = NULL;
     int ret;
-    BlockDriverState *qcow_bs;
 
     /* Read out options */
-    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
-    backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
-    if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ENCRYPT, false)) {
-        flags |= BLOCK_FLAG_ENCRYPT;
-    }
-
-    ret = bdrv_create_file(filename, opts, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto cleanup;
-    }
-
-    qcow_bs = NULL;
-    ret = bdrv_open(&qcow_bs, filename, NULL, NULL,
-                    BDRV_O_RDWR | BDRV_O_PROTOCOL, NULL, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto cleanup;
-    }
-
-    ret = bdrv_truncate(qcow_bs, 0);
-    if (ret < 0) {
-        goto exit;
+    while (options && options->name) {
+        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+            total_size = options->value.n / 512;
+        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
+            backing_file = options->value.s;
+        } else if (!strcmp(options->name, BLOCK_OPT_ENCRYPT)) {
+            flags |= options->value.n ? BLOCK_FLAG_ENCRYPT : 0;
+        }
+        options++;
     }
 
+    fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, 0644);
+    if (fd < 0)
+        return -errno;
     memset(&header, 0, sizeof(header));
     header.magic = cpu_to_be32(QCOW_MAGIC);
     header.version = cpu_to_be32(QCOW_VERSION);
@@ -748,7 +664,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
             backing_file = NULL;
         }
         header.cluster_bits = 9; /* 512 byte cluster to avoid copying
-                                    unmodified sectors */
+                                    unmodifyed sectors */
         header.l2_bits = 12; /* 32 KB L2 tables */
     } else {
         header.cluster_bits = 12; /* 4 KB clusters */
@@ -766,36 +682,33 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     /* write all the data */
-    ret = bdrv_pwrite(qcow_bs, 0, &header, sizeof(header));
+    ret = qemu_write_full(fd, &header, sizeof(header));
     if (ret != sizeof(header)) {
+        ret = -errno;
         goto exit;
     }
 
     if (backing_file) {
-        ret = bdrv_pwrite(qcow_bs, sizeof(header),
-            backing_file, backing_filename_len);
+        ret = qemu_write_full(fd, backing_file, backing_filename_len);
         if (ret != backing_filename_len) {
+            ret = -errno;
+            goto exit;
+        }
+
+    }
+    lseek(fd, header_size, SEEK_SET);
+    tmp = 0;
+    for(i = 0;i < l1_size; i++) {
+        ret = qemu_write_full(fd, &tmp, sizeof(tmp));
+        if (ret != sizeof(tmp)) {
+            ret = -errno;
             goto exit;
         }
     }
 
-    tmp = g_malloc0(BDRV_SECTOR_SIZE);
-    for (i = 0; i < ((sizeof(uint64_t)*l1_size + BDRV_SECTOR_SIZE - 1)/
-        BDRV_SECTOR_SIZE); i++) {
-        ret = bdrv_pwrite(qcow_bs, header_size +
-            BDRV_SECTOR_SIZE*i, tmp, BDRV_SECTOR_SIZE);
-        if (ret != BDRV_SECTOR_SIZE) {
-            g_free(tmp);
-            goto exit;
-        }
-    }
-
-    g_free(tmp);
     ret = 0;
 exit:
-    bdrv_unref(qcow_bs);
-cleanup:
-    g_free(backing_file);
+    close(fd);
     return ret;
 }
 
@@ -831,21 +744,8 @@ static int qcow_write_compressed(BlockDriverState *bs, int64_t sector_num,
     uint8_t *out_buf;
     uint64_t cluster_offset;
 
-    if (nb_sectors != s->cluster_sectors) {
-        ret = -EINVAL;
-
-        /* Zero-pad last write if image size is not cluster aligned */
-        if (sector_num + nb_sectors == bs->total_sectors &&
-            nb_sectors < s->cluster_sectors) {
-            uint8_t *pad_buf = qemu_blockalign(bs, s->cluster_size);
-            memset(pad_buf, 0, s->cluster_size);
-            memcpy(pad_buf, buf, nb_sectors * BDRV_SECTOR_SIZE);
-            ret = qcow_write_compressed(bs, sector_num,
-                                        pad_buf, s->cluster_sectors);
-            qemu_vfree(pad_buf);
-        }
-        return ret;
-    }
+    if (nb_sectors != s->cluster_sectors)
+        return -EINVAL;
 
     out_buf = g_malloc(s->cluster_size + (s->cluster_size / 1000) + 128);
 
@@ -901,6 +801,11 @@ fail:
     return ret;
 }
 
+static coroutine_fn int qcow_co_flush(BlockDriverState *bs)
+{
+    return bdrv_co_flush(bs->file);
+}
+
 static int qcow_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
 {
     BDRVQcowState *s = bs->opaque;
@@ -908,28 +813,24 @@ static int qcow_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
     return 0;
 }
 
-static QemuOptsList qcow_create_opts = {
-    .name = "qcow-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(qcow_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        {
-            .name = BLOCK_OPT_BACKING_FILE,
-            .type = QEMU_OPT_STRING,
-            .help = "File name of a base image"
-        },
-        {
-            .name = BLOCK_OPT_ENCRYPT,
-            .type = QEMU_OPT_BOOL,
-            .help = "Encrypt the image",
-            .def_value_str = "off"
-        },
-        { /* end of list */ }
-    }
+
+static QEMUOptionParameter qcow_create_options[] = {
+    {
+        .name = BLOCK_OPT_SIZE,
+        .type = OPT_SIZE,
+        .help = "Virtual disk size"
+    },
+    {
+        .name = BLOCK_OPT_BACKING_FILE,
+        .type = OPT_STRING,
+        .help = "File name of a base image"
+    },
+    {
+        .name = BLOCK_OPT_ENCRYPT,
+        .type = OPT_FLAG,
+        .help = "Encrypt the image"
+    },
+    { NULL }
 };
 
 static BlockDriver bdrv_qcow = {
@@ -938,21 +839,19 @@ static BlockDriver bdrv_qcow = {
     .bdrv_probe		= qcow_probe,
     .bdrv_open		= qcow_open,
     .bdrv_close		= qcow_close,
-    .bdrv_reopen_prepare    = qcow_reopen_prepare,
-    .bdrv_create            = qcow_create,
-    .bdrv_has_zero_init     = bdrv_has_zero_init_1,
-    .supports_backing       = true,
+    .bdrv_create	= qcow_create,
 
     .bdrv_co_readv          = qcow_co_readv,
     .bdrv_co_writev         = qcow_co_writev,
-    .bdrv_co_get_block_status   = qcow_co_get_block_status,
+    .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,
 
-    .create_opts            = &qcow_create_opts,
+    .create_options = qcow_create_options,
 };
 
 static void bdrv_qcow_init(void)

block/qcow2-cache.c

@@ -22,10 +22,9 @@
  * THE SOFTWARE.
  */
 
-#include "block/block_int.h"
+#include "block_int.h"
 #include "qemu-common.h"
 #include "qcow2.h"
-#include "trace.h"
 
 typedef struct Qcow2CachedTable {
     void*   table;
@@ -40,9 +39,11 @@ struct Qcow2Cache {
     struct Qcow2Cache*      depends;
     int                     size;
     bool                    depends_on_flush;
+    bool                    writethrough;
 };
 
-Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables)
+Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables,
+    bool writethrough)
 {
     BDRVQcowState *s = bs->opaque;
     Qcow2Cache *c;
@@ -51,6 +52,7 @@ Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables)
     c = g_malloc0(sizeof(*c));
     c->size = num_tables;
     c->entries = g_malloc0(sizeof(*c->entries) * num_tables);
+    c->writethrough = writethrough;
 
     for (i = 0; i < c->size; i++) {
         c->entries[i].table = qemu_blockalign(bs, s->cluster_size);
@@ -98,9 +100,6 @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)
         return 0;
     }
 
-    trace_qcow2_cache_entry_flush(qemu_coroutine_self(),
-                                  c == s->l2_table_cache, i);
-
     if (c->depends) {
         ret = qcow2_cache_flush_dependency(bs, c);
     } else if (c->depends_on_flush) {
@@ -114,21 +113,6 @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)
         return ret;
     }
 
-    if (c == s->refcount_block_cache) {
-        ret = qcow2_pre_write_overlap_check(bs, QCOW2_OL_REFCOUNT_BLOCK,
-                c->entries[i].offset, s->cluster_size);
-    } else if (c == s->l2_table_cache) {
-        ret = qcow2_pre_write_overlap_check(bs, QCOW2_OL_ACTIVE_L2,
-                c->entries[i].offset, s->cluster_size);
-    } else {
-        ret = qcow2_pre_write_overlap_check(bs, 0,
-                c->entries[i].offset, s->cluster_size);
-    }
-
-    if (ret < 0) {
-        return ret;
-    }
-
     if (c == s->refcount_block_cache) {
         BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_UPDATE_PART);
     } else if (c == s->l2_table_cache) {
@@ -148,13 +132,10 @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)
 
 int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c)
 {
-    BDRVQcowState *s = bs->opaque;
     int result = 0;
     int ret;
     int i;
 
-    trace_qcow2_cache_flush(qemu_coroutine_self(), c == s->l2_table_cache);
-
     for (i = 0; i < c->size; i++) {
         ret = qcow2_cache_entry_flush(bs, c, i);
         if (ret < 0 && result != -ENOSPC) {
@@ -200,24 +181,6 @@ void qcow2_cache_depends_on_flush(Qcow2Cache *c)
     c->depends_on_flush = true;
 }
 
-int qcow2_cache_empty(BlockDriverState *bs, Qcow2Cache *c)
-{
-    int ret, i;
-
-    ret = qcow2_cache_flush(bs, c);
-    if (ret < 0) {
-        return ret;
-    }
-
-    for (i = 0; i < c->size; i++) {
-        assert(c->entries[i].ref == 0);
-        c->entries[i].offset = 0;
-        c->entries[i].cache_hits = 0;
-    }
-
-    return 0;
-}
-
 static int qcow2_cache_find_entry_to_replace(Qcow2Cache *c)
 {
     int i;
@@ -255,9 +218,6 @@ static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c,
     int i;
     int ret;
 
-    trace_qcow2_cache_get(qemu_coroutine_self(), c == s->l2_table_cache,
-                          offset, read_from_disk);
-
     /* Check if the table is already cached */
     for (i = 0; i < c->size; i++) {
         if (c->entries[i].offset == offset) {
@@ -267,8 +227,6 @@ static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c,
 
     /* If not, write a table back and replace it */
     i = qcow2_cache_find_entry_to_replace(c);
-    trace_qcow2_cache_get_replace_entry(qemu_coroutine_self(),
-                                        c == s->l2_table_cache, i);
     if (i < 0) {
         return i;
     }
@@ -278,8 +236,6 @@ static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c,
         return ret;
     }
 
-    trace_qcow2_cache_get_read(qemu_coroutine_self(),
-                               c == s->l2_table_cache, i);
     c->entries[i].offset = 0;
     if (read_from_disk) {
         if (c == s->l2_table_cache) {
@@ -302,10 +258,6 @@ found:
     c->entries[i].cache_hits++;
     c->entries[i].ref++;
     *table = c->entries[i].table;
-
-    trace_qcow2_cache_get_done(qemu_coroutine_self(),
-                               c == s->l2_table_cache, i);
-
     return 0;
 }
 
@@ -337,7 +289,12 @@ found:
     *table = NULL;
 
     assert(c->entries[i].ref >= 0);
-    return 0;
+
+    if (c->writethrough) {
+        return qcow2_cache_entry_flush(bs, c, i);
+    } else {
+        return 0;
+    }
 }
 
 void qcow2_cache_entry_mark_dirty(Qcow2Cache *c, void *table)
@@ -354,3 +311,16 @@ void qcow2_cache_entry_mark_dirty(Qcow2Cache *c, void *table)
 found:
     c->entries[i].dirty = true;
 }
+
+bool qcow2_cache_set_writethrough(BlockDriverState *bs, Qcow2Cache *c,
+    bool enable)
+{
+    bool old = c->writethrough;
+
+    if (!old && enable) {
+        qcow2_cache_flush(bs, c);
+    }
+
+    c->writethrough = enable;
+    return old;
+}

block/qcow2-snapshot.c

@@ -23,9 +23,29 @@
  */
 
 #include "qemu-common.h"
-#include "block/block_int.h"
+#include "block_int.h"
 #include "block/qcow2.h"
 
+typedef struct QEMU_PACKED QCowSnapshotHeader {
+    /* header is 8 byte aligned */
+    uint64_t l1_table_offset;
+
+    uint32_t l1_size;
+    uint16_t id_str_size;
+    uint16_t name_size;
+
+    uint32_t date_sec;
+    uint32_t date_nsec;
+
+    uint64_t vm_clock_nsec;
+
+    uint32_t vm_state_size;
+    uint32_t extra_data_size; /* for extension */
+    /* extra data follows */
+    /* id_str follows */
+    /* name follows  */
+} QCowSnapshotHeader;
+
 void qcow2_free_snapshots(BlockDriverState *bs)
 {
     BDRVQcowState *s = bs->opaque;
@@ -44,12 +64,10 @@ int qcow2_read_snapshots(BlockDriverState *bs)
 {
     BDRVQcowState *s = bs->opaque;
     QCowSnapshotHeader h;
-    QCowSnapshotExtraData extra;
     QCowSnapshot *sn;
     int i, id_str_size, name_size;
     int64_t offset;
     uint32_t extra_data_size;
-    int ret;
 
     if (!s->nb_snapshots) {
         s->snapshots = NULL;
@@ -59,15 +77,10 @@ int qcow2_read_snapshots(BlockDriverState *bs)
 
     offset = s->snapshots_offset;
     s->snapshots = g_malloc0(s->nb_snapshots * sizeof(QCowSnapshot));
-
     for(i = 0; i < s->nb_snapshots; i++) {
-        /* Read statically sized part of the snapshot header */
         offset = align_offset(offset, 8);
-        ret = bdrv_pread(bs->file, offset, &h, sizeof(h));
-        if (ret < 0) {
+        if (bdrv_pread(bs->file, offset, &h, sizeof(h)) != sizeof(h))
             goto fail;
-        }
-
         offset += sizeof(h);
         sn = s->snapshots + i;
         sn->l1_table_offset = be64_to_cpu(h.l1_table_offset);
@@ -81,55 +94,25 @@ int qcow2_read_snapshots(BlockDriverState *bs)
         id_str_size = be16_to_cpu(h.id_str_size);
         name_size = be16_to_cpu(h.name_size);
 
-        /* Read extra data */
-        ret = bdrv_pread(bs->file, offset, &extra,
-                         MIN(sizeof(extra), extra_data_size));
-        if (ret < 0) {
-            goto fail;
-        }
         offset += extra_data_size;
 
-        if (extra_data_size >= 8) {
-            sn->vm_state_size = be64_to_cpu(extra.vm_state_size_large);
-        }
-
-        if (extra_data_size >= 16) {
-            sn->disk_size = be64_to_cpu(extra.disk_size);
-        } else {
-            sn->disk_size = bs->total_sectors * BDRV_SECTOR_SIZE;
-        }
-
-        /* Read snapshot ID */
         sn->id_str = g_malloc(id_str_size + 1);
-        ret = bdrv_pread(bs->file, offset, sn->id_str, id_str_size);
-        if (ret < 0) {
+        if (bdrv_pread(bs->file, offset, sn->id_str, id_str_size) != id_str_size)
             goto fail;
-        }
         offset += id_str_size;
         sn->id_str[id_str_size] = '\0';
 
-        /* Read snapshot name */
         sn->name = g_malloc(name_size + 1);
-        ret = bdrv_pread(bs->file, offset, sn->name, name_size);
-        if (ret < 0) {
+        if (bdrv_pread(bs->file, offset, sn->name, name_size) != name_size)
             goto fail;
-        }
         offset += name_size;
         sn->name[name_size] = '\0';
-
-        if (offset - s->snapshots_offset > QCOW_MAX_SNAPSHOTS_SIZE) {
-            ret = -EFBIG;
-            goto fail;
-        }
     }
-
-    assert(offset - s->snapshots_offset <= INT_MAX);
     s->snapshots_size = offset - s->snapshots_offset;
     return 0;
-
-fail:
+ fail:
     qcow2_free_snapshots(bs);
-    return ret;
+    return -1;
 }
 
 /* add at the end of the file a new list of snapshots */
@@ -138,14 +121,10 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
     BDRVQcowState *s = bs->opaque;
     QCowSnapshot *sn;
     QCowSnapshotHeader h;
-    QCowSnapshotExtraData extra;
     int i, name_size, id_str_size, snapshots_size;
-    struct {
-        uint32_t nb_snapshots;
-        uint64_t snapshots_offset;
-    } QEMU_PACKED header_data;
-    int64_t offset, snapshots_offset = 0;
-    int ret;
+    uint64_t data64;
+    uint32_t data32;
+    int64_t offset, snapshots_offset;
 
     /* compute the size of the snapshots */
     offset = 0;
@@ -153,125 +132,61 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
         sn = s->snapshots + i;
         offset = align_offset(offset, 8);
         offset += sizeof(h);
-        offset += sizeof(extra);
         offset += strlen(sn->id_str);
         offset += strlen(sn->name);
-
-        if (offset > QCOW_MAX_SNAPSHOTS_SIZE) {
-            ret = -EFBIG;
-            goto fail;
-        }
     }
-
-    assert(offset <= INT_MAX);
     snapshots_size = offset;
 
-    /* Allocate space for the new snapshot list */
     snapshots_offset = qcow2_alloc_clusters(bs, snapshots_size);
+    bdrv_flush(bs->file);
     offset = snapshots_offset;
     if (offset < 0) {
-        ret = offset;
-        goto fail;
-    }
-    ret = bdrv_flush(bs);
-    if (ret < 0) {
-        goto fail;
+        return offset;
     }
 
-    /* The snapshot list position has not yet been updated, so these clusters
-     * must indeed be completely free */
-    ret = qcow2_pre_write_overlap_check(bs, 0, offset, snapshots_size);
-    if (ret < 0) {
-        goto fail;
-    }
-
-
-    /* Write all snapshots to the new list */
     for(i = 0; i < s->nb_snapshots; i++) {
         sn = s->snapshots + i;
         memset(&h, 0, sizeof(h));
         h.l1_table_offset = cpu_to_be64(sn->l1_table_offset);
         h.l1_size = cpu_to_be32(sn->l1_size);
-        /* If it doesn't fit in 32 bit, older implementations should treat it
-         * as a disk-only snapshot rather than truncate the VM state */
-        if (sn->vm_state_size <= 0xffffffff) {
-            h.vm_state_size = cpu_to_be32(sn->vm_state_size);
-        }
+        h.vm_state_size = cpu_to_be32(sn->vm_state_size);
         h.date_sec = cpu_to_be32(sn->date_sec);
         h.date_nsec = cpu_to_be32(sn->date_nsec);
         h.vm_clock_nsec = cpu_to_be64(sn->vm_clock_nsec);
-        h.extra_data_size = cpu_to_be32(sizeof(extra));
-
-        memset(&extra, 0, sizeof(extra));
-        extra.vm_state_size_large = cpu_to_be64(sn->vm_state_size);
-        extra.disk_size = cpu_to_be64(sn->disk_size);
 
         id_str_size = strlen(sn->id_str);
         name_size = strlen(sn->name);
-        assert(id_str_size <= UINT16_MAX && name_size <= UINT16_MAX);
         h.id_str_size = cpu_to_be16(id_str_size);
         h.name_size = cpu_to_be16(name_size);
         offset = align_offset(offset, 8);
-
-        ret = bdrv_pwrite(bs->file, offset, &h, sizeof(h));
-        if (ret < 0) {
+        if (bdrv_pwrite_sync(bs->file, offset, &h, sizeof(h)) < 0)
             goto fail;
-        }
         offset += sizeof(h);
-
-        ret = bdrv_pwrite(bs->file, offset, &extra, sizeof(extra));
-        if (ret < 0) {
+        if (bdrv_pwrite_sync(bs->file, offset, sn->id_str, id_str_size) < 0)
             goto fail;
-        }
-        offset += sizeof(extra);
-
-        ret = bdrv_pwrite(bs->file, offset, sn->id_str, id_str_size);
-        if (ret < 0) {
-            goto fail;
-        }
         offset += id_str_size;
-
-        ret = bdrv_pwrite(bs->file, offset, sn->name, name_size);
-        if (ret < 0) {
+        if (bdrv_pwrite_sync(bs->file, offset, sn->name, name_size) < 0)
             goto fail;
-        }
         offset += name_size;
     }
 
-    /*
-     * Update the header to point to the new snapshot table. This requires the
-     * new table and its refcounts to be stable on disk.
-     */
-    ret = bdrv_flush(bs);
-    if (ret < 0) {
+    /* update the various header fields */
+    data64 = cpu_to_be64(snapshots_offset);
+    if (bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, snapshots_offset),
+                    &data64, sizeof(data64)) < 0)
         goto fail;
-    }
-
-    QEMU_BUILD_BUG_ON(offsetof(QCowHeader, snapshots_offset) !=
-        offsetof(QCowHeader, nb_snapshots) + sizeof(header_data.nb_snapshots));
-
-    header_data.nb_snapshots        = cpu_to_be32(s->nb_snapshots);
-    header_data.snapshots_offset    = cpu_to_be64(snapshots_offset);
-
-    ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, nb_snapshots),
-                           &header_data, sizeof(header_data));
-    if (ret < 0) {
+    data32 = cpu_to_be32(s->nb_snapshots);
+    if (bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, nb_snapshots),
+                    &data32, sizeof(data32)) < 0)
         goto fail;
-    }
 
     /* free the old snapshot table */
-    qcow2_free_clusters(bs, s->snapshots_offset, s->snapshots_size,
-                        QCOW2_DISCARD_SNAPSHOT);
+    qcow2_free_clusters(bs, s->snapshots_offset, s->snapshots_size);
     s->snapshots_offset = snapshots_offset;
     s->snapshots_size = snapshots_size;
     return 0;
-
-fail:
-    if (snapshots_offset > 0) {
-        qcow2_free_clusters(bs, snapshots_offset, snapshots_size,
-                            QCOW2_DISCARD_ALWAYS);
-    }
-    return ret;
+ fail:
+    return -1;
 }
 
 static void find_new_snapshot_id(BlockDriverState *bs,
@@ -279,8 +194,7 @@ static void find_new_snapshot_id(BlockDriverState *bs,
 {
     BDRVQcowState *s = bs->opaque;
     QCowSnapshot *sn;
-    int i;
-    unsigned long id, id_max = 0;
+    int i, id, id_max = 0;
 
     for(i = 0; i < s->nb_snapshots; i++) {
         sn = s->snapshots + i;
@@ -288,170 +202,117 @@ static void find_new_snapshot_id(BlockDriverState *bs,
         if (id > id_max)
             id_max = id;
     }
-    snprintf(id_str, id_str_size, "%lu", id_max + 1);
+    snprintf(id_str, id_str_size, "%d", id_max + 1);
 }
 
-static int find_snapshot_by_id_and_name(BlockDriverState *bs,
-                                        const char *id,
-                                        const char *name)
+static int find_snapshot_by_id(BlockDriverState *bs, const char *id_str)
 {
     BDRVQcowState *s = bs->opaque;
     int i;
 
-    if (id && name) {
-        for (i = 0; i < s->nb_snapshots; i++) {
-            if (!strcmp(s->snapshots[i].id_str, id) &&
-                !strcmp(s->snapshots[i].name, name)) {
-                return i;
-            }
-        }
-    } else if (id) {
-        for (i = 0; i < s->nb_snapshots; i++) {
-            if (!strcmp(s->snapshots[i].id_str, id)) {
-                return i;
-            }
-        }
-    } else if (name) {
-        for (i = 0; i < s->nb_snapshots; i++) {
-            if (!strcmp(s->snapshots[i].name, name)) {
-                return i;
-            }
-        }
+    for(i = 0; i < s->nb_snapshots; i++) {
+        if (!strcmp(s->snapshots[i].id_str, id_str))
+            return i;
     }
-
     return -1;
 }
 
-static int find_snapshot_by_id_or_name(BlockDriverState *bs,
-                                       const char *id_or_name)
+static int find_snapshot_by_id_or_name(BlockDriverState *bs, const char *name)
 {
-    int ret;
+    BDRVQcowState *s = bs->opaque;
+    int i, ret;
 
-    ret = find_snapshot_by_id_and_name(bs, id_or_name, NULL);
-    if (ret >= 0) {
+    ret = find_snapshot_by_id(bs, name);
+    if (ret >= 0)
         return ret;
+    for(i = 0; i < s->nb_snapshots; i++) {
+        if (!strcmp(s->snapshots[i].name, name))
+            return i;
     }
-    return find_snapshot_by_id_and_name(bs, NULL, id_or_name);
+    return -1;
 }
 
 /* if no id is provided, a new one is constructed */
 int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
 {
     BDRVQcowState *s = bs->opaque;
-    QCowSnapshot *new_snapshot_list = NULL;
-    QCowSnapshot *old_snapshot_list = NULL;
-    QCowSnapshot sn1, *sn = &sn1;
+    QCowSnapshot *snapshots1, sn1, *sn = &sn1;
     int i, ret;
     uint64_t *l1_table = NULL;
     int64_t l1_table_offset;
 
-    if (s->nb_snapshots >= QCOW_MAX_SNAPSHOTS) {
-        return -EFBIG;
-    }
-
     memset(sn, 0, sizeof(*sn));
 
-    /* Generate an ID if it wasn't passed */
     if (sn_info->id_str[0] == '\0') {
+        /* compute a new id */
         find_new_snapshot_id(bs, sn_info->id_str, sizeof(sn_info->id_str));
     }
 
-    /* Check that the ID is unique */
-    if (find_snapshot_by_id_and_name(bs, sn_info->id_str, NULL) >= 0) {
-        return -EEXIST;
-    }
+    /* check that the ID is unique */
+    if (find_snapshot_by_id(bs, sn_info->id_str) >= 0)
+        return -ENOENT;
 
-    /* Populate sn with passed data */
     sn->id_str = g_strdup(sn_info->id_str);
+    if (!sn->id_str)
+        goto fail;
     sn->name = g_strdup(sn_info->name);
-
-    sn->disk_size = bs->total_sectors * BDRV_SECTOR_SIZE;
+    if (!sn->name)
+        goto fail;
     sn->vm_state_size = sn_info->vm_state_size;
     sn->date_sec = sn_info->date_sec;
     sn->date_nsec = sn_info->date_nsec;
     sn->vm_clock_nsec = sn_info->vm_clock_nsec;
 
-    /* Allocate the L1 table of the snapshot and copy the current one there. */
+    ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 1);
+    if (ret < 0)
+        goto fail;
+
+    /* create the L1 table of the snapshot */
     l1_table_offset = qcow2_alloc_clusters(bs, s->l1_size * sizeof(uint64_t));
     if (l1_table_offset < 0) {
-        ret = l1_table_offset;
         goto fail;
     }
+    bdrv_flush(bs->file);
 
     sn->l1_table_offset = l1_table_offset;
     sn->l1_size = s->l1_size;
 
-    l1_table = g_malloc(s->l1_size * sizeof(uint64_t));
+    if (s->l1_size != 0) {
+        l1_table = g_malloc(s->l1_size * sizeof(uint64_t));
+    } else {
+        l1_table = NULL;
+    }
+
     for(i = 0; i < s->l1_size; i++) {
         l1_table[i] = cpu_to_be64(s->l1_table[i]);
     }
-
-    ret = qcow2_pre_write_overlap_check(bs, 0, sn->l1_table_offset,
-                                        s->l1_size * sizeof(uint64_t));
-    if (ret < 0) {
+    if (bdrv_pwrite_sync(bs->file, sn->l1_table_offset,
+                    l1_table, s->l1_size * sizeof(uint64_t)) < 0)
         goto fail;
-    }
-
-    ret = bdrv_pwrite(bs->file, sn->l1_table_offset, l1_table,
-                      s->l1_size * sizeof(uint64_t));
-    if (ret < 0) {
-        goto fail;
-    }
-
     g_free(l1_table);
     l1_table = NULL;
 
-    /*
-     * Increase the refcounts of all clusters and make sure everything is
-     * stable on disk before updating the snapshot table to contain a pointer
-     * to the new L1 table.
-     */
-    ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 1);
-    if (ret < 0) {
-        goto fail;
-    }
-
-    /* Append the new snapshot to the snapshot list */
-    new_snapshot_list = g_malloc((s->nb_snapshots + 1) * sizeof(QCowSnapshot));
+    snapshots1 = g_malloc((s->nb_snapshots + 1) * sizeof(QCowSnapshot));
     if (s->snapshots) {
-        memcpy(new_snapshot_list, s->snapshots,
-               s->nb_snapshots * sizeof(QCowSnapshot));
-        old_snapshot_list = s->snapshots;
+        memcpy(snapshots1, s->snapshots, s->nb_snapshots * sizeof(QCowSnapshot));
+        g_free(s->snapshots);
     }
-    s->snapshots = new_snapshot_list;
+    s->snapshots = snapshots1;
     s->snapshots[s->nb_snapshots++] = *sn;
 
-    ret = qcow2_write_snapshots(bs);
-    if (ret < 0) {
-        g_free(s->snapshots);
-        s->snapshots = old_snapshot_list;
-        s->nb_snapshots--;
+    if (qcow2_write_snapshots(bs) < 0)
         goto fail;
-    }
-
-    g_free(old_snapshot_list);
-
-    /* The VM state isn't needed any more in the active L1 table; in fact, it
-     * hurts by causing expensive COW for the next snapshot. */
-    qcow2_discard_clusters(bs, qcow2_vm_state_offset(s),
-                           align_offset(sn->vm_state_size, s->cluster_size)
-                                >> BDRV_SECTOR_BITS,
-                           QCOW2_DISCARD_NEVER);
-
 #ifdef DEBUG_ALLOC
     {
       BdrvCheckResult result = {0};
-      qcow2_check_refcounts(bs, &result, 0);
+      qcow2_check_refcounts(bs, &result);
     }
 #endif
     return 0;
-
-fail:
-    g_free(sn->id_str);
+ fail:
     g_free(sn->name);
     g_free(l1_table);
-
-    return ret;
+    return -1;
 }
 
 /* copy the snapshot 'snapshot_name' into the current disk image */
@@ -461,180 +322,83 @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
     QCowSnapshot *sn;
     int i, snapshot_index;
     int cur_l1_bytes, sn_l1_bytes;
-    int ret;
-    uint64_t *sn_l1_table = NULL;
 
-    /* Search the snapshot */
     snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_id);
-    if (snapshot_index < 0) {
+    if (snapshot_index < 0)
         return -ENOENT;
-    }
     sn = &s->snapshots[snapshot_index];
 
-    if (sn->disk_size != bs->total_sectors * BDRV_SECTOR_SIZE) {
-        error_report("qcow2: Loading snapshots with different disk "
-            "size is not implemented");
-        ret = -ENOTSUP;
+    if (qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, -1) < 0)
         goto fail;
-    }
 
-    /*
-     * Make sure that the current L1 table is big enough to contain the whole
-     * L1 table of the snapshot. If the snapshot L1 table is smaller, the
-     * current one must be padded with zeros.
-     */
-    ret = qcow2_grow_l1_table(bs, sn->l1_size, true);
-    if (ret < 0) {
+    if (qcow2_grow_l1_table(bs, sn->l1_size, true) < 0)
         goto fail;
-    }
 
     cur_l1_bytes = s->l1_size * sizeof(uint64_t);
     sn_l1_bytes = sn->l1_size * sizeof(uint64_t);
 
-    /*
-     * Copy the snapshot L1 table to the current L1 table.
-     *
-     * Before overwriting the old current L1 table on disk, make sure to
-     * increase all refcounts for the clusters referenced by the new one.
-     * Decrease the refcount referenced by the old one only when the L1
-     * table is overwritten.
-     */
-    sn_l1_table = g_malloc0(cur_l1_bytes);
-
-    ret = bdrv_pread(bs->file, sn->l1_table_offset, sn_l1_table, sn_l1_bytes);
-    if (ret < 0) {
-        goto fail;
+    if (cur_l1_bytes > sn_l1_bytes) {
+        memset(s->l1_table + sn->l1_size, 0, cur_l1_bytes - sn_l1_bytes);
     }
 
-    ret = qcow2_update_snapshot_refcount(bs, sn->l1_table_offset,
-                                         sn->l1_size, 1);
-    if (ret < 0) {
+    /* copy the snapshot l1 table to the current l1 table */
+    if (bdrv_pread(bs->file, sn->l1_table_offset,
+                   s->l1_table, sn_l1_bytes) < 0)
         goto fail;
-    }
-
-    ret = qcow2_pre_write_overlap_check(bs, QCOW2_OL_ACTIVE_L1,
-                                        s->l1_table_offset, cur_l1_bytes);
-    if (ret < 0) {
+    if (bdrv_pwrite_sync(bs->file, s->l1_table_offset,
+                    s->l1_table, cur_l1_bytes) < 0)
         goto fail;
-    }
-
-    ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset, sn_l1_table,
-                           cur_l1_bytes);
-    if (ret < 0) {
-        goto fail;
-    }
-
-    /*
-     * Decrease refcount of clusters of current L1 table.
-     *
-     * At this point, the in-memory s->l1_table points to the old L1 table,
-     * whereas on disk we already have the new one.
-     *
-     * qcow2_update_snapshot_refcount special cases the current L1 table to use
-     * the in-memory data instead of really using the offset to load a new one,
-     * which is why this works.
-     */
-    ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset,
-                                         s->l1_size, -1);
-
-    /*
-     * Now update the in-memory L1 table to be in sync with the on-disk one. We
-     * need to do this even if updating refcounts failed.
-     */
     for(i = 0;i < s->l1_size; i++) {
-        s->l1_table[i] = be64_to_cpu(sn_l1_table[i]);
+        be64_to_cpus(&s->l1_table[i]);
     }
 
-    if (ret < 0) {
+    if (qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 1) < 0)
         goto fail;
-    }
-
-    g_free(sn_l1_table);
-    sn_l1_table = NULL;
-
-    /*
-     * Update QCOW_OFLAG_COPIED in the active L1 table (it may have changed
-     * when we decreased the refcount of the old snapshot.
-     */
-    ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 0);
-    if (ret < 0) {
-        goto fail;
-    }
 
 #ifdef DEBUG_ALLOC
     {
         BdrvCheckResult result = {0};
-        qcow2_check_refcounts(bs, &result, 0);
+        qcow2_check_refcounts(bs, &result);
     }
 #endif
     return 0;
-
-fail:
-    g_free(sn_l1_table);
-    return ret;
+ fail:
+    return -EIO;
 }
 
-int qcow2_snapshot_delete(BlockDriverState *bs,
-                          const char *snapshot_id,
-                          const char *name,
-                          Error **errp)
+int qcow2_snapshot_delete(BlockDriverState *bs, const char *snapshot_id)
 {
     BDRVQcowState *s = bs->opaque;
-    QCowSnapshot sn;
+    QCowSnapshot *sn;
     int snapshot_index, ret;
 
-    /* Search the snapshot */
-    snapshot_index = find_snapshot_by_id_and_name(bs, snapshot_id, name);
-    if (snapshot_index < 0) {
-        error_setg(errp, "Can't find the snapshot");
+    snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_id);
+    if (snapshot_index < 0)
         return -ENOENT;
-    }
-    sn = s->snapshots[snapshot_index];
+    sn = &s->snapshots[snapshot_index];
 
-    /* Remove it from the snapshot list */
-    memmove(s->snapshots + snapshot_index,
-            s->snapshots + snapshot_index + 1,
-            (s->nb_snapshots - snapshot_index - 1) * sizeof(sn));
+    ret = qcow2_update_snapshot_refcount(bs, sn->l1_table_offset, sn->l1_size, -1);
+    if (ret < 0)
+        return ret;
+    /* must update the copied flag on the current cluster offsets */
+    ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 0);
+    if (ret < 0)
+        return ret;
+    qcow2_free_clusters(bs, sn->l1_table_offset, sn->l1_size * sizeof(uint64_t));
+
+    g_free(sn->id_str);
+    g_free(sn->name);
+    memmove(sn, sn + 1, (s->nb_snapshots - snapshot_index - 1) * sizeof(*sn));
     s->nb_snapshots--;
     ret = qcow2_write_snapshots(bs);
     if (ret < 0) {
-        error_setg_errno(errp, -ret,
-                         "Failed to remove snapshot from snapshot list");
+        /* XXX: restore snapshot if error ? */
         return ret;
     }
-
-    /*
-     * The snapshot is now unused, clean up. If we fail after this point, we
-     * won't recover but just leak clusters.
-     */
-    g_free(sn.id_str);
-    g_free(sn.name);
-
-    /*
-     * Now decrease the refcounts of clusters referenced by the snapshot and
-     * free the L1 table.
-     */
-    ret = qcow2_update_snapshot_refcount(bs, sn.l1_table_offset,
-                                         sn.l1_size, -1);
-    if (ret < 0) {
-        error_setg_errno(errp, -ret, "Failed to free the cluster and L1 table");
-        return ret;
-    }
-    qcow2_free_clusters(bs, sn.l1_table_offset, sn.l1_size * sizeof(uint64_t),
-                        QCOW2_DISCARD_SNAPSHOT);
-
-    /* must update the copied flag on the current cluster offsets */
-    ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 0);
-    if (ret < 0) {
-        error_setg_errno(errp, -ret,
-                         "Failed to update snapshot status in disk");
-        return ret;
-    }
-
 #ifdef DEBUG_ALLOC
     {
         BdrvCheckResult result = {0};
-        qcow2_check_refcounts(bs, &result, 0);
+        qcow2_check_refcounts(bs, &result);
     }
 #endif
     return 0;
@@ -669,54 +433,34 @@ int qcow2_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
     return s->nb_snapshots;
 }
 
-int qcow2_snapshot_load_tmp(BlockDriverState *bs,
-                            const char *snapshot_id,
-                            const char *name,
-                            Error **errp)
+int qcow2_snapshot_load_tmp(BlockDriverState *bs, const char *snapshot_name)
 {
-    int i, snapshot_index;
+    int i, snapshot_index, l1_size2;
     BDRVQcowState *s = bs->opaque;
     QCowSnapshot *sn;
-    uint64_t *new_l1_table;
-    int new_l1_bytes;
-    int ret;
 
-    assert(bs->read_only);
-
-    /* Search the snapshot */
-    snapshot_index = find_snapshot_by_id_and_name(bs, snapshot_id, name);
+    snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_name);
     if (snapshot_index < 0) {
-        error_setg(errp,
-                   "Can't find snapshot");
         return -ENOENT;
     }
+
     sn = &s->snapshots[snapshot_index];
-
-    /* Allocate and read in the snapshot's L1 table */
-    if (sn->l1_size > QCOW_MAX_L1_SIZE) {
-        error_setg(errp, "Snapshot L1 table too large");
-        return -EFBIG;
-    }
-    new_l1_bytes = sn->l1_size * sizeof(uint64_t);
-    new_l1_table = g_malloc0(align_offset(new_l1_bytes, 512));
-
-    ret = bdrv_pread(bs->file, sn->l1_table_offset, new_l1_table, new_l1_bytes);
-    if (ret < 0) {
-        error_setg(errp, "Failed to read l1 table for snapshot");
-        g_free(new_l1_table);
-        return ret;
-    }
-
-    /* Switch the L1 table */
-    g_free(s->l1_table);
-
     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 = new_l1_table;
+    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;
 }